mempolicy.c 61.4 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 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438
/*
 * Simple NUMA memory policy for the Linux kernel.
 *
 * Copyright 2003,2004 Andi Kleen, SuSE Labs.
 * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
 * Subject to the GNU Public License, version 2.
 *
 * NUMA policy allows the user to give hints in which node(s) memory should
 * be allocated.
 *
 * Support four policies per VMA and per process:
 *
 * The VMA policy has priority over the process policy for a page fault.
 *
 * interleave     Allocate memory interleaved over a set of nodes,
 *                with normal fallback if it fails.
 *                For VMA based allocations this interleaves based on the
 *                offset into the backing object or offset into the mapping
 *                for anonymous memory. For process policy an process counter
 *                is used.
 *
 * bind           Only allocate memory on a specific set of nodes,
 *                no fallback.
 *                FIXME: memory is allocated starting with the first node
 *                to the last. It would be better if bind would truly restrict
 *                the allocation to memory nodes instead
 *
 * preferred       Try a specific node first before normal fallback.
 *                As a special case node -1 here means do the allocation
 *                on the local CPU. This is normally identical to default,
 *                but useful to set in a VMA when you have a non default
 *                process policy.
 *
 * default        Allocate on the local node first, or when on a VMA
 *                use the process policy. This is what Linux always did
 *		  in a NUMA aware kernel and still does by, ahem, default.
 *
 * The process policy is applied for most non interrupt memory allocations
 * in that process' context. Interrupts ignore the policies and always
 * try to allocate on the local CPU. The VMA policy is only applied for memory
 * allocations for a VMA in the VM.
 *
 * Currently there are a few corner cases in swapping where the policy
 * is not applied, but the majority should be handled. When process policy
 * is used it is not remembered over swap outs/swap ins.
 *
 * Only the highest zone in the zone hierarchy gets policied. Allocations
 * requesting a lower zone just use default policy. This implies that
 * on systems with highmem kernel lowmem allocation don't get policied.
 * Same with GFP_DMA allocations.
 *
 * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
 * all users and remembered even when nobody has memory mapped.
 */

/* Notebook:
   fix mmap readahead to honour policy and enable policy for any page cache
   object
   statistics for bigpages
   global policy for page cache? currently it uses process policy. Requires
   first item above.
   handle mremap for shared memory (currently ignored for the policy)
   grows down?
   make bind policy root only? It can trigger oom much faster and the
   kernel is not always grateful with that.
*/

#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/migrate.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>

#include <asm/tlbflush.h>
#include <asm/uaccess.h>

#include "internal.h"

/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)		/* Gather statistics */

static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
enum zone_type policy_zone = 0;

/*
 * run-time system-wide default policy => local allocation
 */
struct mempolicy default_policy = {
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.mode = MPOL_PREFERRED,
	.flags = MPOL_F_LOCAL,
};

static const struct mempolicy_operations {
	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
	void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
} mpol_ops[MPOL_MAX];

/* Check that the nodemask contains at least one populated zone */
static int is_valid_nodemask(const nodemask_t *nodemask)
{
	int nd, k;

	/* Check that there is something useful in this mask */
	k = policy_zone;

	for_each_node_mask(nd, *nodemask) {
		struct zone *z;

		for (k = 0; k <= policy_zone; k++) {
			z = &NODE_DATA(nd)->node_zones[k];
			if (z->present_pages > 0)
				return 1;
		}
	}

	return 0;
}

static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
	return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
}

static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
				   const nodemask_t *rel)
{
	nodemask_t tmp;
	nodes_fold(tmp, *orig, nodes_weight(*rel));
	nodes_onto(*ret, tmp, *rel);
}

static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (nodes_empty(*nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!nodes)
		pol->flags |= MPOL_F_LOCAL;	/* local allocation */
	else if (nodes_empty(*nodes))
		return -EINVAL;			/*  no allowed nodes */
	else
		pol->v.preferred_node = first_node(*nodes);
	return 0;
}

static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!is_valid_nodemask(nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

/*
 * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
 * any, for the new policy.  mpol_new() has already validated the nodes
 * parameter with respect to the policy mode and flags.  But, we need to
 * handle an empty nodemask with MPOL_PREFERRED here.
 *
 * Must be called holding task's alloc_lock to protect task's mems_allowed
 * and mempolicy.  May also be called holding the mmap_semaphore for write.
 */
static int mpol_set_nodemask(struct mempolicy *pol,
		     const nodemask_t *nodes, struct nodemask_scratch *nsc)
{
	int ret;

	/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
	if (pol == NULL)
		return 0;
	/* Check N_HIGH_MEMORY */
	nodes_and(nsc->mask1,
		  cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]);

	VM_BUG_ON(!nodes);
	if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
		nodes = NULL;	/* explicit local allocation */
	else {
		if (pol->flags & MPOL_F_RELATIVE_NODES)
			mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
		else
			nodes_and(nsc->mask2, *nodes, nsc->mask1);

		if (mpol_store_user_nodemask(pol))
			pol->w.user_nodemask = *nodes;
		else
			pol->w.cpuset_mems_allowed =
						cpuset_current_mems_allowed;
	}

	if (nodes)
		ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
	else
		ret = mpol_ops[pol->mode].create(pol, NULL);
	return ret;
}

/*
 * This function just creates a new policy, does some check and simple
 * initialization. You must invoke mpol_set_nodemask() to set nodes.
 */
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
				  nodemask_t *nodes)
{
	struct mempolicy *policy;

	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);

	if (mode == MPOL_DEFAULT) {
		if (nodes && !nodes_empty(*nodes))
			return ERR_PTR(-EINVAL);
		return NULL;	/* simply delete any existing policy */
	}
	VM_BUG_ON(!nodes);

	/*
	 * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
	 * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
	 * All other modes require a valid pointer to a non-empty nodemask.
	 */
	if (mode == MPOL_PREFERRED) {
		if (nodes_empty(*nodes)) {
			if (((flags & MPOL_F_STATIC_NODES) ||
			     (flags & MPOL_F_RELATIVE_NODES)))
				return ERR_PTR(-EINVAL);
		}
	} else if (nodes_empty(*nodes))
		return ERR_PTR(-EINVAL);
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	policy->mode = mode;
	policy->flags = flags;

	return policy;
}

/* Slow path of a mpol destructor. */
void __mpol_put(struct mempolicy *p)
{
	if (!atomic_dec_and_test(&p->refcnt))
		return;
	kmem_cache_free(policy_cache, p);
}

static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
{
}

static void mpol_rebind_nodemask(struct mempolicy *pol,
				 const nodemask_t *nodes)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES)
		nodes_and(tmp, pol->w.user_nodemask, *nodes);
	else if (pol->flags & MPOL_F_RELATIVE_NODES)
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
	else {
		nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed,
			    *nodes);
		pol->w.cpuset_mems_allowed = *nodes;
	}

	pol->v.nodes = tmp;
	if (!node_isset(current->il_next, tmp)) {
		current->il_next = next_node(current->il_next, tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = first_node(tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = numa_node_id();
	}
}

static void mpol_rebind_preferred(struct mempolicy *pol,
				  const nodemask_t *nodes)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES) {
		int node = first_node(pol->w.user_nodemask);

		if (node_isset(node, *nodes)) {
			pol->v.preferred_node = node;
			pol->flags &= ~MPOL_F_LOCAL;
		} else
			pol->flags |= MPOL_F_LOCAL;
	} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
		pol->v.preferred_node = first_node(tmp);
	} else if (!(pol->flags & MPOL_F_LOCAL)) {
		pol->v.preferred_node = node_remap(pol->v.preferred_node,
						   pol->w.cpuset_mems_allowed,
						   *nodes);
		pol->w.cpuset_mems_allowed = *nodes;
	}
}

