summaryrefslogtreecommitdiffstats
path: root/sys/kern/vfs_subr.c
blob: b4e1db43710c60519f52fca588e47de255e0cd48 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
/*
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * 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.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 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.
 *
 *	@(#)vfs_subr.c	8.13 (Berkeley) 4/18/94
 * $Id: vfs_subr.c,v 1.65 1996/11/12 09:24:31 bde Exp $
 */

/*
 * External virtual filesystem routines
 */
#include "opt_ddb.h"
#include "opt_devfs.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/file.h>
#include <sys/proc.h>
#include <sys/mount.h>
#include <sys/time.h>
#include <sys/vnode.h>
#include <sys/stat.h>
#include <sys/namei.h>
#include <sys/ucred.h>
#include <sys/buf.h>
#include <sys/errno.h>
#include <sys/malloc.h>
#include <sys/domain.h>
#include <sys/mbuf.h>

#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_object.h>
#include <vm/vm_extern.h>
#include <vm/vm_pager.h>
#include <vm/vnode_pager.h>
#include <sys/sysctl.h>

#include <miscfs/specfs/specdev.h>

#ifdef DDB
extern void	printlockedvnodes __P((void));
#endif
extern void	vclean __P((struct vnode *vp, int flags));
extern void	vfs_unmountroot __P((struct mount *rootfs));

enum vtype iftovt_tab[16] = {
	VNON, VFIFO, VCHR, VNON, VDIR, VNON, VBLK, VNON,
	VREG, VNON, VLNK, VNON, VSOCK, VNON, VNON, VBAD,
};
int vttoif_tab[9] = {
	0, S_IFREG, S_IFDIR, S_IFBLK, S_IFCHR, S_IFLNK,
	S_IFSOCK, S_IFIFO, S_IFMT,
};

/*
 * Insq/Remq for the vnode usage lists.
 */
#define	bufinsvn(bp, dp)	LIST_INSERT_HEAD(dp, bp, b_vnbufs)
#define	bufremvn(bp) {  \
	LIST_REMOVE(bp, b_vnbufs); \
	(bp)->b_vnbufs.le_next = NOLIST; \
}

TAILQ_HEAD(freelst, vnode) vnode_free_list;	/* vnode free list */
static u_long freevnodes = 0;

struct mntlist mountlist;	/* mounted filesystem list */

int desiredvnodes;
SYSCTL_INT(_kern, KERN_MAXVNODES, maxvnodes, CTLFLAG_RW, &desiredvnodes, 0, "");

static void	vfs_free_addrlist __P((struct netexport *nep));
static int	vfs_free_netcred __P((struct radix_node *rn, void *w));
static int	vfs_hang_addrlist __P((struct mount *mp, struct netexport *nep,
				       struct export_args *argp));

/*
 * Initialize the vnode management data structures.
 */
void
vntblinit()
{
	desiredvnodes = maxproc + vm_object_cache_max + extravnodes;

	TAILQ_INIT(&vnode_free_list);
	CIRCLEQ_INIT(&mountlist);
}

/*
 * Lock a filesystem.
 * Used to prevent access to it while mounting and unmounting.
 */
int
vfs_lock(mp)
	register struct mount *mp;
{

	while (mp->mnt_flag & MNT_MLOCK) {
		mp->mnt_flag |= MNT_MWAIT;
		(void) tsleep((caddr_t) mp, PVFS, "vfslck", 0);
	}
	mp->mnt_flag |= MNT_MLOCK;
	return (0);
}

/*
 * Unlock a locked filesystem.
 * Panic if filesystem is not locked.
 */
void
vfs_unlock(mp)
	register struct mount *mp;
{

	if ((mp->mnt_flag & MNT_MLOCK) == 0)
		panic("vfs_unlock: not locked");
	mp->mnt_flag &= ~MNT_MLOCK;
	if (mp->mnt_flag & MNT_MWAIT) {
		mp->mnt_flag &= ~MNT_MWAIT;
		wakeup((caddr_t) mp);
	}
}

/*
 * Mark a mount point as busy.
 * Used to synchronize access and to delay unmounting.
 */
int
vfs_busy(mp)
	register struct mount *mp;
{

	while (mp->mnt_flag & MNT_MPBUSY) {
		mp->mnt_flag |= MNT_MPWANT;
		(void) tsleep((caddr_t) &mp->mnt_flag, PVFS, "vfsbsy", 0);
	}
	if (mp->mnt_flag & MNT_UNMOUNT)
		return (1);
	mp->mnt_flag |= MNT_MPBUSY;
	return (0);
}

/*
 * Free a busy filesystem.
 * Panic if filesystem is not busy.
 */
void
vfs_unbusy(mp)
	register struct mount *mp;
{

	if ((mp->mnt_flag & MNT_MPBUSY) == 0)
		panic("vfs_unbusy: not busy");
	mp->mnt_flag &= ~MNT_MPBUSY;
	if (mp->mnt_flag & MNT_MPWANT) {
		mp->mnt_flag &= ~MNT_MPWANT;
		wakeup((caddr_t) &mp->mnt_flag);
	}
}

void
vfs_unmountroot(struct mount *rootfs)
{
	struct mount *mp = rootfs;
	int error;

	if (vfs_busy(mp)) {
		printf("failed to unmount root\n");
		return;
	}
	mp->mnt_flag |= MNT_UNMOUNT;
	if ((error = vfs_lock(mp))) {
		printf("lock of root filesystem failed (%d)\n", error);
		return;
	}
	vnode_pager_umount(mp);	/* release cached vnodes */
	cache_purgevfs(mp);	/* remove cache entries for this file sys */

	if ((error = VFS_SYNC(mp, MNT_WAIT, initproc->p_ucred, initproc)))
		printf("sync of root filesystem failed (%d)\n", error);

	if ((error = VFS_UNMOUNT(mp, MNT_FORCE, initproc))) {
		printf("unmount of root filesystem failed (");
		if (error == EBUSY)
			printf("BUSY)\n");
		else
			printf("%d)\n", error);
	}
	mp->mnt_flag &= ~MNT_UNMOUNT;
	vfs_unbusy(mp);
}

