summaryrefslogtreecommitdiff
path: root/fs/gfs2/glock.c
blob: 992c5c0cb5045144f61f7d06032d61301ee484d6 (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
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 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.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/buffer_head.h>
#include <linux/delay.h>
#include <linux/sort.h>
#include <linux/jhash.h>
#include <linux/kallsyms.h>
#include <linux/gfs2_ondisk.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/module.h>
#include <asm/uaccess.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
#include <linux/rcupdate.h>
#include <linux/rculist_bl.h>
#include <linux/bit_spinlock.h>
#include <linux/percpu.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "super.h"
#include "util.h"
#include "bmap.h"
#define CREATE_TRACE_POINTS
#include "trace_gfs2.h"

struct gfs2_glock_iter {
	int hash;			/* hash bucket index           */
	unsigned nhash;			/* Index within current bucket */
	struct gfs2_sbd *sdp;		/* incore superblock           */
	struct gfs2_glock *gl;		/* current glock struct        */
	loff_t last_pos;		/* last position               */
};

typedef void (*glock_examiner) (struct gfs2_glock * gl);

static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);

static struct dentry *gfs2_root;
static struct workqueue_struct *glock_workqueue;
struct workqueue_struct *gfs2_delete_workqueue;
static LIST_HEAD(lru_list);
static atomic_t lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(lru_lock);

#define GFS2_GL_HASH_SHIFT      15
#define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
#define GFS2_GL_HASH_MASK       (GFS2_GL_HASH_SIZE - 1)

static struct hlist_bl_head gl_hash_table[GFS2_GL_HASH_SIZE];
static struct dentry *gfs2_root;

/**
 * gl_hash() - Turn glock number into hash bucket number
 * @lock: The glock number
 *
 * Returns: The number of the corresponding hash bucket
 */

static unsigned int gl_hash(const struct gfs2_sbd *sdp,
			    const struct lm_lockname *name)
{
	unsigned int h;

	h = jhash(&name->ln_number, sizeof(u64), 0);
	h = jhash(&name->ln_type, sizeof(unsigned int), h);
	h = jhash(&sdp, sizeof(struct gfs2_sbd *), h);
	h &= GFS2_GL_HASH_MASK;

	return h;
}

static inline void spin_lock_bucket(unsigned int hash)
{
	hlist_bl_lock(&gl_hash_table[hash]);
}

static inline void spin_unlock_bucket(unsigned int hash)
{
	hlist_bl_unlock(&gl_hash_table[hash]);
}

static void gfs2_glock_dealloc(struct rcu_head *rcu)
{
	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);

	if (gl->gl_ops->go_flags & GLOF_ASPACE) {
		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
	} else {
		kfree(gl->gl_lksb.sb_lvbptr);
		kmem_cache_free(gfs2_glock_cachep, gl);
	}
}

void gfs2_glock_free(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;

	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
		wake_up(&sdp->sd_glock_wait);
}

/**
 * gfs2_glock_hold() - increment reference count on glock
 * @gl: The glock to hold
 *
 */

void gfs2_glock_hold(struct gfs2_glock *gl)
{
	GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0);
	atomic_inc(&gl->gl_ref);
}

/**
 * demote_ok - Check to see if it's ok to unlock a glock
 * @gl: the glock
 *
 * Returns: 1 if it's ok
 */

static int demote_ok(const struct gfs2_glock *gl)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;

	if (gl->gl_state == LM_ST_UNLOCKED)
		return 0;
	if (!list_empty(&gl->gl_holders))
		return 0;
	if (glops->go_demote_ok)
		return glops->go_demote_ok(gl);
	return 1;
}


void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
{
	spin_lock(&lru_lock);

	if (!list_empty(&gl->gl_lru))
		list_del_init(&gl->gl_lru);
	else
		atomic_inc(&lru_count);

	list_add_tail(&gl->gl_lru, &lru_list);
	set_bit(GLF_LRU, &gl->gl_flags);
	spin_unlock(&lru_lock);
}

static void __gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
{
	if (!list_empty(&gl->gl_lru)) {
		list_del_init(&gl->gl_lru);
		atomic_dec(&lru_count);
		clear_bit(GLF_LRU, &gl->gl_flags);
	}
}

static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
{
	spin_lock(&lru_lock);
	__gfs2_glock_remove_from_lru(gl);
	spin_unlock(&lru_lock);
}

/**
 * gfs2_glock_put_nolock() - Decrement reference count on glock
 * @gl: The glock to put
 *
 * This function should only be used if the caller has its own reference
 * to the glock, in addition to the one it is dropping.
 */

void gfs2_glock_put_nolock(struct gfs2_glock *gl)
{
	if (atomic_dec_and_test(&gl->gl_ref))
		GLOCK_BUG_ON(gl, 1);
}

/**
 * gfs2_glock_put() - Decrement reference count on glock
 * @gl: The glock to put
 *
 */

void gfs2_glock_put(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct address_space *mapping = gfs2_glock2aspace(gl);

	if (atomic_dec_and_lock(&gl->gl_ref, &lru_lock)) {
		__gfs2_glock_remove_from_lru(gl);
		spin_unlock(&lru_lock);
		spin_lock_bucket(gl->gl_hash);
		hlist_bl_del_rcu(&gl->gl_list);
		spin_unlock_bucket(gl->gl_hash);
		GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
		GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
		trace_gfs2_glock_put(gl);
		sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
	}
}

/**
 * search_bucket() - Find struct gfs2_glock by lock number
 * @bucket: the bucket to search
 * @name: The lock name
 *
 * Returns: NULL, or the struct gfs2_glock with the requested number
 */

static struct gfs2_glock *search_bucket(unsigned int hash,
					const struct gfs2_sbd *sdp,
					const struct lm_lockname *name)
{
	struct gfs2_glock *gl;
	struct hlist_bl_node *h;

	hlist_bl_for_each_entry_rcu(gl, h, &gl_hash_table[hash], gl_list) {
		if (!lm_name_equal(&gl->gl_name, name))
			continue;
		if (gl->gl_sbd != sdp)
			continue;
		if (atomic_inc_not_zero(&gl->gl_ref))
			return gl;
	}

	return NULL;
}

/**
 * may_grant - check if its ok to grant a new lock
 * @gl: The glock
 * @gh: The lock request which we wish to grant
 *
 * Returns: true if its ok to grant the lock
 */

static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
{
	const struct gfs2_holder *gh_head = list_entry(gl->gl_holders.next, const struct gfs2_holder, gh_list);
	if ((gh->gh_state == LM_ST_EXCLUSIVE ||
	     gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
		return 0;
	if (gl->gl_state == gh->gh_state)
		return 1;
	if (gh->gh_flags & GL_EXACT)
		return 0;
	if (gl->gl_state == LM_ST_EXCLUSIVE) {
		if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
			return 1;
		if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
			return 1;
	}
	if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
		return 1;
	return 0;
}

static void gfs2_holder_wake(struct gfs2_holder *gh)
{
	clear_bit(HIF_WAIT, &gh->gh_iflags);
	smp_mb__after_clear_bit();
	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
}

