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
|
/*-
* Copyright (c) 1999-2004 Poul-Henning Kamp
* Copyright (c) 1999 Michael Smith
* Copyright (c) 1989, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* 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 AUTHOR 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 AUTHOR 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/conf.h>
#include <sys/fcntl.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/libkern.h>
#include <sys/malloc.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/namei.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/filedesc.h>
#include <sys/reboot.h>
#include <sys/syscallsubr.h>
#include <sys/sysproto.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/systm.h>
#include <sys/vnode.h>
#include <vm/uma.h>
#include <geom/geom.h>
#include <machine/stdarg.h>
#include "opt_rootdevname.h"
#define ROOTNAME "root_device"
static int vfs_mountroot_ask(void);
static int vfs_mountroot_try(const char *mountfrom, const char *options);
/*
* The vnode of the system's root (/ in the filesystem, without chroot
* active.)
*/
struct vnode *rootvnode;
/*
* The root filesystem is detailed in the kernel environment variable
* vfs.root.mountfrom, which is expected to be in the general format
*
* <vfsname>:[<path>][ <vfsname>:[<path>] ...]
* vfsname := the name of a VFS known to the kernel and capable
* of being mounted as root
* path := disk device name or other data used by the filesystem
* to locate its physical store
*
* If the environment variable vfs.root.mountfrom is a space separated list,
* each list element is tried in turn and the root filesystem will be mounted
* from the first one that suceeds.
*
* The environment variable vfs.root.mountfrom.options is a comma delimited
* set of string mount options. These mount options must be parseable
* by nmount() in the kernel.
*/
/*
* The root specifiers we will try if RB_CDROM is specified.
*/
static char *cdrom_rootdevnames[] = {
"cd9660:cd0",
"cd9660:acd0",
NULL
};
/* legacy find-root code */
char *rootdevnames[2] = {NULL, NULL};
#ifndef ROOTDEVNAME
# define ROOTDEVNAME NULL
#endif
static const char *ctrootdevname = ROOTDEVNAME;
struct root_hold_token {
const char *who;
LIST_ENTRY(root_hold_token) list;
};
static LIST_HEAD(, root_hold_token) root_holds =
LIST_HEAD_INITIALIZER(root_holds);
static int root_mount_complete;
struct root_hold_token *
root_mount_hold(const char *identifier)
{
struct root_hold_token *h;
if (root_mounted())
return (NULL);
h = malloc(sizeof *h, M_DEVBUF, M_ZERO | M_WAITOK);
h->who = identifier;
mtx_lock(&mountlist_mtx);
LIST_INSERT_HEAD(&root_holds, h, list);
mtx_unlock(&mountlist_mtx);
return (h);
}
void
root_mount_rel(struct root_hold_token *h)
{
if (h == NULL)
return;
mtx_lock(&mountlist_mtx);
LIST_REMOVE(h, list);
wakeup(&root_holds);
mtx_unlock(&mountlist_mtx);
free(h, M_DEVBUF);
}
static void
root_mount_prepare(void)
{
struct root_hold_token *h;
struct timeval lastfail;
int curfail = 0;
for (;;) {
DROP_GIANT();
g_waitidle();
PICKUP_GIANT();
mtx_lock(&mountlist_mtx);
if (LIST_EMPTY(&root_holds)) {
mtx_unlock(&mountlist_mtx);
break;
}
if (ppsratecheck(&lastfail, &curfail, 1)) {
printf("Root mount waiting for:");
LIST_FOREACH(h, &root_holds, list)
printf(" %s", h->who);
printf("\n");
}
msleep(&root_holds, &mountlist_mtx, PZERO | PDROP, "roothold",
hz);
}
}
static void
root_mount_done(void)
{
/* Keep prison0's root in sync with the global rootvnode. */
mtx_lock(&prison0.pr_mtx);
prison0.pr_root = rootvnode;
vref(prison0.pr_root);
mtx_unlock(&prison0.pr_mtx);
/*
* Use a mutex to prevent the wakeup being missed and waiting for
* an extra 1 second sleep.
