sys.c 53.5 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
/*
 *  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>
L
Linus Torvalds 已提交
19
#include <linux/workqueue.h>
20
#include <linux/capability.h>
L
Linus Torvalds 已提交
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>
M
Matt Helsley 已提交
30
#include <linux/cn_proc.h>
31
#include <linux/getcpu.h>
L
Linus Torvalds 已提交
32 33 34

#include <linux/compat.h>
#include <linux/syscalls.h>
35
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
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
L
Linus Torvalds 已提交
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);
L
Linus Torvalds 已提交
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
 */
L
Linus Torvalds 已提交
158 159

/**
160 161
 *	atomic_notifier_chain_register - Add notifier to an atomic notifier chain
 *	@nh: Pointer to head of the atomic notifier chain
L
Linus Torvalds 已提交
162 163
 *	@n: New entry in notifier chain
 *
164
 *	Adds a notifier to an atomic notifier chain.
L
Linus Torvalds 已提交
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

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
218
 *	with %NOTIFY_STOP_MASK then atomic_notifier_call_chain()
219 220 221 222 223
 *	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.
 */
L
Linus Torvalds 已提交
224
 
225
int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh,
226
		unsigned long val, void *v)
L
Linus Torvalds 已提交
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;
L
Linus Torvalds 已提交
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.
 */
L
Linus Torvalds 已提交
242 243

/**
244 245
 *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
 *	@nh: Pointer to head of the blocking notifier chain
L
Linus Torvalds 已提交
246 247
 *	@n: New entry in notifier chain
 *
248 249
 *	Adds a notifier to a blocking notifier chain.
 *	Must be called in process context.
L
Linus Torvalds 已提交
250
 *
251
 *	Currently always returns zero.
L
Linus Torvalds 已提交
252 253
 */
 
254 255
int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
		struct notifier_block *n)
L
Linus Torvalds 已提交
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;
L
Linus Torvalds 已提交
271 272
}

273
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
L
Linus Torvalds 已提交
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
L
Linus Torvalds 已提交
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.
L
Linus Torvalds 已提交
314
 *
315
 *	If the return value of the notifier can be and'ed
316
 *	with %NOTIFY_STOP_MASK then blocking_notifier_call_chain()
L
Linus Torvalds 已提交
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
L
Linus Torvalds 已提交
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)
L
Linus Torvalds 已提交
325
{
326
	int ret = NOTIFY_DONE;
327

328 329 330 331 332 333 334 335 336 337
	/*
	 * We check the head outside the lock, but if this access is
	 * racy then it does not matter what the result of the test
	 * is, we re-check the list after having taken the lock anyway:
	 */
	if (rcu_dereference(nh->head)) {
		down_read(&nh->rwsem);
		ret = notifier_call_chain(&nh->head, val, v);
		up_read(&nh->rwsem);
	}
L
Linus Torvalds 已提交
338 339 340
	return ret;
}

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
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
396
 *	with %NOTIFY_STOP_MASK then raw_notifier_call_chain()
397 398 399 400 401 402 403 404 405 406 407 408 409
 *	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);
L
Linus Torvalds 已提交
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
/*
 *	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
490
 *	with %NOTIFY_STOP_MASK then srcu_notifier_call_chain()
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
 *	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);
527 528
	if (init_srcu_struct(&nh->srcu) < 0)
		BUG();
529 530 531 532 533
	nh->head = NULL;
}

EXPORT_SYMBOL_GPL(srcu_init_notifier_head);

L
Linus Torvalds 已提交
534 535 536 537 538 539 540
/**
 *	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.
 *
541
 *	Currently always returns zero, as blocking_notifier_chain_register()
L
Linus Torvalds 已提交
542 543 544 545 546
 *	always returns zero.
 */
 
int register_reboot_notifier(struct notifier_block * nb)
{
547
	return blocking_notifier_chain_register(&reboot_notifier_list, nb);
L
Linus Torvalds 已提交
548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563
}

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)
{
564
	return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
L
Linus Torvalds 已提交
565 566 567 568 569 570 571 572 573 574 575 576 577
}

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;
	}
M
Matt Mackall 已提交
578
	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
L
Linus Torvalds 已提交
579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
		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;
599
	struct pid *pgrp;
L
Linus Torvalds 已提交
600 601 602 603 604 605 606 607 608 609 610 611 612 613