/*
 * Unmount all filesystems.  Should only be called by halt().
 */
void
vfs_unmountall()
{
	struct mount *mp, *nmp, *rootfs = NULL;
	int error;

	/* unmount all but rootfs */
	for (mp = mountlist.cqh_last; mp != (void *)&mountlist; mp = nmp) {
		nmp = mp->mnt_list.cqe_prev;

		if (mp->mnt_flag & MNT_ROOTFS) {
			rootfs = mp;
			continue;
		}
		error = dounmount(mp, MNT_FORCE, initproc);
		if (error) {
			printf("unmount of %s failed (", mp->mnt_stat.f_mntonname);
			if (error == EBUSY)
				printf("BUSY)\n");
			else
				printf("%d)\n", error);
		}
	}

	/* and finally... */
	if (rootfs) {
		vfs_unmountroot(rootfs);
	} else {
		printf("no root filesystem\n");
	}
}

/*
 * Lookup a mount point by filesystem identifier.
 */
struct mount *
getvfs(fsid)
	fsid_t *fsid;
{
	register struct mount *mp;

	for (mp = mountlist.cqh_first; mp != (void *)&mountlist;
	    mp = mp->mnt_list.cqe_next) {
		if (mp->mnt_stat.f_fsid.val[0] == fsid->val[0] &&
		    mp->mnt_stat.f_fsid.val[1] == fsid->val[1])
			return (mp);
	}
	return ((struct mount *) 0);
}

/*
 * Get a new unique fsid
 */
void
getnewfsid(mp, mtype)
	struct mount *mp;
	int mtype;
{
	static u_short xxxfs_mntid;

	fsid_t tfsid;

	mp->mnt_stat.f_fsid.val[0] = makedev(nblkdev + mtype, 0);
	mp->mnt_stat.f_fsid.val[1] = mtype;
	if (xxxfs_mntid == 0)
		++xxxfs_mntid;
	tfsid.val[0] = makedev(nblkdev + mtype, xxxfs_mntid);
	tfsid.val[1] = mtype;
	if (mountlist.cqh_first != (void *)&mountlist) {
		while (getvfs(&tfsid)) {
			tfsid.val[0]++;
			xxxfs_mntid++;
		}
	}
	mp->mnt_stat.f_fsid.val[0] = tfsid.val[0];
}

/*
 * Set vnode attributes to VNOVAL
 */
void
vattr_null(vap)
	register struct vattr *vap;
{

	vap->va_type = VNON;
	vap->va_size = VNOVAL;
	vap->va_bytes = VNOVAL;
	vap->va_mode = vap->va_nlink = vap->va_uid = vap->va_gid =
	    vap->va_fsid = vap->va_fileid =
	    vap->va_blocksize = vap->va_rdev =
	    vap->va_atime.tv_sec = vap->va_atime.tv_nsec =
	    vap->va_mtime.tv_sec = vap->va_mtime.tv_nsec =
	    vap->va_ctime.tv_sec = vap->va_ctime.tv_nsec =
	    vap->va_flags = vap->va_gen = VNOVAL;
	vap->va_vaflags = 0;
}

/*
 * Routines having to do with the management of the vnode table.
 */
extern vop_t **dead_vnodeop_p;

/*
 * Return the next vnode from the free list.
 */
int
getnewvnode(tag, mp, vops, vpp)
	enum vtagtype tag;
	struct mount *mp;
	vop_t **vops;
	struct vnode **vpp;
{
	register struct vnode *vp;

retry:
	vp = vnode_free_list.tqh_first;
	/*
	 * we allocate a new vnode if
	 * 	1. we don't have any free
	 *		Pretty obvious, we actually used to panic, but that
	 *		is a silly thing to do.
	 *	2. we havn't filled our pool yet
	 *		We don't want to trash the incore (VM-)vnodecache.
	 *	3. if less that 1/4th of our vnodes are free.
	 *		We don't want to trash the namei cache either.
	 */
	if (freevnodes < (numvnodes >> 2) ||
	    numvnodes < desiredvnodes ||
	    vp == NULL) {
		vp = (struct vnode *) malloc((u_long) sizeof *vp,
		    M_VNODE, M_WAITOK);
		bzero((char *) vp, sizeof *vp);
		numvnodes++;
	} else {
		TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
		if (vp->v_usage > 0) {
			--vp->v_usage;
			TAILQ_INSERT_TAIL(&vnode_free_list, vp, v_freelist);
			goto retry;
		}
		freevnodes--;
		if (vp->v_usecount)
			panic("free vnode isn't");

		/* see comment on why 0xdeadb is set at end of vgone (below) */
		vp->v_freelist.tqe_prev = (struct vnode **) 0xdeadb;
		vp->v_lease = NULL;
		if (vp->v_type != VBAD)
			vgone(vp);

#ifdef DIAGNOSTIC
		{
			int s;

			if (vp->v_data)
				panic("cleaned vnode isn't");
			s = splbio();
			if (vp->v_numoutput)
				panic("Clean vnode has pending I/O's");
			splx(s);
		}
#endif
		vp->v_flag = 0;
		vp->v_lastr = 0;
		vp->v_lastw = 0;
		vp->v_lasta = 0;
		vp->v_cstart = 0;
		vp->v_clen = 0;
		vp->v_socket = 0;
		vp->v_writecount = 0;	/* XXX */
		vp->v_usage = 0;
	}
	vp->v_type = VNON;
	cache_purge(vp);
	vp->v_tag = tag;
	vp->v_op = vops;
	insmntque(vp, mp);
	*vpp = vp;
	vp->v_usecount = 1;
	vp->v_data = 0;
	return (0);
}

/*
 * Move a vnode from one mount queue to another.
 */
void
insmntque(vp, mp)
	register struct vnode *vp;
	register struct mount *mp;
{

	/*
	 * Delete from old mount point vnode list, if on one.
	 */
	if (vp->v_mount != NULL)
		LIST_REMOVE(vp, v_mntvnodes);
	/*
	 * Insert into list of vnodes for the new mount point, if available.
	 */
	if ((vp->v_mount = mp) == NULL)
		return;
	LIST_INSERT_HEAD(&mp->mnt_vnodelist, vp, v_mntvnodes);
}

