Eric Lee / smarc-fsl-linux-kernel

core.c 187 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 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 
/*
 * Performance events core code:
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *  Copyright  ยฉ  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 *
 * For licensing details see kernel-base/COPYING
 */

#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/idr.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/hash.h>
#include <linux/tick.h>
#include <linux/sysfs.h>
#include <linux/dcache.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/reboot.h>
#include <linux/vmstat.h>
#include <linux/device.h>
#include <linux/export.h>
#include <linux/vmalloc.h>
#include <linux/hardirq.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
#include <linux/syscalls.h>
#include <linux/anon_inodes.h>
#include <linux/kernel_stat.h>
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
#include <linux/cgroup.h>

#include "internal.h"

#include <asm/irq_regs.h>

struct remote_function_call {
	struct task_struct	*p;
	int			(*func)(void *info);
	void			*info;
	int			ret;
};

static void remote_function(void *data)
{
	struct remote_function_call *tfc = data;
	struct task_struct *p = tfc->p;

	if (p) {
		tfc->ret = -EAGAIN;
		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
			return;
	}

	tfc->ret = tfc->func(tfc->info);
}

/**
 * task_function_call - call a function on the cpu on which a task runs
 * @p:		the task to evaluate
 * @func:	the function to be called
 * @info:	the function call argument
 *
 * Calls the function @func when the task is currently running. This might
 * be on the current CPU, which just calls the function directly
 *
 * returns: @func return value, or
 *	    -ESRCH  - when the process isn't running
 *	    -EAGAIN - when the process moved away
 */
static int
task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
{
	struct remote_function_call data = {
		.p	= p,
		.func	= func,
		.info	= info,
		.ret	= -ESRCH, /* No such (running) process */
	};

	if (task_curr(p))
		smp_call_function_single(task_cpu(p), remote_function, &data, 1);

	return data.ret;
}

/**
 * cpu_function_call - call a function on the cpu
 * @func:	the function to be called
 * @info:	the function call argument
 *
 * Calls the function @func on the remote cpu.
 *
 * returns: @func return value or -ENXIO when the cpu is offline
 */
static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
{
	struct remote_function_call data = {
		.p	= NULL,
		.func	= func,
		.info	= info,
		.ret	= -ENXIO, /* No such CPU */
	};

	smp_call_function_single(cpu, remote_function, &data, 1);

	return data.ret;
}

#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
		       PERF_FLAG_FD_OUTPUT  |\
		       PERF_FLAG_PID_CGROUP |\
		       PERF_FLAG_FD_CLOEXEC)

/*
 * branch priv levels that need permission checks
 */
#define PERF_SAMPLE_BRANCH_PERM_PLM \
	(PERF_SAMPLE_BRANCH_KERNEL |\
	 PERF_SAMPLE_BRANCH_HV)

enum event_type_t {
	EVENT_FLEXIBLE = 0x1,
	EVENT_PINNED = 0x2,
	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};

/*
 * perf_sched_events : >0 events exist
 * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
 */
struct static_key_deferred perf_sched_events __read_mostly;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);

static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
static atomic_t nr_task_events __read_mostly;
static atomic_t nr_freq_events __read_mostly;

static LIST_HEAD(pmus);
static DEFINE_MUTEX(pmus_lock);
static struct srcu_struct pmus_srcu;

/*
 * perf event paranoia level:
 *  -1 - not paranoid at all
 *   0 - disallow raw tracepoint access for unpriv
 *   1 - disallow cpu events for unpriv
 *   2 - disallow kernel profiling for unpriv
 */
int sysctl_perf_event_paranoid __read_mostly = 1;

/* Minimum for 512 kiB + 1 user control page */
int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */

/*
 * max perf event sample rate
 */
#define DEFAULT_MAX_SAMPLE_RATE		100000
#define DEFAULT_SAMPLE_PERIOD_NS	(NSEC_PER_SEC / DEFAULT_MAX_SAMPLE_RATE)
#define DEFAULT_CPU_TIME_MAX_PERCENT	25

int sysctl_perf_event_sample_rate __read_mostly	= DEFAULT_MAX_SAMPLE_RATE;

static int max_samples_per_tick __read_mostly	= DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
static int perf_sample_period_ns __read_mostly	= DEFAULT_SAMPLE_PERIOD_NS;

static int perf_sample_allowed_ns __read_mostly =
	DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100;

void update_perf_cpu_limits(void)
{
	u64 tmp = perf_sample_period_ns;

	tmp *= sysctl_perf_cpu_time_max_percent;
	do_div(tmp, 100);
	ACCESS_ONCE(perf_sample_allowed_ns) = tmp;
}

static int perf_rotate_context(struct perf_cpu_context *cpuctx);

int perf_proc_update_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);

	if (ret || !write)
		return ret;

	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
	update_perf_cpu_limits();

	return 0;
}

int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;

int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp,
				loff_t *ppos)
{
	int ret = proc_dointvec(table, write, buffer, lenp, ppos);

	if (ret || !write)
		return ret;

	update_perf_cpu_limits();

	return 0;
}

/*
 * perf samples are done in some very critical code paths (NMIs).
 * If they take too much CPU time, the system can lock up and not
 * get any real work done.  This will drop the sample rate when
 * we detect that events are taking too long.
 */
#define NR_ACCUMULATED_SAMPLES 128
static DEFINE_PER_CPU(u64, running_sample_length);

static void perf_duration_warn(struct irq_work *w)
{
	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
	u64 avg_local_sample_len;
	u64 local_samples_len;

	local_samples_len = __get_cpu_var(running_sample_length);
	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;

	printk_ratelimited(KERN_WARNING
			"perf interrupt took too long (%lld > %lld), lowering "
			"kernel.perf_event_max_sample_rate to %d\n",
			avg_local_sample_len, allowed_ns >> 1,
			sysctl_perf_event_sample_rate);
}

static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);

void perf_sample_event_took(u64 sample_len_ns)
{
	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
	u64 avg_local_sample_len;
	u64 local_samples_len;

	if (allowed_ns == 0)
		return;

	/* decay the counter by 1 average sample */
	local_samples_len = __get_cpu_var(running_sample_length);
	local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
	local_samples_len += sample_len_ns;
	__get_cpu_var(running_sample_length) = local_samples_len;

	/*
	 * note: this will be biased artifically low until we have
	 * seen NR_ACCUMULATED_SAMPLES.  Doing it this way keeps us
	 * from having to maintain a count.
	 */
	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;

	if (avg_local_sample_len <= allowed_ns)
		return;

	if (max_samples_per_tick <= 1)
		return;

	max_samples_per_tick = DIV_ROUND_UP(max_samples_per_tick, 2);
	sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;

	update_perf_cpu_limits();

	if (!irq_work_queue(&perf_duration_work)) {
		early_printk("perf interrupt took too long (%lld > %lld), lowering "
			     "kernel.perf_event_max_sample_rate to %d\n",
			     avg_local_sample_len, allowed_ns >> 1,
			     sysctl_perf_event_sample_rate);
	}
}

static atomic64_t perf_event_id;

static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
			      enum event_type_t event_type);

static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
			     enum event_type_t event_type,
			     struct task_struct *task);

static void update_context_time(struct perf_event_context *ctx);
static u64 perf_event_time(struct perf_event *event);

void __weak perf_event_print_debug(void)	{ }

extern __weak const char *perf_pmu_name(void)
{
	return "pmu";
}

static inline u64 perf_clock(void)
{
	return local_clock();
}

static inline struct perf_cpu_context *
__get_cpu_context(struct perf_event_context *ctx)
{
	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
}

static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
			  struct perf_event_context *ctx)
{
	raw_spin_lock(&cpuctx->ctx.lock);
	if (ctx)
		raw_spin_lock(&ctx->lock);
}

static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
			    struct perf_event_context *ctx)
{
	if (ctx)
		raw_spin_unlock(&ctx->lock);
	raw_spin_unlock(&cpuctx->ctx.lock);
}

#ifdef CONFIG_CGROUP_PERF

/*
 * perf_cgroup_info keeps track of time_enabled for a cgroup.
 * This is a per-cpu dynamically allocated data structure.
 */
struct perf_cgroup_info {
	u64				time;
	u64				timestamp;
};

struct perf_cgroup {
	struct cgroup_subsys_state	css;
	struct perf_cgroup_info	__percpu *info;
};

/*
 * Must ensure cgroup is pinned (css_get) before calling
 * this function. In other words, we cannot call this function
 * if there is no cgroup event for the current CPU context.
 */
static inline struct perf_cgroup *
perf_cgroup_from_task(struct task_struct *task)
{
	return container_of(task_css(task, perf_event_cgrp_id),
			    struct perf_cgroup, css);
}

static inline bool
perf_cgroup_match(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);

	/* @event doesn't care about cgroup */
	if (!event->cgrp)
		return true;

	/* wants specific cgroup scope but @cpuctx isn't associated with any */
	if (!cpuctx->cgrp)
		return false;

	/*
	 * Cgroup scoping is recursive.  An event enabled for a cgroup is
	 * also enabled for all its descendant cgroups.  If @cpuctx's
	 * cgroup is a descendant of @event's (the test covers identity
	 * case), it's a match.
	 */
	return cgroup_is_descendant(cpuctx->cgrp->css.cgroup,
				    event->cgrp->css.cgroup);
}

static inline void perf_put_cgroup(struct perf_event *event)
{
	css_put(&event->cgrp->css);
}

static inline void perf_detach_cgroup(struct perf_event *event)
{
	perf_put_cgroup(event);
	event->cgrp = NULL;
}

static inline int is_cgroup_event(struct perf_event *event)
{
	return event->cgrp != NULL;
}

static inline u64 perf_cgroup_event_time(struct perf_event *event)
{
	struct perf_cgroup_info *t;

	t = per_cpu_ptr(event->cgrp->info, event->cpu);
	return t->time;
}

static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
{
	struct perf_cgroup_info *info;
	u64 now;

	now = perf_clock();

	info = this_cpu_ptr(cgrp->info);

	info->time += now - info->timestamp;
	info->timestamp = now;
}

static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
{
	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
	if (cgrp_out)
		__update_cgrp_time(cgrp_out);
}

static inline void update_cgrp_time_from_event(struct perf_event *event)
{
	struct perf_cgroup *cgrp;

	/*
	 * ensure we access cgroup data only when needed and
	 * when we know the cgroup is pinned (css_get)
	 */
	if (!is_cgroup_event(event))
		return;

	cgrp = perf_cgroup_from_task(current);
	/*
	 * Do not update time when cgroup is not active
	 */
	if (cgrp == event->cgrp)
		__update_cgrp_time(event->cgrp);
}

static inline void
perf_cgroup_set_timestamp(struct task_struct *task,
			  struct perf_event_context *ctx)
{
	struct perf_cgroup *cgrp;
	struct perf_cgroup_info *info;

	/*
	 * ctx->lock held by caller
	 * ensure we do not access cgroup data
	 * unless we have the cgroup pinned (css_get)
	 */
	if (!task || !ctx->nr_cgroups)
		return;

	cgrp = perf_cgroup_from_task(task);
	info = this_cpu_ptr(cgrp->info);
	info->timestamp = ctx->timestamp;
}

#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */

/*
 * reschedule events based on the cgroup constraint of task.
 *
 * mode SWOUT : schedule out everything
 * mode SWIN : schedule in based on cgroup for next
 */
void perf_cgroup_switch(struct task_struct *task, int mode)
{
	struct perf_cpu_context *cpuctx;
	struct pmu *pmu;
	unsigned long flags;

	/*
	 * disable interrupts to avoid geting nr_cgroup
	 * changes via __perf_event_disable(). Also
	 * avoids preemption.
	 */
	local_irq_save(flags);

	/*
	 * we reschedule only in the presence of cgroup
	 * constrained events.
	 */
	rcu_read_lock();

	list_for_each_entry_rcu(pmu, &pmus, entry) {
		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
		if (cpuctx->unique_pmu != pmu)
			continue; /* ensure we process each cpuctx once */

		/*
		 * perf_cgroup_events says at least one
		 * context on this CPU has cgroup events.
		 *
		 * ctx->nr_cgroups reports the number of cgroup
		 * events for a context.
		 */
		if (cpuctx->ctx.nr_cgroups > 0) {
			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
			perf_pmu_disable(cpuctx->ctx.pmu);

			if (mode & PERF_CGROUP_SWOUT) {
				cpu_ctx_sched_out(cpuctx, EVENT_ALL);
				/*
				 * must not be done before ctxswout due
				 * to event_filter_match() in event_sched_out()
				 */
				cpuctx->cgrp = NULL;
			}

			if (mode & PERF_CGROUP_SWIN) {
				WARN_ON_ONCE(cpuctx->cgrp);
				/*
				 * set cgrp before ctxsw in to allow
				 * event_filter_match() to not have to pass
				 * task around
				 */
				cpuctx->cgrp = perf_cgroup_from_task(task);
				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
			}
			perf_pmu_enable(cpuctx->ctx.pmu);
			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
		}
	}

	rcu_read_unlock();

	local_irq_restore(flags);
}

static inline void perf_cgroup_sched_out(struct task_struct *task,
					 struct task_struct *next)
{
	struct perf_cgroup *cgrp1;
	struct perf_cgroup *cgrp2 = NULL;

	/*
	 * we come here when we know perf_cgroup_events > 0
	 */
	cgrp1 = perf_cgroup_from_task(task);

	/*
	 * next is NULL when called from perf_event_enable_on_exec()
	 * that will systematically cause a cgroup_switch()
	 */
	if (next)
		cgrp2 = perf_cgroup_from_task(next);

	/*
	 * only schedule out current cgroup events if we know
	 * that we are switching to a different cgroup. Otherwise,
	 * do no touch the cgroup events.
	 */
	if (cgrp1 != cgrp2)
		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
}

static inline void perf_cgroup_sched_in(struct task_struct *prev,
					struct task_struct *task)
{
	struct perf_cgroup *cgrp1;
	struct perf_cgroup *cgrp2 = NULL;

	/*
	 * we come here when we know perf_cgroup_events > 0
	 */
	cgrp1 = perf_cgroup_from_task(task);

	/* prev can never be NULL */
	cgrp2 = perf_cgroup_from_task(prev);

	/*
	 * only need to schedule in cgroup events if we are changing
	 * cgroup during ctxsw. Cgroup events were not scheduled
	 * out of ctxsw out if that was not the case.
	 */
	if (cgrp1 != cgrp2)
		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
}

static inline int perf_cgroup_connect(int fd, struct perf_event *event,
				      struct perf_event_attr *attr,
				      struct perf_event *group_leader)
{
	struct perf_cgroup *cgrp;
	struct cgroup_subsys_state *css;
	struct fd f = fdget(fd);
	int ret = 0;

	if (!f.file)
		return -EBADF;

	css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
	if (IS_ERR(css)) {
		ret = PTR_ERR(css);
		goto out;
	}

	cgrp = container_of(css, struct perf_cgroup, css);
	event->cgrp = cgrp;

	/*
	 * all events in a group must monitor
	 * the same cgroup because a task belongs
	 * to only one perf cgroup at a time
	 */
	if (group_leader && group_leader->cgrp != cgrp) {
		perf_detach_cgroup(event);
		ret = -EINVAL;
	}
out:
	fdput(f);
	return ret;
}

static inline void
perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
{
	struct perf_cgroup_info *t;
	t = per_cpu_ptr(event->cgrp->info, event->cpu);
	event->shadow_ctx_time = now - t->timestamp;
}

static inline void
perf_cgroup_defer_enabled(struct perf_event *event)
{
	/*
	 * when the current task's perf cgroup does not match
	 * the event's, we need to remember to call the
	 * perf_mark_enable() function the first time a task with
	 * a matching perf cgroup is scheduled in.
	 */
	if (is_cgroup_event(event) && !perf_cgroup_match(event))
		event->cgrp_defer_enabled = 1;
}

static inline void
perf_cgroup_mark_enabled(struct perf_event *event,
			 struct perf_event_context *ctx)
{
	struct perf_event *sub;
	u64 tstamp = perf_event_time(event);

	if (!event->cgrp_defer_enabled)
		return;

	event->cgrp_defer_enabled = 0;

	event->tstamp_enabled = tstamp - event->total_time_enabled;
	list_for_each_entry(sub, &event->sibling_list, group_entry) {
		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
			sub->cgrp_defer_enabled = 0;
		}
	}
}
#else /* !CONFIG_CGROUP_PERF */

static inline bool
perf_cgroup_match(struct perf_event *event)
{
	return true;
}

static inline void perf_detach_cgroup(struct perf_event *event)
{}

static inline int is_cgroup_event(struct perf_event *event)
{
	return 0;
}

static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
{
	return 0;
}

static inline void update_cgrp_time_from_event(struct perf_event *event)
{
}

static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
{
}

static inline void perf_cgroup_sched_out(struct task_struct *task,
					 struct task_struct *next)
{
}

static inline void perf_cgroup_sched_in(struct task_struct *prev,
					struct task_struct *task)
{
}

static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
				      struct perf_event_attr *attr,
				      struct perf_event *group_leader)
{
	return -EINVAL;
}

static inline void
perf_cgroup_set_timestamp(struct task_struct *task,
			  struct perf_event_context *ctx)
{
}

void
perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
{
}

static inline void
perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
{
}

static inline u64 perf_cgroup_event_time(struct perf_event *event)
{
	return 0;
}

static inline void
perf_cgroup_defer_enabled(struct perf_event *event)
{
}

static inline void
perf_cgroup_mark_enabled(struct perf_event *event,
			 struct perf_event_context *ctx)
{
}
#endif

/*
 * set default to be dependent on timer tick just
 * like original code
 */
#define PERF_CPU_HRTIMER (1000 / HZ)
/*
 * function must be called with interrupts disbled
 */
static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
{
	struct perf_cpu_context *cpuctx;
	enum hrtimer_restart ret = HRTIMER_NORESTART;
	int rotations = 0;

	WARN_ON(!irqs_disabled());

	cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);

	rotations = perf_rotate_context(cpuctx);

	/*
	 * arm timer if needed
	 */
	if (rotations) {
		hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
		ret = HRTIMER_RESTART;
	}

	return ret;
}

/* CPU is going down */
void perf_cpu_hrtimer_cancel(int cpu)
{
	struct perf_cpu_context *cpuctx;
	struct pmu *pmu;
	unsigned long flags;

	if (WARN_ON(cpu != smp_processor_id()))
		return;

	local_irq_save(flags);

	rcu_read_lock();

	list_for_each_entry_rcu(pmu, &pmus, entry) {
		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);

		if (pmu->task_ctx_nr == perf_sw_context)
			continue;

		hrtimer_cancel(&cpuctx->hrtimer);
	}

	rcu_read_unlock();

	local_irq_restore(flags);
}

static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
{
	struct hrtimer *hr = &cpuctx->hrtimer;
	struct pmu *pmu = cpuctx->ctx.pmu;
	int timer;

	/* no multiplexing needed for SW PMU */
	if (pmu->task_ctx_nr == perf_sw_context)
		return;

	/*
	 * check default is sane, if not set then force to
	 * default interval (1/tick)
	 */
	timer = pmu->hrtimer_interval_ms;
	if (timer < 1)
		timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;

	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);

	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
	hr->function = perf_cpu_hrtimer_handler;
}

static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
{
	struct hrtimer *hr = &cpuctx->hrtimer;
	struct pmu *pmu = cpuctx->ctx.pmu;

	/* not for SW PMU */
	if (pmu->task_ctx_nr == perf_sw_context)
		return;

	if (hrtimer_active(hr))
		return;

	if (!hrtimer_callback_running(hr))
		__hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
					 0, HRTIMER_MODE_REL_PINNED, 0);
}

void perf_pmu_disable(struct pmu *pmu)
{
	int *count = this_cpu_ptr(pmu->pmu_disable_count);
	if (!(*count)++)
		pmu->pmu_disable(pmu);
}

void perf_pmu_enable(struct pmu *pmu)
{
	int *count = this_cpu_ptr(pmu->pmu_disable_count);
	if (!--(*count))
		pmu->pmu_enable(pmu);
}

static DEFINE_PER_CPU(struct list_head, rotation_list);

/*
 * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
 * because they're strictly cpu affine and rotate_start is called with IRQs
 * disabled, while rotate_context is called from IRQ context.
 */
static void perf_pmu_rotate_start(struct pmu *pmu)
{
	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
	struct list_head *head = &__get_cpu_var(rotation_list);

	WARN_ON(!irqs_disabled());

	if (list_empty(&cpuctx->rotation_list))
		list_add(&cpuctx->rotation_list, head);
}

static void get_ctx(struct perf_event_context *ctx)
{
	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
}

static void put_ctx(struct perf_event_context *ctx)
{
	if (atomic_dec_and_test(&ctx->refcount)) {
		if (ctx->parent_ctx)
			put_ctx(ctx->parent_ctx);
		if (ctx->task)
			put_task_struct(ctx->task);
		kfree_rcu(ctx, rcu_head);
	}
}

static void unclone_ctx(struct perf_event_context *ctx)
{
	if (ctx->parent_ctx) {
		put_ctx(ctx->parent_ctx);
		ctx->parent_ctx = NULL;
	}
	ctx->generation++;
}

static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
{
	/*
	 * only top level events have the pid namespace they were created in
	 */
	if (event->parent)
		event = event->parent;

	return task_tgid_nr_ns(p, event->ns);
}

static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
{
	/*
	 * only top level events have the pid namespace they were created in
	 */
	if (event->parent)
		event = event->parent;

	return task_pid_nr_ns(p, event->ns);
}

/*
 * If we inherit events we want to return the parent event id
 * to userspace.
 */
static u64 primary_event_id(struct perf_event *event)
{
	u64 id = event->id;

	if (event->parent)
		id = event->parent->id;

	return id;
}

/*
 * Get the perf_event_context for a task and lock it.
 * This has to cope with with the fact that until it is locked,
 * the context could get moved to another task.
 */
static struct perf_event_context *
perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
{
	struct perf_event_context *ctx;

retry:
	/*
	 * One of the few rules of preemptible RCU is that one cannot do
	 * rcu_read_unlock() while holding a scheduler (or nested) lock when
	 * part of the read side critical section was preemptible -- see
	 * rcu_read_unlock_special().
	 *
	 * Since ctx->lock nests under rq->lock we must ensure the entire read
	 * side critical section is non-preemptible.
	 */
	preempt_disable();
	rcu_read_lock();
	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
	if (ctx) {
		/*
		 * If this context is a clone of another, it might
		 * get swapped for another underneath us by
		 * perf_event_task_sched_out, though the
		 * rcu_read_lock() protects us from any context
		 * getting freed.  Lock the context and check if it
		 * got swapped before we could get the lock, and retry
		 * if so.  If we locked the right context, then it
		 * can't get swapped on us any more.
		 */
		raw_spin_lock_irqsave(&ctx->lock, *flags);
		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
			rcu_read_unlock();
			preempt_enable();
			goto retry;
		}

		if (!atomic_inc_not_zero(&ctx->refcount)) {
			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
			ctx = NULL;
		}
	}
	rcu_read_unlock();
	preempt_enable();
	return ctx;
}

/*
 * Get the context for a task and increment its pin_count so it
 * can't get swapped to another task.  This also increments its
 * reference count so that the context can't get freed.
 */
static struct perf_event_context *
perf_pin_task_context(struct task_struct *task, int ctxn)
{
	struct perf_event_context *ctx;
	unsigned long flags;

	ctx = perf_lock_task_context(task, ctxn, &flags);
	if (ctx) {
		++ctx->pin_count;
		raw_spin_unlock_irqrestore(&ctx->lock, flags);
	}
	return ctx;
}

static void perf_unpin_context(struct perf_event_context *ctx)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&ctx->lock, flags);
	--ctx->pin_count;
	raw_spin_unlock_irqrestore(&ctx->lock, flags);
}

/*
 * Update the record of the current time in a context.
 */
static void update_context_time(struct perf_event_context *ctx)
{
	u64 now = perf_clock();

	ctx->time += now - ctx->timestamp;
	ctx->timestamp = now;
}

static u64 perf_event_time(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;

	if (is_cgroup_event(event))
		return perf_cgroup_event_time(event);

	return ctx ? ctx->time : 0;
}

/*
 * Update the total_time_enabled and total_time_running fields for a event.
 * The caller of this function needs to hold the ctx->lock.
 */
static void update_event_times(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;
	u64 run_end;

	if (event->state < PERF_EVENT_STATE_INACTIVE ||
	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
		return;
	/*
	 * in cgroup mode, time_enabled represents
	 * the time the event was enabled AND active
	 * tasks were in the monitored cgroup. This is
	 * independent of the activity of the context as
	 * there may be a mix of cgroup and non-cgroup events.
	 *
	 * That is why we treat cgroup events differently
	 * here.
	 */
	if (is_cgroup_event(event))
		run_end = perf_cgroup_event_time(event);
	else if (ctx->is_active)
		run_end = ctx->time;
	else
		run_end = event->tstamp_stopped;

	event->total_time_enabled = run_end - event->tstamp_enabled;

	if (event->state == PERF_EVENT_STATE_INACTIVE)
		run_end = event->tstamp_stopped;
	else
		run_end = perf_event_time(event);

	event->total_time_running = run_end - event->tstamp_running;

