summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_gem_gtt.c
blob: 0bb4232f66bcac1ad9653c073c1cbe7cb7375c16 (plain)
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
/*
 * Copyright © 2010 Daniel Vetter
 * Copyright © 2011-2014 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.
 *
 */

#include <linux/seq_file.h>
#include <linux/stop_machine.h>
#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_vgpu.h"
#include "i915_trace.h"
#include "intel_drv.h"

#define I915_GFP_DMA (GFP_KERNEL | __GFP_HIGHMEM)

/**
 * DOC: Global GTT views
 *
 * Background and previous state
 *
 * Historically objects could exists (be bound) in global GTT space only as
 * singular instances with a view representing all of the object's backing pages
 * in a linear fashion. This view will be called a normal view.
 *
 * To support multiple views of the same object, where the number of mapped
 * pages is not equal to the backing store, or where the layout of the pages
 * is not linear, concept of a GGTT view was added.
 *
 * One example of an alternative view is a stereo display driven by a single
 * image. In this case we would have a framebuffer looking like this
 * (2x2 pages):
 *
 *    12
 *    34
 *
 * Above would represent a normal GGTT view as normally mapped for GPU or CPU
 * rendering. In contrast, fed to the display engine would be an alternative
 * view which could look something like this:
 *
 *   1212
 *   3434
 *
 * In this example both the size and layout of pages in the alternative view is
 * different from the normal view.
 *
 * Implementation and usage
 *
 * GGTT views are implemented using VMAs and are distinguished via enum
 * i915_ggtt_view_type and struct i915_ggtt_view.
 *
 * A new flavour of core GEM functions which work with GGTT bound objects were
 * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
 * renaming  in large amounts of code. They take the struct i915_ggtt_view
 * parameter encapsulating all metadata required to implement a view.
 *
 * As a helper for callers which are only interested in the normal view,
 * globally const i915_ggtt_view_normal singleton instance exists. All old core
 * GEM API functions, the ones not taking the view parameter, are operating on,
 * or with the normal GGTT view.
 *
 * Code wanting to add or use a new GGTT view needs to:
 *
 * 1. Add a new enum with a suitable name.
 * 2. Extend the metadata in the i915_ggtt_view structure if required.
 * 3. Add support to i915_get_vma_pages().
 *
 * New views are required to build a scatter-gather table from within the
 * i915_get_vma_pages function. This table is stored in the vma.ggtt_view and
 * exists for the lifetime of an VMA.
 *
 * Core API is designed to have copy semantics which means that passed in
 * struct i915_ggtt_view does not need to be persistent (left around after
 * calling the core API functions).
 *
 */

static inline struct i915_ggtt *
i915_vm_to_ggtt(struct i915_address_space *vm)
{
	GEM_BUG_ON(!i915_is_ggtt(vm));
	return container_of(vm, struct i915_ggtt, base);
}

static int
i915_get_ggtt_vma_pages(struct i915_vma *vma);

const struct i915_ggtt_view i915_ggtt_view_normal = {
	.type = I915_GGTT_VIEW_NORMAL,
};
const struct i915_ggtt_view i915_ggtt_view_rotated = {
	.type = I915_GGTT_VIEW_ROTATED,
};

int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
			       	int enable_ppgtt)
{
	bool has_aliasing_ppgtt;
	bool has_full_ppgtt;
	bool has_full_48bit_ppgtt;

	has_aliasing_ppgtt = INTEL_GEN(dev_priv) >= 6;
	has_full_ppgtt = INTEL_GEN(dev_priv) >= 7;
	has_full_48bit_ppgtt =
	       	IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9;

	if (intel_vgpu_active(dev_priv)) {
		/* emulation is too hard */
		has_full_ppgtt = false;
		has_full_48bit_ppgtt = false;
	}

	if (!has_aliasing_ppgtt)
		return 0;

	/*
	 * We don't allow disabling PPGTT for gen9+ as it's a requirement for
	 * execlists, the sole mechanism available to submit work.
	 */
	if (enable_ppgtt == 0 && INTEL_GEN(dev_priv) < 9)
		return 0;

	if (enable_ppgtt == 1)
		return 1;

	if (enable_ppgtt == 2 && has_full_ppgtt)
		return 2;

	if (enable_ppgtt == 3 && has_full_48bit_ppgtt)
		return 3;

#ifdef CONFIG_INTEL_IOMMU
	/* Disable ppgtt on SNB if VT-d is on. */
	if (IS_GEN6(dev_priv) && intel_iommu_gfx_mapped) {
		DRM_INFO("Disabling PPGTT because VT-d is on\n");
		return 0;
	}
#endif

	/* Early VLV doesn't have this */
	if (IS_VALLEYVIEW(dev_priv) && dev_priv->drm.pdev->revision < 0xb) {
		DRM_DEBUG_DRIVER("disabling PPGTT on pre-B3 step VLV\n");
		return 0;
	}

	if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists && has_full_ppgtt)
		return has_full_48bit_ppgtt ? 3 : 2;
	else
		return has_aliasing_ppgtt ? 1 : 0;
}

static int ppgtt_bind_vma(struct i915_vma *vma,
			  enum i915_cache_level cache_level,
			  u32 unused)
{
	u32 pte_flags = 0;

	vma->pages = vma->obj->pages;

	/* Currently applicable only to VLV */
	if (vma->obj->gt_ro)
		pte_flags |= PTE_READ_ONLY;

	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
				cache_level, pte_flags);

	return 0;
}

static void ppgtt_unbind_vma(struct i915_vma *vma)
{
	vma->vm->clear_range(vma->vm,
			     vma->node.start,
			     vma->size,
			     true);
}

static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
				  enum i915_cache_level level,
				  bool valid)
{
	gen8_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
	pte |= addr;

	switch (level) {
	case I915_CACHE_NONE:
		pte |= PPAT_UNCACHED_INDEX;
		break;
	case I915_CACHE_WT:
		pte |= PPAT_DISPLAY_ELLC_INDEX;
		break;
	default:
		pte |= PPAT_CACHED_INDEX;
		break;
	}

	return pte;
}

static gen8_pde_t gen8_pde_encode(const dma_addr_t addr,
				  const enum i915_cache_level level)
{
	gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
	pde |= addr;
	if (level != I915_CACHE_NONE)
		pde |= PPAT_CACHED_PDE_INDEX;
	else
		pde |= PPAT_UNCACHED_INDEX;
	return pde;
}

#define gen8_pdpe_encode gen8_pde_encode
#define gen8_pml4e_encode gen8_pde_encode

static gen6_pte_t snb_pte_encode(dma_addr_t addr,
				 enum i915_cache_level level,
				 bool valid, u32 unused)
{
	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_L3_LLC:
	case I915_CACHE_LLC:
		pte |= GEN6_PTE_CACHE_LLC;
		break;
	case I915_CACHE_NONE:
		pte |= GEN6_PTE_UNCACHED;
		break;
	default:
		MISSING_CASE(level);
	}

	return pte;
}

static gen6_pte_t ivb_pte_encode(dma_addr_t addr,
				 enum i915_cache_level level,
				 bool valid, u32 unused)
{
	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_L3_LLC:
		pte |= GEN7_PTE_CACHE_L3_LLC;
		break;
	case I915_CACHE_LLC:
		pte |= GEN6_PTE_CACHE_LLC;
		break;
	case I915_CACHE_NONE:
		pte |= GEN6_PTE_UNCACHED;
		break;
	default:
		MISSING_CASE(level);
	}

	return pte;
}

static gen6_pte_t byt_pte_encode(dma_addr_t addr,
				 enum i915_cache_level level,
				 bool valid, u32 flags)
{
	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	if (!(flags & PTE_READ_ONLY))
		pte |= BYT_PTE_WRITEABLE;

	if (level != I915_CACHE_NONE)
		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;

	return pte;
}

static gen6_pte_t hsw_pte_encode(dma_addr_t addr,
				 enum i915_cache_level level,
				 bool valid, u32 unused)
{
	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= HSW_PTE_ADDR_ENCODE(addr);

	if (level != I915_CACHE_NONE)
		pte |= HSW_WB_LLC_AGE3;

	return pte;
}

static gen6_pte_t iris_pte_encode(dma_addr_t addr,
				  enum i915_cache_level level,
				  bool valid, u32 unused)
{
	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= HSW_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_NONE:
		break;
	case I915_CACHE_WT:
		pte |= HSW_WT_ELLC_LLC_AGE3;
		break;
	default:
		pte |= HSW_WB_ELLC_LLC_AGE3;
		break;
	}

	return pte;
}

static int __setup_page_dma(struct drm_device *dev,
			    struct i915_page_dma *p, gfp_t flags)
{
	struct device *kdev = &dev->pdev->dev;

	p->page = alloc_page(flags);
	if (!p->page)
		return -ENOMEM;

	p->daddr = dma_map_page(kdev,
				p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL);

	if (dma_mapping_error(kdev, p->daddr)) {
		__free_page(p->page);
		return -EINVAL;
	}

	return 0;
}

static int setup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
{
	return __setup_page_dma(dev, p, I915_GFP_DMA);
}

static void cleanup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
{
	struct pci_dev *pdev = dev->pdev;

	if (WARN_ON(!p->page))
		return;

	dma_unmap_page(&pdev->dev, p->daddr, 4096, PCI_DMA_BIDIRECTIONAL);
	__free_page(p->page);
	memset(p, 0, sizeof(*p));
}

static void *kmap_page_dma(struct i915_page_dma *p)
{
	return kmap_atomic(p->page);
}

/* We use the flushing unmap only with ppgtt structures:
 * page directories, page tables and scratch pages.
 */
static void kunmap_page_dma(struct drm_device *dev, void *vaddr)
{
	/* There are only few exceptions for gen >=6. chv and bxt.
	 * And we are not sure about the latter so play safe for now.
	 */
	if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
		drm_clflush_virt_range(vaddr, PAGE_SIZE);

	kunmap_atomic(vaddr);
}

#define kmap_px(px) kmap_page_dma(px_base(px))
#define kunmap_px(ppgtt, vaddr) kunmap_page_dma((ppgtt)->base.dev, (vaddr))

#define setup_px(dev, px) setup_page_dma((dev), px_base(px))
#define cleanup_px(dev, px) cleanup_page_dma((dev), px_base(px))
#define fill_px(dev, px, v) fill_page_dma((dev), px_base(px), (v))
#define fill32_px(dev, px, v) fill_page_dma_32((dev), px_base(px), (v))

static void fill_page_dma(struct drm_device *dev, struct i915_page_dma *p,
			  const uint64_t val)
{
	int i;
	uint64_t * const vaddr = kmap_page_dma(p);

	for (i = 0; i < 512; i++)
		vaddr[i] = val;

	kunmap_page_dma(dev, vaddr);
}

static void fill_page_dma_32(struct drm_device *dev, struct i915_page_dma *p,
			     const uint32_t val32)
{
	uint64_t v = val32;

	v = v << 32 | val32;

	fill_page_dma(dev, p, v);
}

static int
setup_scratch_page(struct drm_device *dev,
		   struct i915_page_dma *scratch,
		   gfp_t gfp)
{
	return __setup_page_dma(dev, scratch, gfp | __GFP_ZERO);
}

static void cleanup_scratch_page(struct drm_device *dev,
				 struct i915_page_dma *scratch)
{
	cleanup_page_dma(dev, scratch);
}

static struct i915_page_table *alloc_pt(struct drm_device *dev)
{
	struct i915_page_table *pt;
	const size_t count = INTEL_INFO(dev)->gen >= 8 ?
		GEN8_PTES : GEN6_PTES;
	int ret = -ENOMEM;

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

	pt->used_ptes = kcalloc(BITS_TO_LONGS(count), sizeof(*pt->used_ptes),
				GFP_KERNEL);

	if (!pt->used_ptes)
		goto fail_bitmap;

	ret = setup_px(dev, pt);
	if (ret)
		goto fail_page_m;

	return pt;

fail_page_m:
	kfree(pt->used_ptes);
fail_bitmap:
	kfree(pt);

	return ERR_PTR(ret);
}

static void free_pt(struct drm_device *dev, struct i915_page_table *pt)
{
	cleanup_px(dev, pt);
	kfree(pt->used_ptes);
	kfree(pt);
}

static void gen8_initialize_pt(struct i915_address_space *vm,
			       struct i915_page_table *pt)
{
	gen8_pte_t scratch_pte;

	scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
				      I915_CACHE_LLC, true);

	fill_px(vm->dev, pt, scratch_pte);
}

static void gen6_initialize_pt(struct i915_address_space *vm,
			       struct i915_page_table *pt)
{
	gen6_pte_t scratch_pte;

	WARN_ON(vm->scratch_page.daddr == 0);

	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
				     I915_CACHE_LLC, true, 0);

	fill32_px(vm->dev, pt, scratch_pte);
}

static struct i915_page_directory *alloc_pd(struct drm_device *dev)
{
	struct i915_page_directory *pd;
	int ret = -ENOMEM;

