summaryrefslogtreecommitdiffstats
path: root/sys/kern/vfs_default.c
blob: 2c011173d2ab3c5920c9512c15722addcaa47aaa (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
/*-
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed
 * to Berkeley by John Heidemann of the UCLA Ficus project.
 *
 * Source: * @(#)i405_init.c 2.10 92/04/27 UCLA Ficus project
 *
 * 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.
 */

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

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/conf.h>
#include <sys/event.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/lockf.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/namei.h>
#include <sys/rwlock.h>
#include <sys/fcntl.h>
#include <sys/unistd.h>
#include <sys/vnode.h>
#include <sys/dirent.h>
#include <sys/poll.h>

#include <security/mac/mac_framework.h>

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

static int	vop_nolookup(struct vop_lookup_args *);
static int	vop_norename(struct vop_rename_args *);
static int	vop_nostrategy(struct vop_strategy_args *);
static int	get_next_dirent(struct vnode *vp, struct dirent **dpp,
				char *dirbuf, int dirbuflen, off_t *off,
				char **cpos, int *len, int *eofflag,
				struct thread *td);
static int	dirent_exists(struct vnode *vp, const char *dirname,
			      struct thread *td);

#define DIRENT_MINSIZE (sizeof(struct dirent) - (MAXNAMLEN+1) + 4)

static int vop_stdis_text(struct vop_is_text_args *ap);
static int vop_stdset_text(struct vop_set_text_args *ap);
static int vop_stdunset_text(struct vop_unset_text_args *ap);
static int vop_stdget_writecount(struct vop_get_writecount_args *ap);
static int vop_stdadd_writecount(struct vop_add_writecount_args *ap);

/*
 * This vnode table stores what we want to do if the filesystem doesn't
 * implement a particular VOP.
 *
 * If there is no specific entry here, we will return EOPNOTSUPP.
 *
 * Note that every filesystem has to implement either vop_access
 * or vop_accessx; failing to do so will result in immediate crash
 * due to stack overflow, as vop_stdaccess() calls vop_stdaccessx(),
 * which calls vop_stdaccess() etc.
 */

struct vop_vector default_vnodeops = {
	.vop_default =		NULL,
	.vop_bypass =		VOP_EOPNOTSUPP,

	.vop_access =		vop_stdaccess,
	.vop_accessx =		vop_stdaccessx,
	.vop_advise =		vop_stdadvise,
	.vop_advlock =		vop_stdadvlock,
	.vop_advlockasync =	vop_stdadvlockasync,
	.vop_advlockpurge =	vop_stdadvlockpurge,
	.vop_allocate =		vop_stdallocate,
	.vop_bmap =		vop_stdbmap,
	.vop_close =		VOP_NULL,
	.vop_fsync =		VOP_NULL,
	.vop_getpages =		vop_stdgetpages,
	.vop_getwritemount = 	vop_stdgetwritemount,
	.vop_inactive =		VOP_NULL,
	.vop_ioctl =		VOP_ENOTTY,
	.vop_kqfilter =		vop_stdkqfilter,
	.vop_islocked =		vop_stdislocked,
	.vop_lock1 =		vop_stdlock,
	.vop_lookup =		vop_nolookup,
	.vop_open =		VOP_NULL,
	.vop_pathconf =		VOP_EINVAL,
	.vop_poll =		vop_nopoll,
	.vop_putpages =		vop_stdputpages,
	.vop_readlink =		VOP_EINVAL,
	.vop_rename =		vop_norename,
	.vop_revoke =		VOP_PANIC,
	.vop_strategy =		vop_nostrategy,
	.vop_unlock =		vop_stdunlock,
	.vop_vptocnp =		vop_stdvptocnp,
	.vop_vptofh =		vop_stdvptofh,
	.vop_unp_bind =		vop_stdunp_bind,
	.vop_unp_connect =	vop_stdunp_connect,
	.vop_unp_detach =	vop_stdunp_detach,
	.vop_is_text =		vop_stdis_text,
	.vop_set_text =		vop_stdset_text,
	.vop_unset_text =	vop_stdunset_text,
	.vop_get_writecount =	vop_stdget_writecount,
	.vop_add_writecount =	vop_stdadd_writecount,
};