*/
mtx_lock(&mountlist_mtx);
root_mount_complete = 1;
wakeup(&root_mount_complete);
mtx_unlock(&mountlist_mtx);
}
int
root_mounted(void)
{
/* No mutex is acquired here because int stores are atomic. */
return (root_mount_complete);
}
void
root_mount_wait(void)
{
/*
* Panic on an obvious deadlock - the function can't be called from
* a thread which is doing the whole SYSINIT stuff.
*/
KASSERT(curthread->td_proc->p_pid != 0,
("root_mount_wait: cannot be called from the swapper thread"));
mtx_lock(&mountlist_mtx);
while (!root_mount_complete) {
msleep(&root_mount_complete, &mountlist_mtx, PZERO, "rootwait",
hz);
}
mtx_unlock(&mountlist_mtx);
}
static void
set_rootvnode(void)
{
struct proc *p;
if (VFS_ROOT(TAILQ_FIRST(&mountlist), LK_EXCLUSIVE, &rootvnode))
panic("Cannot find root vnode");
VOP_UNLOCK(rootvnode, 0);
p = curthread->td_proc;
FILEDESC_XLOCK(p->p_fd);
if (p->p_fd->fd_cdir != NULL)
vrele(p->p_fd->fd_cdir);
p->p_fd->fd_cdir = rootvnode;
VREF(rootvnode);
if (p->p_fd->fd_rdir != NULL)
vrele(p->p_fd->fd_rdir);
p->p_fd->fd_rdir = rootvnode;
VREF(rootvnode);
FILEDESC_XUNLOCK(p->p_fd);
EVENTHANDLER_INVOKE(mountroot);
}
static void
devfs_first(void)
{
struct thread *td = curthread;
struct vfsoptlist *opts;
struct vfsconf *vfsp;
struct mount *mp = NULL;
int error;
vfsp = vfs_byname("devfs");
KASSERT(vfsp != NULL, ("Could not find devfs by name"));
if (vfsp == NULL)
return;
mp = vfs_mount_alloc(NULLVP, vfsp, "/dev", td->td_ucred);
error = VFS_MOUNT(mp);
KASSERT(error == 0, ("VFS_MOUNT(devfs) failed %d", error));
if (error)
return;
opts = malloc(sizeof(struct vfsoptlist), M_MOUNT, M_WAITOK);
TAILQ_INIT(opts);
mp->mnt_opt = opts;
mtx_lock(&mountlist_mtx);
TAILQ_INSERT_HEAD(&mountlist, mp, mnt_list);
mtx_unlock(&mountlist_mtx);
set_rootvnode();
error = kern_symlink(td, "/", "dev", UIO_SYSSPACE);
if (error)
printf("kern_symlink /dev -> / returns %d\n", error);
}
static void
devfs_fixup(struct thread *td)
{
struct nameidata nd;
struct vnode *vp, *dvp;
struct mount *mp;
int error;
/* Remove our devfs mount from the mountlist and purge the cache */
mtx_lock(&mountlist_mtx);
mp = TAILQ_FIRST(&mountlist);
TAILQ_REMOVE(&mountlist, mp, mnt_list);
mtx_unlock(&mountlist_mtx);
cache_purgevfs(mp);
VFS_ROOT(mp, LK_EXCLUSIVE, &dvp);
VI_LOCK(dvp);
dvp->v_iflag &= ~VI_MOUNT;
VI_UNLOCK(dvp);
dvp->v_mountedhere = NULL;
/* Set up the real rootvnode, and purge the cache */
TAILQ_FIRST(&mountlist)->mnt_vnodecovered = NULL;
set_rootvnode();
cache_purgevfs(rootvnode->v_mount);
NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE, "/dev", td);
error = namei(&nd);
if (error) {
printf("Lookup of /dev for devfs, error: %d\n", error);
vput(dvp);
vfs_unbusy(mp);
return;
}
NDFREE(&nd, NDF_ONLY_PNBUF);
vp = nd.ni_vp;
if (vp->v_type != VDIR) {
printf("/dev is not a directory\n");
vput(dvp);
vput(vp);
vfs_unbusy(mp);
return;
}
error = vinvalbuf(vp, V_SAVE, 0, 0);
if (error) {
printf("vinvalbuf() of /dev failed, error: %d\n", error);
vput(dvp);
vput(vp);
vfs_unbusy(mp);
return;
}
cache_purge(vp);
mp->mnt_vnodecovered = vp;
vp->v_mountedhere = mp;
mtx_lock(&mountlist_mtx);
TAILQ_INSERT_TAIL(&mountlist, mp, mnt_list);
mtx_unlock(&mountlist_mtx);
VOP_UNLOCK(vp, 0);
vput(dvp);
vfs_unbusy(mp);
/* Unlink the no longer needed /dev/dev -> / symlink */
error = kern_unlink(td, "/dev/dev", UIO_SYSSPACE);
if (error)
printf("kern_unlink of /dev/dev failed, error: %d\n", error);
}
void
vfs_mountroot(void)
{
char *cp, *cpt, *options, *tmpdev;
int error, i, asked = 0;
options = NULL;
root_mount_prepare();
devfs_first();
/*
* We are booted with instructions to prompt for the root filesystem.
