summaryrefslogtreecommitdiffstats
path: root/sys/kern/vfs_init.c
blob: 0165b38c3cd55d0f9ec33bd1b34745b8de419f3e (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
/*-
 * 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.
 *
 *	@(#)vfs_init.c	8.3 (Berkeley) 1/4/94
 */

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

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/fnv_hash.h>
#include <sys/kernel.h>
#include <sys/linker.h>
#include <sys/mount.h>
#include <sys/proc.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/vnode.h>
#include <sys/malloc.h>

static int	vfs_register(struct vfsconf *);
static int	vfs_unregister(struct vfsconf *);

MALLOC_DEFINE(M_VNODE, "vnodes", "Dynamically allocated vnodes");

/*
 * The highest defined VFS number.
 */
int maxvfsconf = VFS_GENERIC + 1;

/*
 * Single-linked list of configured VFSes.
 * New entries are added/deleted by vfs_register()/vfs_unregister()
 */
struct vfsconfhead vfsconf = TAILQ_HEAD_INITIALIZER(vfsconf);

/*
 * Loader.conf variable vfs.typenumhash enables setting vfc_typenum using a hash
 * calculation on vfc_name, so that it doesn't change when file systems are
 * loaded in a different order. This will avoid the NFS server file handles from
 * changing for file systems that use vfc_typenum in their fsid.
 */
static int	vfs_typenumhash = 1;
TUNABLE_INT("vfs.typenumhash", &vfs_typenumhash);
SYSCTL_INT(_vfs, OID_AUTO, typenumhash, CTLFLAG_RDTUN, &vfs_typenumhash, 0,
    "Set vfc_typenum using a hash calculation on vfc_name, so that it does not"
    "change when file systems are loaded in a different order.");

/*
 * A Zen vnode attribute structure.
 *
 * Initialized when the first filesystem registers by vfs_register().
 */
struct vattr va_null;

/*
 * vfs_init.c
 *
 * Allocate and fill in operations vectors.
 *
 * An undocumented feature of this approach to defining operations is that
 * there can be multiple entries in vfs_opv_descs for the same operations
 * vector. This allows third parties to extend the set of operations
 * supported by another layer in a binary compatibile way. For example,
 * assume that NFS needed to be modified to support Ficus. NFS has an entry
 * (probably nfs_vnopdeop_decls) declaring all the operations NFS supports by
 * default. Ficus could add another entry (ficus_nfs_vnodeop_decl_entensions)
 * listing those new operations Ficus adds to NFS, all without modifying the
 * NFS code. (Of couse, the OTW NFS protocol still needs to be munged, but
 * that is a(whole)nother story.) This is a feature.
 */

/*
 * Routines having to do with the management of the vnode table.
 */

struct vfsconf *
vfs_byname(const char *name)
{
	struct vfsconf *vfsp;

	if (!strcmp(name, "ffs"))
		name = "ufs";
	TAILQ_FOREACH(vfsp, &vfsconf, vfc_list)
		if (!strcmp(name, vfsp->vfc_name))
			return (vfsp);
	return (NULL);
}

struct vfsconf *
vfs_byname_kld(const char *fstype, struct thread *td, int *error)
{
	struct vfsconf *vfsp;
	int fileid;

	vfsp = vfs_byname(fstype);
	if (vfsp != NULL)
		return (vfsp);

	/* Try to load the respective module. */
	*error = kern_kldload(td, fstype, &fileid);
	if (*error)
		return (NULL);

	/* Look up again to see if the VFS was loaded. */
	vfsp = vfs_byname(fstype);
	if (vfsp == NULL) {
		(void)kern_kldunload(td, fileid, LINKER_UNLOAD_FORCE);
		*error = ENODEV;
		return (NULL);
	}
	return (vfsp);
}


/* Register a new filesystem type in the global table */
static int
vfs_register(struct vfsconf *vfc)
{
	struct sysctl_oid *oidp;
	struct vfsops *vfsops;
	static int once;
	struct vfsconf *tvfc;
	uint32_t hashval;
	int secondpass;

	if (!once) {
		vattr_null(&va_null);
		once = 1;
	}
	
	if (vfc->vfc_version != VFS_VERSION) {
		printf("ERROR: filesystem %s, unsupported ABI version %x\n",
		    vfc->vfc_name, vfc->vfc_version);
		return (EINVAL);
	}
	if (vfs_byname(vfc->vfc_name) != NULL)
		return EEXIST;

	if (vfs_typenumhash != 0) {
		/*
		 * Calculate a hash on vfc_name to use for vfc_typenum. Unless
		 * all of 1<->255 are assigned, it is limited to 8bits since
		 * that is what ZFS uses from vfc_typenum and is also the
		 * preferred range for vfs_getnewfsid().
		 */
		hashval = fnv_32_str(vfc->vfc_name, FNV1_32_INIT);
		hashval &= 0xff;
		secondpass = 0;
		do {
			/* Look for and fix any collision. */
			TAILQ_FOREACH(tvfc, &vfsconf, vfc_list) {
				if (hashval == tvfc->vfc_typenum) {
					if (hashval == 255 && secondpass == 0) {
						hashval = 1;
						secondpass = 1;
					} else
						hashval++;
					break;
				}
			}
		} while (tvfc != NULL);
		vfc->vfc_typenum = hashval;
		if (vfc->vfc_typenum >= maxvfsconf)
			maxvfsconf = vfc->vfc_typenum + 1;
	} else
		vfc->vfc_typenum = maxvfsconf++;
	TAILQ_INSERT_TAIL(&vfsconf, vfc, vfc_list);

