summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/intel_lrc.c
blob: 62bcc770a18109264b3a0fc7958b4630b64de1ee (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
/*
 * Copyright © 2014 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Ben Widawsky <ben@bwidawsk.net>
 *    Michel Thierry <michel.thierry@intel.com>
 *    Thomas Daniel <thomas.daniel@intel.com>
 *    Oscar Mateo <oscar.mateo@intel.com>
 *
 */

/**
 * DOC: Logical Rings, Logical Ring Contexts and Execlists
 *
 * Motivation:
 * GEN8 brings an expansion of the HW contexts: "Logical Ring Contexts".
 * These expanded contexts enable a number of new abilities, especially
 * "Execlists" (also implemented in this file).
 *
 * One of the main differences with the legacy HW contexts is that logical
 * ring contexts incorporate many more things to the context's state, like
 * PDPs or ringbuffer control registers:
 *
 * The reason why PDPs are included in the context is straightforward: as
 * PPGTTs (per-process GTTs) are actually per-context, having the PDPs
 * contained there mean you don't need to do a ppgtt->switch_mm yourself,
 * instead, the GPU will do it for you on the context switch.
 *
 * But, what about the ringbuffer control registers (head, tail, etc..)?
 * shouldn't we just need a set of those per engine command streamer? This is
 * where the name "Logical Rings" starts to make sense: by virtualizing the
 * rings, the engine cs shifts to a new "ring buffer" with every context
 * switch. When you want to submit a workload to the GPU you: A) choose your
 * context, B) find its appropriate virtualized ring, C) write commands to it
 * and then, finally, D) tell the GPU to switch to that context.
 *
 * Instead of the legacy MI_SET_CONTEXT, the way you tell the GPU to switch
 * to a contexts is via a context execution list, ergo "Execlists".
 *
 * LRC implementation:
 * Regarding the creation of contexts, we have:
 *
 * - One global default context.
 * - One local default context for each opened fd.
 * - One local extra context for each context create ioctl call.
 *
 * Now that ringbuffers belong per-context (and not per-engine, like before)
 * and that contexts are uniquely tied to a given engine (and not reusable,
 * like before) we need:
 *
 * - One ringbuffer per-engine inside each context.
 * - One backing object per-engine inside each context.
 *
 * The global default context starts its life with these new objects fully
 * allocated and populated. The local default context for each opened fd is
 * more complex, because we don't know at creation time which engine is going
 * to use them. To handle this, we have implemented a deferred creation of LR
 * contexts:
 *
 * The local context starts its life as a hollow or blank holder, that only
 * gets populated for a given engine once we receive an execbuffer. If later
 * on we receive another execbuffer ioctl for the same context but a different
 * engine, we allocate/populate a new ringbuffer and context backing object and
 * so on.
 *
 * Finally, regarding local contexts created using the ioctl call: as they are
 * only allowed with the render ring, we can allocate & populate them right
 * away (no need to defer anything, at least for now).
 *
 * Execlists implementation:
 * Execlists are the new method by which, on gen8+ hardware, workloads are
 * submitted for execution (as opposed to the legacy, ringbuffer-based, method).
 * This method works as follows:
 *
 * When a request is committed, its commands (the BB start and any leading or
 * trailing commands, like the seqno breadcrumbs) are placed in the ringbuffer
 * for the appropriate context. The tail pointer in the hardware context is not
 * updated at this time, but instead, kept by the driver in the ringbuffer
 * structure. A structure representing this request is added to a request queue
 * for the appropriate engine: this structure contains a copy of the context's
 * tail after the request was written to the ring buffer and a pointer to the
 * context itself.
 *
 * If the engine's request queue was empty before the request was added, the
 * queue is processed immediately. Otherwise the queue will be processed during
 * a context switch interrupt. In any case, elements on the queue will get sent
 * (in pairs) to the GPU's ExecLists Submit Port (ELSP, for short) with a
 * globally unique 20-bits submission ID.
 *
 * When execution of a request completes, the GPU updates the context status
 * buffer with a context complete event and generates a context switch interrupt.
 * During the interrupt handling, the driver examines the events in the buffer:
 * for each context complete event, if the announced ID matches that on the head
 * of the request queue, then that request is retired and removed from the queue.
 *
 * After processing, if any requests were retired and the queue is not empty
 * then a new execution list can be submitted. The two requests at the front of
 * the queue are next to be submitted but since a context may not occur twice in
 * an execution list, if subsequent requests have the same ID as the first then
 * the two requests must be combined. This is done simply by discarding requests
 * at the head of the queue until either only one requests is left (in which case
 * we use a NULL second context) or the first two requests have unique IDs.
 *
 * By always executing the first two requests in the queue the driver ensures
 * that the GPU is kept as busy as possible. In the case where a single context
 * completes but a second context is still executing, the request for this second
 * context will be at the head of the queue when we remove the first one. This
 * request will then be resubmitted along with a new request for a different context,
 * which will cause the hardware to continue executing the second request and queue
 * the new request (the GPU detects the condition of a context getting preempted
 * with the same context and optimizes the context switch flow by not doing
 * preemption, but just sampling the new tail pointer).
 *
 */
#include <linux/interrupt.h>

