kmod.c 14.2 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
	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>
27
#include <linux/mnt_namespace.h>
L
Linus Torvalds 已提交
28 29
#include <linux/completion.h>
#include <linux/file.h>
A
Al Viro 已提交
30
#include <linux/fdtable.h>
L
Linus Torvalds 已提交
31 32 33 34 35
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/kernel.h>
#include <linux/init.h>
36
#include <linux/resource.h>
37 38
#include <linux/notifier.h>
#include <linux/suspend.h>
L
Linus Torvalds 已提交
39 40 41 42 43 44
#include <asm/uaccess.h>

extern int max_threads;

static struct workqueue_struct *khelper_wq;

45
#ifdef CONFIG_MODULES
L
Linus Torvalds 已提交
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

/*
	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 {
119
	struct work_struct work;
L
Linus Torvalds 已提交
120 121 122 123
	struct completion *complete;
	char *path;
	char **argv;
	char **envp;
124
	struct key *ring;
125
	enum umh_wait wait;
L
Linus Torvalds 已提交
126
	int retval;
127
	struct file *stdin;
128
	void (*cleanup)(char **argv, char **envp);
L
Linus Torvalds 已提交
129 130 131 132 133 134 135 136
};

/*
 * This is the task which runs the usermode application
 */
static int ____call_usermodehelper(void *data)
{
	struct subprocess_info *sub_info = data;
137
	struct key *new_session, *old_session;
L
Linus Torvalds 已提交
138 139
	int retval;

140
	/* Unblock all signals and set the session keyring. */
141
	new_session = key_get(sub_info->ring);
L
Linus Torvalds 已提交
142
	spin_lock_irq(&current->sighand->siglock);
143
	old_session = __install_session_keyring(current, new_session);
L
Linus Torvalds 已提交
144 145 146 147 148
	flush_signal_handlers(current, 1);
	sigemptyset(&current->blocked);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

149 150
	key_put(old_session);

151 152 153 154 155 156 157 158 159 160 161 162
	/* 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);
163 164 165

		/* and disallow core files too */
		current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
166 167
	}

L
Linus Torvalds 已提交
168
	/* We can run anywhere, unlike our parent keventd(). */
169
	set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
L
Linus Torvalds 已提交
170

171 172 173 174 175 176
	/*
	 * Our parent is keventd, which runs with elevated scheduling priority.
	 * Avoid propagating that into the userspace child.
	 */
	set_user_nice(current, 0);

177
	retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
L
Linus Torvalds 已提交
178 179 180 181 182 183

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

184 185 186 187 188 189 190 191
void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
	if (info->cleanup)
		(*info->cleanup)(info->argv, info->envp);
	kfree(info);
}
EXPORT_SYMBOL(call_usermodehelper_freeinfo);

L
Linus Torvalds 已提交
192 193 194 195 196 197 198 199 200 201 202 203 204 205
/* 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 {
206 207
		int ret;

L
Linus Torvalds 已提交
208 209 210 211 212 213 214 215 216
		/*
		 * 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.
		 */
217 218 219 220 221 222 223 224 225
		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;
L
Linus Torvalds 已提交
226 227
	}

228
	if (sub_info->wait == UMH_NO_WAIT)
229
		call_usermodehelper_freeinfo(sub_info);
230 231
	else
		complete(sub_info->complete);
L
Linus Torvalds 已提交
232 233 234 235
	return 0;
}

/* This is run by khelper thread  */
236
static void __call_usermodehelper(struct work_struct *work)
L
Linus Torvalds 已提交
237
{
238 239
	struct subprocess_info *sub_info =
		container_of(work, struct subprocess_info, work);
L
Linus Torvalds 已提交
240
	pid_t pid;
241
	enum umh_wait wait = sub_info->wait;
L
Linus Torvalds 已提交
242 243 244 245

	/* CLONE_VFORK: wait until the usermode helper has execve'd
	 * successfully We need the data structures to stay around
	 * until that is done.  */
246
	if (wait == UMH_WAIT_PROC || wait == UMH_NO_WAIT)
L
Linus Torvalds 已提交
247 248 249 250 251 252
		pid = kernel_thread(wait_for_helper, sub_info,
				    CLONE_FS | CLONE_FILES | SIGCHLD);
	else
		pid = kernel_thread(____call_usermodehelper, sub_info,
				    CLONE_VFORK | SIGCHLD);

