aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/kmod.c
blob: c6a4f8aebeba5c8a74a6bfc063e4ad08c3f14792 (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
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
/*
	kmod, the new module loader (replaces kerneld)
	Kirk Petersen

	Reorganized not to be a daemon by Adam Richter, with guidance
	from Greg Zornetzer.

	Modified to avoid chroot and file sharing problems.
	Mikael Pettersson

	Limit the concurrent number of kmod modprobes to catch loops from
	"modprobe needs a service that is in a module".
	Keith Owens <kaos@ocs.com.au> December 1999

	Unblock all signals when we exec a usermode process.
	Shuu Yamaguchi <shuu@wondernetworkresources.com> December 2000

	call_usermodehelper wait flag, and remove exec_usermodehelper.
	Rusty Russell <rusty@rustcorp.com.au>  Jan 2003
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/mnt_namespace.h>
#include <linux/completion.h>
#include <linux/file.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/resource.h>
#include <linux/notifier.h>
#include <linux/suspend.h>
#include <asm/uaccess.h>

extern int max_threads;

static struct workqueue_struct *khelper_wq;

#ifdef CONFIG_KMOD

/*
	modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";

/**
 * request_module - try to load a kernel module
 * @fmt:     printf style format string for the name of the module
 * @varargs: arguements as specified in the format string
 *
 * Load a module using the user mode module loader. The function returns
 * zero on success or a negative errno code on failure. Note that a
 * successful module load does not mean the module did not then unload
 * and exit on an error of its own. Callers must check that the service
 * they requested is now available not blindly invoke it.
 *
 * If module auto-loading support is disabled then this function
 * becomes a no-operation.
 */
int request_module(const char *fmt, ...)
{
	va_list args;
	char module_name[MODULE_NAME_LEN];
	unsigned int max_modprobes;
	int ret;
	char *argv[] = { modprobe_path, "-q", "--", module_name, NULL };
	static char *envp[] = { "HOME=/",
				"TERM=linux",
				"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
				NULL };
	static atomic_t kmod_concurrent = ATOMIC_INIT(0);
#define MAX_KMOD_CONCURRENT 50	/* Completely arbitrary value - KAO */
	static int kmod_loop_msg;

	va_start(args, fmt);
	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
	va_end(args);
	if (ret >= MODULE_NAME_LEN)
		return -ENAMETOOLONG;

	/* If modprobe needs a service that is in a module, we get a recursive
	 * loop.  Limit the number of running kmod threads to max_threads/2 or
	 * MAX_KMOD_CONCURRENT, whichever is the smaller.  A cleaner method
	 * would be to run the parents of this process, counting how many times
	 * kmod was invoked.  That would mean accessing the internals of the
	 * process tables to get the command line, proc_pid_cmdline is static
	 * and it is not worth changing the proc code just to handle this case. 
	 * KAO.
	 *
	 * "trace the ppid" is simple, but will fail if someone's
	 * parent exits.  I think this is as good as it gets. --RR
	 */
	max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT);
	atomic_inc(&kmod_concurrent);
	if (atomic_read(&kmod_concurrent) > max_modprobes) {
		/* We may be blaming an innocent here, but unlikely */
		if (kmod_loop_msg++ < 5)
			printk(KERN_ERR
			       "request_module: runaway loop modprobe %s\n",
			       module_name);
		atomic_dec(&kmod_concurrent);
		return -ENOMEM;
	}

	ret = call_usermodehelper(modprobe_path, argv, envp, 1);
	atomic_dec(&kmod_concurrent);
	return ret;
}
EXPORT_SYMBOL(request_module);
#endif /* CONFIG_KMOD */

struct subprocess_info {
	struct work_struct work;
	struct completion *complete;
	char *path;
	char **argv;
	char **envp;
	struct key *ring;
	enum umh_wait wait;
	int retval;
	struct file *stdin;
	void (*cleanup)(char **argv, char **envp);
};

/*
 * This is the task which runs the usermode application
 */
static int ____call_usermodehelper(void *data)
{
	struct subprocess_info *sub_info = data;
	struct key *new_session, *old_session;
	int retval;

	/* Unblock all signals and set the session keyring. */
	new_session = key_get(sub_info->ring);
	spin_lock_irq(&current->sighand->siglock);
	old_session = __install_session_keyring(current, new_session);
	flush_signal_handlers(current, 1);
	sigemptyset(&current->blocked);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	key_put(old_session);

	/* Install input pipe when needed */
	if (sub_info->stdin) {
		struct files_struct *f = current->files;
		struct fdtable *fdt;
		/* no races because files should be private here */
		sys_close(0);
		fd_install(0, sub_info->stdin);
		spin_lock(&f->file_lock);
		fdt = files_fdtable(f);
		FD_SET(0, fdt->open_fds);
		FD_CLR(0, fdt->close_on_exec);
		spin_unlock(&f->file_lock);

		/* and disallow core files too */
		current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
	}

	/* We can run anywhere, unlike our parent keventd(). */
	set_cpus_allowed(current, CPU_MASK_ALL);

	/*
	 * Our parent is keventd, which runs with elevated scheduling priority.
	 * Avoid propagating that into the userspace child.
	 */
	set_user_nice(current, 0);

	retval = -EPERM;
	if (current->fs->root)
		retval = kernel_execve(sub_info->path,
				sub_info->argv, sub_info->envp);

