aboutsummaryrefslogtreecommitdiff
path: root/kernel/kmod.c
blob: 2f37acde640b6c6e2ce73933a52dbad65f014cf3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
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
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
/*
	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/sched/task.h>
#include <linux/binfmts.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/completion.h>
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.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 <linux/rwsem.h>
#include <linux/ptrace.h>
#include <linux/async.h>
#include <linux/uaccess.h>

#include <trace/events/module.h>

#define CAP_BSET	(void *)1
#define CAP_PI		(void *)2

static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
static DEFINE_SPINLOCK(umh_sysctl_lock);
static DECLARE_RWSEM(umhelper_sem);

#ifdef CONFIG_MODULES
/*
 * Assuming:
 *
 * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
 *		       (u64) THREAD_SIZE * 8UL);
 *
 * If you need less than 50 threads would mean we're dealing with systems
 * smaller than 3200 pages. This assuems you are capable of having ~13M memory,
 * and this would only be an be an upper limit, after which the OOM killer
 * would take effect. Systems like these are very unlikely if modules are
 * enabled.
 */
#define MAX_KMOD_CONCURRENT 50
static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);

/*
 * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads
 * running at the same time without returning. When this happens we
 * believe you've somehow ended up with a recursive module dependency
 * creating a loop.
 *
 * We have no option but to fail.
 *
 * Userspace should proactively try to detect and prevent these.
 */
#define MAX_KMOD_ALL_BUSY_TIMEOUT 5

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

static void free_modprobe_argv(struct subprocess_info *info)
{
	kfree(info->argv[3]); /* check call_modprobe() */
	kfree(info->argv);
}

static int call_modprobe(char *module_name, int wait)
{
	struct subprocess_info *info;
	static char *envp[] = {
		"HOME=/",
		"TERM=linux",
		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
		NULL
	};

	char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL);
	if (!argv)
		goto out;

	module_name = kstrdup(module_name, GFP_KERNEL);
	if (!module_name)
		goto free_argv;

	argv[0] = modprobe_path;
	argv[1] = "-q";
	argv[2] = "--";
	argv[3] = module_name;	/* check free_modprobe_argv() */
	argv[4] = NULL;

	info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL,
					 NULL, free_modprobe_argv, NULL);
	if (!info)
		goto free_module_name;

	return call_usermodehelper_exec(info, wait | UMH_KILLABLE);

free_module_name:
	kfree(module_name);
free_argv:
	kfree(argv);
out:
	return -ENOMEM;
}

/**
 * __request_module - try to load a kernel module
 * @wait: wait (or not) for the operation to complete
 * @fmt: printf style format string for the name of the module
 * @...: arguments 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 or positive exit code from
 * "modprobe" 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(bool wait, const char *fmt, ...)
{
	va_list args;
	char module_name[MODULE_NAME_LEN];
	int ret;

	/*
	 * We don't allow synchronous module loading from async.  Module
	 * init may invoke async_synchronize_full() which will end up
	 * waiting for this task which already is waiting for the module
	 * loading to complete, leading to a deadlock.
	 */
	WARN_ON_ONCE(wait && current_is_async());

	if (!modprobe_path[0])
		return 0;

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

	ret = security_kernel_module_request(module_name);
	if (ret)
		return ret;

	if (atomic_dec_if_positive(&kmod_concurrent_max) < 0) {
		pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...",
				    atomic_read(&kmod_concurrent_max),
				    MAX_KMOD_CONCURRENT, module_name);
		ret = wait_event_killable_timeout(kmod_wq,
						  atomic_dec_if_positive(&kmod_concurrent_max) >= 0,
						  MAX_KMOD_ALL_BUSY_TIMEOUT * HZ);
		if (!ret) {
			pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now",
					    module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT);
			return -ETIME;
		} else if (ret == -ERESTARTSYS) {
			pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name);
			return ret;
		}
	}

	trace_module_request(module_name, wait, _RET_IP_);

	ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);

	atomic_inc(&kmod_concurrent_max);
	wake_up(&kmod_wq);

	return ret;
}
EXPORT_SYMBOL(__request_module);