/*
 * Series of placeholder functions for various error returns for
 * VOPs.
 */

int
vop_eopnotsupp(struct vop_generic_args *ap)
{
	/*
	printf("vop_notsupp[%s]\n", ap->a_desc->vdesc_name);
	*/

	return (EOPNOTSUPP);
}

int
vop_ebadf(struct vop_generic_args *ap)
{

	return (EBADF);
}

int
vop_enotty(struct vop_generic_args *ap)
{

	return (ENOTTY);
}

int
vop_einval(struct vop_generic_args *ap)
{

	return (EINVAL);
}

int
vop_enoent(struct vop_generic_args *ap)
{

	return (ENOENT);
}

int
vop_null(struct vop_generic_args *ap)
{

	return (0);
}

/*
 * Helper function to panic on some bad VOPs in some filesystems.
 */
int
vop_panic(struct vop_generic_args *ap)
{

	panic("filesystem goof: vop_panic[%s]", ap->a_desc->vdesc_name);
}

/*
 * vop_std<something> and vop_no<something> are default functions for use by
 * filesystems that need the "default reasonable" implementation for a
 * particular operation.
 *
 * The documentation for the operations they implement exists (if it exists)
 * in the VOP_<SOMETHING>(9) manpage (all uppercase).
 */

/*
 * Default vop for filesystems that do not support name lookup
 */
static int
vop_nolookup(ap)
	struct vop_lookup_args /* {
		struct vnode *a_dvp;
		struct vnode **a_vpp;
		struct componentname *a_cnp;
	} */ *ap;
{

	*ap->a_vpp = NULL;
	return (ENOTDIR);
}

/*
 * vop_norename:
 *
 * Handle unlock and reference counting for arguments of vop_rename
 * for filesystems that do not implement rename operation.
 */
static int
vop_norename(struct vop_rename_args *ap)
{

	vop_rename_fail(ap);
	return (EOPNOTSUPP);
}

/*
 *	vop_nostrategy:
 *
 *	Strategy routine for VFS devices that have none.
 *
 *	BIO_ERROR and B_INVAL must be cleared prior to calling any strategy
 *	routine.  Typically this is done for a BIO_READ strategy call.
 *	Typically B_INVAL is assumed to already be clear prior to a write
 *	and should not be cleared manually unless you just made the buffer
 *	invalid.  BIO_ERROR should be cleared either way.
 */

static int
vop_nostrategy (struct vop_strategy_args *ap)
{
	printf("No strategy for buffer at %p\n", ap->a_bp);
	vprint("vnode", ap->a_vp);
	ap->a_bp->b_ioflags |= BIO_ERROR;
	ap->a_bp->b_error = EOPNOTSUPP;
	bufdone(ap->a_bp);
	return (EOPNOTSUPP);
}

static int
get_next_dirent(struct vnode *vp, struct dirent **dpp, char *dirbuf,
		int dirbuflen, off_t *off, char **cpos, int *len,
		int *eofflag, struct thread *td)
{
	int error, reclen;
	struct uio uio;
	struct iovec iov;
	struct dirent *dp;

	KASSERT(VOP_ISLOCKED(vp), ("vp %p is not locked", vp));
	KASSERT(vp->v_type == VDIR, ("vp %p is not a directory", vp));

	if (*len == 0) {
		iov.iov_base = dirbuf;
		iov.iov_len = dirbuflen;

		uio.uio_iov = &iov;
		uio.uio_iovcnt = 1;
		uio.uio_offset = *off;
		uio.uio_resid = dirbuflen;
		uio.uio_segflg = UIO_SYSSPACE;
		uio.uio_rw = UIO_READ;
		uio.uio_td = td;

		*eofflag = 0;

#ifdef MAC
		error = mac_vnode_check_readdir(td->td_ucred, vp);
		if (error == 0)
#endif
			error = VOP_READDIR(vp, &uio, td->td_ucred, eofflag,
		    		NULL, NULL);
		if (error)
			return (error);

		*off = uio.uio_offset;

		*cpos = dirbuf;
		*len = (dirbuflen - uio.uio_resid);

		if (*len == 0)
			return (ENOENT);
	}

	dp = (struct dirent *)(*cpos);
	reclen = dp->d_reclen;
	*dpp = dp;

	/* check for malformed directory.. */
	if (reclen < DIRENT_MINSIZE)
		return (EINVAL);

