aboutsummaryrefslogtreecommitdiff
path: root/sys/ufs/ffs/ffs_vnops.c
blob: 942a7e2c5fc477a784cfde159cdda839e512fb45 (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
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
/*-
 * Copyright (c) 2002, 2003 Networks Associates Technology, Inc.
 * All rights reserved.
 *
 * This software was developed for the FreeBSD Project by Marshall
 * Kirk McKusick and Network Associates Laboratories, the Security
 * Research Division of Network Associates, Inc. under DARPA/SPAWAR
 * contract N66001-01-C-8035 ("CBOSS"), as part of the DARPA CHATS
 * research program
 *
 * 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 *
 * Copyright (c) 1982, 1986, 1989, 1993
 *	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.
 *
 *	from: @(#)ufs_readwrite.c	8.11 (Berkeley) 5/8/95
 * from: $FreeBSD: .../ufs/ufs_readwrite.c,v 1.96 2002/08/12 09:22:11 phk ...
 *	@(#)ffs_vnops.c	8.15 (Berkeley) 5/14/95
 */

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

#include <sys/param.h>
#include <sys/bio.h>
#include <sys/systm.h>
#include <sys/buf.h>
#include <sys/conf.h>
#include <sys/extattr.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/stat.h>
#include <sys/vmmeter.h>
#include <sys/vnode.h>

#include <vm/vm.h>
#include <vm/vm_extern.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_pager.h>
#include <vm/vnode_pager.h>

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

#include <ufs/ffs/fs.h>
#include <ufs/ffs/ffs_extern.h>
#include "opt_directio.h"
#include "opt_ffs.h"

#ifdef DIRECTIO
extern int	ffs_rawread(struct vnode *vp, struct uio *uio, int *workdone);
#endif
static vop_fsync_t	ffs_fsync;
static vop_lock_t	ffs_lock;
static vop_getpages_t	ffs_getpages;
static vop_read_t	ffs_read;
static vop_write_t	ffs_write;
static int	ffs_extread(struct vnode *vp, struct uio *uio, int ioflag);
static int	ffs_extwrite(struct vnode *vp, struct uio *uio, int ioflag,
		    struct ucred *cred);
static vop_strategy_t	ffsext_strategy;
static vop_closeextattr_t	ffs_closeextattr;
static vop_deleteextattr_t	ffs_deleteextattr;
static vop_getextattr_t	ffs_getextattr;
static vop_listextattr_t	ffs_listextattr;
static vop_openextattr_t	ffs_openextattr;
static vop_setextattr_t	ffs_setextattr;


/* Global vfs data structures for ufs. */
struct vop_vector ffs_vnodeops = {
	.vop_default =		&ufs_vnodeops,
	.vop_fsync =		ffs_fsync,
	.vop_getpages =		ffs_getpages,
	.vop_lock =		ffs_lock,
	.vop_read =		ffs_read,
	.vop_reallocblks =	ffs_reallocblks,
	.vop_write =		ffs_write,
	.vop_closeextattr =	ffs_closeextattr,
	.vop_deleteextattr =	ffs_deleteextattr,
	.vop_getextattr =	ffs_getextattr,
	.vop_listextattr =	ffs_listextattr,
	.vop_openextattr =	ffs_openextattr,
	.vop_setextattr =	ffs_setextattr,
};

struct vop_vector ffs_fifoops = {
	.vop_default =		&ufs_fifoops,
	.vop_fsync =		ffs_fsync,
	.vop_lock =		ffs_lock,
	.vop_reallocblks =	ffs_reallocblks,
	.vop_strategy =		ffsext_strategy,
	.vop_closeextattr =	ffs_closeextattr,
	.vop_deleteextattr =	ffs_deleteextattr,
	.vop_getextattr =	ffs_getextattr,
	.vop_listextattr =	ffs_listextattr,
	.vop_openextattr =	ffs_openextattr,
	.vop_setextattr =	ffs_setextattr,
};

/*
 * Synch an open file.
 */
/* ARGSUSED */
static int
ffs_fsync(struct vop_fsync_args *ap)
{
	int error;

	error = ffs_syncvnode(ap->a_vp, ap->a_waitfor);
#ifdef SOFTUPDATES
	if (error)
		return (error);
	if (ap->a_waitfor == MNT_WAIT &&
	    (ap->a_vp->v_mount->mnt_flag & MNT_SOFTDEP))
		error = softdep_fsync(ap->a_vp);
#endif
	return (error);
}

int
ffs_syncvnode(struct vnode *vp, int waitfor)
{
	struct inode *ip = VTOI(vp);
	struct buf *bp;
	struct buf *nbp;
	int s, error, wait, passes, skipmeta;
	ufs_lbn_t lbn;

	wait = (waitfor == MNT_WAIT);
	lbn = lblkno(ip->i_fs, (ip->i_size + ip->i_fs->fs_bsize - 1));

	/*
	 * Flush all dirty buffers associated with a vnode.
	 */
	passes = NIADDR + 1;
	skipmeta = 0;
	if (wait)
		skipmeta = 1;
	s = splbio();
	VI_LOCK(vp);
loop:
	TAILQ_FOREACH(bp, &vp->v_bufobj.bo_dirty.bv_hd, b_bobufs)
		bp->b_vflags &= ~BV_SCANNED;
	TAILQ_FOREACH_SAFE(bp, &vp->v_bufobj.bo_dirty.bv_hd, b_bobufs, nbp) {
		/* 
		 * Reasons to skip this buffer: it has already been considered
		 * on this pass, this pass is the first time through on a
		 * synchronous flush request and the buffer being considered
		 * is metadata, the buffer has dependencies that will cause
		 * it to be redirtied and it has not already been deferred,
		 * or it is already being written.
		 */
		if ((bp->b_vflags & BV_SCANNED) != 0)
			continue;
		bp->b_vflags |= BV_SCANNED;
		if ((skipmeta == 1 && bp->b_lblkno < 0))
			continue;
		if (BUF_LOCK(bp, LK_EXCLUSIVE | LK_NOWAIT, NULL))
			continue;
		VI_UNLOCK(vp);
		if (!wait && LIST_FIRST(&bp->b_dep) != NULL &&
		    (bp->b_flags & B_DEFERRED) == 0 &&
		    buf_countdeps(bp, 0)) {
			bp->b_flags |= B_DEFERRED;
			BUF_UNLOCK(bp);
			VI_LOCK(vp);
			continue;
		}
		if ((bp->b_flags & B_DELWRI) == 0)
			panic("ffs_fsync: not dirty");
		/*
		 * If this is a synchronous flush request, or it is not a
		 * file or device, start the write on this buffer immediatly.
		 */
		if (wait || (vp->v_type != VREG && vp->v_type != VBLK)) {

