aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_mount.c
blob: b57423caef9b86fa0f3fb381d0610f8c3afa8f45 (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
/*
 * Copyright (c) 2000-2004 Silicon Graphics, Inc.  All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of version 2 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.
 *
 * Further, this software is distributed without any warranty that it is
 * free of the rightful claim of any third person regarding infringement
 * or the like.  Any license provided herein, whether implied or
 * otherwise, applies only to this software file.  Patent licenses, if
 * any, provided herein do not apply to combinations of this program with
 * other software, or any other product whatsoever.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write the Free Software Foundation, Inc., 59
 * Temple Place - Suite 330, Boston MA 02111-1307, USA.
 *
 * Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy,
 * Mountain View, CA  94043, or:
 *
 * http://www.sgi.com
 *
 * For further information regarding this notice, see:
 *
 * http://oss.sgi.com/projects/GenInfo/SGIGPLNoticeExplan/
 */

#include "xfs.h"
#include "xfs_macros.h"
#include "xfs_types.h"
#include "xfs_inum.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_alloc_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_attr_sf.h"
#include "xfs_dir_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_bit.h"
#include "xfs_rw.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"

STATIC void	xfs_mount_log_sbunit(xfs_mount_t *, __int64_t);
STATIC int	xfs_uuid_mount(xfs_mount_t *);
STATIC void	xfs_uuid_unmount(xfs_mount_t *mp);

static struct {
    short offset;
    short type;     /* 0 = integer
		* 1 = binary / string (no translation)
		*/
} xfs_sb_info[] = {
    { offsetof(xfs_sb_t, sb_magicnum),   0 },
    { offsetof(xfs_sb_t, sb_blocksize),  0 },
    { offsetof(xfs_sb_t, sb_dblocks),    0 },
    { offsetof(xfs_sb_t, sb_rblocks),    0 },
    { offsetof(xfs_sb_t, sb_rextents),   0 },
    { offsetof(xfs_sb_t, sb_uuid),       1 },
    { offsetof(xfs_sb_t, sb_logstart),   0 },
    { offsetof(xfs_sb_t, sb_rootino),    0 },
    { offsetof(xfs_sb_t, sb_rbmino),     0 },
    { offsetof(xfs_sb_t, sb_rsumino),    0 },
    { offsetof(xfs_sb_t, sb_rextsize),   0 },
    { offsetof(xfs_sb_t, sb_agblocks),   0 },
    { offsetof(xfs_sb_t, sb_agcount),    0 },
    { offsetof(xfs_sb_t, sb_rbmblocks),  0 },
    { offsetof(xfs_sb_t, sb_logblocks),  0 },
    { offsetof(xfs_sb_t, sb_versionnum), 0 },
    { offsetof(xfs_sb_t, sb_sectsize),   0 },
    { offsetof(xfs_sb_t, sb_inodesize),  0 },
    { offsetof(xfs_sb_t, sb_inopblock),  0 },
    { offsetof(xfs_sb_t, sb_fname[0]),   1 },
    { offsetof(xfs_sb_t, sb_blocklog),   0 },
    { offsetof(xfs_sb_t, sb_sectlog),    0 },
    { offsetof(xfs_sb_t, sb_inodelog),   0 },
    { offsetof(xfs_sb_t, sb_inopblog),   0 },
    { offsetof(xfs_sb_t, sb_agblklog),   0 },
    { offsetof(xfs_sb_t, sb_rextslog),   0 },
    { offsetof(xfs_sb_t, sb_inprogress), 0 },
    { offsetof(xfs_sb_t, sb_imax_pct),   0 },
    { offsetof(xfs_sb_t, sb_icount),     0 },
    { offsetof(xfs_sb_t, sb_ifree),      0 },
    { offsetof(xfs_sb_t, sb_fdblocks),   0 },
    { offsetof(xfs_sb_t, sb_frextents),  0 },
    { offsetof(xfs_sb_t, sb_uquotino),   0 },
    { offsetof(xfs_sb_t, sb_gquotino),   0 },
    { offsetof(xfs_sb_t, sb_qflags),     0 },
    { offsetof(xfs_sb_t, sb_flags),      0 },
    { offsetof(xfs_sb_t, sb_shared_vn),  0 },
    { offsetof(xfs_sb_t, sb_inoalignmt), 0 },
    { offsetof(xfs_sb_t, sb_unit),	 0 },
    { offsetof(xfs_sb_t, sb_width),	 0 },
    { offsetof(xfs_sb_t, sb_dirblklog),	 0 },
    { offsetof(xfs_sb_t, sb_logsectlog), 0 },
    { offsetof(xfs_sb_t, sb_logsectsize),0 },
    { offsetof(xfs_sb_t, sb_logsunit),	 0 },
    { offsetof(xfs_sb_t, sb_features2),	 0 },
    { sizeof(xfs_sb_t),			 0 }
};

/*
 * Return a pointer to an initialized xfs_mount structure.
 */
xfs_mount_t *
xfs_mount_init(void)
{
	xfs_mount_t *mp;

	mp = kmem_zalloc(sizeof(*mp), KM_SLEEP);

	AIL_LOCKINIT(&mp->m_ail_lock, "xfs_ail");
	spinlock_init(&mp->m_sb_lock, "xfs_sb");
	mutex_init(&mp->m_ilock, MUTEX_DEFAULT, "xfs_ilock");
	initnsema(&mp->m_growlock, 1, "xfs_grow");
	/*
	 * Initialize the AIL.
	 */
	xfs_trans_ail_init(mp);

	atomic_set(&mp->m_active_trans, 0);

	return mp;
}

/*
 * Free up the resources associated with a mount structure.  Assume that
 * the structure was initially zeroed, so we can tell which fields got
 * initialized.
 */
void
xfs_mount_free(
	xfs_mount_t *mp,
	int	    remove_bhv)
{
	if (mp->m_ihash)
		xfs_ihash_free(mp);
	if (mp->m_chash)
		xfs_chash_free(mp);

	if (mp->m_perag) {
		int	agno;

		for (agno = 0; agno < mp->m_maxagi; agno++)
			if (mp->m_perag[agno].pagb_list)
				kmem_free(mp->m_perag[agno].pagb_list,
						sizeof(xfs_perag_busy_t) *
							XFS_PAGB_NUM_SLOTS);
		kmem_free(mp->m_perag,
			  sizeof(xfs_perag_t) * mp->m_sb.sb_agcount);
	}

