sys.c 53.2 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
/*
 *  linux/kernel/sys.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
17
18
#include <linux/kernel.h>
#include <linux/kexec.h>
Linus Torvalds's avatar
Linus Torvalds committed
19
#include <linux/workqueue.h>
20
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
21
22
23
24
25
26
27
28
#include <linux/device.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
#include <linux/dcookies.h>
#include <linux/suspend.h>
#include <linux/tty.h>
29
#include <linux/signal.h>
30
#include <linux/cn_proc.h>
31
#include <linux/getcpu.h>
Linus Torvalds's avatar
Linus Torvalds committed
32
33
34

#include <linux/compat.h>
#include <linux/syscalls.h>
35
#include <linux/kprobes.h>
Linus Torvalds's avatar
Linus Torvalds committed
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58

#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/unistd.h>

#ifndef SET_UNALIGN_CTL
# define SET_UNALIGN_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_UNALIGN_CTL
# define GET_UNALIGN_CTL(a,b)	(-EINVAL)
#endif
#ifndef SET_FPEMU_CTL
# define SET_FPEMU_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_FPEMU_CTL
# define GET_FPEMU_CTL(a,b)	(-EINVAL)
#endif
#ifndef SET_FPEXC_CTL
# define SET_FPEXC_CTL(a,b)	(-EINVAL)
#endif
#ifndef GET_FPEXC_CTL
# define GET_FPEXC_CTL(a,b)	(-EINVAL)
#endif
59
60
61
62
63
64
#ifndef GET_ENDIAN
# define GET_ENDIAN(a,b)	(-EINVAL)
#endif
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b)	(-EINVAL)
#endif
Linus Torvalds's avatar
Linus Torvalds committed
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

/*
 * this is where the system-wide overflow UID and GID are defined, for
 * architectures that now have 32-bit UID/GID but didn't in the past
 */

int overflowuid = DEFAULT_OVERFLOWUID;
int overflowgid = DEFAULT_OVERFLOWGID;

#ifdef CONFIG_UID16
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
#endif

/*
 * the same as above, but for filesystems which can only store a 16-bit
 * UID and GID. as such, this is needed on all architectures
 */

int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;

EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);

/*
 * this indicates whether you can reboot with ctrl-alt-del: the default is yes
 */

int C_A_D = 1;
95
96
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);
Linus Torvalds's avatar
Linus Torvalds committed
97
98
99
100
101
102
103

/*
 *	Notifier list for kernel code which wants to be called
 *	at shutdown. This is used to stop any idling DMA operations
 *	and the like. 
 */

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
static BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);

/*
 *	Notifier chain core routines.  The exported routines below
 *	are layered on top of these, with appropriate locking added.
 */

static int notifier_chain_register(struct notifier_block **nl,
		struct notifier_block *n)
{
	while ((*nl) != NULL) {
		if (n->priority > (*nl)->priority)
			break;
		nl = &((*nl)->next);
	}
	n->next = *nl;
	rcu_assign_pointer(*nl, n);
	return 0;
}

static int notifier_chain_unregister(struct notifier_block **nl,
		struct notifier_block *n)
{
	while ((*nl) != NULL) {
		if ((*nl) == n) {
			rcu_assign_pointer(*nl, n->next);
			return 0;
		}
		nl = &((*nl)->next);
	}
	return -ENOENT;
}

static int __kprobes notifier_call_chain(struct notifier_block **nl,
		unsigned long val, void *v)
{
	int ret = NOTIFY_DONE;
141
	struct notifier_block *nb, *next_nb;
142
143
144

	nb = rcu_dereference(*nl);
	while (nb) {
145
		next_nb = rcu_dereference(nb->next);
146
147
148
		ret = nb->notifier_call(nb, val, v);
		if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK)
			break;
149
		nb = next_nb;
150
151
152
153
154
155
	}
	return ret;
}

/*
 *	Atomic notifier chain routines.  Registration and unregistration
156
 *	use a spinlock, and call_chain is synchronized by RCU (no locks).
157
 */
Linus Torvalds's avatar
Linus Torvalds committed
158
159

/**
160
161
 *	atomic_notifier_chain_register - Add notifier to an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
Linus Torvalds's avatar
Linus Torvalds committed
162
163
 *	@n: New entry in notifier chain
 *
164
 *	Adds a notifier to an atomic notifier chain.
Linus Torvalds's avatar
Linus Torvalds committed
165
166
167
 *
 *	Currently always returns zero.
 */
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

int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
		struct notifier_block *n)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&nh->lock, flags);
	ret = notifier_chain_register(&nh->head, n);
	spin_unlock_irqrestore(&nh->lock, flags);
	return ret;
}

EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);

/**
 *	atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from an atomic notifier chain.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
		struct notifier_block *n)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&nh->lock, flags);
	ret = notifier_chain_unregister(&nh->head, n);
	spin_unlock_irqrestore(&nh->lock, flags);
	synchronize_rcu();
	return ret;
}

EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);

/**
 *	atomic_notifier_call_chain - Call functions in an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in an atomic context, so they must not block.
 *	This routine uses RCU to synchronize with changes to the chain.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then atomic_notifier_call_chain
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */
Linus Torvalds's avatar
Linus Torvalds committed
224
 
225
int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh,
226
		unsigned long val, void *v)
Linus Torvalds's avatar
Linus Torvalds committed
227
{
228
229
230
231
232
233
	int ret;

	rcu_read_lock();
	ret = notifier_call_chain(&nh->head, val, v);
	rcu_read_unlock();
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
234
235
}

236
237
238
239
240
241
EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);

/*
 *	Blocking notifier chain routines.  All access to the chain is
 *	synchronized by an rwsem.
 */
Linus Torvalds's avatar
Linus Torvalds committed
242
243

/**
244
245
 *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
Linus Torvalds's avatar
Linus Torvalds committed
246
247
 *	@n: New entry in notifier chain
 *
248
249
 *	Adds a notifier to a blocking notifier chain.
 *	Must be called in process context.
Linus Torvalds's avatar
Linus Torvalds committed
250
 *
251
 *	Currently always returns zero.
Linus Torvalds's avatar
Linus Torvalds committed
252
253
 */
 
254
255
int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
		struct notifier_block *n)
Linus Torvalds's avatar
Linus Torvalds committed
256
{
257
258
259
260
261
262
263
264
265
266
267
268
269
270
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call down_write().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_register(&nh->head, n);

	down_write(&nh->rwsem);
	ret = notifier_chain_register(&nh->head, n);
	up_write(&nh->rwsem);
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
271
272
}