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

	pd->used_pdes = kcalloc(BITS_TO_LONGS(I915_PDES),
				sizeof(*pd->used_pdes), GFP_KERNEL);
	if (!pd->used_pdes)
		goto fail_bitmap;

	ret = setup_px(dev, pd);
	if (ret)
		goto fail_page_m;

	return pd;

fail_page_m:
	kfree(pd->used_pdes);
fail_bitmap:
	kfree(pd);

	return ERR_PTR(ret);
}

static void free_pd(struct drm_device *dev, struct i915_page_directory *pd)
{
	if (px_page(pd)) {
		cleanup_px(dev, pd);
		kfree(pd->used_pdes);
		kfree(pd);
	}
}

static void gen8_initialize_pd(struct i915_address_space *vm,
			       struct i915_page_directory *pd)
{
	gen8_pde_t scratch_pde;

	scratch_pde = gen8_pde_encode(px_dma(vm->scratch_pt), I915_CACHE_LLC);

	fill_px(vm->dev, pd, scratch_pde);
}

static int __pdp_init(struct drm_device *dev,
		      struct i915_page_directory_pointer *pdp)
{
	size_t pdpes = I915_PDPES_PER_PDP(dev);

	pdp->used_pdpes = kcalloc(BITS_TO_LONGS(pdpes),
				  sizeof(unsigned long),
				  GFP_KERNEL);
	if (!pdp->used_pdpes)
		return -ENOMEM;

	pdp->page_directory = kcalloc(pdpes, sizeof(*pdp->page_directory),
				      GFP_KERNEL);
	if (!pdp->page_directory) {
		kfree(pdp->used_pdpes);
		/* the PDP might be the statically allocated top level. Keep it
		 * as clean as possible */
		pdp->used_pdpes = NULL;
		return -ENOMEM;
	}

	return 0;
}

static void __pdp_fini(struct i915_page_directory_pointer *pdp)
{
	kfree(pdp->used_pdpes);
	kfree(pdp->page_directory);
	pdp->page_directory = NULL;
}

static struct
i915_page_directory_pointer *alloc_pdp(struct drm_device *dev)
{
	struct i915_page_directory_pointer *pdp;
	int ret = -ENOMEM;

	WARN_ON(!USES_FULL_48BIT_PPGTT(dev));

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

	ret = __pdp_init(dev, pdp);
	if (ret)
		goto fail_bitmap;

	ret = setup_px(dev, pdp);
	if (ret)
		goto fail_page_m;

	return pdp;

fail_page_m:
	__pdp_fini(pdp);
fail_bitmap:
	kfree(pdp);

	return ERR_PTR(ret);
}

static void free_pdp(struct drm_device *dev,
		     struct i915_page_directory_pointer *pdp)
{
	__pdp_fini(pdp);
	if (USES_FULL_48BIT_PPGTT(dev)) {
		cleanup_px(dev, pdp);
		kfree(pdp);
	}
}

static void gen8_initialize_pdp(struct i915_address_space *vm,
				struct i915_page_directory_pointer *pdp)
{
	gen8_ppgtt_pdpe_t scratch_pdpe;

	scratch_pdpe = gen8_pdpe_encode(px_dma(vm->scratch_pd), I915_CACHE_LLC);

	fill_px(vm->dev, pdp, scratch_pdpe);
}

static void gen8_initialize_pml4(struct i915_address_space *vm,
				 struct i915_pml4 *pml4)
{
	gen8_ppgtt_pml4e_t scratch_pml4e;

	scratch_pml4e = gen8_pml4e_encode(px_dma(vm->scratch_pdp),
					  I915_CACHE_LLC);

	fill_px(vm->dev, pml4, scratch_pml4e);
}

static void
gen8_setup_page_directory(struct i915_hw_ppgtt *ppgtt,
			  struct i915_page_directory_pointer *pdp,
			  struct i915_page_directory *pd,
			  int index)
{
	gen8_ppgtt_pdpe_t *page_directorypo;

	if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
		return;

	page_directorypo = kmap_px(pdp);
	page_directorypo[index] = gen8_pdpe_encode(px_dma(pd), I915_CACHE_LLC);
	kunmap_px(ppgtt, page_directorypo);
}

static void
gen8_setup_page_directory_pointer(struct i915_hw_ppgtt *ppgtt,
				  struct i915_pml4 *pml4,
				  struct i915_page_directory_pointer *pdp,
				  int index)
{
	gen8_ppgtt_pml4e_t *pagemap = kmap_px(pml4);

	WARN_ON(!USES_FULL_48BIT_PPGTT(ppgtt->base.dev));
	pagemap[index] = gen8_pml4e_encode(px_dma(pdp), I915_CACHE_LLC);
	kunmap_px(ppgtt, pagemap);
}

/* Broadwell Page Directory Pointer Descriptors */
static int gen8_write_pdp(struct drm_i915_gem_request *req,
			  unsigned entry,
			  dma_addr_t addr)
{
	struct intel_ring *ring = req->ring;
	struct intel_engine_cs *engine = req->engine;
	int ret;

	BUG_ON(entry >= 4);

	ret = intel_ring_begin(req, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
	intel_ring_emit_reg(ring, GEN8_RING_PDP_UDW(engine, entry));
	intel_ring_emit(ring, upper_32_bits(addr));
	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
	intel_ring_emit_reg(ring, GEN8_RING_PDP_LDW(engine, entry));
	intel_ring_emit(ring, lower_32_bits(addr));
	intel_ring_advance(ring);

	return 0;
}

static int gen8_legacy_mm_switch(struct i915_hw_ppgtt *ppgtt,
				 struct drm_i915_gem_request *req)
{
	int i, ret;

	for (i = GEN8_LEGACY_PDPES - 1; i >= 0; i--) {
		const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);

		ret = gen8_write_pdp(req, i, pd_daddr);
		if (ret)
			return ret;
	}

	return 0;
}

static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt,
			      struct drm_i915_gem_request *req)
{
	return gen8_write_pdp(req, 0, px_dma(&ppgtt->pml4));
}

static void gen8_ppgtt_clear_pte_range(struct i915_address_space *vm,
				       struct i915_page_directory_pointer *pdp,
				       uint64_t start,
				       uint64_t length,
				       gen8_pte_t scratch_pte)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	gen8_pte_t *pt_vaddr;
	unsigned pdpe = gen8_pdpe_index(start);
	unsigned pde = gen8_pde_index(start);
	unsigned pte = gen8_pte_index(start);
	unsigned num_entries = length >> PAGE_SHIFT;
	unsigned last_pte, i;

	if (WARN_ON(!pdp))
		return;

	while (num_entries) {
		struct i915_page_directory *pd;
		struct i915_page_table *pt;

		if (WARN_ON(!pdp->page_directory[pdpe]))
			break;

		pd = pdp->page_directory[pdpe];

		if (WARN_ON(!pd->page_table[pde]))
			break;

		pt = pd->page_table[pde];

		if (WARN_ON(!px_page(pt)))
			break;

		last_pte = pte + num_entries;
		if (last_pte > GEN8_PTES)
			last_pte = GEN8_PTES;

		pt_vaddr = kmap_px(pt);

		for (i = pte; i < last_pte; i++) {
			pt_vaddr[i] = scratch_pte;
			num_entries--;
		}

		kunmap_px(ppgtt, pt_vaddr);

		pte = 0;
		if (++pde == I915_PDES) {
			if (++pdpe == I915_PDPES_PER_PDP(vm->dev))
				break;
			pde = 0;
		}
	}
}

static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
				   uint64_t start,
				   uint64_t length,
				   bool use_scratch)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
						 I915_CACHE_LLC, use_scratch);

	if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
		gen8_ppgtt_clear_pte_range(vm, &ppgtt->pdp, start, length,
					   scratch_pte);
	} else {
		uint64_t pml4e;
		struct i915_page_directory_pointer *pdp;

		gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, pml4e) {
			gen8_ppgtt_clear_pte_range(vm, pdp, start, length,
						   scratch_pte);
		}
	}
}

static void
gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm,
			      struct i915_page_directory_pointer *pdp,
			      struct sg_page_iter *sg_iter,
			      uint64_t start,
			      enum i915_cache_level cache_level)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	gen8_pte_t *pt_vaddr;
	unsigned pdpe = gen8_pdpe_index(start);
	unsigned pde = gen8_pde_index(start);
	unsigned pte = gen8_pte_index(start);

	pt_vaddr = NULL;

	while (__sg_page_iter_next(sg_iter)) {
		if (pt_vaddr == NULL) {
			struct i915_page_directory *pd = pdp->page_directory[pdpe];
			struct i915_page_table *pt = pd->page_table[pde];
			pt_vaddr = kmap_px(pt);
		}

		pt_vaddr[pte] =
			gen8_pte_encode(sg_page_iter_dma_address(sg_iter),
					cache_level, true);
		if (++pte == GEN8_PTES) {
			kunmap_px(ppgtt, pt_vaddr);
			pt_vaddr = NULL;
			if (++pde == I915_PDES) {
				if (++pdpe == I915_PDPES_PER_PDP(vm->dev))
					break;
				pde = 0;
			}
			pte = 0;
		}
	}

	if (pt_vaddr)
		kunmap_px(ppgtt, pt_vaddr);
}

static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
				      struct sg_table *pages,
				      uint64_t start,
				      enum i915_cache_level cache_level,
				      u32 unused)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	struct sg_page_iter sg_iter;

	__sg_page_iter_start(&sg_iter, pages->sgl, sg_nents(pages->sgl), 0);

	if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
		gen8_ppgtt_insert_pte_entries(vm, &ppgtt->pdp, &sg_iter, start,
					      cache_level);
	} else {
		struct i915_page_directory_pointer *pdp;
		uint64_t pml4e;
		uint64_t length = (uint64_t)pages->orig_nents << PAGE_SHIFT;

		gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, pml4e) {
			gen8_ppgtt_insert_pte_entries(vm, pdp, &sg_iter,
						      start, cache_level);
		}
	}
}

static void gen8_free_page_tables(struct drm_device *dev,
				  struct i915_page_directory *pd)
{
	int i;

	if (!px_page(pd))
		return;

	for_each_set_bit(i, pd->used_pdes, I915_PDES) {
		if (WARN_ON(!pd->page_table[i]))
			continue;

		free_pt(dev, pd->page_table[i]);
		pd->page_table[i] = NULL;
	}
}

static int gen8_init_scratch(struct i915_address_space *vm)
{
	struct drm_device *dev = vm->dev;
	int ret;

	ret = setup_scratch_page(dev, &vm->scratch_page, I915_GFP_DMA);
	if (ret)
		return ret;

	vm->scratch_pt = alloc_pt(dev);
	if (IS_ERR(vm->scratch_pt)) {
		ret = PTR_ERR(vm->scratch_pt);
		goto free_scratch_page;
	}

	vm->scratch_pd = alloc_pd(dev);
	if (IS_ERR(vm->scratch_pd)) {
		ret = PTR_ERR(vm->scratch_pd);
		goto free_pt;
	}

	if (USES_FULL_48BIT_PPGTT(dev)) {
		vm->scratch_pdp = alloc_pdp(dev);
		if (IS_ERR(vm->scratch_pdp)) {
			ret = PTR_ERR(vm->scratch_pdp);
			goto free_pd;
		}
	}

	gen8_initialize_pt(vm, vm->scratch_pt);
	gen8_initialize_pd(vm, vm->scratch_pd);
	if (USES_FULL_48BIT_PPGTT(dev))
		gen8_initialize_pdp(vm, vm->scratch_pdp);

	return 0;

free_pd:
	free_pd(dev, vm->scratch_pd);
free_pt:
	free_pt(dev, vm->scratch_pt);
free_scratch_page:
	cleanup_scratch_page(dev, &vm->scratch_page);

	return ret;
}

static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
{
	enum vgt_g2v_type msg;
	struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
	int i;

	if (USES_FULL_48BIT_PPGTT(dev_priv)) {
		u64 daddr = px_dma(&ppgtt->pml4);

		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
		I915_WRITE(vgtif_reg(pdp[0].hi), upper_32_bits(daddr));

		msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
				VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY);
	} else {
		for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
			u64 daddr = i915_page_dir_dma_addr(ppgtt, i);

			I915_WRITE(vgtif_reg(pdp[i].lo), lower_32_bits(daddr));
			I915_WRITE(vgtif_reg(pdp[i].hi), upper_32_bits(daddr));
		}

		msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
				VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
	}

