Eric Lee / smarc-fsl-linux-kernel

verifier.c 185 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016 Facebook
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>

#include "disasm.h"

static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#define BPF_PROG_TYPE(_id, _name) \
	[_id] = & _name ## _verifier_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};

/* bpf_check() is a static code analyzer that walks eBPF program
 * instruction by instruction and updates register/stack state.
 * All paths of conditional branches are analyzed until 'bpf_exit' insn.
 *
 * The first pass is depth-first-search to check that the program is a DAG.
 * It rejects the following programs:
 * - larger than BPF_MAXINSNS insns
 * - if loop is present (detected via back-edge)
 * - unreachable insns exist (shouldn't be a forest. program = one function)
 * - out of bounds or malformed jumps
 * The second pass is all possible path descent from the 1st insn.
 * Since it's analyzing all pathes through the program, the length of the
 * analysis is limited to 64k insn, which may be hit even if total number of
 * insn is less then 4K, but there are too many branches that change stack/regs.
 * Number of 'branches to be analyzed' is limited to 1k
 *
 * On entry to each instruction, each register has a type, and the instruction
 * changes the types of the registers depending on instruction semantics.
 * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
 * copied to R1.
 *
 * All registers are 64-bit.
 * R0 - return register
 * R1-R5 argument passing registers
 * R6-R9 callee saved registers
 * R10 - frame pointer read-only
 *
 * At the start of BPF program the register R1 contains a pointer to bpf_context
 * and has type PTR_TO_CTX.
 *
 * Verifier tracks arithmetic operations on pointers in case:
 *    BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
 * 1st insn copies R10 (which has FRAME_PTR) type into R1
 * and 2nd arithmetic instruction is pattern matched to recognize
 * that it wants to construct a pointer to some element within stack.
 * So after 2nd insn, the register R1 has type PTR_TO_STACK
 * (and -20 constant is saved for further stack bounds checking).
 * Meaning that this reg is a pointer to stack plus known immediate constant.
 *
 * Most of the time the registers have SCALAR_VALUE type, which
 * means the register has some value, but it's not a valid pointer.
 * (like pointer plus pointer becomes SCALAR_VALUE type)
 *
 * When verifier sees load or store instructions the type of base register
 * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer
 * types recognized by check_mem_access() function.
 *
 * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
 * and the range of [ptr, ptr + map's value_size) is accessible.
 *
 * registers used to pass values to function calls are checked against
 * function argument constraints.
 *
 * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
 * It means that the register type passed to this function must be
 * PTR_TO_STACK and it will be used inside the function as
 * 'pointer to map element key'
 *
 * For example the argument constraints for bpf_map_lookup_elem():
 *   .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 *   .arg1_type = ARG_CONST_MAP_PTR,
 *   .arg2_type = ARG_PTR_TO_MAP_KEY,
 *
 * ret_type says that this function returns 'pointer to map elem value or null'
 * function expects 1st argument to be a const pointer to 'struct bpf_map' and
 * 2nd argument should be a pointer to stack, which will be used inside
 * the helper function as a pointer to map element key.
 *
 * On the kernel side the helper function looks like:
 * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 * {
 *    struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 *    void *key = (void *) (unsigned long) r2;
 *    void *value;
 *
 *    here kernel can access 'key' and 'map' pointers safely, knowing that
 *    [key, key + map->key_size) bytes are valid and were initialized on
 *    the stack of eBPF program.
 * }
 *
 * Corresponding eBPF program may look like:
 *    BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),  // after this insn R2 type is FRAME_PTR
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
 *    BPF_LD_MAP_FD(BPF_REG_1, map_fd),      // after this insn R1 type is CONST_PTR_TO_MAP
 *    BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 * here verifier looks at prototype of map_lookup_elem() and sees:
 * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
 * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
 *
 * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
 * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
 * and were initialized prior to this call.
 * If it's ok, then verifier allows this BPF_CALL insn and looks at
 * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
 * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
 * returns ether pointer to map value or NULL.
 *
 * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
 * insn, the register holding that pointer in the true branch changes state to
 * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
 * branch. See check_cond_jmp_op().
 *
 * After the call R0 is set to return type of the function and registers R1-R5
 * are set to NOT_INIT to indicate that they are no longer readable.
 */

/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
	/* verifer state is 'st'
	 * before processing instruction 'insn_idx'
	 * and after processing instruction 'prev_insn_idx'
	 */
	struct bpf_verifier_state st;
	int insn_idx;
	int prev_insn_idx;
	struct bpf_verifier_stack_elem *next;
};

#define BPF_COMPLEXITY_LIMIT_INSNS	131072
#define BPF_COMPLEXITY_LIMIT_STACK	1024
#define BPF_COMPLEXITY_LIMIT_STATES	64

#define BPF_MAP_PTR_UNPRIV	1UL
#define BPF_MAP_PTR_POISON	((void *)((0xeB9FUL << 1) +	\
					  POISON_POINTER_DELTA))
#define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))

static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
	return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
}

static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
{
	return aux->map_state & BPF_MAP_PTR_UNPRIV;
}

static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
			      const struct bpf_map *map, bool unpriv)
{
	BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
	unpriv |= bpf_map_ptr_unpriv(aux);
	aux->map_state = (unsigned long)map |
			 (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
}

struct bpf_call_arg_meta {
	struct bpf_map *map_ptr;
	bool raw_mode;
	bool pkt_access;
	int regno;
	int access_size;
	s64 msize_smax_value;
	u64 msize_umax_value;
};

static DEFINE_MUTEX(bpf_verifier_lock);

void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
		       va_list args)
{
	unsigned int n;

	n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);

	WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
		  "verifier log line truncated - local buffer too short\n");

	n = min(log->len_total - log->len_used - 1, n);
	log->kbuf[n] = '\0';

	if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
		log->len_used += n;
	else
		log->ubuf = NULL;
}

/* log_level controls verbosity level of eBPF verifier.
 * bpf_verifier_log_write() is used to dump the verification trace to the log,
 * so the user can figure out what's wrong with the program
 */
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
					   const char *fmt, ...)
{
	va_list args;

	if (!bpf_verifier_log_needed(&env->log))
		return;

	va_start(args, fmt);
	bpf_verifier_vlog(&env->log, fmt, args);
	va_end(args);
}
EXPORT_SYMBOL_GPL(bpf_verifier_log_write);

__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
{
	struct bpf_verifier_env *env = private_data;
	va_list args;

	if (!bpf_verifier_log_needed(&env->log))
		return;

	va_start(args, fmt);
	bpf_verifier_vlog(&env->log, fmt, args);
	va_end(args);
}

static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
	return type == PTR_TO_PACKET ||
	       type == PTR_TO_PACKET_META;
}

/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
	[NOT_INIT]		= "?",
	[SCALAR_VALUE]		= "inv",
	[PTR_TO_CTX]		= "ctx",
	[CONST_PTR_TO_MAP]	= "map_ptr",
	[PTR_TO_MAP_VALUE]	= "map_value",
	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
	[PTR_TO_STACK]		= "fp",
	[PTR_TO_PACKET]		= "pkt",
	[PTR_TO_PACKET_META]	= "pkt_meta",
	[PTR_TO_PACKET_END]	= "pkt_end",
};

static void print_liveness(struct bpf_verifier_env *env,
			   enum bpf_reg_liveness live)
{
	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
	    verbose(env, "_");
	if (live & REG_LIVE_READ)
		verbose(env, "r");
	if (live & REG_LIVE_WRITTEN)
		verbose(env, "w");
}

static struct bpf_func_state *func(struct bpf_verifier_env *env,
				   const struct bpf_reg_state *reg)
{
	struct bpf_verifier_state *cur = env->cur_state;

	return cur->frame[reg->frameno];
}

static void print_verifier_state(struct bpf_verifier_env *env,
				 const struct bpf_func_state *state)
{
	const struct bpf_reg_state *reg;
	enum bpf_reg_type t;
	int i;

	if (state->frameno)
		verbose(env, " frame%d:", state->frameno);
	for (i = 0; i < MAX_BPF_REG; i++) {
		reg = &state->regs[i];
		t = reg->type;
		if (t == NOT_INIT)
			continue;
		verbose(env, " R%d", i);
		print_liveness(env, reg->live);
		verbose(env, "=%s", reg_type_str[t]);
		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
		    tnum_is_const(reg->var_off)) {
			/* reg->off should be 0 for SCALAR_VALUE */
			verbose(env, "%lld", reg->var_off.value + reg->off);
			if (t == PTR_TO_STACK)
				verbose(env, ",call_%d", func(env, reg)->callsite);
		} else {
			verbose(env, "(id=%d", reg->id);
			if (t != SCALAR_VALUE)
				verbose(env, ",off=%d", reg->off);
			if (type_is_pkt_pointer(t))
				verbose(env, ",r=%d", reg->range);
			else if (t == CONST_PTR_TO_MAP ||
				 t == PTR_TO_MAP_VALUE ||
				 t == PTR_TO_MAP_VALUE_OR_NULL)
				verbose(env, ",ks=%d,vs=%d",
					reg->map_ptr->key_size,
					reg->map_ptr->value_size);
			if (tnum_is_const(reg->var_off)) {
				/* Typically an immediate SCALAR_VALUE, but
				 * could be a pointer whose offset is too big
				 * for reg->off
				 */
				verbose(env, ",imm=%llx", reg->var_off.value);
			} else {
				if (reg->smin_value != reg->umin_value &&
				    reg->smin_value != S64_MIN)
					verbose(env, ",smin_value=%lld",
						(long long)reg->smin_value);
				if (reg->smax_value != reg->umax_value &&
				    reg->smax_value != S64_MAX)
					verbose(env, ",smax_value=%lld",
						(long long)reg->smax_value);
				if (reg->umin_value != 0)
					verbose(env, ",umin_value=%llu",
						(unsigned long long)reg->umin_value);
				if (reg->umax_value != U64_MAX)
					verbose(env, ",umax_value=%llu",
						(unsigned long long)reg->umax_value);
				if (!tnum_is_unknown(reg->var_off)) {
					char tn_buf[48];

					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
					verbose(env, ",var_off=%s", tn_buf);
				}
			}
			verbose(env, ")");
		}
	}
	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
		if (state->stack[i].slot_type[0] == STACK_SPILL) {
			verbose(env, " fp%d",
				(-i - 1) * BPF_REG_SIZE);
			print_liveness(env, state->stack[i].spilled_ptr.live);
			verbose(env, "=%s",
				reg_type_str[state->stack[i].spilled_ptr.type]);
		}
		if (state->stack[i].slot_type[0] == STACK_ZERO)
			verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
	}
	verbose(env, "\n");
}

static int copy_stack_state(struct bpf_func_state *dst,
			    const struct bpf_func_state *src)
{
	if (!src->stack)
		return 0;
	if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
		/* internal bug, make state invalid to reject the program */
		memset(dst, 0, sizeof(*dst));
		return -EFAULT;
	}
	memcpy(dst->stack, src->stack,
	       sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
	return 0;
}

/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
 * make it consume minimal amount of memory. check_stack_write() access from
 * the program calls into realloc_func_state() to grow the stack size.
 * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
 * which this function copies over. It points to previous bpf_verifier_state
 * which is never reallocated
 */
static int realloc_func_state(struct bpf_func_state *state, int size,
			      bool copy_old)
{
	u32 old_size = state->allocated_stack;
	struct bpf_stack_state *new_stack;
	int slot = size / BPF_REG_SIZE;

	if (size <= old_size || !size) {
		if (copy_old)
			return 0;
		state->allocated_stack = slot * BPF_REG_SIZE;
		if (!size && old_size) {
			kfree(state->stack);
			state->stack = NULL;
		}
		return 0;
	}
	new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
				  GFP_KERNEL);
	if (!new_stack)
		return -ENOMEM;
	if (copy_old) {
		if (state->stack)
			memcpy(new_stack, state->stack,
			       sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
		memset(new_stack + old_size / BPF_REG_SIZE, 0,
		       sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
	}
	state->allocated_stack = slot * BPF_REG_SIZE;
	kfree(state->stack);
	state->stack = new_stack;
	return 0;
}

static void free_func_state(struct bpf_func_state *state)
{
	if (!state)
		return;
	kfree(state->stack);
	kfree(state);
}

static void free_verifier_state(struct bpf_verifier_state *state,
				bool free_self)
{
	int i;

	for (i = 0; i <= state->curframe; i++) {
		free_func_state(state->frame[i]);
		state->frame[i] = NULL;
	}
	if (free_self)
		kfree(state);
}

/* copy verifier state from src to dst growing dst stack space
 * when necessary to accommodate larger src stack
 */
static int copy_func_state(struct bpf_func_state *dst,
			   const struct bpf_func_state *src)
{
	int err;

	err = realloc_func_state(dst, src->allocated_stack, false);
	if (err)
		return err;
	memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
	return copy_stack_state(dst, src);
}

static int copy_verifier_state(struct bpf_verifier_state *dst_state,
			       const struct bpf_verifier_state *src)
{
	struct bpf_func_state *dst;
	int i, err;

	/* if dst has more stack frames then src frame, free them */
	for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
		free_func_state(dst_state->frame[i]);
		dst_state->frame[i] = NULL;
	}
	dst_state->speculative = src->speculative;
	dst_state->curframe = src->curframe;
	dst_state->parent = src->parent;
	for (i = 0; i <= src->curframe; i++) {
		dst = dst_state->frame[i];
		if (!dst) {
			dst = kzalloc(sizeof(*dst), GFP_KERNEL);
			if (!dst)
				return -ENOMEM;
			dst_state->frame[i] = dst;
		}
		err = copy_func_state(dst, src->frame[i]);
		if (err)
			return err;
	}
	return 0;
}

static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
		     int *insn_idx)
{
	struct bpf_verifier_state *cur = env->cur_state;
	struct bpf_verifier_stack_elem *elem, *head = env->head;
	int err;

	if (env->head == NULL)
		return -ENOENT;

	if (cur) {
		err = copy_verifier_state(cur, &head->st);
		if (err)
			return err;
	}
	if (insn_idx)
		*insn_idx = head->insn_idx;
	if (prev_insn_idx)
		*prev_insn_idx = head->prev_insn_idx;
	elem = head->next;
	free_verifier_state(&head->st, false);
	kfree(head);
	env->head = elem;
	env->stack_size--;
	return 0;
}

static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
					     int insn_idx, int prev_insn_idx,
					     bool speculative)
{
	struct bpf_verifier_state *cur = env->cur_state;
	struct bpf_verifier_stack_elem *elem;
	int err;

	elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
	if (!elem)
		goto err;

	elem->insn_idx = insn_idx;
	elem->prev_insn_idx = prev_insn_idx;
	elem->next = env->head;
	env->head = elem;
	env->stack_size++;
	err = copy_verifier_state(&elem->st, cur);
	if (err)
		goto err;
	elem->st.speculative |= speculative;
	if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
		verbose(env, "BPF program is too complex\n");
		goto err;
	}
	return &elem->st;
err:
	free_verifier_state(env->cur_state, true);
	env->cur_state = NULL;
	/* pop all elements and return */
	while (!pop_stack(env, NULL, NULL));
	return NULL;
}

#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};

static void __mark_reg_not_init(struct bpf_reg_state *reg);

/* Mark the unknown part of a register (variable offset or scalar value) as
 * known to have the value @imm.
 */
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
	/* Clear id, off, and union(map_ptr, range) */
	memset(((u8 *)reg) + sizeof(reg->type), 0,
	       offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
	reg->var_off = tnum_const(imm);
	reg->smin_value = (s64)imm;
	reg->smax_value = (s64)imm;
	reg->umin_value = imm;
	reg->umax_value = imm;
}

/* Mark the 'variable offset' part of a register as zero.  This should be
 * used only on registers holding a pointer type.
 */
static void __mark_reg_known_zero(struct bpf_reg_state *reg)
{
	__mark_reg_known(reg, 0);
}

static void __mark_reg_const_zero(struct bpf_reg_state *reg)
{
	__mark_reg_known(reg, 0);
	reg->type = SCALAR_VALUE;
}

static void mark_reg_known_zero(struct bpf_verifier_env *env,
				struct bpf_reg_state *regs, u32 regno)
{
	if (WARN_ON(regno >= MAX_BPF_REG)) {
		verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
		/* Something bad happened, let's kill all regs */
		for (regno = 0; regno < MAX_BPF_REG; regno++)
			__mark_reg_not_init(regs + regno);
		return;
	}
	__mark_reg_known_zero(regs + regno);
}

static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
{
	return type_is_pkt_pointer(reg->type);
}

static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
{
	return reg_is_pkt_pointer(reg) ||
	       reg->type == PTR_TO_PACKET_END;
}

/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
				    enum bpf_reg_type which)
{
	/* The register can already have a range from prior markings.
	 * This is fine as long as it hasn't been advanced from its
	 * origin.
	 */
	return reg->type == which &&
	       reg->id == 0 &&
	       reg->off == 0 &&
	       tnum_equals_const(reg->var_off, 0);
}

/* Attempts to improve min/max values based on var_off information */
static void __update_reg_bounds(struct bpf_reg_state *reg)
{
	/* min signed is max(sign bit) | min(other bits) */
	reg->smin_value = max_t(s64, reg->smin_value,
				reg->var_off.value | (reg->var_off.mask & S64_MIN));
	/* max signed is min(sign bit) | max(other bits) */
	reg->smax_value = min_t(s64, reg->smax_value,
				reg->var_off.value | (reg->var_off.mask & S64_MAX));
	reg->umin_value = max(reg->umin_value, reg->var_off.value);
	reg->umax_value = min(reg->umax_value,
			      reg->var_off.value | reg->var_off.mask);
}

/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
	/* Learn sign from signed bounds.
	 * If we cannot cross the sign boundary, then signed and unsigned bounds
	 * are the same, so combine.  This works even in the negative case, e.g.
	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
	 */
	if (reg->smin_value >= 0 || reg->smax_value < 0) {
		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
							  reg->umin_value);
		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
							  reg->umax_value);
		return;
	}
	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
	 * boundary, so we must be careful.
	 */
	if ((s64)reg->umax_value >= 0) {
		/* Positive.  We can't learn anything from the smin, but smax
		 * is positive, hence safe.
		 */
		reg->smin_value = reg->umin_value;
		reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
							  reg->umax_value);
	} else if ((s64)reg->umin_value < 0) {
		/* Negative.  We can't learn anything from the smax, but smin
		 * is negative, hence safe.
		 */
		reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
							  reg->umin_value);
		reg->smax_value = reg->umax_value;
	}
}

/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
	reg->var_off = tnum_intersect(reg->var_off,
				      tnum_range(reg->umin_value,
						 reg->umax_value));
}

/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
	reg->smin_value = S64_MIN;
	reg->smax_value = S64_MAX;
	reg->umin_value = 0;
	reg->umax_value = U64_MAX;
}

/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(struct bpf_reg_state *reg)
{
	/*
	 * Clear type, id, off, and union(map_ptr, range) and
	 * padding between 'type' and union
	 */
	memset(reg, 0, offsetof(struct bpf_reg_state, var_off));
	reg->type = SCALAR_VALUE;
	reg->var_off = tnum_unknown;
	reg->frameno = 0;
	__mark_reg_unbounded(reg);
}

static void mark_reg_unknown(struct bpf_verifier_env *env,
			     struct bpf_reg_state *regs, u32 regno)
{
	if (WARN_ON(regno >= MAX_BPF_REG)) {
		verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
		/* Something bad happened, let's kill all regs except FP */
		for (regno = 0; regno < BPF_REG_FP; regno++)
			__mark_reg_not_init(regs + regno);
		return;
	}
	__mark_reg_unknown(regs + regno);
}

static void __mark_reg_not_init(struct bpf_reg_state *reg)
{
	__mark_reg_unknown(reg);
	reg->type = NOT_INIT;
}

static void mark_reg_not_init(struct bpf_verifier_env *env,
			      struct bpf_reg_state *regs, u32 regno)
{
	if (WARN_ON(regno >= MAX_BPF_REG)) {
		verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
		/* Something bad happened, let's kill all regs except FP */
		for (regno = 0; regno < BPF_REG_FP; regno++)
			__mark_reg_not_init(regs + regno);
		return;
	}
	__mark_reg_not_init(regs + regno);
}

static void init_reg_state(struct bpf_verifier_env *env,
			   struct bpf_func_state *state)
{
	struct bpf_reg_state *regs = state->regs;
	int i;

	for (i = 0; i < MAX_BPF_REG; i++) {
		mark_reg_not_init(env, regs, i);
		regs[i].live = REG_LIVE_NONE;
	}

	/* frame pointer */
	regs[BPF_REG_FP].type = PTR_TO_STACK;
	mark_reg_known_zero(env, regs, BPF_REG_FP);
	regs[BPF_REG_FP].frameno = state->frameno;

	/* 1st arg to a function */
	regs[BPF_REG_1].type = PTR_TO_CTX;
	mark_reg_known_zero(env, regs, BPF_REG_1);
}

#define BPF_MAIN_FUNC (-1)
static void init_func_state(struct bpf_verifier_env *env,
			    struct bpf_func_state *state,
			    int callsite, int frameno, int subprogno)
{
	state->callsite = callsite;
	state->frameno = frameno;
	state->subprogno = subprogno;
	init_reg_state(env, state);
}

enum reg_arg_type {
	SRC_OP,		/* register is used as source operand */
	DST_OP,		/* register is used as destination operand */
	DST_OP_NO_MARK	/* same as above, check only, don't mark */
};

static int cmp_subprogs(const void *a, const void *b)
{
	return ((struct bpf_subprog_info *)a)->start -
	       ((struct bpf_subprog_info *)b)->start;
}

static int find_subprog(struct bpf_verifier_env *env, int off)
{
	struct bpf_subprog_info *p;

	p = bsearch(&off, env->subprog_info, env->subprog_cnt,
		    sizeof(env->subprog_info[0]), cmp_subprogs);
	if (!p)
		return -ENOENT;
	return p - env->subprog_info;