	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:
614 615 616 617
			if (who)
				p = find_task_by_pid(who);
			else
				p = current;
L
Linus Torvalds 已提交
618 619 620 621
			if (p)
				error = set_one_prio(p, niceval, error);
			break;
		case PRIO_PGRP:
622 623 624 625 626
			if (who)
				pgrp = find_pid(who);
			else
				pgrp = task_pgrp(current);
			do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
627
				error = set_one_prio(p, niceval, error);
628
			} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
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
			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;
663
	struct pid *pgrp;
L
Linus Torvalds 已提交
664 665 666 667 668 669 670

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

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
671 672 673 674
			if (who)
				p = find_task_by_pid(who);
			else
				p = current;
L
Linus Torvalds 已提交
675 676 677 678 679 680 681
			if (p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			}
			break;
		case PRIO_PGRP:
682 683 684 685 686
			if (who)
				pgrp = find_pid(who);
			else
				pgrp = task_pgrp(current);
			do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
L
Linus Torvalds 已提交
687 688 689
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
690
			} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
L
Linus Torvalds 已提交
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
			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;
}

717 718 719 720 721 722 723 724
/**
 *	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.
 */
725 726 727 728 729 730
void emergency_restart(void)
{
	machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);

A
Adrian Bunk 已提交
731
static void kernel_restart_prepare(char *cmd)
732
{
733
	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
734 735
	system_state = SYSTEM_RESTART;
	device_shutdown();
736
}
737 738 739 740

/**
 *	kernel_restart - reboot the system
 *	@cmd: pointer to buffer containing command to execute for restart
741
 *		or %NULL
742 743 744 745
 *
 *	Shutdown everything and perform a clean reboot.
 *	This is not safe to call in interrupt context.
 */
746 747 748
void kernel_restart(char *cmd)
{
	kernel_restart_prepare(cmd);
749
	if (!cmd)
750
		printk(KERN_EMERG "Restarting system.\n");
751
	else
752 753 754 755 756
		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
	machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);

757 758 759 760 761 762
/**
 *	kernel_kexec - reboot the system
 *
 *	Move into place and start executing a preloaded standalone
 *	executable.  If nothing was preloaded return an error.
 */
A
Adrian Bunk 已提交
763
static void kernel_kexec(void)
764 765 766
{
#ifdef CONFIG_KEXEC
	struct kimage *image;
767
	image = xchg(&kexec_image, NULL);
768
	if (!image)
769
		return;
770
	kernel_restart_prepare(NULL);
771 772 773 774 775 776
	printk(KERN_EMERG "Starting new kernel\n");
	machine_shutdown();
	machine_kexec(image);
#endif
}

777 778
void kernel_shutdown_prepare(enum system_states state)
{
779
	blocking_notifier_call_chain(&reboot_notifier_list,
780 781 782 783
		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
	system_state = state;
	device_shutdown();
}
784 785 786 787 788 789 790
/**
 *	kernel_halt - halt the system
 *
 *	Shutdown everything and perform a clean system halt.
 */
void kernel_halt(void)
{
791
	kernel_shutdown_prepare(SYSTEM_HALT);
792 793 794
	printk(KERN_EMERG "System halted.\n");
	machine_halt();
}
795

796 797
EXPORT_SYMBOL_GPL(kernel_halt);

798 799 800 801 802 803 804
/**
 *	kernel_power_off - power_off the system
 *
 *	Shutdown everything and perform a clean system power_off.
 */
void kernel_power_off(void)
{
805
	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
806 807 808 809
	printk(KERN_EMERG "Power down.\n");
	machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
L
Linus Torvalds 已提交
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833
/*
 * 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;

834 835 836 837 838 839
	/* 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;

L
Linus Torvalds 已提交
840 841 842
	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
843
		kernel_restart(NULL);
L
Linus Torvalds 已提交
844 845 846 847 848 849 850 851 852 853 854
		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:
855
		kernel_halt();
L
Linus Torvalds 已提交
856 857 858 859 860
		unlock_kernel();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_POWER_OFF:
861
		kernel_power_off();
L
Linus Torvalds 已提交
862 863 864 865 866 867 868 869 870 871 872
		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';

873
		kernel_restart(buffer);
L
Linus Torvalds 已提交
874 875
		break;

876
	case LINUX_REBOOT_CMD_KEXEC:
877 878 879 880
		kernel_kexec();
		unlock_kernel();
		return -EINVAL;

