summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_icache.c
blob: 9a18f69f6e96c19447eae008612abb72a11256db (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_bmap_util.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_reflink.h"

#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/iversion.h>

/*
 * Allocate and initialise an xfs_inode.
 */
struct xfs_inode *
xfs_inode_alloc(
	struct xfs_mount	*mp,
	xfs_ino_t		ino)
{
	struct xfs_inode	*ip;

	/*
	 * if this didn't occur in transactions, we could use
	 * KM_MAYFAIL and return NULL here on ENOMEM. Set the
	 * code up to do this anyway.
	 */
	ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
	if (!ip)
		return NULL;
	if (inode_init_always(mp->m_super, VFS_I(ip))) {
		kmem_zone_free(xfs_inode_zone, ip);
		return NULL;
	}

	/* VFS doesn't initialise i_mode! */
	VFS_I(ip)->i_mode = 0;

	XFS_STATS_INC(mp, vn_active);
	ASSERT(atomic_read(&ip->i_pincount) == 0);
	ASSERT(!xfs_isiflocked(ip));
	ASSERT(ip->i_ino == 0);

	/* initialise the xfs inode */
	ip->i_ino = ino;
	ip->i_mount = mp;
	memset(&ip->i_imap, 0, sizeof(struct xfs_imap));
	ip->i_afp = NULL;
	ip->i_cowfp = NULL;
	ip->i_cnextents = 0;
	ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
	ip->i_flags = 0;
	ip->i_delayed_blks = 0;
	memset(&ip->i_d, 0, sizeof(ip->i_d));

	return ip;
}

STATIC void
xfs_inode_free_callback(
	struct rcu_head		*head)
{
	struct inode		*inode = container_of(head, struct inode, i_rcu);
	struct xfs_inode	*ip = XFS_I(inode);

	switch (VFS_I(ip)->i_mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
	case S_IFLNK:
		xfs_idestroy_fork(ip, XFS_DATA_FORK);
		break;
	}

	if (ip->i_afp)
		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
	if (ip->i_cowfp)
		xfs_idestroy_fork(ip, XFS_COW_FORK);

	if (ip->i_itemp) {
		ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
		xfs_inode_item_destroy(ip);
		ip->i_itemp = NULL;
	}

	kmem_zone_free(xfs_inode_zone, ip);
}

static void
__xfs_inode_free(
	struct xfs_inode	*ip)
{
	/* asserts to verify all state is correct here */
	ASSERT(atomic_read(&ip->i_pincount) == 0);
	XFS_STATS_DEC(ip->i_mount, vn_active);

	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}

void
xfs_inode_free(
	struct xfs_inode	*ip)
{
	ASSERT(!xfs_isiflocked(ip));

	/*
	 * Because we use RCU freeing we need to ensure the inode always
	 * appears to be reclaimed with an invalid inode number when in the
	 * free state. The ip->i_flags_lock provides the barrier against lookup
	 * races.
	 */
	spin_lock(&ip->i_flags_lock);
	ip->i_flags = XFS_IRECLAIM;
	ip->i_ino = 0;
	spin_unlock(&ip->i_flags_lock);

	__xfs_inode_free(ip);
}

/*
 * Queue a new inode reclaim pass if there are reclaimable inodes and there
 * isn't a reclaim pass already in progress. By default it runs every 5s based
 * on the xfs periodic sync default of 30s. Perhaps this should have it's own
 * tunable, but that can be done if this method proves to be ineffective or too
 * aggressive.
 */
static void
xfs_reclaim_work_queue(
	struct xfs_mount        *mp)
{

	rcu_read_lock();
	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
		queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
	}
	rcu_read_unlock();
}

/*
 * This is a fast pass over the inode cache to try to get reclaim moving on as
 * many inodes as possible in a short period of time. It kicks itself every few
 * seconds, as well as being kicked by the inode cache shrinker when memory
 * goes low. It scans as quickly as possible avoiding locked inodes or those
 * already being flushed, and once done schedules a future pass.
 */
void
xfs_reclaim_worker(
	struct work_struct *work)
{
	struct xfs_mount *mp = container_of(to_delayed_work(work),
					struct xfs_mount, m_reclaim_work);

	xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
	xfs_reclaim_work_queue(mp);
}

static void
xfs_perag_set_reclaim_tag(
	struct xfs_perag	*pag)
{
	struct xfs_mount	*mp = pag->pag_mount;

	lockdep_assert_held(&pag->pag_ici_lock);
	if (pag->pag_ici_reclaimable++)
		return;

	/* propagate the reclaim tag up into the perag radix tree */
	spin_lock(&mp->m_perag_lock);
	radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno,
			   XFS_ICI_RECLAIM_TAG);
	spin_unlock(&mp->m_perag_lock);

	/* schedule periodic background inode reclaim */
	xfs_reclaim_work_queue(mp);

	trace_xfs_perag_set_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
}

static void
xfs_perag_clear_reclaim_tag(
	struct xfs_perag	*pag)
{
	struct xfs_mount	*mp = pag->pag_mount;

	lockdep_assert_held(&pag->pag_ici_lock);
	if (--pag->pag_ici_reclaimable)
		return;

	/* clear the reclaim tag from the perag radix tree */
	spin_lock(&mp->m_perag_lock);
	radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno,
			     XFS_ICI_RECLAIM_TAG);
	spin_unlock(&mp->m_perag_lock);
	trace_xfs_perag_clear_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
}


/*
 * We set the inode flag atomically with the radix tree tag.
 * Once we get tag lookups on the radix tree, this inode flag
 * can go away.
 */
void
xfs_inode_set_reclaim_tag(
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_perag	*pag;

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
	spin_lock(&pag->pag_ici_lock);
	spin_lock(&ip->i_flags_lock);

	radix_tree_tag_set(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino),
			   XFS_ICI_RECLAIM_TAG);
	xfs_perag_set_reclaim_tag(pag);
	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);

	spin_unlock(&ip->i_flags_lock);
	spin_unlock(&pag->pag_ici_lock);
	xfs_perag_put(pag);
}

