sys.c 44.4 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
/*
 *  linux/kernel/sys.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/config.h>
#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/init.h>
#include <linux/highuid.h>
#include <linux/fs.h>
19 20
#include <linux/kernel.h>
#include <linux/kexec.h>
L
Linus Torvalds 已提交
21
#include <linux/workqueue.h>
22
#include <linux/capability.h>
L
Linus Torvalds 已提交
23 24 25 26 27 28 29 30
#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>
31
#include <linux/signal.h>
M
Matt Helsley 已提交
32
#include <linux/cn_proc.h>
L
Linus Torvalds 已提交
33 34 35

#include <linux/compat.h>
#include <linux/syscalls.h>
36
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172

#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

/*
 * 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;
int cad_pid = 1;

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

static struct notifier_block *reboot_notifier_list;
static DEFINE_RWLOCK(notifier_lock);

/**
 *	notifier_chain_register	- Add notifier to a notifier chain
 *	@list: Pointer to root list pointer
 *	@n: New entry in notifier chain
 *
 *	Adds a notifier to a notifier chain.
 *
 *	Currently always returns zero.
 */
 
int notifier_chain_register(struct notifier_block **list, struct notifier_block *n)
{
	write_lock(&notifier_lock);
	while(*list)
	{
		if(n->priority > (*list)->priority)
			break;
		list= &((*list)->next);
	}
	n->next = *list;
	*list=n;
	write_unlock(&notifier_lock);
	return 0;
}

EXPORT_SYMBOL(notifier_chain_register);

/**
 *	notifier_chain_unregister - Remove notifier from a notifier chain
 *	@nl: Pointer to root list pointer
 *	@n: New entry in notifier chain
 *
 *	Removes a notifier from a notifier chain.
 *
 *	Returns zero on success, or %-ENOENT on failure.
 */
 
int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n)
{
	write_lock(&notifier_lock);
	while((*nl)!=NULL)
	{
		if((*nl)==n)
		{
			*nl=n->next;
			write_unlock(&notifier_lock);
			return 0;
		}
		nl=&((*nl)->next);
	}
	write_unlock(&notifier_lock);
	return -ENOENT;
}

EXPORT_SYMBOL(notifier_chain_unregister);

/**
 *	notifier_call_chain - Call functions in a notifier chain
 *	@n: Pointer to root pointer of 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.
 *
 *	If the return value of the notifier can be and'd
 *	with %NOTIFY_STOP_MASK, then 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.
 */
 
173
int __kprobes notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
L
Linus Torvalds 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
{
	int ret=NOTIFY_DONE;
	struct notifier_block *nb = *n;

	while(nb)
	{
		ret=nb->notifier_call(nb,val,v);
		if(ret&NOTIFY_STOP_MASK)
		{
			return ret;
		}
		nb=nb->next;
	}
	return ret;
}

EXPORT_SYMBOL(notifier_call_chain);

/**
 *	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.
 *
 *	Currently always returns zero, as notifier_chain_register
 *	always returns zero.
 */
 
int register_reboot_notifier(struct notifier_block * nb)
{
	return notifier_chain_register(&reboot_notifier_list, nb);
}

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)
{
	return notifier_chain_unregister(&reboot_notifier_list, nb);
}

EXPORT_SYMBOL(unregister_reboot_notifier);

I
Ingo Molnar 已提交
227 228 229 230 231 232 233 234 235 236 237 238
#ifndef CONFIG_SECURITY
int capable(int cap)
{
        if (cap_raised(current->cap_effective, cap)) {
	       current->flags |= PF_SUPERPRIV;
	       return 1;
        }
        return 0;
}
EXPORT_SYMBOL(capable);
#endif

L
Linus Torvalds 已提交
239 240 241 242 243 244 245 246 247
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
248
	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
L
Linus Torvalds 已提交
249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
		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;
}

379 380 381 382 383 384 385 386
/**
 *	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.
 */
387 388 389 390 391 392
void emergency_restart(void)
{
	machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);

393
void kernel_restart_prepare(char *cmd)
394 395 396 397
{
	notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
	system_state = SYSTEM_RESTART;
	device_shutdown();
398
}
399 400 401 402

/**
 *	kernel_restart - reboot the system
 *	@cmd: pointer to buffer containing command to execute for restart
403
 *		or %NULL
404 405 406 407
 *
 *	Shutdown everything and perform a clean reboot.
 *	This is not safe to call in interrupt context.
 */
408 409 410
void kernel_restart(char *cmd)
{
	kernel_restart_prepare(cmd);
411 412 413 414 415 416 417 418 419 420
	if (!cmd) {
		printk(KERN_EMERG "Restarting system.\n");
	} else {
		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
	}
	printk(".\n");
	machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);

