Eric Lee / smarc-fsl-linux-kernel

perf_counter.c 101 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 
/*
 * Performance counter core code
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2008-2009 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/file.h>
#include <linux/poll.h>
#include <linux/sysfs.h>
#include <linux/dcache.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/vmstat.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_counter.h>

#include <asm/irq_regs.h>

/*
 * Each CPU has a list of per CPU counters:
 */
DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);

int perf_max_counters __read_mostly = 1;
static int perf_reserved_percpu __read_mostly;
static int perf_overcommit __read_mostly = 1;

static atomic_t nr_counters __read_mostly;
static atomic_t nr_mmap_counters __read_mostly;
static atomic_t nr_comm_counters __read_mostly;

/*
 * perf counter paranoia level:
 *  0 - not paranoid
 *  1 - disallow cpu counters to unpriv
 *  2 - disallow kernel profiling to unpriv
 */
int sysctl_perf_counter_paranoid __read_mostly;

static inline bool perf_paranoid_cpu(void)
{
	return sysctl_perf_counter_paranoid > 0;
}

static inline bool perf_paranoid_kernel(void)
{
	return sysctl_perf_counter_paranoid > 1;
}

int sysctl_perf_counter_mlock __read_mostly = 512; /* 'free' kb per user */

/*
 * max perf counter sample rate
 */
int sysctl_perf_counter_sample_rate __read_mostly = 100000;

static atomic64_t perf_counter_id;

/*
 * Lock for (sysadmin-configurable) counter reservations:
 */
static DEFINE_SPINLOCK(perf_resource_lock);

/*
 * Architecture provided APIs - weak aliases:
 */
extern __weak const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
{
	return NULL;
}

void __weak hw_perf_disable(void)		{ barrier(); }
void __weak hw_perf_enable(void)		{ barrier(); }

void __weak hw_perf_counter_setup(int cpu)	{ barrier(); }

int __weak
hw_perf_group_sched_in(struct perf_counter *group_leader,
	       struct perf_cpu_context *cpuctx,
	       struct perf_counter_context *ctx, int cpu)
{
	return 0;
}

void __weak perf_counter_print_debug(void)	{ }

static DEFINE_PER_CPU(int, disable_count);

void __perf_disable(void)
{
	__get_cpu_var(disable_count)++;
}

bool __perf_enable(void)
{
	return !--__get_cpu_var(disable_count);
}

void perf_disable(void)
{
	__perf_disable();
	hw_perf_disable();
}

void perf_enable(void)
{
	if (__perf_enable())
		hw_perf_enable();
}

static void get_ctx(struct perf_counter_context *ctx)
{
	atomic_inc(&ctx->refcount);
}

static void free_ctx(struct rcu_head *head)
{
	struct perf_counter_context *ctx;

	ctx = container_of(head, struct perf_counter_context, rcu_head);
	kfree(ctx);
}

static void put_ctx(struct perf_counter_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);
		call_rcu(&ctx->rcu_head, free_ctx);
	}
}

/*
 * Get the perf_counter_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_counter_context *
perf_lock_task_context(struct task_struct *task, unsigned long *flags)
{
	struct perf_counter_context *ctx;

	rcu_read_lock();
 retry:
	ctx = rcu_dereference(task->perf_counter_ctxp);
	if (ctx) {
		/*
		 * If this context is a clone of another, it might
		 * get swapped for another underneath us by
		 * perf_counter_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.
		 */
		spin_lock_irqsave(&ctx->lock, *flags);
		if (ctx != rcu_dereference(task->perf_counter_ctxp)) {
			spin_unlock_irqrestore(&ctx->lock, *flags);
			goto retry;
		}
	}
	rcu_read_unlock();
	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_counter_context *perf_pin_task_context(struct task_struct *task)
{
	struct perf_counter_context *ctx;
	unsigned long flags;

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

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

	spin_lock_irqsave(&ctx->lock, flags);
	--ctx->pin_count;
	spin_unlock_irqrestore(&ctx->lock, flags);
	put_ctx(ctx);
}

/*
 * Add a counter from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
static void
list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
{
	struct perf_counter *group_leader = counter->group_leader;

	/*
	 * Depending on whether it is a standalone or sibling counter,
	 * add it straight to the context's counter list, or to the group
	 * leader's sibling list:
	 */
	if (group_leader == counter)
		list_add_tail(&counter->list_entry, &ctx->counter_list);
	else {
		list_add_tail(&counter->list_entry, &group_leader->sibling_list);
		group_leader->nr_siblings++;
	}

	list_add_rcu(&counter->event_entry, &ctx->event_list);
	ctx->nr_counters++;
}

/*
 * Remove a counter from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
static void
list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
{
	struct perf_counter *sibling, *tmp;

	if (list_empty(&counter->list_entry))
		return;
	ctx->nr_counters--;

	list_del_init(&counter->list_entry);
	list_del_rcu(&counter->event_entry);

	if (counter->group_leader != counter)
		counter->group_leader->nr_siblings--;

	/*
	 * If this was a group counter with sibling counters then
	 * upgrade the siblings to singleton counters by adding them
	 * to the context list directly:
	 */
	list_for_each_entry_safe(sibling, tmp,
				 &counter->sibling_list, list_entry) {

		list_move_tail(&sibling->list_entry, &ctx->counter_list);
		sibling->group_leader = sibling;
	}
}

static void
counter_sched_out(struct perf_counter *counter,
		  struct perf_cpu_context *cpuctx,
		  struct perf_counter_context *ctx)
{
	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
		return;

	counter->state = PERF_COUNTER_STATE_INACTIVE;
	counter->tstamp_stopped = ctx->time;
	counter->pmu->disable(counter);
	counter->oncpu = -1;

	if (!is_software_counter(counter))
		cpuctx->active_oncpu--;
	ctx->nr_active--;
	if (counter->attr.exclusive || !cpuctx->active_oncpu)
		cpuctx->exclusive = 0;
}

static void
group_sched_out(struct perf_counter *group_counter,
		struct perf_cpu_context *cpuctx,
		struct perf_counter_context *ctx)
{
	struct perf_counter *counter;

	if (group_counter->state != PERF_COUNTER_STATE_ACTIVE)
		return;

	counter_sched_out(group_counter, cpuctx, ctx);

	/*
	 * Schedule out siblings (if any):
	 */
	list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
		counter_sched_out(counter, cpuctx, ctx);

	if (group_counter->attr.exclusive)
		cpuctx->exclusive = 0;
}

/*
 * Cross CPU call to remove a performance counter
 *
 * We disable the counter on the hardware level first. After that we
 * remove it from the context list.
 */
static void __perf_counter_remove_from_context(void *info)
{
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
	struct perf_counter *counter = info;
	struct perf_counter_context *ctx = counter->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.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx)
		return;

	spin_lock(&ctx->lock);
	/*
	 * Protect the list operation against NMI by disabling the
	 * counters on a global level.
	 */
	perf_disable();

	counter_sched_out(counter, cpuctx, ctx);

	list_del_counter(counter, ctx);

	if (!ctx->task) {
		/*
		 * Allow more per task counters with respect to the
		 * reservation:
		 */
		cpuctx->max_pertask =
			min(perf_max_counters - ctx->nr_counters,
			    perf_max_counters - perf_reserved_percpu);
	}

	perf_enable();
	spin_unlock(&ctx->lock);
}


/*
 * Remove the counter from a task's (or a CPU's) list of counters.
 *
 * Must be called with ctx->mutex held.
 *
 * CPU counters are removed with a smp call. For task counters we only
 * call when the task is on a CPU.
 *
 * If counter->ctx is a cloned context, callers must make sure that
 * every task struct that counter->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_counter_exit_task, it's OK because the
 * context has been detached from its task.
 */
static void perf_counter_remove_from_context(struct perf_counter *counter)
{
	struct perf_counter_context *ctx = counter->ctx;
	struct task_struct *task = ctx->task;

	if (!task) {
		/*
		 * Per cpu counters are removed via an smp call and
		 * the removal is always sucessful.
		 */
		smp_call_function_single(counter->cpu,
					 __perf_counter_remove_from_context,
					 counter, 1);
		return;
	}

retry:
	task_oncpu_function_call(task, __perf_counter_remove_from_context,
				 counter);

	spin_lock_irq(&ctx->lock);
	/*
	 * If the context is active we need to retry the smp call.
	 */
	if (ctx->nr_active && !list_empty(&counter->list_entry)) {
		spin_unlock_irq(&ctx->lock);
		goto retry;
	}

	/*
	 * The lock prevents that this context is scheduled in so we
	 * can remove the counter safely, if the call above did not
	 * succeed.
	 */
	if (!list_empty(&counter->list_entry)) {
		list_del_counter(counter, ctx);
	}
	spin_unlock_irq(&ctx->lock);
}

static inline u64 perf_clock(void)
{
	return cpu_clock(smp_processor_id());
}

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

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

/*
 * Update the total_time_enabled and total_time_running fields for a counter.
 */
static void update_counter_times(struct perf_counter *counter)
{
	struct perf_counter_context *ctx = counter->ctx;
	u64 run_end;

	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
		return;

	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;

	if (counter->state == PERF_COUNTER_STATE_INACTIVE)
		run_end = counter->tstamp_stopped;
	else
		run_end = ctx->time;

	counter->total_time_running = run_end - counter->tstamp_running;
}

/*
 * Update total_time_enabled and total_time_running for all counters in a group.
 */
static void update_group_times(struct perf_counter *leader)
{
	struct perf_counter *counter;

	update_counter_times(leader);
	list_for_each_entry(counter, &leader->sibling_list, list_entry)
		update_counter_times(counter);
}

/*
 * Cross CPU call to disable a performance counter
 */
static void __perf_counter_disable(void *info)
{
	struct perf_counter *counter = info;
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
	struct perf_counter_context *ctx = counter->ctx;

	/*
	 * If this is a per-task counter, need to check whether this
	 * counter's task is the current task on this cpu.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx)
		return;

	spin_lock(&ctx->lock);

	/*
	 * If the counter is on, turn it off.
	 * If it is in error state, leave it in error state.
	 */
	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
		update_context_time(ctx);
		update_counter_times(counter);
		if (counter == counter->group_leader)
			group_sched_out(counter, cpuctx, ctx);
		else
			counter_sched_out(counter, cpuctx, ctx);
		counter->state = PERF_COUNTER_STATE_OFF;
	}

	spin_unlock(&ctx->lock);
}

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

	if (!task) {
		/*
		 * Disable the counter on the cpu that it's on
		 */
		smp_call_function_single(counter->cpu, __perf_counter_disable,
					 counter, 1);
		return;
	}

 retry:
	task_oncpu_function_call(task, __perf_counter_disable, counter);

	spin_lock_irq(&ctx->lock);
	/*
	 * If the counter is still active, we need to retry the cross-call.
	 */
	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
		spin_unlock_irq(&ctx->lock);
		goto retry;
	}

	/*
	 * Since we have the lock this context can't be scheduled
	 * in, so we can change the state safely.
	 */
	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
		update_counter_times(counter);
		counter->state = PERF_COUNTER_STATE_OFF;
	}

	spin_unlock_irq(&ctx->lock);
}

static int
counter_sched_in(struct perf_counter *counter,
		 struct perf_cpu_context *cpuctx,
		 struct perf_counter_context *ctx,
		 int cpu)
{
	if (counter->state <= PERF_COUNTER_STATE_OFF)
		return 0;

	counter->state = PERF_COUNTER_STATE_ACTIVE;
	counter->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
	/*
	 * The new state must be visible before we turn it on in the hardware:
	 */
	smp_wmb();

	if (counter->pmu->enable(counter)) {
		counter->state = PERF_COUNTER_STATE_INACTIVE;
		counter->oncpu = -1;
		return -EAGAIN;
	}

	counter->tstamp_running += ctx->time - counter->tstamp_stopped;

	if (!is_software_counter(counter))
		cpuctx->active_oncpu++;
	ctx->nr_active++;

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

	return 0;
}

static int
group_sched_in(struct perf_counter *group_counter,
	       struct perf_cpu_context *cpuctx,
	       struct perf_counter_context *ctx,
	       int cpu)
{
	struct perf_counter *counter, *partial_group;
	int ret;

	if (group_counter->state == PERF_COUNTER_STATE_OFF)
		return 0;

	ret = hw_perf_group_sched_in(group_counter, cpuctx, ctx, cpu);
	if (ret)
		return ret < 0 ? ret : 0;

	if (counter_sched_in(group_counter, cpuctx, ctx, cpu))
		return -EAGAIN;