	*cpos += reclen;
	*len -= reclen;

	return (0);
}

/*
 * Check if a named file exists in a given directory vnode.
 */
static int
dirent_exists(struct vnode *vp, const char *dirname, struct thread *td)
{
	char *dirbuf, *cpos;
	int error, eofflag, dirbuflen, len, found;
	off_t off;
	struct dirent *dp;
	struct vattr va;

	KASSERT(VOP_ISLOCKED(vp), ("vp %p is not locked", vp));
	KASSERT(vp->v_type == VDIR, ("vp %p is not a directory", vp));

	found = 0;

	error = VOP_GETATTR(vp, &va, td->td_ucred);
	if (error)
		return (found);

	dirbuflen = DEV_BSIZE;
	if (dirbuflen < va.va_blocksize)
		dirbuflen = va.va_blocksize;
	dirbuf = (char *)malloc(dirbuflen, M_TEMP, M_WAITOK);

	off = 0;
	len = 0;
	do {
		error = get_next_dirent(vp, &dp, dirbuf, dirbuflen, &off,
					&cpos, &len, &eofflag, td);
		if (error)
			goto out;

		if (dp->d_type != DT_WHT && dp->d_fileno != 0 &&
		    strcmp(dp->d_name, dirname) == 0) {
			found = 1;
			goto out;
		}
	} while (len > 0 || !eofflag);

out:
	free(dirbuf, M_TEMP);
	return (found);
}

int
vop_stdaccess(struct vop_access_args *ap)
{

	KASSERT((ap->a_accmode & ~(VEXEC | VWRITE | VREAD | VADMIN |
	    VAPPEND)) == 0, ("invalid bit in accmode"));

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

int
vop_stdaccessx(struct vop_accessx_args *ap)
{
	int error;
	accmode_t accmode = ap->a_accmode;

	error = vfs_unixify_accmode(&accmode);
	if (error != 0)
		return (error);

	if (accmode == 0)
		return (0);

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

/*
 * Advisory record locking support
 */
int
vop_stdadvlock(struct vop_advlock_args *ap)
{
	struct vnode *vp;
	struct ucred *cred;
	struct vattr vattr;
	int error;

	vp = ap->a_vp;
	cred = curthread->td_ucred;
	vn_lock(vp, LK_SHARED | LK_RETRY);
	error = VOP_GETATTR(vp, &vattr, cred);
	VOP_UNLOCK(vp, 0);
	if (error)
		return (error);

	return (lf_advlock(ap, &(vp->v_lockf), vattr.va_size));
}

int
vop_stdadvlockasync(struct vop_advlockasync_args *ap)
{
	struct vnode *vp;
	struct ucred *cred;
	struct vattr vattr;
	int error;

	vp = ap->a_vp;
	cred = curthread->td_ucred;
	vn_lock(vp, LK_SHARED | LK_RETRY);
	error = VOP_GETATTR(vp, &vattr, cred);
	VOP_UNLOCK(vp, 0);
	if (error)
		return (error);

	return (lf_advlockasync(ap, &(vp->v_lockf), vattr.va_size));
}

int
vop_stdadvlockpurge(struct vop_advlockpurge_args *ap)
{
	struct vnode *vp;

	vp = ap->a_vp;
	lf_purgelocks(vp, &vp->v_lockf);
	return (0);
}

/*
 * vop_stdpathconf:
 *
 * Standard implementation of POSIX pathconf, to get information about limits
 * for a filesystem.
 * Override per filesystem for the case where the filesystem has smaller
 * limits.
 */
int
vop_stdpathconf(ap)
	struct vop_pathconf_args /* {
	struct vnode *a_vp;
	int a_name;
	int *a_retval;
	} */ *ap;
{

	switch (ap->a_name) {
		case _PC_NAME_MAX:
			*ap->a_retval = NAME_MAX;
			return (0);
		case _PC_PATH_MAX:
			*ap->a_retval = PATH_MAX;
			return (0);
		case _PC_LINK_MAX:
			*ap->a_retval = LINK_MAX;
			return (0);
		case _PC_MAX_CANON:
			*ap->a_retval = MAX_CANON;
			return (0);
		case _PC_MAX_INPUT:
			*ap->a_retval = MAX_INPUT;
			return (0);
		case _PC_PIPE_BUF:
			*ap->a_retval = PIPE_BUF;
			return (0);
		case _PC_CHOWN_RESTRICTED:
			*ap->a_retval = 1;
			return (0);
		case _PC_VDISABLE:
			*ap->a_retval = _POSIX_VDISABLE;
			return (0);
		default:
			return (EINVAL);
	}
	/* NOTREACHED */
}