421 422 423 424 425 426
/**
 *	kernel_kexec - reboot the system
 *
 *	Move into place and start executing a preloaded standalone
 *	executable.  If nothing was preloaded return an error.
 */
427 428 429 430
void kernel_kexec(void)
{
#ifdef CONFIG_KEXEC
	struct kimage *image;
431
	image = xchg(&kexec_image, NULL);
432 433 434
	if (!image) {
		return;
	}
435
	kernel_restart_prepare(NULL);
436 437 438 439 440 441 442
	printk(KERN_EMERG "Starting new kernel\n");
	machine_shutdown();
	machine_kexec(image);
#endif
}
EXPORT_SYMBOL_GPL(kernel_kexec);

443 444 445 446 447 448 449
void kernel_shutdown_prepare(enum system_states state)
{
	notifier_call_chain(&reboot_notifier_list,
		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
	system_state = state;
	device_shutdown();
}
450 451 452 453 454 455 456
/**
 *	kernel_halt - halt the system
 *
 *	Shutdown everything and perform a clean system halt.
 */
void kernel_halt(void)
{
457
	kernel_shutdown_prepare(SYSTEM_HALT);
458 459 460
	printk(KERN_EMERG "System halted.\n");
	machine_halt();
}
461

462 463
EXPORT_SYMBOL_GPL(kernel_halt);

464 465 466 467 468 469 470
/**
 *	kernel_power_off - power_off the system
 *
 *	Shutdown everything and perform a clean system power_off.
 */
void kernel_power_off(void)
{
471
	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
472 473 474 475
	printk(KERN_EMERG "Power down.\n");
	machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
L
Linus Torvalds 已提交
476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
/*
 * 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;

500 501 502 503 504 505
	/* 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
506 507 508
	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
509
		kernel_restart(NULL);
L
Linus Torvalds 已提交
510 511 512 513 514 515 516 517 518 519 520
		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:
521
		kernel_halt();
L
Linus Torvalds 已提交
522 523 524 525 526
		unlock_kernel();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_POWER_OFF:
527
		kernel_power_off();
L
Linus Torvalds 已提交
528 529 530 531 532 533 534 535 536 537 538
		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';

539
		kernel_restart(buffer);
L
Linus Torvalds 已提交
540 541
		break;

542
	case LINUX_REBOOT_CMD_KEXEC:
543 544 545 546
		kernel_kexec();
		unlock_kernel();
		return -EINVAL;

L
Linus Torvalds 已提交
547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
#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)
{
566
	kernel_restart(NULL);
L
Linus Torvalds 已提交
567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
}

/*
 * 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
		kill_proc(cad_pid, SIGINT, 1);
}
	

/*
 * 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;
		else {
			return -EPERM;
		}
	}
	if (new_egid != old_egid)
	{
A
Alan Cox 已提交
635
		current->mm->dumpable = suid_dumpable;
636
		smp_wmb();
L
Linus Torvalds 已提交
637 638 639 640 641 642 643 644
	}
	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
645
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
	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;

	if (capable(CAP_SETGID))
	{
		if(old_egid != gid)
		{
A
Alan Cox 已提交
667
			current->mm->dumpable = suid_dumpable;
668
			smp_wmb();
L
Linus Torvalds 已提交
669 670 671 672 673 674 675
		}
		current->gid = current->egid = current->sgid = current->fsgid = gid;
	}
	else if ((gid == current->gid) || (gid == current->sgid))
	{
		if(old_egid != gid)
		{
A
Alan Cox 已提交
676
			current->mm->dumpable = suid_dumpable;
677
			smp_wmb();
L
Linus Torvalds 已提交
678 679 680 681 682 683 684
		}
		current->egid = current->fsgid = gid;
	}
	else
		return -EPERM;

	key_fsgid_changed(current);
M
Matt Helsley 已提交
685
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
	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);

	if(dumpclear)
	{
A
Alan Cox 已提交
708
		current->mm->dumpable = suid_dumpable;
709
		smp_wmb();
L
Linus Torvalds 已提交
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764
	}
	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;

	if (new_euid != old_euid)
	{
A
Alan Cox 已提交
765
		current->mm->dumpable = suid_dumpable;
766
		smp_wmb();
L
Linus Torvalds 已提交
767 768 769 770 771 772 773 774
	}
	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
775
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815

