aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_ialloc.c
blob: fc3a2cb2c075f50c4e67a67279a34c45e7586fce (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
/*
 * Copyright (c) 2000-2002,2005 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_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_bmap.h"


/*
 * Allocation group level functions.
 */
static inline int
xfs_ialloc_cluster_alignment(
	xfs_alloc_arg_t	*args)
{
	if (xfs_sb_version_hasalign(&args->mp->m_sb) &&
	    args->mp->m_sb.sb_inoalignmt >=
	     XFS_B_TO_FSBT(args->mp, XFS_INODE_CLUSTER_SIZE(args->mp)))
		return args->mp->m_sb.sb_inoalignmt;
	return 1;
}

/*
 * Lookup a record by ino in the btree given by cur.
 */
int					/* error */
xfs_inobt_lookup(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agino_t		ino,	/* starting inode of chunk */
	xfs_lookup_t		dir,	/* <=, >=, == */
	int			*stat)	/* success/failure */
{
	cur->bc_rec.i.ir_startino = ino;
	cur->bc_rec.i.ir_freecount = 0;
	cur->bc_rec.i.ir_free = 0;
	return xfs_btree_lookup(cur, dir, stat);
}

/*
 * Update the record referred to by cur to the value given.
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int				/* error */
xfs_inobt_update(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_inobt_rec_incore_t	*irec)	/* btree record */
{
	union xfs_btree_rec	rec;

	rec.inobt.ir_startino = cpu_to_be32(irec->ir_startino);
	rec.inobt.ir_freecount = cpu_to_be32(irec->ir_freecount);
	rec.inobt.ir_free = cpu_to_be64(irec->ir_free);
	return xfs_btree_update(cur, &rec);
}

/*
 * Get the data from the pointed-to record.
 */
int					/* error */
xfs_inobt_get_rec(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_inobt_rec_incore_t	*irec,	/* btree record */
	int			*stat)	/* output: success/failure */
{
	union xfs_btree_rec	*rec;
	int			error;

	error = xfs_btree_get_rec(cur, &rec, stat);
	if (!error && *stat == 1) {
		irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino);
		irec->ir_freecount = be32_to_cpu(rec->inobt.ir_freecount);
		irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
	}
	return error;
}

/*
 * Verify that the number of free inodes in the AGI is correct.
 */
#ifdef DEBUG
STATIC int
xfs_check_agi_freecount(
	struct xfs_btree_cur	*cur,
	struct xfs_agi		*agi)
{
	if (cur->bc_nlevels == 1) {
		xfs_inobt_rec_incore_t rec;
		int		freecount = 0;
		int		error;
		int		i;

		error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
		if (error)
			return error;

		do {
			error = xfs_inobt_get_rec(cur, &rec, &i);
			if (error)
				return error;

			if (i) {
				freecount += rec.ir_freecount;
				error = xfs_btree_increment(cur, 0, &i);
				if (error)
					return error;
			}
		} while (i == 1);

		if (!XFS_FORCED_SHUTDOWN(cur->bc_mp))
			ASSERT(freecount == be32_to_cpu(agi->agi_freecount));
	}
	return 0;
}
#else
#define xfs_check_agi_freecount(cur, agi)	0
#endif

/*
 * Initialise a new set of inodes.
 */
STATIC void
xfs_ialloc_inode_init(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		agbno,
	xfs_agblock_t		length,
	unsigned int		gen)
{
	struct xfs_buf		*fbuf;
	struct xfs_dinode	*free;
	int			blks_per_cluster, nbufs, ninodes;
	int			version;
	int			i, j;
	xfs_daddr_t		d;

	/*
	 * Loop over the new block(s), filling in the inodes.
	 * For small block sizes, manipulate the inodes in buffers
	 * which are multiples of the blocks size.
	 */
	if (mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp)) {
		blks_per_cluster = 1;
		nbufs = length;
		ninodes = mp->m_sb.sb_inopblock;
	} else {
		blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) /
				   mp->m_sb.sb_blocksize;
		nbufs = length / blks_per_cluster;
		ninodes = blks_per_cluster * mp->m_sb.sb_inopblock;
	}

	/*
	 * Figure out what version number to use in the inodes we create.
	 * If the superblock version has caught up to the one that supports
	 * the new inode format, then use the new inode version.  Otherwise
	 * use the old version so that old kernels will continue to be
	 * able to use the file system.
	 */
	if (xfs_sb_version_hasnlink(&mp->m_sb))
		version = 2;
	else
		version = 1;

	for (j = 0; j < nbufs; j++) {
		/*
		 * Get the block.
		 */
		d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * blks_per_cluster));
		fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
					 mp->m_bsize * blks_per_cluster,
					 XBF_LOCK);
		ASSERT(fbuf);
		ASSERT(!XFS_BUF_GETERROR(fbuf));

		/*
		 * Initialize all inodes in this buffer and then log them.
		 *
		 * XXX: It would be much better if we had just one transaction
		 *	to log a whole cluster of inodes instead of all the
		 *	individual transactions causing a lot of log traffic.
		 */
		xfs_buf_zero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog);
		for (i = 0; i < ninodes; i++) {
			int	ioffset = i << mp->m_sb.sb_inodelog;
			uint	isize = sizeof(struct xfs_dinode);

			free = xfs_make_iptr(mp, fbuf, i);
			free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
			free->di_version = version;
			free->di_gen = cpu_to_be32(gen);
			free->di_next_unlinked = cpu_to_be32(NULLAGINO);
			xfs_trans_log_buf(tp, fbuf, ioffset, ioffset + isize - 1);
		}
		xfs_trans_inode_alloc_buf(tp, fbuf);
	}
}

