sys.c 42 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 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 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 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 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 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 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 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 1373 1374 1375 1376 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 1514 1515 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 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 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 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 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
/*
 *  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>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.h>
#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>
#include <linux/signal.h>
#include <linux/cn_proc.h>
#include <linux/getcpu.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/seccomp.h>
#include <linux/cpu.h>
#include <linux/ptrace.h>

#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>

#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
#ifndef GET_ENDIAN
# define GET_ENDIAN(a,b)	(-EINVAL)
#endif
#ifndef SET_ENDIAN
# define SET_ENDIAN(a,b)	(-EINVAL)
#endif
#ifndef GET_TSC_CTL
# define GET_TSC_CTL(a)		(-EINVAL)
#endif
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a)		(-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;
struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);

/*
 * If set, this is used for preparing the system to power off.
 */

void (*pm_power_off_prepare)(void);

/*
 * set the priority of a task
 * - the caller must hold the RCU read lock
 */
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
	const struct cred *cred = current_cred(), *pcred = __task_cred(p);
	int no_nice;

	if (pcred->uid  != cred->euid &&
	    pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
		error = -EPERM;
		goto out;
	}
	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
		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;
}

SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
{
	struct task_struct *g, *p;
	struct user_struct *user;
	const struct cred *cred = current_cred();
	int error = -EINVAL;
	struct pid *pgrp;

	if (which > PRIO_USER || which < PRIO_PROCESS)
		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)
				p = find_task_by_vpid(who);
			else
				p = current;
			if (p)
				error = set_one_prio(p, niceval, error);
			break;
		case PRIO_PGRP:
			if (who)
				pgrp = find_vpid(who);
			else
				pgrp = task_pgrp(current);
			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
				error = set_one_prio(p, niceval, error);
			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = (struct user_struct *) cred->user;
			if (!who)
				who = cred->uid;
			else if ((who != cred->uid) &&
				 !(user = find_user(who)))
				goto out_unlock;	/* No processes for this user */

			do_each_thread(g, p)
				if (__task_cred(p)->uid == who)
					error = set_one_prio(p, niceval, error);
			while_each_thread(g, p);
			if (who != cred->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.
 */
SYSCALL_DEFINE2(getpriority, int, which, int, who)
{
	struct task_struct *g, *p;
	struct user_struct *user;
	const struct cred *cred = current_cred();
	long niceval, retval = -ESRCH;
	struct pid *pgrp;

	if (which > PRIO_USER || which < PRIO_PROCESS)
		return -EINVAL;

	read_lock(&tasklist_lock);
	switch (which) {
		case PRIO_PROCESS:
			if (who)
				p = find_task_by_vpid(who);
			else
				p = current;
			if (p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			}
			break;
		case PRIO_PGRP:
			if (who)
				pgrp = find_vpid(who);
			else
				pgrp = task_pgrp(current);
			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
				niceval = 20 - task_nice(p);
				if (niceval > retval)
					retval = niceval;
			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
			break;
		case PRIO_USER:
			user = (struct user_struct *) cred->user;
			if (!who)
				who = cred->uid;
			else if ((who != cred->uid) &&
				 !(user = find_user(who)))
				goto out_unlock;	/* No processes for this user */

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

	return retval;
}

/**
 *	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.
 */
void emergency_restart(void)
{
	machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);

void kernel_restart_prepare(char *cmd)
{
	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
	system_state = SYSTEM_RESTART;
	device_shutdown();
	sysdev_shutdown();
}

/**
 *	kernel_restart - reboot the system
 *	@cmd: pointer to buffer containing command to execute for restart
 *		or %NULL
 *
 *	Shutdown everything and perform a clean reboot.
 *	This is not safe to call in interrupt context.
 */
void kernel_restart(char *cmd)
{
	kernel_restart_prepare(cmd);
	if (!cmd)
		printk(KERN_EMERG "Restarting system.\n");
	else
		printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
	machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);

static void kernel_shutdown_prepare(enum system_states state)
{
	blocking_notifier_call_chain(&reboot_notifier_list,
		(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
	system_state = state;
	device_shutdown();
}
/**
 *	kernel_halt - halt the system
 *
 *	Shutdown everything and perform a clean system halt.
 */
void kernel_halt(void)
{
	kernel_shutdown_prepare(SYSTEM_HALT);
	sysdev_shutdown();
	printk(KERN_EMERG "System halted.\n");
	machine_halt();
}

