Eric Lee / smarc-ti-linux-kernel

i915_gem.c 136 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 
/*
 * Copyright © 2008 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Eric Anholt <eric@anholt.net>
 *
 */

#include <drm/drmP.h>
#include <drm/drm_vma_manager.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_drv.h"
#include <linux/oom.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/pci.h>
#include <linux/dma-buf.h>

static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj);
static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
						   bool force);
static __must_check int
i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
			       bool readonly);
static void
i915_gem_object_retire(struct drm_i915_gem_object *obj);

static void i915_gem_write_fence(struct drm_device *dev, int reg,
				 struct drm_i915_gem_object *obj);
static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
					 struct drm_i915_fence_reg *fence,
					 bool enable);

static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker,
					     struct shrink_control *sc);
static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
					    struct shrink_control *sc);
static int i915_gem_shrinker_oom(struct notifier_block *nb,
				 unsigned long event,
				 void *ptr);
static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);

static bool cpu_cache_is_coherent(struct drm_device *dev,
				  enum i915_cache_level level)
{
	return HAS_LLC(dev) || level != I915_CACHE_NONE;
}

static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
{
	if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
		return true;

	return obj->pin_display;
}

static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
{
	if (obj->tiling_mode)
		i915_gem_release_mmap(obj);

	/* As we do not have an associated fence register, we will force
	 * a tiling change if we ever need to acquire one.
	 */
	obj->fence_dirty = false;
	obj->fence_reg = I915_FENCE_REG_NONE;
}

/* some bookkeeping */
static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
				  size_t size)
{
	spin_lock(&dev_priv->mm.object_stat_lock);
	dev_priv->mm.object_count++;
	dev_priv->mm.object_memory += size;
	spin_unlock(&dev_priv->mm.object_stat_lock);
}

static void i915_gem_info_remove_obj(struct drm_i915_private *dev_priv,
				     size_t size)
{
	spin_lock(&dev_priv->mm.object_stat_lock);
	dev_priv->mm.object_count--;
	dev_priv->mm.object_memory -= size;
	spin_unlock(&dev_priv->mm.object_stat_lock);
}

static int
i915_gem_wait_for_error(struct i915_gpu_error *error)
{
	int ret;

#define EXIT_COND (!i915_reset_in_progress(error) || \
		   i915_terminally_wedged(error))
	if (EXIT_COND)
		return 0;

	/*
	 * Only wait 10 seconds for the gpu reset to complete to avoid hanging
	 * userspace. If it takes that long something really bad is going on and
	 * we should simply try to bail out and fail as gracefully as possible.
	 */
	ret = wait_event_interruptible_timeout(error->reset_queue,
					       EXIT_COND,
					       10*HZ);
	if (ret == 0) {
		DRM_ERROR("Timed out waiting for the gpu reset to complete\n");
		return -EIO;
	} else if (ret < 0) {
		return ret;
	}
#undef EXIT_COND

	return 0;
}

int i915_mutex_lock_interruptible(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	ret = i915_gem_wait_for_error(&dev_priv->gpu_error);
	if (ret)
		return ret;

	ret = mutex_lock_interruptible(&dev->struct_mutex);
	if (ret)
		return ret;

	WARN_ON(i915_verify_lists(dev));
	return 0;
}

static inline bool
i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
{
	return i915_gem_obj_bound_any(obj) && !obj->active;
}

int
i915_gem_init_ioctl(struct drm_device *dev, void *data,
		    struct drm_file *file)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_init *args = data;

	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return -ENODEV;

	if (args->gtt_start >= args->gtt_end ||
	    (args->gtt_end | args->gtt_start) & (PAGE_SIZE - 1))
		return -EINVAL;

	/* GEM with user mode setting was never supported on ilk and later. */
	if (INTEL_INFO(dev)->gen >= 5)
		return -ENODEV;

	mutex_lock(&dev->struct_mutex);
	i915_gem_setup_global_gtt(dev, args->gtt_start, args->gtt_end,
				  args->gtt_end);
	dev_priv->gtt.mappable_end = args->gtt_end;
	mutex_unlock(&dev->struct_mutex);

	return 0;
}

int
i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
			    struct drm_file *file)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_get_aperture *args = data;
	struct drm_i915_gem_object *obj;
	size_t pinned;

	pinned = 0;
	mutex_lock(&dev->struct_mutex);
	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
		if (i915_gem_obj_is_pinned(obj))
			pinned += i915_gem_obj_ggtt_size(obj);
	mutex_unlock(&dev->struct_mutex);

	args->aper_size = dev_priv->gtt.base.total;
	args->aper_available_size = args->aper_size - pinned;

	return 0;
}

static void i915_gem_object_detach_phys(struct drm_i915_gem_object *obj)
{
	drm_dma_handle_t *phys = obj->phys_handle;

	if (!phys)
		return;

	if (obj->madv == I915_MADV_WILLNEED) {
		struct address_space *mapping = file_inode(obj->base.filp)->i_mapping;
		char *vaddr = phys->vaddr;
		int i;

		for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
			struct page *page = shmem_read_mapping_page(mapping, i);
			if (!IS_ERR(page)) {
				char *dst = kmap_atomic(page);
				memcpy(dst, vaddr, PAGE_SIZE);
				drm_clflush_virt_range(dst, PAGE_SIZE);
				kunmap_atomic(dst);

				set_page_dirty(page);
				mark_page_accessed(page);
				page_cache_release(page);
			}
			vaddr += PAGE_SIZE;
		}
		i915_gem_chipset_flush(obj->base.dev);
	}

#ifdef CONFIG_X86
	set_memory_wb((unsigned long)phys->vaddr, phys->size / PAGE_SIZE);
#endif
	drm_pci_free(obj->base.dev, phys);
	obj->phys_handle = NULL;
}

int
i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
			    int align)
{
	drm_dma_handle_t *phys;
	struct address_space *mapping;
	char *vaddr;
	int i;

	if (obj->phys_handle) {
		if ((unsigned long)obj->phys_handle->vaddr & (align -1))
			return -EBUSY;

		return 0;
	}

	if (obj->madv != I915_MADV_WILLNEED)
		return -EFAULT;

	if (obj->base.filp == NULL)
		return -EINVAL;

	/* create a new object */
	phys = drm_pci_alloc(obj->base.dev, obj->base.size, align);
	if (!phys)
		return -ENOMEM;

	vaddr = phys->vaddr;
#ifdef CONFIG_X86
	set_memory_wc((unsigned long)vaddr, phys->size / PAGE_SIZE);
#endif
	mapping = file_inode(obj->base.filp)->i_mapping;
	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
		struct page *page;
		char *src;

		page = shmem_read_mapping_page(mapping, i);
		if (IS_ERR(page)) {
#ifdef CONFIG_X86
			set_memory_wb((unsigned long)phys->vaddr, phys->size / PAGE_SIZE);
#endif
			drm_pci_free(obj->base.dev, phys);
			return PTR_ERR(page);
		}

		src = kmap_atomic(page);
		memcpy(vaddr, src, PAGE_SIZE);
		kunmap_atomic(src);

		mark_page_accessed(page);
		page_cache_release(page);

		vaddr += PAGE_SIZE;
	}

	obj->phys_handle = phys;
	return 0;
}

static int
i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
		     struct drm_i915_gem_pwrite *args,
		     struct drm_file *file_priv)
{
	struct drm_device *dev = obj->base.dev;
	void *vaddr = obj->phys_handle->vaddr + args->offset;
	char __user *user_data = to_user_ptr(args->data_ptr);

	if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) {
		unsigned long unwritten;

		/* The physical object once assigned is fixed for the lifetime
		 * of the obj, so we can safely drop the lock and continue
		 * to access vaddr.
		 */
		mutex_unlock(&dev->struct_mutex);
		unwritten = copy_from_user(vaddr, user_data, args->size);
		mutex_lock(&dev->struct_mutex);
		if (unwritten)
			return -EFAULT;
	}

	i915_gem_chipset_flush(dev);
	return 0;
}

void *i915_gem_object_alloc(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	return kmem_cache_zalloc(dev_priv->slab, GFP_KERNEL);
}

void i915_gem_object_free(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	kmem_cache_free(dev_priv->slab, obj);
}

static int
i915_gem_create(struct drm_file *file,
		struct drm_device *dev,
		uint64_t size,
		uint32_t *handle_p)
{
	struct drm_i915_gem_object *obj;
	int ret;
	u32 handle;

	size = roundup(size, PAGE_SIZE);
	if (size == 0)
		return -EINVAL;

	/* Allocate the new object */
	obj = i915_gem_alloc_object(dev, size);
	if (obj == NULL)
		return -ENOMEM;

	ret = drm_gem_handle_create(file, &obj->base, &handle);
	/* drop reference from allocate - handle holds it now */
	drm_gem_object_unreference_unlocked(&obj->base);
	if (ret)
		return ret;

	*handle_p = handle;
	return 0;
}

int
i915_gem_dumb_create(struct drm_file *file,
		     struct drm_device *dev,
		     struct drm_mode_create_dumb *args)
{
	/* have to work out size/pitch and return them */
	args->pitch = ALIGN(args->width * DIV_ROUND_UP(args->bpp, 8), 64);
	args->size = args->pitch * args->height;
	return i915_gem_create(file, dev,
			       args->size, &args->handle);
}

/**
 * Creates a new mm object and returns a handle to it.
 */
int
i915_gem_create_ioctl(struct drm_device *dev, void *data,
		      struct drm_file *file)
{
	struct drm_i915_gem_create *args = data;

	return i915_gem_create(file, dev,
			       args->size, &args->handle);
}

static inline int
__copy_to_user_swizzled(char __user *cpu_vaddr,
			const char *gpu_vaddr, int gpu_offset,
			int length)
{
	int ret, cpu_offset = 0;

	while (length > 0) {
		int cacheline_end = ALIGN(gpu_offset + 1, 64);
		int this_length = min(cacheline_end - gpu_offset, length);
		int swizzled_gpu_offset = gpu_offset ^ 64;

		ret = __copy_to_user(cpu_vaddr + cpu_offset,
				     gpu_vaddr + swizzled_gpu_offset,
				     this_length);
		if (ret)
			return ret + length;

		cpu_offset += this_length;
		gpu_offset += this_length;
		length -= this_length;
	}

	return 0;
}

static inline int
__copy_from_user_swizzled(char *gpu_vaddr, int gpu_offset,
			  const char __user *cpu_vaddr,
			  int length)
{
	int ret, cpu_offset = 0;

	while (length > 0) {
		int cacheline_end = ALIGN(gpu_offset + 1, 64);
		int this_length = min(cacheline_end - gpu_offset, length);
		int swizzled_gpu_offset = gpu_offset ^ 64;

		ret = __copy_from_user(gpu_vaddr + swizzled_gpu_offset,
				       cpu_vaddr + cpu_offset,
				       this_length);
		if (ret)
			return ret + length;

		cpu_offset += this_length;
		gpu_offset += this_length;
		length -= this_length;
	}

	return 0;
}

/*
 * Pins the specified object's pages and synchronizes the object with
 * GPU accesses. Sets needs_clflush to non-zero if the caller should
 * flush the object from the CPU cache.
 */
int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
				    int *needs_clflush)
{
	int ret;

	*needs_clflush = 0;

	if (!obj->base.filp)
		return -EINVAL;

	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
		/* If we're not in the cpu read domain, set ourself into the gtt
		 * read domain and manually flush cachelines (if required). This
		 * optimizes for the case when the gpu will dirty the data
		 * anyway again before the next pread happens. */
		*needs_clflush = !cpu_cache_is_coherent(obj->base.dev,
							obj->cache_level);
		ret = i915_gem_object_wait_rendering(obj, true);
		if (ret)
			return ret;

		i915_gem_object_retire(obj);
	}

	ret = i915_gem_object_get_pages(obj);
	if (ret)
		return ret;

	i915_gem_object_pin_pages(obj);

	return ret;
}

/* Per-page copy function for the shmem pread fastpath.
 * Flushes invalid cachelines before reading the target if
 * needs_clflush is set. */
static int
shmem_pread_fast(struct page *page, int shmem_page_offset, int page_length,
		 char __user *user_data,
		 bool page_do_bit17_swizzling, bool needs_clflush)
{
	char *vaddr;
	int ret;

	if (unlikely(page_do_bit17_swizzling))
		return -EINVAL;

	vaddr = kmap_atomic(page);
	if (needs_clflush)
		drm_clflush_virt_range(vaddr + shmem_page_offset,
				       page_length);
	ret = __copy_to_user_inatomic(user_data,
				      vaddr + shmem_page_offset,
				      page_length);
	kunmap_atomic(vaddr);

	return ret ? -EFAULT : 0;
}

static void
shmem_clflush_swizzled_range(char *addr, unsigned long length,
			     bool swizzled)
{
	if (unlikely(swizzled)) {
		unsigned long start = (unsigned long) addr;
		unsigned long end = (unsigned long) addr + length;

		/* For swizzling simply ensure that we always flush both
		 * channels. Lame, but simple and it works. Swizzled
		 * pwrite/pread is far from a hotpath - current userspace
		 * doesn't use it at all. */
		start = round_down(start, 128);
		end = round_up(end, 128);

		drm_clflush_virt_range((void *)start, end - start);
	} else {
		drm_clflush_virt_range(addr, length);
	}

}

/* Only difference to the fast-path function is that this can handle bit17
 * and uses non-atomic copy and kmap functions. */
static int
shmem_pread_slow(struct page *page, int shmem_page_offset, int page_length,
		 char __user *user_data,
		 bool page_do_bit17_swizzling, bool needs_clflush)
{
	char *vaddr;
	int ret;

	vaddr = kmap(page);
	if (needs_clflush)
		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
					     page_length,
					     page_do_bit17_swizzling);

	if (page_do_bit17_swizzling)
		ret = __copy_to_user_swizzled(user_data,
					      vaddr, shmem_page_offset,
					      page_length);
	else
		ret = __copy_to_user(user_data,
				     vaddr + shmem_page_offset,
				     page_length);
	kunmap(page);

	return ret ? - EFAULT : 0;
}

static int
i915_gem_shmem_pread(struct drm_device *dev,
		     struct drm_i915_gem_object *obj,
		     struct drm_i915_gem_pread *args,
		     struct drm_file *file)
{
	char __user *user_data;
	ssize_t remain;
	loff_t offset;
	int shmem_page_offset, page_length, ret = 0;
	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
	int prefaulted = 0;
	int needs_clflush = 0;
	struct sg_page_iter sg_iter;

	user_data = to_user_ptr(args->data_ptr);
	remain = args->size;

	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);

	ret = i915_gem_obj_prepare_shmem_read(obj, &needs_clflush);
	if (ret)
		return ret;

	offset = args->offset;

	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents,
			 offset >> PAGE_SHIFT) {
		struct page *page = sg_page_iter_page(&sg_iter);

		if (remain <= 0)
			break;

		/* Operation in this page
		 *
		 * shmem_page_offset = offset within page in shmem file
		 * page_length = bytes to copy for this page
		 */
		shmem_page_offset = offset_in_page(offset);
		page_length = remain;
		if ((shmem_page_offset + page_length) > PAGE_SIZE)
			page_length = PAGE_SIZE - shmem_page_offset;

		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
			(page_to_phys(page) & (1 << 17)) != 0;

		ret = shmem_pread_fast(page, shmem_page_offset, page_length,
				       user_data, page_do_bit17_swizzling,
				       needs_clflush);
		if (ret == 0)
			goto next_page;

		mutex_unlock(&dev->struct_mutex);

		if (likely(!i915.prefault_disable) && !prefaulted) {
			ret = fault_in_multipages_writeable(user_data, remain);
			/* Userspace is tricking us, but we've already clobbered
			 * its pages with the prefault and promised to write the
			 * data up to the first fault. Hence ignore any errors
			 * and just continue. */
			(void)ret;
			prefaulted = 1;
		}

		ret = shmem_pread_slow(page, shmem_page_offset, page_length,
				       user_data, page_do_bit17_swizzling,
				       needs_clflush);

		mutex_lock(&dev->struct_mutex);

		if (ret)
			goto out;

next_page:
		remain -= page_length;
		user_data += page_length;
		offset += page_length;
	}

out:
	i915_gem_object_unpin_pages(obj);

	return ret;
}

/**
 * Reads data from the object referenced by handle.
 *
 * On error, the contents of *data are undefined.
 */
int
i915_gem_pread_ioctl(struct drm_device *dev, void *data,
		     struct drm_file *file)
{
	struct drm_i915_gem_pread *args = data;
	struct drm_i915_gem_object *obj;
	int ret = 0;

	if (args->size == 0)
		return 0;

	if (!access_ok(VERIFY_WRITE,
		       to_user_ptr(args->data_ptr),
		       args->size))
		return -EFAULT;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	/* Bounds check source.  */
	if (args->offset > obj->base.size ||
	    args->size > obj->base.size - args->offset) {
		ret = -EINVAL;
		goto out;
	}