/**
 * do_error - Something unexpected has happened during a lock request
 *
 */

static inline void do_error(struct gfs2_glock *gl, const int ret)
{
	struct gfs2_holder *gh, *tmp;

	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
			continue;
		if (ret & LM_OUT_ERROR)
			gh->gh_error = -EIO;
		else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
			gh->gh_error = GLR_TRYFAILED;
		else
			continue;
		list_del_init(&gh->gh_list);
		trace_gfs2_glock_queue(gh, 0);
		gfs2_holder_wake(gh);
	}
}

/**
 * do_promote - promote as many requests as possible on the current queue
 * @gl: The glock
 * 
 * Returns: 1 if there is a blocked holder at the head of the list, or 2
 *          if a type specific operation is underway.
 */

static int do_promote(struct gfs2_glock *gl)
__releases(&gl->gl_spin)
__acquires(&gl->gl_spin)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	struct gfs2_holder *gh, *tmp;
	int ret;

restart:
	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
			continue;
		if (may_grant(gl, gh)) {
			if (gh->gh_list.prev == &gl->gl_holders &&
			    glops->go_lock) {
				spin_unlock(&gl->gl_spin);
				/* FIXME: eliminate this eventually */
				ret = glops->go_lock(gh);
				spin_lock(&gl->gl_spin);
				if (ret) {
					if (ret == 1)
						return 2;
					gh->gh_error = ret;
					list_del_init(&gh->gh_list);
					trace_gfs2_glock_queue(gh, 0);
					gfs2_holder_wake(gh);
					goto restart;
				}
				set_bit(HIF_HOLDER, &gh->gh_iflags);
				trace_gfs2_promote(gh, 1);
				gfs2_holder_wake(gh);
				goto restart;
			}
			set_bit(HIF_HOLDER, &gh->gh_iflags);
			trace_gfs2_promote(gh, 0);
			gfs2_holder_wake(gh);
			continue;
		}
		if (gh->gh_list.prev == &gl->gl_holders)
			return 1;
		do_error(gl, 0);
		break;
	}
	return 0;
}

/**
 * find_first_waiter - find the first gh that's waiting for the glock
 * @gl: the glock
 */

static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
{
	struct gfs2_holder *gh;

	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
			return gh;
	}
	return NULL;
}

/**
 * state_change - record that the glock is now in a different state
 * @gl: the glock
 * @new_state the new state
 *
 */

static void state_change(struct gfs2_glock *gl, unsigned int new_state)
{
	int held1, held2;

	held1 = (gl->gl_state != LM_ST_UNLOCKED);
	held2 = (new_state != LM_ST_UNLOCKED);

	if (held1 != held2) {
		if (held2)
			gfs2_glock_hold(gl);
		else
			gfs2_glock_put_nolock(gl);
	}
	if (held1 && held2 && list_empty(&gl->gl_holders))
		clear_bit(GLF_QUEUED, &gl->gl_flags);

	if (new_state != gl->gl_target)
		/* shorten our minimum hold time */
		gl->gl_hold_time = max(gl->gl_hold_time - GL_GLOCK_HOLD_DECR,
				       GL_GLOCK_MIN_HOLD);
	gl->gl_state = new_state;
	gl->gl_tchange = jiffies;
}

static void gfs2_demote_wake(struct gfs2_glock *gl)
{
	gl->gl_demote_state = LM_ST_EXCLUSIVE;
	clear_bit(GLF_DEMOTE, &gl->gl_flags);
	smp_mb__after_clear_bit();
	wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
}

/**
 * finish_xmote - The DLM has replied to one of our lock requests
 * @gl: The glock
 * @ret: The status from the DLM
 *
 */

static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	struct gfs2_holder *gh;
	unsigned state = ret & LM_OUT_ST_MASK;
	int rv;

	spin_lock(&gl->gl_spin);
	trace_gfs2_glock_state_change(gl, state);
	state_change(gl, state);
	gh = find_first_waiter(gl);

	/* Demote to UN request arrived during demote to SH or DF */
	if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
	    state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
		gl->gl_target = LM_ST_UNLOCKED;

	/* Check for state != intended state */
	if (unlikely(state != gl->gl_target)) {
		if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
			/* move to back of queue and try next entry */
			if (ret & LM_OUT_CANCELED) {
				if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
					list_move_tail(&gh->gh_list, &gl->gl_holders);
				gh = find_first_waiter(gl);
				gl->gl_target = gh->gh_state;
				goto retry;
			}
			/* Some error or failed "try lock" - report it */
			if ((ret & LM_OUT_ERROR) ||
			    (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
				gl->gl_target = gl->gl_state;
				do_error(gl, ret);
				goto out;
			}
		}
		switch(state) {
		/* Unlocked due to conversion deadlock, try again */
		case LM_ST_UNLOCKED:
retry:
			do_xmote(gl, gh, gl->gl_target);
			break;
		/* Conversion fails, unlock and try again */
		case LM_ST_SHARED:
		case LM_ST_DEFERRED:
			do_xmote(gl, gh, LM_ST_UNLOCKED);
			break;
		default: /* Everything else */
			printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
			GLOCK_BUG_ON(gl, 1);
		}
		spin_unlock(&gl->gl_spin);
		return;
	}

	/* Fast path - we got what we asked for */
	if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
		gfs2_demote_wake(gl);
	if (state != LM_ST_UNLOCKED) {
		if (glops->go_xmote_bh) {
			spin_unlock(&gl->gl_spin);
			rv = glops->go_xmote_bh(gl, gh);
			spin_lock(&gl->gl_spin);
			if (rv) {
				do_error(gl, rv);
				goto out;
			}
		}
		rv = do_promote(gl);
		if (rv == 2)
			goto out_locked;
	}
out:
	clear_bit(GLF_LOCK, &gl->gl_flags);
out_locked:
	spin_unlock(&gl->gl_spin);
}

/**
 * do_xmote - Calls the DLM to change the state of a lock
 * @gl: The lock state
 * @gh: The holder (only for promotes)
 * @target: The target lock state
 *
 */

static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
__releases(&gl->gl_spin)
__acquires(&gl->gl_spin)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	struct gfs2_sbd *sdp = gl->gl_sbd;
	unsigned int lck_flags = gh ? gh->gh_flags : 0;
	int ret;

	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
		      LM_FLAG_PRIORITY);
	GLOCK_BUG_ON(gl, gl->gl_state == target);
	GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
	if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
	    glops->go_inval) {
		set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
		do_error(gl, 0); /* Fail queued try locks */
	}
	gl->gl_req = target;
	set_bit(GLF_BLOCKING, &gl->gl_flags);
	if ((gl->gl_req == LM_ST_UNLOCKED) ||
	    (gl->gl_state == LM_ST_EXCLUSIVE) ||
	    (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
		clear_bit(GLF_BLOCKING, &gl->gl_flags);
	spin_unlock(&gl->gl_spin);
	if (glops->go_sync)
		glops->go_sync(gl);
	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
		glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
	clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);

	gfs2_glock_hold(gl);
	if (sdp->sd_lockstruct.ls_ops->lm_lock)	{
		/* lock_dlm */
		ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
		if (ret) {
			printk(KERN_ERR "GFS2: lm_lock ret %d\n", ret);
			GLOCK_BUG_ON(gl, 1);
		}
	} else { /* lock_nolock */
		finish_xmote(gl, target);
		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
			gfs2_glock_put(gl);
	}

	spin_lock(&gl->gl_spin);
}

/**
 * find_first_holder - find the first "holder" gh
 * @gl: the glock
 */

static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
{
	struct gfs2_holder *gh;

	if (!list_empty(&gl->gl_holders)) {
		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
			return gh;
	}
	return NULL;
}