/* Migrate a policy to a different set of nodes */
static void mpol_rebind_policy(struct mempolicy *pol,
			       const nodemask_t *newmask)
{
	if (!pol)
		return;
	if (!mpol_store_user_nodemask(pol) &&
	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
		return;
	mpol_ops[pol->mode].rebind(pol, newmask);
}

/*
 * Wrapper for mpol_rebind_policy() that just requires task
 * pointer, and updates task mempolicy.
 *
 * Called with task's alloc_lock held.
 */

void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
{
	mpol_rebind_policy(tsk->mempolicy, new);
}

/*
 * Rebind each vma in mm to new nodemask.
 *
 * Call holding a reference to mm.  Takes mm->mmap_sem during call.
 */

void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
	struct vm_area_struct *vma;

	down_write(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next)
		mpol_rebind_policy(vma->vm_policy, new);
	up_write(&mm->mmap_sem);
}

static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
	[MPOL_DEFAULT] = {
		.rebind = mpol_rebind_default,
	},
	[MPOL_INTERLEAVE] = {
		.create = mpol_new_interleave,
		.rebind = mpol_rebind_nodemask,
	},
	[MPOL_PREFERRED] = {
		.create = mpol_new_preferred,
		.rebind = mpol_rebind_preferred,
	},
	[MPOL_BIND] = {
		.create = mpol_new_bind,
		.rebind = mpol_rebind_nodemask,
	},
};

static void gather_stats(struct page *, void *, int pte_dirty);
static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags);

/* Scan through pages checking if pages follow certain conditions. */
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pte_t *orig_pte;
	pte_t *pte;
	spinlock_t *ptl;

	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	do {
		struct page *page;
		int nid;

		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, addr, *pte);
		if (!page)
			continue;
		/*
		 * The check for PageReserved here is important to avoid
		 * handling zero pages and other pages that may have been
		 * marked special by the system.
		 *
		 * If the PageReserved would not be checked here then f.e.
		 * the location of the zero page could have an influence
		 * on MPOL_MF_STRICT, zero pages would be counted for
		 * the per node stats, and there would be useless attempts
		 * to put zero pages on the migration list.
		 */
		if (PageReserved(page))
			continue;
		nid = page_to_nid(page);
		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
			continue;

		if (flags & MPOL_MF_STATS)
			gather_stats(page, private, pte_dirty(*pte));
		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
			migrate_page_add(page, private, flags);
		else
			break;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap_unlock(orig_pte, ptl);
	return addr != end;
}

static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		if (check_pte_range(vma, pmd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		if (check_pmd_range(vma, pud, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static inline int check_pgd_range(struct vm_area_struct *vma,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pgd_t *pgd;
	unsigned long next;

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (check_pud_range(vma, pgd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

/*
 * Check if all pages in a range are on a set of nodes.
 * If pagelist != NULL then isolate pages from the LRU and
 * put them on the pagelist.
 */
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
		const nodemask_t *nodes, unsigned long flags, void *private)
{
	int err;
	struct vm_area_struct *first, *vma, *prev;


	first = find_vma(mm, start);
	if (!first)
		return ERR_PTR(-EFAULT);
	prev = NULL;
	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
			if (!vma->vm_next && vma->vm_end < end)
				return ERR_PTR(-EFAULT);
			if (prev && prev->vm_end < vma->vm_start)
				return ERR_PTR(-EFAULT);
		}
		if (!is_vm_hugetlb_page(vma) &&
		    ((flags & MPOL_MF_STRICT) ||
		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
				vma_migratable(vma)))) {
			unsigned long endvma = vma->vm_end;

			if (endvma > end)
				endvma = end;
			if (vma->vm_start > start)
				start = vma->vm_start;
			err = check_pgd_range(vma, start, endvma, nodes,
						flags, private);
			if (err) {
				first = ERR_PTR(err);
				break;
			}
		}
		prev = vma;
	}
	return first;
}

/* Apply policy to a single VMA */
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
{
	int err = 0;
	struct mempolicy *old = vma->vm_policy;

	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
		 vma->vm_ops, vma->vm_file,
		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);

	if (vma->vm_ops && vma->vm_ops->set_policy)
		err = vma->vm_ops->set_policy(vma, new);
	if (!err) {
		mpol_get(new);
		vma->vm_policy = new;
		mpol_put(old);
	}
	return err;
}

/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
		       unsigned long end, struct mempolicy *new)
{
	struct vm_area_struct *next;
	int err;

	err = 0;
	for (; vma && vma->vm_start < end; vma = next) {
		next = vma->vm_next;
		if (vma->vm_start < start)
			err = split_vma(vma->vm_mm, vma, start, 1);
		if (!err && vma->vm_end > end)
			err = split_vma(vma->vm_mm, vma, end, 0);
		if (!err)
			err = policy_vma(vma, new);
		if (err)
			break;
	}
	return err;
}

/*
 * Update task->flags PF_MEMPOLICY bit: set iff non-default
 * mempolicy.  Allows more rapid checking of this (combined perhaps
 * with other PF_* flag bits) on memory allocation hot code paths.
 *
 * If called from outside this file, the task 'p' should -only- be
 * a newly forked child not yet visible on the task list, because
 * manipulating the task flags of a visible task is not safe.
 *
 * The above limitation is why this routine has the funny name
 * mpol_fix_fork_child_flag().
 *
 * It is also safe to call this with a task pointer of current,
 * which the static wrapper mpol_set_task_struct_flag() does,
 * for use within this file.
 */

void mpol_fix_fork_child_flag(struct task_struct *p)
{
	if (p->mempolicy)
		p->flags |= PF_MEMPOLICY;
	else
		p->flags &= ~PF_MEMPOLICY;
}

static void mpol_set_task_struct_flag(void)
{
	mpol_fix_fork_child_flag(current);
}