	/* prime objects have no backing filp to GEM pread/pwrite
	 * pages from.
	 */
	if (!obj->base.filp) {
		ret = -EINVAL;
		goto out;
	}

	trace_i915_gem_object_pread(obj, args->offset, args->size);

	ret = i915_gem_shmem_pread(dev, obj, args, file);

out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

/* This is the fast write path which cannot handle
 * page faults in the source data
 */

static inline int
fast_user_write(struct io_mapping *mapping,
		loff_t page_base, int page_offset,
		char __user *user_data,
		int length)
{
	void __iomem *vaddr_atomic;
	void *vaddr;
	unsigned long unwritten;

	vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base);
	/* We can use the cpu mem copy function because this is X86. */
	vaddr = (void __force*)vaddr_atomic + page_offset;
	unwritten = __copy_from_user_inatomic_nocache(vaddr,
						      user_data, length);
	io_mapping_unmap_atomic(vaddr_atomic);
	return unwritten;
}

/**
 * This is the fast pwrite path, where we copy the data directly from the
 * user into the GTT, uncached.
 */
static int
i915_gem_gtt_pwrite_fast(struct drm_device *dev,
			 struct drm_i915_gem_object *obj,
			 struct drm_i915_gem_pwrite *args,
			 struct drm_file *file)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	ssize_t remain;
	loff_t offset, page_base;
	char __user *user_data;
	int page_offset, page_length, ret;

	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
	if (ret)
		goto out;

	ret = i915_gem_object_set_to_gtt_domain(obj, true);
	if (ret)
		goto out_unpin;

	ret = i915_gem_object_put_fence(obj);
	if (ret)
		goto out_unpin;

	user_data = to_user_ptr(args->data_ptr);
	remain = args->size;

	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;

	while (remain > 0) {
		/* Operation in this page
		 *
		 * page_base = page offset within aperture
		 * page_offset = offset within page
		 * page_length = bytes to copy for this page
		 */
		page_base = offset & PAGE_MASK;
		page_offset = offset_in_page(offset);
		page_length = remain;
		if ((page_offset + remain) > PAGE_SIZE)
			page_length = PAGE_SIZE - page_offset;

		/* If we get a fault while copying data, then (presumably) our
		 * source page isn't available.  Return the error and we'll
		 * retry in the slow path.
		 */
		if (fast_user_write(dev_priv->gtt.mappable, page_base,
				    page_offset, user_data, page_length)) {
			ret = -EFAULT;
			goto out_unpin;
		}

		remain -= page_length;
		user_data += page_length;
		offset += page_length;
	}

out_unpin:
	i915_gem_object_ggtt_unpin(obj);
out:
	return ret;
}

/* Per-page copy function for the shmem pwrite fastpath.
 * Flushes invalid cachelines before writing to the target if
 * needs_clflush_before is set and flushes out any written cachelines after
 * writing if needs_clflush is set. */
static int
shmem_pwrite_fast(struct page *page, int shmem_page_offset, int page_length,
		  char __user *user_data,
		  bool page_do_bit17_swizzling,
		  bool needs_clflush_before,
		  bool needs_clflush_after)
{
	char *vaddr;
	int ret;

	if (unlikely(page_do_bit17_swizzling))
		return -EINVAL;

	vaddr = kmap_atomic(page);
	if (needs_clflush_before)
		drm_clflush_virt_range(vaddr + shmem_page_offset,
				       page_length);
	ret = __copy_from_user_inatomic(vaddr + shmem_page_offset,
					user_data, page_length);
	if (needs_clflush_after)
		drm_clflush_virt_range(vaddr + shmem_page_offset,
				       page_length);
	kunmap_atomic(vaddr);

	return ret ? -EFAULT : 0;
}

/* Only difference to the fast-path function is that this can handle bit17
 * and uses non-atomic copy and kmap functions. */
static int
shmem_pwrite_slow(struct page *page, int shmem_page_offset, int page_length,
		  char __user *user_data,
		  bool page_do_bit17_swizzling,
		  bool needs_clflush_before,
		  bool needs_clflush_after)
{
	char *vaddr;
	int ret;

	vaddr = kmap(page);
	if (unlikely(needs_clflush_before || page_do_bit17_swizzling))
		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
					     page_length,
					     page_do_bit17_swizzling);
	if (page_do_bit17_swizzling)
		ret = __copy_from_user_swizzled(vaddr, shmem_page_offset,
						user_data,
						page_length);
	else
		ret = __copy_from_user(vaddr + shmem_page_offset,
				       user_data,
				       page_length);
	if (needs_clflush_after)
		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
					     page_length,
					     page_do_bit17_swizzling);
	kunmap(page);

	return ret ? -EFAULT : 0;
}

static int
i915_gem_shmem_pwrite(struct drm_device *dev,
		      struct drm_i915_gem_object *obj,
		      struct drm_i915_gem_pwrite *args,
		      struct drm_file *file)
{
	ssize_t remain;
	loff_t offset;
	char __user *user_data;
	int shmem_page_offset, page_length, ret = 0;
	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
	int hit_slowpath = 0;
	int needs_clflush_after = 0;
	int needs_clflush_before = 0;
	struct sg_page_iter sg_iter;

	user_data = to_user_ptr(args->data_ptr);
	remain = args->size;

	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);

	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
		/* If we're not in the cpu write domain, set ourself into the gtt
		 * write domain and manually flush cachelines (if required). This
		 * optimizes for the case when the gpu will use the data
		 * right away and we therefore have to clflush anyway. */
		needs_clflush_after = cpu_write_needs_clflush(obj);
		ret = i915_gem_object_wait_rendering(obj, false);
		if (ret)
			return ret;

		i915_gem_object_retire(obj);
	}
	/* Same trick applies to invalidate partially written cachelines read
	 * before writing. */
	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0)
		needs_clflush_before =
			!cpu_cache_is_coherent(dev, obj->cache_level);

	ret = i915_gem_object_get_pages(obj);
	if (ret)
		return ret;

	i915_gem_object_pin_pages(obj);

	offset = args->offset;
	obj->dirty = 1;

	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents,
			 offset >> PAGE_SHIFT) {
		struct page *page = sg_page_iter_page(&sg_iter);
		int partial_cacheline_write;

		if (remain <= 0)
			break;

		/* Operation in this page
		 *
		 * shmem_page_offset = offset within page in shmem file
		 * page_length = bytes to copy for this page
		 */
		shmem_page_offset = offset_in_page(offset);

		page_length = remain;
		if ((shmem_page_offset + page_length) > PAGE_SIZE)
			page_length = PAGE_SIZE - shmem_page_offset;

		/* If we don't overwrite a cacheline completely we need to be
		 * careful to have up-to-date data by first clflushing. Don't
		 * overcomplicate things and flush the entire patch. */
		partial_cacheline_write = needs_clflush_before &&
			((shmem_page_offset | page_length)
				& (boot_cpu_data.x86_clflush_size - 1));

		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
			(page_to_phys(page) & (1 << 17)) != 0;

		ret = shmem_pwrite_fast(page, shmem_page_offset, page_length,
					user_data, page_do_bit17_swizzling,
					partial_cacheline_write,
					needs_clflush_after);
		if (ret == 0)
			goto next_page;

		hit_slowpath = 1;
		mutex_unlock(&dev->struct_mutex);
		ret = shmem_pwrite_slow(page, shmem_page_offset, page_length,
					user_data, page_do_bit17_swizzling,
					partial_cacheline_write,
					needs_clflush_after);

		mutex_lock(&dev->struct_mutex);

		if (ret)
			goto out;

next_page:
		remain -= page_length;
		user_data += page_length;
		offset += page_length;
	}

out:
	i915_gem_object_unpin_pages(obj);

	if (hit_slowpath) {
		/*
		 * Fixup: Flush cpu caches in case we didn't flush the dirty
		 * cachelines in-line while writing and the object moved
		 * out of the cpu write domain while we've dropped the lock.
		 */
		if (!needs_clflush_after &&
		    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
			if (i915_gem_clflush_object(obj, obj->pin_display))
				i915_gem_chipset_flush(dev);
		}
	}

	if (needs_clflush_after)
		i915_gem_chipset_flush(dev);

	return ret;
}

/**
 * Writes data to the object referenced by handle.
 *
 * On error, the contents of the buffer that were to be modified are undefined.
 */
int
i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
		      struct drm_file *file)
{
	struct drm_i915_gem_pwrite *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	if (args->size == 0)
		return 0;

	if (!access_ok(VERIFY_READ,
		       to_user_ptr(args->data_ptr),
		       args->size))
		return -EFAULT;

	if (likely(!i915.prefault_disable)) {
		ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
						   args->size);
		if (ret)
			return -EFAULT;
	}

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	/* Bounds check destination. */
	if (args->offset > obj->base.size ||
	    args->size > obj->base.size - args->offset) {
		ret = -EINVAL;
		goto out;
	}

	/* prime objects have no backing filp to GEM pread/pwrite
	 * pages from.
	 */
	if (!obj->base.filp) {
		ret = -EINVAL;
		goto out;
	}

	trace_i915_gem_object_pwrite(obj, args->offset, args->size);

	ret = -EFAULT;
	/* We can only do the GTT pwrite on untiled buffers, as otherwise
	 * it would end up going through the fenced access, and we'll get
	 * different detiling behavior between reading and writing.
	 * pread/pwrite currently are reading and writing from the CPU
	 * perspective, requiring manual detiling by the client.
	 */
	if (obj->phys_handle) {
		ret = i915_gem_phys_pwrite(obj, args, file);
		goto out;
	}

	if (obj->tiling_mode == I915_TILING_NONE &&
	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
	    cpu_write_needs_clflush(obj)) {
		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
		/* Note that the gtt paths might fail with non-page-backed user
		 * pointers (e.g. gtt mappings when moving data between
		 * textures). Fallback to the shmem path in that case. */
	}

	if (ret == -EFAULT || ret == -ENOSPC)
		ret = i915_gem_shmem_pwrite(dev, obj, args, file);

out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int
i915_gem_check_wedge(struct i915_gpu_error *error,
		     bool interruptible)
{
	if (i915_reset_in_progress(error)) {
		/* Non-interruptible callers can't handle -EAGAIN, hence return
		 * -EIO unconditionally for these. */
		if (!interruptible)
			return -EIO;

		/* Recovery complete, but the reset failed ... */
		if (i915_terminally_wedged(error))
			return -EIO;

		/*
		 * Check if GPU Reset is in progress - we need intel_ring_begin
		 * to work properly to reinit the hw state while the gpu is
		 * still marked as reset-in-progress. Handle this with a flag.
		 */
		if (!error->reload_in_reset)
			return -EAGAIN;
	}

	return 0;
}

/*
 * Compare seqno against outstanding lazy request. Emit a request if they are
 * equal.
 */
int
i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno)
{
	int ret;

	BUG_ON(!mutex_is_locked(&ring->dev->struct_mutex));

	ret = 0;
	if (seqno == ring->outstanding_lazy_seqno)
		ret = i915_add_request(ring, NULL);

	return ret;
}

static void fake_irq(unsigned long data)
{
	wake_up_process((struct task_struct *)data);
}

static bool missed_irq(struct drm_i915_private *dev_priv,
		       struct intel_engine_cs *ring)
{
	return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
}

static bool can_wait_boost(struct drm_i915_file_private *file_priv)
{
	if (file_priv == NULL)
		return true;

	return !atomic_xchg(&file_priv->rps_wait_boost, true);
}

/**
 * __wait_seqno - wait until execution of seqno has finished
 * @ring: the ring expected to report seqno
 * @seqno: duh!
 * @reset_counter: reset sequence associated with the given seqno
 * @interruptible: do an interruptible wait (normally yes)
 * @timeout: in - how long to wait (NULL forever); out - how much time remaining
 *
 * Note: It is of utmost importance that the passed in seqno and reset_counter
 * values have been read by the caller in an smp safe manner. Where read-side
 * locks are involved, it is sufficient to read the reset_counter before
 * unlocking the lock that protects the seqno. For lockless tricks, the
 * reset_counter _must_ be read before, and an appropriate smp_rmb must be
 * inserted.
 *
 * Returns 0 if the seqno was found within the alloted time. Else returns the
 * errno with remaining time filled in timeout argument.
 */
static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno,
			unsigned reset_counter,
			bool interruptible,
			s64 *timeout,
			struct drm_i915_file_private *file_priv)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	const bool irq_test_in_progress =
		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
	DEFINE_WAIT(wait);
	unsigned long timeout_expire;
	s64 before, now;
	int ret;

	WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled");

	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
		return 0;

	timeout_expire = timeout ? jiffies + nsecs_to_jiffies((u64)*timeout) : 0;

	if (INTEL_INFO(dev)->gen >= 6 && ring->id == RCS && can_wait_boost(file_priv)) {
		gen6_rps_boost(dev_priv);
		if (file_priv)
			mod_delayed_work(dev_priv->wq,
					 &file_priv->mm.idle_work,
					 msecs_to_jiffies(100));
	}

	if (!irq_test_in_progress && WARN_ON(!ring->irq_get(ring)))
		return -ENODEV;

	/* Record current time in case interrupted by signal, or wedged */
	trace_i915_gem_request_wait_begin(ring, seqno);
	before = ktime_get_raw_ns();
	for (;;) {
		struct timer_list timer;

		prepare_to_wait(&ring->irq_queue, &wait,
				interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);

		/* We need to check whether any gpu reset happened in between
		 * the caller grabbing the seqno and now ... */
		if (reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter)) {
			/* ... but upgrade the -EAGAIN to an -EIO if the gpu
			 * is truely gone. */
			ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible);
			if (ret == 0)
				ret = -EAGAIN;
			break;
		}

		if (i915_seqno_passed(ring->get_seqno(ring, false), seqno)) {
			ret = 0;
			break;
		}

		if (interruptible && signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}

		if (timeout && time_after_eq(jiffies, timeout_expire)) {
			ret = -ETIME;
			break;
		}

		timer.function = NULL;
		if (timeout || missed_irq(dev_priv, ring)) {
			unsigned long expire;

			setup_timer_on_stack(&timer, fake_irq, (unsigned long)current);
			expire = missed_irq(dev_priv, ring) ? jiffies + 1 : timeout_expire;
			mod_timer(&timer, expire);
		}

		io_schedule();

		if (timer.function) {
			del_singleshot_timer_sync(&timer);
			destroy_timer_on_stack(&timer);
		}
	}
	now = ktime_get_raw_ns();
	trace_i915_gem_request_wait_end(ring, seqno);

	if (!irq_test_in_progress)
		ring->irq_put(ring);

	finish_wait(&ring->irq_queue, &wait);

	if (timeout) {
		s64 tres = *timeout - (now - before);

		*timeout = tres < 0 ? 0 : tres;
	}

	return ret;
}

/**
 * Waits for a sequence number to be signaled, and cleans up the
 * request and object lists appropriately for that event.
 */
int
i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	bool interruptible = dev_priv->mm.interruptible;
	int ret;

	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
	BUG_ON(seqno == 0);

	ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible);
	if (ret)
		return ret;

	ret = i915_gem_check_olr(ring, seqno);
	if (ret)
		return ret;

	return __wait_seqno(ring, seqno,
			    atomic_read(&dev_priv->gpu_error.reset_counter),
			    interruptible, NULL, NULL);
}

static int
i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
				     struct intel_engine_cs *ring)
{
	if (!obj->active)
		return 0;

	/* Manually manage the write flush as we may have not yet
	 * retired the buffer.
	 *
	 * Note that the last_write_seqno is always the earlier of
	 * the two (read/write) seqno, so if we haved successfully waited,
	 * we know we have passed the last write.
	 */
	obj->last_write_seqno = 0;

	return 0;
}

/**
 * Ensures that all rendering to the object has completed and the object is
 * safe to unbind from the GTT or access from the CPU.
 */
static __must_check int
i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
			       bool readonly)
{
	struct intel_engine_cs *ring = obj->ring;
	u32 seqno;
	int ret;

	seqno = readonly ? obj->last_write_seqno : obj->last_read_seqno;
	if (seqno == 0)
		return 0;

	ret = i915_wait_seqno(ring, seqno);
	if (ret)
		return ret;

	return i915_gem_object_wait_rendering__tail(obj, ring);
}

/* A nonblocking variant of the above wait. This is a highly dangerous routine
 * as the object state may change during this call.
 */
static __must_check int
i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
					    struct drm_i915_file_private *file_priv,
					    bool readonly)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring = obj->ring;
	unsigned reset_counter;
	u32 seqno;
	int ret;

	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
	BUG_ON(!dev_priv->mm.interruptible);

	seqno = readonly ? obj->last_write_seqno : obj->last_read_seqno;
	if (seqno == 0)
		return 0;

	ret = i915_gem_check_wedge(&dev_priv->gpu_error, true);
	if (ret)
		return ret;

	ret = i915_gem_check_olr(ring, seqno);
	if (ret)
		return ret;

	reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
	mutex_unlock(&dev->struct_mutex);
	ret = __wait_seqno(ring, seqno, reset_counter, true, NULL, file_priv);
	mutex_lock(&dev->struct_mutex);
	if (ret)
		return ret;

	return i915_gem_object_wait_rendering__tail(obj, ring);
}

/**
 * Called when user space prepares to use an object with the CPU, either
 * through the mmap ioctl's mapping or a GTT mapping.
 */
int
i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
			  struct drm_file *file)
{
	struct drm_i915_gem_set_domain *args = data;
	struct drm_i915_gem_object *obj;
	uint32_t read_domains = args->read_domains;
	uint32_t write_domain = args->write_domain;
	int ret;