	/*
	 * If this filesystem has a sysctl node under vfs
	 * (i.e. vfs.xxfs), then change the oid number of that node to 
	 * match the filesystem's type number.  This allows user code
	 * which uses the type number to read sysctl variables defined
	 * by the filesystem to continue working. Since the oids are
	 * in a sorted list, we need to make sure the order is
	 * preserved by re-registering the oid after modifying its
	 * number.
	 */
	sysctl_lock();
	SLIST_FOREACH(oidp, &sysctl__vfs_children, oid_link)
		if (strcmp(oidp->oid_name, vfc->vfc_name) == 0) {
			sysctl_unregister_oid(oidp);
			oidp->oid_number = vfc->vfc_typenum;
			sysctl_register_oid(oidp);
			break;
		}
	sysctl_unlock();

	/*
	 * Initialise unused ``struct vfsops'' fields, to use
	 * the vfs_std*() functions.  Note, we need the mount
	 * and unmount operations, at the least.  The check
	 * for vfsops available is just a debugging aid.
	 */
	KASSERT(vfc->vfc_vfsops != NULL,
	    ("Filesystem %s has no vfsops", vfc->vfc_name));
	/*
	 * Check the mount and unmount operations.
	 */
	vfsops = vfc->vfc_vfsops;
	KASSERT(vfsops->vfs_mount != NULL,
	    ("Filesystem %s has no mount op", vfc->vfc_name));
	KASSERT(vfsops->vfs_unmount != NULL,
	    ("Filesystem %s has no unmount op", vfc->vfc_name));

	if (vfsops->vfs_root == NULL)
		/* return file system's root vnode */
		vfsops->vfs_root =	vfs_stdroot;
	if (vfsops->vfs_quotactl == NULL)
		/* quota control */
		vfsops->vfs_quotactl =	vfs_stdquotactl;
	if (vfsops->vfs_statfs == NULL)
		/* return file system's status */
		vfsops->vfs_statfs =	vfs_stdstatfs;
	if (vfsops->vfs_sync == NULL)
		/*
		 * flush unwritten data (nosync)
		 * file systems can use vfs_stdsync
		 * explicitly by setting it in the
		 * vfsop vector.
		 */
		vfsops->vfs_sync =	vfs_stdnosync;
	if (vfsops->vfs_vget == NULL)
		/* convert an inode number to a vnode */
		vfsops->vfs_vget =	vfs_stdvget;
	if (vfsops->vfs_fhtovp == NULL)
		/* turn an NFS file handle into a vnode */
		vfsops->vfs_fhtovp =	vfs_stdfhtovp;
	if (vfsops->vfs_checkexp == NULL)
		/* check if file system is exported */
		vfsops->vfs_checkexp =	vfs_stdcheckexp;
	if (vfsops->vfs_init == NULL)
		/* file system specific initialisation */
		vfsops->vfs_init =	vfs_stdinit;
	if (vfsops->vfs_uninit == NULL)
		/* file system specific uninitialisation */
		vfsops->vfs_uninit =	vfs_stduninit;
	if (vfsops->vfs_extattrctl == NULL)
		/* extended attribute control */
		vfsops->vfs_extattrctl = vfs_stdextattrctl;
	if (vfsops->vfs_sysctl == NULL)
		vfsops->vfs_sysctl = vfs_stdsysctl;
	
	/*
	 * Call init function for this VFS...
	 */
	(*(vfc->vfc_vfsops->vfs_init))(vfc);

	return 0;
}


/* Remove registration of a filesystem type */
static int
vfs_unregister(struct vfsconf *vfc)
{
	struct vfsconf *vfsp;
	int error, i, maxtypenum;

	i = vfc->vfc_typenum;

	vfsp = vfs_byname(vfc->vfc_name);
	if (vfsp == NULL)
		return EINVAL;
	if (vfsp->vfc_refcount)
		return EBUSY;
	if (vfc->vfc_vfsops->vfs_uninit != NULL) {
		error = (*vfc->vfc_vfsops->vfs_uninit)(vfsp);
		if (error)
			return (error);
	}
	TAILQ_REMOVE(&vfsconf, vfsp, vfc_list);
	maxtypenum = VFS_GENERIC;
	TAILQ_FOREACH(vfsp, &vfsconf, vfc_list)
		if (maxtypenum < vfsp->vfc_typenum)
			maxtypenum = vfsp->vfc_typenum;
	maxvfsconf = maxtypenum + 1;
	return 0;
}

/*
 * Standard kernel module handling code for filesystem modules.
 * Referenced from VFS_SET().
 */
int
vfs_modevent(module_t mod, int type, void *data)
{
	struct vfsconf *vfc;
	int error = 0;

	vfc = (struct vfsconf *)data;

	switch (type) {
	case MOD_LOAD:
		if (vfc)
			error = vfs_register(vfc);
		break;

	case MOD_UNLOAD:
		if (vfc)
			error = vfs_unregister(vfc);
		break;
	default:
		error = EOPNOTSUPP;
		break;
	}
	return (error);
}
OpenPOWER on IntegriCloud