/* Set the process memory policy */
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
			     nodemask_t *nodes)
{
	struct mempolicy *new, *old;
	struct mm_struct *mm = current->mm;
	NODEMASK_SCRATCH(scratch);
	int ret;

	if (!scratch)
		return -ENOMEM;

	new = mpol_new(mode, flags, nodes);
	if (IS_ERR(new)) {
		ret = PTR_ERR(new);
		goto out;
	}
	/*
	 * prevent changing our mempolicy while show_numa_maps()
	 * is using it.
	 * Note:  do_set_mempolicy() can be called at init time
	 * with no 'mm'.
	 */
	if (mm)
		down_write(&mm->mmap_sem);
	task_lock(current);
	ret = mpol_set_nodemask(new, nodes, scratch);
	if (ret) {
		task_unlock(current);
		if (mm)
			up_write(&mm->mmap_sem);
		mpol_put(new);
		goto out;
	}
	old = current->mempolicy;
	current->mempolicy = new;
	mpol_set_task_struct_flag();
	if (new && new->mode == MPOL_INTERLEAVE &&
	    nodes_weight(new->v.nodes))
		current->il_next = first_node(new->v.nodes);
	task_unlock(current);
	if (mm)
		up_write(&mm->mmap_sem);

	mpol_put(old);
	ret = 0;
out:
	NODEMASK_SCRATCH_FREE(scratch);
	return ret;
}

/*
 * Return nodemask for policy for get_mempolicy() query
 *
 * Called with task's alloc_lock held
 */
static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
	nodes_clear(*nodes);
	if (p == &default_policy)
		return;

	switch (p->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		*nodes = p->v.nodes;
		break;
	case MPOL_PREFERRED:
		if (!(p->flags & MPOL_F_LOCAL))
			node_set(p->v.preferred_node, *nodes);
		/* else return empty node mask for local allocation */
		break;
	default:
		BUG();
	}
}

static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
	struct page *p;
	int err;

	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
	if (err >= 0) {
		err = page_to_nid(p);
		put_page(p);
	}
	return err;
}

/* Retrieve NUMA policy */
static long do_get_mempolicy(int *policy, nodemask_t *nmask,
			     unsigned long addr, unsigned long flags)
{
	int err;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct mempolicy *pol = current->mempolicy;

	if (flags &
		~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
		return -EINVAL;

	if (flags & MPOL_F_MEMS_ALLOWED) {
		if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
			return -EINVAL;
		*policy = 0;	/* just so it's initialized */
		task_lock(current);
		*nmask  = cpuset_current_mems_allowed;
		task_unlock(current);
		return 0;
	}

	if (flags & MPOL_F_ADDR) {
		/*
		 * Do NOT fall back to task policy if the
		 * vma/shared policy at addr is NULL.  We
		 * want to return MPOL_DEFAULT in this case.
		 */
		down_read(&mm->mmap_sem);
		vma = find_vma_intersection(mm, addr, addr+1);
		if (!vma) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else
			pol = vma->vm_policy;
	} else if (addr)
		return -EINVAL;

	if (!pol)
		pol = &default_policy;	/* indicates default behavior */

	if (flags & MPOL_F_NODE) {
		if (flags & MPOL_F_ADDR) {
			err = lookup_node(mm, addr);
			if (err < 0)
				goto out;
			*policy = err;
		} else if (pol == current->mempolicy &&
				pol->mode == MPOL_INTERLEAVE) {
			*policy = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else {
		*policy = pol == &default_policy ? MPOL_DEFAULT :
						pol->mode;
		/*
		 * Internal mempolicy flags must be masked off before exposing
		 * the policy to userspace.
		 */
		*policy |= (pol->flags & MPOL_MODE_FLAGS);
	}

	if (vma) {
		up_read(&current->mm->mmap_sem);
		vma = NULL;
	}

	err = 0;
	if (nmask) {
		task_lock(current);
		get_policy_nodemask(pol, nmask);
		task_unlock(current);
	}

 out:
	mpol_cond_put(pol);
	if (vma)
		up_read(&current->mm->mmap_sem);
	return err;
}

#ifdef CONFIG_MIGRATION
/*
 * page migration
 */
static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
	/*
	 * Avoid migrating a page that is shared with others.
	 */
	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
		if (!isolate_lru_page(page)) {
			list_add_tail(&page->lru, pagelist);
		}
	}
}

static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
	return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
}

/*
 * Migrate pages from one node to a target node.
 * Returns error or the number of pages not migrated.
 */
static int migrate_to_node(struct mm_struct *mm, int source, int dest,
			   int flags)
{
	nodemask_t nmask;
	LIST_HEAD(pagelist);
	int err = 0;

	nodes_clear(nmask);
	node_set(source, nmask);

	check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask,
			flags | MPOL_MF_DISCONTIG_OK, &pagelist);

	if (!list_empty(&pagelist))
		err = migrate_pages(&pagelist, new_node_page, dest);

	return err;
}

/*
 * Move pages between the two nodesets so as to preserve the physical
 * layout as much as possible.
 *
 * Returns the number of page that could not be moved.
 */
int do_migrate_pages(struct mm_struct *mm,
	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
	int busy = 0;
	int err;
	nodemask_t tmp;

	err = migrate_prep();
	if (err)
		return err;

	down_read(&mm->mmap_sem);

	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
	if (err)
		goto out;

/*
 * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
 * bit in 'to' is not also set in 'tmp'.  Clear the found 'source'
 * bit in 'tmp', and return that <source, dest> pair for migration.
 * The pair of nodemasks 'to' and 'from' define the map.
 *
 * If no pair of bits is found that way, fallback to picking some
 * pair of 'source' and 'dest' bits that are not the same.  If the
 * 'source' and 'dest' bits are the same, this represents a node
 * that will be migrating to itself, so no pages need move.
 *
 * If no bits are left in 'tmp', or if all remaining bits left
 * in 'tmp' correspond to the same bit in 'to', return false
 * (nothing left to migrate).
 *
 * This lets us pick a pair of nodes to migrate between, such that
 * if possible the dest node is not already occupied by some other
 * source node, minimizing the risk of overloading the memory on a
 * node that would happen if we migrated incoming memory to a node
 * before migrating outgoing memory source that same node.
 *
 * A single scan of tmp is sufficient.  As we go, we remember the
 * most recent <s, d> pair that moved (s != d).  If we find a pair
 * that not only moved, but what's better, moved to an empty slot
 * (d is not set in tmp), then we break out then, with that pair.
 * Otherwise when we finish scannng from_tmp, we at least have the
 * most recent <s, d> pair that moved.  If we get all the way through
 * the scan of tmp without finding any node that moved, much less
 * moved to an empty node, then there is nothing left worth migrating.
 */

	tmp = *from_nodes;
	while (!nodes_empty(tmp)) {
		int s,d;
		int source = -1;
		int dest = 0;

		for_each_node_mask(s, tmp) {
			d = node_remap(s, *from_nodes, *to_nodes);
			if (s == d)
				continue;

			source = s;	/* Node moved. Memorize */
			dest = d;

			/* dest not in remaining from nodes? */
			if (!node_isset(dest, tmp))
				break;
		}
		if (source == -1)
			break;

		node_clear(source, tmp);
		err = migrate_to_node(mm, source, dest, flags);
		if (err > 0)
			busy += err;
		if (err < 0)
			break;
	}
out:
	up_read(&mm->mmap_sem);
	if (err < 0)
		return err;
	return busy;

}

/*
 * Allocate a new page for page migration based on vma policy.
 * Start assuming that page is mapped by vma pointed to by @private.
 * Search forward from there, if not.  N.B., this assumes that the
 * list of pages handed to migrate_pages()--which is how we get here--
 * is in virtual address order.
 */
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	struct vm_area_struct *vma = (struct vm_area_struct *)private;
	unsigned long uninitialized_var(address);

	while (vma) {
		address = page_address_in_vma(page, vma);
		if (address != -EFAULT)
			break;
		vma = vma->vm_next;
	}