/**
 * run_queue - do all outstanding tasks related to a glock
 * @gl: The glock in question
 * @nonblock: True if we must not block in run_queue
 *
 */

static void run_queue(struct gfs2_glock *gl, const int nonblock)
__releases(&gl->gl_spin)
__acquires(&gl->gl_spin)
{
	struct gfs2_holder *gh = NULL;
	int ret;

	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
		return;

	GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));

	if (test_bit(GLF_DEMOTE, &gl->gl_flags) &&
	    gl->gl_demote_state != gl->gl_state) {
		if (find_first_holder(gl))
			goto out_unlock;
		if (nonblock)
			goto out_sched;
		set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
		GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
		gl->gl_target = gl->gl_demote_state;
	} else {
		if (test_bit(GLF_DEMOTE, &gl->gl_flags))
			gfs2_demote_wake(gl);
		ret = do_promote(gl);
		if (ret == 0)
			goto out_unlock;
		if (ret == 2)
			goto out;
		gh = find_first_waiter(gl);
		gl->gl_target = gh->gh_state;
		if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
			do_error(gl, 0); /* Fail queued try locks */
	}
	do_xmote(gl, gh, gl->gl_target);
out:
	return;

out_sched:
	clear_bit(GLF_LOCK, &gl->gl_flags);
	smp_mb__after_clear_bit();
	gfs2_glock_hold(gl);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
		gfs2_glock_put_nolock(gl);
	return;

out_unlock:
	clear_bit(GLF_LOCK, &gl->gl_flags);
	smp_mb__after_clear_bit();
	return;
}

static void delete_work_func(struct work_struct *work)
{
	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct gfs2_inode *ip;
	struct inode *inode;
	u64 no_addr = gl->gl_name.ln_number;

	ip = gl->gl_object;
	/* Note: Unsafe to dereference ip as we don't hold right refs/locks */

	if (ip)
		inode = gfs2_ilookup(sdp->sd_vfs, no_addr, 1);
	else
		inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
	if (inode && !IS_ERR(inode)) {
		d_prune_aliases(inode);
		iput(inode);
	}
	gfs2_glock_put(gl);
}

static void glock_work_func(struct work_struct *work)
{
	unsigned long delay = 0;
	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
	int drop_ref = 0;

	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
		finish_xmote(gl, gl->gl_reply);
		drop_ref = 1;
	}
	spin_lock(&gl->gl_spin);
	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
	    gl->gl_state != LM_ST_UNLOCKED &&
	    gl->gl_demote_state != LM_ST_EXCLUSIVE) {
		unsigned long holdtime, now = jiffies;

		holdtime = gl->gl_tchange + gl->gl_hold_time;
		if (time_before(now, holdtime))
			delay = holdtime - now;

		if (!delay) {
			clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
			set_bit(GLF_DEMOTE, &gl->gl_flags);
		}
	}
	run_queue(gl, 0);
	spin_unlock(&gl->gl_spin);
	if (!delay)
		gfs2_glock_put(gl);
	else {
		if (gl->gl_name.ln_type != LM_TYPE_INODE)
			delay = 0;
		if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
			gfs2_glock_put(gl);
	}
	if (drop_ref)
		gfs2_glock_put(gl);
}

/**
 * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
 * @sdp: The GFS2 superblock
 * @number: the lock number
 * @glops: The glock_operations to use
 * @create: If 0, don't create the glock if it doesn't exist
 * @glp: the glock is returned here
 *
 * This does not lock a glock, just finds/creates structures for one.
 *
 * Returns: errno
 */

int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
		   const struct gfs2_glock_operations *glops, int create,
		   struct gfs2_glock **glp)
{
	struct super_block *s = sdp->sd_vfs;
	struct lm_lockname name = { .ln_number = number, .ln_type = glops->go_type };
	struct gfs2_glock *gl, *tmp;
	unsigned int hash = gl_hash(sdp, &name);
	struct address_space *mapping;
	struct kmem_cache *cachep;

	rcu_read_lock();
	gl = search_bucket(hash, sdp, &name);
	rcu_read_unlock();

	*glp = gl;
	if (gl)
		return 0;
	if (!create)
		return -ENOENT;

	if (glops->go_flags & GLOF_ASPACE)
		cachep = gfs2_glock_aspace_cachep;
	else
		cachep = gfs2_glock_cachep;
	gl = kmem_cache_alloc(cachep, GFP_KERNEL);
	if (!gl)
		return -ENOMEM;

	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));

	if (glops->go_flags & GLOF_LVB) {
		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL);
		if (!gl->gl_lksb.sb_lvbptr) {
			kmem_cache_free(cachep, gl);
			return -ENOMEM;
		}
	}

	atomic_inc(&sdp->sd_glock_disposal);
	gl->gl_sbd = sdp;
	gl->gl_flags = 0;
	gl->gl_name = name;
	atomic_set(&gl->gl_ref, 1);
	gl->gl_state = LM_ST_UNLOCKED;
	gl->gl_target = LM_ST_UNLOCKED;
	gl->gl_demote_state = LM_ST_EXCLUSIVE;
	gl->gl_hash = hash;
	gl->gl_ops = glops;
	gl->gl_dstamp = ktime_set(0, 0);
	preempt_disable();
	/* We use the global stats to estimate the initial per-glock stats */
	gl->gl_stats = this_cpu_ptr(sdp->sd_lkstats)->lkstats[glops->go_type];
	preempt_enable();
	gl->gl_stats.stats[GFS2_LKS_DCOUNT] = 0;
	gl->gl_stats.stats[GFS2_LKS_QCOUNT] = 0;
	gl->gl_tchange = jiffies;
	gl->gl_object = NULL;
	gl->gl_hold_time = GL_GLOCK_DFT_HOLD;
	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
	INIT_WORK(&gl->gl_delete, delete_work_func);

	mapping = gfs2_glock2aspace(gl);
	if (mapping) {
                mapping->a_ops = &gfs2_meta_aops;
		mapping->host = s->s_bdev->bd_inode;
		mapping->flags = 0;
		mapping_set_gfp_mask(mapping, GFP_NOFS);
		mapping->private_data = NULL;
		mapping->backing_dev_info = s->s_bdi;
		mapping->writeback_index = 0;
	}

	spin_lock_bucket(hash);
	tmp = search_bucket(hash, sdp, &name);
	if (tmp) {
		spin_unlock_bucket(hash);
		kfree(gl->gl_lksb.sb_lvbptr);
		kmem_cache_free(cachep, gl);
		atomic_dec(&sdp->sd_glock_disposal);
		gl = tmp;
	} else {
		hlist_bl_add_head_rcu(&gl->gl_list, &gl_hash_table[hash]);
		spin_unlock_bucket(hash);
	}

