aboutsummaryrefslogtreecommitdiff
path: root/sys/ufs/ffs/ffs_vfsops.c
blob: c261e179973a4d0d96a1fa29b9d3676b041d1901 (plain) (blame)
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
/*
 * Copyright (c) 1989, 1991, 1993, 1994
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)ffs_vfsops.c	8.31 (Berkeley) 5/20/95
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_mac.h"
#include "opt_quota.h"
#include "opt_ufs.h"
#include "opt_ffs.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/namei.h>
#include <sys/proc.h>
#include <sys/kernel.h>
#include <sys/mac.h>
#include <sys/vnode.h>
#include <sys/mount.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/conf.h>
#include <sys/fcntl.h>
#include <sys/disk.h>
#include <sys/malloc.h>
#include <sys/mutex.h>

#include <ufs/ufs/extattr.h>
#include <ufs/ufs/quota.h>
#include <ufs/ufs/ufsmount.h>
#include <ufs/ufs/inode.h>
#include <ufs/ufs/ufs_extern.h>

#include <ufs/ffs/fs.h>
#include <ufs/ffs/ffs_extern.h>

#include <vm/vm.h>
#include <vm/uma.h>
#include <vm/vm_page.h>

#include <geom/geom.h>
#include <geom/geom_vfs.h>

uma_zone_t uma_inode, uma_ufs1, uma_ufs2;

static int	ffs_sbupdate(struct ufsmount *, int);
static int	ffs_reload(struct mount *, struct thread *);
static int	ffs_mountfs(struct vnode *, struct mount *, struct thread *);
static void	ffs_oldfscompat_read(struct fs *, struct ufsmount *,
		    ufs2_daddr_t);
static void	ffs_oldfscompat_write(struct fs *, struct ufsmount *);
static void	ffs_ifree(struct ufsmount *ump, struct inode *ip);
static vfs_init_t ffs_init;
static vfs_uninit_t ffs_uninit;
static vfs_extattrctl_t ffs_extattrctl;
static vfs_cmount_t ffs_cmount;
static vfs_mount_t ffs_mount;

static struct vfsops ufs_vfsops = {
	.vfs_extattrctl =	ffs_extattrctl,
	.vfs_fhtovp =		ffs_fhtovp,
	.vfs_init =		ffs_init,
	.vfs_mount =		ffs_mount,
	.vfs_cmount =		ffs_cmount,
	.vfs_quotactl =		ufs_quotactl,
	.vfs_root =		ufs_root,
	.vfs_statfs =		ffs_statfs,
	.vfs_sync =		ffs_sync,
	.vfs_uninit =		ffs_uninit,
	.vfs_unmount =		ffs_unmount,
	.vfs_vget =		ffs_vget,
	.vfs_vptofh =		ffs_vptofh,
};

VFS_SET(ufs_vfsops, ufs, 0);

static b_strategy_t ffs_geom_strategy;

static struct buf_ops ffs_ops = {
	.bop_name =	"FFS",
	.bop_write =	bufwrite,
	.bop_strategy =	ffs_geom_strategy,
};

static const char *ffs_opts[] = { "from", "export", NULL };

static int
ffs_mount(struct mount *mp, struct thread *td)
{
	struct vnode *devvp;
	struct ufsmount *ump = 0;
	struct fs *fs;
	int error, flags;
	mode_t accessmode;
	struct nameidata ndp;
	struct export_args export;
	char *fspec;

	if (vfs_filteropt(mp->mnt_optnew, ffs_opts))
		return (EINVAL);
	if (uma_inode == NULL) {
		uma_inode = uma_zcreate("FFS inode",
		    sizeof(struct inode), NULL, NULL, NULL, NULL,
		    UMA_ALIGN_PTR, 0);
		uma_ufs1 = uma_zcreate("FFS1 dinode",
		    sizeof(struct ufs1_dinode), NULL, NULL, NULL, NULL,
		    UMA_ALIGN_PTR, 0);
		uma_ufs2 = uma_zcreate("FFS2 dinode",
		    sizeof(struct ufs2_dinode), NULL, NULL, NULL, NULL,
		    UMA_ALIGN_PTR, 0);
	}

	fspec = vfs_getopts(mp->mnt_optnew, "from", &error);
	if (error)
		return (error);