273
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
Linus Torvalds's avatar
Linus Torvalds committed
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
 *	blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from a blocking notifier chain.
 *	Must be called from process context.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call down_write().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_unregister(&nh->head, n);

	down_write(&nh->rwsem);
	ret = notifier_chain_unregister(&nh->head, n);
	up_write(&nh->rwsem);
	return ret;
}

EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);

/**
 *	blocking_notifier_call_chain - Call functions in a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
Linus Torvalds's avatar
Linus Torvalds committed
309
310
311
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *
312
313
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in a process context, so they are allowed to block.
Linus Torvalds's avatar
Linus Torvalds committed
314
 *
315
316
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then blocking_notifier_call_chain
Linus Torvalds's avatar
Linus Torvalds committed
317
318
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
319
 *	Otherwise the return value is the return value
Linus Torvalds's avatar
Linus Torvalds committed
320
321
322
 *	of the last notifier function called.
 */
 
323
324
int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
		unsigned long val, void *v)
Linus Torvalds's avatar
Linus Torvalds committed
325
{
326
327
328
329
330
	int ret;

	down_read(&nh->rwsem);
	ret = notifier_call_chain(&nh->head, val, v);
	up_read(&nh->rwsem);
Linus Torvalds's avatar
Linus Torvalds committed
331
332
333
	return ret;
}

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
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);

/*
 *	Raw notifier chain routines.  There is no protection;
 *	the caller must provide it.  Use at your own risk!
 */

/**
 *	raw_notifier_chain_register - Add notifier to a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a raw notifier chain.
 *	All locking must be provided by the caller.
 *
 *	Currently always returns zero.
 */

int raw_notifier_chain_register(struct raw_notifier_head *nh,
		struct notifier_block *n)
{
	return notifier_chain_register(&nh->head, n);
}

EXPORT_SYMBOL_GPL(raw_notifier_chain_register);

/**
 *	raw_notifier_chain_unregister - Remove notifier from a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from a raw notifier chain.
 *	All locking must be provided by the caller.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
		struct notifier_block *n)
{
	return notifier_chain_unregister(&nh->head, n);
}

EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);

/**
 *	raw_notifier_call_chain - Call functions in a raw notifier chain
 *	@nh: Pointer to head of the raw notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in an undefined context.
 *	All locking must be provided by the caller.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then raw_notifier_call_chain
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */

int raw_notifier_call_chain(struct raw_notifier_head *nh,
		unsigned long val, void *v)
{
	return notifier_call_chain(&nh->head, val, v);
}

EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 *	SRCU notifier chain routines.    Registration and unregistration
 *	use a mutex, and call_chain is synchronized by SRCU (no locks).
 */

/**
 *	srcu_notifier_chain_register - Add notifier to an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to an SRCU notifier chain.
 *	Must be called in process context.
 *
 *	Currently always returns zero.
 */

int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call mutex_lock().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_register(&nh->head, n);

	mutex_lock(&nh->mutex);
	ret = notifier_chain_register(&nh->head, n);
	mutex_unlock(&nh->mutex);
	return ret;
}

EXPORT_SYMBOL_GPL(srcu_notifier_chain_register);

/**
 *	srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@n: Entry to remove from notifier chain
 *
 *	Removes a notifier from an SRCU notifier chain.
 *	Must be called from process context.
 *
 *	Returns zero on success or %-ENOENT on failure.
 */
int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
		struct notifier_block *n)
{
	int ret;

	/*
	 * This code gets used during boot-up, when task switching is
	 * not yet working and interrupts must remain disabled.  At
	 * such times we must not call mutex_lock().
	 */
	if (unlikely(system_state == SYSTEM_BOOTING))
		return notifier_chain_unregister(&nh->head, n);

	mutex_lock(&nh->mutex);
	ret = notifier_chain_unregister(&nh->head, n);
	mutex_unlock(&nh->mutex);
	synchronize_srcu(&nh->srcu);
	return ret;
}

EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);

/**
 *	srcu_notifier_call_chain - Call functions in an SRCU notifier chain
 *	@nh: Pointer to head of the SRCU notifier chain
 *	@val: Value passed unmodified to notifier function
 *	@v: Pointer passed unmodified to notifier function
 *
 *	Calls each function in a notifier chain in turn.  The functions
 *	run in a process context, so they are allowed to block.
 *
 *	If the return value of the notifier can be and'ed
 *	with %NOTIFY_STOP_MASK then srcu_notifier_call_chain
 *	will return immediately, with the return value of
 *	the notifier function which halted execution.
 *	Otherwise the return value is the return value
 *	of the last notifier function called.
 */

int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
		unsigned long val, void *v)
{
	int ret;
	int idx;

	idx = srcu_read_lock(&nh->srcu);
	ret = notifier_call_chain(&nh->head, val, v);
	srcu_read_unlock(&nh->srcu, idx);
	return ret;
}

EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);

/**
 *	srcu_init_notifier_head - Initialize an SRCU notifier head
 *	@nh: Pointer to head of the srcu notifier chain
 *
 *	Unlike other sorts of notifier heads, SRCU notifier heads require
 *	dynamic initialization.  Be sure to call this routine before
 *	calling any of the other SRCU notifier routines for this head.
 *
 *	If an SRCU notifier head is deallocated, it must first be cleaned
 *	up by calling srcu_cleanup_notifier_head().  Otherwise the head's
 *	per-cpu data (used by the SRCU mechanism) will leak.
 */

void srcu_init_notifier_head(struct srcu_notifier_head *nh)
{
	mutex_init(&nh->mutex);
	init_srcu_struct(&nh->srcu);
	nh->head = NULL;
}

EXPORT_SYMBOL_GPL(srcu_init_notifier_head);

Linus Torvalds's avatar
Linus Torvalds committed
526
527
528
529
530
531
532
/**
 *	register_reboot_notifier - Register function to be called at reboot time
 *	@nb: Info about notifier function to be called
 *
 *	Registers a function with the list of functions
 *	to be called at reboot time.
 *
533
 *	Currently always returns zero, as blocking_notifier_chain_register
Linus Torvalds's avatar
Linus Torvalds committed
534
535
536
537
538
 *	always returns zero.
 */
 
int register_reboot_notifier(struct notifier_block * nb)
{
539
	return blocking_notifier_chain_register(&reboot_notifier_list, nb);
Linus Torvalds's avatar
Linus Torvalds committed
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
}

EXPORT_SYMBOL(register_reboot_notifier);