}

static int add_subprog(struct bpf_verifier_env *env, int off)
{
	int insn_cnt = env->prog->len;
	int ret;

	if (off >= insn_cnt || off < 0) {
		verbose(env, "call to invalid destination\n");
		return -EINVAL;
	}
	ret = find_subprog(env, off);
	if (ret >= 0)
		return 0;
	if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
		verbose(env, "too many subprograms\n");
		return -E2BIG;
	}
	env->subprog_info[env->subprog_cnt++].start = off;
	sort(env->subprog_info, env->subprog_cnt,
	     sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
	return 0;
}

static int check_subprogs(struct bpf_verifier_env *env)
{
	int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
	struct bpf_subprog_info *subprog = env->subprog_info;
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;

	/* Add entry function. */
	ret = add_subprog(env, 0);
	if (ret < 0)
		return ret;

	/* determine subprog starts. The end is one before the next starts */
	for (i = 0; i < insn_cnt; i++) {
		if (insn[i].code != (BPF_JMP | BPF_CALL))
			continue;
		if (insn[i].src_reg != BPF_PSEUDO_CALL)
			continue;
		if (!env->allow_ptr_leaks) {
			verbose(env, "function calls to other bpf functions are allowed for root only\n");
			return -EPERM;
		}
		if (bpf_prog_is_dev_bound(env->prog->aux)) {
			verbose(env, "function calls in offloaded programs are not supported yet\n");
			return -EINVAL;
		}
		ret = add_subprog(env, i + insn[i].imm + 1);
		if (ret < 0)
			return ret;
	}

	/* Add a fake 'exit' subprog which could simplify subprog iteration
	 * logic. 'subprog_cnt' should not be increased.
	 */
	subprog[env->subprog_cnt].start = insn_cnt;

	if (env->log.level > 1)
		for (i = 0; i < env->subprog_cnt; i++)
			verbose(env, "func#%d @%d\n", i, subprog[i].start);

	/* now check that all jumps are within the same subprog */
	subprog_start = subprog[cur_subprog].start;
	subprog_end = subprog[cur_subprog + 1].start;
	for (i = 0; i < insn_cnt; i++) {
		u8 code = insn[i].code;

		if (BPF_CLASS(code) != BPF_JMP)
			goto next;
		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
			goto next;
		off = i + insn[i].off + 1;
		if (off < subprog_start || off >= subprog_end) {
			verbose(env, "jump out of range from insn %d to %d\n", i, off);
			return -EINVAL;
		}
next:
		if (i == subprog_end - 1) {
			/* to avoid fall-through from one subprog into another
			 * the last insn of the subprog should be either exit
			 * or unconditional jump back
			 */
			if (code != (BPF_JMP | BPF_EXIT) &&
			    code != (BPF_JMP | BPF_JA)) {
				verbose(env, "last insn is not an exit or jmp\n");
				return -EINVAL;
			}
			subprog_start = subprog_end;
			cur_subprog++;
			if (cur_subprog < env->subprog_cnt)
				subprog_end = subprog[cur_subprog + 1].start;
		}
	}
	return 0;
}

static
struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
				       const struct bpf_verifier_state *state,
				       struct bpf_verifier_state *parent,
				       u32 regno)
{
	struct bpf_verifier_state *tmp = NULL;

	/* 'parent' could be a state of caller and
	 * 'state' could be a state of callee. In such case
	 * parent->curframe < state->curframe
	 * and it's ok for r1 - r5 registers
	 *
	 * 'parent' could be a callee's state after it bpf_exit-ed.
	 * In such case parent->curframe > state->curframe
	 * and it's ok for r0 only
	 */
	if (parent->curframe == state->curframe ||
	    (parent->curframe < state->curframe &&
	     regno >= BPF_REG_1 && regno <= BPF_REG_5) ||
	    (parent->curframe > state->curframe &&
	       regno == BPF_REG_0))
		return parent;

	if (parent->curframe > state->curframe &&
	    regno >= BPF_REG_6) {
		/* for callee saved regs we have to skip the whole chain
		 * of states that belong to callee and mark as LIVE_READ
		 * the registers before the call
		 */
		tmp = parent;
		while (tmp && tmp->curframe != state->curframe) {
			tmp = tmp->parent;
		}
		if (!tmp)
			goto bug;
		parent = tmp;
	} else {
		goto bug;
	}
	return parent;
bug:
	verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
	verbose(env, "regno %d parent frame %d current frame %d\n",
		regno, parent->curframe, state->curframe);
	return NULL;
}

static int mark_reg_read(struct bpf_verifier_env *env,
			 const struct bpf_verifier_state *state,
			 struct bpf_verifier_state *parent,
			 u32 regno)
{
	bool writes = parent == state->parent; /* Observe write marks */

	if (regno == BPF_REG_FP)
		/* We don't need to worry about FP liveness because it's read-only */
		return 0;

	while (parent) {
		/* if read wasn't screened by an earlier write ... */
		if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN)
			break;
		parent = skip_callee(env, state, parent, regno);
		if (!parent)
			return -EFAULT;
		/* ... then we depend on parent's value */
		parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ;
		state = parent;
		parent = state->parent;
		writes = true;
	}
	return 0;
}

static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
			 enum reg_arg_type t)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs;

	if (regno >= MAX_BPF_REG) {
		verbose(env, "R%d is invalid\n", regno);
		return -EINVAL;
	}

	if (t == SRC_OP) {
		/* check whether register used as source operand can be read */
		if (regs[regno].type == NOT_INIT) {
			verbose(env, "R%d !read_ok\n", regno);
			return -EACCES;
		}
		return mark_reg_read(env, vstate, vstate->parent, regno);
	} else {
		/* check whether register used as dest operand can be written to */
		if (regno == BPF_REG_FP) {
			verbose(env, "frame pointer is read only\n");
			return -EACCES;
		}
		regs[regno].live |= REG_LIVE_WRITTEN;
		if (t == DST_OP)
			mark_reg_unknown(env, regs, regno);
	}
	return 0;
}

static bool is_spillable_regtype(enum bpf_reg_type type)
{
	switch (type) {
	case PTR_TO_MAP_VALUE:
	case PTR_TO_MAP_VALUE_OR_NULL:
	case PTR_TO_STACK:
	case PTR_TO_CTX:
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
	case PTR_TO_PACKET_END:
	case CONST_PTR_TO_MAP:
		return true;
	default:
		return false;
	}
}

/* Does this register contain a constant zero? */
static bool register_is_null(struct bpf_reg_state *reg)
{
	return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}

/* check_stack_read/write functions track spill/fill of registers,
 * stack boundary and alignment are checked in check_mem_access()
 */
static int check_stack_write(struct bpf_verifier_env *env,
			     struct bpf_func_state *state, /* func where register points to */
			     int off, int size, int value_regno, int insn_idx)
{
	struct bpf_func_state *cur; /* state of the current function */
	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
	enum bpf_reg_type type;

	err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
				 true);
	if (err)
		return err;
	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
	 * so it's aligned access and [off, off + size) are within stack limits
	 */
	if (!env->allow_ptr_leaks &&
	    state->stack[spi].slot_type[0] == STACK_SPILL &&
	    size != BPF_REG_SIZE) {
		verbose(env, "attempt to corrupt spilled pointer on stack\n");
		return -EACCES;
	}

	cur = env->cur_state->frame[env->cur_state->curframe];
	if (value_regno >= 0 &&
	    is_spillable_regtype((type = cur->regs[value_regno].type))) {

		/* register containing pointer is being spilled into stack */
		if (size != BPF_REG_SIZE) {
			verbose(env, "invalid size of register spill\n");
			return -EACCES;
		}

		if (state != cur && type == PTR_TO_STACK) {
			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
			return -EINVAL;
		}

		/* save register state */
		state->stack[spi].spilled_ptr = cur->regs[value_regno];
		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;

		for (i = 0; i < BPF_REG_SIZE; i++) {
			if (state->stack[spi].slot_type[i] == STACK_MISC &&
			    !env->allow_ptr_leaks) {
				int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
				int soff = (-spi - 1) * BPF_REG_SIZE;

				/* detected reuse of integer stack slot with a pointer
				 * which means either llvm is reusing stack slot or
				 * an attacker is trying to exploit CVE-2018-3639
				 * (speculative store bypass)
				 * Have to sanitize that slot with preemptive
				 * store of zero.
				 */
				if (*poff && *poff != soff) {
					/* disallow programs where single insn stores
					 * into two different stack slots, since verifier
					 * cannot sanitize them
					 */
					verbose(env,
						"insn %d cannot access two stack slots fp%d and fp%d",
						insn_idx, *poff, soff);
					return -EINVAL;
				}
				*poff = soff;
			}
			state->stack[spi].slot_type[i] = STACK_SPILL;
		}
	} else {
		u8 type = STACK_MISC;

		/* regular write of data into stack */
		state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};

		/* only mark the slot as written if all 8 bytes were written
		 * otherwise read propagation may incorrectly stop too soon
		 * when stack slots are partially written.
		 * This heuristic means that read propagation will be
		 * conservative, since it will add reg_live_read marks
		 * to stack slots all the way to first state when programs
		 * writes+reads less than 8 bytes
		 */
		if (size == BPF_REG_SIZE)
			state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;

		/* when we zero initialize stack slots mark them as such */
		if (value_regno >= 0 &&
		    register_is_null(&cur->regs[value_regno]))
			type = STACK_ZERO;

		for (i = 0; i < size; i++)
			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
				type;
	}
	return 0;
}

/* registers of every function are unique and mark_reg_read() propagates
 * the liveness in the following cases:
 * - from callee into caller for R1 - R5 that were used as arguments
 * - from caller into callee for R0 that used as result of the call
 * - from caller to the same caller skipping states of the callee for R6 - R9,
 *   since R6 - R9 are callee saved by implicit function prologue and
 *   caller's R6 != callee's R6, so when we propagate liveness up to
 *   parent states we need to skip callee states for R6 - R9.
 *
 * stack slot marking is different, since stacks of caller and callee are
 * accessible in both (since caller can pass a pointer to caller's stack to
 * callee which can pass it to another function), hence mark_stack_slot_read()
 * has to propagate the stack liveness to all parent states at given frame number.
 * Consider code:
 * f1() {
 *   ptr = fp - 8;
 *   *ptr = ctx;
 *   call f2 {
 *      .. = *ptr;
 *   }
 *   .. = *ptr;
 * }
 * First *ptr is reading from f1's stack and mark_stack_slot_read() has
 * to mark liveness at the f1's frame and not f2's frame.
 * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has
 * to propagate liveness to f2 states at f1's frame level and further into
 * f1 states at f1's frame level until write into that stack slot
 */
static void mark_stack_slot_read(struct bpf_verifier_env *env,
				 const struct bpf_verifier_state *state,
				 struct bpf_verifier_state *parent,
				 int slot, int frameno)
{
	bool writes = parent == state->parent; /* Observe write marks */

	while (parent) {
		if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE)
			/* since LIVE_WRITTEN mark is only done for full 8-byte
			 * write the read marks are conservative and parent
			 * state may not even have the stack allocated. In such case
			 * end the propagation, since the loop reached beginning
			 * of the function
			 */
			break;
		/* if read wasn't screened by an earlier write ... */
		if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
			break;
		/* ... then we depend on parent's value */
		parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
		state = parent;
		parent = state->parent;
		writes = true;
	}
}

static int check_stack_read(struct bpf_verifier_env *env,
			    struct bpf_func_state *reg_state /* func where register points to */,
			    int off, int size, int value_regno)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
	u8 *stype;

	if (reg_state->allocated_stack <= slot) {
		verbose(env, "invalid read from stack off %d+0 size %d\n",
			off, size);
		return -EACCES;
	}
	stype = reg_state->stack[spi].slot_type;

	if (stype[0] == STACK_SPILL) {
		if (size != BPF_REG_SIZE) {
			verbose(env, "invalid size of register spill\n");
			return -EACCES;
		}
		for (i = 1; i < BPF_REG_SIZE; i++) {
			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
				verbose(env, "corrupted spill memory\n");
				return -EACCES;
			}
		}

		if (value_regno >= 0) {
			/* restore register state from stack */
			state->regs[value_regno] = reg_state->stack[spi].spilled_ptr;
			/* mark reg as written since spilled pointer state likely
			 * has its liveness marks cleared by is_state_visited()
			 * which resets stack/reg liveness for state transitions
			 */
			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
		}
		mark_stack_slot_read(env, vstate, vstate->parent, spi,
				     reg_state->frameno);
		return 0;
	} else {
		int zeros = 0;

		for (i = 0; i < size; i++) {
			if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
				continue;
			if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
				zeros++;
				continue;
			}
			verbose(env, "invalid read from stack off %d+%d size %d\n",
				off, i, size);
			return -EACCES;
		}
		mark_stack_slot_read(env, vstate, vstate->parent, spi,
				     reg_state->frameno);
		if (value_regno >= 0) {
			if (zeros == size) {
				/* any size read into register is zero extended,
				 * so the whole register == const_zero
				 */
				__mark_reg_const_zero(&state->regs[value_regno]);
			} else {
				/* have read misc data from the stack */
				mark_reg_unknown(env, state->regs, value_regno);
			}
			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
		}
		return 0;
	}
}

static int check_stack_access(struct bpf_verifier_env *env,
			      const struct bpf_reg_state *reg,
			      int off, int size)
{
	/* Stack accesses must be at a fixed offset, so that we
	 * can determine what type of data were returned. See
	 * check_stack_read().
	 */
	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "variable stack access var_off=%s off=%d size=%d",
			tn_buf, off, size);
		return -EACCES;
	}

	if (off >= 0 || off < -MAX_BPF_STACK) {
		verbose(env, "invalid stack off=%d size=%d\n", off, size);
		return -EACCES;
	}

	return 0;
}

/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
			      int size, bool zero_size_allowed)
{
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_map *map = regs[regno].map_ptr;

	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
	    off + size > map->value_size) {
		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
			map->value_size, off, size);
		return -EACCES;
	}
	return 0;
}

/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, u32 regno,
			    int off, int size, bool zero_size_allowed)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *reg = &state->regs[regno];
	int err;

	/* We may have adjusted the register to this map value, so we
	 * need to try adding each of min_value and max_value to off
	 * to make sure our theoretical access will be safe.
	 */
	if (env->log.level)
		print_verifier_state(env, state);

	/* The minimum value is only important with signed
	 * comparisons where we can't assume the floor of a
	 * value is 0.  If we are using signed variables for our
	 * index'es we need to make sure that whatever we use
	 * will have a set floor within our range.
	 */
	if (reg->smin_value < 0 &&
	    (reg->smin_value == S64_MIN ||
	     (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) ||
	      reg->smin_value + off < 0)) {
		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
			regno);
		return -EACCES;
	}
	err = __check_map_access(env, regno, reg->smin_value + off, size,
				 zero_size_allowed);
	if (err) {
		verbose(env, "R%d min value is outside of the array range\n",
			regno);
		return err;
	}

	/* If we haven't set a max value then we need to bail since we can't be
	 * sure we won't do bad things.
	 * If reg->umax_value + off could overflow, treat that as unbounded too.
	 */
	if (reg->umax_value >= BPF_MAX_VAR_OFF) {
		verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
			regno);
		return -EACCES;
	}
	err = __check_map_access(env, regno, reg->umax_value + off, size,
				 zero_size_allowed);
	if (err)
		verbose(env, "R%d max value is outside of the array range\n",
			regno);
	return err;
}

#define MAX_PACKET_OFF 0xffff

static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
				       const struct bpf_call_arg_meta *meta,
				       enum bpf_access_type t)
{
	switch (env->prog->type) {
	case BPF_PROG_TYPE_LWT_IN:
	case BPF_PROG_TYPE_LWT_OUT:
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
	case BPF_PROG_TYPE_SK_REUSEPORT:
		/* dst_input() and dst_output() can't write for now */
		if (t == BPF_WRITE)
			return false;
		/* fallthrough */
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
	case BPF_PROG_TYPE_XDP:
	case BPF_PROG_TYPE_LWT_XMIT:
	case BPF_PROG_TYPE_SK_SKB:
	case BPF_PROG_TYPE_SK_MSG:
		if (meta)
			return meta->pkt_access;

		env->seen_direct_write = true;
		return true;
	default:
		return false;
	}
}

static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
				 int off, int size, bool zero_size_allowed)
{
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state *reg = &regs[regno];

	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
	    (u64)off + size > reg->range) {
		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
			off, size, regno, reg->id, reg->off, reg->range);
		return -EACCES;
	}
	return 0;
}

static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
			       int size, bool zero_size_allowed)
{
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state *reg = &regs[regno];
	int err;

	/* We may have added a variable offset to the packet pointer; but any
	 * reg->range we have comes after that.  We are only checking the fixed
	 * offset.
	 */

	/* We don't allow negative numbers, because we aren't tracking enough
	 * detail to prove they're safe.
	 */
	if (reg->smin_value < 0) {
		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
			regno);
		return -EACCES;
	}
	err = __check_packet_access(env, regno, off, size, zero_size_allowed);
	if (err) {
		verbose(env, "R%d offset is outside of the packet\n", regno);
		return err;
	}
	return err;
}

/* check access to 'struct bpf_context' fields.  Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
	struct bpf_insn_access_aux info = {
		.reg_type = *reg_type,
	};

	if (env->ops->is_valid_access &&
	    env->ops->is_valid_access(off, size, t, env->prog, &info)) {
		/* A non zero info.ctx_field_size indicates that this field is a
		 * candidate for later verifier transformation to load the whole
		 * field and then apply a mask when accessed with a narrower
		 * access than actual ctx access size. A zero info.ctx_field_size
		 * will only allow for whole field access and rejects any other
		 * type of narrower access.
		 */
		*reg_type = info.reg_type;

		env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
		/* remember the offset of last byte accessed in ctx */
		if (env->prog->aux->max_ctx_offset < off + size)
			env->prog->aux->max_ctx_offset = off + size;
		return 0;
	}

	verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
	return -EACCES;
}

static bool __is_pointer_value(bool allow_ptr_leaks,
			       const struct bpf_reg_state *reg)
{
	if (allow_ptr_leaks)
		return false;

	return reg->type != SCALAR_VALUE;
}

static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
	return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
}

static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = cur_regs(env) + regno;

	return reg->type == PTR_TO_CTX;
}

static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = cur_regs(env) + regno;

	return type_is_pkt_pointer(reg->type);
}

static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
				   const struct bpf_reg_state *reg,
				   int off, int size, bool strict)
{
	struct tnum reg_off;
	int ip_align;

	/* Byte size accesses are always allowed. */
	if (!strict || size == 1)
		return 0;

	/* For platforms that do not have a Kconfig enabling
	 * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
	 * NET_IP_ALIGN is universally set to '2'.  And on platforms
	 * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
	 * to this code only in strict mode where we want to emulate
	 * the NET_IP_ALIGN==2 checking.  Therefore use an
	 * unconditional IP align value of '2'.
	 */
	ip_align = 2;

	reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off));
	if (!tnum_is_aligned(reg_off, size)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env,
			"misaligned packet access off %d+%s+%d+%d size %d\n",
			ip_align, tn_buf, reg->off, off, size);
		return -EACCES;
	}

	return 0;
}

static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
				       const struct bpf_reg_state *reg,
				       const char *pointer_desc,
				       int off, int size, bool strict)
{
	struct tnum reg_off;

	/* Byte size accesses are always allowed. */
	if (!strict || size == 1)
		return 0;

	reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off));
	if (!tnum_is_aligned(reg_off, size)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
			pointer_desc, tn_buf, reg->off, off, size);
		return -EACCES;
	}

	return 0;
}

static int check_ptr_alignment(struct bpf_verifier_env *env,
			       const struct bpf_reg_state *reg, int off,
			       int size, bool strict_alignment_once)
{
	bool strict = env->strict_alignment || strict_alignment_once;
	const char *pointer_desc = "";

	switch (reg->type) {
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
		/* Special case, because of NET_IP_ALIGN. Given metadata sits
		 * right in front, treat it the very same way.
		 */
		return check_pkt_ptr_alignment(env, reg, off, size, strict);
	case PTR_TO_MAP_VALUE:
		pointer_desc = "value ";
		break;
	case PTR_TO_CTX:
		pointer_desc = "context ";
		break;
	case PTR_TO_STACK:
		pointer_desc = "stack ";
		/* The stack spill tracking logic in check_stack_write()
		 * and check_stack_read() relies on stack accesses being
		 * aligned.
		 */
		strict = true;
		break;
	default:
		break;
	}
	return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
					   strict);
}

static int update_stack_depth(struct bpf_verifier_env *env,
			      const struct bpf_func_state *func,
			      int off)
{
	u16 stack = env->subprog_info[func->subprogno].stack_depth;

	if (stack >= -off)
		return 0;

	/* update known max for given subprogram */
	env->subprog_info[func->subprogno].stack_depth = -off;
	return 0;
}