	/*
	 * If updating, check whether changing from read-only to
	 * read/write; if there is no device name, that's all we do.
	 */
	if (mp->mnt_flag & MNT_UPDATE) {
		ump = VFSTOUFS(mp);
		fs = ump->um_fs;
		devvp = ump->um_devvp;
		if (fs->fs_ronly == 0 &&
		    vfs_flagopt(mp->mnt_optnew, "ro", NULL, 0)) {
			if ((error = vn_start_write(NULL, &mp, V_WAIT)) != 0)
				return (error);
			/*
			 * Flush any dirty data.
			 */
			if ((error = VFS_SYNC(mp, MNT_WAIT,
			    td->td_ucred, td)) != 0) {
				vn_finished_write(mp);
				return (error);
			}
			/*
			 * Check for and optionally get rid of files open
			 * for writing.
			 */
			flags = WRITECLOSE;
			if (mp->mnt_flag & MNT_FORCE)
				flags |= FORCECLOSE;
			if (mp->mnt_flag & MNT_SOFTDEP) {
				error = softdep_flushfiles(mp, flags, td);
			} else {
				error = ffs_flushfiles(mp, flags, td);
			}
			if (error) {
				vn_finished_write(mp);
				return (error);
			}
			if (fs->fs_pendingblocks != 0 ||
			    fs->fs_pendinginodes != 0) {
				printf("%s: %s: blocks %jd files %d\n",
				    fs->fs_fsmnt, "update error",
				    (intmax_t)fs->fs_pendingblocks,
				    fs->fs_pendinginodes);
				fs->fs_pendingblocks = 0;
				fs->fs_pendinginodes = 0;
			}
			if ((fs->fs_flags & (FS_UNCLEAN | FS_NEEDSFSCK)) == 0)
				fs->fs_clean = 1;
			if ((error = ffs_sbupdate(ump, MNT_WAIT)) != 0) {
				fs->fs_ronly = 0;
				fs->fs_clean = 0;
				vn_finished_write(mp);
				return (error);
			}
			vn_finished_write(mp);
			DROP_GIANT();
			g_topology_lock();
			g_access(ump->um_cp, 0, -1, 0);
			g_topology_unlock();
			PICKUP_GIANT();
			fs->fs_ronly = 1;
			mp->mnt_flag |= MNT_RDONLY;
		}
		if ((mp->mnt_flag & MNT_RELOAD) &&
		    (error = ffs_reload(mp, td)) != 0)
			return (error);
		if (fs->fs_ronly &&
		    !vfs_flagopt(mp->mnt_optnew, "ro", NULL, 0)) {
			/*
			 * If upgrade to read-write by non-root, then verify
			 * that user has necessary permissions on the device.
			 */
			if (suser(td)) {
				vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY, td);
				if ((error = VOP_ACCESS(devvp, VREAD | VWRITE,
				    td->td_ucred, td)) != 0) {
					VOP_UNLOCK(devvp, 0, td);
					return (error);
				}
				VOP_UNLOCK(devvp, 0, td);
			}
			fs->fs_flags &= ~FS_UNCLEAN;
			if (fs->fs_clean == 0) {
				fs->fs_flags |= FS_UNCLEAN;
				if ((mp->mnt_flag & MNT_FORCE) ||
				    ((fs->fs_flags & FS_NEEDSFSCK) == 0 &&
				     (fs->fs_flags & FS_DOSOFTDEP))) {
					printf("WARNING: %s was not %s\n",
					   fs->fs_fsmnt, "properly dismounted");
				} else {
					printf(
"WARNING: R/W mount of %s denied.  Filesystem is not clean - run fsck\n",
					    fs->fs_fsmnt);
					return (EPERM);
				}
			}
			DROP_GIANT();
			g_topology_lock();
			/*
			 * If we're the root device, we may not have an E count
			 * yet, get it now.
			 */
			if (ump->um_cp->ace == 0)
				error = g_access(ump->um_cp, 0, 1, 1);
			else
				error = g_access(ump->um_cp, 0, 1, 0);
			g_topology_unlock();
			PICKUP_GIANT();
			if (error)
				return (error);
			if ((error = vn_start_write(NULL, &mp, V_WAIT)) != 0)
				return (error);
			fs->fs_ronly = 0;
			mp->mnt_flag &= ~MNT_RDONLY;
			fs->fs_clean = 0;
			if ((error = ffs_sbupdate(ump, MNT_WAIT)) != 0) {
				vn_finished_write(mp);
				return (error);
			}
			/* check to see if we need to start softdep */
			if ((fs->fs_flags & FS_DOSOFTDEP) &&
			    (error = softdep_mount(devvp, mp, fs, td->td_ucred))){
				vn_finished_write(mp);
				return (error);
			}
			if (fs->fs_snapinum[0] != 0)
				ffs_snapshot_mount(mp);
			vn_finished_write(mp);
		}
		/*
		 * Soft updates is incompatible with "async",
		 * so if we are doing softupdates stop the user
		 * from setting the async flag in an update.
		 * Softdep_mount() clears it in an initial mount 
		 * or ro->rw remount.
		 */
		if (mp->mnt_flag & MNT_SOFTDEP)
			mp->mnt_flag &= ~MNT_ASYNC;
		/*
		 * If not updating name, process export requests.
		 */
		error = vfs_copyopt(mp->mnt_optnew, "export", &export, sizeof export);
		if (error == 0 && export.ex_flags != 0)
			return (vfs_export(mp, &export));
		/*
		 * If this is a snapshot request, take the snapshot.
		 */
		if (mp->mnt_flag & MNT_SNAPSHOT)
			return (ffs_snapshot(mp, fspec));
	}

	/*
	 * Not an update, or updating the name: look up the name
	 * and verify that it refers to a sensible disk device.
	 */
	NDINIT(&ndp, LOOKUP, FOLLOW, UIO_SYSSPACE, fspec, td);
	if ((error = namei(&ndp)) != 0)
		return (error);
	NDFREE(&ndp, NDF_ONLY_PNBUF);
	devvp = ndp.ni_vp;
	if (!vn_isdisk(devvp, &error)) {
		vrele(devvp);
		return (error);
	}

	/*
	 * If mount by non-root, then verify that user has necessary
	 * permissions on the device.
	 */
	if (suser(td)) {
		accessmode = VREAD;
		if ((mp->mnt_flag & MNT_RDONLY) == 0)
			accessmode |= VWRITE;
		vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY, td);
		if ((error = VOP_ACCESS(devvp, accessmode, td->td_ucred, td))!= 0){
			vput(devvp);
			return (error);
		}
		VOP_UNLOCK(devvp, 0, td);
	}

	if (mp->mnt_flag & MNT_UPDATE) {
		/*
		 * Update only
		 *
		 * If it's not the same vnode, or at least the same device
		 * then it's not correct.
		 */

		if (devvp->v_rdev != ump->um_devvp->v_rdev)
			error = EINVAL;	/* needs translation */
		vrele(devvp);
		if (error)
			return (error);
	} else {
		/*
		 * New mount
		 *
		 * We need the name for the mount point (also used for
		 * "last mounted on") copied in. If an error occurs,
		 * the mount point is discarded by the upper level code.
		 * Note that vfs_mount() populates f_mntonname for us.
		 */
		if ((error = ffs_mountfs(devvp, mp, td)) != 0) {
			vrele(devvp);
			return (error);
		}
	}
	vfs_mountedfrom(mp, fspec);
	return (0);
}

/*
 * Compatibility with old mount system call.
 */

static int
ffs_cmount(struct mntarg *ma, void *data, int flags, struct thread *td)
{
	struct ufs_args args;
	int error;

	if (data == NULL)
		return (EINVAL);
	error = copyin(data, &args, sizeof args);
	if (error)
		return (error);

	ma = mount_argsu(ma, "from", args.fspec, MAXPATHLEN);
	ma = mount_arg(ma, "export", &args.export, sizeof args.export);
	error = kernel_mount(ma, flags);

	return (error);
}

/*
 * Reload all incore data for a filesystem (used after running fsck on
 * the root filesystem and finding things to fix). The filesystem must
 * be mounted read-only.
 *
 * Things to do to update the mount:
 *	1) invalidate all cached meta-data.
 *	2) re-read superblock from disk.
 *	3) re-read summary information from disk.
 *	4) invalidate all inactive vnodes.
 *	5) invalidate all cached file data.
 *	6) re-read inode data for all active vnodes.
 */
static int
ffs_reload(struct mount *mp, struct thread *td)
{
	struct vnode *vp, *nvp, *devvp;
	struct inode *ip;
	void *space;
	struct buf *bp;
	struct fs *fs, *newfs;
	ufs2_daddr_t sblockloc;
	int i, blks, size, error;
	int32_t *lp;

	if ((mp->mnt_flag & MNT_RDONLY) == 0)
		return (EINVAL);
	/*
	 * Step 1: invalidate all cached meta-data.
	 */
	devvp = VFSTOUFS(mp)->um_devvp;
	vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY, td);
	if (vinvalbuf(devvp, 0, td->td_ucred, td, 0, 0) != 0)
		panic("ffs_reload: dirty1");
	vfs_object_create(devvp, td, td->td_ucred);
	VOP_UNLOCK(devvp, 0, td);