EXPORT_SYMBOL_GPL(kernel_halt);

/**
 *	kernel_power_off - power_off the system
 *
 *	Shutdown everything and perform a clean system power_off.
 */
void kernel_power_off(void)
{
	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
	if (pm_power_off_prepare)
		pm_power_off_prepare();
	disable_nonboot_cpus();
	sysdev_shutdown();
	printk(KERN_EMERG "Power down.\n");
	machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
/*
 * 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.
 */
SYSCALL_DEFINE4(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;

	/* 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;

	lock_kernel();
	switch (cmd) {
	case LINUX_REBOOT_CMD_RESTART:
		kernel_restart(NULL);
		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:
		kernel_halt();
		unlock_kernel();
		do_exit(0);
		break;

	case LINUX_REBOOT_CMD_POWER_OFF:
		kernel_power_off();
		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';

		kernel_restart(buffer);
		break;

#ifdef CONFIG_KEXEC
	case LINUX_REBOOT_CMD_KEXEC:
		{
			int ret;
			ret = kernel_kexec();
			unlock_kernel();
			return ret;
		}
#endif

#ifdef CONFIG_HIBERNATION
	case LINUX_REBOOT_CMD_SW_SUSPEND:
		{
			int ret = hibernate();
			unlock_kernel();
			return ret;
		}
#endif

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

static void deferred_cad(struct work_struct *dummy)
{
	kernel_restart(NULL);
}

/*
 * 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);

	if (C_A_D)
		schedule_work(&cad_work);
	else
		kill_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).
 */
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;
	old = current_cred();

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

	retval = -EPERM;
	if (rgid != (gid_t) -1) {
		if (old->gid == rgid ||
		    old->egid == rgid ||
		    capable(CAP_SETGID))
			new->gid = rgid;
		else
			goto error;
	}
	if (egid != (gid_t) -1) {
		if (old->gid == egid ||
		    old->egid == egid ||
		    old->sgid == egid ||
		    capable(CAP_SETGID))
			new->egid = egid;
		else
			goto error;
	}

	if (rgid != (gid_t) -1 ||
	    (egid != (gid_t) -1 && egid != old->gid))
		new->sgid = new->egid;
	new->fsgid = new->egid;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}

/*
 * setgid() is implemented like SysV w/ SAVED_IDS 
 *
 * SMP: Same implicit races as above.
 */
SYSCALL_DEFINE1(setgid, gid_t, gid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;
	old = current_cred();

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

	retval = -EPERM;
	if (capable(CAP_SETGID))
		new->gid = new->egid = new->sgid = new->fsgid = gid;
	else if (gid == old->gid || gid == old->sgid)
		new->egid = new->fsgid = gid;
	else
		goto error;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}

/*
 * change the user struct in a credentials set to match the new UID
 */
static int set_user(struct cred *new)
{
	struct user_struct *new_user;

	new_user = alloc_uid(current_user_ns(), new->uid);
	if (!new_user)
		return -EAGAIN;

	if (!task_can_switch_user(new_user, current)) {
		free_uid(new_user);
		return -EINVAL;
	}

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

	free_uid(new->user);
	new->user = new_user;
	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. 
 */
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;
	old = current_cred();

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

	retval = -EPERM;
	if (ruid != (uid_t) -1) {
		new->uid = ruid;
		if (old->uid != ruid &&
		    old->euid != ruid &&
		    !capable(CAP_SETUID))
			goto error;
	}

	if (euid != (uid_t) -1) {
		new->euid = euid;
		if (old->uid != euid &&
		    old->euid != euid &&
		    old->suid != euid &&
		    !capable(CAP_SETUID))
			goto error;
	}

	if (new->uid != old->uid) {
		retval = set_user(new);
		if (retval < 0)
			goto error;
	}
	if (ruid != (uid_t) -1 ||
	    (euid != (uid_t) -1 && euid != old->uid))
		new->suid = new->euid;
	new->fsuid = new->euid;

	retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
	if (retval < 0)
		goto error;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}
		
/*
 * 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.  
 */
SYSCALL_DEFINE1(setuid, uid_t, uid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;
	old = current_cred();

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

	retval = -EPERM;
	if (capable(CAP_SETUID)) {
		new->suid = new->uid = uid;
		if (uid != old->uid) {
			retval = set_user(new);
			if (retval < 0)
				goto error;
		}
	} else if (uid != old->uid && uid != new->suid) {
		goto error;
	}

	new->fsuid = new->euid = uid;

	retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
	if (retval < 0)
		goto error;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}