	/*
	 * Schedule in siblings as one group (if any):
	 */
	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
		if (counter_sched_in(counter, cpuctx, ctx, cpu)) {
			partial_group = counter;
			goto group_error;
		}
	}

	return 0;

group_error:
	/*
	 * Groups can be scheduled in as one unit only, so undo any
	 * partial group before returning:
	 */
	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
		if (counter == partial_group)
			break;
		counter_sched_out(counter, cpuctx, ctx);
	}
	counter_sched_out(group_counter, cpuctx, ctx);

	return -EAGAIN;
}

/*
 * Return 1 for a group consisting entirely of software counters,
 * 0 if the group contains any hardware counters.
 */
static int is_software_only_group(struct perf_counter *leader)
{
	struct perf_counter *counter;

	if (!is_software_counter(leader))
		return 0;

	list_for_each_entry(counter, &leader->sibling_list, list_entry)
		if (!is_software_counter(counter))
			return 0;

	return 1;
}

/*
 * Work out whether we can put this counter group on the CPU now.
 */
static int group_can_go_on(struct perf_counter *counter,
			   struct perf_cpu_context *cpuctx,
			   int can_add_hw)
{
	/*
	 * Groups consisting entirely of software counters can always go on.
	 */
	if (is_software_only_group(counter))
		return 1;
	/*
	 * If an exclusive group is already on, no other hardware
	 * counters can go on.
	 */
	if (cpuctx->exclusive)
		return 0;
	/*
	 * If this group is exclusive and there are already
	 * counters on the CPU, it can't go on.
	 */
	if (counter->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_counter_to_ctx(struct perf_counter *counter,
			       struct perf_counter_context *ctx)
{
	list_add_counter(counter, ctx);
	counter->tstamp_enabled = ctx->time;
	counter->tstamp_running = ctx->time;
	counter->tstamp_stopped = ctx->time;
}

/*
 * Cross CPU call to install and enable a performance counter
 *
 * Must be called with ctx->mutex held
 */
static void __perf_install_in_context(void *info)
{
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
	struct perf_counter *counter = info;
	struct perf_counter_context *ctx = counter->ctx;
	struct perf_counter *leader = counter->group_leader;
	int cpu = smp_processor_id();
	int err;

	/*
	 * 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.
	 * Or possibly this is the right context but it isn't
	 * on this cpu because it had no counters.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx) {
		if (cpuctx->task_ctx || ctx->task != current)
			return;
		cpuctx->task_ctx = ctx;
	}

	spin_lock(&ctx->lock);
	ctx->is_active = 1;
	update_context_time(ctx);

	/*
	 * Protect the list operation against NMI by disabling the
	 * counters on a global level. NOP for non NMI based counters.
	 */
	perf_disable();

	add_counter_to_ctx(counter, ctx);

	/*
	 * Don't put the counter on if it is disabled or if
	 * it is in a group and the group isn't on.
	 */
	if (counter->state != PERF_COUNTER_STATE_INACTIVE ||
	    (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE))
		goto unlock;

	/*
	 * An exclusive counter can't go on if there are already active
	 * hardware counters, and no hardware counter can go on if there
	 * is already an exclusive counter on.
	 */
	if (!group_can_go_on(counter, cpuctx, 1))
		err = -EEXIST;
	else
		err = counter_sched_in(counter, cpuctx, ctx, cpu);

	if (err) {
		/*
		 * This counter couldn't go on.  If it is in a group
		 * then we have to pull the whole group off.
		 * If the counter group is pinned then put it in error state.
		 */
		if (leader != counter)
			group_sched_out(leader, cpuctx, ctx);
		if (leader->attr.pinned) {
			update_group_times(leader);
			leader->state = PERF_COUNTER_STATE_ERROR;
		}
	}

	if (!err && !ctx->task && cpuctx->max_pertask)
		cpuctx->max_pertask--;

 unlock:
	perf_enable();

	spin_unlock(&ctx->lock);
}

/*
 * Attach a performance counter to a context
 *
 * First we add the counter to the list with the hardware enable bit
 * in counter->hw_config cleared.
 *
 * If the counter 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.
 *
 * Must be called with ctx->mutex held.
 */
static void
perf_install_in_context(struct perf_counter_context *ctx,
			struct perf_counter *counter,
			int cpu)
{
	struct task_struct *task = ctx->task;

	if (!task) {
		/*
		 * Per cpu counters are installed via an smp call and
		 * the install is always sucessful.
		 */
		smp_call_function_single(cpu, __perf_install_in_context,
					 counter, 1);
		return;
	}

retry:
	task_oncpu_function_call(task, __perf_install_in_context,
				 counter);

	spin_lock_irq(&ctx->lock);
	/*
	 * we need to retry the smp call.
	 */
	if (ctx->is_active && list_empty(&counter->list_entry)) {
		spin_unlock_irq(&ctx->lock);
		goto retry;
	}

	/*
	 * The lock prevents that this context is scheduled in so we
	 * can add the counter safely, if it the call above did not
	 * succeed.
	 */
	if (list_empty(&counter->list_entry))
		add_counter_to_ctx(counter, ctx);
	spin_unlock_irq(&ctx->lock);
}

/*
 * Cross CPU call to enable a performance counter
 */
static void __perf_counter_enable(void *info)
{
	struct perf_counter *counter = info;
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
	struct perf_counter_context *ctx = counter->ctx;
	struct perf_counter *leader = counter->group_leader;
	int err;

	/*
	 * If this is a per-task counter, need to check whether this
	 * counter's task is the current task on this cpu.
	 */
	if (ctx->task && cpuctx->task_ctx != ctx) {
		if (cpuctx->task_ctx || ctx->task != current)
			return;
		cpuctx->task_ctx = ctx;
	}

	spin_lock(&ctx->lock);
	ctx->is_active = 1;
	update_context_time(ctx);

	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
		goto unlock;
	counter->state = PERF_COUNTER_STATE_INACTIVE;
	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;

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

	if (!group_can_go_on(counter, cpuctx, 1)) {
		err = -EEXIST;
	} else {
		perf_disable();
		if (counter == leader)
			err = group_sched_in(counter, cpuctx, ctx,
					     smp_processor_id());
		else
			err = counter_sched_in(counter, cpuctx, ctx,
					       smp_processor_id());
		perf_enable();
	}

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

 unlock:
	spin_unlock(&ctx->lock);
}

/*
 * Enable a counter.
 *
 * If counter->ctx is a cloned context, callers must make sure that
 * every task struct that counter->ctx->task could possibly point to
 * remains valid.  This condition is satisfied when called through
 * perf_counter_for_each_child or perf_counter_for_each as described
 * for perf_counter_disable.
 */
static void perf_counter_enable(struct perf_counter *counter)
{
	struct perf_counter_context *ctx = counter->ctx;
	struct task_struct *task = ctx->task;

	if (!task) {
		/*
		 * Enable the counter on the cpu that it's on
		 */
		smp_call_function_single(counter->cpu, __perf_counter_enable,
					 counter, 1);
		return;
	}

	spin_lock_irq(&ctx->lock);
	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
		goto out;

	/*
	 * If the counter is in error state, clear that first.
	 * That way, if we see the counter 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 (counter->state == PERF_COUNTER_STATE_ERROR)
		counter->state = PERF_COUNTER_STATE_OFF;

 retry:
	spin_unlock_irq(&ctx->lock);
	task_oncpu_function_call(task, __perf_counter_enable, counter);

	spin_lock_irq(&ctx->lock);

	/*
	 * If the context is active and the counter is still off,
	 * we need to retry the cross-call.
	 */
	if (ctx->is_active && counter->state == PERF_COUNTER_STATE_OFF)
		goto retry;

	/*
	 * Since we have the lock this context can't be scheduled
	 * in, so we can change the state safely.
	 */
	if (counter->state == PERF_COUNTER_STATE_OFF) {
		counter->state = PERF_COUNTER_STATE_INACTIVE;
		counter->tstamp_enabled =
			ctx->time - counter->total_time_enabled;
	}
 out:
	spin_unlock_irq(&ctx->lock);
}

static int perf_counter_refresh(struct perf_counter *counter, int refresh)
{
	/*
	 * not supported on inherited counters
	 */
	if (counter->attr.inherit)
		return -EINVAL;

	atomic_add(refresh, &counter->event_limit);
	perf_counter_enable(counter);

	return 0;
}

void __perf_counter_sched_out(struct perf_counter_context *ctx,
			      struct perf_cpu_context *cpuctx)
{
	struct perf_counter *counter;

	spin_lock(&ctx->lock);
	ctx->is_active = 0;
	if (likely(!ctx->nr_counters))
		goto out;
	update_context_time(ctx);

	perf_disable();
	if (ctx->nr_active) {
		list_for_each_entry(counter, &ctx->counter_list, list_entry) {
			if (counter != counter->group_leader)
				counter_sched_out(counter, cpuctx, ctx);
			else
				group_sched_out(counter, cpuctx, ctx);
		}
	}
	perf_enable();
 out:
	spin_unlock(&ctx->lock);
}

/*
 * Test whether two contexts are equivalent, i.e. whether they
 * have both been cloned from the same version of the same context
 * and they both have the same number of enabled counters.
 * If the number of enabled counters is the same, then the set
 * of enabled counters should be the same, because these are both
 * inherited contexts, therefore we can't access individual counters
 * in them directly with an fd; we can only enable/disable all
 * counters via prctl, or enable/disable all counters in a family
 * via ioctl, which will have the same effect on both contexts.
 */
static int context_equiv(struct perf_counter_context *ctx1,
			 struct perf_counter_context *ctx2)
{
	return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
		&& ctx1->parent_gen == ctx2->parent_gen
		&& !ctx1->pin_count && !ctx2->pin_count;
}

/*
 * Called from scheduler to remove the counters of the current task,
 * with interrupts disabled.
 *
 * We stop each counter and update the counter value in counter->count.
 *
 * This does not protect us against NMI, but disable()
 * sets the disabled bit in the control field of counter _before_
 * accessing the counter control register. If a NMI hits, then it will
 * not restart the counter.
 */
void perf_counter_task_sched_out(struct task_struct *task,
				 struct task_struct *next, int cpu)
{
	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
	struct perf_counter_context *ctx = task->perf_counter_ctxp;
	struct perf_counter_context *next_ctx;
	struct perf_counter_context *parent;
	struct pt_regs *regs;
	int do_switch = 1;

	regs = task_pt_regs(task);
	perf_swcounter_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);

	if (likely(!ctx || !cpuctx->task_ctx))
		return;

	update_context_time(ctx);

	rcu_read_lock();
	parent = rcu_dereference(ctx->parent_ctx);
	next_ctx = next->perf_counter_ctxp;
	if (parent && next_ctx &&
	    rcu_dereference(next_ctx->parent_ctx) == 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.
		 */
		spin_lock(&ctx->lock);
		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_counter_ctxp
			 */
			task->perf_counter_ctxp = next_ctx;
			next->perf_counter_ctxp = ctx;
			ctx->task = next;
			next_ctx->task = task;
			do_switch = 0;
		}
		spin_unlock(&next_ctx->lock);
		spin_unlock(&ctx->lock);
	}
	rcu_read_unlock();

	if (do_switch) {
		__perf_counter_sched_out(ctx, cpuctx);
		cpuctx->task_ctx = NULL;
	}
}

/*
 * Called with IRQs disabled
 */
static void __perf_counter_task_sched_out(struct perf_counter_context *ctx)
{
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);

	if (!cpuctx->task_ctx)
		return;

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

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

/*
 * Called with IRQs disabled
 */
static void perf_counter_cpu_sched_out(struct perf_cpu_context *cpuctx)
{
	__perf_counter_sched_out(&cpuctx->ctx, cpuctx);
}

static void
__perf_counter_sched_in(struct perf_counter_context *ctx,
			struct perf_cpu_context *cpuctx, int cpu)
{
	struct perf_counter *counter;
	int can_add_hw = 1;

	spin_lock(&ctx->lock);
	ctx->is_active = 1;
	if (likely(!ctx->nr_counters))
		goto out;

	ctx->timestamp = perf_clock();

	perf_disable();

