summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/super.c
blob: 5f4ebe279aaae7ebcda82651b6db650ca32e8d88 (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
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/bio.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/time.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/kernel.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "util.h"
#include "sys.h"
#include "xattr.h"
#include "lops.h"

enum dinode_demise {
	SHOULD_DELETE_DINODE,
	SHOULD_NOT_DELETE_DINODE,
	SHOULD_DEFER_EVICTION,
};

/**
 * gfs2_jindex_free - Clear all the journal index information
 * @sdp: The GFS2 superblock
 *
 */

void gfs2_jindex_free(struct gfs2_sbd *sdp)
{
	struct list_head list;
	struct gfs2_jdesc *jd;

	spin_lock(&sdp->sd_jindex_spin);
	list_add(&list, &sdp->sd_jindex_list);
	list_del_init(&sdp->sd_jindex_list);
	sdp->sd_journals = 0;
	spin_unlock(&sdp->sd_jindex_spin);

	sdp->sd_jdesc = NULL;
	while (!list_empty(&list)) {
		jd = list_first_entry(&list, struct gfs2_jdesc, jd_list);
		gfs2_free_journal_extents(jd);
		list_del(&jd->jd_list);
		iput(jd->jd_inode);
		jd->jd_inode = NULL;
		kfree(jd);
	}
}

static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
{
	struct gfs2_jdesc *jd;

	list_for_each_entry(jd, head, jd_list) {
		if (jd->jd_jid == jid)
			return jd;
	}
	return NULL;
}

struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
{
	struct gfs2_jdesc *jd;

	spin_lock(&sdp->sd_jindex_spin);
	jd = jdesc_find_i(&sdp->sd_jindex_list, jid);
	spin_unlock(&sdp->sd_jindex_spin);

	return jd;
}

int gfs2_jdesc_check(struct gfs2_jdesc *jd)
{
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
	u64 size = i_size_read(jd->jd_inode);

	if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, BIT(30)))
		return -EIO;

	jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;

	if (gfs2_write_alloc_required(ip, 0, size)) {
		gfs2_consist_inode(ip);
		return -EIO;
	}

	return 0;
}

/**
 * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
 * @sdp: the filesystem
 *
 * Returns: errno
 */

int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
	struct gfs2_glock *j_gl = ip->i_gl;
	struct gfs2_log_header_host head;
	int error;

	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
	if (gfs2_withdrawn(sdp))
		return -EIO;

	error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
	if (error) {
		gfs2_consist(sdp);
		return error;
	}

	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
		gfs2_consist(sdp);
		return -EIO;
	}

	/*  Initialize some head of the log stuff  */
	sdp->sd_log_sequence = head.lh_sequence + 1;
	gfs2_log_pointers_init(sdp, head.lh_blkno);

	error = gfs2_quota_init(sdp);
	if (!error && gfs2_withdrawn(sdp))
		error = -EIO;
	if (!error)
		set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
	return error;
}

void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
{
	const struct gfs2_statfs_change *str = buf;

	sc->sc_total = be64_to_cpu(str->sc_total);
	sc->sc_free = be64_to_cpu(str->sc_free);
	sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
}

void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
{
	struct gfs2_statfs_change *str = buf;

	str->sc_total = cpu_to_be64(sc->sc_total);
	str->sc_free = cpu_to_be64(sc->sc_free);
	str->sc_dinodes = cpu_to_be64(sc->sc_dinodes);
}

int gfs2_statfs_init(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
	struct buffer_head *m_bh;
	struct gfs2_holder gh;
	int error;

	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
				   &gh);
	if (error)
		return error;

	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
	if (error)
		goto out;

	if (sdp->sd_args.ar_spectator) {
		spin_lock(&sdp->sd_statfs_spin);
		gfs2_statfs_change_in(m_sc, m_bh->b_data +
				      sizeof(struct gfs2_dinode));
		spin_unlock(&sdp->sd_statfs_spin);
	} else {
		spin_lock(&sdp->sd_statfs_spin);
		gfs2_statfs_change_in(m_sc, m_bh->b_data +
				      sizeof(struct gfs2_dinode));
		gfs2_statfs_change_in(l_sc, sdp->sd_sc_bh->b_data +
				      sizeof(struct gfs2_dinode));
		spin_unlock(&sdp->sd_statfs_spin);

	}

	brelse(m_bh);
out:
	gfs2_glock_dq_uninit(&gh);
	return 0;
}

void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
			s64 dinodes)
{
	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	s64 x, y;
	int need_sync = 0;

	gfs2_trans_add_meta(l_ip->i_gl, sdp->sd_sc_bh);

	spin_lock(&sdp->sd_statfs_spin);
	l_sc->sc_total += total;
	l_sc->sc_free += free;
	l_sc->sc_dinodes += dinodes;
	gfs2_statfs_change_out(l_sc, sdp->sd_sc_bh->b_data +
			       sizeof(struct gfs2_dinode));
	if (sdp->sd_args.ar_statfs_percent) {
		x = 100 * l_sc->sc_free;
		y = m_sc->sc_free * sdp->sd_args.ar_statfs_percent;
		if (x >= y || x <= -y)
			need_sync = 1;
	}
	spin_unlock(&sdp->sd_statfs_spin);

	if (need_sync)
		gfs2_wake_up_statfs(sdp);
}

void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh)
{
	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;

	gfs2_trans_add_meta(l_ip->i_gl, sdp->sd_sc_bh);
	gfs2_trans_add_meta(m_ip->i_gl, m_bh);