/*
 * Allocate new inodes in the allocation group specified by agbp.
 * Return 0 for success, else error code.
 */
STATIC int				/* error code or 0 */
xfs_ialloc_ag_alloc(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_buf_t	*agbp,		/* alloc group buffer */
	int		*alloc)
{
	xfs_agi_t	*agi;		/* allocation group header */
	xfs_alloc_arg_t	args;		/* allocation argument structure */
	xfs_btree_cur_t	*cur;		/* inode btree cursor */
	xfs_agnumber_t	agno;
	int		error;
	int		i;
	xfs_agino_t	newino;		/* new first inode's number */
	xfs_agino_t	newlen;		/* new number of inodes */
	xfs_agino_t	thisino;	/* current inode number, for loop */
	int		isaligned = 0;	/* inode allocation at stripe unit */
					/* boundary */
	struct xfs_perag *pag;

	args.tp = tp;
	args.mp = tp->t_mountp;

	/*
	 * Locking will ensure that we don't have two callers in here
	 * at one time.
	 */
	newlen = XFS_IALLOC_INODES(args.mp);
	if (args.mp->m_maxicount &&
	    args.mp->m_sb.sb_icount + newlen > args.mp->m_maxicount)
		return XFS_ERROR(ENOSPC);
	args.minlen = args.maxlen = XFS_IALLOC_BLOCKS(args.mp);
	/*
	 * First try to allocate inodes contiguous with the last-allocated
	 * chunk of inodes.  If the filesystem is striped, this will fill
	 * an entire stripe unit with inodes.
 	 */
	agi = XFS_BUF_TO_AGI(agbp);
	newino = be32_to_cpu(agi->agi_newino);
	agno = be32_to_cpu(agi->agi_seqno);
	args.agbno = XFS_AGINO_TO_AGBNO(args.mp, newino) +
			XFS_IALLOC_BLOCKS(args.mp);
	if (likely(newino != NULLAGINO &&
		  (args.agbno < be32_to_cpu(agi->agi_length)))) {
		args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
		args.type = XFS_ALLOCTYPE_THIS_BNO;
		args.mod = args.total = args.wasdel = args.isfl =
			args.userdata = args.minalignslop = 0;
		args.prod = 1;

		/*
		 * We need to take into account alignment here to ensure that
		 * we don't modify the free list if we fail to have an exact
		 * block. If we don't have an exact match, and every oher
		 * attempt allocation attempt fails, we'll end up cancelling
		 * a dirty transaction and shutting down.
		 *
		 * For an exact allocation, alignment must be 1,
		 * however we need to take cluster alignment into account when
		 * fixing up the freelist. Use the minalignslop field to
		 * indicate that extra blocks might be required for alignment,
		 * but not to use them in the actual exact allocation.
		 */
		args.alignment = 1;
		args.minalignslop = xfs_ialloc_cluster_alignment(&args) - 1;

		/* Allow space for the inode btree to split. */
		args.minleft = args.mp->m_in_maxlevels - 1;
		if ((error = xfs_alloc_vextent(&args)))
			return error;
	} else
		args.fsbno = NULLFSBLOCK;

	if (unlikely(args.fsbno == NULLFSBLOCK)) {
		/*
		 * Set the alignment for the allocation.
		 * If stripe alignment is turned on then align at stripe unit
		 * boundary.
		 * If the cluster size is smaller than a filesystem block
		 * then we're doing I/O for inodes in filesystem block size
		 * pieces, so don't need alignment anyway.
		 */
		isaligned = 0;
		if (args.mp->m_sinoalign) {
			ASSERT(!(args.mp->m_flags & XFS_MOUNT_NOALIGN));
			args.alignment = args.mp->m_dalign;
			isaligned = 1;
		} else
			args.alignment = xfs_ialloc_cluster_alignment(&args);
		/*
		 * Need to figure out where to allocate the inode blocks.
		 * Ideally they should be spaced out through the a.g.
		 * For now, just allocate blocks up front.
		 */
		args.agbno = be32_to_cpu(agi->agi_root);
		args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
		/*
		 * Allocate a fixed-size extent of inodes.
		 */
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.mod = args.total = args.wasdel = args.isfl =
			args.userdata = args.minalignslop = 0;
		args.prod = 1;
		/*
		 * Allow space for the inode btree to split.
		 */
		args.minleft = args.mp->m_in_maxlevels - 1;
		if ((error = xfs_alloc_vextent(&args)))
			return error;
	}

	/*
	 * If stripe alignment is turned on, then try again with cluster
	 * alignment.
	 */
	if (isaligned && args.fsbno == NULLFSBLOCK) {
		args.type = XFS_ALLOCTYPE_NEAR_BNO;
		args.agbno = be32_to_cpu(agi->agi_root);
		args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
		args.alignment = xfs_ialloc_cluster_alignment(&args);
		if ((error = xfs_alloc_vextent(&args)))
			return error;
	}

	if (args.fsbno == NULLFSBLOCK) {
		*alloc = 0;
		return 0;
	}
	ASSERT(args.len == args.minlen);

	/*
	 * Stamp and write the inode buffers.
	 *
	 * Seed the new inode cluster with a random generation number. This
	 * prevents short-term reuse of generation numbers if a chunk is
	 * freed and then immediately reallocated. We use random numbers
	 * rather than a linear progression to prevent the next generation
	 * number from being easily guessable.
	 */
	xfs_ialloc_inode_init(args.mp, tp, agno, args.agbno, args.len,
			      random32());

	/*
	 * Convert the results.
	 */
	newino = XFS_OFFBNO_TO_AGINO(args.mp, args.agbno, 0);
	be32_add_cpu(&agi->agi_count, newlen);
	be32_add_cpu(&agi->agi_freecount, newlen);
	pag = xfs_perag_get(args.mp, agno);
	pag->pagi_freecount += newlen;
	xfs_perag_put(pag);
	agi->agi_newino = cpu_to_be32(newino);