/* starting from main bpf function walk all instructions of the function
 * and recursively walk all callees that given function can call.
 * Ignore jump and exit insns.
 * Since recursion is prevented by check_cfg() this algorithm
 * only needs a local stack of MAX_CALL_FRAMES to remember callsites
 */
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
	struct bpf_subprog_info *subprog = env->subprog_info;
	struct bpf_insn *insn = env->prog->insnsi;
	int ret_insn[MAX_CALL_FRAMES];
	int ret_prog[MAX_CALL_FRAMES];

process_func:
	/* round up to 32-bytes, since this is granularity
	 * of interpreter stack size
	 */
	depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
	if (depth > MAX_BPF_STACK) {
		verbose(env, "combined stack size of %d calls is %d. Too large\n",
			frame + 1, depth);
		return -EACCES;
	}
continue_func:
	subprog_end = subprog[idx + 1].start;
	for (; i < subprog_end; i++) {
		if (insn[i].code != (BPF_JMP | BPF_CALL))
			continue;
		if (insn[i].src_reg != BPF_PSEUDO_CALL)
			continue;
		/* remember insn and function to return to */
		ret_insn[frame] = i + 1;
		ret_prog[frame] = idx;

		/* find the callee */
		i = i + insn[i].imm + 1;
		idx = find_subprog(env, i);
		if (idx < 0) {
			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
				  i);
			return -EFAULT;
		}
		frame++;
		if (frame >= MAX_CALL_FRAMES) {
			WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
			return -EFAULT;
		}
		goto process_func;
	}
	/* end of for() loop means the last insn of the 'subprog'
	 * was reached. Doesn't matter whether it was JA or EXIT
	 */
	if (frame == 0)
		return 0;
	depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
	frame--;
	i = ret_insn[frame];
	idx = ret_prog[frame];
	goto continue_func;
}

#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
				  const struct bpf_insn *insn, int idx)
{
	int start = idx + insn->imm + 1, subprog;

	subprog = find_subprog(env, start);
	if (subprog < 0) {
		WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
			  start);
		return -EFAULT;
	}
	return env->subprog_info[subprog].stack_depth;
}
#endif

static int check_ctx_reg(struct bpf_verifier_env *env,
			 const struct bpf_reg_state *reg, int regno)
{
	/* Access to ctx or passing it to a helper is only allowed in
	 * its original, unmodified form.
	 */

	if (reg->off) {
		verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
			regno, reg->off);
		return -EACCES;
	}

	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
		return -EACCES;
	}

	return 0;
}

/* truncate register to smaller size (in bytes)
 * must be called with size < BPF_REG_SIZE
 */
static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
{
	u64 mask;

	/* clear high bits in bit representation */
	reg->var_off = tnum_cast(reg->var_off, size);

	/* fix arithmetic bounds */
	mask = ((u64)1 << (size * 8)) - 1;
	if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
		reg->umin_value &= mask;
		reg->umax_value &= mask;
	} else {
		reg->umin_value = 0;
		reg->umax_value = mask;
	}
	reg->smin_value = reg->umin_value;
	reg->smax_value = reg->umax_value;
}

/* check whether memory at (regno + off) is accessible for t = (read | write)
 * if t==write, value_regno is a register which value is stored into memory
 * if t==read, value_regno is a register which will receive the value from memory
 * if t==write && value_regno==-1, some unknown value is stored into memory
 * if t==read && value_regno==-1, don't care what we read from memory
 */
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
			    int off, int bpf_size, enum bpf_access_type t,
			    int value_regno, bool strict_alignment_once)
{
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state *reg = regs + regno;
	struct bpf_func_state *state;
	int size, err = 0;

	size = bpf_size_to_bytes(bpf_size);
	if (size < 0)
		return size;

	/* alignment checks will add in reg->off themselves */
	err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
	if (err)
		return err;

	/* for access checks, reg->off is just part of off */
	off += reg->off;

	if (reg->type == PTR_TO_MAP_VALUE) {
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose(env, "R%d leaks addr into map\n", value_regno);
			return -EACCES;
		}

		err = check_map_access(env, regno, off, size, false);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);

	} else if (reg->type == PTR_TO_CTX) {
		enum bpf_reg_type reg_type = SCALAR_VALUE;

		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose(env, "R%d leaks addr into ctx\n", value_regno);
			return -EACCES;
		}

		err = check_ctx_reg(env, reg, regno);
		if (err < 0)
			return err;

		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
		if (!err && t == BPF_READ && value_regno >= 0) {
			/* ctx access returns either a scalar, or a
			 * PTR_TO_PACKET[_META,_END]. In the latter
			 * case, we know the offset is zero.
			 */
			if (reg_type == SCALAR_VALUE)
				mark_reg_unknown(env, regs, value_regno);
			else
				mark_reg_known_zero(env, regs,
						    value_regno);
			regs[value_regno].type = reg_type;
		}

	} else if (reg->type == PTR_TO_STACK) {
		off += reg->var_off.value;
		err = check_stack_access(env, reg, off, size);
		if (err)
			return err;

		state = func(env, reg);
		err = update_stack_depth(env, state, off);
		if (err)
			return err;

		if (t == BPF_WRITE)
			err = check_stack_write(env, state, off, size,
						value_regno, insn_idx);
		else
			err = check_stack_read(env, state, off, size,
					       value_regno);
	} else if (reg_is_pkt_pointer(reg)) {
		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
			verbose(env, "cannot write into packet\n");
			return -EACCES;
		}
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose(env, "R%d leaks addr into packet\n",
				value_regno);
			return -EACCES;
		}
		err = check_packet_access(env, regno, off, size, false);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else {
		verbose(env, "R%d invalid mem access '%s'\n", regno,
			reg_type_str[reg->type]);
		return -EACCES;
	}

	if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
	    regs[value_regno].type == SCALAR_VALUE) {
		/* b/h/w load zero-extends, mark upper bits as known 0 */
		coerce_reg_to_size(&regs[value_regno], size);
	}
	return err;
}

static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
	int err;

	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
	    insn->imm != 0) {
		verbose(env, "BPF_XADD uses reserved fields\n");
		return -EINVAL;
	}

	/* check src1 operand */
	err = check_reg_arg(env, insn->src_reg, SRC_OP);
	if (err)
		return err;

	/* check src2 operand */
	err = check_reg_arg(env, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	if (is_pointer_value(env, insn->src_reg)) {
		verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
		return -EACCES;
	}

	if (is_ctx_reg(env, insn->dst_reg) ||
	    is_pkt_reg(env, insn->dst_reg)) {
		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
			insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
			"context" : "packet");
		return -EACCES;
	}

	/* check whether atomic_add can read the memory */
	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
			       BPF_SIZE(insn->code), BPF_READ, -1, true);
	if (err)
		return err;

	/* check whether atomic_add can write into the same memory */
	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}

/* when register 'regno' is passed into function that will read 'access_size'
 * bytes from that pointer, make sure that it's within stack boundary
 * and all elements of stack are initialized.
 * Unlike most pointer bounds-checking functions, this one doesn't take an
 * 'off' argument, so it has to add in reg->off itself.
 */
static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
				int access_size, bool zero_size_allowed,
				struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *reg = cur_regs(env) + regno;
	struct bpf_func_state *state = func(env, reg);
	int off, i, slot, spi;

	if (reg->type != PTR_TO_STACK) {
		/* Allow zero-byte read from NULL, regardless of pointer type */
		if (zero_size_allowed && access_size == 0 &&
		    register_is_null(reg))
			return 0;

		verbose(env, "R%d type=%s expected=%s\n", regno,
			reg_type_str[reg->type],
			reg_type_str[PTR_TO_STACK]);
		return -EACCES;
	}

	/* Only allow fixed-offset stack reads */
	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "invalid variable stack read R%d var_off=%s\n",
			regno, tn_buf);
		return -EACCES;
	}
	off = reg->off + reg->var_off.value;
	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
	    access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
		verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
			regno, off, access_size);
		return -EACCES;
	}

	if (meta && meta->raw_mode) {
		meta->access_size = access_size;
		meta->regno = regno;
		return 0;
	}

	for (i = 0; i < access_size; i++) {
		u8 *stype;

		slot = -(off + i) - 1;
		spi = slot / BPF_REG_SIZE;
		if (state->allocated_stack <= slot)
			goto err;
		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
		if (*stype == STACK_MISC)
			goto mark;
		if (*stype == STACK_ZERO) {
			/* helper can write anything into the stack */
			*stype = STACK_MISC;
			goto mark;
		}
err:
		verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
			off, i, access_size);
		return -EACCES;
mark:
		/* reading any byte out of 8-byte 'spill_slot' will cause
		 * the whole slot to be marked as 'read'
		 */
		mark_stack_slot_read(env, env->cur_state, env->cur_state->parent,
				     spi, state->frameno);
	}
	return update_stack_depth(env, state, off);
}

static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
				   int access_size, bool zero_size_allowed,
				   struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];

	switch (reg->type) {
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
		return check_packet_access(env, regno, reg->off, access_size,
					   zero_size_allowed);
	case PTR_TO_MAP_VALUE:
		return check_map_access(env, regno, reg->off, access_size,
					zero_size_allowed);
	default: /* scalar_value|ptr_to_stack or invalid ptr */
		return check_stack_boundary(env, regno, access_size,
					    zero_size_allowed, meta);
	}
}

static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
	return type == ARG_PTR_TO_MEM ||
	       type == ARG_PTR_TO_MEM_OR_NULL ||
	       type == ARG_PTR_TO_UNINIT_MEM;
}

static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
	return type == ARG_CONST_SIZE ||
	       type == ARG_CONST_SIZE_OR_ZERO;
}

static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
			  enum bpf_arg_type arg_type,
			  struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
	enum bpf_reg_type expected_type, type = reg->type;
	int err = 0;

	if (arg_type == ARG_DONTCARE)
		return 0;

	err = check_reg_arg(env, regno, SRC_OP);
	if (err)
		return err;

	if (arg_type == ARG_ANYTHING) {
		if (is_pointer_value(env, regno)) {
			verbose(env, "R%d leaks addr into helper function\n",
				regno);
			return -EACCES;
		}
		return 0;
	}

	if (type_is_pkt_pointer(type) &&
	    !may_access_direct_pkt_data(env, meta, BPF_READ)) {
		verbose(env, "helper access to the packet is not allowed\n");
		return -EACCES;
	}

	if (arg_type == ARG_PTR_TO_MAP_KEY ||
	    arg_type == ARG_PTR_TO_MAP_VALUE) {
		expected_type = PTR_TO_STACK;
		if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
		    type != expected_type)
			goto err_type;
	} else if (arg_type == ARG_CONST_SIZE ||
		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
		expected_type = SCALAR_VALUE;
		if (type != expected_type)
			goto err_type;
	} else if (arg_type == ARG_CONST_MAP_PTR) {
		expected_type = CONST_PTR_TO_MAP;
		if (type != expected_type)
			goto err_type;
	} else if (arg_type == ARG_PTR_TO_CTX) {
		expected_type = PTR_TO_CTX;
		if (type != expected_type)
			goto err_type;
		err = check_ctx_reg(env, reg, regno);
		if (err < 0)
			return err;
	} else if (arg_type_is_mem_ptr(arg_type)) {
		expected_type = PTR_TO_STACK;
		/* One exception here. In case function allows for NULL to be
		 * passed in as argument, it's a SCALAR_VALUE type. Final test
		 * happens during stack boundary checking.
		 */
		if (register_is_null(reg) &&
		    arg_type == ARG_PTR_TO_MEM_OR_NULL)
			/* final test in check_stack_boundary() */;
		else if (!type_is_pkt_pointer(type) &&
			 type != PTR_TO_MAP_VALUE &&
			 type != expected_type)
			goto err_type;
		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
	} else {
		verbose(env, "unsupported arg_type %d\n", arg_type);
		return -EFAULT;
	}

	if (arg_type == ARG_CONST_MAP_PTR) {
		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
		meta->map_ptr = reg->map_ptr;
	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
		/* bpf_map_xxx(..., map_ptr, ..., key) call:
		 * check that [key, key + map->key_size) are within
		 * stack limits and initialized
		 */
		if (!meta->map_ptr) {
			/* in function declaration map_ptr must come before
			 * map_key, so that it's verified and known before
			 * we have to check map_key here. Otherwise it means
			 * that kernel subsystem misconfigured verifier
			 */
			verbose(env, "invalid map_ptr to access map->key\n");
			return -EACCES;
		}
		err = check_helper_mem_access(env, regno,
					      meta->map_ptr->key_size, false,
					      NULL);
	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
		/* bpf_map_xxx(..., map_ptr, ..., value) call:
		 * check [value, value + map->value_size) validity
		 */
		if (!meta->map_ptr) {
			/* kernel subsystem misconfigured verifier */
			verbose(env, "invalid map_ptr to access map->value\n");
			return -EACCES;
		}
		err = check_helper_mem_access(env, regno,
					      meta->map_ptr->value_size, false,
					      NULL);
	} else if (arg_type_is_mem_size(arg_type)) {
		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);

		/* remember the mem_size which may be used later
		 * to refine return values.
		 */
		meta->msize_smax_value = reg->smax_value;
		meta->msize_umax_value = reg->umax_value;

		/* The register is SCALAR_VALUE; the access check
		 * happens using its boundaries.
		 */
		if (!tnum_is_const(reg->var_off))
			/* For unprivileged variable accesses, disable raw
			 * mode so that the program is required to
			 * initialize all the memory that the helper could
			 * just partially fill up.
			 */
			meta = NULL;

		if (reg->smin_value < 0) {
			verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
				regno);
			return -EACCES;
		}

		if (reg->umin_value == 0) {
			err = check_helper_mem_access(env, regno - 1, 0,
						      zero_size_allowed,
						      meta);
			if (err)
				return err;
		}

		if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
			verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
				regno);
			return -EACCES;
		}
		err = check_helper_mem_access(env, regno - 1,
					      reg->umax_value,
					      zero_size_allowed, meta);
	}

	return err;
err_type:
	verbose(env, "R%d type=%s expected=%s\n", regno,
		reg_type_str[type], reg_type_str[expected_type]);
	return -EACCES;
}

static int check_map_func_compatibility(struct bpf_verifier_env *env,
					struct bpf_map *map, int func_id)
{
	if (!map)
		return 0;

	/* We need a two way check, first is from map perspective ... */
	switch (map->map_type) {
	case BPF_MAP_TYPE_PROG_ARRAY:
		if (func_id != BPF_FUNC_tail_call)
			goto error;
		break;
	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
		if (func_id != BPF_FUNC_perf_event_read &&
		    func_id != BPF_FUNC_perf_event_output &&
		    func_id != BPF_FUNC_perf_event_read_value)
			goto error;
		break;
	case BPF_MAP_TYPE_STACK_TRACE:
		if (func_id != BPF_FUNC_get_stackid)
			goto error;
		break;
	case BPF_MAP_TYPE_CGROUP_ARRAY:
		if (func_id != BPF_FUNC_skb_under_cgroup &&
		    func_id != BPF_FUNC_current_task_under_cgroup)
			goto error;
		break;
	case BPF_MAP_TYPE_CGROUP_STORAGE:
		if (func_id != BPF_FUNC_get_local_storage)
			goto error;
		break;
	/* devmap returns a pointer to a live net_device ifindex that we cannot
	 * allow to be modified from bpf side. So do not allow lookup elements
	 * for now.
	 */
	case BPF_MAP_TYPE_DEVMAP:
		if (func_id != BPF_FUNC_redirect_map)
			goto error;
		break;
	/* Restrict bpf side of cpumap and xskmap, open when use-cases
	 * appear.
	 */
	case BPF_MAP_TYPE_CPUMAP:
	case BPF_MAP_TYPE_XSKMAP:
		if (func_id != BPF_FUNC_redirect_map)
			goto error;
		break;
	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
	case BPF_MAP_TYPE_HASH_OF_MAPS:
		if (func_id != BPF_FUNC_map_lookup_elem)
			goto error;
		break;
	case BPF_MAP_TYPE_SOCKMAP:
		if (func_id != BPF_FUNC_sk_redirect_map &&
		    func_id != BPF_FUNC_sock_map_update &&
		    func_id != BPF_FUNC_map_delete_elem &&
		    func_id != BPF_FUNC_msg_redirect_map)
			goto error;
		break;
	case BPF_MAP_TYPE_SOCKHASH:
		if (func_id != BPF_FUNC_sk_redirect_hash &&
		    func_id != BPF_FUNC_sock_hash_update &&
		    func_id != BPF_FUNC_map_delete_elem &&
		    func_id != BPF_FUNC_msg_redirect_hash)
			goto error;
		break;
	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
		if (func_id != BPF_FUNC_sk_select_reuseport)
			goto error;
		break;
	default:
		break;
	}

	/* ... and second from the function itself. */
	switch (func_id) {
	case BPF_FUNC_tail_call:
		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
			goto error;
		if (env->subprog_cnt > 1) {
			verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
			return -EINVAL;
		}
		break;
	case BPF_FUNC_perf_event_read:
	case BPF_FUNC_perf_event_output:
	case BPF_FUNC_perf_event_read_value:
		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
			goto error;
		break;
	case BPF_FUNC_get_stackid:
		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
			goto error;
		break;
	case BPF_FUNC_current_task_under_cgroup:
	case BPF_FUNC_skb_under_cgroup:
		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
			goto error;
		break;
	case BPF_FUNC_redirect_map:
		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
		    map->map_type != BPF_MAP_TYPE_XSKMAP)
			goto error;
		break;
	case BPF_FUNC_sk_redirect_map:
	case BPF_FUNC_msg_redirect_map:
	case BPF_FUNC_sock_map_update:
		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
			goto error;
		break;
	case BPF_FUNC_sk_redirect_hash:
	case BPF_FUNC_msg_redirect_hash:
	case BPF_FUNC_sock_hash_update:
		if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
			goto error;
		break;
	case BPF_FUNC_get_local_storage:
		if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
			goto error;
		break;
	case BPF_FUNC_sk_select_reuseport:
		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
			goto error;
		break;
	default:
		break;
	}

	return 0;
error:
	verbose(env, "cannot pass map_type %d into func %s#%d\n",
		map->map_type, func_id_name(func_id), func_id);
	return -EINVAL;
}

static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
{
	int count = 0;

	if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
		count++;
	if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
		count++;
	if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
		count++;
	if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
		count++;
	if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
		count++;

	/* We only support one arg being in raw mode at the moment,
	 * which is sufficient for the helper functions we have
	 * right now.
	 */
	return count <= 1;
}

static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
				    enum bpf_arg_type arg_next)
{
	return (arg_type_is_mem_ptr(arg_curr) &&
	        !arg_type_is_mem_size(arg_next)) ||
	       (!arg_type_is_mem_ptr(arg_curr) &&
		arg_type_is_mem_size(arg_next));
}

static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
{
	/* bpf_xxx(..., buf, len) call will access 'len'
	 * bytes from memory 'buf'. Both arg types need
	 * to be paired, so make sure there's no buggy
	 * helper function specification.
	 */
	if (arg_type_is_mem_size(fn->arg1_type) ||
	    arg_type_is_mem_ptr(fn->arg5_type)  ||
	    check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
	    check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
	    check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
	    check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
		return false;

	return true;
}

static int check_func_proto(const struct bpf_func_proto *fn)
{
	return check_raw_mode_ok(fn) &&
	       check_arg_pair_ok(fn) ? 0 : -EINVAL;
}

/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
 * are now invalid, so turn them into unknown SCALAR_VALUE.
 */
static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
				     struct bpf_func_state *state)
{
	struct bpf_reg_state *regs = state->regs, *reg;
	int i;

	for (i = 0; i < MAX_BPF_REG; i++)
		if (reg_is_pkt_pointer_any(&regs[i]))
			mark_reg_unknown(env, regs, i);

	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
		if (state->stack[i].slot_type[0] != STACK_SPILL)
			continue;
		reg = &state->stack[i].spilled_ptr;
		if (reg_is_pkt_pointer_any(reg))
			__mark_reg_unknown(reg);
	}
}

static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	int i;

	for (i = 0; i <= vstate->curframe; i++)
		__clear_all_pkt_pointers(env, vstate->frame[i]);
}

static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
			   int *insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_func_state *caller, *callee;
	int i, subprog, target_insn;

	if (state->curframe + 1 >= MAX_CALL_FRAMES) {
		verbose(env, "the call stack of %d frames is too deep\n",
			state->curframe + 2);
		return -E2BIG;
	}

	target_insn = *insn_idx + insn->imm;
	subprog = find_subprog(env, target_insn + 1);
	if (subprog < 0) {
		verbose(env, "verifier bug. No program starts at insn %d\n",
			target_insn + 1);
		return -EFAULT;
	}

	caller = state->frame[state->curframe];
	if (state->frame[state->curframe + 1]) {
		verbose(env, "verifier bug. Frame %d already allocated\n",
			state->curframe + 1);
		return -EFAULT;
	}

	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
	if (!callee)
		return -ENOMEM;
	state->frame[state->curframe + 1] = callee;

	/* callee cannot access r0, r6 - r9 for reading and has to write
	 * into its own stack before reading from it.
	 * callee can read/write into caller's stack
	 */
	init_func_state(env, callee,
			/* remember the callsite, it will be used by bpf_exit */
			*insn_idx /* callsite */,
			state->curframe + 1 /* frameno within this callchain */,
			subprog /* subprog number within this prog */);

	/* copy r1 - r5 args that callee can access */
	for (i = BPF_REG_1; i <= BPF_REG_5; i++)
		callee->regs[i] = caller->regs[i];

	/* after the call regsiters r0 - r5 were scratched */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		mark_reg_not_init(env, caller->regs, caller_saved[i]);
		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
	}

	/* only increment it after check_reg_arg() finished */
	state->curframe++;