L
Linus Torvalds 已提交
881 882 883
#ifdef CONFIG_SOFTWARE_SUSPEND
	case LINUX_REBOOT_CMD_SW_SUSPEND:
		{
J
Johannes Berg 已提交
884
			int ret = pm_suspend(PM_SUSPEND_DISK);
L
Linus Torvalds 已提交
885 886 887 888 889 890 891 892 893 894 895 896 897
			unlock_kernel();
			return ret;
		}
#endif

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

898
static void deferred_cad(struct work_struct *dummy)
L
Linus Torvalds 已提交
899
{
900
	kernel_restart(NULL);
L
Linus Torvalds 已提交
901 902 903 904 905 906 907 908 909
}

/*
 * 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)
{
910
	static DECLARE_WORK(cad_work, deferred_cad);
L
Linus Torvalds 已提交
911 912 913 914

	if (C_A_D)
		schedule_work(&cad_work);
	else
915
		kill_cad_pid(SIGINT, 1);
L
Linus Torvalds 已提交
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
}
	
/*
 * 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;
962
		else
L
Linus Torvalds 已提交
963 964
			return -EPERM;
	}
965
	if (new_egid != old_egid) {
A
Alan Cox 已提交
966
		current->mm->dumpable = suid_dumpable;
967
		smp_wmb();
L
Linus Torvalds 已提交
968 969 970 971 972 973 974 975
	}
	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);
M
Matt Helsley 已提交
976
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
	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;

994 995
	if (capable(CAP_SETGID)) {
		if (old_egid != gid) {
A
Alan Cox 已提交
996
			current->mm->dumpable = suid_dumpable;
997
			smp_wmb();
L
Linus Torvalds 已提交
998 999
		}
		current->gid = current->egid = current->sgid = current->fsgid = gid;
1000 1001
	} else if ((gid == current->gid) || (gid == current->sgid)) {
		if (old_egid != gid) {
A
Alan Cox 已提交
1002
			current->mm->dumpable = suid_dumpable;
1003
			smp_wmb();
L
Linus Torvalds 已提交
1004 1005 1006 1007 1008 1009 1010
		}
		current->egid = current->fsgid = gid;
	}
	else
		return -EPERM;

	key_fsgid_changed(current);
M
Matt Helsley 已提交
1011
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
	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);

1032
	if (dumpclear) {
A
Alan Cox 已提交
1033
		current->mm->dumpable = suid_dumpable;
1034
		smp_wmb();
L
Linus Torvalds 已提交
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 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
	}
	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;

1088
	if (new_euid != old_euid) {
A
Alan Cox 已提交
1089
		current->mm->dumpable = suid_dumpable;
1090
		smp_wmb();
L
Linus Torvalds 已提交
1091 1092 1093 1094 1095 1096 1097 1098
	}
	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);
M
Matt Helsley 已提交
1099
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119

	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;
1120
	int old_ruid, old_suid, new_suid;
L
Linus Torvalds 已提交
1121 1122 1123 1124 1125 1126
	int retval;

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

1127
	old_ruid = current->uid;
L
Linus Torvalds 已提交
1128 1129 1130 1131 1132 1133 1134 1135 1136 1137
	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;

1138
	if (old_euid != uid) {
A
Alan Cox 已提交
1139
		current->mm->dumpable = suid_dumpable;
1140
		smp_wmb();
L
Linus Torvalds 已提交
1141 1142 1143 1144 1145
	}
	current->fsuid = current->euid = uid;
	current->suid = new_suid;

	key_fsuid_changed(current);
M
Matt Helsley 已提交
1146
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182

	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) {
1183
		if (euid != current->euid) {
A
Alan Cox 已提交
1184
			current->mm->dumpable = suid_dumpable;
1185
			smp_wmb();
L
Linus Torvalds 已提交
1186 1187 1188 1189 1190 1191 1192 1193
		}
		current->euid = euid;
	}
	current->fsuid = current->euid;
	if (suid != (uid_t) -1)
		current->suid = suid;

	key_fsuid_changed(current);
M
Matt Helsley 已提交
1194
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232