}

/*
 * Update total_time_enabled and total_time_running for all events in a group.
 */
static void update_group_times(struct perf_event *leader)
{
	struct perf_event *event;

	update_event_times(leader);
	list_for_each_entry(event, &leader->sibling_list, group_entry)
		update_event_times(event);
}

static struct list_head *
ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
{
	if (event->attr.pinned)
		return &ctx->pinned_groups;
	else
		return &ctx->flexible_groups;
}

/*
 * Add a event from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
	event->attach_state |= PERF_ATTACH_CONTEXT;

	/*
	 * If we're a stand alone event or group leader, we go to the context
	 * list, group events are kept attached to the group so that
	 * perf_group_detach can, at all times, locate all siblings.
	 */
	if (event->group_leader == event) {
		struct list_head *list;

		if (is_software_event(event))
			event->group_flags |= PERF_GROUP_SOFTWARE;

		list = ctx_group_list(event, ctx);
		list_add_tail(&event->group_entry, list);
	}

	if (is_cgroup_event(event))
		ctx->nr_cgroups++;

	if (has_branch_stack(event))
		ctx->nr_branch_stack++;

	list_add_rcu(&event->event_entry, &ctx->event_list);
	if (!ctx->nr_events)
		perf_pmu_rotate_start(ctx->pmu);
	ctx->nr_events++;
	if (event->attr.inherit_stat)
		ctx->nr_stat++;

	ctx->generation++;
}

/*
 * Initialize event state based on the perf_event_attr::disabled.
 */
static inline void perf_event__state_init(struct perf_event *event)
{
	event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
					      PERF_EVENT_STATE_INACTIVE;
}

/*
 * Called at perf_event creation and when events are attached/detached from a
 * group.
 */
static void perf_event__read_size(struct perf_event *event)
{
	int entry = sizeof(u64); /* value */
	int size = 0;
	int nr = 1;

	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		size += sizeof(u64);

	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		size += sizeof(u64);

	if (event->attr.read_format & PERF_FORMAT_ID)
		entry += sizeof(u64);

	if (event->attr.read_format & PERF_FORMAT_GROUP) {
		nr += event->group_leader->nr_siblings;
		size += sizeof(u64);
	}

	size += entry * nr;
	event->read_size = size;
}

static void perf_event__header_size(struct perf_event *event)
{
	struct perf_sample_data *data;
	u64 sample_type = event->attr.sample_type;
	u16 size = 0;

	perf_event__read_size(event);

	if (sample_type & PERF_SAMPLE_IP)
		size += sizeof(data->ip);

	if (sample_type & PERF_SAMPLE_ADDR)
		size += sizeof(data->addr);

	if (sample_type & PERF_SAMPLE_PERIOD)
		size += sizeof(data->period);

	if (sample_type & PERF_SAMPLE_WEIGHT)
		size += sizeof(data->weight);

	if (sample_type & PERF_SAMPLE_READ)
		size += event->read_size;

	if (sample_type & PERF_SAMPLE_DATA_SRC)
		size += sizeof(data->data_src.val);

	if (sample_type & PERF_SAMPLE_TRANSACTION)
		size += sizeof(data->txn);

	event->header_size = size;
}

static void perf_event__id_header_size(struct perf_event *event)
{
	struct perf_sample_data *data;
	u64 sample_type = event->attr.sample_type;
	u16 size = 0;

	if (sample_type & PERF_SAMPLE_TID)
		size += sizeof(data->tid_entry);

	if (sample_type & PERF_SAMPLE_TIME)
		size += sizeof(data->time);

	if (sample_type & PERF_SAMPLE_IDENTIFIER)
		size += sizeof(data->id);

	if (sample_type & PERF_SAMPLE_ID)
		size += sizeof(data->id);

	if (sample_type & PERF_SAMPLE_STREAM_ID)
		size += sizeof(data->stream_id);

	if (sample_type & PERF_SAMPLE_CPU)
		size += sizeof(data->cpu_entry);

	event->id_header_size = size;
}

static void perf_group_attach(struct perf_event *event)
{
	struct perf_event *group_leader = event->group_leader, *pos;

	/*
	 * We can have double attach due to group movement in perf_event_open.
	 */
	if (event->attach_state & PERF_ATTACH_GROUP)
		return;

	event->attach_state |= PERF_ATTACH_GROUP;

	if (group_leader == event)
		return;

	if (group_leader->group_flags & PERF_GROUP_SOFTWARE &&
			!is_software_event(event))
		group_leader->group_flags &= ~PERF_GROUP_SOFTWARE;

	list_add_tail(&event->group_entry, &group_leader->sibling_list);
	group_leader->nr_siblings++;

	perf_event__header_size(group_leader);

	list_for_each_entry(pos, &group_leader->sibling_list, group_entry)
		perf_event__header_size(pos);
}

/*
 * Remove a event from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
static void
list_del_event(struct perf_event *event, struct perf_event_context *ctx)
{
	struct perf_cpu_context *cpuctx;
	/*
	 * We can have double detach due to exit/hot-unplug + close.
	 */
	if (!(event->attach_state & PERF_ATTACH_CONTEXT))
		return;

	event->attach_state &= ~PERF_ATTACH_CONTEXT;

	if (is_cgroup_event(event)) {
		ctx->nr_cgroups--;
		cpuctx = __get_cpu_context(ctx);
		/*
		 * if there are no more cgroup events
		 * then cler cgrp to avoid stale pointer
		 * in update_cgrp_time_from_cpuctx()
		 */
		if (!ctx->nr_cgroups)
			cpuctx->cgrp = NULL;
	}

	if (has_branch_stack(event))
		ctx->nr_branch_stack--;

	ctx->nr_events--;
	if (event->attr.inherit_stat)
		ctx->nr_stat--;

	list_del_rcu(&event->event_entry);

	if (event->group_leader == event)
		list_del_init(&event->group_entry);

	update_group_times(event);

	/*
	 * If event was in error state, then keep it
	 * that way, otherwise bogus counts will be
	 * returned on read(). The only way to get out
	 * of error state is by explicit re-enabling
	 * of the event
	 */
	if (event->state > PERF_EVENT_STATE_OFF)
		event->state = PERF_EVENT_STATE_OFF;

	ctx->generation++;
}

static void perf_group_detach(struct perf_event *event)
{
	struct perf_event *sibling, *tmp;
	struct list_head *list = NULL;

	/*
	 * We can have double detach due to exit/hot-unplug + close.
	 */
	if (!(event->attach_state & PERF_ATTACH_GROUP))
		return;

	event->attach_state &= ~PERF_ATTACH_GROUP;

	/*
	 * If this is a sibling, remove it from its group.
	 */
	if (event->group_leader != event) {
		list_del_init(&event->group_entry);
		event->group_leader->nr_siblings--;
		goto out;
	}

	if (!list_empty(&event->group_entry))
		list = &event->group_entry;

	/*
	 * If this was a group event with sibling events then
	 * upgrade the siblings to singleton events by adding them
	 * to whatever list we are on.
	 */
	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, group_entry) {
		if (list)
			list_move_tail(&sibling->group_entry, list);
		sibling->group_leader = sibling;

		/* Inherit group flags from the previous leader */
		sibling->group_flags = event->group_flags;
	}

out:
	perf_event__header_size(event->group_leader);

	list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry)
		perf_event__header_size(tmp);
}

static inline int
event_filter_match(struct perf_event *event)
{
	return (event->cpu == -1 || event->cpu == smp_processor_id())
	    && perf_cgroup_match(event);
}

static void
event_sched_out(struct perf_event *event,
		  struct perf_cpu_context *cpuctx,
		  struct perf_event_context *ctx)
{
	u64 tstamp = perf_event_time(event);
	u64 delta;
	/*
	 * An event which could not be activated because of
	 * filter mismatch still needs to have its timings
	 * maintained, otherwise bogus information is return
	 * via read() for time_enabled, time_running:
	 */
	if (event->state == PERF_EVENT_STATE_INACTIVE
	    && !event_filter_match(event)) {
		delta = tstamp - event->tstamp_stopped;
		event->tstamp_running += delta;
		event->tstamp_stopped = tstamp;
	}

	if (event->state != PERF_EVENT_STATE_ACTIVE)
		return;

	perf_pmu_disable(event->pmu);

	event->state = PERF_EVENT_STATE_INACTIVE;
	if (event->pending_disable) {
		event->pending_disable = 0;
		event->state = PERF_EVENT_STATE_OFF;
	}
	event->tstamp_stopped = tstamp;
	event->pmu->del(event, 0);
	event->oncpu = -1;

	if (!is_software_event(event))
		cpuctx->active_oncpu--;
	ctx->nr_active--;
	if (event->attr.freq && event->attr.sample_freq)
		ctx->nr_freq--;
	if (event->attr.exclusive || !cpuctx->active_oncpu)
		cpuctx->exclusive = 0;

	perf_pmu_enable(event->pmu);
}

static void
group_sched_out(struct perf_event *group_event,
		struct perf_cpu_context *cpuctx,
		struct perf_event_context *ctx)
{
	struct perf_event *event;
	int state = group_event->state;

	event_sched_out(group_event, cpuctx, ctx);

	/*
	 * Schedule out siblings (if any):
	 */
	list_for_each_entry(event, &group_event->sibling_list, group_entry)
		event_sched_out(event, cpuctx, ctx);

	if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive)
		cpuctx->exclusive = 0;
}

/*
 * Cross CPU call to remove a performance event
 *
 * We disable the event on the hardware level first. After that we
 * remove it from the context list.
 */
static int __perf_remove_from_context(void *info)
{
	struct perf_event *event = info;
	struct perf_event_context *ctx = event->ctx;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);

	raw_spin_lock(&ctx->lock);
	event_sched_out(event, cpuctx, ctx);
	list_del_event(event, ctx);
	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
		ctx->is_active = 0;
		cpuctx->task_ctx = NULL;
	}
	raw_spin_unlock(&ctx->lock);

	return 0;
}


/*
 * Remove the event from a task's (or a CPU's) list of events.
 *
 * CPU events are removed with a smp call. For task events we only
 * call when the task is on a CPU.
 *
 * If event->ctx is a cloned context, callers must make sure that
 * every task struct that event->ctx->task could possibly point to
 * remains valid.  This is OK when called from perf_release since
 * that only calls us on the top-level context, which can't be a clone.
 * When called from perf_event_exit_task, it's OK because the
 * context has been detached from its task.
 */
static void perf_remove_from_context(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;
	struct task_struct *task = ctx->task;

	lockdep_assert_held(&ctx->mutex);

	if (!task) {
		/*
		 * Per cpu events are removed via an smp call and
		 * the removal is always successful.
		 */
		cpu_function_call(event->cpu, __perf_remove_from_context, event);
		return;
	}

retry:
	if (!task_function_call(task, __perf_remove_from_context, event))
		return;

	raw_spin_lock_irq(&ctx->lock);
	/*
	 * If we failed to find a running task, but find the context active now
	 * that we've acquired the ctx->lock, retry.
	 */
	if (ctx->is_active) {
		raw_spin_unlock_irq(&ctx->lock);
		goto retry;
	}

	/*
	 * Since the task isn't running, its safe to remove the event, us
	 * holding the ctx->lock ensures the task won't get scheduled in.
	 */
	list_del_event(event, ctx);
	raw_spin_unlock_irq(&ctx->lock);
}

/*
 * Cross CPU call to disable a performance event
 */
int __perf_event_disable(void *info)
{
	struct perf_event *event = info;
	struct perf_event_context *ctx = event->ctx;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);

	/*
	 * If this is a per-task event, need to check whether this
	 * event's task is the current task on this cpu.
	 *
	 * Can trigger due to concurrent perf_event_context_sched_out()
	 * flipping contexts around.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx)
		return -EINVAL;

	raw_spin_lock(&ctx->lock);

	/*
	 * If the event is on, turn it off.
	 * If it is in error state, leave it in error state.
	 */
	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
		update_context_time(ctx);
		update_cgrp_time_from_event(event);
		update_group_times(event);
		if (event == event->group_leader)
			group_sched_out(event, cpuctx, ctx);
		else
			event_sched_out(event, cpuctx, ctx);
		event->state = PERF_EVENT_STATE_OFF;
	}

	raw_spin_unlock(&ctx->lock);

	return 0;
}

/*
 * Disable a event.
 *
 * If event->ctx is a cloned context, callers must make sure that
 * every task struct that event->ctx->task could possibly point to
 * remains valid.  This condition is satisifed when called through
 * perf_event_for_each_child or perf_event_for_each because they
 * hold the top-level event's child_mutex, so any descendant that
 * goes to exit will block in sync_child_event.
 * When called from perf_pending_event it's OK because event->ctx
 * is the current context on this CPU and preemption is disabled,
 * hence we can't get into perf_event_task_sched_out for this context.
 */
void perf_event_disable(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;
	struct task_struct *task = ctx->task;

	if (!task) {
		/*
		 * Disable the event on the cpu that it's on
		 */
		cpu_function_call(event->cpu, __perf_event_disable, event);
		return;
	}

retry:
	if (!task_function_call(task, __perf_event_disable, event))
		return;

	raw_spin_lock_irq(&ctx->lock);
	/*
	 * If the event is still active, we need to retry the cross-call.
	 */
	if (event->state == PERF_EVENT_STATE_ACTIVE) {
		raw_spin_unlock_irq(&ctx->lock);
		/*
		 * Reload the task pointer, it might have been changed by
		 * a concurrent perf_event_context_sched_out().
		 */
		task = ctx->task;
		goto retry;
	}

	/*
	 * Since we have the lock this context can't be scheduled
	 * in, so we can change the state safely.
	 */
	if (event->state == PERF_EVENT_STATE_INACTIVE) {
		update_group_times(event);
		event->state = PERF_EVENT_STATE_OFF;
	}
	raw_spin_unlock_irq(&ctx->lock);
}
EXPORT_SYMBOL_GPL(perf_event_disable);

static void perf_set_shadow_time(struct perf_event *event,
				 struct perf_event_context *ctx,
				 u64 tstamp)
{
	/*
	 * use the correct time source for the time snapshot
	 *
	 * We could get by without this by leveraging the
	 * fact that to get to this function, the caller
	 * has most likely already called update_context_time()
	 * and update_cgrp_time_xx() and thus both timestamp
	 * are identical (or very close). Given that tstamp is,
	 * already adjusted for cgroup, we could say that:
	 *    tstamp - ctx->timestamp
	 * is equivalent to
	 *    tstamp - cgrp->timestamp.
	 *
	 * Then, in perf_output_read(), the calculation would
	 * work with no changes because:
	 * - event is guaranteed scheduled in
	 * - no scheduled out in between
	 * - thus the timestamp would be the same
	 *
	 * But this is a bit hairy.
	 *
	 * So instead, we have an explicit cgroup call to remain
	 * within the time time source all along. We believe it
	 * is cleaner and simpler to understand.
	 */
	if (is_cgroup_event(event))
		perf_cgroup_set_shadow_time(event, tstamp);
	else
		event->shadow_ctx_time = tstamp - ctx->timestamp;
}

#define MAX_INTERRUPTS (~0ULL)

static void perf_log_throttle(struct perf_event *event, int enable);

static int
event_sched_in(struct perf_event *event,
		 struct perf_cpu_context *cpuctx,
		 struct perf_event_context *ctx)
{
	u64 tstamp = perf_event_time(event);
	int ret = 0;

	if (event->state <= PERF_EVENT_STATE_OFF)
		return 0;

	event->state = PERF_EVENT_STATE_ACTIVE;
	event->oncpu = smp_processor_id();

	/*
	 * Unthrottle events, since we scheduled we might have missed several
	 * ticks already, also for a heavily scheduling task there is little
	 * guarantee it'll get a tick in a timely manner.
	 */
	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
		perf_log_throttle(event, 1);
		event->hw.interrupts = 0;
	}

	/*
	 * The new state must be visible before we turn it on in the hardware:
	 */
	smp_wmb();

	perf_pmu_disable(event->pmu);

	if (event->pmu->add(event, PERF_EF_START)) {
		event->state = PERF_EVENT_STATE_INACTIVE;
		event->oncpu = -1;
		ret = -EAGAIN;
		goto out;
	}

	event->tstamp_running += tstamp - event->tstamp_stopped;

	perf_set_shadow_time(event, ctx, tstamp);

	if (!is_software_event(event))
		cpuctx->active_oncpu++;
	ctx->nr_active++;
	if (event->attr.freq && event->attr.sample_freq)
		ctx->nr_freq++;

	if (event->attr.exclusive)
		cpuctx->exclusive = 1;

out:
	perf_pmu_enable(event->pmu);

	return ret;
}

static int
group_sched_in(struct perf_event *group_event,
	       struct perf_cpu_context *cpuctx,
	       struct perf_event_context *ctx)
{
	struct perf_event *event, *partial_group = NULL;
	struct pmu *pmu = ctx->pmu;
	u64 now = ctx->time;
	bool simulate = false;

	if (group_event->state == PERF_EVENT_STATE_OFF)
		return 0;

	pmu->start_txn(pmu);

	if (event_sched_in(group_event, cpuctx, ctx)) {
		pmu->cancel_txn(pmu);
		perf_cpu_hrtimer_restart(cpuctx);
		return -EAGAIN;
	}

	/*
	 * Schedule in siblings as one group (if any):
	 */
	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
		if (event_sched_in(event, cpuctx, ctx)) {
			partial_group = event;
			goto group_error;
		}
	}

	if (!pmu->commit_txn(pmu))
		return 0;

group_error:
	/*
	 * Groups can be scheduled in as one unit only, so undo any
	 * partial group before returning:
	 * The events up to the failed event are scheduled out normally,
	 * tstamp_stopped will be updated.
	 *
	 * The failed events and the remaining siblings need to have
	 * their timings updated as if they had gone thru event_sched_in()
	 * and event_sched_out(). This is required to get consistent timings
	 * across the group. This also takes care of the case where the group
	 * could never be scheduled by ensuring tstamp_stopped is set to mark
	 * the time the event was actually stopped, such that time delta
	 * calculation in update_event_times() is correct.
	 */
	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
		if (event == partial_group)
			simulate = true;

		if (simulate) {
			event->tstamp_running += now - event->tstamp_stopped;
			event->tstamp_stopped = now;
		} else {
			event_sched_out(event, cpuctx, ctx);
		}
	}
	event_sched_out(group_event, cpuctx, ctx);

	pmu->cancel_txn(pmu);

	perf_cpu_hrtimer_restart(cpuctx);

	return -EAGAIN;
}

/*
 * Work out whether we can put this event group on the CPU now.
 */
static int group_can_go_on(struct perf_event *event,
			   struct perf_cpu_context *cpuctx,
			   int can_add_hw)
{
	/*
	 * Groups consisting entirely of software events can always go on.
	 */
	if (event->group_flags & PERF_GROUP_SOFTWARE)
		return 1;
	/*
	 * If an exclusive group is already on, no other hardware
	 * events can go on.
	 */
	if (cpuctx->exclusive)
		return 0;
	/*
	 * If this group is exclusive and there are already
	 * events on the CPU, it can't go on.
	 */
	if (event->attr.exclusive && cpuctx->active_oncpu)
		return 0;
	/*
	 * Otherwise, try to add it if all previous groups were able
	 * to go on.
	 */
	return can_add_hw;
}

static void add_event_to_ctx(struct perf_event *event,
			       struct perf_event_context *ctx)
{
	u64 tstamp = perf_event_time(event);

	list_add_event(event, ctx);
	perf_group_attach(event);
	event->tstamp_enabled = tstamp;
	event->tstamp_running = tstamp;
	event->tstamp_stopped = tstamp;
}

static void task_ctx_sched_out(struct perf_event_context *ctx);
static void
ctx_sched_in(struct perf_event_context *ctx,
	     struct perf_cpu_context *cpuctx,
	     enum event_type_t event_type,
	     struct task_struct *task);

static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
				struct perf_event_context *ctx,
				struct task_struct *task)
{
	cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task);
	if (ctx)
		ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
	if (ctx)
		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}

/*
 * Cross CPU call to install and enable a performance event
 *
 * Must be called with ctx->mutex held
 */
static int  __perf_install_in_context(void *info)
{
	struct perf_event *event = info;
	struct perf_event_context *ctx = event->ctx;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
	struct perf_event_context *task_ctx = cpuctx->task_ctx;
	struct task_struct *task = current;

	perf_ctx_lock(cpuctx, task_ctx);
	perf_pmu_disable(cpuctx->ctx.pmu);

	/*
	 * If there was an active task_ctx schedule it out.
	 */
	if (task_ctx)
		task_ctx_sched_out(task_ctx);

	/*
	 * If the context we're installing events in is not the
	 * active task_ctx, flip them.
	 */
	if (ctx->task && task_ctx != ctx) {
		if (task_ctx)
			raw_spin_unlock(&task_ctx->lock);
		raw_spin_lock(&ctx->lock);
		task_ctx = ctx;
	}

	if (task_ctx) {
		cpuctx->task_ctx = task_ctx;
		task = task_ctx->task;
	}

	cpu_ctx_sched_out(cpuctx, EVENT_ALL);

	update_context_time(ctx);
	/*
	 * update cgrp time only if current cgrp
	 * matches event->cgrp. Must be done before
	 * calling add_event_to_ctx()
	 */
	update_cgrp_time_from_event(event);

	add_event_to_ctx(event, ctx);

	/*
	 * Schedule everything back in
	 */
	perf_event_sched_in(cpuctx, task_ctx, task);

	perf_pmu_enable(cpuctx->ctx.pmu);
	perf_ctx_unlock(cpuctx, task_ctx);

	return 0;
}

/*
 * Attach a performance event to a context
 *
 * First we add the event to the list with the hardware enable bit
 * in event->hw_config cleared.
 *
 * If the event is attached to a task which is on a CPU we use a smp
 * call to enable it in the task context. The task might have been
 * scheduled away, but we check this in the smp call again.
 */
static void
perf_install_in_context(struct perf_event_context *ctx,
			struct perf_event *event,
			int cpu)
{
	struct task_struct *task = ctx->task;

	lockdep_assert_held(&ctx->mutex);

	event->ctx = ctx;
	if (event->cpu != -1)
		event->cpu = cpu;

	if (!task) {
		/*
		 * Per cpu events are installed via an smp call and
		 * the install is always successful.
		 */
		cpu_function_call(cpu, __perf_install_in_context, event);
		return;
	}

retry:
	if (!task_function_call(task, __perf_install_in_context, event))
		return;

	raw_spin_lock_irq(&ctx->lock);
	/*
	 * If we failed to find a running task, but find the context active now
	 * that we've acquired the ctx->lock, retry.
	 */
	if (ctx->is_active) {
		raw_spin_unlock_irq(&ctx->lock);
		goto retry;
	}

	/*
	 * Since the task isn't running, its safe to add the event, us holding
	 * the ctx->lock ensures the task won't get scheduled in.
	 */
	add_event_to_ctx(event, ctx);
	raw_spin_unlock_irq(&ctx->lock);
}

/*
 * Put a event into inactive state and update time fields.
 * Enabling the leader of a group effectively enables all
 * the group members that aren't explicitly disabled, so we
 * have to update their ->tstamp_enabled also.
 * Note: this works for group members as well as group leaders
 * since the non-leader members' sibling_lists will be empty.
 */
static void __perf_event_mark_enabled(struct perf_event *event)
{
	struct perf_event *sub;
	u64 tstamp = perf_event_time(event);

	event->state = PERF_EVENT_STATE_INACTIVE;
	event->tstamp_enabled = tstamp - event->total_time_enabled;
	list_for_each_entry(sub, &event->sibling_list, group_entry) {
		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
	}
}

/*
 * Cross CPU call to enable a performance event
 */
static int __perf_event_enable(void *info)
{
	struct perf_event *event = info;
	struct perf_event_context *ctx = event->ctx;
	struct perf_event *leader = event->group_leader;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
	int err;

	/*
	 * There's a time window between 'ctx->is_active' check
	 * in perf_event_enable function and this place having:
	 *   - IRQs on
	 *   - ctx->lock unlocked
	 *
	 * where the task could be killed and 'ctx' deactivated
	 * by perf_event_exit_task.
	 */
	if (!ctx->is_active)
		return -EINVAL;

	raw_spin_lock(&ctx->lock);
	update_context_time(ctx);

	if (event->state >= PERF_EVENT_STATE_INACTIVE)
		goto unlock;

	/*
	 * set current task's cgroup time reference point
	 */
	perf_cgroup_set_timestamp(current, ctx);

	__perf_event_mark_enabled(event);

	if (!event_filter_match(event)) {
		if (is_cgroup_event(event))
			perf_cgroup_defer_enabled(event);
		goto unlock;
	}

