summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/gt/intel_lrc.c
blob: bbeeb6dde7aee2d70737d1127d8284622a510b31 (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
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2014 Intel Corporation
 */

#include "gem/i915_gem_lmem.h"

#include "gen8_engine_cs.h"
#include "i915_drv.h"
#include "i915_perf.h"
#include "i915_reg.h"
#include "intel_context.h"
#include "intel_engine.h"
#include "intel_engine_regs.h"
#include "intel_gpu_commands.h"
#include "intel_gt.h"
#include "intel_gt_regs.h"
#include "intel_lrc.h"
#include "intel_lrc_reg.h"
#include "intel_ring.h"
#include "shmem_utils.h"

/*
 * The per-platform tables are u8-encoded in @data. Decode @data and set the
 * addresses' offset and commands in @regs. The following encoding is used
 * for each byte. There are 2 steps: decoding commands and decoding addresses.
 *
 * Commands:
 * [7]: create NOPs - number of NOPs are set in lower bits
 * [6]: When creating MI_LOAD_REGISTER_IMM command, allow to set
 *      MI_LRI_FORCE_POSTED
 * [5:0]: Number of NOPs or registers to set values to in case of
 *        MI_LOAD_REGISTER_IMM
 *
 * Addresses: these are decoded after a MI_LOAD_REGISTER_IMM command by "count"
 * number of registers. They are set by using the REG/REG16 macros: the former
 * is used for offsets smaller than 0x200 while the latter is for values bigger
 * than that. Those macros already set all the bits documented below correctly:
 *
 * [7]: When a register offset needs more than 6 bits, use additional bytes, to
 *      follow, for the lower bits
 * [6:0]: Register offset, without considering the engine base.
 *
 * This function only tweaks the commands and register offsets. Values are not
 * filled out.
 */
static void set_offsets(u32 *regs,
			const u8 *data,
			const struct intel_engine_cs *engine,
			bool close)
#define NOP(x) (BIT(7) | (x))
#define LRI(count, flags) ((flags) << 6 | (count) | BUILD_BUG_ON_ZERO(count >= BIT(6)))
#define POSTED BIT(0)
#define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
#define REG16(x) \
	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
	(((x) >> 2) & 0x7f)
#define END 0
{
	const u32 base = engine->mmio_base;

	while (*data) {
		u8 count, flags;

		if (*data & BIT(7)) { /* skip */
			count = *data++ & ~BIT(7);
			regs += count;
			continue;
		}

		count = *data & 0x3f;
		flags = *data >> 6;
		data++;

		*regs = MI_LOAD_REGISTER_IMM(count);
		if (flags & POSTED)
			*regs |= MI_LRI_FORCE_POSTED;
		if (GRAPHICS_VER(engine->i915) >= 11)
			*regs |= MI_LRI_LRM_CS_MMIO;
		regs++;

		GEM_BUG_ON(!count);
		do {
			u32 offset = 0;
			u8 v;

			do {
				v = *data++;
				offset <<= 7;
				offset |= v & ~BIT(7);
			} while (v & BIT(7));

			regs[0] = base + (offset << 2);
			regs += 2;
		} while (--count);
	}

	if (close) {
		/* Close the batch; used mainly by live_lrc_layout() */
		*regs = MI_BATCH_BUFFER_END;
		if (GRAPHICS_VER(engine->i915) >= 11)
			*regs |= BIT(0);
	}
}

static const u8 gen8_xcs_offsets[] = {
	NOP(1),
	LRI(11, 0),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x11c),
	REG(0x114),
	REG(0x118),

	NOP(9),
	LRI(9, 0),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	NOP(13),
	LRI(2, 0),
	REG16(0x200),
	REG(0x028),

	END
};

static const u8 gen9_xcs_offsets[] = {
	NOP(1),
	LRI(14, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x11c),
	REG(0x114),
	REG(0x118),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),

	NOP(3),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	NOP(13),
	LRI(1, POSTED),
	REG16(0x200),

	NOP(13),
	LRI(44, POSTED),
	REG(0x028),
	REG(0x09c),
	REG(0x0c0),
	REG(0x178),
	REG(0x17c),
	REG16(0x358),
	REG(0x170),
	REG(0x150),
	REG(0x154),
	REG(0x158),
	REG16(0x41c),
	REG16(0x600),
	REG16(0x604),
	REG16(0x608),
	REG16(0x60c),
	REG16(0x610),
	REG16(0x614),
	REG16(0x618),
	REG16(0x61c),
	REG16(0x620),
	REG16(0x624),
	REG16(0x628),
	REG16(0x62c),
	REG16(0x630),
	REG16(0x634),
	REG16(0x638),
	REG16(0x63c),
	REG16(0x640),
	REG16(0x644),
	REG16(0x648),
	REG16(0x64c),
	REG16(0x650),
	REG16(0x654),
	REG16(0x658),
	REG16(0x65c),
	REG16(0x660),
	REG16(0x664),
	REG16(0x668),
	REG16(0x66c),
	REG16(0x670),
	REG16(0x674),
	REG16(0x678),
	REG16(0x67c),
	REG(0x068),

	END
};

static const u8 gen12_xcs_offsets[] = {
	NOP(1),
	LRI(13, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),

	NOP(5),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	END
};

static const u8 dg2_xcs_offsets[] = {
	NOP(1),
	LRI(15, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),
	REG(0x120),
	REG(0x124),

	NOP(1),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	END
};

static const u8 gen8_rcs_offsets[] = {
	NOP(1),
	LRI(14, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x11c),
	REG(0x114),
	REG(0x118),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),

	NOP(3),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	NOP(13),
	LRI(1, 0),
	REG(0x0c8),

	END
};

static const u8 gen9_rcs_offsets[] = {
	NOP(1),
	LRI(14, POSTED),
	REG16(0x244),
	REG(0x34),
	REG(0x30),
	REG(0x38),
	REG(0x3c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x11c),
	REG(0x114),
	REG(0x118),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),

	NOP(3),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	NOP(13),
	LRI(1, 0),
	REG(0xc8),