/*
 * This function implements a generic ability to update ruid, euid,
 * and suid.  This allows you to implement the 4.4 compatible seteuid().
 */
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;

	retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
	if (retval)
		goto error;
	old = current_cred();

	retval = -EPERM;
	if (!capable(CAP_SETUID)) {
		if (ruid != (uid_t) -1 && ruid != old->uid &&
		    ruid != old->euid  && ruid != old->suid)
			goto error;
		if (euid != (uid_t) -1 && euid != old->uid &&
		    euid != old->euid  && euid != old->suid)
			goto error;
		if (suid != (uid_t) -1 && suid != old->uid &&
		    suid != old->euid  && suid != old->suid)
			goto error;
	}

	if (ruid != (uid_t) -1) {
		new->uid = ruid;
		if (ruid != old->uid) {
			retval = set_user(new);
			if (retval < 0)
				goto error;
		}
	}
	if (euid != (uid_t) -1)
		new->euid = euid;
	if (suid != (uid_t) -1)
		new->suid = suid;
	new->fsuid = new->euid;

	retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
	if (retval < 0)
		goto error;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}

SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
{
	const struct cred *cred = current_cred();
	int retval;

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

	return retval;
}

/*
 * Same as above, but for rgid, egid, sgid.
 */
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
{
	const struct cred *old;
	struct cred *new;
	int retval;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;
	old = current_cred();

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

	retval = -EPERM;
	if (!capable(CAP_SETGID)) {
		if (rgid != (gid_t) -1 && rgid != old->gid &&
		    rgid != old->egid  && rgid != old->sgid)
			goto error;
		if (egid != (gid_t) -1 && egid != old->gid &&
		    egid != old->egid  && egid != old->sgid)
			goto error;
		if (sgid != (gid_t) -1 && sgid != old->gid &&
		    sgid != old->egid  && sgid != old->sgid)
			goto error;
	}

	if (rgid != (gid_t) -1)
		new->gid = rgid;
	if (egid != (gid_t) -1)
		new->egid = egid;
	if (sgid != (gid_t) -1)
		new->sgid = sgid;
	new->fsgid = new->egid;

	return commit_creds(new);

error:
	abort_creds(new);
	return retval;
}

SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
{
	const struct cred *cred = current_cred();
	int retval;

	if (!(retval   = put_user(cred->gid,  rgid)) &&
	    !(retval   = put_user(cred->egid, egid)))
		retval = put_user(cred->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..
 */
SYSCALL_DEFINE1(setfsuid, uid_t, uid)
{
	const struct cred *old;
	struct cred *new;
	uid_t old_fsuid;

	new = prepare_creds();
	if (!new)
		return current_fsuid();
	old = current_cred();
	old_fsuid = old->fsuid;

	if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
		goto error;

	if (uid == old->uid  || uid == old->euid  ||
	    uid == old->suid || uid == old->fsuid ||
	    capable(CAP_SETUID)) {
		if (uid != old_fsuid) {
			new->fsuid = uid;
			if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
				goto change_okay;
		}
	}

error:
	abort_creds(new);
	return old_fsuid;

change_okay:
	commit_creds(new);
	return old_fsuid;
}

/*
 * Samma på svenska..
 */
SYSCALL_DEFINE1(setfsgid, gid_t, gid)
{
	const struct cred *old;
	struct cred *new;
	gid_t old_fsgid;

	new = prepare_creds();
	if (!new)
		return current_fsgid();
	old = current_cred();
	old_fsgid = old->fsgid;

	if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
		goto error;

	if (gid == old->gid  || gid == old->egid  ||
	    gid == old->sgid || gid == old->fsgid ||
	    capable(CAP_SETGID)) {
		if (gid != old_fsgid) {
			new->fsgid = gid;
			goto change_okay;
		}
	}

error:
	abort_creds(new);
	return old_fsgid;

change_okay:
	commit_creds(new);
	return old_fsgid;
}

void do_sys_times(struct tms *tms)
{
	struct task_cputime cputime;
	cputime_t cutime, cstime;

	thread_group_cputime(current, &cputime);
	spin_lock_irq(&current->sighand->siglock);
	cutime = current->signal->cutime;
	cstime = current->signal->cstime;
	spin_unlock_irq(&current->sighand->siglock);
	tms->tms_utime = cputime_to_clock_t(cputime.utime);
	tms->tms_stime = cputime_to_clock_t(cputime.stime);
	tms->tms_cutime = cputime_to_clock_t(cutime);
	tms->tms_cstime = cputime_to_clock_t(cstime);
}

SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
{
	if (tbuf) {
		struct tms tmp;

		do_sys_times(&tmp);
		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
			return -EFAULT;
	}
	force_successful_syscall_return();
	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
 */
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
{
	struct task_struct *p;
	struct task_struct *group_leader = current->group_leader;
	struct pid *pgrp;
	int err;

	if (!pid)
		pid = task_pid_vnr(group_leader);
	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_vpid(pid);
	if (!p)
		goto out;

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

	if (same_thread_group(p->real_parent, group_leader)) {
		err = -EPERM;
		if (task_session(p) != task_session(group_leader))
			goto out;
		err = -EACCES;
		if (p->did_exec)
			goto out;
	} else {
		err = -ESRCH;
		if (p != group_leader)
			goto out;
	}

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

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

		pgrp = find_vpid(pgid);
		g = pid_task(pgrp, PIDTYPE_PGID);
		if (!g || task_session(g) != task_session(group_leader))
			goto out;
	}

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

	if (task_pgrp(p) != pgrp) {
		change_pid(p, PIDTYPE_PGID, pgrp);
		set_task_pgrp(p, pid_nr(pgrp));
	}

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

SYSCALL_DEFINE1(getpgid, pid_t, pid)
{
	struct task_struct *p;
	struct pid *grp;
	int retval;

	rcu_read_lock();
	if (!pid)
		grp = task_pgrp(current);
	else {
		retval = -ESRCH;
		p = find_task_by_vpid(pid);
		if (!p)
			goto out;
		grp = task_pgrp(p);
		if (!grp)
			goto out;

		retval = security_task_getpgid(p);
		if (retval)
			goto out;
	}
	retval = pid_vnr(grp);
out:
	rcu_read_unlock();
	return retval;
}

#ifdef __ARCH_WANT_SYS_GETPGRP

SYSCALL_DEFINE0(getpgrp)
{
	return sys_getpgid(0);
}

#endif

SYSCALL_DEFINE1(getsid, pid_t, pid)
{
	struct task_struct *p;
	struct pid *sid;
	int retval;

	rcu_read_lock();
	if (!pid)
		sid = task_session(current);
	else {
		retval = -ESRCH;
		p = find_task_by_vpid(pid);
		if (!p)
			goto out;
		sid = task_session(p);
		if (!sid)
			goto out;

		retval = security_task_getsid(p);
		if (retval)
			goto out;
	}
	retval = pid_vnr(sid);
out:
	rcu_read_unlock();
	return retval;
}

SYSCALL_DEFINE0(setsid)
{
	struct task_struct *group_leader = current->group_leader;
	struct pid *sid = task_pid(group_leader);
	pid_t session = pid_vnr(sid);
	int err = -EPERM;

	write_lock_irq(&tasklist_lock);
	/* Fail if I am already a session leader */
	if (group_leader->signal->leader)
		goto out;

	/* Fail if a process group id already exists that equals the
	 * proposed session id.
	 */
	if (pid_task(sid, PIDTYPE_PGID))
		goto out;

	group_leader->signal->leader = 1;
	__set_special_pids(sid);

	proc_clear_tty(group_leader);

	err = session;
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);

	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,
			  const struct group_info *group_info)
{
	int i;
	unsigned int count = group_info->ngroups;

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

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

		grouplist += NGROUPS_PER_BLOCK;
		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;
	unsigned int count = group_info->ngroups;

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

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

		grouplist += NGROUPS_PER_BLOCK;
		count -= cp_count;
	}
	return 0;
}

/* a simple Shell sort */
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 */
int groups_search(const struct group_info *group_info, gid_t grp)
{
	unsigned int left, right;

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
		unsigned 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;
}

/**
 * set_groups - Change a group subscription in a set of credentials
 * @new: The newly prepared set of credentials to alter
 * @group_info: The group list to install
 *
 * Validate a group subscription and, if valid, insert it into a set
 * of credentials.
 */
int set_groups(struct cred *new, struct group_info *group_info)
{
	int retval;

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

	put_group_info(new->group_info);
	groups_sort(group_info);
	get_group_info(group_info);
	new->group_info = group_info;
	return 0;
}