	/*
	 * If the event is in a group and isn't the group leader,
	 * then don't put it on unless the group is on.
	 */
	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
		goto unlock;

	if (!group_can_go_on(event, cpuctx, 1)) {
		err = -EEXIST;
	} else {
		if (event == leader)
			err = group_sched_in(event, cpuctx, ctx);
		else
			err = event_sched_in(event, cpuctx, ctx);
	}

	if (err) {
		/*
		 * If this event can't go on and it's part of a
		 * group, then the whole group has to come off.
		 */
		if (leader != event) {
			group_sched_out(leader, cpuctx, ctx);
			perf_cpu_hrtimer_restart(cpuctx);
		}
		if (leader->attr.pinned) {
			update_group_times(leader);
			leader->state = PERF_EVENT_STATE_ERROR;
		}
	}

unlock:
	raw_spin_unlock(&ctx->lock);

	return 0;
}

/*
 * Enable a event.
 *
 * If event->ctx is a cloned context, callers must make sure that
 * every task struct that event->ctx->task could possibly point to
 * remains valid.  This condition is satisfied when called through
 * perf_event_for_each_child or perf_event_for_each as described
 * for perf_event_disable.
 */
void perf_event_enable(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;
	struct task_struct *task = ctx->task;

	if (!task) {
		/*
		 * Enable the event on the cpu that it's on
		 */
		cpu_function_call(event->cpu, __perf_event_enable, event);
		return;
	}

	raw_spin_lock_irq(&ctx->lock);
	if (event->state >= PERF_EVENT_STATE_INACTIVE)
		goto out;

	/*
	 * If the event is in error state, clear that first.
	 * That way, if we see the event in error state below, we
	 * know that it has gone back into error state, as distinct
	 * from the task having been scheduled away before the
	 * cross-call arrived.
	 */
	if (event->state == PERF_EVENT_STATE_ERROR)
		event->state = PERF_EVENT_STATE_OFF;

retry:
	if (!ctx->is_active) {
		__perf_event_mark_enabled(event);
		goto out;
	}

	raw_spin_unlock_irq(&ctx->lock);

	if (!task_function_call(task, __perf_event_enable, event))
		return;

	raw_spin_lock_irq(&ctx->lock);

	/*
	 * If the context is active and the event is still off,
	 * we need to retry the cross-call.
	 */
	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
		/*
		 * task could have been flipped by a concurrent
		 * perf_event_context_sched_out()
		 */
		task = ctx->task;
		goto retry;
	}

out:
	raw_spin_unlock_irq(&ctx->lock);
}
EXPORT_SYMBOL_GPL(perf_event_enable);

int perf_event_refresh(struct perf_event *event, int refresh)
{
	/*
	 * not supported on inherited events
	 */
	if (event->attr.inherit || !is_sampling_event(event))
		return -EINVAL;

	atomic_add(refresh, &event->event_limit);
	perf_event_enable(event);

	return 0;
}
EXPORT_SYMBOL_GPL(perf_event_refresh);

static void ctx_sched_out(struct perf_event_context *ctx,
			  struct perf_cpu_context *cpuctx,
			  enum event_type_t event_type)
{
	struct perf_event *event;
	int is_active = ctx->is_active;

	ctx->is_active &= ~event_type;
	if (likely(!ctx->nr_events))
		return;

	update_context_time(ctx);
	update_cgrp_time_from_cpuctx(cpuctx);
	if (!ctx->nr_active)
		return;

	perf_pmu_disable(ctx->pmu);
	if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) {
		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
			group_sched_out(event, cpuctx, ctx);
	}

	if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) {
		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
			group_sched_out(event, cpuctx, ctx);
	}
	perf_pmu_enable(ctx->pmu);
}

/*
 * Test whether two contexts are equivalent, i.e. whether they have both been
 * cloned from the same version of the same context.
 *
 * Equivalence is measured using a generation number in the context that is
 * incremented on each modification to it; see unclone_ctx(), list_add_event()
 * and list_del_event().
 */
static int context_equiv(struct perf_event_context *ctx1,
			 struct perf_event_context *ctx2)
{
	/* Pinning disables the swap optimization */
	if (ctx1->pin_count || ctx2->pin_count)
		return 0;

	/* If ctx1 is the parent of ctx2 */
	if (ctx1 == ctx2->parent_ctx && ctx1->generation == ctx2->parent_gen)
		return 1;

	/* If ctx2 is the parent of ctx1 */
	if (ctx1->parent_ctx == ctx2 && ctx1->parent_gen == ctx2->generation)
		return 1;

	/*
	 * If ctx1 and ctx2 have the same parent; we flatten the parent
	 * hierarchy, see perf_event_init_context().
	 */
	if (ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx &&
			ctx1->parent_gen == ctx2->parent_gen)
		return 1;

	/* Unmatched */
	return 0;
}

static void __perf_event_sync_stat(struct perf_event *event,
				     struct perf_event *next_event)
{
	u64 value;

	if (!event->attr.inherit_stat)
		return;

	/*
	 * Update the event value, we cannot use perf_event_read()
	 * because we're in the middle of a context switch and have IRQs
	 * disabled, which upsets smp_call_function_single(), however
	 * we know the event must be on the current CPU, therefore we
	 * don't need to use it.
	 */
	switch (event->state) {
	case PERF_EVENT_STATE_ACTIVE:
		event->pmu->read(event);
		/* fall-through */

	case PERF_EVENT_STATE_INACTIVE:
		update_event_times(event);
		break;

	default:
		break;
	}

	/*
	 * In order to keep per-task stats reliable we need to flip the event
	 * values when we flip the contexts.
	 */
	value = local64_read(&next_event->count);
	value = local64_xchg(&event->count, value);
	local64_set(&next_event->count, value);

	swap(event->total_time_enabled, next_event->total_time_enabled);
	swap(event->total_time_running, next_event->total_time_running);

	/*
	 * Since we swizzled the values, update the user visible data too.
	 */
	perf_event_update_userpage(event);
	perf_event_update_userpage(next_event);
}

static void perf_event_sync_stat(struct perf_event_context *ctx,
				   struct perf_event_context *next_ctx)
{
	struct perf_event *event, *next_event;

	if (!ctx->nr_stat)
		return;

	update_context_time(ctx);

	event = list_first_entry(&ctx->event_list,
				   struct perf_event, event_entry);

	next_event = list_first_entry(&next_ctx->event_list,
					struct perf_event, event_entry);

	while (&event->event_entry != &ctx->event_list &&
	       &next_event->event_entry != &next_ctx->event_list) {

		__perf_event_sync_stat(event, next_event);

		event = list_next_entry(event, event_entry);
		next_event = list_next_entry(next_event, event_entry);
	}
}

static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
					 struct task_struct *next)
{
	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
	struct perf_event_context *next_ctx;
	struct perf_event_context *parent, *next_parent;
	struct perf_cpu_context *cpuctx;
	int do_switch = 1;

	if (likely(!ctx))
		return;

	cpuctx = __get_cpu_context(ctx);
	if (!cpuctx->task_ctx)
		return;

	rcu_read_lock();
	next_ctx = next->perf_event_ctxp[ctxn];
	if (!next_ctx)
		goto unlock;

	parent = rcu_dereference(ctx->parent_ctx);
	next_parent = rcu_dereference(next_ctx->parent_ctx);

	/* If neither context have a parent context; they cannot be clones. */
	if (!parent && !next_parent)
		goto unlock;

	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
		/*
		 * Looks like the two contexts are clones, so we might be
		 * able to optimize the context switch.  We lock both
		 * contexts and check that they are clones under the
		 * lock (including re-checking that neither has been
		 * uncloned in the meantime).  It doesn't matter which
		 * order we take the locks because no other cpu could
		 * be trying to lock both of these tasks.
		 */
		raw_spin_lock(&ctx->lock);
		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
		if (context_equiv(ctx, next_ctx)) {
			/*
			 * XXX do we need a memory barrier of sorts
			 * wrt to rcu_dereference() of perf_event_ctxp
			 */
			task->perf_event_ctxp[ctxn] = next_ctx;
			next->perf_event_ctxp[ctxn] = ctx;
			ctx->task = next;
			next_ctx->task = task;
			do_switch = 0;

			perf_event_sync_stat(ctx, next_ctx);
		}
		raw_spin_unlock(&next_ctx->lock);
		raw_spin_unlock(&ctx->lock);
	}
unlock:
	rcu_read_unlock();

	if (do_switch) {
		raw_spin_lock(&ctx->lock);
		ctx_sched_out(ctx, cpuctx, EVENT_ALL);
		cpuctx->task_ctx = NULL;
		raw_spin_unlock(&ctx->lock);
	}
}

#define for_each_task_context_nr(ctxn)					\
	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)

/*
 * Called from scheduler to remove the events of the current task,
 * with interrupts disabled.
 *
 * We stop each event and update the event value in event->count.
 *
 * This does not protect us against NMI, but disable()
 * sets the disabled bit in the control field of event _before_
 * accessing the event control register. If a NMI hits, then it will
 * not restart the event.
 */
void __perf_event_task_sched_out(struct task_struct *task,
				 struct task_struct *next)
{
	int ctxn;

	for_each_task_context_nr(ctxn)
		perf_event_context_sched_out(task, ctxn, next);

	/*
	 * if cgroup events exist on this CPU, then we need
	 * to check if we have to switch out PMU state.
	 * cgroup event are system-wide mode only
	 */
	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
		perf_cgroup_sched_out(task, next);
}

static void task_ctx_sched_out(struct perf_event_context *ctx)
{
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);

	if (!cpuctx->task_ctx)
		return;

	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
		return;

	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
	cpuctx->task_ctx = NULL;
}

/*
 * Called with IRQs disabled
 */
static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
			      enum event_type_t event_type)
{
	ctx_sched_out(&cpuctx->ctx, cpuctx, event_type);
}

static void
ctx_pinned_sched_in(struct perf_event_context *ctx,
		    struct perf_cpu_context *cpuctx)
{
	struct perf_event *event;

	list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
		if (event->state <= PERF_EVENT_STATE_OFF)
			continue;
		if (!event_filter_match(event))
			continue;

		/* may need to reset tstamp_enabled */
		if (is_cgroup_event(event))
			perf_cgroup_mark_enabled(event, ctx);

		if (group_can_go_on(event, cpuctx, 1))
			group_sched_in(event, cpuctx, ctx);

		/*
		 * If this pinned group hasn't been scheduled,
		 * put it in error state.
		 */
		if (event->state == PERF_EVENT_STATE_INACTIVE) {
			update_group_times(event);
			event->state = PERF_EVENT_STATE_ERROR;
		}
	}
}

static void
ctx_flexible_sched_in(struct perf_event_context *ctx,
		      struct perf_cpu_context *cpuctx)
{
	struct perf_event *event;
	int can_add_hw = 1;

	list_for_each_entry(event, &ctx->flexible_groups, group_entry) {
		/* Ignore events in OFF or ERROR state */
		if (event->state <= PERF_EVENT_STATE_OFF)
			continue;
		/*
		 * Listen to the 'cpu' scheduling filter constraint
		 * of events:
		 */
		if (!event_filter_match(event))
			continue;

		/* may need to reset tstamp_enabled */
		if (is_cgroup_event(event))
			perf_cgroup_mark_enabled(event, ctx);

		if (group_can_go_on(event, cpuctx, can_add_hw)) {
			if (group_sched_in(event, cpuctx, ctx))
				can_add_hw = 0;
		}
	}
}

static void
ctx_sched_in(struct perf_event_context *ctx,
	     struct perf_cpu_context *cpuctx,
	     enum event_type_t event_type,
	     struct task_struct *task)
{
	u64 now;
	int is_active = ctx->is_active;

	ctx->is_active |= event_type;
	if (likely(!ctx->nr_events))
		return;

	now = perf_clock();
	ctx->timestamp = now;
	perf_cgroup_set_timestamp(task, ctx);
	/*
	 * First go through the list and put on any pinned groups
	 * in order to give them the best chance of going on.
	 */
	if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED))
		ctx_pinned_sched_in(ctx, cpuctx);

	/* Then walk through the lower prio flexible groups */
	if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE))
		ctx_flexible_sched_in(ctx, cpuctx);
}

static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
			     enum event_type_t event_type,
			     struct task_struct *task)
{
	struct perf_event_context *ctx = &cpuctx->ctx;

	ctx_sched_in(ctx, cpuctx, event_type, task);
}

static void perf_event_context_sched_in(struct perf_event_context *ctx,
					struct task_struct *task)
{
	struct perf_cpu_context *cpuctx;

	cpuctx = __get_cpu_context(ctx);
	if (cpuctx->task_ctx == ctx)
		return;

	perf_ctx_lock(cpuctx, ctx);
	perf_pmu_disable(ctx->pmu);
	/*
	 * We want to keep the following priority order:
	 * cpu pinned (that don't need to move), task pinned,
	 * cpu flexible, task flexible.
	 */
	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);

	if (ctx->nr_events)
		cpuctx->task_ctx = ctx;

	perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);

	perf_pmu_enable(ctx->pmu);
	perf_ctx_unlock(cpuctx, ctx);

	/*
	 * Since these rotations are per-cpu, we need to ensure the
	 * cpu-context we got scheduled on is actually rotating.
	 */
	perf_pmu_rotate_start(ctx->pmu);
}

/*
 * When sampling the branck stack in system-wide, it may be necessary
 * to flush the stack on context switch. This happens when the branch
 * stack does not tag its entries with the pid of the current task.
 * Otherwise it becomes impossible to associate a branch entry with a
 * task. This ambiguity is more likely to appear when the branch stack
 * supports priv level filtering and the user sets it to monitor only
 * at the user level (which could be a useful measurement in system-wide
 * mode). In that case, the risk is high of having a branch stack with
 * branch from multiple tasks. Flushing may mean dropping the existing
 * entries or stashing them somewhere in the PMU specific code layer.
 *
 * This function provides the context switch callback to the lower code
 * layer. It is invoked ONLY when there is at least one system-wide context
 * with at least one active event using taken branch sampling.
 */
static void perf_branch_stack_sched_in(struct task_struct *prev,
				       struct task_struct *task)
{
	struct perf_cpu_context *cpuctx;
	struct pmu *pmu;
	unsigned long flags;

	/* no need to flush branch stack if not changing task */
	if (prev == task)
		return;

	local_irq_save(flags);

	rcu_read_lock();

	list_for_each_entry_rcu(pmu, &pmus, entry) {
		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);

		/*
		 * check if the context has at least one
		 * event using PERF_SAMPLE_BRANCH_STACK
		 */
		if (cpuctx->ctx.nr_branch_stack > 0
		    && pmu->flush_branch_stack) {

			perf_ctx_lock(cpuctx, cpuctx->task_ctx);

			perf_pmu_disable(pmu);

			pmu->flush_branch_stack();

			perf_pmu_enable(pmu);

			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
		}
	}

	rcu_read_unlock();

	local_irq_restore(flags);
}

/*
 * Called from scheduler to add the events of the current task
 * with interrupts disabled.
 *
 * We restore the event value and then enable it.
 *
 * This does not protect us against NMI, but enable()
 * sets the enabled bit in the control field of event _before_
 * accessing the event control register. If a NMI hits, then it will
 * keep the event running.
 */
void __perf_event_task_sched_in(struct task_struct *prev,
				struct task_struct *task)
{
	struct perf_event_context *ctx;
	int ctxn;

	for_each_task_context_nr(ctxn) {
		ctx = task->perf_event_ctxp[ctxn];
		if (likely(!ctx))
			continue;

		perf_event_context_sched_in(ctx, task);
	}
	/*
	 * if cgroup events exist on this CPU, then we need
	 * to check if we have to switch in PMU state.
	 * cgroup event are system-wide mode only
	 */
	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
		perf_cgroup_sched_in(prev, task);

	/* check for system-wide branch_stack events */
	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
		perf_branch_stack_sched_in(prev, task);
}

static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
{
	u64 frequency = event->attr.sample_freq;
	u64 sec = NSEC_PER_SEC;
	u64 divisor, dividend;

	int count_fls, nsec_fls, frequency_fls, sec_fls;

	count_fls = fls64(count);
	nsec_fls = fls64(nsec);
	frequency_fls = fls64(frequency);
	sec_fls = 30;

	/*
	 * We got @count in @nsec, with a target of sample_freq HZ
	 * the target period becomes:
	 *
	 *             @count * 10^9
	 * period = -------------------
	 *          @nsec * sample_freq
	 *
	 */

	/*
	 * Reduce accuracy by one bit such that @a and @b converge
	 * to a similar magnitude.
	 */
#define REDUCE_FLS(a, b)		\
do {					\
	if (a##_fls > b##_fls) {	\
		a >>= 1;		\
		a##_fls--;		\
	} else {			\
		b >>= 1;		\
		b##_fls--;		\
	}				\
} while (0)

	/*
	 * Reduce accuracy until either term fits in a u64, then proceed with
	 * the other, so that finally we can do a u64/u64 division.
	 */
	while (count_fls + sec_fls > 64 && nsec_fls + frequency_fls > 64) {
		REDUCE_FLS(nsec, frequency);
		REDUCE_FLS(sec, count);
	}

	if (count_fls + sec_fls > 64) {
		divisor = nsec * frequency;

		while (count_fls + sec_fls > 64) {
			REDUCE_FLS(count, sec);
			divisor >>= 1;
		}

		dividend = count * sec;
	} else {
		dividend = count * sec;

		while (nsec_fls + frequency_fls > 64) {
			REDUCE_FLS(nsec, frequency);
			dividend >>= 1;
		}

		divisor = nsec * frequency;
	}

	if (!divisor)
		return dividend;

	return div64_u64(dividend, divisor);
}

static DEFINE_PER_CPU(int, perf_throttled_count);
static DEFINE_PER_CPU(u64, perf_throttled_seq);

static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable)
{
	struct hw_perf_event *hwc = &event->hw;
	s64 period, sample_period;
	s64 delta;

	period = perf_calculate_period(event, nsec, count);

	delta = (s64)(period - hwc->sample_period);
	delta = (delta + 7) / 8; /* low pass filter */

	sample_period = hwc->sample_period + delta;

	if (!sample_period)
		sample_period = 1;

	hwc->sample_period = sample_period;

	if (local64_read(&hwc->period_left) > 8*sample_period) {
		if (disable)
			event->pmu->stop(event, PERF_EF_UPDATE);

		local64_set(&hwc->period_left, 0);

		if (disable)
			event->pmu->start(event, PERF_EF_RELOAD);
	}
}

/*
 * combine freq adjustment with unthrottling to avoid two passes over the
 * events. At the same time, make sure, having freq events does not change
 * the rate of unthrottling as that would introduce bias.
 */
static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
					   int needs_unthr)
{
	struct perf_event *event;
	struct hw_perf_event *hwc;
	u64 now, period = TICK_NSEC;
	s64 delta;

	/*
	 * only need to iterate over all events iff:
	 * - context have events in frequency mode (needs freq adjust)
	 * - there are events to unthrottle on this cpu
	 */
	if (!(ctx->nr_freq || needs_unthr))
		return;

	raw_spin_lock(&ctx->lock);
	perf_pmu_disable(ctx->pmu);

	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
		if (event->state != PERF_EVENT_STATE_ACTIVE)
			continue;

		if (!event_filter_match(event))
			continue;

		perf_pmu_disable(event->pmu);

		hwc = &event->hw;

		if (hwc->interrupts == MAX_INTERRUPTS) {
			hwc->interrupts = 0;
			perf_log_throttle(event, 1);
			event->pmu->start(event, 0);
		}

		if (!event->attr.freq || !event->attr.sample_freq)
			goto next;

		/*
		 * stop the event and update event->count
		 */
		event->pmu->stop(event, PERF_EF_UPDATE);

		now = local64_read(&event->count);
		delta = now - hwc->freq_count_stamp;
		hwc->freq_count_stamp = now;

		/*
		 * restart the event
		 * reload only if value has changed
		 * we have stopped the event so tell that
		 * to perf_adjust_period() to avoid stopping it
		 * twice.
		 */
		if (delta > 0)
			perf_adjust_period(event, period, delta, false);

		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
	next:
		perf_pmu_enable(event->pmu);
	}

	perf_pmu_enable(ctx->pmu);
	raw_spin_unlock(&ctx->lock);
}

/*
 * Round-robin a context's events:
 */
static void rotate_ctx(struct perf_event_context *ctx)
{
	/*
	 * Rotate the first entry last of non-pinned groups. Rotation might be
	 * disabled by the inheritance code.
	 */
	if (!ctx->rotate_disable)
		list_rotate_left(&ctx->flexible_groups);
}

/*
 * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
 * because they're strictly cpu affine and rotate_start is called with IRQs
 * disabled, while rotate_context is called from IRQ context.
 */
static int perf_rotate_context(struct perf_cpu_context *cpuctx)
{
	struct perf_event_context *ctx = NULL;
	int rotate = 0, remove = 1;

	if (cpuctx->ctx.nr_events) {
		remove = 0;
		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
			rotate = 1;
	}

	ctx = cpuctx->task_ctx;
	if (ctx && ctx->nr_events) {
		remove = 0;
		if (ctx->nr_events != ctx->nr_active)
			rotate = 1;
	}

	if (!rotate)
		goto done;

	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
	perf_pmu_disable(cpuctx->ctx.pmu);

	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
	if (ctx)
		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);

	rotate_ctx(&cpuctx->ctx);
	if (ctx)
		rotate_ctx(ctx);

	perf_event_sched_in(cpuctx, ctx, current);

	perf_pmu_enable(cpuctx->ctx.pmu);
	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
done:
	if (remove)
		list_del_init(&cpuctx->rotation_list);

	return rotate;
}

#ifdef CONFIG_NO_HZ_FULL
bool perf_event_can_stop_tick(void)
{
	if (atomic_read(&nr_freq_events) ||
	    __this_cpu_read(perf_throttled_count))
		return false;
	else
		return true;
}
#endif

void perf_event_task_tick(void)
{
	struct list_head *head = &__get_cpu_var(rotation_list);
	struct perf_cpu_context *cpuctx, *tmp;
	struct perf_event_context *ctx;
	int throttled;

	WARN_ON(!irqs_disabled());

	__this_cpu_inc(perf_throttled_seq);
	throttled = __this_cpu_xchg(perf_throttled_count, 0);

	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
		ctx = &cpuctx->ctx;
		perf_adjust_freq_unthr_context(ctx, throttled);

		ctx = cpuctx->task_ctx;
		if (ctx)
			perf_adjust_freq_unthr_context(ctx, throttled);
	}
}

static int event_enable_on_exec(struct perf_event *event,
				struct perf_event_context *ctx)
{
	if (!event->attr.enable_on_exec)
		return 0;

	event->attr.enable_on_exec = 0;
	if (event->state >= PERF_EVENT_STATE_INACTIVE)
		return 0;

	__perf_event_mark_enabled(event);

	return 1;
}

/*
 * Enable all of a task's events that have been marked enable-on-exec.
 * This expects task == current.
 */
static void perf_event_enable_on_exec(struct perf_event_context *ctx)
{
	struct perf_event *event;
	unsigned long flags;
	int enabled = 0;
	int ret;

	local_irq_save(flags);
	if (!ctx || !ctx->nr_events)
		goto out;

	/*
	 * We must ctxsw out cgroup events to avoid conflict
	 * when invoking perf_task_event_sched_in() later on
	 * in this function. Otherwise we end up trying to
	 * ctxswin cgroup events which are already scheduled
	 * in.
	 */
	perf_cgroup_sched_out(current, NULL);

	raw_spin_lock(&ctx->lock);
	task_ctx_sched_out(ctx);

	list_for_each_entry(event, &ctx->event_list, event_entry) {
		ret = event_enable_on_exec(event, ctx);
		if (ret)
			enabled = 1;
	}

	/*
	 * Unclone this context if we enabled any event.
	 */
	if (enabled)
		unclone_ctx(ctx);

	raw_spin_unlock(&ctx->lock);

	/*
	 * Also calls ctxswin for cgroup events, if any:
	 */
	perf_event_context_sched_in(ctx, ctx->task);
out:
	local_irq_restore(flags);
}

/*
 * Cross CPU call to read the hardware event
 */
static void __perf_event_read(void *info)
{
	struct perf_event *event = info;
	struct perf_event_context *ctx = event->ctx;
	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);