	NOP(13),
	LRI(44, POSTED),
	REG(0x28),
	REG(0x9c),
	REG(0xc0),
	REG(0x178),
	REG(0x17c),
	REG16(0x358),
	REG(0x170),
	REG(0x150),
	REG(0x154),
	REG(0x158),
	REG16(0x41c),
	REG16(0x600),
	REG16(0x604),
	REG16(0x608),
	REG16(0x60c),
	REG16(0x610),
	REG16(0x614),
	REG16(0x618),
	REG16(0x61c),
	REG16(0x620),
	REG16(0x624),
	REG16(0x628),
	REG16(0x62c),
	REG16(0x630),
	REG16(0x634),
	REG16(0x638),
	REG16(0x63c),
	REG16(0x640),
	REG16(0x644),
	REG16(0x648),
	REG16(0x64c),
	REG16(0x650),
	REG16(0x654),
	REG16(0x658),
	REG16(0x65c),
	REG16(0x660),
	REG16(0x664),
	REG16(0x668),
	REG16(0x66c),
	REG16(0x670),
	REG16(0x674),
	REG16(0x678),
	REG16(0x67c),
	REG(0x68),

	END
};

static const u8 gen11_rcs_offsets[] = {
	NOP(1),
	LRI(15, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x11c),
	REG(0x114),
	REG(0x118),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),

	NOP(1),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	LRI(1, POSTED),
	REG(0x1b0),

	NOP(10),
	LRI(1, 0),
	REG(0x0c8),

	END
};

static const u8 gen12_rcs_offsets[] = {
	NOP(1),
	LRI(13, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),

	NOP(5),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	LRI(3, POSTED),
	REG(0x1b0),
	REG16(0x5a8),
	REG16(0x5ac),

	NOP(6),
	LRI(1, 0),
	REG(0x0c8),
	NOP(3 + 9 + 1),

	LRI(51, POSTED),
	REG16(0x588),
	REG16(0x588),
	REG16(0x588),
	REG16(0x588),
	REG16(0x588),
	REG16(0x588),
	REG(0x028),
	REG(0x09c),
	REG(0x0c0),
	REG(0x178),
	REG(0x17c),
	REG16(0x358),
	REG(0x170),
	REG(0x150),
	REG(0x154),
	REG(0x158),
	REG16(0x41c),
	REG16(0x600),
	REG16(0x604),
	REG16(0x608),
	REG16(0x60c),
	REG16(0x610),
	REG16(0x614),
	REG16(0x618),
	REG16(0x61c),
	REG16(0x620),
	REG16(0x624),
	REG16(0x628),
	REG16(0x62c),
	REG16(0x630),
	REG16(0x634),
	REG16(0x638),
	REG16(0x63c),
	REG16(0x640),
	REG16(0x644),
	REG16(0x648),
	REG16(0x64c),
	REG16(0x650),
	REG16(0x654),
	REG16(0x658),
	REG16(0x65c),
	REG16(0x660),
	REG16(0x664),
	REG16(0x668),
	REG16(0x66c),
	REG16(0x670),
	REG16(0x674),
	REG16(0x678),
	REG16(0x67c),
	REG(0x068),
	REG(0x084),
	NOP(1),

	END
};

static const u8 xehp_rcs_offsets[] = {
	NOP(1),
	LRI(13, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),

	NOP(5),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	LRI(3, POSTED),
	REG(0x1b0),
	REG16(0x5a8),
	REG16(0x5ac),

	NOP(6),
	LRI(1, 0),
	REG(0x0c8),

	END
};

static const u8 dg2_rcs_offsets[] = {
	NOP(1),
	LRI(15, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),
	REG(0x120),
	REG(0x124),

	NOP(1),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	LRI(3, POSTED),
	REG(0x1b0),
	REG16(0x5a8),
	REG16(0x5ac),

	NOP(6),
	LRI(1, 0),
	REG(0x0c8),

	END
};

static const u8 mtl_rcs_offsets[] = {
	NOP(1),
	LRI(15, POSTED),
	REG16(0x244),
	REG(0x034),
	REG(0x030),
	REG(0x038),
	REG(0x03c),
	REG(0x168),
	REG(0x140),
	REG(0x110),
	REG(0x1c0),
	REG(0x1c4),
	REG(0x1c8),
	REG(0x180),
	REG16(0x2b4),
	REG(0x120),
	REG(0x124),

	NOP(1),
	LRI(9, POSTED),
	REG16(0x3a8),
	REG16(0x28c),
	REG16(0x288),
	REG16(0x284),
	REG16(0x280),
	REG16(0x27c),
	REG16(0x278),
	REG16(0x274),
	REG16(0x270),

	NOP(2),
	LRI(2, POSTED),
	REG16(0x5a8),
	REG16(0x5ac),

	NOP(6),
	LRI(1, 0),
	REG(0x0c8),

	END
};

#undef END
#undef REG16
#undef REG
#undef LRI
#undef NOP

static const u8 *reg_offsets(const struct intel_engine_cs *engine)
{
	/*
	 * The gen12+ lists only have the registers we program in the basic
	 * default state. We rely on the context image using relative
	 * addressing to automatic fixup the register state between the
	 * physical engines for virtual engine.
	 */
	GEM_BUG_ON(GRAPHICS_VER(engine->i915) >= 12 &&
		   !intel_engine_has_relative_mmio(engine));

	if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) {
		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
			return mtl_rcs_offsets;
		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
			return dg2_rcs_offsets;
		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
			return xehp_rcs_offsets;
		else if (GRAPHICS_VER(engine->i915) >= 12)
			return gen12_rcs_offsets;
		else if (GRAPHICS_VER(engine->i915) >= 11)
			return gen11_rcs_offsets;
		else if (GRAPHICS_VER(engine->i915) >= 9)
			return gen9_rcs_offsets;
		else
			return gen8_rcs_offsets;
	} else {
		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
			return dg2_xcs_offsets;
		else if (GRAPHICS_VER(engine->i915) >= 12)
			return gen12_xcs_offsets;
		else if (GRAPHICS_VER(engine->i915) >= 9)
			return gen9_xcs_offsets;
		else
			return gen8_xcs_offsets;
	}
}