	/* Exec failed? */
	sub_info->retval = retval;
	do_exit(0);
}

void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
	if (info->cleanup)
		(*info->cleanup)(info->argv, info->envp);
	kfree(info);
}
EXPORT_SYMBOL(call_usermodehelper_freeinfo);

/* Keventd can't block, but this (a child) can. */
static int wait_for_helper(void *data)
{
	struct subprocess_info *sub_info = data;
	pid_t pid;

	/* Install a handler: if SIGCLD isn't handled sys_wait4 won't
	 * populate the status, but will return -ECHILD. */
	allow_signal(SIGCHLD);

	pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
	if (pid < 0) {
		sub_info->retval = pid;
	} else {
		int ret;

		/*
		 * Normally it is bogus to call wait4() from in-kernel because
		 * wait4() wants to write the exit code to a userspace address.
		 * But wait_for_helper() always runs as keventd, and put_user()
		 * to a kernel address works OK for kernel threads, due to their
		 * having an mm_segment_t which spans the entire address space.
		 *
		 * Thus the __user pointer cast is valid here.
		 */
		sys_wait4(pid, (int __user *)&ret, 0, NULL);

		/*
		 * If ret is 0, either ____call_usermodehelper failed and the
		 * real error code is already in sub_info->retval or
		 * sub_info->retval is 0 anyway, so don't mess with it then.
		 */
		if (ret)
			sub_info->retval = ret;
	}

	if (sub_info->wait == UMH_NO_WAIT)
		call_usermodehelper_freeinfo(sub_info);
	else
		complete(sub_info->complete);
	return 0;
}

/* This is run by khelper thread  */
static void __call_usermodehelper(struct work_struct *work)
{
	struct subprocess_info *sub_info =
		container_of(work, struct subprocess_info, work);
	pid_t pid;
	enum umh_wait wait = sub_info->wait;

	/* CLONE_VFORK: wait until the usermode helper has execve'd
	 * successfully We need the data structures to stay around
	 * until that is done.  */
	if (wait == UMH_WAIT_PROC || wait == UMH_NO_WAIT)
		pid = kernel_thread(wait_for_helper, sub_info,
				    CLONE_FS | CLONE_FILES | SIGCHLD);
	else
		pid = kernel_thread(____call_usermodehelper, sub_info,
				    CLONE_VFORK | SIGCHLD);

	switch (wait) {
	case UMH_NO_WAIT:
		break;

	case UMH_WAIT_PROC:
		if (pid > 0)
			break;
		sub_info->retval = pid;
		/* FALLTHROUGH */

	case UMH_WAIT_EXEC:
		complete(sub_info->complete);
	}
}

#ifdef CONFIG_PM
/*
 * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
 * (used for preventing user land processes from being created after the user
 * land has been frozen during a system-wide hibernation or suspend operation).
 */
static int usermodehelper_disabled;

/* Number of helpers running */
static atomic_t running_helpers = ATOMIC_INIT(0);

/*
 * Wait queue head used by usermodehelper_pm_callback() to wait for all running
 * helpers to finish.
 */
static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);

/*
 * Time to wait for running_helpers to become zero before the setting of
 * usermodehelper_disabled in usermodehelper_pm_callback() fails
 */
#define RUNNING_HELPERS_TIMEOUT	(5 * HZ)

static int usermodehelper_pm_callback(struct notifier_block *nfb,
					unsigned long action,
					void *ignored)
{
	long retval;

	switch (action) {
	case PM_HIBERNATION_PREPARE:
	case PM_SUSPEND_PREPARE:
		usermodehelper_disabled = 1;
		smp_mb();
		/*
		 * From now on call_usermodehelper_exec() won't start any new
		 * helpers, so it is sufficient if running_helpers turns out to
		 * be zero at one point (it may be increased later, but that
		 * doesn't matter).
		 */
		retval = wait_event_timeout(running_helpers_waitq,
					atomic_read(&running_helpers) == 0,
					RUNNING_HELPERS_TIMEOUT);
		if (retval) {
			return NOTIFY_OK;
		} else {
			usermodehelper_disabled = 0;
			return NOTIFY_BAD;
		}
	case PM_POST_HIBERNATION:
	case PM_POST_SUSPEND:
		usermodehelper_disabled = 0;
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

static void helper_lock(void)
{
	atomic_inc(&running_helpers);
	smp_mb__after_atomic_inc();
}

static void helper_unlock(void)
{
	if (atomic_dec_and_test(&running_helpers))
		wake_up(&running_helpers_waitq);
}

static void register_pm_notifier_callback(void)
{
	pm_notifier(usermodehelper_pm_callback, 0);
}
#else /* CONFIG_PM */
#define usermodehelper_disabled	0

static inline void helper_lock(void) {}
static inline void helper_unlock(void) {}
static inline void register_pm_notifier_callback(void) {}
#endif /* CONFIG_PM */

/**
 * call_usermodehelper_setup - prepare to call a usermode helper
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
 *
 * Returns either %NULL on allocation failure, or a subprocess_info
 * structure.  This should be passed to call_usermodehelper_exec to
 * exec the process and free the structure.
 */
struct subprocess_info *call_usermodehelper_setup(char *path,
						  char **argv, char **envp)
{
	struct subprocess_info *sub_info;
	sub_info = kzalloc(sizeof(struct subprocess_info),  GFP_ATOMIC);
	if (!sub_info)
		goto out;