	AIL_LOCK_DESTROY(&mp->m_ail_lock);
	spinlock_destroy(&mp->m_sb_lock);
	mutex_destroy(&mp->m_ilock);
	freesema(&mp->m_growlock);
	if (mp->m_quotainfo)
		XFS_QM_DONE(mp);

	if (mp->m_fsname != NULL)
		kmem_free(mp->m_fsname, mp->m_fsname_len);

	if (remove_bhv) {
		struct vfs	*vfsp = XFS_MTOVFS(mp);

		bhv_remove_all_vfsops(vfsp, 0);
		VFS_REMOVEBHV(vfsp, &mp->m_bhv);
	}

	kmem_free(mp, sizeof(xfs_mount_t));
}


/*
 * Check the validity of the SB found.
 */
STATIC int
xfs_mount_validate_sb(
	xfs_mount_t	*mp,
	xfs_sb_t	*sbp)
{
	/*
	 * If the log device and data device have the
	 * same device number, the log is internal.
	 * Consequently, the sb_logstart should be non-zero.  If
	 * we have a zero sb_logstart in this case, we may be trying to mount
	 * a volume filesystem in a non-volume manner.
	 */
	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
		cmn_err(CE_WARN, "XFS: bad magic number");
		return XFS_ERROR(EWRONGFS);
	}

	if (!XFS_SB_GOOD_VERSION(sbp)) {
		cmn_err(CE_WARN, "XFS: bad version");
		return XFS_ERROR(EWRONGFS);
	}

	if (unlikely(
	    sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
		cmn_err(CE_WARN,
	"XFS: filesystem is marked as having an external log; "
	"specify logdev on the\nmount command line.");
		XFS_CORRUPTION_ERROR("xfs_mount_validate_sb(1)",
				     XFS_ERRLEVEL_HIGH, mp, sbp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	if (unlikely(
	    sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
		cmn_err(CE_WARN,
	"XFS: filesystem is marked as having an internal log; "
	"don't specify logdev on\nthe mount command line.");
		XFS_CORRUPTION_ERROR("xfs_mount_validate_sb(2)",
				     XFS_ERRLEVEL_HIGH, mp, sbp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	/*
	 * More sanity checking. These were stolen directly from
	 * xfs_repair.
	 */
	if (unlikely(
	    sbp->sb_agcount <= 0					||
	    sbp->sb_sectsize < XFS_MIN_SECTORSIZE			||
	    sbp->sb_sectsize > XFS_MAX_SECTORSIZE			||
	    sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG			||
	    sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG			||
	    sbp->sb_blocksize < XFS_MIN_BLOCKSIZE			||
	    sbp->sb_blocksize > XFS_MAX_BLOCKSIZE			||
	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
	    (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)	||
	    sbp->sb_imax_pct > 100)) {
		cmn_err(CE_WARN, "XFS: SB sanity check 1 failed");
		XFS_CORRUPTION_ERROR("xfs_mount_validate_sb(3)",
				     XFS_ERRLEVEL_LOW, mp, sbp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	/*
	 * Sanity check AG count, size fields against data size field
	 */
	if (unlikely(
	    sbp->sb_dblocks == 0 ||
	    sbp->sb_dblocks >
	     (xfs_drfsbno_t)sbp->sb_agcount * sbp->sb_agblocks ||
	    sbp->sb_dblocks < (xfs_drfsbno_t)(sbp->sb_agcount - 1) *
			      sbp->sb_agblocks + XFS_MIN_AG_BLOCKS)) {
		cmn_err(CE_WARN, "XFS: SB sanity check 2 failed");
		XFS_ERROR_REPORT("xfs_mount_validate_sb(4)",
				 XFS_ERRLEVEL_LOW, mp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
	ASSERT(sbp->sb_blocklog >= BBSHIFT);

#if XFS_BIG_BLKNOS     /* Limited by ULONG_MAX of page cache index */
	if (unlikely(
	    (sbp->sb_dblocks >> (PAGE_SHIFT - sbp->sb_blocklog)) > ULONG_MAX ||
	    (sbp->sb_rblocks >> (PAGE_SHIFT - sbp->sb_blocklog)) > ULONG_MAX)) {
#else                  /* Limited by UINT_MAX of sectors */
	if (unlikely(
	    (sbp->sb_dblocks << (sbp->sb_blocklog - BBSHIFT)) > UINT_MAX ||
	    (sbp->sb_rblocks << (sbp->sb_blocklog - BBSHIFT)) > UINT_MAX)) {
#endif
		cmn_err(CE_WARN,
	"XFS: File system is too large to be mounted on this system.");
		return XFS_ERROR(E2BIG);
	}

	if (unlikely(sbp->sb_inprogress)) {
		cmn_err(CE_WARN, "XFS: file system busy");
		XFS_ERROR_REPORT("xfs_mount_validate_sb(5)",
				 XFS_ERRLEVEL_LOW, mp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	/*
	 * Until this is fixed only page-sized or smaller data blocks work.
	 */
	if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
		cmn_err(CE_WARN,
		"XFS: Attempted to mount file system with blocksize %d bytes",
			sbp->sb_blocksize);
		cmn_err(CE_WARN,
		"XFS: Only page-sized (%d) or less blocksizes currently work.",
			PAGE_SIZE);
		return XFS_ERROR(ENOSYS);
	}

	return 0;
}

xfs_agnumber_t
xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount)
{
	xfs_agnumber_t	index, max_metadata;
	xfs_perag_t	*pag;
	xfs_agino_t	agino;
	xfs_ino_t	ino;
	xfs_sb_t	*sbp = &mp->m_sb;
	xfs_ino_t	max_inum = XFS_MAXINUMBER_32;

	/* Check to see if the filesystem can overflow 32 bit inodes */
	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);

	/* Clear the mount flag if no inode can overflow 32 bits
	 * on this filesystem, or if specifically requested..
	 */
	if ((mp->m_flags & XFS_MOUNT_32BITINOOPT) && ino > max_inum) {
		mp->m_flags |= XFS_MOUNT_32BITINODES;
	} else {
		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
	}

