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
|
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2008,2010 Intel Corporation
*/
#include <linux/intel-iommu.h>
#include <linux/reservation.h>
#include <linux/sync_file.h>
#include <linux/uaccess.h>
#include <drm/drm_syncobj.h>
#include <drm/i915_drm.h>
#include "display/intel_frontbuffer.h"
#include "gem/i915_gem_ioctls.h"
#include "gt/intel_context.h"
#include "gt/intel_engine_pool.h"
#include "gt/intel_gt.h"
#include "gt/intel_gt_pm.h"
#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
#include "i915_trace.h"
enum {
FORCE_CPU_RELOC = 1,
FORCE_GTT_RELOC,
FORCE_GPU_RELOC,
#define DBG_FORCE_RELOC 0 /* choose one of the above! */
};
#define __EXEC_OBJECT_HAS_REF BIT(31)
#define __EXEC_OBJECT_HAS_PIN BIT(30)
#define __EXEC_OBJECT_HAS_FENCE BIT(29)
#define __EXEC_OBJECT_NEEDS_MAP BIT(28)
#define __EXEC_OBJECT_NEEDS_BIAS BIT(27)
#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 27) /* all of the above */
#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE)
#define __EXEC_HAS_RELOC BIT(31)
#define __EXEC_VALIDATED BIT(30)
#define __EXEC_INTERNAL_FLAGS (~0u << 30)
#define UPDATE PIN_OFFSET_FIXED
#define BATCH_OFFSET_BIAS (256*1024)
#define __I915_EXEC_ILLEGAL_FLAGS \
(__I915_EXEC_UNKNOWN_FLAGS | \
I915_EXEC_CONSTANTS_MASK | \
I915_EXEC_RESOURCE_STREAMER)
/* Catch emission of unexpected errors for CI! */
#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
#undef EINVAL
#define EINVAL ({ \
DRM_DEBUG_DRIVER("EINVAL at %s:%d\n", __func__, __LINE__); \
22; \
})
#endif
/**
* DOC: User command execution
*
* Userspace submits commands to be executed on the GPU as an instruction
* stream within a GEM object we call a batchbuffer. This instructions may
* refer to other GEM objects containing auxiliary state such as kernels,
* samplers, render targets and even secondary batchbuffers. Userspace does
* not know where in the GPU memory these objects reside and so before the
* batchbuffer is passed to the GPU for execution, those addresses in the
* batchbuffer and auxiliary objects are updated. This is known as relocation,
* or patching. To try and avoid having to relocate each object on the next
* execution, userspace is told the location of those objects in this pass,
* but this remains just a hint as the kernel may choose a new location for
* any object in the future.
*
* At the level of talking to the hardware, submitting a batchbuffer for the
* GPU to execute is to add content to a buffer from which the HW
* command streamer is reading.
*
* 1. Add a command to load the HW context. For Logical Ring Contexts, i.e.
* Execlists, this command is not placed on the same buffer as the
* remaining items.
*
* 2. Add a command to invalidate caches to the buffer.
*
* 3. Add a batchbuffer start command to the buffer; the start command is
* essentially a token together with the GPU address of the batchbuffer
* to be executed.
*
* 4. Add a pipeline flush to the buffer.
*
* 5. Add a memory write command to the buffer to record when the GPU
* is done executing the batchbuffer. The memory write writes the
* global sequence number of the request, ``i915_request::global_seqno``;
* the i915 driver uses the current value in the register to determine
* if the GPU has completed the batchbuffer.
*
* 6. Add a user interrupt command to the buffer. This command instructs
* the GPU to issue an interrupt when the command, pipeline flush and
* memory write are completed.
*
* 7. Inform the hardware of the additional commands added to the buffer
* (by updating the tail pointer).
*
* Processing an execbuf ioctl is conceptually split up into a few phases.
*
* 1. Validation - Ensure all the pointers, handles and flags are valid.
* 2. Reservation - Assign GPU address space for every object
* 3. Relocation - Update any addresses to point to the final locations
* 4. Serialisation - Order the request with respect to its dependencies
* 5. Construction - Construct a request to execute the batchbuffer
* 6. Submission (at some point in the future execution)
*
* Reserving resources for the execbuf is the most complicated phase. We
* neither want to have to migrate the object in the address space, nor do
* we want to have to update any relocations pointing to this object. Ideally,
* we want to leave the object where it is and for all the existing relocations
* to match. If the object is given a new address, or if userspace thinks the
* object is elsewhere, we have to parse all the relocation entries and update
* the addresses. Userspace can set the I915_EXEC_NORELOC flag to hint that
* all the target addresses in all of its objects match the value in the
* relocation entries and that they all match the presumed offsets given by the
* list of execbuffer objects. Using this knowledge, we know that if we haven't
* moved any buffers, all the relocation entries are valid and we can skip
* the update. (If userspace is wrong, the likely outcome is an impromptu GPU
* hang.) The requirement for using I915_EXEC_NO_RELOC are:
*
* The addresses written in the objects must match the corresponding
* reloc.presumed_offset which in turn must match the corresponding
* execobject.offset.
*
* Any render targets written to in the batch must be flagged with
* EXEC_OBJECT_WRITE.
*
* To avoid stalling, execobject.offset should match the current
* address of that object within the active context.
*
* The reservation is done is multiple phases. First we try and keep any
* object already bound in its current location - so as long as meets the
* constraints imposed by the new execbuffer. Any object left unbound after the
* first pass is then fitted into any available idle space. If an object does
* not fit, all objects are removed from the reservation and the process rerun
* after sorting the objects into a priority order (more difficult to fit
* objects are tried first). Failing that, the entire VM is cleared and we try
* to fit the execbuf once last time before concluding that it simply will not
* fit.
*
* A small complication to all of this is that we allow userspace not only to
* specify an alignment and a size for the object in the address space, but
* we also allow userspace to specify the exact offset. This objects are
* simpler to place (the location is known a priori) all we have to do is make
* sure the space is available.
*
* Once all the objects are in place, patching up the buried pointers to point
* to the final locations is a fairly simple job of walking over the relocation
* entry arrays, looking up the right address and rewriting the value into
* the object. Simple! ... The relocation entries are stored in user memory
* and so to access them we have to copy them into a local buffer. That copy
* has to avoid taking any pagefaults as they may lead back to a GEM object
* requiring the struct_mutex (i.e. recursive deadlock). So once again we split
* the relocation into multiple passes. First we try to do everything within an
* atomic context (avoid the pagefaults) which requires that we never wait. If
* we detect that we may wait, or if we need to fault, then we have to fallback
* to a slower path. The slowpath has to drop the mutex. (Can you hear alarm
* bells yet?) Dropping the mutex means that we lose all the state we have
* built up so far for the execbuf and we must reset any global data. However,
* we do leave the objects pinned in their final locations - which is a
* potential issue for concurrent execbufs. Once we have left the mutex, we can
* allocate and copy all the relocation entries into a large array at our
* leisure, reacquire the mutex, reclaim all the objects and other state and
* then proceed to update any incorrect addresses with the objects.
*
* As we process the relocation entries, we maintain a record of whether the
* object is being written to. Using NORELOC, we expect userspace to provide
* this information instead. We also check whether we can skip the relocation
* by comparing the expected value inside the relocation entry with the target's
* final address. If they differ, we have to map the current object and rewrite
* the 4 or 8 byte pointer within.
*
* Serialising an execbuf is quite simple according to the rules of the GEM
* ABI. Execution within each context is ordered by the order of submission.
* Writes to any GEM object are in order of submission and are exclusive. Reads
* from a GEM object are unordered with respect to other reads, but ordered by
* writes. A write submitted after a read cannot occur before the read, and
* similarly any read submitted after a write cannot occur before the write.
* Writes are ordered between engines such that only one write occurs at any
* time (completing any reads beforehand) - using semaphores where available
* and CPU serialisation otherwise. Other GEM access obey the same rules, any
* write (either via mmaps using set-domain, or via pwrite) must flush all GPU
* reads before starting, and any read (either using set-domain or pread) must
* flush all GPU writes before starting. (Note we only employ a barrier before,
* we currently rely on userspace not concurrently starting a new execution
* whilst reading or writing to an object. This may be an advantage or not
* depending on how much you trust userspace not to shoot themselves in the
* foot.) Serialisation may just result in the request being inserted into
* a DAG awaiting its turn, but most simple is to wait on the CPU until
* all dependencies are resolved.
*
* After all of that, is just a matter of closing the request and handing it to
* the hardware (well, leaving it in a queue to be executed). However, we also
* offer the ability for batchbuffers to be run with elevated privileges so
* that they access otherwise hidden registers. (Used to adjust L3 cache etc.)
* Before any batch is given extra privileges we first must check that it
* contains no nefarious instructions, we check that each instruction is from
* our whitelist and all registers are also from an allowed list. We first
* copy the user's batchbuffer to a shadow (so that the user doesn't have
* access to it, either by the CPU or GPU as we scan it) and then parse each
* instruction. If everything is ok, we set a flag telling the hardware to run
* the batchbuffer in trusted mode, otherwise the ioctl is rejected.