	/*
	 * Step 2: re-read superblock from disk.
	 */
	fs = VFSTOUFS(mp)->um_fs;
	if ((error = bread(devvp, btodb(fs->fs_sblockloc), fs->fs_sbsize,
	    NOCRED, &bp)) != 0)
		return (error);
	newfs = (struct fs *)bp->b_data;
	if ((newfs->fs_magic != FS_UFS1_MAGIC &&
	     newfs->fs_magic != FS_UFS2_MAGIC) ||
	    newfs->fs_bsize > MAXBSIZE ||
	    newfs->fs_bsize < sizeof(struct fs)) {
			brelse(bp);
			return (EIO);		/* XXX needs translation */
	}
	/*
	 * Copy pointer fields back into superblock before copying in	XXX
	 * new superblock. These should really be in the ufsmount.	XXX
	 * Note that important parameters (eg fs_ncg) are unchanged.
	 */
	newfs->fs_csp = fs->fs_csp;
	newfs->fs_maxcluster = fs->fs_maxcluster;
	newfs->fs_contigdirs = fs->fs_contigdirs;
	newfs->fs_active = fs->fs_active;
	/* The file system is still read-only. */
	newfs->fs_ronly = 1;
	sblockloc = fs->fs_sblockloc;
	bcopy(newfs, fs, (u_int)fs->fs_sbsize);
	brelse(bp);
	mp->mnt_maxsymlinklen = fs->fs_maxsymlinklen;
	ffs_oldfscompat_read(fs, VFSTOUFS(mp), sblockloc);
	if (fs->fs_pendingblocks != 0 || fs->fs_pendinginodes != 0) {
		printf("%s: reload pending error: blocks %jd files %d\n",
		    fs->fs_fsmnt, (intmax_t)fs->fs_pendingblocks,
		    fs->fs_pendinginodes);
		fs->fs_pendingblocks = 0;
		fs->fs_pendinginodes = 0;
	}

	/*
	 * Step 3: re-read summary information from disk.
	 */
	blks = howmany(fs->fs_cssize, fs->fs_fsize);
	space = fs->fs_csp;
	for (i = 0; i < blks; i += fs->fs_frag) {
		size = fs->fs_bsize;
		if (i + fs->fs_frag > blks)
			size = (blks - i) * fs->fs_fsize;
		error = bread(devvp, fsbtodb(fs, fs->fs_csaddr + i), size,
		    NOCRED, &bp);
		if (error)
			return (error);
		bcopy(bp->b_data, space, (u_int)size);
		space = (char *)space + size;
		brelse(bp);
	}
	/*
	 * We no longer know anything about clusters per cylinder group.
	 */
	if (fs->fs_contigsumsize > 0) {
		lp = fs->fs_maxcluster;
		for (i = 0; i < fs->fs_ncg; i++)
			*lp++ = fs->fs_contigsumsize;
	}

loop:
	MNT_ILOCK(mp);
	MNT_VNODE_FOREACH(vp, mp, nvp) {
		VI_LOCK(vp);
		if (vp->v_iflag & VI_XLOCK) {
			VI_UNLOCK(vp);
			continue;
		}
		MNT_IUNLOCK(mp);
		/*
		 * Step 4: invalidate all inactive vnodes.
		 */
		if (vp->v_usecount == 0) {
			vgonel(vp, td);
			goto loop;
		}
		/*
		 * Step 5: invalidate all cached file data.
		 */
		if (vget(vp, LK_EXCLUSIVE | LK_INTERLOCK, td)) {
			goto loop;
		}
		if (vinvalbuf(vp, 0, td->td_ucred, td, 0, 0))
			panic("ffs_reload: dirty2");
		/*
		 * Step 6: re-read inode data for all active vnodes.
		 */
		ip = VTOI(vp);
		error =
		    bread(devvp, fsbtodb(fs, ino_to_fsba(fs, ip->i_number)),
		    (int)fs->fs_bsize, NOCRED, &bp);
		if (error) {
			VOP_UNLOCK(vp, 0, td);
			vrele(vp);
			return (error);
		}
		ffs_load_inode(bp, ip, fs, ip->i_number);
		ip->i_effnlink = ip->i_nlink;
		brelse(bp);
		VOP_UNLOCK(vp, 0, td);
		vrele(vp);
		MNT_ILOCK(mp);
	}
	MNT_IUNLOCK(mp);
	return (0);
}

/*
 * Possible superblock locations ordered from most to least likely.
 */
static int sblock_try[] = SBLOCKSEARCH;

/*
 * Common code for mount and mountroot
 */
static int
ffs_mountfs(devvp, mp, td)
	struct vnode *devvp;
	struct mount *mp;
	struct thread *td;
{
	struct ufsmount *ump;
	struct buf *bp;
	struct fs *fs;
	struct cdev *dev;
	void *space;
	ufs2_daddr_t sblockloc;
	int error, i, blks, size, ronly;
	int32_t *lp;
	struct ucred *cred;
	struct g_consumer *cp;

	dev = devvp->v_rdev;
	cred = td ? td->td_ucred : NOCRED;

	vfs_object_create(devvp, td, td->td_ucred);
	ronly = (mp->mnt_flag & MNT_RDONLY) != 0;
	DROP_GIANT();
	g_topology_lock();
	error = g_vfs_open(devvp, &cp, "ffs", ronly ? 0 : 1);

	/*
	 * If we are a root mount, drop the E flag so fsck can do its magic.
	 * We will pick it up again when we remount R/W.
	 */
	if (error == 0 && ronly && (mp->mnt_flag & MNT_ROOTFS))
		error = g_access(cp, 0, 0, -1);
	g_topology_unlock();
	PICKUP_GIANT();
	VOP_UNLOCK(devvp, 0, td);
	if (error)
		return (error);
	if (devvp->v_rdev->si_iosize_max != 0)
		mp->mnt_iosize_max = devvp->v_rdev->si_iosize_max;
	if (mp->mnt_iosize_max > MAXPHYS)
		mp->mnt_iosize_max = MAXPHYS;

	devvp->v_bufobj.bo_private = cp;
	devvp->v_bufobj.bo_ops = &ffs_ops;