	/* If we can overflow then setup the ag headers accordingly */
	if (mp->m_flags & XFS_MOUNT_32BITINODES) {
		/* Calculate how much should be reserved for inodes to
		 * meet the max inode percentage.
		 */
		if (mp->m_maxicount) {
			__uint64_t	icount;

			icount = sbp->sb_dblocks * sbp->sb_imax_pct;
			do_div(icount, 100);
			icount += sbp->sb_agblocks - 1;
			do_div(icount, mp->m_ialloc_blks);
			max_metadata = icount;
		} else {
			max_metadata = agcount;
		}
		for (index = 0; index < agcount; index++) {
			ino = XFS_AGINO_TO_INO(mp, index, agino);
			if (ino > max_inum) {
				index++;
				break;
			}

			/* This ag is prefered for inodes */
			pag = &mp->m_perag[index];
			pag->pagi_inodeok = 1;
			if (index < max_metadata)
				pag->pagf_metadata = 1;
		}
	} else {
		/* Setup default behavior for smaller filesystems */
		for (index = 0; index < agcount; index++) {
			pag = &mp->m_perag[index];
			pag->pagi_inodeok = 1;
		}
	}
	return index;
}

/*
 * xfs_xlatesb
 *
 *     data       - on disk version of sb
 *     sb         - a superblock
 *     dir        - conversion direction: <0 - convert sb to buf
 *                                        >0 - convert buf to sb
 *     fields     - which fields to copy (bitmask)
 */
void
xfs_xlatesb(
	void		*data,
	xfs_sb_t	*sb,
	int		dir,
	__int64_t	fields)
{
	xfs_caddr_t	buf_ptr;
	xfs_caddr_t	mem_ptr;
	xfs_sb_field_t	f;
	int		first;
	int		size;

	ASSERT(dir);
	ASSERT(fields);

	if (!fields)
		return;

	buf_ptr = (xfs_caddr_t)data;
	mem_ptr = (xfs_caddr_t)sb;

	while (fields) {
		f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
		first = xfs_sb_info[f].offset;
		size = xfs_sb_info[f + 1].offset - first;

		ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1);

		if (size == 1 || xfs_sb_info[f].type == 1) {
			if (dir > 0) {
				memcpy(mem_ptr + first, buf_ptr + first, size);
			} else {
				memcpy(buf_ptr + first, mem_ptr + first, size);
			}
		} else {
			switch (size) {
			case 2:
				INT_XLATE(*(__uint16_t*)(buf_ptr+first),
					  *(__uint16_t*)(mem_ptr+first),
					  dir, ARCH_CONVERT);
				break;
			case 4:
				INT_XLATE(*(__uint32_t*)(buf_ptr+first),
					  *(__uint32_t*)(mem_ptr+first),
					  dir, ARCH_CONVERT);
				break;
			case 8:
				INT_XLATE(*(__uint64_t*)(buf_ptr+first),
					  *(__uint64_t*)(mem_ptr+first), dir, ARCH_CONVERT);
				break;
			default:
				ASSERT(0);
			}
		}

		fields &= ~(1LL << f);
	}
}

/*
 * xfs_readsb
 *
 * Does the initial read of the superblock.
 */
int
xfs_readsb(xfs_mount_t *mp)
{
	unsigned int	sector_size;
	unsigned int	extra_flags;
	xfs_buf_t	*bp;
	xfs_sb_t	*sbp;
	int		error;

	ASSERT(mp->m_sb_bp == NULL);
	ASSERT(mp->m_ddev_targp != NULL);

	/*
	 * Allocate a (locked) buffer to hold the superblock.
	 * This will be kept around at all times to optimize
	 * access to the superblock.
	 */
	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
	extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;

	bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
				BTOBB(sector_size), extra_flags);
	if (!bp || XFS_BUF_ISERROR(bp)) {
		cmn_err(CE_WARN, "XFS: SB read failed");
		error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
		goto fail;
	}
	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);

	/*
	 * Initialize the mount structure from the superblock.
	 * But first do some basic consistency checking.
	 */
	sbp = XFS_BUF_TO_SBP(bp);
	xfs_xlatesb(XFS_BUF_PTR(bp), &(mp->m_sb), 1, XFS_SB_ALL_BITS);

	error = xfs_mount_validate_sb(mp, &(mp->m_sb));
	if (error) {
		cmn_err(CE_WARN, "XFS: SB validate failed");
		goto fail;
	}

	/*
	 * We must be able to do sector-sized and sector-aligned IO.
	 */
	if (sector_size > mp->m_sb.sb_sectsize) {
		cmn_err(CE_WARN,
			"XFS: device supports only %u byte sectors (not %u)",
			sector_size, mp->m_sb.sb_sectsize);
		error = ENOSYS;
		goto fail;
	}

	/*
	 * If device sector size is smaller than the superblock size,
	 * re-read the superblock so the buffer is correctly sized.
	 */
	if (sector_size < mp->m_sb.sb_sectsize) {
		XFS_BUF_UNMANAGE(bp);
		xfs_buf_relse(bp);
		sector_size = mp->m_sb.sb_sectsize;
		bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
					BTOBB(sector_size), extra_flags);
		if (!bp || XFS_BUF_ISERROR(bp)) {
			cmn_err(CE_WARN, "XFS: SB re-read failed");
			error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
			goto fail;
		}
		ASSERT(XFS_BUF_ISBUSY(bp));
		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
	}

	mp->m_sb_bp = bp;
	xfs_buf_relse(bp);
	ASSERT(XFS_BUF_VALUSEMA(bp) > 0);
	return 0;

 fail:
	if (bp) {
		XFS_BUF_UNMANAGE(bp);
		xfs_buf_relse(bp);
	}
	return error;
}


/*
 * xfs_mount_common
 *
 * Mount initialization code establishing various mount
 * fields from the superblock associated with the given
 * mount structure
 */
void
xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
{
	int	i;

	mp->m_agfrotor = mp->m_agirotor = 0;
	spinlock_init(&mp->m_agirotor_lock, "m_agirotor_lock");
	mp->m_maxagi = mp->m_sb.sb_agcount;
	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
	mp->m_litino = sbp->sb_inodesize -
		((uint)sizeof(xfs_dinode_core_t) + (uint)sizeof(xfs_agino_t));
	mp->m_blockmask = sbp->sb_blocksize - 1;
	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
	mp->m_blockwmask = mp->m_blockwsize - 1;
	INIT_LIST_HEAD(&mp->m_del_inodes);