	/*
	 * Insert records describing the new inode chunk into the btree.
	 */
	cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
	for (thisino = newino;
	     thisino < newino + newlen;
	     thisino += XFS_INODES_PER_CHUNK) {
		cur->bc_rec.i.ir_startino = thisino;
		cur->bc_rec.i.ir_freecount = XFS_INODES_PER_CHUNK;
		cur->bc_rec.i.ir_free = XFS_INOBT_ALL_FREE;
		error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, &i);
		if (error) {
			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
			return error;
		}
		ASSERT(i == 0);
		error = xfs_btree_insert(cur, &i);
		if (error) {
			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
			return error;
		}
		ASSERT(i == 1);
	}
	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	/*
	 * Log allocation group header fields
	 */
	xfs_ialloc_log_agi(tp, agbp,
		XFS_AGI_COUNT | XFS_AGI_FREECOUNT | XFS_AGI_NEWINO);
	/*
	 * Modify/log superblock values for inode count and inode free count.
	 */
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, (long)newlen);
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, (long)newlen);
	*alloc = 1;
	return 0;
}

STATIC xfs_agnumber_t
xfs_ialloc_next_ag(
	xfs_mount_t	*mp)
{
	xfs_agnumber_t	agno;

	spin_lock(&mp->m_agirotor_lock);
	agno = mp->m_agirotor;
	if (++mp->m_agirotor == mp->m_maxagi)
		mp->m_agirotor = 0;
	spin_unlock(&mp->m_agirotor_lock);

	return agno;
}

/*
 * Select an allocation group to look for a free inode in, based on the parent
 * inode and then mode.  Return the allocation group buffer.
 */
STATIC xfs_buf_t *			/* allocation group buffer */
xfs_ialloc_ag_select(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_ino_t	parent,		/* parent directory inode number */
	mode_t		mode,		/* bits set to indicate file type */
	int		okalloc)	/* ok to allocate more space */
{
	xfs_buf_t	*agbp;		/* allocation group header buffer */
	xfs_agnumber_t	agcount;	/* number of ag's in the filesystem */
	xfs_agnumber_t	agno;		/* current ag number */
	int		flags;		/* alloc buffer locking flags */
	xfs_extlen_t	ineed;		/* blocks needed for inode allocation */
	xfs_extlen_t	longest = 0;	/* longest extent available */
	xfs_mount_t	*mp;		/* mount point structure */
	int		needspace;	/* file mode implies space allocated */
	xfs_perag_t	*pag;		/* per allocation group data */
	xfs_agnumber_t	pagno;		/* parent (starting) ag number */

	/*
	 * Files of these types need at least one block if length > 0
	 * (and they won't fit in the inode, but that's hard to figure out).
	 */
	needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode);
	mp = tp->t_mountp;
	agcount = mp->m_maxagi;
	if (S_ISDIR(mode))
		pagno = xfs_ialloc_next_ag(mp);
	else {
		pagno = XFS_INO_TO_AGNO(mp, parent);
		if (pagno >= agcount)
			pagno = 0;
	}
	ASSERT(pagno < agcount);
	/*
	 * Loop through allocation groups, looking for one with a little
	 * free space in it.  Note we don't look for free inodes, exactly.
	 * Instead, we include whether there is a need to allocate inodes
	 * to mean that blocks must be allocated for them,
	 * if none are currently free.
	 */
	agno = pagno;
	flags = XFS_ALLOC_FLAG_TRYLOCK;
	for (;;) {
		pag = xfs_perag_get(mp, agno);
		if (!pag->pagi_init) {
			if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
				agbp = NULL;
				goto nextag;
			}
		} else
			agbp = NULL;

		if (!pag->pagi_inodeok) {
			xfs_ialloc_next_ag(mp);
			goto unlock_nextag;
		}

		/*
		 * Is there enough free space for the file plus a block
		 * of inodes (if we need to allocate some)?
		 */
		ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
		if (ineed && !pag->pagf_init) {
			if (agbp == NULL &&
			    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
				agbp = NULL;
				goto nextag;
			}
			(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
		}
		if (!ineed || pag->pagf_init) {
			if (ineed && !(longest = pag->pagf_longest))
				longest = pag->pagf_flcount > 0;
			if (!ineed ||
			    (pag->pagf_freeblks >= needspace + ineed &&
			     longest >= ineed &&
			     okalloc)) {
				if (agbp == NULL &&
				    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
					agbp = NULL;
					goto nextag;
				}
				xfs_perag_put(pag);
				return agbp;
			}
		}
unlock_nextag:
		if (agbp)
			xfs_trans_brelse(tp, agbp);
nextag:
		xfs_perag_put(pag);
		/*
		 * No point in iterating over the rest, if we're shutting
		 * down.
		 */
		if (XFS_FORCED_SHUTDOWN(mp))
			return NULL;
		agno++;
		if (agno >= agcount)
			agno = 0;
		if (agno == pagno) {
			if (flags == 0)
				return NULL;
			flags = 0;
		}
	}
}

/*
 * Try to retrieve the next record to the left/right from the current one.
 */
STATIC int
xfs_ialloc_next_rec(
	struct xfs_btree_cur	*cur,
	xfs_inobt_rec_incore_t	*rec,
	int			*done,
	int			left)
{
	int                     error;
	int			i;

	if (left)
		error = xfs_btree_decrement(cur, 0, &i);
	else
		error = xfs_btree_increment(cur, 0, &i);

	if (error)
		return error;
	*done = !i;
	if (i) {
		error = xfs_inobt_get_rec(cur, rec, &i);
		if (error)
			return error;
		XFS_WANT_CORRUPTED_RETURN(i == 1);
	}

	return 0;
}

STATIC int
xfs_ialloc_get_rec(
	struct xfs_btree_cur	*cur,
	xfs_agino_t		agino,
	xfs_inobt_rec_incore_t	*rec,
	int			*done,
	int			left)
{
	int                     error;
	int			i;