*/
struct i915_execbuffer {
struct drm_i915_private *i915; /** i915 backpointer */
struct drm_file *file; /** per-file lookup tables and limits */
struct drm_i915_gem_execbuffer2 *args; /** ioctl parameters */
struct drm_i915_gem_exec_object2 *exec; /** ioctl execobj[] */
struct i915_vma **vma;
unsigned int *flags;
struct intel_engine_cs *engine; /** engine to queue the request to */
struct intel_context *context; /* logical state for the request */
struct i915_gem_context *gem_context; /** caller's context */
struct i915_request *request; /** our request to build */
struct i915_vma *batch; /** identity of the batch obj/vma */
/** actual size of execobj[] as we may extend it for the cmdparser */
unsigned int buffer_count;
/** list of vma not yet bound during reservation phase */
struct list_head unbound;
/** list of vma that have execobj.relocation_count */
struct list_head relocs;
/**
* Track the most recently used object for relocations, as we
* frequently have to perform multiple relocations within the same
* obj/page
*/
struct reloc_cache {
struct drm_mm_node node; /** temporary GTT binding */
unsigned long vaddr; /** Current kmap address */
unsigned long page; /** Currently mapped page index */
unsigned int gen; /** Cached value of INTEL_GEN */
bool use_64bit_reloc : 1;
bool has_llc : 1;
bool has_fence : 1;
bool needs_unfenced : 1;
struct i915_request *rq;
u32 *rq_cmd;
unsigned int rq_size;
} reloc_cache;
u64 invalid_flags; /** Set of execobj.flags that are invalid */
u32 context_flags; /** Set of execobj.flags to insert from the ctx */
u32 batch_start_offset; /** Location within object of batch */
u32 batch_len; /** Length of batch within object */
u32 batch_flags; /** Flags composed for emit_bb_start() */
/**
* Indicate either the size of the hastable used to resolve
* relocation handles, or if negative that we are using a direct
* index into the execobj[].
*/
int lut_size;
struct hlist_head *buckets; /** ht for relocation handles */
};
#define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
/*
* Used to convert any address to canonical form.
* Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
* MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
* addresses to be in a canonical form:
* "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
* canonical form [63:48] == [47]."
*/
#define GEN8_HIGH_ADDRESS_BIT 47
static inline u64 gen8_canonical_addr(u64 address)
{
return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
}
static inline u64 gen8_noncanonical_addr(u64 address)
{
return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0);
}
static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
{
return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
}
static int eb_create(struct i915_execbuffer *eb)
{
if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) {
unsigned int size = 1 + ilog2(eb->buffer_count);
/*
* Without a 1:1 association between relocation handles and
* the execobject[] index, we instead create a hashtable.
* We size it dynamically based on available memory, starting
* first with 1:1 assocative hash and scaling back until
* the allocation succeeds.
*
* Later on we use a positive lut_size to indicate we are
* using this hashtable, and a negative value to indicate a
* direct lookup.
*/
do {
gfp_t flags;
/* While we can still reduce the allocation size, don't
* raise a warning and allow the allocation to fail.
* On the last pass though, we want to try as hard
* as possible to perform the allocation and warn
* if it fails.
*/
flags = GFP_KERNEL;
if (size > 1)
flags |= __GFP_NORETRY | __GFP_NOWARN;
eb->buckets = kzalloc(sizeof(struct hlist_head) << size,
flags);
if (eb->buckets)
break;
} while (--size);
if (unlikely(!size))
return -ENOMEM;
eb->lut_size = size;
} else {
eb->lut_size = -eb->buffer_count;
}
return 0;
}
static bool
eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry,
const struct i915_vma *vma,
unsigned int flags)
{
if (vma->node.size < entry->pad_to_size)
return true;
if (entry->alignment && !IS_ALIGNED(vma->node.start, entry->alignment))
return true;
if (flags & EXEC_OBJECT_PINNED &&
vma->node.start != entry->offset)
return true;
if (flags & __EXEC_OBJECT_NEEDS_BIAS &&
vma->node.start < BATCH_OFFSET_BIAS)
return true;
if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) &&
(vma->node.start + vma->node.size - 1) >> 32)
return true;
if (flags & __EXEC_OBJECT_NEEDS_MAP &&
!i915_vma_is_map_and_fenceable(vma))
return true;
return false;
}
static inline bool
eb_pin_vma(struct i915_execbuffer *eb,
const struct drm_i915_gem_exec_object2 *entry,
struct i915_vma *vma)
{
unsigned int exec_flags = *vma->exec_flags;
u64 pin_flags;
if (vma->node.size)
pin_flags = vma->node.start;
else
pin_flags = entry->offset & PIN_OFFSET_MASK;
pin_flags |= PIN_USER | PIN_NOEVICT | PIN_OFFSET_FIXED;
if (unlikely(exec_flags & EXEC_OBJECT_NEEDS_GTT))
pin_flags |= PIN_GLOBAL;
if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags)))
return false;
if (unlikely(exec_flags & EXEC_OBJECT_NEEDS_FENCE)) {
if (unlikely(i915_vma_pin_fence(vma))) {
i915_vma_unpin(vma);
return false;
}
if (vma->fence)
exec_flags |= __EXEC_OBJECT_HAS_FENCE;
}
*vma->exec_flags = exec_flags | __EXEC_OBJECT_HAS_PIN;
return !eb_vma_misplaced(entry, vma, exec_flags);
}
static inline void __eb_unreserve_vma(struct i915_vma *vma, unsigned int flags)
{
GEM_BUG_ON(!(flags & __EXEC_OBJECT_HAS_PIN));
if (unlikely(flags & __EXEC_OBJECT_HAS_FENCE))
__i915_vma_unpin_fence(vma);
__i915_vma_unpin(vma);
}
static inline void
eb_unreserve_vma(struct i915_vma *vma, unsigned int *flags)
{
if (!(*flags & __EXEC_OBJECT_HAS_PIN))
return;
__eb_unreserve_vma(vma, *flags);
*flags &= ~__EXEC_OBJECT_RESERVED;
}
static int
eb_validate_vma(struct i915_execbuffer *eb,
struct drm_i915_gem_exec_object2 *entry,
struct i915_vma *vma)
{
if (unlikely(entry->flags & eb->invalid_flags))
return -EINVAL;
if (unlikely(entry->alignment && !is_power_of_2(entry->alignment)))
return -EINVAL;
/*
* Offset can be used as input (EXEC_OBJECT_PINNED), reject
* any non-page-aligned or non-canonical addresses.
*/
if (unlikely(entry->flags & EXEC_OBJECT_PINNED &&
entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK)))
return -EINVAL;
/* pad_to_size was once a reserved field, so sanitize it */
if (entry->flags & EXEC_OBJECT_PAD_TO_SIZE) {
if (unlikely(offset_in_page(entry->pad_to_size)))
return -EINVAL;
} else {
entry->pad_to_size = 0;
}
if (unlikely(vma->exec_flags)) {
DRM_DEBUG("Object [handle %d, index %d] appears more than once in object list\n",
entry->handle, (int)(entry - eb->exec));
return -EINVAL;
}
/*
* From drm_mm perspective address space is continuous,
* so from this point we're always using non-canonical
* form internally.
*/
entry->offset = gen8_noncanonical_addr(entry->offset);
if (!eb->reloc_cache.has_fence) {
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
} else {
if ((entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
eb->reloc_cache.needs_unfenced) &&
i915_gem_object_is_tiled(vma->obj))
entry->flags |= EXEC_OBJECT_NEEDS_GTT | __EXEC_OBJECT_NEEDS_MAP;
}
if (!(entry->flags & EXEC_OBJECT_PINNED))
entry->flags |= eb->context_flags;
return 0;
}
static int
eb_add_vma(struct i915_execbuffer *eb,
unsigned int i, unsigned batch_idx,
struct i915_vma *vma)
{
struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
int err;
GEM_BUG_ON(i915_vma_is_closed(vma));
if (!(eb->args->flags & __EXEC_VALIDATED)) {
err = eb_validate_vma(eb, entry, vma);
if (unlikely(err))
return err;
}
if (eb->lut_size > 0) {
vma->exec_handle = entry->handle;
hlist_add_head(&vma->exec_node,
&eb->buckets[hash_32(entry->handle,
eb->lut_size)]);
}
if (entry->relocation_count)
list_add_tail(&vma->reloc_link, &eb->relocs);
/*
* Stash a pointer from the vma to execobj, so we can query its flags,
* size, alignment etc as provided by the user. Also we stash a pointer
* to the vma inside the execobj so that we can use a direct lookup
* to find the right target VMA when doing relocations.
*/
eb->vma[i] = vma;
eb->flags[i] = entry->flags;
vma->exec_flags = &eb->flags[i];
/*
* SNA is doing fancy tricks with compressing batch buffers, which leads
* to negative relocation deltas. Usually that works out ok since the
* relocate address is still positive, except when the batch is placed
* very low in the GTT. Ensure this doesn't happen.
*
* Note that actual hangs have only been observed on gen7, but for
* paranoia do it everywhere.
*/
if (i == batch_idx) {
if (entry->relocation_count &&
!(eb->flags[i] & EXEC_OBJECT_PINNED))
eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
if (eb->reloc_cache.has_fence)
eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
eb->batch = vma;
}
err = 0;
if (eb_pin_vma(eb, entry, vma)) {
if (entry->offset != vma->node.start) {
entry->offset = vma->node.start | UPDATE;
eb->args->flags |= __EXEC_HAS_RELOC;
}
} else {
eb_unreserve_vma(vma, vma->exec_flags);
list_add_tail(&vma->exec_link, &eb->unbound);
if (drm_mm_node_allocated(&vma->node))
err = i915_vma_unbind(vma);
if (unlikely(err))
vma->exec_flags = NULL;
}
return err;
}
static inline int use_cpu_reloc(const struct reloc_cache *cache,
const struct drm_i915_gem_object *obj)
{
if (!i915_gem_object_has_struct_page(obj))
return false;
if (DBG_FORCE_RELOC == FORCE_CPU_RELOC)
return true;
if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
return false;
return (cache->has_llc ||
obj->cache_dirty ||
obj->cache_level != I915_CACHE_NONE);
}
static int eb_reserve_vma(const struct i915_execbuffer *eb,
struct i915_vma *vma)
{
struct drm_i915_gem_exec_object2 *entry = exec_entry(eb, vma);
unsigned int exec_flags = *vma->exec_flags;
u64 pin_flags;
int err;
pin_flags = PIN_USER | PIN_NONBLOCK;
if (exec_flags & EXEC_OBJECT_NEEDS_GTT)
pin_flags |= PIN_GLOBAL;
/*
* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
* limit address to the first 4GBs for unflagged objects.