	/* and go analyze first insn of the callee */
	*insn_idx = target_insn;

	if (env->log.level) {
		verbose(env, "caller:\n");
		print_verifier_state(env, caller);
		verbose(env, "callee:\n");
		print_verifier_state(env, callee);
	}
	return 0;
}

static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_func_state *caller, *callee;
	struct bpf_reg_state *r0;

	callee = state->frame[state->curframe];
	r0 = &callee->regs[BPF_REG_0];
	if (r0->type == PTR_TO_STACK) {
		/* technically it's ok to return caller's stack pointer
		 * (or caller's caller's pointer) back to the caller,
		 * since these pointers are valid. Only current stack
		 * pointer will be invalid as soon as function exits,
		 * but let's be conservative
		 */
		verbose(env, "cannot return stack pointer to the caller\n");
		return -EINVAL;
	}

	state->curframe--;
	caller = state->frame[state->curframe];
	/* return to the caller whatever r0 had in the callee */
	caller->regs[BPF_REG_0] = *r0;

	*insn_idx = callee->callsite + 1;
	if (env->log.level) {
		verbose(env, "returning from callee:\n");
		print_verifier_state(env, callee);
		verbose(env, "to caller at %d:\n", *insn_idx);
		print_verifier_state(env, caller);
	}
	/* clear everything in the callee */
	free_func_state(callee);
	state->frame[state->curframe + 1] = NULL;
	return 0;
}

static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
				   int func_id,
				   struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];

	if (ret_type != RET_INTEGER ||
	    (func_id != BPF_FUNC_get_stack &&
	     func_id != BPF_FUNC_probe_read_str))
		return;

	ret_reg->smax_value = meta->msize_smax_value;
	ret_reg->umax_value = meta->msize_umax_value;
	__reg_deduce_bounds(ret_reg);
	__reg_bound_offset(ret_reg);
}

static int
record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
		int func_id, int insn_idx)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];

	if (func_id != BPF_FUNC_tail_call &&
	    func_id != BPF_FUNC_map_lookup_elem &&
	    func_id != BPF_FUNC_map_update_elem &&
	    func_id != BPF_FUNC_map_delete_elem)
		return 0;

	if (meta->map_ptr == NULL) {
		verbose(env, "kernel subsystem misconfigured verifier\n");
		return -EINVAL;
	}

	if (!BPF_MAP_PTR(aux->map_state))
		bpf_map_ptr_store(aux, meta->map_ptr,
				  meta->map_ptr->unpriv_array);
	else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr)
		bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
				  meta->map_ptr->unpriv_array);
	return 0;
}

static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
	const struct bpf_func_proto *fn = NULL;
	struct bpf_reg_state *regs;
	struct bpf_call_arg_meta meta;
	bool changes_data;
	int i, err;

	/* find function prototype */
	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
		verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
			func_id);
		return -EINVAL;
	}

	if (env->ops->get_func_proto)
		fn = env->ops->get_func_proto(func_id, env->prog);
	if (!fn) {
		verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
			func_id);
		return -EINVAL;
	}

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
	if (!env->prog->gpl_compatible && fn->gpl_only) {
		verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n");
		return -EINVAL;
	}

	/* With LD_ABS/IND some JITs save/restore skb from r1. */
	changes_data = bpf_helper_changes_pkt_data(fn->func);
	if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
		verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
			func_id_name(func_id), func_id);
		return -EINVAL;
	}

	memset(&meta, 0, sizeof(meta));
	meta.pkt_access = fn->pkt_access;

	err = check_func_proto(fn);
	if (err) {
		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
			func_id_name(func_id), func_id);
		return err;
	}

	/* check args */
	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
	if (err)
		return err;
	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
	if (err)
		return err;

	err = record_func_map(env, &meta, func_id, insn_idx);
	if (err)
		return err;

	/* Mark slots with STACK_MISC in case of raw mode, stack offset
	 * is inferred from register state.
	 */
	for (i = 0; i < meta.access_size; i++) {
		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
				       BPF_WRITE, -1, false);
		if (err)
			return err;
	}

	regs = cur_regs(env);

	/* check that flags argument in get_local_storage(map, flags) is 0,
	 * this is required because get_local_storage() can't return an error.
	 */
	if (func_id == BPF_FUNC_get_local_storage &&
	    !register_is_null(&regs[BPF_REG_2])) {
		verbose(env, "get_local_storage() doesn't support non-zero flags\n");
		return -EINVAL;
	}

	/* reset caller saved regs */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		mark_reg_not_init(env, regs, caller_saved[i]);
		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
	}

	/* update return register (already marked as written above) */
	if (fn->ret_type == RET_INTEGER) {
		/* sets type to SCALAR_VALUE */
		mark_reg_unknown(env, regs, BPF_REG_0);
	} else if (fn->ret_type == RET_VOID) {
		regs[BPF_REG_0].type = NOT_INIT;
	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
		   fn->ret_type == RET_PTR_TO_MAP_VALUE) {
		if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
		else
			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
		/* There is no offset yet applied, variable or fixed */
		mark_reg_known_zero(env, regs, BPF_REG_0);
		/* remember map_ptr, so that check_map_access()
		 * can check 'value_size' boundary of memory access
		 * to map element returned from bpf_map_lookup_elem()
		 */
		if (meta.map_ptr == NULL) {
			verbose(env,
				"kernel subsystem misconfigured verifier\n");
			return -EINVAL;
		}
		regs[BPF_REG_0].map_ptr = meta.map_ptr;
		regs[BPF_REG_0].id = ++env->id_gen;
	} else {
		verbose(env, "unknown return type %d of func %s#%d\n",
			fn->ret_type, func_id_name(func_id), func_id);
		return -EINVAL;
	}

	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);

	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
	if (err)
		return err;

	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
		const char *err_str;

#ifdef CONFIG_PERF_EVENTS
		err = get_callchain_buffers(sysctl_perf_event_max_stack);
		err_str = "cannot get callchain buffer for func %s#%d\n";
#else
		err = -ENOTSUPP;
		err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
#endif
		if (err) {
			verbose(env, err_str, func_id_name(func_id), func_id);
			return err;
		}

		env->prog->has_callchain_buf = true;
	}

	if (changes_data)
		clear_all_pkt_pointers(env);
	return 0;
}

static bool signed_add_overflows(s64 a, s64 b)
{
	/* Do the add in u64, where overflow is well-defined */
	s64 res = (s64)((u64)a + (u64)b);

	if (b < 0)
		return res > a;
	return res < a;
}

static bool signed_sub_overflows(s64 a, s64 b)
{
	/* Do the sub in u64, where overflow is well-defined */
	s64 res = (s64)((u64)a - (u64)b);

	if (b < 0)
		return res < a;
	return res > a;
}

static bool check_reg_sane_offset(struct bpf_verifier_env *env,
				  const struct bpf_reg_state *reg,
				  enum bpf_reg_type type)
{
	bool known = tnum_is_const(reg->var_off);
	s64 val = reg->var_off.value;
	s64 smin = reg->smin_value;

	if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
		verbose(env, "math between %s pointer and %lld is not allowed\n",
			reg_type_str[type], val);
		return false;
	}

	if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
		verbose(env, "%s pointer offset %d is not allowed\n",
			reg_type_str[type], reg->off);
		return false;
	}

	if (smin == S64_MIN) {
		verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
			reg_type_str[type]);
		return false;
	}

	if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
		verbose(env, "value %lld makes %s pointer be out of bounds\n",
			smin, reg_type_str[type]);
		return false;
	}

	return true;
}

static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
{
	return &env->insn_aux_data[env->insn_idx];
}

static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
			      u32 *ptr_limit, u8 opcode, bool off_is_neg)
{
	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
			    (opcode == BPF_SUB && !off_is_neg);
	u32 off;

	switch (ptr_reg->type) {
	case PTR_TO_STACK:
		off = ptr_reg->off + ptr_reg->var_off.value;
		if (mask_to_left)
			*ptr_limit = MAX_BPF_STACK + off;
		else
			*ptr_limit = -off;
		return 0;
	case PTR_TO_MAP_VALUE:
		if (mask_to_left) {
			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
		} else {
			off = ptr_reg->smin_value + ptr_reg->off;
			*ptr_limit = ptr_reg->map_ptr->value_size - off;
		}
		return 0;
	default:
		return -EINVAL;
	}
}

static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
				    const struct bpf_insn *insn)
{
	return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K;
}

static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
				       u32 alu_state, u32 alu_limit)
{
	/* If we arrived here from different branches with different
	 * state or limits to sanitize, then this won't work.
	 */
	if (aux->alu_state &&
	    (aux->alu_state != alu_state ||
	     aux->alu_limit != alu_limit))
		return -EACCES;

	/* Corresponding fixup done in fixup_bpf_calls(). */
	aux->alu_state = alu_state;
	aux->alu_limit = alu_limit;
	return 0;
}

static int sanitize_val_alu(struct bpf_verifier_env *env,
			    struct bpf_insn *insn)
{
	struct bpf_insn_aux_data *aux = cur_aux(env);

	if (can_skip_alu_sanitation(env, insn))
		return 0;

	return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}

static int sanitize_ptr_alu(struct bpf_verifier_env *env,
			    struct bpf_insn *insn,
			    const struct bpf_reg_state *ptr_reg,
			    struct bpf_reg_state *dst_reg,
			    bool off_is_neg)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_insn_aux_data *aux = cur_aux(env);
	bool ptr_is_dst_reg = ptr_reg == dst_reg;
	u8 opcode = BPF_OP(insn->code);
	u32 alu_state, alu_limit;
	struct bpf_reg_state tmp;
	bool ret;

	if (can_skip_alu_sanitation(env, insn))
		return 0;

	/* We already marked aux for masking from non-speculative
	 * paths, thus we got here in the first place. We only care
	 * to explore bad access from here.
	 */
	if (vstate->speculative)
		goto do_sim;

	alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
	alu_state |= ptr_is_dst_reg ?
		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;

	if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
		return 0;
	if (update_alu_sanitation_state(aux, alu_state, alu_limit))
		return -EACCES;
do_sim:
	/* Simulate and find potential out-of-bounds access under
	 * speculative execution from truncation as a result of
	 * masking when off was not within expected range. If off
	 * sits in dst, then we temporarily need to move ptr there
	 * to simulate dst (== 0) +/-= ptr. Needed, for example,
	 * for cases where we use K-based arithmetic in one direction
	 * and truncated reg-based in the other in order to explore
	 * bad access.
	 */
	if (!ptr_is_dst_reg) {
		tmp = *dst_reg;
		*dst_reg = *ptr_reg;
	}
	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
	if (!ptr_is_dst_reg && ret)
		*dst_reg = tmp;
	return !ret ? -EFAULT : 0;
}

/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
 * Caller should also handle BPF_MOV case separately.
 * If we return -EACCES, caller may want to try again treating pointer as a
 * scalar.  So we only emit a diagnostic if !env->allow_ptr_leaks.
 */
static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
				   struct bpf_insn *insn,
				   const struct bpf_reg_state *ptr_reg,
				   const struct bpf_reg_state *off_reg)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs, *dst_reg;
	bool known = tnum_is_const(off_reg->var_off);
	s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
	    smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
	u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
	    umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
	u32 dst = insn->dst_reg, src = insn->src_reg;
	u8 opcode = BPF_OP(insn->code);
	int ret;

	dst_reg = &regs[dst];

	if ((known && (smin_val != smax_val || umin_val != umax_val)) ||
	    smin_val > smax_val || umin_val > umax_val) {
		/* Taint dst register if offset had invalid bounds derived from
		 * e.g. dead branches.
		 */
		__mark_reg_unknown(dst_reg);
		return 0;
	}

	if (BPF_CLASS(insn->code) != BPF_ALU64) {
		/* 32-bit ALU ops on pointers produce (meaningless) scalars */
		verbose(env,
			"R%d 32-bit pointer arithmetic prohibited\n",
			dst);
		return -EACCES;
	}

	if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
		verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
			dst);
		return -EACCES;
	}
	if (ptr_reg->type == CONST_PTR_TO_MAP) {
		verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
			dst);
		return -EACCES;
	}
	if (ptr_reg->type == PTR_TO_PACKET_END) {
		verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
			dst);
		return -EACCES;
	}
	if (ptr_reg->type == PTR_TO_MAP_VALUE &&
	    !env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
		verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
			off_reg == dst_reg ? dst : src);
		return -EACCES;
	}

	/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
	 * The id may be overwritten later if we create a new variable offset.
	 */
	dst_reg->type = ptr_reg->type;
	dst_reg->id = ptr_reg->id;

	if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
	    !check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
		return -EINVAL;

	switch (opcode) {
	case BPF_ADD:
		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
		if (ret < 0) {
			verbose(env, "R%d tried to add from different maps or paths\n", dst);
			return ret;
		}
		/* We can take a fixed offset as long as it doesn't overflow
		 * the s32 'off' field
		 */
		if (known && (ptr_reg->off + smin_val ==
			      (s64)(s32)(ptr_reg->off + smin_val))) {
			/* pointer += K.  Accumulate it into fixed offset */
			dst_reg->smin_value = smin_ptr;
			dst_reg->smax_value = smax_ptr;
			dst_reg->umin_value = umin_ptr;
			dst_reg->umax_value = umax_ptr;
			dst_reg->var_off = ptr_reg->var_off;
			dst_reg->off = ptr_reg->off + smin_val;
			dst_reg->raw = ptr_reg->raw;
			break;
		}
		/* A new variable offset is created.  Note that off_reg->off
		 * == 0, since it's a scalar.
		 * dst_reg gets the pointer type and since some positive
		 * integer value was added to the pointer, give it a new 'id'
		 * if it's a PTR_TO_PACKET.
		 * this creates a new 'base' pointer, off_reg (variable) gets
		 * added into the variable offset, and we copy the fixed offset
		 * from ptr_reg.
		 */
		if (signed_add_overflows(smin_ptr, smin_val) ||
		    signed_add_overflows(smax_ptr, smax_val)) {
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			dst_reg->smin_value = smin_ptr + smin_val;
			dst_reg->smax_value = smax_ptr + smax_val;
		}
		if (umin_ptr + umin_val < umin_ptr ||
		    umax_ptr + umax_val < umax_ptr) {
			dst_reg->umin_value = 0;
			dst_reg->umax_value = U64_MAX;
		} else {
			dst_reg->umin_value = umin_ptr + umin_val;
			dst_reg->umax_value = umax_ptr + umax_val;
		}
		dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
		dst_reg->off = ptr_reg->off;
		dst_reg->raw = ptr_reg->raw;
		if (reg_is_pkt_pointer(ptr_reg)) {
			dst_reg->id = ++env->id_gen;
			/* something was added to pkt_ptr, set range to zero */
			dst_reg->raw = 0;
		}
		break;
	case BPF_SUB:
		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
		if (ret < 0) {
			verbose(env, "R%d tried to sub from different maps or paths\n", dst);
			return ret;
		}
		if (dst_reg == off_reg) {
			/* scalar -= pointer.  Creates an unknown scalar */
			verbose(env, "R%d tried to subtract pointer from scalar\n",
				dst);
			return -EACCES;
		}
		/* We don't allow subtraction from FP, because (according to
		 * test_verifier.c test "invalid fp arithmetic", JITs might not
		 * be able to deal with it.
		 */
		if (ptr_reg->type == PTR_TO_STACK) {
			verbose(env, "R%d subtraction from stack pointer prohibited\n",
				dst);
			return -EACCES;
		}
		if (known && (ptr_reg->off - smin_val ==
			      (s64)(s32)(ptr_reg->off - smin_val))) {
			/* pointer -= K.  Subtract it from fixed offset */
			dst_reg->smin_value = smin_ptr;
			dst_reg->smax_value = smax_ptr;
			dst_reg->umin_value = umin_ptr;
			dst_reg->umax_value = umax_ptr;
			dst_reg->var_off = ptr_reg->var_off;
			dst_reg->id = ptr_reg->id;
			dst_reg->off = ptr_reg->off - smin_val;
			dst_reg->raw = ptr_reg->raw;
			break;
		}
		/* A new variable offset is created.  If the subtrahend is known
		 * nonnegative, then any reg->range we had before is still good.
		 */
		if (signed_sub_overflows(smin_ptr, smax_val) ||
		    signed_sub_overflows(smax_ptr, smin_val)) {
			/* Overflow possible, we know nothing */
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			dst_reg->smin_value = smin_ptr - smax_val;
			dst_reg->smax_value = smax_ptr - smin_val;
		}
		if (umin_ptr < umax_val) {
			/* Overflow possible, we know nothing */
			dst_reg->umin_value = 0;
			dst_reg->umax_value = U64_MAX;
		} else {
			/* Cannot overflow (as long as bounds are consistent) */
			dst_reg->umin_value = umin_ptr - umax_val;
			dst_reg->umax_value = umax_ptr - umin_val;
		}
		dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
		dst_reg->off = ptr_reg->off;
		dst_reg->raw = ptr_reg->raw;
		if (reg_is_pkt_pointer(ptr_reg)) {
			dst_reg->id = ++env->id_gen;
			/* something was added to pkt_ptr, set range to zero */
			if (smin_val < 0)
				dst_reg->raw = 0;
		}
		break;
	case BPF_AND:
	case BPF_OR:
	case BPF_XOR:
		/* bitwise ops on pointers are troublesome, prohibit. */
		verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
			dst, bpf_alu_string[opcode >> 4]);
		return -EACCES;
	default:
		/* other operators (e.g. MUL,LSH) produce non-pointer results */
		verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
			dst, bpf_alu_string[opcode >> 4]);
		return -EACCES;
	}

	if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
		return -EINVAL;

	__update_reg_bounds(dst_reg);
	__reg_deduce_bounds(dst_reg);
	__reg_bound_offset(dst_reg);

	/* For unprivileged we require that resulting offset must be in bounds
	 * in order to be able to sanitize access later on.
	 */
	if (!env->allow_ptr_leaks) {
		if (dst_reg->type == PTR_TO_MAP_VALUE &&
		    check_map_access(env, dst, dst_reg->off, 1, false)) {
			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
				"prohibited for !root\n", dst);
			return -EACCES;
		} else if (dst_reg->type == PTR_TO_STACK &&
			   check_stack_access(env, dst_reg, dst_reg->off +
					      dst_reg->var_off.value, 1)) {
			verbose(env, "R%d stack pointer arithmetic goes out of range, "
				"prohibited for !root\n", dst);
			return -EACCES;
		}
	}

	return 0;
}

/* WARNING: This function does calculations on 64-bit values, but the actual
 * execution may occur on 32-bit values. Therefore, things like bitshifts
 * need extra checks in the 32-bit case.
 */
static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
				      struct bpf_insn *insn,
				      struct bpf_reg_state *dst_reg,
				      struct bpf_reg_state src_reg)
{
	struct bpf_reg_state *regs = cur_regs(env);
	u8 opcode = BPF_OP(insn->code);
	bool src_known, dst_known;
	s64 smin_val, smax_val;
	u64 umin_val, umax_val;
	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
	u32 dst = insn->dst_reg;
	int ret;

	if (insn_bitness == 32) {
		/* Relevant for 32-bit RSH: Information can propagate towards
		 * LSB, so it isn't sufficient to only truncate the output to
		 * 32 bits.
		 */
		coerce_reg_to_size(dst_reg, 4);
		coerce_reg_to_size(&src_reg, 4);
	}

	smin_val = src_reg.smin_value;
	smax_val = src_reg.smax_value;
	umin_val = src_reg.umin_value;
	umax_val = src_reg.umax_value;
	src_known = tnum_is_const(src_reg.var_off);
	dst_known = tnum_is_const(dst_reg->var_off);

	if ((src_known && (smin_val != smax_val || umin_val != umax_val)) ||
	    smin_val > smax_val || umin_val > umax_val) {
		/* Taint dst register if offset had invalid bounds derived from
		 * e.g. dead branches.
		 */
		__mark_reg_unknown(dst_reg);
		return 0;
	}

	if (!src_known &&
	    opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
		__mark_reg_unknown(dst_reg);
		return 0;
	}