/**
 *	unregister_reboot_notifier - Unregister previously registered reboot notifier
 *	@nb: Hook to be unregistered
 *
 *	Unregisters a previously registered reboot
 *	notifier function.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
 
int unregister_reboot_notifier(struct notifier_block * nb)
{
556
	return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
Linus Torvalds's avatar
Linus Torvalds committed
557
558
559
560
561
562
563
564
565
566
567
568
569
}

EXPORT_SYMBOL(unregister_reboot_notifier);

static int set_one_prio(struct task_struct *p, int niceval, int error)
{
	int no_nice;

	if (p->uid != current->euid &&
		p->euid != current->euid && !capable(CAP_SYS_NICE)) {
		error = -EPERM;
		goto out;
	}
570
	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
Linus Torvalds's avatar
Linus Torvalds committed
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
		error = -EACCES;
		goto out;
	}
	no_nice = security_task_setnice(p, niceval);
	if (no_nice) {
		error = no_nice;
		goto out;
	}
	if (error == -ESRCH)
		error = 0;
	set_user_nice(p, niceval);
out:
	return error;
}

asmlinkage long sys_setpriority(int which, int who, int niceval)
{
	struct task_struct *g, *p;
	struct user_struct *user;
	int error = -EINVAL;

	if (which > 2 || which < 0)
		goto out;

	/* normalize: avoid signed division (rounding problems) */
	error = -ESRCH;
	if (niceval < -20)
		niceval = -20;
	if (niceval > 19)
		niceval = 19;

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
			if (!who)
				who = current->pid;
			p = find_task_by_pid(who);
			if (p)
				error = set_one_prio(p, niceval, error);
			break;
		case PRIO_PGRP:
			if (!who)
				who = process_group(current);
			do_each_task_pid(who, PIDTYPE_PGID, p) {
				error = set_one_prio(p, niceval, error);
			} while_each_task_pid(who, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = current->user;
			if (!who)
				who = current->uid;
			else
				if ((who != current->uid) && !(user = find_user(who)))
					goto out_unlock;	/* No processes for this user */

			do_each_thread(g, p)
				if (p->uid == who)
					error = set_one_prio(p, niceval, error);
			while_each_thread(g, p);
			if (who != current->uid)
				free_uid(user);		/* For find_user() */
			break;
	}
out_unlock:
	read_unlock(&tasklist_lock);
out:
	return error;
}

/*
 * Ugh. To avoid negative return values, "getpriority()" will
 * not return the normal nice-value, but a negated value that
 * has been offset by 20 (ie it returns 40..1 instead of -20..19)
 * to stay compatible.
 */
asmlinkage long sys_getpriority(int which, int who)
{
	struct task_struct *g, *p;
	struct user_struct *user;
	long niceval, retval = -ESRCH;

	if (which > 2 || which < 0)
		return -EINVAL;

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
			if (!who)
				who = current->pid;
			p = find_task_by_pid(who);
			if (p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			}
			break;
		case PRIO_PGRP:
			if (!who)
				who = process_group(current);
			do_each_task_pid(who, PIDTYPE_PGID, p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			} while_each_task_pid(who, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = current->user;
			if (!who)
				who = current->uid;
			else
				if ((who != current->uid) && !(user = find_user(who)))
					goto out_unlock;	/* No processes for this user */

			do_each_thread(g, p)
				if (p->uid == who) {
					niceval = 20 - task_nice(p);
					if (niceval > retval)
						retval = niceval;
				}
			while_each_thread(g, p);
			if (who != current->uid)
				free_uid(user);		/* for find_user() */
			break;
	}
out_unlock:
	read_unlock(&tasklist_lock);

	return retval;
}

701
702
703
704
705
706
707
708
/**
 *	emergency_restart - reboot the system
 *
 *	Without shutting down any hardware or taking any locks
 *	reboot the system.  This is called when we know we are in
 *	trouble so this is our best effort to reboot.  This is
 *	safe to call in interrupt context.
 */
709
710
711
712
713
714
void emergency_restart(void)
{
	machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);

Adrian Bunk's avatar
Adrian Bunk committed
715
static void kernel_restart_prepare(char *cmd)
716
{
717
	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
718
719
	system_state = SYSTEM_RESTART;
	device_shutdown();
720
}
721
722
723
724

/**
 *	kernel_restart - reboot the system
 *	@cmd: pointer to buffer containing command to execute for restart
725
 *		or %NULL
726
727
728
729
 *
 *	Shutdown everything and perform a clean reboot.
 *	This is not safe to call in interrupt context.
 */
730
731
732
void kernel_restart(char *cmd)
{
	kernel_restart_prepare(cmd);
733
	if (!cmd)
734
		printk(KERN_EMERG "Restarting system.\n");
735
	else
736
737
738
739
740
		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
	machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);

741
742
743
744
745
746
/**
 *	kernel_kexec - reboot the system
 *
 *	Move into place and start executing a preloaded standalone
 *	executable.  If nothing was preloaded return an error.
 */
Adrian Bunk's avatar
Adrian Bunk committed
747
static void kernel_kexec(void)
748
749
750
{
#ifdef CONFIG_KEXEC
	struct kimage *image;
751
	image = xchg(&kexec_image, NULL);
752
	if (!image)
753
		return;
754
	kernel_restart_prepare(NULL);
755
756
757
758
759
760
	printk(KERN_EMERG "Starting new kernel\n");
	machine_shutdown();
	machine_kexec(image);
#endif
}

761
762
void kernel_shutdown_prepare(enum system_states state)
{
763
	blocking_notifier_call_chain(&reboot_notifier_list,
764
765
766
767
		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
	system_state = state;
	device_shutdown();
}
768
769
770
771
772
773
774
/**
 *	kernel_halt - halt the system
 *
 *	Shutdown everything and perform a clean system halt.
 */
void kernel_halt(void)
{
775
	kernel_shutdown_prepare(SYSTEM_HALT);
776
777
778
	printk(KERN_EMERG "System halted.\n");
	machine_halt();
}
779

780
781
EXPORT_SYMBOL_GPL(kernel_halt);

782
783
784
785
786
787
788
/**
 *	kernel_power_off - power_off the system
 *
 *	Shutdown everything and perform a clean system power_off.
 */
void kernel_power_off(void)
{
789
	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
790
791
792
793
	printk(KERN_EMERG "Power down.\n");
	machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
Linus Torvalds's avatar
Linus Torvalds committed
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
/*
 * Reboot system call: for obvious reasons only root may call it,
 * and even root needs to set up some magic numbers in the registers
 * so that some mistake won't make this reboot the whole machine.
 * You can also set the meaning of the ctrl-alt-del-key here.
 *
 * reboot doesn't sync: do that yourself before calling this.
 */
asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg)
{
	char buffer[256];