*/
if (boothowto & RB_ASKNAME) {
if (!vfs_mountroot_ask())
goto mounted;
asked = 1;
}
options = getenv("vfs.root.mountfrom.options");
/*
* The root filesystem information is compiled in, and we are
* booted with instructions to use it.
*/
if (ctrootdevname != NULL && (boothowto & RB_DFLTROOT)) {
if (!vfs_mountroot_try(ctrootdevname, options))
goto mounted;
ctrootdevname = NULL;
}
/*
* We've been given the generic "use CDROM as root" flag. This is
* necessary because one media may be used in many different
* devices, so we need to search for them.
*/
if (boothowto & RB_CDROM) {
for (i = 0; cdrom_rootdevnames[i] != NULL; i++) {
if (!vfs_mountroot_try(cdrom_rootdevnames[i], options))
goto mounted;
}
}
/*
* Try to use the value read by the loader from /etc/fstab, or
* supplied via some other means. This is the preferred
* mechanism.
*/
cp = getenv("vfs.root.mountfrom");
if (cp != NULL) {
cpt = cp;
while ((tmpdev = strsep(&cpt, " \t")) != NULL) {
error = vfs_mountroot_try(tmpdev, options);
if (error == 0) {
freeenv(cp);
goto mounted;
}
}
freeenv(cp);
}
/*
* Try values that may have been computed by code during boot
*/
if (!vfs_mountroot_try(rootdevnames[0], options))
goto mounted;
if (!vfs_mountroot_try(rootdevnames[1], options))
goto mounted;
/*
* If we (still) have a compiled-in default, try it.
*/
if (ctrootdevname != NULL)
if (!vfs_mountroot_try(ctrootdevname, options))
goto mounted;
/*
* Everything so far has failed, prompt on the console if we haven't
* already tried that.
*/
if (!asked)
if (!vfs_mountroot_ask())
goto mounted;
panic("Root mount failed, startup aborted.");
mounted:
root_mount_done();
freeenv(options);
}
static struct mntarg *
parse_mountroot_options(struct mntarg *ma, const char *options)
{
char *p;
char *name, *name_arg;
char *val, *val_arg;
char *opts;
if (options == NULL || options[0] == '\0')
return (ma);
p = opts = strdup(options, M_MOUNT);
if (opts == NULL) {
return (ma);
}
while((name = strsep(&p, ",")) != NULL) {
if (name[0] == '\0')
break;
val = strchr(name, '=');
if (val != NULL) {
*val = '\0';
++val;
}
if( strcmp(name, "rw") == 0 ||
strcmp(name, "noro") == 0) {
/*
* The first time we mount the root file system,
* we need to mount 'ro', so We need to ignore
* 'rw' and 'noro' mount options.
*/
continue;
}
name_arg = strdup(name, M_MOUNT);
val_arg = NULL;
if (val != NULL)
val_arg = strdup(val, M_MOUNT);
ma = mount_arg(ma, name_arg, val_arg,
(val_arg != NULL ? -1 : 0));
}
free(opts, M_MOUNT);
return (ma);
}
/*
* Mount (mountfrom) as the root filesystem.