			/*
			 * On our final pass through, do all I/O synchronously
			 * so that we can find out if our flush is failing
			 * because of write errors.
			 */
			if (passes > 0 || !wait) {
				if ((bp->b_flags & B_CLUSTEROK) && !wait) {
					(void) vfs_bio_awrite(bp);
				} else {
					bremfree(bp);
					splx(s);
					(void) bawrite(bp);
					s = splbio();
				}
			} else {
				bremfree(bp);
				splx(s);
				if ((error = bwrite(bp)) != 0)
					return (error);
				s = splbio();
			}
		} else if ((vp->v_type == VREG) && (bp->b_lblkno >= lbn)) {
			/* 
			 * If the buffer is for data that has been truncated
			 * off the file, then throw it away.
			 */
			bremfree(bp);
			bp->b_flags |= B_INVAL | B_NOCACHE;
			splx(s);
			brelse(bp);
			s = splbio();
		} else
			vfs_bio_awrite(bp);

		/*
		 * Since we may have slept during the I/O, we need 
		 * to start from a known point.
		 */
		VI_LOCK(vp);
		nbp = TAILQ_FIRST(&vp->v_bufobj.bo_dirty.bv_hd);
	}
	/*
	 * If we were asked to do this synchronously, then go back for
	 * another pass, this time doing the metadata.
	 */
	if (skipmeta) {
		skipmeta = 0;
		goto loop;
	}

	if (wait) {
		bufobj_wwait(&vp->v_bufobj, 3, 0);
		VI_UNLOCK(vp);

		/* 
		 * Ensure that any filesystem metatdata associated
		 * with the vnode has been written.
		 */
		splx(s);
		if ((error = softdep_sync_metadata(vp)) != 0)
			return (error);
		s = splbio();

		VI_LOCK(vp);
		if (vp->v_bufobj.bo_dirty.bv_cnt > 0) {
			/*
			 * Block devices associated with filesystems may
			 * have new I/O requests posted for them even if
			 * the vnode is locked, so no amount of trying will
			 * get them clean. Thus we give block devices a
			 * good effort, then just give up. For all other file
			 * types, go around and try again until it is clean.
			 */
			if (passes > 0) {
				passes -= 1;
				goto loop;
			}
#ifdef DIAGNOSTIC
			if (!vn_isdisk(vp, NULL))
				vprint("ffs_fsync: dirty", vp);
#endif
		}
	}
	VI_UNLOCK(vp);
	splx(s);
	return (ffs_update(vp, wait));
}

/*
 * Snapshots require all lock requests to be exclusive.
 */
static int
ffs_lock(ap)
	struct vop_lock_args /* {
		struct vnode *a_vp;
		int a_flags;
		struct thread *a_td;
	} */ *ap;
{
	struct vnode *vp = ap->a_vp;

	if ((VTOI(vp)->i_flags & SF_SNAPSHOT) &&
	    ((ap->a_flags & LK_TYPE_MASK) == LK_SHARED)) {
		ap->a_flags &= ~LK_TYPE_MASK;
		ap->a_flags |= LK_EXCLUSIVE;
	}
	return (VOP_LOCK_APV(&ufs_vnodeops, ap));
}

/*
 * Vnode op for reading.
 */
/* ARGSUSED */
static int
ffs_read(ap)
	struct vop_read_args /* {
		struct vnode *a_vp;
		struct uio *a_uio;
		int a_ioflag;
		struct ucred *a_cred;
	} */ *ap;
{
	struct vnode *vp;
	struct inode *ip;
	struct uio *uio;
	struct fs *fs;
	struct buf *bp;
	ufs_lbn_t lbn, nextlbn;
	off_t bytesinfile;
	long size, xfersize, blkoffset;
	int error, orig_resid;
	int seqcount;
	int ioflag;

	vp = ap->a_vp;
	uio = ap->a_uio;
	ioflag = ap->a_ioflag;
	if (ap->a_ioflag & IO_EXT)
#ifdef notyet
		return (ffs_extread(vp, uio, ioflag));
#else
		panic("ffs_read+IO_EXT");
#endif
#ifdef DIRECTIO
	if ((ioflag & IO_DIRECT) != 0) {
		int workdone;

		error = ffs_rawread(vp, uio, &workdone);
		if (error != 0 || workdone != 0)
			return error;
	}
#endif

	seqcount = ap->a_ioflag >> IO_SEQSHIFT;
	ip = VTOI(vp);

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_READ)
		panic("ffs_read: mode");

	if (vp->v_type == VLNK) {
		if ((int)ip->i_size < vp->v_mount->mnt_maxsymlinklen)
			panic("ffs_read: short symlink");
	} else if (vp->v_type != VREG && vp->v_type != VDIR)
		panic("ffs_read: type %d",  vp->v_type);
#endif
	orig_resid = uio->uio_resid;
	KASSERT(orig_resid >= 0, ("ffs_read: uio->uio_resid < 0"));
	if (orig_resid == 0)
		return (0);
	KASSERT(uio->uio_offset >= 0, ("ffs_read: uio->uio_offset < 0"));
	fs = ip->i_fs;
	if (uio->uio_offset < ip->i_size &&
	    uio->uio_offset >= fs->fs_maxfilesize)
		return (EOVERFLOW);

	for (error = 0, bp = NULL; uio->uio_resid > 0; bp = NULL) {
		if ((bytesinfile = ip->i_size - uio->uio_offset) <= 0)
			break;
		lbn = lblkno(fs, uio->uio_offset);
		nextlbn = lbn + 1;