	/* Only handle setting domains to types used by the CPU. */
	if (write_domain & I915_GEM_GPU_DOMAINS)
		return -EINVAL;

	if (read_domains & I915_GEM_GPU_DOMAINS)
		return -EINVAL;

	/* Having something in the write domain implies it's in the read
	 * domain, and only that read domain.  Enforce that in the request.
	 */
	if (write_domain != 0 && read_domains != write_domain)
		return -EINVAL;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	/* Try to flush the object off the GPU without holding the lock.
	 * We will repeat the flush holding the lock in the normal manner
	 * to catch cases where we are gazumped.
	 */
	ret = i915_gem_object_wait_rendering__nonblocking(obj,
							  file->driver_priv,
							  !write_domain);
	if (ret)
		goto unref;

	if (read_domains & I915_GEM_DOMAIN_GTT) {
		ret = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0);

		/* Silently promote "you're not bound, there was nothing to do"
		 * to success, since the client was just asking us to
		 * make sure everything was done.
		 */
		if (ret == -EINVAL)
			ret = 0;
	} else {
		ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
	}

unref:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

/**
 * Called when user space has done writes to this buffer
 */
int
i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
			 struct drm_file *file)
{
	struct drm_i915_gem_sw_finish *args = data;
	struct drm_i915_gem_object *obj;
	int ret = 0;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	/* Pinned buffers may be scanout, so flush the cache */
	if (obj->pin_display)
		i915_gem_object_flush_cpu_write_domain(obj, true);

	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

/**
 * Maps the contents of an object, returning the address it is mapped
 * into.
 *
 * While the mapping holds a reference on the contents of the object, it doesn't
 * imply a ref on the object itself.
 */
int
i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
		    struct drm_file *file)
{
	struct drm_i915_gem_mmap *args = data;
	struct drm_gem_object *obj;
	unsigned long addr;

	obj = drm_gem_object_lookup(dev, file, args->handle);
	if (obj == NULL)
		return -ENOENT;

	/* prime objects have no backing filp to GEM mmap
	 * pages from.
	 */
	if (!obj->filp) {
		drm_gem_object_unreference_unlocked(obj);
		return -EINVAL;
	}

	addr = vm_mmap(obj->filp, 0, args->size,
		       PROT_READ | PROT_WRITE, MAP_SHARED,
		       args->offset);
	drm_gem_object_unreference_unlocked(obj);
	if (IS_ERR((void *)addr))
		return addr;

	args->addr_ptr = (uint64_t) addr;

	return 0;
}

/**
 * i915_gem_fault - fault a page into the GTT
 * vma: VMA in question
 * vmf: fault info
 *
 * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
 * from userspace.  The fault handler takes care of binding the object to
 * the GTT (if needed), allocating and programming a fence register (again,
 * only if needed based on whether the old reg is still valid or the object
 * is tiled) and inserting a new PTE into the faulting process.
 *
 * Note that the faulting process may involve evicting existing objects
 * from the GTT and/or fence registers to make room.  So performance may
 * suffer if the GTT working set is large or there are few fence registers
 * left.
 */
int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct drm_i915_gem_object *obj = to_intel_bo(vma->vm_private_data);
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	pgoff_t page_offset;
	unsigned long pfn;
	int ret = 0;
	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);

	intel_runtime_pm_get(dev_priv);

	/* We don't use vmf->pgoff since that has the fake offset */
	page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >>
		PAGE_SHIFT;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		goto out;

	trace_i915_gem_object_fault(obj, page_offset, true, write);

	/* Try to flush the object off the GPU first without holding the lock.
	 * Upon reacquiring the lock, we will perform our sanity checks and then
	 * repeat the flush holding the lock in the normal manner to catch cases
	 * where we are gazumped.
	 */
	ret = i915_gem_object_wait_rendering__nonblocking(obj, NULL, !write);
	if (ret)
		goto unlock;

	/* Access to snoopable pages through the GTT is incoherent. */
	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(dev)) {
		ret = -EFAULT;
		goto unlock;
	}

	/* Now bind it into the GTT if needed */
	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE);
	if (ret)
		goto unlock;

	ret = i915_gem_object_set_to_gtt_domain(obj, write);
	if (ret)
		goto unpin;

	ret = i915_gem_object_get_fence(obj);
	if (ret)
		goto unpin;

	/* Finally, remap it using the new GTT offset */
	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
	pfn >>= PAGE_SHIFT;

	if (!obj->fault_mappable) {
		unsigned long size = min_t(unsigned long,
					   vma->vm_end - vma->vm_start,
					   obj->base.size);
		int i;

		for (i = 0; i < size >> PAGE_SHIFT; i++) {
			ret = vm_insert_pfn(vma,
					    (unsigned long)vma->vm_start + i * PAGE_SIZE,
					    pfn + i);
			if (ret)
				break;
		}

		obj->fault_mappable = true;
	} else
		ret = vm_insert_pfn(vma,
				    (unsigned long)vmf->virtual_address,
				    pfn + page_offset);
unpin:
	i915_gem_object_ggtt_unpin(obj);
unlock:
	mutex_unlock(&dev->struct_mutex);
out:
	switch (ret) {
	case -EIO:
		/*
		 * We eat errors when the gpu is terminally wedged to avoid
		 * userspace unduly crashing (gl has no provisions for mmaps to
		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
		 * and so needs to be reported.
		 */
		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
			ret = VM_FAULT_SIGBUS;
			break;
		}
	case -EAGAIN:
		/*
		 * EAGAIN means the gpu is hung and we'll wait for the error
		 * handler to reset everything when re-faulting in
		 * i915_mutex_lock_interruptible.
		 */
	case 0:
	case -ERESTARTSYS:
	case -EINTR:
	case -EBUSY:
		/*
		 * EBUSY is ok: this just means that another thread
		 * already did the job.
		 */
		ret = VM_FAULT_NOPAGE;
		break;
	case -ENOMEM:
		ret = VM_FAULT_OOM;
		break;
	case -ENOSPC:
	case -EFAULT:
		ret = VM_FAULT_SIGBUS;
		break;
	default:
		WARN_ONCE(ret, "unhandled error in i915_gem_fault: %i\n", ret);
		ret = VM_FAULT_SIGBUS;
		break;
	}

	intel_runtime_pm_put(dev_priv);
	return ret;
}

/**
 * i915_gem_release_mmap - remove physical page mappings
 * @obj: obj in question
 *
 * Preserve the reservation of the mmapping with the DRM core code, but
 * relinquish ownership of the pages back to the system.
 *
 * It is vital that we remove the page mapping if we have mapped a tiled
 * object through the GTT and then lose the fence register due to
 * resource pressure. Similarly if the object has been moved out of the
 * aperture, than pages mapped into userspace must be revoked. Removing the
 * mapping will then trigger a page fault on the next user access, allowing
 * fixup by i915_gem_fault().
 */
void
i915_gem_release_mmap(struct drm_i915_gem_object *obj)
{
	if (!obj->fault_mappable)
		return;

	drm_vma_node_unmap(&obj->base.vma_node,
			   obj->base.dev->anon_inode->i_mapping);
	obj->fault_mappable = false;
}

void
i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
{
	struct drm_i915_gem_object *obj;

	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
		i915_gem_release_mmap(obj);
}

uint32_t
i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
{
	uint32_t gtt_size;

	if (INTEL_INFO(dev)->gen >= 4 ||
	    tiling_mode == I915_TILING_NONE)
		return size;

	/* Previous chips need a power-of-two fence region when tiling */
	if (INTEL_INFO(dev)->gen == 3)
		gtt_size = 1024*1024;
	else
		gtt_size = 512*1024;

	while (gtt_size < size)
		gtt_size <<= 1;

	return gtt_size;
}

/**
 * i915_gem_get_gtt_alignment - return required GTT alignment for an object
 * @obj: object to check
 *
 * Return the required GTT alignment for an object, taking into account
 * potential fence register mapping.
 */
uint32_t
i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size,
			   int tiling_mode, bool fenced)
{
	/*
	 * Minimum alignment is 4k (GTT page size), but might be greater
	 * if a fence register is needed for the object.
	 */
	if (INTEL_INFO(dev)->gen >= 4 || (!fenced && IS_G33(dev)) ||
	    tiling_mode == I915_TILING_NONE)
		return 4096;

	/*
	 * Previous chips need to be aligned to the size of the smallest
	 * fence register that can contain the object.
	 */
	return i915_gem_get_gtt_size(dev, size, tiling_mode);
}

static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	int ret;

	if (drm_vma_node_has_offset(&obj->base.vma_node))
		return 0;

	dev_priv->mm.shrinker_no_lock_stealing = true;

	ret = drm_gem_create_mmap_offset(&obj->base);
	if (ret != -ENOSPC)
		goto out;

	/* Badly fragmented mmap space? The only way we can recover
	 * space is by destroying unwanted objects. We can't randomly release
	 * mmap_offsets as userspace expects them to be persistent for the
	 * lifetime of the objects. The closest we can is to release the
	 * offsets on purgeable objects by truncating it and marking it purged,
	 * which prevents userspace from ever using that object again.
	 */
	i915_gem_shrink(dev_priv,
			obj->base.size >> PAGE_SHIFT,
			I915_SHRINK_BOUND |
			I915_SHRINK_UNBOUND |
			I915_SHRINK_PURGEABLE);
	ret = drm_gem_create_mmap_offset(&obj->base);
	if (ret != -ENOSPC)
		goto out;

	i915_gem_shrink_all(dev_priv);
	ret = drm_gem_create_mmap_offset(&obj->base);
out:
	dev_priv->mm.shrinker_no_lock_stealing = false;

	return ret;
}

static void i915_gem_object_free_mmap_offset(struct drm_i915_gem_object *obj)
{
	drm_gem_free_mmap_offset(&obj->base);
}

int
i915_gem_mmap_gtt(struct drm_file *file,
		  struct drm_device *dev,
		  uint32_t handle,
		  uint64_t *offset)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj;
	int ret;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	if (obj->base.size > dev_priv->gtt.mappable_end) {
		ret = -E2BIG;
		goto out;
	}

	if (obj->madv != I915_MADV_WILLNEED) {
		DRM_DEBUG("Attempting to mmap a purgeable buffer\n");
		ret = -EFAULT;
		goto out;
	}

	ret = i915_gem_object_create_mmap_offset(obj);
	if (ret)
		goto out;

	*offset = drm_vma_node_offset_addr(&obj->base.vma_node);

out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

/**
 * i915_gem_mmap_gtt_ioctl - prepare an object for GTT mmap'ing
 * @dev: DRM device
 * @data: GTT mapping ioctl data
 * @file: GEM object info
 *
 * Simply returns the fake offset to userspace so it can mmap it.
 * The mmap call will end up in drm_gem_mmap(), which will set things
 * up so we can get faults in the handler above.
 *
 * The fault handler will take care of binding the object into the GTT
 * (since it may have been evicted to make room for something), allocating
 * a fence register, and mapping the appropriate aperture address into
 * userspace.
 */
int
i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file)
{
	struct drm_i915_gem_mmap_gtt *args = data;

	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
}

static inline int
i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
{
	return obj->madv == I915_MADV_DONTNEED;
}

/* Immediately discard the backing storage */
static void
i915_gem_object_truncate(struct drm_i915_gem_object *obj)
{
	i915_gem_object_free_mmap_offset(obj);

	if (obj->base.filp == NULL)
		return;

	/* Our goal here is to return as much of the memory as
	 * is possible back to the system as we are called from OOM.
	 * To do this we must instruct the shmfs to drop all of its
	 * backing pages, *now*.
	 */
	shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
	obj->madv = __I915_MADV_PURGED;
}

/* Try to discard unwanted pages */
static void
i915_gem_object_invalidate(struct drm_i915_gem_object *obj)
{
	struct address_space *mapping;

	switch (obj->madv) {
	case I915_MADV_DONTNEED:
		i915_gem_object_truncate(obj);
	case __I915_MADV_PURGED:
		return;
	}

	if (obj->base.filp == NULL)
		return;

	mapping = file_inode(obj->base.filp)->i_mapping,
	invalidate_mapping_pages(mapping, 0, (loff_t)-1);
}

static void
i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
{
	struct sg_page_iter sg_iter;
	int ret;

	BUG_ON(obj->madv == __I915_MADV_PURGED);

	ret = i915_gem_object_set_to_cpu_domain(obj, true);
	if (ret) {
		/* In the event of a disaster, abandon all caches and
		 * hope for the best.
		 */
		WARN_ON(ret != -EIO);
		i915_gem_clflush_object(obj, true);
		obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
	}

	if (i915_gem_object_needs_bit17_swizzle(obj))
		i915_gem_object_save_bit_17_swizzle(obj);

	if (obj->madv == I915_MADV_DONTNEED)
		obj->dirty = 0;

	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
		struct page *page = sg_page_iter_page(&sg_iter);

		if (obj->dirty)
			set_page_dirty(page);

		if (obj->madv == I915_MADV_WILLNEED)
			mark_page_accessed(page);

		page_cache_release(page);
	}
	obj->dirty = 0;

	sg_free_table(obj->pages);
	kfree(obj->pages);
}

int
i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
{
	const struct drm_i915_gem_object_ops *ops = obj->ops;

	if (obj->pages == NULL)
		return 0;

	if (obj->pages_pin_count)
		return -EBUSY;

	BUG_ON(i915_gem_obj_bound_any(obj));

	/* ->put_pages might need to allocate memory for the bit17 swizzle
	 * array, hence protect them from being reaped by removing them from gtt
	 * lists early. */
	list_del(&obj->global_list);

	ops->put_pages(obj);
	obj->pages = NULL;

	i915_gem_object_invalidate(obj);

	return 0;
}

unsigned long
i915_gem_shrink(struct drm_i915_private *dev_priv,
		long target, unsigned flags)
{
	const bool purgeable_only = flags & I915_SHRINK_PURGEABLE;
	unsigned long count = 0;

	/*
	 * As we may completely rewrite the (un)bound list whilst unbinding
	 * (due to retiring requests) we have to strictly process only
	 * one element of the list at the time, and recheck the list
	 * on every iteration.
	 *
	 * In particular, we must hold a reference whilst removing the
	 * object as we may end up waiting for and/or retiring the objects.
	 * This might release the final reference (held by the active list)
	 * and result in the object being freed from under us. This is
	 * similar to the precautions the eviction code must take whilst
	 * removing objects.
	 *
	 * Also note that although these lists do not hold a reference to
	 * the object we can safely grab one here: The final object
	 * unreferencing and the bound_list are both protected by the
	 * dev->struct_mutex and so we won't ever be able to observe an
	 * object on the bound_list with a reference count equals 0.
	 */
	if (flags & I915_SHRINK_UNBOUND) {
		struct list_head still_in_list;

		INIT_LIST_HEAD(&still_in_list);
		while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
			struct drm_i915_gem_object *obj;

			obj = list_first_entry(&dev_priv->mm.unbound_list,
					       typeof(*obj), global_list);
			list_move_tail(&obj->global_list, &still_in_list);

			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
				continue;

			drm_gem_object_reference(&obj->base);

			if (i915_gem_object_put_pages(obj) == 0)
				count += obj->base.size >> PAGE_SHIFT;

			drm_gem_object_unreference(&obj->base);
		}
		list_splice(&still_in_list, &dev_priv->mm.unbound_list);
	}

	if (flags & I915_SHRINK_BOUND) {
		struct list_head still_in_list;

		INIT_LIST_HEAD(&still_in_list);
		while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
			struct drm_i915_gem_object *obj;
			struct i915_vma *vma, *v;

			obj = list_first_entry(&dev_priv->mm.bound_list,
					       typeof(*obj), global_list);
			list_move_tail(&obj->global_list, &still_in_list);

			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
				continue;

			drm_gem_object_reference(&obj->base);

			list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
				if (i915_vma_unbind(vma))
					break;

			if (i915_gem_object_put_pages(obj) == 0)
				count += obj->base.size >> PAGE_SHIFT;

			drm_gem_object_unreference(&obj->base);
		}
		list_splice(&still_in_list, &dev_priv->mm.bound_list);
	}

	return count;
}

static unsigned long
i915_gem_shrink_all(struct drm_i915_private *dev_priv)
{
	i915_gem_evict_everything(dev_priv->dev);
	return i915_gem_shrink(dev_priv, LONG_MAX,
			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
}

static int
i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	int page_count, i;
	struct address_space *mapping;
	struct sg_table *st;
	struct scatterlist *sg;
	struct sg_page_iter sg_iter;
	struct page *page;
	unsigned long last_pfn = 0;	/* suppress gcc warning */
	gfp_t gfp;

	/* Assert that the object is not currently in any GPU domain. As it
	 * wasn't in the GTT, there shouldn't be any way it could have been in
	 * a GPU cache
	 */
	BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
	BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);

	st = kmalloc(sizeof(*st), GFP_KERNEL);
	if (st == NULL)
		return -ENOMEM;

	page_count = obj->base.size / PAGE_SIZE;
	if (sg_alloc_table(st, page_count, GFP_KERNEL)) {
		kfree(st);
		return -ENOMEM;
	}