/*
 * Update outstanding I/O count and do wakeup if requested.
 */
void
vwakeup(bp)
	register struct buf *bp;
{
	register struct vnode *vp;

	bp->b_flags &= ~B_WRITEINPROG;
	if ((vp = bp->b_vp)) {
		vp->v_numoutput--;
		if (vp->v_numoutput < 0)
			panic("vwakeup: neg numoutput");
		if ((vp->v_numoutput == 0) && (vp->v_flag & VBWAIT)) {
			vp->v_flag &= ~VBWAIT;
			wakeup((caddr_t) &vp->v_numoutput);
		}
	}
}

/*
 * Flush out and invalidate all buffers associated with a vnode.
 * Called with the underlying object locked.
 */
int
vinvalbuf(vp, flags, cred, p, slpflag, slptimeo)
	register struct vnode *vp;
	int flags;
	struct ucred *cred;
	struct proc *p;
	int slpflag, slptimeo;
{
	register struct buf *bp;
	struct buf *nbp, *blist;
	int s, error;
	vm_object_t object;

	if (flags & V_SAVE) {
		if ((error = VOP_FSYNC(vp, cred, MNT_WAIT, p)))
			return (error);
		if (vp->v_dirtyblkhd.lh_first != NULL)
			panic("vinvalbuf: dirty bufs");
	}

	s = splbio();
	for (;;) {
		if ((blist = vp->v_cleanblkhd.lh_first) && (flags & V_SAVEMETA))
			while (blist && blist->b_lblkno < 0)
				blist = blist->b_vnbufs.le_next;
		if (!blist && (blist = vp->v_dirtyblkhd.lh_first) &&
		    (flags & V_SAVEMETA))
			while (blist && blist->b_lblkno < 0)
				blist = blist->b_vnbufs.le_next;
		if (!blist)
			break;

		for (bp = blist; bp; bp = nbp) {
			nbp = bp->b_vnbufs.le_next;
			if ((flags & V_SAVEMETA) && bp->b_lblkno < 0)
				continue;
			if (bp->b_flags & B_BUSY) {
				bp->b_flags |= B_WANTED;
				error = tsleep((caddr_t) bp,
				    slpflag | (PRIBIO + 1), "vinvalbuf",
				    slptimeo);
				splx(s);
				if (error)
					return (error);
				break;
			}
			bremfree(bp);
			bp->b_flags |= B_BUSY;
			/*
			 * XXX Since there are no node locks for NFS, I
			 * believe there is a slight chance that a delayed
			 * write will occur while sleeping just above, so
			 * check for it.
			 */
			if ((bp->b_flags & B_DELWRI) && (flags & V_SAVE)) {
				(void) VOP_BWRITE(bp);
				break;
			}
			bp->b_flags |= (B_INVAL|B_NOCACHE|B_RELBUF);
			brelse(bp);
		}
	}
	splx(s);

	s = splbio();
	while (vp->v_numoutput > 0) {
		vp->v_flag |= VBWAIT;
		tsleep(&vp->v_numoutput, PVM, "vnvlbv", 0);
	}
	splx(s);

	/*
	 * Destroy the copy in the VM cache, too.
	 */
	object = vp->v_object;
	if (object != NULL) {
		vm_object_page_remove(object, 0, object->size,
		    (flags & V_SAVE) ? TRUE : FALSE);
	}
	if (!(flags & V_SAVEMETA) &&
	    (vp->v_dirtyblkhd.lh_first || vp->v_cleanblkhd.lh_first))
		panic("vinvalbuf: flush failed");
	return (0);
}

/*
 * Associate a buffer with a vnode.
 */
void
bgetvp(vp, bp)
	register struct vnode *vp;
	register struct buf *bp;
{
	int s;

	if (bp->b_vp)
		panic("bgetvp: not free");
	VHOLD(vp);
	bp->b_vp = vp;
	if (vp->v_type == VBLK || vp->v_type == VCHR)
		bp->b_dev = vp->v_rdev;
	else
		bp->b_dev = NODEV;
	/*
	 * Insert onto list for new vnode.
	 */
	s = splbio();
	bufinsvn(bp, &vp->v_cleanblkhd);
	splx(s);
}

/*
 * Disassociate a buffer from a vnode.
 */
void
brelvp(bp)
	register struct buf *bp;
{
	struct vnode *vp;
	int s;

	if (bp->b_vp == (struct vnode *) 0)
		panic("brelvp: NULL");
	/*
	 * Delete from old vnode list, if on one.
	 */
	s = splbio();
	if (bp->b_vnbufs.le_next != NOLIST)
		bufremvn(bp);
	splx(s);

	vp = bp->b_vp;
	bp->b_vp = (struct vnode *) 0;
	HOLDRELE(vp);
}

/*
 * Associate a p-buffer with a vnode.
 */
void
pbgetvp(vp, bp)
	register struct vnode *vp;
	register struct buf *bp;
{
	if (bp->b_vp)
		panic("pbgetvp: not free");
	VHOLD(vp);
	bp->b_vp = vp;
	if (vp->v_type == VBLK || vp->v_type == VCHR)
		bp->b_dev = vp->v_rdev;
	else
		bp->b_dev = NODEV;
}