	/*
	 * First go through the list and put on any pinned groups
	 * in order to give them the best chance of going on.
	 */
	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
		if (counter->state <= PERF_COUNTER_STATE_OFF ||
		    !counter->attr.pinned)
			continue;
		if (counter->cpu != -1 && counter->cpu != cpu)
			continue;

		if (counter != counter->group_leader)
			counter_sched_in(counter, cpuctx, ctx, cpu);
		else {
			if (group_can_go_on(counter, cpuctx, 1))
				group_sched_in(counter, cpuctx, ctx, cpu);
		}

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

	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
		/*
		 * Ignore counters in OFF or ERROR state, and
		 * ignore pinned counters since we did them already.
		 */
		if (counter->state <= PERF_COUNTER_STATE_OFF ||
		    counter->attr.pinned)
			continue;

		/*
		 * Listen to the 'cpu' scheduling filter constraint
		 * of counters:
		 */
		if (counter->cpu != -1 && counter->cpu != cpu)
			continue;

		if (counter != counter->group_leader) {
			if (counter_sched_in(counter, cpuctx, ctx, cpu))
				can_add_hw = 0;
		} else {
			if (group_can_go_on(counter, cpuctx, can_add_hw)) {
				if (group_sched_in(counter, cpuctx, ctx, cpu))
					can_add_hw = 0;
			}
		}
	}
	perf_enable();
 out:
	spin_unlock(&ctx->lock);
}

/*
 * Called from scheduler to add the counters of the current task
 * with interrupts disabled.
 *
 * We restore the counter value and then enable it.
 *
 * This does not protect us against NMI, but enable()
 * sets the enabled bit in the control field of counter _before_
 * accessing the counter control register. If a NMI hits, then it will
 * keep the counter running.
 */
void perf_counter_task_sched_in(struct task_struct *task, int cpu)
{
	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
	struct perf_counter_context *ctx = task->perf_counter_ctxp;

	if (likely(!ctx))
		return;
	if (cpuctx->task_ctx == ctx)
		return;
	__perf_counter_sched_in(ctx, cpuctx, cpu);
	cpuctx->task_ctx = ctx;
}

static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
{
	struct perf_counter_context *ctx = &cpuctx->ctx;

	__perf_counter_sched_in(ctx, cpuctx, cpu);
}

#define MAX_INTERRUPTS (~0ULL)

static void perf_log_throttle(struct perf_counter *counter, int enable);
static void perf_log_period(struct perf_counter *counter, u64 period);

static void perf_adjust_period(struct perf_counter *counter, u64 events)
{
	struct hw_perf_counter *hwc = &counter->hw;
	u64 period, sample_period;
	s64 delta;

	events *= hwc->sample_period;
	period = div64_u64(events, counter->attr.sample_freq);

	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;

	perf_log_period(counter, sample_period);

	hwc->sample_period = sample_period;
}

static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
{
	struct perf_counter *counter;
	struct hw_perf_counter *hwc;
	u64 interrupts, freq;

	spin_lock(&ctx->lock);
	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
		if (counter->state != PERF_COUNTER_STATE_ACTIVE)
			continue;

		hwc = &counter->hw;

		interrupts = hwc->interrupts;
		hwc->interrupts = 0;

		/*
		 * unthrottle counters on the tick
		 */
		if (interrupts == MAX_INTERRUPTS) {
			perf_log_throttle(counter, 1);
			counter->pmu->unthrottle(counter);
			interrupts = 2*sysctl_perf_counter_sample_rate/HZ;
		}

		if (!counter->attr.freq || !counter->attr.sample_freq)
			continue;

		/*
		 * if the specified freq < HZ then we need to skip ticks
		 */
		if (counter->attr.sample_freq < HZ) {
			freq = counter->attr.sample_freq;

			hwc->freq_count += freq;
			hwc->freq_interrupts += interrupts;

			if (hwc->freq_count < HZ)
				continue;

			interrupts = hwc->freq_interrupts;
			hwc->freq_interrupts = 0;
			hwc->freq_count -= HZ;
		} else
			freq = HZ;

		perf_adjust_period(counter, freq * interrupts);

		/*
		 * In order to avoid being stalled by an (accidental) huge
		 * sample period, force reset the sample period if we didn't
		 * get any events in this freq period.
		 */
		if (!interrupts) {
			perf_disable();
			counter->pmu->disable(counter);
			atomic_set(&hwc->period_left, 0);
			counter->pmu->enable(counter);
			perf_enable();
		}
	}
	spin_unlock(&ctx->lock);
}

/*
 * Round-robin a context's counters:
 */
static void rotate_ctx(struct perf_counter_context *ctx)
{
	struct perf_counter *counter;

	if (!ctx->nr_counters)
		return;

	spin_lock(&ctx->lock);
	/*
	 * Rotate the first entry last (works just fine for group counters too):
	 */
	perf_disable();
	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
		list_move_tail(&counter->list_entry, &ctx->counter_list);
		break;
	}
	perf_enable();

	spin_unlock(&ctx->lock);
}

void perf_counter_task_tick(struct task_struct *curr, int cpu)
{
	struct perf_cpu_context *cpuctx;
	struct perf_counter_context *ctx;

	if (!atomic_read(&nr_counters))
		return;

	cpuctx = &per_cpu(perf_cpu_context, cpu);
	ctx = curr->perf_counter_ctxp;

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

	perf_counter_cpu_sched_out(cpuctx);
	if (ctx)
		__perf_counter_task_sched_out(ctx);

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

	perf_counter_cpu_sched_in(cpuctx, cpu);
	if (ctx)
		perf_counter_task_sched_in(curr, cpu);
}

/*
 * Cross CPU call to read the hardware counter
 */
static void __read(void *info)
{
	struct perf_counter *counter = info;
	struct perf_counter_context *ctx = counter->ctx;
	unsigned long flags;

	local_irq_save(flags);
	if (ctx->is_active)
		update_context_time(ctx);
	counter->pmu->read(counter);
	update_counter_times(counter);
	local_irq_restore(flags);
}

static u64 perf_counter_read(struct perf_counter *counter)
{
	/*
	 * If counter is enabled and currently active on a CPU, update the
	 * value in the counter structure:
	 */
	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
		smp_call_function_single(counter->oncpu,
					 __read, counter, 1);
	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
		update_counter_times(counter);
	}

	return atomic64_read(&counter->count);
}

/*
 * Initialize the perf_counter context in a task_struct:
 */
static void
__perf_counter_init_context(struct perf_counter_context *ctx,
			    struct task_struct *task)
{
	memset(ctx, 0, sizeof(*ctx));
	spin_lock_init(&ctx->lock);
	mutex_init(&ctx->mutex);
	INIT_LIST_HEAD(&ctx->counter_list);
	INIT_LIST_HEAD(&ctx->event_list);
	atomic_set(&ctx->refcount, 1);
	ctx->task = task;
}

static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
{
	struct perf_counter_context *parent_ctx;
	struct perf_counter_context *ctx;
	struct perf_cpu_context *cpuctx;
	struct task_struct *task;
	unsigned long flags;
	int err;

	/*
	 * If cpu is not a wildcard then this is a percpu counter:
	 */
	if (cpu != -1) {
		/* Must be root to operate on a CPU counter: */
		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
			return ERR_PTR(-EACCES);

		if (cpu < 0 || cpu > num_possible_cpus())
			return ERR_PTR(-EINVAL);

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

		cpuctx = &per_cpu(perf_cpu_context, cpu);
		ctx = &cpuctx->ctx;
		get_ctx(ctx);

		return ctx;
	}

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

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

	/*
	 * Can't attach counters to a dying task.
	 */
	err = -ESRCH;
	if (task->flags & PF_EXITING)
		goto errout;

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

 retry:
	ctx = perf_lock_task_context(task, &flags);
	if (ctx) {
		parent_ctx = ctx->parent_ctx;
		if (parent_ctx) {
			put_ctx(parent_ctx);
			ctx->parent_ctx = NULL;		/* no longer a clone */
		}
		/*
		 * Get an extra reference before dropping the lock so that
		 * this context won't get freed if the task exits.
		 */
		get_ctx(ctx);
		spin_unlock_irqrestore(&ctx->lock, flags);
	}

	if (!ctx) {
		ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
		err = -ENOMEM;
		if (!ctx)
			goto errout;
		__perf_counter_init_context(ctx, task);
		get_ctx(ctx);
		if (cmpxchg(&task->perf_counter_ctxp, NULL, ctx)) {
			/*
			 * We raced with some other task; use
			 * the context they set.
			 */
			kfree(ctx);
			goto retry;
		}
		get_task_struct(task);
	}

	put_task_struct(task);
	return ctx;

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

static void free_counter_rcu(struct rcu_head *head)
{
	struct perf_counter *counter;

	counter = container_of(head, struct perf_counter, rcu_head);
	if (counter->ns)
		put_pid_ns(counter->ns);
	kfree(counter);
}

static void perf_pending_sync(struct perf_counter *counter);

static void free_counter(struct perf_counter *counter)
{
	perf_pending_sync(counter);

	atomic_dec(&nr_counters);
	if (counter->attr.mmap)
		atomic_dec(&nr_mmap_counters);
	if (counter->attr.comm)
		atomic_dec(&nr_comm_counters);

	if (counter->destroy)
		counter->destroy(counter);

	put_ctx(counter->ctx);
	call_rcu(&counter->rcu_head, free_counter_rcu);
}

/*
 * Called when the last reference to the file is gone.
 */
static int perf_release(struct inode *inode, struct file *file)
{
	struct perf_counter *counter = file->private_data;
	struct perf_counter_context *ctx = counter->ctx;

	file->private_data = NULL;

	WARN_ON_ONCE(ctx->parent_ctx);
	mutex_lock(&ctx->mutex);
	perf_counter_remove_from_context(counter);
	mutex_unlock(&ctx->mutex);

	mutex_lock(&counter->owner->perf_counter_mutex);
	list_del_init(&counter->owner_entry);
	mutex_unlock(&counter->owner->perf_counter_mutex);
	put_task_struct(counter->owner);

	free_counter(counter);

	return 0;
}

/*
 * Read the performance counter - simple non blocking version for now
 */
static ssize_t
perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
{
	u64 values[3];
	int n;

	/*
	 * Return end-of-file for a read on a counter 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 (counter->state == PERF_COUNTER_STATE_ERROR)
		return 0;

	WARN_ON_ONCE(counter->ctx->parent_ctx);
	mutex_lock(&counter->child_mutex);
	values[0] = perf_counter_read(counter);
	n = 1;
	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		values[n++] = counter->total_time_enabled +
			atomic64_read(&counter->child_total_time_enabled);
	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		values[n++] = counter->total_time_running +
			atomic64_read(&counter->child_total_time_running);
	if (counter->attr.read_format & PERF_FORMAT_ID)
		values[n++] = counter->id;
	mutex_unlock(&counter->child_mutex);

	if (count < n * sizeof(u64))
		return -EINVAL;
	count = n * sizeof(u64);

	if (copy_to_user(buf, values, count))
		return -EFAULT;

	return count;
}

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

	return perf_read_hw(counter, buf, count);
}

static unsigned int perf_poll(struct file *file, poll_table *wait)
{
	struct perf_counter *counter = file->private_data;
	struct perf_mmap_data *data;
	unsigned int events = POLL_HUP;

	rcu_read_lock();
	data = rcu_dereference(counter->data);
	if (data)
		events = atomic_xchg(&data->poll, 0);
	rcu_read_unlock();

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

	return events;
}

static void perf_counter_reset(struct perf_counter *counter)
{
	(void)perf_counter_read(counter);
	atomic64_set(&counter->count, 0);
	perf_counter_update_userpage(counter);
}

static void perf_counter_for_each_sibling(struct perf_counter *counter,
					  void (*func)(struct perf_counter *))
{
	struct perf_counter_context *ctx = counter->ctx;
	struct perf_counter *sibling;

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

	func(counter);
	list_for_each_entry(sibling, &counter->sibling_list, list_entry)
		func(sibling);
	mutex_unlock(&ctx->mutex);
}

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

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

static void perf_counter_for_each(struct perf_counter *counter,
				  void (*func)(struct perf_counter *))
{
	struct perf_counter *child;