*/
if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
pin_flags |= PIN_ZONE_4G;
if (exec_flags & __EXEC_OBJECT_NEEDS_MAP)
pin_flags |= PIN_MAPPABLE;
if (exec_flags & EXEC_OBJECT_PINNED) {
pin_flags |= entry->offset | PIN_OFFSET_FIXED;
pin_flags &= ~PIN_NONBLOCK; /* force overlapping checks */
} else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS) {
pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
}
err = i915_vma_pin(vma,
entry->pad_to_size, entry->alignment,
pin_flags);
if (err)
return err;
if (entry->offset != vma->node.start) {
entry->offset = vma->node.start | UPDATE;
eb->args->flags |= __EXEC_HAS_RELOC;
}
if (unlikely(exec_flags & EXEC_OBJECT_NEEDS_FENCE)) {
err = i915_vma_pin_fence(vma);
if (unlikely(err)) {
i915_vma_unpin(vma);
return err;
}
if (vma->fence)
exec_flags |= __EXEC_OBJECT_HAS_FENCE;
}
*vma->exec_flags = exec_flags | __EXEC_OBJECT_HAS_PIN;
GEM_BUG_ON(eb_vma_misplaced(entry, vma, exec_flags));
return 0;
}
static int eb_reserve(struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
struct list_head last;
struct i915_vma *vma;
unsigned int i, pass;
int err;
/*
* Attempt to pin all of the buffers into the GTT.
* This is done in 3 phases:
*
* 1a. Unbind all objects that do not match the GTT constraints for
* the execbuffer (fenceable, mappable, alignment etc).
* 1b. Increment pin count for already bound objects.
* 2. Bind new objects.
* 3. Decrement pin count.
*
* This avoid unnecessary unbinding of later objects in order to make
* room for the earlier objects *unless* we need to defragment.
*/
pass = 0;
err = 0;
do {
list_for_each_entry(vma, &eb->unbound, exec_link) {
err = eb_reserve_vma(eb, vma);
if (err)
break;
}
if (err != -ENOSPC)
return err;
/* Resort *all* the objects into priority order */
INIT_LIST_HEAD(&eb->unbound);
INIT_LIST_HEAD(&last);
for (i = 0; i < count; i++) {
unsigned int flags = eb->flags[i];
struct i915_vma *vma = eb->vma[i];
if (flags & EXEC_OBJECT_PINNED &&
flags & __EXEC_OBJECT_HAS_PIN)
continue;
eb_unreserve_vma(vma, &eb->flags[i]);
if (flags & EXEC_OBJECT_PINNED)
/* Pinned must have their slot */
list_add(&vma->exec_link, &eb->unbound);
else if (flags & __EXEC_OBJECT_NEEDS_MAP)
/* Map require the lowest 256MiB (aperture) */
list_add_tail(&vma->exec_link, &eb->unbound);
else if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
/* Prioritise 4GiB region for restricted bo */
list_add(&vma->exec_link, &last);
else
list_add_tail(&vma->exec_link, &last);
}
list_splice_tail(&last, &eb->unbound);
switch (pass++) {
case 0:
break;
case 1:
/* Too fragmented, unbind everything and retry */
err = i915_gem_evict_vm(eb->context->vm);
if (err)
return err;
break;
default:
return -ENOSPC;
}
} while (1);
}
static unsigned int eb_batch_index(const struct i915_execbuffer *eb)
{
if (eb->args->flags & I915_EXEC_BATCH_FIRST)
return 0;
else
return eb->buffer_count - 1;
}
static int eb_select_context(struct i915_execbuffer *eb)
{
struct i915_gem_context *ctx;
ctx = i915_gem_context_lookup(eb->file->driver_priv, eb->args->rsvd1);
if (unlikely(!ctx))
return -ENOENT;
eb->gem_context = ctx;
if (ctx->vm)
eb->invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
eb->context_flags = 0;
if (test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags))
eb->context_flags |= __EXEC_OBJECT_NEEDS_BIAS;
return 0;
}
static int eb_lookup_vmas(struct i915_execbuffer *eb)
{
struct radix_tree_root *handles_vma = &eb->gem_context->handles_vma;
struct drm_i915_gem_object *obj;
unsigned int i, batch;
int err;
if (unlikely(i915_gem_context_is_banned(eb->gem_context)))
return -EIO;
INIT_LIST_HEAD(&eb->relocs);
INIT_LIST_HEAD(&eb->unbound);
batch = eb_batch_index(eb);
mutex_lock(&eb->gem_context->mutex);
if (unlikely(i915_gem_context_is_closed(eb->gem_context))) {
err = -ENOENT;
goto err_ctx;
}
for (i = 0; i < eb->buffer_count; i++) {
u32 handle = eb->exec[i].handle;
struct i915_lut_handle *lut;
struct i915_vma *vma;
vma = radix_tree_lookup(handles_vma, handle);
if (likely(vma))
goto add_vma;
obj = i915_gem_object_lookup(eb->file, handle);
if (unlikely(!obj)) {
err = -ENOENT;
goto err_vma;
}
vma = i915_vma_instance(obj, eb->context->vm, NULL);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto err_obj;
}
lut = i915_lut_handle_alloc();
if (unlikely(!lut)) {
err = -ENOMEM;
goto err_obj;
}
err = radix_tree_insert(handles_vma, handle, vma);
if (unlikely(err)) {
i915_lut_handle_free(lut);
goto err_obj;
}
/* transfer ref to lut */
if (!atomic_fetch_inc(&vma->open_count))
i915_vma_reopen(vma);
lut->handle = handle;
lut->ctx = eb->gem_context;
i915_gem_object_lock(obj);
list_add(&lut->obj_link, &obj->lut_list);
i915_gem_object_unlock(obj);
add_vma:
err = eb_add_vma(eb, i, batch, vma);
if (unlikely(err))
goto err_vma;
GEM_BUG_ON(vma != eb->vma[i]);
GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i]));
}
mutex_unlock(&eb->gem_context->mutex);
eb->args->flags |= __EXEC_VALIDATED;
return eb_reserve(eb);
err_obj:
i915_gem_object_put(obj);
err_vma:
eb->vma[i] = NULL;
err_ctx:
mutex_unlock(&eb->gem_context->mutex);
return err;
}
static struct i915_vma *
eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
{
if (eb->lut_size < 0) {
if (handle >= -eb->lut_size)
return NULL;
return eb->vma[handle];
} else {
struct hlist_head *head;
struct i915_vma *vma;
head = &eb->buckets[hash_32(handle, eb->lut_size)];
hlist_for_each_entry(vma, head, exec_node) {
if (vma->exec_handle == handle)
return vma;
}
return NULL;
}
}
static void eb_release_vmas(const struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
unsigned int i;
for (i = 0; i < count; i++) {
struct i915_vma *vma = eb->vma[i];
unsigned int flags = eb->flags[i];
if (!vma)
break;
GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
vma->exec_flags = NULL;
eb->vma[i] = NULL;
if (flags & __EXEC_OBJECT_HAS_PIN)
__eb_unreserve_vma(vma, flags);
if (flags & __EXEC_OBJECT_HAS_REF)
i915_vma_put(vma);
}
}
static void eb_reset_vmas(const struct i915_execbuffer *eb)
{
eb_release_vmas(eb);
if (eb->lut_size > 0)
memset(eb->buckets, 0,
sizeof(struct hlist_head) << eb->lut_size);
}
static void eb_destroy(const struct i915_execbuffer *eb)
{
GEM_BUG_ON(eb->reloc_cache.rq);
if (eb->lut_size > 0)
kfree(eb->buckets);
}
static inline u64
relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
const struct i915_vma *target)
{
return gen8_canonical_addr((int)reloc->delta + target->node.start);
}
static void reloc_cache_init(struct reloc_cache *cache,
struct drm_i915_private *i915)
{
cache->page = -1;
cache->vaddr = 0;
/* Must be a variable in the struct to allow GCC to unroll. */
cache->gen = INTEL_GEN(i915);
cache->has_llc = HAS_LLC(i915);
cache->use_64bit_reloc = HAS_64BIT_RELOC(i915);
cache->has_fence = cache->gen < 4;
cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
cache->node.allocated = false;
cache->rq = NULL;
cache->rq_size = 0;
}
static inline void *unmask_page(unsigned long p)
{
return (void *)(uintptr_t)(p & PAGE_MASK);
}
static inline unsigned int unmask_flags(unsigned long p)
{
return p & ~PAGE_MASK;
}
#define KMAP 0x4 /* after CLFLUSH_FLAGS */
static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
{
struct drm_i915_private *i915 =
container_of(cache, struct i915_execbuffer, reloc_cache)->i915;
return &i915->ggtt;
}
static void reloc_gpu_flush(struct reloc_cache *cache)
{
GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32));
cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
__i915_gem_object_flush_map(cache->rq->batch->obj, 0, cache->rq_size);
i915_gem_object_unpin_map(cache->rq->batch->obj);
intel_gt_chipset_flush(cache->rq->engine->gt);
i915_request_add(cache->rq);
cache->rq = NULL;
}
static void reloc_cache_reset(struct reloc_cache *cache)
{
void *vaddr;
if (cache->rq)
reloc_gpu_flush(cache);
if (!cache->vaddr)
return;
vaddr = unmask_page(cache->vaddr);
if (cache->vaddr & KMAP) {
if (cache->vaddr & CLFLUSH_AFTER)
mb();
kunmap_atomic(vaddr);
i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm);
} else {
struct i915_ggtt *ggtt = cache_to_ggtt(cache);
intel_gt_flush_ggtt_writes(ggtt->vm.gt);
io_mapping_unmap_atomic((void __iomem *)vaddr);
if (cache->node.allocated) {
ggtt->vm.clear_range(&ggtt->vm,
cache->node.start,
cache->node.size);
drm_mm_remove_node(&cache->node);
} else {
i915_vma_unpin((struct i915_vma *)cache->node.mm);
}
}
cache->vaddr = 0;
cache->page = -1;
}
static void *reloc_kmap(struct drm_i915_gem_object *obj,
struct reloc_cache *cache,
unsigned long page)
{
void *vaddr;
if (cache->vaddr) {
kunmap_atomic(unmask_page(cache->vaddr));
} else {
unsigned int flushes;
int err;
err = i915_gem_object_prepare_write(obj, &flushes);
if (err)
return ERR_PTR(err);
BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);
cache->vaddr = flushes | KMAP;
cache->node.mm = (void *)obj;
if (flushes)
mb();
}
vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page));
cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr;
cache->page = page;
return vaddr;
}
static void *reloc_iomap(struct drm_i915_gem_object *obj,
struct reloc_cache *cache,
unsigned long page)
{
struct i915_ggtt *ggtt = cache_to_ggtt(cache);
unsigned long offset;
void *vaddr;
if (cache->vaddr) {
intel_gt_flush_ggtt_writes(ggtt->vm.gt);
io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr));
} else {
struct i915_vma *vma;
int err;
if (use_cpu_reloc(cache, obj))
return NULL;
i915_gem_object_lock(obj);
err = i915_gem_object_set_to_gtt_domain(obj, true);
i915_gem_object_unlock(obj);
if (err)
return ERR_PTR(err);
vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
PIN_MAPPABLE |
PIN_NONBLOCK /* NOWARN */ |
PIN_NOEVICT);
if (IS_ERR(vma)) {
memset(&cache->node, 0, sizeof(cache->node));
err = drm_mm_insert_node_in_range
(&ggtt->vm.mm, &cache->node,
PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
0, ggtt->mappable_end,
DRM_MM_INSERT_LOW);
if (err) /* no inactive aperture space, use cpu reloc */
return NULL;
} else {
err = i915_vma_put_fence(vma);
if (err) {
i915_vma_unpin(vma);
return ERR_PTR(err);
}
cache->node.start = vma->node.start;
cache->node.mm = (void *)vma;
}
}
offset = cache->node.start;
if (cache->node.allocated) {
ggtt->vm.insert_page(&ggtt->vm,
i915_gem_object_get_dma_address(obj, page),
offset, I915_CACHE_NONE, 0);
} else {
offset += page << PAGE_SHIFT;
}
vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap,
offset);
cache->page = page;
cache->vaddr = (unsigned long)vaddr;
return vaddr;
}
static void *reloc_vaddr(struct drm_i915_gem_object *obj,
struct reloc_cache *cache,
unsigned long page)
{
void *vaddr;
if (cache->page == page) {
vaddr = unmask_page(cache->vaddr);
} else {
vaddr = NULL;
if ((cache->vaddr & KMAP) == 0)
vaddr = reloc_iomap(obj, cache, page);
if (!vaddr)
vaddr = reloc_kmap(obj, cache, page);
}
return vaddr;
}
static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
{
if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
if (flushes & CLFLUSH_BEFORE) {
clflushopt(addr);
mb();
}
*addr = value;
/*
* Writes to the same cacheline are serialised by the CPU
* (including clflush). On the write path, we only require
* that it hits memory in an orderly fashion and place
* mb barriers at the start and end of the relocation phase
* to ensure ordering of clflush wrt to the system.