STATIC void
xfs_inode_clear_reclaim_tag(
	struct xfs_perag	*pag,
	xfs_ino_t		ino)
{
	radix_tree_tag_clear(&pag->pag_ici_root,
			     XFS_INO_TO_AGINO(pag->pag_mount, ino),
			     XFS_ICI_RECLAIM_TAG);
	xfs_perag_clear_reclaim_tag(pag);
}

static void
xfs_inew_wait(
	struct xfs_inode	*ip)
{
	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);

	do {
		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
		if (!xfs_iflags_test(ip, XFS_INEW))
			break;
		schedule();
	} while (true);
	finish_wait(wq, &wait.wq_entry);
}

/*
 * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
 * part of the structure. This is made more complex by the fact we store
 * information about the on-disk values in the VFS inode and so we can't just
 * overwrite the values unconditionally. Hence we save the parameters we
 * need to retain across reinitialisation, and rewrite them into the VFS inode
 * after reinitialisation even if it fails.
 */
static int
xfs_reinit_inode(
	struct xfs_mount	*mp,
	struct inode		*inode)
{
	int		error;
	uint32_t	nlink = inode->i_nlink;
	uint32_t	generation = inode->i_generation;
	uint64_t	version = inode_peek_iversion(inode);
	umode_t		mode = inode->i_mode;
	dev_t		dev = inode->i_rdev;

	error = inode_init_always(mp->m_super, inode);

	set_nlink(inode, nlink);
	inode->i_generation = generation;
	inode_set_iversion_queried(inode, version);
	inode->i_mode = mode;
	inode->i_rdev = dev;
	return error;
}

/*
 * Check the validity of the inode we just found it the cache
 */
static int
xfs_iget_cache_hit(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip,
	xfs_ino_t		ino,
	int			flags,
	int			lock_flags) __releases(RCU)
{
	struct inode		*inode = VFS_I(ip);
	struct xfs_mount	*mp = ip->i_mount;
	int			error;

	/*
	 * check for re-use of an inode within an RCU grace period due to the
	 * radix tree nodes not being updated yet. We monitor for this by
	 * setting the inode number to zero before freeing the inode structure.
	 * If the inode has been reallocated and set up, then the inode number
	 * will not match, so check for that, too.
	 */
	spin_lock(&ip->i_flags_lock);
	if (ip->i_ino != ino) {
		trace_xfs_iget_skip(ip);
		XFS_STATS_INC(mp, xs_ig_frecycle);
		error = -EAGAIN;
		goto out_error;
	}


	/*
	 * If we are racing with another cache hit that is currently
	 * instantiating this inode or currently recycling it out of
	 * reclaimabe state, wait for the initialisation to complete
	 * before continuing.
	 *
	 * XXX(hch): eventually we should do something equivalent to
	 *	     wait_on_inode to wait for these flags to be cleared
	 *	     instead of polling for it.
	 */
	if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
		trace_xfs_iget_skip(ip);
		XFS_STATS_INC(mp, xs_ig_frecycle);
		error = -EAGAIN;
		goto out_error;
	}

	/*
	 * If lookup is racing with unlink return an error immediately.
	 */
	if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
		error = -ENOENT;
		goto out_error;
	}

	/*
	 * If IRECLAIMABLE is set, we've torn down the VFS inode already.
	 * Need to carefully get it back into useable state.
	 */
	if (ip->i_flags & XFS_IRECLAIMABLE) {
		trace_xfs_iget_reclaim(ip);

		if (flags & XFS_IGET_INCORE) {
			error = -EAGAIN;
			goto out_error;
		}

		/*
		 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
		 * from stomping over us while we recycle the inode.  We can't
		 * clear the radix tree reclaimable tag yet as it requires
		 * pag_ici_lock to be held exclusive.
		 */
		ip->i_flags |= XFS_IRECLAIM;

		spin_unlock(&ip->i_flags_lock);
		rcu_read_unlock();

		error = xfs_reinit_inode(mp, inode);
		if (error) {
			bool wake;
			/*
			 * Re-initializing the inode failed, and we are in deep
			 * trouble.  Try to re-add it to the reclaim list.
			 */
			rcu_read_lock();
			spin_lock(&ip->i_flags_lock);
			wake = !!__xfs_iflags_test(ip, XFS_INEW);
			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
			if (wake)
				wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
			trace_xfs_iget_reclaim_fail(ip);
			goto out_error;
		}

		spin_lock(&pag->pag_ici_lock);
		spin_lock(&ip->i_flags_lock);

		/*
		 * Clear the per-lifetime state in the inode as we are now
		 * effectively a new inode and need to return to the initial
		 * state before reuse occurs.
		 */
		ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
		ip->i_flags |= XFS_INEW;
		xfs_inode_clear_reclaim_tag(pag, ip->i_ino);
		inode->i_state = I_NEW;

		ASSERT(!rwsem_is_locked(&inode->i_rwsem));
		init_rwsem(&inode->i_rwsem);

		spin_unlock(&ip->i_flags_lock);
		spin_unlock(&pag->pag_ici_lock);
	} else {
		/* If the VFS inode is being torn down, pause and try again. */
		if (!igrab(inode)) {
			trace_xfs_iget_skip(ip);
			error = -EAGAIN;
			goto out_error;
		}

		/* We've got a live one. */
		spin_unlock(&ip->i_flags_lock);
		rcu_read_unlock();
		trace_xfs_iget_hit(ip);
	}

	if (lock_flags != 0)
		xfs_ilock(ip, lock_flags);

	if (!(flags & XFS_IGET_INCORE))
		xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
	XFS_STATS_INC(mp, xs_ig_found);

	return 0;

out_error:
	spin_unlock(&ip->i_flags_lock);
	rcu_read_unlock();
	return error;
}


static int
xfs_iget_cache_miss(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	xfs_trans_t		*tp,
	xfs_ino_t		ino,
	struct xfs_inode	**ipp,
	int			flags,
	int			lock_flags)
{
	struct xfs_inode	*ip;
	int			error;
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
	int			iflags;

	ip = xfs_inode_alloc(mp, ino);
	if (!ip)
		return -ENOMEM;

	error = xfs_iread(mp, tp, ip, flags);
	if (error)
		goto out_destroy;

	if (!xfs_inode_verify_forks(ip)) {
		error = -EFSCORRUPTED;
		goto out_destroy;
	}

	trace_xfs_iget_miss(ip);