static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
{
	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
		return 0x70;
	else if (GRAPHICS_VER(engine->i915) >= 12)
		return 0x60;
	else if (GRAPHICS_VER(engine->i915) >= 9)
		return 0x54;
	else if (engine->class == RENDER_CLASS)
		return 0x58;
	else
		return -1;
}

static int lrc_ring_bb_offset(const struct intel_engine_cs *engine)
{
	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
		return 0x80;
	else if (GRAPHICS_VER(engine->i915) >= 12)
		return 0x70;
	else if (GRAPHICS_VER(engine->i915) >= 9)
		return 0x64;
	else if (GRAPHICS_VER(engine->i915) >= 8 &&
		 engine->class == RENDER_CLASS)
		return 0xc4;
	else
		return -1;
}

static int lrc_ring_gpr0(const struct intel_engine_cs *engine)
{
	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
		return 0x84;
	else if (GRAPHICS_VER(engine->i915) >= 12)
		return 0x74;
	else if (GRAPHICS_VER(engine->i915) >= 9)
		return 0x68;
	else if (engine->class == RENDER_CLASS)
		return 0xd8;
	else
		return -1;
}

static int lrc_ring_wa_bb_per_ctx(const struct intel_engine_cs *engine)
{
	if (GRAPHICS_VER(engine->i915) >= 12)
		return 0x12;
	else if (GRAPHICS_VER(engine->i915) >= 9 || engine->class == RENDER_CLASS)
		return 0x18;
	else
		return -1;
}

static int lrc_ring_indirect_ptr(const struct intel_engine_cs *engine)
{
	int x;

	x = lrc_ring_wa_bb_per_ctx(engine);
	if (x < 0)
		return x;

	return x + 2;
}

static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
{
	int x;

	x = lrc_ring_indirect_ptr(engine);
	if (x < 0)
		return x;

	return x + 2;
}

static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
{

	if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
		/*
		 * Note that the CSFE context has a dummy slot for CMD_BUF_CCTL
		 * simply to match the RCS context image layout.
		 */
		return 0xc6;
	else if (engine->class != RENDER_CLASS)
		return -1;
	else if (GRAPHICS_VER(engine->i915) >= 12)
		return 0xb6;
	else if (GRAPHICS_VER(engine->i915) >= 11)
		return 0xaa;
	else
		return -1;
}

static u32
lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
{
	if (GRAPHICS_VER(engine->i915) >= 12)
		return GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
	else if (GRAPHICS_VER(engine->i915) >= 11)
		return GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
	else if (GRAPHICS_VER(engine->i915) >= 9)
		return GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
	else if (GRAPHICS_VER(engine->i915) >= 8)
		return GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;

	GEM_BUG_ON(GRAPHICS_VER(engine->i915) < 8);

	return 0;
}

static void
lrc_setup_indirect_ctx(u32 *regs,
		       const struct intel_engine_cs *engine,
		       u32 ctx_bb_ggtt_addr,
		       u32 size)
{
	GEM_BUG_ON(!size);
	GEM_BUG_ON(!IS_ALIGNED(size, CACHELINE_BYTES));
	GEM_BUG_ON(lrc_ring_indirect_ptr(engine) == -1);
	regs[lrc_ring_indirect_ptr(engine) + 1] =
		ctx_bb_ggtt_addr | (size / CACHELINE_BYTES);

	GEM_BUG_ON(lrc_ring_indirect_offset(engine) == -1);
	regs[lrc_ring_indirect_offset(engine) + 1] =
		lrc_ring_indirect_offset_default(engine) << 6;
}

static void init_common_regs(u32 * const regs,
			     const struct intel_context *ce,
			     const struct intel_engine_cs *engine,
			     bool inhibit)
{
	u32 ctl;
	int loc;

	ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
	ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
	if (inhibit)
		ctl |= CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
	if (GRAPHICS_VER(engine->i915) < 11)
		ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
					   CTX_CTRL_RS_CTX_ENABLE);
	regs[CTX_CONTEXT_CONTROL] = ctl;

	regs[CTX_TIMESTAMP] = ce->stats.runtime.last;

	loc = lrc_ring_bb_offset(engine);
	if (loc != -1)
		regs[loc + 1] = 0;
}

static void init_wa_bb_regs(u32 * const regs,
			    const struct intel_engine_cs *engine)
{
	const struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;

	if (wa_ctx->per_ctx.size) {
		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);

		GEM_BUG_ON(lrc_ring_wa_bb_per_ctx(engine) == -1);
		regs[lrc_ring_wa_bb_per_ctx(engine) + 1] =
			(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
	}

	if (wa_ctx->indirect_ctx.size) {
		lrc_setup_indirect_ctx(regs, engine,
				       i915_ggtt_offset(wa_ctx->vma) +
				       wa_ctx->indirect_ctx.offset,
				       wa_ctx->indirect_ctx.size);
	}
}

static void init_ppgtt_regs(u32 *regs, const struct i915_ppgtt *ppgtt)
{
	if (i915_vm_is_4lvl(&ppgtt->vm)) {
		/* 64b PPGTT (48bit canonical)
		 * PDP0_DESCRIPTOR contains the base address to PML4 and
		 * other PDP Descriptors are ignored.
		 */
		ASSIGN_CTX_PML4(ppgtt, regs);
	} else {
		ASSIGN_CTX_PDP(ppgtt, regs, 3);
		ASSIGN_CTX_PDP(ppgtt, regs, 2);
		ASSIGN_CTX_PDP(ppgtt, regs, 1);
		ASSIGN_CTX_PDP(ppgtt, regs, 0);
	}
}

static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
{
	if (i915_is_ggtt(vm))
		return i915_vm_to_ggtt(vm)->alias;
	else
		return i915_vm_to_ppgtt(vm);
}

static void __reset_stop_ring(u32 *regs, const struct intel_engine_cs *engine)
{
	int x;

	x = lrc_ring_mi_mode(engine);
	if (x != -1) {
		regs[x + 1] &= ~STOP_RING;
		regs[x + 1] |= STOP_RING << 16;
	}
}

static void __lrc_init_regs(u32 *regs,
			    const struct intel_context *ce,
			    const struct intel_engine_cs *engine,
			    bool inhibit)
{
	/*
	 * A context is actually a big batch buffer with several
	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
	 * values we are setting here are only for the first context restore:
	 * on a subsequent save, the GPU will recreate this batchbuffer with new
	 * values (including all the missing MI_LOAD_REGISTER_IMM commands that
	 * we are not initializing here).
	 *
	 * Must keep consistent with virtual_update_register_offsets().
	 */

	if (inhibit)
		memset(regs, 0, PAGE_SIZE);

	set_offsets(regs, reg_offsets(engine), engine, inhibit);

	init_common_regs(regs, ce, engine, inhibit);
	init_ppgtt_regs(regs, vm_alias(ce->vm));

	init_wa_bb_regs(regs, engine);