	/*
	 * if !vma, alloc_page_vma() will use task or system default policy
	 */
	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else

static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
}

int do_migrate_pages(struct mm_struct *mm,
	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
	return -ENOSYS;
}

static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	return NULL;
}
#endif

static long do_mbind(unsigned long start, unsigned long len,
		     unsigned short mode, unsigned short mode_flags,
		     nodemask_t *nmask, unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	struct mempolicy *new;
	unsigned long end;
	int err;
	LIST_HEAD(pagelist);

	if (flags & ~(unsigned long)(MPOL_MF_STRICT |
				     MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
		return -EINVAL;
	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		return -EPERM;

	if (start & ~PAGE_MASK)
		return -EINVAL;

	if (mode == MPOL_DEFAULT)
		flags &= ~MPOL_MF_STRICT;

	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
	end = start + len;

	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;

	new = mpol_new(mode, mode_flags, nmask);
	if (IS_ERR(new))
		return PTR_ERR(new);

	/*
	 * If we are using the default policy then operation
	 * on discontinuous address spaces is okay after all
	 */
	if (!new)
		flags |= MPOL_MF_DISCONTIG_OK;

	pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
		 start, start + len, mode, mode_flags,
		 nmask ? nodes_addr(*nmask)[0] : -1);

	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {

		err = migrate_prep();
		if (err)
			return err;
	}
	{
		NODEMASK_SCRATCH(scratch);
		if (scratch) {
			down_write(&mm->mmap_sem);
			task_lock(current);
			err = mpol_set_nodemask(new, nmask, scratch);
			task_unlock(current);
			if (err)
				up_write(&mm->mmap_sem);
		} else
			err = -ENOMEM;
		NODEMASK_SCRATCH_FREE(scratch);
	}
	if (err) {
		mpol_put(new);
		return err;
	}
	vma = check_range(mm, start, end, nmask,
			  flags | MPOL_MF_INVERT, &pagelist);

	err = PTR_ERR(vma);
	if (!IS_ERR(vma)) {
		int nr_failed = 0;

		err = mbind_range(vma, start, end, new);

		if (!list_empty(&pagelist))
			nr_failed = migrate_pages(&pagelist, new_vma_page,
						(unsigned long)vma);

		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
			err = -EIO;
	}

	up_write(&mm->mmap_sem);
	mpol_put(new);
	return err;
}

/*
 * User space interface with variable sized bitmaps for nodelists.
 */

/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
		     unsigned long maxnode)
{
	unsigned long k;
	unsigned long nlongs;
	unsigned long endmask;

	--maxnode;
	nodes_clear(*nodes);
	if (maxnode == 0 || !nmask)
		return 0;
	if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
		return -EINVAL;

	nlongs = BITS_TO_LONGS(maxnode);
	if ((maxnode % BITS_PER_LONG) == 0)
		endmask = ~0UL;
	else
		endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;

	/* When the user specified more nodes than supported just check
	   if the non supported part is all zero. */
	if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
		if (nlongs > PAGE_SIZE/sizeof(long))
			return -EINVAL;
		for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
			unsigned long t;
			if (get_user(t, nmask + k))
				return -EFAULT;
			if (k == nlongs - 1) {
				if (t & endmask)
					return -EINVAL;
			} else if (t)
				return -EINVAL;
		}
		nlongs = BITS_TO_LONGS(MAX_NUMNODES);
		endmask = ~0UL;
	}

	if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
		return -EFAULT;
	nodes_addr(*nodes)[nlongs-1] &= endmask;
	return 0;
}

/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
			      nodemask_t *nodes)
{
	unsigned long copy = ALIGN(maxnode-1, 64) / 8;
	const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);

	if (copy > nbytes) {
		if (copy > PAGE_SIZE)
			return -EINVAL;
		if (clear_user((char __user *)mask + nbytes, copy - nbytes))
			return -EFAULT;
		copy = nbytes;
	}
	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}

SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
		unsigned long, mode, unsigned long __user *, nmask,
		unsigned long, maxnode, unsigned, flags)
{
	nodemask_t nodes;
	int err;
	unsigned short mode_flags;

	mode_flags = mode & MPOL_MODE_FLAGS;
	mode &= ~MPOL_MODE_FLAGS;
	if (mode >= MPOL_MAX)
		return -EINVAL;
	if ((mode_flags & MPOL_F_STATIC_NODES) &&
	    (mode_flags & MPOL_F_RELATIVE_NODES))
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
}

/* Set the process memory policy */
SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask,
		unsigned long, maxnode)
{
	int err;
	nodemask_t nodes;
	unsigned short flags;

	flags = mode & MPOL_MODE_FLAGS;
	mode &= ~MPOL_MODE_FLAGS;
	if ((unsigned int)mode >= MPOL_MAX)
		return -EINVAL;
	if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_set_mempolicy(mode, flags, &nodes);
}

SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
		const unsigned long __user *, old_nodes,
		const unsigned long __user *, new_nodes)
{
	const struct cred *cred = current_cred(), *tcred;
	struct mm_struct *mm;
	struct task_struct *task;
	nodemask_t old;
	nodemask_t new;
	nodemask_t task_nodes;
	int err;

	err = get_nodes(&old, old_nodes, maxnode);
	if (err)
		return err;

	err = get_nodes(&new, new_nodes, maxnode);
	if (err)
		return err;

	/* Find the mm_struct */
	read_lock(&tasklist_lock);
	task = pid ? find_task_by_vpid(pid) : current;
	if (!task) {
		read_unlock(&tasklist_lock);
		return -ESRCH;
	}
	mm = get_task_mm(task);
	read_unlock(&tasklist_lock);

	if (!mm)
		return -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser privileges or the same
	 * userid as the target process.
	 */
	rcu_read_lock();
	tcred = __task_cred(task);
	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
	    !capable(CAP_SYS_NICE)) {
		rcu_read_unlock();
		err = -EPERM;
		goto out;
	}
	rcu_read_unlock();

	task_nodes = cpuset_mems_allowed(task);
	/* Is the user allowed to access the target nodes? */
	if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) {
		err = -EPERM;
		goto out;
	}

	if (!nodes_subset(new, node_states[N_HIGH_MEMORY])) {
		err = -EINVAL;
		goto out;
	}

	err = security_task_movememory(task);
	if (err)
		goto out;

	err = do_migrate_pages(mm, &old, &new,
		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
out:
	mmput(mm);
	return err;
}


/* Retrieve NUMA policy */
SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
		unsigned long __user *, nmask, unsigned long, maxnode,
		unsigned long, addr, unsigned long, flags)
{
	int err;
	int uninitialized_var(pval);
	nodemask_t nodes;

	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;

	err = do_get_mempolicy(&pval, &nodes, addr, flags);

	if (err)
		return err;

	if (policy && put_user(pval, policy))
		return -EFAULT;

	if (nmask)
		err = copy_nodes_to_user(nmask, maxnode, &nodes);

	return err;
}

#ifdef CONFIG_COMPAT

asmlinkage long compat_sys_get_mempolicy(int __user *policy,
				     compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode,
				     compat_ulong_t addr, compat_ulong_t flags)
{
	long err;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask)
		nm = compat_alloc_user_space(alloc_size);