		/*
		 * size of buffer.  The buffer representing the
		 * end of the file is rounded up to the size of
		 * the block type ( fragment or full block, 
		 * depending ).
		 */
		size = blksize(fs, ip, lbn);
		blkoffset = blkoff(fs, uio->uio_offset);
		
		/*
		 * The amount we want to transfer in this iteration is
		 * one FS block less the amount of the data before
		 * our startpoint (duh!)
		 */
		xfersize = fs->fs_bsize - blkoffset;

		/*
		 * But if we actually want less than the block,
		 * or the file doesn't have a whole block more of data,
		 * then use the lesser number.
		 */
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;
		if (bytesinfile < xfersize)
			xfersize = bytesinfile;

		if (lblktosize(fs, nextlbn) >= ip->i_size) {
			/*
			 * Don't do readahead if this is the end of the file.
			 */
			error = bread(vp, lbn, size, NOCRED, &bp);
		} else if ((vp->v_mount->mnt_flag & MNT_NOCLUSTERR) == 0) {
			/* 
			 * Otherwise if we are allowed to cluster,
			 * grab as much as we can.
			 *
			 * XXX  This may not be a win if we are not
			 * doing sequential access.
			 */
			error = cluster_read(vp, ip->i_size, lbn,
				size, NOCRED, uio->uio_resid, seqcount, &bp);
		} else if (seqcount > 1) {
			/*
			 * If we are NOT allowed to cluster, then
			 * if we appear to be acting sequentially,
			 * fire off a request for a readahead
			 * as well as a read. Note that the 4th and 5th
			 * arguments point to arrays of the size specified in
			 * the 6th argument.
			 */
			int nextsize = blksize(fs, ip, nextlbn);
			error = breadn(vp, lbn,
			    size, &nextlbn, &nextsize, 1, NOCRED, &bp);
		} else {
			/*
			 * Failing all of the above, just read what the 
			 * user asked for. Interestingly, the same as
			 * the first option above.
			 */
			error = bread(vp, lbn, size, NOCRED, &bp);
		}
		if (error) {
			brelse(bp);
			bp = NULL;
			break;
		}

		/*
		 * If IO_DIRECT then set B_DIRECT for the buffer.  This
		 * will cause us to attempt to release the buffer later on
		 * and will cause the buffer cache to attempt to free the
		 * underlying pages.
		 */
		if (ioflag & IO_DIRECT)
			bp->b_flags |= B_DIRECT;

		/*
		 * We should only get non-zero b_resid when an I/O error
		 * has occurred, which should cause us to break above.
		 * However, if the short read did not cause an error,
		 * then we want to ensure that we do not uiomove bad
		 * or uninitialized data.
		 */
		size -= bp->b_resid;
		if (size < xfersize) {
			if (size == 0)
				break;
			xfersize = size;
		}

		error = uiomove((char *)bp->b_data + blkoffset,
		    (int)xfersize, uio);
		if (error)
			break;

		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			/*
			 * If there are no dependencies, and it's VMIO,
			 * then we don't need the buf, mark it available
			 * for freeing. The VM has the data.
			 */
			bp->b_flags |= B_RELBUF;
			brelse(bp);
		} else {
			/*
			 * Otherwise let whoever
			 * made the request take care of
			 * freeing it. We just queue
			 * it onto another list.
			 */
			bqrelse(bp);
		}
	}

	/* 
	 * This can only happen in the case of an error
	 * because the loop above resets bp to NULL on each iteration
	 * and on normal completion has not set a new value into it.
	 * so it must have come from a 'break' statement
	 */
	if (bp != NULL) {
		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			bp->b_flags |= B_RELBUF;
			brelse(bp);
		} else {
			bqrelse(bp);
		}
	}

	if ((error == 0 || uio->uio_resid != orig_resid) &&
	    (vp->v_mount->mnt_flag & MNT_NOATIME) == 0)
		ip->i_flag |= IN_ACCESS;
	return (error);
}

/*
 * Vnode op for writing.
 */
static int
ffs_write(ap)
	struct vop_write_args /* {
		struct vnode *a_vp;
		struct uio *a_uio;
		int a_ioflag;
		struct ucred *a_cred;
	} */ *ap;
{
	struct vnode *vp;
	struct uio *uio;
	struct inode *ip;
	struct fs *fs;
	struct buf *bp;
	struct thread *td;
	ufs_lbn_t lbn;
	off_t osize;
	int seqcount;
	int blkoffset, error, extended, flags, ioflag, resid, size, xfersize;

	vp = ap->a_vp;
	uio = ap->a_uio;
	ioflag = ap->a_ioflag;
	if (ap->a_ioflag & IO_EXT)
#ifdef notyet
		return (ffs_extwrite(vp, uio, ioflag, ap->a_cred));
#else
		panic("ffs_write+IO_EXT");
#endif

	extended = 0;
	seqcount = ap->a_ioflag >> IO_SEQSHIFT;
	ip = VTOI(vp);

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_WRITE)
		panic("ffs_write: mode");
#endif

	switch (vp->v_type) {
	case VREG:
		if (ioflag & IO_APPEND)
			uio->uio_offset = ip->i_size;
		if ((ip->i_flags & APPEND) && uio->uio_offset != ip->i_size)
			return (EPERM);
		/* FALLTHROUGH */
	case VLNK:
		break;
	case VDIR:
		panic("ffs_write: dir write");
		break;
	default:
		panic("ffs_write: type %p %d (%d,%d)", vp, (int)vp->v_type,
			(int)uio->uio_offset,
			(int)uio->uio_resid
		);
	}