	__reset_stop_ring(regs, engine);
}

void lrc_init_regs(const struct intel_context *ce,
		   const struct intel_engine_cs *engine,
		   bool inhibit)
{
	__lrc_init_regs(ce->lrc_reg_state, ce, engine, inhibit);
}

void lrc_reset_regs(const struct intel_context *ce,
		    const struct intel_engine_cs *engine)
{
	__reset_stop_ring(ce->lrc_reg_state, engine);
}

static void
set_redzone(void *vaddr, const struct intel_engine_cs *engine)
{
	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
		return;

	vaddr += engine->context_size;

	memset(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE);
}

static void
check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
{
	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
		return;

	vaddr += engine->context_size;

	if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE))
		drm_err_once(&engine->i915->drm,
			     "%s context redzone overwritten!\n",
			     engine->name);
}

static u32 context_wa_bb_offset(const struct intel_context *ce)
{
	return PAGE_SIZE * ce->wa_bb_page;
}

static u32 *context_indirect_bb(const struct intel_context *ce)
{
	void *ptr;

	GEM_BUG_ON(!ce->wa_bb_page);

	ptr = ce->lrc_reg_state;
	ptr -= LRC_STATE_OFFSET; /* back to start of context image */
	ptr += context_wa_bb_offset(ce);

	return ptr;
}

void lrc_init_state(struct intel_context *ce,
		    struct intel_engine_cs *engine,
		    void *state)
{
	bool inhibit = true;

	set_redzone(state, engine);

	if (engine->default_state) {
		shmem_read(engine->default_state, 0,
			   state, engine->context_size);
		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
		inhibit = false;
	}

	/* Clear the ppHWSP (inc. per-context counters) */
	memset(state, 0, PAGE_SIZE);

	/* Clear the indirect wa and storage */
	if (ce->wa_bb_page)
		memset(state + context_wa_bb_offset(ce), 0, PAGE_SIZE);

	/*
	 * The second page of the context object contains some registers which
	 * must be set up prior to the first execution.
	 */
	__lrc_init_regs(state + LRC_STATE_OFFSET, ce, engine, inhibit);
}

u32 lrc_indirect_bb(const struct intel_context *ce)
{
	return i915_ggtt_offset(ce->state) + context_wa_bb_offset(ce);
}

static u32 *setup_predicate_disable_wa(const struct intel_context *ce, u32 *cs)
{
	/* If predication is active, this will be noop'ed */
	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT | (4 - 2);
	*cs++ = lrc_indirect_bb(ce) + DG2_PREDICATE_RESULT_WA;
	*cs++ = 0;
	*cs++ = 0; /* No predication */

	/* predicated end, only terminates if SET_PREDICATE_RESULT:0 is clear */
	*cs++ = MI_BATCH_BUFFER_END | BIT(15);
	*cs++ = MI_SET_PREDICATE | MI_SET_PREDICATE_DISABLE;

	/* Instructions are no longer predicated (disabled), we can proceed */
	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT | (4 - 2);
	*cs++ = lrc_indirect_bb(ce) + DG2_PREDICATE_RESULT_WA;
	*cs++ = 0;
	*cs++ = 1; /* enable predication before the next BB */

	*cs++ = MI_BATCH_BUFFER_END;
	GEM_BUG_ON(offset_in_page(cs) > DG2_PREDICATE_RESULT_WA);

	return cs;
}

static struct i915_vma *
__lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	u32 context_size;

	context_size = round_up(engine->context_size, I915_GTT_PAGE_SIZE);

	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
		context_size += I915_GTT_PAGE_SIZE; /* for redzone */

	if (GRAPHICS_VER(engine->i915) >= 12) {
		ce->wa_bb_page = context_size / PAGE_SIZE;
		context_size += PAGE_SIZE;
	}

	if (intel_context_is_parent(ce) && intel_engine_uses_guc(engine)) {
		ce->parallel.guc.parent_page = context_size / PAGE_SIZE;
		context_size += PARENT_SCRATCH_SIZE;
	}

	obj = i915_gem_object_create_lmem(engine->i915, context_size,
					  I915_BO_ALLOC_PM_VOLATILE);
	if (IS_ERR(obj))
		obj = i915_gem_object_create_shmem(engine->i915, context_size);
	if (IS_ERR(obj))
		return ERR_CAST(obj);

	vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
	if (IS_ERR(vma)) {
		i915_gem_object_put(obj);
		return vma;
	}

	return vma;
}

static struct intel_timeline *
pinned_timeline(struct intel_context *ce, struct intel_engine_cs *engine)
{
	struct intel_timeline *tl = fetch_and_zero(&ce->timeline);

	return intel_timeline_create_from_engine(engine, page_unmask_bits(tl));
}

int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
{
	struct intel_ring *ring;
	struct i915_vma *vma;
	int err;

	GEM_BUG_ON(ce->state);

	vma = __lrc_alloc_state(ce, engine);
	if (IS_ERR(vma))
		return PTR_ERR(vma);

	ring = intel_engine_create_ring(engine, ce->ring_size);
	if (IS_ERR(ring)) {
		err = PTR_ERR(ring);
		goto err_vma;
	}

	if (!page_mask_bits(ce->timeline)) {
		struct intel_timeline *tl;