	/*
	 * If we are allocating a new inode, then check what was returned is
	 * actually a free, empty inode. If we are not allocating an inode,
	 * the check we didn't find a free inode.
	 */
	if (flags & XFS_IGET_CREATE) {
		if (VFS_I(ip)->i_mode != 0) {
			xfs_warn(mp,
"Corruption detected! Free inode 0x%llx not marked free on disk",
				ino);
			error = -EFSCORRUPTED;
			goto out_destroy;
		}
		if (ip->i_d.di_nblocks != 0) {
			xfs_warn(mp,
"Corruption detected! Free inode 0x%llx has blocks allocated!",
				ino);
			error = -EFSCORRUPTED;
			goto out_destroy;
		}
	} else if (VFS_I(ip)->i_mode == 0) {
		error = -ENOENT;
		goto out_destroy;
	}

	/*
	 * Preload the radix tree so we can insert safely under the
	 * write spinlock. Note that we cannot sleep inside the preload
	 * region. Since we can be called from transaction context, don't
	 * recurse into the file system.
	 */
	if (radix_tree_preload(GFP_NOFS)) {
		error = -EAGAIN;
		goto out_destroy;
	}

	/*
	 * Because the inode hasn't been added to the radix-tree yet it can't
	 * be found by another thread, so we can do the non-sleeping lock here.
	 */
	if (lock_flags) {
		if (!xfs_ilock_nowait(ip, lock_flags))
			BUG();
	}

	/*
	 * These values must be set before inserting the inode into the radix
	 * tree as the moment it is inserted a concurrent lookup (allowed by the
	 * RCU locking mechanism) can find it and that lookup must see that this
	 * is an inode currently under construction (i.e. that XFS_INEW is set).
	 * The ip->i_flags_lock that protects the XFS_INEW flag forms the
	 * memory barrier that ensures this detection works correctly at lookup
	 * time.
	 */
	iflags = XFS_INEW;
	if (flags & XFS_IGET_DONTCACHE)
		iflags |= XFS_IDONTCACHE;
	ip->i_udquot = NULL;
	ip->i_gdquot = NULL;
	ip->i_pdquot = NULL;
	xfs_iflags_set(ip, iflags);

	/* insert the new inode */
	spin_lock(&pag->pag_ici_lock);
	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
	if (unlikely(error)) {
		WARN_ON(error != -EEXIST);
		XFS_STATS_INC(mp, xs_ig_dup);
		error = -EAGAIN;
		goto out_preload_end;
	}
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();

	*ipp = ip;
	return 0;

out_preload_end:
	spin_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
out_destroy:
	__destroy_inode(VFS_I(ip));
	xfs_inode_free(ip);
	return error;
}

/*
 * Look up an inode by number in the given file system.
 * The inode is looked up in the cache held in each AG.
 * If the inode is found in the cache, initialise the vfs inode
 * if necessary.
 *
 * If it is not in core, read it in from the file system's device,
 * add it to the cache and initialise the vfs inode.
 *
 * The inode is locked according to the value of the lock_flags parameter.
 * This flag parameter indicates how and if the inode's IO lock and inode lock
 * should be taken.
 *
 * mp -- the mount point structure for the current file system.  It points
 *       to the inode hash table.
 * tp -- a pointer to the current transaction if there is one.  This is
 *       simply passed through to the xfs_iread() call.
 * ino -- the number of the inode desired.  This is the unique identifier
 *        within the file system for the inode being requested.
 * lock_flags -- flags indicating how to lock the inode.  See the comment
 *		 for xfs_ilock() for a list of valid values.
 */
int
xfs_iget(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	uint		flags,
	uint		lock_flags,
	xfs_inode_t	**ipp)
{
	xfs_inode_t	*ip;
	int		error;
	xfs_perag_t	*pag;
	xfs_agino_t	agino;

	/*
	 * xfs_reclaim_inode() uses the ILOCK to ensure an inode
	 * doesn't get freed while it's being referenced during a
	 * radix tree traversal here.  It assumes this function
	 * aqcuires only the ILOCK (and therefore it has no need to
	 * involve the IOLOCK in this synchronization).
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0);

	/* reject inode numbers outside existing AGs */
	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
		return -EINVAL;

	XFS_STATS_INC(mp, xs_ig_attempts);

	/* get the perag structure and ensure that it's inode capable */
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
	agino = XFS_INO_TO_AGINO(mp, ino);

again:
	error = 0;
	rcu_read_lock();
	ip = radix_tree_lookup(&pag->pag_ici_root, agino);

	if (ip) {
		error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
		if (error)
			goto out_error_or_again;
	} else {
		rcu_read_unlock();
		if (flags & XFS_IGET_INCORE) {
			error = -ENODATA;
			goto out_error_or_again;
		}
		XFS_STATS_INC(mp, xs_ig_missed);

		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
							flags, lock_flags);
		if (error)
			goto out_error_or_again;
	}
	xfs_perag_put(pag);

	*ipp = ip;

	/*
	 * If we have a real type for an on-disk inode, we can setup the inode
	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
	 */
	if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
		xfs_setup_existing_inode(ip);
	return 0;

out_error_or_again:
	if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) {
		delay(1);
		goto again;
	}
	xfs_perag_put(pag);
	return error;
}

/*
 * "Is this a cached inode that's also allocated?"
 *
 * Look up an inode by number in the given file system.  If the inode is
 * in cache and isn't in purgatory, return 1 if the inode is allocated
 * and 0 if it is not.  For all other cases (not in cache, being torn
 * down, etc.), return a negative error code.
 *
 * The caller has to prevent inode allocation and freeing activity,
 * presumably by locking the AGI buffer.   This is to ensure that an
 * inode cannot transition from allocated to freed until the caller is
 * ready to allow that.  If the inode is in an intermediate state (new,
 * reclaimable, or being reclaimed), -EAGAIN will be returned; if the
 * inode is not in the cache, -ENOENT will be returned.  The caller must
 * deal with these scenarios appropriately.
 *
 * This is a specialized use case for the online scrubber; if you're
 * reading this, you probably want xfs_iget.
 */
int
xfs_icache_inode_is_allocated(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_ino_t		ino,
	bool			*inuse)
{
	struct xfs_inode	*ip;
	int			error;

	error = xfs_iget(mp, tp, ino, XFS_IGET_INCORE, 0, &ip);
	if (error)
		return error;