	spin_lock(&sdp->sd_statfs_spin);
	m_sc->sc_total += l_sc->sc_total;
	m_sc->sc_free += l_sc->sc_free;
	m_sc->sc_dinodes += l_sc->sc_dinodes;
	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
	memset(sdp->sd_sc_bh->b_data + sizeof(struct gfs2_dinode),
	       0, sizeof(struct gfs2_statfs_change));
	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
	spin_unlock(&sdp->sd_statfs_spin);
}

int gfs2_statfs_sync(struct super_block *sb, int type)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
	struct gfs2_holder gh;
	struct buffer_head *m_bh;
	int error;

	error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE,
				   &gh);
	if (error)
		goto out;

	error = gfs2_meta_inode_buffer(m_ip, &m_bh);
	if (error)
		goto out_unlock;

	spin_lock(&sdp->sd_statfs_spin);
	gfs2_statfs_change_in(m_sc, m_bh->b_data +
			      sizeof(struct gfs2_dinode));
	if (!l_sc->sc_total && !l_sc->sc_free && !l_sc->sc_dinodes) {
		spin_unlock(&sdp->sd_statfs_spin);
		goto out_bh;
	}
	spin_unlock(&sdp->sd_statfs_spin);

	error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
	if (error)
		goto out_bh;

	update_statfs(sdp, m_bh);
	sdp->sd_statfs_force_sync = 0;

	gfs2_trans_end(sdp);

out_bh:
	brelse(m_bh);
out_unlock:
	gfs2_glock_dq_uninit(&gh);
out:
	return error;
}

struct lfcc {
	struct list_head list;
	struct gfs2_holder gh;
};

/**
 * gfs2_lock_fs_check_clean - Stop all writes to the FS and check that all
 *                            journals are clean
 * @sdp: the file system
 *
 * Returns: errno
 */

static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *ip;
	struct gfs2_jdesc *jd;
	struct lfcc *lfcc;
	LIST_HEAD(list);
	struct gfs2_log_header_host lh;
	int error, error2;

	/*
	 * Grab all the journal glocks in SH mode.  We are *probably* doing
	 * that to prevent recovery.
	 */

	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
		lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL);
		if (!lfcc) {
			error = -ENOMEM;
			goto out;
		}
		ip = GFS2_I(jd->jd_inode);
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &lfcc->gh);
		if (error) {
			kfree(lfcc);
			goto out;
		}
		list_add(&lfcc->list, &list);
	}

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
				   LM_FLAG_NOEXP | GL_NOPID,
				   &sdp->sd_freeze_gh);
	if (error)
		goto relock_shared;

	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
		error = gfs2_jdesc_check(jd);
		if (error)
			break;
		error = gfs2_find_jhead(jd, &lh, false);
		if (error)
			break;
		if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
			error = -EBUSY;
			break;
		}
	}

	if (!error)
		goto out;  /* success */

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

relock_shared:
	error2 = gfs2_freeze_lock_shared(sdp);
	gfs2_assert_withdraw(sdp, !error2);

out:
	while (!list_empty(&list)) {
		lfcc = list_first_entry(&list, struct lfcc, list);
		list_del(&lfcc->list);
		gfs2_glock_dq_uninit(&lfcc->gh);
		kfree(lfcc);
	}
	return error;
}

void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
{
	const struct inode *inode = &ip->i_inode;
	struct gfs2_dinode *str = buf;

	str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
	str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
	str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
	str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
	str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
	str->di_mode = cpu_to_be32(inode->i_mode);
	str->di_uid = cpu_to_be32(i_uid_read(inode));
	str->di_gid = cpu_to_be32(i_gid_read(inode));
	str->di_nlink = cpu_to_be32(inode->i_nlink);
	str->di_size = cpu_to_be64(i_size_read(inode));
	str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(inode));
	str->di_atime = cpu_to_be64(inode->i_atime.tv_sec);
	str->di_mtime = cpu_to_be64(inode->i_mtime.tv_sec);
	str->di_ctime = cpu_to_be64(inode_get_ctime(inode).tv_sec);

	str->di_goal_meta = cpu_to_be64(ip->i_goal);
	str->di_goal_data = cpu_to_be64(ip->i_goal);
	str->di_generation = cpu_to_be64(ip->i_generation);

	str->di_flags = cpu_to_be32(ip->i_diskflags);
	str->di_height = cpu_to_be16(ip->i_height);
	str->di_payload_format = cpu_to_be32(S_ISDIR(inode->i_mode) &&
					     !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
					     GFS2_FORMAT_DE : 0);
	str->di_depth = cpu_to_be16(ip->i_depth);
	str->di_entries = cpu_to_be32(ip->i_entries);

	str->di_eattr = cpu_to_be64(ip->i_eattr);
	str->di_atime_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
	str->di_mtime_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
	str->di_ctime_nsec = cpu_to_be32(inode_get_ctime(inode).tv_nsec);
}