		/*
		 * Use the static global HWSP for the kernel context, and
		 * a dynamically allocated cacheline for everyone else.
		 */
		if (unlikely(ce->timeline))
			tl = pinned_timeline(ce, engine);
		else
			tl = intel_timeline_create(engine->gt);
		if (IS_ERR(tl)) {
			err = PTR_ERR(tl);
			goto err_ring;
		}

		ce->timeline = tl;
	}

	ce->ring = ring;
	ce->state = vma;

	return 0;

err_ring:
	intel_ring_put(ring);
err_vma:
	i915_vma_put(vma);
	return err;
}

void lrc_reset(struct intel_context *ce)
{
	GEM_BUG_ON(!intel_context_is_pinned(ce));

	intel_ring_reset(ce->ring, ce->ring->emit);

	/* Scrub away the garbage */
	lrc_init_regs(ce, ce->engine, true);
	ce->lrc.lrca = lrc_update_regs(ce, ce->engine, ce->ring->tail);
}

int
lrc_pre_pin(struct intel_context *ce,
	    struct intel_engine_cs *engine,
	    struct i915_gem_ww_ctx *ww,
	    void **vaddr)
{
	GEM_BUG_ON(!ce->state);
	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));

	*vaddr = i915_gem_object_pin_map(ce->state->obj,
					 i915_coherent_map_type(ce->engine->i915,
								ce->state->obj,
								false) |
					 I915_MAP_OVERRIDE);

	return PTR_ERR_OR_ZERO(*vaddr);
}

int
lrc_pin(struct intel_context *ce,
	struct intel_engine_cs *engine,
	void *vaddr)
{
	ce->lrc_reg_state = vaddr + LRC_STATE_OFFSET;

	if (!__test_and_set_bit(CONTEXT_INIT_BIT, &ce->flags))
		lrc_init_state(ce, engine, vaddr);

	ce->lrc.lrca = lrc_update_regs(ce, engine, ce->ring->tail);
	return 0;
}

void lrc_unpin(struct intel_context *ce)
{
	if (unlikely(ce->parallel.last_rq)) {
		i915_request_put(ce->parallel.last_rq);
		ce->parallel.last_rq = NULL;
	}
	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
		      ce->engine);
}

void lrc_post_unpin(struct intel_context *ce)
{
	i915_gem_object_unpin_map(ce->state->obj);
}

void lrc_fini(struct intel_context *ce)
{
	if (!ce->state)
		return;

	intel_ring_put(fetch_and_zero(&ce->ring));
	i915_vma_put(fetch_and_zero(&ce->state));
}

void lrc_destroy(struct kref *kref)
{
	struct intel_context *ce = container_of(kref, typeof(*ce), ref);

	GEM_BUG_ON(!i915_active_is_idle(&ce->active));
	GEM_BUG_ON(intel_context_is_pinned(ce));

	lrc_fini(ce);

	intel_context_fini(ce);
	intel_context_free(ce);
}

static u32 *
gen12_emit_timestamp_wa(const struct intel_context *ce, u32 *cs)
{
	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
		MI_SRM_LRM_GLOBAL_GTT |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
		CTX_TIMESTAMP * sizeof(u32);
	*cs++ = 0;

	*cs++ = MI_LOAD_REGISTER_REG |
		MI_LRR_SOURCE_CS_MMIO |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_mmio_reg_offset(RING_CTX_TIMESTAMP(0));

	*cs++ = MI_LOAD_REGISTER_REG |
		MI_LRR_SOURCE_CS_MMIO |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_mmio_reg_offset(RING_CTX_TIMESTAMP(0));

	return cs;
}

static u32 *
gen12_emit_restore_scratch(const struct intel_context *ce, u32 *cs)
{
	GEM_BUG_ON(lrc_ring_gpr0(ce->engine) == -1);

	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
		MI_SRM_LRM_GLOBAL_GTT |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
		(lrc_ring_gpr0(ce->engine) + 1) * sizeof(u32);
	*cs++ = 0;

	return cs;
}

static u32 *
gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs)
{
	GEM_BUG_ON(lrc_ring_cmd_buf_cctl(ce->engine) == -1);

	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
		MI_SRM_LRM_GLOBAL_GTT |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_ggtt_offset(ce->state) + LRC_STATE_OFFSET +
		(lrc_ring_cmd_buf_cctl(ce->engine) + 1) * sizeof(u32);
	*cs++ = 0;

	*cs++ = MI_LOAD_REGISTER_REG |
		MI_LRR_SOURCE_CS_MMIO |
		MI_LRI_LRM_CS_MMIO;
	*cs++ = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
	*cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));

	return cs;
}

/*
 * On DG2 during context restore of a preempted context in GPGPU mode,
 * RCS restore hang is detected. This is extremely timing dependent.
 * To address this below sw wabb is implemented for DG2 A steppings.
 */
static u32 *
dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs)
{
	*cs++ = MI_LOAD_REGISTER_IMM(1);
	*cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG);
	*cs++ = 0x21;

	*cs++ = MI_LOAD_REGISTER_REG;
	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT1);

	*cs++ = MI_LOAD_REGISTER_REG;
	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT2);

	return cs;
}

/*
 * The bspec's tuning guide asks us to program a vertical watermark value of
 * 0x3FF.  However this register is not saved/restored properly by the
 * hardware, so we're required to apply the desired value via INDIRECT_CTX
 * batch buffer to ensure the value takes effect properly.  All other bits
 * in this register should remain at 0 (the hardware default).
 */
static u32 *
dg2_emit_draw_watermark_setting(u32 *cs)
{
	*cs++ = MI_LOAD_REGISTER_IMM(1);
	*cs++ = i915_mmio_reg_offset(DRAW_WATERMARK);
	*cs++ = REG_FIELD_PREP(VERT_WM_VAL, 0x3FF);

	return cs;
}

static u32 *
gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
{
	cs = gen12_emit_timestamp_wa(ce, cs);
	cs = gen12_emit_cmd_buf_wa(ce, cs);
	cs = gen12_emit_restore_scratch(ce, cs);

	/* Wa_22011450934:dg2 */
	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_A0, STEP_B0) ||
	    IS_DG2_GRAPHICS_STEP(ce->engine->i915, G11, STEP_A0, STEP_B0))
		cs = dg2_emit_rcs_hang_wabb(ce, cs);

	/* Wa_16013000631:dg2 */
	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) ||
	    IS_DG2_G11(ce->engine->i915))
		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);