	/*
	 * Setup for attributes, in case they get created.
	 * This value is for inodes getting attributes for the first time,
	 * the per-inode value is for old attribute values.
	 */
	ASSERT(sbp->sb_inodesize >= 256 && sbp->sb_inodesize <= 2048);
	switch (sbp->sb_inodesize) {
	case 256:
		mp->m_attroffset = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(2);
		break;
	case 512:
	case 1024:
	case 2048:
		mp->m_attroffset = XFS_BMDR_SPACE_CALC(12);
		break;
	default:
		ASSERT(0);
	}
	ASSERT(mp->m_attroffset < XFS_LITINO(mp));

	for (i = 0; i < 2; i++) {
		mp->m_alloc_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_alloc, i == 0);
		mp->m_alloc_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_alloc, i == 0);
	}
	for (i = 0; i < 2; i++) {
		mp->m_bmap_dmxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_bmbt, i == 0);
		mp->m_bmap_dmnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_bmbt, i == 0);
	}
	for (i = 0; i < 2; i++) {
		mp->m_inobt_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
			xfs_inobt, i == 0);
		mp->m_inobt_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
			xfs_inobt, i == 0);
	}

	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
					sbp->sb_inopblock);
	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
}
/*
 * xfs_mountfs
 *
 * This function does the following on an initial mount of a file system:
 *	- reads the superblock from disk and init the mount struct
 *	- if we're a 32-bit kernel, do a size check on the superblock
 *		so we don't mount terabyte filesystems
 *	- init mount struct realtime fields
 *	- allocate inode hash table for fs
 *	- init directory manager
 *	- perform recovery and init the log manager
 */
int
xfs_mountfs(
	vfs_t		*vfsp,
	xfs_mount_t	*mp,
	int		mfsi_flags)
{
	xfs_buf_t	*bp;
	xfs_sb_t	*sbp = &(mp->m_sb);
	xfs_inode_t	*rip;
	vnode_t		*rvp = NULL;
	int		readio_log, writeio_log;
	xfs_daddr_t	d;
	__uint64_t	ret64;
	__int64_t	update_flags;
	uint		quotamount, quotaflags;
	int		agno;
	int		uuid_mounted = 0;
	int		error = 0;

	if (mp->m_sb_bp == NULL) {
		if ((error = xfs_readsb(mp))) {
			return (error);
		}
	}
	xfs_mount_common(mp, sbp);

	/*
	 * Check if sb_agblocks is aligned at stripe boundary
	 * If sb_agblocks is NOT aligned turn off m_dalign since
	 * allocator alignment is within an ag, therefore ag has
	 * to be aligned at stripe boundary.
	 */
	update_flags = 0LL;
	if (mp->m_dalign && !(mfsi_flags & XFS_MFSI_SECOND)) {
		/*
		 * If stripe unit and stripe width are not multiples
		 * of the fs blocksize turn off alignment.
		 */
		if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
		    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
			if (mp->m_flags & XFS_MOUNT_RETERR) {
				cmn_err(CE_WARN,
					"XFS: alignment check 1 failed");
				error = XFS_ERROR(EINVAL);
				goto error1;
			}
			mp->m_dalign = mp->m_swidth = 0;
		} else {
			/*
			 * Convert the stripe unit and width to FSBs.
			 */
			mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
			if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
				if (mp->m_flags & XFS_MOUNT_RETERR) {
					error = XFS_ERROR(EINVAL);
					goto error1;
				}
				xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d)/swidth(%d) incompatible with agsize(%d)",
					mp->m_dalign, mp->m_swidth,
					sbp->sb_agblocks);

				mp->m_dalign = 0;
				mp->m_swidth = 0;
			} else if (mp->m_dalign) {
				mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
			} else {
				if (mp->m_flags & XFS_MOUNT_RETERR) {
					xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d) less than bsize(%d)",
                                        	mp->m_dalign,
						mp->m_blockmask +1);
					error = XFS_ERROR(EINVAL);
					goto error1;
				}
				mp->m_swidth = 0;
			}
		}

		/*
		 * Update superblock with new values
		 * and log changes
		 */
		if (XFS_SB_VERSION_HASDALIGN(sbp)) {
			if (sbp->sb_unit != mp->m_dalign) {
				sbp->sb_unit = mp->m_dalign;
				update_flags |= XFS_SB_UNIT;
			}
			if (sbp->sb_width != mp->m_swidth) {
				sbp->sb_width = mp->m_swidth;
				update_flags |= XFS_SB_WIDTH;
			}
		}
	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
		    XFS_SB_VERSION_HASDALIGN(&mp->m_sb)) {
			mp->m_dalign = sbp->sb_unit;
			mp->m_swidth = sbp->sb_width;
	}

	xfs_alloc_compute_maxlevels(mp);
	xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
	xfs_ialloc_compute_maxlevels(mp);

	if (sbp->sb_imax_pct) {
		__uint64_t	icount;

		/* Make sure the maximum inode count is a multiple of the
		 * units we allocate inodes in.
		 */

		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
		do_div(icount, 100);
		do_div(icount, mp->m_ialloc_blks);
		mp->m_maxicount = (icount * mp->m_ialloc_blks)  <<
				   sbp->sb_inopblog;
	} else
		mp->m_maxicount = 0;

	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);

	/*
	 * XFS uses the uuid from the superblock as the unique
	 * identifier for fsid.  We can not use the uuid from the volume
	 * since a single partition filesystem is identical to a single
	 * partition volume/filesystem.
	 */
	if ((mfsi_flags & XFS_MFSI_SECOND) == 0 &&
	    (mp->m_flags & XFS_MOUNT_NOUUID) == 0) {
		if (xfs_uuid_mount(mp)) {
			error = XFS_ERROR(EINVAL);
			goto error1;
		}
		uuid_mounted=1;
		ret64 = uuid_hash64(&sbp->sb_uuid);
		memcpy(&vfsp->vfs_fsid, &ret64, sizeof(ret64));
	}