*/
if (flushes & CLFLUSH_AFTER)
clflushopt(addr);
} else
*addr = value;
}
static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
{
struct drm_i915_gem_object *obj = vma->obj;
int err;
i915_vma_lock(vma);
if (obj->cache_dirty & ~obj->cache_coherent)
i915_gem_clflush_object(obj, 0);
obj->write_domain = 0;
err = i915_request_await_object(rq, vma->obj, true);
if (err == 0)
err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
i915_vma_unlock(vma);
return err;
}
static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
struct i915_vma *vma,
unsigned int len)
{
struct reloc_cache *cache = &eb->reloc_cache;
struct intel_engine_pool_node *pool;
struct i915_request *rq;
struct i915_vma *batch;
u32 *cmd;
int err;
pool = intel_engine_pool_get(&eb->engine->pool, PAGE_SIZE);
if (IS_ERR(pool))
return PTR_ERR(pool);
cmd = i915_gem_object_pin_map(pool->obj,
cache->has_llc ?
I915_MAP_FORCE_WB :
I915_MAP_FORCE_WC);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto out_pool;
}
batch = i915_vma_instance(pool->obj, vma->vm, NULL);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
goto err_unmap;
}
err = i915_vma_pin(batch, 0, 0, PIN_USER | PIN_NONBLOCK);
if (err)
goto err_unmap;
rq = i915_request_create(eb->context);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
goto err_unpin;
}
err = intel_engine_pool_mark_active(pool, rq);
if (err)
goto err_request;
err = reloc_move_to_gpu(rq, vma);
if (err)
goto err_request;
err = eb->engine->emit_bb_start(rq,
batch->node.start, PAGE_SIZE,
cache->gen > 5 ? 0 : I915_DISPATCH_SECURE);
if (err)
goto skip_request;
i915_vma_lock(batch);
err = i915_request_await_object(rq, batch->obj, false);
if (err == 0)
err = i915_vma_move_to_active(batch, rq, 0);
i915_vma_unlock(batch);
if (err)
goto skip_request;
rq->batch = batch;
i915_vma_unpin(batch);
cache->rq = rq;
cache->rq_cmd = cmd;
cache->rq_size = 0;
/* Return with batch mapping (cmd) still pinned */
goto out_pool;
skip_request:
i915_request_skip(rq, err);
err_request:
i915_request_add(rq);
err_unpin:
i915_vma_unpin(batch);
err_unmap:
i915_gem_object_unpin_map(pool->obj);
out_pool:
intel_engine_pool_put(pool);
return err;
}
static u32 *reloc_gpu(struct i915_execbuffer *eb,
struct i915_vma *vma,
unsigned int len)
{
struct reloc_cache *cache = &eb->reloc_cache;
u32 *cmd;
if (cache->rq_size > PAGE_SIZE/sizeof(u32) - (len + 1))
reloc_gpu_flush(cache);
if (unlikely(!cache->rq)) {
int err;
/* If we need to copy for the cmdparser, we will stall anyway */
if (eb_use_cmdparser(eb))
return ERR_PTR(-EWOULDBLOCK);
if (!intel_engine_can_store_dword(eb->engine))
return ERR_PTR(-ENODEV);
err = __reloc_gpu_alloc(eb, vma, len);
if (unlikely(err))
return ERR_PTR(err);
}
cmd = cache->rq_cmd + cache->rq_size;
cache->rq_size += len;
return cmd;
}
static u64
relocate_entry(struct i915_vma *vma,
const struct drm_i915_gem_relocation_entry *reloc,
struct i915_execbuffer *eb,
const struct i915_vma *target)
{
u64 offset = reloc->offset;
u64 target_offset = relocation_target(reloc, target);
bool wide = eb->reloc_cache.use_64bit_reloc;
void *vaddr;
if (!eb->reloc_cache.vaddr &&
(DBG_FORCE_RELOC == FORCE_GPU_RELOC ||
!reservation_object_test_signaled_rcu(vma->resv, true))) {
const unsigned int gen = eb->reloc_cache.gen;
unsigned int len;
u32 *batch;
u64 addr;
if (wide)
len = offset & 7 ? 8 : 5;
else if (gen >= 4)
len = 4;
else
len = 3;
batch = reloc_gpu(eb, vma, len);
if (IS_ERR(batch))
goto repeat;
addr = gen8_canonical_addr(vma->node.start + offset);
if (wide) {
if (offset & 7) {
*batch++ = MI_STORE_DWORD_IMM_GEN4;
*batch++ = lower_32_bits(addr);
*batch++ = upper_32_bits(addr);
*batch++ = lower_32_bits(target_offset);
addr = gen8_canonical_addr(addr + 4);
*batch++ = MI_STORE_DWORD_IMM_GEN4;
*batch++ = lower_32_bits(addr);
*batch++ = upper_32_bits(addr);
*batch++ = upper_32_bits(target_offset);
} else {
*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
*batch++ = lower_32_bits(addr);
*batch++ = upper_32_bits(addr);
*batch++ = lower_32_bits(target_offset);
*batch++ = upper_32_bits(target_offset);
}
} else if (gen >= 6) {
*batch++ = MI_STORE_DWORD_IMM_GEN4;
*batch++ = 0;
*batch++ = addr;
*batch++ = target_offset;
} else if (gen >= 4) {
*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
*batch++ = 0;
*batch++ = addr;
*batch++ = target_offset;
} else {
*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
*batch++ = addr;
*batch++ = target_offset;
}
goto out;
}
repeat:
vaddr = reloc_vaddr(vma->obj, &eb->reloc_cache, offset >> PAGE_SHIFT);
if (IS_ERR(vaddr))
return PTR_ERR(vaddr);
clflush_write32(vaddr + offset_in_page(offset),
lower_32_bits(target_offset),
eb->reloc_cache.vaddr);
if (wide) {
offset += sizeof(u32);
target_offset >>= 32;
wide = false;
goto repeat;
}
out:
return target->node.start | UPDATE;
}
static u64
eb_relocate_entry(struct i915_execbuffer *eb,
struct i915_vma *vma,
const struct drm_i915_gem_relocation_entry *reloc)
{
struct i915_vma *target;
int err;
/* we've already hold a reference to all valid objects */
target = eb_get_vma(eb, reloc->target_handle);
if (unlikely(!target))
return -ENOENT;
/* Validate that the target is in a valid r/w GPU domain */
if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) {
DRM_DEBUG("reloc with multiple write domains: "
"target %d offset %d "
"read %08x write %08x",
reloc->target_handle,
(int) reloc->offset,
reloc->read_domains,
reloc->write_domain);
return -EINVAL;
}
if (unlikely((reloc->write_domain | reloc->read_domains)
& ~I915_GEM_GPU_DOMAINS)) {
DRM_DEBUG("reloc with read/write non-GPU domains: "
"target %d offset %d "
"read %08x write %08x",
reloc->target_handle,
(int) reloc->offset,
reloc->read_domains,
reloc->write_domain);
return -EINVAL;
}
if (reloc->write_domain) {
*target->exec_flags |= EXEC_OBJECT_WRITE;
/*
* Sandybridge PPGTT errata: We need a global gtt mapping
* for MI and pipe_control writes because the gpu doesn't
* properly redirect them through the ppgtt for non_secure
* batchbuffers.