/*
 * Standard lock, unlock and islocked functions.
 */
int
vop_stdlock(ap)
	struct vop_lock1_args /* {
		struct vnode *a_vp;
		int a_flags;
		char *file;
		int line;
	} */ *ap;
{
	struct vnode *vp = ap->a_vp;

	return (_lockmgr_args(vp->v_vnlock, ap->a_flags, VI_MTX(vp),
	    LK_WMESG_DEFAULT, LK_PRIO_DEFAULT, LK_TIMO_DEFAULT, ap->a_file,
	    ap->a_line));
}

/* See above. */
int
vop_stdunlock(ap)
	struct vop_unlock_args /* {
		struct vnode *a_vp;
		int a_flags;
	} */ *ap;
{
	struct vnode *vp = ap->a_vp;

	return (lockmgr(vp->v_vnlock, ap->a_flags | LK_RELEASE, VI_MTX(vp)));
}

/* See above. */
int
vop_stdislocked(ap)
	struct vop_islocked_args /* {
		struct vnode *a_vp;
	} */ *ap;
{

	return (lockstatus(ap->a_vp->v_vnlock));
}

/*
 * Return true for select/poll.
 */
int
vop_nopoll(ap)
	struct vop_poll_args /* {
		struct vnode *a_vp;
		int  a_events;
		struct ucred *a_cred;
		struct thread *a_td;
	} */ *ap;
{

	return (poll_no_poll(ap->a_events));
}

/*
 * Implement poll for local filesystems that support it.
 */
int
vop_stdpoll(ap)
	struct vop_poll_args /* {
		struct vnode *a_vp;
		int  a_events;
		struct ucred *a_cred;
		struct thread *a_td;
	} */ *ap;
{
	if (ap->a_events & ~POLLSTANDARD)
		return (vn_pollrecord(ap->a_vp, ap->a_td, ap->a_events));
	return (ap->a_events & (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM));
}

/*
 * Return our mount point, as we will take charge of the writes.
 */
int
vop_stdgetwritemount(ap)
	struct vop_getwritemount_args /* {
		struct vnode *a_vp;
		struct mount **a_mpp;
	} */ *ap;
{
	struct mount *mp;

	/*
	 * XXX Since this is called unlocked we may be recycled while
	 * attempting to ref the mount.  If this is the case or mountpoint
	 * will be set to NULL.  We only have to prevent this call from
	 * returning with a ref to an incorrect mountpoint.  It is not
	 * harmful to return with a ref to our previous mountpoint.
	 */
	mp = ap->a_vp->v_mount;
	if (mp != NULL) {
		vfs_ref(mp);
		if (mp != ap->a_vp->v_mount) {
			vfs_rel(mp);
			mp = NULL;
		}
	}
	*(ap->a_mpp) = mp;
	return (0);
}

/* XXX Needs good comment and VOP_BMAP(9) manpage */
int
vop_stdbmap(ap)
	struct vop_bmap_args /* {
		struct vnode *a_vp;
		daddr_t  a_bn;
		struct bufobj **a_bop;
		daddr_t *a_bnp;
		int *a_runp;
		int *a_runb;
	} */ *ap;
{

	if (ap->a_bop != NULL)
		*ap->a_bop = &ap->a_vp->v_bufobj;
	if (ap->a_bnp != NULL)
		*ap->a_bnp = ap->a_bn * btodb(ap->a_vp->v_mount->mnt_stat.f_iosize);
	if (ap->a_runp != NULL)
		*ap->a_runp = 0;
	if (ap->a_runb != NULL)
		*ap->a_runb = 0;
	return (0);
}

int
vop_stdfsync(ap)
	struct vop_fsync_args /* {
		struct vnode *a_vp;
		struct ucred *a_cred;
		int a_waitfor;
		struct thread *a_td;
	} */ *ap;
{
	struct vnode *vp = ap->a_vp;
	struct buf *bp;
	struct bufobj *bo;
	struct buf *nbp;
	int error = 0;
	int maxretry = 1000;     /* large, arbitrarily chosen */

	bo = &vp->v_bufobj;
	BO_LOCK(bo);
loop1:
	/*
	 * MARK/SCAN initialization to avoid infinite loops.
	 */
        TAILQ_FOREACH(bp, &bo->bo_dirty.bv_hd, b_bobufs) {
                bp->b_vflags &= ~BV_SCANNED;
		bp->b_error = 0;
	}