	/* hsdes: 1809175790 */
	if (!HAS_FLAT_CCS(ce->engine->i915))
		cs = gen12_emit_aux_table_inv(ce->engine->gt,
					      cs, GEN12_GFX_CCS_AUX_NV);

	/* Wa_16014892111 */
	if (IS_DG2(ce->engine->i915))
		cs = dg2_emit_draw_watermark_setting(cs);

	return cs;
}

static u32 *
gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
{
	cs = gen12_emit_timestamp_wa(ce, cs);
	cs = gen12_emit_restore_scratch(ce, cs);

	/* Wa_16013000631:dg2 */
	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) ||
	    IS_DG2_G11(ce->engine->i915))
		if (ce->engine->class == COMPUTE_CLASS)
			cs = gen8_emit_pipe_control(cs,
						    PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE,
						    0);

	/* hsdes: 1809175790 */
	if (!HAS_FLAT_CCS(ce->engine->i915)) {
		if (ce->engine->class == VIDEO_DECODE_CLASS)
			cs = gen12_emit_aux_table_inv(ce->engine->gt,
						      cs, GEN12_VD0_AUX_NV);
		else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS)
			cs = gen12_emit_aux_table_inv(ce->engine->gt,
						      cs, GEN12_VE0_AUX_NV);
	}

	return cs;
}

static void
setup_indirect_ctx_bb(const struct intel_context *ce,
		      const struct intel_engine_cs *engine,
		      u32 *(*emit)(const struct intel_context *, u32 *))
{
	u32 * const start = context_indirect_bb(ce);
	u32 *cs;

	cs = emit(ce, start);
	GEM_BUG_ON(cs - start > I915_GTT_PAGE_SIZE / sizeof(*cs));
	while ((unsigned long)cs % CACHELINE_BYTES)
		*cs++ = MI_NOOP;

	GEM_BUG_ON(cs - start > DG2_PREDICATE_RESULT_BB / sizeof(*start));
	setup_predicate_disable_wa(ce, start + DG2_PREDICATE_RESULT_BB / sizeof(*start));

	lrc_setup_indirect_ctx(ce->lrc_reg_state, engine,
			       lrc_indirect_bb(ce),
			       (cs - start) * sizeof(*cs));
}

/*
 * The context descriptor encodes various attributes of a context,
 * including its GTT address and some flags. Because it's fairly
 * expensive to calculate, we'll just do it once and cache the result,
 * which remains valid until the context is unpinned.
 *
 * This is what a descriptor looks like, from LSB to MSB::
 *
 *      bits  0-11:    flags, GEN8_CTX_* (cached in ctx->desc_template)
 *      bits 12-31:    LRCA, GTT address of (the HWSP of) this context
 *      bits 32-52:    ctx ID, a globally unique tag (highest bit used by GuC)
 *      bits 53-54:    mbz, reserved for use by hardware
 *      bits 55-63:    group ID, currently unused and set to 0
 *
 * Starting from Gen11, the upper dword of the descriptor has a new format:
 *
 *      bits 32-36:    reserved
 *      bits 37-47:    SW context ID
 *      bits 48:53:    engine instance
 *      bit 54:        mbz, reserved for use by hardware
 *      bits 55-60:    SW counter
 *      bits 61-63:    engine class
 *
 * On Xe_HP, the upper dword of the descriptor has a new format:
 *
 *      bits 32-37:    virtual function number
 *      bit 38:        mbz, reserved for use by hardware
 *      bits 39-54:    SW context ID
 *      bits 55-57:    reserved
 *      bits 58-63:    SW counter
 *
 * engine info, SW context ID and SW counter need to form a unique number
 * (Context ID) per lrc.
 */
static u32 lrc_descriptor(const struct intel_context *ce)
{
	u32 desc;

	desc = INTEL_LEGACY_32B_CONTEXT;
	if (i915_vm_is_4lvl(ce->vm))
		desc = INTEL_LEGACY_64B_CONTEXT;
	desc <<= GEN8_CTX_ADDRESSING_MODE_SHIFT;

	desc |= GEN8_CTX_VALID | GEN8_CTX_PRIVILEGE;
	if (GRAPHICS_VER(ce->vm->i915) == 8)
		desc |= GEN8_CTX_L3LLC_COHERENT;

	return i915_ggtt_offset(ce->state) | desc;
}

u32 lrc_update_regs(const struct intel_context *ce,
		    const struct intel_engine_cs *engine,
		    u32 head)
{
	struct intel_ring *ring = ce->ring;
	u32 *regs = ce->lrc_reg_state;

	GEM_BUG_ON(!intel_ring_offset_valid(ring, head));
	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));

	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
	regs[CTX_RING_HEAD] = head;
	regs[CTX_RING_TAIL] = ring->tail;
	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;

	/* RPCS */
	if (engine->class == RENDER_CLASS) {
		regs[CTX_R_PWR_CLK_STATE] =
			intel_sseu_make_rpcs(engine->gt, &ce->sseu);

		i915_oa_init_reg_state(ce, engine);
	}

	if (ce->wa_bb_page) {
		u32 *(*fn)(const struct intel_context *ce, u32 *cs);

		fn = gen12_emit_indirect_ctx_xcs;
		if (ce->engine->class == RENDER_CLASS)
			fn = gen12_emit_indirect_ctx_rcs;