	/*
	 * If this is a task context, we need to check whether it is
	 * the current task context of this cpu.  If not it has been
	 * scheduled out before the smp call arrived.  In that case
	 * event->count would have been updated to a recent sample
	 * when the event was scheduled out.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx)
		return;

	raw_spin_lock(&ctx->lock);
	if (ctx->is_active) {
		update_context_time(ctx);
		update_cgrp_time_from_event(event);
	}
	update_event_times(event);
	if (event->state == PERF_EVENT_STATE_ACTIVE)
		event->pmu->read(event);
	raw_spin_unlock(&ctx->lock);
}

static inline u64 perf_event_count(struct perf_event *event)
{
	return local64_read(&event->count) + atomic64_read(&event->child_count);
}

static u64 perf_event_read(struct perf_event *event)
{
	/*
	 * If event is enabled and currently active on a CPU, update the
	 * value in the event structure:
	 */
	if (event->state == PERF_EVENT_STATE_ACTIVE) {
		smp_call_function_single(event->oncpu,
					 __perf_event_read, event, 1);
	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
		struct perf_event_context *ctx = event->ctx;
		unsigned long flags;

		raw_spin_lock_irqsave(&ctx->lock, flags);
		/*
		 * may read while context is not active
		 * (e.g., thread is blocked), in that case
		 * we cannot update context time
		 */
		if (ctx->is_active) {
			update_context_time(ctx);
			update_cgrp_time_from_event(event);
		}
		update_event_times(event);
		raw_spin_unlock_irqrestore(&ctx->lock, flags);
	}

	return perf_event_count(event);
}

/*
 * Initialize the perf_event context in a task_struct:
 */
static void __perf_event_init_context(struct perf_event_context *ctx)
{
	raw_spin_lock_init(&ctx->lock);
	mutex_init(&ctx->mutex);
	INIT_LIST_HEAD(&ctx->pinned_groups);
	INIT_LIST_HEAD(&ctx->flexible_groups);
	INIT_LIST_HEAD(&ctx->event_list);
	atomic_set(&ctx->refcount, 1);
}

static struct perf_event_context *
alloc_perf_context(struct pmu *pmu, struct task_struct *task)
{
	struct perf_event_context *ctx;

	ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
	if (!ctx)
		return NULL;

	__perf_event_init_context(ctx);
	if (task) {
		ctx->task = task;
		get_task_struct(task);
	}
	ctx->pmu = pmu;

	return ctx;
}

static struct task_struct *
find_lively_task_by_vpid(pid_t vpid)
{
	struct task_struct *task;
	int err;

	rcu_read_lock();
	if (!vpid)
		task = current;
	else
		task = find_task_by_vpid(vpid);
	if (task)
		get_task_struct(task);
	rcu_read_unlock();

	if (!task)
		return ERR_PTR(-ESRCH);

	/* Reuse ptrace permission checks for now. */
	err = -EACCES;
	if (!ptrace_may_access(task, PTRACE_MODE_READ))
		goto errout;

	return task;
errout:
	put_task_struct(task);
	return ERR_PTR(err);

}

/*
 * Returns a matching context with refcount and pincount.
 */
static struct perf_event_context *
find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
{
	struct perf_event_context *ctx;
	struct perf_cpu_context *cpuctx;
	unsigned long flags;
	int ctxn, err;

	if (!task) {
		/* Must be root to operate on a CPU event: */
		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
			return ERR_PTR(-EACCES);

		/*
		 * We could be clever and allow to attach a event to an
		 * offline CPU and activate it when the CPU comes up, but
		 * that's for later.
		 */
		if (!cpu_online(cpu))
			return ERR_PTR(-ENODEV);

		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
		ctx = &cpuctx->ctx;
		get_ctx(ctx);
		++ctx->pin_count;

		return ctx;
	}

	err = -EINVAL;
	ctxn = pmu->task_ctx_nr;
	if (ctxn < 0)
		goto errout;

retry:
	ctx = perf_lock_task_context(task, ctxn, &flags);
	if (ctx) {
		unclone_ctx(ctx);
		++ctx->pin_count;
		raw_spin_unlock_irqrestore(&ctx->lock, flags);
	} else {
		ctx = alloc_perf_context(pmu, task);
		err = -ENOMEM;
		if (!ctx)
			goto errout;

		err = 0;
		mutex_lock(&task->perf_event_mutex);
		/*
		 * If it has already passed perf_event_exit_task().
		 * we must see PF_EXITING, it takes this mutex too.
		 */
		if (task->flags & PF_EXITING)
			err = -ESRCH;
		else if (task->perf_event_ctxp[ctxn])
			err = -EAGAIN;
		else {
			get_ctx(ctx);
			++ctx->pin_count;
			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
		}
		mutex_unlock(&task->perf_event_mutex);

		if (unlikely(err)) {
			put_ctx(ctx);

			if (err == -EAGAIN)
				goto retry;
			goto errout;
		}
	}

	return ctx;

errout:
	return ERR_PTR(err);
}

static void perf_event_free_filter(struct perf_event *event);

static void free_event_rcu(struct rcu_head *head)
{
	struct perf_event *event;

	event = container_of(head, struct perf_event, rcu_head);
	if (event->ns)
		put_pid_ns(event->ns);
	perf_event_free_filter(event);
	kfree(event);
}

static void ring_buffer_put(struct ring_buffer *rb);
static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);

static void unaccount_event_cpu(struct perf_event *event, int cpu)
{
	if (event->parent)
		return;

	if (has_branch_stack(event)) {
		if (!(event->attach_state & PERF_ATTACH_TASK))
			atomic_dec(&per_cpu(perf_branch_stack_events, cpu));
	}
	if (is_cgroup_event(event))
		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
}

static void unaccount_event(struct perf_event *event)
{
	if (event->parent)
		return;

	if (event->attach_state & PERF_ATTACH_TASK)
		static_key_slow_dec_deferred(&perf_sched_events);
	if (event->attr.mmap || event->attr.mmap_data)
		atomic_dec(&nr_mmap_events);
	if (event->attr.comm)
		atomic_dec(&nr_comm_events);
	if (event->attr.task)
		atomic_dec(&nr_task_events);
	if (event->attr.freq)
		atomic_dec(&nr_freq_events);
	if (is_cgroup_event(event))
		static_key_slow_dec_deferred(&perf_sched_events);
	if (has_branch_stack(event))
		static_key_slow_dec_deferred(&perf_sched_events);

	unaccount_event_cpu(event, event->cpu);
}

static void __free_event(struct perf_event *event)
{
	if (!event->parent) {
		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
			put_callchain_buffers();
	}

	if (event->destroy)
		event->destroy(event);

	if (event->ctx)
		put_ctx(event->ctx);

	call_rcu(&event->rcu_head, free_event_rcu);
}
static void free_event(struct perf_event *event)
{
	irq_work_sync(&event->pending);

	unaccount_event(event);

	if (event->rb) {
		struct ring_buffer *rb;

		/*
		 * Can happen when we close an event with re-directed output.
		 *
		 * Since we have a 0 refcount, perf_mmap_close() will skip
		 * over us; possibly making our ring_buffer_put() the last.
		 */
		mutex_lock(&event->mmap_mutex);
		rb = event->rb;
		if (rb) {
			rcu_assign_pointer(event->rb, NULL);
			ring_buffer_detach(event, rb);
			ring_buffer_put(rb); /* could be last */
		}
		mutex_unlock(&event->mmap_mutex);
	}

	if (is_cgroup_event(event))
		perf_detach_cgroup(event);


	__free_event(event);
}

int perf_event_release_kernel(struct perf_event *event)
{
	struct perf_event_context *ctx = event->ctx;

	WARN_ON_ONCE(ctx->parent_ctx);
	/*
	 * There are two ways this annotation is useful:
	 *
	 *  1) there is a lock recursion from perf_event_exit_task
	 *     see the comment there.
	 *
	 *  2) there is a lock-inversion with mmap_sem through
	 *     perf_event_read_group(), which takes faults while
	 *     holding ctx->mutex, however this is called after
	 *     the last filedesc died, so there is no possibility
	 *     to trigger the AB-BA case.
	 */
	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
	raw_spin_lock_irq(&ctx->lock);
	perf_group_detach(event);
	raw_spin_unlock_irq(&ctx->lock);
	perf_remove_from_context(event);
	mutex_unlock(&ctx->mutex);

	free_event(event);

	return 0;
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);

/*
 * Called when the last reference to the file is gone.
 */
static void put_event(struct perf_event *event)
{
	struct task_struct *owner;

	if (!atomic_long_dec_and_test(&event->refcount))
		return;

	rcu_read_lock();
	owner = ACCESS_ONCE(event->owner);
	/*
	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
	 * !owner it means the list deletion is complete and we can indeed
	 * free this event, otherwise we need to serialize on
	 * owner->perf_event_mutex.
	 */
	smp_read_barrier_depends();
	if (owner) {
		/*
		 * Since delayed_put_task_struct() also drops the last
		 * task reference we can safely take a new reference
		 * while holding the rcu_read_lock().
		 */
		get_task_struct(owner);
	}
	rcu_read_unlock();

	if (owner) {
		mutex_lock(&owner->perf_event_mutex);
		/*
		 * We have to re-check the event->owner field, if it is cleared
		 * we raced with perf_event_exit_task(), acquiring the mutex
		 * ensured they're done, and we can proceed with freeing the
		 * event.
		 */
		if (event->owner)
			list_del_init(&event->owner_entry);
		mutex_unlock(&owner->perf_event_mutex);
		put_task_struct(owner);
	}

	perf_event_release_kernel(event);
}

static int perf_release(struct inode *inode, struct file *file)
{
	put_event(file->private_data);
	return 0;
}

u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
{
	struct perf_event *child;
	u64 total = 0;

	*enabled = 0;
	*running = 0;

	mutex_lock(&event->child_mutex);
	total += perf_event_read(event);
	*enabled += event->total_time_enabled +
			atomic64_read(&event->child_total_time_enabled);
	*running += event->total_time_running +
			atomic64_read(&event->child_total_time_running);

	list_for_each_entry(child, &event->child_list, child_list) {
		total += perf_event_read(child);
		*enabled += child->total_time_enabled;
		*running += child->total_time_running;
	}
	mutex_unlock(&event->child_mutex);

	return total;
}
EXPORT_SYMBOL_GPL(perf_event_read_value);

static int perf_event_read_group(struct perf_event *event,
				   u64 read_format, char __user *buf)
{
	struct perf_event *leader = event->group_leader, *sub;
	int n = 0, size = 0, ret = -EFAULT;
	struct perf_event_context *ctx = leader->ctx;
	u64 values[5];
	u64 count, enabled, running;

	mutex_lock(&ctx->mutex);
	count = perf_event_read_value(leader, &enabled, &running);

	values[n++] = 1 + leader->nr_siblings;
	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		values[n++] = enabled;
	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		values[n++] = running;
	values[n++] = count;
	if (read_format & PERF_FORMAT_ID)
		values[n++] = primary_event_id(leader);

	size = n * sizeof(u64);

	if (copy_to_user(buf, values, size))
		goto unlock;

	ret = size;

	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
		n = 0;

		values[n++] = perf_event_read_value(sub, &enabled, &running);
		if (read_format & PERF_FORMAT_ID)
			values[n++] = primary_event_id(sub);

		size = n * sizeof(u64);

		if (copy_to_user(buf + ret, values, size)) {
			ret = -EFAULT;
			goto unlock;
		}

		ret += size;
	}
unlock:
	mutex_unlock(&ctx->mutex);

	return ret;
}

static int perf_event_read_one(struct perf_event *event,
				 u64 read_format, char __user *buf)
{
	u64 enabled, running;
	u64 values[4];
	int n = 0;

	values[n++] = perf_event_read_value(event, &enabled, &running);
	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		values[n++] = enabled;
	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		values[n++] = running;
	if (read_format & PERF_FORMAT_ID)
		values[n++] = primary_event_id(event);

	if (copy_to_user(buf, values, n * sizeof(u64)))
		return -EFAULT;

	return n * sizeof(u64);
}

/*
 * Read the performance event - simple non blocking version for now
 */
static ssize_t
perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
{
	u64 read_format = event->attr.read_format;
	int ret;

	/*
	 * Return end-of-file for a read on a event that is in
	 * error state (i.e. because it was pinned but it couldn't be
	 * scheduled on to the CPU at some point).
	 */
	if (event->state == PERF_EVENT_STATE_ERROR)
		return 0;

	if (count < event->read_size)
		return -ENOSPC;

	WARN_ON_ONCE(event->ctx->parent_ctx);
	if (read_format & PERF_FORMAT_GROUP)
		ret = perf_event_read_group(event, read_format, buf);
	else
		ret = perf_event_read_one(event, read_format, buf);

	return ret;
}

static ssize_t
perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	struct perf_event *event = file->private_data;

	return perf_read_hw(event, buf, count);
}

static unsigned int perf_poll(struct file *file, poll_table *wait)
{
	struct perf_event *event = file->private_data;
	struct ring_buffer *rb;
	unsigned int events = POLL_HUP;

	/*
	 * Pin the event->rb by taking event->mmap_mutex; otherwise
	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
	 */
	mutex_lock(&event->mmap_mutex);
	rb = event->rb;
	if (rb)
		events = atomic_xchg(&rb->poll, 0);
	mutex_unlock(&event->mmap_mutex);

	poll_wait(file, &event->waitq, wait);

	return events;
}

static void perf_event_reset(struct perf_event *event)
{
	(void)perf_event_read(event);
	local64_set(&event->count, 0);
	perf_event_update_userpage(event);
}

/*
 * Holding the top-level event's child_mutex means that any
 * descendant process that has inherited this event will block
 * in sync_child_event if it goes to exit, thus satisfying the
 * task existence requirements of perf_event_enable/disable.
 */
static void perf_event_for_each_child(struct perf_event *event,
					void (*func)(struct perf_event *))
{
	struct perf_event *child;

	WARN_ON_ONCE(event->ctx->parent_ctx);
	mutex_lock(&event->child_mutex);
	func(event);
	list_for_each_entry(child, &event->child_list, child_list)
		func(child);
	mutex_unlock(&event->child_mutex);
}

static void perf_event_for_each(struct perf_event *event,
				  void (*func)(struct perf_event *))
{
	struct perf_event_context *ctx = event->ctx;
	struct perf_event *sibling;

	WARN_ON_ONCE(ctx->parent_ctx);
	mutex_lock(&ctx->mutex);
	event = event->group_leader;

	perf_event_for_each_child(event, func);
	list_for_each_entry(sibling, &event->sibling_list, group_entry)
		perf_event_for_each_child(sibling, func);
	mutex_unlock(&ctx->mutex);
}

static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
	struct perf_event_context *ctx = event->ctx;
	int ret = 0, active;
	u64 value;

	if (!is_sampling_event(event))
		return -EINVAL;

	if (copy_from_user(&value, arg, sizeof(value)))
		return -EFAULT;

	if (!value)
		return -EINVAL;

	raw_spin_lock_irq(&ctx->lock);
	if (event->attr.freq) {
		if (value > sysctl_perf_event_sample_rate) {
			ret = -EINVAL;
			goto unlock;
		}

		event->attr.sample_freq = value;
	} else {
		event->attr.sample_period = value;
		event->hw.sample_period = value;
	}

	active = (event->state == PERF_EVENT_STATE_ACTIVE);
	if (active) {
		perf_pmu_disable(ctx->pmu);
		event->pmu->stop(event, PERF_EF_UPDATE);
	}

	local64_set(&event->hw.period_left, 0);

	if (active) {
		event->pmu->start(event, PERF_EF_RELOAD);
		perf_pmu_enable(ctx->pmu);
	}

unlock:
	raw_spin_unlock_irq(&ctx->lock);

	return ret;
}

static const struct file_operations perf_fops;

static inline int perf_fget_light(int fd, struct fd *p)
{
	struct fd f = fdget(fd);
	if (!f.file)
		return -EBADF;

	if (f.file->f_op != &perf_fops) {
		fdput(f);
		return -EBADF;
	}
	*p = f;
	return 0;
}

static int perf_event_set_output(struct perf_event *event,
				 struct perf_event *output_event);
static int perf_event_set_filter(struct perf_event *event, void __user *arg);

static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct perf_event *event = file->private_data;
	void (*func)(struct perf_event *);
	u32 flags = arg;

	switch (cmd) {
	case PERF_EVENT_IOC_ENABLE:
		func = perf_event_enable;
		break;
	case PERF_EVENT_IOC_DISABLE:
		func = perf_event_disable;
		break;
	case PERF_EVENT_IOC_RESET:
		func = perf_event_reset;
		break;

	case PERF_EVENT_IOC_REFRESH:
		return perf_event_refresh(event, arg);

	case PERF_EVENT_IOC_PERIOD:
		return perf_event_period(event, (u64 __user *)arg);

	case PERF_EVENT_IOC_ID:
	{
		u64 id = primary_event_id(event);

		if (copy_to_user((void __user *)arg, &id, sizeof(id)))
			return -EFAULT;
		return 0;
	}

	case PERF_EVENT_IOC_SET_OUTPUT:
	{
		int ret;
		if (arg != -1) {
			struct perf_event *output_event;
			struct fd output;
			ret = perf_fget_light(arg, &output);
			if (ret)
				return ret;
			output_event = output.file->private_data;
			ret = perf_event_set_output(event, output_event);
			fdput(output);
		} else {
			ret = perf_event_set_output(event, NULL);
		}
		return ret;
	}

	case PERF_EVENT_IOC_SET_FILTER:
		return perf_event_set_filter(event, (void __user *)arg);

	default:
		return -ENOTTY;
	}

	if (flags & PERF_IOC_FLAG_GROUP)
		perf_event_for_each(event, func);
	else
		perf_event_for_each_child(event, func);

	return 0;
}

int perf_event_task_enable(void)
{
	struct perf_event *event;

	mutex_lock(&current->perf_event_mutex);
	list_for_each_entry(event, &current->perf_event_list, owner_entry)
		perf_event_for_each_child(event, perf_event_enable);
	mutex_unlock(&current->perf_event_mutex);

	return 0;
}

int perf_event_task_disable(void)
{
	struct perf_event *event;

	mutex_lock(&current->perf_event_mutex);
	list_for_each_entry(event, &current->perf_event_list, owner_entry)
		perf_event_for_each_child(event, perf_event_disable);
	mutex_unlock(&current->perf_event_mutex);

	return 0;
}

static int perf_event_index(struct perf_event *event)
{
	if (event->hw.state & PERF_HES_STOPPED)
		return 0;

	if (event->state != PERF_EVENT_STATE_ACTIVE)
		return 0;

	return event->pmu->event_idx(event);
}

static void calc_timer_values(struct perf_event *event,
				u64 *now,
				u64 *enabled,
				u64 *running)
{
	u64 ctx_time;

	*now = perf_clock();
	ctx_time = event->shadow_ctx_time + *now;
	*enabled = ctx_time - event->tstamp_enabled;
	*running = ctx_time - event->tstamp_running;
}

static void perf_event_init_userpage(struct perf_event *event)
{
	struct perf_event_mmap_page *userpg;
	struct ring_buffer *rb;

	rcu_read_lock();
	rb = rcu_dereference(event->rb);
	if (!rb)
		goto unlock;

	userpg = rb->user_page;

	/* Allow new userspace to detect that bit 0 is deprecated */
	userpg->cap_bit0_is_deprecated = 1;
	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);

unlock:
	rcu_read_unlock();
}

void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
}

/*
 * Callers need to ensure there can be no nesting of this function, otherwise
 * the seqlock logic goes bad. We can not serialize this because the arch
 * code calls this from NMI context.
 */
void perf_event_update_userpage(struct perf_event *event)
{
	struct perf_event_mmap_page *userpg;
	struct ring_buffer *rb;
	u64 enabled, running, now;

	rcu_read_lock();
	rb = rcu_dereference(event->rb);
	if (!rb)
		goto unlock;

	/*
	 * compute total_time_enabled, total_time_running
	 * based on snapshot values taken when the event
	 * was last scheduled in.
	 *
	 * we cannot simply called update_context_time()
	 * because of locking issue as we can be called in
	 * NMI context
	 */
	calc_timer_values(event, &now, &enabled, &running);

	userpg = rb->user_page;
	/*
	 * Disable preemption so as to not let the corresponding user-space
	 * spin too long if we get preempted.
	 */
	preempt_disable();
	++userpg->lock;
	barrier();
	userpg->index = perf_event_index(event);
	userpg->offset = perf_event_count(event);
	if (userpg->index)
		userpg->offset -= local64_read(&event->hw.prev_count);

	userpg->time_enabled = enabled +
			atomic64_read(&event->child_total_time_enabled);

	userpg->time_running = running +
			atomic64_read(&event->child_total_time_running);

	arch_perf_update_userpage(userpg, now);

	barrier();
	++userpg->lock;
	preempt_enable();
unlock:
	rcu_read_unlock();
}

static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct perf_event *event = vma->vm_file->private_data;
	struct ring_buffer *rb;
	int ret = VM_FAULT_SIGBUS;

	if (vmf->flags & FAULT_FLAG_MKWRITE) {
		if (vmf->pgoff == 0)
			ret = 0;
		return ret;
	}

	rcu_read_lock();
	rb = rcu_dereference(event->rb);
	if (!rb)
		goto unlock;

	if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
		goto unlock;

	vmf->page = perf_mmap_to_page(rb, vmf->pgoff);
	if (!vmf->page)
		goto unlock;

	get_page(vmf->page);
	vmf->page->mapping = vma->vm_file->f_mapping;
	vmf->page->index   = vmf->pgoff;

	ret = 0;
unlock:
	rcu_read_unlock();

	return ret;
}

static void ring_buffer_attach(struct perf_event *event,
			       struct ring_buffer *rb)
{
	unsigned long flags;

	if (!list_empty(&event->rb_entry))
		return;

	spin_lock_irqsave(&rb->event_lock, flags);
	if (list_empty(&event->rb_entry))
		list_add(&event->rb_entry, &rb->event_list);
	spin_unlock_irqrestore(&rb->event_lock, flags);
}

static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
{
	unsigned long flags;

	if (list_empty(&event->rb_entry))
		return;

	spin_lock_irqsave(&rb->event_lock, flags);
	list_del_init(&event->rb_entry);
	wake_up_all(&event->waitq);
	spin_unlock_irqrestore(&rb->event_lock, flags);
}

static void ring_buffer_wakeup(struct perf_event *event)
{
	struct ring_buffer *rb;

	rcu_read_lock();
	rb = rcu_dereference(event->rb);
	if (rb) {
		list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
			wake_up_all(&event->waitq);
	}
	rcu_read_unlock();
}

static void rb_free_rcu(struct rcu_head *rcu_head)
{
	struct ring_buffer *rb;

	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
	rb_free(rb);
}

static struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
	struct ring_buffer *rb;

	rcu_read_lock();
	rb = rcu_dereference(event->rb);
	if (rb) {
		if (!atomic_inc_not_zero(&rb->refcount))
			rb = NULL;
	}
	rcu_read_unlock();

	return rb;
}

static void ring_buffer_put(struct ring_buffer *rb)
{
	if (!atomic_dec_and_test(&rb->refcount))
		return;

	WARN_ON_ONCE(!list_empty(&rb->event_list));

	call_rcu(&rb->rcu_head, rb_free_rcu);
}

static void perf_mmap_open(struct vm_area_struct *vma)
{
	struct perf_event *event = vma->vm_file->private_data;

	atomic_inc(&event->mmap_count);
	atomic_inc(&event->rb->mmap_count);
}

/*
 * A buffer can be mmap()ed multiple times; either directly through the same
 * event, or through other events by use of perf_event_set_output().
 *
 * In order to undo the VM accounting done by perf_mmap() we need to destroy
 * the buffer here, where we still have a VM context. This means we need
 * to detach all events redirecting to us.
 */
static void perf_mmap_close(struct vm_area_struct *vma)
{
	struct perf_event *event = vma->vm_file->private_data;

	struct ring_buffer *rb = event->rb;
	struct user_struct *mmap_user = rb->mmap_user;
	int mmap_locked = rb->mmap_locked;
	unsigned long size = perf_data_size(rb);

	atomic_dec(&rb->mmap_count);

	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
		return;

	/* Detach current event from the buffer. */
	rcu_assign_pointer(event->rb, NULL);
	ring_buffer_detach(event, rb);
	mutex_unlock(&event->mmap_mutex);

	/* If there's still other mmap()s of this buffer, we're done. */
	if (atomic_read(&rb->mmap_count)) {
		ring_buffer_put(rb); /* can't be last */
		return;
	}

	/*
	 * No other mmap()s, detach from all other events that might redirect
	 * into the now unreachable buffer. Somewhat complicated by the
	 * fact that rb::event_lock otherwise nests inside mmap_mutex.
	 */
again:
	rcu_read_lock();
	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
		if (!atomic_long_inc_not_zero(&event->refcount)) {
			/*
			 * This event is en-route to free_event() which will
			 * detach it and remove it from the list.
			 */
			continue;
		}
		rcu_read_unlock();

		mutex_lock(&event->mmap_mutex);
		/*
		 * Check we didn't race with perf_event_set_output() which can
		 * swizzle the rb from under us while we were waiting to
		 * acquire mmap_mutex.
		 *
		 * If we find a different rb; ignore this event, a next
		 * iteration will no longer find it on the list. We have to
		 * still restart the iteration to make sure we're not now
		 * iterating the wrong list.
		 */
		if (event->rb == rb) {
			rcu_assign_pointer(event->rb, NULL);
			ring_buffer_detach(event, rb);
			ring_buffer_put(rb); /* can't be last, we still have one */
		}
		mutex_unlock(&event->mmap_mutex);
		put_event(event);