*/
static int
vfs_mountroot_try(const char *mountfrom, const char *options)
{
struct mount *mp;
struct mntarg *ma;
char *vfsname, *path;
time_t timebase;
int error;
char patt[32];
char errmsg[255];
vfsname = NULL;
path = NULL;
mp = NULL;
ma = NULL;
error = EINVAL;
bzero(errmsg, sizeof(errmsg));
if (mountfrom == NULL)
return (error); /* don't complain */
printf("Trying to mount root from %s\n", mountfrom);
/* parse vfs name and path */
vfsname = malloc(MFSNAMELEN, M_MOUNT, M_WAITOK);
path = malloc(MNAMELEN, M_MOUNT, M_WAITOK);
vfsname[0] = path[0] = 0;
sprintf(patt, "%%%d[a-z0-9]:%%%ds", MFSNAMELEN, MNAMELEN);
if (sscanf(mountfrom, patt, vfsname, path) < 1)
goto out;
if (path[0] == '\0')
strcpy(path, ROOTNAME);
ma = mount_arg(ma, "fstype", vfsname, -1);
ma = mount_arg(ma, "fspath", "/", -1);
ma = mount_arg(ma, "from", path, -1);
ma = mount_arg(ma, "errmsg", errmsg, sizeof(errmsg));
ma = mount_arg(ma, "ro", NULL, 0);
ma = parse_mountroot_options(ma, options);
error = kernel_mount(ma, MNT_ROOTFS);
if (error == 0) {
/*
* We mount devfs prior to mounting the / FS, so the first
* entry will typically be devfs.
*/
mp = TAILQ_FIRST(&mountlist);
KASSERT(mp != NULL, ("%s: mountlist is empty", __func__));
/*
* Iterate over all currently mounted file systems and use
* the time stamp found to check and/or initialize the RTC.
* Typically devfs has no time stamp and the only other FS
* is the actual / FS.
* Call inittodr() only once and pass it the largest of the
* timestamps we encounter.
*/
timebase = 0;
do {
if (mp->mnt_time > timebase)
timebase = mp->mnt_time;
mp = TAILQ_NEXT(mp, mnt_list);
} while (mp != NULL);
inittodr(timebase);
devfs_fixup(curthread);
}
if (error != 0 ) {
printf("ROOT MOUNT ERROR: %s\n", errmsg);
printf("If you have invalid mount options, reboot, and ");
printf("first try the following from\n");
printf("the loader prompt:\n\n");
printf(" set vfs.root.mountfrom.options=rw\n\n");
printf("and then remove invalid mount options from ");
printf("/etc/fstab.\n\n");
}
out:
free(path, M_MOUNT);
free(vfsname, M_MOUNT);
return (error);
}
static int
vfs_mountroot_ask(void)
{
char name[128];
char *mountfrom;
char *options;
for(;;) {
printf("Loader variables:\n");
printf("vfs.root.mountfrom=");
mountfrom = getenv("vfs.root.mountfrom");
if (mountfrom != NULL) {
printf("%s", mountfrom);
}
printf("\n");
printf("vfs.root.mountfrom.options=");
options = getenv("vfs.root.mountfrom.options");
if (options != NULL) {
printf("%s", options);
}
printf("\n");
freeenv(mountfrom);
freeenv(options);
printf("\nManual root filesystem specification:\n");
printf(" <fstype>:<device> Mount <device> using filesystem <fstype>\n");
printf(" eg. zfs:tank\n");
printf(" eg. ufs:/dev/da0s1a\n");
printf(" eg. cd9660:/dev/acd0\n");
printf(" This is equivalent to: ");
printf("mount -t cd9660 /dev/acd0 /\n");
printf("\n");
printf(" ? List valid disk boot devices\n");
printf(" <empty line> Abort manual input\n");
printf("\nmountroot> ");
gets(name, sizeof(name), 1);
if (name[0] == '\0')
return (1);
if (name[0] == '?') {
printf("\nList of GEOM managed disk devices:\n ");
g_dev_print();
continue;
}
if (!vfs_mountroot_try(name, NULL))
return (0);
}
}
|