/**
 * gfs2_write_inode - Make sure the inode is stable on the disk
 * @inode: The inode
 * @wbc: The writeback control structure
 *
 * Returns: errno
 */

static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
	struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
	int ret = 0;
	bool flush_all = (wbc->sync_mode == WB_SYNC_ALL || gfs2_is_jdata(ip));

	if (flush_all)
		gfs2_log_flush(GFS2_SB(inode), ip->i_gl,
			       GFS2_LOG_HEAD_FLUSH_NORMAL |
			       GFS2_LFC_WRITE_INODE);
	if (bdi->wb.dirty_exceeded)
		gfs2_ail1_flush(sdp, wbc);
	else
		filemap_fdatawrite(metamapping);
	if (flush_all)
		ret = filemap_fdatawait(metamapping);
	if (ret)
		mark_inode_dirty_sync(inode);
	else {
		spin_lock(&inode->i_lock);
		if (!(inode->i_flags & I_DIRTY))
			gfs2_ordered_del_inode(ip);
		spin_unlock(&inode->i_lock);
	}
	return ret;
}

/**
 * gfs2_dirty_inode - check for atime updates
 * @inode: The inode in question
 * @flags: The type of dirty
 *
 * Unfortunately it can be called under any combination of inode
 * glock and freeze glock, so we have to check carefully.
 *
 * At the moment this deals only with atime - it should be possible
 * to expand that role in future, once a review of the locking has
 * been carried out.
 */

static void gfs2_dirty_inode(struct inode *inode, int flags)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct buffer_head *bh;
	struct gfs2_holder gh;
	int need_unlock = 0;
	int need_endtrans = 0;
	int ret;

	if (unlikely(!ip->i_gl)) {
		/* This can only happen during incomplete inode creation. */
		BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
		return;
	}

	if (unlikely(gfs2_withdrawn(sdp)))
		return;
	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
		if (ret) {
			fs_err(sdp, "dirty_inode: glock %d\n", ret);
			gfs2_dump_glock(NULL, ip->i_gl, true);
			return;
		}
		need_unlock = 1;
	} else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE))
		return;

	if (current->journal_info == NULL) {
		ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
		if (ret) {
			fs_err(sdp, "dirty_inode: gfs2_trans_begin %d\n", ret);
			goto out;
		}
		need_endtrans = 1;
	}

	ret = gfs2_meta_inode_buffer(ip, &bh);
	if (ret == 0) {
		gfs2_trans_add_meta(ip->i_gl, bh);
		gfs2_dinode_out(ip, bh->b_data);
		brelse(bh);
	}

	if (need_endtrans)
		gfs2_trans_end(sdp);
out:
	if (need_unlock)
		gfs2_glock_dq_uninit(&gh);
}

/**
 * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
 * @sdp: the filesystem
 *
 * Returns: errno
 */

void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
{
	int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);

	if (!test_bit(SDF_KILL, &sdp->sd_flags))
		gfs2_flush_delete_work(sdp);

	gfs2_destroy_threads(sdp);

	if (log_write_allowed) {
		gfs2_quota_sync(sdp->sd_vfs, 0);
		gfs2_statfs_sync(sdp->sd_vfs, 0);

		/* We do two log flushes here. The first one commits dirty inodes
		 * and rgrps to the journal, but queues up revokes to the ail list.
		 * The second flush writes out and removes the revokes.
		 *
		 * The first must be done before the FLUSH_SHUTDOWN code
		 * clears the LIVE flag, otherwise it will not be able to start
		 * a transaction to write its revokes, and the error will cause
		 * a withdraw of the file system. */
		gfs2_log_flush(sdp, NULL, GFS2_LFC_MAKE_FS_RO);
		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
			       GFS2_LFC_MAKE_FS_RO);
		wait_event_timeout(sdp->sd_log_waitq,
				   gfs2_log_is_empty(sdp),
				   HZ * 5);
		gfs2_assert_warn(sdp, gfs2_log_is_empty(sdp));
	}
	gfs2_quota_cleanup(sdp);
}

/**
 * gfs2_put_super - Unmount the filesystem
 * @sb: The VFS superblock
 *
 */

static void gfs2_put_super(struct super_block *sb)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_jdesc *jd;

	/* No more recovery requests */
	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
	smp_mb();

	/* Wait on outstanding recovery */
restart:
	spin_lock(&sdp->sd_jindex_spin);
	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
			continue;
		spin_unlock(&sdp->sd_jindex_spin);
		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
			    TASK_UNINTERRUPTIBLE);
		goto restart;
	}
	spin_unlock(&sdp->sd_jindex_spin);

	if (!sb_rdonly(sb))
		gfs2_make_fs_ro(sdp);
	else {
		if (gfs2_withdrawn(sdp))
			gfs2_destroy_threads(sdp);

		gfs2_quota_cleanup(sdp);
	}

	WARN_ON(gfs2_withdrawing(sdp));

	/*  At this point, we're through modifying the disk  */

	/*  Release stuff  */

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

	iput(sdp->sd_jindex);
	iput(sdp->sd_statfs_inode);
	iput(sdp->sd_rindex);
	iput(sdp->sd_quota_inode);

	gfs2_glock_put(sdp->sd_rename_gl);
	gfs2_glock_put(sdp->sd_freeze_gl);

	if (!sdp->sd_args.ar_spectator) {
		if (gfs2_holder_initialized(&sdp->sd_journal_gh))
			gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
		if (gfs2_holder_initialized(&sdp->sd_jinode_gh))
			gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
		brelse(sdp->sd_sc_bh);
		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
		free_local_statfs_inodes(sdp);
		iput(sdp->sd_qc_inode);
	}

	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
	gfs2_clear_rgrpd(sdp);
	gfs2_jindex_free(sdp);
	/*  Take apart glock structures and buffer lists  */
	gfs2_gl_hash_clear(sdp);
	truncate_inode_pages_final(&sdp->sd_aspace);
	gfs2_delete_debugfs_file(sdp);
	/*  Unmount the locking protocol  */
	gfs2_lm_unmount(sdp);