	/* Get the list of pages out of our struct file.  They'll be pinned
	 * at this point until we release them.
	 *
	 * Fail silently without starting the shrinker
	 */
	mapping = file_inode(obj->base.filp)->i_mapping;
	gfp = mapping_gfp_mask(mapping);
	gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
	gfp &= ~(__GFP_IO | __GFP_WAIT);
	sg = st->sgl;
	st->nents = 0;
	for (i = 0; i < page_count; i++) {
		page = shmem_read_mapping_page_gfp(mapping, i, gfp);
		if (IS_ERR(page)) {
			i915_gem_shrink(dev_priv,
					page_count,
					I915_SHRINK_BOUND |
					I915_SHRINK_UNBOUND |
					I915_SHRINK_PURGEABLE);
			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
		}
		if (IS_ERR(page)) {
			/* We've tried hard to allocate the memory by reaping
			 * our own buffer, now let the real VM do its job and
			 * go down in flames if truly OOM.
			 */
			i915_gem_shrink_all(dev_priv);
			page = shmem_read_mapping_page(mapping, i);
			if (IS_ERR(page))
				goto err_pages;
		}
#ifdef CONFIG_SWIOTLB
		if (swiotlb_nr_tbl()) {
			st->nents++;
			sg_set_page(sg, page, PAGE_SIZE, 0);
			sg = sg_next(sg);
			continue;
		}
#endif
		if (!i || page_to_pfn(page) != last_pfn + 1) {
			if (i)
				sg = sg_next(sg);
			st->nents++;
			sg_set_page(sg, page, PAGE_SIZE, 0);
		} else {
			sg->length += PAGE_SIZE;
		}
		last_pfn = page_to_pfn(page);

		/* Check that the i965g/gm workaround works. */
		WARN_ON((gfp & __GFP_DMA32) && (last_pfn >= 0x00100000UL));
	}
#ifdef CONFIG_SWIOTLB
	if (!swiotlb_nr_tbl())
#endif
		sg_mark_end(sg);
	obj->pages = st;

	if (i915_gem_object_needs_bit17_swizzle(obj))
		i915_gem_object_do_bit_17_swizzle(obj);

	return 0;

err_pages:
	sg_mark_end(sg);
	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0)
		page_cache_release(sg_page_iter_page(&sg_iter));
	sg_free_table(st);
	kfree(st);

	/* shmemfs first checks if there is enough memory to allocate the page
	 * and reports ENOSPC should there be insufficient, along with the usual
	 * ENOMEM for a genuine allocation failure.
	 *
	 * We use ENOSPC in our driver to mean that we have run out of aperture
	 * space and so want to translate the error from shmemfs back to our
	 * usual understanding of ENOMEM.
	 */
	if (PTR_ERR(page) == -ENOSPC)
		return -ENOMEM;
	else
		return PTR_ERR(page);
}

/* Ensure that the associated pages are gathered from the backing storage
 * and pinned into our object. i915_gem_object_get_pages() may be called
 * multiple times before they are released by a single call to
 * i915_gem_object_put_pages() - once the pages are no longer referenced
 * either as a result of memory pressure (reaping pages under the shrinker)
 * or as the object is itself released.
 */
int
i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	const struct drm_i915_gem_object_ops *ops = obj->ops;
	int ret;

	if (obj->pages)
		return 0;

	if (obj->madv != I915_MADV_WILLNEED) {
		DRM_DEBUG("Attempting to obtain a purgeable object\n");
		return -EFAULT;
	}

	BUG_ON(obj->pages_pin_count);

	ret = ops->get_pages(obj);
	if (ret)
		return ret;

	list_add_tail(&obj->global_list, &dev_priv->mm.unbound_list);
	return 0;
}

static void
i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
			       struct intel_engine_cs *ring)
{
	u32 seqno = intel_ring_get_seqno(ring);

	BUG_ON(ring == NULL);
	if (obj->ring != ring && obj->last_write_seqno) {
		/* Keep the seqno relative to the current ring */
		obj->last_write_seqno = seqno;
	}
	obj->ring = ring;

	/* Add a reference if we're newly entering the active list. */
	if (!obj->active) {
		drm_gem_object_reference(&obj->base);
		obj->active = 1;
	}

	list_move_tail(&obj->ring_list, &ring->active_list);

	obj->last_read_seqno = seqno;
}

void i915_vma_move_to_active(struct i915_vma *vma,
			     struct intel_engine_cs *ring)
{
	list_move_tail(&vma->mm_list, &vma->vm->active_list);
	return i915_gem_object_move_to_active(vma->obj, ring);
}

static void
i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	struct i915_address_space *vm;
	struct i915_vma *vma;

	BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS);
	BUG_ON(!obj->active);

	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
		vma = i915_gem_obj_to_vma(obj, vm);
		if (vma && !list_empty(&vma->mm_list))
			list_move_tail(&vma->mm_list, &vm->inactive_list);
	}

	intel_fb_obj_flush(obj, true);

	list_del_init(&obj->ring_list);
	obj->ring = NULL;

	obj->last_read_seqno = 0;
	obj->last_write_seqno = 0;
	obj->base.write_domain = 0;

	obj->last_fenced_seqno = 0;

	obj->active = 0;
	drm_gem_object_unreference(&obj->base);

	WARN_ON(i915_verify_lists(dev));
}

static void
i915_gem_object_retire(struct drm_i915_gem_object *obj)
{
	struct intel_engine_cs *ring = obj->ring;

	if (ring == NULL)
		return;

	if (i915_seqno_passed(ring->get_seqno(ring, true),
			      obj->last_read_seqno))
		i915_gem_object_move_to_inactive(obj);
}

static int
i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int ret, i, j;

	/* Carefully retire all requests without writing to the rings */
	for_each_ring(ring, dev_priv, i) {
		ret = intel_ring_idle(ring);
		if (ret)
			return ret;
	}
	i915_gem_retire_requests(dev);

	/* Finally reset hw state */
	for_each_ring(ring, dev_priv, i) {
		intel_ring_init_seqno(ring, seqno);

		for (j = 0; j < ARRAY_SIZE(ring->semaphore.sync_seqno); j++)
			ring->semaphore.sync_seqno[j] = 0;
	}

	return 0;
}

int i915_gem_set_seqno(struct drm_device *dev, u32 seqno)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	if (seqno == 0)
		return -EINVAL;

	/* HWS page needs to be set less than what we
	 * will inject to ring
	 */
	ret = i915_gem_init_seqno(dev, seqno - 1);
	if (ret)
		return ret;

	/* Carefully set the last_seqno value so that wrap
	 * detection still works
	 */
	dev_priv->next_seqno = seqno;
	dev_priv->last_seqno = seqno - 1;
	if (dev_priv->last_seqno == 0)
		dev_priv->last_seqno--;

	return 0;
}

int
i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
{
	struct drm_i915_private *dev_priv = dev->dev_private;

	/* reserve 0 for non-seqno */
	if (dev_priv->next_seqno == 0) {
		int ret = i915_gem_init_seqno(dev, 0);
		if (ret)
			return ret;

		dev_priv->next_seqno = 1;
	}

	*seqno = dev_priv->last_seqno = dev_priv->next_seqno++;
	return 0;
}

int __i915_add_request(struct intel_engine_cs *ring,
		       struct drm_file *file,
		       struct drm_i915_gem_object *obj,
		       u32 *out_seqno)
{
	struct drm_i915_private *dev_priv = ring->dev->dev_private;
	struct drm_i915_gem_request *request;
	struct intel_ringbuffer *ringbuf;
	u32 request_ring_position, request_start;
	int ret;

	request = ring->preallocated_lazy_request;
	if (WARN_ON(request == NULL))
		return -ENOMEM;

	if (i915.enable_execlists) {
		struct intel_context *ctx = request->ctx;
		ringbuf = ctx->engine[ring->id].ringbuf;
	} else
		ringbuf = ring->buffer;

	request_start = intel_ring_get_tail(ringbuf);
	/*
	 * Emit any outstanding flushes - execbuf can fail to emit the flush
	 * after having emitted the batchbuffer command. Hence we need to fix
	 * things up similar to emitting the lazy request. The difference here
	 * is that the flush _must_ happen before the next request, no matter
	 * what.
	 */
	if (i915.enable_execlists) {
		ret = logical_ring_flush_all_caches(ringbuf);
		if (ret)
			return ret;
	} else {
		ret = intel_ring_flush_all_caches(ring);
		if (ret)
			return ret;
	}

	/* Record the position of the start of the request so that
	 * should we detect the updated seqno part-way through the
	 * GPU processing the request, we never over-estimate the
	 * position of the head.
	 */
	request_ring_position = intel_ring_get_tail(ringbuf);

	if (i915.enable_execlists) {
		ret = ring->emit_request(ringbuf);
		if (ret)
			return ret;
	} else {
		ret = ring->add_request(ring);
		if (ret)
			return ret;
	}

	request->seqno = intel_ring_get_seqno(ring);
	request->ring = ring;
	request->head = request_start;
	request->tail = request_ring_position;

	/* Whilst this request exists, batch_obj will be on the
	 * active_list, and so will hold the active reference. Only when this
	 * request is retired will the the batch_obj be moved onto the
	 * inactive_list and lose its active reference. Hence we do not need
	 * to explicitly hold another reference here.
	 */
	request->batch_obj = obj;

	if (!i915.enable_execlists) {
		/* Hold a reference to the current context so that we can inspect
		 * it later in case a hangcheck error event fires.
		 */
		request->ctx = ring->last_context;
		if (request->ctx)
			i915_gem_context_reference(request->ctx);
	}

	request->emitted_jiffies = jiffies;
	list_add_tail(&request->list, &ring->request_list);
	request->file_priv = NULL;

	if (file) {
		struct drm_i915_file_private *file_priv = file->driver_priv;

		spin_lock(&file_priv->mm.lock);
		request->file_priv = file_priv;
		list_add_tail(&request->client_list,
			      &file_priv->mm.request_list);
		spin_unlock(&file_priv->mm.lock);
	}

	trace_i915_gem_request_add(ring, request->seqno);
	ring->outstanding_lazy_seqno = 0;
	ring->preallocated_lazy_request = NULL;

	if (!dev_priv->ums.mm_suspended) {
		i915_queue_hangcheck(ring->dev);

		cancel_delayed_work_sync(&dev_priv->mm.idle_work);
		queue_delayed_work(dev_priv->wq,
				   &dev_priv->mm.retire_work,
				   round_jiffies_up_relative(HZ));
		intel_mark_busy(dev_priv->dev);
	}

	if (out_seqno)
		*out_seqno = request->seqno;
	return 0;
}

static inline void
i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
{
	struct drm_i915_file_private *file_priv = request->file_priv;

	if (!file_priv)
		return;

	spin_lock(&file_priv->mm.lock);
	list_del(&request->client_list);
	request->file_priv = NULL;
	spin_unlock(&file_priv->mm.lock);
}

static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
				   const struct intel_context *ctx)
{
	unsigned long elapsed;

	elapsed = get_seconds() - ctx->hang_stats.guilty_ts;

	if (ctx->hang_stats.banned)
		return true;

	if (elapsed <= DRM_I915_CTX_BAN_PERIOD) {
		if (!i915_gem_context_is_default(ctx)) {
			DRM_DEBUG("context hanging too fast, banning!\n");
			return true;
		} else if (i915_stop_ring_allow_ban(dev_priv)) {
			if (i915_stop_ring_allow_warn(dev_priv))
				DRM_ERROR("gpu hanging too fast, banning!\n");
			return true;
		}
	}

	return false;
}

static void i915_set_reset_status(struct drm_i915_private *dev_priv,
				  struct intel_context *ctx,
				  const bool guilty)
{
	struct i915_ctx_hang_stats *hs;

	if (WARN_ON(!ctx))
		return;

	hs = &ctx->hang_stats;

	if (guilty) {
		hs->banned = i915_context_is_banned(dev_priv, ctx);
		hs->batch_active++;
		hs->guilty_ts = get_seconds();
	} else {
		hs->batch_pending++;
	}
}

static void i915_gem_free_request(struct drm_i915_gem_request *request)
{
	list_del(&request->list);
	i915_gem_request_remove_from_client(request);

	if (request->ctx)
		i915_gem_context_unreference(request->ctx);

	kfree(request);
}

struct drm_i915_gem_request *
i915_gem_find_active_request(struct intel_engine_cs *ring)
{
	struct drm_i915_gem_request *request;
	u32 completed_seqno;

	completed_seqno = ring->get_seqno(ring, false);

	list_for_each_entry(request, &ring->request_list, list) {
		if (i915_seqno_passed(completed_seqno, request->seqno))
			continue;

		return request;
	}

	return NULL;
}

static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
				       struct intel_engine_cs *ring)
{
	struct drm_i915_gem_request *request;
	bool ring_hung;

	request = i915_gem_find_active_request(ring);

	if (request == NULL)
		return;

	ring_hung = ring->hangcheck.score >= HANGCHECK_SCORE_RING_HUNG;

	i915_set_reset_status(dev_priv, request->ctx, ring_hung);

	list_for_each_entry_continue(request, &ring->request_list, list)
		i915_set_reset_status(dev_priv, request->ctx, false);
}

static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
					struct intel_engine_cs *ring)
{
	while (!list_empty(&ring->active_list)) {
		struct drm_i915_gem_object *obj;

		obj = list_first_entry(&ring->active_list,
				       struct drm_i915_gem_object,
				       ring_list);

		i915_gem_object_move_to_inactive(obj);
	}

	/*
	 * We must free the requests after all the corresponding objects have
	 * been moved off active lists. Which is the same order as the normal
	 * retire_requests function does. This is important if object hold
	 * implicit references on things like e.g. ppgtt address spaces through
	 * the request.
	 */
	while (!list_empty(&ring->request_list)) {
		struct drm_i915_gem_request *request;

		request = list_first_entry(&ring->request_list,
					   struct drm_i915_gem_request,
					   list);

		i915_gem_free_request(request);
	}

	while (!list_empty(&ring->execlist_queue)) {
		struct intel_ctx_submit_request *submit_req;

		submit_req = list_first_entry(&ring->execlist_queue,
				struct intel_ctx_submit_request,
				execlist_link);
		list_del(&submit_req->execlist_link);
		intel_runtime_pm_put(dev_priv);
		i915_gem_context_unreference(submit_req->ctx);
		kfree(submit_req);
	}

	/* These may not have been flush before the reset, do so now */
	kfree(ring->preallocated_lazy_request);
	ring->preallocated_lazy_request = NULL;
	ring->outstanding_lazy_seqno = 0;
}

void i915_gem_restore_fences(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int i;

	for (i = 0; i < dev_priv->num_fence_regs; i++) {
		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];

		/*
		 * Commit delayed tiling changes if we have an object still
		 * attached to the fence, otherwise just clear the fence.
		 */
		if (reg->obj) {
			i915_gem_object_update_fence(reg->obj, reg,
						     reg->obj->tiling_mode);
		} else {
			i915_gem_write_fence(dev, i, NULL);
		}
	}
}

void i915_gem_reset(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int i;

	/*
	 * Before we free the objects from the requests, we need to inspect
	 * them for finding the guilty party. As the requests only borrow
	 * their reference to the objects, the inspection must be done first.
	 */
	for_each_ring(ring, dev_priv, i)
		i915_gem_reset_ring_status(dev_priv, ring);

	for_each_ring(ring, dev_priv, i)
		i915_gem_reset_ring_cleanup(dev_priv, ring);

	i915_gem_context_reset(dev);

	i915_gem_restore_fences(dev);
}

/**
 * This function clears the request list as sequence numbers are passed.
 */
void
i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
{
	uint32_t seqno;

	if (list_empty(&ring->request_list))
		return;

	WARN_ON(i915_verify_lists(ring->dev));

	seqno = ring->get_seqno(ring, true);

	/* Move any buffers on the active list that are no longer referenced
	 * by the ringbuffer to the flushing/inactive lists as appropriate,
	 * before we free the context associated with the requests.
	 */
	while (!list_empty(&ring->active_list)) {
		struct drm_i915_gem_object *obj;

		obj = list_first_entry(&ring->active_list,
				      struct drm_i915_gem_object,
				      ring_list);

		if (!i915_seqno_passed(seqno, obj->last_read_seqno))
			break;

		i915_gem_object_move_to_inactive(obj);
	}


	while (!list_empty(&ring->request_list)) {
		struct drm_i915_gem_request *request;
		struct intel_ringbuffer *ringbuf;

		request = list_first_entry(&ring->request_list,
					   struct drm_i915_gem_request,
					   list);

		if (!i915_seqno_passed(seqno, request->seqno))
			break;

		trace_i915_gem_request_retire(ring, request->seqno);

		/* This is one of the few common intersection points
		 * between legacy ringbuffer submission and execlists:
		 * we need to tell them apart in order to find the correct
		 * ringbuffer to which the request belongs to.
		 */
		if (i915.enable_execlists) {
			struct intel_context *ctx = request->ctx;
			ringbuf = ctx->engine[ring->id].ringbuf;
		} else
			ringbuf = ring->buffer;

		/* We know the GPU must have read the request to have
		 * sent us the seqno + interrupt, so use the position
		 * of tail of the request to update the last known position
		 * of the GPU head.
		 */
		ringbuf->last_retired_head = request->tail;

		i915_gem_free_request(request);
	}

	if (unlikely(ring->trace_irq_seqno &&
		     i915_seqno_passed(seqno, ring->trace_irq_seqno))) {
		ring->irq_put(ring);
		ring->trace_irq_seqno = 0;
	}