	/* We only trust the superuser with rebooting the system. */
	if (!capable(CAP_SYS_BOOT))
		return -EPERM;

	/* For safety, we require "magic" arguments. */
	if (magic1 != LINUX_REBOOT_MAGIC1 ||
	    (magic2 != LINUX_REBOOT_MAGIC2 &&
	                magic2 != LINUX_REBOOT_MAGIC2A &&
			magic2 != LINUX_REBOOT_MAGIC2B &&
	                magic2 != LINUX_REBOOT_MAGIC2C))
		return -EINVAL;

818
819
820
821
822
823
	/* Instead of trying to make the power_off code look like
	 * halt when pm_power_off is not set do it the easy way.
	 */
	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
		cmd = LINUX_REBOOT_CMD_HALT;

Linus Torvalds's avatar
Linus Torvalds committed
824
825
826
	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
827
		kernel_restart(NULL);
Linus Torvalds's avatar
Linus Torvalds committed
828
829
830
831
832
833
834
835
836
837
838
		break;

	case LINUX_REBOOT_CMD_CAD_ON:
		C_A_D = 1;
		break;

	case LINUX_REBOOT_CMD_CAD_OFF:
		C_A_D = 0;
		break;

	case LINUX_REBOOT_CMD_HALT:
839
		kernel_halt();
Linus Torvalds's avatar
Linus Torvalds committed
840
841
842
843
844
		unlock_kernel();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_POWER_OFF:
845
		kernel_power_off();
Linus Torvalds's avatar
Linus Torvalds committed
846
847
848
849
850
851
852
853
854
855
856
		unlock_kernel();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_RESTART2:
		if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
			unlock_kernel();
			return -EFAULT;
		}
		buffer[sizeof(buffer) - 1] = '\0';

857
		kernel_restart(buffer);
Linus Torvalds's avatar
Linus Torvalds committed
858
859
		break;

860
	case LINUX_REBOOT_CMD_KEXEC:
861
862
863
864
		kernel_kexec();
		unlock_kernel();
		return -EINVAL;

Linus Torvalds's avatar
Linus Torvalds committed
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
#ifdef CONFIG_SOFTWARE_SUSPEND
	case LINUX_REBOOT_CMD_SW_SUSPEND:
		{
			int ret = software_suspend();
			unlock_kernel();
			return ret;
		}
#endif

	default:
		unlock_kernel();
		return -EINVAL;
	}
	unlock_kernel();
	return 0;
}

static void deferred_cad(void *dummy)
{
884
	kernel_restart(NULL);
Linus Torvalds's avatar
Linus Torvalds committed
885
886
887
888
889
890
891
892
893
894
895
896
897
898
}

/*
 * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
 * As it's called within an interrupt, it may NOT sync: the only choice
 * is whether to reboot at once, or just ignore the ctrl-alt-del.
 */
void ctrl_alt_del(void)
{
	static DECLARE_WORK(cad_work, deferred_cad, NULL);

	if (C_A_D)
		schedule_work(&cad_work);
	else
899
		kill_cad_pid(SIGINT, 1);
Linus Torvalds's avatar
Linus Torvalds committed
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
}
	
/*
 * Unprivileged users may change the real gid to the effective gid
 * or vice versa.  (BSD-style)
 *
 * If you set the real gid at all, or set the effective gid to a value not
 * equal to the real gid, then the saved gid is set to the new effective gid.
 *
 * This makes it possible for a setgid program to completely drop its
 * privileges, which is often a useful assertion to make when you are doing
 * a security audit over a program.
 *
 * The general idea is that a program which uses just setregid() will be
 * 100% compatible with BSD.  A program which uses just setgid() will be
 * 100% compatible with POSIX with saved IDs. 
 *
 * SMP: There are not races, the GIDs are checked only by filesystem
 *      operations (as far as semantic preservation is concerned).
 */
asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
{
	int old_rgid = current->gid;
	int old_egid = current->egid;
	int new_rgid = old_rgid;
	int new_egid = old_egid;
	int retval;

	retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
	if (retval)
		return retval;

	if (rgid != (gid_t) -1) {
		if ((old_rgid == rgid) ||
		    (current->egid==rgid) ||
		    capable(CAP_SETGID))
			new_rgid = rgid;
		else
			return -EPERM;
	}
	if (egid != (gid_t) -1) {
		if ((old_rgid == egid) ||
		    (current->egid == egid) ||
		    (current->sgid == egid) ||
		    capable(CAP_SETGID))
			new_egid = egid;
946
		else
Linus Torvalds's avatar
Linus Torvalds committed
947
948
			return -EPERM;
	}
949
	if (new_egid != old_egid) {
Alan Cox's avatar
Alan Cox committed
950
		current->mm->dumpable = suid_dumpable;
951
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
952
953
954
955
956
957
958
959
	}
	if (rgid != (gid_t) -1 ||
	    (egid != (gid_t) -1 && egid != old_rgid))
		current->sgid = new_egid;
	current->fsgid = new_egid;
	current->egid = new_egid;
	current->gid = new_rgid;
	key_fsgid_changed(current);
960
	proc_id_connector(current, PROC_EVENT_GID);
Linus Torvalds's avatar
Linus Torvalds committed
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
	return 0;
}

/*
 * setgid() is implemented like SysV w/ SAVED_IDS 
 *
 * SMP: Same implicit races as above.
 */
asmlinkage long sys_setgid(gid_t gid)
{
	int old_egid = current->egid;
	int retval;

	retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
	if (retval)
		return retval;

978
979
	if (capable(CAP_SETGID)) {
		if (old_egid != gid) {
Alan Cox's avatar
Alan Cox committed
980
			current->mm->dumpable = suid_dumpable;
981
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
982
983
		}
		current->gid = current->egid = current->sgid = current->fsgid = gid;
984
985
	} else if ((gid == current->gid) || (gid == current->sgid)) {
		if (old_egid != gid) {
Alan Cox's avatar
Alan Cox committed
986
			current->mm->dumpable = suid_dumpable;
987
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
988
989
990
991
992
993
994
		}
		current->egid = current->fsgid = gid;
	}
	else
		return -EPERM;

	key_fsgid_changed(current);
995
	proc_id_connector(current, PROC_EVENT_GID);
Linus Torvalds's avatar
Linus Torvalds committed
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
	return 0;
}
  
static int set_user(uid_t new_ruid, int dumpclear)
{
	struct user_struct *new_user;

	new_user = alloc_uid(new_ruid);
	if (!new_user)
		return -EAGAIN;

	if (atomic_read(&new_user->processes) >=
				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
			new_user != &root_user) {
		free_uid(new_user);
		return -EAGAIN;
	}

	switch_uid(new_user);

