aboutsummaryrefslogtreecommitdiff
path: root/sys/fs/nullfs/null_vfsops.c
blob: 0ad2385116a9cba513950b2fc7a015ff90526ca6 (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
/*-
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (c) 1992, 1993, 1995
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software donated to Berkeley by
 * Jan-Simon Pendry.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. 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.
 *
 *	@(#)null_vfsops.c	8.2 (Berkeley) 1/21/94
 *
 * @(#)lofs_vfsops.c	1.2 (Berkeley) 6/18/92
 * $FreeBSD$
 */

/*
 * Null Layer
 * (See null_vnops.c for a description of what this does.)
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/fcntl.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/namei.h>
#include <sys/proc.h>
#include <sys/vnode.h>
#include <sys/jail.h>

#include <fs/nullfs/null.h>

static MALLOC_DEFINE(M_NULLFSMNT, "nullfs_mount", "NULLFS mount structure");

static vfs_fhtovp_t	nullfs_fhtovp;
static vfs_mount_t	nullfs_mount;
static vfs_quotactl_t	nullfs_quotactl;
static vfs_root_t	nullfs_root;
static vfs_sync_t	nullfs_sync;
static vfs_statfs_t	nullfs_statfs;
static vfs_unmount_t	nullfs_unmount;
static vfs_vget_t	nullfs_vget;
static vfs_extattrctl_t	nullfs_extattrctl;

/*
 * Mount null layer
 */
static int
nullfs_mount(struct mount *mp)
{
	struct vnode *lowerrootvp;
	struct vnode *nullm_rootvp;
	struct null_mount *xmp;
	struct null_node *nn;
	struct nameidata nd, *ndp;
	char *target;
	int error, len;
	bool isvnunlocked;

	NULLFSDEBUG("nullfs_mount(mp = %p)\n", (void *)mp);

	if (mp->mnt_flag & MNT_ROOTFS)
		return (EOPNOTSUPP);

	/*
	 * Update is a no-op
	 */
	if (mp->mnt_flag & MNT_UPDATE) {
		/*
		 * Only support update mounts for NFS export.
		 */
		if (vfs_flagopt(mp->mnt_optnew, "export", NULL, 0))
			return (0);
		else
			return (EOPNOTSUPP);
	}

	/*
	 * Get argument
	 */
	error = vfs_getopt(mp->mnt_optnew, "from", (void **)&target, &len);
	if (error != 0)
		error = vfs_getopt(mp->mnt_optnew, "target", (void **)&target, &len);
	if (error || target[len - 1] != '\0')
		return (EINVAL);

	/*
	 * Unlock lower node to avoid possible deadlock.
	 */
	if (mp->mnt_vnodecovered->v_op == &null_vnodeops &&
	    VOP_ISLOCKED(mp->mnt_vnodecovered) == LK_EXCLUSIVE) {
		VOP_UNLOCK(mp->mnt_vnodecovered);
		isvnunlocked = true;
	} else {
		isvnunlocked = false;
	}

	/*
	 * Find lower node
	 */
	ndp = &nd;
	NDINIT(ndp, LOOKUP, FOLLOW|LOCKLEAF, UIO_SYSSPACE, target, curthread);
	error = namei(ndp);

	/*
	 * Re-lock vnode.
	 * XXXKIB This is deadlock-prone as well.
	 */
	if (isvnunlocked)
		vn_lock(mp->mnt_vnodecovered, LK_EXCLUSIVE | LK_RETRY);

	if (error)
		return (error);
	NDFREE(ndp, NDF_ONLY_PNBUF);

	/*
	 * Sanity check on lower vnode
	 */
	lowerrootvp = ndp->ni_vp;

	/*
	 * Check multi null mount to avoid `lock against myself' panic.
	 */
	if (mp->mnt_vnodecovered->v_op == &null_vnodeops) {
		nn = VTONULL(mp->mnt_vnodecovered);
		if (nn == NULL || lowerrootvp == nn->null_lowervp) {
			NULLFSDEBUG("nullfs_mount: multi null mount?\n");
			vput(lowerrootvp);
			return (EDEADLK);
		}
	}

	xmp = (struct null_mount *) malloc(sizeof(struct null_mount),
	    M_NULLFSMNT, M_WAITOK | M_ZERO);