	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;

	if (old_euid != uid)
	{
A
Alan Cox 已提交
816
		current->mm->dumpable = suid_dumpable;
817
		smp_wmb();
L
Linus Torvalds 已提交
818 819 820 821 822
	}
	current->fsuid = current->euid = uid;
	current->suid = new_suid;

	key_fsuid_changed(current);
M
Matt Helsley 已提交
823
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861

	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) {
		if (euid != current->euid)
		{
A
Alan Cox 已提交
862
			current->mm->dumpable = suid_dumpable;
863
			smp_wmb();
L
Linus Torvalds 已提交
864 865 866 867 868 869 870 871
		}
		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
872
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912

	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) {
		if (egid != current->egid)
		{
A
Alan Cox 已提交
913
			current->mm->dumpable = suid_dumpable;
914
			smp_wmb();
L
Linus Torvalds 已提交
915 916 917 918 919 920 921 922 923 924
		}
		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
925
	proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
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
	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 || 
	    capable(CAP_SETUID))
	{
		if (uid != old_fsuid)
		{
A
Alan Cox 已提交
961
			current->mm->dumpable = suid_dumpable;
962
			smp_wmb();
L
Linus Torvalds 已提交
963 964 965 966 967
		}
		current->fsuid = uid;
	}

	key_fsuid_changed(current);
M
Matt Helsley 已提交
968
	proc_id_connector(current, PROC_EVENT_UID);
L
Linus Torvalds 已提交
969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991

	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 || 
	    capable(CAP_SETGID))
	{
		if (gid != old_fsgid)
		{
A
Alan Cox 已提交
992
			current->mm->dumpable = suid_dumpable;
993
			smp_wmb();
L
Linus Torvalds 已提交
994 995 996
		}
		current->fsgid = gid;
		key_fsgid_changed(current);
M
Matt Helsley 已提交
997
		proc_id_connector(current, PROC_EVENT_GID);
L
Linus Torvalds 已提交
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
	}
	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;
		cputime_t utime, stime, cutime, cstime;

1014 1015 1016 1017 1018 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
#ifdef CONFIG_SMP
		if (thread_group_empty(current)) {
			/*
			 * Single thread case without the use of any locks.
			 *
			 * We may race with release_task if two threads are
			 * executing. However, release task first adds up the
			 * counters (__exit_signal) before  removing the task
			 * from the process tasklist (__unhash_process).
			 * __exit_signal also acquires and releases the
			 * siglock which results in the proper memory ordering
			 * so that the list modifications are always visible
			 * after the counters have been updated.
			 *
			 * If the counters have been updated by the second thread
			 * but the thread has not yet been removed from the list
			 * then the other branch will be executing which will
			 * block on tasklist_lock until the exit handling of the
			 * other task is finished.
			 *
			 * This also implies that the sighand->siglock cannot
			 * be held by another processor. So we can also
			 * skip acquiring that lock.
			 */
			utime = cputime_add(current->signal->utime, current->utime);
			stime = cputime_add(current->signal->utime, current->stime);
			cutime = current->signal->cutime;
			cstime = current->signal->cstime;
		} else
#endif
		{
L
Linus Torvalds 已提交
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
			/* Process with multiple threads */
			struct task_struct *tsk = current;
			struct task_struct *t;

			read_lock(&tasklist_lock);
			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);

			/*
			 * While we have tasklist_lock read-locked, no dying thread
			 * can be updating current->signal->[us]time.  Instead,
			 * we got their counts included in the live thread loop.
			 * However, another thread can come in right now and
			 * do a wait call that updates current->signal->c[us]time.
			 * To make sure we always see that pair updated atomically,
			 * we take the siglock around fetching them.
			 */
			spin_lock_irq(&tsk->sighand->siglock);
			cutime = tsk->signal->cutime;
			cstime = tsk->signal->cstime;
			spin_unlock_irq(&tsk->sighand->siglock);
			read_unlock(&tasklist_lock);
		}
L
Linus Torvalds 已提交
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
		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;
1101
	struct task_struct *group_leader = current->group_leader;
L
Linus Torvalds 已提交
1102 1103 1104
	int err = -EINVAL;

	if (!pid)
1105
		pid = group_leader->pid;
L
Linus Torvalds 已提交
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
	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;