	/*
	 * Flush all dirty buffers associated with a vnode.
	 */
loop2:
	TAILQ_FOREACH_SAFE(bp, &bo->bo_dirty.bv_hd, b_bobufs, nbp) {
		if ((bp->b_vflags & BV_SCANNED) != 0)
			continue;
		bp->b_vflags |= BV_SCANNED;
		if (BUF_LOCK(bp, LK_EXCLUSIVE | LK_NOWAIT, NULL)) {
			if (ap->a_waitfor != MNT_WAIT)
				continue;
			if (BUF_LOCK(bp,
			    LK_EXCLUSIVE | LK_INTERLOCK | LK_SLEEPFAIL,
			    BO_LOCKPTR(bo)) != 0) {
				BO_LOCK(bo);
				goto loop1;
			}
			BO_LOCK(bo);
		}
		BO_UNLOCK(bo);
		KASSERT(bp->b_bufobj == bo,
		    ("bp %p wrong b_bufobj %p should be %p",
		    bp, bp->b_bufobj, bo));
		if ((bp->b_flags & B_DELWRI) == 0)
			panic("fsync: not dirty");
		if ((vp->v_object != NULL) && (bp->b_flags & B_CLUSTEROK)) {
			vfs_bio_awrite(bp);
		} else {
			bremfree(bp);
			bawrite(bp);
		}
		BO_LOCK(bo);
		goto loop2;
	}

	/*
	 * If synchronous the caller expects us to completely resolve all
	 * dirty buffers in the system.  Wait for in-progress I/O to
	 * complete (which could include background bitmap writes), then
	 * retry if dirty blocks still exist.
	 */
	if (ap->a_waitfor == MNT_WAIT) {
		bufobj_wwait(bo, 0, 0);
		if (bo->bo_dirty.bv_cnt > 0) {
			/*
			 * If we are unable to write any of these buffers
			 * then we fail now rather than trying endlessly
			 * to write them out.
			 */
			TAILQ_FOREACH(bp, &bo->bo_dirty.bv_hd, b_bobufs)
				if ((error = bp->b_error) == 0)
					continue;
			if (error == 0 && --maxretry >= 0)
				goto loop1;
			error = EAGAIN;
		}
	}
	BO_UNLOCK(bo);
	if (error == EAGAIN)
		vprint("fsync: giving up on dirty", vp);

	return (error);
}

/* XXX Needs good comment and more info in the manpage (VOP_GETPAGES(9)). */
int
vop_stdgetpages(ap)
	struct vop_getpages_args /* {
		struct vnode *a_vp;
		vm_page_t *a_m;
		int a_count;
		int a_reqpage;
		vm_ooffset_t a_offset;
	} */ *ap;
{

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

int
vop_stdkqfilter(struct vop_kqfilter_args *ap)
{
	return vfs_kqfilter(ap);
}

/* XXX Needs good comment and more info in the manpage (VOP_PUTPAGES(9)). */
int
vop_stdputpages(ap)
	struct vop_putpages_args /* {
		struct vnode *a_vp;
		vm_page_t *a_m;
		int a_count;
		int a_sync;
		int *a_rtvals;
		vm_ooffset_t a_offset;
	} */ *ap;
{

	return vnode_pager_generic_putpages(ap->a_vp, ap->a_m, ap->a_count,
	     ap->a_sync, ap->a_rtvals);
}

int
vop_stdvptofh(struct vop_vptofh_args *ap)
{
	return (EOPNOTSUPP);
}

int
vop_stdvptocnp(struct vop_vptocnp_args *ap)
{
	struct vnode *vp = ap->a_vp;
	struct vnode **dvp = ap->a_vpp;
	struct ucred *cred = ap->a_cred;
	char *buf = ap->a_buf;
	int *buflen = ap->a_buflen;
	char *dirbuf, *cpos;
	int i, error, eofflag, dirbuflen, flags, locked, len, covered;
	off_t off;
	ino_t fileno;
	struct vattr va;
	struct nameidata nd;
	struct thread *td;
	struct dirent *dp;
	struct vnode *mvp;

	i = *buflen;
	error = 0;
	covered = 0;
	td = curthread;

	if (vp->v_type != VDIR)
		return (ENOENT);

	error = VOP_GETATTR(vp, &va, cred);
	if (error)
		return (error);