		/* Mutually exclusive wrt to global indirect bb */
		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
		setup_indirect_ctx_bb(ce, engine, fn);
	}

	return lrc_descriptor(ce) | CTX_DESC_FORCE_RESTORE;
}

void lrc_update_offsets(struct intel_context *ce,
			struct intel_engine_cs *engine)
{
	set_offsets(ce->lrc_reg_state, reg_offsets(engine), engine, false);
}

void lrc_check_regs(const struct intel_context *ce,
		    const struct intel_engine_cs *engine,
		    const char *when)
{
	const struct intel_ring *ring = ce->ring;
	u32 *regs = ce->lrc_reg_state;
	bool valid = true;
	int x;

	if (regs[CTX_RING_START] != i915_ggtt_offset(ring->vma)) {
		pr_err("%s: context submitted with incorrect RING_START [%08x], expected %08x\n",
		       engine->name,
		       regs[CTX_RING_START],
		       i915_ggtt_offset(ring->vma));
		regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
		valid = false;
	}

	if ((regs[CTX_RING_CTL] & ~(RING_WAIT | RING_WAIT_SEMAPHORE)) !=
	    (RING_CTL_SIZE(ring->size) | RING_VALID)) {
		pr_err("%s: context submitted with incorrect RING_CTL [%08x], expected %08x\n",
		       engine->name,
		       regs[CTX_RING_CTL],
		       (u32)(RING_CTL_SIZE(ring->size) | RING_VALID));
		regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
		valid = false;
	}

	x = lrc_ring_mi_mode(engine);
	if (x != -1 && regs[x + 1] & (regs[x + 1] >> 16) & STOP_RING) {
		pr_err("%s: context submitted with STOP_RING [%08x] in RING_MI_MODE\n",
		       engine->name, regs[x + 1]);
		regs[x + 1] &= ~STOP_RING;
		regs[x + 1] |= STOP_RING << 16;
		valid = false;
	}

	WARN_ONCE(!valid, "Invalid lrc state found %s submission\n", when);
}

/*
 * In this WA we need to set GEN8_L3SQCREG4[21:21] and reset it after
 * PIPE_CONTROL instruction. This is required for the flush to happen correctly
 * but there is a slight complication as this is applied in WA batch where the
 * values are only initialized once so we cannot take register value at the
 * beginning and reuse it further; hence we save its value to memory, upload a
 * constant value with bit21 set and then we restore it back with the saved value.
 * To simplify the WA, a constant value is formed by using the default value
 * of this register. This shouldn't be a problem because we are only modifying
 * it for a short period and this batch in non-premptible. We can ofcourse
 * use additional instructions that read the actual value of the register
 * at that time and set our bit of interest but it makes the WA complicated.
 *
 * This WA is also required for Gen9 so extracting as a function avoids
 * code duplication.
 */
static u32 *
gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch)
{
	/* NB no one else is allowed to scribble over scratch + 256! */
	*batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT;
	*batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4);
	*batch++ = intel_gt_scratch_offset(engine->gt,
					   INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA);
	*batch++ = 0;

	*batch++ = MI_LOAD_REGISTER_IMM(1);
	*batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4);
	*batch++ = 0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES;

	batch = gen8_emit_pipe_control(batch,
				       PIPE_CONTROL_CS_STALL |
				       PIPE_CONTROL_DC_FLUSH_ENABLE,
				       0);

	*batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT;
	*batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4);
	*batch++ = intel_gt_scratch_offset(engine->gt,
					   INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA);
	*batch++ = 0;

	return batch;
}

/*
 * Typically we only have one indirect_ctx and per_ctx batch buffer which are
 * initialized at the beginning and shared across all contexts but this field
 * helps us to have multiple batches at different offsets and select them based
 * on a criteria. At the moment this batch always start at the beginning of the page
 * and at this point we don't have multiple wa_ctx batch buffers.
 *
 * The number of WA applied are not known at the beginning; we use this field
 * to return the no of DWORDS written.
 *
 * It is to be noted that this batch does not contain MI_BATCH_BUFFER_END
 * so it adds NOOPs as padding to make it cacheline aligned.
 * MI_BATCH_BUFFER_END will be added to perctx batch and both of them together
 * makes a complete batch buffer.
 */
static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
{
	/* WaDisableCtxRestoreArbitration:bdw,chv */
	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;

	/* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */
	if (IS_BROADWELL(engine->i915))
		batch = gen8_emit_flush_coherentl3_wa(engine, batch);

	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
	/* Actual scratch location is at 128 bytes offset */
	batch = gen8_emit_pipe_control(batch,
				       PIPE_CONTROL_FLUSH_L3 |
				       PIPE_CONTROL_STORE_DATA_INDEX |
				       PIPE_CONTROL_CS_STALL |
				       PIPE_CONTROL_QW_WRITE,
				       LRC_PPHWSP_SCRATCH_ADDR);

	*batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;

	/* Pad to end of cacheline */
	while ((unsigned long)batch % CACHELINE_BYTES)
		*batch++ = MI_NOOP;

	/*
	 * MI_BATCH_BUFFER_END is not required in Indirect ctx BB because
	 * execution depends on the length specified in terms of cache lines
	 * in the register CTX_RCS_INDIRECT_CTX
	 */

	return batch;
}

struct lri {
	i915_reg_t reg;
	u32 value;
};

static u32 *emit_lri(u32 *batch, const struct lri *lri, unsigned int count)
{
	GEM_BUG_ON(!count || count > 63);

	*batch++ = MI_LOAD_REGISTER_IMM(count);
	do {
		*batch++ = i915_mmio_reg_offset(lri->reg);
		*batch++ = lri->value;
	} while (lri++, --count);
	*batch++ = MI_NOOP;

	return batch;
}

static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
{
	static const struct lri lri[] = {
		/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
		{
			COMMON_SLICE_CHICKEN2,
			__MASKED_FIELD(GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE,
				       0),
		},

		/* BSpec: 11391 */
		{
			FF_SLICE_CHICKEN,
			__MASKED_FIELD(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX,
				       FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX),
		},

		/* BSpec: 11299 */
		{
			_3D_CHICKEN3,
			__MASKED_FIELD(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX,
				       _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX),
		}
	};

	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;

	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
	batch = gen8_emit_flush_coherentl3_wa(engine, batch);

	/* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */
	batch = gen8_emit_pipe_control(batch,
				       PIPE_CONTROL_FLUSH_L3 |
				       PIPE_CONTROL_STORE_DATA_INDEX |
				       PIPE_CONTROL_CS_STALL |
				       PIPE_CONTROL_QW_WRITE,
				       LRC_PPHWSP_SCRATCH_ADDR);

	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));