	*glp = gl;

	return 0;
}

/**
 * gfs2_holder_init - initialize a struct gfs2_holder in the default way
 * @gl: the glock
 * @state: the state we're requesting
 * @flags: the modifier flags
 * @gh: the holder structure
 *
 */

void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
		      struct gfs2_holder *gh)
{
	INIT_LIST_HEAD(&gh->gh_list);
	gh->gh_gl = gl;
	gh->gh_ip = (unsigned long)__builtin_return_address(0);
	gh->gh_owner_pid = get_pid(task_pid(current));
	gh->gh_state = state;
	gh->gh_flags = flags;
	gh->gh_error = 0;
	gh->gh_iflags = 0;
	gfs2_glock_hold(gl);
}

/**
 * gfs2_holder_reinit - reinitialize a struct gfs2_holder so we can requeue it
 * @state: the state we're requesting
 * @flags: the modifier flags
 * @gh: the holder structure
 *
 * Don't mess with the glock.
 *
 */

void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
{
	gh->gh_state = state;
	gh->gh_flags = flags;
	gh->gh_iflags = 0;
	gh->gh_ip = (unsigned long)__builtin_return_address(0);
	if (gh->gh_owner_pid)
		put_pid(gh->gh_owner_pid);
	gh->gh_owner_pid = get_pid(task_pid(current));
}

/**
 * gfs2_holder_uninit - uninitialize a holder structure (drop glock reference)
 * @gh: the holder structure
 *
 */

void gfs2_holder_uninit(struct gfs2_holder *gh)
{
	put_pid(gh->gh_owner_pid);
	gfs2_glock_put(gh->gh_gl);
	gh->gh_gl = NULL;
	gh->gh_ip = 0;
}

/**
 * gfs2_glock_holder_wait
 * @word: unused
 *
 * This function and gfs2_glock_demote_wait both show up in the WCHAN
 * field. Thus I've separated these otherwise identical functions in
 * order to be more informative to the user.
 */

static int gfs2_glock_holder_wait(void *word)
{
        schedule();
        return 0;
}

static int gfs2_glock_demote_wait(void *word)
{
	schedule();
	return 0;
}

/**
 * gfs2_glock_wait - wait on a glock acquisition
 * @gh: the glock holder
 *
 * Returns: 0 on success
 */

int gfs2_glock_wait(struct gfs2_holder *gh)
{
	unsigned long time1 = jiffies;

	might_sleep();
	wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
	if (time_after(jiffies, time1 + HZ)) /* have we waited > a second? */
		/* Lengthen the minimum hold time. */
		gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time +
					      GL_GLOCK_HOLD_INCR,
					      GL_GLOCK_MAX_HOLD);
	return gh->gh_error;
}

/**
 * handle_callback - process a demote request
 * @gl: the glock
 * @state: the state the caller wants us to change to
 *
 * There are only two requests that we are going to see in actual
 * practise: LM_ST_SHARED and LM_ST_UNLOCKED
 */

static void handle_callback(struct gfs2_glock *gl, unsigned int state,
			    unsigned long delay)
{
	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;

	set_bit(bit, &gl->gl_flags);
	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
		gl->gl_demote_state = state;
		gl->gl_demote_time = jiffies;
	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
			gl->gl_demote_state != state) {
		gl->gl_demote_state = LM_ST_UNLOCKED;
	}
	if (gl->gl_ops->go_callback)
		gl->gl_ops->go_callback(gl);
	trace_gfs2_demote_rq(gl);
}

void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);

	if (seq) {
		seq_vprintf(seq, fmt, args);
	} else {
		vaf.fmt = fmt;
		vaf.va = &args;

		printk(KERN_ERR " %pV", &vaf);
	}

	va_end(args);
}

/**
 * add_to_queue - Add a holder to the wait queue (but look for recursion)
 * @gh: the holder structure to add
 *
 * Eventually we should move the recursive locking trap to a
 * debugging option or something like that. This is the fast
 * path and needs to have the minimum number of distractions.
 * 
 */

static inline void add_to_queue(struct gfs2_holder *gh)
__releases(&gl->gl_spin)
__acquires(&gl->gl_spin)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct list_head *insert_pt = NULL;
	struct gfs2_holder *gh2;
	int try_futile = 0;

	BUG_ON(gh->gh_owner_pid == NULL);
	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
		BUG();

	if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
		if (test_bit(GLF_LOCK, &gl->gl_flags))
			try_futile = !may_grant(gl, gh);
		if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
			goto fail;
	}

	list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
		if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
			goto trap_recursive;
		if (try_futile &&
		    !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
fail:
			gh->gh_error = GLR_TRYFAILED;
			gfs2_holder_wake(gh);
			return;
		}
		if (test_bit(HIF_HOLDER, &gh2->gh_iflags))
			continue;
		if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
			insert_pt = &gh2->gh_list;
	}
	set_bit(GLF_QUEUED, &gl->gl_flags);
	trace_gfs2_glock_queue(gh, 1);
	gfs2_glstats_inc(gl, GFS2_LKS_QCOUNT);
	gfs2_sbstats_inc(gl, GFS2_LKS_QCOUNT);
	if (likely(insert_pt == NULL)) {
		list_add_tail(&gh->gh_list, &gl->gl_holders);
		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
			goto do_cancel;
		return;
	}
	list_add_tail(&gh->gh_list, insert_pt);
do_cancel:
	gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
	if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
		spin_unlock(&gl->gl_spin);
		if (sdp->sd_lockstruct.ls_ops->lm_cancel)
			sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
		spin_lock(&gl->gl_spin);
	}
	return;

trap_recursive:
	print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip);
	printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
	printk(KERN_ERR "lock type: %d req lock state : %d\n",
	       gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
	print_symbol(KERN_ERR "new: %s\n", gh->gh_ip);
	printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
	printk(KERN_ERR "lock type: %d req lock state : %d\n",
	       gh->gh_gl->gl_name.ln_type, gh->gh_state);
	gfs2_dump_glock(NULL, gl);
	BUG();
}

/**
 * gfs2_glock_nq - enqueue a struct gfs2_holder onto a glock (acquire a glock)
 * @gh: the holder structure
 *
 * if (gh->gh_flags & GL_ASYNC), this never returns an error
 *
 * Returns: 0, GLR_TRYFAILED, or errno on failure
 */

int gfs2_glock_nq(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_sbd *sdp = gl->gl_sbd;
	int error = 0;