	/*
	 * Save pointer to underlying FS and the reference to the
	 * lower root vnode.
	 */
	xmp->nullm_vfs = lowerrootvp->v_mount;
	vref(lowerrootvp);
	xmp->nullm_lowerrootvp = lowerrootvp;
	mp->mnt_data = xmp;

	/*
	 * Make sure the node alias worked.
	 */
	error = null_nodeget(mp, lowerrootvp, &nullm_rootvp);
	if (error != 0) {
		vrele(lowerrootvp);
		free(xmp, M_NULLFSMNT);
		return (error);
	}

	if (NULLVPTOLOWERVP(nullm_rootvp)->v_mount->mnt_flag & MNT_LOCAL) {
		MNT_ILOCK(mp);
		mp->mnt_flag |= MNT_LOCAL;
		MNT_IUNLOCK(mp);
	}

	xmp->nullm_flags |= NULLM_CACHE;
	if (vfs_getopt(mp->mnt_optnew, "nocache", NULL, NULL) == 0 ||
	    (xmp->nullm_vfs->mnt_kern_flag & MNTK_NULL_NOCACHE) != 0)
		xmp->nullm_flags &= ~NULLM_CACHE;

	MNT_ILOCK(mp);
	if ((xmp->nullm_flags & NULLM_CACHE) != 0) {
		mp->mnt_kern_flag |= lowerrootvp->v_mount->mnt_kern_flag &
		    (MNTK_SHARED_WRITES | MNTK_LOOKUP_SHARED |
		    MNTK_EXTENDED_SHARED);
	}
	mp->mnt_kern_flag |= MNTK_LOOKUP_EXCL_DOTDOT | MNTK_NOMSYNC;
	mp->mnt_kern_flag |= lowerrootvp->v_mount->mnt_kern_flag &
	    (MNTK_USES_BCACHE | MNTK_NO_IOPF | MNTK_UNMAPPED_BUFS);
	MNT_IUNLOCK(mp);
	vfs_getnewfsid(mp);
	if ((xmp->nullm_flags & NULLM_CACHE) != 0) {
		MNT_ILOCK(xmp->nullm_vfs);
		TAILQ_INSERT_TAIL(&xmp->nullm_vfs->mnt_uppers, mp,
		    mnt_upper_link);
		MNT_IUNLOCK(xmp->nullm_vfs);
	}

	vfs_mountedfrom(mp, target);
	vput(nullm_rootvp);

	NULLFSDEBUG("nullfs_mount: lower %s, alias at %s\n",
		mp->mnt_stat.f_mntfromname, mp->mnt_stat.f_mntonname);
	return (0);
}

/*
 * Free reference to null layer
 */
static int
nullfs_unmount(mp, mntflags)
	struct mount *mp;
	int mntflags;
{
	struct null_mount *mntdata;
	struct mount *ump;
	int error, flags;

	NULLFSDEBUG("nullfs_unmount: mp = %p\n", (void *)mp);

	if (mntflags & MNT_FORCE)
		flags = FORCECLOSE;
	else
		flags = 0;

	for (;;) {
		/* There is 1 extra root vnode reference (nullm_rootvp). */
		error = vflush(mp, 0, flags, curthread);
		if (error)
			return (error);
		MNT_ILOCK(mp);
		if (mp->mnt_nvnodelistsize == 0) {
			MNT_IUNLOCK(mp);
			break;
		}
		MNT_IUNLOCK(mp);
		if ((mntflags & MNT_FORCE) == 0)
			return (EBUSY);
	}