	*inuse = !!(VFS_I(ip)->i_mode);
	IRELE(ip);
	return 0;
}

/*
 * The inode lookup is done in batches to keep the amount of lock traffic and
 * radix tree lookups to a minimum. The batch size is a trade off between
 * lookup reduction and stack usage. This is in the reclaim path, so we can't
 * be too greedy.
 */
#define XFS_LOOKUP_BATCH	32

STATIC int
xfs_inode_ag_walk_grab(
	struct xfs_inode	*ip,
	int			flags)
{
	struct inode		*inode = VFS_I(ip);
	bool			newinos = !!(flags & XFS_AGITER_INEW_WAIT);

	ASSERT(rcu_read_lock_held());

	/*
	 * check for stale RCU freed inode
	 *
	 * If the inode has been reallocated, it doesn't matter if it's not in
	 * the AG we are walking - we are walking for writeback, so if it
	 * passes all the "valid inode" checks and is dirty, then we'll write
	 * it back anyway.  If it has been reallocated and still being
	 * initialised, the XFS_INEW check below will catch it.
	 */
	spin_lock(&ip->i_flags_lock);
	if (!ip->i_ino)
		goto out_unlock_noent;

	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
	if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
	    __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
		goto out_unlock_noent;
	spin_unlock(&ip->i_flags_lock);

	/* nothing to sync during shutdown */
	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return -EFSCORRUPTED;

	/* If we can't grab the inode, it must on it's way to reclaim. */
	if (!igrab(inode))
		return -ENOENT;

	/* inode is valid */
	return 0;

out_unlock_noent:
	spin_unlock(&ip->i_flags_lock);
	return -ENOENT;
}

STATIC int
xfs_inode_ag_walk(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	int			(*execute)(struct xfs_inode *ip, int flags,
					   void *args),
	int			flags,
	void			*args,
	int			tag,
	int			iter_flags)
{
	uint32_t		first_index;
	int			last_error = 0;
	int			skipped;
	int			done;
	int			nr_found;

restart:
	done = 0;
	skipped = 0;
	first_index = 0;
	nr_found = 0;
	do {
		struct xfs_inode *batch[XFS_LOOKUP_BATCH];
		int		error = 0;
		int		i;

		rcu_read_lock();

		if (tag == -1)
			nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH);
		else
			nr_found = radix_tree_gang_lookup_tag(
					&pag->pag_ici_root,
					(void **) batch, first_index,
					XFS_LOOKUP_BATCH, tag);

		if (!nr_found) {
			rcu_read_unlock();
			break;
		}

		/*
		 * Grab the inodes before we drop the lock. if we found
		 * nothing, nr == 0 and the loop will be skipped.
		 */
		for (i = 0; i < nr_found; i++) {
			struct xfs_inode *ip = batch[i];

			if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
				batch[i] = NULL;

			/*
			 * Update the index for the next lookup. Catch
			 * overflows into the next AG range which can occur if
			 * we have inodes in the last block of the AG and we
			 * are currently pointing to the last inode.
			 *
			 * Because we may see inodes that are from the wrong AG
			 * due to RCU freeing and reallocation, only update the
			 * index if it lies in this AG. It was a race that lead
			 * us to see this inode, so another lookup from the
			 * same index will not find it again.
			 */
			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
				continue;
			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
				done = 1;
		}

		/* unlock now we've grabbed the inodes. */
		rcu_read_unlock();

		for (i = 0; i < nr_found; i++) {
			if (!batch[i])
				continue;
			if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
			    xfs_iflags_test(batch[i], XFS_INEW))
				xfs_inew_wait(batch[i]);
			error = execute(batch[i], flags, args);
			IRELE(batch[i]);
			if (error == -EAGAIN) {
				skipped++;
				continue;
			}
			if (error && last_error != -EFSCORRUPTED)
				last_error = error;
		}

		/* bail out if the filesystem is corrupted.  */
		if (error == -EFSCORRUPTED)
			break;

		cond_resched();

	} while (nr_found && !done);

	if (skipped) {
		delay(1);
		goto restart;
	}
	return last_error;
}

/*
 * Background scanning to trim post-EOF preallocated space. This is queued
 * based on the 'speculative_prealloc_lifetime' tunable (5m by default).
 */
void
xfs_queue_eofblocks(
	struct xfs_mount *mp)
{
	rcu_read_lock();
	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_EOFBLOCKS_TAG))
		queue_delayed_work(mp->m_eofblocks_workqueue,
				   &mp->m_eofblocks_work,
				   msecs_to_jiffies(xfs_eofb_secs * 1000));
	rcu_read_unlock();
}

void
xfs_eofblocks_worker(
	struct work_struct *work)
{
	struct xfs_mount *mp = container_of(to_delayed_work(work),
				struct xfs_mount, m_eofblocks_work);
	xfs_icache_free_eofblocks(mp, NULL);
	xfs_queue_eofblocks(mp);
}

/*
 * Background scanning to trim preallocated CoW space. This is queued
 * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default).
 * (We'll just piggyback on the post-EOF prealloc space workqueue.)
 */
void
xfs_queue_cowblocks(
	struct xfs_mount *mp)
{
	rcu_read_lock();
	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_COWBLOCKS_TAG))
		queue_delayed_work(mp->m_eofblocks_workqueue,
				   &mp->m_cowblocks_work,
				   msecs_to_jiffies(xfs_cowb_secs * 1000));
	rcu_read_unlock();
}

void
xfs_cowblocks_worker(
	struct work_struct *work)
{
	struct xfs_mount *mp = container_of(to_delayed_work(work),
				struct xfs_mount, m_cowblocks_work);
	xfs_icache_free_cowblocks(mp, NULL);
	xfs_queue_cowblocks(mp);
}

int
xfs_inode_ag_iterator_flags(
	struct xfs_mount	*mp,
	int			(*execute)(struct xfs_inode *ip, int flags,
					   void *args),
	int			flags,
	void			*args,
	int			iter_flags)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;

	ag = 0;
	while ((pag = xfs_perag_get(mp, ag))) {
		ag = pag->pag_agno + 1;
		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
					  iter_flags);
		xfs_perag_put(pag);
		if (error) {
			last_error = error;
			if (error == -EFSCORRUPTED)
				break;
		}
	}
	return last_error;
}

int
xfs_inode_ag_iterator(
	struct xfs_mount	*mp,
	int			(*execute)(struct xfs_inode *ip, int flags,
					   void *args),
	int			flags,
	void			*args)
{
	return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
}

int
xfs_inode_ag_iterator_tag(
	struct xfs_mount	*mp,
	int			(*execute)(struct xfs_inode *ip, int flags,
					   void *args),
	int			flags,
	void			*args,
	int			tag)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;

	ag = 0;
	while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
		ag = pag->pag_agno + 1;
		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
					  0);
		xfs_perag_put(pag);
		if (error) {
			last_error = error;
			if (error == -EFSCORRUPTED)
				break;
		}
	}
	return last_error;
}