#endif /* CONFIG_MODULES */

static void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
	if (info->cleanup)
		(*info->cleanup)(info);
	kfree(info);
}

static void umh_complete(struct subprocess_info *sub_info)
{
	struct completion *comp = xchg(&sub_info->complete, NULL);
	/*
	 * See call_usermodehelper_exec(). If xchg() returns NULL
	 * we own sub_info, the UMH_KILLABLE caller has gone away
	 * or the caller used UMH_NO_WAIT.
	 */
	if (comp)
		complete(comp);
	else
		call_usermodehelper_freeinfo(sub_info);
}

/*
 * This is the task which runs the usermode application
 */
static int call_usermodehelper_exec_async(void *data)
{
	struct subprocess_info *sub_info = data;
	struct cred *new;
	int retval;

	spin_lock_irq(&current->sighand->siglock);
	flush_signal_handlers(current, 1);
	spin_unlock_irq(&current->sighand->siglock);

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

	retval = -ENOMEM;
	new = prepare_kernel_cred(current);
	if (!new)
		goto out;

	spin_lock(&umh_sysctl_lock);
	new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
	new->cap_inheritable = cap_intersect(usermodehelper_inheritable,
					     new->cap_inheritable);
	spin_unlock(&umh_sysctl_lock);

	if (sub_info->init) {
		retval = sub_info->init(sub_info, new);
		if (retval) {
			abort_creds(new);
			goto out;
		}
	}

	commit_creds(new);

	retval = do_execve(getname_kernel(sub_info->path),
			   (const char __user *const __user *)sub_info->argv,
			   (const char __user *const __user *)sub_info->envp);
out:
	sub_info->retval = retval;
	/*
	 * call_usermodehelper_exec_sync() will call umh_complete
	 * if UHM_WAIT_PROC.
	 */
	if (!(sub_info->wait & UMH_WAIT_PROC))
		umh_complete(sub_info);
	if (!retval)
		return 0;
	do_exit(0);
}

/* Handles UMH_WAIT_PROC.  */
static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
{
	pid_t pid;

	/* If SIGCLD is ignored sys_wait4 won't populate the status. */
	kernel_sigaction(SIGCHLD, SIG_DFL);
	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
	if (pid < 0) {
		sub_info->retval = pid;
	} else {
		int ret = -ECHILD;
		/*
		 * Normally it is bogus to call wait4() from in-kernel because
		 * wait4() wants to write the exit code to a userspace address.
		 * But call_usermodehelper_exec_sync() always runs as kernel
		 * thread (workqueue) 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_exec_async 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;
	}

	/* Restore default kernel sig handler */
	kernel_sigaction(SIGCHLD, SIG_IGN);

	umh_complete(sub_info);
}

/*
 * We need to create the usermodehelper kernel thread from a task that is affine
 * to an optimized set of CPUs (or nohz housekeeping ones) such that they
 * inherit a widest affinity irrespective of call_usermodehelper() callers with
 * possibly reduced affinity (eg: per-cpu workqueues). We don't want
 * usermodehelper targets to contend a busy CPU.
 *
 * Unbound workqueues provide such wide affinity and allow to block on
 * UMH_WAIT_PROC requests without blocking pending request (up to some limit).
 *
 * Besides, workqueues provide the privilege level that caller might not have
 * to perform the usermodehelper request.
 *
 */
static void call_usermodehelper_exec_work(struct work_struct *work)
{
	struct subprocess_info *sub_info =
		container_of(work, struct subprocess_info, work);

	if (sub_info->wait & UMH_WAIT_PROC) {
		call_usermodehelper_exec_sync(sub_info);
	} else {
		pid_t pid;
		/*
		 * Use CLONE_PARENT to reparent it to kthreadd; we do not
		 * want to pollute current->children, and we need a parent
		 * that always ignores SIGCHLD to ensure auto-reaping.
		 */
		pid = kernel_thread(call_usermodehelper_exec_async, sub_info,
				    CLONE_PARENT | SIGCHLD);
		if (pid < 0) {
			sub_info->retval = pid;
			umh_complete(sub_info);
		}
	}
}