	switch (opcode) {
	case BPF_ADD:
		ret = sanitize_val_alu(env, insn);
		if (ret < 0) {
			verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
			return ret;
		}
		if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
		    signed_add_overflows(dst_reg->smax_value, smax_val)) {
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			dst_reg->smin_value += smin_val;
			dst_reg->smax_value += smax_val;
		}
		if (dst_reg->umin_value + umin_val < umin_val ||
		    dst_reg->umax_value + umax_val < umax_val) {
			dst_reg->umin_value = 0;
			dst_reg->umax_value = U64_MAX;
		} else {
			dst_reg->umin_value += umin_val;
			dst_reg->umax_value += umax_val;
		}
		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
		break;
	case BPF_SUB:
		ret = sanitize_val_alu(env, insn);
		if (ret < 0) {
			verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
			return ret;
		}
		if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
		    signed_sub_overflows(dst_reg->smax_value, smin_val)) {
			/* Overflow possible, we know nothing */
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			dst_reg->smin_value -= smax_val;
			dst_reg->smax_value -= smin_val;
		}
		if (dst_reg->umin_value < umax_val) {
			/* Overflow possible, we know nothing */
			dst_reg->umin_value = 0;
			dst_reg->umax_value = U64_MAX;
		} else {
			/* Cannot overflow (as long as bounds are consistent) */
			dst_reg->umin_value -= umax_val;
			dst_reg->umax_value -= umin_val;
		}
		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
		break;
	case BPF_MUL:
		dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
		if (smin_val < 0 || dst_reg->smin_value < 0) {
			/* Ain't nobody got time to multiply that sign */
			__mark_reg_unbounded(dst_reg);
			__update_reg_bounds(dst_reg);
			break;
		}
		/* Both values are positive, so we can work with unsigned and
		 * copy the result to signed (unless it exceeds S64_MAX).
		 */
		if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
			/* Potential overflow, we know nothing */
			__mark_reg_unbounded(dst_reg);
			/* (except what we can learn from the var_off) */
			__update_reg_bounds(dst_reg);
			break;
		}
		dst_reg->umin_value *= umin_val;
		dst_reg->umax_value *= umax_val;
		if (dst_reg->umax_value > S64_MAX) {
			/* Overflow possible, we know nothing */
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			dst_reg->smin_value = dst_reg->umin_value;
			dst_reg->smax_value = dst_reg->umax_value;
		}
		break;
	case BPF_AND:
		if (src_known && dst_known) {
			__mark_reg_known(dst_reg, dst_reg->var_off.value &
						  src_reg.var_off.value);
			break;
		}
		/* We get our minimum from the var_off, since that's inherently
		 * bitwise.  Our maximum is the minimum of the operands' maxima.
		 */
		dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
		dst_reg->umin_value = dst_reg->var_off.value;
		dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
		if (dst_reg->smin_value < 0 || smin_val < 0) {
			/* Lose signed bounds when ANDing negative numbers,
			 * ain't nobody got time for that.
			 */
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			/* ANDing two positives gives a positive, so safe to
			 * cast result into s64.
			 */
			dst_reg->smin_value = dst_reg->umin_value;
			dst_reg->smax_value = dst_reg->umax_value;
		}
		/* We may learn something more from the var_off */
		__update_reg_bounds(dst_reg);
		break;
	case BPF_OR:
		if (src_known && dst_known) {
			__mark_reg_known(dst_reg, dst_reg->var_off.value |
						  src_reg.var_off.value);
			break;
		}
		/* We get our maximum from the var_off, and our minimum is the
		 * maximum of the operands' minima
		 */
		dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
		dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
		dst_reg->umax_value = dst_reg->var_off.value |
				      dst_reg->var_off.mask;
		if (dst_reg->smin_value < 0 || smin_val < 0) {
			/* Lose signed bounds when ORing negative numbers,
			 * ain't nobody got time for that.
			 */
			dst_reg->smin_value = S64_MIN;
			dst_reg->smax_value = S64_MAX;
		} else {
			/* ORing two positives gives a positive, so safe to
			 * cast result into s64.
			 */
			dst_reg->smin_value = dst_reg->umin_value;
			dst_reg->smax_value = dst_reg->umax_value;
		}
		/* We may learn something more from the var_off */
		__update_reg_bounds(dst_reg);
		break;
	case BPF_LSH:
		if (umax_val >= insn_bitness) {
			/* Shifts greater than 31 or 63 are undefined.
			 * This includes shifts by a negative number.
			 */
			mark_reg_unknown(env, regs, insn->dst_reg);
			break;
		}
		/* We lose all sign bit information (except what we can pick
		 * up from var_off)
		 */
		dst_reg->smin_value = S64_MIN;
		dst_reg->smax_value = S64_MAX;
		/* If we might shift our top bit out, then we know nothing */
		if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
			dst_reg->umin_value = 0;
			dst_reg->umax_value = U64_MAX;
		} else {
			dst_reg->umin_value <<= umin_val;
			dst_reg->umax_value <<= umax_val;
		}
		dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
		/* We may learn something more from the var_off */
		__update_reg_bounds(dst_reg);
		break;
	case BPF_RSH:
		if (umax_val >= insn_bitness) {
			/* Shifts greater than 31 or 63 are undefined.
			 * This includes shifts by a negative number.
			 */
			mark_reg_unknown(env, regs, insn->dst_reg);
			break;
		}
		/* BPF_RSH is an unsigned shift.  If the value in dst_reg might
		 * be negative, then either:
		 * 1) src_reg might be zero, so the sign bit of the result is
		 *    unknown, so we lose our signed bounds
		 * 2) it's known negative, thus the unsigned bounds capture the
		 *    signed bounds
		 * 3) the signed bounds cross zero, so they tell us nothing
		 *    about the result
		 * If the value in dst_reg is known nonnegative, then again the
		 * unsigned bounts capture the signed bounds.
		 * Thus, in all cases it suffices to blow away our signed bounds
		 * and rely on inferring new ones from the unsigned bounds and
		 * var_off of the result.
		 */
		dst_reg->smin_value = S64_MIN;
		dst_reg->smax_value = S64_MAX;
		dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
		dst_reg->umin_value >>= umax_val;
		dst_reg->umax_value >>= umin_val;
		/* We may learn something more from the var_off */
		__update_reg_bounds(dst_reg);
		break;
	case BPF_ARSH:
		if (umax_val >= insn_bitness) {
			/* Shifts greater than 31 or 63 are undefined.
			 * This includes shifts by a negative number.
			 */
			mark_reg_unknown(env, regs, insn->dst_reg);
			break;
		}

		/* Upon reaching here, src_known is true and
		 * umax_val is equal to umin_val.
		 */
		dst_reg->smin_value >>= umin_val;
		dst_reg->smax_value >>= umin_val;
		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);

		/* blow away the dst_reg umin_value/umax_value and rely on
		 * dst_reg var_off to refine the result.
		 */
		dst_reg->umin_value = 0;
		dst_reg->umax_value = U64_MAX;
		__update_reg_bounds(dst_reg);
		break;
	default:
		mark_reg_unknown(env, regs, insn->dst_reg);
		break;
	}

	if (BPF_CLASS(insn->code) != BPF_ALU64) {
		/* 32-bit ALU ops are (32,32)->32 */
		coerce_reg_to_size(dst_reg, 4);
	}

	__reg_deduce_bounds(dst_reg);
	__reg_bound_offset(dst_reg);
	return 0;
}

/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max
 * and var_off.
 */
static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
				   struct bpf_insn *insn)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
	u8 opcode = BPF_OP(insn->code);

	dst_reg = &regs[insn->dst_reg];
	src_reg = NULL;
	if (dst_reg->type != SCALAR_VALUE)
		ptr_reg = dst_reg;
	if (BPF_SRC(insn->code) == BPF_X) {
		src_reg = &regs[insn->src_reg];
		if (src_reg->type != SCALAR_VALUE) {
			if (dst_reg->type != SCALAR_VALUE) {
				/* Combining two pointers by any ALU op yields
				 * an arbitrary scalar. Disallow all math except
				 * pointer subtraction
				 */
				if (opcode == BPF_SUB && env->allow_ptr_leaks) {
					mark_reg_unknown(env, regs, insn->dst_reg);
					return 0;
				}
				verbose(env, "R%d pointer %s pointer prohibited\n",
					insn->dst_reg,
					bpf_alu_string[opcode >> 4]);
				return -EACCES;
			} else {
				/* scalar += pointer
				 * This is legal, but we have to reverse our
				 * src/dest handling in computing the range
				 */
				return adjust_ptr_min_max_vals(env, insn,
							       src_reg, dst_reg);
			}
		} else if (ptr_reg) {
			/* pointer += scalar */
			return adjust_ptr_min_max_vals(env, insn,
						       dst_reg, src_reg);
		}
	} else {
		/* Pretend the src is a reg with a known value, since we only
		 * need to be able to read from this state.
		 */
		off_reg.type = SCALAR_VALUE;
		__mark_reg_known(&off_reg, insn->imm);
		src_reg = &off_reg;
		if (ptr_reg) /* pointer += K */
			return adjust_ptr_min_max_vals(env, insn,
						       ptr_reg, src_reg);
	}

	/* Got here implies adding two SCALAR_VALUEs */
	if (WARN_ON_ONCE(ptr_reg)) {
		print_verifier_state(env, state);
		verbose(env, "verifier internal error: unexpected ptr_reg\n");
		return -EINVAL;
	}
	if (WARN_ON(!src_reg)) {
		print_verifier_state(env, state);
		verbose(env, "verifier internal error: no src_reg\n");
		return -EINVAL;
	}
	return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
}

/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_reg_state *regs = cur_regs(env);
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode == BPF_END || opcode == BPF_NEG) {
		if (opcode == BPF_NEG) {
			if (BPF_SRC(insn->code) != 0 ||
			    insn->src_reg != BPF_REG_0 ||
			    insn->off != 0 || insn->imm != 0) {
				verbose(env, "BPF_NEG uses reserved fields\n");
				return -EINVAL;
			}
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
			    BPF_CLASS(insn->code) == BPF_ALU64) {
				verbose(env, "BPF_END uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src operand */
		err = check_reg_arg(env, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		if (is_pointer_value(env, insn->dst_reg)) {
			verbose(env, "R%d pointer arithmetic prohibited\n",
				insn->dst_reg);
			return -EACCES;
		}

		/* check dest operand */
		err = check_reg_arg(env, insn->dst_reg, DST_OP);
		if (err)
			return err;

	} else if (opcode == BPF_MOV) {

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose(env, "BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}

			/* check src operand */
			err = check_reg_arg(env, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose(env, "BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check dest operand, mark as required later */
		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
		if (err)
			return err;

		if (BPF_SRC(insn->code) == BPF_X) {
			struct bpf_reg_state *src_reg = regs + insn->src_reg;
			struct bpf_reg_state *dst_reg = regs + insn->dst_reg;

			if (BPF_CLASS(insn->code) == BPF_ALU64) {
				/* case: R1 = R2
				 * copy register state to dest reg
				 */
				*dst_reg = *src_reg;
				dst_reg->live |= REG_LIVE_WRITTEN;
			} else {
				/* R1 = (u32) R2 */
				if (is_pointer_value(env, insn->src_reg)) {
					verbose(env,
						"R%d partial copy of pointer\n",
						insn->src_reg);
					return -EACCES;
				} else if (src_reg->type == SCALAR_VALUE) {
					*dst_reg = *src_reg;
					dst_reg->live |= REG_LIVE_WRITTEN;
				} else {
					mark_reg_unknown(env, regs,
							 insn->dst_reg);
				}
				coerce_reg_to_size(dst_reg, 4);
			}
		} else {
			/* case: R = imm
			 * remember the value we stored into this reg
			 */
			/* clear any state __mark_reg_known doesn't set */
			mark_reg_unknown(env, regs, insn->dst_reg);
			regs[insn->dst_reg].type = SCALAR_VALUE;
			if (BPF_CLASS(insn->code) == BPF_ALU64) {
				__mark_reg_known(regs + insn->dst_reg,
						 insn->imm);
			} else {
				__mark_reg_known(regs + insn->dst_reg,
						 (u32)insn->imm);
			}
		}

	} else if (opcode > BPF_END) {
		verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
		return -EINVAL;

	} else {	/* all other ALU ops: and, sub, xor, add, ... */

		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || insn->off != 0) {
				verbose(env, "BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
			/* check src1 operand */
			err = check_reg_arg(env, insn->src_reg, SRC_OP);
			if (err)
				return err;
		} else {
			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
				verbose(env, "BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
		}

		/* check src2 operand */
		err = check_reg_arg(env, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
		    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
			verbose(env, "div by zero\n");
			return -EINVAL;
		}

		if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
			verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
			return -EINVAL;
		}

		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;

			if (insn->imm < 0 || insn->imm >= size) {
				verbose(env, "invalid shift %d\n", insn->imm);
				return -EINVAL;
			}
		}

		/* check dest operand */
		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
		if (err)
			return err;

		return adjust_reg_min_max_vals(env, insn);
	}

	return 0;
}

static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
				   struct bpf_reg_state *dst_reg,
				   enum bpf_reg_type type,
				   bool range_right_open)
{
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs, *reg;
	u16 new_range;
	int i, j;

	if (dst_reg->off < 0 ||
	    (dst_reg->off == 0 && range_right_open))
		/* This doesn't give us any range */
		return;

	if (dst_reg->umax_value > MAX_PACKET_OFF ||
	    dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF)
		/* Risk of overflow.  For instance, ptr + (1<<63) may be less
		 * than pkt_end, but that's because it's also less than pkt.
		 */
		return;

	new_range = dst_reg->off;
	if (range_right_open)
		new_range--;

	/* Examples for register markings:
	 *
	 * pkt_data in dst register:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (r2 > pkt_end) goto <handle exception>
	 *   <access okay>
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (r2 < pkt_end) goto <access okay>
	 *   <handle exception>
	 *
	 *   Where:
	 *     r2 == dst_reg, pkt_end == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * pkt_data in src register:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (pkt_end >= r2) goto <access okay>
	 *   <handle exception>
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (pkt_end <= r2) goto <handle exception>
	 *   <access okay>
	 *
	 *   Where:
	 *     pkt_end == dst_reg, r2 == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
	 * and [r3, r3 + 8-1) respectively is safe to access depending on
	 * the check.
	 */

	/* If our ids match, then we must have the same max_value.  And we
	 * don't care about the other reg's fixed offset, since if it's too big
	 * the range won't allow anything.
	 * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
	 */
	for (i = 0; i < MAX_BPF_REG; i++)
		if (regs[i].type == type && regs[i].id == dst_reg->id)
			/* keep the maximum range already checked */
			regs[i].range = max(regs[i].range, new_range);

	for (j = 0; j <= vstate->curframe; j++) {
		state = vstate->frame[j];
		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
			if (state->stack[i].slot_type[0] != STACK_SPILL)
				continue;
			reg = &state->stack[i].spilled_ptr;
			if (reg->type == type && reg->id == dst_reg->id)
				reg->range = max(reg->range, new_range);
		}
	}
}

/* compute branch direction of the expression "if (reg opcode val) goto target;"
 * and return:
 *  1 - branch will be taken and "goto target" will be executed
 *  0 - branch will not be taken and fall-through to next insn
 * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
 */
static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
{
	if (__is_pointer_value(false, reg))
		return -1;

	switch (opcode) {
	case BPF_JEQ:
		if (tnum_is_const(reg->var_off))
			return !!tnum_equals_const(reg->var_off, val);
		break;
	case BPF_JNE:
		if (tnum_is_const(reg->var_off))
			return !tnum_equals_const(reg->var_off, val);
		break;
	case BPF_JGT:
		if (reg->umin_value > val)
			return 1;
		else if (reg->umax_value <= val)
			return 0;
		break;
	case BPF_JSGT:
		if (reg->smin_value > (s64)val)
			return 1;
		else if (reg->smax_value < (s64)val)
			return 0;
		break;
	case BPF_JLT:
		if (reg->umax_value < val)
			return 1;
		else if (reg->umin_value >= val)
			return 0;
		break;
	case BPF_JSLT:
		if (reg->smax_value < (s64)val)
			return 1;
		else if (reg->smin_value >= (s64)val)
			return 0;
		break;
	case BPF_JGE:
		if (reg->umin_value >= val)
			return 1;
		else if (reg->umax_value < val)
			return 0;
		break;
	case BPF_JSGE:
		if (reg->smin_value >= (s64)val)
			return 1;
		else if (reg->smax_value < (s64)val)
			return 0;
		break;
	case BPF_JLE:
		if (reg->umax_value <= val)
			return 1;
		else if (reg->umin_value > val)
			return 0;
		break;
	case BPF_JSLE:
		if (reg->smax_value <= (s64)val)
			return 1;
		else if (reg->smin_value > (s64)val)
			return 0;
		break;
	}

	return -1;
}

/* Adjusts the register min/max values in the case that the dst_reg is the
 * variable register that we are working on, and src_reg is a constant or we're
 * simply doing a BPF_K check.
 * In JEQ/JNE cases we also adjust the var_off values.
 */
static void reg_set_min_max(struct bpf_reg_state *true_reg,
			    struct bpf_reg_state *false_reg, u64 val,
			    u8 opcode)
{
	/* If the dst_reg is a pointer, we can't learn anything about its
	 * variable offset from the compare (unless src_reg were a pointer into
	 * the same object, but we don't bother with that.
	 * Since false_reg and true_reg have the same type by construction, we
	 * only need to check one of them for pointerness.
	 */
	if (__is_pointer_value(false, false_reg))
		return;

	switch (opcode) {
	case BPF_JEQ:
		/* If this is false then we know nothing Jon Snow, but if it is
		 * true then we know for sure.
		 */
		__mark_reg_known(true_reg, val);
		break;
	case BPF_JNE:
		/* If this is true we know nothing Jon Snow, but if it is false
		 * we know the value for sure;
		 */
		__mark_reg_known(false_reg, val);
		break;
	case BPF_JGT:
		false_reg->umax_value = min(false_reg->umax_value, val);
		true_reg->umin_value = max(true_reg->umin_value, val + 1);
		break;
	case BPF_JSGT:
		false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
		true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
		break;
	case BPF_JLT:
		false_reg->umin_value = max(false_reg->umin_value, val);
		true_reg->umax_value = min(true_reg->umax_value, val - 1);
		break;
	case BPF_JSLT:
		false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
		true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
		break;
	case BPF_JGE:
		false_reg->umax_value = min(false_reg->umax_value, val - 1);
		true_reg->umin_value = max(true_reg->umin_value, val);
		break;
	case BPF_JSGE:
		false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
		true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
		break;
	case BPF_JLE:
		false_reg->umin_value = max(false_reg->umin_value, val + 1);
		true_reg->umax_value = min(true_reg->umax_value, val);
		break;
	case BPF_JSLE:
		false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
		true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
		break;
	default:
		break;
	}

	__reg_deduce_bounds(false_reg);
	__reg_deduce_bounds(true_reg);
	/* We might have learned some bits from the bounds. */
	__reg_bound_offset(false_reg);
	__reg_bound_offset(true_reg);
	/* Intersecting with the old var_off might have improved our bounds
	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
	 * then new var_off is (0; 0x7f...fc) which improves our umax.
	 */
	__update_reg_bounds(false_reg);
	__update_reg_bounds(true_reg);
}

/* Same as above, but for the case that dst_reg holds a constant and src_reg is
 * the variable reg.
 */
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
				struct bpf_reg_state *false_reg, u64 val,
				u8 opcode)
{
	if (__is_pointer_value(false, false_reg))
		return;

	switch (opcode) {
	case BPF_JEQ:
		/* If this is false then we know nothing Jon Snow, but if it is
		 * true then we know for sure.
		 */
		__mark_reg_known(true_reg, val);
		break;
	case BPF_JNE:
		/* If this is true we know nothing Jon Snow, but if it is false
		 * we know the value for sure;
		 */
		__mark_reg_known(false_reg, val);
		break;
	case BPF_JGT:
		true_reg->umax_value = min(true_reg->umax_value, val - 1);
		false_reg->umin_value = max(false_reg->umin_value, val);
		break;
	case BPF_JSGT:
		true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
		false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
		break;
	case BPF_JLT:
		true_reg->umin_value = max(true_reg->umin_value, val + 1);
		false_reg->umax_value = min(false_reg->umax_value, val);
		break;
	case BPF_JSLT:
		true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
		false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
		break;
	case BPF_JGE:
		true_reg->umax_value = min(true_reg->umax_value, val);
		false_reg->umin_value = max(false_reg->umin_value, val + 1);
		break;
	case BPF_JSGE:
		true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
		false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
		break;
	case BPF_JLE:
		true_reg->umin_value = max(true_reg->umin_value, val);
		false_reg->umax_value = min(false_reg->umax_value, val - 1);
		break;
	case BPF_JSLE:
		true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
		false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
		break;
	default:
		break;
	}

	__reg_deduce_bounds(false_reg);
	__reg_deduce_bounds(true_reg);
	/* We might have learned some bits from the bounds. */
	__reg_bound_offset(false_reg);
	__reg_bound_offset(true_reg);
	/* Intersecting with the old var_off might have improved our bounds
	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
	 * then new var_off is (0; 0x7f...fc) which improves our umax.
	 */
	__update_reg_bounds(false_reg);
	__update_reg_bounds(true_reg);
}

/* Regs are known to be equal, so intersect their min/max/var_off */
static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
				  struct bpf_reg_state *dst_reg)
{
	src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
							dst_reg->umin_value);
	src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
							dst_reg->umax_value);
	src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
							dst_reg->smin_value);
	src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
							dst_reg->smax_value);
	src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
							     dst_reg->var_off);
	/* We might have learned new bounds from the var_off. */
	__update_reg_bounds(src_reg);
	__update_reg_bounds(dst_reg);
	/* We might have learned something about the sign bit. */
	__reg_deduce_bounds(src_reg);
	__reg_deduce_bounds(dst_reg);
	/* We might have learned some bits from the bounds. */
	__reg_bound_offset(src_reg);
	__reg_bound_offset(dst_reg);
	/* Intersecting with the old var_off might have improved our bounds
	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
	 * then new var_off is (0; 0x7f...fc) which improves our umax.
	 */
	__update_reg_bounds(src_reg);
	__update_reg_bounds(dst_reg);
}

static void reg_combine_min_max(struct bpf_reg_state *true_src,
				struct bpf_reg_state *true_dst,
				struct bpf_reg_state *false_src,
				struct bpf_reg_state *false_dst,
				u8 opcode)
{
	switch (opcode) {
	case BPF_JEQ:
		__reg_combine_min_max(true_src, true_dst);
		break;
	case BPF_JNE:
		__reg_combine_min_max(false_src, false_dst);
		break;
	}
}

static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
			 bool is_null)
{
	struct bpf_reg_state *reg = &regs[regno];