	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) {
1233
		if (egid != current->egid) {
A
Alan Cox 已提交
1234
			current->mm->dumpable = suid_dumpable;
1235
			smp_wmb();
L
Linus Torvalds 已提交
1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
		}
		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);
M
Matt Helsley 已提交
1246
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
	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 || 
1278 1279
	    capable(CAP_SETUID)) {
		if (uid != old_fsuid) {
A
Alan Cox 已提交
1280
			current->mm->dumpable = suid_dumpable;
1281
			smp_wmb();
L
Linus Torvalds 已提交
1282 1283 1284 1285 1286
		}
		current->fsuid = uid;
	}

	key_fsuid_changed(current);
M
Matt Helsley 已提交
1287
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306

	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 || 
1307 1308
	    capable(CAP_SETGID)) {
		if (gid != old_fsgid) {
A
Alan Cox 已提交
1309
			current->mm->dumpable = suid_dumpable;
1310
			smp_wmb();
L
Linus Torvalds 已提交
1311 1312 1313
		}
		current->fsgid = gid;
		key_fsgid_changed(current);
M
Matt Helsley 已提交
1314
		proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
	}
	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;
1329 1330
		struct task_struct *tsk = current;
		struct task_struct *t;
L
Linus Torvalds 已提交
1331 1332
		cputime_t utime, stime, cutime, cstime;

1333
		spin_lock_irq(&tsk->sighand->siglock);
1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345
		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);
L
Linus Torvalds 已提交
1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372

		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;
1373
	struct task_struct *group_leader = current->group_leader;
L
Linus Torvalds 已提交
1374 1375 1376
	int err = -EINVAL;

	if (!pid)
1377
		pid = group_leader->pid;
L
Linus Torvalds 已提交
1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
	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;

1397
	if (p->real_parent == group_leader) {
L
Linus Torvalds 已提交
1398
		err = -EPERM;
1399
		if (task_session(p) != task_session(group_leader))
L
Linus Torvalds 已提交
1400 1401 1402 1403 1404 1405
			goto out;
		err = -EACCES;
		if (p->did_exec)
			goto out;
	} else {
		err = -ESRCH;
1406
		if (p != group_leader)
L
Linus Torvalds 已提交
1407 1408 1409 1410 1411 1412 1413 1414
			goto out;
	}

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

	if (pgid != pid) {
1415 1416
		struct task_struct *g =
			find_task_by_pid_type(PIDTYPE_PGID, pgid);
L
Linus Torvalds 已提交
1417

1418
		if (!g || task_session(g) != task_session(group_leader))
1419
			goto out;
L
Linus Torvalds 已提交
1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
	}

	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)
{
1441
	if (!pid)
L
Linus Torvalds 已提交
1442
		return process_group(current);
1443
	else {
L
Linus Torvalds 已提交
1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472
		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)
{
1473
	if (!pid)
1474
		return process_session(current);
1475
	else {
L
Linus Torvalds 已提交
1476 1477 1478 1479 1480 1481 1482
		int retval;
		struct task_struct *p;

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

		retval = -ESRCH;
1483
		if (p) {
L
Linus Torvalds 已提交
1484 1485
			retval = security_task_getsid(p);
			if (!retval)
1486
				retval = process_session(p);
L
Linus Torvalds 已提交
1487 1488 1489 1490 1491 1492 1493 1494
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

asmlinkage long sys_setsid(void)
{
1495
	struct task_struct *group_leader = current->group_leader;
1496
	pid_t session;
L
Linus Torvalds 已提交
1497 1498 1499 1500
	int err = -EPERM;

	write_lock_irq(&tasklist_lock);

1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513
	/* 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))
L
Linus Torvalds 已提交
1514 1515
		goto out;

1516
	group_leader->signal->leader = 1;
1517
	__set_special_pids(session, session);
1518 1519

	spin_lock(&group_leader->sighand->siglock);
1520
	group_leader->signal->tty = NULL;
1521 1522
	spin_unlock(&group_leader->sighand->siglock);

1523
	err = process_group(group_leader);
L
Linus Torvalds 已提交
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551
out:
	write_unlock_irq(&tasklist_lock);
	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);

1552
	if (gidsetsize <= NGROUPS_SMALL)
L
Linus Torvalds 已提交
1553
		group_info->blocks[0] = group_info->small_block;
1554
	else {
L
Linus Torvalds 已提交
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 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609
		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)
1610
{
L
Linus Torvalds 已提交
1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626
	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;
}