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

static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
{
	struct perf_counter_context *ctx = counter->ctx;
	unsigned long size;
	int ret = 0;
	u64 value;

	if (!counter->attr.sample_period)
		return -EINVAL;

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

	if (!value)
		return -EINVAL;

	spin_lock_irq(&ctx->lock);
	if (counter->attr.freq) {
		if (value > sysctl_perf_counter_sample_rate) {
			ret = -EINVAL;
			goto unlock;
		}

		counter->attr.sample_freq = value;
	} else {
		perf_log_period(counter, value);

		counter->attr.sample_period = value;
		counter->hw.sample_period = value;
	}
unlock:
	spin_unlock_irq(&ctx->lock);

	return ret;
}

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

	switch (cmd) {
	case PERF_COUNTER_IOC_ENABLE:
		func = perf_counter_enable;
		break;
	case PERF_COUNTER_IOC_DISABLE:
		func = perf_counter_disable;
		break;
	case PERF_COUNTER_IOC_RESET:
		func = perf_counter_reset;
		break;

	case PERF_COUNTER_IOC_REFRESH:
		return perf_counter_refresh(counter, arg);

	case PERF_COUNTER_IOC_PERIOD:
		return perf_counter_period(counter, (u64 __user *)arg);

	default:
		return -ENOTTY;
	}

	if (flags & PERF_IOC_FLAG_GROUP)
		perf_counter_for_each(counter, func);
	else
		perf_counter_for_each_child(counter, func);

	return 0;
}

int perf_counter_task_enable(void)
{
	struct perf_counter *counter;

	mutex_lock(&current->perf_counter_mutex);
	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
		perf_counter_for_each_child(counter, perf_counter_enable);
	mutex_unlock(&current->perf_counter_mutex);

	return 0;
}

int perf_counter_task_disable(void)
{
	struct perf_counter *counter;

	mutex_lock(&current->perf_counter_mutex);
	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
		perf_counter_for_each_child(counter, perf_counter_disable);
	mutex_unlock(&current->perf_counter_mutex);

	return 0;
}

/*
 * 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_counter_update_userpage(struct perf_counter *counter)
{
	struct perf_counter_mmap_page *userpg;
	struct perf_mmap_data *data;

	rcu_read_lock();
	data = rcu_dereference(counter->data);
	if (!data)
		goto unlock;

	userpg = data->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 = counter->hw.idx;
	userpg->offset = atomic64_read(&counter->count);
	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
		userpg->offset -= atomic64_read(&counter->hw.prev_count);

	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_counter *counter = vma->vm_file->private_data;
	struct perf_mmap_data *data;
	int ret = VM_FAULT_SIGBUS;

	rcu_read_lock();
	data = rcu_dereference(counter->data);
	if (!data)
		goto unlock;

	if (vmf->pgoff == 0) {
		vmf->page = virt_to_page(data->user_page);
	} else {
		int nr = vmf->pgoff - 1;

		if ((unsigned)nr > data->nr_pages)
			goto unlock;

		vmf->page = virt_to_page(data->data_pages[nr]);
	}
	get_page(vmf->page);
	ret = 0;
unlock:
	rcu_read_unlock();

	return ret;
}

static int perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
{
	struct perf_mmap_data *data;
	unsigned long size;
	int i;

	WARN_ON(atomic_read(&counter->mmap_count));

	size = sizeof(struct perf_mmap_data);
	size += nr_pages * sizeof(void *);

	data = kzalloc(size, GFP_KERNEL);
	if (!data)
		goto fail;

	data->user_page = (void *)get_zeroed_page(GFP_KERNEL);
	if (!data->user_page)
		goto fail_user_page;

	for (i = 0; i < nr_pages; i++) {
		data->data_pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
		if (!data->data_pages[i])
			goto fail_data_pages;
	}

	data->nr_pages = nr_pages;
	atomic_set(&data->lock, -1);

	rcu_assign_pointer(counter->data, data);

	return 0;

fail_data_pages:
	for (i--; i >= 0; i--)
		free_page((unsigned long)data->data_pages[i]);

	free_page((unsigned long)data->user_page);

fail_user_page:
	kfree(data);

fail:
	return -ENOMEM;
}

static void __perf_mmap_data_free(struct rcu_head *rcu_head)
{
	struct perf_mmap_data *data;
	int i;

	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);

	free_page((unsigned long)data->user_page);
	for (i = 0; i < data->nr_pages; i++)
		free_page((unsigned long)data->data_pages[i]);
	kfree(data);
}

static void perf_mmap_data_free(struct perf_counter *counter)
{
	struct perf_mmap_data *data = counter->data;

	WARN_ON(atomic_read(&counter->mmap_count));

	rcu_assign_pointer(counter->data, NULL);
	call_rcu(&data->rcu_head, __perf_mmap_data_free);
}

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

	atomic_inc(&counter->mmap_count);
}

static void perf_mmap_close(struct vm_area_struct *vma)
{
	struct perf_counter *counter = vma->vm_file->private_data;

	WARN_ON_ONCE(counter->ctx->parent_ctx);
	if (atomic_dec_and_mutex_lock(&counter->mmap_count, &counter->mmap_mutex)) {
		struct user_struct *user = current_user();

		atomic_long_sub(counter->data->nr_pages + 1, &user->locked_vm);
		vma->vm_mm->locked_vm -= counter->data->nr_locked;
		perf_mmap_data_free(counter);
		mutex_unlock(&counter->mmap_mutex);
	}
}

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

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

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

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

	/*
	 * If we have data 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(counter->ctx->parent_ctx);
	mutex_lock(&counter->mmap_mutex);
	if (atomic_inc_not_zero(&counter->mmap_count)) {
		if (nr_pages != counter->data->nr_pages)
			ret = -EINVAL;
		goto unlock;
	}

	user_extra = nr_pages + 1;
	user_lock_limit = sysctl_perf_counter_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 = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
	lock_limit >>= PAGE_SHIFT;
	locked = vma->vm_mm->locked_vm + extra;

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

	WARN_ON(counter->data);
	ret = perf_mmap_data_alloc(counter, nr_pages);
	if (ret)
		goto unlock;

	atomic_set(&counter->mmap_count, 1);
	atomic_long_add(user_extra, &user->locked_vm);
	vma->vm_mm->locked_vm += extra;
	counter->data->nr_locked = extra;
unlock:
	mutex_unlock(&counter->mmap_mutex);

	vma->vm_flags &= ~VM_MAYWRITE;
	vma->vm_flags |= VM_RESERVED;
	vma->vm_ops = &perf_mmap_vmops;

	return ret;
}

static int perf_fasync(int fd, struct file *filp, int on)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct perf_counter *counter = filp->private_data;
	int retval;

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

	if (retval < 0)
		return retval;

	return 0;
}

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

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

void perf_counter_wakeup(struct perf_counter *counter)
{
	wake_up_all(&counter->waitq);

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

/*
 * Pending wakeups
 *
 * Handle the case where we need to wakeup up from NMI (or rq->lock) context.
 *
 * The NMI bit means we cannot possibly take locks. Therefore, maintain a
 * single linked list and use cmpxchg() to add entries lockless.
 */

static void perf_pending_counter(struct perf_pending_entry *entry)
{
	struct perf_counter *counter = container_of(entry,
			struct perf_counter, pending);

	if (counter->pending_disable) {
		counter->pending_disable = 0;
		perf_counter_disable(counter);
	}

	if (counter->pending_wakeup) {
		counter->pending_wakeup = 0;
		perf_counter_wakeup(counter);
	}
}

#define PENDING_TAIL ((struct perf_pending_entry *)-1UL)

static DEFINE_PER_CPU(struct perf_pending_entry *, perf_pending_head) = {
	PENDING_TAIL,
};

static void perf_pending_queue(struct perf_pending_entry *entry,
			       void (*func)(struct perf_pending_entry *))
{
	struct perf_pending_entry **head;

	if (cmpxchg(&entry->next, NULL, PENDING_TAIL) != NULL)
		return;

	entry->func = func;

	head = &get_cpu_var(perf_pending_head);

	do {
		entry->next = *head;
	} while (cmpxchg(head, entry->next, entry) != entry->next);

	set_perf_counter_pending();

	put_cpu_var(perf_pending_head);
}

static int __perf_pending_run(void)
{
	struct perf_pending_entry *list;
	int nr = 0;

	list = xchg(&__get_cpu_var(perf_pending_head), PENDING_TAIL);
	while (list != PENDING_TAIL) {
		void (*func)(struct perf_pending_entry *);
		struct perf_pending_entry *entry = list;

		list = list->next;

		func = entry->func;
		entry->next = NULL;
		/*
		 * Ensure we observe the unqueue before we issue the wakeup,
		 * so that we won't be waiting forever.
		 * -- see perf_not_pending().
		 */
		smp_wmb();

		func(entry);
		nr++;
	}

	return nr;
}

static inline int perf_not_pending(struct perf_counter *counter)
{
	/*
	 * If we flush on whatever cpu we run, there is a chance we don't
	 * need to wait.
	 */
	get_cpu();
	__perf_pending_run();
	put_cpu();

	/*
	 * Ensure we see the proper queue state before going to sleep
	 * so that we do not miss the wakeup. -- see perf_pending_handle()
	 */
	smp_rmb();
	return counter->pending.next == NULL;
}

static void perf_pending_sync(struct perf_counter *counter)
{
	wait_event(counter->waitq, perf_not_pending(counter));
}

void perf_counter_do_pending(void)
{
	__perf_pending_run();
}

/*
 * Callchain support -- arch specific
 */

__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
{
	return NULL;
}

/*
 * Output
 */

struct perf_output_handle {
	struct perf_counter	*counter;
	struct perf_mmap_data	*data;
	unsigned long		head;
	unsigned long		offset;
	int			nmi;
	int			overflow;
	int			locked;
	unsigned long		flags;
};

static void perf_output_wakeup(struct perf_output_handle *handle)
{
	atomic_set(&handle->data->poll, POLL_IN);

	if (handle->nmi) {
		handle->counter->pending_wakeup = 1;
		perf_pending_queue(&handle->counter->pending,
				   perf_pending_counter);
	} else
		perf_counter_wakeup(handle->counter);
}

/*
 * Curious locking construct.
 *
 * We need to ensure a later event doesn't publish a head when a former
 * event isn't done writing. However since we need to deal with NMIs we
 * cannot fully serialize things.
 *
 * What we do is serialize between CPUs so we only have to deal with NMI
 * nesting on a single CPU.
 *
 * We only publish the head (and generate a wakeup) when the outer-most
 * event completes.
 */
static void perf_output_lock(struct perf_output_handle *handle)
{
	struct perf_mmap_data *data = handle->data;
	int cpu;

	handle->locked = 0;

	local_irq_save(handle->flags);
	cpu = smp_processor_id();

	if (in_nmi() && atomic_read(&data->lock) == cpu)
		return;

	while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
		cpu_relax();

	handle->locked = 1;
}

static void perf_output_unlock(struct perf_output_handle *handle)
{
	struct perf_mmap_data *data = handle->data;
	unsigned long head;
	int cpu;

	data->done_head = data->head;

	if (!handle->locked)
		goto out;

again:
	/*
	 * The xchg implies a full barrier that ensures all writes are done
	 * before we publish the new head, matched by a rmb() in userspace when
	 * reading this position.
	 */
	while ((head = atomic_long_xchg(&data->done_head, 0)))
		data->user_page->data_head = head;

	/*
	 * NMI can happen here, which means we can miss a done_head update.
	 */

	cpu = atomic_xchg(&data->lock, -1);
	WARN_ON_ONCE(cpu != smp_processor_id());

	/*
	 * Therefore we have to validate we did not indeed do so.
	 */
	if (unlikely(atomic_long_read(&data->done_head))) {
		/*
		 * Since we had it locked, we can lock it again.
		 */
		while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
			cpu_relax();

		goto again;
	}

	if (atomic_xchg(&data->wakeup, 0))
		perf_output_wakeup(handle);
out:
	local_irq_restore(handle->flags);
}

static int perf_output_begin(struct perf_output_handle *handle,
			     struct perf_counter *counter, unsigned int size,
			     int nmi, int overflow)
{
	struct perf_mmap_data *data;
	unsigned int offset, head;