	INIT_WORK(&sub_info->work, __call_usermodehelper);
	sub_info->path = path;
	sub_info->argv = argv;
	sub_info->envp = envp;

  out:
	return sub_info;
}
EXPORT_SYMBOL(call_usermodehelper_setup);

/**
 * call_usermodehelper_setkeys - set the session keys for usermode helper
 * @info: a subprocess_info returned by call_usermodehelper_setup
 * @session_keyring: the session keyring for the process
 */
void call_usermodehelper_setkeys(struct subprocess_info *info,
				 struct key *session_keyring)
{
	info->ring = session_keyring;
}
EXPORT_SYMBOL(call_usermodehelper_setkeys);

/**
 * call_usermodehelper_setcleanup - set a cleanup function
 * @info: a subprocess_info returned by call_usermodehelper_setup
 * @cleanup: a cleanup function
 *
 * The cleanup function is just befor ethe subprocess_info is about to
 * be freed.  This can be used for freeing the argv and envp.  The
 * Function must be runnable in either a process context or the
 * context in which call_usermodehelper_exec is called.
 */
void call_usermodehelper_setcleanup(struct subprocess_info *info,
				    void (*cleanup)(char **argv, char **envp))
{
	info->cleanup = cleanup;
}
EXPORT_SYMBOL(call_usermodehelper_setcleanup);

/**
 * call_usermodehelper_stdinpipe - set up a pipe to be used for stdin
 * @sub_info: a subprocess_info returned by call_usermodehelper_setup
 * @filp: set to the write-end of a pipe
 *
 * This constructs a pipe, and sets the read end to be the stdin of the
 * subprocess, and returns the write-end in *@filp.
 */
int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info,
				  struct file **filp)
{
	struct file *f;

	f = create_write_pipe();
	if (IS_ERR(f))
		return PTR_ERR(f);
	*filp = f;

	f = create_read_pipe(f);
	if (IS_ERR(f)) {
		free_write_pipe(*filp);
		return PTR_ERR(f);
	}
	sub_info->stdin = f;

	return 0;
}
EXPORT_SYMBOL(call_usermodehelper_stdinpipe);

/**
 * call_usermodehelper_exec - start a usermode application
 * @sub_info: information about the subprocessa
 * @wait: wait for the application to finish and return status.
 *        when -1 don't wait at all, but you get no useful error back when
 *        the program couldn't be exec'ed. This makes it safe to call
 *        from interrupt context.
 *
 * Runs a user-space application.  The application is started
 * asynchronously if wait is not set, and runs as a child of keventd.
 * (ie. it runs with full root capabilities).
 */
int call_usermodehelper_exec(struct subprocess_info *sub_info,
			     enum umh_wait wait)
{
	DECLARE_COMPLETION_ONSTACK(done);
	int retval;

	helper_lock();
	if (sub_info->path[0] == '\0') {
		retval = 0;
		goto out;
	}

	if (!khelper_wq || usermodehelper_disabled) {
		retval = -EBUSY;
		goto out;
	}

	sub_info->complete = &done;
	sub_info->wait = wait;

	queue_work(khelper_wq, &sub_info->work);
	if (wait == UMH_NO_WAIT) /* task has freed sub_info */
		return 0;
	wait_for_completion(&done);
	retval = sub_info->retval;

  out:
	call_usermodehelper_freeinfo(sub_info);
	helper_unlock();
	return retval;
}
EXPORT_SYMBOL(call_usermodehelper_exec);

/**
 * call_usermodehelper_pipe - call a usermode helper process with a pipe stdin
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
 * @filp: set to the write-end of a pipe
 *
 * This is a simple wrapper which executes a usermode-helper function
 * with a pipe as stdin.  It is implemented entirely in terms of
 * lower-level call_usermodehelper_* functions.
 */
int call_usermodehelper_pipe(char *path, char **argv, char **envp,
			     struct file **filp)
{
	struct subprocess_info *sub_info;
	int ret;

	sub_info = call_usermodehelper_setup(path, argv, envp);
	if (sub_info == NULL)
		return -ENOMEM;

	ret = call_usermodehelper_stdinpipe(sub_info, filp);
	if (ret < 0)
		goto out;

	return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);

  out:
	call_usermodehelper_freeinfo(sub_info);
	return ret;
}
EXPORT_SYMBOL(call_usermodehelper_pipe);