/*
 * Disassociate a p-buffer from a vnode.
 */
void
pbrelvp(bp)
	register struct buf *bp;
{
	struct vnode *vp;

	if (bp->b_vp == (struct vnode *) 0)
		panic("brelvp: NULL");

	vp = bp->b_vp;
	bp->b_vp = (struct vnode *) 0;
	HOLDRELE(vp);
}

/*
 * Reassign a buffer from one vnode to another.
 * Used to assign file specific control information
 * (indirect blocks) to the vnode to which they belong.
 */
void
reassignbuf(bp, newvp)
	register struct buf *bp;
	register struct vnode *newvp;
{
	int s;

	if (newvp == NULL) {
		printf("reassignbuf: NULL");
		return;
	}

	s = splbio();
	/*
	 * Delete from old vnode list, if on one.
	 */
	if (bp->b_vnbufs.le_next != NOLIST)
		bufremvn(bp);
	/*
	 * If dirty, put on list of dirty buffers; otherwise insert onto list
	 * of clean buffers.
	 */
	if (bp->b_flags & B_DELWRI) {
		struct buf *tbp;

		tbp = newvp->v_dirtyblkhd.lh_first;
		if (!tbp || (tbp->b_lblkno > bp->b_lblkno)) {
			bufinsvn(bp, &newvp->v_dirtyblkhd);
		} else {
			while (tbp->b_vnbufs.le_next &&
				(tbp->b_vnbufs.le_next->b_lblkno < bp->b_lblkno)) {
				tbp = tbp->b_vnbufs.le_next;
			}
			LIST_INSERT_AFTER(tbp, bp, b_vnbufs);
		}
	} else {
		bufinsvn(bp, &newvp->v_cleanblkhd);
	}
	splx(s);
}

#ifndef DEVFS_ROOT
/*
 * Create a vnode for a block device.
 * Used for root filesystem, argdev, and swap areas.
 * Also used for memory file system special devices.
 */
int
bdevvp(dev, vpp)
	dev_t dev;
	struct vnode **vpp;
{
	register struct vnode *vp;
	struct vnode *nvp;
	int error;

	if (dev == NODEV)
		return (0);
	error = getnewvnode(VT_NON, (struct mount *) 0, spec_vnodeop_p, &nvp);
	if (error) {
		*vpp = 0;
		return (error);
	}
	vp = nvp;
	vp->v_type = VBLK;
	if ((nvp = checkalias(vp, dev, (struct mount *) 0))) {
		vput(vp);
		vp = nvp;
	}
	*vpp = vp;
	return (0);
}
#endif /* !DEVFS_ROOT */

/*
 * Check to see if the new vnode represents a special device
 * for which we already have a vnode (either because of
 * bdevvp() or because of a different vnode representing
 * the same block device). If such an alias exists, deallocate
 * the existing contents and return the aliased vnode. The
 * caller is responsible for filling it with its new contents.
 */
struct vnode *
checkalias(nvp, nvp_rdev, mp)
	register struct vnode *nvp;
	dev_t nvp_rdev;
	struct mount *mp;
{
	register struct vnode *vp;
	struct vnode **vpp;

	if (nvp->v_type != VBLK && nvp->v_type != VCHR)
		return (NULLVP);

	vpp = &speclisth[SPECHASH(nvp_rdev)];
loop:
	for (vp = *vpp; vp; vp = vp->v_specnext) {
		if (nvp_rdev != vp->v_rdev || nvp->v_type != vp->v_type)
			continue;
		/*
		 * Alias, but not in use, so flush it out.
		 */
		if (vp->v_usecount == 0) {
			vgone(vp);
			goto loop;
		}
		if (vget(vp, 1))
			goto loop;
		break;
	}

	if (vp == NULL || vp->v_tag != VT_NON) {
		MALLOC(nvp->v_specinfo, struct specinfo *,
		    sizeof(struct specinfo), M_VNODE, M_WAITOK);
		nvp->v_rdev = nvp_rdev;
		nvp->v_hashchain = vpp;
		nvp->v_specnext = *vpp;
		nvp->v_specflags = 0;
		*vpp = nvp;
		if (vp != NULL) {
			nvp->v_flag |= VALIASED;
			vp->v_flag |= VALIASED;
			vput(vp);
		}
		return (NULLVP);
	}
	VOP_UNLOCK(vp);
	vclean(vp, 0);
	vp->v_op = nvp->v_op;
	vp->v_tag = nvp->v_tag;
	nvp->v_type = VNON;
	insmntque(vp, mp);
	return (vp);
}

/*
 * Grab a particular vnode from the free list, increment its
 * reference count and lock it. The vnode lock bit is set the
 * vnode is being eliminated in vgone. The process is awakened
 * when the transition is completed, and an error returned to
 * indicate that the vnode is no longer usable (possibly having
 * been changed to a new file system type).
 */
int
vget(vp, lockflag)
	register struct vnode *vp;
	int lockflag;
{

	/*
	 * If the vnode is in the process of being cleaned out for another
	 * use, we wait for the cleaning to finish and then return failure.
	 * Cleaning is determined either by checking that the VXLOCK flag is
	 * set, or that the use count is zero with the back pointer set to
	 * show that it has been removed from the free list by getnewvnode.
	 * The VXLOCK flag may not have been set yet because vclean is blocked
	 * in the VOP_LOCK call waiting for the VOP_INACTIVE to complete.
	 */
	if ((vp->v_flag & VXLOCK) ||
	    (vp->v_usecount == 0 &&
		vp->v_freelist.tqe_prev == (struct vnode **) 0xdeadb)) {
		vp->v_flag |= VXWANT;
		(void) tsleep((caddr_t) vp, PINOD, "vget", 0);
		return (1);
	}
	if (vp->v_usecount == 0) {
		TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
		freevnodes--;
	}
	vp->v_usecount++;

	/*
	 * Create the VM object, if needed
	 */
	if ((vp->v_type == VREG) &&
		((vp->v_object == NULL) ||
			(vp->v_object->flags & OBJ_VFS_REF) == 0)) {
		vfs_object_create(vp, curproc, curproc->p_ucred, 0);
	}
	if (lockflag)
		VOP_LOCK(vp);

	return (0);
}

/*
 * Vnode reference, just increment the count
 */
void
vref(vp)
	struct vnode *vp;
{
	if (vp->v_usecount <= 0)
		panic("vref used where vget required");

	vp->v_usecount++;

	if ((vp->v_type == VREG) &&
		((vp->v_object == NULL) ||
			((vp->v_object->flags & OBJ_VFS_REF) == 0)) ) {
		/*
		 * We need to lock to VP during the time that
		 * the object is created.  This is necessary to
		 * keep the system from re-entrantly doing it
		 * multiple times.
		 */
		vfs_object_create(vp, curproc, curproc->p_ucred, 0);
	}
}

/*
 * vput(), just unlock and vrele()
 */
void
vput(vp)
	register struct vnode *vp;
{
	VOP_UNLOCK(vp);
	vrele(vp);
}