	/*  At this point, we're through participating in the lockspace  */
	gfs2_sys_fs_del(sdp);
	free_sbd(sdp);
}

/**
 * gfs2_sync_fs - sync the filesystem
 * @sb: the superblock
 * @wait: true to wait for completion
 *
 * Flushes the log to disk.
 */

static int gfs2_sync_fs(struct super_block *sb, int wait)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;

	gfs2_quota_sync(sb, -1);
	if (wait)
		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
			       GFS2_LFC_SYNC_FS);
	return sdp->sd_log_error;
}

static int gfs2_freeze_locally(struct gfs2_sbd *sdp)
{
	struct super_block *sb = sdp->sd_vfs;
	int error;

	error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
	if (error)
		return error;

	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
			       GFS2_LFC_FREEZE_GO_SYNC);
		if (gfs2_withdrawn(sdp)) {
			error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
			if (error)
				return error;
			return -EIO;
		}
	}
	return 0;
}

static int gfs2_do_thaw(struct gfs2_sbd *sdp)
{
	struct super_block *sb = sdp->sd_vfs;
	int error;

	error = gfs2_freeze_lock_shared(sdp);
	if (error)
		goto fail;
	error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
	if (!error)
		return 0;

fail:
	fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n", error);
	gfs2_assert_withdraw(sdp, 0);
	return error;
}

void gfs2_freeze_func(struct work_struct *work)
{
	struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_freeze_work);
	struct super_block *sb = sdp->sd_vfs;
	int error;

	mutex_lock(&sdp->sd_freeze_mutex);
	error = -EBUSY;
	if (test_bit(SDF_FROZEN, &sdp->sd_flags))
		goto freeze_failed;

	error = gfs2_freeze_locally(sdp);
	if (error)
		goto freeze_failed;

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);
	set_bit(SDF_FROZEN, &sdp->sd_flags);

	error = gfs2_do_thaw(sdp);
	if (error)
		goto out;

	clear_bit(SDF_FROZEN, &sdp->sd_flags);
	goto out;

freeze_failed:
	fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", error);

out:
	mutex_unlock(&sdp->sd_freeze_mutex);
	deactivate_super(sb);
}

/**
 * gfs2_freeze_super - prevent further writes to the filesystem
 * @sb: the VFS structure for the filesystem
 *
 */

static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	int error;

	if (!mutex_trylock(&sdp->sd_freeze_mutex))
		return -EBUSY;
	error = -EBUSY;
	if (test_bit(SDF_FROZEN, &sdp->sd_flags))
		goto out;

	for (;;) {
		error = gfs2_freeze_locally(sdp);
		if (error) {
			fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
				error);
			goto out;
		}

		error = gfs2_lock_fs_check_clean(sdp);
		if (!error)
			break;  /* success */

		error = gfs2_do_thaw(sdp);
		if (error)
			goto out;

		if (error == -EBUSY)
			fs_err(sdp, "waiting for recovery before freeze\n");
		else if (error == -EIO) {
			fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
			       "to recovery error.\n");
			goto out;
		} else {
			fs_err(sdp, "error freezing FS: %d\n", error);
		}
		fs_err(sdp, "retrying...\n");
		msleep(1000);
	}

out:
	if (!error) {
		set_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
		set_bit(SDF_FROZEN, &sdp->sd_flags);
	}
	mutex_unlock(&sdp->sd_freeze_mutex);
	return error;
}

/**
 * gfs2_thaw_super - reallow writes to the filesystem
 * @sb: the VFS structure for the filesystem
 *
 */

static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	int error;

	if (!mutex_trylock(&sdp->sd_freeze_mutex))
		return -EBUSY;
	error = -EINVAL;
	if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags))
		goto out;

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

	error = gfs2_do_thaw(sdp);

	if (!error) {
		clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
		clear_bit(SDF_FROZEN, &sdp->sd_flags);
	}
out:
	mutex_unlock(&sdp->sd_freeze_mutex);
	return error;
}

void gfs2_thaw_freeze_initiator(struct super_block *sb)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;

	mutex_lock(&sdp->sd_freeze_mutex);
	if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags))
		goto out;

	gfs2_freeze_unlock(&sdp->sd_freeze_gh);

out:
	mutex_unlock(&sdp->sd_freeze_mutex);
}

/**
 * statfs_slow_fill - fill in the sg for a given RG
 * @rgd: the RG
 * @sc: the sc structure
 *
 * Returns: 0 on success, -ESTALE if the LVB is invalid
 */

static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
			    struct gfs2_statfs_change_host *sc)
{
	gfs2_rgrp_verify(rgd);
	sc->sc_total += rgd->rd_data;
	sc->sc_free += rgd->rd_free;
	sc->sc_dinodes += rgd->rd_dinodes;
	return 0;
}

/**
 * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
 * @sdp: the filesystem
 * @sc: the sc info that will be returned
 *
 * Any error (other than a signal) will cause this routine to fall back
 * to the synchronous version.
 *
 * FIXME: This really shouldn't busy wait like this.
 *
 * Returns: errno
 */

static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
	struct gfs2_rgrpd *rgd_next;
	struct gfs2_holder *gha, *gh;
	unsigned int slots = 64;
	unsigned int x;
	int done;
	int error = 0, err;