void __init usermodehelper_init(void)
{
	khelper_wq = create_singlethread_workqueue("khelper");
	BUG_ON(!khelper_wq);
	register_pm_notifier_callback();
}
; p = NULL; if (tmp == head) break; p = list_entry(tmp, struct vfsmount, mnt_hash); if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) { found = mntget(p); break; } } spin_unlock(&vfsmount_lock); return found; } static inline int check_mnt(struct vfsmount *mnt) { return mnt->mnt_namespace == current->namespace; } static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd) { old_nd->dentry = mnt->mnt_mountpoint; old_nd->mnt = mnt->mnt_parent; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt_root; list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_hash); old_nd->dentry->d_mounted--; } static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd) { mnt->mnt_parent = mntget(nd->mnt); mnt->mnt_mountpoint = dget(nd->dentry); list_add(&mnt->mnt_hash, mount_hashtable+hash(nd->mnt, nd->dentry)); list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts); nd->dentry->d_mounted++; } static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct vfsmount, mnt_child); } static struct vfsmount * clone_mnt(struct vfsmount *old, struct dentry *root) { struct super_block *sb = old->mnt_sb; struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname); if (mnt) { mnt->mnt_flags = old->mnt_flags; atomic_inc(&sb->s_active); mnt->mnt_sb = sb; mnt->mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; mnt->mnt_namespace = old->mnt_namespace; /* stick the duplicate mount on the same expiry list * as the original if that was on one */ spin_lock(&vfsmount_lock); if (!list_empty(&old->mnt_fslink)) list_add(&mnt->mnt_fslink, &old->mnt_fslink); spin_unlock(&vfsmount_lock); } return mnt; } void __mntput(struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; dput(mnt->mnt_root); free_vfsmnt(mnt); deactivate_super(sb); } EXPORT_SYMBOL(__mntput); /* iterator */ static void *m_start(struct seq_file *m, loff_t *pos) { struct namespace *n = m->private; struct list_head *p; loff_t l = *pos; down_read(&n->sem); list_for_each(p, &n->list) if (!l--) return list_entry(p, struct vfsmount, mnt_list); return NULL; } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct namespace *n = m->private; struct list_head *p = ((struct vfsmount *)v)->mnt_list.next; (*pos)++; return p==&n->list ? NULL : list_entry(p, struct vfsmount, mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct namespace *n = m->private; up_read(&n->sem); } static inline void mangle(struct seq_file *m, const char *s) { seq_escape(m, s, " \t\n\\"); } static int show_vfsmnt(struct seq_file *m, void *v) { struct vfsmount *mnt = v; int err = 0; static struct proc_fs_info { int flag; char *str; } fs_info[] = { { MS_SYNCHRONOUS, ",sync" }, { MS_DIRSYNC, ",dirsync" }, { MS_MANDLOCK, ",mand" }, { MS_NOATIME, ",noatime" }, { MS_NODIRATIME, ",nodiratime" }, { 0, NULL } }; static struct proc_fs_info mnt_info[] = { { MNT_NOSUID, ",nosuid" }, { MNT_NODEV, ",nodev" }, { MNT_NOEXEC, ",noexec" }, { 0, NULL } }; struct proc_fs_info *fs_infop; mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none"); seq_putc(m, ' '); seq_path(m, mnt, mnt->mnt_root, " \t\n\\"); seq_putc(m, ' '); mangle(m, mnt->mnt_sb->s_type->name); seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw"); for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { if (mnt->mnt_sb->s_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) { if (mnt->mnt_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } if (mnt->mnt_sb->s_op->show_options) err = mnt->mnt_sb->s_op->show_options(m, mnt); seq_puts(m, " 0 0\n"); return err; } struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = show_vfsmnt }; /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *mnt) { struct list_head *next; struct vfsmount *this_parent = mnt; int actual_refs; int minimum_refs; spin_lock(&vfsmount_lock); actual_refs = atomic_read(&mnt->mnt_count); minimum_refs = 2; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct vfsmount *p = list_entry(next, struct vfsmount, mnt_child); next = next->next; actual_refs += atomic_read(&p->mnt_count); minimum_refs += 2; if (!list_empty(&p->mnt_mounts)) { this_parent = p; goto repeat; } } if (this_parent != mnt) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } spin_unlock(&vfsmount_lock); if (actual_refs > minimum_refs) return -EBUSY; return 0; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { if (atomic_read(&mnt->mnt_count) > 2) return -EBUSY; return 0; } EXPORT_SYMBOL(may_umount); void umount_tree(struct vfsmount *mnt) { struct vfsmount *p; LIST_HEAD(kill); for (p = mnt; p; p = next_mnt(p, mnt)) { list_del(&p->mnt_list); list_add(&p->mnt_list, &kill); } while (!list_empty(&kill)) { mnt = list_entry(kill.next, struct vfsmount, mnt_list); list_del_init(&mnt->mnt_list); list_del_init(&mnt->mnt_fslink); if (mnt->mnt_parent == mnt) { spin_unlock(&vfsmount_lock); } else { struct nameidata old_nd; detach_mnt(mnt, &old_nd); spin_unlock(&vfsmount_lock); path_release(&old_nd); } mntput(mnt); spin_lock(&vfsmount_lock); } } static int do_umount(struct vfsmount *mnt, int flags) { struct super_block * sb = mnt->mnt_sb; int retval; retval = security_sb_umount(mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (mnt == current->fs->rootmnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; if (atomic_read(&mnt->mnt_count) != 2) return -EBUSY; if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ lock_kernel(); if( (flags&MNT_FORCE) && sb->s_op->umount_begin) sb->s_op->umount_begin(sb); unlock_kernel(); /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (mnt == current->fs->rootmnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ down_write(&sb->s_umount); if (!