EXPORT_SYMBOL(set_groups);

/**
 * set_current_groups - Change current's group subscription
 * @group_info: The group list to impose
 *
 * Validate a group subscription and, if valid, impose it upon current's task
 * security record.
 */
int set_current_groups(struct group_info *group_info)
{
	struct cred *new;
	int ret;

	new = prepare_creds();
	if (!new)
		return -ENOMEM;

	ret = set_groups(new, group_info);
	if (ret < 0) {
		abort_creds(new);
		return ret;
	}

	return commit_creds(new);
}

EXPORT_SYMBOL(set_current_groups);

SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
{
	const struct cred *cred = current_cred();
	int i;

	if (gidsetsize < 0)
		return -EINVAL;

	/* no need to grab task_lock here; it cannot change */
	i = cred->group_info->ngroups;
	if (gidsetsize) {
		if (i > gidsetsize) {
			i = -EINVAL;
			goto out;
		}
		if (groups_to_user(grouplist, cred->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.
 */
 
SYSCALL_DEFINE2(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)
{
	const struct cred *cred = current_cred();
	int retval = 1;

	if (grp != cred->fsgid)
		retval = groups_search(cred->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	const struct cred *cred = current_cred();
	int retval = 1;

	if (grp != cred->egid)
		retval = groups_search(cred->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_egroup_p);

DECLARE_RWSEM(uts_sem);

SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
{
	int errno = 0;

	down_read(&uts_sem);
	if (copy_to_user(name, utsname(), sizeof *name))
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

SYSCALL_DEFINE2(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)) {
		struct new_utsname *u = utsname();

		memcpy(u->nodename, tmp, len);
		memset(u->nodename + len, 0, sizeof(u->nodename) - len);
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

#ifdef __ARCH_WANT_SYS_GETHOSTNAME

SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
{
	int i, errno;
	struct new_utsname *u;

	if (len < 0)
		return -EINVAL;
	down_read(&uts_sem);
	u = utsname();
	i = 1 + strlen(u->nodename);
	if (i > len)
		i = len;
	errno = 0;
	if (copy_to_user(name, u->nodename, i))
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

#endif

/*
 * Only setdomainname; getdomainname can be implemented by calling
 * uname()
 */
SYSCALL_DEFINE2(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)) {
		struct new_utsname *u = utsname();

		memcpy(u->domainname, tmp, len);
		memset(u->domainname + len, 0, sizeof(u->domainname) - len);
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

SYSCALL_DEFINE2(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.
 */
 
SYSCALL_DEFINE2(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

SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
{
	struct rlimit new_rlim, *old_rlim;
	int retval;

	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
		return -EFAULT;
	if (new_rlim.rlim_cur > new_rlim.rlim_max)
		return -EINVAL;
	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 > sysctl_nr_open)
		return -EPERM;

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

	if (resource == RLIMIT_CPU && new_rlim.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
		 */
		new_rlim.rlim_cur = 1;
	}

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

	if (resource != RLIMIT_CPU)
		goto out;

	/*
	 * 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
	 */
	if (new_rlim.rlim_cur == RLIM_INFINITY)
		goto out;

	update_rlimit_cpu(new_rlim.rlim_cur);
out:
	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.
 *
 * 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.
 *
 */

static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
{
	r->ru_nvcsw += t->nvcsw;
	r->ru_nivcsw += t->nivcsw;
	r->ru_minflt += t->min_flt;
	r->ru_majflt += t->maj_flt;
	r->ru_inblock += task_io_get_inblock(t);
	r->ru_oublock += task_io_get_oublock(t);
}

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

	memset((char *) r, 0, sizeof *r);
	utime = stime = cputime_zero;

	if (who == RUSAGE_THREAD) {
		utime = task_utime(current);
		stime = task_stime(current);
		accumulate_thread_rusage(p, r);
		goto out;
	}

	if (!lock_task_sighand(p, &flags))
		return;

	switch (who) {
		case RUSAGE_BOTH:
		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;
			r->ru_inblock = p->signal->cinblock;
			r->ru_oublock = p->signal->coublock;

			if (who == RUSAGE_CHILDREN)
				break;

		case RUSAGE_SELF:
			thread_group_cputime(p, &cputime);
			utime = cputime_add(utime, cputime.utime);
			stime = cputime_add(stime, cputime.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;
			r->ru_inblock += p->signal->inblock;
			r->ru_oublock += p->signal->oublock;
			t = p;
			do {
				accumulate_thread_rusage(t, r);
				t = next_thread(t);
			} while (t != p);
			break;

		default:
			BUG();
	}
	unlock_task_sighand(p, &flags);

out:
	cputime_to_timeval(utime, &r->ru_utime);
	cputime_to_timeval(stime, &r->ru_stime);
}