/*
 * Vnode release.
 * If count drops to zero, call inactive routine and return to freelist.
 */
void
vrele(vp)
	register struct vnode *vp;
{

#ifdef DIAGNOSTIC
	if (vp == NULL)
		panic("vrele: null vp");
#endif

	vp->v_usecount--;

	if ((vp->v_usecount == 1) &&
		vp->v_object &&
		(vp->v_object->flags & OBJ_VFS_REF)) {
		vp->v_object->flags &= ~OBJ_VFS_REF;
		vm_object_deallocate(vp->v_object);
		return;
	}

	if (vp->v_usecount > 0)
		return;

	if (vp->v_usecount < 0) {
#ifdef DIAGNOSTIC
		vprint("vrele: negative ref count", vp);
#endif
		panic("vrele: negative reference cnt");
	}
	if (vp->v_flag & VAGE) {
		if(vp->v_tag != VT_TFS)
			TAILQ_INSERT_HEAD(&vnode_free_list, vp, v_freelist);
		vp->v_flag &= ~VAGE;
		vp->v_usage = 0;
	} else {
		if(vp->v_tag != VT_TFS)
			TAILQ_INSERT_TAIL(&vnode_free_list, vp, v_freelist);
	}
	freevnodes++;

	VOP_INACTIVE(vp);
}

#ifdef DIAGNOSTIC
/*
 * Page or buffer structure gets a reference.
 */
void
vhold(vp)
	register struct vnode *vp;
{

	vp->v_holdcnt++;
}

/*
 * Page or buffer structure frees a reference.
 */
void
holdrele(vp)
	register struct vnode *vp;
{

	if (vp->v_holdcnt <= 0)
		panic("holdrele: holdcnt");
	vp->v_holdcnt--;
}
#endif /* DIAGNOSTIC */

/*
 * Remove any vnodes in the vnode table belonging to mount point mp.
 *
 * If MNT_NOFORCE is specified, there should not be any active ones,
 * return error if any are found (nb: this is a user error, not a
 * system error). If MNT_FORCE is specified, detach any active vnodes
 * that are found.
 */
#ifdef DIAGNOSTIC
static int busyprt = 0;		/* print out busy vnodes */
SYSCTL_INT(_debug, 1, busyprt, CTLFLAG_RW, &busyprt, 0, "");
#endif

int
vflush(mp, skipvp, flags)
	struct mount *mp;
	struct vnode *skipvp;
	int flags;
{
	register struct vnode *vp, *nvp;
	int busy = 0;

	if ((mp->mnt_flag & MNT_MPBUSY) == 0)
		panic("vflush: not busy");
loop:
	for (vp = mp->mnt_vnodelist.lh_first; vp; vp = nvp) {
		/*
		 * Make sure this vnode wasn't reclaimed in getnewvnode().
		 * Start over if it has (it won't be on the list anymore).
		 */
		if (vp->v_mount != mp)
			goto loop;
		nvp = vp->v_mntvnodes.le_next;
		/*
		 * Skip over a selected vnode.
		 */
		if (vp == skipvp)
			continue;
		/*
		 * Skip over a vnodes marked VSYSTEM.
		 */
		if ((flags & SKIPSYSTEM) && (vp->v_flag & VSYSTEM))
			continue;
		/*
		 * If WRITECLOSE is set, only flush out regular file vnodes
		 * open for writing.
		 */
		if ((flags & WRITECLOSE) &&
		    (vp->v_writecount == 0 || vp->v_type != VREG))
			continue;

		if (vp->v_object && (vp->v_object->flags & OBJ_VFS_REF)) {
			vm_object_reference(vp->v_object);
			pager_cache(vp->v_object, FALSE);
			vp->v_object->flags &= ~OBJ_VFS_REF;
			vm_object_deallocate(vp->v_object);
		}

		/*
		 * With v_usecount == 0, all we need to do is clear out the
		 * vnode data structures and we are done.
		 */
		if (vp->v_usecount == 0) {
			vgone(vp);
			continue;
		}

		/*
		 * If FORCECLOSE is set, forcibly close the vnode. For block
		 * or character devices, revert to an anonymous device. For
		 * all other files, just kill them.
		 */
		if (flags & FORCECLOSE) {
			if (vp->v_type != VBLK && vp->v_type != VCHR) {
				vgone(vp);
			} else {
				vclean(vp, 0);
				vp->v_op = spec_vnodeop_p;
				insmntque(vp, (struct mount *) 0);
			}
			continue;
		}
#ifdef DIAGNOSTIC
		if (busyprt)
			vprint("vflush: busy vnode", vp);
#endif
		busy++;
	}
	if (busy)
		return (EBUSY);
	return (0);
}

/*
 * Disassociate the underlying file system from a vnode.
 */
void
vclean(struct vnode *vp, int flags)
{
	int active;

	/*
	 * Check to see if the vnode is in use. If so we have to reference it
	 * before we clean it out so that its count cannot fall to zero and
	 * generate a race against ourselves to recycle it.
	 */
	if ((active = vp->v_usecount))
		VREF(vp);
	/*
	 * Even if the count is zero, the VOP_INACTIVE routine may still have
	 * the object locked while it cleans it out. The VOP_LOCK ensures that
	 * the VOP_INACTIVE routine is done with its work. For active vnodes,
	 * it ensures that no other activity can occur while the underlying
	 * object is being cleaned out.
	 */
	VOP_LOCK(vp);
	/*
	 * Prevent the vnode from being recycled or brought into use while we
	 * clean it out.
	 */
	if (vp->v_flag & VXLOCK)
		panic("vclean: deadlock");
	vp->v_flag |= VXLOCK;
	/*
	 * Clean out any buffers associated with the vnode.
	 */
	if (flags & DOCLOSE)
		vinvalbuf(vp, V_SAVE, NOCRED, NULL, 0, 0);
	/*
	 * Any other processes trying to obtain this lock must first wait for
	 * VXLOCK to clear, then call the new lock operation.
	 */
	VOP_UNLOCK(vp);
	/*
	 * If purging an active vnode, it must be closed and deactivated
	 * before being reclaimed.
	 */
	if (active) {
		if (flags & DOCLOSE)
			VOP_CLOSE(vp, FNONBLOCK, NOCRED, NULL);
		VOP_INACTIVE(vp);
	}
	/*
	 * Reclaim the vnode.
	 */
	if (VOP_RECLAIM(vp))
		panic("vclean: cannot reclaim");
	if (active)
		vrele(vp);