	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
	gha = kmalloc_array(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
	if (!gha)
		return -ENOMEM;
	for (x = 0; x < slots; x++)
		gfs2_holder_mark_uninitialized(gha + x);

	rgd_next = gfs2_rgrpd_get_first(sdp);

	for (;;) {
		done = 1;

		for (x = 0; x < slots; x++) {
			gh = gha + x;

			if (gfs2_holder_initialized(gh) && gfs2_glock_poll(gh)) {
				err = gfs2_glock_wait(gh);
				if (err) {
					gfs2_holder_uninit(gh);
					error = err;
				} else {
					if (!error) {
						struct gfs2_rgrpd *rgd =
							gfs2_glock2rgrp(gh->gh_gl);

						error = statfs_slow_fill(rgd, sc);
					}
					gfs2_glock_dq_uninit(gh);
				}
			}

			if (gfs2_holder_initialized(gh))
				done = 0;
			else if (rgd_next && !error) {
				error = gfs2_glock_nq_init(rgd_next->rd_gl,
							   LM_ST_SHARED,
							   GL_ASYNC,
							   gh);
				rgd_next = gfs2_rgrpd_get_next(rgd_next);
				done = 0;
			}

			if (signal_pending(current))
				error = -ERESTARTSYS;
		}

		if (done)
			break;

		yield();
	}

	kfree(gha);
	return error;
}

/**
 * gfs2_statfs_i - Do a statfs
 * @sdp: the filesystem
 * @sc: the sc structure
 *
 * Returns: errno
 */

static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;

	spin_lock(&sdp->sd_statfs_spin);

	*sc = *m_sc;
	sc->sc_total += l_sc->sc_total;
	sc->sc_free += l_sc->sc_free;
	sc->sc_dinodes += l_sc->sc_dinodes;

	spin_unlock(&sdp->sd_statfs_spin);

	if (sc->sc_free < 0)
		sc->sc_free = 0;
	if (sc->sc_free > sc->sc_total)
		sc->sc_free = sc->sc_total;
	if (sc->sc_dinodes < 0)
		sc->sc_dinodes = 0;

	return 0;
}

/**
 * gfs2_statfs - Gather and return stats about the filesystem
 * @dentry: The name of the link
 * @buf: The buffer
 *
 * Returns: 0 on success or error code
 */

static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_statfs_change_host sc;
	int error;

	error = gfs2_rindex_update(sdp);
	if (error)
		return error;

	if (gfs2_tune_get(sdp, gt_statfs_slow))
		error = gfs2_statfs_slow(sdp, &sc);
	else
		error = gfs2_statfs_i(sdp, &sc);

	if (error)
		return error;

	buf->f_type = GFS2_MAGIC;
	buf->f_bsize = sdp->sd_sb.sb_bsize;
	buf->f_blocks = sc.sc_total;
	buf->f_bfree = sc.sc_free;
	buf->f_bavail = sc.sc_free;
	buf->f_files = sc.sc_dinodes + sc.sc_free;
	buf->f_ffree = sc.sc_free;
	buf->f_namelen = GFS2_FNAMESIZE;

	return 0;
}

/**
 * gfs2_drop_inode - Drop an inode (test for remote unlink)
 * @inode: The inode to drop
 *
 * If we've received a callback on an iopen lock then it's because a
 * remote node tried to deallocate the inode but failed due to this node
 * still having the inode open. Here we mark the link count zero
 * since we know that it must have reached zero if the GLF_DEMOTE flag
 * is set on the iopen glock. If we didn't do a disk read since the
 * remote node removed the final link then we might otherwise miss
 * this event. This check ensures that this node will deallocate the
 * inode's blocks, or alternatively pass the baton on to another
 * node for later deallocation.
 */

static int gfs2_drop_inode(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (inode->i_nlink &&
	    gfs2_holder_initialized(&ip->i_iopen_gh)) {
		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
		if (test_bit(GLF_DEMOTE, &gl->gl_flags))
			clear_nlink(inode);
	}

	/*
	 * When under memory pressure when an inode's link count has dropped to
	 * zero, defer deleting the inode to the delete workqueue.  This avoids
	 * calling into DLM under memory pressure, which can deadlock.
	 */
	if (!inode->i_nlink &&
	    unlikely(current->flags & PF_MEMALLOC) &&
	    gfs2_holder_initialized(&ip->i_iopen_gh)) {
		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;

		gfs2_glock_hold(gl);
		if (!gfs2_queue_try_to_evict(gl))
			gfs2_glock_queue_put(gl);
		return 0;
	}

	/*
	 * No longer cache inodes when trying to evict them all.
	 */
	if (test_bit(SDF_EVICTING, &sdp->sd_flags))
		return 1;

	return generic_drop_inode(inode);
}

static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
{
	do {
		if (d1 == d2)
			return 1;
		d1 = d1->d_parent;
	} while (!IS_ROOT(d1));
	return 0;
}