(sb->s_flags & MS_RDONLY)) { lock_kernel(); DQUOT_OFF(sb); retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); unlock_kernel(); } up_write(&sb->s_umount); return retval; } down_write(&current->namespace->sem); spin_lock(&vfsmount_lock); if (atomic_read(&sb->s_active) == 1) { /* last instance - try to be smart */ spin_unlock(&vfsmount_lock); lock_kernel(); DQUOT_OFF(sb); acct_auto_close(sb); unlock_kernel(); security_sb_umount_close(mnt); spin_lock(&vfsmount_lock); } retval = -EBUSY; if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt); retval = 0; } spin_unlock(&vfsmount_lock); if (retval) security_sb_umount_busy(mnt); up_write(&current->namespace->sem); return retval; } /* * Now umount can handle mount points as well as block devices. * This is important for filesystems which use unnamed block devices. * * We now support a flag for forced unmount like the other 'big iron' * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD */ asmlinkage long sys_umount(char __user * name, int flags) { struct nameidata nd; int retval; retval = __user_walk(name, LOOKUP_FOLLOW, &nd); if (retval) goto out; retval = -EINVAL; if (nd.dentry != nd.mnt->mnt_root) goto dput_and_out; if (!check_mnt(nd.mnt)) goto dput_and_out; retval = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto dput_and_out; retval = do_umount(nd.mnt, flags); dput_and_out: path_release_on_umount(&nd); out: return retval; } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ asmlinkage long sys_oldumount(char __user * name) { return sys_umount(name,0); } #endif static int mount_is_safe(struct nameidata *nd) { if (capable(CAP_SYS_ADMIN)) return 0; return -EPERM; #ifdef notyet if (S_ISLNK(nd->dentry->d_inode->i_mode)) return -EPERM; if (nd->dentry->d_inode->i_mode & S_ISVTX) { if (current->uid != nd->dentry->d_inode->i_uid) return -EPERM; } if (permission(nd->dentry->d_inode, MAY_WRITE, nd)) return -EPERM; return 0; #endif } static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry) { while (1) { if (d == dentry) return 1; if (d == NULL || d == d->d_parent) return 0; d = d->d_parent; } } static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry) { struct vfsmount *res, *p, *q, *r, *s; struct list_head *h; struct nameidata nd; res = q = clone_mnt(mnt, dentry); if (!q) goto Enomem; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; for (h = mnt->mnt_mounts.next; h != &mnt->mnt_mounts; h = h->next) { r = list_entry(h, struct vfsmount, mnt_child); if (!lives_below_in_same_fs(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; nd.mnt = q; nd.dentry = p->mnt_mountpoint; q = clone_mnt(p, p->mnt_root); if (!q) goto Enomem; spin_lock(&vfsmount_lock); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, &nd); spin_unlock(&vfsmount_lock); } } return res; Enomem: if (res) { spin_lock(&vfsmount_lock); umount_tree(res); spin_unlock(&vfsmount_lock); } return NULL; } static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) { int err; if (mnt->mnt_sb->s_flags & MS_NOUSER) return -EINVAL; if (S_ISDIR(nd->dentry->d_inode->i_mode) != S_ISDIR(mnt->mnt_root->d_inode->i_mode)) return -ENOTDIR; err = -ENOENT; down(&nd->dentry->d_inode->i_sem); if (IS_DEADDIR(nd->dentry->d_inode)) goto out_unlock; err = security_sb_check_sb(mnt, nd); if (err) goto out_unlock; err = -ENOENT; spin_lock(&vfsmount_lock); if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) { struct list_head head; attach_mnt(mnt, nd); list_add_tail(&head, &mnt->mnt_list); list_splice(&head, current->namespace->list.prev); mntget(mnt); err = 0; } spin_unlock(&vfsmount_lock); out_unlock: up(&nd->dentry->d_inode->i_sem); if (!err) security_sb_post_addmount(mnt, nd); return err; } /* * do loopback mount. */ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) { struct nameidata old_nd; struct vfsmount *mnt = NULL; int err = mount_is_safe(nd); if (err) return err; if (!old_name || !*old_name) return -EINVAL; err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd); if (err) return err; down_write(&current->namespace->sem); err = -EINVAL; if (check_mnt(nd->mnt) && (!recurse || check_mnt(old_nd.mnt))) { err = -ENOMEM; if (recurse) mnt = copy_tree(old_nd.mnt, old_nd.dentry); else mnt = clone_mnt(old_nd.mnt, old_nd.dentry); } if (mnt) { /* stop bind mounts from expiring */ spin_lock(&vfsmount_lock); list_del_init(&mnt->mnt_fslink); spin_unlock(&vfsmount_lock); err = graft_tree(mnt, nd); if (err) { spin_lock(&vfsmount_lock); umount_tree(mnt); spin_unlock(&vfsmount_lock); } else mntput(mnt); } up_write(&current->namespace->sem); path_release(&old_nd); return err; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct nameidata *nd, int flags, int mnt_flags, void *data) { int err; struct super_block * sb = nd->mnt->mnt_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!check_mnt(nd->mnt)) return -EINVAL; if (nd->dentry != nd->mnt->mnt_root) return -EINVAL; down_write(&sb->s_umount); err = do_remount_sb(sb, flags, data, 0); if (!err) nd->mnt->mnt_flags=mnt_flags; up_write(&sb->s_umount); if (!err) security_sb_post_remount(nd->mnt, flags, data); return err; } static int do_move_mount(struct nameidata *nd, char *old_name) { struct nameidata old_nd, parent_nd; struct vfsmount *p; int err = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!old_name || !