/*
 * Grab the inode for reclaim exclusively.
 * Return 0 if we grabbed it, non-zero otherwise.
 */
STATIC int
xfs_reclaim_inode_grab(
	struct xfs_inode	*ip,
	int			flags)
{
	ASSERT(rcu_read_lock_held());

	/* quick check for stale RCU freed inode */
	if (!ip->i_ino)
		return 1;

	/*
	 * If we are asked for non-blocking operation, do unlocked checks to
	 * see if the inode already is being flushed or in reclaim to avoid
	 * lock traffic.
	 */
	if ((flags & SYNC_TRYLOCK) &&
	    __xfs_iflags_test(ip, XFS_IFLOCK | XFS_IRECLAIM))
		return 1;

	/*
	 * The radix tree lock here protects a thread in xfs_iget from racing
	 * with us starting reclaim on the inode.  Once we have the
	 * XFS_IRECLAIM flag set it will not touch us.
	 *
	 * Due to RCU lookup, we may find inodes that have been freed and only
	 * have XFS_IRECLAIM set.  Indeed, we may see reallocated inodes that
	 * aren't candidates for reclaim at all, so we must check the
	 * XFS_IRECLAIMABLE is set first before proceeding to reclaim.
	 */
	spin_lock(&ip->i_flags_lock);
	if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) ||
	    __xfs_iflags_test(ip, XFS_IRECLAIM)) {
		/* not a reclaim candidate. */
		spin_unlock(&ip->i_flags_lock);
		return 1;
	}
	__xfs_iflags_set(ip, XFS_IRECLAIM);
	spin_unlock(&ip->i_flags_lock);
	return 0;
}

/*
 * Inodes in different states need to be treated differently. The following
 * table lists the inode states and the reclaim actions necessary:
 *
 *	inode state	     iflush ret		required action
 *      ---------------      ----------         ---------------
 *	bad			-		reclaim
 *	shutdown		EIO		unpin and reclaim
 *	clean, unpinned		0		reclaim
 *	stale, unpinned		0		reclaim
 *	clean, pinned(*)	0		requeue
 *	stale, pinned		EAGAIN		requeue
 *	dirty, async		-		requeue
 *	dirty, sync		0		reclaim
 *
 * (*) dgc: I don't think the clean, pinned state is possible but it gets
 * handled anyway given the order of checks implemented.
 *
 * Also, because we get the flush lock first, we know that any inode that has
 * been flushed delwri has had the flush completed by the time we check that
 * the inode is clean.
 *
 * Note that because the inode is flushed delayed write by AIL pushing, the
 * flush lock may already be held here and waiting on it can result in very
 * long latencies.  Hence for sync reclaims, where we wait on the flush lock,
 * the caller should push the AIL first before trying to reclaim inodes to
 * minimise the amount of time spent waiting.  For background relaim, we only
 * bother to reclaim clean inodes anyway.
 *
 * Hence the order of actions after gaining the locks should be:
 *	bad		=> reclaim
 *	shutdown	=> unpin and reclaim
 *	pinned, async	=> requeue
 *	pinned, sync	=> unpin
 *	stale		=> reclaim
 *	clean		=> reclaim
 *	dirty, async	=> requeue
 *	dirty, sync	=> flush, wait and reclaim
 */
STATIC int
xfs_reclaim_inode(
	struct xfs_inode	*ip,
	struct xfs_perag	*pag,
	int			sync_mode)
{
	struct xfs_buf		*bp = NULL;
	xfs_ino_t		ino = ip->i_ino; /* for radix_tree_delete */
	int			error;

restart:
	error = 0;
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	if (!xfs_iflock_nowait(ip)) {
		if (!(sync_mode & SYNC_WAIT))
			goto out;
		xfs_iflock(ip);
	}

	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
		xfs_iunpin_wait(ip);
		/* xfs_iflush_abort() drops the flush lock */
		xfs_iflush_abort(ip, false);
		goto reclaim;
	}
	if (xfs_ipincount(ip)) {
		if (!(sync_mode & SYNC_WAIT))
			goto out_ifunlock;
		xfs_iunpin_wait(ip);
	}
	if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
		xfs_ifunlock(ip);
		goto reclaim;
	}

	/*
	 * Never flush out dirty data during non-blocking reclaim, as it would
	 * just contend with AIL pushing trying to do the same job.
	 */
	if (!(sync_mode & SYNC_WAIT))
		goto out_ifunlock;

	/*
	 * Now we have an inode that needs flushing.
	 *
	 * Note that xfs_iflush will never block on the inode buffer lock, as
	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
	 * ip->i_lock, and we are doing the exact opposite here.  As a result,
	 * doing a blocking xfs_imap_to_bp() to get the cluster buffer would
	 * result in an ABBA deadlock with xfs_ifree_cluster().
	 *
	 * As xfs_ifree_cluser() must gather all inodes that are active in the
	 * cache to mark them stale, if we hit this case we don't actually want
	 * to do IO here - we want the inode marked stale so we can simply
	 * reclaim it.  Hence if we get an EAGAIN error here,  just unlock the
	 * inode, back off and try again.  Hopefully the next pass through will
	 * see the stale flag set on the inode.
	 */
	error = xfs_iflush(ip, &bp);
	if (error == -EAGAIN) {
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		/* backoff longer than in xfs_ifree_cluster */
		delay(2);
		goto restart;
	}

	if (!error) {
		error = xfs_bwrite(bp);
		xfs_buf_relse(bp);
	}

reclaim:
	ASSERT(!xfs_isiflocked(ip));