	/*
	 * Done with purge, notify sleepers of the grim news.
	 */
	vp->v_op = dead_vnodeop_p;
	vp->v_tag = VT_NON;
	vp->v_flag &= ~VXLOCK;
	if (vp->v_flag & VXWANT) {
		vp->v_flag &= ~VXWANT;
		wakeup((caddr_t) vp);
	}
}

/*
 * Eliminate all activity associated with  the requested vnode
 * and with all vnodes aliased to the requested vnode.
 */
void
vgoneall(vp)
	register struct vnode *vp;
{
	register struct vnode *vq;

	if (vp->v_flag & VALIASED) {
		/*
		 * If a vgone (or vclean) is already in progress, wait until
		 * it is done and return.
		 */
		if (vp->v_flag & VXLOCK) {
			vp->v_flag |= VXWANT;
			(void) tsleep((caddr_t) vp, PINOD, "vgall", 0);
			return;
		}
		/*
		 * Ensure that vp will not be vgone'd while we are eliminating
		 * its aliases.
		 */
		vp->v_flag |= VXLOCK;
		while (vp->v_flag & VALIASED) {
			for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
				if (vq->v_rdev != vp->v_rdev ||
				    vq->v_type != vp->v_type || vp == vq)
					continue;
				vgone(vq);
				break;
			}
		}
		/*
		 * Remove the lock so that vgone below will really eliminate
		 * the vnode after which time vgone will awaken any sleepers.
		 */
		vp->v_flag &= ~VXLOCK;
	}
	vgone(vp);
}

/*
 * Eliminate all activity associated with a vnode
 * in preparation for reuse.
 */
void
vgone(vp)
	register struct vnode *vp;
{
	register struct vnode *vq;
	struct vnode *vx;

	/*
	 * If a vgone (or vclean) is already in progress, wait until it is
	 * done and return.
	 */
	if (vp->v_flag & VXLOCK) {
		vp->v_flag |= VXWANT;
		(void) tsleep((caddr_t) vp, PINOD, "vgone", 0);
		return;
	}

	if (vp->v_object) {
		vp->v_object->flags |= OBJ_VNODE_GONE;
	}

	/*
	 * Clean out the filesystem specific data.
	 */
	vclean(vp, DOCLOSE);
	/*
	 * Delete from old mount point vnode list, if on one.
	 */
	if (vp->v_mount != NULL) {
		LIST_REMOVE(vp, v_mntvnodes);
		vp->v_mount = NULL;
	}
	/*
	 * If special device, remove it from special device alias list.
	 */
	if (vp->v_type == VBLK || vp->v_type == VCHR) {
		if (*vp->v_hashchain == vp) {
			*vp->v_hashchain = vp->v_specnext;
		} else {
			for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
				if (vq->v_specnext != vp)
					continue;
				vq->v_specnext = vp->v_specnext;
				break;
			}
			if (vq == NULL)
				panic("missing bdev");
		}
		if (vp->v_flag & VALIASED) {
			vx = NULL;
			for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
				if (vq->v_rdev != vp->v_rdev ||
				    vq->v_type != vp->v_type)
					continue;
				if (vx)
					break;
				vx = vq;
			}
			if (vx == NULL)
				panic("missing alias");
			if (vq == NULL)
				vx->v_flag &= ~VALIASED;
			vp->v_flag &= ~VALIASED;
		}
		FREE(vp->v_specinfo, M_VNODE);
		vp->v_specinfo = NULL;
	}
	/*
	 * If it is on the freelist and not already at the head, move it to
	 * the head of the list. The test of the back pointer and the
	 * reference count of zero is because it will be removed from the free
	 * list by getnewvnode, but will not have its reference count
	 * incremented until after calling vgone. If the reference count were
	 * incremented first, vgone would (incorrectly) try to close the
	 * previous instance of the underlying object. So, the back pointer is
	 * explicitly set to `0xdeadb' in getnewvnode after removing it from
	 * the freelist to ensure that we do not try to move it here.
	 */
	if (vp->v_usecount == 0 &&
	    vp->v_freelist.tqe_prev != (struct vnode **) 0xdeadb &&
	    vnode_free_list.tqh_first != vp) {
		if(vp->v_tag != VT_TFS) {
			TAILQ_REMOVE(&vnode_free_list, vp, v_freelist);
			TAILQ_INSERT_HEAD(&vnode_free_list, vp, v_freelist);
		}
	}
	vp->v_type = VBAD;
}

/*
 * Lookup a vnode by device number.
 */
int
vfinddev(dev, type, vpp)
	dev_t dev;
	enum vtype type;
	struct vnode **vpp;
{
	register struct vnode *vp;

	for (vp = speclisth[SPECHASH(dev)]; vp; vp = vp->v_specnext) {
		if (dev != vp->v_rdev || type != vp->v_type)
			continue;
		*vpp = vp;
		return (1);
	}
	return (0);
}

/*
 * Calculate the total number of references to a special device.
 */
int
vcount(vp)
	register struct vnode *vp;
{
	register struct vnode *vq, *vnext;
	int count;

loop:
	if ((vp->v_flag & VALIASED) == 0)
		return (vp->v_usecount);
	for (count = 0, vq = *vp->v_hashchain; vq; vq = vnext) {
		vnext = vq->v_specnext;
		if (vq->v_rdev != vp->v_rdev || vq->v_type != vp->v_type)
			continue;
		/*
		 * Alias, but not in use, so flush it out.
		 */
		if (vq->v_usecount == 0 && vq != vp) {
			vgone(vq);
			goto loop;
		}
		count += vq->v_usecount;
	}
	return (count);
}