	/*
	 * Set the default minimum read and write sizes unless
	 * already specified in a mount option.
	 * We use smaller I/O sizes when the file system
	 * is being used for NFS service (wsync mount option).
	 */
	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
		if (mp->m_flags & XFS_MOUNT_WSYNC) {
			readio_log = XFS_WSYNC_READIO_LOG;
			writeio_log = XFS_WSYNC_WRITEIO_LOG;
		} else {
			readio_log = XFS_READIO_LOG_LARGE;
			writeio_log = XFS_WRITEIO_LOG_LARGE;
		}
	} else {
		readio_log = mp->m_readio_log;
		writeio_log = mp->m_writeio_log;
	}

	/*
	 * Set the number of readahead buffers to use based on
	 * physical memory size.
	 */
	if (xfs_physmem <= 4096)		/* <= 16MB */
		mp->m_nreadaheads = XFS_RW_NREADAHEAD_16MB;
	else if (xfs_physmem <= 8192)	/* <= 32MB */
		mp->m_nreadaheads = XFS_RW_NREADAHEAD_32MB;
	else
		mp->m_nreadaheads = XFS_RW_NREADAHEAD_K32;
	if (sbp->sb_blocklog > readio_log) {
		mp->m_readio_log = sbp->sb_blocklog;
	} else {
		mp->m_readio_log = readio_log;
	}
	mp->m_readio_blocks = 1 << (mp->m_readio_log - sbp->sb_blocklog);
	if (sbp->sb_blocklog > writeio_log) {
		mp->m_writeio_log = sbp->sb_blocklog;
	} else {
		mp->m_writeio_log = writeio_log;
	}
	mp->m_writeio_blocks = 1 << (mp->m_writeio_log - sbp->sb_blocklog);

	/*
	 * Set the inode cluster size based on the physical memory
	 * size.  This may still be overridden by the file system
	 * block size if it is larger than the chosen cluster size.
	 */
	if (xfs_physmem <= btoc(32 * 1024 * 1024)) { /* <= 32 MB */
		mp->m_inode_cluster_size = XFS_INODE_SMALL_CLUSTER_SIZE;
	} else {
		mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
	}
	/*
	 * Set whether we're using inode alignment.
	 */
	if (XFS_SB_VERSION_HASALIGN(&mp->m_sb) &&
	    mp->m_sb.sb_inoalignmt >=
	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
	else
		mp->m_inoalign_mask = 0;
	/*
	 * If we are using stripe alignment, check whether
	 * the stripe unit is a multiple of the inode alignment
	 */
	if (mp->m_dalign && mp->m_inoalign_mask &&
	    !(mp->m_dalign & mp->m_inoalign_mask))
		mp->m_sinoalign = mp->m_dalign;
	else
		mp->m_sinoalign = 0;
	/*
	 * Check that the data (and log if separate) are an ok size.
	 */
	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
		cmn_err(CE_WARN, "XFS: size check 1 failed");
		error = XFS_ERROR(E2BIG);
		goto error1;
	}
	error = xfs_read_buf(mp, mp->m_ddev_targp,
			     d - XFS_FSS_TO_BB(mp, 1),
			     XFS_FSS_TO_BB(mp, 1), 0, &bp);
	if (!error) {
		xfs_buf_relse(bp);
	} else {
		cmn_err(CE_WARN, "XFS: size check 2 failed");
		if (error == ENOSPC) {
			error = XFS_ERROR(E2BIG);
		}
		goto error1;
	}

	if (((mfsi_flags & XFS_MFSI_CLIENT) == 0) &&
	    mp->m_logdev_targp != mp->m_ddev_targp) {
		d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
		if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
			cmn_err(CE_WARN, "XFS: size check 3 failed");
			error = XFS_ERROR(E2BIG);
			goto error1;
		}
		error = xfs_read_buf(mp, mp->m_logdev_targp,
				     d - XFS_FSB_TO_BB(mp, 1),
				     XFS_FSB_TO_BB(mp, 1), 0, &bp);
		if (!error) {
			xfs_buf_relse(bp);
		} else {
			cmn_err(CE_WARN, "XFS: size check 3 failed");
			if (error == ENOSPC) {
				error = XFS_ERROR(E2BIG);
			}
			goto error1;
		}
	}

	/*
	 * Initialize realtime fields in the mount structure
	 */
	if ((error = xfs_rtmount_init(mp))) {
		cmn_err(CE_WARN, "XFS: RT mount failed");
		goto error1;
	}

	/*
	 * For client case we are done now
	 */
	if (mfsi_flags & XFS_MFSI_CLIENT) {
		return(0);
	}

	/*
	 *  Copies the low order bits of the timestamp and the randomly
	 *  set "sequence" number out of a UUID.
	 */
	uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid);

	/*
	 *  The vfs structure needs to have a file system independent
	 *  way of checking for the invariant file system ID.  Since it
	 *  can't look at mount structures it has a pointer to the data
	 *  in the mount structure.
	 *
	 *  File systems that don't support user level file handles (i.e.
	 *  all of them except for XFS) will leave vfs_altfsid as NULL.
	 */
	vfsp->vfs_altfsid = (xfs_fsid_t *)mp->m_fixedfsid;
	mp->m_dmevmask = 0;	/* not persistent; set after each mount */

	/*
	 * Select the right directory manager.
	 */
	mp->m_dirops =
		XFS_SB_VERSION_HASDIRV2(&mp->m_sb) ?
			xfsv2_dirops :
			xfsv1_dirops;

	/*
	 * Initialize directory manager's entries.
	 */
	XFS_DIR_MOUNT(mp);

	/*
	 * Initialize the attribute manager's entries.
	 */
	mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;

	/*
	 * Initialize the precomputed transaction reservations values.
	 */
	xfs_trans_init(mp);

	/*
	 * Allocate and initialize the inode hash table for this
	 * file system.
	 */
	xfs_ihash_init(mp);
	xfs_chash_init(mp);

	/*
	 * Allocate and initialize the per-ag data.
	 */
	init_rwsem(&mp->m_peraglock);
	mp->m_perag =
		kmem_zalloc(sbp->sb_agcount * sizeof(xfs_perag_t), KM_SLEEP);

	mp->m_maxagi = xfs_initialize_perag(mp, sbp->sb_agcount);