	KASSERT(uio->uio_resid >= 0, ("ffs_write: uio->uio_resid < 0"));
	KASSERT(uio->uio_offset >= 0, ("ffs_write: uio->uio_offset < 0"));
	fs = ip->i_fs;
	if ((uoff_t)uio->uio_offset + uio->uio_resid > fs->fs_maxfilesize)
		return (EFBIG);
	/*
	 * Maybe this should be above the vnode op call, but so long as
	 * file servers have no limits, I don't think it matters.
	 */
	td = uio->uio_td;
	if (vp->v_type == VREG && td != NULL) {
		PROC_LOCK(td->td_proc);
		if (uio->uio_offset + uio->uio_resid >
		    lim_cur(td->td_proc, RLIMIT_FSIZE)) {
			psignal(td->td_proc, SIGXFSZ);
			PROC_UNLOCK(td->td_proc);
			return (EFBIG);
		}
		PROC_UNLOCK(td->td_proc);
	}

	resid = uio->uio_resid;
	osize = ip->i_size;
	if (seqcount > BA_SEQMAX)
		flags = BA_SEQMAX << BA_SEQSHIFT;
	else
		flags = seqcount << BA_SEQSHIFT;
	if ((ioflag & IO_SYNC) && !DOINGASYNC(vp))
		flags |= IO_SYNC;

	for (error = 0; uio->uio_resid > 0;) {
		lbn = lblkno(fs, uio->uio_offset);
		blkoffset = blkoff(fs, uio->uio_offset);
		xfersize = fs->fs_bsize - blkoffset;
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;
		if (uio->uio_offset + xfersize > ip->i_size)
			vnode_pager_setsize(vp, uio->uio_offset + xfersize);

                /*      
		 * We must perform a read-before-write if the transfer size
		 * does not cover the entire buffer.
                 */
		if (fs->fs_bsize > xfersize)
			flags |= BA_CLRBUF;
		else
			flags &= ~BA_CLRBUF;
/* XXX is uio->uio_offset the right thing here? */
		error = UFS_BALLOC(vp, uio->uio_offset, xfersize,
		    ap->a_cred, flags, &bp);
		if (error != 0)
			break;
		/*
		 * If the buffer is not valid we have to clear out any
		 * garbage data from the pages instantiated for the buffer.
		 * If we do not, a failed uiomove() during a write can leave
		 * the prior contents of the pages exposed to a userland
		 * mmap().  XXX deal with uiomove() errors a better way.
		 */
		if ((bp->b_flags & B_CACHE) == 0 && fs->fs_bsize <= xfersize)
			vfs_bio_clrbuf(bp);
		if (ioflag & IO_DIRECT)
			bp->b_flags |= B_DIRECT;
		if ((ioflag & (IO_SYNC|IO_INVAL)) == (IO_SYNC|IO_INVAL))
			bp->b_flags |= B_NOCACHE;

		if (uio->uio_offset + xfersize > ip->i_size) {
			ip->i_size = uio->uio_offset + xfersize;
			DIP_SET(ip, i_size, ip->i_size);
			extended = 1;
		}

		size = blksize(fs, ip, lbn) - bp->b_resid;
		if (size < xfersize)
			xfersize = size;

		error =
		    uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			bp->b_flags |= B_RELBUF;
		}

		/*
		 * If IO_SYNC each buffer is written synchronously.  Otherwise
		 * if we have a severe page deficiency write the buffer 
		 * asynchronously.  Otherwise try to cluster, and if that
		 * doesn't do it then either do an async write (if O_DIRECT),
		 * or a delayed write (if not).
		 */
		if (ioflag & IO_SYNC) {
			(void)bwrite(bp);
		} else if (vm_page_count_severe() ||
			    buf_dirty_count_severe() ||
			    (ioflag & IO_ASYNC)) {
			bp->b_flags |= B_CLUSTEROK;
			bawrite(bp);
		} else if (xfersize + blkoffset == fs->fs_bsize) {
			if ((vp->v_mount->mnt_flag & MNT_NOCLUSTERW) == 0) {
				bp->b_flags |= B_CLUSTEROK;
				cluster_write(vp, bp, ip->i_size, seqcount);
			} else {
				bawrite(bp);
			}
		} else if (ioflag & IO_DIRECT) {
			bp->b_flags |= B_CLUSTEROK;
			bawrite(bp);
		} else {
			bp->b_flags |= B_CLUSTEROK;
			bdwrite(bp);
		}
		if (error || xfersize == 0)
			break;
		ip->i_flag |= IN_CHANGE | IN_UPDATE;
	}
	/*
	 * If we successfully wrote any data, and we are not the superuser
	 * we clear the setuid and setgid bits as a precaution against
	 * tampering.
	 */
	if (resid > uio->uio_resid && ap->a_cred && 
	    suser_cred(ap->a_cred, SUSER_ALLOWJAIL)) {
		ip->i_mode &= ~(ISUID | ISGID);
		DIP_SET(ip, i_mode, ip->i_mode);
	}
	if (resid > uio->uio_resid)
		VN_KNOTE_UNLOCKED(vp, NOTE_WRITE | (extended ? NOTE_EXTEND : 0));
	if (error) {
		if (ioflag & IO_UNIT) {
			(void)ffs_truncate(vp, osize,
			    IO_NORMAL | (ioflag & IO_SYNC),
			    ap->a_cred, uio->uio_td);
			uio->uio_offset -= resid - uio->uio_resid;
			uio->uio_resid = resid;
		}
	} else if (resid > uio->uio_resid && (ioflag & IO_SYNC))
		error = ffs_update(vp, 1);
	return (error);
}

/*
 * get page routine
 */
static int
ffs_getpages(ap)
	struct vop_getpages_args *ap;
{
	int i;
	vm_page_t mreq;
	int pcount;

	pcount = round_page(ap->a_count) / PAGE_SIZE;
	mreq = ap->a_m[ap->a_reqpage];

	/*
	 * if ANY DEV_BSIZE blocks are valid on a large filesystem block,
	 * then the entire page is valid.  Since the page may be mapped,
	 * user programs might reference data beyond the actual end of file
	 * occuring within the page.  We have to zero that data.
	 */
	VM_OBJECT_LOCK(mreq->object);
	if (mreq->valid) {
		if (mreq->valid != VM_PAGE_BITS_ALL)
			vm_page_zero_invalid(mreq, TRUE);
		vm_page_lock_queues();
		for (i = 0; i < pcount; i++) {
			if (i != ap->a_reqpage) {
				vm_page_free(ap->a_m[i]);
			}
		}
		vm_page_unlock_queues();
		VM_OBJECT_UNLOCK(mreq->object);
		return VM_PAGER_OK;
	}
	VM_OBJECT_UNLOCK(mreq->object);

	return vnode_pager_generic_getpages(ap->a_vp, ap->a_m,
					    ap->a_count,
					    ap->a_reqpage);
}