*/
if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
IS_GEN(eb->i915, 6)) {
err = i915_vma_bind(target, target->obj->cache_level,
PIN_GLOBAL);
if (WARN_ONCE(err,
"Unexpected failure to bind target VMA!"))
return err;
}
}
/*
* If the relocation already has the right value in it, no
* more work needs to be done.
*/
if (!DBG_FORCE_RELOC &&
gen8_canonical_addr(target->node.start) == reloc->presumed_offset)
return 0;
/* Check that the relocation address is valid... */
if (unlikely(reloc->offset >
vma->size - (eb->reloc_cache.use_64bit_reloc ? 8 : 4))) {
DRM_DEBUG("Relocation beyond object bounds: "
"target %d offset %d size %d.\n",
reloc->target_handle,
(int)reloc->offset,
(int)vma->size);
return -EINVAL;
}
if (unlikely(reloc->offset & 3)) {
DRM_DEBUG("Relocation not 4-byte aligned: "
"target %d offset %d.\n",
reloc->target_handle,
(int)reloc->offset);
return -EINVAL;
}
/*
* If we write into the object, we need to force the synchronisation
* barrier, either with an asynchronous clflush or if we executed the
* patching using the GPU (though that should be serialised by the
* timeline). To be completely sure, and since we are required to
* do relocations we are already stalling, disable the user's opt
* out of our synchronisation.
*/
*vma->exec_flags &= ~EXEC_OBJECT_ASYNC;
/* and update the user's relocation entry */
return relocate_entry(vma, reloc, eb, target);
}
static int eb_relocate_vma(struct i915_execbuffer *eb, struct i915_vma *vma)
{
#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
struct drm_i915_gem_relocation_entry stack[N_RELOC(512)];
struct drm_i915_gem_relocation_entry __user *urelocs;
const struct drm_i915_gem_exec_object2 *entry = exec_entry(eb, vma);
unsigned int remain;
urelocs = u64_to_user_ptr(entry->relocs_ptr);
remain = entry->relocation_count;
if (unlikely(remain > N_RELOC(ULONG_MAX)))
return -EINVAL;
/*
* We must check that the entire relocation array is safe
* to read. However, if the array is not writable the user loses
* the updated relocation values.
*/
if (unlikely(!access_ok(urelocs, remain*sizeof(*urelocs))))
return -EFAULT;
do {
struct drm_i915_gem_relocation_entry *r = stack;
unsigned int count =
min_t(unsigned int, remain, ARRAY_SIZE(stack));
unsigned int copied;
/*
* This is the fast path and we cannot handle a pagefault
* whilst holding the struct mutex lest the user pass in the
* relocations contained within a mmaped bo. For in such a case
* we, the page fault handler would call i915_gem_fault() and
* we would try to acquire the struct mutex again. Obviously
* this is bad and so lockdep complains vehemently.
*/
pagefault_disable();
copied = __copy_from_user_inatomic(r, urelocs, count * sizeof(r[0]));
pagefault_enable();
if (unlikely(copied)) {
remain = -EFAULT;
goto out;
}
remain -= count;
do {
u64 offset = eb_relocate_entry(eb, vma, r);
if (likely(offset == 0)) {
} else if ((s64)offset < 0) {
remain = (int)offset;
goto out;
} else {
/*
* Note that reporting an error now
* leaves everything in an inconsistent
* state as we have *already* changed
* the relocation value inside the
* object. As we have not changed the
* reloc.presumed_offset or will not
* change the execobject.offset, on the
* call we may not rewrite the value
* inside the object, leaving it
* dangling and causing a GPU hang. Unless
* userspace dynamically rebuilds the
* relocations on each execbuf rather than
* presume a static tree.
*
* We did previously check if the relocations
* were writable (access_ok), an error now
* would be a strange race with mprotect,
* having already demonstrated that we
* can read from this userspace address.
*/
offset = gen8_canonical_addr(offset & ~UPDATE);
if (unlikely(__put_user(offset, &urelocs[r-stack].presumed_offset))) {
remain = -EFAULT;
goto out;
}
}
} while (r++, --count);
urelocs += ARRAY_SIZE(stack);
} while (remain);
out:
reloc_cache_reset(&eb->reloc_cache);
return remain;
}
static int
eb_relocate_vma_slow(struct i915_execbuffer *eb, struct i915_vma *vma)
{
const struct drm_i915_gem_exec_object2 *entry = exec_entry(eb, vma);
struct drm_i915_gem_relocation_entry *relocs =
u64_to_ptr(typeof(*relocs), entry->relocs_ptr);
unsigned int i;
int err;
for (i = 0; i < entry->relocation_count; i++) {
u64 offset = eb_relocate_entry(eb, vma, &relocs[i]);
if ((s64)offset < 0) {
err = (int)offset;
goto err;
}
}
err = 0;
err:
reloc_cache_reset(&eb->reloc_cache);
return err;
}
static int check_relocations(const struct drm_i915_gem_exec_object2 *entry)
{
const char __user *addr, *end;
unsigned long size;
char __maybe_unused c;
size = entry->relocation_count;
if (size == 0)
return 0;
if (size > N_RELOC(ULONG_MAX))
return -EINVAL;
addr = u64_to_user_ptr(entry->relocs_ptr);
size *= sizeof(struct drm_i915_gem_relocation_entry);
if (!access_ok(addr, size))
return -EFAULT;
end = addr + size;
for (; addr < end; addr += PAGE_SIZE) {
int err = __get_user(c, addr);
if (err)
return err;
}
return __get_user(c, end - 1);
}
static int eb_copy_relocations(const struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
unsigned int i;
int err;
for (i = 0; i < count; i++) {
const unsigned int nreloc = eb->exec[i].relocation_count;
struct drm_i915_gem_relocation_entry __user *urelocs;
struct drm_i915_gem_relocation_entry *relocs;
unsigned long size;
unsigned long copied;
if (nreloc == 0)
continue;
err = check_relocations(&eb->exec[i]);
if (err)
goto err;
urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
size = nreloc * sizeof(*relocs);
relocs = kvmalloc_array(size, 1, GFP_KERNEL);
if (!relocs) {
err = -ENOMEM;
goto err;
}
/* copy_from_user is limited to < 4GiB */
copied = 0;
do {
unsigned int len =
min_t(u64, BIT_ULL(31), size - copied);
if (__copy_from_user((char *)relocs + copied,
(char __user *)urelocs + copied,
len)) {
end_user:
user_access_end();
end:
kvfree(relocs);
err = -EFAULT;
goto err;
}
copied += len;
} while (copied < size);
/*
* As we do not update the known relocation offsets after
* relocating (due to the complexities in lock handling),
* we need to mark them as invalid now so that we force the
* relocation processing next time. Just in case the target
* object is evicted and then rebound into its old
* presumed_offset before the next execbuffer - if that
* happened we would make the mistake of assuming that the
* relocations were valid.
*/
if (!user_access_begin(urelocs, size))
goto end;
for (copied = 0; copied < nreloc; copied++)
unsafe_put_user(-1,
&urelocs[copied].presumed_offset,
end_user);
user_access_end();
eb->exec[i].relocs_ptr = (uintptr_t)relocs;
}
return 0;
err:
while (i--) {
struct drm_i915_gem_relocation_entry *relocs =
u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr);
if (eb->exec[i].relocation_count)
kvfree(relocs);
}
return err;
}
static int eb_prefault_relocations(const struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
unsigned int i;
if (unlikely(i915_modparams.prefault_disable))
return 0;
for (i = 0; i < count; i++) {
int err;
err = check_relocations(&eb->exec[i]);
if (err)
return err;
}
return 0;
}
static noinline int eb_relocate_slow(struct i915_execbuffer *eb)
{
struct drm_device *dev = &eb->i915->drm;
bool have_copy = false;
struct i915_vma *vma;
int err = 0;
repeat:
if (signal_pending(current)) {
err = -ERESTARTSYS;
goto out;
}
/* We may process another execbuffer during the unlock... */
eb_reset_vmas(eb);
mutex_unlock(&dev->struct_mutex);
/*
* We take 3 passes through the slowpatch.
*
* 1 - we try to just prefault all the user relocation entries and
* then attempt to reuse the atomic pagefault disabled fast path again.
*
* 2 - we copy the user entries to a local buffer here outside of the
* local and allow ourselves to wait upon any rendering before
* relocations
*
* 3 - we already have a local copy of the relocation entries, but
* were interrupted (EAGAIN) whilst waiting for the objects, try again.
*/
if (!err) {
err = eb_prefault_relocations(eb);
} else if (!have_copy) {
err = eb_copy_relocations(eb);
have_copy = err == 0;
} else {
cond_resched();
err = 0;
}
if (err) {
mutex_lock(&dev->struct_mutex);
goto out;
}
/* A frequent cause for EAGAIN are currently unavailable client pages */
flush_workqueue(eb->i915->mm.userptr_wq);
err = i915_mutex_lock_interruptible(dev);
if (err) {
mutex_lock(&dev->struct_mutex);
goto out;
}
/* reacquire the objects */
err = eb_lookup_vmas(eb);
if (err)
goto err;
GEM_BUG_ON(!eb->batch);
list_for_each_entry(vma, &eb->relocs, reloc_link) {
if (!have_copy) {
pagefault_disable();
err = eb_relocate_vma(eb, vma);
pagefault_enable();
if (err)
goto repeat;
} else {
err = eb_relocate_vma_slow(eb, vma);
if (err)
goto err;
}
}
/*
* Leave the user relocations as are, this is the painfully slow path,
* and we want to avoid the complication of dropping the lock whilst
* having buffers reserved in the aperture and so causing spurious
* ENOSPC for random operations.