	/*
	 * Because we use RCU freeing we need to ensure the inode always appears
	 * to be reclaimed with an invalid inode number when in the free state.
	 * We do this as early as possible under the ILOCK so that
	 * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to
	 * detect races with us here. By doing this, we guarantee that once
	 * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that
	 * it will see either a valid inode that will serialise correctly, or it
	 * will see an invalid inode that it can skip.
	 */
	spin_lock(&ip->i_flags_lock);
	ip->i_flags = XFS_IRECLAIM;
	ip->i_ino = 0;
	spin_unlock(&ip->i_flags_lock);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
	/*
	 * Remove the inode from the per-AG radix tree.
	 *
	 * Because radix_tree_delete won't complain even if the item was never
	 * added to the tree assert that it's been there before to catch
	 * problems with the inode life time early on.
	 */
	spin_lock(&pag->pag_ici_lock);
	if (!radix_tree_delete(&pag->pag_ici_root,
				XFS_INO_TO_AGINO(ip->i_mount, ino)))
		ASSERT(0);
	xfs_perag_clear_reclaim_tag(pag);
	spin_unlock(&pag->pag_ici_lock);

	/*
	 * Here we do an (almost) spurious inode lock in order to coordinate
	 * with inode cache radix tree lookups.  This is because the lookup
	 * can reference the inodes in the cache without taking references.
	 *
	 * We make that OK here by ensuring that we wait until the inode is
	 * unlocked after the lookup before we go ahead and free it.
	 */
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_qm_dqdetach(ip);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	__xfs_inode_free(ip);
	return error;

out_ifunlock:
	xfs_ifunlock(ip);
out:
	xfs_iflags_clear(ip, XFS_IRECLAIM);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	/*
	 * We could return -EAGAIN here to make reclaim rescan the inode tree in
	 * a short while. However, this just burns CPU time scanning the tree
	 * waiting for IO to complete and the reclaim work never goes back to
	 * the idle state. Instead, return 0 to let the next scheduled
	 * background reclaim attempt to reclaim the inode again.
	 */
	return 0;
}

/*
 * Walk the AGs and reclaim the inodes in them. Even if the filesystem is
 * corrupted, we still want to try to reclaim all the inodes. If we don't,
 * then a shut down during filesystem unmount reclaim walk leak all the
 * unreclaimed inodes.
 */
STATIC int
xfs_reclaim_inodes_ag(
	struct xfs_mount	*mp,
	int			flags,
	int			*nr_to_scan)
{
	struct xfs_perag	*pag;
	int			error = 0;
	int			last_error = 0;
	xfs_agnumber_t		ag;
	int			trylock = flags & SYNC_TRYLOCK;
	int			skipped;

restart:
	ag = 0;
	skipped = 0;
	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		unsigned long	first_index = 0;
		int		done = 0;
		int		nr_found = 0;

		ag = pag->pag_agno + 1;

		if (trylock) {
			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
				skipped++;
				xfs_perag_put(pag);
				continue;
			}
			first_index = pag->pag_ici_reclaim_cursor;
		} else
			mutex_lock(&pag->pag_ici_reclaim_lock);

		do {
			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
			int	i;

			rcu_read_lock();
			nr_found = radix_tree_gang_lookup_tag(
					&pag->pag_ici_root,
					(void **)batch, first_index,
					XFS_LOOKUP_BATCH,
					XFS_ICI_RECLAIM_TAG);
			if (!nr_found) {
				done = 1;
				rcu_read_unlock();
				break;
			}

			/*
			 * Grab the inodes before we drop the lock. if we found
			 * nothing, nr == 0 and the loop will be skipped.
			 */
			for (i = 0; i < nr_found; i++) {
				struct xfs_inode *ip = batch[i];

				if (done || xfs_reclaim_inode_grab(ip, flags))
					batch[i] = NULL;

				/*
				 * Update the index for the next lookup. Catch
				 * overflows into the next AG range which can
				 * occur if we have inodes in the last block of
				 * the AG and we are currently pointing to the
				 * last inode.
				 *
				 * Because we may see inodes that are from the
				 * wrong AG due to RCU freeing and
				 * reallocation, only update the index if it
				 * lies in this AG. It was a race that lead us
				 * to see this inode, so another lookup from
				 * the same index will not find it again.
				 */
				if (XFS_INO_TO_AGNO(mp, ip->i_ino) !=
								pag->pag_agno)
					continue;
				first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
				if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
					done = 1;
			}

			/* unlock now we've grabbed the inodes. */
			rcu_read_unlock();

			for (i = 0; i < nr_found; i++) {
				if (!batch[i])
					continue;
				error = xfs_reclaim_inode(batch[i], pag, flags);
				if (error && last_error != -EFSCORRUPTED)
					last_error = error;
			}

			*nr_to_scan -= XFS_LOOKUP_BATCH;

			cond_resched();

		} while (nr_found && !done && *nr_to_scan > 0);

		if (trylock && !done)
			pag->pag_ici_reclaim_cursor = first_index;
		else
			pag->pag_ici_reclaim_cursor = 0;
		mutex_unlock(&pag->pag_ici_reclaim_lock);
		xfs_perag_put(pag);
	}

	/*
	 * if we skipped any AG, and we still have scan count remaining, do
	 * another pass this time using blocking reclaim semantics (i.e
	 * waiting on the reclaim locks and ignoring the reclaim cursors). This
	 * ensure that when we get more reclaimers than AGs we block rather
	 * than spin trying to execute reclaim.
	 */
	if (skipped && (flags & SYNC_WAIT) && *nr_to_scan > 0) {
		trylock = 0;
		goto restart;
	}
	return last_error;
}

int
xfs_reclaim_inodes(
	xfs_mount_t	*mp,
	int		mode)
{
	int		nr_to_scan = INT_MAX;