	/* WaMediaPoolStateCmdInWABB:bxt,glk */
	if (HAS_POOLED_EU(engine->i915)) {
		/*
		 * EU pool configuration is setup along with golden context
		 * during context initialization. This value depends on
		 * device type (2x6 or 3x6) and needs to be updated based
		 * on which subslice is disabled especially for 2x6
		 * devices, however it is safe to load default
		 * configuration of 3x6 device instead of masking off
		 * corresponding bits because HW ignores bits of a disabled
		 * subslice and drops down to appropriate config. Please
		 * see render_state_setup() in i915_gem_render_state.c for
		 * possible configurations, to avoid duplication they are
		 * not shown here again.
		 */
		*batch++ = GEN9_MEDIA_POOL_STATE;
		*batch++ = GEN9_MEDIA_POOL_ENABLE;
		*batch++ = 0x00777000;
		*batch++ = 0;
		*batch++ = 0;
		*batch++ = 0;
	}

	*batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;

	/* Pad to end of cacheline */
	while ((unsigned long)batch % CACHELINE_BYTES)
		*batch++ = MI_NOOP;

	return batch;
}

#define CTX_WA_BB_SIZE (PAGE_SIZE)

static int lrc_create_wa_ctx(struct intel_engine_cs *engine)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	int err;

	obj = i915_gem_object_create_shmem(engine->i915, CTX_WA_BB_SIZE);
	if (IS_ERR(obj))
		return PTR_ERR(obj);

	vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
	if (IS_ERR(vma)) {
		err = PTR_ERR(vma);
		goto err;
	}

	engine->wa_ctx.vma = vma;
	return 0;

err:
	i915_gem_object_put(obj);
	return err;
}

void lrc_fini_wa_ctx(struct intel_engine_cs *engine)
{
	i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0);
}

typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch);

void lrc_init_wa_ctx(struct intel_engine_cs *engine)
{
	struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
	struct i915_wa_ctx_bb *wa_bb[] = {
		&wa_ctx->indirect_ctx, &wa_ctx->per_ctx
	};
	wa_bb_func_t wa_bb_fn[ARRAY_SIZE(wa_bb)];
	struct i915_gem_ww_ctx ww;
	void *batch, *batch_ptr;
	unsigned int i;
	int err;

	if (GRAPHICS_VER(engine->i915) >= 11 ||
	    !(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
		return;

	if (GRAPHICS_VER(engine->i915) == 9) {
		wa_bb_fn[0] = gen9_init_indirectctx_bb;
		wa_bb_fn[1] = NULL;
	} else if (GRAPHICS_VER(engine->i915) == 8) {
		wa_bb_fn[0] = gen8_init_indirectctx_bb;
		wa_bb_fn[1] = NULL;
	}

	err = lrc_create_wa_ctx(engine);
	if (err) {
		/*
		 * We continue even if we fail to initialize WA batch
		 * because we only expect rare glitches but nothing
		 * critical to prevent us from using GPU
		 */
		drm_err(&engine->i915->drm,
			"Ignoring context switch w/a allocation error:%d\n",
			err);
		return;
	}

	if (!engine->wa_ctx.vma)
		return;

	i915_gem_ww_ctx_init(&ww, true);
retry:
	err = i915_gem_object_lock(wa_ctx->vma->obj, &ww);
	if (!err)
		err = i915_ggtt_pin(wa_ctx->vma, &ww, 0, PIN_HIGH);
	if (err)
		goto err;

	batch = i915_gem_object_pin_map(wa_ctx->vma->obj, I915_MAP_WB);
	if (IS_ERR(batch)) {
		err = PTR_ERR(batch);
		goto err_unpin;
	}

	/*
	 * Emit the two workaround batch buffers, recording the offset from the
	 * start of the workaround batch buffer object for each and their
	 * respective sizes.
	 */
	batch_ptr = batch;
	for (i = 0; i < ARRAY_SIZE(wa_bb_fn); i++) {
		wa_bb[i]->offset = batch_ptr - batch;
		if (GEM_DEBUG_WARN_ON(!IS_ALIGNED(wa_bb[i]->offset,
						  CACHELINE_BYTES))) {
			err = -EINVAL;
			break;
		}
		if (wa_bb_fn[i])
			batch_ptr = wa_bb_fn[i](engine, batch_ptr);
		wa_bb[i]->size = batch_ptr - (batch + wa_bb[i]->offset);
	}
	GEM_BUG_ON(batch_ptr - batch > CTX_WA_BB_SIZE);

	__i915_gem_object_flush_map(wa_ctx->vma->obj, 0, batch_ptr - batch);
	__i915_gem_object_release_map(wa_ctx->vma->obj);

	/* Verify that we can handle failure to setup the wa_ctx */
	if (!err)
		err = i915_inject_probe_error(engine->i915, -ENODEV);

err_unpin:
	if (err)
		i915_vma_unpin(wa_ctx->vma);
err:
	if (err == -EDEADLK) {
		err = i915_gem_ww_ctx_backoff(&ww);
		if (!err)
			goto retry;
	}
	i915_gem_ww_ctx_fini(&ww);

	if (err) {
		i915_vma_put(engine->wa_ctx.vma);

		/* Clear all flags to prevent further use */
		memset(wa_ctx, 0, sizeof(*wa_ctx));
	}
}

static void st_runtime_underflow(struct intel_context_stats *stats, s32 dt)
{
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
	stats->runtime.num_underflow++;
	stats->runtime.max_underflow =
		max_t(u32, stats->runtime.max_underflow, -dt);
#endif
}

static u32 lrc_get_runtime(const struct intel_context *ce)
{
	/*
	 * We can use either ppHWSP[16] which is recorded before the context
	 * switch (and so excludes the cost of context switches) or use the
	 * value from the context image itself, which is saved/restored earlier
	 * and so includes the cost of the save.
	 */
	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
}

void lrc_update_runtime(struct intel_context *ce)
{
	struct intel_context_stats *stats = &ce->stats;
	u32 old;
	s32 dt;

	old = stats->runtime.last;
	stats->runtime.last = lrc_get_runtime(ce);
	dt = stats->runtime.last - old;
	if (!dt)
		return;

	if (unlikely(dt < 0)) {
		CE_TRACE(ce, "runtime underflow: last=%u, new=%u, delta=%d\n",
			 old, stats->runtime.last, dt);
		st_runtime_underflow(stats, dt);
		return;
	}

	ewma_runtime_add(&stats->runtime.avg, dt);
	stats->runtime.total += dt;
}

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_lrc.c"
#endif