/*
 * Extended attribute area reading.
 */
static int
ffs_extread(struct vnode *vp, struct uio *uio, int ioflag)
{
	struct inode *ip;
	struct ufs2_dinode *dp;
	struct fs *fs;
	struct buf *bp;
	ufs_lbn_t lbn, nextlbn;
	off_t bytesinfile;
	long size, xfersize, blkoffset;
	int error, orig_resid;

	ip = VTOI(vp);
	fs = ip->i_fs;
	dp = ip->i_din2;

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_READ || fs->fs_magic != FS_UFS2_MAGIC)
		panic("ffs_extread: mode");

#endif
	orig_resid = uio->uio_resid;
	KASSERT(orig_resid >= 0, ("ffs_extread: uio->uio_resid < 0"));
	if (orig_resid == 0)
		return (0);
	KASSERT(uio->uio_offset >= 0, ("ffs_extread: uio->uio_offset < 0"));

	for (error = 0, bp = NULL; uio->uio_resid > 0; bp = NULL) {
		if ((bytesinfile = dp->di_extsize - uio->uio_offset) <= 0)
			break;
		lbn = lblkno(fs, uio->uio_offset);
		nextlbn = lbn + 1;

		/*
		 * size of buffer.  The buffer representing the
		 * end of the file is rounded up to the size of
		 * the block type ( fragment or full block, 
		 * depending ).
		 */
		size = sblksize(fs, dp->di_extsize, lbn);
		blkoffset = blkoff(fs, uio->uio_offset);
		
		/*
		 * The amount we want to transfer in this iteration is
		 * one FS block less the amount of the data before
		 * our startpoint (duh!)
		 */
		xfersize = fs->fs_bsize - blkoffset;

		/*
		 * But if we actually want less than the block,
		 * or the file doesn't have a whole block more of data,
		 * then use the lesser number.
		 */
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;
		if (bytesinfile < xfersize)
			xfersize = bytesinfile;

		if (lblktosize(fs, nextlbn) >= dp->di_extsize) {
			/*
			 * Don't do readahead if this is the end of the info.
			 */
			error = bread(vp, -1 - lbn, size, NOCRED, &bp);
		} else {
			/*
			 * If we have a second block, then
			 * fire off a request for a readahead
			 * as well as a read. Note that the 4th and 5th
			 * arguments point to arrays of the size specified in
			 * the 6th argument.
			 */
			int nextsize = sblksize(fs, dp->di_extsize, nextlbn);

			nextlbn = -1 - nextlbn;
			error = breadn(vp, -1 - lbn,
			    size, &nextlbn, &nextsize, 1, NOCRED, &bp);
		}
		if (error) {
			brelse(bp);
			bp = NULL;
			break;
		}

		/*
		 * If IO_DIRECT then set B_DIRECT for the buffer.  This
		 * will cause us to attempt to release the buffer later on
		 * and will cause the buffer cache to attempt to free the
		 * underlying pages.
		 */
		if (ioflag & IO_DIRECT)
			bp->b_flags |= B_DIRECT;

		/*
		 * We should only get non-zero b_resid when an I/O error
		 * has occurred, which should cause us to break above.
		 * However, if the short read did not cause an error,
		 * then we want to ensure that we do not uiomove bad
		 * or uninitialized data.
		 */
		size -= bp->b_resid;
		if (size < xfersize) {
			if (size == 0)
				break;
			xfersize = size;
		}

		error = uiomove((char *)bp->b_data + blkoffset,
					(int)xfersize, uio);
		if (error)
			break;

		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			/*
			 * If there are no dependencies, and it's VMIO,
			 * then we don't need the buf, mark it available
			 * for freeing. The VM has the data.
			 */
			bp->b_flags |= B_RELBUF;
			brelse(bp);
		} else {
			/*
			 * Otherwise let whoever
			 * made the request take care of
			 * freeing it. We just queue
			 * it onto another list.
			 */
			bqrelse(bp);
		}
	}

	/* 
	 * This can only happen in the case of an error
	 * because the loop above resets bp to NULL on each iteration
	 * and on normal completion has not set a new value into it.
	 * so it must have come from a 'break' statement
	 */
	if (bp != NULL) {
		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			bp->b_flags |= B_RELBUF;
			brelse(bp);
		} else {
			bqrelse(bp);
		}
	}

	if ((error == 0 || uio->uio_resid != orig_resid) &&
	    (vp->v_mount->mnt_flag & MNT_NOATIME) == 0)
		ip->i_flag |= IN_ACCESS;
	return (error);
}

/*
 * Extended attribute area writing.
 */
static int
ffs_extwrite(struct vnode *vp, struct uio *uio, int ioflag, struct ucred *ucred)
{
	struct inode *ip;
	struct ufs2_dinode *dp;
	struct fs *fs;
	struct buf *bp;
	ufs_lbn_t lbn;
	off_t osize;
	int blkoffset, error, flags, resid, size, xfersize;

	ip = VTOI(vp);
	fs = ip->i_fs;
	dp = ip->i_din2;

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_WRITE || fs->fs_magic != FS_UFS2_MAGIC)
		panic("ffs_extwrite: mode");
#endif

	if (ioflag & IO_APPEND)
		uio->uio_offset = dp->di_extsize;
	KASSERT(uio->uio_offset >= 0, ("ffs_extwrite: uio->uio_offset < 0"));
	KASSERT(uio->uio_resid >= 0, ("ffs_extwrite: uio->uio_resid < 0"));
	if ((uoff_t)uio->uio_offset + uio->uio_resid > NXADDR * fs->fs_bsize)
		return (EFBIG);

	resid = uio->uio_resid;
	osize = dp->di_extsize;
	flags = IO_EXT;
	if ((ioflag & IO_SYNC) && !DOINGASYNC(vp))
		flags |= IO_SYNC;

	for (error = 0; uio->uio_resid > 0;) {
		lbn = lblkno(fs, uio->uio_offset);
		blkoffset = blkoff(fs, uio->uio_offset);
		xfersize = fs->fs_bsize - blkoffset;
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;

