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
|
/* $NetBSD: tmpfs_vfsops.c,v 1.10 2005/12/11 12:24:29 christos Exp $ */
/*-
* Copyright (c) 2005 The NetBSD Foundation, Inc.
* All rights reserved.
*
* This code is derived from software contributed to The NetBSD Foundation
* by Julio M. Merino Vidal, developed as part of Google's Summer of Code
* 2005 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 NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
*/
/*
* Efficient memory file system.
*
* tmpfs is a file system that uses NetBSD's virtual memory sub-system
* (the well-known UVM) to store file data and metadata in an efficient
* way. This means that it does not follow the structure of an on-disk
* file system because it simply does not need to. Instead, it uses
* memory-specific data structures and algorithms to automatically
* allocate and release resources.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/kernel.h>
#include <sys/stat.h>
#include <sys/systm.h>
#include <sys/sysctl.h>
#include <vm/vm.h>
#include <vm/vm_object.h>
#include <vm/vm_param.h>
#include <fs/tmpfs/tmpfs.h>
/*
* Default permission for root node
*/
#define TMPFS_DEFAULT_ROOT_MODE (S_IRWXU|S_IRGRP|S_IXGRP|S_IROTH|S_IXOTH)
MALLOC_DEFINE(M_TMPFSMNT, "tmpfs mount", "tmpfs mount structures");
MALLOC_DEFINE(M_TMPFSNAME, "tmpfs name", "tmpfs file names");
/* --------------------------------------------------------------------- */
static int tmpfs_mount(struct mount *);
static int tmpfs_unmount(struct mount *, int);
static int tmpfs_root(struct mount *, int flags, struct vnode **);
static int tmpfs_fhtovp(struct mount *, struct fid *, int,
struct vnode **);
static int tmpfs_statfs(struct mount *, struct statfs *);
/* --------------------------------------------------------------------- */
static const char *tmpfs_opts[] = {
"from", "size", "maxfilesize", "inodes", "uid", "gid", "mode", "export",
NULL
};
static const char *tmpfs_updateopts[] = {
"from", "export", NULL
};
/* --------------------------------------------------------------------- */
static int
tmpfs_node_ctor(void *mem, int size, void *arg, int flags)
{
struct tmpfs_node *node = (struct tmpfs_node *)mem;
node->tn_gen++;
node->tn_size = 0;
node->tn_status = 0;
node->tn_flags = 0;
node->tn_links = 0;
node->tn_vnode = NULL;
node->tn_vpstate = 0;
return (0);
}
static void
tmpfs_node_dtor(void *mem, int size, void *arg)
{
struct tmpfs_node *node = (struct tmpfs_node *)mem;
node->tn_type = VNON;
}
static int
tmpfs_node_init(void *mem, int size, int flags)
{
struct tmpfs_node *node = (struct tmpfs_node *)mem;
node->tn_id = 0;
mtx_init(&node->tn_interlock, "tmpfs node interlock", NULL, MTX_DEF);
node->tn_gen = arc4random();
return (0);
}
static void
tmpfs_node_fini(void *mem, int size)
{
struct tmpfs_node *node = (struct tmpfs_node *)mem;
mtx_destroy(&node->tn_interlock);
}
static int
tmpfs_mount(struct mount *mp)
{
const size_t nodes_per_page = howmany(PAGE_SIZE,
sizeof(struct tmpfs_dirent) + sizeof(struct tmpfs_node));
struct tmpfs_mount *tmp;
struct tmpfs_node *root;
int error;
/* Size counters. */
u_quad_t pages;
off_t nodes_max, size_max, maxfilesize;
/* Root node attributes. */
uid_t root_uid;
gid_t root_gid;
mode_t root_mode;
struct vattr va;
if (vfs_filteropt(mp->mnt_optnew, tmpfs_opts))
return (EINVAL);
if (mp->mnt_flag & MNT_UPDATE) {
/* Only support update mounts for certain options. */