	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		return -EIO;

	if (test_bit(GLF_LRU, &gl->gl_flags))
		gfs2_glock_remove_from_lru(gl);

	spin_lock(&gl->gl_spin);
	add_to_queue(gh);
	if ((LM_FLAG_NOEXP & gh->gh_flags) &&
	    test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
		set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
	run_queue(gl, 1);
	spin_unlock(&gl->gl_spin);

	if (!(gh->gh_flags & GL_ASYNC))
		error = gfs2_glock_wait(gh);

	return error;
}

/**
 * gfs2_glock_poll - poll to see if an async request has been completed
 * @gh: the holder
 *
 * Returns: 1 if the request is ready to be gfs2_glock_wait()ed on
 */

int gfs2_glock_poll(struct gfs2_holder *gh)
{
	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
}

/**
 * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
 * @gh: the glock holder
 *
 */

void gfs2_glock_dq(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	unsigned delay = 0;
	int fast_path = 0;

	spin_lock(&gl->gl_spin);
	if (gh->gh_flags & GL_NOCACHE)
		handle_callback(gl, LM_ST_UNLOCKED, 0);

	list_del_init(&gh->gh_list);
	if (find_first_holder(gl) == NULL) {
		if (glops->go_unlock) {
			GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
			spin_unlock(&gl->gl_spin);
			glops->go_unlock(gh);
			spin_lock(&gl->gl_spin);
			clear_bit(GLF_LOCK, &gl->gl_flags);
		}
		if (list_empty(&gl->gl_holders) &&
		    !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
		    !test_bit(GLF_DEMOTE, &gl->gl_flags))
			fast_path = 1;
	}
	if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl))
		gfs2_glock_add_to_lru(gl);

	trace_gfs2_glock_queue(gh, 0);
	spin_unlock(&gl->gl_spin);
	if (likely(fast_path))
		return;

	gfs2_glock_hold(gl);
	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
	    !test_bit(GLF_DEMOTE, &gl->gl_flags) &&
	    gl->gl_name.ln_type == LM_TYPE_INODE)
		delay = gl->gl_hold_time;
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
		gfs2_glock_put(gl);
}

void gfs2_glock_dq_wait(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	gfs2_glock_dq(gh);
	might_sleep();
	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
}

/**
 * gfs2_glock_dq_uninit - dequeue a holder from a glock and initialize it
 * @gh: the holder structure
 *
 */

void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
{
	gfs2_glock_dq(gh);
	gfs2_holder_uninit(gh);
}

/**
 * gfs2_glock_nq_num - acquire a glock based on lock number
 * @sdp: the filesystem
 * @number: the lock number
 * @glops: the glock operations for the type of glock
 * @state: the state to acquire the glock in
 * @flags: modifier flags for the acquisition
 * @gh: the struct gfs2_holder
 *
 * Returns: errno
 */

int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
		      const struct gfs2_glock_operations *glops,
		      unsigned int state, int flags, struct gfs2_holder *gh)
{
	struct gfs2_glock *gl;
	int error;

	error = gfs2_glock_get(sdp, number, glops, CREATE, &gl);
	if (!error) {
		error = gfs2_glock_nq_init(gl, state, flags, gh);
		gfs2_glock_put(gl);
	}

	return error;
}

/**
 * glock_compare - Compare two struct gfs2_glock structures for sorting
 * @arg_a: the first structure
 * @arg_b: the second structure
 *
 */

static int glock_compare(const void *arg_a, const void *arg_b)
{
	const struct gfs2_holder *gh_a = *(const struct gfs2_holder **)arg_a;
	const struct gfs2_holder *gh_b = *(const struct gfs2_holder **)arg_b;
	const struct lm_lockname *a = &gh_a->gh_gl->gl_name;
	const struct lm_lockname *b = &gh_b->gh_gl->gl_name;

	if (a->ln_number > b->ln_number)
		return 1;
	if (a->ln_number < b->ln_number)
		return -1;
	BUG_ON(gh_a->gh_gl->gl_ops->go_type == gh_b->gh_gl->gl_ops->go_type);
	return 0;
}

/**
 * nq_m_sync - synchonously acquire more than one glock in deadlock free order
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 * Returns: 0 on success (all glocks acquired),
 *          errno on failure (no glocks acquired)
 */

static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs,
		     struct gfs2_holder **p)
{
	unsigned int x;
	int error = 0;

	for (x = 0; x < num_gh; x++)
		p[x] = &ghs[x];

	sort(p, num_gh, sizeof(struct gfs2_holder *), glock_compare, NULL);

	for (x = 0; x < num_gh; x++) {
		p[x]->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);

		error = gfs2_glock_nq(p[x]);
		if (error) {
			while (x--)
				gfs2_glock_dq(p[x]);
			break;
		}
	}

	return error;
}

/**
 * gfs2_glock_nq_m - acquire multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 *
 * Returns: 0 on success (all glocks acquired),
 *          errno on failure (no glocks acquired)
 */

int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	struct gfs2_holder *tmp[4];
	struct gfs2_holder **pph = tmp;
	int error = 0;

	switch(num_gh) {
	case 0:
		return 0;
	case 1:
		ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
		return gfs2_glock_nq(ghs);
	default:
		if (num_gh <= 4)
			break;
		pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
		if (!pph)
			return -ENOMEM;
	}

	error = nq_m_sync(num_gh, ghs, pph);

	if (pph != tmp)
		kfree(pph);

	return error;
}

/**
 * gfs2_glock_dq_m - release multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 */

void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	while (num_gh--)
		gfs2_glock_dq(&ghs[num_gh]);
}

/**
 * gfs2_glock_dq_uninit_m - release multiple glocks
 * @num_gh: the number of structures
 * @ghs: an array of struct gfs2_holder structures
 *
 */

void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
	while (num_gh--)
		gfs2_glock_dq_uninit(&ghs[num_gh]);
}

void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
{
	unsigned long delay = 0;
	unsigned long holdtime;
	unsigned long now = jiffies;

	gfs2_glock_hold(gl);
	holdtime = gl->gl_tchange + gl->gl_hold_time;
	if (test_bit(GLF_QUEUED, &gl->gl_flags) &&
	    gl->gl_name.ln_type == LM_TYPE_INODE) {
		if (time_before(now, holdtime))
			delay = holdtime - now;
		if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
			delay = gl->gl_hold_time;
	}

	spin_lock(&gl->gl_spin);
	handle_callback(gl, state, delay);
	spin_unlock(&gl->gl_spin);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
		gfs2_glock_put(gl);
}

/**
 * gfs2_should_freeze - Figure out if glock should be frozen
 * @gl: The glock in question
 *
 * Glocks are not frozen if (a) the result of the dlm operation is
 * an error, (b) the locking operation was an unlock operation or
 * (c) if there is a "noexp" flagged request anywhere in the queue
 *
 * Returns: 1 if freezing should occur, 0 otherwise
 */

static int gfs2_should_freeze(const struct gfs2_glock *gl)
{
	const struct gfs2_holder *gh;

	if (gl->gl_reply & ~LM_OUT_ST_MASK)
		return 0;
	if (gl->gl_target == LM_ST_UNLOCKED)
		return 0;