	/*
	 * For inherited counters we send all the output towards the parent.
	 */
	if (counter->parent)
		counter = counter->parent;

	rcu_read_lock();
	data = rcu_dereference(counter->data);
	if (!data)
		goto out;

	handle->data	 = data;
	handle->counter	 = counter;
	handle->nmi	 = nmi;
	handle->overflow = overflow;

	if (!data->nr_pages)
		goto fail;

	perf_output_lock(handle);

	do {
		offset = head = atomic_long_read(&data->head);
		head += size;
	} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);

	handle->offset	= offset;
	handle->head	= head;

	if ((offset >> PAGE_SHIFT) != (head >> PAGE_SHIFT))
		atomic_set(&data->wakeup, 1);

	return 0;

fail:
	perf_output_wakeup(handle);
out:
	rcu_read_unlock();

	return -ENOSPC;
}

static void perf_output_copy(struct perf_output_handle *handle,
			     const void *buf, unsigned int len)
{
	unsigned int pages_mask;
	unsigned int offset;
	unsigned int size;
	void **pages;

	offset		= handle->offset;
	pages_mask	= handle->data->nr_pages - 1;
	pages		= handle->data->data_pages;

	do {
		unsigned int page_offset;
		int nr;

		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
		page_offset = offset & (PAGE_SIZE - 1);
		size	    = min_t(unsigned int, PAGE_SIZE - page_offset, len);

		memcpy(pages[nr] + page_offset, buf, size);

		len	    -= size;
		buf	    += size;
		offset	    += size;
	} while (len);

	handle->offset = offset;

	/*
	 * Check we didn't copy past our reservation window, taking the
	 * possible unsigned int wrap into account.
	 */
	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
}

#define perf_output_put(handle, x) \
	perf_output_copy((handle), &(x), sizeof(x))

static void perf_output_end(struct perf_output_handle *handle)
{
	struct perf_counter *counter = handle->counter;
	struct perf_mmap_data *data = handle->data;

	int wakeup_events = counter->attr.wakeup_events;

	if (handle->overflow && wakeup_events) {
		int events = atomic_inc_return(&data->events);
		if (events >= wakeup_events) {
			atomic_sub(wakeup_events, &data->events);
			atomic_set(&data->wakeup, 1);
		}
	}

	perf_output_unlock(handle);
	rcu_read_unlock();
}

static u32 perf_counter_pid(struct perf_counter *counter, struct task_struct *p)
{
	/*
	 * only top level counters have the pid namespace they were created in
	 */
	if (counter->parent)
		counter = counter->parent;

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

static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p)
{
	/*
	 * only top level counters have the pid namespace they were created in
	 */
	if (counter->parent)
		counter = counter->parent;

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

static void perf_counter_output(struct perf_counter *counter, int nmi,
				struct perf_sample_data *data)
{
	int ret;
	u64 sample_type = counter->attr.sample_type;
	struct perf_output_handle handle;
	struct perf_event_header header;
	u64 ip;
	struct {
		u32 pid, tid;
	} tid_entry;
	struct {
		u64 id;
		u64 counter;
	} group_entry;
	struct perf_callchain_entry *callchain = NULL;
	int callchain_size = 0;
	u64 time;
	struct {
		u32 cpu, reserved;
	} cpu_entry;

	header.type = 0;
	header.size = sizeof(header);

	header.misc = PERF_EVENT_MISC_OVERFLOW;
	header.misc |= perf_misc_flags(data->regs);

	if (sample_type & PERF_SAMPLE_IP) {
		ip = perf_instruction_pointer(data->regs);
		header.type |= PERF_SAMPLE_IP;
		header.size += sizeof(ip);
	}

	if (sample_type & PERF_SAMPLE_TID) {
		/* namespace issues */
		tid_entry.pid = perf_counter_pid(counter, current);
		tid_entry.tid = perf_counter_tid(counter, current);

		header.type |= PERF_SAMPLE_TID;
		header.size += sizeof(tid_entry);
	}

	if (sample_type & PERF_SAMPLE_TIME) {
		/*
		 * Maybe do better on x86 and provide cpu_clock_nmi()
		 */
		time = sched_clock();

		header.type |= PERF_SAMPLE_TIME;
		header.size += sizeof(u64);
	}

	if (sample_type & PERF_SAMPLE_ADDR) {
		header.type |= PERF_SAMPLE_ADDR;
		header.size += sizeof(u64);
	}

	if (sample_type & PERF_SAMPLE_ID) {
		header.type |= PERF_SAMPLE_ID;
		header.size += sizeof(u64);
	}

	if (sample_type & PERF_SAMPLE_CPU) {
		header.type |= PERF_SAMPLE_CPU;
		header.size += sizeof(cpu_entry);

		cpu_entry.cpu = raw_smp_processor_id();
	}

	if (sample_type & PERF_SAMPLE_PERIOD) {
		header.type |= PERF_SAMPLE_PERIOD;
		header.size += sizeof(u64);
	}

	if (sample_type & PERF_SAMPLE_GROUP) {
		header.type |= PERF_SAMPLE_GROUP;
		header.size += sizeof(u64) +
			counter->nr_siblings * sizeof(group_entry);
	}

	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
		callchain = perf_callchain(data->regs);

		if (callchain) {
			callchain_size = (1 + callchain->nr) * sizeof(u64);

			header.type |= PERF_SAMPLE_CALLCHAIN;
			header.size += callchain_size;
		}
	}

	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
	if (ret)
		return;

	perf_output_put(&handle, header);

	if (sample_type & PERF_SAMPLE_IP)
		perf_output_put(&handle, ip);

	if (sample_type & PERF_SAMPLE_TID)
		perf_output_put(&handle, tid_entry);

	if (sample_type & PERF_SAMPLE_TIME)
		perf_output_put(&handle, time);

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

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

	if (sample_type & PERF_SAMPLE_CPU)
		perf_output_put(&handle, cpu_entry);

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

	/*
	 * XXX PERF_SAMPLE_GROUP vs inherited counters seems difficult.
	 */
	if (sample_type & PERF_SAMPLE_GROUP) {
		struct perf_counter *leader, *sub;
		u64 nr = counter->nr_siblings;

		perf_output_put(&handle, nr);

		leader = counter->group_leader;
		list_for_each_entry(sub, &leader->sibling_list, list_entry) {
			if (sub != counter)
				sub->pmu->read(sub);

			group_entry.id = sub->id;
			group_entry.counter = atomic64_read(&sub->count);

			perf_output_put(&handle, group_entry);
		}
	}

	if (callchain)
		perf_output_copy(&handle, callchain, callchain_size);

	perf_output_end(&handle);
}

/*
 * fork tracking
 */

struct perf_fork_event {
	struct task_struct	*task;

	struct {
		struct perf_event_header	header;

		u32				pid;
		u32				ppid;
	} event;
};

static void perf_counter_fork_output(struct perf_counter *counter,
				     struct perf_fork_event *fork_event)
{
	struct perf_output_handle handle;
	int size = fork_event->event.header.size;
	struct task_struct *task = fork_event->task;
	int ret = perf_output_begin(&handle, counter, size, 0, 0);

	if (ret)
		return;

	fork_event->event.pid = perf_counter_pid(counter, task);
	fork_event->event.ppid = perf_counter_pid(counter, task->real_parent);

	perf_output_put(&handle, fork_event->event);
	perf_output_end(&handle);
}

static int perf_counter_fork_match(struct perf_counter *counter)
{
	if (counter->attr.comm || counter->attr.mmap)
		return 1;

	return 0;
}

static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
				  struct perf_fork_event *fork_event)
{
	struct perf_counter *counter;

	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
		return;

	rcu_read_lock();
	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
		if (perf_counter_fork_match(counter))
			perf_counter_fork_output(counter, fork_event);
	}
	rcu_read_unlock();
}

static void perf_counter_fork_event(struct perf_fork_event *fork_event)
{
	struct perf_cpu_context *cpuctx;
	struct perf_counter_context *ctx;

	cpuctx = &get_cpu_var(perf_cpu_context);
	perf_counter_fork_ctx(&cpuctx->ctx, fork_event);
	put_cpu_var(perf_cpu_context);

	rcu_read_lock();
	/*
	 * doesn't really matter which of the child contexts the
	 * events ends up in.
	 */
	ctx = rcu_dereference(current->perf_counter_ctxp);
	if (ctx)
		perf_counter_fork_ctx(ctx, fork_event);
	rcu_read_unlock();
}

void perf_counter_fork(struct task_struct *task)
{
	struct perf_fork_event fork_event;

	if (!atomic_read(&nr_comm_counters) &&
	    !atomic_read(&nr_mmap_counters))
		return;

	fork_event = (struct perf_fork_event){
		.task	= task,
		.event  = {
			.header = {
				.type = PERF_EVENT_FORK,
				.size = sizeof(fork_event.event),
			},
		},
	};

	perf_counter_fork_event(&fork_event);
}

/*
 * 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;
};

static void perf_counter_comm_output(struct perf_counter *counter,
				     struct perf_comm_event *comm_event)
{
	struct perf_output_handle handle;
	int size = comm_event->event.header.size;
	int ret = perf_output_begin(&handle, counter, size, 0, 0);

	if (ret)
		return;

	comm_event->event.pid = perf_counter_pid(counter, comm_event->task);
	comm_event->event.tid = perf_counter_tid(counter, comm_event->task);

	perf_output_put(&handle, comm_event->event);
	perf_output_copy(&handle, comm_event->comm,
				   comm_event->comm_size);
	perf_output_end(&handle);
}

static int perf_counter_comm_match(struct perf_counter *counter)
{
	if (counter->attr.comm)
		return 1;

	return 0;
}

static void perf_counter_comm_ctx(struct perf_counter_context *ctx,
				  struct perf_comm_event *comm_event)
{
	struct perf_counter *counter;

	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
		return;

	rcu_read_lock();
	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
		if (perf_counter_comm_match(counter))
			perf_counter_comm_output(counter, comm_event);
	}
	rcu_read_unlock();
}

static void perf_counter_comm_event(struct perf_comm_event *comm_event)
{
	struct perf_cpu_context *cpuctx;
	struct perf_counter_context *ctx;
	unsigned int size;
	char *comm = comm_event->task->comm;

	size = ALIGN(strlen(comm)+1, sizeof(u64));

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

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

	cpuctx = &get_cpu_var(perf_cpu_context);
	perf_counter_comm_ctx(&cpuctx->ctx, comm_event);
	put_cpu_var(perf_cpu_context);

	rcu_read_lock();
	/*
	 * doesn't really matter which of the child contexts the
	 * events ends up in.
	 */
	ctx = rcu_dereference(current->perf_counter_ctxp);
	if (ctx)
		perf_counter_comm_ctx(ctx, comm_event);
	rcu_read_unlock();
}

void perf_counter_comm(struct task_struct *task)
{
	struct perf_comm_event comm_event;

	if (!atomic_read(&nr_comm_counters))
		return;

	comm_event = (struct perf_comm_event){
		.task	= task,
		.event  = {
			.header = { .type = PERF_EVENT_COMM, },
		},
	};

	perf_counter_comm_event(&comm_event);
}

/*
 * mmap tracking
 */

struct perf_mmap_event {
	struct vm_area_struct	*vma;

	const char		*file_name;
	int			file_size;

	struct {
		struct perf_event_header	header;

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

static void perf_counter_mmap_output(struct perf_counter *counter,
				     struct perf_mmap_event *mmap_event)
{
	struct perf_output_handle handle;
	int size = mmap_event->event.header.size;
	int ret = perf_output_begin(&handle, counter, size, 0, 0);

	if (ret)
		return;

	mmap_event->event.pid = perf_counter_pid(counter, current);
	mmap_event->event.tid = perf_counter_tid(counter, current);

	perf_output_put(&handle, mmap_event->event);
	perf_output_copy(&handle, mmap_event->file_name,
				   mmap_event->file_size);
	perf_output_end(&handle);
}

static int perf_counter_mmap_match(struct perf_counter *counter,
				   struct perf_mmap_event *mmap_event)
{
	if (counter->attr.mmap)
		return 1;

	return 0;
}

static void perf_counter_mmap_ctx(struct perf_counter_context *ctx,
				  struct perf_mmap_event *mmap_event)
{
	struct perf_counter *counter;