	/*
	 * log's mount-time initialization. Perform 1st part recovery if needed
	 */
	if (likely(sbp->sb_logblocks > 0)) {	/* check for volume case */
		error = xfs_log_mount(mp, mp->m_logdev_targp,
				      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
				      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
		if (error) {
			cmn_err(CE_WARN, "XFS: log mount failed");
			goto error2;
		}
	} else {	/* No log has been defined */
		cmn_err(CE_WARN, "XFS: no log defined");
		XFS_ERROR_REPORT("xfs_mountfs_int(1)", XFS_ERRLEVEL_LOW, mp);
		error = XFS_ERROR(EFSCORRUPTED);
		goto error2;
	}

	/*
	 * Get and sanity-check the root inode.
	 * Save the pointer to it in the mount structure.
	 */
	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0);
	if (error) {
		cmn_err(CE_WARN, "XFS: failed to read root inode");
		goto error3;
	}

	ASSERT(rip != NULL);
	rvp = XFS_ITOV(rip);

	if (unlikely((rip->i_d.di_mode & S_IFMT) != S_IFDIR)) {
		cmn_err(CE_WARN, "XFS: corrupted root inode");
		prdev("Root inode %llu is not a directory",
		      mp->m_ddev_targp, (unsigned long long)rip->i_ino);
		xfs_iunlock(rip, XFS_ILOCK_EXCL);
		XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
				 mp);
		error = XFS_ERROR(EFSCORRUPTED);
		goto error4;
	}
	mp->m_rootip = rip;	/* save it */

	xfs_iunlock(rip, XFS_ILOCK_EXCL);

	/*
	 * Initialize realtime inode pointers in the mount structure
	 */
	if ((error = xfs_rtmount_inodes(mp))) {
		/*
		 * Free up the root inode.
		 */
		cmn_err(CE_WARN, "XFS: failed to read RT inodes");
		goto error4;
	}

	/*
	 * If fs is not mounted readonly, then update the superblock
	 * unit and width changes.
	 */
	if (update_flags && !(vfsp->vfs_flag & VFS_RDONLY))
		xfs_mount_log_sbunit(mp, update_flags);

	/*
	 * Initialise the XFS quota management subsystem for this mount
	 */
	if ((error = XFS_QM_INIT(mp, &quotamount, &quotaflags)))
		goto error4;

	/*
	 * Finish recovering the file system.  This part needed to be
	 * delayed until after the root and real-time bitmap inodes
	 * were consistently read in.
	 */
	error = xfs_log_mount_finish(mp, mfsi_flags);
	if (error) {
		cmn_err(CE_WARN, "XFS: log mount finish failed");
		goto error4;
	}

	/*
	 * Complete the quota initialisation, post-log-replay component.
	 */
	if ((error = XFS_QM_MOUNT(mp, quotamount, quotaflags, mfsi_flags)))
		goto error4;

	return 0;

 error4:
	/*
	 * Free up the root inode.
	 */
	VN_RELE(rvp);
 error3:
	xfs_log_unmount_dealloc(mp);
 error2:
	xfs_ihash_free(mp);
	xfs_chash_free(mp);
	for (agno = 0; agno < sbp->sb_agcount; agno++)
		if (mp->m_perag[agno].pagb_list)
			kmem_free(mp->m_perag[agno].pagb_list,
			  sizeof(xfs_perag_busy_t) * XFS_PAGB_NUM_SLOTS);
	kmem_free(mp->m_perag, sbp->sb_agcount * sizeof(xfs_perag_t));
	mp->m_perag = NULL;
	/* FALLTHROUGH */
 error1:
	if (uuid_mounted)
		xfs_uuid_unmount(mp);
	xfs_freesb(mp);
	return error;
}

/*
 * xfs_unmountfs
 *
 * This flushes out the inodes,dquots and the superblock, unmounts the
 * log and makes sure that incore structures are freed.
 */
int
xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
{
	struct vfs	*vfsp = XFS_MTOVFS(mp);
#if defined(DEBUG) || defined(INDUCE_IO_ERROR)
	int64_t		fsid;
#endif

	xfs_iflush_all(mp, XFS_FLUSH_ALL);

	XFS_QM_DQPURGEALL(mp,
		XFS_QMOPT_UQUOTA | XFS_QMOPT_GQUOTA | XFS_QMOPT_UMOUNTING);

	/*
	 * Flush out the log synchronously so that we know for sure
	 * that nothing is pinned.  This is important because bflush()
	 * will skip pinned buffers.
	 */
	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);

	xfs_binval(mp->m_ddev_targp);
	if (mp->m_rtdev_targp) {
		xfs_binval(mp->m_rtdev_targp);
	}

	xfs_unmountfs_writesb(mp);

	xfs_unmountfs_wait(mp); 		/* wait for async bufs */

	xfs_log_unmount(mp);			/* Done! No more fs ops. */

	xfs_freesb(mp);

	/*
	 * All inodes from this mount point should be freed.
	 */
	ASSERT(mp->m_inodes == NULL);

	/*
	 * We may have bufs that are in the process of getting written still.
	 * We must wait for the I/O completion of those. The sync flag here
	 * does a two pass iteration thru the bufcache.
	 */
	if (XFS_FORCED_SHUTDOWN(mp)) {
		xfs_incore_relse(mp->m_ddev_targp, 0, 1); /* synchronous */
	}

	xfs_unmountfs_close(mp, cr);
	if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0)
		xfs_uuid_unmount(mp);

#if defined(DEBUG) || defined(INDUCE_IO_ERROR)
	/*
	 * clear all error tags on this filesystem
	 */
	memcpy(&fsid, &vfsp->vfs_fsid, sizeof(int64_t));
	xfs_errortag_clearall_umount(fsid, mp->m_fsname, 0);
#endif
	XFS_IODONE(vfsp);
	xfs_mount_free(mp, 1);
	return 0;
}

void
xfs_unmountfs_close(xfs_mount_t *mp, struct cred *cr)
{
	if (mp->m_logdev_targp != mp->m_ddev_targp)
		xfs_free_buftarg(mp->m_logdev_targp, 1);
	if (mp->m_rtdev_targp)
		xfs_free_buftarg(mp->m_rtdev_targp, 1);
	xfs_free_buftarg(mp->m_ddev_targp, 0);
}

void
xfs_unmountfs_wait(xfs_mount_t *mp)
{
	if (mp->m_logdev_targp != mp->m_ddev_targp)
		xfs_wait_buftarg(mp->m_logdev_targp);
	if (mp->m_rtdev_targp)
		xfs_wait_buftarg(mp->m_rtdev_targp);
	xfs_wait_buftarg(mp->m_ddev_targp);
}

int
xfs_unmountfs_writesb(xfs_mount_t *mp)
{
	xfs_buf_t	*sbp;
	xfs_sb_t	*sb;
	int		error = 0;