*old_name) return -EINVAL; err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd); if (err) return err; down_write(&current->namespace->sem); while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) ; err = -EINVAL; if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) goto out; err = -ENOENT; down(&nd->dentry->d_inode->i_sem); if (IS_DEADDIR(nd->dentry->d_inode)) goto out1; spin_lock(&vfsmount_lock); if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry)) goto out2; err = -EINVAL; if (old_nd.dentry != old_nd.mnt->mnt_root) goto out2; if (old_nd.mnt == old_nd.mnt->mnt_parent) goto out2; if (S_ISDIR(nd->dentry->d_inode->i_mode) != S_ISDIR(old_nd.dentry->d_inode->i_mode)) goto out2; err = -ELOOP; for (p = nd->mnt; p->mnt_parent!=p; p = p->mnt_parent) if (p == old_nd.mnt) goto out2; err = 0; detach_mnt(old_nd.mnt, &parent_nd); attach_mnt(old_nd.mnt, nd); /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old_nd.mnt->mnt_fslink); out2: spin_unlock(&vfsmount_lock); out1: up(&nd->dentry->d_inode->i_sem); out: up_write(&current->namespace->sem); if (!err) path_release(&parent_nd); path_release(&old_nd); return err; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct nameidata *nd, char *type, int flags, int mnt_flags, char *name, void *data) { struct vfsmount *mnt; if (!type || !memchr(type, 0, PAGE_SIZE)) return -EINVAL; /* we need capabilities... */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; mnt = do_kern_mount(type, flags, name, data); if (IS_ERR(mnt)) return PTR_ERR(mnt); return do_add_mount(mnt, nd, mnt_flags, NULL); } /* * add a mount into a namespace's mount tree * - provide the option of adding the new mount to an expiration list */ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, int mnt_flags, struct list_head *fslist) { int err; down_write(&current->namespace->sem); /* Something was mounted here while we slept */ while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) ; err = -EINVAL; if (!check_mnt(nd->mnt)) goto unlock; /* Refuse the same filesystem on the same mount point */ err = -EBUSY; if (nd->mnt->mnt_sb == newmnt->mnt_sb && nd->mnt->mnt_root == nd->dentry) goto unlock; err = -EINVAL; if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode)) goto unlock; newmnt->mnt_flags = mnt_flags; err = graft_tree(newmnt, nd); if (err == 0 && fslist) { /* add to the specified expiration list */ spin_lock(&vfsmount_lock); list_add_tail(&newmnt->mnt_fslink, fslist); spin_unlock(&vfsmount_lock); } unlock: up_write(&current->namespace->sem); mntput(newmnt); return err; } EXPORT_SYMBOL_GPL(do_add_mount); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct namespace *namespace; struct vfsmount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; spin_lock(&vfsmount_lock); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_fslink) { if (!xchg(&mnt->mnt_expiry_mark, 1) || atomic_read(&mnt->mnt_count) != 1) continue; mntget(mnt); list_move(&mnt->mnt_fslink, &graveyard); } /* * go through the vfsmounts we've just consigned to the graveyard to * - check that they're still dead * - delete the vfsmount from the appropriate namespace under lock * - dispose of the corpse */ while (!list_empty(&graveyard)) { mnt = list_entry(graveyard.next, struct vfsmount, mnt_fslink); list_del_init(&mnt->mnt_fslink); /* don't do anything if the namespace is dead - all the * vfsmounts from it are going away anyway */ namespace = mnt->mnt_namespace; if (!namespace || atomic_read(&namespace->count) <= 0) continue; get_namespace(namespace); spin_unlock(&vfsmount_lock); down_write(&namespace->sem); spin_lock(&vfsmount_lock); /* check that it is still dead: the count should now be 2 - as * contributed by the vfsmount parent and the mntget above */ if (atomic_read(&mnt->mnt_count) == 2) { struct vfsmount *xdmnt; struct dentry *xdentry; /* delete from the namespace */ list_del_init(&mnt->mnt_list); list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_hash); mnt->mnt_mountpoint->d_mounted--; xdentry = mnt->mnt_mountpoint; mnt->mnt_mountpoint = mnt->mnt_root; xdmnt = mnt->mnt_parent; mnt->mnt_parent = mnt; spin_unlock(&vfsmount_lock); mntput(xdmnt); dput(xdentry); /* now lay it to rest if this was the last ref on the * superblock */ if (atomic_read(&mnt->mnt_sb->s_active) == 1) { /* last instance - try to be smart */ lock_kernel(); DQUOT_OFF(mnt->mnt_sb); acct_auto_close(mnt->mnt_sb); unlock_kernel(); } mntput(mnt); } else { /* someone brought it back to life whilst we didn't * have any locks held so return it to the expiration * list */ list_add_tail(&mnt->mnt_fslink, mounts); spin_unlock(&vfsmount_lock); } up_write(&namespace->sem); mntput(mnt); put_namespace(namespace); spin_lock(&vfsmount_lock); } spin_unlock(&vfsmount_lock); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Some copy_from_user() implementations do not return the exact number of * bytes remaining to copy on a fault. But copy_mount_options() requires that. * Note that this function differs from copy_from_user() in that it will oops * on bad values of `to', rather than returning a short copy. */ static long exact_copy_from_user(void *to, const void __user *from, unsigned long n) { char *t = to; const char __user *f = from; char c; if (!access_ok(VERIFY_READ, from, n)) return n; while (n) { if (__get_user(c, f)) { memset(t, 0, n); break; } *t++ = c; f++; n--; } return n; } int copy_mount_options(const void __user *data, unsigned long *where) { int i; unsigned long page; unsigned long size; *where = 0; if (!data) return 0; if (!