	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
		return;

	rcu_read_lock();
	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
		if (perf_counter_mmap_match(counter, mmap_event))
			perf_counter_mmap_output(counter, mmap_event);
	}
	rcu_read_unlock();
}

static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
{
	struct perf_cpu_context *cpuctx;
	struct perf_counter_context *ctx;
	struct vm_area_struct *vma = mmap_event->vma;
	struct file *file = vma->vm_file;
	unsigned int size;
	char tmp[16];
	char *buf = NULL;
	const char *name;

	if (file) {
		buf = kzalloc(PATH_MAX, GFP_KERNEL);
		if (!buf) {
			name = strncpy(tmp, "//enomem", sizeof(tmp));
			goto got_name;
		}
		name = d_path(&file->f_path, buf, PATH_MAX);
		if (IS_ERR(name)) {
			name = strncpy(tmp, "//toolong", sizeof(tmp));
			goto got_name;
		}
	} else {
		name = arch_vma_name(mmap_event->vma);
		if (name)
			goto got_name;

		if (!vma->vm_mm) {
			name = strncpy(tmp, "[vdso]", sizeof(tmp));
			goto got_name;
		}

		name = strncpy(tmp, "//anon", sizeof(tmp));
		goto got_name;
	}

got_name:
	size = ALIGN(strlen(name)+1, sizeof(u64));

	mmap_event->file_name = name;
	mmap_event->file_size = size;

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

	cpuctx = &get_cpu_var(perf_cpu_context);
	perf_counter_mmap_ctx(&cpuctx->ctx, mmap_event);
	put_cpu_var(perf_cpu_context);

	rcu_read_lock();
	/*
	 * doesn't really matter which of the child contexts the
	 * events ends up in.
	 */
	ctx = rcu_dereference(current->perf_counter_ctxp);
	if (ctx)
		perf_counter_mmap_ctx(ctx, mmap_event);
	rcu_read_unlock();

	kfree(buf);
}

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

	if (!atomic_read(&nr_mmap_counters))
		return;

	mmap_event = (struct perf_mmap_event){
		.vma	= vma,
		.event  = {
			.header = { .type = PERF_EVENT_MMAP, },
			.start  = vma->vm_start,
			.len    = vma->vm_end - vma->vm_start,
			.pgoff  = vma->vm_pgoff,
		},
	};

	perf_counter_mmap_event(&mmap_event);
}

/*
 * Log sample_period changes so that analyzing tools can re-normalize the
 * event flow.
 */

struct freq_event {
	struct perf_event_header	header;
	u64				time;
	u64				id;
	u64				period;
};

static void perf_log_period(struct perf_counter *counter, u64 period)
{
	struct perf_output_handle handle;
	struct freq_event event;
	int ret;

	if (counter->hw.sample_period == period)
		return;

	if (counter->attr.sample_type & PERF_SAMPLE_PERIOD)
		return;

	event = (struct freq_event) {
		.header = {
			.type = PERF_EVENT_PERIOD,
			.misc = 0,
			.size = sizeof(event),
		},
		.time = sched_clock(),
		.id = counter->id,
		.period = period,
	};

	ret = perf_output_begin(&handle, counter, sizeof(event), 1, 0);
	if (ret)
		return;

	perf_output_put(&handle, event);
	perf_output_end(&handle);
}

/*
 * IRQ throttle logging
 */

static void perf_log_throttle(struct perf_counter *counter, int enable)
{
	struct perf_output_handle handle;
	int ret;

	struct {
		struct perf_event_header	header;
		u64				time;
		u64				id;
	} throttle_event = {
		.header = {
			.type = PERF_EVENT_THROTTLE + 1,
			.misc = 0,
			.size = sizeof(throttle_event),
		},
		.time	= sched_clock(),
		.id	= counter->id,
	};

	ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
	if (ret)
		return;

	perf_output_put(&handle, throttle_event);
	perf_output_end(&handle);
}

/*
 * Generic counter overflow handling.
 */

int perf_counter_overflow(struct perf_counter *counter, int nmi,
			  struct perf_sample_data *data)
{
	int events = atomic_read(&counter->event_limit);
	int throttle = counter->pmu->unthrottle != NULL;
	struct hw_perf_counter *hwc = &counter->hw;
	int ret = 0;

	if (!throttle) {
		hwc->interrupts++;
	} else {
		if (hwc->interrupts != MAX_INTERRUPTS) {
			hwc->interrupts++;
			if (HZ * hwc->interrupts >
					(u64)sysctl_perf_counter_sample_rate) {
				hwc->interrupts = MAX_INTERRUPTS;
				perf_log_throttle(counter, 0);
				ret = 1;
			}
		} else {
			/*
			 * Keep re-disabling counters even though on the previous
			 * pass we disabled it - just in case we raced with a
			 * sched-in and the counter got enabled again:
			 */
			ret = 1;
		}
	}

	if (counter->attr.freq) {
		u64 now = sched_clock();
		s64 delta = now - hwc->freq_stamp;

		hwc->freq_stamp = now;

		if (delta > 0 && delta < TICK_NSEC)
			perf_adjust_period(counter, NSEC_PER_SEC / (int)delta);
	}

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

	counter->pending_kill = POLL_IN;
	if (events && atomic_dec_and_test(&counter->event_limit)) {
		ret = 1;
		counter->pending_kill = POLL_HUP;
		if (nmi) {
			counter->pending_disable = 1;
			perf_pending_queue(&counter->pending,
					   perf_pending_counter);
		} else
			perf_counter_disable(counter);
	}

	perf_counter_output(counter, nmi, data);
	return ret;
}

/*
 * Generic software counter infrastructure
 */

static void perf_swcounter_update(struct perf_counter *counter)
{
	struct hw_perf_counter *hwc = &counter->hw;
	u64 prev, now;
	s64 delta;

again:
	prev = atomic64_read(&hwc->prev_count);
	now = atomic64_read(&hwc->count);
	if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev)
		goto again;

	delta = now - prev;

	atomic64_add(delta, &counter->count);
	atomic64_sub(delta, &hwc->period_left);
}

static void perf_swcounter_set_period(struct perf_counter *counter)
{
	struct hw_perf_counter *hwc = &counter->hw;
	s64 left = atomic64_read(&hwc->period_left);
	s64 period = hwc->sample_period;

	if (unlikely(left <= -period)) {
		left = period;
		atomic64_set(&hwc->period_left, left);
		hwc->last_period = period;
	}

	if (unlikely(left <= 0)) {
		left += period;
		atomic64_add(period, &hwc->period_left);
		hwc->last_period = period;
	}

	atomic64_set(&hwc->prev_count, -left);
	atomic64_set(&hwc->count, -left);
}

static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
{
	enum hrtimer_restart ret = HRTIMER_RESTART;
	struct perf_sample_data data;
	struct perf_counter *counter;
	u64 period;

	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
	counter->pmu->read(counter);

	data.addr = 0;
	data.regs = get_irq_regs();
	/*
	 * In case we exclude kernel IPs or are somehow not in interrupt
	 * context, provide the next best thing, the user IP.
	 */
	if ((counter->attr.exclude_kernel || !data.regs) &&
			!counter->attr.exclude_user)
		data.regs = task_pt_regs(current);

	if (data.regs) {
		if (perf_counter_overflow(counter, 0, &data))
			ret = HRTIMER_NORESTART;
	}

	period = max_t(u64, 10000, counter->hw.sample_period);
	hrtimer_forward_now(hrtimer, ns_to_ktime(period));

	return ret;
}

static void perf_swcounter_overflow(struct perf_counter *counter,
				    int nmi, struct pt_regs *regs, u64 addr)
{
	struct perf_sample_data data = {
		.regs	= regs,
		.addr	= addr,
		.period	= counter->hw.last_period,
	};

	perf_swcounter_update(counter);
	perf_swcounter_set_period(counter);
	if (perf_counter_overflow(counter, nmi, &data))
		/* soft-disable the counter */
		;

}

static int perf_swcounter_is_counting(struct perf_counter *counter)
{
	struct perf_counter_context *ctx;
	unsigned long flags;
	int count;

	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
		return 1;

	if (counter->state != PERF_COUNTER_STATE_INACTIVE)
		return 0;

	/*
	 * If the counter is inactive, it could be just because
	 * its task is scheduled out, or because it's in a group
	 * which could not go on the PMU.  We want to count in
	 * the first case but not the second.  If the context is
	 * currently active then an inactive software counter must
	 * be the second case.  If it's not currently active then
	 * we need to know whether the counter was active when the
	 * context was last active, which we can determine by
	 * comparing counter->tstamp_stopped with ctx->time.
	 *
	 * We are within an RCU read-side critical section,
	 * which protects the existence of *ctx.
	 */
	ctx = counter->ctx;
	spin_lock_irqsave(&ctx->lock, flags);
	count = 1;
	/* Re-check state now we have the lock */
	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
	    counter->ctx->is_active ||
	    counter->tstamp_stopped < ctx->time)
		count = 0;
	spin_unlock_irqrestore(&ctx->lock, flags);
	return count;
}

static int perf_swcounter_match(struct perf_counter *counter,
				enum perf_type_id type,
				u32 event, struct pt_regs *regs)
{
	if (!perf_swcounter_is_counting(counter))
		return 0;

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

	if (regs) {
		if (counter->attr.exclude_user && user_mode(regs))
			return 0;

		if (counter->attr.exclude_kernel && !user_mode(regs))
			return 0;
	}

	return 1;
}

static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
			       int nmi, struct pt_regs *regs, u64 addr)
{
	int neg = atomic64_add_negative(nr, &counter->hw.count);

	if (counter->hw.sample_period && !neg && regs)
		perf_swcounter_overflow(counter, nmi, regs, addr);
}

static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
				     enum perf_type_id type, u32 event,
				     u64 nr, int nmi, struct pt_regs *regs,
				     u64 addr)
{
	struct perf_counter *counter;

	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
		return;

	rcu_read_lock();
	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
		if (perf_swcounter_match(counter, type, event, regs))
			perf_swcounter_add(counter, nr, nmi, regs, addr);
	}
	rcu_read_unlock();
}

static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
{
	if (in_nmi())
		return &cpuctx->recursion[3];

	if (in_irq())
		return &cpuctx->recursion[2];

	if (in_softirq())
		return &cpuctx->recursion[1];

	return &cpuctx->recursion[0];
}

static void __perf_swcounter_event(enum perf_type_id type, u32 event,
				   u64 nr, int nmi, struct pt_regs *regs,
				   u64 addr)
{
	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
	int *recursion = perf_swcounter_recursion_context(cpuctx);
	struct perf_counter_context *ctx;

	if (*recursion)
		goto out;

	(*recursion)++;
	barrier();

	perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
				 nr, nmi, regs, addr);
	rcu_read_lock();
	/*
	 * doesn't really matter which of the child contexts the
	 * events ends up in.
	 */
	ctx = rcu_dereference(current->perf_counter_ctxp);
	if (ctx)
		perf_swcounter_ctx_event(ctx, type, event, nr, nmi, regs, addr);
	rcu_read_unlock();

	barrier();
	(*recursion)--;

out:
	put_cpu_var(perf_cpu_context);
}

void
perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
{
	__perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs, addr);
}

static void perf_swcounter_read(struct perf_counter *counter)
{
	perf_swcounter_update(counter);
}

static int perf_swcounter_enable(struct perf_counter *counter)
{
	perf_swcounter_set_period(counter);
	return 0;
}

static void perf_swcounter_disable(struct perf_counter *counter)
{
	perf_swcounter_update(counter);
}

static const struct pmu perf_ops_generic = {
	.enable		= perf_swcounter_enable,
	.disable	= perf_swcounter_disable,
	.read		= perf_swcounter_read,
};

/*
 * Software counter: cpu wall time clock
 */

static void cpu_clock_perf_counter_update(struct perf_counter *counter)
{
	int cpu = raw_smp_processor_id();
	s64 prev;
	u64 now;

	now = cpu_clock(cpu);
	prev = atomic64_read(&counter->hw.prev_count);
	atomic64_set(&counter->hw.prev_count, now);
	atomic64_add(now - prev, &counter->count);
}

static int cpu_clock_perf_counter_enable(struct perf_counter *counter)
{
	struct hw_perf_counter *hwc = &counter->hw;
	int cpu = raw_smp_processor_id();

	atomic64_set(&hwc->prev_count, cpu_clock(cpu));
	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	hwc->hrtimer.function = perf_swcounter_hrtimer;
	if (hwc->sample_period) {
		u64 period = max_t(u64, 10000, hwc->sample_period);
		__hrtimer_start_range_ns(&hwc->hrtimer,
				ns_to_ktime(period), 0,
				HRTIMER_MODE_REL, 0);
	}

	return 0;
}

static void cpu_clock_perf_counter_disable(struct perf_counter *counter)
{
	if (counter->hw.sample_period)
		hrtimer_cancel(&counter->hw.hrtimer);
	cpu_clock_perf_counter_update(counter);
}

static void cpu_clock_perf_counter_read(struct perf_counter *counter)
{
	cpu_clock_perf_counter_update(counter);
}

static const struct pmu perf_ops_cpu_clock = {
	.enable		= cpu_clock_perf_counter_enable,
	.disable	= cpu_clock_perf_counter_disable,
	.read		= cpu_clock_perf_counter_read,
};