1016
	if (dumpclear) {
Alan Cox's avatar
Alan Cox committed
1017
		current->mm->dumpable = suid_dumpable;
1018
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
	}
	current->uid = new_ruid;
	return 0;
}

/*
 * Unprivileged users may change the real uid to the effective uid
 * or vice versa.  (BSD-style)
 *
 * If you set the real uid at all, or set the effective uid to a value not
 * equal to the real uid, then the saved uid is set to the new effective uid.
 *
 * This makes it possible for a setuid program to completely drop its
 * privileges, which is often a useful assertion to make when you are doing
 * a security audit over a program.
 *
 * The general idea is that a program which uses just setreuid() will be
 * 100% compatible with BSD.  A program which uses just setuid() will be
 * 100% compatible with POSIX with saved IDs. 
 */
asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
{
	int old_ruid, old_euid, old_suid, new_ruid, new_euid;
	int retval;

	retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
	if (retval)
		return retval;

	new_ruid = old_ruid = current->uid;
	new_euid = old_euid = current->euid;
	old_suid = current->suid;

	if (ruid != (uid_t) -1) {
		new_ruid = ruid;
		if ((old_ruid != ruid) &&
		    (current->euid != ruid) &&
		    !capable(CAP_SETUID))
			return -EPERM;
	}

	if (euid != (uid_t) -1) {
		new_euid = euid;
		if ((old_ruid != euid) &&
		    (current->euid != euid) &&
		    (current->suid != euid) &&
		    !capable(CAP_SETUID))
			return -EPERM;
	}

	if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
		return -EAGAIN;

1072
	if (new_euid != old_euid) {
Alan Cox's avatar
Alan Cox committed
1073
		current->mm->dumpable = suid_dumpable;
1074
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1075
1076
1077
1078
1079
1080
1081
1082
	}
	current->fsuid = current->euid = new_euid;
	if (ruid != (uid_t) -1 ||
	    (euid != (uid_t) -1 && euid != old_ruid))
		current->suid = current->euid;
	current->fsuid = current->euid;

	key_fsuid_changed(current);
1083
	proc_id_connector(current, PROC_EVENT_UID);
Linus Torvalds's avatar
Linus Torvalds committed
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
}


		
/*
 * setuid() is implemented like SysV with SAVED_IDS 
 * 
 * Note that SAVED_ID's is deficient in that a setuid root program
 * like sendmail, for example, cannot set its uid to be a normal 
 * user and then switch back, because if you're root, setuid() sets
 * the saved uid too.  If you don't like this, blame the bright people
 * in the POSIX committee and/or USG.  Note that the BSD-style setreuid()
 * will allow a root program to temporarily drop privileges and be able to
 * regain them by swapping the real and effective uid.  
 */
asmlinkage long sys_setuid(uid_t uid)
{
	int old_euid = current->euid;
	int old_ruid, old_suid, new_ruid, new_suid;
	int retval;

	retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
	if (retval)
		return retval;

	old_ruid = new_ruid = current->uid;
	old_suid = current->suid;
	new_suid = old_suid;
	
	if (capable(CAP_SETUID)) {
		if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
			return -EAGAIN;
		new_suid = uid;
	} else if ((uid != current->uid) && (uid != new_suid))
		return -EPERM;

1122
	if (old_euid != uid) {
Alan Cox's avatar
Alan Cox committed
1123
		current->mm->dumpable = suid_dumpable;
1124
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1125
1126
1127
1128
1129
	}
	current->fsuid = current->euid = uid;
	current->suid = new_suid;

	key_fsuid_changed(current);
1130
	proc_id_connector(current, PROC_EVENT_UID);
Linus Torvalds's avatar
Linus Torvalds committed
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
}


/*
 * This function implements a generic ability to update ruid, euid,
 * and suid.  This allows you to implement the 4.4 compatible seteuid().
 */
asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
{
	int old_ruid = current->uid;
	int old_euid = current->euid;
	int old_suid = current->suid;
	int retval;

	retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
	if (retval)
		return retval;

	if (!capable(CAP_SETUID)) {
		if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
		    (ruid != current->euid) && (ruid != current->suid))
			return -EPERM;
		if ((euid != (uid_t) -1) && (euid != current->uid) &&
		    (euid != current->euid) && (euid != current->suid))
			return -EPERM;
		if ((suid != (uid_t) -1) && (suid != current->uid) &&
		    (suid != current->euid) && (suid != current->suid))
			return -EPERM;
	}
	if (ruid != (uid_t) -1) {
		if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
			return -EAGAIN;
	}
	if (euid != (uid_t) -1) {
1167
		if (euid != current->euid) {
Alan Cox's avatar
Alan Cox committed
1168
			current->mm->dumpable = suid_dumpable;
1169
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1170
1171
1172
1173
1174
1175
1176
1177
		}
		current->euid = euid;
	}
	current->fsuid = current->euid;
	if (suid != (uid_t) -1)
		current->suid = suid;

	key_fsuid_changed(current);
1178
	proc_id_connector(current, PROC_EVENT_UID);
Linus Torvalds's avatar
Linus Torvalds committed
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216

	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
}

asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
{
	int retval;

	if (!(retval = put_user(current->uid, ruid)) &&
	    !(retval = put_user(current->euid, euid)))
		retval = put_user(current->suid, suid);

	return retval;
}

/*
 * Same as above, but for rgid, egid, sgid.
 */
asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
{
	int retval;

	retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
	if (retval)
		return retval;

	if (!capable(CAP_SETGID)) {
		if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
		    (rgid != current->egid) && (rgid != current->sgid))
			return -EPERM;
		if ((egid != (gid_t) -1) && (egid != current->gid) &&
		    (egid != current->egid) && (egid != current->sgid))
			return -EPERM;
		if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
		    (sgid != current->egid) && (sgid != current->sgid))
			return -EPERM;
	}
	if (egid != (gid_t) -1) {
1217
		if (egid != current->egid) {
Alan Cox's avatar
Alan Cox committed
1218
			current->mm->dumpable = suid_dumpable;
1219
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
		}
		current->egid = egid;
	}
	current->fsgid = current->egid;
	if (rgid != (gid_t) -1)
		current->gid = rgid;
	if (sgid != (gid_t) -1)
		current->sgid = sgid;