/**
 * gfs2_show_options - Show mount options for /proc/mounts
 * @s: seq_file structure
 * @root: root of this (sub)tree
 *
 * Returns: 0 on success or error code
 */

static int gfs2_show_options(struct seq_file *s, struct dentry *root)
{
	struct gfs2_sbd *sdp = root->d_sb->s_fs_info;
	struct gfs2_args *args = &sdp->sd_args;
	unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum;

	spin_lock(&sdp->sd_tune.gt_spin);
	logd_secs = sdp->sd_tune.gt_logd_secs;
	quota_quantum = sdp->sd_tune.gt_quota_quantum;
	statfs_quantum = sdp->sd_tune.gt_statfs_quantum;
	statfs_slow = sdp->sd_tune.gt_statfs_slow;
	spin_unlock(&sdp->sd_tune.gt_spin);

	if (is_ancestor(root, sdp->sd_master_dir))
		seq_puts(s, ",meta");
	if (args->ar_lockproto[0])
		seq_show_option(s, "lockproto", args->ar_lockproto);
	if (args->ar_locktable[0])
		seq_show_option(s, "locktable", args->ar_locktable);
	if (args->ar_hostdata[0])
		seq_show_option(s, "hostdata", args->ar_hostdata);
	if (args->ar_spectator)
		seq_puts(s, ",spectator");
	if (args->ar_localflocks)
		seq_puts(s, ",localflocks");
	if (args->ar_debug)
		seq_puts(s, ",debug");
	if (args->ar_posix_acl)
		seq_puts(s, ",acl");
	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
		char *state;
		switch (args->ar_quota) {
		case GFS2_QUOTA_OFF:
			state = "off";
			break;
		case GFS2_QUOTA_ACCOUNT:
			state = "account";
			break;
		case GFS2_QUOTA_ON:
			state = "on";
			break;
		case GFS2_QUOTA_QUIET:
			state = "quiet";
			break;
		default:
			state = "unknown";
			break;
		}
		seq_printf(s, ",quota=%s", state);
	}
	if (args->ar_suiddir)
		seq_puts(s, ",suiddir");
	if (args->ar_data != GFS2_DATA_DEFAULT) {
		char *state;
		switch (args->ar_data) {
		case GFS2_DATA_WRITEBACK:
			state = "writeback";
			break;
		case GFS2_DATA_ORDERED:
			state = "ordered";
			break;
		default:
			state = "unknown";
			break;
		}
		seq_printf(s, ",data=%s", state);
	}
	if (args->ar_discard)
		seq_puts(s, ",discard");
	if (logd_secs != 30)
		seq_printf(s, ",commit=%d", logd_secs);
	if (statfs_quantum != 30)
		seq_printf(s, ",statfs_quantum=%d", statfs_quantum);
	else if (statfs_slow)
		seq_puts(s, ",statfs_quantum=0");
	if (quota_quantum != 60)
		seq_printf(s, ",quota_quantum=%d", quota_quantum);
	if (args->ar_statfs_percent)
		seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent);
	if (args->ar_errors != GFS2_ERRORS_DEFAULT) {
		const char *state;

		switch (args->ar_errors) {
		case GFS2_ERRORS_WITHDRAW:
			state = "withdraw";
			break;
		case GFS2_ERRORS_PANIC:
			state = "panic";
			break;
		default:
			state = "unknown";
			break;
		}
		seq_printf(s, ",errors=%s", state);
	}
	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
		seq_puts(s, ",nobarrier");
	if (test_bit(SDF_DEMOTE, &sdp->sd_flags))
		seq_puts(s, ",demote_interface_used");
	if (args->ar_rgrplvb)
		seq_puts(s, ",rgrplvb");
	if (args->ar_loccookie)
		seq_puts(s, ",loccookie");
	return 0;
}

static void gfs2_final_release_pages(struct gfs2_inode *ip)
{
	struct inode *inode = &ip->i_inode;
	struct gfs2_glock *gl = ip->i_gl;

	if (unlikely(!gl)) {
		/* This can only happen during incomplete inode creation. */
		BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
		return;
	}

	truncate_inode_pages(gfs2_glock2aspace(gl), 0);
	truncate_inode_pages(&inode->i_data, 0);

	if (atomic_read(&gl->gl_revokes) == 0) {
		clear_bit(GLF_LFLUSH, &gl->gl_flags);
		clear_bit(GLF_DIRTY, &gl->gl_flags);
	}
}

static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_rgrpd *rgd;
	struct gfs2_holder gh;
	int error;

	if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
		gfs2_consist_inode(ip);
		return -EIO;
	}

	gfs2_rindex_update(sdp);

	error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
	if (error)
		return error;

	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
	if (!rgd) {
		gfs2_consist_inode(ip);
		error = -EIO;
		goto out_qs;
	}

	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
				   LM_FLAG_NODE_SCOPE, &gh);
	if (error)
		goto out_qs;

	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
				 sdp->sd_jdesc->jd_blocks);
	if (error)
		goto out_rg_gunlock;

	gfs2_free_di(rgd, ip);

	gfs2_final_release_pages(ip);

	gfs2_trans_end(sdp);

out_rg_gunlock:
	gfs2_glock_dq_uninit(&gh);
out_qs:
	gfs2_quota_unhold(ip);
	return error;
}

/**
 * gfs2_glock_put_eventually
 * @gl:	The glock to put
 *
 * When under memory pressure, trigger a deferred glock put to make sure we
 * won't call into DLM and deadlock.  Otherwise, put the glock directly.
 */

static void gfs2_glock_put_eventually(struct gfs2_glock *gl)
{
	if (current->flags & PF_MEMALLOC)
		gfs2_glock_queue_put(gl);
	else
		gfs2_glock_put(gl);
}

static bool gfs2_upgrade_iopen_glock(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_holder *gh = &ip->i_iopen_gh;
	long timeout = 5 * HZ;
	int error;

	gh->gh_flags |= GL_NOCACHE;
	gfs2_glock_dq_wait(gh);