	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
}

/*
 * Scan a certain number of inodes for reclaim.
 *
 * When called we make sure that there is a background (fast) inode reclaim in
 * progress, while we will throttle the speed of reclaim via doing synchronous
 * reclaim of inodes. That means if we come across dirty inodes, we wait for
 * them to be cleaned, which we hope will not be very long due to the
 * background walker having already kicked the IO off on those dirty inodes.
 */
long
xfs_reclaim_inodes_nr(
	struct xfs_mount	*mp,
	int			nr_to_scan)
{
	/* kick background reclaimer and push the AIL */
	xfs_reclaim_work_queue(mp);
	xfs_ail_push_all(mp->m_ail);

	return xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);
}

/*
 * Return the number of reclaimable inodes in the filesystem for
 * the shrinker to determine how much to reclaim.
 */
int
xfs_reclaim_inodes_count(
	struct xfs_mount	*mp)
{
	struct xfs_perag	*pag;
	xfs_agnumber_t		ag = 0;
	int			reclaimable = 0;

	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
		ag = pag->pag_agno + 1;
		reclaimable += pag->pag_ici_reclaimable;
		xfs_perag_put(pag);
	}
	return reclaimable;
}

STATIC int
xfs_inode_match_id(
	struct xfs_inode	*ip,
	struct xfs_eofblocks	*eofb)
{
	if ((eofb->eof_flags & XFS_EOF_FLAGS_UID) &&
	    !uid_eq(VFS_I(ip)->i_uid, eofb->eof_uid))
		return 0;

	if ((eofb->eof_flags & XFS_EOF_FLAGS_GID) &&
	    !gid_eq(VFS_I(ip)->i_gid, eofb->eof_gid))
		return 0;

	if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
	    xfs_get_projid(ip) != eofb->eof_prid)
		return 0;

	return 1;
}

/*
 * A union-based inode filtering algorithm. Process the inode if any of the
 * criteria match. This is for global/internal scans only.
 */
STATIC int
xfs_inode_match_id_union(
	struct xfs_inode	*ip,
	struct xfs_eofblocks	*eofb)
{
	if ((eofb->eof_flags & XFS_EOF_FLAGS_UID) &&
	    uid_eq(VFS_I(ip)->i_uid, eofb->eof_uid))
		return 1;

	if ((eofb->eof_flags & XFS_EOF_FLAGS_GID) &&
	    gid_eq(VFS_I(ip)->i_gid, eofb->eof_gid))
		return 1;

	if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
	    xfs_get_projid(ip) == eofb->eof_prid)
		return 1;

	return 0;
}

STATIC int
xfs_inode_free_eofblocks(
	struct xfs_inode	*ip,
	int			flags,
	void			*args)
{
	int ret = 0;
	struct xfs_eofblocks *eofb = args;
	int match;

	if (!xfs_can_free_eofblocks(ip, false)) {
		/* inode could be preallocated or append-only */
		trace_xfs_inode_free_eofblocks_invalid(ip);
		xfs_inode_clear_eofblocks_tag(ip);
		return 0;
	}

	/*
	 * If the mapping is dirty the operation can block and wait for some
	 * time. Unless we are waiting, skip it.
	 */
	if (!(flags & SYNC_WAIT) &&
	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY))
		return 0;

	if (eofb) {
		if (eofb->eof_flags & XFS_EOF_FLAGS_UNION)
			match = xfs_inode_match_id_union(ip, eofb);
		else
			match = xfs_inode_match_id(ip, eofb);
		if (!match)
			return 0;

		/* skip the inode if the file size is too small */
		if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
		    XFS_ISIZE(ip) < eofb->eof_min_file_size)
			return 0;
	}

	/*
	 * If the caller is waiting, return -EAGAIN to keep the background
	 * scanner moving and revisit the inode in a subsequent pass.
	 */
	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
		if (flags & SYNC_WAIT)
			ret = -EAGAIN;
		return ret;
	}
	ret = xfs_free_eofblocks(ip);
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);

	return ret;
}

static int
__xfs_icache_free_eofblocks(
	struct xfs_mount	*mp,
	struct xfs_eofblocks	*eofb,
	int			(*execute)(struct xfs_inode *ip, int flags,
					   void *args),
	int			tag)
{
	int flags = SYNC_TRYLOCK;

	if (eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC))
		flags = SYNC_WAIT;

	return xfs_inode_ag_iterator_tag(mp, execute, flags,
					 eofb, tag);
}

int
xfs_icache_free_eofblocks(
	struct xfs_mount	*mp,
	struct xfs_eofblocks	*eofb)
{
	return __xfs_icache_free_eofblocks(mp, eofb, xfs_inode_free_eofblocks,
			XFS_ICI_EOFBLOCKS_TAG);
}

/*
 * Run eofblocks scans on the quotas applicable to the inode. For inodes with
 * multiple quotas, we don't know exactly which quota caused an allocation
 * failure. We make a best effort by including each quota under low free space
 * conditions (less than 1% free space) in the scan.
 */
static int
__xfs_inode_free_quota_eofblocks(
	struct xfs_inode	*ip,
	int			(*execute)(struct xfs_mount *mp,
					   struct xfs_eofblocks	*eofb))
{
	int scan = 0;
	struct xfs_eofblocks eofb = {0};
	struct xfs_dquot *dq;

	/*
	 * Run a sync scan to increase effectiveness and use the union filter to
	 * cover all applicable quotas in a single scan.
	 */
	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;

	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
		dq = xfs_inode_dquot(ip, XFS_DQ_USER);
		if (dq && xfs_dquot_lowsp(dq)) {
			eofb.eof_uid = VFS_I(ip)->i_uid;
			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
			scan = 1;
		}
	}

	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
		dq = xfs_inode_dquot(ip, XFS_DQ_GROUP);
		if (dq && xfs_dquot_lowsp(dq)) {
			eofb.eof_gid = VFS_I(ip)->i_gid;
			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
			scan = 1;
		}
	}

	if (scan)
		execute(ip->i_mount, &eofb);

	return scan;
}

int
xfs_inode_free_quota_eofblocks(
	struct xfs_inode *ip)
{
	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks);
}

static inline unsigned long
xfs_iflag_for_tag(
	int		tag)
{
	switch (tag) {
	case XFS_ICI_EOFBLOCKS_TAG:
		return XFS_IEOFBLOCKS;
	case XFS_ICI_COWBLOCKS_TAG:
		return XFS_ICOWBLOCKS;
	default:
		ASSERT(0);
		return 0;
	}
}

static void
__xfs_inode_set_blocks_tag(
	xfs_inode_t	*ip,
	void		(*execute)(struct xfs_mount *mp),
	void		(*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
				  int error, unsigned long caller_ip),
	int		tag)
{
	struct xfs_mount *mp = ip->i_mount;
	struct xfs_perag *pag;
	int tagged;