253 254 255
	switch (wait) {
	case UMH_NO_WAIT:
		break;
256

257 258 259
	case UMH_WAIT_PROC:
		if (pid > 0)
			break;
L
Linus Torvalds 已提交
260
		sub_info->retval = pid;
261 262 263
		/* FALLTHROUGH */

	case UMH_WAIT_EXEC:
L
Linus Torvalds 已提交
264
		complete(sub_info->complete);
265
	}
L
Linus Torvalds 已提交
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
#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)

291 292 293 294
static int usermodehelper_pm_callback(struct notifier_block *nfb,
					unsigned long action,
					void *ignored)
{
295 296
	long retval;

297 298 299 300
	switch (action) {
	case PM_HIBERNATION_PREPARE:
	case PM_SUSPEND_PREPARE:
		usermodehelper_disabled = 1;
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
		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;
		}
317 318 319 320 321 322 323 324 325
	case PM_POST_HIBERNATION:
	case PM_POST_SUSPEND:
		usermodehelper_disabled = 0;
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349
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 */

L
Linus Torvalds 已提交
350
/**
351
 * call_usermodehelper_setup - prepare to call a usermode helper
R
Randy Dunlap 已提交
352 353 354
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
355
 * @gfp_mask: gfp mask for memory allocation
356
 *
R
Randy Dunlap 已提交
357
 * Returns either %NULL on allocation failure, or a subprocess_info
358 359 360
 * structure.  This should be passed to call_usermodehelper_exec to
 * exec the process and free the structure.
 */
361 362
struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
						  char **envp, gfp_t gfp_mask)
363 364
{
	struct subprocess_info *sub_info;
365
	sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
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
	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;

421
	f = create_write_pipe(0);
422 423 424 425
	if (IS_ERR(f))
		return PTR_ERR(f);
	*filp = f;

426
	f = create_read_pipe(f, 0);
427 428 429 430 431 432 433 434 435 436 437 438 439
	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
L
Linus Torvalds 已提交
440
 * @wait: wait for the application to finish and return status.
441 442 443
 *        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.
L
Linus Torvalds 已提交
444 445 446 447 448
 *
 * 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).
 */
449
int call_usermodehelper_exec(struct subprocess_info *sub_info,
450
			     enum umh_wait wait)
L
Linus Torvalds 已提交
451
{
452
	DECLARE_COMPLETION_ONSTACK(done);
453
	int retval = 0;
L
Linus Torvalds 已提交
454

455
	helper_lock();
456
	if (sub_info->path[0] == '\0')
457
		goto out;
L
Linus Torvalds 已提交
458

459
	if (!khelper_wq || usermodehelper_disabled) {
460 461 462
		retval = -EBUSY;
		goto out;
	}
463 464 465 466 467

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

	queue_work(khelper_wq, &sub_info->work);
468 469
	if (wait == UMH_NO_WAIT)	/* task has freed sub_info */
		goto unlock;
L
Linus Torvalds 已提交
470
	wait_for_completion(&done);
471
	retval = sub_info->retval;
472

473
out:
474
	call_usermodehelper_freeinfo(sub_info);
475
unlock:
476
	helper_unlock();
477
	return retval;
L
Linus Torvalds 已提交
478
}
479
EXPORT_SYMBOL(call_usermodehelper_exec);
L
Linus Torvalds 已提交
480

481 482 483 484 485 486 487 488 489 490 491
/**
 * 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.
 */
492 493 494
int call_usermodehelper_pipe(char *path, char **argv, char **envp,
			     struct file **filp)
{
495 496
	struct subprocess_info *sub_info;
	int ret;
497

498
	sub_info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL);
499 500
	if (sub_info == NULL)
		return -ENOMEM;
501

502 503 504
	ret = call_usermodehelper_stdinpipe(sub_info, filp);
	if (ret < 0)
		goto out;
505

506
	return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
507

508 509 510
  out:
	call_usermodehelper_freeinfo(sub_info);
	return ret;
511 512 513
}
EXPORT_SYMBOL(call_usermodehelper_pipe);

L
Linus Torvalds 已提交
514 515 516 517
void __init usermodehelper_init(void)
{
	khelper_wq = create_singlethread_workqueue("khelper");
	BUG_ON(!khelper_wq);
518
	register_pm_notifier_callback();
L
Linus Torvalds 已提交
519
}