	/*
	 * If there are no other lock holders, we will immediately get
	 * exclusive access to the iopen glock here.
	 *
	 * Otherwise, the other nodes holding the lock will be notified about
	 * our locking request.  If they do not have the inode open, they are
	 * expected to evict the cached inode and release the lock, allowing us
	 * to proceed.
	 *
	 * Otherwise, if they cannot evict the inode, they are expected to poke
	 * the inode glock (note: not the iopen glock).  We will notice that
	 * and stop waiting for the iopen glock immediately.  The other node(s)
	 * are then expected to take care of deleting the inode when they no
	 * longer use it.
	 *
	 * As a last resort, if another node keeps holding the iopen glock
	 * without showing any activity on the inode glock, we will eventually
	 * time out and fail the iopen glock upgrade.
	 *
	 * Note that we're passing the LM_FLAG_TRY_1CB flag to the first
	 * locking request as an optimization to notify lock holders as soon as
	 * possible.  Without that flag, they'd be notified implicitly by the
	 * second locking request.
	 */

	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, gh);
	error = gfs2_glock_nq(gh);
	if (error != GLR_TRYFAILED)
		return !error;

	gfs2_holder_reinit(LM_ST_EXCLUSIVE, GL_ASYNC | GL_NOCACHE, gh);
	error = gfs2_glock_nq(gh);
	if (error)
		return false;

	timeout = wait_event_interruptible_timeout(sdp->sd_async_glock_wait,
		!test_bit(HIF_WAIT, &gh->gh_iflags) ||
		test_bit(GLF_DEMOTE, &ip->i_gl->gl_flags),
		timeout);
	if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) {
		gfs2_glock_dq(gh);
		return false;
	}
	return gfs2_glock_holder_ready(gh) == 0;
}

/**
 * evict_should_delete - determine whether the inode is eligible for deletion
 * @inode: The inode to evict
 * @gh: The glock holder structure
 *
 * This function determines whether the evicted inode is eligible to be deleted
 * and locks the inode glock.
 *
 * Returns: the fate of the dinode
 */
static enum dinode_demise evict_should_delete(struct inode *inode,
					      struct gfs2_holder *gh)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct super_block *sb = inode->i_sb;
	struct gfs2_sbd *sdp = sb->s_fs_info;
	int ret;

	if (unlikely(test_bit(GIF_ALLOC_FAILED, &ip->i_flags)))
		goto should_delete;

	if (test_bit(GIF_DEFERRED_DELETE, &ip->i_flags))
		return SHOULD_DEFER_EVICTION;

	/* Deletes should never happen under memory pressure anymore.  */
	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
		return SHOULD_DEFER_EVICTION;

	/* Must not read inode block until block type has been verified */
	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, gh);
	if (unlikely(ret)) {
		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
		return SHOULD_DEFER_EVICTION;
	}

	if (gfs2_inode_already_deleted(ip->i_gl, ip->i_no_formal_ino))
		return SHOULD_NOT_DELETE_DINODE;
	ret = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
	if (ret)
		return SHOULD_NOT_DELETE_DINODE;

	ret = gfs2_instantiate(gh);
	if (ret)
		return SHOULD_NOT_DELETE_DINODE;

	/*
	 * The inode may have been recreated in the meantime.
	 */
	if (inode->i_nlink)
		return SHOULD_NOT_DELETE_DINODE;

should_delete:
	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
		if (!gfs2_upgrade_iopen_glock(inode)) {
			gfs2_holder_uninit(&ip->i_iopen_gh);
			return SHOULD_NOT_DELETE_DINODE;
		}
	}
	return SHOULD_DELETE_DINODE;
}

/**
 * evict_unlinked_inode - delete the pieces of an unlinked evicted inode
 * @inode: The inode to evict
 */
static int evict_unlinked_inode(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	int ret;

	if (S_ISDIR(inode->i_mode) &&
	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
		ret = gfs2_dir_exhash_dealloc(ip);
		if (ret)
			goto out;
	}

	if (ip->i_eattr) {
		ret = gfs2_ea_dealloc(ip);
		if (ret)
			goto out;
	}

	if (!gfs2_is_stuffed(ip)) {
		ret = gfs2_file_dealloc(ip);
		if (ret)
			goto out;
	}

	/*
	 * As soon as we clear the bitmap for the dinode, gfs2_create_inode()
	 * can get called to recreate it, or even gfs2_inode_lookup() if the
	 * inode was recreated on another node in the meantime.
	 *
	 * However, inserting the new inode into the inode hash table will not
	 * succeed until the old inode is removed, and that only happens after
	 * ->evict_inode() returns.  The new inode is attached to its inode and
	 *  iopen glocks after inserting it into the inode hash table, so at
	 *  that point we can be sure that both glocks are unused.
	 */

	ret = gfs2_dinode_dealloc(ip);
	if (!ret && ip->i_gl)
		gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino);

out:
	return ret;
}

/*
 * evict_linked_inode - evict an inode whose dinode has not been unlinked
 * @inode: The inode to evict
 */
static int evict_linked_inode(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct address_space *metamapping;
	int ret;

	gfs2_log_flush(sdp, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
		       GFS2_LFC_EVICT_INODE);
	metamapping = gfs2_glock2aspace(ip->i_gl);
	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
		filemap_fdatawrite(metamapping);
		filemap_fdatawait(metamapping);
	}
	write_inode_now(inode, 1);
	gfs2_ail_flush(ip->i_gl, 0);

	ret = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
	if (ret)
		return ret;