	/*
	 * Don't bother locking the AG and looking up in the radix trees
	 * if we already know that we have the tag set.
	 */
	if (ip->i_flags & xfs_iflag_for_tag(tag))
		return;
	spin_lock(&ip->i_flags_lock);
	ip->i_flags |= xfs_iflag_for_tag(tag);
	spin_unlock(&ip->i_flags_lock);

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
	spin_lock(&pag->pag_ici_lock);

	tagged = radix_tree_tagged(&pag->pag_ici_root, tag);
	radix_tree_tag_set(&pag->pag_ici_root,
			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
	if (!tagged) {
		/* propagate the eofblocks tag up into the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_set(&ip->i_mount->m_perag_tree,
				   XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				   tag);
		spin_unlock(&ip->i_mount->m_perag_lock);

		/* kick off background trimming */
		execute(ip->i_mount);

		set_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
	}

	spin_unlock(&pag->pag_ici_lock);
	xfs_perag_put(pag);
}

void
xfs_inode_set_eofblocks_tag(
	xfs_inode_t	*ip)
{
	trace_xfs_inode_set_eofblocks_tag(ip);
	return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks,
			trace_xfs_perag_set_eofblocks,
			XFS_ICI_EOFBLOCKS_TAG);
}

static void
__xfs_inode_clear_blocks_tag(
	xfs_inode_t	*ip,
	void		(*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
				    int error, unsigned long caller_ip),
	int		tag)
{
	struct xfs_mount *mp = ip->i_mount;
	struct xfs_perag *pag;

	spin_lock(&ip->i_flags_lock);
	ip->i_flags &= ~xfs_iflag_for_tag(tag);
	spin_unlock(&ip->i_flags_lock);

	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
	spin_lock(&pag->pag_ici_lock);

	radix_tree_tag_clear(&pag->pag_ici_root,
			     XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
	if (!radix_tree_tagged(&pag->pag_ici_root, tag)) {
		/* clear the eofblocks tag from the perag radix tree */
		spin_lock(&ip->i_mount->m_perag_lock);
		radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
				     XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
				     tag);
		spin_unlock(&ip->i_mount->m_perag_lock);
		clear_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
	}

	spin_unlock(&pag->pag_ici_lock);
	xfs_perag_put(pag);
}

void
xfs_inode_clear_eofblocks_tag(
	xfs_inode_t	*ip)
{
	trace_xfs_inode_clear_eofblocks_tag(ip);
	return __xfs_inode_clear_blocks_tag(ip,
			trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG);
}

/*
 * Set ourselves up to free CoW blocks from this file.  If it's already clean
 * then we can bail out quickly, but otherwise we must back off if the file
 * is undergoing some kind of write.
 */
static bool
xfs_prep_free_cowblocks(
	struct xfs_inode	*ip,
	struct xfs_ifork	*ifp)
{
	/*
	 * Just clear the tag if we have an empty cow fork or none at all. It's
	 * possible the inode was fully unshared since it was originally tagged.
	 */
	if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
		trace_xfs_inode_free_cowblocks_invalid(ip);
		xfs_inode_clear_cowblocks_tag(ip);
		return false;
	}

	/*
	 * If the mapping is dirty or under writeback we cannot touch the
	 * CoW fork.  Leave it alone if we're in the midst of a directio.
	 */
	if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
	    atomic_read(&VFS_I(ip)->i_dio_count))
		return false;

	return true;
}

/*
 * Automatic CoW Reservation Freeing
 *
 * These functions automatically garbage collect leftover CoW reservations
 * that were made on behalf of a cowextsize hint when we start to run out
 * of quota or when the reservations sit around for too long.  If the file
 * has dirty pages or is undergoing writeback, its CoW reservations will
 * be retained.
 *
 * The actual garbage collection piggybacks off the same code that runs
 * the speculative EOF preallocation garbage collector.
 */
STATIC int
xfs_inode_free_cowblocks(
	struct xfs_inode	*ip,
	int			flags,
	void			*args)
{
	struct xfs_eofblocks	*eofb = args;
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
	int			match;
	int			ret = 0;

	if (!xfs_prep_free_cowblocks(ip, ifp))
		return 0;

	if (eofb) {
		if (eofb->eof_flags & XFS_EOF_FLAGS_UNION)
			match = xfs_inode_match_id_union(ip, eofb);
		else
			match = xfs_inode_match_id(ip, eofb);
		if (!match)
			return 0;

		/* skip the inode if the file size is too small */
		if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
		    XFS_ISIZE(ip) < eofb->eof_min_file_size)
			return 0;
	}

	/* Free the CoW blocks */
	xfs_ilock(ip, XFS_IOLOCK_EXCL);
	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);

	/*
	 * Check again, nobody else should be able to dirty blocks or change
	 * the reflink iflag now that we have the first two locks held.
	 */
	if (xfs_prep_free_cowblocks(ip, ifp))
		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);

	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);

	return ret;
}

int
xfs_icache_free_cowblocks(
	struct xfs_mount	*mp,
	struct xfs_eofblocks	*eofb)
{
	return __xfs_icache_free_eofblocks(mp, eofb, xfs_inode_free_cowblocks,
			XFS_ICI_COWBLOCKS_TAG);
}

int
xfs_inode_free_quota_cowblocks(
	struct xfs_inode *ip)
{
	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_cowblocks);
}

void
xfs_inode_set_cowblocks_tag(
	xfs_inode_t	*ip)
{
	trace_xfs_inode_set_cowblocks_tag(ip);
	return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks,
			trace_xfs_perag_set_cowblocks,
			XFS_ICI_COWBLOCKS_TAG);
}

void
xfs_inode_clear_cowblocks_tag(
	xfs_inode_t	*ip)
{
	trace_xfs_inode_clear_cowblocks_tag(ip);
	return __xfs_inode_clear_blocks_tag(ip,
			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
}