/*
 * 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).
 * Should always be manipulated under umhelper_sem acquired for write.
 */
static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED;

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

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

/*
 * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled
 * to become 'false'.
 */
static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq);

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

int usermodehelper_read_trylock(void)
{
	DEFINE_WAIT(wait);
	int ret = 0;

	down_read(&umhelper_sem);
	for (;;) {
		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
				TASK_INTERRUPTIBLE);
		if (!usermodehelper_disabled)
			break;

		if (usermodehelper_disabled == UMH_DISABLED)
			ret = -EAGAIN;

		up_read(&umhelper_sem);

		if (ret)
			break;

		schedule();
		try_to_freeze();

		down_read(&umhelper_sem);
	}
	finish_wait(&usermodehelper_disabled_waitq, &wait);
	return ret;
}
EXPORT_SYMBOL_GPL(usermodehelper_read_trylock);

long usermodehelper_read_lock_wait(long timeout)
{
	DEFINE_WAIT(wait);

	if (timeout < 0)
		return -EINVAL;

	down_read(&umhelper_sem);
	for (;;) {
		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
				TASK_UNINTERRUPTIBLE);
		if (!usermodehelper_disabled)
			break;

		up_read(&umhelper_sem);

		timeout = schedule_timeout(timeout);
		if (!timeout)
			break;

		down_read(&umhelper_sem);
	}
	finish_wait(&usermodehelper_disabled_waitq, &wait);
	return timeout;
}
EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait);

void usermodehelper_read_unlock(void)
{
	up_read(&umhelper_sem);
}
EXPORT_SYMBOL_GPL(usermodehelper_read_unlock);

/**
 * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled.
 * @depth: New value to assign to usermodehelper_disabled.
 *
 * Change the value of usermodehelper_disabled (under umhelper_sem locked for
 * writing) and wakeup tasks waiting for it to change.
 */
void __usermodehelper_set_disable_depth(enum umh_disable_depth depth)
{
	down_write(&umhelper_sem);
	usermodehelper_disabled = depth;
	wake_up(&usermodehelper_disabled_waitq);
	up_write(&umhelper_sem);
}

/**
 * __usermodehelper_disable - Prevent new helpers from being started.
 * @depth: New value to assign to usermodehelper_disabled.
 *
 * Set usermodehelper_disabled to @depth and wait for running helpers to exit.
 */
int __usermodehelper_disable(enum umh_disable_depth depth)
{
	long retval;

	if (!depth)
		return -EINVAL;

	down_write(&umhelper_sem);
	usermodehelper_disabled = depth;
	up_write(&umhelper_sem);

	/*
	 * 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 0;

	__usermodehelper_set_disable_depth(UMH_ENABLED);
	return -EAGAIN;
}

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

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

/**
 * call_usermodehelper_setup - prepare to call a usermode helper
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
 * @gfp_mask: gfp mask for memory allocation
 * @cleanup: a cleanup function
 * @init: an init function
 * @data: arbitrary context sensitive data
 *
 * 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.
 *
 * The init function is used to customize the helper process prior to
 * exec.  A non-zero return code causes the process to error out, exit,
 * and return the failure to the calling process
 *
 * The cleanup function is just before 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.
 */
struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv,
		char **envp, gfp_t gfp_mask,
		int (*init)(struct subprocess_info *info, struct cred *new),
		void (*cleanup)(struct subprocess_info *info),
		void *data)
{
	struct subprocess_info *sub_info;
	sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
	if (!sub_info)
		goto out;

	INIT_WORK(&sub_info->work, call_usermodehelper_exec_work);

#ifdef CONFIG_STATIC_USERMODEHELPER
	sub_info->path = CONFIG_STATIC_USERMODEHELPER_PATH;
#else
	sub_info->path = path;
#endif
	sub_info->argv = argv;
	sub_info->envp = envp;

	sub_info->cleanup = cleanup;
	sub_info->init = init;
	sub_info->data = data;
  out:
	return sub_info;
}
EXPORT_SYMBOL(call_usermodehelper_setup);