	/* Needs to be done before glock release & also in a transaction */
	truncate_inode_pages(&inode->i_data, 0);
	truncate_inode_pages(metamapping, 0);
	gfs2_trans_end(sdp);
	return 0;
}

/**
 * gfs2_evict_inode - Remove an inode from cache
 * @inode: The inode to evict
 *
 * There are three cases to consider:
 * 1. i_nlink == 0, we are final opener (and must deallocate)
 * 2. i_nlink == 0, we are not the final opener (and cannot deallocate)
 * 3. i_nlink > 0
 *
 * If the fs is read only, then we have to treat all cases as per #3
 * since we are unable to do any deallocation. The inode will be
 * deallocated by the next read/write node to attempt an allocation
 * in the same resource group
 *
 * We have to (at the moment) hold the inodes main lock to cover
 * the gap between unlocking the shared lock on the iopen lock and
 * taking the exclusive lock. I'd rather do a shared -> exclusive
 * conversion on the iopen lock, but we can change that later. This
 * is safe, just less efficient.
 */

static void gfs2_evict_inode(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int ret;

	if (inode->i_nlink || sb_rdonly(sb) || !ip->i_no_addr)
		goto out;

	/*
	 * In case of an incomplete mount, gfs2_evict_inode() may be called for
	 * system files without having an active journal to write to.  In that
	 * case, skip the filesystem evict.
	 */
	if (!sdp->sd_jdesc)
		goto out;

	gfs2_holder_mark_uninitialized(&gh);
	ret = evict_should_delete(inode, &gh);
	if (ret == SHOULD_DEFER_EVICTION)
		goto out;
	if (ret == SHOULD_DELETE_DINODE)
		ret = evict_unlinked_inode(inode);
	else
		ret = evict_linked_inode(inode);

	if (gfs2_rs_active(&ip->i_res))
		gfs2_rs_deltree(&ip->i_res);

	if (gfs2_holder_initialized(&gh))
		gfs2_glock_dq_uninit(&gh);
	if (ret && ret != GLR_TRYFAILED && ret != -EROFS)
		fs_warn(sdp, "gfs2_evict_inode: %d\n", ret);
out:
	truncate_inode_pages_final(&inode->i_data);
	if (ip->i_qadata)
		gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);
	gfs2_rs_deltree(&ip->i_res);
	gfs2_ordered_del_inode(ip);
	clear_inode(inode);
	gfs2_dir_hash_inval(ip);
	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;

		glock_clear_object(gl, ip);
		gfs2_glock_hold(gl);
		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
		gfs2_glock_put_eventually(gl);
	}
	if (ip->i_gl) {
		glock_clear_object(ip->i_gl, ip);
		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
		gfs2_glock_add_to_lru(ip->i_gl);
		gfs2_glock_put_eventually(ip->i_gl);
		rcu_assign_pointer(ip->i_gl, NULL);
	}
}

static struct inode *gfs2_alloc_inode(struct super_block *sb)
{
	struct gfs2_inode *ip;

	ip = alloc_inode_sb(sb, gfs2_inode_cachep, GFP_KERNEL);
	if (!ip)
		return NULL;
	ip->i_no_addr = 0;
	ip->i_flags = 0;
	ip->i_gl = NULL;
	gfs2_holder_mark_uninitialized(&ip->i_iopen_gh);
	memset(&ip->i_res, 0, sizeof(ip->i_res));
	RB_CLEAR_NODE(&ip->i_res.rs_node);
	ip->i_rahead = 0;
	return &ip->i_inode;
}

static void gfs2_free_inode(struct inode *inode)
{
	kmem_cache_free(gfs2_inode_cachep, GFS2_I(inode));
}

extern void free_local_statfs_inodes(struct gfs2_sbd *sdp)
{
	struct local_statfs_inode *lsi, *safe;

	/* Run through the statfs inodes list to iput and free memory */
	list_for_each_entry_safe(lsi, safe, &sdp->sd_sc_inodes_list, si_list) {
		if (lsi->si_jid == sdp->sd_jdesc->jd_jid)
			sdp->sd_sc_inode = NULL; /* belongs to this node */
		if (lsi->si_sc_inode)
			iput(lsi->si_sc_inode);
		list_del(&lsi->si_list);
		kfree(lsi);
	}
}

extern struct inode *find_local_statfs_inode(struct gfs2_sbd *sdp,
					     unsigned int index)
{
	struct local_statfs_inode *lsi;

	/* Return the local (per node) statfs inode in the
	 * sdp->sd_sc_inodes_list corresponding to the 'index'. */
	list_for_each_entry(lsi, &sdp->sd_sc_inodes_list, si_list) {
		if (lsi->si_jid == index)
			return lsi->si_sc_inode;
	}
	return NULL;
}

const struct super_operations gfs2_super_ops = {
	.alloc_inode		= gfs2_alloc_inode,
	.free_inode		= gfs2_free_inode,
	.write_inode		= gfs2_write_inode,
	.dirty_inode		= gfs2_dirty_inode,
	.evict_inode		= gfs2_evict_inode,
	.put_super		= gfs2_put_super,
	.sync_fs		= gfs2_sync_fs,
	.freeze_super		= gfs2_freeze_super,
	.thaw_super		= gfs2_thaw_super,
	.statfs			= gfs2_statfs,
	.drop_inode		= gfs2_drop_inode,
	.show_options		= gfs2_show_options,
};