	/*
	 * skip superblock write if fs is read-only, or
	 * if we are doing a forced umount.
	 */
	sbp = xfs_getsb(mp, 0);
	if (!(XFS_MTOVFS(mp)->vfs_flag & VFS_RDONLY ||
		XFS_FORCED_SHUTDOWN(mp))) {
		/*
		 * mark shared-readonly if desired
		 */
		sb = XFS_BUF_TO_SBP(sbp);
		if (mp->m_mk_sharedro) {
			if (!(sb->sb_flags & XFS_SBF_READONLY))
				sb->sb_flags |= XFS_SBF_READONLY;
			if (!XFS_SB_VERSION_HASSHARED(sb))
				XFS_SB_VERSION_ADDSHARED(sb);
			xfs_fs_cmn_err(CE_NOTE, mp,
				"Unmounting, marking shared read-only");
		}
		XFS_BUF_UNDONE(sbp);
		XFS_BUF_UNREAD(sbp);
		XFS_BUF_UNDELAYWRITE(sbp);
		XFS_BUF_WRITE(sbp);
		XFS_BUF_UNASYNC(sbp);
		ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp);
		xfsbdstrat(mp, sbp);
		/* Nevermind errors we might get here. */
		error = xfs_iowait(sbp);
		if (error)
			xfs_ioerror_alert("xfs_unmountfs_writesb",
					  mp, sbp, XFS_BUF_ADDR(sbp));
		if (error && mp->m_mk_sharedro)
			xfs_fs_cmn_err(CE_ALERT, mp, "Superblock write error detected while unmounting.  Filesystem may not be marked shared readonly");
	}
	xfs_buf_relse(sbp);
	return (error);
}

/*
 * xfs_mod_sb() can be used to copy arbitrary changes to the
 * in-core superblock into the superblock buffer to be logged.
 * It does not provide the higher level of locking that is
 * needed to protect the in-core superblock from concurrent
 * access.
 */
void
xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
{
	xfs_buf_t	*bp;
	int		first;
	int		last;
	xfs_mount_t	*mp;
	xfs_sb_t	*sbp;
	xfs_sb_field_t	f;

	ASSERT(fields);
	if (!fields)
		return;
	mp = tp->t_mountp;
	bp = xfs_trans_getsb(tp, mp, 0);
	sbp = XFS_BUF_TO_SBP(bp);
	first = sizeof(xfs_sb_t);
	last = 0;

	/* translate/copy */

	xfs_xlatesb(XFS_BUF_PTR(bp), &(mp->m_sb), -1, fields);

	/* find modified range */

	f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
	first = xfs_sb_info[f].offset;

	f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
	last = xfs_sb_info[f + 1].offset - 1;

	xfs_trans_log_buf(tp, bp, first, last);
}

/*
 * xfs_mod_incore_sb_unlocked() is a utility routine common used to apply
 * a delta to a specified field in the in-core superblock.  Simply
 * switch on the field indicated and apply the delta to that field.
 * Fields are not allowed to dip below zero, so if the delta would
 * do this do not apply it and return EINVAL.
 *
 * The SB_LOCK must be held when this routine is called.
 */
STATIC int
xfs_mod_incore_sb_unlocked(xfs_mount_t *mp, xfs_sb_field_t field,
			int delta, int rsvd)
{
	int		scounter;	/* short counter for 32 bit fields */
	long long	lcounter;	/* long counter for 64 bit fields */
	long long	res_used, rem;

	/*
	 * With the in-core superblock spin lock held, switch
	 * on the indicated field.  Apply the delta to the
	 * proper field.  If the fields value would dip below
	 * 0, then do not apply the delta and return EINVAL.
	 */
	switch (field) {
	case XFS_SBS_ICOUNT:
		lcounter = (long long)mp->m_sb.sb_icount;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_icount = lcounter;
		return (0);
	case XFS_SBS_IFREE:
		lcounter = (long long)mp->m_sb.sb_ifree;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_ifree = lcounter;
		return (0);
	case XFS_SBS_FDBLOCKS:

		lcounter = (long long)mp->m_sb.sb_fdblocks;
		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);

		if (delta > 0) {		/* Putting blocks back */
			if (res_used > delta) {
				mp->m_resblks_avail += delta;
			} else {
				rem = delta - res_used;
				mp->m_resblks_avail = mp->m_resblks;
				lcounter += rem;
			}
		} else {				/* Taking blocks away */

			lcounter += delta;

		/*
		 * If were out of blocks, use any available reserved blocks if
		 * were allowed to.
		 */

			if (lcounter < 0) {
				if (rsvd) {
					lcounter = (long long)mp->m_resblks_avail + delta;
					if (lcounter < 0) {
						return (XFS_ERROR(ENOSPC));
					}
					mp->m_resblks_avail = lcounter;
					return (0);
				} else {	/* not reserved */
					return (XFS_ERROR(ENOSPC));
				}
			}
		}

		mp->m_sb.sb_fdblocks = lcounter;
		return (0);
	case XFS_SBS_FREXTENTS:
		lcounter = (long long)mp->m_sb.sb_frextents;
		lcounter += delta;
		if (lcounter < 0) {
			return (XFS_ERROR(ENOSPC));
		}
		mp->m_sb.sb_frextents = lcounter;
		return (0);
	case XFS_SBS_DBLOCKS:
		lcounter = (long long)mp->m_sb.sb_dblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_dblocks = lcounter;
		return (0);
	case XFS_SBS_AGCOUNT:
		scounter = mp->m_sb.sb_agcount;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_agcount = scounter;
		return (0);
	case XFS_SBS_IMAX_PCT:
		scounter = mp->m_sb.sb_imax_pct;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_imax_pct = scounter;
		return (0);
	case XFS_SBS_REXTSIZE:
		scounter = mp->m_sb.sb_rextsize;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_rextsize = scounter;
		return (0);
	case XFS_SBS_RBMBLOCKS:
		scounter = mp->m_sb.sb_rbmblocks;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_rbmblocks = scounter;
		return (0);
	case XFS_SBS_RBLOCKS:
		lcounter = (long long)mp->m_sb.sb_rblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_rblocks = lcounter;
		return (0);
	case XFS_SBS_REXTENTS:
		lcounter = (long long)mp->m_sb.sb_rextents;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_rextents = lcounter;
		return (0);
	case XFS_SBS_REXTSLOG:
		scounter = mp->m_sb.sb_rextslog;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return (XFS_ERROR(EINVAL));
		}
		mp->m_sb.sb_rextslog = scounter;
		return (0);
	default:
		ASSERT(0);
		return (XFS_ERROR(EINVAL));
	}
}