	WARN_ON(i915_verify_lists(ring->dev));
}

bool
i915_gem_retire_requests(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	bool idle = true;
	int i;

	for_each_ring(ring, dev_priv, i) {
		i915_gem_retire_requests_ring(ring);
		idle &= list_empty(&ring->request_list);
	}

	if (idle)
		mod_delayed_work(dev_priv->wq,
				   &dev_priv->mm.idle_work,
				   msecs_to_jiffies(100));

	return idle;
}

static void
i915_gem_retire_work_handler(struct work_struct *work)
{
	struct drm_i915_private *dev_priv =
		container_of(work, typeof(*dev_priv), mm.retire_work.work);
	struct drm_device *dev = dev_priv->dev;
	bool idle;

	/* Come back later if the device is busy... */
	idle = false;
	if (mutex_trylock(&dev->struct_mutex)) {
		idle = i915_gem_retire_requests(dev);
		mutex_unlock(&dev->struct_mutex);
	}
	if (!idle)
		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work,
				   round_jiffies_up_relative(HZ));
}

static void
i915_gem_idle_work_handler(struct work_struct *work)
{
	struct drm_i915_private *dev_priv =
		container_of(work, typeof(*dev_priv), mm.idle_work.work);

	intel_mark_idle(dev_priv->dev);
}

/**
 * Ensures that an object will eventually get non-busy by flushing any required
 * write domains, emitting any outstanding lazy request and retiring and
 * completed requests.
 */
static int
i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
{
	int ret;

	if (obj->active) {
		ret = i915_gem_check_olr(obj->ring, obj->last_read_seqno);
		if (ret)
			return ret;

		i915_gem_retire_requests_ring(obj->ring);
	}

	return 0;
}

/**
 * i915_gem_wait_ioctl - implements DRM_IOCTL_I915_GEM_WAIT
 * @DRM_IOCTL_ARGS: standard ioctl arguments
 *
 * Returns 0 if successful, else an error is returned with the remaining time in
 * the timeout parameter.
 *  -ETIME: object is still busy after timeout
 *  -ERESTARTSYS: signal interrupted the wait
 *  -ENONENT: object doesn't exist
 * Also possible, but rare:
 *  -EAGAIN: GPU wedged
 *  -ENOMEM: damn
 *  -ENODEV: Internal IRQ fail
 *  -E?: The add request failed
 *
 * The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
 * non-zero timeout parameter the wait ioctl will wait for the given number of
 * nanoseconds on an object becoming unbusy. Since the wait itself does so
 * without holding struct_mutex the object may become re-busied before this
 * function completes. A similar but shorter * race condition exists in the busy
 * ioctl
 */
int
i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_wait *args = data;
	struct drm_i915_gem_object *obj;
	struct intel_engine_cs *ring = NULL;
	unsigned reset_counter;
	u32 seqno = 0;
	int ret = 0;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->bo_handle));
	if (&obj->base == NULL) {
		mutex_unlock(&dev->struct_mutex);
		return -ENOENT;
	}

	/* Need to make sure the object gets inactive eventually. */
	ret = i915_gem_object_flush_active(obj);
	if (ret)
		goto out;

	if (obj->active) {
		seqno = obj->last_read_seqno;
		ring = obj->ring;
	}

	if (seqno == 0)
		 goto out;

	/* Do this after OLR check to make sure we make forward progress polling
	 * on this IOCTL with a timeout <=0 (like busy ioctl)
	 */
	if (args->timeout_ns <= 0) {
		ret = -ETIME;
		goto out;
	}

	drm_gem_object_unreference(&obj->base);
	reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
	mutex_unlock(&dev->struct_mutex);

	return __wait_seqno(ring, seqno, reset_counter, true, &args->timeout_ns,
			    file->driver_priv);

out:
	drm_gem_object_unreference(&obj->base);
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

/**
 * i915_gem_object_sync - sync an object to a ring.
 *
 * @obj: object which may be in use on another ring.
 * @to: ring we wish to use the object on. May be NULL.
 *
 * This code is meant to abstract object synchronization with the GPU.
 * Calling with NULL implies synchronizing the object with the CPU
 * rather than a particular GPU ring.
 *
 * Returns 0 if successful, else propagates up the lower layer error.
 */
int
i915_gem_object_sync(struct drm_i915_gem_object *obj,
		     struct intel_engine_cs *to)
{
	struct intel_engine_cs *from = obj->ring;
	u32 seqno;
	int ret, idx;

	if (from == NULL || to == from)
		return 0;

	if (to == NULL || !i915_semaphore_is_enabled(obj->base.dev))
		return i915_gem_object_wait_rendering(obj, false);

	idx = intel_ring_sync_index(from, to);

	seqno = obj->last_read_seqno;
	/* Optimization: Avoid semaphore sync when we are sure we already
	 * waited for an object with higher seqno */
	if (seqno <= from->semaphore.sync_seqno[idx])
		return 0;

	ret = i915_gem_check_olr(obj->ring, seqno);
	if (ret)
		return ret;

	trace_i915_gem_ring_sync_to(from, to, seqno);
	ret = to->semaphore.sync_to(to, from, seqno);
	if (!ret)
		/* We use last_read_seqno because sync_to()
		 * might have just caused seqno wrap under
		 * the radar.
		 */
		from->semaphore.sync_seqno[idx] = obj->last_read_seqno;

	return ret;
}

static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
{
	u32 old_write_domain, old_read_domains;

	/* Force a pagefault for domain tracking on next user access */
	i915_gem_release_mmap(obj);

	if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0)
		return;

	/* Wait for any direct GTT access to complete */
	mb();

	old_read_domains = obj->base.read_domains;
	old_write_domain = obj->base.write_domain;

	obj->base.read_domains &= ~I915_GEM_DOMAIN_GTT;
	obj->base.write_domain &= ~I915_GEM_DOMAIN_GTT;

	trace_i915_gem_object_change_domain(obj,
					    old_read_domains,
					    old_write_domain);
}

int i915_vma_unbind(struct i915_vma *vma)
{
	struct drm_i915_gem_object *obj = vma->obj;
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	int ret;

	if (list_empty(&vma->vma_link))
		return 0;

	if (!drm_mm_node_allocated(&vma->node)) {
		i915_gem_vma_destroy(vma);
		return 0;
	}

	if (vma->pin_count)
		return -EBUSY;

	BUG_ON(obj->pages == NULL);

	ret = i915_gem_object_finish_gpu(obj);
	if (ret)
		return ret;
	/* Continue on if we fail due to EIO, the GPU is hung so we
	 * should be safe and we need to cleanup or else we might
	 * cause memory corruption through use-after-free.
	 */

	/* Throw away the active reference before moving to the unbound list */
	i915_gem_object_retire(obj);

	if (i915_is_ggtt(vma->vm)) {
		i915_gem_object_finish_gtt(obj);

		/* release the fence reg _after_ flushing */
		ret = i915_gem_object_put_fence(obj);
		if (ret)
			return ret;
	}

	trace_i915_vma_unbind(vma);

	vma->unbind_vma(vma);

	list_del_init(&vma->mm_list);
	if (i915_is_ggtt(vma->vm))
		obj->map_and_fenceable = false;

	drm_mm_remove_node(&vma->node);
	i915_gem_vma_destroy(vma);

	/* Since the unbound list is global, only move to that list if
	 * no more VMAs exist. */
	if (list_empty(&obj->vma_list)) {
		i915_gem_gtt_finish_object(obj);
		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
	}

	/* And finally now the object is completely decoupled from this vma,
	 * we can drop its hold on the backing storage and allow it to be
	 * reaped by the shrinker.
	 */
	i915_gem_object_unpin_pages(obj);

	return 0;
}

int i915_gpu_idle(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int ret, i;

	/* Flush everything onto the inactive list. */
	for_each_ring(ring, dev_priv, i) {
		if (!i915.enable_execlists) {
			ret = i915_switch_context(ring, ring->default_context);
			if (ret)
				return ret;
		}

		ret = intel_ring_idle(ring);
		if (ret)
			return ret;
	}

	return 0;
}

static void i965_write_fence_reg(struct drm_device *dev, int reg,
				 struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int fence_reg;
	int fence_pitch_shift;

	if (INTEL_INFO(dev)->gen >= 6) {
		fence_reg = FENCE_REG_SANDYBRIDGE_0;
		fence_pitch_shift = SANDYBRIDGE_FENCE_PITCH_SHIFT;
	} else {
		fence_reg = FENCE_REG_965_0;
		fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
	}

	fence_reg += reg * 8;

	/* To w/a incoherency with non-atomic 64-bit register updates,
	 * we split the 64-bit update into two 32-bit writes. In order
	 * for a partial fence not to be evaluated between writes, we
	 * precede the update with write to turn off the fence register,
	 * and only enable the fence as the last step.
	 *
	 * For extra levels of paranoia, we make sure each step lands
	 * before applying the next step.
	 */
	I915_WRITE(fence_reg, 0);
	POSTING_READ(fence_reg);

	if (obj) {
		u32 size = i915_gem_obj_ggtt_size(obj);
		uint64_t val;

		/* Adjust fence size to match tiled area */
		if (obj->tiling_mode != I915_TILING_NONE) {
			uint32_t row_size = obj->stride *
				(obj->tiling_mode == I915_TILING_Y ? 32 : 8);
			size = (size / row_size) * row_size;
		}

		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
				 0xfffff000) << 32;
		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
		val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift;
		if (obj->tiling_mode == I915_TILING_Y)
			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
		val |= I965_FENCE_REG_VALID;

		I915_WRITE(fence_reg + 4, val >> 32);
		POSTING_READ(fence_reg + 4);

		I915_WRITE(fence_reg + 0, val);
		POSTING_READ(fence_reg);
	} else {
		I915_WRITE(fence_reg + 4, 0);
		POSTING_READ(fence_reg + 4);
	}
}

static void i915_write_fence_reg(struct drm_device *dev, int reg,
				 struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	u32 val;

	if (obj) {
		u32 size = i915_gem_obj_ggtt_size(obj);
		int pitch_val;
		int tile_width;

		WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) ||
		     (size & -size) != size ||
		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
		     "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
		     i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size);

		if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
			tile_width = 128;
		else
			tile_width = 512;

		/* Note: pitch better be a power of two tile widths */
		pitch_val = obj->stride / tile_width;
		pitch_val = ffs(pitch_val) - 1;

		val = i915_gem_obj_ggtt_offset(obj);
		if (obj->tiling_mode == I915_TILING_Y)
			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
		val |= I915_FENCE_SIZE_BITS(size);
		val |= pitch_val << I830_FENCE_PITCH_SHIFT;
		val |= I830_FENCE_REG_VALID;
	} else
		val = 0;

	if (reg < 8)
		reg = FENCE_REG_830_0 + reg * 4;
	else
		reg = FENCE_REG_945_8 + (reg - 8) * 4;

	I915_WRITE(reg, val);
	POSTING_READ(reg);
}

static void i830_write_fence_reg(struct drm_device *dev, int reg,
				struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	uint32_t val;

	if (obj) {
		u32 size = i915_gem_obj_ggtt_size(obj);
		uint32_t pitch_val;

		WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) ||
		     (size & -size) != size ||
		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
		     "object 0x%08lx not 512K or pot-size 0x%08x aligned\n",
		     i915_gem_obj_ggtt_offset(obj), size);

		pitch_val = obj->stride / 128;
		pitch_val = ffs(pitch_val) - 1;

		val = i915_gem_obj_ggtt_offset(obj);
		if (obj->tiling_mode == I915_TILING_Y)
			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
		val |= I830_FENCE_SIZE_BITS(size);
		val |= pitch_val << I830_FENCE_PITCH_SHIFT;
		val |= I830_FENCE_REG_VALID;
	} else
		val = 0;

	I915_WRITE(FENCE_REG_830_0 + reg * 4, val);
	POSTING_READ(FENCE_REG_830_0 + reg * 4);
}

inline static bool i915_gem_object_needs_mb(struct drm_i915_gem_object *obj)
{
	return obj && obj->base.read_domains & I915_GEM_DOMAIN_GTT;
}

static void i915_gem_write_fence(struct drm_device *dev, int reg,
				 struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = dev->dev_private;

	/* Ensure that all CPU reads are completed before installing a fence
	 * and all writes before removing the fence.
	 */
	if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj))
		mb();

	WARN(obj && (!obj->stride || !obj->tiling_mode),
	     "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
	     obj->stride, obj->tiling_mode);

	switch (INTEL_INFO(dev)->gen) {
	case 8:
	case 7:
	case 6:
	case 5:
	case 4: i965_write_fence_reg(dev, reg, obj); break;
	case 3: i915_write_fence_reg(dev, reg, obj); break;
	case 2: i830_write_fence_reg(dev, reg, obj); break;
	default: BUG();
	}

	/* And similarly be paranoid that no direct access to this region
	 * is reordered to before the fence is installed.
	 */
	if (i915_gem_object_needs_mb(obj))
		mb();
}

static inline int fence_number(struct drm_i915_private *dev_priv,
			       struct drm_i915_fence_reg *fence)
{
	return fence - dev_priv->fence_regs;
}

static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
					 struct drm_i915_fence_reg *fence,
					 bool enable)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	int reg = fence_number(dev_priv, fence);

	i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);

	if (enable) {
		obj->fence_reg = reg;
		fence->obj = obj;
		list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
	} else {
		obj->fence_reg = I915_FENCE_REG_NONE;
		fence->obj = NULL;
		list_del_init(&fence->lru_list);
	}
	obj->fence_dirty = false;
}

static int
i915_gem_object_wait_fence(struct drm_i915_gem_object *obj)
{
	if (obj->last_fenced_seqno) {
		int ret = i915_wait_seqno(obj->ring, obj->last_fenced_seqno);
		if (ret)
			return ret;

		obj->last_fenced_seqno = 0;
	}

	return 0;
}

int
i915_gem_object_put_fence(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	struct drm_i915_fence_reg *fence;
	int ret;

	ret = i915_gem_object_wait_fence(obj);
	if (ret)
		return ret;

	if (obj->fence_reg == I915_FENCE_REG_NONE)
		return 0;

	fence = &dev_priv->fence_regs[obj->fence_reg];

	if (WARN_ON(fence->pin_count))
		return -EBUSY;

	i915_gem_object_fence_lost(obj);
	i915_gem_object_update_fence(obj, fence, false);

	return 0;
}

static struct drm_i915_fence_reg *
i915_find_fence_reg(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_fence_reg *reg, *avail;
	int i;

	/* First try to find a free reg */
	avail = NULL;
	for (i = dev_priv->fence_reg_start; i < dev_priv->num_fence_regs; i++) {
		reg = &dev_priv->fence_regs[i];
		if (!reg->obj)
			return reg;

		if (!reg->pin_count)
			avail = reg;
	}

	if (avail == NULL)
		goto deadlock;

	/* None available, try to steal one or wait for a user to finish */
	list_for_each_entry(reg, &dev_priv->mm.fence_list, lru_list) {
		if (reg->pin_count)
			continue;

		return reg;
	}

deadlock:
	/* Wait for completion of pending flips which consume fences */
	if (intel_has_pending_fb_unpin(dev))
		return ERR_PTR(-EAGAIN);

	return ERR_PTR(-EDEADLK);
}

/**
 * i915_gem_object_get_fence - set up fencing for an object
 * @obj: object to map through a fence reg
 *
 * When mapping objects through the GTT, userspace wants to be able to write
 * to them without having to worry about swizzling if the object is tiled.
 * This function walks the fence regs looking for a free one for @obj,
 * stealing one if it can't find any.
 *
 * It then sets up the reg based on the object's properties: address, pitch
 * and tiling format.
 *
 * For an untiled surface, this removes any existing fence.
 */
int
i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	bool enable = obj->tiling_mode != I915_TILING_NONE;
	struct drm_i915_fence_reg *reg;
	int ret;

	/* Have we updated the tiling parameters upon the object and so
	 * will need to serialise the write to the associated fence register?
	 */
	if (obj->fence_dirty) {
		ret = i915_gem_object_wait_fence(obj);
		if (ret)
			return ret;
	}

	/* Just update our place in the LRU if our fence is getting reused. */
	if (obj->fence_reg != I915_FENCE_REG_NONE) {
		reg = &dev_priv->fence_regs[obj->fence_reg];
		if (!obj->fence_dirty) {
			list_move_tail(&reg->lru_list,
				       &dev_priv->mm.fence_list);
			return 0;
		}
	} else if (enable) {
		if (WARN_ON(!obj->map_and_fenceable))
			return -EINVAL;

		reg = i915_find_fence_reg(dev);
		if (IS_ERR(reg))
			return PTR_ERR(reg);

		if (reg->obj) {
			struct drm_i915_gem_object *old = reg->obj;

			ret = i915_gem_object_wait_fence(old);
			if (ret)
				return ret;

			i915_gem_object_fence_lost(old);
		}
	} else
		return 0;

	i915_gem_object_update_fence(obj, reg, enable);

	return 0;
}

static bool i915_gem_valid_gtt_space(struct i915_vma *vma,
				     unsigned long cache_level)
{
	struct drm_mm_node *gtt_space = &vma->node;
	struct drm_mm_node *other;