	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

	if (!err && nmask) {
		err = copy_from_user(bm, nm, alloc_size);
		/* ensure entire bitmap is zeroed */
		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
		err |= compat_put_bitmap(nmask, bm, nr_bits);
	}

	return err;
}

asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_set_mempolicy(mode, nm, nr_bits+1);
}

asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
			     compat_ulong_t mode, compat_ulong_t __user *nmask,
			     compat_ulong_t maxnode, compat_ulong_t flags)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	nodemask_t bm;

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}

#endif

/*
 * get_vma_policy(@task, @vma, @addr)
 * @task - task for fallback if vma policy == default
 * @vma   - virtual memory area whose policy is sought
 * @addr  - address in @vma for shared policy lookup
 *
 * Returns effective policy for a VMA at specified address.
 * Falls back to @task or system default policy, as necessary.
 * Current or other task's task mempolicy and non-shared vma policies
 * are protected by the task's mmap_sem, which must be held for read by
 * the caller.
 * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
 * count--added by the get_policy() vm_op, as appropriate--to protect against
 * freeing by another task.  It is the caller's responsibility to free the
 * extra reference for shared policies.
 */
static struct mempolicy *get_vma_policy(struct task_struct *task,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = task->mempolicy;

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy) {
			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
									addr);
			if (vpol)
				pol = vpol;
		} else if (vma->vm_policy)
			pol = vma->vm_policy;
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

/*
 * Return a nodemask representing a mempolicy for filtering nodes for
 * page allocation
 */
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
{
	/* Lower zones don't get a nodemask applied for MPOL_BIND */
	if (unlikely(policy->mode == MPOL_BIND) &&
			gfp_zone(gfp) >= policy_zone &&
			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
		return &policy->v.nodes;

	return NULL;
}

/* Return a zonelist indicated by gfp for node representing a mempolicy */
static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
{
	int nd = numa_node_id();

	switch (policy->mode) {
	case MPOL_PREFERRED:
		if (!(policy->flags & MPOL_F_LOCAL))
			nd = policy->v.preferred_node;
		break;
	case MPOL_BIND:
		/*
		 * Normally, MPOL_BIND allocations are node-local within the
		 * allowed nodemask.  However, if __GFP_THISNODE is set and the
		 * current node is part of the mask, we use the zonelist for
		 * the first node in the mask instead.
		 */
		if (unlikely(gfp & __GFP_THISNODE) &&
				unlikely(!node_isset(nd, policy->v.nodes)))
			nd = first_node(policy->v.nodes);
		break;
	case MPOL_INTERLEAVE: /* should not happen */
		break;
	default:
		BUG();
	}
	return node_zonelist(nd, gfp);
}

/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
	unsigned nid, next;
	struct task_struct *me = current;

	nid = me->il_next;
	next = next_node(nid, policy->v.nodes);
	if (next >= MAX_NUMNODES)
		next = first_node(policy->v.nodes);
	if (next < MAX_NUMNODES)
		me->il_next = next;
	return nid;
}

/*
 * Depending on the memory policy provide a node from which to allocate the
 * next slab entry.
 * @policy must be protected by freeing by the caller.  If @policy is
 * the current task's mempolicy, this protection is implicit, as only the
 * task can change it's policy.  The system default policy requires no
 * such protection.
 */
unsigned slab_node(struct mempolicy *policy)
{
	if (!policy || policy->flags & MPOL_F_LOCAL)
		return numa_node_id();

	switch (policy->mode) {
	case MPOL_PREFERRED:
		/*
		 * handled MPOL_F_LOCAL above
		 */
		return policy->v.preferred_node;

	case MPOL_INTERLEAVE:
		return interleave_nodes(policy);

	case MPOL_BIND: {
		/*
		 * Follow bind policy behavior and start allocation at the
		 * first node.
		 */
		struct zonelist *zonelist;
		struct zone *zone;
		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
		(void)first_zones_zonelist(zonelist, highest_zoneidx,
							&policy->v.nodes,
							&zone);
		return zone->node;
	}

	default:
		BUG();
	}
}

/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
		struct vm_area_struct *vma, unsigned long off)
{
	unsigned nnodes = nodes_weight(pol->v.nodes);
	unsigned target;
	int c;
	int nid = -1;

	if (!nnodes)
		return numa_node_id();
	target = (unsigned int)off % nnodes;
	c = 0;
	do {
		nid = next_node(nid, pol->v.nodes);
		c++;
	} while (c <= target);
	return nid;
}

/* Determine a node number for interleave */
static inline unsigned interleave_nid(struct mempolicy *pol,
		 struct vm_area_struct *vma, unsigned long addr, int shift)
{
	if (vma) {
		unsigned long off;

		/*
		 * for small pages, there is no difference between
		 * shift and PAGE_SHIFT, so the bit-shift is safe.
		 * for huge pages, since vm_pgoff is in units of small
		 * pages, we need to shift off the always 0 bits to get
		 * a useful offset.
		 */
		BUG_ON(shift < PAGE_SHIFT);
		off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
		off += (addr - vma->vm_start) >> shift;
		return offset_il_node(pol, vma, off);
	} else
		return interleave_nodes(pol);
}

#ifdef CONFIG_HUGETLBFS
/*
 * huge_zonelist(@vma, @addr, @gfp_flags, @mpol)
 * @vma = virtual memory area whose policy is sought
 * @addr = address in @vma for shared policy lookup and interleave policy
 * @gfp_flags = for requested zone
 * @mpol = pointer to mempolicy pointer for reference counted mempolicy
 * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
 *
 * Returns a zonelist suitable for a huge page allocation and a pointer
 * to the struct mempolicy for conditional unref after allocation.
 * If the effective policy is 'BIND, returns a pointer to the mempolicy's
 * @nodemask for filtering the zonelist.
 */
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
				gfp_t gfp_flags, struct mempolicy **mpol,
				nodemask_t **nodemask)
{
	struct zonelist *zl;

	*mpol = get_vma_policy(current, vma, addr);
	*nodemask = NULL;	/* assume !MPOL_BIND */

	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
				huge_page_shift(hstate_vma(vma))), gfp_flags);
	} else {
		zl = policy_zonelist(gfp_flags, *mpol);
		if ((*mpol)->mode == MPOL_BIND)
			*nodemask = &(*mpol)->v.nodes;
	}
	return zl;
}
#endif

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
					unsigned nid)
{
	struct zonelist *zl;
	struct page *page;

	zl = node_zonelist(nid, gfp);
	page = __alloc_pages(gfp, order, zl);
	if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
	return page;
}

/**
 * 	alloc_page_vma	- Allocate a page for a VMA.
 *
 * 	@gfp:
 *      %GFP_USER    user allocation.
 *      %GFP_KERNEL  kernel allocations,
 *      %GFP_HIGHMEM highmem/user allocations,
 *      %GFP_FS      allocation should not call back into a file system.
 *      %GFP_ATOMIC  don't sleep.
 *
 * 	@vma:  Pointer to VMA or NULL if not available.
 *	@addr: Virtual Address of the allocation. Must be inside the VMA.
 *
 * 	This function allocates a page from the kernel page pool and applies
 *	a NUMA policy associated with the VMA or the current process.
 *	When VMA is not NULL caller must hold down_read on the mmap_sem of the
 *	mm_struct of the VMA to prevent it from going away. Should be used for
 *	all allocations for pages that will be mapped into
 * 	user space. Returns NULL when no page can be allocated.
 *
 *	Should be called with the mm_sem of the vma hold.
 */
struct page *
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = get_vma_policy(current, vma, addr);
	struct zonelist *zl;