1627
/* a simple Shell sort */
L
Linus Torvalds 已提交
1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656
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 */
1657
int groups_search(struct group_info *group_info, gid_t grp)
L
Linus Torvalds 已提交
1658
{
1659
	unsigned int left, right;
L
Linus Torvalds 已提交
1660 1661 1662 1663 1664 1665 1666

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
1667
		unsigned int mid = (left+right)/2;
L
Linus Torvalds 已提交
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 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
		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;
1768
	if (grp != current->fsgid)
L
Linus Torvalds 已提交
1769 1770 1771 1772 1773 1774 1775 1776 1777
		retval = groups_search(current->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	int retval = 1;
1778
	if (grp != current->egid)
L
Linus Torvalds 已提交
1779 1780 1781 1782 1783 1784 1785 1786
		retval = groups_search(current->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_egroup_p);

DECLARE_RWSEM(uts_sem);

1787 1788
EXPORT_SYMBOL(uts_sem);

L
Linus Torvalds 已提交
1789 1790 1791 1792 1793
asmlinkage long sys_newuname(struct new_utsname __user * name)
{
	int errno = 0;

	down_read(&uts_sem);
1794
	if (copy_to_user(name, utsname(), sizeof *name))
L
Linus Torvalds 已提交
1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811
		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)) {
1812 1813
		memcpy(utsname()->nodename, tmp, len);
		utsname()->nodename[len] = 0;
L
Linus Torvalds 已提交
1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828
		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);
1829
	i = 1 + strlen(utsname()->nodename);
L
Linus Torvalds 已提交
1830 1831 1832
	if (i > len)
		i = len;
	errno = 0;
1833
	if (copy_to_user(name, utsname()->nodename, i))
L
Linus Torvalds 已提交
1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857
		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)) {
1858 1859
		memcpy(utsname()->domainname, tmp, len);
		utsname()->domainname[len] = 0;
L
Linus Torvalds 已提交
1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893
		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);
1894
	if (x.rlim_cur > 0x7FFFFFFF)
L
Linus Torvalds 已提交
1895
		x.rlim_cur = 0x7FFFFFFF;
1896
	if (x.rlim_max > 0x7FFFFFFF)
L
Linus Torvalds 已提交
1897 1898 1899 1900 1901 1902 1903 1904 1905
		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;
A
Andrew Morton 已提交
1906
	unsigned long it_prof_secs;
L
Linus Torvalds 已提交
1907 1908 1909 1910
	int retval;

	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
A
Andrew Morton 已提交
1911
	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
L
Linus Torvalds 已提交
1912
		return -EFAULT;
A
Andrew Morton 已提交
1913 1914
	if (new_rlim.rlim_cur > new_rlim.rlim_max)
		return -EINVAL;
L
Linus Torvalds 已提交
1915 1916 1917 1918 1919
	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)
A
Andrew Morton 已提交
1920
		return -EPERM;
L
Linus Torvalds 已提交
1921 1922 1923 1924 1925 1926 1927 1928 1929

	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);

A
Andrew Morton 已提交
1930 1931
	if (resource != RLIMIT_CPU)
		goto out;
1932 1933 1934 1935 1936 1937 1938

	/*
	 * 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 risks breakage of
	 * applications, so we live with it
	 */
A
Andrew Morton 已提交
1939 1940 1941 1942 1943
	if (new_rlim.rlim_cur == RLIM_INFINITY)
		goto out;

	it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
	if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
1944 1945
		unsigned long rlim_cur = new_rlim.rlim_cur;
		cputime_t cputime;
A
Andrew Morton 已提交
1946

1947 1948 1949 1950 1951 1952 1953 1954 1955 1956
		if (rlim_cur == 0) {
			/*
			 * The caller is asking for an immediate RLIMIT_CPU
			 * expiry.  But we use the zero value to mean "it was
			 * never set".  So let's cheat and make it one second
			 * instead
			 */
			rlim_cur = 1;
		}
		cputime = secs_to_cputime(rlim_cur);
L
Linus Torvalds 已提交
1957 1958
		read_lock(&tasklist_lock);
		spin_lock_irq(&current->sighand->siglock);
A
Andrew Morton 已提交
1959
		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
L
Linus Torvalds 已提交
1960 1961 1962
		spin_unlock_irq(&current->sighand->siglock);
		read_unlock(&tasklist_lock);
	}
A
Andrew Morton 已提交
1963
out:
L
Linus Torvalds 已提交
1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981
	return 0;
}