	/*
	 * On some machines we have to be careful when putting differing types
	 * of snoopable memory together to avoid the prefetcher crossing memory
	 * domains and dying. During vm initialisation, we decide whether or not
	 * these constraints apply and set the drm_mm.color_adjust
	 * appropriately.
	 */
	if (vma->vm->mm.color_adjust == NULL)
		return true;

	if (!drm_mm_node_allocated(gtt_space))
		return true;

	if (list_empty(&gtt_space->node_list))
		return true;

	other = list_entry(gtt_space->node_list.prev, struct drm_mm_node, node_list);
	if (other->allocated && !other->hole_follows && other->color != cache_level)
		return false;

	other = list_entry(gtt_space->node_list.next, struct drm_mm_node, node_list);
	if (other->allocated && !gtt_space->hole_follows && other->color != cache_level)
		return false;

	return true;
}

static void i915_gem_verify_gtt(struct drm_device *dev)
{
#if WATCH_GTT
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj;
	int err = 0;

	list_for_each_entry(obj, &dev_priv->mm.gtt_list, global_list) {
		if (obj->gtt_space == NULL) {
			printk(KERN_ERR "object found on GTT list with no space reserved\n");
			err++;
			continue;
		}

		if (obj->cache_level != obj->gtt_space->color) {
			printk(KERN_ERR "object reserved space [%08lx, %08lx] with wrong color, cache_level=%x, color=%lx\n",
			       i915_gem_obj_ggtt_offset(obj),
			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
			       obj->cache_level,
			       obj->gtt_space->color);
			err++;
			continue;
		}

		if (!i915_gem_valid_gtt_space(dev,
					      obj->gtt_space,
					      obj->cache_level)) {
			printk(KERN_ERR "invalid GTT space found at [%08lx, %08lx] - color=%x\n",
			       i915_gem_obj_ggtt_offset(obj),
			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
			       obj->cache_level);
			err++;
			continue;
		}
	}

	WARN_ON(err);
#endif
}

/**
 * Finds free space in the GTT aperture and binds the object there.
 */
static struct i915_vma *
i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
			   struct i915_address_space *vm,
			   unsigned alignment,
			   uint64_t flags)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	u32 size, fence_size, fence_alignment, unfenced_alignment;
	unsigned long start =
		flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
	unsigned long end =
		flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
	struct i915_vma *vma;
	int ret;

	fence_size = i915_gem_get_gtt_size(dev,
					   obj->base.size,
					   obj->tiling_mode);
	fence_alignment = i915_gem_get_gtt_alignment(dev,
						     obj->base.size,
						     obj->tiling_mode, true);
	unfenced_alignment =
		i915_gem_get_gtt_alignment(dev,
					   obj->base.size,
					   obj->tiling_mode, false);

	if (alignment == 0)
		alignment = flags & PIN_MAPPABLE ? fence_alignment :
						unfenced_alignment;
	if (flags & PIN_MAPPABLE && alignment & (fence_alignment - 1)) {
		DRM_DEBUG("Invalid object alignment requested %u\n", alignment);
		return ERR_PTR(-EINVAL);
	}

	size = flags & PIN_MAPPABLE ? fence_size : obj->base.size;

	/* If the object is bigger than the entire aperture, reject it early
	 * before evicting everything in a vain attempt to find space.
	 */
	if (obj->base.size > end) {
		DRM_DEBUG("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%lu\n",
			  obj->base.size,
			  flags & PIN_MAPPABLE ? "mappable" : "total",
			  end);
		return ERR_PTR(-E2BIG);
	}

	ret = i915_gem_object_get_pages(obj);
	if (ret)
		return ERR_PTR(ret);

	i915_gem_object_pin_pages(obj);

	vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
	if (IS_ERR(vma))
		goto err_unpin;

search_free:
	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
						  size, alignment,
						  obj->cache_level,
						  start, end,
						  DRM_MM_SEARCH_DEFAULT,
						  DRM_MM_CREATE_DEFAULT);
	if (ret) {
		ret = i915_gem_evict_something(dev, vm, size, alignment,
					       obj->cache_level,
					       start, end,
					       flags);
		if (ret == 0)
			goto search_free;

		goto err_free_vma;
	}
	if (WARN_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level))) {
		ret = -EINVAL;
		goto err_remove_node;
	}

	ret = i915_gem_gtt_prepare_object(obj);
	if (ret)
		goto err_remove_node;

	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
	list_add_tail(&vma->mm_list, &vm->inactive_list);

	if (i915_is_ggtt(vm)) {
		bool mappable, fenceable;

		fenceable = (vma->node.size == fence_size &&
			     (vma->node.start & (fence_alignment - 1)) == 0);

		mappable = (vma->node.start + obj->base.size <=
			    dev_priv->gtt.mappable_end);

		obj->map_and_fenceable = mappable && fenceable;
	}

	WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);

	trace_i915_vma_bind(vma, flags);
	vma->bind_vma(vma, obj->cache_level,
		      flags & (PIN_MAPPABLE | PIN_GLOBAL) ? GLOBAL_BIND : 0);

	i915_gem_verify_gtt(dev);
	return vma;

err_remove_node:
	drm_mm_remove_node(&vma->node);
err_free_vma:
	i915_gem_vma_destroy(vma);
	vma = ERR_PTR(ret);
err_unpin:
	i915_gem_object_unpin_pages(obj);
	return vma;
}

bool
i915_gem_clflush_object(struct drm_i915_gem_object *obj,
			bool force)
{
	/* If we don't have a page list set up, then we're not pinned
	 * to GPU, and we can ignore the cache flush because it'll happen
	 * again at bind time.
	 */
	if (obj->pages == NULL)
		return false;

	/*
	 * Stolen memory is always coherent with the GPU as it is explicitly
	 * marked as wc by the system, or the system is cache-coherent.
	 */
	if (obj->stolen)
		return false;

	/* If the GPU is snooping the contents of the CPU cache,
	 * we do not need to manually clear the CPU cache lines.  However,
	 * the caches are only snooped when the render cache is
	 * flushed/invalidated.  As we always have to emit invalidations
	 * and flushes when moving into and out of the RENDER domain, correct
	 * snooping behaviour occurs naturally as the result of our domain
	 * tracking.
	 */
	if (!force && cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
		return false;

	trace_i915_gem_object_clflush(obj);
	drm_clflush_sg(obj->pages);

	return true;
}

/** Flushes the GTT write domain for the object if it's dirty. */
static void
i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
{
	uint32_t old_write_domain;

	if (obj->base.write_domain != I915_GEM_DOMAIN_GTT)
		return;

	/* No actual flushing is required for the GTT write domain.  Writes
	 * to it immediately go to main memory as far as we know, so there's
	 * no chipset flush.  It also doesn't land in render cache.
	 *
	 * However, we do have to enforce the order so that all writes through
	 * the GTT land before any writes to the device, such as updates to
	 * the GATT itself.
	 */
	wmb();

	old_write_domain = obj->base.write_domain;
	obj->base.write_domain = 0;

	intel_fb_obj_flush(obj, false);

	trace_i915_gem_object_change_domain(obj,
					    obj->base.read_domains,
					    old_write_domain);
}

/** Flushes the CPU write domain for the object if it's dirty. */
static void
i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
				       bool force)
{
	uint32_t old_write_domain;

	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU)
		return;

	if (i915_gem_clflush_object(obj, force))
		i915_gem_chipset_flush(obj->base.dev);

	old_write_domain = obj->base.write_domain;
	obj->base.write_domain = 0;

	intel_fb_obj_flush(obj, false);

	trace_i915_gem_object_change_domain(obj,
					    obj->base.read_domains,
					    old_write_domain);
}

/**
 * Moves a single object to the GTT read, and possibly write domain.
 *
 * This function returns when the move is complete, including waiting on
 * flushes to occur.
 */
int
i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
	uint32_t old_write_domain, old_read_domains;
	int ret;

	/* Not valid to be called on unbound objects. */
	if (vma == NULL)
		return -EINVAL;

	if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
		return 0;

	ret = i915_gem_object_wait_rendering(obj, !write);
	if (ret)
		return ret;

	i915_gem_object_retire(obj);
	i915_gem_object_flush_cpu_write_domain(obj, false);

	/* Serialise direct access to this object with the barriers for
	 * coherent writes from the GPU, by effectively invalidating the
	 * GTT domain upon first access.
	 */
	if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0)
		mb();

	old_write_domain = obj->base.write_domain;
	old_read_domains = obj->base.read_domains;

	/* It should now be out of any other write domains, and we can update
	 * the domain values for our changes.
	 */
	BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
	obj->base.read_domains |= I915_GEM_DOMAIN_GTT;
	if (write) {
		obj->base.read_domains = I915_GEM_DOMAIN_GTT;
		obj->base.write_domain = I915_GEM_DOMAIN_GTT;
		obj->dirty = 1;
	}

	if (write)
		intel_fb_obj_invalidate(obj, NULL);

	trace_i915_gem_object_change_domain(obj,
					    old_read_domains,
					    old_write_domain);

	/* And bump the LRU for this access */
	if (i915_gem_object_is_inactive(obj))
		list_move_tail(&vma->mm_list,
			       &dev_priv->gtt.base.inactive_list);

	return 0;
}

int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
				    enum i915_cache_level cache_level)
{
	struct drm_device *dev = obj->base.dev;
	struct i915_vma *vma, *next;
	int ret;

	if (obj->cache_level == cache_level)
		return 0;

	if (i915_gem_obj_is_pinned(obj)) {
		DRM_DEBUG("can not change the cache level of pinned objects\n");
		return -EBUSY;
	}

	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
		if (!i915_gem_valid_gtt_space(vma, cache_level)) {
			ret = i915_vma_unbind(vma);
			if (ret)
				return ret;
		}
	}

	if (i915_gem_obj_bound_any(obj)) {
		ret = i915_gem_object_finish_gpu(obj);
		if (ret)
			return ret;

		i915_gem_object_finish_gtt(obj);

		/* Before SandyBridge, you could not use tiling or fence
		 * registers with snooped memory, so relinquish any fences
		 * currently pointing to our region in the aperture.
		 */
		if (INTEL_INFO(dev)->gen < 6) {
			ret = i915_gem_object_put_fence(obj);
			if (ret)
				return ret;
		}

		list_for_each_entry(vma, &obj->vma_list, vma_link)
			if (drm_mm_node_allocated(&vma->node))
				vma->bind_vma(vma, cache_level,
					      obj->has_global_gtt_mapping ? GLOBAL_BIND : 0);
	}

	list_for_each_entry(vma, &obj->vma_list, vma_link)
		vma->node.color = cache_level;
	obj->cache_level = cache_level;

	if (cpu_write_needs_clflush(obj)) {
		u32 old_read_domains, old_write_domain;

		/* If we're coming from LLC cached, then we haven't
		 * actually been tracking whether the data is in the
		 * CPU cache or not, since we only allow one bit set
		 * in obj->write_domain and have been skipping the clflushes.
		 * Just set it to the CPU cache for now.
		 */
		i915_gem_object_retire(obj);
		WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);

		old_read_domains = obj->base.read_domains;
		old_write_domain = obj->base.write_domain;

		obj->base.read_domains = I915_GEM_DOMAIN_CPU;
		obj->base.write_domain = I915_GEM_DOMAIN_CPU;

		trace_i915_gem_object_change_domain(obj,
						    old_read_domains,
						    old_write_domain);
	}

	i915_gem_verify_gtt(dev);
	return 0;
}

int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
			       struct drm_file *file)
{
	struct drm_i915_gem_caching *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	switch (obj->cache_level) {
	case I915_CACHE_LLC:
	case I915_CACHE_L3_LLC:
		args->caching = I915_CACHING_CACHED;
		break;

	case I915_CACHE_WT:
		args->caching = I915_CACHING_DISPLAY;
		break;

	default:
		args->caching = I915_CACHING_NONE;
		break;
	}

	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
			       struct drm_file *file)
{
	struct drm_i915_gem_caching *args = data;
	struct drm_i915_gem_object *obj;
	enum i915_cache_level level;
	int ret;

	switch (args->caching) {
	case I915_CACHING_NONE:
		level = I915_CACHE_NONE;
		break;
	case I915_CACHING_CACHED:
		level = I915_CACHE_LLC;
		break;
	case I915_CACHING_DISPLAY:
		level = HAS_WT(dev) ? I915_CACHE_WT : I915_CACHE_NONE;
		break;
	default:
		return -EINVAL;
	}

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	ret = i915_gem_object_set_cache_level(obj, level);

	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

static bool is_pin_display(struct drm_i915_gem_object *obj)
{
	struct i915_vma *vma;

	vma = i915_gem_obj_to_ggtt(obj);
	if (!vma)
		return false;

	/* There are 3 sources that pin objects:
	 *   1. The display engine (scanouts, sprites, cursors);
	 *   2. Reservations for execbuffer;
	 *   3. The user.
	 *
	 * We can ignore reservations as we hold the struct_mutex and
	 * are only called outside of the reservation path.  The user
	 * can only increment pin_count once, and so if after
	 * subtracting the potential reference by the user, any pin_count
	 * remains, it must be due to another use by the display engine.
	 */
	return vma->pin_count - !!obj->user_pin_count;
}

/*
 * Prepare buffer for display plane (scanout, cursors, etc).
 * Can be called from an uninterruptible phase (modesetting) and allows
 * any flushes to be pipelined (for pageflips).
 */
int
i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
				     u32 alignment,
				     struct intel_engine_cs *pipelined)
{
	u32 old_read_domains, old_write_domain;
	bool was_pin_display;
	int ret;

	if (pipelined != obj->ring) {
		ret = i915_gem_object_sync(obj, pipelined);
		if (ret)
			return ret;
	}

	/* Mark the pin_display early so that we account for the
	 * display coherency whilst setting up the cache domains.
	 */
	was_pin_display = obj->pin_display;
	obj->pin_display = true;

	/* The display engine is not coherent with the LLC cache on gen6.  As
	 * a result, we make sure that the pinning that is about to occur is
	 * done with uncached PTEs. This is lowest common denominator for all
	 * chipsets.
	 *
	 * However for gen6+, we could do better by using the GFDT bit instead
	 * of uncaching, which would allow us to flush all the LLC-cached data
	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
	 */
	ret = i915_gem_object_set_cache_level(obj,
					      HAS_WT(obj->base.dev) ? I915_CACHE_WT : I915_CACHE_NONE);
	if (ret)
		goto err_unpin_display;

	/* As the user may map the buffer once pinned in the display plane
	 * (e.g. libkms for the bootup splash), we have to ensure that we
	 * always use map_and_fenceable for all scanout buffers.
	 */
	ret = i915_gem_obj_ggtt_pin(obj, alignment, PIN_MAPPABLE);
	if (ret)
		goto err_unpin_display;

	i915_gem_object_flush_cpu_write_domain(obj, true);

	old_write_domain = obj->base.write_domain;
	old_read_domains = obj->base.read_domains;

	/* It should now be out of any other write domains, and we can update
	 * the domain values for our changes.
	 */
	obj->base.write_domain = 0;
	obj->base.read_domains |= I915_GEM_DOMAIN_GTT;

	trace_i915_gem_object_change_domain(obj,
					    old_read_domains,
					    old_write_domain);

	return 0;

err_unpin_display:
	WARN_ON(was_pin_display != is_pin_display(obj));
	obj->pin_display = was_pin_display;
	return ret;
}

void
i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj)
{
	i915_gem_object_ggtt_unpin(obj);
	obj->pin_display = is_pin_display(obj);
}

int
i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj)
{
	int ret;

	if ((obj->base.read_domains & I915_GEM_GPU_DOMAINS) == 0)
		return 0;

	ret = i915_gem_object_wait_rendering(obj, false);
	if (ret)
		return ret;

	/* Ensure that we invalidate the GPU's caches and TLBs. */
	obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
	return 0;
}

/**
 * Moves a single object to the CPU read, and possibly write domain.
 *
 * This function returns when the move is complete, including waiting on
 * flushes to occur.
 */
int
i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
{
	uint32_t old_write_domain, old_read_domains;
	int ret;

	if (obj->base.write_domain == I915_GEM_DOMAIN_CPU)
		return 0;

	ret = i915_gem_object_wait_rendering(obj, !write);
	if (ret)
		return ret;

	i915_gem_object_retire(obj);
	i915_gem_object_flush_gtt_write_domain(obj);

	old_write_domain = obj->base.write_domain;
	old_read_domains = obj->base.read_domains;

	/* Flush the CPU cache if it's still invalid. */
	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) {
		i915_gem_clflush_object(obj, false);

		obj->base.read_domains |= I915_GEM_DOMAIN_CPU;
	}

	/* It should now be out of any other write domains, and we can update
	 * the domain values for our changes.
	 */
	BUG_ON((obj->base.write_domain & ~I915_GEM_DOMAIN_CPU) != 0);