/*
 * Software counter: task time clock
 */

static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
{
	u64 prev;
	s64 delta;

	prev = atomic64_xchg(&counter->hw.prev_count, now);
	delta = now - prev;
	atomic64_add(delta, &counter->count);
}

static int task_clock_perf_counter_enable(struct perf_counter *counter)
{
	struct hw_perf_counter *hwc = &counter->hw;
	u64 now;

	now = counter->ctx->time;

	atomic64_set(&hwc->prev_count, now);
	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	hwc->hrtimer.function = perf_swcounter_hrtimer;
	if (hwc->sample_period) {
		u64 period = max_t(u64, 10000, hwc->sample_period);
		__hrtimer_start_range_ns(&hwc->hrtimer,
				ns_to_ktime(period), 0,
				HRTIMER_MODE_REL, 0);
	}

	return 0;
}

static void task_clock_perf_counter_disable(struct perf_counter *counter)
{
	if (counter->hw.sample_period)
		hrtimer_cancel(&counter->hw.hrtimer);
	task_clock_perf_counter_update(counter, counter->ctx->time);

}

static void task_clock_perf_counter_read(struct perf_counter *counter)
{
	u64 time;

	if (!in_nmi()) {
		update_context_time(counter->ctx);
		time = counter->ctx->time;
	} else {
		u64 now = perf_clock();
		u64 delta = now - counter->ctx->timestamp;
		time = counter->ctx->time + delta;
	}

	task_clock_perf_counter_update(counter, time);
}

static const struct pmu perf_ops_task_clock = {
	.enable		= task_clock_perf_counter_enable,
	.disable	= task_clock_perf_counter_disable,
	.read		= task_clock_perf_counter_read,
};

/*
 * Software counter: cpu migrations
 */
void perf_counter_task_migration(struct task_struct *task, int cpu)
{
	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
	struct perf_counter_context *ctx;

	perf_swcounter_ctx_event(&cpuctx->ctx, PERF_TYPE_SOFTWARE,
				 PERF_COUNT_SW_CPU_MIGRATIONS,
				 1, 1, NULL, 0);

	ctx = perf_pin_task_context(task);
	if (ctx) {
		perf_swcounter_ctx_event(ctx, PERF_TYPE_SOFTWARE,
					 PERF_COUNT_SW_CPU_MIGRATIONS,
					 1, 1, NULL, 0);
		perf_unpin_context(ctx);
	}
}

#ifdef CONFIG_EVENT_PROFILE
void perf_tpcounter_event(int event_id)
{
	struct pt_regs *regs = get_irq_regs();

	if (!regs)
		regs = task_pt_regs(current);

	__perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs, 0);
}
EXPORT_SYMBOL_GPL(perf_tpcounter_event);

extern int ftrace_profile_enable(int);
extern void ftrace_profile_disable(int);

static void tp_perf_counter_destroy(struct perf_counter *counter)
{
	ftrace_profile_disable(perf_event_id(&counter->attr));
}

static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
{
	int event_id = perf_event_id(&counter->attr);
	int ret;

	ret = ftrace_profile_enable(event_id);
	if (ret)
		return NULL;

	counter->destroy = tp_perf_counter_destroy;

	return &perf_ops_generic;
}
#else
static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
{
	return NULL;
}
#endif

static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
{
	const struct pmu *pmu = NULL;

	/*
	 * Software counters (currently) can't in general distinguish
	 * between user, kernel and hypervisor events.
	 * However, context switches and cpu migrations are considered
	 * to be kernel events, and page faults are never hypervisor
	 * events.
	 */
	switch (counter->attr.config) {
	case PERF_COUNT_SW_CPU_CLOCK:
		pmu = &perf_ops_cpu_clock;

		break;
	case PERF_COUNT_SW_TASK_CLOCK:
		/*
		 * If the user instantiates this as a per-cpu counter,
		 * use the cpu_clock counter instead.
		 */
		if (counter->ctx->task)
			pmu = &perf_ops_task_clock;
		else
			pmu = &perf_ops_cpu_clock;

		break;
	case PERF_COUNT_SW_PAGE_FAULTS:
	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
	case PERF_COUNT_SW_CONTEXT_SWITCHES:
	case PERF_COUNT_SW_CPU_MIGRATIONS:
		pmu = &perf_ops_generic;
		break;
	}

	return pmu;
}

/*
 * Allocate and initialize a counter structure
 */
static struct perf_counter *
perf_counter_alloc(struct perf_counter_attr *attr,
		   int cpu,
		   struct perf_counter_context *ctx,
		   struct perf_counter *group_leader,
		   gfp_t gfpflags)
{
	const struct pmu *pmu;
	struct perf_counter *counter;
	struct hw_perf_counter *hwc;
	long err;

	counter = kzalloc(sizeof(*counter), gfpflags);
	if (!counter)
		return ERR_PTR(-ENOMEM);

	/*
	 * Single counters are their own group leaders, with an
	 * empty sibling list:
	 */
	if (!group_leader)
		group_leader = counter;

	mutex_init(&counter->child_mutex);
	INIT_LIST_HEAD(&counter->child_list);

	INIT_LIST_HEAD(&counter->list_entry);
	INIT_LIST_HEAD(&counter->event_entry);
	INIT_LIST_HEAD(&counter->sibling_list);
	init_waitqueue_head(&counter->waitq);

	mutex_init(&counter->mmap_mutex);

	counter->cpu		= cpu;
	counter->attr		= *attr;
	counter->group_leader	= group_leader;
	counter->pmu		= NULL;
	counter->ctx		= ctx;
	counter->oncpu		= -1;

	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
	counter->id		= atomic64_inc_return(&perf_counter_id);

	counter->state		= PERF_COUNTER_STATE_INACTIVE;

	if (attr->disabled)
		counter->state = PERF_COUNTER_STATE_OFF;

	pmu = NULL;

	hwc = &counter->hw;
	hwc->sample_period = attr->sample_period;
	if (attr->freq && attr->sample_freq)
		hwc->sample_period = 1;

	atomic64_set(&hwc->period_left, hwc->sample_period);

	/*
	 * we currently do not support PERF_SAMPLE_GROUP on inherited counters
	 */
	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
		goto done;

	switch (attr->type) {
	case PERF_TYPE_RAW:
	case PERF_TYPE_HARDWARE:
	case PERF_TYPE_HW_CACHE:
		pmu = hw_perf_counter_init(counter);
		break;

	case PERF_TYPE_SOFTWARE:
		pmu = sw_perf_counter_init(counter);
		break;

	case PERF_TYPE_TRACEPOINT:
		pmu = tp_perf_counter_init(counter);
		break;

	default:
		break;
	}
done:
	err = 0;
	if (!pmu)
		err = -EINVAL;
	else if (IS_ERR(pmu))
		err = PTR_ERR(pmu);

	if (err) {
		if (counter->ns)
			put_pid_ns(counter->ns);
		kfree(counter);
		return ERR_PTR(err);
	}

	counter->pmu = pmu;

	atomic_inc(&nr_counters);
	if (counter->attr.mmap)
		atomic_inc(&nr_mmap_counters);
	if (counter->attr.comm)
		atomic_inc(&nr_comm_counters);

	return counter;
}

static int perf_copy_attr(struct perf_counter_attr __user *uattr,
			  struct perf_counter_attr *attr)
{
	int ret;
	u32 size;

	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.
	 */
	if (size > sizeof(*attr)) {
		unsigned long val;
		unsigned long __user *addr;
		unsigned long __user *end;

		addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
				sizeof(unsigned long));
		end  = PTR_ALIGN((void __user *)uattr + size,
				sizeof(unsigned long));

		for (; addr < end; addr += sizeof(unsigned long)) {
			ret = get_user(val, addr);
			if (ret)
				return ret;
			if (val)
				goto err_size;
		}
	}

	ret = copy_from_user(attr, uattr, size);
	if (ret)
		return -EFAULT;

	/*
	 * If the type exists, the corresponding creation will verify
	 * the attr->config.
	 */
	if (attr->type >= PERF_TYPE_MAX)
		return -EINVAL;

	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
		return -EINVAL;

	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
		return -EINVAL;

	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
		return -EINVAL;

out:
	return ret;

err_size:
	put_user(sizeof(*attr), &uattr->size);
	ret = -E2BIG;
	goto out;
}

/**
 * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
 *
 * @attr_uptr:	event type attributes for monitoring/sampling
 * @pid:		target pid
 * @cpu:		target cpu
 * @group_fd:		group leader counter fd
 */
SYSCALL_DEFINE5(perf_counter_open,
		struct perf_counter_attr __user *, attr_uptr,
		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
{
	struct perf_counter *counter, *group_leader;
	struct perf_counter_attr attr;
	struct perf_counter_context *ctx;
	struct file *counter_file = NULL;
	struct file *group_file = NULL;
	int fput_needed = 0;
	int fput_needed2 = 0;
	int ret;

	/* for future expandability... */
	if (flags)
		return -EINVAL;

	ret = perf_copy_attr(attr_uptr, &attr);
	if (ret)
		return ret;

	if (!attr.exclude_kernel) {
		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
			return -EACCES;
	}

	if (attr.freq) {
		if (attr.sample_freq > sysctl_perf_counter_sample_rate)
			return -EINVAL;
	}

	/*
	 * Get the target context (task or percpu):
	 */
	ctx = find_get_context(pid, cpu);
	if (IS_ERR(ctx))
		return PTR_ERR(ctx);

	/*
	 * Look up the group leader (we will attach this counter to it):
	 */
	group_leader = NULL;
	if (group_fd != -1) {
		ret = -EINVAL;
		group_file = fget_light(group_fd, &fput_needed);
		if (!group_file)
			goto err_put_context;
		if (group_file->f_op != &perf_fops)
			goto err_put_context;

		group_leader = group_file->private_data;
		/*
		 * Do not allow a recursive hierarchy (this new sibling
		 * becoming part of another group-sibling):
		 */
		if (group_leader->group_leader != group_leader)
			goto err_put_context;
		/*
		 * Do not allow to attach to a group in a different
		 * task or CPU context:
		 */
		if (group_leader->ctx != ctx)
			goto err_put_context;
		/*
		 * Only a group leader can be exclusive or pinned
		 */
		if (attr.exclusive || attr.pinned)
			goto err_put_context;
	}

	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
				     GFP_KERNEL);
	ret = PTR_ERR(counter);
	if (IS_ERR(counter))
		goto err_put_context;

	ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
	if (ret < 0)
		goto err_free_put_context;

	counter_file = fget_light(ret, &fput_needed2);
	if (!counter_file)
		goto err_free_put_context;

	counter->filp = counter_file;
	WARN_ON_ONCE(ctx->parent_ctx);
	mutex_lock(&ctx->mutex);
	perf_install_in_context(ctx, counter, cpu);
	++ctx->generation;
	mutex_unlock(&ctx->mutex);

	counter->owner = current;
	get_task_struct(current);
	mutex_lock(&current->perf_counter_mutex);
	list_add_tail(&counter->owner_entry, &current->perf_counter_list);
	mutex_unlock(&current->perf_counter_mutex);

	fput_light(counter_file, fput_needed2);

out_fput:
	fput_light(group_file, fput_needed);

	return ret;

err_free_put_context:
	kfree(counter);

err_put_context:
	put_ctx(ctx);

	goto out_fput;
}

/*
 * inherit a counter from parent task to child task:
 */
static struct perf_counter *
inherit_counter(struct perf_counter *parent_counter,
	      struct task_struct *parent,
	      struct perf_counter_context *parent_ctx,
	      struct task_struct *child,
	      struct perf_counter *group_leader,
	      struct perf_counter_context *child_ctx)
{
	struct perf_counter *child_counter;