/*
 * It would make sense to put struct rusage in the task_struct,
 * except that would make the task_struct be *really big*.  After
 * task_struct gets moved into malloc'ed memory, it would
 * make sense to do this.  It will make moving the rest of the information
 * a lot simpler!  (Which we're not doing right now because we're not
 * measuring them yet).
 *
 * When sampling multiple threads for RUSAGE_SELF, under SMP we might have
 * races with threads incrementing their own counters.  But since word
 * reads are atomic, we either get new values or old values and we don't
 * care which for the sums.  We always take the siglock to protect reading
 * the c* fields from p->signal from races with exit.c updating those
 * fields when reaping, so a sample either gets all the additions of a
 * given child after it's reaped, or none so this sample is before reaping.
1982
 *
1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996
 * Locking:
 * We need to take the siglock for CHILDEREN, SELF and BOTH
 * for  the cases current multithreaded, non-current single threaded
 * non-current multithreaded.  Thread traversal is now safe with
 * the siglock held.
 * Strictly speaking, we donot need to take the siglock if we are current and
 * single threaded,  as no one else can take our signal_struct away, no one
 * else can  reap the  children to update signal->c* counters, and no one else
 * can race with the signal-> fields. If we do not take any lock, the
 * signal-> fields could be read out of order while another thread was just
 * exiting. So we should  place a read memory barrier when we avoid the lock.
 * On the writer side,  write memory barrier is implied in  __exit_signal
 * as __exit_signal releases  the siglock spinlock after updating the signal->
 * fields. But we don't do this yet to keep things simple.
1997
 *
L
Linus Torvalds 已提交
1998 1999 2000 2001 2002 2003 2004 2005 2006
 */

static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
	struct task_struct *t;
	unsigned long flags;
	cputime_t utime, stime;

	memset((char *) r, 0, sizeof *r);
2007
	utime = stime = cputime_zero;
L
Linus Torvalds 已提交
2008

2009 2010 2011 2012 2013
	rcu_read_lock();
	if (!lock_task_sighand(p, &flags)) {
		rcu_read_unlock();
		return;
	}
O
Oleg Nesterov 已提交
2014

L
Linus Torvalds 已提交
2015
	switch (who) {
O
Oleg Nesterov 已提交
2016
		case RUSAGE_BOTH:
L
Linus Torvalds 已提交
2017 2018 2019 2020 2021 2022 2023
		case RUSAGE_CHILDREN:
			utime = p->signal->cutime;
			stime = p->signal->cstime;
			r->ru_nvcsw = p->signal->cnvcsw;
			r->ru_nivcsw = p->signal->cnivcsw;
			r->ru_minflt = p->signal->cmin_flt;
			r->ru_majflt = p->signal->cmaj_flt;
O
Oleg Nesterov 已提交
2024 2025 2026 2027

			if (who == RUSAGE_CHILDREN)
				break;

L
Linus Torvalds 已提交
2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045
		case RUSAGE_SELF:
			utime = cputime_add(utime, p->signal->utime);
			stime = cputime_add(stime, p->signal->stime);
			r->ru_nvcsw += p->signal->nvcsw;
			r->ru_nivcsw += p->signal->nivcsw;
			r->ru_minflt += p->signal->min_flt;
			r->ru_majflt += p->signal->maj_flt;
			t = p;
			do {
				utime = cputime_add(utime, t->utime);
				stime = cputime_add(stime, t->stime);
				r->ru_nvcsw += t->nvcsw;
				r->ru_nivcsw += t->nivcsw;
				r->ru_minflt += t->min_flt;
				r->ru_majflt += t->maj_flt;
				t = next_thread(t);
			} while (t != p);
			break;
O
Oleg Nesterov 已提交
2046

L
Linus Torvalds 已提交
2047 2048 2049
		default:
			BUG();
	}
O
Oleg Nesterov 已提交
2050

2051 2052 2053
	unlock_task_sighand(p, &flags);
	rcu_read_unlock();

O
Oleg Nesterov 已提交
2054 2055
	cputime_to_timeval(utime, &r->ru_utime);
	cputime_to_timeval(stime, &r->ru_stime);
L
Linus Torvalds 已提交
2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088
}

int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
{
	struct rusage r;
	k_getrusage(p, who, &r);
	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
}

asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
{
	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
		return -EINVAL;
	return getrusage(current, who, ru);
}

asmlinkage long sys_umask(int mask)
{
	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
	return mask;
}
    