		/*
		 * Restart the iteration; either we're on the wrong list or
		 * destroyed its integrity by doing a deletion.
		 */
		goto again;
	}
	rcu_read_unlock();

	/*
	 * It could be there's still a few 0-ref events on the list; they'll
	 * get cleaned up by free_event() -- they'll also still have their
	 * ref on the rb and will free it whenever they are done with it.
	 *
	 * Aside from that, this buffer is 'fully' detached and unmapped,
	 * undo the VM accounting.
	 */

	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
	vma->vm_mm->pinned_vm -= mmap_locked;
	free_uid(mmap_user);

	ring_buffer_put(rb); /* could be last */
}

static const struct vm_operations_struct perf_mmap_vmops = {
	.open		= perf_mmap_open,
	.close		= perf_mmap_close,
	.fault		= perf_mmap_fault,
	.page_mkwrite	= perf_mmap_fault,
};

static int perf_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct perf_event *event = file->private_data;
	unsigned long user_locked, user_lock_limit;
	struct user_struct *user = current_user();
	unsigned long locked, lock_limit;
	struct ring_buffer *rb;
	unsigned long vma_size;
	unsigned long nr_pages;
	long user_extra, extra;
	int ret = 0, flags = 0;

	/*
	 * Don't allow mmap() of inherited per-task counters. This would
	 * create a performance issue due to all children writing to the
	 * same rb.
	 */
	if (event->cpu == -1 && event->attr.inherit)
		return -EINVAL;

	if (!(vma->vm_flags & VM_SHARED))
		return -EINVAL;

	vma_size = vma->vm_end - vma->vm_start;
	nr_pages = (vma_size / PAGE_SIZE) - 1;

	/*
	 * If we have rb pages ensure they're a power-of-two number, so we
	 * can do bitmasks instead of modulo.
	 */
	if (nr_pages != 0 && !is_power_of_2(nr_pages))
		return -EINVAL;

	if (vma_size != PAGE_SIZE * (1 + nr_pages))
		return -EINVAL;

	if (vma->vm_pgoff != 0)
		return -EINVAL;

	WARN_ON_ONCE(event->ctx->parent_ctx);
again:
	mutex_lock(&event->mmap_mutex);
	if (event->rb) {
		if (event->rb->nr_pages != nr_pages) {
			ret = -EINVAL;
			goto unlock;
		}

		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
			/*
			 * Raced against perf_mmap_close() through
			 * perf_event_set_output(). Try again, hope for better
			 * luck.
			 */
			mutex_unlock(&event->mmap_mutex);
			goto again;
		}

		goto unlock;
	}

	user_extra = nr_pages + 1;
	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);

	/*
	 * Increase the limit linearly with more CPUs:
	 */
	user_lock_limit *= num_online_cpus();

	user_locked = atomic_long_read(&user->locked_vm) + user_extra;

	extra = 0;
	if (user_locked > user_lock_limit)
		extra = user_locked - user_lock_limit;

	lock_limit = rlimit(RLIMIT_MEMLOCK);
	lock_limit >>= PAGE_SHIFT;
	locked = vma->vm_mm->pinned_vm + extra;

	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
		!capable(CAP_IPC_LOCK)) {
		ret = -EPERM;
		goto unlock;
	}

	WARN_ON(event->rb);

	if (vma->vm_flags & VM_WRITE)
		flags |= RING_BUFFER_WRITABLE;

	rb = rb_alloc(nr_pages, 
		event->attr.watermark ? event->attr.wakeup_watermark : 0,
		event->cpu, flags);

	if (!rb) {
		ret = -ENOMEM;
		goto unlock;
	}

	atomic_set(&rb->mmap_count, 1);
	rb->mmap_locked = extra;
	rb->mmap_user = get_current_user();

	atomic_long_add(user_extra, &user->locked_vm);
	vma->vm_mm->pinned_vm += extra;

	ring_buffer_attach(event, rb);
	rcu_assign_pointer(event->rb, rb);

	perf_event_init_userpage(event);
	perf_event_update_userpage(event);

unlock:
	if (!ret)
		atomic_inc(&event->mmap_count);
	mutex_unlock(&event->mmap_mutex);

	/*
	 * Since pinned accounting is per vm we cannot allow fork() to copy our
	 * vma.
	 */
	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
	vma->vm_ops = &perf_mmap_vmops;

	return ret;
}

static int perf_fasync(int fd, struct file *filp, int on)
{
	struct inode *inode = file_inode(filp);
	struct perf_event *event = filp->private_data;
	int retval;

	mutex_lock(&inode->i_mutex);
	retval = fasync_helper(fd, filp, on, &event->fasync);
	mutex_unlock(&inode->i_mutex);

	if (retval < 0)
		return retval;

	return 0;
}

static const struct file_operations perf_fops = {
	.llseek			= no_llseek,
	.release		= perf_release,
	.read			= perf_read,
	.poll			= perf_poll,
	.unlocked_ioctl		= perf_ioctl,
	.compat_ioctl		= perf_ioctl,
	.mmap			= perf_mmap,
	.fasync			= perf_fasync,
};

/*
 * Perf event wakeup
 *
 * If there's data, ensure we set the poll() state and publish everything
 * to user-space before waking everybody up.
 */

void perf_event_wakeup(struct perf_event *event)
{
	ring_buffer_wakeup(event);

	if (event->pending_kill) {
		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
		event->pending_kill = 0;
	}
}

static void perf_pending_event(struct irq_work *entry)
{
	struct perf_event *event = container_of(entry,
			struct perf_event, pending);

	if (event->pending_disable) {
		event->pending_disable = 0;
		__perf_event_disable(event);
	}

	if (event->pending_wakeup) {
		event->pending_wakeup = 0;
		perf_event_wakeup(event);
	}
}

/*
 * We assume there is only KVM supporting the callbacks.
 * Later on, we might change it to a list if there is
 * another virtualization implementation supporting the callbacks.
 */
struct perf_guest_info_callbacks *perf_guest_cbs;

int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
	perf_guest_cbs = cbs;
	return 0;
}
EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);

int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
	perf_guest_cbs = NULL;
	return 0;
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);

static void
perf_output_sample_regs(struct perf_output_handle *handle,
			struct pt_regs *regs, u64 mask)
{
	int bit;

	for_each_set_bit(bit, (const unsigned long *) &mask,
			 sizeof(mask) * BITS_PER_BYTE) {
		u64 val;

		val = perf_reg_value(regs, bit);
		perf_output_put(handle, val);
	}
}

static void perf_sample_regs_user(struct perf_regs_user *regs_user,
				  struct pt_regs *regs)
{
	if (!user_mode(regs)) {
		if (current->mm)
			regs = task_pt_regs(current);
		else
			regs = NULL;
	}

	if (regs) {
		regs_user->regs = regs;
		regs_user->abi  = perf_reg_abi(current);
	}
}

/*
 * Get remaining task size from user stack pointer.
 *
 * It'd be better to take stack vma map and limit this more
 * precisly, but there's no way to get it safely under interrupt,
 * so using TASK_SIZE as limit.
 */
static u64 perf_ustack_task_size(struct pt_regs *regs)
{
	unsigned long addr = perf_user_stack_pointer(regs);

	if (!addr || addr >= TASK_SIZE)
		return 0;

	return TASK_SIZE - addr;
}

static u16
perf_sample_ustack_size(u16 stack_size, u16 header_size,
			struct pt_regs *regs)
{
	u64 task_size;

	/* No regs, no stack pointer, no dump. */
	if (!regs)
		return 0;

	/*
	 * Check if we fit in with the requested stack size into the:
	 * - TASK_SIZE
	 *   If we don't, we limit the size to the TASK_SIZE.
	 *
	 * - remaining sample size
	 *   If we don't, we customize the stack size to
	 *   fit in to the remaining sample size.
	 */

	task_size  = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
	stack_size = min(stack_size, (u16) task_size);

	/* Current header size plus static size and dynamic size. */
	header_size += 2 * sizeof(u64);

	/* Do we fit in with the current stack dump size? */
	if ((u16) (header_size + stack_size) < header_size) {
		/*
		 * If we overflow the maximum size for the sample,
		 * we customize the stack dump size to fit in.
		 */
		stack_size = USHRT_MAX - header_size - sizeof(u64);
		stack_size = round_up(stack_size, sizeof(u64));
	}

	return stack_size;
}

static void
perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
			  struct pt_regs *regs)
{
	/* Case of a kernel thread, nothing to dump */
	if (!regs) {
		u64 size = 0;
		perf_output_put(handle, size);
	} else {
		unsigned long sp;
		unsigned int rem;
		u64 dyn_size;

		/*
		 * We dump:
		 * static size
		 *   - the size requested by user or the best one we can fit
		 *     in to the sample max size
		 * data
		 *   - user stack dump data
		 * dynamic size
		 *   - the actual dumped size
		 */

		/* Static size. */
		perf_output_put(handle, dump_size);

		/* Data. */
		sp = perf_user_stack_pointer(regs);
		rem = __output_copy_user(handle, (void *) sp, dump_size);
		dyn_size = dump_size - rem;

		perf_output_skip(handle, rem);

		/* Dynamic size. */
		perf_output_put(handle, dyn_size);
	}
}

static void __perf_event_header__init_id(struct perf_event_header *header,
					 struct perf_sample_data *data,
					 struct perf_event *event)
{
	u64 sample_type = event->attr.sample_type;

	data->type = sample_type;
	header->size += event->id_header_size;

	if (sample_type & PERF_SAMPLE_TID) {
		/* namespace issues */
		data->tid_entry.pid = perf_event_pid(event, current);
		data->tid_entry.tid = perf_event_tid(event, current);
	}

	if (sample_type & PERF_SAMPLE_TIME)
		data->time = perf_clock();

	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
		data->id = primary_event_id(event);

	if (sample_type & PERF_SAMPLE_STREAM_ID)
		data->stream_id = event->id;

	if (sample_type & PERF_SAMPLE_CPU) {
		data->cpu_entry.cpu	 = raw_smp_processor_id();
		data->cpu_entry.reserved = 0;
	}
}

void perf_event_header__init_id(struct perf_event_header *header,
				struct perf_sample_data *data,
				struct perf_event *event)
{
	if (event->attr.sample_id_all)
		__perf_event_header__init_id(header, data, event);
}

static void __perf_event__output_id_sample(struct perf_output_handle *handle,
					   struct perf_sample_data *data)
{
	u64 sample_type = data->type;

	if (sample_type & PERF_SAMPLE_TID)
		perf_output_put(handle, data->tid_entry);

	if (sample_type & PERF_SAMPLE_TIME)
		perf_output_put(handle, data->time);

	if (sample_type & PERF_SAMPLE_ID)
		perf_output_put(handle, data->id);

	if (sample_type & PERF_SAMPLE_STREAM_ID)
		perf_output_put(handle, data->stream_id);

	if (sample_type & PERF_SAMPLE_CPU)
		perf_output_put(handle, data->cpu_entry);

	if (sample_type & PERF_SAMPLE_IDENTIFIER)
		perf_output_put(handle, data->id);
}

void perf_event__output_id_sample(struct perf_event *event,
				  struct perf_output_handle *handle,
				  struct perf_sample_data *sample)
{
	if (event->attr.sample_id_all)
		__perf_event__output_id_sample(handle, sample);
}

static void perf_output_read_one(struct perf_output_handle *handle,
				 struct perf_event *event,
				 u64 enabled, u64 running)
{
	u64 read_format = event->attr.read_format;
	u64 values[4];
	int n = 0;

	values[n++] = perf_event_count(event);
	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
		values[n++] = enabled +
			atomic64_read(&event->child_total_time_enabled);
	}
	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
		values[n++] = running +
			atomic64_read(&event->child_total_time_running);
	}
	if (read_format & PERF_FORMAT_ID)
		values[n++] = primary_event_id(event);

	__output_copy(handle, values, n * sizeof(u64));
}

/*
 * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
 */
static void perf_output_read_group(struct perf_output_handle *handle,
			    struct perf_event *event,
			    u64 enabled, u64 running)
{
	struct perf_event *leader = event->group_leader, *sub;
	u64 read_format = event->attr.read_format;
	u64 values[5];
	int n = 0;

	values[n++] = 1 + leader->nr_siblings;

	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		values[n++] = enabled;

	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		values[n++] = running;

	if (leader != event)
		leader->pmu->read(leader);

	values[n++] = perf_event_count(leader);
	if (read_format & PERF_FORMAT_ID)
		values[n++] = primary_event_id(leader);

	__output_copy(handle, values, n * sizeof(u64));

	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
		n = 0;

		if ((sub != event) &&
		    (sub->state == PERF_EVENT_STATE_ACTIVE))
			sub->pmu->read(sub);

		values[n++] = perf_event_count(sub);
		if (read_format & PERF_FORMAT_ID)
			values[n++] = primary_event_id(sub);

		__output_copy(handle, values, n * sizeof(u64));
	}
}

#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
				 PERF_FORMAT_TOTAL_TIME_RUNNING)

static void perf_output_read(struct perf_output_handle *handle,
			     struct perf_event *event)
{
	u64 enabled = 0, running = 0, now;
	u64 read_format = event->attr.read_format;

	/*
	 * compute total_time_enabled, total_time_running
	 * based on snapshot values taken when the event
	 * was last scheduled in.
	 *
	 * we cannot simply called update_context_time()
	 * because of locking issue as we are called in
	 * NMI context
	 */
	if (read_format & PERF_FORMAT_TOTAL_TIMES)
		calc_timer_values(event, &now, &enabled, &running);

	if (event->attr.read_format & PERF_FORMAT_GROUP)
		perf_output_read_group(handle, event, enabled, running);
	else
		perf_output_read_one(handle, event, enabled, running);
}

void perf_output_sample(struct perf_output_handle *handle,
			struct perf_event_header *header,
			struct perf_sample_data *data,
			struct perf_event *event)
{
	u64 sample_type = data->type;

	perf_output_put(handle, *header);

	if (sample_type & PERF_SAMPLE_IDENTIFIER)
		perf_output_put(handle, data->id);

	if (sample_type & PERF_SAMPLE_IP)
		perf_output_put(handle, data->ip);

	if (sample_type & PERF_SAMPLE_TID)
		perf_output_put(handle, data->tid_entry);

	if (sample_type & PERF_SAMPLE_TIME)
		perf_output_put(handle, data->time);

	if (sample_type & PERF_SAMPLE_ADDR)
		perf_output_put(handle, data->addr);

	if (sample_type & PERF_SAMPLE_ID)
		perf_output_put(handle, data->id);

	if (sample_type & PERF_SAMPLE_STREAM_ID)
		perf_output_put(handle, data->stream_id);

	if (sample_type & PERF_SAMPLE_CPU)
		perf_output_put(handle, data->cpu_entry);

	if (sample_type & PERF_SAMPLE_PERIOD)
		perf_output_put(handle, data->period);

	if (sample_type & PERF_SAMPLE_READ)
		perf_output_read(handle, event);

	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
		if (data->callchain) {
			int size = 1;

			if (data->callchain)
				size += data->callchain->nr;

			size *= sizeof(u64);

			__output_copy(handle, data->callchain, size);
		} else {
			u64 nr = 0;
			perf_output_put(handle, nr);
		}
	}

	if (sample_type & PERF_SAMPLE_RAW) {
		if (data->raw) {
			perf_output_put(handle, data->raw->size);
			__output_copy(handle, data->raw->data,
					   data->raw->size);
		} else {
			struct {
				u32	size;
				u32	data;
			} raw = {
				.size = sizeof(u32),
				.data = 0,
			};
			perf_output_put(handle, raw);
		}
	}

	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
		if (data->br_stack) {
			size_t size;

			size = data->br_stack->nr
			     * sizeof(struct perf_branch_entry);

			perf_output_put(handle, data->br_stack->nr);
			perf_output_copy(handle, data->br_stack->entries, size);
		} else {
			/*
			 * we always store at least the value of nr
			 */
			u64 nr = 0;
			perf_output_put(handle, nr);
		}
	}

	if (sample_type & PERF_SAMPLE_REGS_USER) {
		u64 abi = data->regs_user.abi;

		/*
		 * If there are no regs to dump, notice it through
		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
		 */
		perf_output_put(handle, abi);

		if (abi) {
			u64 mask = event->attr.sample_regs_user;
			perf_output_sample_regs(handle,
						data->regs_user.regs,
						mask);
		}
	}

	if (sample_type & PERF_SAMPLE_STACK_USER) {
		perf_output_sample_ustack(handle,
					  data->stack_user_size,
					  data->regs_user.regs);
	}

	if (sample_type & PERF_SAMPLE_WEIGHT)
		perf_output_put(handle, data->weight);

	if (sample_type & PERF_SAMPLE_DATA_SRC)
		perf_output_put(handle, data->data_src.val);

	if (sample_type & PERF_SAMPLE_TRANSACTION)
		perf_output_put(handle, data->txn);

	if (!event->attr.watermark) {
		int wakeup_events = event->attr.wakeup_events;

		if (wakeup_events) {
			struct ring_buffer *rb = handle->rb;
			int events = local_inc_return(&rb->events);

			if (events >= wakeup_events) {
				local_sub(wakeup_events, &rb->events);
				local_inc(&rb->wakeup);
			}
		}
	}
}

void perf_prepare_sample(struct perf_event_header *header,
			 struct perf_sample_data *data,
			 struct perf_event *event,
			 struct pt_regs *regs)
{
	u64 sample_type = event->attr.sample_type;

	header->type = PERF_RECORD_SAMPLE;
	header->size = sizeof(*header) + event->header_size;

	header->misc = 0;
	header->misc |= perf_misc_flags(regs);

	__perf_event_header__init_id(header, data, event);

	if (sample_type & PERF_SAMPLE_IP)
		data->ip = perf_instruction_pointer(regs);

	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
		int size = 1;

		data->callchain = perf_callchain(event, regs);

		if (data->callchain)
			size += data->callchain->nr;

		header->size += size * sizeof(u64);
	}

	if (sample_type & PERF_SAMPLE_RAW) {
		int size = sizeof(u32);

		if (data->raw)
			size += data->raw->size;
		else
			size += sizeof(u32);

		WARN_ON_ONCE(size & (sizeof(u64)-1));
		header->size += size;
	}

	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
		int size = sizeof(u64); /* nr */
		if (data->br_stack) {
			size += data->br_stack->nr
			      * sizeof(struct perf_branch_entry);
		}
		header->size += size;
	}

	if (sample_type & PERF_SAMPLE_REGS_USER) {
		/* regs dump ABI info */
		int size = sizeof(u64);

		perf_sample_regs_user(&data->regs_user, regs);

		if (data->regs_user.regs) {
			u64 mask = event->attr.sample_regs_user;
			size += hweight64(mask) * sizeof(u64);
		}

		header->size += size;
	}

	if (sample_type & PERF_SAMPLE_STACK_USER) {
		/*
		 * Either we need PERF_SAMPLE_STACK_USER bit to be allways
		 * processed as the last one or have additional check added
		 * in case new sample type is added, because we could eat
		 * up the rest of the sample size.
		 */
		struct perf_regs_user *uregs = &data->regs_user;
		u16 stack_size = event->attr.sample_stack_user;
		u16 size = sizeof(u64);

		if (!uregs->abi)
			perf_sample_regs_user(uregs, regs);

		stack_size = perf_sample_ustack_size(stack_size, header->size,
						     uregs->regs);

		/*
		 * If there is something to dump, add space for the dump
		 * itself and for the field that tells the dynamic size,
		 * which is how many have been actually dumped.
		 */
		if (stack_size)
			size += sizeof(u64) + stack_size;

		data->stack_user_size = stack_size;
		header->size += size;
	}
}

static void perf_event_output(struct perf_event *event,
				struct perf_sample_data *data,
				struct pt_regs *regs)
{
	struct perf_output_handle handle;
	struct perf_event_header header;

	/* protect the callchain buffers */
	rcu_read_lock();

	perf_prepare_sample(&header, data, event, regs);

	if (perf_output_begin(&handle, event, header.size))
		goto exit;

	perf_output_sample(&handle, &header, data, event);

	perf_output_end(&handle);

exit:
	rcu_read_unlock();
}

/*
 * read event_id
 */

struct perf_read_event {
	struct perf_event_header	header;

	u32				pid;
	u32				tid;
};

static void
perf_event_read_event(struct perf_event *event,
			struct task_struct *task)
{
	struct perf_output_handle handle;
	struct perf_sample_data sample;
	struct perf_read_event read_event = {
		.header = {
			.type = PERF_RECORD_READ,
			.misc = 0,
			.size = sizeof(read_event) + event->read_size,
		},
		.pid = perf_event_pid(event, task),
		.tid = perf_event_tid(event, task),
	};
	int ret;

	perf_event_header__init_id(&read_event.header, &sample, event);
	ret = perf_output_begin(&handle, event, read_event.header.size);
	if (ret)
		return;

	perf_output_put(&handle, read_event);
	perf_output_read(&handle, event);
	perf_event__output_id_sample(event, &handle, &sample);

	perf_output_end(&handle);
}

typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);

static void
perf_event_aux_ctx(struct perf_event_context *ctx,
		   perf_event_aux_output_cb output,
		   void *data)
{
	struct perf_event *event;

	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
		if (event->state < PERF_EVENT_STATE_INACTIVE)
			continue;
		if (!event_filter_match(event))
			continue;
		output(event, data);
	}
}

static void
perf_event_aux(perf_event_aux_output_cb output, void *data,
	       struct perf_event_context *task_ctx)
{
	struct perf_cpu_context *cpuctx;
	struct perf_event_context *ctx;
	struct pmu *pmu;
	int ctxn;

	rcu_read_lock();
	list_for_each_entry_rcu(pmu, &pmus, entry) {
		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
		if (cpuctx->unique_pmu != pmu)
			goto next;
		perf_event_aux_ctx(&cpuctx->ctx, output, data);
		if (task_ctx)
			goto next;
		ctxn = pmu->task_ctx_nr;
		if (ctxn < 0)
			goto next;
		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
		if (ctx)
			perf_event_aux_ctx(ctx, output, data);
next:
		put_cpu_ptr(pmu->pmu_cpu_context);
	}

	if (task_ctx) {
		preempt_disable();
		perf_event_aux_ctx(task_ctx, output, data);
		preempt_enable();
	}
	rcu_read_unlock();
}

/*
 * task tracking -- fork/exit
 *
 * enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task
 */

struct perf_task_event {
	struct task_struct		*task;
	struct perf_event_context	*task_ctx;

	struct {
		struct perf_event_header	header;

		u32				pid;
		u32				ppid;
		u32				tid;
		u32				ptid;
		u64				time;
	} event_id;
};

static int perf_event_task_match(struct perf_event *event)
{
	return event->attr.comm  || event->attr.mmap ||
	       event->attr.mmap2 || event->attr.mmap_data ||
	       event->attr.task;
}

static void perf_event_task_output(struct perf_event *event,
				   void *data)
{
	struct perf_task_event *task_event = data;
	struct perf_output_handle handle;
	struct perf_sample_data	sample;
	struct task_struct *task = task_event->task;
	int ret, size = task_event->event_id.header.size;

	if (!perf_event_task_match(event))
		return;

	perf_event_header__init_id(&task_event->event_id.header, &sample, event);

	ret = perf_output_begin(&handle, event,
				task_event->event_id.header.size);
	if (ret)
		goto out;

	task_event->event_id.pid = perf_event_pid(event, task);
	task_event->event_id.ppid = perf_event_pid(event, current);

	task_event->event_id.tid = perf_event_tid(event, task);
	task_event->event_id.ptid = perf_event_tid(event, current);

	perf_output_put(&handle, task_event->event_id);

	perf_event__output_id_sample(event, &handle, &sample);

	perf_output_end(&handle);
out:
	task_event->event_id.header.size = size;
}

static void perf_event_task(struct task_struct *task,
			      struct perf_event_context *task_ctx,
			      int new)
{
	struct perf_task_event task_event;

	if (!atomic_read(&nr_comm_events) &&
	    !atomic_read(&nr_mmap_events) &&
	    !atomic_read(&nr_task_events))
		return;

	task_event = (struct perf_task_event){
		.task	  = task,
		.task_ctx = task_ctx,
		.event_id    = {
			.header = {
				.type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT,
				.misc = 0,
				.size = sizeof(task_event.event_id),
			},
			/* .pid  */
			/* .ppid */
			/* .tid  */
			/* .ptid */
			.time = perf_clock(),
		},
	};

	perf_event_aux(perf_event_task_output,
		       &task_event,
		       task_ctx);
}

void perf_event_fork(struct task_struct *task)
{
	perf_event_task(task, NULL, 1);
}