if (vfs_filteropt(mp->mnt_optnew, tmpfs_updateopts) != 0)
return (EOPNOTSUPP);
if (vfs_flagopt(mp->mnt_optnew, "ro", NULL, 0) !=
((struct tmpfs_mount *)mp->mnt_data)->tm_ronly)
return (EOPNOTSUPP);
return (0);
}
vn_lock(mp->mnt_vnodecovered, LK_SHARED | LK_RETRY);
error = VOP_GETATTR(mp->mnt_vnodecovered, &va, mp->mnt_cred);
VOP_UNLOCK(mp->mnt_vnodecovered, 0);
if (error)
return (error);
if (mp->mnt_cred->cr_ruid != 0 ||
vfs_scanopt(mp->mnt_optnew, "gid", "%d", &root_gid) != 1)
root_gid = va.va_gid;
if (mp->mnt_cred->cr_ruid != 0 ||
vfs_scanopt(mp->mnt_optnew, "uid", "%d", &root_uid) != 1)
root_uid = va.va_uid;
if (mp->mnt_cred->cr_ruid != 0 ||
vfs_scanopt(mp->mnt_optnew, "mode", "%ho", &root_mode) != 1)
root_mode = va.va_mode;
if (vfs_getopt_size(mp->mnt_optnew, "inodes", &nodes_max) != 0)
nodes_max = 0;
if (vfs_getopt_size(mp->mnt_optnew, "size", &size_max) != 0)
size_max = 0;
if (vfs_getopt_size(mp->mnt_optnew, "maxfilesize", &maxfilesize) != 0)
maxfilesize = 0;
/* Do not allow mounts if we do not have enough memory to preserve
* the minimum reserved pages. */
if (tmpfs_mem_avail() < TMPFS_PAGES_MINRESERVED)
return ENOSPC;
/* Get the maximum number of memory pages this file system is
* allowed to use, based on the maximum size the user passed in
* the mount structure. A value of zero is treated as if the
* maximum available space was requested. */
if (size_max < PAGE_SIZE || size_max > OFF_MAX - PAGE_SIZE ||
(SIZE_MAX < OFF_MAX && size_max / PAGE_SIZE >= SIZE_MAX))
pages = SIZE_MAX;
else
pages = howmany(size_max, PAGE_SIZE);
MPASS(pages > 0);
if (nodes_max <= 3) {
if (pages < INT_MAX / nodes_per_page)
nodes_max = pages * nodes_per_page;
else
nodes_max = INT_MAX;
}
if (nodes_max > INT_MAX)
nodes_max = INT_MAX;
MPASS(nodes_max >= 3);
/* Allocate the tmpfs mount structure and fill it. */
tmp = (struct tmpfs_mount *)malloc(sizeof(struct tmpfs_mount),
M_TMPFSMNT, M_WAITOK | M_ZERO);
mtx_init(&tmp->allnode_lock, "tmpfs allnode lock", NULL, MTX_DEF);
tmp->tm_nodes_max = nodes_max;
tmp->tm_nodes_inuse = 0;
tmp->tm_maxfilesize = maxfilesize > 0 ? maxfilesize : OFF_MAX;
LIST_INIT(&tmp->tm_nodes_used);
tmp->tm_pages_max = pages;
tmp->tm_pages_used = 0;
tmp->tm_ino_unr = new_unrhdr(2, INT_MAX, &tmp->allnode_lock);
tmp->tm_dirent_pool = uma_zcreate("TMPFS dirent",
sizeof(struct tmpfs_dirent),
NULL, NULL, NULL, NULL,
UMA_ALIGN_PTR, 0);
tmp->tm_node_pool = uma_zcreate("TMPFS node",
sizeof(struct tmpfs_node),
tmpfs_node_ctor, tmpfs_node_dtor,
tmpfs_node_init, tmpfs_node_fini,
UMA_ALIGN_PTR, 0);
tmp->tm_ronly = (mp->mnt_flag & MNT_RDONLY) != 0;
/* Allocate the root node. */
error = tmpfs_alloc_node(tmp, VDIR, root_uid,
root_gid, root_mode & ALLPERMS, NULL, NULL,
VNOVAL, &root);
if (error != 0 || root == NULL) {
uma_zdestroy(tmp->tm_node_pool);
uma_zdestroy(tmp->tm_dirent_pool);
delete_unrhdr(tmp->tm_ino_unr);
free(tmp, M_TMPFSMNT);
return error;
}
KASSERT(root->tn_id == 2, ("tmpfs root with invalid ino: %d", root->tn_id));
tmp->tm_root = root;
MNT_ILOCK(mp);
mp->mnt_flag |= MNT_LOCAL;
mp->mnt_kern_flag |= MNTK_MPSAFE;
MNT_IUNLOCK(mp);
mp->mnt_data = tmp;
mp->mnt_stat.f_namemax = MAXNAMLEN;
vfs_getnewfsid(mp);
vfs_mountedfrom(mp, "tmpfs");
return 0;
}
/* --------------------------------------------------------------------- */
/* ARGSUSED2 */
static int
tmpfs_unmount(struct mount *mp, int mntflags)
{
int error;
int flags = 0;
struct tmpfs_mount *tmp;