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
			  unsigned long arg4, unsigned long arg5)
{
	long error;

	error = security_task_prctl(option, arg2, arg3, arg4, arg5);
	if (error)
		return error;

	switch (option) {
		case PR_SET_PDEATHSIG:
2089
			if (!valid_signal(arg2)) {
L
Linus Torvalds 已提交
2090 2091 2092
				error = -EINVAL;
				break;
			}
2093
			current->pdeath_signal = arg2;
L
Linus Torvalds 已提交
2094 2095 2096 2097 2098
			break;
		case PR_GET_PDEATHSIG:
			error = put_user(current->pdeath_signal, (int __user *)arg2);
			break;
		case PR_GET_DUMPABLE:
2099
			error = current->mm->dumpable;
L
Linus Torvalds 已提交
2100 2101
			break;
		case PR_SET_DUMPABLE:
2102
			if (arg2 < 0 || arg2 > 1) {
L
Linus Torvalds 已提交
2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167
				error = -EINVAL;
				break;
			}
			current->mm->dumpable = arg2;
			break;

		case PR_SET_UNALIGN:
			error = SET_UNALIGN_CTL(current, arg2);
			break;
		case PR_GET_UNALIGN:
			error = GET_UNALIGN_CTL(current, arg2);
			break;
		case PR_SET_FPEMU:
			error = SET_FPEMU_CTL(current, arg2);
			break;
		case PR_GET_FPEMU:
			error = GET_FPEMU_CTL(current, arg2);
			break;
		case PR_SET_FPEXC:
			error = SET_FPEXC_CTL(current, arg2);
			break;
		case PR_GET_FPEXC:
			error = GET_FPEXC_CTL(current, arg2);
			break;
		case PR_GET_TIMING:
			error = PR_TIMING_STATISTICAL;
			break;
		case PR_SET_TIMING:
			if (arg2 == PR_TIMING_STATISTICAL)
				error = 0;
			else
				error = -EINVAL;
			break;

		case PR_GET_KEEPCAPS:
			if (current->keep_capabilities)
				error = 1;
			break;
		case PR_SET_KEEPCAPS:
			if (arg2 != 0 && arg2 != 1) {
				error = -EINVAL;
				break;
			}
			current->keep_capabilities = arg2;
			break;
		case PR_SET_NAME: {
			struct task_struct *me = current;
			unsigned char ncomm[sizeof(me->comm)];

			ncomm[sizeof(me->comm)-1] = 0;
			if (strncpy_from_user(ncomm, (char __user *)arg2,
						sizeof(me->comm)-1) < 0)
				return -EFAULT;
			set_task_comm(me, ncomm);
			return 0;
		}
		case PR_GET_NAME: {
			struct task_struct *me = current;
			unsigned char tcomm[sizeof(me->comm)];

			get_task_comm(tcomm, me);
			if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
				return -EFAULT;
			return 0;
		}
2168 2169 2170 2171 2172 2173 2174
		case PR_GET_ENDIAN:
			error = GET_ENDIAN(current, arg2);
			break;
		case PR_SET_ENDIAN:
			error = SET_ENDIAN(current, arg2);
			break;

L
Linus Torvalds 已提交
2175 2176 2177 2178 2179 2180
		default:
			error = -EINVAL;
			break;
	}
	return error;
}
2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201

asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
	   		   struct getcpu_cache __user *cache)
{
	int err = 0;
	int cpu = raw_smp_processor_id();
	if (cpup)
		err |= put_user(cpu, cpup);
	if (nodep)
		err |= put_user(cpu_to_node(cpu), nodep);
	if (cache) {
		/*
		 * The cache is not needed for this implementation,
		 * but make sure user programs pass something
		 * valid. vsyscall implementations can instead make
		 * good use of the cache. Only use t0 and t1 because
		 * these are available in both 32bit and 64bit ABI (no
		 * need for a compat_getcpu). 32bit has enough
		 * padding
		 */
		unsigned long t0, t1;
2202 2203
		get_user(t0, &cache->blob[0]);
		get_user(t1, &cache->blob[1]);
2204 2205
		t0++;
		t1++;
2206 2207
		put_user(t0, &cache->blob[0]);
		put_user(t1, &cache->blob[1]);
2208 2209 2210
	}
	return err ? -EFAULT : 0;
}