	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_EQ, &i);
	if (error)
		return error;
	*done = !i;
	if (i) {
		error = xfs_inobt_get_rec(cur, rec, &i);
		if (error)
			return error;
		XFS_WANT_CORRUPTED_RETURN(i == 1);
	}

	return 0;
}

/*
 * Visible inode allocation functions.
 */

/*
 * Allocate an inode on disk.
 * Mode is used to tell whether the new inode will need space, and whether
 * it is a directory.
 *
 * The arguments IO_agbp and alloc_done are defined to work within
 * the constraint of one allocation per transaction.
 * xfs_dialloc() is designed to be called twice if it has to do an
 * allocation to make more free inodes.  On the first call,
 * IO_agbp should be set to NULL. If an inode is available,
 * i.e., xfs_dialloc() did not need to do an allocation, an inode
 * number is returned.  In this case, IO_agbp would be set to the
 * current ag_buf and alloc_done set to false.
 * If an allocation needed to be done, xfs_dialloc would return
 * the current ag_buf in IO_agbp and set alloc_done to true.
 * The caller should then commit the current transaction, allocate a new
 * transaction, and call xfs_dialloc() again, passing in the previous
 * value of IO_agbp.  IO_agbp should be held across the transactions.
 * Since the agbp is locked across the two calls, the second call is
 * guaranteed to have a free inode available.
 *
 * Once we successfully pick an inode its number is returned and the
 * on-disk data structures are updated.  The inode itself is not read
 * in, since doing so would break ordering constraints with xfs_reclaim.
 */
int
xfs_dialloc(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_ino_t	parent,		/* parent inode (directory) */
	mode_t		mode,		/* mode bits for new inode */
	int		okalloc,	/* ok to allocate more space */
	xfs_buf_t	**IO_agbp,	/* in/out ag header's buffer */
	boolean_t	*alloc_done,	/* true if we needed to replenish
					   inode freelist */
	xfs_ino_t	*inop)		/* inode number allocated */
{
	xfs_agnumber_t	agcount;	/* number of allocation groups */
	xfs_buf_t	*agbp;		/* allocation group header's buffer */
	xfs_agnumber_t	agno;		/* allocation group number */
	xfs_agi_t	*agi;		/* allocation group header structure */
	xfs_btree_cur_t	*cur;		/* inode allocation btree cursor */
	int		error;		/* error return value */
	int		i;		/* result code */
	int		ialloced;	/* inode allocation status */
	int		noroom = 0;	/* no space for inode blk allocation */
	xfs_ino_t	ino;		/* fs-relative inode to be returned */
	/* REFERENCED */
	int		j;		/* result code */
	xfs_mount_t	*mp;		/* file system mount structure */
	int		offset;		/* index of inode in chunk */
	xfs_agino_t	pagino;		/* parent's AG relative inode # */
	xfs_agnumber_t	pagno;		/* parent's AG number */
	xfs_inobt_rec_incore_t rec;	/* inode allocation record */
	xfs_agnumber_t	tagno;		/* testing allocation group number */
	xfs_btree_cur_t	*tcur;		/* temp cursor */
	xfs_inobt_rec_incore_t trec;	/* temp inode allocation record */
	struct xfs_perag *pag;


	if (*IO_agbp == NULL) {
		/*
		 * We do not have an agbp, so select an initial allocation
		 * group for inode allocation.
		 */
		agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
		/*
		 * Couldn't find an allocation group satisfying the
		 * criteria, give up.
		 */
		if (!agbp) {
			*inop = NULLFSINO;
			return 0;
		}
		agi = XFS_BUF_TO_AGI(agbp);
		ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
	} else {
		/*
		 * Continue where we left off before.  In this case, we
		 * know that the allocation group has free inodes.
		 */
		agbp = *IO_agbp;
		agi = XFS_BUF_TO_AGI(agbp);
		ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
		ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
	}
	mp = tp->t_mountp;
	agcount = mp->m_sb.sb_agcount;
	agno = be32_to_cpu(agi->agi_seqno);
	tagno = agno;
	pagno = XFS_INO_TO_AGNO(mp, parent);
	pagino = XFS_INO_TO_AGINO(mp, parent);

	/*
	 * If we have already hit the ceiling of inode blocks then clear
	 * okalloc so we scan all available agi structures for a free
	 * inode.
	 */

	if (mp->m_maxicount &&
	    mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
		noroom = 1;
		okalloc = 0;
	}

	/*
	 * Loop until we find an allocation group that either has free inodes
	 * or in which we can allocate some inodes.  Iterate through the
	 * allocation groups upward, wrapping at the end.
	 */
	*alloc_done = B_FALSE;
	while (!agi->agi_freecount) {
		/*
		 * Don't do anything if we're not supposed to allocate
		 * any blocks, just go on to the next ag.
		 */
		if (okalloc) {
			/*
			 * Try to allocate some new inodes in the allocation
			 * group.
			 */
			if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
				xfs_trans_brelse(tp, agbp);
				if (error == ENOSPC) {
					*inop = NULLFSINO;
					return 0;
				} else
					return error;
			}
			if (ialloced) {
				/*
				 * We successfully allocated some inodes, return
				 * the current context to the caller so that it
				 * can commit the current transaction and call
				 * us again where we left off.
				 */
				ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
				*alloc_done = B_TRUE;
				*IO_agbp = agbp;
				*inop = NULLFSINO;
				return 0;
			}
		}
		/*
		 * If it failed, give up on this ag.
		 */
		xfs_trans_brelse(tp, agbp);
		/*
		 * Go on to the next ag: get its ag header.
		 */
nextag:
		if (++tagno == agcount)
			tagno = 0;
		if (tagno == agno) {
			*inop = NULLFSINO;
			return noroom ? ENOSPC : 0;
		}
		pag = xfs_perag_get(mp, tagno);
		if (pag->pagi_inodeok == 0) {
			xfs_perag_put(pag);
			goto nextag;
		}
		error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
		xfs_perag_put(pag);
		if (error)
			goto nextag;
		agi = XFS_BUF_TO_AGI(agbp);
		ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
	}
	/*
	 * Here with an allocation group that has a free inode.
	 * Reset agno since we may have chosen a new ag in the
	 * loop above.
	 */
	agno = tagno;
	*IO_agbp = NULL;
	pag = xfs_perag_get(mp, agno);

 restart_pagno:
	cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
	/*
	 * If pagino is 0 (this is the root inode allocation) use newino.
	 * This must work because we've just allocated some.
	 */
	if (!pagino)
		pagino = be32_to_cpu(agi->agi_newino);

	error = xfs_check_agi_freecount(cur, agi);
	if (error)
		goto error0;