/*
 * comm tracking
 */

struct perf_comm_event {
	struct task_struct	*task;
	char			*comm;
	int			comm_size;

	struct {
		struct perf_event_header	header;

		u32				pid;
		u32				tid;
	} event_id;
};

static int perf_event_comm_match(struct perf_event *event)
{
	return event->attr.comm;
}

static void perf_event_comm_output(struct perf_event *event,
				   void *data)
{
	struct perf_comm_event *comm_event = data;
	struct perf_output_handle handle;
	struct perf_sample_data sample;
	int size = comm_event->event_id.header.size;
	int ret;

	if (!perf_event_comm_match(event))
		return;

	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
	ret = perf_output_begin(&handle, event,
				comm_event->event_id.header.size);

	if (ret)
		goto out;

	comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
	comm_event->event_id.tid = perf_event_tid(event, comm_event->task);

	perf_output_put(&handle, comm_event->event_id);
	__output_copy(&handle, comm_event->comm,
				   comm_event->comm_size);

	perf_event__output_id_sample(event, &handle, &sample);

	perf_output_end(&handle);
out:
	comm_event->event_id.header.size = size;
}

static void perf_event_comm_event(struct perf_comm_event *comm_event)
{
	char comm[TASK_COMM_LEN];
	unsigned int size;

	memset(comm, 0, sizeof(comm));
	strlcpy(comm, comm_event->task->comm, sizeof(comm));
	size = ALIGN(strlen(comm)+1, sizeof(u64));

	comm_event->comm = comm;
	comm_event->comm_size = size;

	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;

	perf_event_aux(perf_event_comm_output,
		       comm_event,
		       NULL);
}

void perf_event_comm(struct task_struct *task)
{
	struct perf_comm_event comm_event;
	struct perf_event_context *ctx;
	int ctxn;

	rcu_read_lock();
	for_each_task_context_nr(ctxn) {
		ctx = task->perf_event_ctxp[ctxn];
		if (!ctx)
			continue;

		perf_event_enable_on_exec(ctx);
	}
	rcu_read_unlock();

	if (!atomic_read(&nr_comm_events))
		return;

	comm_event = (struct perf_comm_event){
		.task	= task,
		/* .comm      */
		/* .comm_size */
		.event_id  = {
			.header = {
				.type = PERF_RECORD_COMM,
				.misc = 0,
				/* .size */
			},
			/* .pid */
			/* .tid */
		},
	};

	perf_event_comm_event(&comm_event);
}

/*
 * mmap tracking
 */

struct perf_mmap_event {
	struct vm_area_struct	*vma;

	const char		*file_name;
	int			file_size;
	int			maj, min;
	u64			ino;
	u64			ino_generation;

	struct {
		struct perf_event_header	header;

		u32				pid;
		u32				tid;
		u64				start;
		u64				len;
		u64				pgoff;
	} event_id;
};

static int perf_event_mmap_match(struct perf_event *event,
				 void *data)
{
	struct perf_mmap_event *mmap_event = data;
	struct vm_area_struct *vma = mmap_event->vma;
	int executable = vma->vm_flags & VM_EXEC;

	return (!executable && event->attr.mmap_data) ||
	       (executable && (event->attr.mmap || event->attr.mmap2));
}

static void perf_event_mmap_output(struct perf_event *event,
				   void *data)
{
	struct perf_mmap_event *mmap_event = data;
	struct perf_output_handle handle;
	struct perf_sample_data sample;
	int size = mmap_event->event_id.header.size;
	int ret;

	if (!perf_event_mmap_match(event, data))
		return;

	if (event->attr.mmap2) {
		mmap_event->event_id.header.type = PERF_RECORD_MMAP2;
		mmap_event->event_id.header.size += sizeof(mmap_event->maj);
		mmap_event->event_id.header.size += sizeof(mmap_event->min);
		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
	}

	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
	ret = perf_output_begin(&handle, event,
				mmap_event->event_id.header.size);
	if (ret)
		goto out;

	mmap_event->event_id.pid = perf_event_pid(event, current);
	mmap_event->event_id.tid = perf_event_tid(event, current);

	perf_output_put(&handle, mmap_event->event_id);

	if (event->attr.mmap2) {
		perf_output_put(&handle, mmap_event->maj);
		perf_output_put(&handle, mmap_event->min);
		perf_output_put(&handle, mmap_event->ino);
		perf_output_put(&handle, mmap_event->ino_generation);
	}

	__output_copy(&handle, mmap_event->file_name,
				   mmap_event->file_size);

	perf_event__output_id_sample(event, &handle, &sample);

	perf_output_end(&handle);
out:
	mmap_event->event_id.header.size = size;
}

static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
{
	struct vm_area_struct *vma = mmap_event->vma;
	struct file *file = vma->vm_file;
	int maj = 0, min = 0;
	u64 ino = 0, gen = 0;
	unsigned int size;
	char tmp[16];
	char *buf = NULL;
	char *name;

	if (file) {
		struct inode *inode;
		dev_t dev;

		buf = kmalloc(PATH_MAX, GFP_KERNEL);
		if (!buf) {
			name = "//enomem";
			goto cpy_name;
		}
		/*
		 * d_path() works from the end of the rb backwards, so we
		 * need to add enough zero bytes after the string to handle
		 * the 64bit alignment we do later.
		 */
		name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
		if (IS_ERR(name)) {
			name = "//toolong";
			goto cpy_name;
		}
		inode = file_inode(vma->vm_file);
		dev = inode->i_sb->s_dev;
		ino = inode->i_ino;
		gen = inode->i_generation;
		maj = MAJOR(dev);
		min = MINOR(dev);
		goto got_name;
	} else {
		name = (char *)arch_vma_name(vma);
		if (name)
			goto cpy_name;

		if (vma->vm_start <= vma->vm_mm->start_brk &&
				vma->vm_end >= vma->vm_mm->brk) {
			name = "[heap]";
			goto cpy_name;
		}
		if (vma->vm_start <= vma->vm_mm->start_stack &&
				vma->vm_end >= vma->vm_mm->start_stack) {
			name = "[stack]";
			goto cpy_name;
		}

		name = "//anon";
		goto cpy_name;
	}

cpy_name:
	strlcpy(tmp, name, sizeof(tmp));
	name = tmp;
got_name:
	/*
	 * Since our buffer works in 8 byte units we need to align our string
	 * size to a multiple of 8. However, we must guarantee the tail end is
	 * zero'd out to avoid leaking random bits to userspace.
	 */
	size = strlen(name)+1;
	while (!IS_ALIGNED(size, sizeof(u64)))
		name[size++] = '\0';

	mmap_event->file_name = name;
	mmap_event->file_size = size;
	mmap_event->maj = maj;
	mmap_event->min = min;
	mmap_event->ino = ino;
	mmap_event->ino_generation = gen;

	if (!(vma->vm_flags & VM_EXEC))
		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;

	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;

	perf_event_aux(perf_event_mmap_output,
		       mmap_event,
		       NULL);

	kfree(buf);
}

void perf_event_mmap(struct vm_area_struct *vma)
{
	struct perf_mmap_event mmap_event;

	if (!atomic_read(&nr_mmap_events))
		return;

	mmap_event = (struct perf_mmap_event){
		.vma	= vma,
		/* .file_name */
		/* .file_size */
		.event_id  = {
			.header = {
				.type = PERF_RECORD_MMAP,
				.misc = PERF_RECORD_MISC_USER,
				/* .size */
			},
			/* .pid */
			/* .tid */
			.start  = vma->vm_start,
			.len    = vma->vm_end - vma->vm_start,
			.pgoff  = (u64)vma->vm_pgoff << PAGE_SHIFT,
		},
		/* .maj (attr_mmap2 only) */
		/* .min (attr_mmap2 only) */
		/* .ino (attr_mmap2 only) */
		/* .ino_generation (attr_mmap2 only) */
	};

	perf_event_mmap_event(&mmap_event);
}

/*
 * IRQ throttle logging
 */

static void perf_log_throttle(struct perf_event *event, int enable)
{
	struct perf_output_handle handle;
	struct perf_sample_data sample;
	int ret;

	struct {
		struct perf_event_header	header;
		u64				time;
		u64				id;
		u64				stream_id;
	} throttle_event = {
		.header = {
			.type = PERF_RECORD_THROTTLE,
			.misc = 0,
			.size = sizeof(throttle_event),
		},
		.time		= perf_clock(),
		.id		= primary_event_id(event),
		.stream_id	= event->id,
	};

	if (enable)
		throttle_event.header.type = PERF_RECORD_UNTHROTTLE;

	perf_event_header__init_id(&throttle_event.header, &sample, event);

	ret = perf_output_begin(&handle, event,
				throttle_event.header.size);
	if (ret)
		return;

	perf_output_put(&handle, throttle_event);
	perf_event__output_id_sample(event, &handle, &sample);
	perf_output_end(&handle);
}

/*
 * Generic event overflow handling, sampling.
 */

static int __perf_event_overflow(struct perf_event *event,
				   int throttle, struct perf_sample_data *data,
				   struct pt_regs *regs)
{
	int events = atomic_read(&event->event_limit);
	struct hw_perf_event *hwc = &event->hw;
	u64 seq;
	int ret = 0;

	/*
	 * Non-sampling counters might still use the PMI to fold short
	 * hardware counters, ignore those.
	 */
	if (unlikely(!is_sampling_event(event)))
		return 0;

	seq = __this_cpu_read(perf_throttled_seq);
	if (seq != hwc->interrupts_seq) {
		hwc->interrupts_seq = seq;
		hwc->interrupts = 1;
	} else {
		hwc->interrupts++;
		if (unlikely(throttle
			     && hwc->interrupts >= max_samples_per_tick)) {
			__this_cpu_inc(perf_throttled_count);
			hwc->interrupts = MAX_INTERRUPTS;
			perf_log_throttle(event, 0);
			tick_nohz_full_kick();
			ret = 1;
		}
	}

	if (event->attr.freq) {
		u64 now = perf_clock();
		s64 delta = now - hwc->freq_time_stamp;

		hwc->freq_time_stamp = now;

		if (delta > 0 && delta < 2*TICK_NSEC)
			perf_adjust_period(event, delta, hwc->last_period, true);
	}

	/*
	 * XXX event_limit might not quite work as expected on inherited
	 * events
	 */

	event->pending_kill = POLL_IN;
	if (events && atomic_dec_and_test(&event->event_limit)) {
		ret = 1;
		event->pending_kill = POLL_HUP;
		event->pending_disable = 1;
		irq_work_queue(&event->pending);
	}

	if (event->overflow_handler)
		event->overflow_handler(event, data, regs);
	else
		perf_event_output(event, data, regs);

	if (event->fasync && event->pending_kill) {
		event->pending_wakeup = 1;
		irq_work_queue(&event->pending);
	}

	return ret;
}

int perf_event_overflow(struct perf_event *event,
			  struct perf_sample_data *data,
			  struct pt_regs *regs)
{
	return __perf_event_overflow(event, 1, data, regs);
}

/*
 * Generic software event infrastructure
 */

struct swevent_htable {
	struct swevent_hlist		*swevent_hlist;
	struct mutex			hlist_mutex;
	int				hlist_refcount;

	/* Recursion avoidance in each contexts */
	int				recursion[PERF_NR_CONTEXTS];
};

static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);

/*
 * We directly increment event->count and keep a second value in
 * event->hw.period_left to count intervals. This period event
 * is kept in the range [-sample_period, 0] so that we can use the
 * sign as trigger.
 */

u64 perf_swevent_set_period(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	u64 period = hwc->last_period;
	u64 nr, offset;
	s64 old, val;

	hwc->last_period = hwc->sample_period;

again:
	old = val = local64_read(&hwc->period_left);
	if (val < 0)
		return 0;

	nr = div64_u64(period + val, period);
	offset = nr * period;
	val -= offset;
	if (local64_cmpxchg(&hwc->period_left, old, val) != old)
		goto again;

	return nr;
}

static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
				    struct perf_sample_data *data,
				    struct pt_regs *regs)
{
	struct hw_perf_event *hwc = &event->hw;
	int throttle = 0;

	if (!overflow)
		overflow = perf_swevent_set_period(event);

	if (hwc->interrupts == MAX_INTERRUPTS)
		return;

	for (; overflow; overflow--) {
		if (__perf_event_overflow(event, throttle,
					    data, regs)) {
			/*
			 * We inhibit the overflow from happening when
			 * hwc->interrupts == MAX_INTERRUPTS.
			 */
			break;
		}
		throttle = 1;
	}
}

static void perf_swevent_event(struct perf_event *event, u64 nr,
			       struct perf_sample_data *data,
			       struct pt_regs *regs)
{
	struct hw_perf_event *hwc = &event->hw;

	local64_add(nr, &event->count);

	if (!regs)
		return;

	if (!is_sampling_event(event))
		return;

	if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
		data->period = nr;
		return perf_swevent_overflow(event, 1, data, regs);
	} else
		data->period = event->hw.last_period;

	if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
		return perf_swevent_overflow(event, 1, data, regs);

	if (local64_add_negative(nr, &hwc->period_left))
		return;

	perf_swevent_overflow(event, 0, data, regs);
}

static int perf_exclude_event(struct perf_event *event,
			      struct pt_regs *regs)
{
	if (event->hw.state & PERF_HES_STOPPED)
		return 1;

	if (regs) {
		if (event->attr.exclude_user && user_mode(regs))
			return 1;

		if (event->attr.exclude_kernel && !user_mode(regs))
			return 1;
	}

	return 0;
}

static int perf_swevent_match(struct perf_event *event,
				enum perf_type_id type,
				u32 event_id,
				struct perf_sample_data *data,
				struct pt_regs *regs)
{
	if (event->attr.type != type)
		return 0;

	if (event->attr.config != event_id)
		return 0;

	if (perf_exclude_event(event, regs))
		return 0;

	return 1;
}

static inline u64 swevent_hash(u64 type, u32 event_id)
{
	u64 val = event_id | (type << 32);

	return hash_64(val, SWEVENT_HLIST_BITS);
}

static inline struct hlist_head *
__find_swevent_head(struct swevent_hlist *hlist, u64 type, u32 event_id)
{
	u64 hash = swevent_hash(type, event_id);

	return &hlist->heads[hash];
}

/* For the read side: events when they trigger */
static inline struct hlist_head *
find_swevent_head_rcu(struct swevent_htable *swhash, u64 type, u32 event_id)
{
	struct swevent_hlist *hlist;

	hlist = rcu_dereference(swhash->swevent_hlist);
	if (!hlist)
		return NULL;

	return __find_swevent_head(hlist, type, event_id);
}

/* For the event head insertion and removal in the hlist */
static inline struct hlist_head *
find_swevent_head(struct swevent_htable *swhash, struct perf_event *event)
{
	struct swevent_hlist *hlist;
	u32 event_id = event->attr.config;
	u64 type = event->attr.type;

	/*
	 * Event scheduling is always serialized against hlist allocation
	 * and release. Which makes the protected version suitable here.
	 * The context lock guarantees that.
	 */
	hlist = rcu_dereference_protected(swhash->swevent_hlist,
					  lockdep_is_held(&event->ctx->lock));
	if (!hlist)
		return NULL;

	return __find_swevent_head(hlist, type, event_id);
}

static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
				    u64 nr,
				    struct perf_sample_data *data,
				    struct pt_regs *regs)
{
	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
	struct perf_event *event;
	struct hlist_head *head;

	rcu_read_lock();
	head = find_swevent_head_rcu(swhash, type, event_id);
	if (!head)
		goto end;

	hlist_for_each_entry_rcu(event, head, hlist_entry) {
		if (perf_swevent_match(event, type, event_id, data, regs))
			perf_swevent_event(event, nr, data, regs);
	}
end:
	rcu_read_unlock();
}

int perf_swevent_get_recursion_context(void)
{
	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);

	return get_recursion_context(swhash->recursion);
}
EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);

inline void perf_swevent_put_recursion_context(int rctx)
{
	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);

	put_recursion_context(swhash->recursion, rctx);
}

void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
	struct perf_sample_data data;
	int rctx;

	preempt_disable_notrace();
	rctx = perf_swevent_get_recursion_context();
	if (rctx < 0)
		return;

	perf_sample_data_init(&data, addr, 0);

	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);

	perf_swevent_put_recursion_context(rctx);
	preempt_enable_notrace();
}

static void perf_swevent_read(struct perf_event *event)
{
}

static int perf_swevent_add(struct perf_event *event, int flags)
{
	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
	struct hw_perf_event *hwc = &event->hw;
	struct hlist_head *head;

	if (is_sampling_event(event)) {
		hwc->last_period = hwc->sample_period;
		perf_swevent_set_period(event);
	}

	hwc->state = !(flags & PERF_EF_START);

	head = find_swevent_head(swhash, event);
	if (WARN_ON_ONCE(!head))
		return -EINVAL;

	hlist_add_head_rcu(&event->hlist_entry, head);

	return 0;
}

static void perf_swevent_del(struct perf_event *event, int flags)
{
	hlist_del_rcu(&event->hlist_entry);
}

static void perf_swevent_start(struct perf_event *event, int flags)
{
	event->hw.state = 0;
}

static void perf_swevent_stop(struct perf_event *event, int flags)
{
	event->hw.state = PERF_HES_STOPPED;
}

/* Deref the hlist from the update side */
static inline struct swevent_hlist *
swevent_hlist_deref(struct swevent_htable *swhash)
{
	return rcu_dereference_protected(swhash->swevent_hlist,
					 lockdep_is_held(&swhash->hlist_mutex));
}

static void swevent_hlist_release(struct swevent_htable *swhash)
{
	struct swevent_hlist *hlist = swevent_hlist_deref(swhash);

	if (!hlist)
		return;

	rcu_assign_pointer(swhash->swevent_hlist, NULL);
	kfree_rcu(hlist, rcu_head);
}

static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
{
	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);

	mutex_lock(&swhash->hlist_mutex);

	if (!--swhash->hlist_refcount)
		swevent_hlist_release(swhash);

	mutex_unlock(&swhash->hlist_mutex);
}

static void swevent_hlist_put(struct perf_event *event)
{
	int cpu;

	for_each_possible_cpu(cpu)
		swevent_hlist_put_cpu(event, cpu);
}

static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
{
	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
	int err = 0;

	mutex_lock(&swhash->hlist_mutex);

	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
		struct swevent_hlist *hlist;

		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
		if (!hlist) {
			err = -ENOMEM;
			goto exit;
		}
		rcu_assign_pointer(swhash->swevent_hlist, hlist);
	}
	swhash->hlist_refcount++;
exit:
	mutex_unlock(&swhash->hlist_mutex);

	return err;
}

static int swevent_hlist_get(struct perf_event *event)
{
	int err;
	int cpu, failed_cpu;

	get_online_cpus();
	for_each_possible_cpu(cpu) {
		err = swevent_hlist_get_cpu(event, cpu);
		if (err) {
			failed_cpu = cpu;
			goto fail;
		}
	}
	put_online_cpus();

	return 0;
fail:
	for_each_possible_cpu(cpu) {
		if (cpu == failed_cpu)
			break;
		swevent_hlist_put_cpu(event, cpu);
	}

	put_online_cpus();
	return err;
}

struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];

static void sw_perf_event_destroy(struct perf_event *event)
{
	u64 event_id = event->attr.config;

	WARN_ON(event->parent);

	static_key_slow_dec(&perf_swevent_enabled[event_id]);
	swevent_hlist_put(event);
}

static int perf_swevent_init(struct perf_event *event)
{
	u64 event_id = event->attr.config;

	if (event->attr.type != PERF_TYPE_SOFTWARE)
		return -ENOENT;

	/*
	 * no branch sampling for software events
	 */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	switch (event_id) {
	case PERF_COUNT_SW_CPU_CLOCK:
	case PERF_COUNT_SW_TASK_CLOCK:
		return -ENOENT;

	default:
		break;
	}

	if (event_id >= PERF_COUNT_SW_MAX)
		return -ENOENT;

	if (!event->parent) {
		int err;

		err = swevent_hlist_get(event);
		if (err)
			return err;

		static_key_slow_inc(&perf_swevent_enabled[event_id]);
		event->destroy = sw_perf_event_destroy;
	}

	return 0;
}

static int perf_swevent_event_idx(struct perf_event *event)
{
	return 0;
}

static struct pmu perf_swevent = {
	.task_ctx_nr	= perf_sw_context,

	.event_init	= perf_swevent_init,
	.add		= perf_swevent_add,
	.del		= perf_swevent_del,
	.start		= perf_swevent_start,
	.stop		= perf_swevent_stop,
	.read		= perf_swevent_read,

	.event_idx	= perf_swevent_event_idx,
};

#ifdef CONFIG_EVENT_TRACING

static int perf_tp_filter_match(struct perf_event *event,
				struct perf_sample_data *data)
{
	void *record = data->raw->data;

	if (likely(!event->filter) || filter_match_preds(event->filter, record))
		return 1;
	return 0;
}

static int perf_tp_event_match(struct perf_event *event,
				struct perf_sample_data *data,
				struct pt_regs *regs)
{
	if (event->hw.state & PERF_HES_STOPPED)
		return 0;
	/*
	 * All tracepoints are from kernel-space.
	 */
	if (event->attr.exclude_kernel)
		return 0;

	if (!perf_tp_filter_match(event, data))
		return 0;

	return 1;
}

void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
		   struct pt_regs *regs, struct hlist_head *head, int rctx,
		   struct task_struct *task)
{
	struct perf_sample_data data;
	struct perf_event *event;

	struct perf_raw_record raw = {
		.size = entry_size,
		.data = record,
	};

	perf_sample_data_init(&data, addr, 0);
	data.raw = &raw;

	hlist_for_each_entry_rcu(event, head, hlist_entry) {
		if (perf_tp_event_match(event, &data, regs))
			perf_swevent_event(event, count, &data, regs);
	}

	/*
	 * If we got specified a target task, also iterate its context and
	 * deliver this event there too.
	 */
	if (task && task != current) {
		struct perf_event_context *ctx;
		struct trace_entry *entry = record;

		rcu_read_lock();
		ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]);
		if (!ctx)
			goto unlock;

		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
			if (event->attr.type != PERF_TYPE_TRACEPOINT)
				continue;
			if (event->attr.config != entry->type)
				continue;
			if (perf_tp_event_match(event, &data, regs))
				perf_swevent_event(event, count, &data, regs);
		}
unlock:
		rcu_read_unlock();
	}

	perf_swevent_put_recursion_context(rctx);
}
EXPORT_SYMBOL_GPL(perf_tp_event);

static void tp_perf_event_destroy(struct perf_event *event)
{
	perf_trace_destroy(event);
}

static int perf_tp_event_init(struct perf_event *event)
{
	int err;

	if (event->attr.type != PERF_TYPE_TRACEPOINT)
		return -ENOENT;

	/*
	 * no branch sampling for tracepoint events
	 */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	err = perf_trace_init(event);
	if (err)
		return err;

	event->destroy = tp_perf_event_destroy;

	return 0;
}

static struct pmu perf_tracepoint = {
	.task_ctx_nr	= perf_sw_context,

	.event_init	= perf_tp_event_init,
	.add		= perf_trace_add,
	.del		= perf_trace_del,
	.start		= perf_swevent_start,
	.stop		= perf_swevent_stop,
	.read		= perf_swevent_read,

	.event_idx	= perf_swevent_event_idx,
};

static inline void perf_tp_register(void)
{
	perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}

static int perf_event_set_filter(struct perf_event *event, void __user *arg)
{
	char *filter_str;
	int ret;

	if (event->attr.type != PERF_TYPE_TRACEPOINT)
		return -EINVAL;

	filter_str = strndup_user(arg, PAGE_SIZE);
	if (IS_ERR(filter_str))
		return PTR_ERR(filter_str);

	ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);

	kfree(filter_str);
	return ret;
}

static void perf_event_free_filter(struct perf_event *event)
{
	ftrace_profile_free_filter(event);
}

#else

static inline void perf_tp_register(void)
{
}

static int perf_event_set_filter(struct perf_event *event, void __user *arg)
{
	return -ENOENT;
}

static void perf_event_free_filter(struct perf_event *event)
{
}

#endif /* CONFIG_EVENT_TRACING */

#ifdef CONFIG_HAVE_HW_BREAKPOINT
void perf_bp_event(struct perf_event *bp, void *data)
{
	struct perf_sample_data sample;
	struct pt_regs *regs = data;

	perf_sample_data_init(&sample, bp->attr.bp_addr, 0);

	if (!bp->hw.state && !perf_exclude_event(bp, regs))
		perf_swevent_event(bp, 1, &sample, regs);
}
#endif