	/*
	 * Finally, throw away the null_mount structure
	 */
	mntdata = mp->mnt_data;
	ump = mntdata->nullm_vfs;
	if ((mntdata->nullm_flags & NULLM_CACHE) != 0) {
		MNT_ILOCK(ump);
		while ((ump->mnt_kern_flag & MNTK_VGONE_UPPER) != 0) {
			ump->mnt_kern_flag |= MNTK_VGONE_WAITER;
			msleep(&ump->mnt_uppers, &ump->mnt_mtx, 0, "vgnupw", 0);
		}
		TAILQ_REMOVE(&ump->mnt_uppers, mp, mnt_upper_link);
		MNT_IUNLOCK(ump);
	}
	vrele(mntdata->nullm_lowerrootvp);
	mp->mnt_data = NULL;
	free(mntdata, M_NULLFSMNT);
	return (0);
}

static int
nullfs_root(mp, flags, vpp)
	struct mount *mp;
	int flags;
	struct vnode **vpp;
{
	struct vnode *vp;
	struct null_mount *mntdata;
	int error;

	mntdata = MOUNTTONULLMOUNT(mp);
	NULLFSDEBUG("nullfs_root(mp = %p, vp = %p)\n", mp,
	    mntdata->nullm_lowerrootvp);

	error = vget(mntdata->nullm_lowerrootvp, flags);
	if (error == 0) {
		error = null_nodeget(mp, mntdata->nullm_lowerrootvp, &vp);
		if (error == 0) {
			*vpp = vp;
		}
	}
	return (error);
}

static int
nullfs_quotactl(mp, cmd, uid, arg, mp_busy)
	struct mount *mp;
	int cmd;
	uid_t uid;
	void *arg;
	bool *mp_busy;
{
	struct mount *lowermp;
	struct null_mount *mntdata;
	int error;
	bool unbusy;

	mntdata = MOUNTTONULLMOUNT(mp);
	lowermp = atomic_load_ptr(&mntdata->nullm_vfs);
	KASSERT(*mp_busy == true, ("upper mount not busy"));
	/*
	 * See comment in sys_quotactl() for an explanation of why the
	 * lower mount needs to be busied by the caller of VFS_QUOTACTL()
	 * but may be unbusied by the implementation.  We must unbusy
	 * the upper mount for the same reason; otherwise a namei lookup
	 * issued by the VFS_QUOTACTL() implementation could traverse the
	 * upper mount and deadlock.
	 */
	vfs_unbusy(mp);
	*mp_busy = false;
	unbusy = true;
	error = vfs_busy(lowermp, 0);
	if (error == 0)
		error = VFS_QUOTACTL(lowermp, cmd, uid, arg, &unbusy);
	if (unbusy)
		vfs_unbusy(lowermp);

	return (error);
}

static int
nullfs_statfs(mp, sbp)
	struct mount *mp;
	struct statfs *sbp;
{
	int error;
	struct statfs *mstat;

	NULLFSDEBUG("nullfs_statfs(mp = %p, vp = %p->%p)\n", (void *)mp,
	    (void *)MOUNTTONULLMOUNT(mp)->nullm_rootvp,
	    (void *)NULLVPTOLOWERVP(MOUNTTONULLMOUNT(mp)->nullm_rootvp));

	mstat = malloc(sizeof(struct statfs), M_STATFS, M_WAITOK | M_ZERO);

	error = VFS_STATFS(MOUNTTONULLMOUNT(mp)->nullm_vfs, mstat);
	if (error) {
		free(mstat, M_STATFS);
		return (error);
	}

	/* now copy across the "interesting" information and fake the rest */
	sbp->f_type = mstat->f_type;
	sbp->f_flags = (sbp->f_flags & (MNT_RDONLY | MNT_NOEXEC | MNT_NOSUID |
	    MNT_UNION | MNT_NOSYMFOLLOW | MNT_AUTOMOUNTED)) |
	    (mstat->f_flags & ~(MNT_ROOTFS | MNT_AUTOMOUNTED));
	sbp->f_bsize = mstat->f_bsize;
	sbp->f_iosize = mstat->f_iosize;
	sbp->f_blocks = mstat->f_blocks;
	sbp->f_bfree = mstat->f_bfree;
	sbp->f_bavail = mstat->f_bavail;
	sbp->f_files = mstat->f_files;
	sbp->f_ffree = mstat->f_ffree;

	free(mstat, M_STATFS);
	return (0);
}

static int
nullfs_sync(mp, waitfor)
	struct mount *mp;
	int waitfor;
{
	/*
	 * XXX - Assumes no data cached at null layer.
	 */
	return (0);
}

static int
nullfs_vget(mp, ino, flags, vpp)
	struct mount *mp;
	ino_t ino;
	int flags;
	struct vnode **vpp;
{
	int error;