	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
		/* Old offset (both fixed and variable parts) should
		 * have been known-zero, because we don't allow pointer
		 * arithmetic on pointers that might be NULL.
		 */
		if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
				 !tnum_equals_const(reg->var_off, 0) ||
				 reg->off)) {
			__mark_reg_known_zero(reg);
			reg->off = 0;
		}
		if (is_null) {
			reg->type = SCALAR_VALUE;
		} else if (reg->map_ptr->inner_map_meta) {
			reg->type = CONST_PTR_TO_MAP;
			reg->map_ptr = reg->map_ptr->inner_map_meta;
		} else {
			reg->type = PTR_TO_MAP_VALUE;
		}
		/* We don't need id from this point onwards anymore, thus we
		 * should better reset it, so that state pruning has chances
		 * to take effect.
		 */
		reg->id = 0;
	}
}

/* The logic is similar to find_good_pkt_pointers(), both could eventually
 * be folded together at some point.
 */
static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno,
			  bool is_null)
{
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs;
	u32 id = regs[regno].id;
	int i, j;

	for (i = 0; i < MAX_BPF_REG; i++)
		mark_map_reg(regs, i, id, is_null);

	for (j = 0; j <= vstate->curframe; j++) {
		state = vstate->frame[j];
		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
			if (state->stack[i].slot_type[0] != STACK_SPILL)
				continue;
			mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
		}
	}
}

static bool try_match_pkt_pointers(const struct bpf_insn *insn,
				   struct bpf_reg_state *dst_reg,
				   struct bpf_reg_state *src_reg,
				   struct bpf_verifier_state *this_branch,
				   struct bpf_verifier_state *other_branch)
{
	if (BPF_SRC(insn->code) != BPF_X)
		return false;

	switch (BPF_OP(insn->code)) {
	case BPF_JGT:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
			find_good_pkt_pointers(this_branch, dst_reg,
					       dst_reg->type, false);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end > pkt_data', pkt_data > pkt_meta' */
			find_good_pkt_pointers(other_branch, src_reg,
					       src_reg->type, true);
		} else {
			return false;
		}
		break;
	case BPF_JLT:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
			find_good_pkt_pointers(other_branch, dst_reg,
					       dst_reg->type, true);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end < pkt_data', pkt_data > pkt_meta' */
			find_good_pkt_pointers(this_branch, src_reg,
					       src_reg->type, false);
		} else {
			return false;
		}
		break;
	case BPF_JGE:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
			find_good_pkt_pointers(this_branch, dst_reg,
					       dst_reg->type, true);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
			find_good_pkt_pointers(other_branch, src_reg,
					       src_reg->type, false);
		} else {
			return false;
		}
		break;
	case BPF_JLE:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
			find_good_pkt_pointers(other_branch, dst_reg,
					       dst_reg->type, false);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
			find_good_pkt_pointers(this_branch, src_reg,
					       src_reg->type, true);
		} else {
			return false;
		}
		break;
	default:
		return false;
	}

	return true;
}

static int check_cond_jmp_op(struct bpf_verifier_env *env,
			     struct bpf_insn *insn, int *insn_idx)
{
	struct bpf_verifier_state *this_branch = env->cur_state;
	struct bpf_verifier_state *other_branch;
	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
	struct bpf_reg_state *dst_reg, *other_branch_regs;
	u8 opcode = BPF_OP(insn->code);
	int err;

	if (opcode > BPF_JSLE) {
		verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
		return -EINVAL;
	}

	if (BPF_SRC(insn->code) == BPF_X) {
		if (insn->imm != 0) {
			verbose(env, "BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}

		/* check src1 operand */
		err = check_reg_arg(env, insn->src_reg, SRC_OP);
		if (err)
			return err;

		if (is_pointer_value(env, insn->src_reg)) {
			verbose(env, "R%d pointer comparison prohibited\n",
				insn->src_reg);
			return -EACCES;
		}
	} else {
		if (insn->src_reg != BPF_REG_0) {
			verbose(env, "BPF_JMP uses reserved fields\n");
			return -EINVAL;
		}
	}

	/* check src2 operand */
	err = check_reg_arg(env, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	dst_reg = &regs[insn->dst_reg];

	if (BPF_SRC(insn->code) == BPF_K) {
		int pred = is_branch_taken(dst_reg, insn->imm, opcode);

		if (pred == 1) {
			 /* only follow the goto, ignore fall-through */
			*insn_idx += insn->off;
			return 0;
		} else if (pred == 0) {
			/* only follow fall-through branch, since
			 * that's where the program will go
			 */
			return 0;
		}
	}

	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
				  false);
	if (!other_branch)
		return -EFAULT;
	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;

	/* detect if we are comparing against a constant value so we can adjust
	 * our min/max values for our dst register.
	 * this is only legit if both are scalars (or pointers to the same
	 * object, I suppose, but we don't support that right now), because
	 * otherwise the different base pointers mean the offsets aren't
	 * comparable.
	 */
	if (BPF_SRC(insn->code) == BPF_X) {
		if (dst_reg->type == SCALAR_VALUE &&
		    regs[insn->src_reg].type == SCALAR_VALUE) {
			if (tnum_is_const(regs[insn->src_reg].var_off))
				reg_set_min_max(&other_branch_regs[insn->dst_reg],
						dst_reg, regs[insn->src_reg].var_off.value,
						opcode);
			else if (tnum_is_const(dst_reg->var_off))
				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
						    &regs[insn->src_reg],
						    dst_reg->var_off.value, opcode);
			else if (opcode == BPF_JEQ || opcode == BPF_JNE)
				/* Comparing for equality, we can combine knowledge */
				reg_combine_min_max(&other_branch_regs[insn->src_reg],
						    &other_branch_regs[insn->dst_reg],
						    &regs[insn->src_reg],
						    &regs[insn->dst_reg], opcode);
		}
	} else if (dst_reg->type == SCALAR_VALUE) {
		reg_set_min_max(&other_branch_regs[insn->dst_reg],
					dst_reg, insn->imm, opcode);
	}

	/* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
	if (BPF_SRC(insn->code) == BPF_K &&
	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
	    dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
		/* Mark all identical map registers in each branch as either
		 * safe or unknown depending R == 0 or R != 0 conditional.
		 */
		mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
		mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
	} else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
					   this_branch, other_branch) &&
		   is_pointer_value(env, insn->dst_reg)) {
		verbose(env, "R%d pointer comparison prohibited\n",
			insn->dst_reg);
		return -EACCES;
	}
	if (env->log.level)
		print_verifier_state(env, this_branch->frame[this_branch->curframe]);
	return 0;
}

/* return the map pointer stored inside BPF_LD_IMM64 instruction */
static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
{
	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;

	return (struct bpf_map *) (unsigned long) imm64;
}

/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_reg_state *regs = cur_regs(env);
	int err;

	if (BPF_SIZE(insn->code) != BPF_DW) {
		verbose(env, "invalid BPF_LD_IMM insn\n");
		return -EINVAL;
	}
	if (insn->off != 0) {
		verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
		return -EINVAL;
	}

	err = check_reg_arg(env, insn->dst_reg, DST_OP);
	if (err)
		return err;

	if (insn->src_reg == 0) {
		u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;

		regs[insn->dst_reg].type = SCALAR_VALUE;
		__mark_reg_known(&regs[insn->dst_reg], imm);
		return 0;
	}

	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);

	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
	return 0;
}

static bool may_access_skb(enum bpf_prog_type type)
{
	switch (type) {
	case BPF_PROG_TYPE_SOCKET_FILTER:
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
		return true;
	default:
		return false;
	}
}

/* verify safety of LD_ABS|LD_IND instructions:
 * - they can only appear in the programs where ctx == skb
 * - since they are wrappers of function calls, they scratch R1-R5 registers,
 *   preserve R6-R9, and store return value into R0
 *
 * Implicit input:
 *   ctx == skb == R6 == CTX
 *
 * Explicit input:
 *   SRC == any register
 *   IMM == 32-bit immediate
 *
 * Output:
 *   R0 - 8/16/32-bit skb data converted to cpu endianness
 */
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_reg_state *regs = cur_regs(env);
	u8 mode = BPF_MODE(insn->code);
	int i, err;

	if (!may_access_skb(env->prog->type)) {
		verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
		return -EINVAL;
	}

	if (!env->ops->gen_ld_abs) {
		verbose(env, "bpf verifier is misconfigured\n");
		return -EINVAL;
	}

	if (env->subprog_cnt > 1) {
		/* when program has LD_ABS insn JITs and interpreter assume
		 * that r1 == ctx == skb which is not the case for callees
		 * that can have arbitrary arguments. It's problematic
		 * for main prog as well since JITs would need to analyze
		 * all functions in order to make proper register save/restore
		 * decisions in the main prog. Hence disallow LD_ABS with calls
		 */
		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
		return -EINVAL;
	}

	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
	    BPF_SIZE(insn->code) == BPF_DW ||
	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
		verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
		return -EINVAL;
	}

	/* check whether implicit source operand (register R6) is readable */
	err = check_reg_arg(env, BPF_REG_6, SRC_OP);
	if (err)
		return err;

	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
		verbose(env,
			"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
		return -EINVAL;
	}

	if (mode == BPF_IND) {
		/* check explicit source operand */
		err = check_reg_arg(env, insn->src_reg, SRC_OP);
		if (err)
			return err;
	}

	/* reset caller saved regs to unreadable */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		mark_reg_not_init(env, regs, caller_saved[i]);
		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
	}

	/* mark destination R0 register as readable, since it contains
	 * the value fetched from the packet.
	 * Already marked as written above.
	 */
	mark_reg_unknown(env, regs, BPF_REG_0);
	return 0;
}

static int check_return_code(struct bpf_verifier_env *env)
{
	struct bpf_reg_state *reg;
	struct tnum range = tnum_range(0, 1);

	switch (env->prog->type) {
	case BPF_PROG_TYPE_CGROUP_SKB:
	case BPF_PROG_TYPE_CGROUP_SOCK:
	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
	case BPF_PROG_TYPE_SOCK_OPS:
	case BPF_PROG_TYPE_CGROUP_DEVICE:
		break;
	default:
		return 0;
	}

	reg = cur_regs(env) + BPF_REG_0;
	if (reg->type != SCALAR_VALUE) {
		verbose(env, "At program exit the register R0 is not a known value (%s)\n",
			reg_type_str[reg->type]);
		return -EINVAL;
	}

	if (!tnum_in(range, reg->var_off)) {
		verbose(env, "At program exit the register R0 ");
		if (!tnum_is_unknown(reg->var_off)) {
			char tn_buf[48];

			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
			verbose(env, "has value %s", tn_buf);
		} else {
			verbose(env, "has unknown scalar value");
		}
		verbose(env, " should have been 0 or 1\n");
		return -EINVAL;
	}
	return 0;
}

/* non-recursive DFS pseudo code
 * 1  procedure DFS-iterative(G,v):
 * 2      label v as discovered
 * 3      let S be a stack
 * 4      S.push(v)
 * 5      while S is not empty
 * 6            t <- S.pop()
 * 7            if t is what we're looking for:
 * 8                return t
 * 9            for all edges e in G.adjacentEdges(t) do
 * 10               if edge e is already labelled
 * 11                   continue with the next edge
 * 12               w <- G.adjacentVertex(t,e)
 * 13               if vertex w is not discovered and not explored
 * 14                   label e as tree-edge
 * 15                   label w as discovered
 * 16                   S.push(w)
 * 17                   continue at 5
 * 18               else if vertex w is discovered
 * 19                   label e as back-edge
 * 20               else
 * 21                   // vertex w is explored
 * 22                   label e as forward- or cross-edge
 * 23           label t as explored
 * 24           S.pop()
 *
 * convention:
 * 0x10 - discovered
 * 0x11 - discovered and fall-through edge labelled
 * 0x12 - discovered and fall-through and branch edges labelled
 * 0x20 - explored
 */

enum {
	DISCOVERED = 0x10,
	EXPLORED = 0x20,
	FALLTHROUGH = 1,
	BRANCH = 2,
};

#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)

static int *insn_stack;	/* stack of insns to process */
static int cur_stack;	/* current stack index */
static int *insn_state;

/* t, w, e - match pseudo-code above:
 * t - index of current instruction
 * w - next instruction
 * e - edge
 */
static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
	if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
		return 0;

	if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
		return 0;

	if (w < 0 || w >= env->prog->len) {
		verbose(env, "jump out of range from insn %d to %d\n", t, w);
		return -EINVAL;
	}

	if (e == BRANCH)
		/* mark branch target for state pruning */
		env->explored_states[w] = STATE_LIST_MARK;

	if (insn_state[w] == 0) {
		/* tree-edge */
		insn_state[t] = DISCOVERED | e;
		insn_state[w] = DISCOVERED;
		if (cur_stack >= env->prog->len)
			return -E2BIG;
		insn_stack[cur_stack++] = w;
		return 1;
	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
		verbose(env, "back-edge from insn %d to %d\n", t, w);
		return -EINVAL;
	} else if (insn_state[w] == EXPLORED) {
		/* forward- or cross-edge */
		insn_state[t] = DISCOVERED | e;
	} else {
		verbose(env, "insn state internal bug\n");
		return -EFAULT;
	}
	return 0;
}

/* non-recursive depth-first-search to detect loops in BPF program
 * loop == back-edge in directed graph
 */
static int check_cfg(struct bpf_verifier_env *env)
{
	struct bpf_insn *insns = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int ret = 0;
	int i, t;

	ret = check_subprogs(env);
	if (ret < 0)
		return ret;

	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_state)
		return -ENOMEM;

	insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
	if (!insn_stack) {
		kfree(insn_state);
		return -ENOMEM;
	}

	insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
	insn_stack[0] = 0; /* 0 is the first instruction */
	cur_stack = 1;

peek_stack:
	if (cur_stack == 0)
		goto check_state;
	t = insn_stack[cur_stack - 1];

	if (BPF_CLASS(insns[t].code) == BPF_JMP) {
		u8 opcode = BPF_OP(insns[t].code);

		if (opcode == BPF_EXIT) {
			goto mark_explored;
		} else if (opcode == BPF_CALL) {
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
			if (t + 1 < insn_cnt)
				env->explored_states[t + 1] = STATE_LIST_MARK;
			if (insns[t].src_reg == BPF_PSEUDO_CALL) {
				env->explored_states[t] = STATE_LIST_MARK;
				ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
				if (ret == 1)
					goto peek_stack;
				else if (ret < 0)
					goto err_free;
			}
		} else if (opcode == BPF_JA) {
			if (BPF_SRC(insns[t].code) != BPF_K) {
				ret = -EINVAL;
				goto err_free;
			}
			/* unconditional jump with single edge */
			ret = push_insn(t, t + insns[t].off + 1,
					FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
			/* tell verifier to check for equivalent states
			 * after every call and jump
			 */
			if (t + 1 < insn_cnt)
				env->explored_states[t + 1] = STATE_LIST_MARK;
		} else {
			/* conditional jump with two edges */
			env->explored_states[t] = STATE_LIST_MARK;
			ret = push_insn(t, t + 1, FALLTHROUGH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;

			ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
			if (ret == 1)
				goto peek_stack;
			else if (ret < 0)
				goto err_free;
		}
	} else {
		/* all other non-branch instructions with single
		 * fall-through edge
		 */
		ret = push_insn(t, t + 1, FALLTHROUGH, env);
		if (ret == 1)
			goto peek_stack;
		else if (ret < 0)
			goto err_free;
	}

mark_explored:
	insn_state[t] = EXPLORED;
	if (cur_stack-- <= 0) {
		verbose(env, "pop stack internal bug\n");
		ret = -EFAULT;
		goto err_free;
	}
	goto peek_stack;

check_state:
	for (i = 0; i < insn_cnt; i++) {
		if (insn_state[i] != EXPLORED) {
			verbose(env, "unreachable insn %d\n", i);
			ret = -EINVAL;
			goto err_free;
		}
	}
	ret = 0; /* cfg looks good */

err_free:
	kfree(insn_state);
	kfree(insn_stack);
	return ret;
}

/* check %cur's range satisfies %old's */
static bool range_within(struct bpf_reg_state *old,
			 struct bpf_reg_state *cur)
{
	return old->umin_value <= cur->umin_value &&
	       old->umax_value >= cur->umax_value &&
	       old->smin_value <= cur->smin_value &&
	       old->smax_value >= cur->smax_value;
}

/* Maximum number of register states that can exist at once */
#define ID_MAP_SIZE	(MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
struct idpair {
	u32 old;
	u32 cur;
};

/* If in the old state two registers had the same id, then they need to have
 * the same id in the new state as well.  But that id could be different from
 * the old state, so we need to track the mapping from old to new ids.
 * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent
 * regs with old id 5 must also have new id 9 for the new state to be safe.  But
 * regs with a different old id could still have new id 9, we don't care about
 * that.
 * So we look through our idmap to see if this old id has been seen before.  If
 * so, we require the new id to match; otherwise, we add the id pair to the map.
 */
static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
{
	unsigned int i;

	for (i = 0; i < ID_MAP_SIZE; i++) {
		if (!idmap[i].old) {
			/* Reached an empty slot; haven't seen this id before */
			idmap[i].old = old_id;
			idmap[i].cur = cur_id;
			return true;
		}
		if (idmap[i].old == old_id)
			return idmap[i].cur == cur_id;
	}
	/* We ran out of idmap slots, which should be impossible */
	WARN_ON_ONCE(1);
	return false;
}

/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
		    struct idpair *idmap)
{
	bool equal;

	if (!(rold->live & REG_LIVE_READ))
		/* explored state didn't use this */
		return true;

	equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0;

	if (rold->type == PTR_TO_STACK)
		/* two stack pointers are equal only if they're pointing to
		 * the same stack frame, since fp-8 in foo != fp-8 in bar
		 */
		return equal && rold->frameno == rcur->frameno;

	if (equal)
		return true;

	if (rold->type == NOT_INIT)
		/* explored state can't have used this */
		return true;
	if (rcur->type == NOT_INIT)
		return false;
	switch (rold->type) {
	case SCALAR_VALUE:
		if (rcur->type == SCALAR_VALUE) {
			/* new val must satisfy old val knowledge */
			return range_within(rold, rcur) &&
			       tnum_in(rold->var_off, rcur->var_off);
		} else {
			/* We're trying to use a pointer in place of a scalar.
			 * Even if the scalar was unbounded, this could lead to
			 * pointer leaks because scalars are allowed to leak
			 * while pointers are not. We could make this safe in
			 * special cases if root is calling us, but it's
			 * probably not worth the hassle.
			 */
			return false;
		}
	case PTR_TO_MAP_VALUE:
		/* If the new min/max/var_off satisfy the old ones and
		 * everything else matches, we are OK.
		 * We don't care about the 'id' value, because nothing
		 * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
		 */
		return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
		       range_within(rold, rcur) &&
		       tnum_in(rold->var_off, rcur->var_off);
	case PTR_TO_MAP_VALUE_OR_NULL:
		/* a PTR_TO_MAP_VALUE could be safe to use as a
		 * PTR_TO_MAP_VALUE_OR_NULL into the same map.
		 * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
		 * checked, doing so could have affected others with the same
		 * id, and we can't check for that because we lost the id when
		 * we converted to a PTR_TO_MAP_VALUE.
		 */
		if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
			return false;
		if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
			return false;
		/* Check our ids match any regs they're supposed to */
		return check_ids(rold->id, rcur->id, idmap);
	case PTR_TO_PACKET_META:
	case PTR_TO_PACKET:
		if (rcur->type != rold->type)
			return false;
		/* We must have at least as much range as the old ptr
		 * did, so that any accesses which were safe before are
		 * still safe.  This is true even if old range < old off,
		 * since someone could have accessed through (ptr - k), or
		 * even done ptr -= k in a register, to get a safe access.
		 */
		if (rold->range > rcur->range)
			return false;
		/* If the offsets don't match, we can't trust our alignment;
		 * nor can we be sure that we won't fall out of range.
		 */
		if (rold->off != rcur->off)
			return false;
		/* id relations must be preserved */
		if (rold->id && !check_ids(rold->id, rcur->id, idmap))
			return false;
		/* new val must satisfy old val knowledge */
		return range_within(rold, rcur) &&
		       tnum_in(rold->var_off, rcur->var_off);
	case PTR_TO_CTX:
	case CONST_PTR_TO_MAP:
	case PTR_TO_PACKET_END:
		/* Only valid matches are exact, which memcmp() above
		 * would have accepted
		 */
	default:
		/* Don't know what's going on, just say it's not safe */
		return false;
	}

	/* Shouldn't get here; if we do, say it's not safe */
	WARN_ON_ONCE(1);
	return false;
}

static bool stacksafe(struct bpf_func_state *old,
		      struct bpf_func_state *cur,
		      struct idpair *idmap)
{
	int i, spi;

	/* if explored stack has more populated slots than current stack
	 * such stacks are not equivalent
	 */
	if (old->allocated_stack > cur->allocated_stack)
		return false;

	/* walk slots of the explored stack and ignore any additional
	 * slots in the current stack, since explored(safe) state
	 * didn't use them
	 */
	for (i = 0; i < old->allocated_stack; i++) {
		spi = i / BPF_REG_SIZE;

		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
			/* explored state didn't use this */
			continue;

		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
			continue;
		/* if old state was safe with misc data in the stack
		 * it will be safe with zero-initialized stack.
		 * The opposite is not true
		 */
		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC &&
		    cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO)
			continue;
		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
		    cur->stack[spi].slot_type[i % BPF_REG_SIZE])
			/* Ex: old explored (safe) state has STACK_SPILL in
			 * this stack slot, but current has has STACK_MISC ->
			 * this verifier states are not equivalent,
			 * return false to continue verification of this path
			 */
			return false;
		if (i % BPF_REG_SIZE)
			continue;
		if (old->stack[spi].slot_type[0] != STACK_SPILL)
			continue;
		if (!regsafe(&old->stack[spi].spilled_ptr,
			     &cur->stack[spi].spilled_ptr,
			     idmap))
			/* when explored and current stack slot are both storing
			 * spilled registers, check that stored pointers types
			 * are the same as well.
			 * Ex: explored safe path could have stored
			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
			 * but current path has stored:
			 * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
			 * such verifier states are not equivalent.
			 * return false to continue verification of this path
			 */
			return false;
	}
	return true;
}