1125
	if (p->real_parent == group_leader) {
L
Linus Torvalds 已提交
1126
		err = -EPERM;
1127
		if (p->signal->session != group_leader->signal->session)
L
Linus Torvalds 已提交
1128 1129 1130 1131 1132 1133
			goto out;
		err = -EACCES;
		if (p->did_exec)
			goto out;
	} else {
		err = -ESRCH;
1134
		if (p != group_leader)
L
Linus Torvalds 已提交
1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
			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) {
1146
			if (p->signal->session == group_leader->signal->session)
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 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 1217 1218 1219 1220 1221 1222 1223 1224 1225
				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)
{
	if (!pid) {
		return process_group(current);
	} else {
		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)
{
	if (!pid) {
		return current->signal->session;
	} else {
		int retval;
		struct task_struct *p;

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

		retval = -ESRCH;
		if(p) {
			retval = security_task_getsid(p);
			if (!retval)
				retval = p->signal->session;
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

asmlinkage long sys_setsid(void)
{
1226
	struct task_struct *group_leader = current->group_leader;
L
Linus Torvalds 已提交
1227 1228 1229
	struct pid *pid;
	int err = -EPERM;

I
Ingo Molnar 已提交
1230
	mutex_lock(&tty_mutex);
L
Linus Torvalds 已提交
1231 1232
	write_lock_irq(&tasklist_lock);

1233
	pid = find_pid(PIDTYPE_PGID, group_leader->pid);
L
Linus Torvalds 已提交
1234 1235 1236
	if (pid)
		goto out;

1237 1238 1239 1240 1241
	group_leader->signal->leader = 1;
	__set_special_pids(group_leader->pid, group_leader->pid);
	group_leader->signal->tty = NULL;
	group_leader->signal->tty_old_pgrp = 0;
	err = process_group(group_leader);
L
Linus Torvalds 已提交
1242 1243
out:
	write_unlock_irq(&tasklist_lock);
I
Ingo Molnar 已提交
1244
	mutex_unlock(&tty_mutex);
L
Linus Torvalds 已提交
1245 1246 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 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345
	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);

	if (gidsetsize <= NGROUPS_SMALL) {
		group_info->blocks[0] = group_info->small_block;
	} else {
		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)
 {
	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;
}

1346
/* a simple Shell sort */
L
Linus Torvalds 已提交
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 1373 1374 1375
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 */
1376
int groups_search(struct group_info *group_info, gid_t grp)
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 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 1428 1429 1430 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 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513
{
	int left, right;

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
		int mid = (left+right)/2;
		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 */
	get_group_info(current->group_info);
	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:
	put_group_info(current->group_info);
	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;
	if (grp != current->fsgid) {
		get_group_info(current->group_info);
		retval = groups_search(current->group_info, grp);
		put_group_info(current->group_info);
	}
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	int retval = 1;
	if (grp != current->egid) {
		get_group_info(current->group_info);
		retval = groups_search(current->group_info, grp);
		put_group_info(current->group_info);
	}
	return retval;
}

EXPORT_SYMBOL(in_egroup_p);

DECLARE_RWSEM(uts_sem);

1514 1515
EXPORT_SYMBOL(uts_sem);

L
Linus Torvalds 已提交
1516 1517 1518 1519 1520 1521 1522 1523 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 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 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632
asmlinkage long sys_newuname(struct new_utsname __user * name)
{
	int errno = 0;

	down_read(&uts_sem);
	if (copy_to_user(name,&system_utsname,sizeof *name))
		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)) {
		memcpy(system_utsname.nodename, tmp, len);
		system_utsname.nodename[len] = 0;
		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);
	i = 1 + strlen(system_utsname.nodename);
	if (i > len)
		i = len;
	errno = 0;
	if (copy_to_user(name, system_utsname.nodename, i))
		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)) {
		memcpy(system_utsname.domainname, tmp, len);
		system_utsname.domainname[len] = 0;
		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);
	if(x.rlim_cur > 0x7FFFFFFF)
		x.rlim_cur = 0x7FFFFFFF;
	if(x.rlim_max > 0x7FFFFFFF)
		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
1633
	unsigned long it_prof_secs;
L
Linus Torvalds 已提交
1634 1635 1636 1637
	int retval;

	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
A
Andrew Morton 已提交
1638
	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
L
Linus Torvalds 已提交
1639
		return -EFAULT;
A
Andrew Morton 已提交
1640 1641
	if (new_rlim.rlim_cur > new_rlim.rlim_max)
		return -EINVAL;
L
Linus Torvalds 已提交
1642 1643 1644 1645 1646
	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
1647
		return -EPERM;
L
Linus Torvalds 已提交
1648 1649 1650 1651 1652 1653 1654 1655 1656