	key_fsgid_changed(current);
1230
	proc_id_connector(current, PROC_EVENT_GID);
Linus Torvalds's avatar
Linus Torvalds committed
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
	return 0;
}

asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
{
	int retval;

	if (!(retval = put_user(current->gid, rgid)) &&
	    !(retval = put_user(current->egid, egid)))
		retval = put_user(current->sgid, sgid);

	return retval;
}


/*
 * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
 * is used for "access()" and for the NFS daemon (letting nfsd stay at
 * whatever uid it wants to). It normally shadows "euid", except when
 * explicitly set by setfsuid() or for access..
 */
asmlinkage long sys_setfsuid(uid_t uid)
{
	int old_fsuid;

	old_fsuid = current->fsuid;
	if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
		return old_fsuid;

	if (uid == current->uid || uid == current->euid ||
	    uid == current->suid || uid == current->fsuid || 
1262
1263
	    capable(CAP_SETUID)) {
		if (uid != old_fsuid) {
Alan Cox's avatar
Alan Cox committed
1264
			current->mm->dumpable = suid_dumpable;
1265
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1266
1267
1268
1269
1270
		}
		current->fsuid = uid;
	}

	key_fsuid_changed(current);
1271
	proc_id_connector(current, PROC_EVENT_UID);
Linus Torvalds's avatar
Linus Torvalds committed
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290

	security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);

	return old_fsuid;
}

/*
 * Samma p svenska..
 */
asmlinkage long sys_setfsgid(gid_t gid)
{
	int old_fsgid;

	old_fsgid = current->fsgid;
	if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
		return old_fsgid;

	if (gid == current->gid || gid == current->egid ||
	    gid == current->sgid || gid == current->fsgid || 
1291
1292
	    capable(CAP_SETGID)) {
		if (gid != old_fsgid) {
Alan Cox's avatar
Alan Cox committed
1293
			current->mm->dumpable = suid_dumpable;
1294
			smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
1295
1296
1297
		}
		current->fsgid = gid;
		key_fsgid_changed(current);
1298
		proc_id_connector(current, PROC_EVENT_GID);
Linus Torvalds's avatar
Linus Torvalds committed
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
	}
	return old_fsgid;
}

asmlinkage long sys_times(struct tms __user * tbuf)
{
	/*
	 *	In the SMP world we might just be unlucky and have one of
	 *	the times increment as we use it. Since the value is an
	 *	atomically safe type this is just fine. Conceptually its
	 *	as if the syscall took an instant longer to occur.
	 */
	if (tbuf) {
		struct tms tmp;
1313
1314
		struct task_struct *tsk = current;
		struct task_struct *t;
Linus Torvalds's avatar
Linus Torvalds committed
1315
1316
		cputime_t utime, stime, cutime, cstime;

1317
		spin_lock_irq(&tsk->sighand->siglock);
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
		utime = tsk->signal->utime;
		stime = tsk->signal->stime;
		t = tsk;
		do {
			utime = cputime_add(utime, t->utime);
			stime = cputime_add(stime, t->stime);
			t = next_thread(t);
		} while (t != tsk);

		cutime = tsk->signal->cutime;
		cstime = tsk->signal->cstime;
		spin_unlock_irq(&tsk->sighand->siglock);
Linus Torvalds's avatar
Linus Torvalds committed
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356

		tmp.tms_utime = cputime_to_clock_t(utime);
		tmp.tms_stime = cputime_to_clock_t(stime);
		tmp.tms_cutime = cputime_to_clock_t(cutime);
		tmp.tms_cstime = cputime_to_clock_t(cstime);
		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
			return -EFAULT;
	}
	return (long) jiffies_64_to_clock_t(get_jiffies_64());
}

/*
 * This needs some heavy checking ...
 * I just haven't the stomach for it. I also don't fully
 * understand sessions/pgrp etc. Let somebody who does explain it.
 *
 * OK, I think I have the protection semantics right.... this is really
 * only important on a multi-user system anyway, to make sure one user
 * can't send a signal to a process owned by another.  -TYT, 12/12/91
 *
 * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
 * LBT 04.03.94
 */

asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
	struct task_struct *p;
1357
	struct task_struct *group_leader = current->group_leader;
Linus Torvalds's avatar
Linus Torvalds committed
1358
1359
1360
	int err = -EINVAL;

	if (!pid)
1361
		pid = group_leader->pid;
Linus Torvalds's avatar
Linus Torvalds committed
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
	if (!pgid)
		pgid = pid;
	if (pgid < 0)
		return -EINVAL;

	/* From this point forward we keep holding onto the tasklist lock
	 * so that our parent does not change from under us. -DaveM
	 */
	write_lock_irq(&tasklist_lock);

	err = -ESRCH;
	p = find_task_by_pid(pid);
	if (!p)
		goto out;

	err = -EINVAL;
	if (!thread_group_leader(p))
		goto out;

1381
	if (p->real_parent == group_leader) {
Linus Torvalds's avatar
Linus Torvalds committed
1382
		err = -EPERM;
1383
		if (p->signal->session != group_leader->signal->session)
Linus Torvalds's avatar
Linus Torvalds committed
1384
1385
1386
1387
1388
1389
			goto out;
		err = -EACCES;
		if (p->did_exec)
			goto out;
	} else {
		err = -ESRCH;
1390
		if (p != group_leader)
Linus Torvalds's avatar
Linus Torvalds committed
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
			goto out;
	}

	err = -EPERM;
	if (p->signal->leader)
		goto out;

	if (pgid != pid) {
		struct task_struct *p;

		do_each_task_pid(pgid, PIDTYPE_PGID, p) {
1402
			if (p->signal->session == group_leader->signal->session)
Linus Torvalds's avatar
Linus Torvalds committed
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
				goto ok_pgid;
		} while_each_task_pid(pgid, PIDTYPE_PGID, p);
		goto out;
	}

ok_pgid:
	err = security_task_setpgid(p, pgid);
	if (err)
		goto out;

	if (process_group(p) != pgid) {
		detach_pid(p, PIDTYPE_PGID);
		p->signal->pgrp = pgid;
		attach_pid(p, PIDTYPE_PGID, pgid);
	}

	err = 0;
out:
	/* All paths lead to here, thus we are safe. -DaveM */
	write_unlock_irq(&tasklist_lock);
	return err;
}

asmlinkage long sys_getpgid(pid_t pid)
{
1428
	if (!pid)
Linus Torvalds's avatar
Linus Torvalds committed
1429
		return process_group(current);
1430
	else {
Linus Torvalds's avatar
Linus Torvalds committed
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
		int retval;
		struct task_struct *p;

