summaryrefslogtreecommitdiffstats
path: root/sys/kern/vfs_default.c
blob: 0ac6c11ecb83d01d697bbc4c9734b2b7934cf13e (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
/*-
 * 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/malloc.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/unistd.h>
#include <sys/vnode.h>
#include <sys/poll.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_nostrategy(struct vop_strategy_args *);

/*
 * 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.
 *
 */

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

	.vop_advlock =		VOP_EINVAL,
	.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_lease =		VOP_NULL,
	.vop_lock =		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_revoke =		VOP_PANIC,
	.vop_strategy =		vop_nostrategy,
	.vop_unlock =		vop_stdunlock,
};

/*
 * 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_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_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);
}

/*
 * 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_lock_args /* {
		struct vnode *a_vp;
		int a_flags;
		struct thread *a_td;
	} */ *ap;
{
	struct vnode *vp = ap->a_vp;

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

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

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

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

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

/*
 * 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 true for read/write.  If the user asked for something
	 * special, return POLLNVAL, so that clients have a way of
	 * determining reliably whether or not the extended
	 * functionality is present without hard-coding knowledge
	 * of specific filesystem implementations.
	 * Stay in sync with kern_conf.c::no_poll().
	 */
	if (ap->a_events & ~POLLSTANDARD)
		return (POLLNVAL);

	return (ap->a_events & (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM));
}

/*
 * 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;
{

	*(ap->a_mpp) = ap->a_vp->v_mount;
	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 */

	VI_LOCK(vp);
loop1:
	/*
	 * MARK/SCAN initialization to avoid infinite loops.
	 */
        TAILQ_FOREACH(bp, &vp->v_bufobj.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, &vp->v_bufobj.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))
			continue;
		VI_UNLOCK(vp);
		KASSERT(bp->b_bufobj == &vp->v_bufobj,
		    ("bp %p wrong b_bufobj %p should be %p",
		    bp, bp->b_bufobj, &vp->v_bufobj));
		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);
		}
		VI_LOCK(vp);
		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) {
		bo = &vp->v_bufobj;
		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;
		}
	}
	VI_UNLOCK(vp);
	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);
}

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

	return (EOPNOTSUPP);
}

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

	return (EOPNOTSUPP);
}

int
vfs_stdvptofh (vp, fhp)
	struct vnode *vp;
	struct fid *fhp;
{

	return (EOPNOTSUPP);
}

int
vfs_stdquotactl (mp, cmds, uid, arg, td)
	struct mount *mp;
	int cmds;
	uid_t uid;
	caddr_t arg;
	struct thread *td;
{

	return (EOPNOTSUPP);
}

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

	lockreq = LK_EXCLUSIVE | LK_INTERLOCK;
	if (waitfor != MNT_WAIT)
		lockreq |= LK_NOWAIT;
	/*
	 * Force stale buffer cache information to be flushed.
	 */
	MNT_ILOCK(mp);
loop:
	MNT_VNODE_FOREACH(vp, mp, nvp) {

		VI_LOCK(vp);
		if (vp->v_bufobj.bo_dirty.bv_cnt == 0) {
			VI_UNLOCK(vp);
			continue;
		}
		MNT_IUNLOCK(mp);

		if ((error = vget(vp, lockreq, td)) != 0) {
			MNT_ILOCK(mp);
			if (error == ENOENT)
				goto loop;
			continue;
		}
		error = VOP_FSYNC(vp, waitfor, td);
		if (error)
			allerror = error;

		VOP_UNLOCK(vp, 0, td);
		vrele(vp);
		MNT_ILOCK(mp);
	}
	MNT_IUNLOCK(mp);
	return (allerror);
}

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

	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, vpp)
	struct mount *mp;
	struct fid *fhp;
	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, td)
	struct mount *mp;
	int cmd;
	struct vnode *filename_vp;
	int attrnamespace;
	const char *attrname;
	struct thread *td;
{

	if (filename_vp != NULL)
		VOP_UNLOCK(filename_vp, 0, td);
	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