/*
 * Print out a description of a vnode.
 */
static char *typename[] =
{"VNON", "VREG", "VDIR", "VBLK", "VCHR", "VLNK", "VSOCK", "VFIFO", "VBAD"};

void
vprint(label, vp)
	char *label;
	register struct vnode *vp;
{
	char buf[64];

	if (label != NULL)
		printf("%s: ", label);
	printf("type %s, usecount %d, writecount %d, refcount %ld,",
	    typename[vp->v_type], vp->v_usecount, vp->v_writecount,
	    vp->v_holdcnt);
	buf[0] = '\0';
	if (vp->v_flag & VROOT)
		strcat(buf, "|VROOT");
	if (vp->v_flag & VTEXT)
		strcat(buf, "|VTEXT");
	if (vp->v_flag & VSYSTEM)
		strcat(buf, "|VSYSTEM");
	if (vp->v_flag & VXLOCK)
		strcat(buf, "|VXLOCK");
	if (vp->v_flag & VXWANT)
		strcat(buf, "|VXWANT");
	if (vp->v_flag & VBWAIT)
		strcat(buf, "|VBWAIT");
	if (vp->v_flag & VALIASED)
		strcat(buf, "|VALIASED");
	if (buf[0] != '\0')
		printf(" flags (%s)", &buf[1]);
	if (vp->v_data == NULL) {
		printf("\n");
	} else {
		printf("\n\t");
		VOP_PRINT(vp);
	}
}

#ifdef DDB
/*
 * List all of the locked vnodes in the system.
 * Called when debugging the kernel.
 */
void
printlockedvnodes(void)
{
	register struct mount *mp;
	register struct vnode *vp;

	printf("Locked vnodes\n");
	for (mp = mountlist.cqh_first; mp != (void *)&mountlist;
	    mp = mp->mnt_list.cqe_next) {
		for (vp = mp->mnt_vnodelist.lh_first;
		    vp != NULL;
		    vp = vp->v_mntvnodes.le_next)
			if (VOP_ISLOCKED(vp))
				vprint((char *) 0, vp);
	}
}
#endif

int kinfo_vdebug = 1;
int kinfo_vgetfailed;

#define KINFO_VNODESLOP	10
/*
 * Dump vnode list (via sysctl).
 * Copyout address of vnode followed by vnode.
 */
/* ARGSUSED */
static int
sysctl_vnode SYSCTL_HANDLER_ARGS
{
	register struct mount *mp, *nmp;
	struct vnode *vp;
	int error;

#define VPTRSZ	sizeof (struct vnode *)
#define VNODESZ	sizeof (struct vnode)

	req->lock = 0;
	if (!req->oldptr) /* Make an estimate */
		return (SYSCTL_OUT(req, 0,
			(numvnodes + KINFO_VNODESLOP) * (VPTRSZ + VNODESZ)));

	for (mp = mountlist.cqh_first; mp != (void *)&mountlist; mp = nmp) {
		nmp = mp->mnt_list.cqe_next;
		if (vfs_busy(mp))
			continue;
again:
		for (vp = mp->mnt_vnodelist.lh_first;
		    vp != NULL;
		    vp = vp->v_mntvnodes.le_next) {
			/*
			 * Check that the vp is still associated with this
			 * filesystem.  RACE: could have been recycled onto
			 * the same filesystem.
			 */
			if (vp->v_mount != mp) {
				if (kinfo_vdebug)
					printf("kinfo: vp changed\n");
				goto again;
			}
			if ((error = SYSCTL_OUT(req, &vp, VPTRSZ)) ||
			    (error = SYSCTL_OUT(req, vp, VNODESZ))) {
				vfs_unbusy(mp);
				return (error);
			}
		}
		vfs_unbusy(mp);
	}

	return (0);
}

SYSCTL_PROC(_kern, KERN_VNODE, vnode, CTLTYPE_OPAQUE|CTLFLAG_RD,
	0, 0, sysctl_vnode, "S,vnode", "");

/*
 * Check to see if a filesystem is mounted on a block device.
 */
int
vfs_mountedon(vp)
	register struct vnode *vp;
{
	register struct vnode *vq;

	if (vp->v_specflags & SI_MOUNTEDON)
		return (EBUSY);
	if (vp->v_flag & VALIASED) {
		for (vq = *vp->v_hashchain; vq; vq = vq->v_specnext) {
			if (vq->v_rdev != vp->v_rdev ||
			    vq->v_type != vp->v_type)
				continue;
			if (vq->v_specflags & SI_MOUNTEDON)
				return (EBUSY);
		}
	}
	return (0);
}

/*
 * Build hash lists of net addresses and hang them off the mount point.
 * Called by ufs_mount() to set up the lists of export addresses.
 */
static int
vfs_hang_addrlist(struct mount *mp, struct netexport *nep, 
	struct export_args *argp)
{
	register struct netcred *np;
	register struct radix_node_head *rnh;
	register int i;
	struct radix_node *rn;
	struct sockaddr *saddr, *smask = 0;
	struct domain *dom;
	int error;