(page = __get_free_page(GFP_KERNEL))) return -ENOMEM; /* We only care that *some* data at the address the user * gave us is valid. Just in case, we'll zero * the remainder of the page. */ /* copy_from_user cannot cross TASK_SIZE ! */ size = TASK_SIZE - (unsigned long)data; if (size > PAGE_SIZE) size = PAGE_SIZE; i = size - exact_copy_from_user((void *)page, data, size); if (!i) { free_page(page); return -EFAULT; } if (i != PAGE_SIZE) memset((char *)page + i, 0, PAGE_SIZE - i); *where = page; return 0; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ long do_mount(char * dev_name, char * dir_name, char *type_page, unsigned long flags, void *data_page) { struct nameidata nd; int retval = 0; int mnt_flags = 0; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE)) return -EINVAL; if (dev_name && !memchr(dev_name, 0, PAGE_SIZE)) return -EINVAL; if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; flags &= ~(MS_NOSUID|MS_NOEXEC|MS_NODEV|MS_ACTIVE); /* ... and get the mountpoint */ retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); if (retval) return retval; retval = security_sb_mount(dev_name, &nd, type_page, flags, data_page); if (retval) goto dput_out; if (flags & MS_REMOUNT) retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags, data_page); else if (flags & MS_BIND) retval = do_loopback(&nd, dev_name, flags & MS_REC); else if (flags & MS_MOVE) retval = do_move_mount(&nd, dev_name); else retval = do_new_mount(&nd, type_page, flags, mnt_flags, dev_name, data_page); dput_out: path_release(&nd); return retval; } int copy_namespace(int flags, struct task_struct *tsk) { struct namespace *namespace = tsk->namespace; struct namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL; struct fs_struct *fs = tsk->fs; struct vfsmount *p, *q; if (!namespace) return 0; get_namespace(namespace); if (!(flags & CLONE_NEWNS)) return 0; if (!capable(CAP_SYS_ADMIN)) { put_namespace(namespace); return -EPERM; } new_ns = kmalloc(sizeof(struct namespace), GFP_KERNEL); if (!new_ns) goto out; atomic_set(&new_ns->count, 1); init_rwsem(&new_ns->sem); INIT_LIST_HEAD(&new_ns->list); down_write(&tsk->namespace->sem); /* First pass: copy the tree topology */ new_ns->root = copy_tree(namespace->root, namespace->root->mnt_root); if (!new_ns->root) { up_write(&tsk->namespace->sem); kfree(new_ns); goto out; } spin_lock(&vfsmount_lock); list_add_tail(&new_ns->list, &new_ns->root->mnt_list); spin_unlock(&vfsmount_lock); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = namespace->root; q = new_ns->root; while (p) { q->mnt_namespace = new_ns; if (fs) { if (p == fs->rootmnt) { rootmnt = p; fs->rootmnt = mntget(q); } if (p == fs->pwdmnt) { pwdmnt = p; fs->pwdmnt = mntget(q); } if (p == fs->altrootmnt) { altrootmnt = p; fs->altrootmnt = mntget(q); } } p = next_mnt(p, namespace->root); q = next_mnt(q, new_ns->root); } up_write(&tsk->namespace->sem); tsk->namespace = new_ns; if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); if (altrootmnt) mntput(altrootmnt); put_namespace(namespace); return 0; out: put_namespace(namespace); return -ENOMEM; } asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, char __user * type, unsigned long flags, void __user * data) { int retval; unsigned long data_page; unsigned long type_page; unsigned long dev_page; char *dir_page; retval = copy_mount_options (type, &type_page); if (retval < 0) return retval; dir_page = getname(dir_name); retval = PTR_ERR(dir_page); if (IS_ERR(dir_page)) goto out1; retval = copy_mount_options (dev_name, &dev_page); if (retval < 0) goto out2; retval = copy_mount_options (data, &data_page); if (retval < 0) goto out3; lock_kernel(); retval = do_mount((char*)dev_page, dir_page, (char*)type_page, flags, (void*)data_page); unlock_kernel(); free_page(data_page); out3: free_page(dev_page); out2: putname(dir_page); out1: free_page(type_page); return retval; } /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. Requires the big lock held. */ void set_fs_root(struct fs_struct *fs, struct vfsmount *mnt, struct dentry *dentry) { struct dentry *old_root; struct vfsmount *old_rootmnt; write_lock(&fs->lock); old_root = fs->root; old_rootmnt = fs->rootmnt; fs->rootmnt = mntget(mnt); fs->root = dget(dentry); write_unlock(&fs->lock); if (old_root) { dput(old_root); mntput(old_rootmnt); } } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. Requires the big lock held. */ void set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt, struct dentry *dentry) { struct