	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
		mpol_cond_put(pol);
		return alloc_page_interleave(gfp, 0, nid);
	}
	zl = policy_zonelist(gfp, pol);
	if (unlikely(mpol_needs_cond_ref(pol))) {
		/*
		 * slow path: ref counted shared policy
		 */
		struct page *page =  __alloc_pages_nodemask(gfp, 0,
						zl, policy_nodemask(gfp, pol));
		__mpol_put(pol);
		return page;
	}
	/*
	 * fast path:  default or task policy
	 */
	return __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
}

/**
 * 	alloc_pages_current - Allocate pages.
 *
 *	@gfp:
 *		%GFP_USER   user allocation,
 *      	%GFP_KERNEL kernel allocation,
 *      	%GFP_HIGHMEM highmem allocation,
 *      	%GFP_FS     don't call back into a file system.
 *      	%GFP_ATOMIC don't sleep.
 *	@order: Power of two of allocation size in pages. 0 is a single page.
 *
 *	Allocate a page from the kernel page pool.  When not in
 *	interrupt context and apply the current process NUMA policy.
 *	Returns NULL when no page can be allocated.
 *
 *	Don't call cpuset_update_task_memory_state() unless
 *	1) it's ok to take cpuset_sem (can WAIT), and
 *	2) allocating for current task (not interrupt).
 */
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
	struct mempolicy *pol = current->mempolicy;

	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
		pol = &default_policy;

	/*
	 * No reference counting needed for current->mempolicy
	 * nor system default_policy
	 */
	if (pol->mode == MPOL_INTERLEAVE)
		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
	return __alloc_pages_nodemask(gfp, order,
			policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);

/*
 * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
 * rebinds the mempolicy its copying by calling mpol_rebind_policy()
 * with the mems_allowed returned by cpuset_mems_allowed().  This
 * keeps mempolicies cpuset relative after its cpuset moves.  See
 * further kernel/cpuset.c update_nodemask().
 */

/* Slow path of a mempolicy duplicate */
struct mempolicy *__mpol_dup(struct mempolicy *old)
{
	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);

	if (!new)
		return ERR_PTR(-ENOMEM);
	if (current_cpuset_is_being_rebound()) {
		nodemask_t mems = cpuset_mems_allowed(current);
		mpol_rebind_policy(old, &mems);
	}
	*new = *old;
	atomic_set(&new->refcnt, 1);
	return new;
}

/*
 * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
 * eliminate the * MPOL_F_* flags that require conditional ref and
 * [NOTE!!!] drop the extra ref.  Not safe to reference *frompol directly
 * after return.  Use the returned value.
 *
 * Allows use of a mempolicy for, e.g., multiple allocations with a single
 * policy lookup, even if the policy needs/has extra ref on lookup.
 * shmem_readahead needs this.
 */
struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
						struct mempolicy *frompol)
{
	if (!mpol_needs_cond_ref(frompol))
		return frompol;

	*tompol = *frompol;
	tompol->flags &= ~MPOL_F_SHARED;	/* copy doesn't need unref */
	__mpol_put(frompol);
	return tompol;
}

static int mpol_match_intent(const struct mempolicy *a,
			     const struct mempolicy *b)
{
	if (a->flags != b->flags)
		return 0;
	if (!mpol_store_user_nodemask(a))
		return 1;
	return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
}

/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return 0;
	if (a->mode != b->mode)
		return 0;
	if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
		return 0;
	switch (a->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		return nodes_equal(a->v.nodes, b->v.nodes);
	case MPOL_PREFERRED:
		return a->v.preferred_node == b->v.preferred_node &&
			a->flags == b->flags;
	default:
		BUG();
		return 0;
	}
}

/*
 * Shared memory backing store policy support.
 *
 * Remember policies even when nobody has shared memory mapped.
 * The policies are kept in Red-Black tree linked from the inode.
 * They are protected by the sp->lock spinlock, which should be held
 * for any accesses to the tree.
 */

/* lookup first element intersecting start-end */
/* Caller holds sp->lock */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
	struct rb_node *n = sp->root.rb_node;

	while (n) {
		struct sp_node *p = rb_entry(n, struct sp_node, nd);

		if (start >= p->end)
			n = n->rb_right;
		else if (end <= p->start)
			n = n->rb_left;
		else
			break;
	}
	if (!n)
		return NULL;
	for (;;) {
		struct sp_node *w = NULL;
		struct rb_node *prev = rb_prev(n);
		if (!prev)
			break;
		w = rb_entry(prev, struct sp_node, nd);
		if (w->end <= start)
			break;
		n = prev;
	}
	return rb_entry(n, struct sp_node, nd);
}

/* Insert a new shared policy into the list. */
/* Caller holds sp->lock */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
	struct rb_node **p = &sp->root.rb_node;
	struct rb_node *parent = NULL;
	struct sp_node *nd;

	while (*p) {
		parent = *p;
		nd = rb_entry(parent, struct sp_node, nd);
		if (new->start < nd->start)
			p = &(*p)->rb_left;
		else if (new->end > nd->end)
			p = &(*p)->rb_right;
		else
			BUG();
	}
	rb_link_node(&new->nd, parent, p);
	rb_insert_color(&new->nd, &sp->root);
	pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->mode : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	struct mempolicy *pol = NULL;
	struct sp_node *sn;

	if (!sp->root.rb_node)
		return NULL;
	spin_lock(&sp->lock);
	sn = sp_lookup(sp, idx, idx+1);
	if (sn) {
		mpol_get(sn->policy);
		pol = sn->policy;
	}
	spin_unlock(&sp->lock);
	return pol;
}

static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
	rb_erase(&n->nd, &sp->root);
	mpol_put(n->policy);
	kmem_cache_free(sn_cache, n);
}

static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
				struct mempolicy *pol)
{
	struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);

	if (!n)
		return NULL;
	n->start = start;
	n->end = end;
	mpol_get(pol);
	pol->flags |= MPOL_F_SHARED;	/* for unref */
	n->policy = pol;
	return n;
}

/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
				 unsigned long end, struct sp_node *new)
{
	struct sp_node *n, *new2 = NULL;

restart:
	spin_lock(&sp->lock);
	n = sp_lookup(sp, start, end);
	/* Take care of old policies in the same range. */
	while (n && n->start < end) {
		struct rb_node *next = rb_next(&n->nd);
		if (n->start >= start) {
			if (n->end <= end)
				sp_delete(sp, n);
			else
				n->start = end;
		} else {
			/* Old policy spanning whole new range. */
			if (n->end > end) {
				if (!new2) {
					spin_unlock(&sp->lock);
					new2 = sp_alloc(end, n->end, n->policy);
					if (!new2)
						return -ENOMEM;
					goto restart;
				}
				n->end = start;
				sp_insert(sp, new2);
				new2 = NULL;
				break;
			} else
				n->end = start;
		}
		if (!next)
			break;
		n = rb_entry(next, struct sp_node, nd);
	}
	if (new)
		sp_insert(sp, new);
	spin_unlock(&sp->lock);
	if (new2) {
		mpol_put(new2->policy);
		kmem_cache_free(sn_cache, new2);
	}
	return 0;
}