struct tmpfs_node *node;
/* Handle forced unmounts. */
if (mntflags & MNT_FORCE)
flags |= FORCECLOSE;
/* Finalize all pending I/O. */
error = vflush(mp, 0, flags, curthread);
if (error != 0)
return error;
tmp = VFS_TO_TMPFS(mp);
/* Free all associated data. The loop iterates over the linked list
* we have containing all used nodes. For each of them that is
* a directory, we free all its directory entries. Note that after
* freeing a node, it will automatically go to the available list,
* so we will later have to iterate over it to release its items. */
node = LIST_FIRST(&tmp->tm_nodes_used);
while (node != NULL) {
struct tmpfs_node *next;
if (node->tn_type == VDIR) {
struct tmpfs_dirent *de;
de = TAILQ_FIRST(&node->tn_dir.tn_dirhead);
while (de != NULL) {
struct tmpfs_dirent *nde;
nde = TAILQ_NEXT(de, td_entries);
tmpfs_free_dirent(tmp, de, FALSE);
de = nde;
node->tn_size -= sizeof(struct tmpfs_dirent);
}
}
next = LIST_NEXT(node, tn_entries);
tmpfs_free_node(tmp, node);
node = next;
}
uma_zdestroy(tmp->tm_dirent_pool);
uma_zdestroy(tmp->tm_node_pool);
delete_unrhdr(tmp->tm_ino_unr);
mtx_destroy(&tmp->allnode_lock);
MPASS(tmp->tm_pages_used == 0);
MPASS(tmp->tm_nodes_inuse == 0);
/* Throw away the tmpfs_mount structure. */
free(mp->mnt_data, M_TMPFSMNT);
mp->mnt_data = NULL;
MNT_ILOCK(mp);
mp->mnt_flag &= ~MNT_LOCAL;
MNT_IUNLOCK(mp);
return 0;
}
/* --------------------------------------------------------------------- */
static int
tmpfs_root(struct mount *mp, int flags, struct vnode **vpp)
{
int error;
error = tmpfs_alloc_vp(mp, VFS_TO_TMPFS(mp)->tm_root, flags, vpp);
if (!error)
(*vpp)->v_vflag |= VV_ROOT;
return error;
}
/* --------------------------------------------------------------------- */
static int
tmpfs_fhtovp(struct mount *mp, struct fid *fhp, int flags,
struct vnode **vpp)
{
boolean_t found;
struct tmpfs_fid *tfhp;
struct tmpfs_mount *tmp;
struct tmpfs_node *node;
tmp = VFS_TO_TMPFS(mp);
tfhp = (struct tmpfs_fid *)fhp;
if (tfhp->tf_len != sizeof(struct tmpfs_fid))
return EINVAL;
if (tfhp->tf_id >= tmp->tm_nodes_max)
return EINVAL;
found = FALSE;
TMPFS_LOCK(tmp);
LIST_FOREACH(node, &tmp->tm_nodes_used, tn_entries) {
if (node->tn_id == tfhp->tf_id &&
node->tn_gen == tfhp->tf_gen) {
found = TRUE;
break;
}
}
TMPFS_UNLOCK(tmp);
if (found)
return (tmpfs_alloc_vp(mp, node, LK_EXCLUSIVE, vpp));
return (EINVAL);
}
/* --------------------------------------------------------------------- */
/* ARGSUSED2 */
static int
tmpfs_statfs(struct mount *mp, struct statfs *sbp)
{
struct tmpfs_mount *tmp;
size_t used;
tmp = VFS_TO_TMPFS(mp);
sbp->f_iosize = PAGE_SIZE;
sbp->f_bsize = PAGE_SIZE;
used = tmpfs_pages_used(tmp);
if (tmp->tm_pages_max != SIZE_MAX)
sbp->f_blocks = tmp->tm_pages_max;
else
sbp->f_blocks = used + tmpfs_mem_avail();
if (sbp->f_blocks <= used)
sbp->f_bavail = 0;
else
sbp->f_bavail = sbp->f_blocks - used;
sbp->f_bfree = sbp->f_bavail;
used = tmp->tm_nodes_inuse;
sbp->f_files = tmp->tm_nodes_max;
if (sbp->f_files <= used)
sbp->f_ffree = 0;
else
sbp->f_ffree = sbp->f_files - used;
/* sbp->f_owner = tmp->tn_uid; */
return 0;
}
/* --------------------------------------------------------------------- */
/*
* tmpfs vfs operations.
*/
struct vfsops tmpfs_vfsops = {
.vfs_mount = tmpfs_mount,
.vfs_unmount = tmpfs_unmount,
.vfs_root = tmpfs_root,
.vfs_statfs = tmpfs_statfs,
.vfs_fhtovp = tmpfs_fhtovp,
};
VFS_SET(tmpfs_vfsops, tmpfs, 0);
|