                /*      
		 * We must perform a read-before-write if the transfer size
		 * does not cover the entire buffer.
                 */
		if (fs->fs_bsize > xfersize)
			flags |= BA_CLRBUF;
		else
			flags &= ~BA_CLRBUF;
		error = UFS_BALLOC(vp, uio->uio_offset, xfersize,
		    ucred, flags, &bp);
		if (error != 0)
			break;
		/*
		 * If the buffer is not valid we have to clear out any
		 * garbage data from the pages instantiated for the buffer.
		 * If we do not, a failed uiomove() during a write can leave
		 * the prior contents of the pages exposed to a userland
		 * mmap().  XXX deal with uiomove() errors a better way.
		 */
		if ((bp->b_flags & B_CACHE) == 0 && fs->fs_bsize <= xfersize)
			vfs_bio_clrbuf(bp);
		if (ioflag & IO_DIRECT)
			bp->b_flags |= B_DIRECT;

		if (uio->uio_offset + xfersize > dp->di_extsize)
			dp->di_extsize = uio->uio_offset + xfersize;

		size = sblksize(fs, dp->di_extsize, lbn) - bp->b_resid;
		if (size < xfersize)
			xfersize = size;

		error =
		    uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
		if ((ioflag & (IO_VMIO|IO_DIRECT)) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) {
			bp->b_flags |= B_RELBUF;
		}

		/*
		 * If IO_SYNC each buffer is written synchronously.  Otherwise
		 * if we have a severe page deficiency write the buffer 
		 * asynchronously.  Otherwise try to cluster, and if that
		 * doesn't do it then either do an async write (if O_DIRECT),
		 * or a delayed write (if not).
		 */
		if (ioflag & IO_SYNC) {
			(void)bwrite(bp);
		} else if (vm_page_count_severe() ||
			    buf_dirty_count_severe() ||
			    xfersize + blkoffset == fs->fs_bsize ||
			    (ioflag & (IO_ASYNC | IO_DIRECT)))
			bawrite(bp);
		else
			bdwrite(bp);
		if (error || xfersize == 0)
			break;
		ip->i_flag |= IN_CHANGE | IN_UPDATE;
	}
	/*
	 * If we successfully wrote any data, and we are not the superuser
	 * we clear the setuid and setgid bits as a precaution against
	 * tampering.
	 */
	if (resid > uio->uio_resid && ucred && 
	    suser_cred(ucred, SUSER_ALLOWJAIL)) {
		ip->i_mode &= ~(ISUID | ISGID);
		dp->di_mode = ip->i_mode;
	}
	if (error) {
		if (ioflag & IO_UNIT) {
			(void)ffs_truncate(vp, osize,
			    IO_EXT | (ioflag&IO_SYNC), ucred, uio->uio_td);
			uio->uio_offset -= resid - uio->uio_resid;
			uio->uio_resid = resid;
		}
	} else if (resid > uio->uio_resid && (ioflag & IO_SYNC))
		error = ffs_update(vp, 1);
	return (error);
}


/*
 * Vnode operating to retrieve a named extended attribute.
 *
 * Locate a particular EA (nspace:name) in the area (ptr:length), and return
 * the length of the EA, and possibly the pointer to the entry and to the data.
 */
static int
ffs_findextattr(u_char *ptr, u_int length, int nspace, const char *name, u_char **eap, u_char **eac)
{
	u_char *p, *pe, *pn, *p0;
	int eapad1, eapad2, ealength, ealen, nlen;
	uint32_t ul;

	pe = ptr + length;
	nlen = strlen(name);

	for (p = ptr; p < pe; p = pn) {
		p0 = p;
		bcopy(p, &ul, sizeof(ul));
		pn = p + ul;
		/* make sure this entry is complete */
		if (pn > pe)
			break;
		p += sizeof(uint32_t);
		if (*p != nspace)
			continue;
		p++;
		eapad2 = *p++;
		if (*p != nlen)
			continue;
		p++;
		if (bcmp(p, name, nlen))
			continue;
		ealength = sizeof(uint32_t) + 3 + nlen;
		eapad1 = 8 - (ealength % 8);
		if (eapad1 == 8)
			eapad1 = 0;
		ealength += eapad1;
		ealen = ul - ealength - eapad2;
		p += nlen + eapad1;
		if (eap != NULL)
			*eap = p0;
		if (eac != NULL)
			*eac = p;
		return (ealen);
	}
	return(-1);
}

static int
ffs_rdextattr(u_char **p, struct vnode *vp, struct thread *td, int extra)
{
	struct inode *ip;
	struct ufs2_dinode *dp;
	struct uio luio;
	struct iovec liovec;
	int easize, error;
	u_char *eae;

	ip = VTOI(vp);
	dp = ip->i_din2;
	easize = dp->di_extsize;

	eae = malloc(easize + extra, M_TEMP, M_WAITOK);

	liovec.iov_base = eae;
	liovec.iov_len = easize;
	luio.uio_iov = &liovec;
	luio.uio_iovcnt = 1;
	luio.uio_offset = 0;
	luio.uio_resid = easize;
	luio.uio_segflg = UIO_SYSSPACE;
	luio.uio_rw = UIO_READ;
	luio.uio_td = td;

	error = ffs_extread(vp, &luio, IO_EXT | IO_SYNC);
	if (error) {
		free(eae, M_TEMP);
		return(error);
	}
	*p = eae;
	return (0);
}

static int
ffs_open_ea(struct vnode *vp, struct ucred *cred, struct thread *td)
{
	struct inode *ip;
	struct ufs2_dinode *dp;
	int error;

	ip = VTOI(vp);

	if (ip->i_ea_area != NULL)
		return (EBUSY);
	dp = ip->i_din2;
	error = ffs_rdextattr(&ip->i_ea_area, vp, td, 0);
	if (error)
		return (error);
	ip->i_ea_len = dp->di_extsize;
	ip->i_ea_error = 0;
	return (0);
}