	bp = NULL;
	ump = NULL;
	fs = NULL;
	sblockloc = 0;
	/*
	 * Try reading the superblock in each of its possible locations.
	 */
	for (i = 0; sblock_try[i] != -1; i++) {
		if ((error = bread(devvp, sblock_try[i] / DEV_BSIZE, SBLOCKSIZE,
		    cred, &bp)) != 0)
			goto out;
		fs = (struct fs *)bp->b_data;
		sblockloc = sblock_try[i];
		if ((fs->fs_magic == FS_UFS1_MAGIC ||
		     (fs->fs_magic == FS_UFS2_MAGIC &&
		      (fs->fs_sblockloc == sblockloc ||
		       (fs->fs_old_flags & FS_FLAGS_UPDATED) == 0))) &&
		    fs->fs_bsize <= MAXBSIZE &&
		    fs->fs_bsize >= sizeof(struct fs))
			break;
		brelse(bp);
		bp = NULL;
	}
	if (sblock_try[i] == -1) {
		error = EINVAL;		/* XXX needs translation */
		goto out;
	}
	fs->fs_fmod = 0;
	fs->fs_flags &= ~FS_INDEXDIRS;	/* no support for directory indicies */
	fs->fs_flags &= ~FS_UNCLEAN;
	if (fs->fs_clean == 0) {
		fs->fs_flags |= FS_UNCLEAN;
		if (ronly || (mp->mnt_flag & MNT_FORCE) ||
		    ((fs->fs_flags & FS_NEEDSFSCK) == 0 &&
		     (fs->fs_flags & FS_DOSOFTDEP))) {
			printf(
"WARNING: %s was not properly dismounted\n",
			    fs->fs_fsmnt);
		} else {
			printf(
"WARNING: R/W mount of %s denied.  Filesystem is not clean - run fsck\n",
			    fs->fs_fsmnt);
			error = EPERM;
			goto out;
		}
		if ((fs->fs_pendingblocks != 0 || fs->fs_pendinginodes != 0) &&
		    (mp->mnt_flag & MNT_FORCE)) {
			printf("%s: lost blocks %jd files %d\n", fs->fs_fsmnt,
			    (intmax_t)fs->fs_pendingblocks,
			    fs->fs_pendinginodes);
			fs->fs_pendingblocks = 0;
			fs->fs_pendinginodes = 0;
		}
	}
	if (fs->fs_pendingblocks != 0 || fs->fs_pendinginodes != 0) {
		printf("%s: mount pending error: blocks %jd files %d\n",
		    fs->fs_fsmnt, (intmax_t)fs->fs_pendingblocks,
		    fs->fs_pendinginodes);
		fs->fs_pendingblocks = 0;
		fs->fs_pendinginodes = 0;
	}
	ump = malloc(sizeof *ump, M_UFSMNT, M_WAITOK | M_ZERO);
	ump->um_cp = cp;
	ump->um_bo = &devvp->v_bufobj;
	ump->um_fs = malloc((u_long)fs->fs_sbsize, M_UFSMNT, M_WAITOK);
	if (fs->fs_magic == FS_UFS1_MAGIC) {
		ump->um_fstype = UFS1;
		ump->um_balloc = ffs_balloc_ufs1;
	} else {
		ump->um_fstype = UFS2;
		ump->um_balloc = ffs_balloc_ufs2;
	}
	ump->um_blkatoff = ffs_blkatoff;
	ump->um_truncate = ffs_truncate;
	ump->um_update = ffs_update;
	ump->um_valloc = ffs_valloc;
	ump->um_vfree = ffs_vfree;
	ump->um_ifree = ffs_ifree;
	bcopy(bp->b_data, ump->um_fs, (u_int)fs->fs_sbsize);
	if (fs->fs_sbsize < SBLOCKSIZE)
		bp->b_flags |= B_INVAL | B_NOCACHE;
	brelse(bp);
	bp = NULL;
	fs = ump->um_fs;
	ffs_oldfscompat_read(fs, ump, sblockloc);
	fs->fs_ronly = ronly;
	size = fs->fs_cssize;
	blks = howmany(size, fs->fs_fsize);
	if (fs->fs_contigsumsize > 0)
		size += fs->fs_ncg * sizeof(int32_t);
	size += fs->fs_ncg * sizeof(u_int8_t);
	space = malloc((u_long)size, M_UFSMNT, M_WAITOK);
	fs->fs_csp = space;
	for (i = 0; i < blks; i += fs->fs_frag) {
		size = fs->fs_bsize;
		if (i + fs->fs_frag > blks)
			size = (blks - i) * fs->fs_fsize;
		if ((error = bread(devvp, fsbtodb(fs, fs->fs_csaddr + i), size,
		    cred, &bp)) != 0) {
			free(fs->fs_csp, M_UFSMNT);
			goto out;
		}
		bcopy(bp->b_data, space, (u_int)size);
		space = (char *)space + size;
		brelse(bp);
		bp = NULL;
	}
	if (fs->fs_contigsumsize > 0) {
		fs->fs_maxcluster = lp = space;
		for (i = 0; i < fs->fs_ncg; i++)
			*lp++ = fs->fs_contigsumsize;
		space = lp;
	}
	size = fs->fs_ncg * sizeof(u_int8_t);
	fs->fs_contigdirs = (u_int8_t *)space;
	bzero(fs->fs_contigdirs, size);
	fs->fs_active = NULL;
	mp->mnt_data = (qaddr_t)ump;
	mp->mnt_stat.f_fsid.val[0] = fs->fs_id[0];
	mp->mnt_stat.f_fsid.val[1] = fs->fs_id[1];
	if (fs->fs_id[0] == 0 || fs->fs_id[1] == 0 || 
	    vfs_getvfs(&mp->mnt_stat.f_fsid)) 
		vfs_getnewfsid(mp);
	mp->mnt_maxsymlinklen = fs->fs_maxsymlinklen;
	mp->mnt_flag |= MNT_LOCAL;
	if ((fs->fs_flags & FS_MULTILABEL) != 0)
#ifdef MAC
		mp->mnt_flag |= MNT_MULTILABEL;
#else
		printf(
"WARNING: %s: multilabel flag on fs but no MAC support\n",
		    fs->fs_fsmnt);
#endif
	if ((fs->fs_flags & FS_ACLS) != 0)
#ifdef UFS_ACL
		mp->mnt_flag |= MNT_ACLS;
#else
		printf(
"WARNING: %s: ACLs flag on fs but no ACLs support\n",
		    fs->fs_fsmnt);
#endif
	ump->um_mountp = mp;
	ump->um_dev = dev;
	ump->um_devvp = devvp;
	ump->um_nindir = fs->fs_nindir;
	ump->um_bptrtodb = fs->fs_fsbtodb;
	ump->um_seqinc = fs->fs_frag;
	for (i = 0; i < MAXQUOTAS; i++)
		ump->um_quotas[i] = NULLVP;
#ifdef UFS_EXTATTR
	ufs_extattr_uepm_init(&ump->um_extattr);
#endif
	/*
	 * Set FS local "last mounted on" information (NULL pad)
	 */
	vfs_mountedfrom(mp, fs->fs_fsmnt);