	I915_WRITE(vgtif_reg(g2v_notify), msg);

	return 0;
}

static void gen8_free_scratch(struct i915_address_space *vm)
{
	struct drm_device *dev = vm->dev;

	if (USES_FULL_48BIT_PPGTT(dev))
		free_pdp(dev, vm->scratch_pdp);
	free_pd(dev, vm->scratch_pd);
	free_pt(dev, vm->scratch_pt);
	cleanup_scratch_page(dev, &vm->scratch_page);
}

static void gen8_ppgtt_cleanup_3lvl(struct drm_device *dev,
				    struct i915_page_directory_pointer *pdp)
{
	int i;

	for_each_set_bit(i, pdp->used_pdpes, I915_PDPES_PER_PDP(dev)) {
		if (WARN_ON(!pdp->page_directory[i]))
			continue;

		gen8_free_page_tables(dev, pdp->page_directory[i]);
		free_pd(dev, pdp->page_directory[i]);
	}

	free_pdp(dev, pdp);
}

static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt)
{
	int i;

	for_each_set_bit(i, ppgtt->pml4.used_pml4es, GEN8_PML4ES_PER_PML4) {
		if (WARN_ON(!ppgtt->pml4.pdps[i]))
			continue;

		gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, ppgtt->pml4.pdps[i]);
	}

	cleanup_px(ppgtt->base.dev, &ppgtt->pml4);
}

static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);

	if (intel_vgpu_active(to_i915(vm->dev)))
		gen8_ppgtt_notify_vgt(ppgtt, false);

	if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
		gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, &ppgtt->pdp);
	else
		gen8_ppgtt_cleanup_4lvl(ppgtt);

	gen8_free_scratch(vm);
}

/**
 * gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range.
 * @vm:	Master vm structure.
 * @pd:	Page directory for this address range.
 * @start:	Starting virtual address to begin allocations.
 * @length:	Size of the allocations.
 * @new_pts:	Bitmap set by function with new allocations. Likely used by the
 *		caller to free on error.
 *
 * Allocate the required number of page tables. Extremely similar to
 * gen8_ppgtt_alloc_page_directories(). The main difference is here we are limited by
 * the page directory boundary (instead of the page directory pointer). That
 * boundary is 1GB virtual. Therefore, unlike gen8_ppgtt_alloc_page_directories(), it is
 * possible, and likely that the caller will need to use multiple calls of this
 * function to achieve the appropriate allocation.
 *
 * Return: 0 if success; negative error code otherwise.
 */
static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,
				     struct i915_page_directory *pd,
				     uint64_t start,
				     uint64_t length,
				     unsigned long *new_pts)
{
	struct drm_device *dev = vm->dev;
	struct i915_page_table *pt;
	uint32_t pde;

	gen8_for_each_pde(pt, pd, start, length, pde) {
		/* Don't reallocate page tables */
		if (test_bit(pde, pd->used_pdes)) {
			/* Scratch is never allocated this way */
			WARN_ON(pt == vm->scratch_pt);
			continue;
		}

		pt = alloc_pt(dev);
		if (IS_ERR(pt))
			goto unwind_out;

		gen8_initialize_pt(vm, pt);
		pd->page_table[pde] = pt;
		__set_bit(pde, new_pts);
		trace_i915_page_table_entry_alloc(vm, pde, start, GEN8_PDE_SHIFT);
	}

	return 0;

unwind_out:
	for_each_set_bit(pde, new_pts, I915_PDES)
		free_pt(dev, pd->page_table[pde]);

	return -ENOMEM;
}

/**
 * gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range.
 * @vm:	Master vm structure.
 * @pdp:	Page directory pointer for this address range.
 * @start:	Starting virtual address to begin allocations.
 * @length:	Size of the allocations.
 * @new_pds:	Bitmap set by function with new allocations. Likely used by the
 *		caller to free on error.
 *
 * Allocate the required number of page directories starting at the pde index of
 * @start, and ending at the pde index @start + @length. This function will skip
 * over already allocated page directories within the range, and only allocate
 * new ones, setting the appropriate pointer within the pdp as well as the
 * correct position in the bitmap @new_pds.
 *
 * The function will only allocate the pages within the range for a give page
 * directory pointer. In other words, if @start + @length straddles a virtually
 * addressed PDP boundary (512GB for 4k pages), there will be more allocations
 * required by the caller, This is not currently possible, and the BUG in the
 * code will prevent it.
 *
 * Return: 0 if success; negative error code otherwise.
 */
static int
gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,
				  struct i915_page_directory_pointer *pdp,
				  uint64_t start,
				  uint64_t length,
				  unsigned long *new_pds)
{
	struct drm_device *dev = vm->dev;
	struct i915_page_directory *pd;
	uint32_t pdpe;
	uint32_t pdpes = I915_PDPES_PER_PDP(dev);

	WARN_ON(!bitmap_empty(new_pds, pdpes));

	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
		if (test_bit(pdpe, pdp->used_pdpes))
			continue;

		pd = alloc_pd(dev);
		if (IS_ERR(pd))
			goto unwind_out;

		gen8_initialize_pd(vm, pd);
		pdp->page_directory[pdpe] = pd;
		__set_bit(pdpe, new_pds);
		trace_i915_page_directory_entry_alloc(vm, pdpe, start, GEN8_PDPE_SHIFT);
	}

	return 0;

unwind_out:
	for_each_set_bit(pdpe, new_pds, pdpes)
		free_pd(dev, pdp->page_directory[pdpe]);

	return -ENOMEM;
}

/**
 * gen8_ppgtt_alloc_page_dirpointers() - Allocate pdps for VA range.
 * @vm:	Master vm structure.
 * @pml4:	Page map level 4 for this address range.
 * @start:	Starting virtual address to begin allocations.
 * @length:	Size of the allocations.
 * @new_pdps:	Bitmap set by function with new allocations. Likely used by the
 *		caller to free on error.
 *
 * Allocate the required number of page directory pointers. Extremely similar to
 * gen8_ppgtt_alloc_page_directories() and gen8_ppgtt_alloc_pagetabs().
 * The main difference is here we are limited by the pml4 boundary (instead of
 * the page directory pointer).
 *
 * Return: 0 if success; negative error code otherwise.
 */
static int
gen8_ppgtt_alloc_page_dirpointers(struct i915_address_space *vm,
				  struct i915_pml4 *pml4,
				  uint64_t start,
				  uint64_t length,
				  unsigned long *new_pdps)
{
	struct drm_device *dev = vm->dev;
	struct i915_page_directory_pointer *pdp;
	uint32_t pml4e;

	WARN_ON(!bitmap_empty(new_pdps, GEN8_PML4ES_PER_PML4));

	gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
		if (!test_bit(pml4e, pml4->used_pml4es)) {
			pdp = alloc_pdp(dev);
			if (IS_ERR(pdp))
				goto unwind_out;

			gen8_initialize_pdp(vm, pdp);
			pml4->pdps[pml4e] = pdp;
			__set_bit(pml4e, new_pdps);
			trace_i915_page_directory_pointer_entry_alloc(vm,
								      pml4e,
								      start,
								      GEN8_PML4E_SHIFT);
		}
	}

	return 0;

unwind_out:
	for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4)
		free_pdp(dev, pml4->pdps[pml4e]);

	return -ENOMEM;
}

static void
free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long *new_pts)
{
	kfree(new_pts);
	kfree(new_pds);
}

/* Fills in the page directory bitmap, and the array of page tables bitmap. Both
 * of these are based on the number of PDPEs in the system.
 */
static
int __must_check alloc_gen8_temp_bitmaps(unsigned long **new_pds,
					 unsigned long **new_pts,
					 uint32_t pdpes)
{
	unsigned long *pds;
	unsigned long *pts;

	pds = kcalloc(BITS_TO_LONGS(pdpes), sizeof(unsigned long), GFP_TEMPORARY);
	if (!pds)
		return -ENOMEM;

	pts = kcalloc(pdpes, BITS_TO_LONGS(I915_PDES) * sizeof(unsigned long),
		      GFP_TEMPORARY);
	if (!pts)
		goto err_out;

	*new_pds = pds;
	*new_pts = pts;

	return 0;

err_out:
	free_gen8_temp_bitmaps(pds, pts);
	return -ENOMEM;
}

/* PDE TLBs are a pain to invalidate on GEN8+. When we modify
 * the page table structures, we mark them dirty so that
 * context switching/execlist queuing code takes extra steps
 * to ensure that tlbs are flushed.
 */
static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
{
	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask;
}

static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,
				    struct i915_page_directory_pointer *pdp,
				    uint64_t start,
				    uint64_t length)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	unsigned long *new_page_dirs, *new_page_tables;
	struct drm_device *dev = vm->dev;
	struct i915_page_directory *pd;
	const uint64_t orig_start = start;
	const uint64_t orig_length = length;
	uint32_t pdpe;
	uint32_t pdpes = I915_PDPES_PER_PDP(dev);
	int ret;

	/* Wrap is never okay since we can only represent 48b, and we don't
	 * actually use the other side of the canonical address space.
	 */
	if (WARN_ON(start + length < start))
		return -ENODEV;

	if (WARN_ON(start + length > vm->total))
		return -ENODEV;

	ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes);
	if (ret)
		return ret;

	/* Do the allocations first so we can easily bail out */
	ret = gen8_ppgtt_alloc_page_directories(vm, pdp, start, length,
						new_page_dirs);
	if (ret) {
		free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
		return ret;
	}

	/* For every page directory referenced, allocate page tables */
	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
		ret = gen8_ppgtt_alloc_pagetabs(vm, pd, start, length,
						new_page_tables + pdpe * BITS_TO_LONGS(I915_PDES));
		if (ret)
			goto err_out;
	}

	start = orig_start;
	length = orig_length;

	/* Allocations have completed successfully, so set the bitmaps, and do
	 * the mappings. */
	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
		gen8_pde_t *const page_directory = kmap_px(pd);
		struct i915_page_table *pt;
		uint64_t pd_len = length;
		uint64_t pd_start = start;
		uint32_t pde;

		/* Every pd should be allocated, we just did that above. */
		WARN_ON(!pd);

		gen8_for_each_pde(pt, pd, pd_start, pd_len, pde) {
			/* Same reasoning as pd */
			WARN_ON(!pt);
			WARN_ON(!pd_len);
			WARN_ON(!gen8_pte_count(pd_start, pd_len));

			/* Set our used ptes within the page table */
			bitmap_set(pt->used_ptes,
				   gen8_pte_index(pd_start),
				   gen8_pte_count(pd_start, pd_len));

			/* Our pde is now pointing to the pagetable, pt */
			__set_bit(pde, pd->used_pdes);

			/* Map the PDE to the page table */
			page_directory[pde] = gen8_pde_encode(px_dma(pt),
							      I915_CACHE_LLC);
			trace_i915_page_table_entry_map(&ppgtt->base, pde, pt,
							gen8_pte_index(start),
							gen8_pte_count(start, length),
							GEN8_PTES);

			/* NB: We haven't yet mapped ptes to pages. At this
			 * point we're still relying on insert_entries() */
		}

		kunmap_px(ppgtt, page_directory);
		__set_bit(pdpe, pdp->used_pdpes);
		gen8_setup_page_directory(ppgtt, pdp, pd, pdpe);
	}

	free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
	mark_tlbs_dirty(ppgtt);
	return 0;

err_out:
	while (pdpe--) {
		unsigned long temp;

		for_each_set_bit(temp, new_page_tables + pdpe *
				BITS_TO_LONGS(I915_PDES), I915_PDES)
			free_pt(dev, pdp->page_directory[pdpe]->page_table[temp]);
	}

	for_each_set_bit(pdpe, new_page_dirs, pdpes)
		free_pd(dev, pdp->page_directory[pdpe]);

	free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
	mark_tlbs_dirty(ppgtt);
	return ret;
}

static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm,
				    struct i915_pml4 *pml4,
				    uint64_t start,
				    uint64_t length)
{
	DECLARE_BITMAP(new_pdps, GEN8_PML4ES_PER_PML4);
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	struct i915_page_directory_pointer *pdp;
	uint64_t pml4e;
	int ret = 0;

	/* Do the pml4 allocations first, so we don't need to track the newly
	 * allocated tables below the pdp */
	bitmap_zero(new_pdps, GEN8_PML4ES_PER_PML4);

	/* The pagedirectory and pagetable allocations are done in the shared 3
	 * and 4 level code. Just allocate the pdps.
	 */
	ret = gen8_ppgtt_alloc_page_dirpointers(vm, pml4, start, length,
						new_pdps);
	if (ret)
		return ret;

	WARN(bitmap_weight(new_pdps, GEN8_PML4ES_PER_PML4) > 2,
	     "The allocation has spanned more than 512GB. "
	     "It is highly likely this is incorrect.");

	gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
		WARN_ON(!pdp);

		ret = gen8_alloc_va_range_3lvl(vm, pdp, start, length);
		if (ret)
			goto err_out;

		gen8_setup_page_directory_pointer(ppgtt, pml4, pdp, pml4e);
	}

	bitmap_or(pml4->used_pml4es, new_pdps, pml4->used_pml4es,
		  GEN8_PML4ES_PER_PML4);

	return 0;

err_out:
	for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4)
		gen8_ppgtt_cleanup_3lvl(vm->dev, pml4->pdps[pml4e]);

	return ret;
}

static int gen8_alloc_va_range(struct i915_address_space *vm,
			       uint64_t start, uint64_t length)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);

	if (USES_FULL_48BIT_PPGTT(vm->dev))
		return gen8_alloc_va_range_4lvl(vm, &ppgtt->pml4, start, length);
	else
		return gen8_alloc_va_range_3lvl(vm, &ppgtt->pdp, start, length);
}

static void gen8_dump_pdp(struct i915_page_directory_pointer *pdp,
			  uint64_t start, uint64_t length,
			  gen8_pte_t scratch_pte,
			  struct seq_file *m)
{
	struct i915_page_directory *pd;
	uint32_t pdpe;