/*
 * xfs_mod_incore_sb() is used to change a field in the in-core
 * superblock structure by the specified delta.  This modification
 * is protected by the SB_LOCK.  Just use the xfs_mod_incore_sb_unlocked()
 * routine to do the work.
 */
int
xfs_mod_incore_sb(xfs_mount_t *mp, xfs_sb_field_t field, int delta, int rsvd)
{
	unsigned long	s;
	int	status;

	s = XFS_SB_LOCK(mp);
	status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
	XFS_SB_UNLOCK(mp, s);
	return (status);
}

/*
 * xfs_mod_incore_sb_batch() is used to change more than one field
 * in the in-core superblock structure at a time.  This modification
 * is protected by a lock internal to this module.  The fields and
 * changes to those fields are specified in the array of xfs_mod_sb
 * structures passed in.
 *
 * Either all of the specified deltas will be applied or none of
 * them will.  If any modified field dips below 0, then all modifications
 * will be backed out and EINVAL will be returned.
 */
int
xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd)
{
	unsigned long	s;
	int		status=0;
	xfs_mod_sb_t	*msbp;

	/*
	 * Loop through the array of mod structures and apply each
	 * individually.  If any fail, then back out all those
	 * which have already been applied.  Do all of this within
	 * the scope of the SB_LOCK so that all of the changes will
	 * be atomic.
	 */
	s = XFS_SB_LOCK(mp);
	msbp = &msb[0];
	for (msbp = &msbp[0]; msbp < (msb + nmsb); msbp++) {
		/*
		 * Apply the delta at index n.  If it fails, break
		 * from the loop so we'll fall into the undo loop
		 * below.
		 */
		status = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
						    msbp->msb_delta, rsvd);
		if (status != 0) {
			break;
		}
	}

	/*
	 * If we didn't complete the loop above, then back out
	 * any changes made to the superblock.  If you add code
	 * between the loop above and here, make sure that you
	 * preserve the value of status. Loop back until
	 * we step below the beginning of the array.  Make sure
	 * we don't touch anything back there.
	 */
	if (status != 0) {
		msbp--;
		while (msbp >= msb) {
			status = xfs_mod_incore_sb_unlocked(mp,
				    msbp->msb_field, -(msbp->msb_delta), rsvd);
			ASSERT(status == 0);
			msbp--;
		}
	}
	XFS_SB_UNLOCK(mp, s);
	return (status);
}

/*
 * xfs_getsb() is called to obtain the buffer for the superblock.
 * The buffer is returned locked and read in from disk.
 * The buffer should be released with a call to xfs_brelse().
 *
 * If the flags parameter is BUF_TRYLOCK, then we'll only return
 * the superblock buffer if it can be locked without sleeping.
 * If it can't then we'll return NULL.
 */
xfs_buf_t *
xfs_getsb(
	xfs_mount_t	*mp,
	int		flags)
{
	xfs_buf_t	*bp;

	ASSERT(mp->m_sb_bp != NULL);
	bp = mp->m_sb_bp;
	if (flags & XFS_BUF_TRYLOCK) {
		if (!XFS_BUF_CPSEMA(bp)) {
			return NULL;
		}
	} else {
		XFS_BUF_PSEMA(bp, PRIBIO);
	}
	XFS_BUF_HOLD(bp);
	ASSERT(XFS_BUF_ISDONE(bp));
	return (bp);
}

/*
 * Used to free the superblock along various error paths.
 */
void
xfs_freesb(
	xfs_mount_t	*mp)
{
	xfs_buf_t	*bp;

	/*
	 * Use xfs_getsb() so that the buffer will be locked
	 * when we call xfs_buf_relse().
	 */
	bp = xfs_getsb(mp, 0);
	XFS_BUF_UNMANAGE(bp);
	xfs_buf_relse(bp);
	mp->m_sb_bp = NULL;
}

/*
 * See if the UUID is unique among mounted XFS filesystems.
 * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
 */
STATIC int
xfs_uuid_mount(
	xfs_mount_t	*mp)
{
	if (uuid_is_nil(&mp->m_sb.sb_uuid)) {
		cmn_err(CE_WARN,
			"XFS: Filesystem %s has nil UUID - can't mount",
			mp->m_fsname);
		return -1;
	}
	if (!uuid_table_insert(&mp->m_sb.sb_uuid)) {
		cmn_err(CE_WARN,
			"XFS: Filesystem %s has duplicate UUID - can't mount",
			mp->m_fsname);
		return -1;
	}
	return 0;
}

/*
 * Remove filesystem from the UUID table.
 */
STATIC void
xfs_uuid_unmount(
	xfs_mount_t	*mp)
{
	uuid_table_remove(&mp->m_sb.sb_uuid);
}

/*
 * Used to log changes to the superblock unit and width fields which could
 * be altered by the mount options. Only the first superblock is updated.
 */
STATIC void
xfs_mount_log_sbunit(
	xfs_mount_t	*mp,
	__int64_t	fields)
{
	xfs_trans_t	*tp;

	ASSERT(fields & (XFS_SB_UNIT|XFS_SB_WIDTH|XFS_SB_UUID));

	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
	if (xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
				XFS_DEFAULT_LOG_COUNT)) {
		xfs_trans_cancel(tp, 0);
		return;
	}
	xfs_mod_sb(tp, fields);
	xfs_trans_commit(tp, 0, NULL);
}