	if( mp->mnt_flag & MNT_ROOTFS) {
		/*
		 * Root mount; update timestamp in mount structure.
		 * this will be used by the common root mount code
		 * to update the system clock.
		 */
		mp->mnt_time = fs->fs_time;
	}

	if (ronly == 0) {
		if ((fs->fs_flags & FS_DOSOFTDEP) &&
		    (error = softdep_mount(devvp, mp, fs, cred)) != 0) {
			free(fs->fs_csp, M_UFSMNT);
			goto out;
		}
		if (fs->fs_snapinum[0] != 0)
			ffs_snapshot_mount(mp);
		fs->fs_fmod = 1;
		fs->fs_clean = 0;
		(void) ffs_sbupdate(ump, MNT_WAIT);
	}
	/*
	 * Initialize filesystem stat information in mount struct.
	 */
#ifdef UFS_EXTATTR
#ifdef UFS_EXTATTR_AUTOSTART
	/*
	 *
	 * Auto-starting does the following:
	 *	- check for /.attribute in the fs, and extattr_start if so
	 *	- for each file in .attribute, enable that file with
	 * 	  an attribute of the same name.
	 * Not clear how to report errors -- probably eat them.
	 * This would all happen while the filesystem was busy/not
	 * available, so would effectively be "atomic".
	 */
	(void) ufs_extattr_autostart(mp, td);
#endif /* !UFS_EXTATTR_AUTOSTART */
#endif /* !UFS_EXTATTR */
	return (0);
out:
	if (bp)
		brelse(bp);
	vinvalbuf(devvp, V_SAVE, NOCRED, td, 0, 0);
	if (cp != NULL) {
		DROP_GIANT();
		g_topology_lock();
		g_wither_geom_close(cp->geom, ENXIO);
		g_topology_unlock();
		PICKUP_GIANT();
	}
	if (ump) {
		free(ump->um_fs, M_UFSMNT);
		free(ump, M_UFSMNT);
		mp->mnt_data = (qaddr_t)0;
	}
	return (error);
}

#include <sys/sysctl.h>
int bigcgs = 0;
SYSCTL_INT(_debug, OID_AUTO, bigcgs, CTLFLAG_RW, &bigcgs, 0, "");

/*
 * Sanity checks for loading old filesystem superblocks.
 * See ffs_oldfscompat_write below for unwound actions.
 *
 * XXX - Parts get retired eventually.
 * Unfortunately new bits get added.
 */
static void
ffs_oldfscompat_read(fs, ump, sblockloc)
	struct fs *fs;
	struct ufsmount *ump;
	ufs2_daddr_t sblockloc;
{
	off_t maxfilesize;

	/*
	 * If not yet done, update fs_flags location and value of fs_sblockloc.
	 */
	if ((fs->fs_old_flags & FS_FLAGS_UPDATED) == 0) {
		fs->fs_flags = fs->fs_old_flags;
		fs->fs_old_flags |= FS_FLAGS_UPDATED;
		fs->fs_sblockloc = sblockloc;
	}
	/*
	 * If not yet done, update UFS1 superblock with new wider fields.
	 */
	if (fs->fs_magic == FS_UFS1_MAGIC && fs->fs_maxbsize != fs->fs_bsize) {
		fs->fs_maxbsize = fs->fs_bsize;
		fs->fs_time = fs->fs_old_time;
		fs->fs_size = fs->fs_old_size;
		fs->fs_dsize = fs->fs_old_dsize;
		fs->fs_csaddr = fs->fs_old_csaddr;
		fs->fs_cstotal.cs_ndir = fs->fs_old_cstotal.cs_ndir;
		fs->fs_cstotal.cs_nbfree = fs->fs_old_cstotal.cs_nbfree;
		fs->fs_cstotal.cs_nifree = fs->fs_old_cstotal.cs_nifree;
		fs->fs_cstotal.cs_nffree = fs->fs_old_cstotal.cs_nffree;
	}
	if (fs->fs_magic == FS_UFS1_MAGIC &&
	    fs->fs_old_inodefmt < FS_44INODEFMT) {
		fs->fs_maxfilesize = (u_quad_t) 1LL << 39;
		fs->fs_qbmask = ~fs->fs_bmask;
		fs->fs_qfmask = ~fs->fs_fmask;
	}
	if (fs->fs_magic == FS_UFS1_MAGIC) {
		ump->um_savedmaxfilesize = fs->fs_maxfilesize;
		maxfilesize = (u_int64_t)0x40000000 * fs->fs_bsize - 1;
		if (fs->fs_maxfilesize > maxfilesize)
			fs->fs_maxfilesize = maxfilesize;
	}
	/* Compatibility for old filesystems */
	if (fs->fs_avgfilesize <= 0)
		fs->fs_avgfilesize = AVFILESIZ;
	if (fs->fs_avgfpdir <= 0)
		fs->fs_avgfpdir = AFPDIR;
	if (bigcgs) {
		fs->fs_save_cgsize = fs->fs_cgsize;
		fs->fs_cgsize = fs->fs_bsize;
	}
}

/*
 * Unwinding superblock updates for old filesystems.
 * See ffs_oldfscompat_read above for details.
 *
 * XXX - Parts get retired eventually.
 * Unfortunately new bits get added.
 */
static void
ffs_oldfscompat_write(fs, ump)
	struct fs *fs;
	struct ufsmount *ump;
{

	/*
	 * Copy back UFS2 updated fields that UFS1 inspects.
	 */
	if (fs->fs_magic == FS_UFS1_MAGIC) {
		fs->fs_old_time = fs->fs_time;
		fs->fs_old_cstotal.cs_ndir = fs->fs_cstotal.cs_ndir;
		fs->fs_old_cstotal.cs_nbfree = fs->fs_cstotal.cs_nbfree;
		fs->fs_old_cstotal.cs_nifree = fs->fs_cstotal.cs_nifree;
		fs->fs_old_cstotal.cs_nffree = fs->fs_cstotal.cs_nffree;
		fs->fs_maxfilesize = ump->um_savedmaxfilesize;
	}
	if (bigcgs) {
		fs->fs_cgsize = fs->fs_save_cgsize;
		fs->fs_save_cgsize = 0;
	}
}