	VREF(vp);
	locked = VOP_ISLOCKED(vp);
	VOP_UNLOCK(vp, 0);
	NDINIT_ATVP(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE,
	    "..", vp, td);
	flags = FREAD;
	error = vn_open_cred(&nd, &flags, 0, VN_OPEN_NOAUDIT, cred, NULL);
	if (error) {
		vn_lock(vp, locked | LK_RETRY);
		return (error);
	}
	NDFREE(&nd, NDF_ONLY_PNBUF);

	mvp = *dvp = nd.ni_vp;

	if (vp->v_mount != (*dvp)->v_mount &&
	    ((*dvp)->v_vflag & VV_ROOT) &&
	    ((*dvp)->v_mount->mnt_flag & MNT_UNION)) {
		*dvp = (*dvp)->v_mount->mnt_vnodecovered;
		VREF(mvp);
		VOP_UNLOCK(mvp, 0);
		vn_close(mvp, FREAD, cred, td);
		VREF(*dvp);
		vn_lock(*dvp, LK_EXCLUSIVE | LK_RETRY);
		covered = 1;
	}

	fileno = va.va_fileid;

	dirbuflen = DEV_BSIZE;
	if (dirbuflen < va.va_blocksize)
		dirbuflen = va.va_blocksize;
	dirbuf = (char *)malloc(dirbuflen, M_TEMP, M_WAITOK);

	if ((*dvp)->v_type != VDIR) {
		error = ENOENT;
		goto out;
	}

	off = 0;
	len = 0;
	do {
		/* call VOP_READDIR of parent */
		error = get_next_dirent(*dvp, &dp, dirbuf, dirbuflen, &off,
					&cpos, &len, &eofflag, td);
		if (error)
			goto out;

		if ((dp->d_type != DT_WHT) &&
		    (dp->d_fileno == fileno)) {
			if (covered) {
				VOP_UNLOCK(*dvp, 0);
				vn_lock(mvp, LK_EXCLUSIVE | LK_RETRY);
				if (dirent_exists(mvp, dp->d_name, td)) {
					error = ENOENT;
					VOP_UNLOCK(mvp, 0);
					vn_lock(*dvp, LK_EXCLUSIVE | LK_RETRY);
					goto out;
				}
				VOP_UNLOCK(mvp, 0);
				vn_lock(*dvp, LK_EXCLUSIVE | LK_RETRY);
			}
			i -= dp->d_namlen;

			if (i < 0) {
				error = ENOMEM;
				goto out;
			}
			if (dp->d_namlen == 1 && dp->d_name[0] == '.') {
				error = ENOENT;
			} else {
				bcopy(dp->d_name, buf + i, dp->d_namlen);
				error = 0;
			}
			goto out;
		}
	} while (len > 0 || !eofflag);
	error = ENOENT;

out:
	free(dirbuf, M_TEMP);
	if (!error) {
		*buflen = i;
		vref(*dvp);
	}
	if (covered) {
		vput(*dvp);
		vrele(mvp);
	} else {
		VOP_UNLOCK(mvp, 0);
		vn_close(mvp, FREAD, cred, td);
	}
	vn_lock(vp, locked | LK_RETRY);
	return (error);
}

int
vop_stdallocate(struct vop_allocate_args *ap)
{
#ifdef __notyet__
	struct statfs sfs;
#endif
	struct iovec aiov;
	struct vattr vattr, *vap;
	struct uio auio;
	off_t fsize, len, cur, offset;
	uint8_t *buf;
	struct thread *td;
	struct vnode *vp;
	size_t iosize;
	int error;

	buf = NULL;
	error = 0;
	td = curthread;
	vap = &vattr;
	vp = ap->a_vp;
	len = *ap->a_len;
	offset = *ap->a_offset;

	error = VOP_GETATTR(vp, vap, td->td_ucred);
	if (error != 0)
		goto out;
	fsize = vap->va_size;
	iosize = vap->va_blocksize;
	if (iosize == 0)
		iosize = BLKDEV_IOSIZE;
	if (iosize > MAXPHYS)
		iosize = MAXPHYS;
	buf = malloc(iosize, M_TEMP, M_WAITOK);