/*
 * Vnode extattr transaction commit/abort
 */
static int
ffs_close_ea(struct vnode *vp, int commit, struct ucred *cred, struct thread *td)
{
	struct inode *ip;
	struct uio luio;
	struct iovec liovec;
	int error;
	struct ufs2_dinode *dp;

	ip = VTOI(vp);
	if (ip->i_ea_area == NULL)
		return (EINVAL);
	dp = ip->i_din2;
	error = ip->i_ea_error;
	if (commit && error == 0) {
		if (cred == NOCRED)
			cred =  vp->v_mount->mnt_cred;
		liovec.iov_base = ip->i_ea_area;
		liovec.iov_len = ip->i_ea_len;
		luio.uio_iov = &liovec;
		luio.uio_iovcnt = 1;
		luio.uio_offset = 0;
		luio.uio_resid = ip->i_ea_len;
		luio.uio_segflg = UIO_SYSSPACE;
		luio.uio_rw = UIO_WRITE;
		luio.uio_td = td;
		/* XXX: I'm not happy about truncating to zero size */
		if (ip->i_ea_len < dp->di_extsize)
			error = ffs_truncate(vp, 0, IO_EXT, cred, td);
		error = ffs_extwrite(vp, &luio, IO_EXT | IO_SYNC, cred);
	}
	free(ip->i_ea_area, M_TEMP);
	ip->i_ea_area = NULL;
	ip->i_ea_len = 0;
	ip->i_ea_error = 0;
	return (error);
}

/*
 * Vnode extattr strategy routine for fifos.
 *
 * We need to check for a read or write of the external attributes.
 * Otherwise we just fall through and do the usual thing.
 */
static int
ffsext_strategy(struct vop_strategy_args *ap)
/*
struct vop_strategy_args {
	struct vnodeop_desc *a_desc;
	struct vnode *a_vp;
	struct buf *a_bp;
};
*/
{
	struct vnode *vp;
	daddr_t lbn;

	vp = ap->a_vp;
	lbn = ap->a_bp->b_lblkno;
	if (VTOI(vp)->i_fs->fs_magic == FS_UFS2_MAGIC &&
	    lbn < 0 && lbn >= -NXADDR)
		return (VOP_STRATEGY_APV(&ufs_vnodeops, ap));
	if (vp->v_type == VFIFO)
		return (VOP_STRATEGY_APV(&ufs_fifoops, ap));
	panic("spec nodes went here");
}

/*
 * Vnode extattr transaction commit/abort
 */
static int
ffs_openextattr(struct vop_openextattr_args *ap)
/*
struct vop_openextattr_args {
	struct vnodeop_desc *a_desc;
	struct vnode *a_vp;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;
	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_openextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	return (ffs_open_ea(ap->a_vp, ap->a_cred, ap->a_td));
}


/*
 * Vnode extattr transaction commit/abort
 */
static int
ffs_closeextattr(struct vop_closeextattr_args *ap)
/*
struct vop_closeextattr_args {
	struct vnodeop_desc *a_desc;
	struct vnode *a_vp;
	int a_commit;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;
	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_closeextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	return (ffs_close_ea(ap->a_vp, ap->a_commit, ap->a_cred, ap->a_td));
}

/*
 * Vnode operation to remove a named attribute.
 */
static int
ffs_deleteextattr(struct vop_deleteextattr_args *ap)
/*
vop_deleteextattr {
	IN struct vnode *a_vp;
	IN int a_attrnamespace;
	IN const char *a_name;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;
	uint32_t ealength, ul;
	int ealen, olen, eapad1, eapad2, error, i, easize;
	u_char *eae, *p;
	int stand_alone;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;

	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_deleteextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	if (strlen(ap->a_name) == 0)
		return (EINVAL);

	error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace,
	    ap->a_cred, ap->a_td, IWRITE);
	if (error) {
		if (ip->i_ea_area != NULL && ip->i_ea_error == 0)
			ip->i_ea_error = error;
		return (error);
	}

	if (ip->i_ea_area == NULL) {
		error = ffs_open_ea(ap->a_vp, ap->a_cred, ap->a_td);
		if (error)
			return (error);
		stand_alone = 1;
	} else {
		stand_alone = 0;
	}

	ealength = eapad1 = ealen = eapad2 = 0;

	eae = malloc(ip->i_ea_len, M_TEMP, M_WAITOK);
	bcopy(ip->i_ea_area, eae, ip->i_ea_len);
	easize = ip->i_ea_len;

	olen = ffs_findextattr(eae, easize, ap->a_attrnamespace, ap->a_name,
	    &p, NULL);
	if (olen == -1) {
		/* delete but nonexistent */
		free(eae, M_TEMP);
		if (stand_alone)
			ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
		return(ENOATTR);
	}
	bcopy(p, &ul, sizeof ul);
	i = p - eae + ul;
	if (ul != ealength) {
		bcopy(p + ul, p + ealength, easize - i);
		easize += (ealength - ul);
	}
	if (easize > NXADDR * fs->fs_bsize) {
		free(eae, M_TEMP);
		if (stand_alone)
			ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
		else if (ip->i_ea_error == 0)
			ip->i_ea_error = ENOSPC;
		return(ENOSPC);
	}
	p = ip->i_ea_area;
	ip->i_ea_area = eae;
	ip->i_ea_len = easize;
	free(p, M_TEMP);
	if (stand_alone)
		error = ffs_close_ea(ap->a_vp, 1, ap->a_cred, ap->a_td);
	return(error);
}

/*
 * Vnode operation to retrieve a named extended attribute.
 */
static int
ffs_getextattr(struct vop_getextattr_args *ap)
/*
vop_getextattr {
	IN struct vnode *a_vp;
	IN int a_attrnamespace;
	IN const char *a_name;
	INOUT struct uio *a_uio;
	OUT size_t *a_size;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;
	u_char *eae, *p;
	unsigned easize;
	int error, ealen, stand_alone;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;