*/
err:
if (err == -EAGAIN)
goto repeat;
out:
if (have_copy) {
const unsigned int count = eb->buffer_count;
unsigned int i;
for (i = 0; i < count; i++) {
const struct drm_i915_gem_exec_object2 *entry =
&eb->exec[i];
struct drm_i915_gem_relocation_entry *relocs;
if (!entry->relocation_count)
continue;
relocs = u64_to_ptr(typeof(*relocs), entry->relocs_ptr);
kvfree(relocs);
}
}
return err;
}
static int eb_relocate(struct i915_execbuffer *eb)
{
if (eb_lookup_vmas(eb))
goto slow;
/* The objects are in their final locations, apply the relocations. */
if (eb->args->flags & __EXEC_HAS_RELOC) {
struct i915_vma *vma;
list_for_each_entry(vma, &eb->relocs, reloc_link) {
if (eb_relocate_vma(eb, vma))
goto slow;
}
}
return 0;
slow:
return eb_relocate_slow(eb);
}
static int eb_move_to_gpu(struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
struct ww_acquire_ctx acquire;
unsigned int i;
int err = 0;
ww_acquire_init(&acquire, &reservation_ww_class);
for (i = 0; i < count; i++) {
struct i915_vma *vma = eb->vma[i];
err = ww_mutex_lock_interruptible(&vma->resv->lock, &acquire);
if (!err)
continue;
GEM_BUG_ON(err == -EALREADY); /* No duplicate vma */
if (err == -EDEADLK) {
GEM_BUG_ON(i == 0);
do {
int j = i - 1;
ww_mutex_unlock(&eb->vma[j]->resv->lock);
swap(eb->flags[i], eb->flags[j]);
swap(eb->vma[i], eb->vma[j]);
eb->vma[i]->exec_flags = &eb->flags[i];
} while (--i);
GEM_BUG_ON(vma != eb->vma[0]);
vma->exec_flags = &eb->flags[0];
err = ww_mutex_lock_slow_interruptible(&vma->resv->lock,
&acquire);
}
if (err)
break;
}
ww_acquire_done(&acquire);
while (i--) {
unsigned int flags = eb->flags[i];
struct i915_vma *vma = eb->vma[i];
struct drm_i915_gem_object *obj = vma->obj;
assert_vma_held(vma);
if (flags & EXEC_OBJECT_CAPTURE) {
struct i915_capture_list *capture;
capture = kmalloc(sizeof(*capture), GFP_KERNEL);
if (capture) {
capture->next = eb->request->capture_list;
capture->vma = vma;
eb->request->capture_list = capture;
}
}
/*
* If the GPU is not _reading_ through the CPU cache, we need
* to make sure that any writes (both previous GPU writes from
* before a change in snooping levels and normal CPU writes)
* caught in that cache are flushed to main memory.
*
* We want to say
* obj->cache_dirty &&
* !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ)
* but gcc's optimiser doesn't handle that as well and emits
* two jumps instead of one. Maybe one day...
*/
if (unlikely(obj->cache_dirty & ~obj->cache_coherent)) {
if (i915_gem_clflush_object(obj, 0))
flags &= ~EXEC_OBJECT_ASYNC;
}
if (err == 0 && !(flags & EXEC_OBJECT_ASYNC)) {
err = i915_request_await_object
(eb->request, obj, flags & EXEC_OBJECT_WRITE);
}
if (err == 0)
err = i915_vma_move_to_active(vma, eb->request, flags);
i915_vma_unlock(vma);
__eb_unreserve_vma(vma, flags);
vma->exec_flags = NULL;
if (unlikely(flags & __EXEC_OBJECT_HAS_REF))
i915_vma_put(vma);
}
ww_acquire_fini(&acquire);
if (unlikely(err))
goto err_skip;
eb->exec = NULL;
/* Unconditionally flush any chipset caches (for streaming writes). */
intel_gt_chipset_flush(eb->engine->gt);
return 0;
err_skip:
i915_request_skip(eb->request, err);
return err;
}
static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
{
if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS)
return false;
/* Kernel clipping was a DRI1 misfeature */
if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
if (exec->num_cliprects || exec->cliprects_ptr)
return false;
}
if (exec->DR4 == 0xffffffff) {
DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
exec->DR4 = 0;
}
if (exec->DR1 || exec->DR4)
return false;
if ((exec->batch_start_offset | exec->batch_len) & 0x7)
return false;
return true;
}
static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
{
u32 *cs;
int i;
if (!IS_GEN(rq->i915, 7) || rq->engine->id != RCS0) {
DRM_DEBUG("sol reset is gen7/rcs only\n");
return -EINVAL;
}
cs = intel_ring_begin(rq, 4 * 2 + 2);
if (IS_ERR(cs))
return PTR_ERR(cs);
*cs++ = MI_LOAD_REGISTER_IMM(4);
for (i = 0; i < 4; i++) {
*cs++ = i915_mmio_reg_offset(GEN7_SO_WRITE_OFFSET(i));
*cs++ = 0;
}
*cs++ = MI_NOOP;
intel_ring_advance(rq, cs);
return 0;
}
static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
{
struct intel_engine_pool_node *pool;
struct i915_vma *vma;
int err;
pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
if (IS_ERR(pool))
return ERR_CAST(pool);
err = intel_engine_cmd_parser(eb->engine,
eb->batch->obj,
pool->obj,
eb->batch_start_offset,
eb->batch_len,
is_master);
if (err) {
if (err == -EACCES) /* unhandled chained batch */
vma = NULL;
else
vma = ERR_PTR(err);
goto err;
}
vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
if (IS_ERR(vma))
goto err;
eb->vma[eb->buffer_count] = i915_vma_get(vma);
eb->flags[eb->buffer_count] =
__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
vma->exec_flags = &eb->flags[eb->buffer_count];
eb->buffer_count++;
vma->private = pool;
return vma;
err:
intel_engine_pool_put(pool);
return vma;
}
static void
add_to_client(struct i915_request *rq, struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
rq->file_priv = file_priv;
spin_lock(&file_priv->mm.lock);
list_add_tail(&rq->client_link, &file_priv->mm.request_list);
spin_unlock(&file_priv->mm.lock);
}
static int eb_submit(struct i915_execbuffer *eb)
{
int err;
err = eb_move_to_gpu(eb);
if (err)
return err;
if (eb->args->flags & I915_EXEC_GEN7_SOL_RESET) {
err = i915_reset_gen7_sol_offsets(eb->request);
if (err)
return err;
}
/*
* After we completed waiting for other engines (using HW semaphores)
* then we can signal that this request/batch is ready to run. This
* allows us to determine if the batch is still waiting on the GPU
* or actually running by checking the breadcrumb.
*/
if (eb->engine->emit_init_breadcrumb) {
err = eb->engine->emit_init_breadcrumb(eb->request);
if (err)
return err;
}
err = eb->engine->emit_bb_start(eb->request,
eb->batch->node.start +
eb->batch_start_offset,
eb->batch_len,
eb->batch_flags);
if (err)
return err;
return 0;
}
static int num_vcs_engines(const struct drm_i915_private *i915)
{
return hweight64(INTEL_INFO(i915)->engine_mask &
GENMASK_ULL(VCS0 + I915_MAX_VCS - 1, VCS0));
}
/*
* Find one BSD ring to dispatch the corresponding BSD command.
* The engine index is returned.
*/
static unsigned int
gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv,
struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
/* Check whether the file_priv has already selected one ring. */
if ((int)file_priv->bsd_engine < 0)
file_priv->bsd_engine =
get_random_int() % num_vcs_engines(dev_priv);
return file_priv->bsd_engine;
}
static const enum intel_engine_id user_ring_map[] = {
[I915_EXEC_DEFAULT] = RCS0,
[I915_EXEC_RENDER] = RCS0,
[I915_EXEC_BLT] = BCS0,
[I915_EXEC_BSD] = VCS0,
[I915_EXEC_VEBOX] = VECS0
};
static struct i915_request *eb_throttle(struct intel_context *ce)
{
struct intel_ring *ring = ce->ring;
struct intel_timeline *tl = ce->timeline;
struct i915_request *rq;
/*
* Completely unscientific finger-in-the-air estimates for suitable
* maximum user request size (to avoid blocking) and then backoff.
*/
if (intel_ring_update_space(ring) >= PAGE_SIZE)
return NULL;
/*
* Find a request that after waiting upon, there will be at least half
* the ring available. The hysteresis allows us to compete for the
* shared ring and should mean that we sleep less often prior to
* claiming our resources, but not so long that the ring completely
* drains before we can submit our next request.
*/
list_for_each_entry(rq, &tl->requests, link) {
if (rq->ring != ring)
continue;
if (__intel_ring_space(rq->postfix,
ring->emit, ring->size) > ring->size / 2)
break;
}
if (&rq->link == &tl->requests)
return NULL; /* weird, we will check again later for real */
return i915_request_get(rq);
}
static int
__eb_pin_context(struct i915_execbuffer *eb, struct intel_context *ce)
{
int err;
if (likely(atomic_inc_not_zero(&ce->pin_count)))
return 0;
err = mutex_lock_interruptible(&eb->i915->drm.struct_mutex);
if (err)
return err;
err = __intel_context_do_pin(ce);
mutex_unlock(&eb->i915->drm.struct_mutex);
return err;
}
static void
__eb_unpin_context(struct i915_execbuffer *eb, struct intel_context *ce)
{
if (likely(atomic_add_unless(&ce->pin_count, -1, 1)))
return;
mutex_lock(&eb->i915->drm.struct_mutex);
intel_context_unpin(ce);
mutex_unlock(&eb->i915->drm.struct_mutex);
}
static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
{
struct intel_timeline *tl;
struct i915_request *rq;
int err;
/*
* ABI: Before userspace accesses the GPU (e.g. execbuffer), report
* EIO if the GPU is already wedged.
*/
err = intel_gt_terminally_wedged(ce->engine->gt);
if (err)
return err;
/*
* Pinning the contexts may generate requests in order to acquire
* GGTT space, so do this first before we reserve a seqno for
* ourselves.