/*
 * unmount system call
 */
int
ffs_unmount(mp, mntflags, td)
	struct mount *mp;
	int mntflags;
	struct thread *td;
{
	struct ufsmount *ump = VFSTOUFS(mp);
	struct fs *fs;
	int error, flags;

	flags = 0;
	if (mntflags & MNT_FORCE) {
		flags |= FORCECLOSE;
	}
#ifdef UFS_EXTATTR
	if ((error = ufs_extattr_stop(mp, td))) {
		if (error != EOPNOTSUPP)
			printf("ffs_unmount: ufs_extattr_stop returned %d\n",
			    error);
	} else {
		ufs_extattr_uepm_destroy(&ump->um_extattr);
	}
#endif
	if (mp->mnt_flag & MNT_SOFTDEP) {
		if ((error = softdep_flushfiles(mp, flags, td)) != 0)
			return (error);
	} else {
		if ((error = ffs_flushfiles(mp, flags, td)) != 0)
			return (error);
	}
	fs = ump->um_fs;
	if (fs->fs_pendingblocks != 0 || fs->fs_pendinginodes != 0) {
		printf("%s: unmount pending error: blocks %jd files %d\n",
		    fs->fs_fsmnt, (intmax_t)fs->fs_pendingblocks,
		    fs->fs_pendinginodes);
		fs->fs_pendingblocks = 0;
		fs->fs_pendinginodes = 0;
	}
	if (fs->fs_ronly == 0) {
		fs->fs_clean = fs->fs_flags & (FS_UNCLEAN|FS_NEEDSFSCK) ? 0 : 1;
		error = ffs_sbupdate(ump, MNT_WAIT);
		if (error) {
			fs->fs_clean = 0;
			return (error);
		}
	}
	vinvalbuf(ump->um_devvp, V_SAVE, NOCRED, td, 0, 0);
	DROP_GIANT();
	g_topology_lock();
	g_wither_geom_close(ump->um_cp->geom, ENXIO);
	g_topology_unlock();
	PICKUP_GIANT();
	vrele(ump->um_devvp);
	free(fs->fs_csp, M_UFSMNT);
	free(fs, M_UFSMNT);
	free(ump, M_UFSMNT);
	mp->mnt_data = (qaddr_t)0;
	mp->mnt_flag &= ~MNT_LOCAL;
	return (error);
}

/*
 * Flush out all the files in a filesystem.
 */
int
ffs_flushfiles(mp, flags, td)
	struct mount *mp;
	int flags;
	struct thread *td;
{
	struct ufsmount *ump;
	int error;

	ump = VFSTOUFS(mp);
#ifdef QUOTA
	if (mp->mnt_flag & MNT_QUOTA) {
		int i;
		error = vflush(mp, 0, SKIPSYSTEM|flags, td);
		if (error)
			return (error);
		for (i = 0; i < MAXQUOTAS; i++) {
			if (ump->um_quotas[i] == NULLVP)
				continue;
			quotaoff(td, mp, i);
		}
		/*
		 * Here we fall through to vflush again to ensure
		 * that we have gotten rid of all the system vnodes.
		 */
	}
#endif
	ASSERT_VOP_LOCKED(ump->um_devvp, "ffs_flushfiles");
	if (ump->um_devvp->v_vflag & VV_COPYONWRITE) {
		if ((error = vflush(mp, 0, SKIPSYSTEM | flags, td)) != 0)
			return (error);
		ffs_snapshot_unmount(mp);
		/*
		 * Here we fall through to vflush again to ensure
		 * that we have gotten rid of all the system vnodes.
		 */
	}
        /*
	 * Flush all the files.
	 */
	if ((error = vflush(mp, 0, flags, td)) != 0)
		return (error);
	/*
	 * Flush filesystem metadata.
	 */
	vn_lock(ump->um_devvp, LK_EXCLUSIVE | LK_RETRY, td);
	error = VOP_FSYNC(ump->um_devvp, td->td_ucred, MNT_WAIT, td);
	VOP_UNLOCK(ump->um_devvp, 0, td);
	return (error);
}

/*
 * Get filesystem statistics.
 */
int
ffs_statfs(mp, sbp, td)
	struct mount *mp;
	struct statfs *sbp;
	struct thread *td;
{
	struct ufsmount *ump;
	struct fs *fs;

	ump = VFSTOUFS(mp);
	fs = ump->um_fs;
	if (fs->fs_magic != FS_UFS1_MAGIC && fs->fs_magic != FS_UFS2_MAGIC)
		panic("ffs_statfs");
	sbp->f_version = STATFS_VERSION;
	sbp->f_bsize = fs->fs_fsize;
	sbp->f_iosize = fs->fs_bsize;
	sbp->f_blocks = fs->fs_dsize;
	sbp->f_bfree = fs->fs_cstotal.cs_nbfree * fs->fs_frag +
	    fs->fs_cstotal.cs_nffree + dbtofsb(fs, fs->fs_pendingblocks);
	sbp->f_bavail = freespace(fs, fs->fs_minfree) +
	    dbtofsb(fs, fs->fs_pendingblocks);
	sbp->f_files =  fs->fs_ncg * fs->fs_ipg - ROOTINO;
	sbp->f_ffree = fs->fs_cstotal.cs_nifree + fs->fs_pendinginodes;
	sbp->f_namemax = NAME_MAX;
	return (0);
}

/*
 * Go through the disk queues to initiate sandbagged IO;
 * go through the inodes to write those that have been modified;
 * initiate the writing of the super block if it has been modified.
 *
 * Note: we are always called with the filesystem marked `MPBUSY'.
 */
int
ffs_sync(mp, waitfor, cred, td)
	struct mount *mp;
	int waitfor;
	struct ucred *cred;
	struct thread *td;
{
	struct vnode *nvp, *vp, *devvp;
	struct inode *ip;
	struct ufsmount *ump = VFSTOUFS(mp);
	struct fs *fs;
	int error, count, wait, lockreq, allerror = 0;
	struct bufobj *bo;