/*
 * hrtimer based swevent callback
 */

static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
{
	enum hrtimer_restart ret = HRTIMER_RESTART;
	struct perf_sample_data data;
	struct pt_regs *regs;
	struct perf_event *event;
	u64 period;

	event = container_of(hrtimer, struct perf_event, hw.hrtimer);

	if (event->state != PERF_EVENT_STATE_ACTIVE)
		return HRTIMER_NORESTART;

	event->pmu->read(event);

	perf_sample_data_init(&data, 0, event->hw.last_period);
	regs = get_irq_regs();

	if (regs && !perf_exclude_event(event, regs)) {
		if (!(event->attr.exclude_idle && is_idle_task(current)))
			if (__perf_event_overflow(event, 1, &data, regs))
				ret = HRTIMER_NORESTART;
	}

	period = max_t(u64, 10000, event->hw.sample_period);
	hrtimer_forward_now(hrtimer, ns_to_ktime(period));

	return ret;
}

static void perf_swevent_start_hrtimer(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	s64 period;

	if (!is_sampling_event(event))
		return;

	period = local64_read(&hwc->period_left);
	if (period) {
		if (period < 0)
			period = 10000;

		local64_set(&hwc->period_left, 0);
	} else {
		period = max_t(u64, 10000, hwc->sample_period);
	}
	__hrtimer_start_range_ns(&hwc->hrtimer,
				ns_to_ktime(period), 0,
				HRTIMER_MODE_REL_PINNED, 0);
}

static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	if (is_sampling_event(event)) {
		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
		local64_set(&hwc->period_left, ktime_to_ns(remaining));

		hrtimer_cancel(&hwc->hrtimer);
	}
}

static void perf_swevent_init_hrtimer(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	if (!is_sampling_event(event))
		return;

	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	hwc->hrtimer.function = perf_swevent_hrtimer;

	/*
	 * Since hrtimers have a fixed rate, we can do a static freq->period
	 * mapping and avoid the whole period adjust feedback stuff.
	 */
	if (event->attr.freq) {
		long freq = event->attr.sample_freq;

		event->attr.sample_period = NSEC_PER_SEC / freq;
		hwc->sample_period = event->attr.sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
		hwc->last_period = hwc->sample_period;
		event->attr.freq = 0;
	}
}

/*
 * Software event: cpu wall time clock
 */

static void cpu_clock_event_update(struct perf_event *event)
{
	s64 prev;
	u64 now;

	now = local_clock();
	prev = local64_xchg(&event->hw.prev_count, now);
	local64_add(now - prev, &event->count);
}

static void cpu_clock_event_start(struct perf_event *event, int flags)
{
	local64_set(&event->hw.prev_count, local_clock());
	perf_swevent_start_hrtimer(event);
}

static void cpu_clock_event_stop(struct perf_event *event, int flags)
{
	perf_swevent_cancel_hrtimer(event);
	cpu_clock_event_update(event);
}

static int cpu_clock_event_add(struct perf_event *event, int flags)
{
	if (flags & PERF_EF_START)
		cpu_clock_event_start(event, flags);

	return 0;
}

static void cpu_clock_event_del(struct perf_event *event, int flags)
{
	cpu_clock_event_stop(event, flags);
}

static void cpu_clock_event_read(struct perf_event *event)
{
	cpu_clock_event_update(event);
}

static int cpu_clock_event_init(struct perf_event *event)
{
	if (event->attr.type != PERF_TYPE_SOFTWARE)
		return -ENOENT;

	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
		return -ENOENT;

	/*
	 * no branch sampling for software events
	 */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	perf_swevent_init_hrtimer(event);

	return 0;
}

static struct pmu perf_cpu_clock = {
	.task_ctx_nr	= perf_sw_context,

	.event_init	= cpu_clock_event_init,
	.add		= cpu_clock_event_add,
	.del		= cpu_clock_event_del,
	.start		= cpu_clock_event_start,
	.stop		= cpu_clock_event_stop,
	.read		= cpu_clock_event_read,

	.event_idx	= perf_swevent_event_idx,
};

/*
 * Software event: task time clock
 */

static void task_clock_event_update(struct perf_event *event, u64 now)
{
	u64 prev;
	s64 delta;

	prev = local64_xchg(&event->hw.prev_count, now);
	delta = now - prev;
	local64_add(delta, &event->count);
}

static void task_clock_event_start(struct perf_event *event, int flags)
{
	local64_set(&event->hw.prev_count, event->ctx->time);
	perf_swevent_start_hrtimer(event);
}

static void task_clock_event_stop(struct perf_event *event, int flags)
{
	perf_swevent_cancel_hrtimer(event);
	task_clock_event_update(event, event->ctx->time);
}

static int task_clock_event_add(struct perf_event *event, int flags)
{
	if (flags & PERF_EF_START)
		task_clock_event_start(event, flags);

	return 0;
}

static void task_clock_event_del(struct perf_event *event, int flags)
{
	task_clock_event_stop(event, PERF_EF_UPDATE);
}

static void task_clock_event_read(struct perf_event *event)
{
	u64 now = perf_clock();
	u64 delta = now - event->ctx->timestamp;
	u64 time = event->ctx->time + delta;

	task_clock_event_update(event, time);
}

static int task_clock_event_init(struct perf_event *event)
{
	if (event->attr.type != PERF_TYPE_SOFTWARE)
		return -ENOENT;

	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
		return -ENOENT;

	/*
	 * no branch sampling for software events
	 */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	perf_swevent_init_hrtimer(event);

	return 0;
}

static struct pmu perf_task_clock = {
	.task_ctx_nr	= perf_sw_context,

	.event_init	= task_clock_event_init,
	.add		= task_clock_event_add,
	.del		= task_clock_event_del,
	.start		= task_clock_event_start,
	.stop		= task_clock_event_stop,
	.read		= task_clock_event_read,

	.event_idx	= perf_swevent_event_idx,
};

static void perf_pmu_nop_void(struct pmu *pmu)
{
}

static int perf_pmu_nop_int(struct pmu *pmu)
{
	return 0;
}

static void perf_pmu_start_txn(struct pmu *pmu)
{
	perf_pmu_disable(pmu);
}

static int perf_pmu_commit_txn(struct pmu *pmu)
{
	perf_pmu_enable(pmu);
	return 0;
}

static void perf_pmu_cancel_txn(struct pmu *pmu)
{
	perf_pmu_enable(pmu);
}

static int perf_event_idx_default(struct perf_event *event)
{
	return event->hw.idx + 1;
}

/*
 * Ensures all contexts with the same task_ctx_nr have the same
 * pmu_cpu_context too.
 */
static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
{
	struct pmu *pmu;

	if (ctxn < 0)
		return NULL;

	list_for_each_entry(pmu, &pmus, entry) {
		if (pmu->task_ctx_nr == ctxn)
			return pmu->pmu_cpu_context;
	}

	return NULL;
}

static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct perf_cpu_context *cpuctx;

		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);

		if (cpuctx->unique_pmu == old_pmu)
			cpuctx->unique_pmu = pmu;
	}
}

static void free_pmu_context(struct pmu *pmu)
{
	struct pmu *i;

	mutex_lock(&pmus_lock);
	/*
	 * Like a real lame refcount.
	 */
	list_for_each_entry(i, &pmus, entry) {
		if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
			update_pmu_context(i, pmu);
			goto out;
		}
	}

	free_percpu(pmu->pmu_cpu_context);
out:
	mutex_unlock(&pmus_lock);
}
static struct idr pmu_idr;

static ssize_t
type_show(struct device *dev, struct device_attribute *attr, char *page)
{
	struct pmu *pmu = dev_get_drvdata(dev);

	return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
}
static DEVICE_ATTR_RO(type);

static ssize_t
perf_event_mux_interval_ms_show(struct device *dev,
				struct device_attribute *attr,
				char *page)
{
	struct pmu *pmu = dev_get_drvdata(dev);

	return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
}

static ssize_t
perf_event_mux_interval_ms_store(struct device *dev,
				 struct device_attribute *attr,
				 const char *buf, size_t count)
{
	struct pmu *pmu = dev_get_drvdata(dev);
	int timer, cpu, ret;

	ret = kstrtoint(buf, 0, &timer);
	if (ret)
		return ret;

	if (timer < 1)
		return -EINVAL;

	/* same value, noting to do */
	if (timer == pmu->hrtimer_interval_ms)
		return count;

	pmu->hrtimer_interval_ms = timer;

	/* update all cpuctx for this PMU */
	for_each_possible_cpu(cpu) {
		struct perf_cpu_context *cpuctx;
		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
		cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);

		if (hrtimer_active(&cpuctx->hrtimer))
			hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
	}

	return count;
}
static DEVICE_ATTR_RW(perf_event_mux_interval_ms);

static struct attribute *pmu_dev_attrs[] = {
	&dev_attr_type.attr,
	&dev_attr_perf_event_mux_interval_ms.attr,
	NULL,
};
ATTRIBUTE_GROUPS(pmu_dev);

static int pmu_bus_running;
static struct bus_type pmu_bus = {
	.name		= "event_source",
	.dev_groups	= pmu_dev_groups,
};

static void pmu_dev_release(struct device *dev)
{
	kfree(dev);
}

static int pmu_dev_alloc(struct pmu *pmu)
{
	int ret = -ENOMEM;

	pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
	if (!pmu->dev)
		goto out;

	pmu->dev->groups = pmu->attr_groups;
	device_initialize(pmu->dev);
	ret = dev_set_name(pmu->dev, "%s", pmu->name);
	if (ret)
		goto free_dev;

	dev_set_drvdata(pmu->dev, pmu);
	pmu->dev->bus = &pmu_bus;
	pmu->dev->release = pmu_dev_release;
	ret = device_add(pmu->dev);
	if (ret)
		goto free_dev;

out:
	return ret;

free_dev:
	put_device(pmu->dev);
	goto out;
}

static struct lock_class_key cpuctx_mutex;
static struct lock_class_key cpuctx_lock;

int perf_pmu_register(struct pmu *pmu, const char *name, int type)
{
	int cpu, ret;

	mutex_lock(&pmus_lock);
	ret = -ENOMEM;
	pmu->pmu_disable_count = alloc_percpu(int);
	if (!pmu->pmu_disable_count)
		goto unlock;

	pmu->type = -1;
	if (!name)
		goto skip_type;
	pmu->name = name;

	if (type < 0) {
		type = idr_alloc(&pmu_idr, pmu, PERF_TYPE_MAX, 0, GFP_KERNEL);
		if (type < 0) {
			ret = type;
			goto free_pdc;
		}
	}
	pmu->type = type;

	if (pmu_bus_running) {
		ret = pmu_dev_alloc(pmu);
		if (ret)
			goto free_idr;
	}

skip_type:
	pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
	if (pmu->pmu_cpu_context)
		goto got_cpu_context;

	ret = -ENOMEM;
	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
	if (!pmu->pmu_cpu_context)
		goto free_dev;

	for_each_possible_cpu(cpu) {
		struct perf_cpu_context *cpuctx;

		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
		__perf_event_init_context(&cpuctx->ctx);
		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
		cpuctx->ctx.type = cpu_context;
		cpuctx->ctx.pmu = pmu;

		__perf_cpu_hrtimer_init(cpuctx, cpu);

		INIT_LIST_HEAD(&cpuctx->rotation_list);
		cpuctx->unique_pmu = pmu;
	}

got_cpu_context:
	if (!pmu->start_txn) {
		if (pmu->pmu_enable) {
			/*
			 * If we have pmu_enable/pmu_disable calls, install
			 * transaction stubs that use that to try and batch
			 * hardware accesses.
			 */
			pmu->start_txn  = perf_pmu_start_txn;
			pmu->commit_txn = perf_pmu_commit_txn;
			pmu->cancel_txn = perf_pmu_cancel_txn;
		} else {
			pmu->start_txn  = perf_pmu_nop_void;
			pmu->commit_txn = perf_pmu_nop_int;
			pmu->cancel_txn = perf_pmu_nop_void;
		}
	}

	if (!pmu->pmu_enable) {
		pmu->pmu_enable  = perf_pmu_nop_void;
		pmu->pmu_disable = perf_pmu_nop_void;
	}

	if (!pmu->event_idx)
		pmu->event_idx = perf_event_idx_default;

	list_add_rcu(&pmu->entry, &pmus);
	ret = 0;
unlock:
	mutex_unlock(&pmus_lock);

	return ret;

free_dev:
	device_del(pmu->dev);
	put_device(pmu->dev);

free_idr:
	if (pmu->type >= PERF_TYPE_MAX)
		idr_remove(&pmu_idr, pmu->type);

free_pdc:
	free_percpu(pmu->pmu_disable_count);
	goto unlock;
}

void perf_pmu_unregister(struct pmu *pmu)
{
	mutex_lock(&pmus_lock);
	list_del_rcu(&pmu->entry);
	mutex_unlock(&pmus_lock);

	/*
	 * We dereference the pmu list under both SRCU and regular RCU, so
	 * synchronize against both of those.
	 */
	synchronize_srcu(&pmus_srcu);
	synchronize_rcu();

	free_percpu(pmu->pmu_disable_count);
	if (pmu->type >= PERF_TYPE_MAX)
		idr_remove(&pmu_idr, pmu->type);
	device_del(pmu->dev);
	put_device(pmu->dev);
	free_pmu_context(pmu);
}

struct pmu *perf_init_event(struct perf_event *event)
{
	struct pmu *pmu = NULL;
	int idx;
	int ret;

	idx = srcu_read_lock(&pmus_srcu);

	rcu_read_lock();
	pmu = idr_find(&pmu_idr, event->attr.type);
	rcu_read_unlock();
	if (pmu) {
		event->pmu = pmu;
		ret = pmu->event_init(event);
		if (ret)
			pmu = ERR_PTR(ret);
		goto unlock;
	}

	list_for_each_entry_rcu(pmu, &pmus, entry) {
		event->pmu = pmu;
		ret = pmu->event_init(event);
		if (!ret)
			goto unlock;

		if (ret != -ENOENT) {
			pmu = ERR_PTR(ret);
			goto unlock;
		}
	}
	pmu = ERR_PTR(-ENOENT);
unlock:
	srcu_read_unlock(&pmus_srcu, idx);

	return pmu;
}

static void account_event_cpu(struct perf_event *event, int cpu)
{
	if (event->parent)
		return;

	if (has_branch_stack(event)) {
		if (!(event->attach_state & PERF_ATTACH_TASK))
			atomic_inc(&per_cpu(perf_branch_stack_events, cpu));
	}
	if (is_cgroup_event(event))
		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
}

static void account_event(struct perf_event *event)
{
	if (event->parent)
		return;

	if (event->attach_state & PERF_ATTACH_TASK)
		static_key_slow_inc(&perf_sched_events.key);
	if (event->attr.mmap || event->attr.mmap_data)
		atomic_inc(&nr_mmap_events);
	if (event->attr.comm)
		atomic_inc(&nr_comm_events);
	if (event->attr.task)
		atomic_inc(&nr_task_events);
	if (event->attr.freq) {
		if (atomic_inc_return(&nr_freq_events) == 1)
			tick_nohz_full_kick_all();
	}
	if (has_branch_stack(event))
		static_key_slow_inc(&perf_sched_events.key);
	if (is_cgroup_event(event))
		static_key_slow_inc(&perf_sched_events.key);

	account_event_cpu(event, event->cpu);
}

/*
 * Allocate and initialize a event structure
 */
static struct perf_event *
perf_event_alloc(struct perf_event_attr *attr, int cpu,
		 struct task_struct *task,
		 struct perf_event *group_leader,
		 struct perf_event *parent_event,
		 perf_overflow_handler_t overflow_handler,
		 void *context)
{
	struct pmu *pmu;
	struct perf_event *event;
	struct hw_perf_event *hwc;
	long err = -EINVAL;

	if ((unsigned)cpu >= nr_cpu_ids) {
		if (!task || cpu != -1)
			return ERR_PTR(-EINVAL);
	}

	event = kzalloc(sizeof(*event), GFP_KERNEL);
	if (!event)
		return ERR_PTR(-ENOMEM);

	/*
	 * Single events are their own group leaders, with an
	 * empty sibling list:
	 */
	if (!group_leader)
		group_leader = event;

	mutex_init(&event->child_mutex);
	INIT_LIST_HEAD(&event->child_list);

	INIT_LIST_HEAD(&event->group_entry);
	INIT_LIST_HEAD(&event->event_entry);
	INIT_LIST_HEAD(&event->sibling_list);
	INIT_LIST_HEAD(&event->rb_entry);
	INIT_LIST_HEAD(&event->active_entry);
	INIT_HLIST_NODE(&event->hlist_entry);


	init_waitqueue_head(&event->waitq);
	init_irq_work(&event->pending, perf_pending_event);

	mutex_init(&event->mmap_mutex);

	atomic_long_set(&event->refcount, 1);
	event->cpu		= cpu;
	event->attr		= *attr;
	event->group_leader	= group_leader;
	event->pmu		= NULL;
	event->oncpu		= -1;

	event->parent		= parent_event;

	event->ns		= get_pid_ns(task_active_pid_ns(current));
	event->id		= atomic64_inc_return(&perf_event_id);

	event->state		= PERF_EVENT_STATE_INACTIVE;

	if (task) {
		event->attach_state = PERF_ATTACH_TASK;

		if (attr->type == PERF_TYPE_TRACEPOINT)
			event->hw.tp_target = task;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
		/*
		 * hw_breakpoint is a bit difficult here..
		 */
		else if (attr->type == PERF_TYPE_BREAKPOINT)
			event->hw.bp_target = task;
#endif
	}

	if (!overflow_handler && parent_event) {
		overflow_handler = parent_event->overflow_handler;
		context = parent_event->overflow_handler_context;
	}

	event->overflow_handler	= overflow_handler;
	event->overflow_handler_context = context;

	perf_event__state_init(event);

	pmu = NULL;

	hwc = &event->hw;
	hwc->sample_period = attr->sample_period;
	if (attr->freq && attr->sample_freq)
		hwc->sample_period = 1;
	hwc->last_period = hwc->sample_period;

	local64_set(&hwc->period_left, hwc->sample_period);

	/*
	 * we currently do not support PERF_FORMAT_GROUP on inherited events
	 */
	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
		goto err_ns;

	pmu = perf_init_event(event);
	if (!pmu)
		goto err_ns;
	else if (IS_ERR(pmu)) {
		err = PTR_ERR(pmu);
		goto err_ns;
	}

	if (!event->parent) {
		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
			err = get_callchain_buffers();
			if (err)
				goto err_pmu;
		}
	}

	return event;

err_pmu:
	if (event->destroy)
		event->destroy(event);
err_ns:
	if (event->ns)
		put_pid_ns(event->ns);
	kfree(event);

	return ERR_PTR(err);
}

static int perf_copy_attr(struct perf_event_attr __user *uattr,
			  struct perf_event_attr *attr)
{
	u32 size;
	int ret;

	if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
		return -EFAULT;

	/*
	 * zero the full structure, so that a short copy will be nice.
	 */
	memset(attr, 0, sizeof(*attr));

	ret = get_user(size, &uattr->size);
	if (ret)
		return ret;

	if (size > PAGE_SIZE)	/* silly large */
		goto err_size;

	if (!size)		/* abi compat */
		size = PERF_ATTR_SIZE_VER0;

	if (size < PERF_ATTR_SIZE_VER0)
		goto err_size;

	/*
	 * If we're handed a bigger struct than we know of,
	 * ensure all the unknown bits are 0 - i.e. new
	 * user-space does not rely on any kernel feature
	 * extensions we dont know about yet.
	 */
	if (size > sizeof(*attr)) {
		unsigned char __user *addr;
		unsigned char __user *end;
		unsigned char val;

		addr = (void __user *)uattr + sizeof(*attr);
		end  = (void __user *)uattr + size;

		for (; addr < end; addr++) {
			ret = get_user(val, addr);
			if (ret)
				return ret;
			if (val)
				goto err_size;
		}
		size = sizeof(*attr);
	}

	ret = copy_from_user(attr, uattr, size);
	if (ret)
		return -EFAULT;

	/* disabled for now */
	if (attr->mmap2)
		return -EINVAL;

	if (attr->__reserved_1)
		return -EINVAL;

	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
		return -EINVAL;

	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
		return -EINVAL;

	if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
		u64 mask = attr->branch_sample_type;

		/* only using defined bits */
		if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
			return -EINVAL;

		/* at least one branch bit must be set */
		if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
			return -EINVAL;

		/* propagate priv level, when not set for branch */
		if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {

			/* exclude_kernel checked on syscall entry */
			if (!attr->exclude_kernel)
				mask |= PERF_SAMPLE_BRANCH_KERNEL;

			if (!attr->exclude_user)
				mask |= PERF_SAMPLE_BRANCH_USER;

			if (!attr->exclude_hv)
				mask |= PERF_SAMPLE_BRANCH_HV;
			/*
			 * adjust user setting (for HW filter setup)
			 */
			attr->branch_sample_type = mask;
		}
		/* privileged levels capture (kernel, hv): check permissions */
		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
			return -EACCES;
	}

	if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
		ret = perf_reg_validate(attr->sample_regs_user);
		if (ret)
			return ret;
	}

	if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
		if (!arch_perf_have_user_stack_dump())
			return -ENOSYS;

		/*
		 * We have __u32 type for the size, but so far
		 * we can only use __u16 as maximum due to the
		 * __u16 sample size limit.
		 */
		if (attr->sample_stack_user >= USHRT_MAX)
			ret = -EINVAL;
		else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
			ret = -EINVAL;
	}

out:
	return ret;

err_size:
	put_user(sizeof(*attr), &uattr->size);
	ret = -E2BIG;
	goto out;
}

static int
perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
{
	struct ring_buffer *rb = NULL, *old_rb = NULL;
	int ret = -EINVAL;

	if (!output_event)
		goto set;

	/* don't allow circular references */
	if (event == output_event)
		goto out;

	/*
	 * Don't allow cross-cpu buffers
	 */
	if (output_event->cpu != event->cpu)
		goto out;

	/*
	 * If its not a per-cpu rb, it must be the same task.
	 */
	if (output_event->cpu == -1 && output_event->ctx != event->ctx)
		goto out;

set:
	mutex_lock(&event->mmap_mutex);
	/* Can't redirect output if we've got an active mmap() */
	if (atomic_read(&event->mmap_count))
		goto unlock;

	old_rb = event->rb;

	if (output_event) {
		/* get the rb we want to redirect to */
		rb = ring_buffer_get(output_event);
		if (!rb)
			goto unlock;
	}

	if (old_rb)
		ring_buffer_detach(event, old_rb);

	if (rb)
		ring_buffer_attach(event, rb);

	rcu_assign_pointer(event->rb, rb);

	if (old_rb) {
		ring_buffer_put(old_rb);
		/*
		 * Since we detached before setting the new rb, so that we
		 * could attach the new rb, we could have missed a wakeup.
		 * Provide it now.
		 */
		wake_up_all(&event->waitq);
	}

	ret = 0;
unlock:
	mutex_unlock(&event->mmap_mutex);

out:
	return ret;
}

/**
 * sys_perf_event_open - open a performance event, associate it to a task/cpu
 *
 * @attr_uptr:	event_id type attributes for monitoring/sampling
 * @pid:		target pid
 * @cpu:		target cpu
 * @group_fd:		group leader event fd
 */
SYSCALL_DEFINE5(perf_event_open,
		struct perf_event_attr __user *, attr_uptr,
		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
{
	struct perf_event *group_leader = NULL, *output_event = NULL;
	struct perf_event *event, *sibling;
	struct perf_event_attr attr;
	struct perf_event_context *ctx;
	struct file *event_file = NULL;
	struct fd group = {NULL, 0};
	struct task_struct *task = NULL;
	struct pmu *pmu;
	int event_fd;
	int move_group = 0;
	int err;
	int f_flags = O_RDWR;

	/* for future expandability... */
	if (flags & ~PERF_FLAG_ALL)
		return -EINVAL;

	err = perf_copy_attr(attr_uptr, &attr);
	if (err)
		return err;

	if (!attr.exclude_kernel) {
		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
			return -EACCES;
	}

	if (attr.freq) {
		if (attr.sample_freq > sysctl_perf_event_sample_rate)
			return -EINVAL;
	}

	/*
	 * In cgroup mode, the pid argument is used to pass the fd
	 * opened to the cgroup directory in cgroupfs. The cpu argument
	 * designates the cpu on which to monitor threads from that
	 * cgroup.
	 */
	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
		return -EINVAL;

	if (flags & PERF_FLAG_FD_CLOEXEC)
		f_flags |= O_CLOEXEC;

	event_fd = get_unused_fd_flags(f_flags);
	if (event_fd < 0)
		return event_fd;

	if (group_fd != -1) {
		err = perf_fget_light(group_fd, &group);
		if (err)
			goto err_fd;
		group_leader = group.file->private_data;
		if (flags & PERF_FLAG_FD_OUTPUT)
			output_event = group_leader;
		if (flags & PERF_FLAG_FD_NO_GROUP)
			group_leader = NULL;
	}

	if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
		task = find_lively_task_by_vpid(pid);
		if (IS_ERR(task)) {
			err = PTR_ERR(task);
			goto err_group_fd;
		}
	}

	get_online_cpus();

	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
				 NULL, NULL);
	if (IS_ERR(event)) {
		err = PTR_ERR(event);
		goto err_task;
	}

	if (flags & PERF_FLAG_PID_CGROUP) {
		err = perf_cgroup_connect(pid, event, &attr, group_leader);
		if (err) {
			__free_event(event);
			goto err_task;
		}
	}

	account_event(event);