/**
 * mpol_shared_policy_init - initialize shared policy for inode
 * @sp: pointer to inode shared policy
 * @mpol:  struct mempolicy to install
 *
 * Install non-NULL @mpol in inode's shared policy rb-tree.
 * On entry, the current task has a reference on a non-NULL @mpol.
 * This must be released on exit.
 * This is called at get_inode() calls and we can use GFP_KERNEL.
 */
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
	int ret;

	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
	spin_lock_init(&sp->lock);

	if (mpol) {
		struct vm_area_struct pvma;
		struct mempolicy *new;
		NODEMASK_SCRATCH(scratch);

		if (!scratch)
			return;
		/* contextualize the tmpfs mount point mempolicy */
		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
		if (IS_ERR(new)) {
			mpol_put(mpol);	/* drop our ref on sb mpol */
			NODEMASK_SCRATCH_FREE(scratch);
			return;		/* no valid nodemask intersection */
		}

		task_lock(current);
		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
		task_unlock(current);
		mpol_put(mpol);	/* drop our ref on sb mpol */
		if (ret) {
			NODEMASK_SCRATCH_FREE(scratch);
			mpol_put(new);
			return;
		}

		/* Create pseudo-vma that contains just the policy */
		memset(&pvma, 0, sizeof(struct vm_area_struct));
		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
		mpol_put(new);			/* drop initial ref */
		NODEMASK_SCRATCH_FREE(scratch);
	}
}

int mpol_set_shared_policy(struct shared_policy *info,
			struct vm_area_struct *vma, struct mempolicy *npol)
{
	int err;
	struct sp_node *new = NULL;
	unsigned long sz = vma_pages(vma);

	pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
		 vma->vm_pgoff,
		 sz, npol ? npol->mode : -1,
		 npol ? npol->flags : -1,
		 npol ? nodes_addr(npol->v.nodes)[0] : -1);

	if (npol) {
		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
		if (!new)
			return -ENOMEM;
	}
	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
	if (err && new)
		kmem_cache_free(sn_cache, new);
	return err;
}

/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
	struct sp_node *n;
	struct rb_node *next;

	if (!p->root.rb_node)
		return;
	spin_lock(&p->lock);
	next = rb_first(&p->root);
	while (next) {
		n = rb_entry(next, struct sp_node, nd);
		next = rb_next(&n->nd);
		rb_erase(&n->nd, &p->root);
		mpol_put(n->policy);
		kmem_cache_free(sn_cache, n);
	}
	spin_unlock(&p->lock);
}

/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
	nodemask_t interleave_nodes;
	unsigned long largest = 0;
	int nid, prefer = 0;

	policy_cache = kmem_cache_create("numa_policy",
					 sizeof(struct mempolicy),
					 0, SLAB_PANIC, NULL);

	sn_cache = kmem_cache_create("shared_policy_node",
				     sizeof(struct sp_node),
				     0, SLAB_PANIC, NULL);

	/*
	 * Set interleaving policy for system init. Interleaving is only
	 * enabled across suitably sized nodes (default is >= 16MB), or
	 * fall back to the largest node if they're all smaller.
	 */
	nodes_clear(interleave_nodes);
	for_each_node_state(nid, N_HIGH_MEMORY) {
		unsigned long total_pages = node_present_pages(nid);

		/* Preserve the largest node */
		if (largest < total_pages) {
			largest = total_pages;
			prefer = nid;
		}

		/* Interleave this node? */
		if ((total_pages << PAGE_SHIFT) >= (16 << 20))
			node_set(nid, interleave_nodes);
	}

	/* All too small, use the largest */
	if (unlikely(nodes_empty(interleave_nodes)))
		node_set(prefer, interleave_nodes);

	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
		printk("numa_policy_init: interleaving failed\n");
}

/* Reset policy of current process to default */
void numa_default_policy(void)
{
	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}

/*
 * Parse and format mempolicy from/to strings
 */

/*
 * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
 * Used only for mpol_parse_str() and mpol_to_str()
 */
#define MPOL_LOCAL (MPOL_INTERLEAVE + 1)
static const char * const policy_types[] =
	{ "default", "prefer", "bind", "interleave", "local" };


#ifdef CONFIG_TMPFS
/**
 * mpol_parse_str - parse string to mempolicy
 * @str:  string containing mempolicy to parse
 * @mpol:  pointer to struct mempolicy pointer, returned on success.
 * @no_context:  flag whether to "contextualize" the mempolicy
 *
 * Format of input:
 *	<mode>[=<flags>][:<nodelist>]
 *
 * if @no_context is true, save the input nodemask in w.user_nodemask in
 * the returned mempolicy.  This will be used to "clone" the mempolicy in
 * a specific context [cpuset] at a later time.  Used to parse tmpfs mpol
 * mount option.  Note that if 'static' or 'relative' mode flags were
 * specified, the input nodemask will already have been saved.  Saving
 * it again is redundant, but safe.
 *
 * On success, returns 0, else 1
 */
int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
{
	struct mempolicy *new = NULL;
	unsigned short uninitialized_var(mode);
	unsigned short uninitialized_var(mode_flags);
	nodemask_t nodes;
	char *nodelist = strchr(str, ':');
	char *flags = strchr(str, '=');
	int i;
	int err = 1;

	if (nodelist) {
		/* NUL-terminate mode or flags string */
		*nodelist++ = '\0';
		if (nodelist_parse(nodelist, nodes))
			goto out;
		if (!nodes_subset(nodes, node_states[N_HIGH_MEMORY]))
			goto out;
	} else
		nodes_clear(nodes);

	if (flags)
		*flags++ = '\0';	/* terminate mode string */

	for (i = 0; i <= MPOL_LOCAL; i++) {
		if (!strcmp(str, policy_types[i])) {
			mode = i;
			break;
		}
	}
	if (i > MPOL_LOCAL)
		goto out;

	switch (mode) {
	case MPOL_PREFERRED:
		/*
		 * Insist on a nodelist of one node only
		 */
		if (nodelist) {
			char *rest = nodelist;
			while (isdigit(*rest))
				rest++;
			if (!*rest)
				err = 0;
		}
		break;
	case MPOL_INTERLEAVE:
		/*
		 * Default to online nodes with memory if no nodelist
		 */
		if (!nodelist)
			nodes = node_states[N_HIGH_MEMORY];
		err = 0;
		break;
	case MPOL_LOCAL:
		/*
		 * Don't allow a nodelist;  mpol_new() checks flags
		 */
		if (nodelist)
			goto out;
		mode = MPOL_PREFERRED;
		break;