/* compare two verifier states
 *
 * all states stored in state_list are known to be valid, since
 * verifier reached 'bpf_exit' instruction through them
 *
 * this function is called when verifier exploring different branches of
 * execution popped from the state stack. If it sees an old state that has
 * more strict register state and more strict stack state then this execution
 * branch doesn't need to be explored further, since verifier already
 * concluded that more strict state leads to valid finish.
 *
 * Therefore two states are equivalent if register state is more conservative
 * and explored stack state is more conservative than the current one.
 * Example:
 *       explored                   current
 * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
 * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
 *
 * In other words if current stack state (one being explored) has more
 * valid slots than old one that already passed validation, it means
 * the verifier can stop exploring and conclude that current state is valid too
 *
 * Similarly with registers. If explored state has register type as invalid
 * whereas register type in current state is meaningful, it means that
 * the current state will reach 'bpf_exit' instruction safely
 */
static bool func_states_equal(struct bpf_func_state *old,
			      struct bpf_func_state *cur)
{
	struct idpair *idmap;
	bool ret = false;
	int i;

	idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL);
	/* If we failed to allocate the idmap, just say it's not safe */
	if (!idmap)
		return false;

	for (i = 0; i < MAX_BPF_REG; i++) {
		if (!regsafe(&old->regs[i], &cur->regs[i], idmap))
			goto out_free;
	}

	if (!stacksafe(old, cur, idmap))
		goto out_free;
	ret = true;
out_free:
	kfree(idmap);
	return ret;
}

static bool states_equal(struct bpf_verifier_env *env,
			 struct bpf_verifier_state *old,
			 struct bpf_verifier_state *cur)
{
	int i;

	if (old->curframe != cur->curframe)
		return false;

	/* Verification state from speculative execution simulation
	 * must never prune a non-speculative execution one.
	 */
	if (old->speculative && !cur->speculative)
		return false;

	/* for states to be equal callsites have to be the same
	 * and all frame states need to be equivalent
	 */
	for (i = 0; i <= old->curframe; i++) {
		if (old->frame[i]->callsite != cur->frame[i]->callsite)
			return false;
		if (!func_states_equal(old->frame[i], cur->frame[i]))
			return false;
	}
	return true;
}

/* A write screens off any subsequent reads; but write marks come from the
 * straight-line code between a state and its parent.  When we arrive at an
 * equivalent state (jump target or such) we didn't arrive by the straight-line
 * code, so read marks in the state must propagate to the parent regardless
 * of the state's write marks. That's what 'parent == state->parent' comparison
 * in mark_reg_read() and mark_stack_slot_read() is for.
 */
static int propagate_liveness(struct bpf_verifier_env *env,
			      const struct bpf_verifier_state *vstate,
			      struct bpf_verifier_state *vparent)
{
	int i, frame, err = 0;
	struct bpf_func_state *state, *parent;

	if (vparent->curframe != vstate->curframe) {
		WARN(1, "propagate_live: parent frame %d current frame %d\n",
		     vparent->curframe, vstate->curframe);
		return -EFAULT;
	}
	/* Propagate read liveness of registers... */
	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
	/* We don't need to worry about FP liveness because it's read-only */
	for (i = 0; i < BPF_REG_FP; i++) {
		if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
			continue;
		if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
			err = mark_reg_read(env, vstate, vparent, i);
			if (err)
				return err;
		}
	}

	/* ... and stack slots */
	for (frame = 0; frame <= vstate->curframe; frame++) {
		state = vstate->frame[frame];
		parent = vparent->frame[frame];
		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
			    i < parent->allocated_stack / BPF_REG_SIZE; i++) {
			if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
				continue;
			if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
				mark_stack_slot_read(env, vstate, vparent, i, frame);
		}
	}
	return err;
}

static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
	struct bpf_verifier_state_list *new_sl;
	struct bpf_verifier_state_list *sl;
	struct bpf_verifier_state *cur = env->cur_state;
	int i, j, err, states_cnt = 0;

	sl = env->explored_states[insn_idx];
	if (!sl)
		/* this 'insn_idx' instruction wasn't marked, so we will not
		 * be doing state search here
		 */
		return 0;

	while (sl != STATE_LIST_MARK) {
		if (states_equal(env, &sl->state, cur)) {
			/* reached equivalent register/stack state,
			 * prune the search.
			 * Registers read by the continuation are read by us.
			 * If we have any write marks in env->cur_state, they
			 * will prevent corresponding reads in the continuation
			 * from reaching our parent (an explored_state).  Our
			 * own state will get the read marks recorded, but
			 * they'll be immediately forgotten as we're pruning
			 * this state and will pop a new one.
			 */
			err = propagate_liveness(env, &sl->state, cur);
			if (err)
				return err;
			return 1;
		}
		sl = sl->next;
		states_cnt++;
	}

	if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
		return 0;

	/* there were no equivalent states, remember current one.
	 * technically the current state is not proven to be safe yet,
	 * but it will either reach outer most bpf_exit (which means it's safe)
	 * or it will be rejected. Since there are no loops, we won't be
	 * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
	 * again on the way to bpf_exit
	 */
	new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
	if (!new_sl)
		return -ENOMEM;

	/* add new state to the head of linked list */
	err = copy_verifier_state(&new_sl->state, cur);
	if (err) {
		free_verifier_state(&new_sl->state, false);
		kfree(new_sl);
		return err;
	}
	new_sl->next = env->explored_states[insn_idx];
	env->explored_states[insn_idx] = new_sl;
	/* connect new state to parentage chain */
	cur->parent = &new_sl->state;
	/* clear write marks in current state: the writes we did are not writes
	 * our child did, so they don't screen off its reads from us.
	 * (There are no read marks in current state, because reads always mark
	 * their parent and current state never has children yet.  Only
	 * explored_states can get read marks.)
	 */
	for (i = 0; i < BPF_REG_FP; i++)
		cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;

	/* all stack frames are accessible from callee, clear them all */
	for (j = 0; j <= cur->curframe; j++) {
		struct bpf_func_state *frame = cur->frame[j];

		for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++)
			frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
	}
	return 0;
}

static int do_check(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *state;
	struct bpf_insn *insns = env->prog->insnsi;
	struct bpf_reg_state *regs;
	int insn_cnt = env->prog->len, i;
	int insn_processed = 0;
	bool do_print_state = false;

	state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
	if (!state)
		return -ENOMEM;
	state->curframe = 0;
	state->speculative = false;
	state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
	if (!state->frame[0]) {
		kfree(state);
		return -ENOMEM;
	}
	env->cur_state = state;
	init_func_state(env, state->frame[0],
			BPF_MAIN_FUNC /* callsite */,
			0 /* frameno */,
			0 /* subprogno, zero == main subprog */);

	for (;;) {
		struct bpf_insn *insn;
		u8 class;
		int err;

		if (env->insn_idx >= insn_cnt) {
			verbose(env, "invalid insn idx %d insn_cnt %d\n",
				env->insn_idx, insn_cnt);
			return -EFAULT;
		}

		insn = &insns[env->insn_idx];
		class = BPF_CLASS(insn->code);

		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
			verbose(env,
				"BPF program is too large. Processed %d insn\n",
				insn_processed);
			return -E2BIG;
		}

		err = is_state_visited(env, env->insn_idx);
		if (err < 0)
			return err;
		if (err == 1) {
			/* found equivalent state, can prune the search */
			if (env->log.level) {
				if (do_print_state)
					verbose(env, "\nfrom %d to %d%s: safe\n",
						env->prev_insn_idx, env->insn_idx,
						env->cur_state->speculative ?
						" (speculative execution)" : "");
				else
					verbose(env, "%d: safe\n", env->insn_idx);
			}
			goto process_bpf_exit;
		}

		if (signal_pending(current))
			return -EAGAIN;

		if (need_resched())
			cond_resched();

		if (env->log.level > 1 || (env->log.level && do_print_state)) {
			if (env->log.level > 1)
				verbose(env, "%d:", env->insn_idx);
			else
				verbose(env, "\nfrom %d to %d%s:",
					env->prev_insn_idx, env->insn_idx,
					env->cur_state->speculative ?
					" (speculative execution)" : "");
			print_verifier_state(env, state->frame[state->curframe]);
			do_print_state = false;
		}

		if (env->log.level) {
			const struct bpf_insn_cbs cbs = {
				.cb_print	= verbose,
				.private_data	= env,
			};

			verbose(env, "%d: ", env->insn_idx);
			print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
		}

		if (bpf_prog_is_dev_bound(env->prog->aux)) {
			err = bpf_prog_offload_verify_insn(env, env->insn_idx,
							   env->prev_insn_idx);
			if (err)
				return err;
		}

		regs = cur_regs(env);
		env->insn_aux_data[env->insn_idx].seen = true;

		if (class == BPF_ALU || class == BPF_ALU64) {
			err = check_alu_op(env, insn);
			if (err)
				return err;

		} else if (class == BPF_LDX) {
			enum bpf_reg_type *prev_src_type, src_reg_type;

			/* check for reserved fields is already done */

			/* check src operand */
			err = check_reg_arg(env, insn->src_reg, SRC_OP);
			if (err)
				return err;

			err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
			if (err)
				return err;

			src_reg_type = regs[insn->src_reg].type;

			/* check that memory (src_reg + off) is readable,
			 * the state of dst_reg will be updated by this func
			 */
			err = check_mem_access(env, env->insn_idx, insn->src_reg,
					       insn->off, BPF_SIZE(insn->code),
					       BPF_READ, insn->dst_reg, false);
			if (err)
				return err;

			prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type;

			if (*prev_src_type == NOT_INIT) {
				/* saw a valid insn
				 * dst_reg = *(u32 *)(src_reg + off)
				 * save type to validate intersecting paths
				 */
				*prev_src_type = src_reg_type;

			} else if (src_reg_type != *prev_src_type &&
				   (src_reg_type == PTR_TO_CTX ||
				    *prev_src_type == PTR_TO_CTX)) {
				/* ABuser program is trying to use the same insn
				 * dst_reg = *(u32*) (src_reg + off)
				 * with different pointer types:
				 * src_reg == ctx in one branch and
				 * src_reg == stack|map in some other branch.
				 * Reject it.
				 */
				verbose(env, "same insn cannot be used with different pointers\n");
				return -EINVAL;
			}

		} else if (class == BPF_STX) {
			enum bpf_reg_type *prev_dst_type, dst_reg_type;

			if (BPF_MODE(insn->code) == BPF_XADD) {
				err = check_xadd(env, env->insn_idx, insn);
				if (err)
					return err;
				env->insn_idx++;
				continue;
			}

			/* check src1 operand */
			err = check_reg_arg(env, insn->src_reg, SRC_OP);
			if (err)
				return err;
			/* check src2 operand */
			err = check_reg_arg(env, insn->dst_reg, SRC_OP);
			if (err)
				return err;

			dst_reg_type = regs[insn->dst_reg].type;

			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
					       insn->off, BPF_SIZE(insn->code),
					       BPF_WRITE, insn->src_reg, false);
			if (err)
				return err;

			prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type;

			if (*prev_dst_type == NOT_INIT) {
				*prev_dst_type = dst_reg_type;
			} else if (dst_reg_type != *prev_dst_type &&
				   (dst_reg_type == PTR_TO_CTX ||
				    *prev_dst_type == PTR_TO_CTX)) {
				verbose(env, "same insn cannot be used with different pointers\n");
				return -EINVAL;
			}

		} else if (class == BPF_ST) {
			if (BPF_MODE(insn->code) != BPF_MEM ||
			    insn->src_reg != BPF_REG_0) {
				verbose(env, "BPF_ST uses reserved fields\n");
				return -EINVAL;
			}
			/* check src operand */
			err = check_reg_arg(env, insn->dst_reg, SRC_OP);
			if (err)
				return err;

			if (is_ctx_reg(env, insn->dst_reg)) {
				verbose(env, "BPF_ST stores into R%d context is not allowed\n",
					insn->dst_reg);
				return -EACCES;
			}

			/* check that memory (dst_reg + off) is writeable */
			err = check_mem_access(env, env->insn_idx, insn->dst_reg,
					       insn->off, BPF_SIZE(insn->code),
					       BPF_WRITE, -1, false);
			if (err)
				return err;

		} else if (class == BPF_JMP) {
			u8 opcode = BPF_OP(insn->code);

			if (opcode == BPF_CALL) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->off != 0 ||
				    (insn->src_reg != BPF_REG_0 &&
				     insn->src_reg != BPF_PSEUDO_CALL) ||
				    insn->dst_reg != BPF_REG_0) {
					verbose(env, "BPF_CALL uses reserved fields\n");
					return -EINVAL;
				}

				if (insn->src_reg == BPF_PSEUDO_CALL)
					err = check_func_call(env, insn, &env->insn_idx);
				else
					err = check_helper_call(env, insn->imm, env->insn_idx);
				if (err)
					return err;

			} else if (opcode == BPF_JA) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose(env, "BPF_JA uses reserved fields\n");
					return -EINVAL;
				}

				env->insn_idx += insn->off + 1;
				continue;

			} else if (opcode == BPF_EXIT) {
				if (BPF_SRC(insn->code) != BPF_K ||
				    insn->imm != 0 ||
				    insn->src_reg != BPF_REG_0 ||
				    insn->dst_reg != BPF_REG_0) {
					verbose(env, "BPF_EXIT uses reserved fields\n");
					return -EINVAL;
				}

				if (state->curframe) {
					/* exit from nested function */
					env->prev_insn_idx = env->insn_idx;
					err = prepare_func_exit(env, &env->insn_idx);
					if (err)
						return err;
					do_print_state = true;
					continue;
				}

				/* eBPF calling convetion is such that R0 is used
				 * to return the value from eBPF program.
				 * Make sure that it's readable at this time
				 * of bpf_exit, which means that program wrote
				 * something into it earlier
				 */
				err = check_reg_arg(env, BPF_REG_0, SRC_OP);
				if (err)
					return err;

				if (is_pointer_value(env, BPF_REG_0)) {
					verbose(env, "R0 leaks addr as return value\n");
					return -EACCES;
				}

				err = check_return_code(env);
				if (err)
					return err;
process_bpf_exit:
				err = pop_stack(env, &env->prev_insn_idx,
						&env->insn_idx);
				if (err < 0) {
					if (err != -ENOENT)
						return err;
					break;
				} else {
					do_print_state = true;
					continue;
				}
			} else {
				err = check_cond_jmp_op(env, insn, &env->insn_idx);
				if (err)
					return err;
			}
		} else if (class == BPF_LD) {
			u8 mode = BPF_MODE(insn->code);

			if (mode == BPF_ABS || mode == BPF_IND) {
				err = check_ld_abs(env, insn);
				if (err)
					return err;

			} else if (mode == BPF_IMM) {
				err = check_ld_imm(env, insn);
				if (err)
					return err;

				env->insn_idx++;
				env->insn_aux_data[env->insn_idx].seen = true;
			} else {
				verbose(env, "invalid BPF_LD mode\n");
				return -EINVAL;
			}
		} else {
			verbose(env, "unknown insn class %d\n", class);
			return -EINVAL;
		}

		env->insn_idx++;
	}

	verbose(env, "processed %d insns (limit %d), stack depth ",
		insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
	for (i = 0; i < env->subprog_cnt; i++) {
		u32 depth = env->subprog_info[i].stack_depth;

		verbose(env, "%d", depth);
		if (i + 1 < env->subprog_cnt)
			verbose(env, "+");
	}
	verbose(env, "\n");
	env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
	return 0;
}

static int check_map_prealloc(struct bpf_map *map)
{
	return (map->map_type != BPF_MAP_TYPE_HASH &&
		map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
		map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
		!(map->map_flags & BPF_F_NO_PREALLOC);
}

static int check_map_prog_compatibility(struct bpf_verifier_env *env,
					struct bpf_map *map,
					struct bpf_prog *prog)

{
	/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
	 * preallocated hash maps, since doing memory allocation
	 * in overflow_handler can crash depending on where nmi got
	 * triggered.
	 */
	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
		if (!check_map_prealloc(map)) {
			verbose(env, "perf_event programs can only use preallocated hash map\n");
			return -EINVAL;
		}
		if (map->inner_map_meta &&
		    !check_map_prealloc(map->inner_map_meta)) {
			verbose(env, "perf_event programs can only use preallocated inner hash map\n");
			return -EINVAL;
		}
	}

	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
	    !bpf_offload_prog_map_match(prog, map)) {
		verbose(env, "offload device mismatch between prog and map\n");
		return -EINVAL;
	}

	return 0;
}

/* look for pseudo eBPF instructions that access map FDs and
 * replace them with actual map pointers
 */
static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i, j, err;

	err = bpf_prog_calc_tag(env->prog);
	if (err)
		return err;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (BPF_CLASS(insn->code) == BPF_LDX &&
		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
			verbose(env, "BPF_LDX uses reserved fields\n");
			return -EINVAL;
		}

		if (BPF_CLASS(insn->code) == BPF_STX &&
		    ((BPF_MODE(insn->code) != BPF_MEM &&
		      BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
			verbose(env, "BPF_STX uses reserved fields\n");
			return -EINVAL;
		}

		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
			struct bpf_map *map;
			struct fd f;

			if (i == insn_cnt - 1 || insn[1].code != 0 ||
			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
			    insn[1].off != 0) {
				verbose(env, "invalid bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			if (insn->src_reg == 0)
				/* valid generic load 64-bit imm */
				goto next_insn;

			if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
				verbose(env,
					"unrecognized bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			f = fdget(insn->imm);
			map = __bpf_map_get(f);
			if (IS_ERR(map)) {
				verbose(env, "fd %d is not pointing to valid bpf_map\n",
					insn->imm);
				return PTR_ERR(map);
			}

			err = check_map_prog_compatibility(env, map, env->prog);
			if (err) {
				fdput(f);
				return err;
			}

			/* store map pointer inside BPF_LD_IMM64 instruction */
			insn[0].imm = (u32) (unsigned long) map;
			insn[1].imm = ((u64) (unsigned long) map) >> 32;

			/* check whether we recorded this map already */
			for (j = 0; j < env->used_map_cnt; j++)
				if (env->used_maps[j] == map) {
					fdput(f);
					goto next_insn;
				}

			if (env->used_map_cnt >= MAX_USED_MAPS) {
				fdput(f);
				return -E2BIG;
			}

			/* hold the map. If the program is rejected by verifier,
			 * the map will be released by release_maps() or it
			 * will be used by the valid program until it's unloaded
			 * and all maps are released in free_used_maps()
			 */
			map = bpf_map_inc(map, false);
			if (IS_ERR(map)) {
				fdput(f);
				return PTR_ERR(map);
			}
			env->used_maps[env->used_map_cnt++] = map;

			if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
			    bpf_cgroup_storage_assign(env->prog, map)) {
				verbose(env,
					"only one cgroup storage is allowed\n");
				fdput(f);
				return -EBUSY;
			}

			fdput(f);
next_insn:
			insn++;
			i++;
			continue;
		}

		/* Basic sanity check before we invest more work here. */
		if (!bpf_opcode_in_insntable(insn->code)) {
			verbose(env, "unknown opcode %02x\n", insn->code);
			return -EINVAL;
		}
	}

	/* now all pseudo BPF_LD_IMM64 instructions load valid
	 * 'struct bpf_map *' into a register instead of user map_fd.
	 * These pointers will be used later by verifier to validate map access.
	 */
	return 0;
}

/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
	int i;

	if (env->prog->aux->cgroup_storage)
		bpf_cgroup_storage_release(env->prog,
					   env->prog->aux->cgroup_storage);

	for (i = 0; i < env->used_map_cnt; i++)
		bpf_map_put(env->used_maps[i]);
}

/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++, insn++)
		if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
			insn->src_reg = 0;
}

/* single env->prog->insni[off] instruction was replaced with the range
 * insni[off, off + cnt).  Adjust corresponding insn_aux_data by copying
 * [0, off) and [off, end) to new locations, so the patched range stays zero
 */
static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
				u32 off, u32 cnt)
{
	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
	int i;

	if (cnt == 1)
		return 0;
	new_data = vzalloc(array_size(prog_len,
				      sizeof(struct bpf_insn_aux_data)));
	if (!new_data)
		return -ENOMEM;
	memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
	memcpy(new_data + off + cnt - 1, old_data + off,
	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
	for (i = off; i < off + cnt - 1; i++)
		new_data[i].seen = true;
	env->insn_aux_data = new_data;
	vfree(old_data);
	return 0;
}

static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
{
	int i;

	if (len == 1)
		return;
	/* NOTE: fake 'exit' subprog should be updated as well. */
	for (i = 0; i <= env->subprog_cnt; i++) {
		if (env->subprog_info[i].start <= off)
			continue;
		env->subprog_info[i].start += len - 1;
	}
}

static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
					    const struct bpf_insn *patch, u32 len)
{
	struct bpf_prog *new_prog;

	new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
	if (!new_prog)
		return NULL;
	if (adjust_insn_aux_data(env, new_prog->len, off, len))
		return NULL;
	adjust_subprog_starts(env, off, len);
	return new_prog;
}