		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);

		retval = -ESRCH;
		if (p) {
			retval = security_task_getpgid(p);
			if (!retval)
				retval = process_group(p);
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

#ifdef __ARCH_WANT_SYS_GETPGRP

asmlinkage long sys_getpgrp(void)
{
	/* SMP - assuming writes are word atomic this is fine */
	return process_group(current);
}

#endif

asmlinkage long sys_getsid(pid_t pid)
{
1460
	if (!pid)
Linus Torvalds's avatar
Linus Torvalds committed
1461
		return current->signal->session;
1462
	else {
Linus Torvalds's avatar
Linus Torvalds committed
1463
1464
1465
1466
1467
1468
1469
		int retval;
		struct task_struct *p;

		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);

		retval = -ESRCH;
1470
		if (p) {
Linus Torvalds's avatar
Linus Torvalds committed
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
			retval = security_task_getsid(p);
			if (!retval)
				retval = p->signal->session;
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

asmlinkage long sys_setsid(void)
{
1482
	struct task_struct *group_leader = current->group_leader;
1483
	pid_t session;
Linus Torvalds's avatar
Linus Torvalds committed
1484
1485
	int err = -EPERM;

Ingo Molnar's avatar
Ingo Molnar committed
1486
	mutex_lock(&tty_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
1487
1488
	write_lock_irq(&tasklist_lock);

1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
	/* Fail if I am already a session leader */
	if (group_leader->signal->leader)
		goto out;

	session = group_leader->pid;
	/* Fail if a process group id already exists that equals the
	 * proposed session id.
	 *
	 * Don't check if session id == 1 because kernel threads use this
	 * session id and so the check will always fail and make it so
	 * init cannot successfully call setsid.
	 */
	if (session > 1 && find_task_by_pid_type(PIDTYPE_PGID, session))
Linus Torvalds's avatar
Linus Torvalds committed
1502
1503
		goto out;

1504
	group_leader->signal->leader = 1;
1505
	__set_special_pids(session, session);
1506
1507
1508
	group_leader->signal->tty = NULL;
	group_leader->signal->tty_old_pgrp = 0;
	err = process_group(group_leader);
Linus Torvalds's avatar
Linus Torvalds committed
1509
1510
out:
	write_unlock_irq(&tasklist_lock);
Ingo Molnar's avatar
Ingo Molnar committed
1511
	mutex_unlock(&tty_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
	return err;
}

/*
 * Supplementary group IDs
 */

/* init to 2 - one for init_task, one to ensure it is never freed */
struct group_info init_groups = { .usage = ATOMIC_INIT(2) };

struct group_info *groups_alloc(int gidsetsize)
{
	struct group_info *group_info;
	int nblocks;
	int i;

	nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
	/* Make sure we always allocate at least one indirect block pointer */
	nblocks = nblocks ? : 1;
	group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
	if (!group_info)
		return NULL;
	group_info->ngroups = gidsetsize;
	group_info->nblocks = nblocks;
	atomic_set(&group_info->usage, 1);

1538
	if (gidsetsize <= NGROUPS_SMALL)
Linus Torvalds's avatar
Linus Torvalds committed
1539
		group_info->blocks[0] = group_info->small_block;
1540
	else {
Linus Torvalds's avatar
Linus Torvalds committed
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
		for (i = 0; i < nblocks; i++) {
			gid_t *b;
			b = (void *)__get_free_page(GFP_USER);
			if (!b)
				goto out_undo_partial_alloc;
			group_info->blocks[i] = b;
		}
	}
	return group_info;

out_undo_partial_alloc:
	while (--i >= 0) {
		free_page((unsigned long)group_info->blocks[i]);
	}
	kfree(group_info);
	return NULL;
}

EXPORT_SYMBOL(groups_alloc);

void groups_free(struct group_info *group_info)
{
	if (group_info->blocks[0] != group_info->small_block) {
		int i;
		for (i = 0; i < group_info->nblocks; i++)
			free_page((unsigned long)group_info->blocks[i]);
	}
	kfree(group_info);
}

EXPORT_SYMBOL(groups_free);

/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
    struct group_info *group_info)
{
	int i;
	int count = group_info->ngroups;

	for (i = 0; i < group_info->nblocks; i++) {
		int cp_count = min(NGROUPS_PER_BLOCK, count);
		int off = i * NGROUPS_PER_BLOCK;
		int len = cp_count * sizeof(*grouplist);

		if (copy_to_user(grouplist+off, group_info->blocks[i], len))
			return -EFAULT;

		count -= cp_count;
	}
	return 0;
}

/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
    gid_t __user *grouplist)
1596
{
Linus Torvalds's avatar
Linus Torvalds committed
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
	int i;
	int count = group_info->ngroups;

	for (i = 0; i < group_info->nblocks; i++) {
		int cp_count = min(NGROUPS_PER_BLOCK, count);
		int off = i * NGROUPS_PER_BLOCK;
		int len = cp_count * sizeof(*grouplist);

		if (copy_from_user(group_info->blocks[i], grouplist+off, len))
			return -EFAULT;

		count -= cp_count;
	}
	return 0;
}

1613
/* a simple Shell sort */
Linus Torvalds's avatar
Linus Torvalds committed
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
static void groups_sort(struct group_info *group_info)
{
	int base, max, stride;
	int gidsetsize = group_info->ngroups;

	for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
		; /* nothing */
	stride /= 3;

	while (stride) {
		max = gidsetsize - stride;
		for (base = 0; base < max; base++) {
			int left = base;
			int right = left + stride;
			gid_t tmp = GROUP_AT(group_info, right);

			while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
				GROUP_AT(group_info, right) =
				    GROUP_AT(group_info, left);
				right = left;
				left -= stride;
			}
			GROUP_AT(group_info, right) = tmp;
		}
		stride /= 3;
	}
}

/* a simple bsearch */
1643
int groups_search(struct group_info *group_info, gid_t grp)
Linus Torvalds's avatar
Linus Torvalds committed
1644
{
1645
	unsigned int left, right;
Linus Torvalds's avatar
Linus Torvalds committed
1646
1647
1648
1649
1650
1651
1652

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
1653
		unsigned int mid = (left+right)/2;
Linus Torvalds's avatar
Linus Torvalds committed
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
		int cmp = grp - GROUP_AT(group_info, mid);
		if (cmp > 0)
			left = mid + 1;
		else if (cmp < 0)
			right = mid;
		else
			return 1;
	}
	return 0;
}