/**
 * call_usermodehelper_exec - start a usermode application
 * @sub_info: information about the subprocessa
 * @wait: wait for the application to finish and return status.
 *        when UMH_NO_WAIT 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 system workqueues.
 * (ie. it runs with full root capabilities and optimized affinity).
 */
int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
{
	DECLARE_COMPLETION_ONSTACK(done);
	int retval = 0;

	if (!sub_info->path) {
		call_usermodehelper_freeinfo(sub_info);
		return -EINVAL;
	}
	helper_lock();
	if (usermodehelper_disabled) {
		retval = -EBUSY;
		goto out;
	}

	/*
	 * If there is no binary for us to call, then just return and get out of
	 * here.  This allows us to set STATIC_USERMODEHELPER_PATH to "" and
	 * disable all call_usermodehelper() calls.
	 */
	if (strlen(sub_info->path) == 0)
		goto out;

	/*
	 * Set the completion pointer only if there is a waiter.
	 * This makes it possible to use umh_complete to free
	 * the data structure in case of UMH_NO_WAIT.
	 */
	sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done;
	sub_info->wait = wait;

	queue_work(system_unbound_wq, &sub_info->work);
	if (wait == UMH_NO_WAIT)	/* task has freed sub_info */
		goto unlock;

	if (wait & UMH_KILLABLE) {
		retval = wait_for_completion_killable(&done);
		if (!retval)
			goto wait_done;

		/* umh_complete() will see NULL and free sub_info */
		if (xchg(&sub_info->complete, NULL))
			goto unlock;
		/* fallthrough, umh_complete() was already called */
	}

	wait_for_completion(&done);
wait_done:
	retval = sub_info->retval;
out:
	call_usermodehelper_freeinfo(sub_info);
unlock:
	helper_unlock();
	return retval;
}
EXPORT_SYMBOL(call_usermodehelper_exec);

/**
 * call_usermodehelper() - prepare and start a usermode application
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
 * @wait: wait for the application to finish and return status.
 *        when UMH_NO_WAIT 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.
 *
 * This function is the equivalent to use call_usermodehelper_setup() and
 * call_usermodehelper_exec().
 */
int call_usermodehelper(const char *path, char **argv, char **envp, int wait)
{
	struct subprocess_info *info;
	gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL;

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

	return call_usermodehelper_exec(info, wait);
}
EXPORT_SYMBOL(call_usermodehelper);

static int proc_cap_handler(struct ctl_table *table, int write,
			 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
	unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
	kernel_cap_t new_cap;
	int err, i;

	if (write && (!capable(CAP_SETPCAP) ||
		      !capable(CAP_SYS_MODULE)))
		return -EPERM;

	/*
	 * convert from the global kernel_cap_t to the ulong array to print to
	 * userspace if this is a read.
	 */
	spin_lock(&umh_sysctl_lock);
	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)  {
		if (table->data == CAP_BSET)
			cap_array[i] = usermodehelper_bset.cap[i];
		else if (table->data == CAP_PI)
			cap_array[i] = usermodehelper_inheritable.cap[i];
		else
			BUG();
	}
	spin_unlock(&umh_sysctl_lock);

	t = *table;
	t.data = &cap_array;

	/*
	 * actually read or write and array of ulongs from userspace.  Remember
	 * these are least significant 32 bits first
	 */
	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
	if (err < 0)
		return err;

	/*
	 * convert from the sysctl array of ulongs to the kernel_cap_t
	 * internal representation
	 */
	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
		new_cap.cap[i] = cap_array[i];

	/*
	 * Drop everything not in the new_cap (but don't add things)
	 */
	spin_lock(&umh_sysctl_lock);
	if (write) {
		if (table->data == CAP_BSET)
			usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
		if (table->data == CAP_PI)
			usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
	}
	spin_unlock(&umh_sysctl_lock);

	return 0;
}

struct ctl_table usermodehelper_table[] = {
	{
		.procname	= "bset",
		.data		= CAP_BSET,
		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
		.mode		= 0600,
		.proc_handler	= proc_cap_handler,
	},
	{
		.procname	= "inheritable",
		.data		= CAP_PI,
		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
		.mode		= 0600,
		.proc_handler	= proc_cap_handler,
	},
	{ }
};