#ifdef __notyet__
	/*
	 * Check if the filesystem sets f_maxfilesize; if not use
	 * VOP_SETATTR to perform the check.
	 */
	error = VFS_STATFS(vp->v_mount, &sfs, td);
	if (error != 0)
		goto out;
	if (sfs.f_maxfilesize) {
		if (offset > sfs.f_maxfilesize || len > sfs.f_maxfilesize ||
		    offset + len > sfs.f_maxfilesize) {
			error = EFBIG;
			goto out;
		}
	} else
#endif
	if (offset + len > vap->va_size) {
		/*
		 * Test offset + len against the filesystem's maxfilesize.
		 */
		VATTR_NULL(vap);
		vap->va_size = offset + len;
		error = VOP_SETATTR(vp, vap, td->td_ucred);
		if (error != 0)
			goto out;
		VATTR_NULL(vap);
		vap->va_size = fsize;
		error = VOP_SETATTR(vp, vap, td->td_ucred);
		if (error != 0)
			goto out;
	}

	for (;;) {
		/*
		 * Read and write back anything below the nominal file
		 * size.  There's currently no way outside the filesystem
		 * to know whether this area is sparse or not.
		 */
		cur = iosize;
		if ((offset % iosize) != 0)
			cur -= (offset % iosize);
		if (cur > len)
			cur = len;
		if (offset < fsize) {
			aiov.iov_base = buf;
			aiov.iov_len = cur;
			auio.uio_iov = &aiov;
			auio.uio_iovcnt = 1;
			auio.uio_offset = offset;
			auio.uio_resid = cur;
			auio.uio_segflg = UIO_SYSSPACE;
			auio.uio_rw = UIO_READ;
			auio.uio_td = td;
			error = VOP_READ(vp, &auio, 0, td->td_ucred);
			if (error != 0)
				break;
			if (auio.uio_resid > 0) {
				bzero(buf + cur - auio.uio_resid,
				    auio.uio_resid);
			}
		} else {
			bzero(buf, cur);
		}

		aiov.iov_base = buf;
		aiov.iov_len = cur;
		auio.uio_iov = &aiov;
		auio.uio_iovcnt = 1;
		auio.uio_offset = offset;
		auio.uio_resid = cur;
		auio.uio_segflg = UIO_SYSSPACE;
		auio.uio_rw = UIO_WRITE;
		auio.uio_td = td;

		error = VOP_WRITE(vp, &auio, 0, td->td_ucred);
		if (error != 0)
			break;

		len -= cur;
		offset += cur;
		if (len == 0)
			break;
		if (should_yield())
			break;
	}

 out:
	*ap->a_len = len;
	*ap->a_offset = offset;
	free(buf, M_TEMP);
	return (error);
}

int
vop_stdadvise(struct vop_advise_args *ap)
{
	struct vnode *vp;
	off_t start, end;
	int error;

	vp = ap->a_vp;
	switch (ap->a_advice) {
	case POSIX_FADV_WILLNEED:
		/*
		 * Do nothing for now.  Filesystems should provide a
		 * custom method which starts an asynchronous read of
		 * the requested region.
		 */
		error = 0;
		break;
	case POSIX_FADV_DONTNEED:
		/*
		 * Flush any open FS buffers and then remove pages
		 * from the backing VM object.  Using vinvalbuf() here
		 * is a bit heavy-handed as it flushes all buffers for
		 * the given vnode, not just the buffers covering the
		 * requested range.
		 */
		error = 0;
		vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
		if (vp->v_iflag & VI_DOOMED) {
			VOP_UNLOCK(vp, 0);
			break;
		}
		vinvalbuf(vp, V_CLEANONLY, 0, 0);
		if (vp->v_object != NULL) {
			start = trunc_page(ap->a_start);
			end = round_page(ap->a_end);
			VM_OBJECT_WLOCK(vp->v_object);
			vm_object_page_cache(vp->v_object, OFF_TO_IDX(start),
			    OFF_TO_IDX(end));
			VM_OBJECT_WUNLOCK(vp->v_object);
		}
		VOP_UNLOCK(vp, 0);
		break;
	default:
		error = EINVAL;
		break;
	}
	return (error);
}