	/* If we're writing through the CPU, then the GPU read domains will
	 * need to be invalidated at next use.
	 */
	if (write) {
		obj->base.read_domains = I915_GEM_DOMAIN_CPU;
		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
	}

	if (write)
		intel_fb_obj_invalidate(obj, NULL);

	trace_i915_gem_object_change_domain(obj,
					    old_read_domains,
					    old_write_domain);

	return 0;
}

/* Throttle our rendering by waiting until the ring has completed our requests
 * emitted over 20 msec ago.
 *
 * Note that if we were to use the current jiffies each time around the loop,
 * we wouldn't escape the function with any frames outstanding if the time to
 * render a frame was over 20ms.
 *
 * This should get us reasonable parallelism between CPU and GPU but also
 * relatively low latency when blocking on a particular request to finish.
 */
static int
i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_file_private *file_priv = file->driver_priv;
	unsigned long recent_enough = jiffies - msecs_to_jiffies(20);
	struct drm_i915_gem_request *request;
	struct intel_engine_cs *ring = NULL;
	unsigned reset_counter;
	u32 seqno = 0;
	int ret;

	ret = i915_gem_wait_for_error(&dev_priv->gpu_error);
	if (ret)
		return ret;

	ret = i915_gem_check_wedge(&dev_priv->gpu_error, false);
	if (ret)
		return ret;

	spin_lock(&file_priv->mm.lock);
	list_for_each_entry(request, &file_priv->mm.request_list, client_list) {
		if (time_after_eq(request->emitted_jiffies, recent_enough))
			break;

		ring = request->ring;
		seqno = request->seqno;
	}
	reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
	spin_unlock(&file_priv->mm.lock);

	if (seqno == 0)
		return 0;

	ret = __wait_seqno(ring, seqno, reset_counter, true, NULL, NULL);
	if (ret == 0)
		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0);

	return ret;
}

static bool
i915_vma_misplaced(struct i915_vma *vma, uint32_t alignment, uint64_t flags)
{
	struct drm_i915_gem_object *obj = vma->obj;

	if (alignment &&
	    vma->node.start & (alignment - 1))
		return true;

	if (flags & PIN_MAPPABLE && !obj->map_and_fenceable)
		return true;

	if (flags & PIN_OFFSET_BIAS &&
	    vma->node.start < (flags & PIN_OFFSET_MASK))
		return true;

	return false;
}

int
i915_gem_object_pin(struct drm_i915_gem_object *obj,
		    struct i915_address_space *vm,
		    uint32_t alignment,
		    uint64_t flags)
{
	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
	struct i915_vma *vma;
	int ret;

	if (WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base))
		return -ENODEV;

	if (WARN_ON(flags & (PIN_GLOBAL | PIN_MAPPABLE) && !i915_is_ggtt(vm)))
		return -EINVAL;

	vma = i915_gem_obj_to_vma(obj, vm);
	if (vma) {
		if (WARN_ON(vma->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
			return -EBUSY;

		if (i915_vma_misplaced(vma, alignment, flags)) {
			WARN(vma->pin_count,
			     "bo is already pinned with incorrect alignment:"
			     " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
			     " obj->map_and_fenceable=%d\n",
			     i915_gem_obj_offset(obj, vm), alignment,
			     !!(flags & PIN_MAPPABLE),
			     obj->map_and_fenceable);
			ret = i915_vma_unbind(vma);
			if (ret)
				return ret;

			vma = NULL;
		}
	}

	if (vma == NULL || !drm_mm_node_allocated(&vma->node)) {
		vma = i915_gem_object_bind_to_vm(obj, vm, alignment, flags);
		if (IS_ERR(vma))
			return PTR_ERR(vma);
	}

	if (flags & PIN_GLOBAL && !obj->has_global_gtt_mapping)
		vma->bind_vma(vma, obj->cache_level, GLOBAL_BIND);

	vma->pin_count++;
	if (flags & PIN_MAPPABLE)
		obj->pin_mappable |= true;

	return 0;
}

void
i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj)
{
	struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);

	BUG_ON(!vma);
	BUG_ON(vma->pin_count == 0);
	BUG_ON(!i915_gem_obj_ggtt_bound(obj));

	if (--vma->pin_count == 0)
		obj->pin_mappable = false;
}

bool
i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
{
	if (obj->fence_reg != I915_FENCE_REG_NONE) {
		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
		struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj);

		WARN_ON(!ggtt_vma ||
			dev_priv->fence_regs[obj->fence_reg].pin_count >
			ggtt_vma->pin_count);
		dev_priv->fence_regs[obj->fence_reg].pin_count++;
		return true;
	} else
		return false;
}

void
i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
{
	if (obj->fence_reg != I915_FENCE_REG_NONE) {
		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0);
		dev_priv->fence_regs[obj->fence_reg].pin_count--;
	}
}

int
i915_gem_pin_ioctl(struct drm_device *dev, void *data,
		   struct drm_file *file)
{
	struct drm_i915_gem_pin *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return -ENODEV;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	if (obj->madv != I915_MADV_WILLNEED) {
		DRM_DEBUG("Attempting to pin a purgeable buffer\n");
		ret = -EFAULT;
		goto out;
	}

	if (obj->pin_filp != NULL && obj->pin_filp != file) {
		DRM_DEBUG("Already pinned in i915_gem_pin_ioctl(): %d\n",
			  args->handle);
		ret = -EINVAL;
		goto out;
	}

	if (obj->user_pin_count == ULONG_MAX) {
		ret = -EBUSY;
		goto out;
	}

	if (obj->user_pin_count == 0) {
		ret = i915_gem_obj_ggtt_pin(obj, args->alignment, PIN_MAPPABLE);
		if (ret)
			goto out;
	}

	obj->user_pin_count++;
	obj->pin_filp = file;

	args->offset = i915_gem_obj_ggtt_offset(obj);
out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int
i915_gem_unpin_ioctl(struct drm_device *dev, void *data,
		     struct drm_file *file)
{
	struct drm_i915_gem_pin *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return -ENODEV;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	if (obj->pin_filp != file) {
		DRM_DEBUG("Not pinned by caller in i915_gem_pin_ioctl(): %d\n",
			  args->handle);
		ret = -EINVAL;
		goto out;
	}
	obj->user_pin_count--;
	if (obj->user_pin_count == 0) {
		obj->pin_filp = NULL;
		i915_gem_object_ggtt_unpin(obj);
	}

out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int
i915_gem_busy_ioctl(struct drm_device *dev, void *data,
		    struct drm_file *file)
{
	struct drm_i915_gem_busy *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	/* Count all active objects as busy, even if they are currently not used
	 * by the gpu. Users of this interface expect objects to eventually
	 * become non-busy without any further actions, therefore emit any
	 * necessary flushes here.
	 */
	ret = i915_gem_object_flush_active(obj);

	args->busy = obj->active;
	if (obj->ring) {
		BUILD_BUG_ON(I915_NUM_RINGS > 16);
		args->busy |= intel_ring_flag(obj->ring) << 16;
	}

	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int
i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file_priv)
{
	return i915_gem_ring_throttle(dev, file_priv);
}

int
i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
		       struct drm_file *file_priv)
{
	struct drm_i915_gem_madvise *args = data;
	struct drm_i915_gem_object *obj;
	int ret;

	switch (args->madv) {
	case I915_MADV_DONTNEED:
	case I915_MADV_WILLNEED:
	    break;
	default:
	    return -EINVAL;
	}

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		return ret;

	obj = to_intel_bo(drm_gem_object_lookup(dev, file_priv, args->handle));
	if (&obj->base == NULL) {
		ret = -ENOENT;
		goto unlock;
	}

	if (i915_gem_obj_is_pinned(obj)) {
		ret = -EINVAL;
		goto out;
	}

	if (obj->madv != __I915_MADV_PURGED)
		obj->madv = args->madv;

	/* if the object is no longer attached, discard its backing storage */
	if (i915_gem_object_is_purgeable(obj) && obj->pages == NULL)
		i915_gem_object_truncate(obj);

	args->retained = obj->madv != __I915_MADV_PURGED;

out:
	drm_gem_object_unreference(&obj->base);
unlock:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

void i915_gem_object_init(struct drm_i915_gem_object *obj,
			  const struct drm_i915_gem_object_ops *ops)
{
	INIT_LIST_HEAD(&obj->global_list);
	INIT_LIST_HEAD(&obj->ring_list);
	INIT_LIST_HEAD(&obj->obj_exec_link);
	INIT_LIST_HEAD(&obj->vma_list);

	obj->ops = ops;

	obj->fence_reg = I915_FENCE_REG_NONE;
	obj->madv = I915_MADV_WILLNEED;

	i915_gem_info_add_obj(obj->base.dev->dev_private, obj->base.size);
}

static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
	.get_pages = i915_gem_object_get_pages_gtt,
	.put_pages = i915_gem_object_put_pages_gtt,
};

struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
						  size_t size)
{
	struct drm_i915_gem_object *obj;
	struct address_space *mapping;
	gfp_t mask;

	obj = i915_gem_object_alloc(dev);
	if (obj == NULL)
		return NULL;

	if (drm_gem_object_init(dev, &obj->base, size) != 0) {
		i915_gem_object_free(obj);
		return NULL;
	}

	mask = GFP_HIGHUSER | __GFP_RECLAIMABLE;
	if (IS_CRESTLINE(dev) || IS_BROADWATER(dev)) {
		/* 965gm cannot relocate objects above 4GiB. */
		mask &= ~__GFP_HIGHMEM;
		mask |= __GFP_DMA32;
	}

	mapping = file_inode(obj->base.filp)->i_mapping;
	mapping_set_gfp_mask(mapping, mask);

	i915_gem_object_init(obj, &i915_gem_object_ops);

	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
	obj->base.read_domains = I915_GEM_DOMAIN_CPU;

	if (HAS_LLC(dev)) {
		/* On some devices, we can have the GPU use the LLC (the CPU
		 * cache) for about a 10% performance improvement
		 * compared to uncached.  Graphics requests other than
		 * display scanout are coherent with the CPU in
		 * accessing this cache.  This means in this mode we
		 * don't need to clflush on the CPU side, and on the
		 * GPU side we only need to flush internal caches to
		 * get data visible to the CPU.
		 *
		 * However, we maintain the display planes as UC, and so
		 * need to rebind when first used as such.
		 */
		obj->cache_level = I915_CACHE_LLC;
	} else
		obj->cache_level = I915_CACHE_NONE;

	trace_i915_gem_object_create(obj);

	return obj;
}

static bool discard_backing_storage(struct drm_i915_gem_object *obj)
{
	/* If we are the last user of the backing storage (be it shmemfs
	 * pages or stolen etc), we know that the pages are going to be
	 * immediately released. In this case, we can then skip copying
	 * back the contents from the GPU.
	 */

	if (obj->madv != I915_MADV_WILLNEED)
		return false;

	if (obj->base.filp == NULL)
		return true;

	/* At first glance, this looks racy, but then again so would be
	 * userspace racing mmap against close. However, the first external
	 * reference to the filp can only be obtained through the
	 * i915_gem_mmap_ioctl() which safeguards us against the user
	 * acquiring such a reference whilst we are in the middle of
	 * freeing the object.
	 */
	return atomic_long_read(&obj->base.filp->f_count) == 1;
}

void i915_gem_free_object(struct drm_gem_object *gem_obj)
{
	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct i915_vma *vma, *next;

	intel_runtime_pm_get(dev_priv);

	trace_i915_gem_object_destroy(obj);

	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
		int ret;

		vma->pin_count = 0;
		ret = i915_vma_unbind(vma);
		if (WARN_ON(ret == -ERESTARTSYS)) {
			bool was_interruptible;

			was_interruptible = dev_priv->mm.interruptible;
			dev_priv->mm.interruptible = false;

			WARN_ON(i915_vma_unbind(vma));

			dev_priv->mm.interruptible = was_interruptible;
		}
	}

	i915_gem_object_detach_phys(obj);

	/* Stolen objects don't hold a ref, but do hold pin count. Fix that up
	 * before progressing. */
	if (obj->stolen)
		i915_gem_object_unpin_pages(obj);

	WARN_ON(obj->frontbuffer_bits);

	if (WARN_ON(obj->pages_pin_count))
		obj->pages_pin_count = 0;
	if (discard_backing_storage(obj))
		obj->madv = I915_MADV_DONTNEED;
	i915_gem_object_put_pages(obj);
	i915_gem_object_free_mmap_offset(obj);

	BUG_ON(obj->pages);

	if (obj->base.import_attach)
		drm_prime_gem_destroy(&obj->base, NULL);

	if (obj->ops->release)
		obj->ops->release(obj);

	drm_gem_object_release(&obj->base);
	i915_gem_info_remove_obj(dev_priv, obj->base.size);

	kfree(obj->bit_17);
	i915_gem_object_free(obj);

	intel_runtime_pm_put(dev_priv);
}

struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
				     struct i915_address_space *vm)
{
	struct i915_vma *vma;
	list_for_each_entry(vma, &obj->vma_list, vma_link)
		if (vma->vm == vm)
			return vma;

	return NULL;
}

void i915_gem_vma_destroy(struct i915_vma *vma)
{
	struct i915_address_space *vm = NULL;
	WARN_ON(vma->node.allocated);

	/* Keep the vma as a placeholder in the execbuffer reservation lists */
	if (!list_empty(&vma->exec_list))
		return;

	vm = vma->vm;

	if (!i915_is_ggtt(vm))
		i915_ppgtt_put(i915_vm_to_ppgtt(vm));

	list_del(&vma->vma_link);

	kfree(vma);
}

static void
i915_gem_stop_ringbuffers(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int i;

	for_each_ring(ring, dev_priv, i)
		dev_priv->gt.stop_ring(ring);
}

int
i915_gem_suspend(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret = 0;

	mutex_lock(&dev->struct_mutex);
	if (dev_priv->ums.mm_suspended)
		goto err;

	ret = i915_gpu_idle(dev);
	if (ret)
		goto err;

	i915_gem_retire_requests(dev);

	/* Under UMS, be paranoid and evict. */
	if (!drm_core_check_feature(dev, DRIVER_MODESET))
		i915_gem_evict_everything(dev);

	i915_kernel_lost_context(dev);
	i915_gem_stop_ringbuffers(dev);

	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
	 * We need to replace this with a semaphore, or something.
	 * And not confound ums.mm_suspended!
	 */
	dev_priv->ums.mm_suspended = !drm_core_check_feature(dev,
							     DRIVER_MODESET);
	mutex_unlock(&dev->struct_mutex);

	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
	cancel_delayed_work_sync(&dev_priv->mm.retire_work);
	flush_delayed_work(&dev_priv->mm.idle_work);

	return 0;

err:
	mutex_unlock(&dev->struct_mutex);
	return ret;
}

int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
{
	struct drm_device *dev = ring->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
	int i, ret;

	if (!HAS_L3_DPF(dev) || !remap_info)
		return 0;

	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
	if (ret)
		return ret;

	/*
	 * Note: We do not worry about the concurrent register cacheline hang
	 * here because no other code should access these registers other than
	 * at initialization time.
	 */
	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
		intel_ring_emit(ring, reg_base + i);
		intel_ring_emit(ring, remap_info[i/4]);
	}

	intel_ring_advance(ring);

	return ret;
}

void i915_gem_init_swizzling(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;

	if (INTEL_INFO(dev)->gen < 5 ||
	    dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
		return;

	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
				 DISP_TILE_SURFACE_SWIZZLING);

	if (IS_GEN5(dev))
		return;

	I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_SWZCTL);
	if (IS_GEN6(dev))
		I915_WRITE(ARB_MODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_SNB));
	else if (IS_GEN7(dev))
		I915_WRITE(ARB_MODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_IVB));
	else if (IS_GEN8(dev))
		I915_WRITE(GAMTARBMODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_BDW));
	else
		BUG();
}

static bool
intel_enable_blt(struct drm_device *dev)
{
	if (!HAS_BLT(dev))
		return false;

	/* The blitter was dysfunctional on early prototypes */
	if (IS_GEN6(dev) && dev->pdev->revision < 8) {
		DRM_INFO("BLT not supported on this pre-production hardware;"
			 " graphics performance will be degraded.\n");
		return false;
	}

	return true;
}

static void init_unused_ring(struct drm_device *dev, u32 base)
{
	struct drm_i915_private *dev_priv = dev->dev_private;

	I915_WRITE(RING_CTL(base), 0);
	I915_WRITE(RING_HEAD(base), 0);
	I915_WRITE(RING_TAIL(base), 0);
	I915_WRITE(RING_START(base), 0);
}

static void init_unused_rings(struct drm_device *dev)
{
	if (IS_I830(dev)) {
		init_unused_ring(dev, PRB1_BASE);
		init_unused_ring(dev, SRB0_BASE);
		init_unused_ring(dev, SRB1_BASE);
		init_unused_ring(dev, SRB2_BASE);
		init_unused_ring(dev, SRB3_BASE);
	} else if (IS_GEN2(dev)) {
		init_unused_ring(dev, SRB0_BASE);
		init_unused_ring(dev, SRB1_BASE);
	} else if (IS_GEN3(dev)) {
		init_unused_ring(dev, PRB1_BASE);
		init_unused_ring(dev, PRB2_BASE);
	}
}

int i915_gem_init_rings(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	/*
	 * At least 830 can leave some of the unused rings
	 * "active" (ie. head != tail) after resume which
	 * will prevent c3 entry. Makes sure all unused rings
	 * are totally idle.
	 */
	init_unused_rings(dev);

	ret = intel_init_render_ring_buffer(dev);
	if (ret)
		return ret;

	if (HAS_BSD(dev)) {
		ret = intel_init_bsd_ring_buffer(dev);
		if (ret)
			goto cleanup_render_ring;
	}

	if (intel_enable_blt(dev)) {
		ret = intel_init_blt_ring_buffer(dev);
		if (ret)
			goto cleanup_bsd_ring;
	}

	if (HAS_VEBOX(dev)) {
		ret = intel_init_vebox_ring_buffer(dev);
		if (ret)
			goto cleanup_blt_ring;
	}

	if (HAS_BSD2(dev)) {
		ret = intel_init_bsd2_ring_buffer(dev);
		if (ret)
			goto cleanup_vebox_ring;
	}