	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
		struct i915_page_table *pt;
		uint64_t pd_len = length;
		uint64_t pd_start = start;
		uint32_t pde;

		if (!test_bit(pdpe, pdp->used_pdpes))
			continue;

		seq_printf(m, "\tPDPE #%d\n", pdpe);
		gen8_for_each_pde(pt, pd, pd_start, pd_len, pde) {
			uint32_t  pte;
			gen8_pte_t *pt_vaddr;

			if (!test_bit(pde, pd->used_pdes))
				continue;

			pt_vaddr = kmap_px(pt);
			for (pte = 0; pte < GEN8_PTES; pte += 4) {
				uint64_t va =
					(pdpe << GEN8_PDPE_SHIFT) |
					(pde << GEN8_PDE_SHIFT) |
					(pte << GEN8_PTE_SHIFT);
				int i;
				bool found = false;

				for (i = 0; i < 4; i++)
					if (pt_vaddr[pte + i] != scratch_pte)
						found = true;
				if (!found)
					continue;

				seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte);
				for (i = 0; i < 4; i++) {
					if (pt_vaddr[pte + i] != scratch_pte)
						seq_printf(m, " %llx", pt_vaddr[pte + i]);
					else
						seq_puts(m, "  SCRATCH ");
				}
				seq_puts(m, "\n");
			}
			/* don't use kunmap_px, it could trigger
			 * an unnecessary flush.
			 */
			kunmap_atomic(pt_vaddr);
		}
	}
}

static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
{
	struct i915_address_space *vm = &ppgtt->base;
	uint64_t start = ppgtt->base.start;
	uint64_t length = ppgtt->base.total;
	gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
						 I915_CACHE_LLC, true);

	if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
		gen8_dump_pdp(&ppgtt->pdp, start, length, scratch_pte, m);
	} else {
		uint64_t pml4e;
		struct i915_pml4 *pml4 = &ppgtt->pml4;
		struct i915_page_directory_pointer *pdp;

		gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
			if (!test_bit(pml4e, pml4->used_pml4es))
				continue;

			seq_printf(m, "    PML4E #%llu\n", pml4e);
			gen8_dump_pdp(pdp, start, length, scratch_pte, m);
		}
	}
}

static int gen8_preallocate_top_level_pdps(struct i915_hw_ppgtt *ppgtt)
{
	unsigned long *new_page_dirs, *new_page_tables;
	uint32_t pdpes = I915_PDPES_PER_PDP(dev);
	int ret;

	/* We allocate temp bitmap for page tables for no gain
	 * but as this is for init only, lets keep the things simple
	 */
	ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes);
	if (ret)
		return ret;

	/* Allocate for all pdps regardless of how the ppgtt
	 * was defined.
	 */
	ret = gen8_ppgtt_alloc_page_directories(&ppgtt->base, &ppgtt->pdp,
						0, 1ULL << 32,
						new_page_dirs);
	if (!ret)
		*ppgtt->pdp.used_pdpes = *new_page_dirs;

	free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);

	return ret;
}

/*
 * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
 * with a net effect resembling a 2-level page table in normal x86 terms. Each
 * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
 * space.
 *
 */
static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
	int ret;

	ret = gen8_init_scratch(&ppgtt->base);
	if (ret)
		return ret;

	ppgtt->base.start = 0;
	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
	ppgtt->base.allocate_va_range = gen8_alloc_va_range;
	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
	ppgtt->base.bind_vma = ppgtt_bind_vma;
	ppgtt->debug_dump = gen8_dump_ppgtt;

	if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
		ret = setup_px(ppgtt->base.dev, &ppgtt->pml4);
		if (ret)
			goto free_scratch;

		gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4);

		ppgtt->base.total = 1ULL << 48;
		ppgtt->switch_mm = gen8_48b_mm_switch;
	} else {
		ret = __pdp_init(ppgtt->base.dev, &ppgtt->pdp);
		if (ret)
			goto free_scratch;

		ppgtt->base.total = 1ULL << 32;
		ppgtt->switch_mm = gen8_legacy_mm_switch;
		trace_i915_page_directory_pointer_entry_alloc(&ppgtt->base,
							      0, 0,
							      GEN8_PML4E_SHIFT);

		if (intel_vgpu_active(to_i915(ppgtt->base.dev))) {
			ret = gen8_preallocate_top_level_pdps(ppgtt);
			if (ret)
				goto free_scratch;
		}
	}

	if (intel_vgpu_active(to_i915(ppgtt->base.dev)))
		gen8_ppgtt_notify_vgt(ppgtt, true);

	return 0;

free_scratch:
	gen8_free_scratch(&ppgtt->base);
	return ret;
}

static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
{
	struct i915_address_space *vm = &ppgtt->base;
	struct i915_page_table *unused;
	gen6_pte_t scratch_pte;
	uint32_t pd_entry;
	uint32_t  pte, pde;
	uint32_t start = ppgtt->base.start, length = ppgtt->base.total;

	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
				     I915_CACHE_LLC, true, 0);

	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) {
		u32 expected;
		gen6_pte_t *pt_vaddr;
		const dma_addr_t pt_addr = px_dma(ppgtt->pd.page_table[pde]);
		pd_entry = readl(ppgtt->pd_addr + pde);
		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);

		if (pd_entry != expected)
			seq_printf(m, "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
				   pde,
				   pd_entry,
				   expected);
		seq_printf(m, "\tPDE: %x\n", pd_entry);

		pt_vaddr = kmap_px(ppgtt->pd.page_table[pde]);

		for (pte = 0; pte < GEN6_PTES; pte+=4) {
			unsigned long va =
				(pde * PAGE_SIZE * GEN6_PTES) +
				(pte * PAGE_SIZE);
			int i;
			bool found = false;
			for (i = 0; i < 4; i++)
				if (pt_vaddr[pte + i] != scratch_pte)
					found = true;
			if (!found)
				continue;

			seq_printf(m, "\t\t0x%lx [%03d,%04d]: =", va, pde, pte);
			for (i = 0; i < 4; i++) {
				if (pt_vaddr[pte + i] != scratch_pte)
					seq_printf(m, " %08x", pt_vaddr[pte + i]);
				else
					seq_puts(m, "  SCRATCH ");
			}
			seq_puts(m, "\n");
		}
		kunmap_px(ppgtt, pt_vaddr);
	}
}

/* Write pde (index) from the page directory @pd to the page table @pt */
static void gen6_write_pde(struct i915_page_directory *pd,
			    const int pde, struct i915_page_table *pt)
{
	/* Caller needs to make sure the write completes if necessary */
	struct i915_hw_ppgtt *ppgtt =
		container_of(pd, struct i915_hw_ppgtt, pd);
	u32 pd_entry;

	pd_entry = GEN6_PDE_ADDR_ENCODE(px_dma(pt));
	pd_entry |= GEN6_PDE_VALID;

	writel(pd_entry, ppgtt->pd_addr + pde);
}

/* Write all the page tables found in the ppgtt structure to incrementing page
 * directories. */
static void gen6_write_page_range(struct drm_i915_private *dev_priv,
				  struct i915_page_directory *pd,
				  uint32_t start, uint32_t length)
{
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	struct i915_page_table *pt;
	uint32_t pde;

	gen6_for_each_pde(pt, pd, start, length, pde)
		gen6_write_pde(pd, pde, pt);

	/* Make sure write is complete before other code can use this page
	 * table. Also require for WC mapped PTEs */
	readl(ggtt->gsm);
}

static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
{
	BUG_ON(ppgtt->pd.base.ggtt_offset & 0x3f);

	return (ppgtt->pd.base.ggtt_offset / 64) << 16;
}

static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
			 struct drm_i915_gem_request *req)
{
	struct intel_ring *ring = req->ring;
	struct intel_engine_cs *engine = req->engine;
	int ret;

	/* NB: TLBs must be flushed and invalidated before a switch */
	ret = engine->emit_flush(req, EMIT_INVALIDATE | EMIT_FLUSH);
	if (ret)
		return ret;

	ret = intel_ring_begin(req, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
	intel_ring_emit_reg(ring, RING_PP_DIR_DCLV(engine));
	intel_ring_emit(ring, PP_DIR_DCLV_2G);
	intel_ring_emit_reg(ring, RING_PP_DIR_BASE(engine));
	intel_ring_emit(ring, get_pd_offset(ppgtt));
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
			  struct drm_i915_gem_request *req)
{
	struct intel_ring *ring = req->ring;
	struct intel_engine_cs *engine = req->engine;
	int ret;

	/* NB: TLBs must be flushed and invalidated before a switch */
	ret = engine->emit_flush(req, EMIT_INVALIDATE | EMIT_FLUSH);
	if (ret)
		return ret;

	ret = intel_ring_begin(req, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
	intel_ring_emit_reg(ring, RING_PP_DIR_DCLV(engine));
	intel_ring_emit(ring, PP_DIR_DCLV_2G);
	intel_ring_emit_reg(ring, RING_PP_DIR_BASE(engine));
	intel_ring_emit(ring, get_pd_offset(ppgtt));
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	/* XXX: RCS is the only one to auto invalidate the TLBs? */
	if (engine->id != RCS) {
		ret = engine->emit_flush(req, EMIT_INVALIDATE | EMIT_FLUSH);
		if (ret)
			return ret;
	}

	return 0;
}

static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
			  struct drm_i915_gem_request *req)
{
	struct intel_engine_cs *engine = req->engine;
	struct drm_i915_private *dev_priv = req->i915;

	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
	return 0;
}

static void gen8_ppgtt_enable(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_engine_cs *engine;

	for_each_engine(engine, dev_priv) {
		u32 four_level = USES_FULL_48BIT_PPGTT(dev) ? GEN8_GFX_PPGTT_48B : 0;
		I915_WRITE(RING_MODE_GEN7(engine),
			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE | four_level));
	}
}

static void gen7_ppgtt_enable(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_engine_cs *engine;
	uint32_t ecochk, ecobits;

	ecobits = I915_READ(GAC_ECO_BITS);
	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);

	ecochk = I915_READ(GAM_ECOCHK);
	if (IS_HASWELL(dev)) {
		ecochk |= ECOCHK_PPGTT_WB_HSW;
	} else {
		ecochk |= ECOCHK_PPGTT_LLC_IVB;
		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
	}
	I915_WRITE(GAM_ECOCHK, ecochk);

	for_each_engine(engine, dev_priv) {
		/* GFX_MODE is per-ring on gen7+ */
		I915_WRITE(RING_MODE_GEN7(engine),
			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
	}
}

static void gen6_ppgtt_enable(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	uint32_t ecochk, gab_ctl, ecobits;

	ecobits = I915_READ(GAC_ECO_BITS);
	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_SNB_BIT |
		   ECOBITS_PPGTT_CACHE64B);

	gab_ctl = I915_READ(GAB_CTL);
	I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);

	ecochk = I915_READ(GAM_ECOCHK);
	I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);

	I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
}

/* PPGTT support for Sandybdrige/Gen6 and later */
static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
				   uint64_t start,
				   uint64_t length,
				   bool use_scratch)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	gen6_pte_t *pt_vaddr, scratch_pte;
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	unsigned act_pt = first_entry / GEN6_PTES;
	unsigned first_pte = first_entry % GEN6_PTES;
	unsigned last_pte, i;

	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
				     I915_CACHE_LLC, true, 0);

	while (num_entries) {
		last_pte = first_pte + num_entries;
		if (last_pte > GEN6_PTES)
			last_pte = GEN6_PTES;

		pt_vaddr = kmap_px(ppgtt->pd.page_table[act_pt]);

		for (i = first_pte; i < last_pte; i++)
			pt_vaddr[i] = scratch_pte;

		kunmap_px(ppgtt, pt_vaddr);

		num_entries -= last_pte - first_pte;
		first_pte = 0;
		act_pt++;
	}
}

static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
				      struct sg_table *pages,
				      uint64_t start,
				      enum i915_cache_level cache_level, u32 flags)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned act_pt = first_entry / GEN6_PTES;
	unsigned act_pte = first_entry % GEN6_PTES;
	gen6_pte_t *pt_vaddr = NULL;
	struct sgt_iter sgt_iter;
	dma_addr_t addr;

	for_each_sgt_dma(addr, sgt_iter, pages) {
		if (pt_vaddr == NULL)
			pt_vaddr = kmap_px(ppgtt->pd.page_table[act_pt]);

		pt_vaddr[act_pte] =
			vm->pte_encode(addr, cache_level, true, flags);

		if (++act_pte == GEN6_PTES) {
			kunmap_px(ppgtt, pt_vaddr);
			pt_vaddr = NULL;
			act_pt++;
			act_pte = 0;
		}
	}

	if (pt_vaddr)
		kunmap_px(ppgtt, pt_vaddr);
}

static int gen6_alloc_va_range(struct i915_address_space *vm,
			       uint64_t start_in, uint64_t length_in)
{
	DECLARE_BITMAP(new_page_tables, I915_PDES);
	struct drm_device *dev = vm->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	struct i915_page_table *pt;
	uint32_t start, length, start_save, length_save;
	uint32_t pde;
	int ret;

	if (WARN_ON(start_in + length_in > ppgtt->base.total))
		return -ENODEV;

	start = start_save = start_in;
	length = length_save = length_in;

	bitmap_zero(new_page_tables, I915_PDES);