	/*
	 * case MPOL_BIND:    mpol_new() enforces non-empty nodemask.
	 * case MPOL_DEFAULT: mpol_new() enforces empty nodemask, ignores flags.
	 */
	}

	mode_flags = 0;
	if (flags) {
		/*
		 * Currently, we only support two mutually exclusive
		 * mode flags.
		 */
		if (!strcmp(flags, "static"))
			mode_flags |= MPOL_F_STATIC_NODES;
		else if (!strcmp(flags, "relative"))
			mode_flags |= MPOL_F_RELATIVE_NODES;
		else
			err = 1;
	}

	new = mpol_new(mode, mode_flags, &nodes);
	if (IS_ERR(new))
		err = 1;
	else {
		int ret;
		NODEMASK_SCRATCH(scratch);
		if (scratch) {
			task_lock(current);
			ret = mpol_set_nodemask(new, &nodes, scratch);
			task_unlock(current);
		} else
			ret = -ENOMEM;
		NODEMASK_SCRATCH_FREE(scratch);
		if (ret) {
			err = 1;
			mpol_put(new);
		} else if (no_context) {
			/* save for contextualization */
			new->w.user_nodemask = nodes;
		}
	}

out:
	/* Restore string for error message */
	if (nodelist)
		*--nodelist = ':';
	if (flags)
		*--flags = '=';
	if (!err)
		*mpol = new;
	return err;
}
#endif /* CONFIG_TMPFS */

/**
 * mpol_to_str - format a mempolicy structure for printing
 * @buffer:  to contain formatted mempolicy string
 * @maxlen:  length of @buffer
 * @pol:  pointer to mempolicy to be formatted
 * @no_context:  "context free" mempolicy - use nodemask in w.user_nodemask
 *
 * Convert a mempolicy into a string.
 * Returns the number of characters in buffer (if positive)
 * or an error (negative)
 */
int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
{
	char *p = buffer;
	int l;
	nodemask_t nodes;
	unsigned short mode;
	unsigned short flags = pol ? pol->flags : 0;

	/*
	 * Sanity check:  room for longest mode, flag and some nodes
	 */
	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);

	if (!pol || pol == &default_policy)
		mode = MPOL_DEFAULT;
	else
		mode = pol->mode;

	switch (mode) {
	case MPOL_DEFAULT:
		nodes_clear(nodes);
		break;

	case MPOL_PREFERRED:
		nodes_clear(nodes);
		if (flags & MPOL_F_LOCAL)
			mode = MPOL_LOCAL;	/* pseudo-policy */
		else
			node_set(pol->v.preferred_node, nodes);
		break;

	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		if (no_context)
			nodes = pol->w.user_nodemask;
		else
			nodes = pol->v.nodes;
		break;

	default:
		BUG();
	}

	l = strlen(policy_types[mode]);
	if (buffer + maxlen < p + l + 1)
		return -ENOSPC;

	strcpy(p, policy_types[mode]);
	p += l;

	if (flags & MPOL_MODE_FLAGS) {
		if (buffer + maxlen < p + 2)
			return -ENOSPC;
		*p++ = '=';

		/*
		 * Currently, the only defined flags are mutually exclusive
		 */
		if (flags & MPOL_F_STATIC_NODES)
			p += snprintf(p, buffer + maxlen - p, "static");
		else if (flags & MPOL_F_RELATIVE_NODES)
			p += snprintf(p, buffer + maxlen - p, "relative");
	}

	if (!nodes_empty(nodes)) {
		if (buffer + maxlen < p + 2)
			return -ENOSPC;
		*p++ = ':';
	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
	}
	return p - buffer;
}

struct numa_maps {
	unsigned long pages;
	unsigned long anon;
	unsigned long active;
	unsigned long writeback;
	unsigned long mapcount_max;
	unsigned long dirty;
	unsigned long swapcache;
	unsigned long node[MAX_NUMNODES];
};

static void gather_stats(struct page *page, void *private, int pte_dirty)
{
	struct numa_maps *md = private;
	int count = page_mapcount(page);

	md->pages++;
	if (pte_dirty || PageDirty(page))
		md->dirty++;

	if (PageSwapCache(page))
		md->swapcache++;

	if (PageActive(page) || PageUnevictable(page))
		md->active++;

	if (PageWriteback(page))
		md->writeback++;

	if (PageAnon(page))
		md->anon++;

	if (count > md->mapcount_max)
		md->mapcount_max = count;

	md->node[page_to_nid(page)]++;
}

#ifdef CONFIG_HUGETLB_PAGE
static void check_huge_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end,
		struct numa_maps *md)
{
	unsigned long addr;
	struct page *page;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	for (addr = start; addr < end; addr += sz) {
		pte_t *ptep = huge_pte_offset(vma->vm_mm,
						addr & huge_page_mask(h));
		pte_t pte;

		if (!ptep)
			continue;

		pte = *ptep;
		if (pte_none(pte))
			continue;

		page = pte_page(pte);
		if (!page)
			continue;

		gather_stats(page, md, pte_dirty(*ptep));
	}
}
#else
static inline void check_huge_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end,
		struct numa_maps *md)
{
}
#endif

/*
 * Display pages allocated per node and memory policy via /proc.
 */
int show_numa_map(struct seq_file *m, void *v)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;
	struct numa_maps *md;
	struct file *file = vma->vm_file;
	struct mm_struct *mm = vma->vm_mm;
	struct mempolicy *pol;
	int n;
	char buffer[50];

	if (!mm)
		return 0;

	md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
	if (!md)
		return 0;

	pol = get_vma_policy(priv->task, vma, vma->vm_start);
	mpol_to_str(buffer, sizeof(buffer), pol, 0);
	mpol_cond_put(pol);

	seq_printf(m, "%08lx %s", vma->vm_start, buffer);

	if (file) {
		seq_printf(m, " file=");
		seq_path(m, &file->f_path, "\n\t= ");
	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
		seq_printf(m, " heap");
	} else if (vma->vm_start <= mm->start_stack &&
			vma->vm_end >= mm->start_stack) {
		seq_printf(m, " stack");
	}

	if (is_vm_hugetlb_page(vma)) {
		check_huge_range(vma, vma->vm_start, vma->vm_end, md);
		seq_printf(m, " huge");
	} else {
		check_pgd_range(vma, vma->vm_start, vma->vm_end,
			&node_states[N_HIGH_MEMORY], MPOL_MF_STATS, md);
	}

	if (!md->pages)
		goto out;

	if (md->anon)
		seq_printf(m," anon=%lu",md->anon);

	if (md->dirty)
		seq_printf(m," dirty=%lu",md->dirty);

	if (md->pages != md->anon && md->pages != md->dirty)
		seq_printf(m, " mapped=%lu", md->pages);

	if (md->mapcount_max > 1)
		seq_printf(m, " mapmax=%lu", md->mapcount_max);

	if (md->swapcache)
		seq_printf(m," swapcache=%lu", md->swapcache);

	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
		seq_printf(m," active=%lu", md->active);

	if (md->writeback)
		seq_printf(m," writeback=%lu", md->writeback);

	for_each_node_state(n, N_HIGH_MEMORY)
		if (md->node[n])
			seq_printf(m, " N%d=%lu", n, md->node[n]);
out:
	seq_putc(m, '\n');
	kfree(md);

	if (m->count < m->size)
		m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
	return 0;
}