/* validate and set current->group_info */
int set_current_groups(struct group_info *group_info)
{
	int retval;
	struct group_info *old_info;

	retval = security_task_setgroups(group_info);
	if (retval)
		return retval;

	groups_sort(group_info);
	get_group_info(group_info);

	task_lock(current);
	old_info = current->group_info;
	current->group_info = group_info;
	task_unlock(current);

	put_group_info(old_info);

	return 0;
}

EXPORT_SYMBOL(set_current_groups);

asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
	int i = 0;

	/*
	 *	SMP: Nobody else can change our grouplist. Thus we are
	 *	safe.
	 */

	if (gidsetsize < 0)
		return -EINVAL;

	/* no need to grab task_lock here; it cannot change */
	i = current->group_info->ngroups;
	if (gidsetsize) {
		if (i > gidsetsize) {
			i = -EINVAL;
			goto out;
		}
		if (groups_to_user(grouplist, current->group_info)) {
			i = -EFAULT;
			goto out;
		}
	}
out:
	return i;
}

/*
 *	SMP: Our groups are copy-on-write. We can set them safely
 *	without another task interfering.
 */
 
asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
{
	struct group_info *group_info;
	int retval;

	if (!capable(CAP_SETGID))
		return -EPERM;
	if ((unsigned)gidsetsize > NGROUPS_MAX)
		return -EINVAL;

	group_info = groups_alloc(gidsetsize);
	if (!group_info)
		return -ENOMEM;
	retval = groups_from_user(group_info, grouplist);
	if (retval) {
		put_group_info(group_info);
		return retval;
	}

	retval = set_current_groups(group_info);
	put_group_info(group_info);

	return retval;
}

/*
 * Check whether we're fsgid/egid or in the supplemental group..
 */
int in_group_p(gid_t grp)
{
	int retval = 1;
1754
	if (grp != current->fsgid)
Linus Torvalds's avatar
Linus Torvalds committed
1755
1756
1757
1758
1759
1760
1761
1762
1763
		retval = groups_search(current->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	int retval = 1;
1764
	if (grp != current->egid)
Linus Torvalds's avatar
Linus Torvalds committed
1765
1766
1767
1768
1769
1770
1771
1772
		retval = groups_search(current->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_egroup_p);

DECLARE_RWSEM(uts_sem);

1773
1774
EXPORT_SYMBOL(uts_sem);

Linus Torvalds's avatar
Linus Torvalds committed
1775
1776
1777
1778
1779
asmlinkage long sys_newuname(struct new_utsname __user * name)
{
	int errno = 0;

	down_read(&uts_sem);
1780
	if (copy_to_user(name, utsname(), sizeof *name))
Linus Torvalds's avatar
Linus Torvalds committed
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

asmlinkage long sys_sethostname(char __user *name, int len)
{
	int errno;
	char tmp[__NEW_UTS_LEN];

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (len < 0 || len > __NEW_UTS_LEN)
		return -EINVAL;
	down_write(&uts_sem);
	errno = -EFAULT;
	if (!copy_from_user(tmp, name, len)) {
1798
1799
		memcpy(utsname()->nodename, tmp, len);
		utsname()->nodename[len] = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

#ifdef __ARCH_WANT_SYS_GETHOSTNAME

asmlinkage long sys_gethostname(char __user *name, int len)
{
	int i, errno;

	if (len < 0)
		return -EINVAL;
	down_read(&uts_sem);
1815
	i = 1 + strlen(utsname()->nodename);
Linus Torvalds's avatar
Linus Torvalds committed
1816
1817
1818
	if (i > len)
		i = len;
	errno = 0;
1819
	if (copy_to_user(name, utsname()->nodename, i))
Linus Torvalds's avatar
Linus Torvalds committed
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

#endif

/*
 * Only setdomainname; getdomainname can be implemented by calling
 * uname()
 */
asmlinkage long sys_setdomainname(char __user *name, int len)
{
	int errno;
	char tmp[__NEW_UTS_LEN];

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (len < 0 || len > __NEW_UTS_LEN)
		return -EINVAL;

	down_write(&uts_sem);
	errno = -EFAULT;
	if (!copy_from_user(tmp, name, len)) {
1844
1845
		memcpy(utsname()->domainname, tmp, len);
		utsname()->domainname[len] = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
	else {
		struct rlimit value;
		task_lock(current->group_leader);
		value = current->signal->rlim[resource];
		task_unlock(current->group_leader);
		return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
	}
}

#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT

/*
 *	Back compatibility for getrlimit. Needed for some apps.
 */
 
asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	struct rlimit x;
	if (resource >= RLIM_NLIMITS)
		return -EINVAL;

	task_lock(current->group_leader);
	x = current->signal->rlim[resource];
	task_unlock(current->group_leader);
1880
	if (x.rlim_cur > 0x7FFFFFFF)
Linus Torvalds's avatar
Linus Torvalds committed
1881
		x.rlim_cur = 0x7FFFFFFF;
1882
	if (x.rlim_max > 0x7FFFFFFF)
Linus Torvalds's avatar
Linus Torvalds committed
1883
1884
1885
1886
1887
1888
1889
1890
1891
		x.rlim_max = 0x7FFFFFFF;
	return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}

#endif

asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	struct rlimit new_rlim, *old_rlim;
1892
	unsigned long it_prof_secs;
Linus Torvalds's avatar
Linus Torvalds committed
1893
1894
1895
1896
	int retval;

	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
1897
	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
Linus Torvalds's avatar
Linus Torvalds committed
1898
		return -EFAULT;
1899
1900
	if (new_rlim.rlim_cur > new_rlim.rlim_max)
		return -EINVAL;
Linus Torvalds's avatar
Linus Torvalds committed
1901
1902
1903
1904
1905
	old_rlim = current->signal->rlim + resource;
	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
	    !capable(CAP_SYS_RESOURCE))
		return -EPERM;
	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN)
1906
		return -EPERM;
Linus Torvalds's avatar
Linus Torvalds committed
1907
1908
1909
1910
1911
1912
1913
1914
1915

	retval = security_task_setrlimit(resource, &new_rlim);
	if (retval)
		return retval;

	task_lock(current->group_leader);
	*old_rlim = new_rlim;
	task_unlock(current->group_leader);

1916
1917
	if (resource != RLIMIT_CPU)
		goto out;
1918
1919
1920
1921
1922
1923
1924

	/*
	 * RLIMIT_CPU handling.   Note that the kernel fails to return an error
	 * code if it rejected the user's attempt to set RLIMIT_CPU.  This is a
	 * very long-standing error, and fixing it now ri