	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_getextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace,
	    ap->a_cred, ap->a_td, IREAD);
	if (error)
		return (error);

	if (ip->i_ea_area == NULL) {
		error = ffs_open_ea(ap->a_vp, ap->a_cred, ap->a_td);
		if (error)
			return (error);
		stand_alone = 1;
	} else {
		stand_alone = 0;
	}
	eae = ip->i_ea_area;
	easize = ip->i_ea_len;

	ealen = ffs_findextattr(eae, easize, ap->a_attrnamespace, ap->a_name,
	    NULL, &p);
	if (ealen >= 0) {
		error = 0;
		if (ap->a_size != NULL)
			*ap->a_size = ealen;
		else if (ap->a_uio != NULL)
			error = uiomove(p, ealen, ap->a_uio);
	} else
		error = ENOATTR;
	if (stand_alone)
		ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
	return(error);
}

/*
 * Vnode operation to retrieve extended attributes on a vnode.
 */
static int
ffs_listextattr(struct vop_listextattr_args *ap)
/*
vop_listextattr {
	IN struct vnode *a_vp;
	IN int a_attrnamespace;
	INOUT struct uio *a_uio;
	OUT size_t *a_size;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;
	u_char *eae, *p, *pe, *pn;
	unsigned easize;
	uint32_t ul;
	int error, ealen, stand_alone;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;

	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_listextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace,
	    ap->a_cred, ap->a_td, IREAD);
	if (error)
		return (error);

	if (ip->i_ea_area == NULL) {
		error = ffs_open_ea(ap->a_vp, ap->a_cred, ap->a_td);
		if (error)
			return (error);
		stand_alone = 1;
	} else {
		stand_alone = 0;
	}
	eae = ip->i_ea_area;
	easize = ip->i_ea_len;

	error = 0;
	if (ap->a_size != NULL)
		*ap->a_size = 0;
	pe = eae + easize;
	for(p = eae; error == 0 && p < pe; p = pn) {
		bcopy(p, &ul, sizeof(ul));
		pn = p + ul;
		if (pn > pe)
			break;
		p += sizeof(ul);
		if (*p++ != ap->a_attrnamespace)
			continue;
		p++;	/* pad2 */
		ealen = *p;
		if (ap->a_size != NULL) {
			*ap->a_size += ealen + 1;
		} else if (ap->a_uio != NULL) {
			error = uiomove(p, ealen + 1, ap->a_uio);
		}
	}
	if (stand_alone)
		ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
	return(error);
}

/*
 * Vnode operation to set a named attribute.
 */
static int
ffs_setextattr(struct vop_setextattr_args *ap)
/*
vop_setextattr {
	IN struct vnode *a_vp;
	IN int a_attrnamespace;
	IN const char *a_name;
	INOUT struct uio *a_uio;
	IN struct ucred *a_cred;
	IN struct thread *a_td;
};
*/
{
	struct inode *ip;
	struct fs *fs;
	uint32_t ealength, ul;
	int ealen, olen, eapad1, eapad2, error, i, easize;
	u_char *eae, *p;
	int stand_alone;

	ip = VTOI(ap->a_vp);
	fs = ip->i_fs;

	if (fs->fs_magic == FS_UFS1_MAGIC)
		return (ufs_vnodeops.vop_setextattr(ap));

	if (ap->a_vp->v_type == VCHR)
		return (EOPNOTSUPP);

	if (strlen(ap->a_name) == 0)
		return (EINVAL);

	/* XXX Now unsupported API to delete EAs using NULL uio. */
	if (ap->a_uio == NULL)
		return (EOPNOTSUPP);

	error = extattr_check_cred(ap->a_vp, ap->a_attrnamespace,
	    ap->a_cred, ap->a_td, IWRITE);
	if (error) {
		if (ip->i_ea_area != NULL && ip->i_ea_error == 0)
			ip->i_ea_error = error;
		return (error);
	}

	if (ip->i_ea_area == NULL) {
		error = ffs_open_ea(ap->a_vp, ap->a_cred, ap->a_td);
		if (error)
			return (error);
		stand_alone = 1;
	} else {
		stand_alone = 0;
	}

	ealen = ap->a_uio->uio_resid;
	ealength = sizeof(uint32_t) + 3 + strlen(ap->a_name);
	eapad1 = 8 - (ealength % 8);
	if (eapad1 == 8)
		eapad1 = 0;
	eapad2 = 8 - (ealen % 8);
	if (eapad2 == 8)
		eapad2 = 0;
	ealength += eapad1 + ealen + eapad2;

	eae = malloc(ip->i_ea_len + ealength, M_TEMP, M_WAITOK);
	bcopy(ip->i_ea_area, eae, ip->i_ea_len);
	easize = ip->i_ea_len;

	olen = ffs_findextattr(eae, easize,
	    ap->a_attrnamespace, ap->a_name, &p, NULL);
        if (olen == -1) {
		/* new, append at end */
		p = eae + easize;
		easize += ealength;
	} else {
		bcopy(p, &ul, sizeof ul);
		i = p - eae + ul;
		if (ul != ealength) {
			bcopy(p + ul, p + ealength, easize - i);
			easize += (ealength - ul);
		}
	}
	if (easize > NXADDR * fs->fs_bsize) {
		free(eae, M_TEMP);
		if (stand_alone)
			ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
		else if (ip->i_ea_error == 0)
			ip->i_ea_error = ENOSPC;
		return(ENOSPC);
	}
	bcopy(&ealength, p, sizeof(ealength));
	p += sizeof(ealength);
	*p++ = ap->a_attrnamespace;
	*p++ = eapad2;
	*p++ = strlen(ap->a_name);
	strcpy(p, ap->a_name);
	p += strlen(ap->a_name);
	bzero(p, eapad1);
	p += eapad1;
	error = uiomove(p, ealen, ap->a_uio);
	if (error) {
		free(eae, M_TEMP);
		if (stand_alone)
			ffs_close_ea(ap->a_vp, 0, ap->a_cred, ap->a_td);
		else if (ip->i_ea_error == 0)
			ip->i_ea_error = error;
		return(error);
	}
	p += ealen;
	bzero(p, eapad2);

	p = ip->i_ea_area;
	ip->i_ea_area = eae;
	ip->i_ea_len = easize;
	free(p, M_TEMP);
	if (stand_alone)
		error = ffs_close_ea(ap->a_vp, 1, ap->a_cred, ap->a_td);
	return(error);
}