	fs = ump->um_fs;
	if (fs->fs_fmod != 0 && fs->fs_ronly != 0) {		/* XXX */
		printf("fs = %s\n", fs->fs_fsmnt);
		panic("ffs_sync: rofs mod");
	}
	/*
	 * Write back each (modified) inode.
	 */
	wait = 0;
	lockreq = LK_EXCLUSIVE | LK_NOWAIT;
	if (waitfor == MNT_WAIT) {
		wait = 1;
		lockreq = LK_EXCLUSIVE;
	}
	lockreq |= LK_INTERLOCK;
	MNT_ILOCK(mp);
loop:
	MNT_VNODE_FOREACH(vp, mp, nvp) {
		/*
		 * Depend on the mntvnode_slock to keep things stable enough
		 * for a quick test.  Since there might be hundreds of
		 * thousands of vnodes, we cannot afford even a subroutine
		 * call unless there's a good chance that we have work to do.
		 */
		VI_LOCK(vp);
		if (vp->v_iflag & VI_XLOCK) {
			VI_UNLOCK(vp);
			continue;
		}
		ip = VTOI(vp);
		if (vp->v_type == VNON || ((ip->i_flag &
		    (IN_ACCESS | IN_CHANGE | IN_MODIFIED | IN_UPDATE)) == 0 &&
		    vp->v_bufobj.bo_dirty.bv_cnt == 0)) {
			VI_UNLOCK(vp);
			continue;
		}
		MNT_IUNLOCK(mp);
		if ((error = vget(vp, lockreq, td)) != 0) {
			MNT_ILOCK(mp);
			if (error == ENOENT)
				goto loop;
			continue;
		}
		if ((error = VOP_FSYNC(vp, cred, waitfor, td)) != 0)
			allerror = error;
		VOP_UNLOCK(vp, 0, td);
		vrele(vp);
		MNT_ILOCK(mp);
	}
	MNT_IUNLOCK(mp);
	/*
	 * Force stale filesystem control information to be flushed.
	 */
	if (waitfor == MNT_WAIT) {
		if ((error = softdep_flushworklist(ump->um_mountp, &count, td)))
			allerror = error;
		/* Flushed work items may create new vnodes to clean */
		if (allerror == 0 && count) {
			MNT_ILOCK(mp);
			goto loop;
		}
	}
#ifdef QUOTA
	qsync(mp);
#endif
	devvp = ump->um_devvp;
	VI_LOCK(devvp);
	bo = &devvp->v_bufobj;
	if (waitfor != MNT_LAZY &&
	    (bo->bo_numoutput > 0 || bo->bo_dirty.bv_cnt > 0)) {
		vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY | LK_INTERLOCK, td);
		if ((error = VOP_FSYNC(devvp, cred, waitfor, td)) != 0)
			allerror = error;
		VOP_UNLOCK(devvp, 0, td);
		if (allerror == 0 && waitfor == MNT_WAIT) {
			MNT_ILOCK(mp);
			goto loop;
		}
	} else
		VI_UNLOCK(devvp);
	/*
	 * Write back modified superblock.
	 */
	if (fs->fs_fmod != 0 && (error = ffs_sbupdate(ump, waitfor)) != 0)
		allerror = error;
	return (allerror);
}

int
ffs_vget(mp, ino, flags, vpp)
	struct mount *mp;
	ino_t ino;
	int flags;
	struct vnode **vpp;
{
	struct thread *td = curthread; 		/* XXX */
	struct fs *fs;
	struct inode *ip;
	struct ufsmount *ump;
	struct buf *bp;
	struct vnode *vp;
	struct cdev *dev;
	int error;

	ump = VFSTOUFS(mp);
	dev = ump->um_dev;

	/*
	 * We do not lock vnode creation as it is believed to be too
	 * expensive for such rare case as simultaneous creation of vnode
	 * for same ino by different processes. We just allow them to race
	 * and check later to decide who wins. Let the race begin!
	 */
	if ((error = ufs_ihashget(dev, ino, flags, vpp)) != 0)
		return (error);
	if (*vpp != NULL)
		return (0);

	/*
	 * If this MALLOC() is performed after the getnewvnode()
	 * it might block, leaving a vnode with a NULL v_data to be
	 * found by ffs_sync() if a sync happens to fire right then,
	 * which will cause a panic because ffs_sync() blindly
	 * dereferences vp->v_data (as well it should).
	 */
	ip = uma_zalloc(uma_inode, M_WAITOK);

	/* Allocate a new vnode/inode. */
	error = getnewvnode("ufs", mp, &ffs_vnodeops, &vp);
	if (error) {
		*vpp = NULL;
		uma_zfree(uma_inode, ip);
		return (error);
	}
	bzero((caddr_t)ip, sizeof(struct inode));
	/*
	 * FFS supports recursive locking.
	 */
	fs = ump->um_fs;
	vp->v_vnlock->lk_flags |= LK_CANRECURSE;
	vp->v_data = ip;
	vp->v_bufobj.bo_bsize = fs->fs_bsize;
	ip->i_vnode = vp;
	ip->i_ump = ump;
	ip->i_fs = fs;
	ip->i_dev = dev;
	ip->i_number = ino;
#ifdef QUOTA
	{
		int i;
		for (i = 0; i < MAXQUOTAS; i++)
			ip->i_dquot[i] = NODQUOT;
	}
#endif
	/*
	 * Exclusively lock the vnode before adding to hash. Note, that we
	 * must not release nor downgrade the lock (despite flags argument
	 * says) till it is fully initialized.
	 */
	lockmgr(vp->v_vnlock, LK_EXCLUSIVE, (struct mtx *)0, td);

	/*
	 * Atomicaly (in terms of ufs_hash operations) check the hash for
	 * duplicate of vnode being created and add it to the hash. If a
	 * duplicate vnode was found, it will be vget()ed from hash for us.
	 */
	if ((error = ufs_ihashins(ip, flags, vpp)) != 0) {
		vput(vp);
		*vpp = NULL;
		return (error);
	}

	/* We lost the race, then throw away our vnode and return existing */
	if (*vpp != NULL) {
		vput(vp);
		return (0);
	}

	/* Read in the disk contents for the inode, copy into the inode. */
	error = bread(ump->um_devvp, fsbtodb(fs, ino_to_fsba(fs, ino)),
	    (int)fs->fs_bsize, NOCRED, &bp);
	if (error) {
		/*
		 * The inode does not contain anything useful, so it would
		 * be misleading to leave it on its hash chain. With mode
		 * still zero, it will be unlinked and returned to the free
		 * list by vput().
		 */
		brelse(bp);
		vput(vp);
		*vpp = NULL;
		return (error);
	}
	if (ip->i_ump->um_fstype == UFS1)
		ip->i_din1 = uma_zalloc(uma_ufs1, M_WAITOK);
	else
		ip->i_din2 = uma_zalloc(uma_ufs2, M_WAITOK);
	ffs_load_inode(bp, ip, fs, ino);
	if (DOINGSOFTDEP(vp))
		softdep_load_inodeblock(ip);
	else
		ip->i_effnlink = ip->i_nlink;
	bqrelse(bp);

	/*
	 * Initialize the vnode from the inode, check for aliases.
	 * Note that the underlying vnode may have changed.
	 */
	error = ufs_vinit(mp, &ffs_fifoops, &vp);
	if (error) {
		vput(vp);
		*vpp = NULL;
		return (error);
	}
	/*
	 * Finish inode initialization.
	 */
	VREF(ip->i_devvp);
	/*
	 * Set up a generation number for this inode if it does not
	 * already have one. This should only happen on old filesystems.
	 */
	if (ip->i_gen == 0) {
		ip->i_gen = arc4random() / 2 + 1;
		if ((vp->v_mount->mnt_flag & MNT_RDONLY) == 0) {
			ip->i_flag |= IN_MODIFIED;
			DIP_SET(ip, i_gen, ip->i_gen);
		}
	}
	/*
	 * Ensure that uid and gid are correct. This is a temporary
	 * fix until fsck has been changed to do the update.
	 */
	if (fs->fs_magic == FS_UFS1_MAGIC &&		/* XXX */
	    fs->fs_old_inodefmt < FS_44INODEFMT) {	/* XXX */
		ip->i_uid = ip->i_din1->di_ouid;	/* XXX */
		ip->i_gid = ip->i_din1->di_ogid;	/* XXX */
	}						/* XXX */