	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
	if (ret)
		goto cleanup_bsd2_ring;

	return 0;

cleanup_bsd2_ring:
	intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]);
cleanup_vebox_ring:
	intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
cleanup_blt_ring:
	intel_cleanup_ring_buffer(&dev_priv->ring[BCS]);
cleanup_bsd_ring:
	intel_cleanup_ring_buffer(&dev_priv->ring[VCS]);
cleanup_render_ring:
	intel_cleanup_ring_buffer(&dev_priv->ring[RCS]);

	return ret;
}

int
i915_gem_init_hw(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret, i;

	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
		return -EIO;

	if (dev_priv->ellc_size)
		I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf));

	if (IS_HASWELL(dev))
		I915_WRITE(MI_PREDICATE_RESULT_2, IS_HSW_GT3(dev) ?
			   LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED);

	if (HAS_PCH_NOP(dev)) {
		if (IS_IVYBRIDGE(dev)) {
			u32 temp = I915_READ(GEN7_MSG_CTL);
			temp &= ~(WAIT_FOR_PCH_FLR_ACK | WAIT_FOR_PCH_RESET_ACK);
			I915_WRITE(GEN7_MSG_CTL, temp);
		} else if (INTEL_INFO(dev)->gen >= 7) {
			u32 temp = I915_READ(HSW_NDE_RSTWRN_OPT);
			temp &= ~RESET_PCH_HANDSHAKE_ENABLE;
			I915_WRITE(HSW_NDE_RSTWRN_OPT, temp);
		}
	}

	i915_gem_init_swizzling(dev);

	ret = dev_priv->gt.init_rings(dev);
	if (ret)
		return ret;

	for (i = 0; i < NUM_L3_SLICES(dev); i++)
		i915_gem_l3_remap(&dev_priv->ring[RCS], i);

	ret = i915_ppgtt_init_hw(dev);
	if (ret && ret != -EIO) {
		DRM_ERROR("PPGTT enable failed %d\n", ret);
		i915_gem_cleanup_ringbuffer(dev);
	}

	ret = i915_gem_context_enable(dev_priv);
	if (ret && ret != -EIO) {
		DRM_ERROR("Context enable failed %d\n", ret);
		i915_gem_cleanup_ringbuffer(dev);

		return ret;
	}

	return ret;
}

int i915_gem_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	i915.enable_execlists = intel_sanitize_enable_execlists(dev,
			i915.enable_execlists);

	mutex_lock(&dev->struct_mutex);

	if (IS_VALLEYVIEW(dev)) {
		/* VLVA0 (potential hack), BIOS isn't actually waking us */
		I915_WRITE(VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ);
		if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) &
			      VLV_GTLC_ALLOWWAKEACK), 10))
			DRM_DEBUG_DRIVER("allow wake ack timed out\n");
	}

	if (!i915.enable_execlists) {
		dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
		dev_priv->gt.init_rings = i915_gem_init_rings;
		dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
		dev_priv->gt.stop_ring = intel_stop_ring_buffer;
	} else {
		dev_priv->gt.do_execbuf = intel_execlists_submission;
		dev_priv->gt.init_rings = intel_logical_rings_init;
		dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
		dev_priv->gt.stop_ring = intel_logical_ring_stop;
	}

	ret = i915_gem_init_userptr(dev);
	if (ret) {
		mutex_unlock(&dev->struct_mutex);
		return ret;
	}

	i915_gem_init_global_gtt(dev);

	ret = i915_gem_context_init(dev);
	if (ret) {
		mutex_unlock(&dev->struct_mutex);
		return ret;
	}

	ret = i915_gem_init_hw(dev);
	if (ret == -EIO) {
		/* Allow ring initialisation to fail by marking the GPU as
		 * wedged. But we only want to do this where the GPU is angry,
		 * for all other failure, such as an allocation failure, bail.
		 */
		DRM_ERROR("Failed to initialize GPU, declaring it wedged\n");
		atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
		ret = 0;
	}
	mutex_unlock(&dev->struct_mutex);

	/* Allow hardware batchbuffers unless told otherwise, but not for KMS. */
	if (!drm_core_check_feature(dev, DRIVER_MODESET))
		dev_priv->dri1.allow_batchbuffer = 1;
	return ret;
}

void
i915_gem_cleanup_ringbuffer(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int i;

	for_each_ring(ring, dev_priv, i)
		dev_priv->gt.cleanup_ring(ring);
}

int
i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
		       struct drm_file *file_priv)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return 0;

	if (i915_reset_in_progress(&dev_priv->gpu_error)) {
		DRM_ERROR("Reenabling wedged hardware, good luck\n");
		atomic_set(&dev_priv->gpu_error.reset_counter, 0);
	}

	mutex_lock(&dev->struct_mutex);
	dev_priv->ums.mm_suspended = 0;

	ret = i915_gem_init_hw(dev);
	if (ret != 0) {
		mutex_unlock(&dev->struct_mutex);
		return ret;
	}

	BUG_ON(!list_empty(&dev_priv->gtt.base.active_list));

	ret = drm_irq_install(dev, dev->pdev->irq);
	if (ret)
		goto cleanup_ringbuffer;
	mutex_unlock(&dev->struct_mutex);

	return 0;

cleanup_ringbuffer:
	i915_gem_cleanup_ringbuffer(dev);
	dev_priv->ums.mm_suspended = 1;
	mutex_unlock(&dev->struct_mutex);

	return ret;
}

int
i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
		       struct drm_file *file_priv)
{
	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return 0;

	mutex_lock(&dev->struct_mutex);
	drm_irq_uninstall(dev);
	mutex_unlock(&dev->struct_mutex);

	return i915_gem_suspend(dev);
}

void
i915_gem_lastclose(struct drm_device *dev)
{
	int ret;

	if (drm_core_check_feature(dev, DRIVER_MODESET))
		return;

	ret = i915_gem_suspend(dev);
	if (ret)
		DRM_ERROR("failed to idle hardware: %d\n", ret);
}

static void
init_ring_lists(struct intel_engine_cs *ring)
{
	INIT_LIST_HEAD(&ring->active_list);
	INIT_LIST_HEAD(&ring->request_list);
}

void i915_init_vm(struct drm_i915_private *dev_priv,
		  struct i915_address_space *vm)
{
	if (!i915_is_ggtt(vm))
		drm_mm_init(&vm->mm, vm->start, vm->total);
	vm->dev = dev_priv->dev;
	INIT_LIST_HEAD(&vm->active_list);
	INIT_LIST_HEAD(&vm->inactive_list);
	INIT_LIST_HEAD(&vm->global_link);
	list_add_tail(&vm->global_link, &dev_priv->vm_list);
}

void
i915_gem_load(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int i;

	dev_priv->slab =
		kmem_cache_create("i915_gem_object",
				  sizeof(struct drm_i915_gem_object), 0,
				  SLAB_HWCACHE_ALIGN,
				  NULL);

	INIT_LIST_HEAD(&dev_priv->vm_list);
	i915_init_vm(dev_priv, &dev_priv->gtt.base);

	INIT_LIST_HEAD(&dev_priv->context_list);
	INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
	INIT_LIST_HEAD(&dev_priv->mm.bound_list);
	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
	for (i = 0; i < I915_NUM_RINGS; i++)
		init_ring_lists(&dev_priv->ring[i]);
	for (i = 0; i < I915_MAX_NUM_FENCES; i++)
		INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list);
	INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
			  i915_gem_retire_work_handler);
	INIT_DELAYED_WORK(&dev_priv->mm.idle_work,
			  i915_gem_idle_work_handler);
	init_waitqueue_head(&dev_priv->gpu_error.reset_queue);

	/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
	if (!drm_core_check_feature(dev, DRIVER_MODESET) && IS_GEN3(dev)) {
		I915_WRITE(MI_ARB_STATE,
			   _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
	}

	dev_priv->relative_constants_mode = I915_EXEC_CONSTANTS_REL_GENERAL;

	/* Old X drivers will take 0-2 for front, back, depth buffers */
	if (!drm_core_check_feature(dev, DRIVER_MODESET))
		dev_priv->fence_reg_start = 3;

	if (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev))
		dev_priv->num_fence_regs = 32;
	else if (INTEL_INFO(dev)->gen >= 4 || IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
		dev_priv->num_fence_regs = 16;
	else
		dev_priv->num_fence_regs = 8;

	/* Initialize fence registers to zero */
	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
	i915_gem_restore_fences(dev);

	i915_gem_detect_bit_6_swizzle(dev);
	init_waitqueue_head(&dev_priv->pending_flip_queue);

	dev_priv->mm.interruptible = true;

	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
	register_shrinker(&dev_priv->mm.shrinker);

	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
	register_oom_notifier(&dev_priv->mm.oom_notifier);

	mutex_init(&dev_priv->fb_tracking.lock);
}

void i915_gem_release(struct drm_device *dev, struct drm_file *file)
{
	struct drm_i915_file_private *file_priv = file->driver_priv;

	cancel_delayed_work_sync(&file_priv->mm.idle_work);

	/* Clean up our request list when the client is going away, so that
	 * later retire_requests won't dereference our soon-to-be-gone
	 * file_priv.
	 */
	spin_lock(&file_priv->mm.lock);
	while (!list_empty(&file_priv->mm.request_list)) {
		struct drm_i915_gem_request *request;

		request = list_first_entry(&file_priv->mm.request_list,
					   struct drm_i915_gem_request,
					   client_list);
		list_del(&request->client_list);
		request->file_priv = NULL;
	}
	spin_unlock(&file_priv->mm.lock);
}

static void
i915_gem_file_idle_work_handler(struct work_struct *work)
{
	struct drm_i915_file_private *file_priv =
		container_of(work, typeof(*file_priv), mm.idle_work.work);

	atomic_set(&file_priv->rps_wait_boost, false);
}

int i915_gem_open(struct drm_device *dev, struct drm_file *file)
{
	struct drm_i915_file_private *file_priv;
	int ret;

	DRM_DEBUG_DRIVER("\n");

	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
	if (!file_priv)
		return -ENOMEM;

	file->driver_priv = file_priv;
	file_priv->dev_priv = dev->dev_private;
	file_priv->file = file;

	spin_lock_init(&file_priv->mm.lock);
	INIT_LIST_HEAD(&file_priv->mm.request_list);
	INIT_DELAYED_WORK(&file_priv->mm.idle_work,
			  i915_gem_file_idle_work_handler);

	ret = i915_gem_context_open(dev, file);
	if (ret)
		kfree(file_priv);

	return ret;
}

void i915_gem_track_fb(struct drm_i915_gem_object *old,
		       struct drm_i915_gem_object *new,
		       unsigned frontbuffer_bits)
{
	if (old) {
		WARN_ON(!mutex_is_locked(&old->base.dev->struct_mutex));
		WARN_ON(!(old->frontbuffer_bits & frontbuffer_bits));
		old->frontbuffer_bits &= ~frontbuffer_bits;
	}

	if (new) {
		WARN_ON(!mutex_is_locked(&new->base.dev->struct_mutex));
		WARN_ON(new->frontbuffer_bits & frontbuffer_bits);
		new->frontbuffer_bits |= frontbuffer_bits;
	}
}

static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
{
	if (!mutex_is_locked(mutex))
		return false;

#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
	return mutex->owner == task;
#else
	/* Since UP may be pre-empted, we cannot assume that we own the lock */
	return false;
#endif
}

static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
{
	if (!mutex_trylock(&dev->struct_mutex)) {
		if (!mutex_is_locked_by(&dev->struct_mutex, current))
			return false;

		if (to_i915(dev)->mm.shrinker_no_lock_stealing)
			return false;

		*unlock = false;
	} else
		*unlock = true;

	return true;
}

static int num_vma_bound(struct drm_i915_gem_object *obj)
{
	struct i915_vma *vma;
	int count = 0;

	list_for_each_entry(vma, &obj->vma_list, vma_link)
		if (drm_mm_node_allocated(&vma->node))
			count++;

	return count;
}

static unsigned long
i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
{
	struct drm_i915_private *dev_priv =
		container_of(shrinker, struct drm_i915_private, mm.shrinker);
	struct drm_device *dev = dev_priv->dev;
	struct drm_i915_gem_object *obj;
	unsigned long count;
	bool unlock;

	if (!i915_gem_shrinker_lock(dev, &unlock))
		return 0;

	count = 0;
	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
		if (obj->pages_pin_count == 0)
			count += obj->base.size >> PAGE_SHIFT;

	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
		if (!i915_gem_obj_is_pinned(obj) &&
		    obj->pages_pin_count == num_vma_bound(obj))
			count += obj->base.size >> PAGE_SHIFT;
	}

	if (unlock)
		mutex_unlock(&dev->struct_mutex);

	return count;
}

/* All the new VM stuff */
unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
				  struct i915_address_space *vm)
{
	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
	struct i915_vma *vma;

	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);

	list_for_each_entry(vma, &o->vma_list, vma_link) {
		if (vma->vm == vm)
			return vma->node.start;

	}
	WARN(1, "%s vma for this object not found.\n",
	     i915_is_ggtt(vm) ? "global" : "ppgtt");
	return -1;
}

bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
			struct i915_address_space *vm)
{
	struct i915_vma *vma;

	list_for_each_entry(vma, &o->vma_list, vma_link)
		if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
			return true;

	return false;
}

bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o)
{
	struct i915_vma *vma;

	list_for_each_entry(vma, &o->vma_list, vma_link)
		if (drm_mm_node_allocated(&vma->node))
			return true;

	return false;
}

unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
				struct i915_address_space *vm)
{
	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
	struct i915_vma *vma;

	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);

	BUG_ON(list_empty(&o->vma_list));

	list_for_each_entry(vma, &o->vma_list, vma_link)
		if (vma->vm == vm)
			return vma->node.size;

	return 0;
}

static unsigned long
i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
{
	struct drm_i915_private *dev_priv =
		container_of(shrinker, struct drm_i915_private, mm.shrinker);
	struct drm_device *dev = dev_priv->dev;
	unsigned long freed;
	bool unlock;

	if (!i915_gem_shrinker_lock(dev, &unlock))
		return SHRINK_STOP;

	freed = i915_gem_shrink(dev_priv,
				sc->nr_to_scan,
				I915_SHRINK_BOUND |
				I915_SHRINK_UNBOUND |
				I915_SHRINK_PURGEABLE);
	if (freed < sc->nr_to_scan)
		freed += i915_gem_shrink(dev_priv,
					 sc->nr_to_scan - freed,
					 I915_SHRINK_BOUND |
					 I915_SHRINK_UNBOUND);
	if (unlock)
		mutex_unlock(&dev->struct_mutex);

	return freed;
}

static int
i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
{
	struct drm_i915_private *dev_priv =
		container_of(nb, struct drm_i915_private, mm.oom_notifier);
	struct drm_device *dev = dev_priv->dev;
	struct drm_i915_gem_object *obj;
	unsigned long timeout = msecs_to_jiffies(5000) + 1;
	unsigned long pinned, bound, unbound, freed;
	bool was_interruptible;
	bool unlock;

	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) {
		schedule_timeout_killable(1);
		if (fatal_signal_pending(current))
			return NOTIFY_DONE;
	}
	if (timeout == 0) {
		pr_err("Unable to purge GPU memory due lock contention.\n");
		return NOTIFY_DONE;
	}

	was_interruptible = dev_priv->mm.interruptible;
	dev_priv->mm.interruptible = false;

	freed = i915_gem_shrink_all(dev_priv);

	dev_priv->mm.interruptible = was_interruptible;

	/* Because we may be allocating inside our own driver, we cannot
	 * assert that there are no objects with pinned pages that are not
	 * being pointed to by hardware.
	 */
	unbound = bound = pinned = 0;
	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
		if (!obj->base.filp) /* not backed by a freeable object */
			continue;

		if (obj->pages_pin_count)
			pinned += obj->base.size;
		else
			unbound += obj->base.size;
	}
	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
		if (!obj->base.filp)
			continue;

		if (obj->pages_pin_count)
			pinned += obj->base.size;
		else
			bound += obj->base.size;
	}

	if (unlock)
		mutex_unlock(&dev->struct_mutex);

	pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n",
		freed, pinned);
	if (unbound || bound)
		pr_err("%lu and %lu bytes still available in the "
		       "bound and unbound GPU page lists.\n",
		       bound, unbound);

	*(unsigned long *)ptr += freed;
	return NOTIFY_DONE;
}

struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
{
	struct i915_vma *vma;

	vma = list_first_entry(&obj->vma_list, typeof(*vma), vma_link);
	if (vma->vm != i915_obj_to_ggtt(obj))
		return NULL;

	return vma;
}