	/* The allocation is done in two stages so that we can bail out with
	 * minimal amount of pain. The first stage finds new page tables that
	 * need allocation. The second stage marks use ptes within the page
	 * tables.
	 */
	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
		if (pt != vm->scratch_pt) {
			WARN_ON(bitmap_empty(pt->used_ptes, GEN6_PTES));
			continue;
		}

		/* We've already allocated a page table */
		WARN_ON(!bitmap_empty(pt->used_ptes, GEN6_PTES));

		pt = alloc_pt(dev);
		if (IS_ERR(pt)) {
			ret = PTR_ERR(pt);
			goto unwind_out;
		}

		gen6_initialize_pt(vm, pt);

		ppgtt->pd.page_table[pde] = pt;
		__set_bit(pde, new_page_tables);
		trace_i915_page_table_entry_alloc(vm, pde, start, GEN6_PDE_SHIFT);
	}

	start = start_save;
	length = length_save;

	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
		DECLARE_BITMAP(tmp_bitmap, GEN6_PTES);

		bitmap_zero(tmp_bitmap, GEN6_PTES);
		bitmap_set(tmp_bitmap, gen6_pte_index(start),
			   gen6_pte_count(start, length));

		if (__test_and_clear_bit(pde, new_page_tables))
			gen6_write_pde(&ppgtt->pd, pde, pt);

		trace_i915_page_table_entry_map(vm, pde, pt,
					 gen6_pte_index(start),
					 gen6_pte_count(start, length),
					 GEN6_PTES);
		bitmap_or(pt->used_ptes, tmp_bitmap, pt->used_ptes,
				GEN6_PTES);
	}

	WARN_ON(!bitmap_empty(new_page_tables, I915_PDES));

	/* Make sure write is complete before other code can use this page
	 * table. Also require for WC mapped PTEs */
	readl(ggtt->gsm);

	mark_tlbs_dirty(ppgtt);
	return 0;

unwind_out:
	for_each_set_bit(pde, new_page_tables, I915_PDES) {
		struct i915_page_table *pt = ppgtt->pd.page_table[pde];

		ppgtt->pd.page_table[pde] = vm->scratch_pt;
		free_pt(vm->dev, pt);
	}

	mark_tlbs_dirty(ppgtt);
	return ret;
}

static int gen6_init_scratch(struct i915_address_space *vm)
{
	struct drm_device *dev = vm->dev;
	int ret;

	ret = setup_scratch_page(dev, &vm->scratch_page, I915_GFP_DMA);
	if (ret)
		return ret;

	vm->scratch_pt = alloc_pt(dev);
	if (IS_ERR(vm->scratch_pt)) {
		cleanup_scratch_page(dev, &vm->scratch_page);
		return PTR_ERR(vm->scratch_pt);
	}

	gen6_initialize_pt(vm, vm->scratch_pt);

	return 0;
}

static void gen6_free_scratch(struct i915_address_space *vm)
{
	struct drm_device *dev = vm->dev;

	free_pt(dev, vm->scratch_pt);
	cleanup_scratch_page(dev, &vm->scratch_page);
}

static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
{
	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
	struct i915_page_directory *pd = &ppgtt->pd;
	struct drm_device *dev = vm->dev;
	struct i915_page_table *pt;
	uint32_t pde;

	drm_mm_remove_node(&ppgtt->node);

	gen6_for_all_pdes(pt, pd, pde)
		if (pt != vm->scratch_pt)
			free_pt(dev, pt);

	gen6_free_scratch(vm);
}

static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
{
	struct i915_address_space *vm = &ppgtt->base;
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	bool retried = false;
	int ret;

	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
	 * allocator works in address space sizes, so it's multiplied by page
	 * size. We allocate at the top of the GTT to avoid fragmentation.
	 */
	BUG_ON(!drm_mm_initialized(&ggtt->base.mm));

	ret = gen6_init_scratch(vm);
	if (ret)
		return ret;

alloc:
	ret = drm_mm_insert_node_in_range_generic(&ggtt->base.mm,
						  &ppgtt->node, GEN6_PD_SIZE,
						  GEN6_PD_ALIGN, 0,
						  0, ggtt->base.total,
						  DRM_MM_TOPDOWN);
	if (ret == -ENOSPC && !retried) {
		ret = i915_gem_evict_something(&ggtt->base,
					       GEN6_PD_SIZE, GEN6_PD_ALIGN,
					       I915_CACHE_NONE,
					       0, ggtt->base.total,
					       0);
		if (ret)
			goto err_out;

		retried = true;
		goto alloc;
	}

	if (ret)
		goto err_out;


	if (ppgtt->node.start < ggtt->mappable_end)
		DRM_DEBUG("Forced to use aperture for PDEs\n");

	return 0;

err_out:
	gen6_free_scratch(vm);
	return ret;
}

static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
{
	return gen6_ppgtt_allocate_page_directories(ppgtt);
}

static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
				  uint64_t start, uint64_t length)
{
	struct i915_page_table *unused;
	uint32_t pde;

	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde)
		ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt;
}

static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	int ret;

	ppgtt->base.pte_encode = ggtt->base.pte_encode;
	if (intel_vgpu_active(dev_priv) || IS_GEN6(dev))
		ppgtt->switch_mm = gen6_mm_switch;
	else if (IS_HASWELL(dev))
		ppgtt->switch_mm = hsw_mm_switch;
	else if (IS_GEN7(dev))
		ppgtt->switch_mm = gen7_mm_switch;
	else
		BUG();

	ret = gen6_ppgtt_alloc(ppgtt);
	if (ret)
		return ret;

	ppgtt->base.allocate_va_range = gen6_alloc_va_range;
	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
	ppgtt->base.bind_vma = ppgtt_bind_vma;
	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
	ppgtt->base.start = 0;
	ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
	ppgtt->debug_dump = gen6_dump_ppgtt;

	ppgtt->pd.base.ggtt_offset =
		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);

	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm +
		ppgtt->pd.base.ggtt_offset / sizeof(gen6_pte_t);

	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);

	gen6_write_page_range(dev_priv, &ppgtt->pd, 0, ppgtt->base.total);

	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
			 ppgtt->node.size >> 20,
			 ppgtt->node.start / PAGE_SIZE);

	DRM_DEBUG("Adding PPGTT at offset %x\n",
		  ppgtt->pd.base.ggtt_offset << 10);

	return 0;
}

static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
			   struct drm_i915_private *dev_priv)
{
	ppgtt->base.dev = &dev_priv->drm;

	if (INTEL_INFO(dev_priv)->gen < 8)
		return gen6_ppgtt_init(ppgtt);
	else
		return gen8_ppgtt_init(ppgtt);
}

static void i915_address_space_init(struct i915_address_space *vm,
				    struct drm_i915_private *dev_priv)
{
	drm_mm_init(&vm->mm, vm->start, vm->total);
	INIT_LIST_HEAD(&vm->active_list);
	INIT_LIST_HEAD(&vm->inactive_list);
	INIT_LIST_HEAD(&vm->unbound_list);
	list_add_tail(&vm->global_link, &dev_priv->vm_list);
}

static void gtt_write_workarounds(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);

	/* This function is for gtt related workarounds. This function is
	 * called on driver load and after a GPU reset, so you can place
	 * workarounds here even if they get overwritten by GPU reset.
	 */
	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt */
	if (IS_BROADWELL(dev))
		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
	else if (IS_CHERRYVIEW(dev))
		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
	else if (IS_SKYLAKE(dev))
		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
	else if (IS_BROXTON(dev))
		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
}

static int i915_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
			   struct drm_i915_private *dev_priv,
			   struct drm_i915_file_private *file_priv)
{
	int ret;

	ret = __hw_ppgtt_init(ppgtt, dev_priv);
	if (ret == 0) {
		kref_init(&ppgtt->ref);
		i915_address_space_init(&ppgtt->base, dev_priv);
		ppgtt->base.file = file_priv;
	}

	return ret;
}

int i915_ppgtt_init_hw(struct drm_device *dev)
{
	gtt_write_workarounds(dev);

	/* In the case of execlists, PPGTT is enabled by the context descriptor
	 * and the PDPs are contained within the context itself.  We don't
	 * need to do anything here. */
	if (i915.enable_execlists)
		return 0;

	if (!USES_PPGTT(dev))
		return 0;

	if (IS_GEN6(dev))
		gen6_ppgtt_enable(dev);
	else if (IS_GEN7(dev))
		gen7_ppgtt_enable(dev);
	else if (INTEL_INFO(dev)->gen >= 8)
		gen8_ppgtt_enable(dev);
	else
		MISSING_CASE(INTEL_INFO(dev)->gen);

	return 0;
}

struct i915_hw_ppgtt *
i915_ppgtt_create(struct drm_i915_private *dev_priv,
		  struct drm_i915_file_private *fpriv)
{
	struct i915_hw_ppgtt *ppgtt;
	int ret;

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

	ret = i915_ppgtt_init(ppgtt, dev_priv, fpriv);
	if (ret) {
		kfree(ppgtt);
		return ERR_PTR(ret);
	}

	trace_i915_ppgtt_create(&ppgtt->base);

	return ppgtt;
}

void  i915_ppgtt_release(struct kref *kref)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(kref, struct i915_hw_ppgtt, ref);

	trace_i915_ppgtt_release(&ppgtt->base);

	/* vmas should already be unbound and destroyed */
	WARN_ON(!list_empty(&ppgtt->base.active_list));
	WARN_ON(!list_empty(&ppgtt->base.inactive_list));
	WARN_ON(!list_empty(&ppgtt->base.unbound_list));

	list_del(&ppgtt->base.global_link);
	drm_mm_takedown(&ppgtt->base.mm);

	ppgtt->base.cleanup(&ppgtt->base);
	kfree(ppgtt);
}

/* Certain Gen5 chipsets require require idling the GPU before
 * unmapping anything from the GTT when VT-d is enabled.
 */
static bool needs_idle_maps(struct drm_i915_private *dev_priv)
{
#ifdef CONFIG_INTEL_IOMMU
	/* Query intel_iommu to see if we need the workaround. Presumably that
	 * was loaded first.
	 */
	if (IS_GEN5(dev_priv) && IS_MOBILE(dev_priv) && intel_iommu_gfx_mapped)
		return true;
#endif
	return false;
}

void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
{
	struct intel_engine_cs *engine;

	if (INTEL_INFO(dev_priv)->gen < 6)
		return;

	for_each_engine(engine, dev_priv) {
		u32 fault_reg;
		fault_reg = I915_READ(RING_FAULT_REG(engine));
		if (fault_reg & RING_FAULT_VALID) {
			DRM_DEBUG_DRIVER("Unexpected fault\n"
					 "\tAddr: 0x%08lx\n"
					 "\tAddress space: %s\n"
					 "\tSource ID: %d\n"
					 "\tType: %d\n",
					 fault_reg & PAGE_MASK,
					 fault_reg & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT",
					 RING_FAULT_SRCID(fault_reg),
					 RING_FAULT_FAULT_TYPE(fault_reg));
			I915_WRITE(RING_FAULT_REG(engine),
				   fault_reg & ~RING_FAULT_VALID);
		}
	}
	POSTING_READ(RING_FAULT_REG(&dev_priv->engine[RCS]));
}

static void i915_ggtt_flush(struct drm_i915_private *dev_priv)
{
	if (INTEL_INFO(dev_priv)->gen < 6) {
		intel_gtt_chipset_flush();
	} else {
		I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
		POSTING_READ(GFX_FLSH_CNTL_GEN6);
	}
}

void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct i915_ggtt *ggtt = &dev_priv->ggtt;

	/* Don't bother messing with faults pre GEN6 as we have little
	 * documentation supporting that it's a good idea.
	 */
	if (INTEL_INFO(dev)->gen < 6)
		return;

	i915_check_and_clear_faults(dev_priv);

	ggtt->base.clear_range(&ggtt->base, ggtt->base.start, ggtt->base.total,
			     true);

	i915_ggtt_flush(dev_priv);
}

int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
{
	if (!dma_map_sg(&obj->base.dev->pdev->dev,
			obj->pages->sgl, obj->pages->nents,
			PCI_DMA_BIDIRECTIONAL))
		return -ENOSPC;

	return 0;
}

static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
{
	writeq(pte, addr);
}

static void gen8_ggtt_insert_page(struct i915_address_space *vm,
				  dma_addr_t addr,
				  uint64_t offset,
				  enum i915_cache_level level,
				  u32 unused)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	gen8_pte_t __iomem *pte =
		(gen8_pte_t __iomem *)dev_priv->ggtt.gsm +
		(offset >> PAGE_SHIFT);
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	gen8_set_pte(pte, gen8_pte_encode(addr, level, true));