#ifdef MAC
	if ((mp->mnt_flag & MNT_MULTILABEL) && ip->i_mode) {
		/*
		 * If this vnode is already allocated, and we're running
		 * multi-label, attempt to perform a label association
		 * from the extended attributes on the inode.
		 */
		error = mac_associate_vnode_extattr(mp, vp);
		if (error) {
			/* ufs_inactive will release ip->i_devvp ref. */
			vput(vp);
			*vpp = NULL;
			return (error);
		}
	}
#endif

	*vpp = vp;
	return (0);
}

/*
 * File handle to vnode
 *
 * Have to be really careful about stale file handles:
 * - check that the inode number is valid
 * - call ffs_vget() to get the locked inode
 * - check for an unallocated inode (i_mode == 0)
 * - check that the given client host has export rights and return
 *   those rights via. exflagsp and credanonp
 */
int
ffs_fhtovp(mp, fhp, vpp)
	struct mount *mp;
	struct fid *fhp;
	struct vnode **vpp;
{
	struct ufid *ufhp;
	struct fs *fs;

	ufhp = (struct ufid *)fhp;
	fs = VFSTOUFS(mp)->um_fs;
	if (ufhp->ufid_ino < ROOTINO ||
	    ufhp->ufid_ino >= fs->fs_ncg * fs->fs_ipg)
		return (ESTALE);
	return (ufs_fhtovp(mp, ufhp, vpp));
}

/*
 * Vnode pointer to File handle
 */
/* ARGSUSED */
int
ffs_vptofh(vp, fhp)
	struct vnode *vp;
	struct fid *fhp;
{
	struct inode *ip;
	struct ufid *ufhp;

	ip = VTOI(vp);
	ufhp = (struct ufid *)fhp;
	ufhp->ufid_len = sizeof(struct ufid);
	ufhp->ufid_ino = ip->i_number;
	ufhp->ufid_gen = ip->i_gen;
	return (0);
}

/*
 * Initialize the filesystem.
 */
static int
ffs_init(vfsp)
	struct vfsconf *vfsp;
{

	softdep_initialize();
	return (ufs_init(vfsp));
}

/*
 * Undo the work of ffs_init().
 */
static int
ffs_uninit(vfsp)
	struct vfsconf *vfsp;
{
	int ret;

	ret = ufs_uninit(vfsp);
	softdep_uninitialize();
	return (ret);
}

/*
 * Write a superblock and associated information back to disk.
 */
static int
ffs_sbupdate(mp, waitfor)
	struct ufsmount *mp;
	int waitfor;
{
	struct fs *fs = mp->um_fs;
	struct buf *bp;
	int blks;
	void *space;
	int i, size, error, allerror = 0;

	if (fs->fs_ronly == 1 &&
	    (mp->um_mountp->mnt_flag & (MNT_RDONLY | MNT_UPDATE)) != 
	    (MNT_RDONLY | MNT_UPDATE))
		panic("ffs_sbupdate: write read-only filesystem");
	/*
	 * First write back the summary information.
	 */
	blks = howmany(fs->fs_cssize, fs->fs_fsize);
	space = fs->fs_csp;
	for (i = 0; i < blks; i += fs->fs_frag) {
		size = fs->fs_bsize;
		if (i + fs->fs_frag > blks)
			size = (blks - i) * fs->fs_fsize;
		bp = getblk(mp->um_devvp, fsbtodb(fs, fs->fs_csaddr + i),
		    size, 0, 0, 0);
		bcopy(space, bp->b_data, (u_int)size);
		space = (char *)space + size;
		if (waitfor != MNT_WAIT)
			bawrite(bp);
		else if ((error = bwrite(bp)) != 0)
			allerror = error;
	}
	/*
	 * Now write back the superblock itself. If any errors occurred
	 * up to this point, then fail so that the superblock avoids
	 * being written out as clean.
	 */
	if (allerror)
		return (allerror);
	if (fs->fs_magic == FS_UFS1_MAGIC && fs->fs_sblockloc != SBLOCK_UFS1 &&
	    (fs->fs_flags & FS_FLAGS_UPDATED) == 0) {
		printf("%s: correcting fs_sblockloc from %jd to %d\n",
		    fs->fs_fsmnt, fs->fs_sblockloc, SBLOCK_UFS1);
		fs->fs_sblockloc = SBLOCK_UFS1;
	}
	if (fs->fs_magic == FS_UFS2_MAGIC && fs->fs_sblockloc != SBLOCK_UFS2 &&
	    (fs->fs_flags & FS_FLAGS_UPDATED) == 0) {
		printf("%s: correcting fs_sblockloc from %jd to %d\n",
		    fs->fs_fsmnt, fs->fs_sblockloc, SBLOCK_UFS2);
		fs->fs_sblockloc = SBLOCK_UFS2;
	}
	bp = getblk(mp->um_devvp, btodb(fs->fs_sblockloc), (int)fs->fs_sbsize,
	    0, 0, 0);
	fs->fs_fmod = 0;
	fs->fs_time = time_second;
	bcopy((caddr_t)fs, bp->b_data, (u_int)fs->fs_sbsize);
	ffs_oldfscompat_write((struct fs *)bp->b_data, mp);
	if (waitfor != MNT_WAIT)
		bawrite(bp);
	else if ((error = bwrite(bp)) != 0)
		allerror = error;
	return (allerror);
}

static int
ffs_extattrctl(struct mount *mp, int cmd, struct vnode *filename_vp,
	int attrnamespace, const char *attrname, struct thread *td)
{

#ifdef UFS_EXTATTR
	return (ufs_extattrctl(mp, cmd, filename_vp, attrnamespace,
	    attrname, td));
#else
	return (vfs_stdextattrctl(mp, cmd, filename_vp, attrnamespace,
	    attrname, td));
#endif
}

static void
ffs_ifree(struct ufsmount *ump, struct inode *ip)
{

	if (ump->um_fstype == UFS1 && ip->i_din1 != NULL)
		uma_zfree(uma_ufs1, ip->i_din1);
	else if (ip->i_din2 != NULL)
		uma_zfree(uma_ufs2, ip->i_din2);
	uma_zfree(uma_inode, ip);
}

static void
ffs_geom_strategy(struct bufobj *bo, struct buf *bp)
{

#ifdef SOFTUPDATES
	if (bp->b_iocmd == BIO_WRITE && softdep_disk_prewrite(bp))
		return;
#endif
	g_vfs_strategy(bo, bp);
}