	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
1657 1658 1659 1660 1661 1662 1663
	if (resource != RLIMIT_CPU)
		goto out;
	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) {
L
Linus Torvalds 已提交
1664
		cputime_t cputime = secs_to_cputime(new_rlim.rlim_cur);
A
Andrew Morton 已提交
1665

L
Linus Torvalds 已提交
1666 1667
		read_lock(&tasklist_lock);
		spin_lock_irq(&current->sighand->siglock);
A
Andrew Morton 已提交
1668
		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
L
Linus Torvalds 已提交
1669 1670 1671
		spin_unlock_irq(&current->sighand->siglock);
		read_unlock(&tasklist_lock);
	}
A
Andrew Morton 已提交
1672
out:
L
Linus Torvalds 已提交
1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690
	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.
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709
 *
 * tasklist_lock locking optimisation:
 * If we are current and single threaded, we do not need to take the tasklist
 * lock or the siglock.  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 the tasklist_lock, the signal-> fields could be read
 * out of order while another thread was just exiting. So we 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.
 *
 * We don't really need the siglock when we access the non c* fields
 * of the signal_struct (for RUSAGE_SELF) even in multithreaded
 * case, since we take the tasklist lock for read and the non c* signal->
 * fields are updated only in __exit_signal, which is called with
 * tasklist_lock taken for write, hence these two threads cannot execute
 * concurrently.
 *
L
Linus Torvalds 已提交
1710 1711 1712 1713 1714 1715 1716
 */

static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
	struct task_struct *t;
	unsigned long flags;
	cputime_t utime, stime;
1717
	int need_lock = 0;
L
Linus Torvalds 已提交
1718 1719

	memset((char *) r, 0, sizeof *r);
1720
	utime = stime = cputime_zero;
L
Linus Torvalds 已提交
1721

1722 1723
	if (p != current || !thread_group_empty(p))
		need_lock = 1;
L
Linus Torvalds 已提交
1724

1725 1726 1727 1728 1729 1730 1731 1732 1733
	if (need_lock) {
		read_lock(&tasklist_lock);
		if (unlikely(!p->signal)) {
			read_unlock(&tasklist_lock);
			return;
		}
	} else
		/* See locking comments above */
		smp_rmb();
O
Oleg Nesterov 已提交
1734

L
Linus Torvalds 已提交
1735
	switch (who) {
O
Oleg Nesterov 已提交
1736
		case RUSAGE_BOTH:
L
Linus Torvalds 已提交
1737 1738 1739 1740 1741 1742 1743 1744 1745
		case RUSAGE_CHILDREN:
			spin_lock_irqsave(&p->sighand->siglock, flags);
			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;
			spin_unlock_irqrestore(&p->sighand->siglock, flags);
O
Oleg Nesterov 已提交
1746 1747 1748 1749

			if (who == RUSAGE_CHILDREN)
				break;

L
Linus Torvalds 已提交
1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
		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
1768

L
Linus Torvalds 已提交
1769 1770 1771
		default:
			BUG();
	}
O
Oleg Nesterov 已提交
1772

1773 1774
	if (need_lock)
		read_unlock(&tasklist_lock);
O
Oleg Nesterov 已提交
1775 1776
	cputime_to_timeval(utime, &r->ru_utime);
	cputime_to_timeval(stime, &r->ru_stime);
L
Linus Torvalds 已提交
1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809
}

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:
1810
			if (!valid_signal(arg2)) {
L
Linus Torvalds 已提交
1811 1812 1813
				error = -EINVAL;
				break;
			}
1814
			current->pdeath_signal = arg2;
L
Linus Torvalds 已提交
1815 1816 1817 1818 1819
			break;
		case PR_GET_PDEATHSIG:
			error = put_user(current->pdeath_signal, (int __user *)arg2);
			break;
		case PR_GET_DUMPABLE:
1820
			error = current->mm->dumpable;
L
Linus Torvalds 已提交
1821 1822
			break;
		case PR_SET_DUMPABLE:
A
Alan Cox 已提交
1823
			if (arg2 < 0 || arg2 > 2) {
L
Linus Torvalds 已提交
1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 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 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894
				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;
		}
		default:
			error = -EINVAL;
			break;
	}
	return error;
}