	/*
	 * Special case software events and allow them to be part of
	 * any hardware group.
	 */
	pmu = event->pmu;

	if (group_leader &&
	    (is_software_event(event) != is_software_event(group_leader))) {
		if (is_software_event(event)) {
			/*
			 * If event and group_leader are not both a software
			 * event, and event is, then group leader is not.
			 *
			 * Allow the addition of software events to !software
			 * groups, this is safe because software events never
			 * fail to schedule.
			 */
			pmu = group_leader->pmu;
		} else if (is_software_event(group_leader) &&
			   (group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
			/*
			 * In case the group is a pure software group, and we
			 * try to add a hardware event, move the whole group to
			 * the hardware context.
			 */
			move_group = 1;
		}
	}

	/*
	 * Get the target context (task or percpu):
	 */
	ctx = find_get_context(pmu, task, event->cpu);
	if (IS_ERR(ctx)) {
		err = PTR_ERR(ctx);
		goto err_alloc;
	}

	if (task) {
		put_task_struct(task);
		task = NULL;
	}

	/*
	 * Look up the group leader (we will attach this event to it):
	 */
	if (group_leader) {
		err = -EINVAL;

		/*
		 * Do not allow a recursive hierarchy (this new sibling
		 * becoming part of another group-sibling):
		 */
		if (group_leader->group_leader != group_leader)
			goto err_context;
		/*
		 * Do not allow to attach to a group in a different
		 * task or CPU context:
		 */
		if (move_group) {
			if (group_leader->ctx->type != ctx->type)
				goto err_context;
		} else {
			if (group_leader->ctx != ctx)
				goto err_context;
		}

		/*
		 * Only a group leader can be exclusive or pinned
		 */
		if (attr.exclusive || attr.pinned)
			goto err_context;
	}

	if (output_event) {
		err = perf_event_set_output(event, output_event);
		if (err)
			goto err_context;
	}

	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
					f_flags);
	if (IS_ERR(event_file)) {
		err = PTR_ERR(event_file);
		goto err_context;
	}

	if (move_group) {
		struct perf_event_context *gctx = group_leader->ctx;

		mutex_lock(&gctx->mutex);
		perf_remove_from_context(group_leader);

		/*
		 * Removing from the context ends up with disabled
		 * event. What we want here is event in the initial
		 * startup state, ready to be add into new context.
		 */
		perf_event__state_init(group_leader);
		list_for_each_entry(sibling, &group_leader->sibling_list,
				    group_entry) {
			perf_remove_from_context(sibling);
			perf_event__state_init(sibling);
			put_ctx(gctx);
		}
		mutex_unlock(&gctx->mutex);
		put_ctx(gctx);
	}

	WARN_ON_ONCE(ctx->parent_ctx);
	mutex_lock(&ctx->mutex);

	if (move_group) {
		synchronize_rcu();
		perf_install_in_context(ctx, group_leader, event->cpu);
		get_ctx(ctx);
		list_for_each_entry(sibling, &group_leader->sibling_list,
				    group_entry) {
			perf_install_in_context(ctx, sibling, event->cpu);
			get_ctx(ctx);
		}
	}

	perf_install_in_context(ctx, event, event->cpu);
	perf_unpin_context(ctx);
	mutex_unlock(&ctx->mutex);

	put_online_cpus();

	event->owner = current;

	mutex_lock(&current->perf_event_mutex);
	list_add_tail(&event->owner_entry, &current->perf_event_list);
	mutex_unlock(&current->perf_event_mutex);

	/*
	 * Precalculate sample_data sizes
	 */
	perf_event__header_size(event);
	perf_event__id_header_size(event);

	/*
	 * Drop the reference on the group_event after placing the
	 * new event on the sibling_list. This ensures destruction
	 * of the group leader will find the pointer to itself in
	 * perf_group_detach().
	 */
	fdput(group);
	fd_install(event_fd, event_file);
	return event_fd;

err_context:
	perf_unpin_context(ctx);
	put_ctx(ctx);
err_alloc:
	free_event(event);
err_task:
	put_online_cpus();
	if (task)
		put_task_struct(task);
err_group_fd:
	fdput(group);
err_fd:
	put_unused_fd(event_fd);
	return err;
}

/**
 * perf_event_create_kernel_counter
 *
 * @attr: attributes of the counter to create
 * @cpu: cpu in which the counter is bound
 * @task: task to profile (NULL for percpu)
 */
struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
				 struct task_struct *task,
				 perf_overflow_handler_t overflow_handler,
				 void *context)
{
	struct perf_event_context *ctx;
	struct perf_event *event;
	int err;

	/*
	 * Get the target context (task or percpu):
	 */

	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
				 overflow_handler, context);
	if (IS_ERR(event)) {
		err = PTR_ERR(event);
		goto err;
	}

	account_event(event);

	ctx = find_get_context(event->pmu, task, cpu);
	if (IS_ERR(ctx)) {
		err = PTR_ERR(ctx);
		goto err_free;
	}

	WARN_ON_ONCE(ctx->parent_ctx);
	mutex_lock(&ctx->mutex);
	perf_install_in_context(ctx, event, cpu);
	perf_unpin_context(ctx);
	mutex_unlock(&ctx->mutex);

	return event;

err_free:
	free_event(event);
err:
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);

void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
{
	struct perf_event_context *src_ctx;
	struct perf_event_context *dst_ctx;
	struct perf_event *event, *tmp;
	LIST_HEAD(events);

	src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
	dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;

	mutex_lock(&src_ctx->mutex);
	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
				 event_entry) {
		perf_remove_from_context(event);
		unaccount_event_cpu(event, src_cpu);
		put_ctx(src_ctx);
		list_add(&event->migrate_entry, &events);
	}
	mutex_unlock(&src_ctx->mutex);

	synchronize_rcu();

	mutex_lock(&dst_ctx->mutex);
	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
		list_del(&event->migrate_entry);
		if (event->state >= PERF_EVENT_STATE_OFF)
			event->state = PERF_EVENT_STATE_INACTIVE;
		account_event_cpu(event, dst_cpu);
		perf_install_in_context(dst_ctx, event, dst_cpu);
		get_ctx(dst_ctx);
	}
	mutex_unlock(&dst_ctx->mutex);
}
EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);

static void sync_child_event(struct perf_event *child_event,
			       struct task_struct *child)
{
	struct perf_event *parent_event = child_event->parent;
	u64 child_val;

	if (child_event->attr.inherit_stat)
		perf_event_read_event(child_event, child);

	child_val = perf_event_count(child_event);

	/*
	 * Add back the child's count to the parent's count:
	 */
	atomic64_add(child_val, &parent_event->child_count);
	atomic64_add(child_event->total_time_enabled,
		     &parent_event->child_total_time_enabled);
	atomic64_add(child_event->total_time_running,
		     &parent_event->child_total_time_running);

	/*
	 * Remove this event from the parent's list
	 */
	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
	mutex_lock(&parent_event->child_mutex);
	list_del_init(&child_event->child_list);
	mutex_unlock(&parent_event->child_mutex);

	/*
	 * Release the parent event, if this was the last
	 * reference to it.
	 */
	put_event(parent_event);
}

static void
__perf_event_exit_task(struct perf_event *child_event,
			 struct perf_event_context *child_ctx,
			 struct task_struct *child)
{
	if (child_event->parent) {
		raw_spin_lock_irq(&child_ctx->lock);
		perf_group_detach(child_event);
		raw_spin_unlock_irq(&child_ctx->lock);
	}

	perf_remove_from_context(child_event);

	/*
	 * It can happen that the parent exits first, and has events
	 * that are still around due to the child reference. These
	 * events need to be zapped.
	 */
	if (child_event->parent) {
		sync_child_event(child_event, child);
		free_event(child_event);
	}
}

static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
{
	struct perf_event *child_event, *tmp;
	struct perf_event_context *child_ctx;
	unsigned long flags;

	if (likely(!child->perf_event_ctxp[ctxn])) {
		perf_event_task(child, NULL, 0);
		return;
	}

	local_irq_save(flags);
	/*
	 * We can't reschedule here because interrupts are disabled,
	 * and either child is current or it is a task that can't be
	 * scheduled, so we are now safe from rescheduling changing
	 * our context.
	 */
	child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);

	/*
	 * Take the context lock here so that if find_get_context is
	 * reading child->perf_event_ctxp, we wait until it has
	 * incremented the context's refcount before we do put_ctx below.
	 */
	raw_spin_lock(&child_ctx->lock);
	task_ctx_sched_out(child_ctx);
	child->perf_event_ctxp[ctxn] = NULL;
	/*
	 * If this context is a clone; unclone it so it can't get
	 * swapped to another process while we're removing all
	 * the events from it.
	 */
	unclone_ctx(child_ctx);
	update_context_time(child_ctx);
	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);

	/*
	 * Report the task dead after unscheduling the events so that we
	 * won't get any samples after PERF_RECORD_EXIT. We can however still
	 * get a few PERF_RECORD_READ events.
	 */
	perf_event_task(child, child_ctx, 0);

	/*
	 * We can recurse on the same lock type through:
	 *
	 *   __perf_event_exit_task()
	 *     sync_child_event()
	 *       put_event()
	 *         mutex_lock(&ctx->mutex)
	 *
	 * But since its the parent context it won't be the same instance.
	 */
	mutex_lock(&child_ctx->mutex);

again:
	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
				 group_entry)
		__perf_event_exit_task(child_event, child_ctx, child);

	list_for_each_entry_safe(child_event, tmp, &child_ctx->flexible_groups,
				 group_entry)
		__perf_event_exit_task(child_event, child_ctx, child);

	/*
	 * If the last event was a group event, it will have appended all
	 * its siblings to the list, but we obtained 'tmp' before that which
	 * will still point to the list head terminating the iteration.
	 */
	if (!list_empty(&child_ctx->pinned_groups) ||
	    !list_empty(&child_ctx->flexible_groups))
		goto again;

	mutex_unlock(&child_ctx->mutex);

	put_ctx(child_ctx);
}

/*
 * When a child task exits, feed back event values to parent events.
 */
void perf_event_exit_task(struct task_struct *child)
{
	struct perf_event *event, *tmp;
	int ctxn;

	mutex_lock(&child->perf_event_mutex);
	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
				 owner_entry) {
		list_del_init(&event->owner_entry);

		/*
		 * Ensure the list deletion is visible before we clear
		 * the owner, closes a race against perf_release() where
		 * we need to serialize on the owner->perf_event_mutex.
		 */
		smp_wmb();
		event->owner = NULL;
	}
	mutex_unlock(&child->perf_event_mutex);

	for_each_task_context_nr(ctxn)
		perf_event_exit_task_context(child, ctxn);
}

static void perf_free_event(struct perf_event *event,
			    struct perf_event_context *ctx)
{
	struct perf_event *parent = event->parent;

	if (WARN_ON_ONCE(!parent))
		return;

	mutex_lock(&parent->child_mutex);
	list_del_init(&event->child_list);
	mutex_unlock(&parent->child_mutex);

	put_event(parent);

	perf_group_detach(event);
	list_del_event(event, ctx);
	free_event(event);
}

/*
 * free an unexposed, unused context as created by inheritance by
 * perf_event_init_task below, used by fork() in case of fail.
 */
void perf_event_free_task(struct task_struct *task)
{
	struct perf_event_context *ctx;
	struct perf_event *event, *tmp;
	int ctxn;

	for_each_task_context_nr(ctxn) {
		ctx = task->perf_event_ctxp[ctxn];
		if (!ctx)
			continue;

		mutex_lock(&ctx->mutex);
again:
		list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
				group_entry)
			perf_free_event(event, ctx);

		list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
				group_entry)
			perf_free_event(event, ctx);

		if (!list_empty(&ctx->pinned_groups) ||
				!list_empty(&ctx->flexible_groups))
			goto again;

		mutex_unlock(&ctx->mutex);

		put_ctx(ctx);
	}
}

void perf_event_delayed_put(struct task_struct *task)
{
	int ctxn;

	for_each_task_context_nr(ctxn)
		WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
}

/*
 * inherit a event from parent task to child task:
 */
static struct perf_event *
inherit_event(struct perf_event *parent_event,
	      struct task_struct *parent,
	      struct perf_event_context *parent_ctx,
	      struct task_struct *child,
	      struct perf_event *group_leader,
	      struct perf_event_context *child_ctx)
{
	struct perf_event *child_event;
	unsigned long flags;

	/*
	 * Instead of creating recursive hierarchies of events,
	 * we link inherited events back to the original parent,
	 * which has a filp for sure, which we use as the reference
	 * count:
	 */
	if (parent_event->parent)
		parent_event = parent_event->parent;

	child_event = perf_event_alloc(&parent_event->attr,
					   parent_event->cpu,
					   child,
					   group_leader, parent_event,
				           NULL, NULL);
	if (IS_ERR(child_event))
		return child_event;

	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
		free_event(child_event);
		return NULL;
	}

	get_ctx(child_ctx);

	/*
	 * Make the child state follow the state of the parent event,
	 * not its attr.disabled bit.  We hold the parent's mutex,
	 * so we won't race with perf_event_{en, dis}able_family.
	 */
	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
		child_event->state = PERF_EVENT_STATE_INACTIVE;
	else
		child_event->state = PERF_EVENT_STATE_OFF;

	if (parent_event->attr.freq) {
		u64 sample_period = parent_event->hw.sample_period;
		struct hw_perf_event *hwc = &child_event->hw;

		hwc->sample_period = sample_period;
		hwc->last_period   = sample_period;

		local64_set(&hwc->period_left, sample_period);
	}

	child_event->ctx = child_ctx;
	child_event->overflow_handler = parent_event->overflow_handler;
	child_event->overflow_handler_context
		= parent_event->overflow_handler_context;

	/*
	 * Precalculate sample_data sizes
	 */
	perf_event__header_size(child_event);
	perf_event__id_header_size(child_event);

	/*
	 * Link it up in the child's context:
	 */
	raw_spin_lock_irqsave(&child_ctx->lock, flags);
	add_event_to_ctx(child_event, child_ctx);
	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);

	/*
	 * Link this into the parent event's child list
	 */
	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
	mutex_lock(&parent_event->child_mutex);
	list_add_tail(&child_event->child_list, &parent_event->child_list);
	mutex_unlock(&parent_event->child_mutex);

	return child_event;
}

static int inherit_group(struct perf_event *parent_event,
	      struct task_struct *parent,
	      struct perf_event_context *parent_ctx,
	      struct task_struct *child,
	      struct perf_event_context *child_ctx)
{
	struct perf_event *leader;
	struct perf_event *sub;
	struct perf_event *child_ctr;

	leader = inherit_event(parent_event, parent, parent_ctx,
				 child, NULL, child_ctx);
	if (IS_ERR(leader))
		return PTR_ERR(leader);
	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
		child_ctr = inherit_event(sub, parent, parent_ctx,
					    child, leader, child_ctx);
		if (IS_ERR(child_ctr))
			return PTR_ERR(child_ctr);
	}
	return 0;
}

static int
inherit_task_group(struct perf_event *event, struct task_struct *parent,
		   struct perf_event_context *parent_ctx,
		   struct task_struct *child, int ctxn,
		   int *inherited_all)
{
	int ret;
	struct perf_event_context *child_ctx;

	if (!event->attr.inherit) {
		*inherited_all = 0;
		return 0;
	}

	child_ctx = child->perf_event_ctxp[ctxn];
	if (!child_ctx) {
		/*
		 * This is executed from the parent task context, so
		 * inherit events that have been marked for cloning.
		 * First allocate and initialize a context for the
		 * child.
		 */

		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
		if (!child_ctx)
			return -ENOMEM;

		child->perf_event_ctxp[ctxn] = child_ctx;
	}

	ret = inherit_group(event, parent, parent_ctx,
			    child, child_ctx);

	if (ret)
		*inherited_all = 0;

	return ret;
}

/*
 * Initialize the perf_event context in task_struct
 */
int perf_event_init_context(struct task_struct *child, int ctxn)
{
	struct perf_event_context *child_ctx, *parent_ctx;
	struct perf_event_context *cloned_ctx;
	struct perf_event *event;
	struct task_struct *parent = current;
	int inherited_all = 1;
	unsigned long flags;
	int ret = 0;

	if (likely(!parent->perf_event_ctxp[ctxn]))
		return 0;

	/*
	 * If the parent's context is a clone, pin it so it won't get
	 * swapped under us.
	 */
	parent_ctx = perf_pin_task_context(parent, ctxn);

	/*
	 * No need to check if parent_ctx != NULL here; since we saw
	 * it non-NULL earlier, the only reason for it to become NULL
	 * is if we exit, and since we're currently in the middle of
	 * a fork we can't be exiting at the same time.
	 */

	/*
	 * Lock the parent list. No need to lock the child - not PID
	 * hashed yet and not running, so nobody can access it.
	 */
	mutex_lock(&parent_ctx->mutex);

	/*
	 * We dont have to disable NMIs - we are only looking at
	 * the list, not manipulating it:
	 */
	list_for_each_entry(event, &parent_ctx->pinned_groups, group_entry) {
		ret = inherit_task_group(event, parent, parent_ctx,
					 child, ctxn, &inherited_all);
		if (ret)
			break;
	}

	/*
	 * We can't hold ctx->lock when iterating the ->flexible_group list due
	 * to allocations, but we need to prevent rotation because
	 * rotate_ctx() will change the list from interrupt context.
	 */
	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
	parent_ctx->rotate_disable = 1;
	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);

	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
		ret = inherit_task_group(event, parent, parent_ctx,
					 child, ctxn, &inherited_all);
		if (ret)
			break;
	}

	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
	parent_ctx->rotate_disable = 0;

	child_ctx = child->perf_event_ctxp[ctxn];

	if (child_ctx && inherited_all) {
		/*
		 * Mark the child context as a clone of the parent
		 * context, or of whatever the parent is a clone of.
		 *
		 * Note that if the parent is a clone, the holding of
		 * parent_ctx->lock avoids it from being uncloned.
		 */
		cloned_ctx = parent_ctx->parent_ctx;
		if (cloned_ctx) {
			child_ctx->parent_ctx = cloned_ctx;
			child_ctx->parent_gen = parent_ctx->parent_gen;
		} else {
			child_ctx->parent_ctx = parent_ctx;
			child_ctx->parent_gen = parent_ctx->generation;
		}
		get_ctx(child_ctx->parent_ctx);
	}

	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
	mutex_unlock(&parent_ctx->mutex);

	perf_unpin_context(parent_ctx);
	put_ctx(parent_ctx);

	return ret;
}

/*
 * Initialize the perf_event context in task_struct
 */
int perf_event_init_task(struct task_struct *child)
{
	int ctxn, ret;

	memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
	mutex_init(&child->perf_event_mutex);
	INIT_LIST_HEAD(&child->perf_event_list);

	for_each_task_context_nr(ctxn) {
		ret = perf_event_init_context(child, ctxn);
		if (ret)
			return ret;
	}

	return 0;
}

static void __init perf_event_init_all_cpus(void)
{
	struct swevent_htable *swhash;
	int cpu;

	for_each_possible_cpu(cpu) {
		swhash = &per_cpu(swevent_htable, cpu);
		mutex_init(&swhash->hlist_mutex);
		INIT_LIST_HEAD(&per_cpu(rotation_list, cpu));
	}
}

static void perf_event_init_cpu(int cpu)
{
	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);

	mutex_lock(&swhash->hlist_mutex);
	if (swhash->hlist_refcount > 0) {
		struct swevent_hlist *hlist;

		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
		WARN_ON(!hlist);
		rcu_assign_pointer(swhash->swevent_hlist, hlist);
	}
	mutex_unlock(&swhash->hlist_mutex);
}

#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
static void perf_pmu_rotate_stop(struct pmu *pmu)
{
	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);

	WARN_ON(!irqs_disabled());

	list_del_init(&cpuctx->rotation_list);
}

static void __perf_event_exit_context(void *__info)
{
	struct perf_event_context *ctx = __info;
	struct perf_event *event;

	perf_pmu_rotate_stop(ctx->pmu);

	rcu_read_lock();
	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
		__perf_remove_from_context(event);
	rcu_read_unlock();
}

static void perf_event_exit_cpu_context(int cpu)
{
	struct perf_event_context *ctx;
	struct pmu *pmu;
	int idx;

	idx = srcu_read_lock(&pmus_srcu);
	list_for_each_entry_rcu(pmu, &pmus, entry) {
		ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx;

		mutex_lock(&ctx->mutex);
		smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1);
		mutex_unlock(&ctx->mutex);
	}
	srcu_read_unlock(&pmus_srcu, idx);
}

static void perf_event_exit_cpu(int cpu)
{
	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);

	perf_event_exit_cpu_context(cpu);

	mutex_lock(&swhash->hlist_mutex);
	swevent_hlist_release(swhash);
	mutex_unlock(&swhash->hlist_mutex);
}
#else
static inline void perf_event_exit_cpu(int cpu) { }
#endif

static int
perf_reboot(struct notifier_block *notifier, unsigned long val, void *v)
{
	int cpu;

	for_each_online_cpu(cpu)
		perf_event_exit_cpu(cpu);

	return NOTIFY_OK;
}

/*
 * Run the perf reboot notifier at the very last possible moment so that
 * the generic watchdog code runs as long as possible.
 */
static struct notifier_block perf_reboot_notifier = {
	.notifier_call = perf_reboot,
	.priority = INT_MIN,
};

static int
perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
{
	unsigned int cpu = (long)hcpu;

	switch (action & ~CPU_TASKS_FROZEN) {

	case CPU_UP_PREPARE:
	case CPU_DOWN_FAILED:
		perf_event_init_cpu(cpu);
		break;

	case CPU_UP_CANCELED:
	case CPU_DOWN_PREPARE:
		perf_event_exit_cpu(cpu);
		break;
	default:
		break;
	}

	return NOTIFY_OK;
}

void __init perf_event_init(void)
{
	int ret;

	idr_init(&pmu_idr);

	perf_event_init_all_cpus();
	init_srcu_struct(&pmus_srcu);
	perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);
	perf_pmu_register(&perf_cpu_clock, NULL, -1);
	perf_pmu_register(&perf_task_clock, NULL, -1);
	perf_tp_register();
	perf_cpu_notifier(perf_cpu_notify);
	register_reboot_notifier(&perf_reboot_notifier);

	ret = init_hw_breakpoint();
	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);

	/* do not patch jump label more than once per second */
	jump_label_rate_limit(&perf_sched_events, HZ);

	/*
	 * Build time assertion that we keep the data_head at the intended
	 * location.  IOW, validation we got the __reserved[] size right.
	 */
	BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head))
		     != 1024);
}

static int __init perf_event_sysfs_init(void)
{
	struct pmu *pmu;
	int ret;

	mutex_lock(&pmus_lock);

	ret = bus_register(&pmu_bus);
	if (ret)
		goto unlock;

	list_for_each_entry(pmu, &pmus, entry) {
		if (!pmu->name || pmu->type < 0)
			continue;

		ret = pmu_dev_alloc(pmu);
		WARN(ret, "Failed to register pmu: %s, reason %d\n", pmu->name, ret);
	}
	pmu_bus_running = 1;
	ret = 0;

unlock:
	mutex_unlock(&pmus_lock);

	return ret;
}
device_initcall(perf_event_sysfs_init);

#ifdef CONFIG_CGROUP_PERF
static struct cgroup_subsys_state *
perf_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct perf_cgroup *jc;

	jc = kzalloc(sizeof(*jc), GFP_KERNEL);
	if (!jc)
		return ERR_PTR(-ENOMEM);

	jc->info = alloc_percpu(struct perf_cgroup_info);
	if (!jc->info) {
		kfree(jc);
		return ERR_PTR(-ENOMEM);
	}

	return &jc->css;
}

static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
{
	struct perf_cgroup *jc = container_of(css, struct perf_cgroup, css);

	free_percpu(jc->info);
	kfree(jc);
}

static int __perf_cgroup_move(void *info)
{
	struct task_struct *task = info;
	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
	return 0;
}

static void perf_cgroup_attach(struct cgroup_subsys_state *css,
			       struct cgroup_taskset *tset)
{
	struct task_struct *task;

	cgroup_taskset_for_each(task, tset)
		task_function_call(task, __perf_cgroup_move, task);
}

static void perf_cgroup_exit(struct cgroup_subsys_state *css,
			     struct cgroup_subsys_state *old_css,
			     struct task_struct *task)
{
	/*
	 * cgroup_exit() is called in the copy_process() failure path.
	 * Ignore this case since the task hasn't ran yet, this avoids
	 * trying to poke a half freed task state from generic code.
	 */
	if (!(task->flags & PF_EXITING))
		return;

	task_function_call(task, __perf_cgroup_move, task);
}

struct cgroup_subsys perf_event_cgrp_subsys = {
	.css_alloc	= perf_cgroup_css_alloc,
	.css_free	= perf_cgroup_css_free,
	.exit		= perf_cgroup_exit,
	.attach		= perf_cgroup_attach,
};
#endif /* CONFIG_CGROUP_PERF */