	KASSERT((flags & LK_TYPE_MASK) != 0,
	    ("nullfs_vget: no lock requested"));

	error = VFS_VGET(MOUNTTONULLMOUNT(mp)->nullm_vfs, ino, flags, vpp);
	if (error != 0)
		return (error);
	return (null_nodeget(mp, *vpp, vpp));
}

static int
nullfs_fhtovp(mp, fidp, flags, vpp)
	struct mount *mp;
	struct fid *fidp;
	int flags;
	struct vnode **vpp;
{
	int error;

	error = VFS_FHTOVP(MOUNTTONULLMOUNT(mp)->nullm_vfs, fidp, flags,
	    vpp);
	if (error != 0)
		return (error);
	return (null_nodeget(mp, *vpp, vpp));
}

static int                        
nullfs_extattrctl(mp, cmd, filename_vp, namespace, attrname)
	struct mount *mp;
	int cmd;
	struct vnode *filename_vp;
	int namespace;
	const char *attrname;
{

	return (VFS_EXTATTRCTL(MOUNTTONULLMOUNT(mp)->nullm_vfs, cmd,
	    filename_vp, namespace, attrname));
}

static void
nullfs_reclaim_lowervp(struct mount *mp, struct vnode *lowervp)
{
	struct vnode *vp;

	vp = null_hashget(mp, lowervp);
	if (vp == NULL)
		return;
	VTONULL(vp)->null_flags |= NULLV_NOUNLOCK;
	vgone(vp);
	vput(vp);
}

static void
nullfs_unlink_lowervp(struct mount *mp, struct vnode *lowervp)
{
	struct vnode *vp;
	struct null_node *xp;

	vp = null_hashget(mp, lowervp);
	if (vp == NULL)
		return;
	xp = VTONULL(vp);
	xp->null_flags |= NULLV_DROP | NULLV_NOUNLOCK;
	vhold(vp);
	vunref(vp);

	if (vp->v_usecount == 0) {
		/*
		 * If vunref() dropped the last use reference on the
		 * nullfs vnode, it must be reclaimed, and its lock
		 * was split from the lower vnode lock.  Need to do
		 * extra unlock before allowing the final vdrop() to
		 * free the vnode.
		 */
		KASSERT(VN_IS_DOOMED(vp),
		    ("not reclaimed nullfs vnode %p", vp));
		VOP_UNLOCK(vp);
	} else {
		/*
		 * Otherwise, the nullfs vnode still shares the lock
		 * with the lower vnode, and must not be unlocked.
		 * Also clear the NULLV_NOUNLOCK, the flag is not
		 * relevant for future reclamations.
		 */
		ASSERT_VOP_ELOCKED(vp, "unlink_lowervp");
		KASSERT(!VN_IS_DOOMED(vp),
		    ("reclaimed nullfs vnode %p", vp));
		xp->null_flags &= ~NULLV_NOUNLOCK;
	}
	vdrop(vp);
}

static struct vfsops null_vfsops = {
	.vfs_extattrctl =	nullfs_extattrctl,
	.vfs_fhtovp =		nullfs_fhtovp,
	.vfs_init =		nullfs_init,
	.vfs_mount =		nullfs_mount,
	.vfs_quotactl =		nullfs_quotactl,
	.vfs_root =		nullfs_root,
	.vfs_statfs =		nullfs_statfs,
	.vfs_sync =		nullfs_sync,
	.vfs_uninit =		nullfs_uninit,
	.vfs_unmount =		nullfs_unmount,
	.vfs_vget =		nullfs_vget,
	.vfs_reclaim_lowervp =	nullfs_reclaim_lowervp,
	.vfs_unlink_lowervp =	nullfs_unlink_lowervp,
};

VFS_SET(null_vfsops, nullfs, VFCF_LOOPBACK | VFCF_JAIL);