	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
				     struct sg_table *st,
				     uint64_t start,
				     enum i915_cache_level level, u32 unused)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
	struct sgt_iter sgt_iter;
	gen8_pte_t __iomem *gtt_entries;
	gen8_pte_t gtt_entry;
	dma_addr_t addr;
	int rpm_atomic_seq;
	int i = 0;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT);

	for_each_sgt_dma(addr, sgt_iter, st) {
		gtt_entry = gen8_pte_encode(addr, level, true);
		gen8_set_pte(&gtt_entries[i++], gtt_entry);
	}

	/*
	 * XXX: This serves as a posting read to make sure that the PTE has
	 * actually been updated. There is some concern that even though
	 * registers and PTEs are within the same BAR that they are potentially
	 * of NUMA access patterns. Therefore, even with the way we assume
	 * hardware should work, we must keep this posting read for paranoia.
	 */
	if (i != 0)
		WARN_ON(readq(&gtt_entries[i-1]) != gtt_entry);

	/* This next bit makes the above posting read even more important. We
	 * want to flush the TLBs only after we're certain all the PTE updates
	 * have finished.
	 */
	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

struct insert_entries {
	struct i915_address_space *vm;
	struct sg_table *st;
	uint64_t start;
	enum i915_cache_level level;
	u32 flags;
};

static int gen8_ggtt_insert_entries__cb(void *_arg)
{
	struct insert_entries *arg = _arg;
	gen8_ggtt_insert_entries(arg->vm, arg->st,
				 arg->start, arg->level, arg->flags);
	return 0;
}

static void gen8_ggtt_insert_entries__BKL(struct i915_address_space *vm,
					  struct sg_table *st,
					  uint64_t start,
					  enum i915_cache_level level,
					  u32 flags)
{
	struct insert_entries arg = { vm, st, start, level, flags };
	stop_machine(gen8_ggtt_insert_entries__cb, &arg, NULL);
}

static void gen6_ggtt_insert_page(struct i915_address_space *vm,
				  dma_addr_t addr,
				  uint64_t offset,
				  enum i915_cache_level level,
				  u32 flags)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	gen6_pte_t __iomem *pte =
		(gen6_pte_t __iomem *)dev_priv->ggtt.gsm +
		(offset >> PAGE_SHIFT);
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	iowrite32(vm->pte_encode(addr, level, true, flags), pte);

	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

/*
 * Binds an object into the global gtt with the specified cache level. The object
 * will be accessible to the GPU via commands whose operands reference offsets
 * within the global GTT as well as accessible by the GPU through the GMADR
 * mapped BAR (dev_priv->mm.gtt->gtt).
 */
static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
				     struct sg_table *st,
				     uint64_t start,
				     enum i915_cache_level level, u32 flags)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
	struct sgt_iter sgt_iter;
	gen6_pte_t __iomem *gtt_entries;
	gen6_pte_t gtt_entry;
	dma_addr_t addr;
	int rpm_atomic_seq;
	int i = 0;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	gtt_entries = (gen6_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT);

	for_each_sgt_dma(addr, sgt_iter, st) {
		gtt_entry = vm->pte_encode(addr, level, true, flags);
		iowrite32(gtt_entry, &gtt_entries[i++]);
	}

	/* XXX: This serves as a posting read to make sure that the PTE has
	 * actually been updated. There is some concern that even though
	 * registers and PTEs are within the same BAR that they are potentially
	 * of NUMA access patterns. Therefore, even with the way we assume
	 * hardware should work, we must keep this posting read for paranoia.
	 */
	if (i != 0)
		WARN_ON(readl(&gtt_entries[i-1]) != gtt_entry);

	/* This next bit makes the above posting read even more important. We
	 * want to flush the TLBs only after we're certain all the PTE updates
	 * have finished.
	 */
	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static void nop_clear_range(struct i915_address_space *vm,
			    uint64_t start,
			    uint64_t length,
			    bool use_scratch)
{
}

static void gen8_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool use_scratch)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	gen8_pte_t scratch_pte, __iomem *gtt_base =
		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
	int i;
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	if (WARN(num_entries > max_entries,
		 "First entry = %d; Num entries = %d (max=%d)\n",
		 first_entry, num_entries, max_entries))
		num_entries = max_entries;

	scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
				      I915_CACHE_LLC,
				      use_scratch);
	for (i = 0; i < num_entries; i++)
		gen8_set_pte(&gtt_base[i], scratch_pte);
	readl(gtt_base);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static void gen6_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool use_scratch)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	gen6_pte_t scratch_pte, __iomem *gtt_base =
		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
	int i;
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	if (WARN(num_entries > max_entries,
		 "First entry = %d; Num entries = %d (max=%d)\n",
		 first_entry, num_entries, max_entries))
		num_entries = max_entries;

	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
				     I915_CACHE_LLC, use_scratch, 0);

	for (i = 0; i < num_entries; i++)
		iowrite32(scratch_pte, &gtt_base[i]);
	readl(gtt_base);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static void i915_ggtt_insert_page(struct i915_address_space *vm,
				  dma_addr_t addr,
				  uint64_t offset,
				  enum i915_cache_level cache_level,
				  u32 unused)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static void i915_ggtt_insert_entries(struct i915_address_space *vm,
				     struct sg_table *pages,
				     uint64_t start,
				     enum i915_cache_level cache_level, u32 unused)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	intel_gtt_insert_sg_entries(pages, start >> PAGE_SHIFT, flags);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);

}

static void i915_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool unused)
{
	struct drm_i915_private *dev_priv = to_i915(vm->dev);
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	int rpm_atomic_seq;

	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);

	intel_gtt_clear_range(first_entry, num_entries);

	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
}

static int ggtt_bind_vma(struct i915_vma *vma,
			 enum i915_cache_level cache_level,
			 u32 flags)
{
	struct drm_i915_gem_object *obj = vma->obj;
	u32 pte_flags = 0;
	int ret;

	ret = i915_get_ggtt_vma_pages(vma);
	if (ret)
		return ret;

	/* Currently applicable only to VLV */
	if (obj->gt_ro)
		pte_flags |= PTE_READ_ONLY;

	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
				cache_level, pte_flags);

	/*
	 * Without aliasing PPGTT there's no difference between
	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
	 * upgrade to both bound if we bind either to avoid double-binding.
	 */
	vma->flags |= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;

	return 0;
}

static int aliasing_gtt_bind_vma(struct i915_vma *vma,
				 enum i915_cache_level cache_level,
				 u32 flags)
{
	u32 pte_flags;
	int ret;

	ret = i915_get_ggtt_vma_pages(vma);
	if (ret)
		return ret;

	/* Currently applicable only to VLV */
	pte_flags = 0;
	if (vma->obj->gt_ro)
		pte_flags |= PTE_READ_ONLY;


	if (flags & I915_VMA_GLOBAL_BIND) {
		vma->vm->insert_entries(vma->vm,
					vma->pages, vma->node.start,
					cache_level, pte_flags);
	}

	if (flags & I915_VMA_LOCAL_BIND) {
		struct i915_hw_ppgtt *appgtt =
			to_i915(vma->vm->dev)->mm.aliasing_ppgtt;
		appgtt->base.insert_entries(&appgtt->base,
					    vma->pages, vma->node.start,
					    cache_level, pte_flags);
	}

	return 0;
}

static void ggtt_unbind_vma(struct i915_vma *vma)
{
	struct i915_hw_ppgtt *appgtt = to_i915(vma->vm->dev)->mm.aliasing_ppgtt;
	const u64 size = min(vma->size, vma->node.size);

	if (vma->flags & I915_VMA_GLOBAL_BIND)
		vma->vm->clear_range(vma->vm,
				     vma->node.start, size,
				     true);

	if (vma->flags & I915_VMA_LOCAL_BIND && appgtt)
		appgtt->base.clear_range(&appgtt->base,
					 vma->node.start, size,
					 true);
}

void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
	struct device *kdev = &dev_priv->drm.pdev->dev;
	struct i915_ggtt *ggtt = &dev_priv->ggtt;

	if (unlikely(ggtt->do_idle_maps)) {
		if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) {
			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
			/* Wait a bit, in hopes it avoids the hang */
			udelay(10);
		}
	}

	dma_unmap_sg(kdev, obj->pages->sgl, obj->pages->nents,
		     PCI_DMA_BIDIRECTIONAL);
}

static void i915_gtt_color_adjust(struct drm_mm_node *node,
				  unsigned long color,
				  u64 *start,
				  u64 *end)
{
	if (node->color != color)
		*start += 4096;

	node = list_first_entry_or_null(&node->node_list,
					struct drm_mm_node,
					node_list);
	if (node && node->allocated && node->color != color)
		*end -= 4096;
}

int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
{
	/* Let GEM Manage all of the aperture.
	 *
	 * However, leave one page at the end still bound to the scratch page.
	 * There are a number of places where the hardware apparently prefetches
	 * past the end of the object, and we've seen multiple hangs with the
	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
	 * aperture.  One page should be enough to keep any prefetching inside
	 * of the aperture.
	 */
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	unsigned long hole_start, hole_end;
	struct drm_mm_node *entry;
	int ret;

	ret = intel_vgt_balloon(dev_priv);
	if (ret)
		return ret;

	/* Clear any non-preallocated blocks */
	drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) {
		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
			      hole_start, hole_end);
		ggtt->base.clear_range(&ggtt->base, hole_start,
				     hole_end - hole_start, true);
	}

	/* And finally clear the reserved guard page */
	ggtt->base.clear_range(&ggtt->base,
			       ggtt->base.total - PAGE_SIZE, PAGE_SIZE,
			       true);

	if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) {
		struct i915_hw_ppgtt *ppgtt;

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

		ret = __hw_ppgtt_init(ppgtt, dev_priv);
		if (ret) {
			kfree(ppgtt);
			return ret;
		}

		if (ppgtt->base.allocate_va_range)
			ret = ppgtt->base.allocate_va_range(&ppgtt->base, 0,
							    ppgtt->base.total);
		if (ret) {
			ppgtt->base.cleanup(&ppgtt->base);
			kfree(ppgtt);
			return ret;
		}

		ppgtt->base.clear_range(&ppgtt->base,
					ppgtt->base.start,
					ppgtt->base.total,
					true);

		dev_priv->mm.aliasing_ppgtt = ppgtt;
		WARN_ON(ggtt->base.bind_vma != ggtt_bind_vma);
		ggtt->base.bind_vma = aliasing_gtt_bind_vma;
	}

	return 0;
}

/**
 * i915_ggtt_cleanup_hw - Clean up GGTT hardware initialization
 * @dev_priv: i915 device
 */
void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
{
	struct i915_ggtt *ggtt = &dev_priv->ggtt;

	if (dev_priv->mm.aliasing_ppgtt) {
		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
		ppgtt->base.cleanup(&ppgtt->base);
		kfree(ppgtt);
	}

	i915_gem_cleanup_stolen(&dev_priv->drm);

	if (drm_mm_initialized(&ggtt->base.mm)) {
		intel_vgt_deballoon(dev_priv);

		drm_mm_takedown(&ggtt->base.mm);
		list_del(&ggtt->base.global_link);
	}

	ggtt->base.cleanup(&ggtt->base);

	arch_phys_wc_del(ggtt->mtrr);
	io_mapping_fini(&ggtt->mappable);
}

static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
{
	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
	return snb_gmch_ctl << 20;
}

static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
{
	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
	if (bdw_gmch_ctl)
		bdw_gmch_ctl = 1 << bdw_gmch_ctl;

#ifdef CONFIG_X86_32
	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * PAGE_SIZE */
	if (bdw_gmch_ctl > 4)
		bdw_gmch_ctl = 4;
#endif

	return bdw_gmch_ctl << 20;
}

static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
{
	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
	gmch_ctrl &= SNB_GMCH_GGMS_MASK;

	if (gmch_ctrl)
		return 1 << (20 + gmch_ctrl);

	return 0;
}

static size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
{
	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
	snb_gmch_ctl &= SNB_GMCH_GMS_MASK;
	return snb_gmch_ctl << 25; /* 32 MB units */
}

static size_t gen8_get_stolen_size(u16 bdw_gmch_ctl)
{
	bdw_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
	bdw_gmch_ctl &= BDW_GMCH_GMS_MASK;
	return bdw_gmch_ctl << 25; /* 32 MB units */
}

static size_t chv_get_stolen_size(u16 gmch_ctrl)
{
	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
	gmch_ctrl &= SNB_GMCH_GMS_MASK;