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;
}

SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
{
	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
	    who != RUSAGE_THREAD)
		return -EINVAL;
	return getrusage(current, who, ru);
}

SYSCALL_DEFINE1(umask, int, mask)
{
	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
	return mask;
}

SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
		unsigned long, arg4, unsigned long, arg5)
{
	struct task_struct *me = current;
	unsigned char comm[sizeof(me->comm)];
	long error;

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

	error = 0;
	switch (option) {
		case PR_SET_PDEATHSIG:
			if (!valid_signal(arg2)) {
				error = -EINVAL;
				break;
			}
			me->pdeath_signal = arg2;
			error = 0;
			break;
		case PR_GET_PDEATHSIG:
			error = put_user(me->pdeath_signal, (int __user *)arg2);
			break;
		case PR_GET_DUMPABLE:
			error = get_dumpable(me->mm);
			break;
		case PR_SET_DUMPABLE:
			if (arg2 < 0 || arg2 > 1) {
				error = -EINVAL;
				break;
			}
			set_dumpable(me->mm, arg2);
			error = 0;
			break;

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

		case PR_SET_NAME:
			comm[sizeof(me->comm)-1] = 0;
			if (strncpy_from_user(comm, (char __user *)arg2,
					      sizeof(me->comm) - 1) < 0)
				return -EFAULT;
			set_task_comm(me, comm);
			return 0;
		case PR_GET_NAME:
			get_task_comm(comm, me);
			if (copy_to_user((char __user *)arg2, comm,
					 sizeof(comm)))
				return -EFAULT;
			return 0;
		case PR_GET_ENDIAN:
			error = GET_ENDIAN(me, arg2);
			break;
		case PR_SET_ENDIAN:
			error = SET_ENDIAN(me, arg2);
			break;

		case PR_GET_SECCOMP:
			error = prctl_get_seccomp();
			break;
		case PR_SET_SECCOMP:
			error = prctl_set_seccomp(arg2);
			break;
		case PR_GET_TSC:
			error = GET_TSC_CTL(arg2);
			break;
		case PR_SET_TSC:
			error = SET_TSC_CTL(arg2);
			break;
		case PR_GET_TIMERSLACK:
			error = current->timer_slack_ns;
			break;
		case PR_SET_TIMERSLACK:
			if (arg2 <= 0)
				current->timer_slack_ns =
					current->default_timer_slack_ns;
			else
				current->timer_slack_ns = arg2;
			error = 0;
			break;
		default:
			error = -EINVAL;
			break;
	}
	return error;
}

SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
		struct getcpu_cache __user *, unused)
{
	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);
	return err ? -EFAULT : 0;
}

char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";

static void argv_cleanup(char **argv, char **envp)
{
	argv_free(argv);
}

/**
 * orderly_poweroff - Trigger an orderly system poweroff
 * @force: force poweroff if command execution fails
 *
 * This may be called from any context to trigger a system shutdown.
 * If the orderly shutdown fails, it will force an immediate shutdown.
 */
int orderly_poweroff(bool force)
{
	int argc;
	char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
	static char *envp[] = {
		"HOME=/",
		"PATH=/sbin:/bin:/usr/sbin:/usr/bin",
		NULL
	};
	int ret = -ENOMEM;
	struct subprocess_info *info;

	if (argv == NULL) {
		printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
		       __func__, poweroff_cmd);
		goto out;
	}

	info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
	if (info == NULL) {
		argv_free(argv);
		goto out;
	}

	call_usermodehelper_setcleanup(info, argv_cleanup);

	ret = call_usermodehelper_exec(info, UMH_NO_WAIT);

  out:
	if (ret && force) {
		printk(KERN_WARNING "Failed to start orderly shutdown: "
		       "forcing the issue\n");

		/* I guess this should try to kick off some daemon to
		   sync and poweroff asap.  Or not even bother syncing
		   if we're doing an emergency shutdown? */
		emergency_sync();
		kernel_power_off();
	}

	return ret;
}
EXPORT_SYMBOL_GPL(orderly_poweroff);