	/*
	 * If in the same AG as the parent, try to get near the parent.
	 */
	if (pagno == agno) {
		int		doneleft;	/* done, to the left */
		int		doneright;	/* done, to the right */
		int		searchdistance = 10;

		error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i);
		if (error)
			goto error0;
		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);

		error = xfs_inobt_get_rec(cur, &rec, &j);
		if (error)
			goto error0;
		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);

		if (rec.ir_freecount > 0) {
			/*
			 * Found a free inode in the same chunk
			 * as the parent, done.
			 */
			goto alloc_inode;
		}


		/*
		 * In the same AG as parent, but parent's chunk is full.
		 */

		/* duplicate the cursor, search left & right simultaneously */
		error = xfs_btree_dup_cursor(cur, &tcur);
		if (error)
			goto error0;

		/*
		 * Skip to last blocks looked up if same parent inode.
		 */
		if (pagino != NULLAGINO &&
		    pag->pagl_pagino == pagino &&
		    pag->pagl_leftrec != NULLAGINO &&
		    pag->pagl_rightrec != NULLAGINO) {
			error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec,
						   &trec, &doneleft, 1);
			if (error)
				goto error1;

			error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec,
						   &rec, &doneright, 0);
			if (error)
				goto error1;
		} else {
			/* search left with tcur, back up 1 record */
			error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1);
			if (error)
				goto error1;

			/* search right with cur, go forward 1 record. */
			error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0);
			if (error)
				goto error1;
		}

		/*
		 * Loop until we find an inode chunk with a free inode.
		 */
		while (!doneleft || !doneright) {
			int	useleft;  /* using left inode chunk this time */

			if (!--searchdistance) {
				/*
				 * Not in range - save last search
				 * location and allocate a new inode
				 */
				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
				pag->pagl_leftrec = trec.ir_startino;
				pag->pagl_rightrec = rec.ir_startino;
				pag->pagl_pagino = pagino;
				goto newino;
			}

			/* figure out the closer block if both are valid. */
			if (!doneleft && !doneright) {
				useleft = pagino -
				 (trec.ir_startino + XFS_INODES_PER_CHUNK - 1) <
				  rec.ir_startino - pagino;
			} else {
				useleft = !doneleft;
			}

			/* free inodes to the left? */
			if (useleft && trec.ir_freecount) {
				rec = trec;
				xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
				cur = tcur;

				pag->pagl_leftrec = trec.ir_startino;
				pag->pagl_rightrec = rec.ir_startino;
				pag->pagl_pagino = pagino;
				goto alloc_inode;
			}

			/* free inodes to the right? */
			if (!useleft && rec.ir_freecount) {
				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);

				pag->pagl_leftrec = trec.ir_startino;
				pag->pagl_rightrec = rec.ir_startino;
				pag->pagl_pagino = pagino;
				goto alloc_inode;
			}

			/* get next record to check */
			if (useleft) {
				error = xfs_ialloc_next_rec(tcur, &trec,
								 &doneleft, 1);
			} else {
				error = xfs_ialloc_next_rec(cur, &rec,
								 &doneright, 0);
			}
			if (error)
				goto error1;
		}

		/*
		 * We've reached the end of the btree. because
		 * we are only searching a small chunk of the
		 * btree each search, there is obviously free
		 * inodes closer to the parent inode than we
		 * are now. restart the search again.
		 */
		pag->pagl_pagino = NULLAGINO;
		pag->pagl_leftrec = NULLAGINO;
		pag->pagl_rightrec = NULLAGINO;
		xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
		goto restart_pagno;
	}

	/*
	 * In a different AG from the parent.
	 * See if the most recently allocated block has any free.
	 */
newino:
	if (be32_to_cpu(agi->agi_newino) != NULLAGINO) {
		error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
					 XFS_LOOKUP_EQ, &i);
		if (error)
			goto error0;

		if (i == 1) {
			error = xfs_inobt_get_rec(cur, &rec, &j);
			if (error)
				goto error0;

			if (j == 1 && rec.ir_freecount > 0) {
				/*
				 * The last chunk allocated in the group
				 * still has a free inode.
				 */
				goto alloc_inode;
			}
		}
	}

	/*
	 * None left in the last group, search the whole AG
	 */
	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
	if (error)
		goto error0;
	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);

	for (;;) {
		error = xfs_inobt_get_rec(cur, &rec, &i);
		if (error)
			goto error0;
		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
		if (rec.ir_freecount > 0)
			break;
		error = xfs_btree_increment(cur, 0, &i);
		if (error)
			goto error0;
		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
	}

alloc_inode:
	offset = xfs_ialloc_find_free(&rec.ir_free);
	ASSERT(offset >= 0);
	ASSERT(offset < XFS_INODES_PER_CHUNK);
	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
				   XFS_INODES_PER_CHUNK) == 0);
	ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
	rec.ir_free &= ~XFS_INOBT_MASK(offset);
	rec.ir_freecount--;
	error = xfs_inobt_update(cur, &rec);
	if (error)
		goto error0;
	be32_add_cpu(&agi->agi_freecount, -1);
	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
	pag->pagi_freecount--;

	error = xfs_check_agi_freecount(cur, agi);
	if (error)
		goto error0;

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
	xfs_perag_put(pag);
	*inop = ino;
	return 0;
error1:
	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
error0:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	xfs_perag_put(pag);
	return error;
}