	/*
	 * 0x0  to 0x10: 32MB increments starting at 0MB
	 * 0x11 to 0x16: 4MB increments starting at 8MB
	 * 0x17 to 0x1d: 4MB increments start at 36MB
	 */
	if (gmch_ctrl < 0x11)
		return gmch_ctrl << 25;
	else if (gmch_ctrl < 0x17)
		return (gmch_ctrl - 0x11 + 2) << 22;
	else
		return (gmch_ctrl - 0x17 + 9) << 22;
}

static size_t gen9_get_stolen_size(u16 gen9_gmch_ctl)
{
	gen9_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
	gen9_gmch_ctl &= BDW_GMCH_GMS_MASK;

	if (gen9_gmch_ctl < 0xf0)
		return gen9_gmch_ctl << 25; /* 32 MB units */
	else
		/* 4MB increments starting at 0xf0 for 4MB */
		return (gen9_gmch_ctl - 0xf0 + 1) << 22;
}

static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
{
	struct pci_dev *pdev = ggtt->base.dev->pdev;
	phys_addr_t phys_addr;
	int ret;

	/* For Modern GENs the PTEs and register space are split in the BAR */
	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;

	/*
	 * On BXT writes larger than 64 bit to the GTT pagetable range will be
	 * dropped. For WC mappings in general we have 64 byte burst writes
	 * when the WC buffer is flushed, so we can't use it, but have to
	 * resort to an uncached mapping. The WC issue is easily caught by the
	 * readback check when writing GTT PTE entries.
	 */
	if (IS_BROXTON(ggtt->base.dev))
		ggtt->gsm = ioremap_nocache(phys_addr, size);
	else
		ggtt->gsm = ioremap_wc(phys_addr, size);
	if (!ggtt->gsm) {
		DRM_ERROR("Failed to map the ggtt page table\n");
		return -ENOMEM;
	}

	ret = setup_scratch_page(ggtt->base.dev,
				 &ggtt->base.scratch_page,
				 GFP_DMA32);
	if (ret) {
		DRM_ERROR("Scratch setup failed\n");
		/* iounmap will also get called at remove, but meh */
		iounmap(ggtt->gsm);
		return ret;
	}

	return 0;
}

/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
 * bits. When using advanced contexts each context stores its own PAT, but
 * writing this data shouldn't be harmful even in those cases. */
static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
{
	uint64_t pat;

	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC)     | /* for normal objects, no eLLC */
	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) | /* for something pointing to ptes? */
	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) | /* for scanout with eLLC */
	      GEN8_PPAT(3, GEN8_PPAT_UC)                     | /* Uncached objects, mostly for scanout */
	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));

	if (!USES_PPGTT(dev_priv))
		/* Spec: "For GGTT, there is NO pat_sel[2:0] from the entry,
		 * so RTL will always use the value corresponding to
		 * pat_sel = 000".
		 * So let's disable cache for GGTT to avoid screen corruptions.
		 * MOCS still can be used though.
		 * - System agent ggtt writes (i.e. cpu gtt mmaps) already work
		 * before this patch, i.e. the same uncached + snooping access
		 * like on gen6/7 seems to be in effect.
		 * - So this just fixes blitter/render access. Again it looks
		 * like it's not just uncached access, but uncached + snooping.
		 * So we can still hold onto all our assumptions wrt cpu
		 * clflushing on LLC machines.
		 */
		pat = GEN8_PPAT(0, GEN8_PPAT_UC);

	/* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
	 * write would work. */
	I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
	I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
}

static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
{
	uint64_t pat;

	/*
	 * Map WB on BDW to snooped on CHV.
	 *
	 * Only the snoop bit has meaning for CHV, the rest is
	 * ignored.
	 *
	 * The hardware will never snoop for certain types of accesses:
	 * - CPU GTT (GMADR->GGTT->no snoop->memory)
	 * - PPGTT page tables
	 * - some other special cycles
	 *
	 * As with BDW, we also need to consider the following for GT accesses:
	 * "For GGTT, there is NO pat_sel[2:0] from the entry,
	 * so RTL will always use the value corresponding to
	 * pat_sel = 000".
	 * Which means we must set the snoop bit in PAT entry 0
	 * in order to keep the global status page working.
	 */
	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(1, 0) |
	      GEN8_PPAT(2, 0) |
	      GEN8_PPAT(3, 0) |
	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(7, CHV_PPAT_SNOOP);

	I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
	I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
}

static void gen6_gmch_remove(struct i915_address_space *vm)
{
	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);

	iounmap(ggtt->gsm);
	cleanup_scratch_page(vm->dev, &vm->scratch_page);
}

static int gen8_gmch_probe(struct i915_ggtt *ggtt)
{
	struct drm_i915_private *dev_priv = to_i915(ggtt->base.dev);
	struct pci_dev *pdev = dev_priv->drm.pdev;
	unsigned int size;
	u16 snb_gmch_ctl;

	/* TODO: We're not aware of mappable constraints on gen8 yet */
	ggtt->mappable_base = pci_resource_start(pdev, 2);
	ggtt->mappable_end = pci_resource_len(pdev, 2);

	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(39)))
		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));

	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);

	if (INTEL_GEN(dev_priv) >= 9) {
		ggtt->stolen_size = gen9_get_stolen_size(snb_gmch_ctl);
		size = gen8_get_total_gtt_size(snb_gmch_ctl);
	} else if (IS_CHERRYVIEW(dev_priv)) {
		ggtt->stolen_size = chv_get_stolen_size(snb_gmch_ctl);
		size = chv_get_total_gtt_size(snb_gmch_ctl);
	} else {
		ggtt->stolen_size = gen8_get_stolen_size(snb_gmch_ctl);
		size = gen8_get_total_gtt_size(snb_gmch_ctl);
	}

	ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;

	if (IS_CHERRYVIEW(dev_priv) || IS_BROXTON(dev_priv))
		chv_setup_private_ppat(dev_priv);
	else
		bdw_setup_private_ppat(dev_priv);

	ggtt->base.cleanup = gen6_gmch_remove;
	ggtt->base.bind_vma = ggtt_bind_vma;
	ggtt->base.unbind_vma = ggtt_unbind_vma;
	ggtt->base.insert_page = gen8_ggtt_insert_page;
	ggtt->base.clear_range = nop_clear_range;
	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
		ggtt->base.clear_range = gen8_ggtt_clear_range;

	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
	if (IS_CHERRYVIEW(dev_priv))
		ggtt->base.insert_entries = gen8_ggtt_insert_entries__BKL;

	return ggtt_probe_common(ggtt, size);
}

static int gen6_gmch_probe(struct i915_ggtt *ggtt)
{
	struct drm_i915_private *dev_priv = to_i915(ggtt->base.dev);
	struct pci_dev *pdev = dev_priv->drm.pdev;
	unsigned int size;
	u16 snb_gmch_ctl;

	ggtt->mappable_base = pci_resource_start(pdev, 2);
	ggtt->mappable_end = pci_resource_len(pdev, 2);

	/* 64/512MB is the current min/max we actually know of, but this is just
	 * a coarse sanity check.
	 */
	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
		DRM_ERROR("Unknown GMADR size (%llx)\n", ggtt->mappable_end);
		return -ENXIO;
	}

	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(40)))
		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);

	ggtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl);

	size = gen6_get_total_gtt_size(snb_gmch_ctl);
	ggtt->base.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;

	ggtt->base.clear_range = gen6_ggtt_clear_range;
	ggtt->base.insert_page = gen6_ggtt_insert_page;
	ggtt->base.insert_entries = gen6_ggtt_insert_entries;
	ggtt->base.bind_vma = ggtt_bind_vma;
	ggtt->base.unbind_vma = ggtt_unbind_vma;
	ggtt->base.cleanup = gen6_gmch_remove;

	if (HAS_EDRAM(dev_priv))
		ggtt->base.pte_encode = iris_pte_encode;
	else if (IS_HASWELL(dev_priv))
		ggtt->base.pte_encode = hsw_pte_encode;
	else if (IS_VALLEYVIEW(dev_priv))
		ggtt->base.pte_encode = byt_pte_encode;
	else if (INTEL_GEN(dev_priv) >= 7)
		ggtt->base.pte_encode = ivb_pte_encode;
	else
		ggtt->base.pte_encode = snb_pte_encode;

	return ggtt_probe_common(ggtt, size);
}

static void i915_gmch_remove(struct i915_address_space *vm)
{
	intel_gmch_remove();
}

static int i915_gmch_probe(struct i915_ggtt *ggtt)
{
	struct drm_i915_private *dev_priv = to_i915(ggtt->base.dev);
	int ret;

	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->drm.pdev, NULL);
	if (!ret) {
		DRM_ERROR("failed to set up gmch\n");
		return -EIO;
	}

	intel_gtt_get(&ggtt->base.total, &ggtt->stolen_size,
		      &ggtt->mappable_base, &ggtt->mappable_end);

	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
	ggtt->base.insert_page = i915_ggtt_insert_page;
	ggtt->base.insert_entries = i915_ggtt_insert_entries;
	ggtt->base.clear_range = i915_ggtt_clear_range;
	ggtt->base.bind_vma = ggtt_bind_vma;
	ggtt->base.unbind_vma = ggtt_unbind_vma;
	ggtt->base.cleanup = i915_gmch_remove;

	if (unlikely(ggtt->do_idle_maps))
		DRM_INFO("applying Ironlake quirks for intel_iommu\n");

	return 0;
}

/**
 * i915_ggtt_probe_hw - Probe GGTT hardware location
 * @dev_priv: i915 device
 */
int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
{
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	int ret;

	ggtt->base.dev = &dev_priv->drm;

	if (INTEL_GEN(dev_priv) <= 5)
		ret = i915_gmch_probe(ggtt);
	else if (INTEL_GEN(dev_priv) < 8)
		ret = gen6_gmch_probe(ggtt);
	else
		ret = gen8_gmch_probe(ggtt);
	if (ret)
		return ret;

	if ((ggtt->base.total - 1) >> 32) {
		DRM_ERROR("We never expected a Global GTT with more than 32bits"
			  " of address space! Found %lldM!\n",
			  ggtt->base.total >> 20);
		ggtt->base.total = 1ULL << 32;
		ggtt->mappable_end = min(ggtt->mappable_end, ggtt->base.total);
	}

	if (ggtt->mappable_end > ggtt->base.total) {
		DRM_ERROR("mappable aperture extends past end of GGTT,"
			  " aperture=%llx, total=%llx\n",
			  ggtt->mappable_end, ggtt->base.total);
		ggtt->mappable_end = ggtt->base.total;
	}

	/* GMADR is the PCI mmio aperture into the global GTT. */
	DRM_INFO("Memory usable by graphics device = %lluM\n",
		 ggtt->base.total >> 20);
	DRM_DEBUG_DRIVER("GMADR size = %lldM\n", ggtt->mappable_end >> 20);
	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", ggtt->stolen_size >> 20);
#ifdef CONFIG_INTEL_IOMMU
	if (intel_iommu_gfx_mapped)
		DRM_INFO("VT-d active for gfx access\n");
#endif

	return 0;
}

/**
 * i915_ggtt_init_hw - Initialize GGTT hardware
 * @dev_priv: i915 device
 */
int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
{
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	int ret;

	INIT_LIST_HEAD(&dev_priv->vm_list);

	/* Subtract the guard page before address space initialization to
	 * shrink the range used by drm_mm.
	 */
	ggtt->base.total -= PAGE_SIZE;
	i915_address_space_init(&ggtt->base, dev_priv);
	ggtt->base.total += PAGE_SIZE;
	if (!HAS_LLC(dev_priv))
		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;

	if (!io_mapping_init_wc(&dev_priv->ggtt.mappable,
				dev_priv->ggtt.mappable_base,
				dev_priv->ggtt.mappable_end)) {
		ret = -EIO;
		goto out_gtt_cleanup;
	}

	ggtt->mtrr = arch_phys_wc_add(ggtt->mappable_base, ggtt->mappable_end);

	/*
	 * Initialise stolen early so that we may reserve preallocated
	 * objects for the BIOS to KMS transition.
	 */
	ret = i915_gem_init_stolen(&dev_priv->drm);
	if (ret)
		goto out_gtt_cleanup;

	return 0;

out_gtt_cleanup:
	ggtt->base.cleanup(&ggtt->base);
	return ret;
}

int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv)
{
	if (INTEL_GEN(dev_priv) < 6 && !intel_enable_gtt())
		return -EIO;

	return 0;
}

void i915_gem_restore_gtt_mappings(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct i915_ggtt *ggtt = &dev_priv->ggtt;
	struct drm_i915_gem_object *obj, *on;

	i915_check_and_clear_faults(dev_priv);