/* The verifier does more data flow analysis than llvm and will not
 * explore branches that are dead at run time. Malicious programs can
 * have dead code too. Therefore replace all dead at-run-time code
 * with 'ja -1'.
 *
 * Just nops are not optimal, e.g. if they would sit at the end of the
 * program and through another bug we would manage to jump there, then
 * we'd execute beyond program memory otherwise. Returning exception
 * code also wouldn't work since we can have subprogs where the dead
 * code could be located.
 */
static void sanitize_dead_code(struct bpf_verifier_env *env)
{
	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
	struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
	struct bpf_insn *insn = env->prog->insnsi;
	const int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++) {
		if (aux_data[i].seen)
			continue;
		memcpy(insn + i, &trap, sizeof(trap));
	}
}

/* convert load instructions that access fields of 'struct __sk_buff'
 * into sequence of instructions that access fields of 'struct sk_buff'
 */
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
	const struct bpf_verifier_ops *ops = env->ops;
	int i, cnt, size, ctx_field_size, delta = 0;
	const int insn_cnt = env->prog->len;
	struct bpf_insn insn_buf[16], *insn;
	u32 target_size, size_default, off;
	struct bpf_prog *new_prog;
	enum bpf_access_type type;
	bool is_narrower_load;

	if (ops->gen_prologue) {
		cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
					env->prog);
		if (cnt >= ARRAY_SIZE(insn_buf)) {
			verbose(env, "bpf verifier is misconfigured\n");
			return -EINVAL;
		} else if (cnt) {
			new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
			if (!new_prog)
				return -ENOMEM;

			env->prog = new_prog;
			delta += cnt - 1;
		}
	}

	if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux))
		return 0;

	insn = env->prog->insnsi + delta;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
		    insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
		    insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
			type = BPF_READ;
		else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
			 insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
			 insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
			 insn->code == (BPF_STX | BPF_MEM | BPF_DW))
			type = BPF_WRITE;
		else
			continue;

		if (type == BPF_WRITE &&
		    env->insn_aux_data[i + delta].sanitize_stack_off) {
			struct bpf_insn patch[] = {
				/* Sanitize suspicious stack slot with zero.
				 * There are no memory dependencies for this store,
				 * since it's only using frame pointer and immediate
				 * constant of zero
				 */
				BPF_ST_MEM(BPF_DW, BPF_REG_FP,
					   env->insn_aux_data[i + delta].sanitize_stack_off,
					   0),
				/* the original STX instruction will immediately
				 * overwrite the same stack slot with appropriate value
				 */
				*insn,
			};

			cnt = ARRAY_SIZE(patch);
			new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
			if (!new_prog)
				return -ENOMEM;

			delta    += cnt - 1;
			env->prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
			continue;

		ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
		size = BPF_LDST_BYTES(insn);

		/* If the read access is a narrower load of the field,
		 * convert to a 4/8-byte load, to minimum program type specific
		 * convert_ctx_access changes. If conversion is successful,
		 * we will apply proper mask to the result.
		 */
		is_narrower_load = size < ctx_field_size;
		size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
		off = insn->off;
		if (is_narrower_load) {
			u8 size_code;

			if (type == BPF_WRITE) {
				verbose(env, "bpf verifier narrow ctx access misconfigured\n");
				return -EINVAL;
			}

			size_code = BPF_H;
			if (ctx_field_size == 4)
				size_code = BPF_W;
			else if (ctx_field_size == 8)
				size_code = BPF_DW;

			insn->off = off & ~(size_default - 1);
			insn->code = BPF_LDX | BPF_MEM | size_code;
		}

		target_size = 0;
		cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog,
					      &target_size);
		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
		    (ctx_field_size && !target_size)) {
			verbose(env, "bpf verifier is misconfigured\n");
			return -EINVAL;
		}

		if (is_narrower_load && size < target_size) {
			u8 shift = (off & (size_default - 1)) * 8;

			if (ctx_field_size <= 4) {
				if (shift)
					insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
									insn->dst_reg,
									shift);
				insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
								(1 << size * 8) - 1);
			} else {
				if (shift)
					insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
									insn->dst_reg,
									shift);
				insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
								(1 << size * 8) - 1);
			}
		}

		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
		if (!new_prog)
			return -ENOMEM;

		delta += cnt - 1;

		/* keep walking new program and skip insns we just inserted */
		env->prog = new_prog;
		insn      = new_prog->insnsi + i + delta;
	}

	return 0;
}

static int jit_subprogs(struct bpf_verifier_env *env)
{
	struct bpf_prog *prog = env->prog, **func, *tmp;
	int i, j, subprog_start, subprog_end = 0, len, subprog;
	struct bpf_insn *insn;
	void *old_bpf_func;
	int err = -ENOMEM;

	if (env->subprog_cnt <= 1)
		return 0;

	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
		if (insn->code != (BPF_JMP | BPF_CALL) ||
		    insn->src_reg != BPF_PSEUDO_CALL)
			continue;
		/* Upon error here we cannot fall back to interpreter but
		 * need a hard reject of the program. Thus -EFAULT is
		 * propagated in any case.
		 */
		subprog = find_subprog(env, i + insn->imm + 1);
		if (subprog < 0) {
			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
				  i + insn->imm + 1);
			return -EFAULT;
		}
		/* temporarily remember subprog id inside insn instead of
		 * aux_data, since next loop will split up all insns into funcs
		 */
		insn->off = subprog;
		/* remember original imm in case JIT fails and fallback
		 * to interpreter will be needed
		 */
		env->insn_aux_data[i].call_imm = insn->imm;
		/* point imm to __bpf_call_base+1 from JITs point of view */
		insn->imm = 1;
	}

	func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
	if (!func)
		goto out_undo_insn;

	for (i = 0; i < env->subprog_cnt; i++) {
		subprog_start = subprog_end;
		subprog_end = env->subprog_info[i + 1].start;

		len = subprog_end - subprog_start;
		func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
		if (!func[i])
			goto out_free;
		memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
		       len * sizeof(struct bpf_insn));
		func[i]->type = prog->type;
		func[i]->len = len;
		if (bpf_prog_calc_tag(func[i]))
			goto out_free;
		func[i]->is_func = 1;
		/* Use bpf_prog_F_tag to indicate functions in stack traces.
		 * Long term would need debug info to populate names
		 */
		func[i]->aux->name[0] = 'F';
		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
		func[i]->jit_requested = 1;
		func[i] = bpf_int_jit_compile(func[i]);
		if (!func[i]->jited) {
			err = -ENOTSUPP;
			goto out_free;
		}
		cond_resched();
	}
	/* at this point all bpf functions were successfully JITed
	 * now populate all bpf_calls with correct addresses and
	 * run last pass of JIT
	 */
	for (i = 0; i < env->subprog_cnt; i++) {
		insn = func[i]->insnsi;
		for (j = 0; j < func[i]->len; j++, insn++) {
			if (insn->code != (BPF_JMP | BPF_CALL) ||
			    insn->src_reg != BPF_PSEUDO_CALL)
				continue;
			subprog = insn->off;
			insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
				func[subprog]->bpf_func -
				__bpf_call_base;
		}

		/* we use the aux data to keep a list of the start addresses
		 * of the JITed images for each function in the program
		 *
		 * for some architectures, such as powerpc64, the imm field
		 * might not be large enough to hold the offset of the start
		 * address of the callee's JITed image from __bpf_call_base
		 *
		 * in such cases, we can lookup the start address of a callee
		 * by using its subprog id, available from the off field of
		 * the call instruction, as an index for this list
		 */
		func[i]->aux->func = func;
		func[i]->aux->func_cnt = env->subprog_cnt;
	}
	for (i = 0; i < env->subprog_cnt; i++) {
		old_bpf_func = func[i]->bpf_func;
		tmp = bpf_int_jit_compile(func[i]);
		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
			verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
			err = -ENOTSUPP;
			goto out_free;
		}
		cond_resched();
	}

	/* finally lock prog and jit images for all functions and
	 * populate kallsysm
	 */
	for (i = 0; i < env->subprog_cnt; i++) {
		bpf_prog_lock_ro(func[i]);
		bpf_prog_kallsyms_add(func[i]);
	}

	/* Last step: make now unused interpreter insns from main
	 * prog consistent for later dump requests, so they can
	 * later look the same as if they were interpreted only.
	 */
	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
		if (insn->code != (BPF_JMP | BPF_CALL) ||
		    insn->src_reg != BPF_PSEUDO_CALL)
			continue;
		insn->off = env->insn_aux_data[i].call_imm;
		subprog = find_subprog(env, i + insn->off + 1);
		insn->imm = subprog;
	}

	prog->jited = 1;
	prog->bpf_func = func[0]->bpf_func;
	prog->aux->func = func;
	prog->aux->func_cnt = env->subprog_cnt;
	return 0;
out_free:
	for (i = 0; i < env->subprog_cnt; i++)
		if (func[i])
			bpf_jit_free(func[i]);
	kfree(func);
out_undo_insn:
	/* cleanup main prog to be interpreted */
	prog->jit_requested = 0;
	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
		if (insn->code != (BPF_JMP | BPF_CALL) ||
		    insn->src_reg != BPF_PSEUDO_CALL)
			continue;
		insn->off = 0;
		insn->imm = env->insn_aux_data[i].call_imm;
	}
	return err;
}

static int fixup_call_args(struct bpf_verifier_env *env)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
	struct bpf_prog *prog = env->prog;
	struct bpf_insn *insn = prog->insnsi;
	int i, depth;
#endif
	int err;

	err = 0;
	if (env->prog->jit_requested) {
		err = jit_subprogs(env);
		if (err == 0)
			return 0;
		if (err == -EFAULT)
			return err;
	}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
	for (i = 0; i < prog->len; i++, insn++) {
		if (insn->code != (BPF_JMP | BPF_CALL) ||
		    insn->src_reg != BPF_PSEUDO_CALL)
			continue;
		depth = get_callee_stack_depth(env, insn, i);
		if (depth < 0)
			return depth;
		bpf_patch_call_args(insn, depth);
	}
	err = 0;
#endif
	return err;
}

/* fixup insn->imm field of bpf_call instructions
 * and inline eligible helpers as explicit sequence of BPF instructions
 *
 * this function is called after eBPF program passed verification
 */
static int fixup_bpf_calls(struct bpf_verifier_env *env)
{
	struct bpf_prog *prog = env->prog;
	struct bpf_insn *insn = prog->insnsi;
	const struct bpf_func_proto *fn;
	const int insn_cnt = prog->len;
	const struct bpf_map_ops *ops;
	struct bpf_insn_aux_data *aux;
	struct bpf_insn insn_buf[16];
	struct bpf_prog *new_prog;
	struct bpf_map *map_ptr;
	int i, cnt, delta = 0;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
		    insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
		    insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
		    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
			struct bpf_insn mask_and_div[] = {
				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
				/* Rx div 0 -> 0 */
				BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2),
				BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
				BPF_JMP_IMM(BPF_JA, 0, 0, 1),
				*insn,
			};
			struct bpf_insn mask_and_mod[] = {
				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
				/* Rx mod 0 -> Rx */
				BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1),
				*insn,
			};
			struct bpf_insn *patchlet;

			if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
			    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
				patchlet = mask_and_div + (is64 ? 1 : 0);
				cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0);
			} else {
				patchlet = mask_and_mod + (is64 ? 1 : 0);
				cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0);
			}

			new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
			if (!new_prog)
				return -ENOMEM;

			delta    += cnt - 1;
			env->prog = prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

		if (BPF_CLASS(insn->code) == BPF_LD &&
		    (BPF_MODE(insn->code) == BPF_ABS ||
		     BPF_MODE(insn->code) == BPF_IND)) {
			cnt = env->ops->gen_ld_abs(insn, insn_buf);
			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
				verbose(env, "bpf verifier is misconfigured\n");
				return -EINVAL;
			}

			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
			if (!new_prog)
				return -ENOMEM;

			delta    += cnt - 1;
			env->prog = prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

		if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) ||
		    insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
			const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
			const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
			struct bpf_insn insn_buf[16];
			struct bpf_insn *patch = &insn_buf[0];
			bool issrc, isneg;
			u32 off_reg;

			aux = &env->insn_aux_data[i + delta];
			if (!aux->alu_state ||
			    aux->alu_state == BPF_ALU_NON_POINTER)
				continue;

			isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
			issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
				BPF_ALU_SANITIZE_SRC;

			off_reg = issrc ? insn->src_reg : insn->dst_reg;
			if (isneg)
				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
			*patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
			if (issrc) {
				*patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX,
							 off_reg);
				insn->src_reg = BPF_REG_AX;
			} else {
				*patch++ = BPF_ALU64_REG(BPF_AND, off_reg,
							 BPF_REG_AX);
			}
			if (isneg)
				insn->code = insn->code == code_add ?
					     code_sub : code_add;
			*patch++ = *insn;
			if (issrc && isneg)
				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
			cnt = patch - insn_buf;

			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
			if (!new_prog)
				return -ENOMEM;

			delta    += cnt - 1;
			env->prog = prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

		if (insn->code != (BPF_JMP | BPF_CALL))
			continue;
		if (insn->src_reg == BPF_PSEUDO_CALL)
			continue;

		if (insn->imm == BPF_FUNC_get_route_realm)
			prog->dst_needed = 1;
		if (insn->imm == BPF_FUNC_get_prandom_u32)
			bpf_user_rnd_init_once();
		if (insn->imm == BPF_FUNC_override_return)
			prog->kprobe_override = 1;
		if (insn->imm == BPF_FUNC_tail_call) {
			/* If we tail call into other programs, we
			 * cannot make any assumptions since they can
			 * be replaced dynamically during runtime in
			 * the program array.
			 */
			prog->cb_access = 1;
			env->prog->aux->stack_depth = MAX_BPF_STACK;

			/* mark bpf_tail_call as different opcode to avoid
			 * conditional branch in the interpeter for every normal
			 * call and to prevent accidental JITing by JIT compiler
			 * that doesn't support bpf_tail_call yet
			 */
			insn->imm = 0;
			insn->code = BPF_JMP | BPF_TAIL_CALL;

			aux = &env->insn_aux_data[i + delta];
			if (!bpf_map_ptr_unpriv(aux))
				continue;

			/* instead of changing every JIT dealing with tail_call
			 * emit two extra insns:
			 * if (index >= max_entries) goto out;
			 * index &= array->index_mask;
			 * to avoid out-of-bounds cpu speculation
			 */
			if (bpf_map_ptr_poisoned(aux)) {
				verbose(env, "tail_call abusing map_ptr\n");
				return -EINVAL;
			}

			map_ptr = BPF_MAP_PTR(aux->map_state);
			insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
						  map_ptr->max_entries, 2);
			insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
						    container_of(map_ptr,
								 struct bpf_array,
								 map)->index_mask);
			insn_buf[2] = *insn;
			cnt = 3;
			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
			if (!new_prog)
				return -ENOMEM;

			delta    += cnt - 1;
			env->prog = prog = new_prog;
			insn      = new_prog->insnsi + i + delta;
			continue;
		}

		/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
		 * and other inlining handlers are currently limited to 64 bit
		 * only.
		 */
		if (prog->jit_requested && BITS_PER_LONG == 64 &&
		    (insn->imm == BPF_FUNC_map_lookup_elem ||
		     insn->imm == BPF_FUNC_map_update_elem ||
		     insn->imm == BPF_FUNC_map_delete_elem)) {
			aux = &env->insn_aux_data[i + delta];
			if (bpf_map_ptr_poisoned(aux))
				goto patch_call_imm;

			map_ptr = BPF_MAP_PTR(aux->map_state);
			ops = map_ptr->ops;
			if (insn->imm == BPF_FUNC_map_lookup_elem &&
			    ops->map_gen_lookup) {
				cnt = ops->map_gen_lookup(map_ptr, insn_buf);
				if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
					verbose(env, "bpf verifier is misconfigured\n");
					return -EINVAL;
				}

				new_prog = bpf_patch_insn_data(env, i + delta,
							       insn_buf, cnt);
				if (!new_prog)
					return -ENOMEM;

				delta    += cnt - 1;
				env->prog = prog = new_prog;
				insn      = new_prog->insnsi + i + delta;
				continue;
			}

			BUILD_BUG_ON(!__same_type(ops->map_lookup_elem,
				     (void *(*)(struct bpf_map *map, void *key))NULL));
			BUILD_BUG_ON(!__same_type(ops->map_delete_elem,
				     (int (*)(struct bpf_map *map, void *key))NULL));
			BUILD_BUG_ON(!__same_type(ops->map_update_elem,
				     (int (*)(struct bpf_map *map, void *key, void *value,
					      u64 flags))NULL));
			switch (insn->imm) {
			case BPF_FUNC_map_lookup_elem:
				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
					    __bpf_call_base;
				continue;
			case BPF_FUNC_map_update_elem:
				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
					    __bpf_call_base;
				continue;
			case BPF_FUNC_map_delete_elem:
				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
					    __bpf_call_base;
				continue;
			}

			goto patch_call_imm;
		}

patch_call_imm:
		fn = env->ops->get_func_proto(insn->imm, env->prog);
		/* all functions that have prototype and verifier allowed
		 * programs to call them, must be real in-kernel functions
		 */
		if (!fn->func) {
			verbose(env,
				"kernel subsystem misconfigured func %s#%d\n",
				func_id_name(insn->imm), insn->imm);
			return -EFAULT;
		}
		insn->imm = fn->func - __bpf_call_base;
	}

	return 0;
}

static void free_states(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state_list *sl, *sln;
	int i;

	if (!env->explored_states)
		return;

	for (i = 0; i < env->prog->len; i++) {
		sl = env->explored_states[i];

		if (sl)
			while (sl != STATE_LIST_MARK) {
				sln = sl->next;
				free_verifier_state(&sl->state, false);
				kfree(sl);
				sl = sln;
			}
	}

	kfree(env->explored_states);
}

int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
{
	struct bpf_verifier_env *env;
	struct bpf_verifier_log *log;
	int ret = -EINVAL;

	/* no program is valid */
	if (ARRAY_SIZE(bpf_verifier_ops) == 0)
		return -EINVAL;

	/* 'struct bpf_verifier_env' can be global, but since it's not small,
	 * allocate/free it every time bpf_check() is called
	 */
	env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
	if (!env)
		return -ENOMEM;
	log = &env->log;

	env->insn_aux_data =
		vzalloc(array_size(sizeof(struct bpf_insn_aux_data),
				   (*prog)->len));
	ret = -ENOMEM;
	if (!env->insn_aux_data)
		goto err_free_env;
	env->prog = *prog;
	env->ops = bpf_verifier_ops[env->prog->type];

	/* grab the mutex to protect few globals used by verifier */
	mutex_lock(&bpf_verifier_lock);

	if (attr->log_level || attr->log_buf || attr->log_size) {
		/* user requested verbose verifier output
		 * and supplied buffer to store the verification trace
		 */
		log->level = attr->log_level;
		log->ubuf = (char __user *) (unsigned long) attr->log_buf;
		log->len_total = attr->log_size;

		ret = -EINVAL;
		/* log attributes have to be sane */
		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
		    !log->level || !log->ubuf)
			goto err_unlock;
	}

	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
		env->strict_alignment = true;

	ret = replace_map_fd_with_map_ptr(env);
	if (ret < 0)
		goto skip_full_check;

	if (bpf_prog_is_dev_bound(env->prog->aux)) {
		ret = bpf_prog_offload_verifier_prep(env);
		if (ret)
			goto skip_full_check;
	}

	env->explored_states = kcalloc(env->prog->len,
				       sizeof(struct bpf_verifier_state_list *),
				       GFP_USER);
	ret = -ENOMEM;
	if (!env->explored_states)
		goto skip_full_check;

	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);

	ret = check_cfg(env);
	if (ret < 0)
		goto skip_full_check;

	ret = do_check(env);
	if (env->cur_state) {
		free_verifier_state(env->cur_state, true);
		env->cur_state = NULL;
	}

skip_full_check:
	while (!pop_stack(env, NULL, NULL));
	free_states(env);

	if (ret == 0)
		sanitize_dead_code(env);

	if (ret == 0)
		ret = check_max_stack_depth(env);

	if (ret == 0)
		/* program is valid, convert *(u32*)(ctx + off) accesses */
		ret = convert_ctx_accesses(env);

	if (ret == 0)
		ret = fixup_bpf_calls(env);

	if (ret == 0)
		ret = fixup_call_args(env);

	if (log->level && bpf_verifier_log_full(log))
		ret = -ENOSPC;
	if (log->level && !log->ubuf) {
		ret = -EFAULT;
		goto err_release_maps;
	}

	if (ret == 0 && env->used_map_cnt) {
		/* if program passed verifier, update used_maps in bpf_prog_info */
		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
							  sizeof(env->used_maps[0]),
							  GFP_KERNEL);

		if (!env->prog->aux->used_maps) {
			ret = -ENOMEM;
			goto err_release_maps;
		}

		memcpy(env->prog->aux->used_maps, env->used_maps,
		       sizeof(env->used_maps[0]) * env->used_map_cnt);
		env->prog->aux->used_map_cnt = env->used_map_cnt;

		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
		 * bpf_ld_imm64 instructions
		 */
		convert_pseudo_ld_imm64(env);
	}

err_release_maps:
	if (!env->prog->aux->used_maps)
		/* if we didn't copy map pointers into bpf_prog_info, release
		 * them now. Otherwise free_used_maps() will release them.
		 */
		release_maps(env);
	*prog = env->prog;
err_unlock:
	mutex_unlock(&bpf_verifier_lock);
	vfree(env->insn_aux_data);
err_free_env:
	kfree(env);
	return ret;
}