*/
err = __eb_pin_context(eb, ce);
if (err)
return err;
/*
* Take a local wakeref for preparing to dispatch the execbuf as
* we expect to access the hardware fairly frequently in the
* process, and require the engine to be kept awake between accesses.
* Upon dispatch, we acquire another prolonged wakeref that we hold
* until the timeline is idle, which in turn releases the wakeref
* taken on the engine, and the parent device.
*/
tl = intel_context_timeline_lock(ce);
if (IS_ERR(tl)) {
err = PTR_ERR(tl);
goto err_unpin;
}
intel_context_enter(ce);
rq = eb_throttle(ce);
intel_context_timeline_unlock(tl);
if (rq) {
if (i915_request_wait(rq,
I915_WAIT_INTERRUPTIBLE,
MAX_SCHEDULE_TIMEOUT) < 0) {
i915_request_put(rq);
err = -EINTR;
goto err_exit;
}
i915_request_put(rq);
}
eb->engine = ce->engine;
eb->context = ce;
return 0;
err_exit:
mutex_lock(&tl->mutex);
intel_context_exit(ce);
intel_context_timeline_unlock(tl);
err_unpin:
__eb_unpin_context(eb, ce);
return err;
}
static void eb_unpin_engine(struct i915_execbuffer *eb)
{
struct intel_context *ce = eb->context;
struct intel_timeline *tl = ce->timeline;
mutex_lock(&tl->mutex);
intel_context_exit(ce);
mutex_unlock(&tl->mutex);
__eb_unpin_context(eb, ce);
}
static unsigned int
eb_select_legacy_ring(struct i915_execbuffer *eb,
struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args)
{
struct drm_i915_private *i915 = eb->i915;
unsigned int user_ring_id = args->flags & I915_EXEC_RING_MASK;
if (user_ring_id != I915_EXEC_BSD &&
(args->flags & I915_EXEC_BSD_MASK)) {
DRM_DEBUG("execbuf with non bsd ring but with invalid "
"bsd dispatch flags: %d\n", (int)(args->flags));
return -1;
}
if (user_ring_id == I915_EXEC_BSD && num_vcs_engines(i915) > 1) {
unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK;
if (bsd_idx == I915_EXEC_BSD_DEFAULT) {
bsd_idx = gen8_dispatch_bsd_engine(i915, file);
} else if (bsd_idx >= I915_EXEC_BSD_RING1 &&
bsd_idx <= I915_EXEC_BSD_RING2) {
bsd_idx >>= I915_EXEC_BSD_SHIFT;
bsd_idx--;
} else {
DRM_DEBUG("execbuf with unknown bsd ring: %u\n",
bsd_idx);
return -1;
}
return _VCS(bsd_idx);
}
if (user_ring_id >= ARRAY_SIZE(user_ring_map)) {
DRM_DEBUG("execbuf with unknown ring: %u\n", user_ring_id);
return -1;
}
return user_ring_map[user_ring_id];
}
static int
eb_pin_engine(struct i915_execbuffer *eb,
struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args)
{
struct intel_context *ce;
unsigned int idx;
int err;
if (i915_gem_context_user_engines(eb->gem_context))
idx = args->flags & I915_EXEC_RING_MASK;
else
idx = eb_select_legacy_ring(eb, file, args);
ce = i915_gem_context_get_engine(eb->gem_context, idx);
if (IS_ERR(ce))
return PTR_ERR(ce);
err = __eb_pin_engine(eb, ce);
intel_context_put(ce);
return err;
}
static void
__free_fence_array(struct drm_syncobj **fences, unsigned int n)
{
while (n--)
drm_syncobj_put(ptr_mask_bits(fences[n], 2));
kvfree(fences);
}
static struct drm_syncobj **
get_fence_array(struct drm_i915_gem_execbuffer2 *args,
struct drm_file *file)
{
const unsigned long nfences = args->num_cliprects;
struct drm_i915_gem_exec_fence __user *user;
struct drm_syncobj **fences;
unsigned long n;
int err;
if (!(args->flags & I915_EXEC_FENCE_ARRAY))
return NULL;
/* Check multiplication overflow for access_ok() and kvmalloc_array() */
BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
if (nfences > min_t(unsigned long,
ULONG_MAX / sizeof(*user),
SIZE_MAX / sizeof(*fences)))
return ERR_PTR(-EINVAL);
user = u64_to_user_ptr(args->cliprects_ptr);
if (!access_ok(user, nfences * sizeof(*user)))
return ERR_PTR(-EFAULT);
fences = kvmalloc_array(nfences, sizeof(*fences),
__GFP_NOWARN | GFP_KERNEL);
if (!fences)
return ERR_PTR(-ENOMEM);
for (n = 0; n < nfences; n++) {
struct drm_i915_gem_exec_fence fence;
struct drm_syncobj *syncobj;
if (__copy_from_user(&fence, user++, sizeof(fence))) {
err = -EFAULT;
goto err;
}
if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
err = -EINVAL;
goto err;
}
syncobj = drm_syncobj_find(file, fence.handle);
if (!syncobj) {
DRM_DEBUG("Invalid syncobj handle provided\n");
err = -ENOENT;
goto err;
}
BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
}
return fences;
err:
__free_fence_array(fences, n);
return ERR_PTR(err);
}
static void
put_fence_array(struct drm_i915_gem_execbuffer2 *args,
struct drm_syncobj **fences)
{
if (fences)
__free_fence_array(fences, args->num_cliprects);
}
static int
await_fence_array(struct i915_execbuffer *eb,
struct drm_syncobj **fences)
{
const unsigned int nfences = eb->args->num_cliprects;
unsigned int n;
int err;
for (n = 0; n < nfences; n++) {
struct drm_syncobj *syncobj;
struct dma_fence *fence;
unsigned int flags;
syncobj = ptr_unpack_bits(fences[n], &flags, 2);
if (!(flags & I915_EXEC_FENCE_WAIT))
continue;
fence = drm_syncobj_fence_get(syncobj);
if (!fence)
return -EINVAL;
err = i915_request_await_dma_fence(eb->request, fence);
dma_fence_put(fence);
if (err < 0)
return err;
}
return 0;
}
static void
signal_fence_array(struct i915_execbuffer *eb,
struct drm_syncobj **fences)
{
const unsigned int nfences = eb->args->num_cliprects;
struct dma_fence * const fence = &eb->request->fence;
unsigned int n;
for (n = 0; n < nfences; n++) {
struct drm_syncobj *syncobj;
unsigned int flags;
syncobj = ptr_unpack_bits(fences[n], &flags, 2);
if (!(flags & I915_EXEC_FENCE_SIGNAL))
continue;
drm_syncobj_replace_fence(syncobj, fence);
}
}
static int
i915_gem_do_execbuffer(struct drm_device *dev,
struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args,
struct drm_i915_gem_exec_object2 *exec,
struct drm_syncobj **fences)
{
struct i915_execbuffer eb;
struct dma_fence *in_fence = NULL;
struct dma_fence *exec_fence = NULL;
struct sync_file *out_fence = NULL;
int out_fence_fd = -1;
int err;
BUILD_BUG_ON(__EXEC_INTERNAL_FLAGS & ~__I915_EXEC_ILLEGAL_FLAGS);
BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
~__EXEC_OBJECT_UNKNOWN_FLAGS);
eb.i915 = to_i915(dev);
eb.file = file;
eb.args = args;
if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
args->flags |= __EXEC_HAS_RELOC;
eb.exec = exec;
eb.vma = (struct i915_vma **)(exec + args->buffer_count + 1);
eb.vma[0] = NULL;
eb.flags = (unsigned int *)(eb.vma + args->buffer_count + 1);
eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
reloc_cache_init(&eb.reloc_cache, eb.i915);
eb.buffer_count = args->buffer_count;
eb.batch_start_offset = args->batch_start_offset;
eb.batch_len = args->batch_len;
eb.batch_flags = 0;
if (args->flags & I915_EXEC_SECURE) {
if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
return -EPERM;
eb.batch_flags |= I915_DISPATCH_SECURE;
}
if (args->flags & I915_EXEC_IS_PINNED)
eb.batch_flags |= I915_DISPATCH_PINNED;
if (args->flags & I915_EXEC_FENCE_IN) {
in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
if (!in_fence)
return -EINVAL;
}
if (args->flags & I915_EXEC_FENCE_SUBMIT) {
if (in_fence) {
err = -EINVAL;
goto err_in_fence;
}
exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
if (!exec_fence) {
err = -EINVAL;
goto err_in_fence;
}
}
if (args->flags & I915_EXEC_FENCE_OUT) {
out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
if (out_fence_fd < 0) {
err = out_fence_fd;
goto err_exec_fence;
}
}
err = eb_create(&eb);
if (err)
goto err_out_fence;
GEM_BUG_ON(!eb.lut_size);
err = eb_select_context(&eb);
if (unlikely(err))
goto err_destroy;
err = eb_pin_engine(&eb, file, args);
if (unlikely(err))
goto err_context;
err = i915_mutex_lock_interruptible(dev);
if (err)
goto err_engine;
err = eb_relocate(&eb);
if (err) {
/*
* If the user expects the execobject.offset and
* reloc.presumed_offset to be an exact match,
* as for using NO_RELOC, then we cannot update
* the execobject.offset until we have completed
* relocation.
*/
args->flags &= ~__EXEC_HAS_RELOC;
goto err_vma;
}
if (unlikely(*eb.batch->exec_flags & EXEC_OBJECT_WRITE)) {
DRM_DEBUG("Attempting to use self-modifying batch buffer\n");
err = -EINVAL;
goto err_vma;
}
if (eb.batch_start_offset > eb.batch->size ||
eb.batch_len > eb.batch->size - eb.batch_start_offset) {
DRM_DEBUG("Attempting to use out-of-bounds batch\n");
err = -EINVAL;
goto err_vma;
}
if (eb_use_cmdparser(&eb)) {
struct i915_vma *vma;
vma = eb_parse(&eb, drm_is_current_master(file));
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto err_vma;
}
if (vma) {
/*
* Batch parsed and accepted:
*
* Set the DISPATCH_SECURE bit to remove the NON_SECURE
* bit from MI_BATCH_BUFFER_START commands issued in
* the dispatch_execbuffer implementations. We
* specifically don't want that set on batches the
* command parser has accepted.