/*
 * Free disk inode.  Carefully avoids touching the incore inode, all
 * manipulations incore are the caller's responsibility.
 * The on-disk inode is not changed by this operation, only the
 * btree (free inode mask) is changed.
 */
int
xfs_difree(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_ino_t	inode,		/* inode to be freed */
	xfs_bmap_free_t	*flist,		/* extents to free */
	int		*delete,	/* set if inode cluster was deleted */
	xfs_ino_t	*first_ino)	/* first inode in deleted cluster */
{
	/* REFERENCED */
	xfs_agblock_t	agbno;	/* block number containing inode */
	xfs_buf_t	*agbp;	/* buffer containing allocation group header */
	xfs_agino_t	agino;	/* inode number relative to allocation group */
	xfs_agnumber_t	agno;	/* allocation group number */
	xfs_agi_t	*agi;	/* allocation group header */
	xfs_btree_cur_t	*cur;	/* inode btree cursor */
	int		error;	/* error return value */
	int		i;	/* result code */
	int		ilen;	/* inodes in an inode cluster */
	xfs_mount_t	*mp;	/* mount structure for filesystem */
	int		off;	/* offset of inode in inode chunk */
	xfs_inobt_rec_incore_t rec;	/* btree record */
	struct xfs_perag *pag;

	mp = tp->t_mountp;

	/*
	 * Break up inode number into its components.
	 */
	agno = XFS_INO_TO_AGNO(mp, inode);
	if (agno >= mp->m_sb.sb_agcount)  {
		cmn_err(CE_WARN,
			"xfs_difree: agno >= mp->m_sb.sb_agcount (%d >= %d) on %s.  Returning EINVAL.",
			agno, mp->m_sb.sb_agcount, mp->m_fsname);
		ASSERT(0);
		return XFS_ERROR(EINVAL);
	}
	agino = XFS_INO_TO_AGINO(mp, inode);
	if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
		cmn_err(CE_WARN,
			"xfs_difree: inode != XFS_AGINO_TO_INO() "
			"(%llu != %llu) on %s.  Returning EINVAL.",
			(unsigned long long)inode,
			(unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino),
			mp->m_fsname);
		ASSERT(0);
		return XFS_ERROR(EINVAL);
	}
	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
	if (agbno >= mp->m_sb.sb_agblocks)  {
		cmn_err(CE_WARN,
			"xfs_difree: agbno >= mp->m_sb.sb_agblocks (%d >= %d) on %s.  Returning EINVAL.",
			agbno, mp->m_sb.sb_agblocks, mp->m_fsname);
		ASSERT(0);
		return XFS_ERROR(EINVAL);
	}
	/*
	 * Get the allocation group header.
	 */
	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
	if (error) {
		cmn_err(CE_WARN,
			"xfs_difree: xfs_ialloc_read_agi() returned an error %d on %s.  Returning error.",
			error, mp->m_fsname);
		return error;
	}
	agi = XFS_BUF_TO_AGI(agbp);
	ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
	ASSERT(agbno < be32_to_cpu(agi->agi_length));
	/*
	 * Initialize the cursor.
	 */
	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);

	error = xfs_check_agi_freecount(cur, agi);
	if (error)
		goto error0;

	/*
	 * Look for the entry describing this inode.
	 */
	if ((error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i))) {
		cmn_err(CE_WARN,
			"xfs_difree: xfs_inobt_lookup returned()  an error %d on %s.  Returning error.",
			error, mp->m_fsname);
		goto error0;
	}
	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
	error = xfs_inobt_get_rec(cur, &rec, &i);
	if (error) {
		cmn_err(CE_WARN,
			"xfs_difree: xfs_inobt_get_rec()  returned an error %d on %s.  Returning error.",
			error, mp->m_fsname);
		goto error0;
	}
	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
	/*
	 * Get the offset in the inode chunk.
	 */
	off = agino - rec.ir_startino;
	ASSERT(off >= 0 && off < XFS_INODES_PER_CHUNK);
	ASSERT(!(rec.ir_free & XFS_INOBT_MASK(off)));
	/*
	 * Mark the inode free & increment the count.
	 */
	rec.ir_free |= XFS_INOBT_MASK(off);
	rec.ir_freecount++;

	/*
	 * When an inode cluster is free, it becomes eligible for removal
	 */
	if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
	    (rec.ir_freecount == XFS_IALLOC_INODES(mp))) {

		*delete = 1;
		*first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino);

		/*
		 * Remove the inode cluster from the AGI B+Tree, adjust the
		 * AGI and Superblock inode counts, and mark the disk space
		 * to be freed when the transaction is committed.
		 */
		ilen = XFS_IALLOC_INODES(mp);
		be32_add_cpu(&agi->agi_count, -ilen);
		be32_add_cpu(&agi->agi_freecount, -(ilen - 1));
		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT);
		pag = xfs_perag_get(mp, agno);
		pag->pagi_freecount -= ilen - 1;
		xfs_perag_put(pag);
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen);
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));

		if ((error = xfs_btree_delete(cur, &i))) {
			cmn_err(CE_WARN, "xfs_difree: xfs_btree_delete returned an error %d on %s.\n",
				error, mp->m_fsname);
			goto error0;
		}

		xfs_bmap_add_free(XFS_AGB_TO_FSB(mp,
				agno, XFS_INO_TO_AGBNO(mp,rec.ir_startino)),
				XFS_IALLOC_BLOCKS(mp), flist, mp);
	} else {
		*delete = 0;

		error = xfs_inobt_update(cur, &rec);
		if (error) {
			cmn_err(CE_WARN,
	"xfs_difree: xfs_inobt_update returned an error %d on %s.",
				error, mp->m_fsname);
			goto error0;
		}