	if (argp->ex_addrlen == 0) {
		if (mp->mnt_flag & MNT_DEFEXPORTED)
			return (EPERM);
		np = &nep->ne_defexported;
		np->netc_exflags = argp->ex_flags;
		np->netc_anon = argp->ex_anon;
		np->netc_anon.cr_ref = 1;
		mp->mnt_flag |= MNT_DEFEXPORTED;
		return (0);
	}
	i = sizeof(struct netcred) + argp->ex_addrlen + argp->ex_masklen;
	np = (struct netcred *) malloc(i, M_NETADDR, M_WAITOK);
	bzero((caddr_t) np, i);
	saddr = (struct sockaddr *) (np + 1);
	if ((error = copyin(argp->ex_addr, (caddr_t) saddr, argp->ex_addrlen)))
		goto out;
	if (saddr->sa_len > argp->ex_addrlen)
		saddr->sa_len = argp->ex_addrlen;
	if (argp->ex_masklen) {
		smask = (struct sockaddr *) ((caddr_t) saddr + argp->ex_addrlen);
		error = copyin(argp->ex_addr, (caddr_t) smask, argp->ex_masklen);
		if (error)
			goto out;
		if (smask->sa_len > argp->ex_masklen)
			smask->sa_len = argp->ex_masklen;
	}
	i = saddr->sa_family;
	if ((rnh = nep->ne_rtable[i]) == 0) {
		/*
		 * Seems silly to initialize every AF when most are not used,
		 * do so on demand here
		 */
		for (dom = domains; dom; dom = dom->dom_next)
			if (dom->dom_family == i && dom->dom_rtattach) {
				dom->dom_rtattach((void **) &nep->ne_rtable[i],
				    dom->dom_rtoffset);
				break;
			}
		if ((rnh = nep->ne_rtable[i]) == 0) {
			error = ENOBUFS;
			goto out;
		}
	}
	rn = (*rnh->rnh_addaddr) ((caddr_t) saddr, (caddr_t) smask, rnh,
	    np->netc_rnodes);
	if (rn == 0 || np != (struct netcred *) rn) {	/* already exists */
		error = EPERM;
		goto out;
	}
	np->netc_exflags = argp->ex_flags;
	np->netc_anon = argp->ex_anon;
	np->netc_anon.cr_ref = 1;
	return (0);
out:
	free(np, M_NETADDR);
	return (error);
}

/* ARGSUSED */
static int
vfs_free_netcred(struct radix_node *rn, void *w)
{
	register struct radix_node_head *rnh = (struct radix_node_head *) w;

	(*rnh->rnh_deladdr) (rn->rn_key, rn->rn_mask, rnh);
	free((caddr_t) rn, M_NETADDR);
	return (0);
}

/*
 * Free the net address hash lists that are hanging off the mount points.
 */
static void
vfs_free_addrlist(struct netexport *nep)
{
	register int i;
	register struct radix_node_head *rnh;

	for (i = 0; i <= AF_MAX; i++)
		if ((rnh = nep->ne_rtable[i])) {
			(*rnh->rnh_walktree) (rnh, vfs_free_netcred,
			    (caddr_t) rnh);
			free((caddr_t) rnh, M_RTABLE);
			nep->ne_rtable[i] = 0;
		}
}

int
vfs_export(mp, nep, argp)
	struct mount *mp;
	struct netexport *nep;
	struct export_args *argp;
{
	int error;

	if (argp->ex_flags & MNT_DELEXPORT) {
		vfs_free_addrlist(nep);
		mp->mnt_flag &= ~(MNT_EXPORTED | MNT_DEFEXPORTED);
	}
	if (argp->ex_flags & MNT_EXPORTED) {
		if ((error = vfs_hang_addrlist(mp, nep, argp)))
			return (error);
		mp->mnt_flag |= MNT_EXPORTED;
	}
	return (0);
}

struct netcred *
vfs_export_lookup(mp, nep, nam)
	register struct mount *mp;
	struct netexport *nep;
	struct mbuf *nam;
{
	register struct netcred *np;
	register struct radix_node_head *rnh;
	struct sockaddr *saddr;

	np = NULL;
	if (mp->mnt_flag & MNT_EXPORTED) {
		/*
		 * Lookup in the export list first.
		 */
		if (nam != NULL) {
			saddr = mtod(nam, struct sockaddr *);
			rnh = nep->ne_rtable[saddr->sa_family];
			if (rnh != NULL) {
				np = (struct netcred *)
				    (*rnh->rnh_matchaddr) ((caddr_t) saddr,
				    rnh);
				if (np && np->netc_rnodes->rn_flags & RNF_ROOT)
					np = NULL;
			}
		}
		/*
		 * If no address match, use the default if it exists.
		 */
		if (np == NULL && mp->mnt_flag & MNT_DEFEXPORTED)
			np = &nep->ne_defexported;
	}
	return (np);
}


/*
 * perform msync on all vnodes under a mount point
 * the mount point must be locked.
 */
void
vfs_msync(struct mount *mp, int flags) {
	struct vnode *vp, *nvp;
loop:
	for (vp = mp->mnt_vnodelist.lh_first; vp != NULL; vp = nvp) {

		if (vp->v_mount != mp)
			goto loop;
		nvp = vp->v_mntvnodes.le_next;
		if (VOP_ISLOCKED(vp) && (flags != MNT_WAIT))
			continue;
		if (vp->v_object &&
		   (vp->v_object->flags & OBJ_MIGHTBEDIRTY)) {
			vm_object_page_clean(vp->v_object, 0, 0, TRUE, TRUE);
		}
	}
}

/*
 * Create the VM object needed for VMIO and mmap support.  This
 * is done for all VREG files in the system.  Some filesystems might
 * afford the additional metadata buffering capability of the
 * VMIO code by making the device node be VMIO mode also.
 */
int
vfs_object_create(vp, p, cred, waslocked)
	struct vnode *vp;
	struct proc *p;
	struct ucred *cred;
	int waslocked;
{
	struct vattr vat;
	vm_object_t object;
	int error = 0;

retry:
	if ((object = vp->v_object) == NULL) {
		if (vp->v_type == VREG) {
			if ((error = VOP_GETATTR(vp, &vat, cred, p)) != 0)
				goto retn;
			(void) vnode_pager_alloc(vp,
				OFF_TO_IDX(round_page(vat.va_size)), 0, 0);
		} else {
			/*
			 * This simply allocates the biggest object possible
			 * for a VBLK vnode.  This should be fixed, but doesn't
			 * cause any problems (yet).
			 */
			(void) vnode_pager_alloc(vp, INT_MAX, 0, 0);
		}
		vp->v_object->flags |= OBJ_VFS_REF;
	} else {
		if (object->flags & OBJ_DEAD) {
			if (waslocked)
				VOP_UNLOCK(vp);
			tsleep(object, PVM, "vodead", 0);
			if (waslocked)
				VOP_LOCK(vp);
			goto retry;
		}
		if ((object->flags & OBJ_VFS_REF) == 0) {
			object->flags |= OBJ_VFS_REF;
			vm_object_reference(object);
		}
	}
	if (vp->v_object)
		vp->v_flag |= VVMIO;

retn:
	return error;
}
OpenPOWER on IntegriCloud