*/
eb.batch_flags |= I915_DISPATCH_SECURE;
eb.batch_start_offset = 0;
eb.batch = vma;
}
}
if (eb.batch_len == 0)
eb.batch_len = eb.batch->size - eb.batch_start_offset;
/*
* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
* batch" bit. Hence we need to pin secure batches into the global gtt.
* hsw should have this fixed, but bdw mucks it up again. */
if (eb.batch_flags & I915_DISPATCH_SECURE) {
struct i915_vma *vma;
/*
* So on first glance it looks freaky that we pin the batch here
* outside of the reservation loop. But:
* - The batch is already pinned into the relevant ppgtt, so we
* already have the backing storage fully allocated.
* - No other BO uses the global gtt (well contexts, but meh),
* so we don't really have issues with multiple objects not
* fitting due to fragmentation.
* So this is actually safe.
*/
vma = i915_gem_object_ggtt_pin(eb.batch->obj, NULL, 0, 0, 0);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto err_vma;
}
eb.batch = vma;
}
/* All GPU relocation batches must be submitted prior to the user rq */
GEM_BUG_ON(eb.reloc_cache.rq);
/* Allocate a request for this batch buffer nice and early. */
eb.request = i915_request_create(eb.context);
if (IS_ERR(eb.request)) {
err = PTR_ERR(eb.request);
goto err_batch_unpin;
}
if (in_fence) {
err = i915_request_await_dma_fence(eb.request, in_fence);
if (err < 0)
goto err_request;
}
if (exec_fence) {
err = i915_request_await_execution(eb.request, exec_fence,
eb.engine->bond_execute);
if (err < 0)
goto err_request;
}
if (fences) {
err = await_fence_array(&eb, fences);
if (err)
goto err_request;
}
if (out_fence_fd != -1) {
out_fence = sync_file_create(&eb.request->fence);
if (!out_fence) {
err = -ENOMEM;
goto err_request;
}
}
/*
* Whilst this request exists, batch_obj will be on the
* active_list, and so will hold the active reference. Only when this
* request is retired will the the batch_obj be moved onto the
* inactive_list and lose its active reference. Hence we do not need
* to explicitly hold another reference here.
*/
eb.request->batch = eb.batch;
if (eb.batch->private)
intel_engine_pool_mark_active(eb.batch->private, eb.request);
trace_i915_request_queue(eb.request, eb.batch_flags);
err = eb_submit(&eb);
err_request:
add_to_client(eb.request, file);
i915_request_add(eb.request);
if (fences)
signal_fence_array(&eb, fences);
if (out_fence) {
if (err == 0) {
fd_install(out_fence_fd, out_fence->file);
args->rsvd2 &= GENMASK_ULL(31, 0); /* keep in-fence */
args->rsvd2 |= (u64)out_fence_fd << 32;
out_fence_fd = -1;
} else {
fput(out_fence->file);
}
}
err_batch_unpin:
if (eb.batch_flags & I915_DISPATCH_SECURE)
i915_vma_unpin(eb.batch);
if (eb.batch->private)
intel_engine_pool_put(eb.batch->private);
err_vma:
if (eb.exec)
eb_release_vmas(&eb);
mutex_unlock(&dev->struct_mutex);
err_engine:
eb_unpin_engine(&eb);
err_context:
i915_gem_context_put(eb.gem_context);
err_destroy:
eb_destroy(&eb);
err_out_fence:
if (out_fence_fd != -1)
put_unused_fd(out_fence_fd);
err_exec_fence:
dma_fence_put(exec_fence);
err_in_fence:
dma_fence_put(in_fence);
return err;
}
static size_t eb_element_size(void)
{
return (sizeof(struct drm_i915_gem_exec_object2) +
sizeof(struct i915_vma *) +
sizeof(unsigned int));
}
static bool check_buffer_count(size_t count)
{
const size_t sz = eb_element_size();
/*
* When using LUT_HANDLE, we impose a limit of INT_MAX for the lookup
* array size (see eb_create()). Otherwise, we can accept an array as
* large as can be addressed (though use large arrays at your peril)!
*/
return !(count < 1 || count > INT_MAX || count > SIZE_MAX / sz - 1);
}
/*
* Legacy execbuffer just creates an exec2 list from the original exec object
* list array and passes it to the real function.
*/
int
i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_execbuffer *args = data;
struct drm_i915_gem_execbuffer2 exec2;
struct drm_i915_gem_exec_object *exec_list = NULL;
struct drm_i915_gem_exec_object2 *exec2_list = NULL;
const size_t count = args->buffer_count;
unsigned int i;
int err;
if (!check_buffer_count(count)) {
DRM_DEBUG("execbuf2 with %zd buffers\n", count);
return -EINVAL;
}
exec2.buffers_ptr = args->buffers_ptr;
exec2.buffer_count = args->buffer_count;
exec2.batch_start_offset = args->batch_start_offset;
exec2.batch_len = args->batch_len;
exec2.DR1 = args->DR1;
exec2.DR4 = args->DR4;
exec2.num_cliprects = args->num_cliprects;
exec2.cliprects_ptr = args->cliprects_ptr;
exec2.flags = I915_EXEC_RENDER;
i915_execbuffer2_set_context_id(exec2, 0);
if (!i915_gem_check_execbuffer(&exec2))
return -EINVAL;
/* Copy in the exec list from userland */
exec_list = kvmalloc_array(count, sizeof(*exec_list),
__GFP_NOWARN | GFP_KERNEL);
exec2_list = kvmalloc_array(count + 1, eb_element_size(),
__GFP_NOWARN | GFP_KERNEL);
if (exec_list == NULL || exec2_list == NULL) {
DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
args->buffer_count);
kvfree(exec_list);
kvfree(exec2_list);
return -ENOMEM;
}
err = copy_from_user(exec_list,
u64_to_user_ptr(args->buffers_ptr),
sizeof(*exec_list) * count);
if (err) {
DRM_DEBUG("copy %d exec entries failed %d\n",
args->buffer_count, err);
kvfree(exec_list);
kvfree(exec2_list);
return -EFAULT;
}
for (i = 0; i < args->buffer_count; i++) {
exec2_list[i].handle = exec_list[i].handle;
exec2_list[i].relocation_count = exec_list[i].relocation_count;
exec2_list[i].relocs_ptr = exec_list[i].relocs_ptr;
exec2_list[i].alignment = exec_list[i].alignment;
exec2_list[i].offset = exec_list[i].offset;
if (INTEL_GEN(to_i915(dev)) < 4)
exec2_list[i].flags = EXEC_OBJECT_NEEDS_FENCE;
else
exec2_list[i].flags = 0;
}
err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
if (exec2.flags & __EXEC_HAS_RELOC) {
struct drm_i915_gem_exec_object __user *user_exec_list =
u64_to_user_ptr(args->buffers_ptr);
/* Copy the new buffer offsets back to the user's exec list. */
for (i = 0; i < args->buffer_count; i++) {
if (!(exec2_list[i].offset & UPDATE))
continue;
exec2_list[i].offset =
gen8_canonical_addr(exec2_list[i].offset & PIN_OFFSET_MASK);
exec2_list[i].offset &= PIN_OFFSET_MASK;
if (__copy_to_user(&user_exec_list[i].offset,
&exec2_list[i].offset,
sizeof(user_exec_list[i].offset)))
break;
}
}
kvfree(exec_list);
kvfree(exec2_list);
return err;
}
int
i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_execbuffer2 *args = data;
struct drm_i915_gem_exec_object2 *exec2_list;
struct drm_syncobj **fences = NULL;
const size_t count = args->buffer_count;
int err;
if (!check_buffer_count(count)) {
DRM_DEBUG("execbuf2 with %zd buffers\n", count);
return -EINVAL;
}
if (!i915_gem_check_execbuffer(args))
return -EINVAL;
/* Allocate an extra slot for use by the command parser */
exec2_list = kvmalloc_array(count + 1, eb_element_size(),
__GFP_NOWARN | GFP_KERNEL);
if (exec2_list == NULL) {
DRM_DEBUG("Failed to allocate exec list for %zd buffers\n",
count);
return -ENOMEM;
}
if (copy_from_user(exec2_list,
u64_to_user_ptr(args->buffers_ptr),
sizeof(*exec2_list) * count)) {
DRM_DEBUG("copy %zd exec entries failed\n", count);
kvfree(exec2_list);
return -EFAULT;
}
if (args->flags & I915_EXEC_FENCE_ARRAY) {
fences = get_fence_array(args, file);
if (IS_ERR(fences)) {
kvfree(exec2_list);
return PTR_ERR(fences);
}
}
err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
/*
* Now that we have begun execution of the batchbuffer, we ignore
* any new error after this point. Also given that we have already
* updated the associated relocations, we try to write out the current
* object locations irrespective of any error.
*/
if (args->flags & __EXEC_HAS_RELOC) {
struct drm_i915_gem_exec_object2 __user *user_exec_list =
u64_to_user_ptr(args->buffers_ptr);
unsigned int i;
/* Copy the new buffer offsets back to the user's exec list. */
/*
* Note: count * sizeof(*user_exec_list) does not overflow,
* because we checked 'count' in check_buffer_count().
*
* And this range already got effectively checked earlier
* when we did the "copy_from_user()" above.
*/
if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
goto end;
for (i = 0; i < args->buffer_count; i++) {
if (!(exec2_list[i].offset & UPDATE))
continue;
exec2_list[i].offset =
gen8_canonical_addr(exec2_list[i].offset & PIN_OFFSET_MASK);
unsafe_put_user(exec2_list[i].offset,
&user_exec_list[i].offset,
end_user);
}
end_user:
user_access_end();
end:;
}
args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
put_fence_array(args, fences);
kvfree(exec2_list);
return err;
}
|