		/* 
		 * Change the inode free counts and log the ag/sb changes.
		 */
		be32_add_cpu(&agi->agi_freecount, 1);
		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
		pag = xfs_perag_get(mp, agno);
		pag->pagi_freecount++;
		xfs_perag_put(pag);
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, 1);
	}

	error = xfs_check_agi_freecount(cur, agi);
	if (error)
		goto error0;

	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	return 0;

error0:
	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
	return error;
}

STATIC int
xfs_imap_lookup(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agino_t		agino,
	xfs_agblock_t		agbno,
	xfs_agblock_t		*chunk_agbno,
	xfs_agblock_t		*offset_agbno,
	int			flags)
{
	struct xfs_inobt_rec_incore rec;
	struct xfs_btree_cur	*cur;
	struct xfs_buf		*agbp;
	int			error;
	int			i;

	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
	if (error) {
		xfs_alert(mp,
			"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
			__func__, error, agno);
		return error;
	}

	/*
	 * Lookup the inode record for the given agino. If the record cannot be
	 * found, then it's an invalid inode number and we should abort. Once
	 * we have a record, we need to ensure it contains the inode number
	 * we are looking up.
	 */
	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
	if (!error) {
		if (i)
			error = xfs_inobt_get_rec(cur, &rec, &i);
		if (!error && i == 0)
			error = EINVAL;
	}

	xfs_trans_brelse(tp, agbp);
	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
	if (error)
		return error;

	/* check that the returned record contains the required inode */
	if (rec.ir_startino > agino ||
	    rec.ir_startino + XFS_IALLOC_INODES(mp) <= agino)
		return EINVAL;

	/* for untrusted inodes check it is allocated first */
	if ((flags & XFS_IGET_UNTRUSTED) &&
	    (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino)))
		return EINVAL;

	*chunk_agbno = XFS_AGINO_TO_AGBNO(mp, rec.ir_startino);
	*offset_agbno = agbno - *chunk_agbno;
	return 0;
}

/*
 * Return the location of the inode in imap, for mapping it into a buffer.
 */
int
xfs_imap(
	xfs_mount_t	 *mp,	/* file system mount structure */
	xfs_trans_t	 *tp,	/* transaction pointer */
	xfs_ino_t	ino,	/* inode to locate */
	struct xfs_imap	*imap,	/* location map structure */
	uint		flags)	/* flags for inode btree lookup */
{
	xfs_agblock_t	agbno;	/* block number of inode in the alloc group */
	xfs_agino_t	agino;	/* inode number within alloc group */
	xfs_agnumber_t	agno;	/* allocation group number */
	int		blks_per_cluster; /* num blocks per inode cluster */
	xfs_agblock_t	chunk_agbno;	/* first block in inode chunk */
	xfs_agblock_t	cluster_agbno;	/* first block in inode cluster */
	int		error;	/* error code */
	int		offset;	/* index of inode in its buffer */
	int		offset_agbno;	/* blks from chunk start to inode */

	ASSERT(ino != NULLFSINO);

	/*
	 * Split up the inode number into its parts.
	 */
	agno = XFS_INO_TO_AGNO(mp, ino);
	agino = XFS_INO_TO_AGINO(mp, ino);
	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
	if (agno >= mp->m_sb.sb_agcount || agbno >= mp->m_sb.sb_agblocks ||
	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
#ifdef DEBUG
		/*
		 * Don't output diagnostic information for untrusted inodes
		 * as they can be invalid without implying corruption.
		 */
		if (flags & XFS_IGET_UNTRUSTED)
			return XFS_ERROR(EINVAL);
		if (agno >= mp->m_sb.sb_agcount) {
			xfs_alert(mp,
				"%s: agno (%d) >= mp->m_sb.sb_agcount (%d)",
				__func__, agno, mp->m_sb.sb_agcount);
		}
		if (agbno >= mp->m_sb.sb_agblocks) {
			xfs_alert(mp,
		"%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)",
				__func__, (unsigned long long)agbno,
				(unsigned long)mp->m_sb.sb_agblocks);
		}
		if (ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
			xfs_alert(mp,
		"%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
				__func__, ino,
				XFS_AGINO_TO_INO(mp, agno, agino));
		}
		xfs_stack_trace();
#endif /* DEBUG */
		return XFS_ERROR(EINVAL);
	}

	blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog;

	/*
	 * For bulkstat and handle lookups, we have an untrusted inode number
	 * that we have to verify is valid. We cannot do this just by reading
	 * the inode buffer as it may have been unlinked and removed leaving
	 * inodes in stale state on disk. Hence we have to do a btree lookup
	 * in all cases where an untrusted inode number is passed.
	 */
	if (flags & XFS_IGET_UNTRUSTED) {
		error = xfs_imap_lookup(mp, tp, agno, agino, agbno,
					&chunk_agbno, &offset_agbno, flags);
		if (error)
			return error;
		goto out_map;
	}

	/*
	 * If the inode cluster size is the same as the blocksize or
	 * smaller we get to the buffer by simple arithmetics.
	 */
	if (XFS_INODE_CLUSTER_SIZE(mp) <= mp->m_sb.sb_blocksize) {
		offset = XFS_INO_TO_OFFSET(mp, ino);
		ASSERT(offset < mp->m_sb.sb_inopblock);

		imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno);
		imap->im_len = XFS_FSB_TO_BB(mp, 1);
		imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);
		return 0;
	}

	/*
	 * If the inode chunks are aligned then use simple maths to
	 * find the location. Otherwise we have to do a btree
	 * lookup to find the location.
	 */
	if (mp->m_inoalign_mask) {
		offset_agbno = agbno & mp->m_inoalign_mask;
		chunk_agbno = agbno - offset_agbno;
	} else {
		error = xfs_imap_lookup(mp, tp, agno, agino, agbno,
					&chunk_agbno, &offset_agbno, flags);
		if (error)
			return error;
	}

out_map:
	ASSERT(agbno >= chunk_agbno);
	cluster_agbno = chunk_agbno +
		((offset_agbno / blks_per_cluster) * blks_per_cluster);
	offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
		XFS_INO_TO_OFFSET(mp, ino);

	imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, cluster_agbno);
	imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster);
	imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);