	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
			continue;
		if (LM_FLAG_NOEXP & gh->gh_flags)
			return 0;
	}

	return 1;
}

/**
 * gfs2_glock_complete - Callback used by locking
 * @gl: Pointer to the glock
 * @ret: The return value from the dlm
 *
 * The gl_reply field is under the gl_spin lock so that it is ok
 * to use a bitfield shared with other glock state fields.
 */

void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
{
	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;

	spin_lock(&gl->gl_spin);
	gl->gl_reply = ret;

	if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))) {
		if (gfs2_should_freeze(gl)) {
			set_bit(GLF_FROZEN, &gl->gl_flags);
			spin_unlock(&gl->gl_spin);
			return;
		}
	}

	spin_unlock(&gl->gl_spin);
	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
	smp_wmb();
	gfs2_glock_hold(gl);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
		gfs2_glock_put(gl);
}


static int gfs2_shrink_glock_memory(struct shrinker *shrink,
				    struct shrink_control *sc)
{
	struct gfs2_glock *gl;
	int may_demote;
	int nr_skipped = 0;
	int nr = sc->nr_to_scan;
	gfp_t gfp_mask = sc->gfp_mask;
	LIST_HEAD(skipped);

	if (nr == 0)
		goto out;

	if (!(gfp_mask & __GFP_FS))
		return -1;

	spin_lock(&lru_lock);
	while(nr && !list_empty(&lru_list)) {
		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
		list_del_init(&gl->gl_lru);
		clear_bit(GLF_LRU, &gl->gl_flags);
		atomic_dec(&lru_count);

		/* Test for being demotable */
		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
			gfs2_glock_hold(gl);
			spin_unlock(&lru_lock);
			spin_lock(&gl->gl_spin);
			may_demote = demote_ok(gl);
			if (may_demote) {
				handle_callback(gl, LM_ST_UNLOCKED, 0);
				nr--;
			}
			clear_bit(GLF_LOCK, &gl->gl_flags);
			smp_mb__after_clear_bit();
			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
				gfs2_glock_put_nolock(gl);
			spin_unlock(&gl->gl_spin);
			spin_lock(&lru_lock);
			continue;
		}
		nr_skipped++;
		list_add(&gl->gl_lru, &skipped);
		set_bit(GLF_LRU, &gl->gl_flags);
	}
	list_splice(&skipped, &lru_list);
	atomic_add(nr_skipped, &lru_count);
	spin_unlock(&lru_lock);
out:
	return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
}

static struct shrinker glock_shrinker = {
	.shrink = gfs2_shrink_glock_memory,
	.seeks = DEFAULT_SEEKS,
};

/**
 * examine_bucket - Call a function for glock in a hash bucket
 * @examiner: the function
 * @sdp: the filesystem
 * @bucket: the bucket
 *
 */

static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
			  unsigned int hash)
{
	struct gfs2_glock *gl;
	struct hlist_bl_head *head = &gl_hash_table[hash];
	struct hlist_bl_node *pos;

	rcu_read_lock();
	hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
		if ((gl->gl_sbd == sdp) && atomic_read(&gl->gl_ref))
			examiner(gl);
	}
	rcu_read_unlock();
	cond_resched();
}

static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
{
	unsigned x;

	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
		examine_bucket(examiner, sdp, x);
}


/**
 * thaw_glock - thaw out a glock which has an unprocessed reply waiting
 * @gl: The glock to thaw
 *
 * N.B. When we freeze a glock, we leave a ref to the glock outstanding,
 * so this has to result in the ref count being dropped by one.
 */

static void thaw_glock(struct gfs2_glock *gl)
{
	if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
		return;
	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
	gfs2_glock_hold(gl);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
		gfs2_glock_put(gl);
}

/**
 * clear_glock - look at a glock and see if we can free it from glock cache
 * @gl: the glock to look at
 *
 */

static void clear_glock(struct gfs2_glock *gl)
{
	gfs2_glock_remove_from_lru(gl);

	spin_lock(&gl->gl_spin);
	if (gl->gl_state != LM_ST_UNLOCKED)
		handle_callback(gl, LM_ST_UNLOCKED, 0);
	spin_unlock(&gl->gl_spin);
	gfs2_glock_hold(gl);
	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
		gfs2_glock_put(gl);
}

/**
 * gfs2_glock_thaw - Thaw any frozen glocks
 * @sdp: The super block
 *
 */

void gfs2_glock_thaw(struct gfs2_sbd *sdp)
{
	glock_hash_walk(thaw_glock, sdp);
}

static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
{
	int ret;
	spin_lock(&gl->gl_spin);
	ret = gfs2_dump_glock(seq, gl);
	spin_unlock(&gl->gl_spin);
	return ret;
}

static void dump_glock_func(struct gfs2_glock *gl)
{
	dump_glock(NULL, gl);
}

/**
 * gfs2_gl_hash_clear - Empty out the glock hash table
 * @sdp: the filesystem
 * @wait: wait until it's all gone
 *
 * Called when unmounting the filesystem.
 */

void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
{
	set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
	glock_hash_walk(clear_glock, sdp);
	flush_workqueue(glock_workqueue);
	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
	glock_hash_walk(dump_glock_func, sdp);
}

void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
{
	struct gfs2_glock *gl = ip->i_gl;
	int ret;

	ret = gfs2_truncatei_resume(ip);
	gfs2_assert_withdraw(gl->gl_sbd, ret == 0);

	spin_lock(&gl->gl_spin);
	clear_bit(GLF_LOCK, &gl->gl_flags);
	run_queue(gl, 1);
	spin_unlock(&gl->gl_spin);
}

static const char *state2str(unsigned state)
{
	switch(state) {
	case LM_ST_UNLOCKED:
		return "UN";
	case LM_ST_SHARED:
		return "SH";
	case LM_ST_DEFERRED:
		return "DF";
	case LM_ST_EXCLUSIVE:
		return "EX";
	}
	return "??";
}

static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
{
	char *p = buf;
	if (flags & LM_FLAG_TRY)
		*p++ = 't';
	if (flags & LM_FLAG_TRY_1CB)
		*p++ = 'T';
	if (flags & LM_FLAG_NOEXP)
		*p++ = 'e';
	if (flags & LM_FLAG_ANY)
		*p++ = 'A';
	if (flags & LM_FLAG_PRIORITY)
		*p++ = 'p';
	if (flags & GL_ASYNC)
		*p++ = 'a';
	if (flags & GL_EXACT)
		*p++ = 'E';
	if (flags & GL_NOCACHE)
		*p++ = 'c';
	if (test_bit(HIF_HOLDER, &iflags))
		*p++ = 'H';
	if (test_bit(HIF_WAIT, &iflags))
		*p++ = 'W';
	if (test_bit(HIF_FIRST, &iflags))
		*p++ = 'F';
	*p = 0;
	return buf;
}