int
vop_stdunp_bind(struct vop_unp_bind_args *ap)
{

	ap->a_vp->v_socket = ap->a_socket;
	return (0);
}

int
vop_stdunp_connect(struct vop_unp_connect_args *ap)
{

	*ap->a_socket = ap->a_vp->v_socket;
	return (0);
}

int
vop_stdunp_detach(struct vop_unp_detach_args *ap)
{

	ap->a_vp->v_socket = NULL;
	return (0);
}

static int
vop_stdis_text(struct vop_is_text_args *ap)
{

	return ((ap->a_vp->v_vflag & VV_TEXT) != 0);
}

static int
vop_stdset_text(struct vop_set_text_args *ap)
{

	ap->a_vp->v_vflag |= VV_TEXT;
	return (0);
}

static int
vop_stdunset_text(struct vop_unset_text_args *ap)
{

	ap->a_vp->v_vflag &= ~VV_TEXT;
	return (0);
}

static int
vop_stdget_writecount(struct vop_get_writecount_args *ap)
{

	*ap->a_writecount = ap->a_vp->v_writecount;
	return (0);
}

static int
vop_stdadd_writecount(struct vop_add_writecount_args *ap)
{

	ap->a_vp->v_writecount += ap->a_inc;
	return (0);
}

/*
 * vfs default ops
 * used to fill the vfs function table to get reasonable default return values.
 */
int
vfs_stdroot (mp, flags, vpp)
	struct mount *mp;
	int flags;
	struct vnode **vpp;
{

	return (EOPNOTSUPP);
}

int
vfs_stdstatfs (mp, sbp)
	struct mount *mp;
	struct statfs *sbp;
{

	return (EOPNOTSUPP);
}

int
vfs_stdquotactl (mp, cmds, uid, arg)
	struct mount *mp;
	int cmds;
	uid_t uid;
	void *arg;
{

	return (EOPNOTSUPP);
}

int
vfs_stdsync(mp, waitfor)
	struct mount *mp;
	int waitfor;
{
	struct vnode *vp, *mvp;
	struct thread *td;
	int error, lockreq, allerror = 0;

	td = curthread;
	lockreq = LK_EXCLUSIVE | LK_INTERLOCK;
	if (waitfor != MNT_WAIT)
		lockreq |= LK_NOWAIT;
	/*
	 * Force stale buffer cache information to be flushed.
	 */
loop:
	MNT_VNODE_FOREACH_ALL(vp, mp, mvp) {
		if (vp->v_bufobj.bo_dirty.bv_cnt == 0) {
			VI_UNLOCK(vp);
			continue;
		}
		if ((error = vget(vp, lockreq, td)) != 0) {
			if (error == ENOENT) {
				MNT_VNODE_FOREACH_ALL_ABORT(mp, mvp);
				goto loop;
			}
			continue;
		}
		error = VOP_FSYNC(vp, waitfor, td);
		if (error)
			allerror = error;
		vput(vp);
	}
	return (allerror);
}

int
vfs_stdnosync (mp, waitfor)
	struct mount *mp;
	int waitfor;
{

	return (0);
}

int
vfs_stdvget (mp, ino, flags, vpp)
	struct mount *mp;
	ino_t ino;
	int flags;
	struct vnode **vpp;
{

	return (EOPNOTSUPP);
}

int
vfs_stdfhtovp (mp, fhp, flags, vpp)
	struct mount *mp;
	struct fid *fhp;
	int flags;
	struct vnode **vpp;
{

	return (EOPNOTSUPP);
}

int
vfs_stdinit (vfsp)
	struct vfsconf *vfsp;
{

	return (0);
}

int
vfs_stduninit (vfsp)
	struct vfsconf *vfsp;
{

	return(0);
}

int
vfs_stdextattrctl(mp, cmd, filename_vp, attrnamespace, attrname)
	struct mount *mp;
	int cmd;
	struct vnode *filename_vp;
	int attrnamespace;
	const char *attrname;
{

	if (filename_vp != NULL)
		VOP_UNLOCK(filename_vp, 0);
	return (EOPNOTSUPP);
}

int
vfs_stdsysctl(mp, op, req)
	struct mount *mp;
	fsctlop_t op;
	struct sysctl_req *req;
{

	return (EOPNOTSUPP);
}

/* end of vfs default ops */
OpenPOWER on IntegriCloud