	/*
	 * If the inode number maps to a block outside the bounds
	 * of the file system then return NULL rather than calling
	 * read_buf and panicing when we get an error from the
	 * driver.
	 */
	if ((imap->im_blkno + imap->im_len) >
	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
		xfs_alert(mp,
	"%s: (im_blkno (0x%llx) + im_len (0x%llx)) > sb_dblocks (0x%llx)",
			__func__, (unsigned long long) imap->im_blkno,
			(unsigned long long) imap->im_len,
			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
		return XFS_ERROR(EINVAL);
	}
	return 0;
}

/*
 * Compute and fill in value of m_in_maxlevels.
 */
void
xfs_ialloc_compute_maxlevels(
	xfs_mount_t	*mp)		/* file system mount structure */
{
	int		level;
	uint		maxblocks;
	uint		maxleafents;
	int		minleafrecs;
	int		minnoderecs;

	maxleafents = (1LL << XFS_INO_AGINO_BITS(mp)) >>
		XFS_INODES_PER_CHUNK_LOG;
	minleafrecs = mp->m_alloc_mnr[0];
	minnoderecs = mp->m_alloc_mnr[1];
	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
	for (level = 1; maxblocks > 1; level++)
		maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
	mp->m_in_maxlevels = level;
}

/*
 * Log specified fields for the ag hdr (inode section)
 */
void
xfs_ialloc_log_agi(
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_buf_t	*bp,		/* allocation group header buffer */
	int		fields)		/* bitmask of fields to log */
{
	int			first;		/* first byte number */
	int			last;		/* last byte number */
	static const short	offsets[] = {	/* field starting offsets */
					/* keep in sync with bit definitions */
		offsetof(xfs_agi_t, agi_magicnum),
		offsetof(xfs_agi_t, agi_versionnum),
		offsetof(xfs_agi_t, agi_seqno),
		offsetof(xfs_agi_t, agi_length),
		offsetof(xfs_agi_t, agi_count),
		offsetof(xfs_agi_t, agi_root),
		offsetof(xfs_agi_t, agi_level),
		offsetof(xfs_agi_t, agi_freecount),
		offsetof(xfs_agi_t, agi_newino),
		offsetof(xfs_agi_t, agi_dirino),
		offsetof(xfs_agi_t, agi_unlinked),
		sizeof(xfs_agi_t)
	};
#ifdef DEBUG
	xfs_agi_t		*agi;	/* allocation group header */

	agi = XFS_BUF_TO_AGI(bp);
	ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC);
#endif
	/*
	 * Compute byte offsets for the first and last fields.
	 */
	xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS, &first, &last);
	/*
	 * Log the allocation group inode header buffer.
	 */
	xfs_trans_log_buf(tp, bp, first, last);
}

#ifdef DEBUG
STATIC void
xfs_check_agi_unlinked(
	struct xfs_agi		*agi)
{
	int			i;

	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
		ASSERT(agi->agi_unlinked[i]);
}
#else
#define xfs_check_agi_unlinked(agi)
#endif

/*
 * Read in the allocation group header (inode allocation section)
 */
int
xfs_read_agi(
	struct xfs_mount	*mp,	/* file system mount structure */
	struct xfs_trans	*tp,	/* transaction pointer */
	xfs_agnumber_t		agno,	/* allocation group number */
	struct xfs_buf		**bpp)	/* allocation group hdr buf */
{
	struct xfs_agi		*agi;	/* allocation group header */
	int			agi_ok;	/* agi is consistent */
	int			error;

	ASSERT(agno != NULLAGNUMBER);

	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, bpp);
	if (error)
		return error;

	ASSERT(*bpp && !XFS_BUF_GETERROR(*bpp));
	agi = XFS_BUF_TO_AGI(*bpp);

	/*
	 * Validate the magic number of the agi block.
	 */
	agi_ok = be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)) &&
		be32_to_cpu(agi->agi_seqno) == agno;
	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
			XFS_RANDOM_IALLOC_READ_AGI))) {
		XFS_CORRUPTION_ERROR("xfs_read_agi", XFS_ERRLEVEL_LOW,
				     mp, agi);
		xfs_trans_brelse(tp, *bpp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_AGI, XFS_AGI_REF);

	xfs_check_agi_unlinked(agi);
	return 0;
}

int
xfs_ialloc_read_agi(
	struct xfs_mount	*mp,	/* file system mount structure */
	struct xfs_trans	*tp,	/* transaction pointer */
	xfs_agnumber_t		agno,	/* allocation group number */
	struct xfs_buf		**bpp)	/* allocation group hdr buf */
{
	struct xfs_agi		*agi;	/* allocation group header */
	struct xfs_perag	*pag;	/* per allocation group data */
	int			error;

	error = xfs_read_agi(mp, tp, agno, bpp);
	if (error)
		return error;

	agi = XFS_BUF_TO_AGI(*bpp);
	pag = xfs_perag_get(mp, agno);
	if (!pag->pagi_init) {
		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
		pag->pagi_count = be32_to_cpu(agi->agi_count);
		pag->pagi_init = 1;
	}

	/*
	 * It's possible for these to be out of sync if
	 * we are in the middle of a forced shutdown.
	 */
	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
		XFS_FORCED_SHUTDOWN(mp));
	xfs_perag_put(pag);
	return 0;
}

/*
 * Read in the agi to initialise the per-ag data in the mount structure
 */
int
xfs_ialloc_pagi_init(
	xfs_mount_t	*mp,		/* file system mount structure */
	xfs_trans_t	*tp,		/* transaction pointer */
	xfs_agnumber_t	agno)		/* allocation group number */
{
	xfs_buf_t	*bp = NULL;
	int		error;

	error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
	if (error)
		return error;
	if (bp)
		xfs_trans_brelse(tp, bp);
	return 0;
}