/**
 * dump_holder - print information about a glock holder
 * @seq: the seq_file struct
 * @gh: the glock holder
 *
 * Returns: 0 on success, -ENOBUFS when we run out of space
 */

static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
{
	struct task_struct *gh_owner = NULL;
	char flags_buf[32];

	if (gh->gh_owner_pid)
		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
		       state2str(gh->gh_state),
		       hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
		       gh->gh_error,
		       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
		       gh_owner ? gh_owner->comm : "(ended)",
		       (void *)gh->gh_ip);
	return 0;
}

static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
{
	const unsigned long *gflags = &gl->gl_flags;
	char *p = buf;

	if (test_bit(GLF_LOCK, gflags))
		*p++ = 'l';
	if (test_bit(GLF_DEMOTE, gflags))
		*p++ = 'D';
	if (test_bit(GLF_PENDING_DEMOTE, gflags))
		*p++ = 'd';
	if (test_bit(GLF_DEMOTE_IN_PROGRESS, gflags))
		*p++ = 'p';
	if (test_bit(GLF_DIRTY, gflags))
		*p++ = 'y';
	if (test_bit(GLF_LFLUSH, gflags))
		*p++ = 'f';
	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, gflags))
		*p++ = 'i';
	if (test_bit(GLF_REPLY_PENDING, gflags))
		*p++ = 'r';
	if (test_bit(GLF_INITIAL, gflags))
		*p++ = 'I';
	if (test_bit(GLF_FROZEN, gflags))
		*p++ = 'F';
	if (test_bit(GLF_QUEUED, gflags))
		*p++ = 'q';
	if (test_bit(GLF_LRU, gflags))
		*p++ = 'L';
	if (gl->gl_object)
		*p++ = 'o';
	if (test_bit(GLF_BLOCKING, gflags))
		*p++ = 'b';
	*p = 0;
	return buf;
}

/**
 * gfs2_dump_glock - print information about a glock
 * @seq: The seq_file struct
 * @gl: the glock
 *
 * The file format is as follows:
 * One line per object, capital letters are used to indicate objects
 * G = glock, I = Inode, R = rgrp, H = holder. Glocks are not indented,
 * other objects are indented by a single space and follow the glock to
 * which they are related. Fields are indicated by lower case letters
 * followed by a colon and the field value, except for strings which are in
 * [] so that its possible to see if they are composed of spaces for
 * example. The field's are n = number (id of the object), f = flags,
 * t = type, s = state, r = refcount, e = error, p = pid.
 *
 * Returns: 0 on success, -ENOBUFS when we run out of space
 */

int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
{
	const struct gfs2_glock_operations *glops = gl->gl_ops;
	unsigned long long dtime;
	const struct gfs2_holder *gh;
	char gflags_buf[32];
	int error = 0;

	dtime = jiffies - gl->gl_demote_time;
	dtime *= 1000000/HZ; /* demote time in uSec */
	if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
		dtime = 0;
	gfs2_print_dbg(seq, "G:  s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d m:%ld\n",
		  state2str(gl->gl_state),
		  gl->gl_name.ln_type,
		  (unsigned long long)gl->gl_name.ln_number,
		  gflags2str(gflags_buf, gl),
		  state2str(gl->gl_target),
		  state2str(gl->gl_demote_state), dtime,
		  atomic_read(&gl->gl_ail_count),
		  atomic_read(&gl->gl_revokes),
		  atomic_read(&gl->gl_ref), gl->gl_hold_time);

	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
		error = dump_holder(seq, gh);
		if (error)
			goto out;
	}
	if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
		error = glops->go_dump(seq, gl);
out:
	return error;
}

static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr)
{
	struct gfs2_glock *gl = iter_ptr;

	seq_printf(seq, "G: n:%u/%llx rtt:%lld/%lld rttb:%lld/%lld irt:%lld/%lld dcnt: %lld qcnt: %lld\n",
		   gl->gl_name.ln_type,
		   (unsigned long long)gl->gl_name.ln_number,
		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTT],
		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVAR],
		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTB],
		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVARB],
		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRT],
		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRTVAR],
		   (long long)gl->gl_stats.stats[GFS2_LKS_DCOUNT],
		   (long long)gl->gl_stats.stats[GFS2_LKS_QCOUNT]);
	return 0;
}

static const char *gfs2_gltype[] = {
	"type",
	"reserved",
	"nondisk",
	"inode",
	"rgrp",
	"meta",
	"iopen",
	"flock",
	"plock",
	"quota",
	"journal",
};

static const char *gfs2_stype[] = {
	[GFS2_LKS_SRTT]		= "srtt",
	[GFS2_LKS_SRTTVAR]	= "srttvar",
	[GFS2_LKS_SRTTB]	= "srttb",
	[GFS2_LKS_SRTTVARB]	= "srttvarb",
	[GFS2_LKS_SIRT]		= "sirt",
	[GFS2_LKS_SIRTVAR]	= "sirtvar",
	[GFS2_LKS_DCOUNT]	= "dlm",
	[GFS2_LKS_QCOUNT]	= "queue",
};

#define GFS2_NR_SBSTATS (ARRAY_SIZE(gfs2_gltype) * ARRAY_SIZE(gfs2_stype))

static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
{
	struct gfs2_glock_iter *gi = seq->private;
	struct gfs2_sbd *sdp = gi->sdp;
	unsigned index = gi->hash >> 3;
	unsigned subindex = gi->hash & 0x07;
	s64 value;
	int i;

	if (index == 0 && subindex != 0)
		return 0;

	seq_printf(seq, "%-10s %8s:", gfs2_gltype[index],
		   (index == 0) ? "cpu": gfs2_stype[subindex]);

	for_each_possible_cpu(i) {
                const struct gfs2_pcpu_lkstats *lkstats = per_cpu_ptr(sdp->sd_lkstats, i);
		if (index == 0) {
			value = i;
		} else {
			value = lkstats->lkstats[index - 1].stats[subindex];
		}
		seq_printf(seq, " %15lld", (long long)value);
	}
	seq_putc(seq, '\n');
	return 0;
}

int __init gfs2_glock_init(void)
{
	unsigned i;
	for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
		INIT_HLIST_BL_HEAD(&gl_hash_table[i]);
	}

	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
					  WQ_HIGHPRI | WQ_FREEZABLE, 0);
	if (IS_ERR(glock_workqueue))
		return PTR_ERR(glock_workqueue);
	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
						WQ_MEM_RECLAIM | WQ_FREEZABLE,
						0);
	if (IS_ERR(gfs2_delete_workqueue)) {
		destroy_workqueue(glock_workqueue);
		return PTR_ERR(gfs2_delete_workqueue);
	}

	register_shrinker(&glock_shrinker);

	return 0;
}

void gfs2_glock_exit(void)
{
	unregister_shrinker(&glock_shrinker);
	destroy_workqueue(glock_workqueue);
	destroy_workqueue(gfs2_delete_workqueue);
}

static inline struct gfs2_glock *glock_hash_chain(unsigned hash)
{
	return hlist_bl_entry(hlist_bl_first_rcu(&gl_hash_table[hash]),
			      struct gfs2_glock, gl_list);
}

static inline struct gfs2_glock *glock_hash_next(struct gfs2_glock *gl)
{
	return hlist_bl_entry(rcu_dereference(gl->gl_list.next),
			      struct gfs2_glock, gl_list);
}

static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
{
	struct gfs2_glock *gl;