	/* First fill our portion of the GTT with scratch pages */
	ggtt->base.clear_range(&ggtt->base, ggtt->base.start, ggtt->base.total,
			       true);

	ggtt->base.closed = true; /* skip rewriting PTE on VMA unbind */

	/* clflush objects bound into the GGTT and rebind them. */
	list_for_each_entry_safe(obj, on,
				 &dev_priv->mm.bound_list, global_list) {
		bool ggtt_bound = false;
		struct i915_vma *vma;

		list_for_each_entry(vma, &obj->vma_list, obj_link) {
			if (vma->vm != &ggtt->base)
				continue;

			if (!i915_vma_unbind(vma))
				continue;

			WARN_ON(i915_vma_bind(vma, obj->cache_level,
					      PIN_UPDATE));
			ggtt_bound = true;
		}

		if (ggtt_bound)
			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
	}

	ggtt->base.closed = false;

	if (INTEL_INFO(dev)->gen >= 8) {
		if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
			chv_setup_private_ppat(dev_priv);
		else
			bdw_setup_private_ppat(dev_priv);

		return;
	}

	if (USES_PPGTT(dev)) {
		struct i915_address_space *vm;

		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
			/* TODO: Perhaps it shouldn't be gen6 specific */

			struct i915_hw_ppgtt *ppgtt;

			if (i915_is_ggtt(vm))
				ppgtt = dev_priv->mm.aliasing_ppgtt;
			else
				ppgtt = i915_vm_to_ppgtt(vm);

			gen6_write_page_range(dev_priv, &ppgtt->pd,
					      0, ppgtt->base.total);
		}
	}

	i915_ggtt_flush(dev_priv);
}

static void
i915_vma_retire(struct i915_gem_active *active,
		struct drm_i915_gem_request *rq)
{
	const unsigned int idx = rq->engine->id;
	struct i915_vma *vma =
		container_of(active, struct i915_vma, last_read[idx]);

	GEM_BUG_ON(!i915_vma_has_active_engine(vma, idx));

	i915_vma_clear_active(vma, idx);
	if (i915_vma_is_active(vma))
		return;

	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
	if (unlikely(i915_vma_is_closed(vma) && !i915_vma_is_pinned(vma)))
		WARN_ON(i915_vma_unbind(vma));
}

void i915_vma_destroy(struct i915_vma *vma)
{
	GEM_BUG_ON(vma->node.allocated);
	GEM_BUG_ON(i915_vma_is_active(vma));
	GEM_BUG_ON(!i915_vma_is_closed(vma));
	GEM_BUG_ON(vma->fence);

	list_del(&vma->vm_link);
	if (!i915_vma_is_ggtt(vma))
		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));

	kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
}

void i915_vma_close(struct i915_vma *vma)
{
	GEM_BUG_ON(i915_vma_is_closed(vma));
	vma->flags |= I915_VMA_CLOSED;

	list_del_init(&vma->obj_link);
	if (!i915_vma_is_active(vma) && !i915_vma_is_pinned(vma))
		WARN_ON(i915_vma_unbind(vma));
}

static struct i915_vma *
__i915_vma_create(struct drm_i915_gem_object *obj,
		  struct i915_address_space *vm,
		  const struct i915_ggtt_view *view)
{
	struct i915_vma *vma;
	int i;

	GEM_BUG_ON(vm->closed);

	vma = kmem_cache_zalloc(to_i915(obj->base.dev)->vmas, GFP_KERNEL);
	if (vma == NULL)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&vma->exec_list);
	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
		init_request_active(&vma->last_read[i], i915_vma_retire);
	init_request_active(&vma->last_fence, NULL);
	list_add(&vma->vm_link, &vm->unbound_list);
	vma->vm = vm;
	vma->obj = obj;
	vma->size = obj->base.size;

	if (view) {
		vma->ggtt_view = *view;
		if (view->type == I915_GGTT_VIEW_PARTIAL) {
			vma->size = view->params.partial.size;
			vma->size <<= PAGE_SHIFT;
		} else if (view->type == I915_GGTT_VIEW_ROTATED) {
			vma->size =
				intel_rotation_info_size(&view->params.rotated);
			vma->size <<= PAGE_SHIFT;
		}
	}

	if (i915_is_ggtt(vm)) {
		vma->flags |= I915_VMA_GGTT;
	} else {
		i915_ppgtt_get(i915_vm_to_ppgtt(vm));
	}

	list_add_tail(&vma->obj_link, &obj->vma_list);
	return vma;
}

static inline bool vma_matches(struct i915_vma *vma,
			       struct i915_address_space *vm,
			       const struct i915_ggtt_view *view)
{
	if (vma->vm != vm)
		return false;

	if (!i915_vma_is_ggtt(vma))
		return true;

	if (!view)
		return vma->ggtt_view.type == 0;

	if (vma->ggtt_view.type != view->type)
		return false;

	return memcmp(&vma->ggtt_view.params,
		      &view->params,
		      sizeof(view->params)) == 0;
}

struct i915_vma *
i915_vma_create(struct drm_i915_gem_object *obj,
		struct i915_address_space *vm,
		const struct i915_ggtt_view *view)
{
	GEM_BUG_ON(view && !i915_is_ggtt(vm));
	GEM_BUG_ON(i915_gem_obj_to_vma(obj, vm, view));

	return __i915_vma_create(obj, vm, view);
}

struct i915_vma *
i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
		    struct i915_address_space *vm,
		    const struct i915_ggtt_view *view)
{
	struct i915_vma *vma;

	list_for_each_entry_reverse(vma, &obj->vma_list, obj_link)
		if (vma_matches(vma, vm, view))
			return vma;

	return NULL;
}

struct i915_vma *
i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
				  struct i915_address_space *vm,
				  const struct i915_ggtt_view *view)
{
	struct i915_vma *vma;

	GEM_BUG_ON(view && !i915_is_ggtt(vm));

	vma = i915_gem_obj_to_vma(obj, vm, view);
	if (!vma)
		vma = __i915_vma_create(obj, vm, view);

	GEM_BUG_ON(i915_vma_is_closed(vma));
	return vma;
}

static struct scatterlist *
rotate_pages(const dma_addr_t *in, unsigned int offset,
	     unsigned int width, unsigned int height,
	     unsigned int stride,
	     struct sg_table *st, struct scatterlist *sg)
{
	unsigned int column, row;
	unsigned int src_idx;

	for (column = 0; column < width; column++) {
		src_idx = stride * (height - 1) + column;
		for (row = 0; row < height; row++) {
			st->nents++;
			/* We don't need the pages, but need to initialize
			 * the entries so the sg list can be happily traversed.
			 * The only thing we need are DMA addresses.
			 */
			sg_set_page(sg, NULL, PAGE_SIZE, 0);
			sg_dma_address(sg) = in[offset + src_idx];
			sg_dma_len(sg) = PAGE_SIZE;
			sg = sg_next(sg);
			src_idx -= stride;
		}
	}

	return sg;
}

static struct sg_table *
intel_rotate_fb_obj_pages(const struct intel_rotation_info *rot_info,
			  struct drm_i915_gem_object *obj)
{
	const size_t n_pages = obj->base.size / PAGE_SIZE;
	unsigned int size = intel_rotation_info_size(rot_info);
	struct sgt_iter sgt_iter;
	dma_addr_t dma_addr;
	unsigned long i;
	dma_addr_t *page_addr_list;
	struct sg_table *st;
	struct scatterlist *sg;
	int ret = -ENOMEM;

	/* Allocate a temporary list of source pages for random access. */
	page_addr_list = drm_malloc_gfp(n_pages,
					sizeof(dma_addr_t),
					GFP_TEMPORARY);
	if (!page_addr_list)
		return ERR_PTR(ret);

	/* Allocate target SG list. */
	st = kmalloc(sizeof(*st), GFP_KERNEL);
	if (!st)
		goto err_st_alloc;

	ret = sg_alloc_table(st, size, GFP_KERNEL);
	if (ret)
		goto err_sg_alloc;

	/* Populate source page list from the object. */
	i = 0;
	for_each_sgt_dma(dma_addr, sgt_iter, obj->pages)
		page_addr_list[i++] = dma_addr;

	GEM_BUG_ON(i != n_pages);
	st->nents = 0;
	sg = st->sgl;

	for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
		sg = rotate_pages(page_addr_list, rot_info->plane[i].offset,
				  rot_info->plane[i].width, rot_info->plane[i].height,
				  rot_info->plane[i].stride, st, sg);
	}

	DRM_DEBUG_KMS("Created rotated page mapping for object size %zu (%ux%u tiles, %u pages)\n",
		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);

	drm_free_large(page_addr_list);

	return st;

err_sg_alloc:
	kfree(st);
err_st_alloc:
	drm_free_large(page_addr_list);

	DRM_DEBUG_KMS("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);

	return ERR_PTR(ret);
}

static struct sg_table *
intel_partial_pages(const struct i915_ggtt_view *view,
		    struct drm_i915_gem_object *obj)
{
	struct sg_table *st;
	struct scatterlist *sg;
	struct sg_page_iter obj_sg_iter;
	int ret = -ENOMEM;

	st = kmalloc(sizeof(*st), GFP_KERNEL);
	if (!st)
		goto err_st_alloc;

	ret = sg_alloc_table(st, view->params.partial.size, GFP_KERNEL);
	if (ret)
		goto err_sg_alloc;

	sg = st->sgl;
	st->nents = 0;
	for_each_sg_page(obj->pages->sgl, &obj_sg_iter, obj->pages->nents,
		view->params.partial.offset)
	{
		if (st->nents >= view->params.partial.size)
			break;

		sg_set_page(sg, NULL, PAGE_SIZE, 0);
		sg_dma_address(sg) = sg_page_iter_dma_address(&obj_sg_iter);
		sg_dma_len(sg) = PAGE_SIZE;

		sg = sg_next(sg);
		st->nents++;
	}

	return st;

err_sg_alloc:
	kfree(st);
err_st_alloc:
	return ERR_PTR(ret);
}

static int
i915_get_ggtt_vma_pages(struct i915_vma *vma)
{
	int ret = 0;

	if (vma->pages)
		return 0;

	if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
		vma->pages = vma->obj->pages;
	else if (vma->ggtt_view.type == I915_GGTT_VIEW_ROTATED)
		vma->pages =
			intel_rotate_fb_obj_pages(&vma->ggtt_view.params.rotated, vma->obj);
	else if (vma->ggtt_view.type == I915_GGTT_VIEW_PARTIAL)
		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
	else
		WARN_ONCE(1, "GGTT view %u not implemented!\n",
			  vma->ggtt_view.type);

	if (!vma->pages) {
		DRM_ERROR("Failed to get pages for GGTT view type %u!\n",
			  vma->ggtt_view.type);
		ret = -EINVAL;
	} else if (IS_ERR(vma->pages)) {
		ret = PTR_ERR(vma->pages);
		vma->pages = NULL;
		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
			  vma->ggtt_view.type, ret);
	}

	return ret;
}

/**
 * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space.
 * @vma: VMA to map
 * @cache_level: mapping cache level
 * @flags: flags like global or local mapping
 *
 * DMA addresses are taken from the scatter-gather table of this object (or of
 * this VMA in case of non-default GGTT views) and PTE entries set up.
 * Note that DMA addresses are also the only part of the SG table we care about.
 */
int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
		  u32 flags)
{
	u32 bind_flags;
	u32 vma_flags;
	int ret;

	if (WARN_ON(flags == 0))
		return -EINVAL;

	bind_flags = 0;
	if (flags & PIN_GLOBAL)
		bind_flags |= I915_VMA_GLOBAL_BIND;
	if (flags & PIN_USER)
		bind_flags |= I915_VMA_LOCAL_BIND;

	vma_flags = vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
	if (flags & PIN_UPDATE)
		bind_flags |= vma_flags;
	else
		bind_flags &= ~vma_flags;
	if (bind_flags == 0)
		return 0;

	if (vma_flags == 0 && vma->vm->allocate_va_range) {
		trace_i915_va_alloc(vma);
		ret = vma->vm->allocate_va_range(vma->vm,
						 vma->node.start,
						 vma->node.size);
		if (ret)
			return ret;
	}

	ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
	if (ret)
		return ret;

	vma->flags |= bind_flags;
	return 0;
}

void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
{
	void __iomem *ptr;

	/* Access through the GTT requires the device to be awake. */
	assert_rpm_wakelock_held(to_i915(vma->vm->dev));

	lockdep_assert_held(&vma->vm->dev->struct_mutex);
	if (WARN_ON(!i915_vma_is_map_and_fenceable(vma)))
		return IO_ERR_PTR(-ENODEV);

	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
	GEM_BUG_ON((vma->flags & I915_VMA_GLOBAL_BIND) == 0);

	ptr = vma->iomap;
	if (ptr == NULL) {
		ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->mappable,
					vma->node.start,
					vma->node.size);
		if (ptr == NULL)
			return IO_ERR_PTR(-ENOMEM);

		vma->iomap = ptr;
	}

	__i915_vma_pin(vma);
	return ptr;
}

void i915_vma_unpin_and_release(struct i915_vma **p_vma)
{
	struct i915_vma *vma;

	vma = fetch_and_zero(p_vma);
	if (!vma)
		return;

	i915_vma_unpin(vma);
	i915_vma_put(vma);
}