dentry *old_pwd; struct vfsmount *old_pwdmnt; write_lock(&fs->lock); old_pwd = fs->pwd; old_pwdmnt = fs->pwdmnt; fs->pwdmnt = mntget(mnt); fs->pwd = dget(dentry); write_unlock(&fs->lock); if (old_pwd) { dput(old_pwd); mntput(old_pwdmnt); } } static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) { struct task_struct *g, *p; struct fs_struct *fs; read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { atomic_inc(&fs->count); task_unlock(p); if (fs->root==old_nd->dentry&&fs->rootmnt==old_nd->mnt) set_fs_root(fs, new_nd->mnt, new_nd->dentry); if (fs->pwd==old_nd->dentry&&fs->pwdmnt==old_nd->mnt) set_fs_pwd(fs, new_nd->mnt, new_nd->dentry); put_fs_struct(fs); } else task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); } /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *put_old) { struct vfsmount *tmp; struct nameidata new_nd, old_nd, parent_nd, root_parent, user_nd; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; lock_kernel(); error = __user_walk(new_root, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &new_nd); if (error) goto out0; error = -EINVAL; if (!check_mnt(new_nd.mnt)) goto out1; error = __user_walk(put_old, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &old_nd); if (error) goto out1; error = security_sb_pivotroot(&old_nd, &new_nd); if (error) { path_release(&old_nd); goto out1; } read_lock(&current->fs->lock); user_nd.mnt = mntget(current->fs->rootmnt); user_nd.dentry = dget(current->fs->root); read_unlock(&current->fs->lock); down_write(&current->namespace->sem); down(&old_nd.dentry->d_inode->i_sem); error = -EINVAL; if (!check_mnt(user_nd.mnt)) goto out2; error = -ENOENT; if (IS_DEADDIR(new_nd.dentry->d_inode)) goto out2; if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry)) goto out2; if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry)) goto out2; error = -EBUSY; if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt) goto out2; /* loop, on the same file system */ error = -EINVAL; if (user_nd.mnt->mnt_root != user_nd.dentry) goto out2; /* not a mountpoint */ if (new_nd.mnt->mnt_root != new_nd.dentry) goto out2; /* not a mountpoint */ tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */ spin_lock(&vfsmount_lock); if (tmp != new_nd.mnt) { for (;;) { if (tmp->mnt_parent == tmp) goto out3; /* already mounted on put_old */ if (tmp->mnt_parent == new_nd.mnt) break; tmp = tmp->mnt_parent; } if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry)) goto out3; } else if (!is_subdir(old_nd.dentry, new_nd.dentry)) goto out3; detach_mnt(new_nd.mnt, &parent_nd); detach_mnt(user_nd.mnt, &root_parent); attach_mnt(user_nd.mnt, &old_nd); /* mount old root on put_old */ attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */ spin_unlock(&vfsmount_lock); chroot_fs_refs(&user_nd, &new_nd); security_sb_post_pivotroot(&user_nd, &new_nd); error = 0; path_release(&root_parent); path_release(&parent_nd); out2: up(&old_nd.dentry->d_inode->i_sem); up_write(&current->namespace->sem); path_release(&user_nd); path_release(&old_nd); out1: path_release(&new_nd); out0: unlock_kernel(); return error; out3: spin_unlock(&vfsmount_lock); goto out2; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct namespace *namespace; struct task_struct *g, *p; mnt = do_kern_mount("rootfs", 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); namespace = kmalloc(sizeof(*namespace), GFP_KERNEL); if (!namespace) panic("Can't allocate initial namespace"); atomic_set(&namespace->count, 1); INIT_LIST_HEAD(&namespace->list); init_rwsem(&namespace->sem); list_add(&mnt->mnt_list, &namespace->list); namespace->root = mnt; mnt->mnt_namespace = namespace; init_task.namespace = namespace; read_lock(&tasklist_lock); do_each_thread(g, p) { get_namespace(namespace); p->namespace = namespace; } while_each_thread(g, p); read_unlock(&tasklist_lock); set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root); set_fs_root(current->fs, namespace->root, namespace->root->mnt_root); } void __init mnt_init(unsigned long mempages) { struct list_head *d; unsigned int nr_hash; int i; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); mount_hashtable = (struct list_head *) __get_free_page(GFP_ATOMIC); if (!mount_hashtable) panic("Failed to allocate mount hash table\n"); /* * Find the power-of-two list-heads that can fit into the allocation.. * We don't guarantee that "sizeof(struct list_head)" is necessarily * a power-of-two. */ nr_hash = PAGE_SIZE / sizeof(struct list_head); hash_bits = 0; do { hash_bits++; } while ((nr_hash >> hash_bits) != 0); hash_bits--; /* * Re-calculate the actual number of entries and the mask * from the number of bits we can fit. */ nr_hash = 1UL << hash_bits; hash_mask = nr_hash-1; printk("Mount-cache hash table entries: %d\n", nr_hash); /* And initialize the newly allocated array */ d = mount_hashtable; i = nr_hash; do { INIT_LIST_HEAD(d); d++; i--; } while (i); sysfs_init(); init_rootfs(); init_mount_tree(); } void __put_namespace(struct namespace *namespace) { struct vfsmount *mnt; down_write(&namespace->sem); spin_lock(&vfsmount_lock); list_for_each_entry(mnt, &namespace->list, mnt_list) { mnt->mnt_namespace = NULL; } umount_tree(namespace->root); spin_unlock(&vfsmount_lock); up_write(&namespace->sem); kfree(namespace); }