	do {
		gl = gi->gl;
		if (gl) {
			gi->gl = glock_hash_next(gl);
			gi->nhash++;
		} else {
			if (gi->hash >= GFS2_GL_HASH_SIZE) {
				rcu_read_unlock();
				return 1;
			}
			gi->gl = glock_hash_chain(gi->hash);
			gi->nhash = 0;
		}
		while (gi->gl == NULL) {
			gi->hash++;
			if (gi->hash >= GFS2_GL_HASH_SIZE) {
				rcu_read_unlock();
				return 1;
			}
			gi->gl = glock_hash_chain(gi->hash);
			gi->nhash = 0;
		}
	/* Skip entries for other sb and dead entries */
	} while (gi->sdp != gi->gl->gl_sbd || atomic_read(&gi->gl->gl_ref) == 0);

	return 0;
}

static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct gfs2_glock_iter *gi = seq->private;
	loff_t n = *pos;

	if (gi->last_pos <= *pos)
		n = gi->nhash + (*pos - gi->last_pos);
	else
		gi->hash = 0;

	gi->nhash = 0;
	rcu_read_lock();

	do {
		if (gfs2_glock_iter_next(gi))
			return NULL;
	} while (n--);

	gi->last_pos = *pos;
	return gi->gl;
}

static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
				 loff_t *pos)
{
	struct gfs2_glock_iter *gi = seq->private;

	(*pos)++;
	gi->last_pos = *pos;
	if (gfs2_glock_iter_next(gi))
		return NULL;

	return gi->gl;
}

static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
{
	struct gfs2_glock_iter *gi = seq->private;

	if (gi->gl)
		rcu_read_unlock();
	gi->gl = NULL;
}

static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
{
	return dump_glock(seq, iter_ptr);
}

static void *gfs2_sbstats_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct gfs2_glock_iter *gi = seq->private;

	gi->hash = *pos;
	if (*pos >= GFS2_NR_SBSTATS)
		return NULL;
	preempt_disable();
	return SEQ_START_TOKEN;
}

static void *gfs2_sbstats_seq_next(struct seq_file *seq, void *iter_ptr,
				   loff_t *pos)
{
	struct gfs2_glock_iter *gi = seq->private;
	(*pos)++;
	gi->hash++;
	if (gi->hash >= GFS2_NR_SBSTATS) {
		preempt_enable();
		return NULL;
	}
	return SEQ_START_TOKEN;
}

static void gfs2_sbstats_seq_stop(struct seq_file *seq, void *iter_ptr)
{
	preempt_enable();
}

static const struct seq_operations gfs2_glock_seq_ops = {
	.start = gfs2_glock_seq_start,
	.next  = gfs2_glock_seq_next,
	.stop  = gfs2_glock_seq_stop,
	.show  = gfs2_glock_seq_show,
};

static const struct seq_operations gfs2_glstats_seq_ops = {
	.start = gfs2_glock_seq_start,
	.next  = gfs2_glock_seq_next,
	.stop  = gfs2_glock_seq_stop,
	.show  = gfs2_glstats_seq_show,
};

static const struct seq_operations gfs2_sbstats_seq_ops = {
	.start = gfs2_sbstats_seq_start,
	.next  = gfs2_sbstats_seq_next,
	.stop  = gfs2_sbstats_seq_stop,
	.show  = gfs2_sbstats_seq_show,
};

#define GFS2_SEQ_GOODSIZE min(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER, 65536UL)

static int gfs2_glocks_open(struct inode *inode, struct file *file)
{
	int ret = seq_open_private(file, &gfs2_glock_seq_ops,
				   sizeof(struct gfs2_glock_iter));
	if (ret == 0) {
		struct seq_file *seq = file->private_data;
		struct gfs2_glock_iter *gi = seq->private;
		gi->sdp = inode->i_private;
		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
		if (seq->buf)
			seq->size = GFS2_SEQ_GOODSIZE;
	}
	return ret;
}

static int gfs2_glstats_open(struct inode *inode, struct file *file)
{
	int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
				   sizeof(struct gfs2_glock_iter));
	if (ret == 0) {
		struct seq_file *seq = file->private_data;
		struct gfs2_glock_iter *gi = seq->private;
		gi->sdp = inode->i_private;
		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
		if (seq->buf)
			seq->size = GFS2_SEQ_GOODSIZE;
	}
	return ret;
}

static int gfs2_sbstats_open(struct inode *inode, struct file *file)
{
	int ret = seq_open_private(file, &gfs2_sbstats_seq_ops,
				   sizeof(struct gfs2_glock_iter));
	if (ret == 0) {
		struct seq_file *seq = file->private_data;
		struct gfs2_glock_iter *gi = seq->private;
		gi->sdp = inode->i_private;
	}
	return ret;
}

static const struct file_operations gfs2_glocks_fops = {
	.owner   = THIS_MODULE,
	.open    = gfs2_glocks_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};

static const struct file_operations gfs2_glstats_fops = {
	.owner   = THIS_MODULE,
	.open    = gfs2_glstats_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};

static const struct file_operations gfs2_sbstats_fops = {
	.owner   = THIS_MODULE,
	.open	 = gfs2_sbstats_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};

int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
{
	sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root);
	if (!sdp->debugfs_dir)
		return -ENOMEM;
	sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
							 S_IFREG | S_IRUGO,
							 sdp->debugfs_dir, sdp,
							 &gfs2_glocks_fops);
	if (!sdp->debugfs_dentry_glocks)
		goto fail;

	sdp->debugfs_dentry_glstats = debugfs_create_file("glstats",
							S_IFREG | S_IRUGO,
							sdp->debugfs_dir, sdp,
							&gfs2_glstats_fops);
	if (!sdp->debugfs_dentry_glstats)
		goto fail;

	sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats",
							S_IFREG | S_IRUGO,
							sdp->debugfs_dir, sdp,
							&gfs2_sbstats_fops);
	if (!sdp->debugfs_dentry_sbstats)
		goto fail;

	return 0;
fail:
	gfs2_delete_debugfs_file(sdp);
	return -ENOMEM;
}

void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
{
	if (sdp->debugfs_dir) {
		if (sdp->debugfs_dentry_glocks) {
			debugfs_remove(sdp->debugfs_dentry_glocks);
			sdp->debugfs_dentry_glocks = NULL;
		}
		if (sdp->debugfs_dentry_glstats) {
			debugfs_remove(sdp->debugfs_dentry_glstats);
			sdp->debugfs_dentry_glstats = NULL;
		}
		if (sdp->debugfs_dentry_sbstats) {
			debugfs_remove(sdp->debugfs_dentry_sbstats);
			sdp->debugfs_dentry_sbstats = NULL;
		}
		debugfs_remove(sdp->debugfs_dir);
		sdp->debugfs_dir = NULL;
	}
}

int gfs2_register_debugfs(void)
{
	gfs2_root = debugfs_create_dir("gfs2", NULL);
	return gfs2_root ? 0 : -ENOMEM;
}

void gfs2_unregister_debugfs(void)
{
	debugfs_remove(gfs2_root);
	gfs2_root = NULL;
}