	/*
	 * Instead of creating recursive hierarchies of counters,
	 * we link inherited counters back to the original parent,
	 * which has a filp for sure, which we use as the reference
	 * count:
	 */
	if (parent_counter->parent)
		parent_counter = parent_counter->parent;

	child_counter = perf_counter_alloc(&parent_counter->attr,
					   parent_counter->cpu, child_ctx,
					   group_leader, GFP_KERNEL);
	if (IS_ERR(child_counter))
		return child_counter;
	get_ctx(child_ctx);

	/*
	 * Make the child state follow the state of the parent counter,
	 * not its attr.disabled bit.  We hold the parent's mutex,
	 * so we won't race with perf_counter_{en, dis}able_family.
	 */
	if (parent_counter->state >= PERF_COUNTER_STATE_INACTIVE)
		child_counter->state = PERF_COUNTER_STATE_INACTIVE;
	else
		child_counter->state = PERF_COUNTER_STATE_OFF;

	if (parent_counter->attr.freq)
		child_counter->hw.sample_period = parent_counter->hw.sample_period;

	/*
	 * Link it up in the child's context:
	 */
	add_counter_to_ctx(child_counter, child_ctx);

	child_counter->parent = parent_counter;
	/*
	 * inherit into child's child as well:
	 */
	child_counter->attr.inherit = 1;

	/*
	 * Get a reference to the parent filp - we will fput it
	 * when the child counter exits. This is safe to do because
	 * we are in the parent and we know that the filp still
	 * exists and has a nonzero count:
	 */
	atomic_long_inc(&parent_counter->filp->f_count);

	/*
	 * Link this into the parent counter's child list
	 */
	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
	mutex_lock(&parent_counter->child_mutex);
	list_add_tail(&child_counter->child_list, &parent_counter->child_list);
	mutex_unlock(&parent_counter->child_mutex);

	return child_counter;
}

static int inherit_group(struct perf_counter *parent_counter,
	      struct task_struct *parent,
	      struct perf_counter_context *parent_ctx,
	      struct task_struct *child,
	      struct perf_counter_context *child_ctx)
{
	struct perf_counter *leader;
	struct perf_counter *sub;
	struct perf_counter *child_ctr;

	leader = inherit_counter(parent_counter, parent, parent_ctx,
				 child, NULL, child_ctx);
	if (IS_ERR(leader))
		return PTR_ERR(leader);
	list_for_each_entry(sub, &parent_counter->sibling_list, list_entry) {
		child_ctr = inherit_counter(sub, parent, parent_ctx,
					    child, leader, child_ctx);
		if (IS_ERR(child_ctr))
			return PTR_ERR(child_ctr);
	}
	return 0;
}

static void sync_child_counter(struct perf_counter *child_counter,
			       struct perf_counter *parent_counter)
{
	u64 child_val;

	child_val = atomic64_read(&child_counter->count);

	/*
	 * Add back the child's count to the parent's count:
	 */
	atomic64_add(child_val, &parent_counter->count);
	atomic64_add(child_counter->total_time_enabled,
		     &parent_counter->child_total_time_enabled);
	atomic64_add(child_counter->total_time_running,
		     &parent_counter->child_total_time_running);

	/*
	 * Remove this counter from the parent's list
	 */
	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
	mutex_lock(&parent_counter->child_mutex);
	list_del_init(&child_counter->child_list);
	mutex_unlock(&parent_counter->child_mutex);

	/*
	 * Release the parent counter, if this was the last
	 * reference to it.
	 */
	fput(parent_counter->filp);
}

static void
__perf_counter_exit_task(struct perf_counter *child_counter,
			 struct perf_counter_context *child_ctx)
{
	struct perf_counter *parent_counter;

	update_counter_times(child_counter);
	perf_counter_remove_from_context(child_counter);

	parent_counter = child_counter->parent;
	/*
	 * It can happen that parent exits first, and has counters
	 * that are still around due to the child reference. These
	 * counters need to be zapped - but otherwise linger.
	 */
	if (parent_counter) {
		sync_child_counter(child_counter, parent_counter);
		free_counter(child_counter);
	}
}

/*
 * When a child task exits, feed back counter values to parent counters.
 */
void perf_counter_exit_task(struct task_struct *child)
{
	struct perf_counter *child_counter, *tmp;
	struct perf_counter_context *child_ctx;
	unsigned long flags;

	if (likely(!child->perf_counter_ctxp))
		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 = child->perf_counter_ctxp;
	__perf_counter_task_sched_out(child_ctx);

	/*
	 * Take the context lock here so that if find_get_context is
	 * reading child->perf_counter_ctxp, we wait until it has
	 * incremented the context's refcount before we do put_ctx below.
	 */
	spin_lock(&child_ctx->lock);
	child->perf_counter_ctxp = NULL;
	if (child_ctx->parent_ctx) {
		/*
		 * This context is a clone; unclone it so it can't get
		 * swapped to another process while we're removing all
		 * the counters from it.
		 */
		put_ctx(child_ctx->parent_ctx);
		child_ctx->parent_ctx = NULL;
	}
	spin_unlock(&child_ctx->lock);
	local_irq_restore(flags);

	/*
	 * We can recurse on the same lock type through:
	 *
	 *   __perf_counter_exit_task()
	 *     sync_child_counter()
	 *       fput(parent_counter->filp)
	 *         perf_release()
	 *           mutex_lock(&ctx->mutex)
	 *
	 * But since its the parent context it won't be the same instance.
	 */
	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);

again:
	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
				 list_entry)
		__perf_counter_exit_task(child_counter, child_ctx);

	/*
	 * If the last counter was a group counter, 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->counter_list))
		goto again;

	mutex_unlock(&child_ctx->mutex);

	put_ctx(child_ctx);
}

/*
 * free an unexposed, unused context as created by inheritance by
 * init_task below, used by fork() in case of fail.
 */
void perf_counter_free_task(struct task_struct *task)
{
	struct perf_counter_context *ctx = task->perf_counter_ctxp;
	struct perf_counter *counter, *tmp;

	if (!ctx)
		return;

	mutex_lock(&ctx->mutex);
again:
	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry) {
		struct perf_counter *parent = counter->parent;

		if (WARN_ON_ONCE(!parent))
			continue;

		mutex_lock(&parent->child_mutex);
		list_del_init(&counter->child_list);
		mutex_unlock(&parent->child_mutex);

		fput(parent->filp);

		list_del_counter(counter, ctx);
		free_counter(counter);
	}

	if (!list_empty(&ctx->counter_list))
		goto again;

	mutex_unlock(&ctx->mutex);

	put_ctx(ctx);
}

/*
 * Initialize the perf_counter context in task_struct
 */
int perf_counter_init_task(struct task_struct *child)
{
	struct perf_counter_context *child_ctx, *parent_ctx;
	struct perf_counter_context *cloned_ctx;
	struct perf_counter *counter;
	struct task_struct *parent = current;
	int inherited_all = 1;
	int ret = 0;

	child->perf_counter_ctxp = NULL;

	mutex_init(&child->perf_counter_mutex);
	INIT_LIST_HEAD(&child->perf_counter_list);

	if (likely(!parent->perf_counter_ctxp))
		return 0;

	/*
	 * This is executed from the parent task context, so inherit
	 * counters that have been marked for cloning.
	 * First allocate and initialize a context for the child.
	 */

	child_ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
	if (!child_ctx)
		return -ENOMEM;

	__perf_counter_init_context(child_ctx, child);
	child->perf_counter_ctxp = child_ctx;
	get_task_struct(child);

	/*
	 * 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);

	/*
	 * 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_rcu(counter, &parent_ctx->event_list, event_entry) {
		if (counter != counter->group_leader)
			continue;

		if (!counter->attr.inherit) {
			inherited_all = 0;
			continue;
		}

		ret = inherit_group(counter, parent, parent_ctx,
					     child, child_ctx);
		if (ret) {
			inherited_all = 0;
			break;
		}
	}

	if (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, it could get
		 * uncloned at any point, but that doesn't matter
		 * because the list of counters and the generation
		 * count can't have changed since we took the mutex.
		 */
		cloned_ctx = rcu_dereference(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);
	}

	mutex_unlock(&parent_ctx->mutex);

	perf_unpin_context(parent_ctx);

	return ret;
}

static void __cpuinit perf_counter_init_cpu(int cpu)
{
	struct perf_cpu_context *cpuctx;

	cpuctx = &per_cpu(perf_cpu_context, cpu);
	__perf_counter_init_context(&cpuctx->ctx, NULL);

	spin_lock(&perf_resource_lock);
	cpuctx->max_pertask = perf_max_counters - perf_reserved_percpu;
	spin_unlock(&perf_resource_lock);

	hw_perf_counter_setup(cpu);
}

#ifdef CONFIG_HOTPLUG_CPU
static void __perf_counter_exit_cpu(void *info)
{
	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
	struct perf_counter_context *ctx = &cpuctx->ctx;
	struct perf_counter *counter, *tmp;

	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry)
		__perf_counter_remove_from_context(counter);
}
static void perf_counter_exit_cpu(int cpu)
{
	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
	struct perf_counter_context *ctx = &cpuctx->ctx;

	mutex_lock(&ctx->mutex);
	smp_call_function_single(cpu, __perf_counter_exit_cpu, NULL, 1);
	mutex_unlock(&ctx->mutex);
}
#else
static inline void perf_counter_exit_cpu(int cpu) { }
#endif

static int __cpuinit
perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
{
	unsigned int cpu = (long)hcpu;

	switch (action) {

	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		perf_counter_init_cpu(cpu);
		break;

	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		perf_counter_exit_cpu(cpu);
		break;

	default:
		break;
	}

	return NOTIFY_OK;
}

/*
 * This has to have a higher priority than migration_notifier in sched.c.
 */
static struct notifier_block __cpuinitdata perf_cpu_nb = {
	.notifier_call		= perf_cpu_notify,
	.priority		= 20,
};

void __init perf_counter_init(void)
{
	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
			(void *)(long)smp_processor_id());
	register_cpu_notifier(&perf_cpu_nb);
}

static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf)
{
	return sprintf(buf, "%d\n", perf_reserved_percpu);
}

static ssize_t
perf_set_reserve_percpu(struct sysdev_class *class,
			const char *buf,
			size_t count)
{
	struct perf_cpu_context *cpuctx;
	unsigned long val;
	int err, cpu, mpt;

	err = strict_strtoul(buf, 10, &val);
	if (err)
		return err;
	if (val > perf_max_counters)
		return -EINVAL;

	spin_lock(&perf_resource_lock);
	perf_reserved_percpu = val;
	for_each_online_cpu(cpu) {
		cpuctx = &per_cpu(perf_cpu_context, cpu);
		spin_lock_irq(&cpuctx->ctx.lock);
		mpt = min(perf_max_counters - cpuctx->ctx.nr_counters,
			  perf_max_counters - perf_reserved_percpu);
		cpuctx->max_pertask = mpt;
		spin_unlock_irq(&cpuctx->ctx.lock);
	}
	spin_unlock(&perf_resource_lock);

	return count;
}

static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf)
{
	return sprintf(buf, "%d\n", perf_overcommit);
}

static ssize_t
perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count)
{
	unsigned long val;
	int err;

	err = strict_strtoul(buf, 10, &val);
	if (err)
		return err;
	if (val > 1)
		return -EINVAL;

	spin_lock(&perf_resource_lock);
	perf_overcommit = val;
	spin_unlock(&perf_resource_lock);

	return count;
}

static SYSDEV_CLASS_ATTR(
				reserve_percpu,
				0644,
				perf_show_reserve_percpu,
				perf_set_reserve_percpu
			);

static SYSDEV_CLASS_ATTR(
				overcommit,
				0644,
				perf_show_overcommit,
				perf_set_overcommit
			);

static struct attribute *perfclass_attrs[] = {
	&attr_reserve_percpu.attr,
	&attr_overcommit.attr,
	NULL
};

static struct attribute_group perfclass_attr_group = {
	.attrs			= perfclass_attrs,
	.name			= "perf_counters",
};

static int __init perf_counter_sysfs_init(void)
{
	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
				  &perfclass_attr_group);
}
device_initcall(perf_counter_sysfs_init);