#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "intel_mocs.h"

#define GEN9_LR_CONTEXT_RENDER_SIZE (22 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE)

#define RING_EXECLIST_QFULL		(1 << 0x2)
#define RING_EXECLIST1_VALID		(1 << 0x3)
#define RING_EXECLIST0_VALID		(1 << 0x4)
#define RING_EXECLIST_ACTIVE_STATUS	(3 << 0xE)
#define RING_EXECLIST1_ACTIVE		(1 << 0x11)
#define RING_EXECLIST0_ACTIVE		(1 << 0x12)

#define GEN8_CTX_STATUS_IDLE_ACTIVE	(1 << 0)
#define GEN8_CTX_STATUS_PREEMPTED	(1 << 1)
#define GEN8_CTX_STATUS_ELEMENT_SWITCH	(1 << 2)
#define GEN8_CTX_STATUS_ACTIVE_IDLE	(1 << 3)
#define GEN8_CTX_STATUS_COMPLETE	(1 << 4)
#define GEN8_CTX_STATUS_LITE_RESTORE	(1 << 15)

#define GEN8_CTX_STATUS_COMPLETED_MASK \
	 (GEN8_CTX_STATUS_ACTIVE_IDLE | \
	  GEN8_CTX_STATUS_PREEMPTED | \
	  GEN8_CTX_STATUS_ELEMENT_SWITCH)

#define CTX_LRI_HEADER_0		0x01
#define CTX_CONTEXT_CONTROL		0x02
#define CTX_RING_HEAD			0x04
#define CTX_RING_TAIL			0x06
#define CTX_RING_BUFFER_START		0x08
#define CTX_RING_BUFFER_CONTROL		0x0a
#define CTX_BB_HEAD_U			0x0c
#define CTX_BB_HEAD_L			0x0e
#define CTX_BB_STATE			0x10
#define CTX_SECOND_BB_HEAD_U		0x12
#define CTX_SECOND_BB_HEAD_L		0x14
#define CTX_SECOND_BB_STATE		0x16
#define CTX_BB_PER_CTX_PTR		0x18
#define CTX_RCS_INDIRECT_CTX		0x1a
#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
#define CTX_LRI_HEADER_1		0x21
#define CTX_CTX_TIMESTAMP		0x22
#define CTX_PDP3_UDW			0x24
#define CTX_PDP3_LDW			0x26
#define CTX_PDP2_UDW			0x28
#define CTX_PDP2_LDW			0x2a
#define CTX_PDP1_UDW			0x2c
#define CTX_PDP1_LDW			0x2e
#define CTX_PDP0_UDW			0x30
#define CTX_PDP0_LDW			0x32
#define CTX_LRI_HEADER_2		0x41
#define CTX_R_PWR_CLK_STATE		0x42
#define CTX_GPGPU_CSR_BASE_ADDRESS	0x44

#define GEN8_CTX_VALID (1<<0)
#define GEN8_CTX_FORCE_PD_RESTORE (1<<1)
#define GEN8_CTX_FORCE_RESTORE (1<<2)
#define GEN8_CTX_L3LLC_COHERENT (1<<5)
#define GEN8_CTX_PRIVILEGE (1<<8)

#define ASSIGN_CTX_REG(reg_state, pos, reg, val) do { \
	(reg_state)[(pos)+0] = i915_mmio_reg_offset(reg); \
	(reg_state)[(pos)+1] = (val); \
} while (0)

#define ASSIGN_CTX_PDP(ppgtt, reg_state, n) do {		\
	const u64 _addr = i915_page_dir_dma_addr((ppgtt), (n));	\
	reg_state[CTX_PDP ## n ## _UDW+1] = upper_32_bits(_addr); \
	reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
} while (0)

#define ASSIGN_CTX_PML4(ppgtt, reg_state) do { \
	reg_state[CTX_PDP0_UDW + 1] = upper_32_bits(px_dma(&ppgtt->pml4)); \
	reg_state[CTX_PDP0_LDW + 1] = lower_32_bits(px_dma(&ppgtt->pml4)); \
} while (0)

enum {
	FAULT_AND_HANG = 0,
	FAULT_AND_HALT, /* Debug only */
	FAULT_AND_STREAM,
	FAULT_AND_CONTINUE /* Unsupported */
};
#define GEN8_CTX_ID_SHIFT 32
#define GEN8_CTX_ID_WIDTH 21
#define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
#define GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x26

/* Typical size of the average request (2 pipecontrols and a MI_BB) */
#define EXECLISTS_REQUEST_SIZE 64 /* bytes */

#define WA_TAIL_DWORDS 2

static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
					    struct intel_engine_cs *engine);
static int intel_lr_context_pin(struct i915_gem_context *ctx,
				struct intel_engine_cs *engine);
static void execlists_init_reg_state(u32 *reg_state,
				     struct i915_gem_context *ctx,
				     struct intel_engine_cs *engine,
				     struct intel_ring *ring);

/**
 * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
 * @dev_priv: i915 device private
 * @enable_execlists: value of i915.enable_execlists module parameter.
 *
 * Only certain platforms support Execlists (the prerequisites being
 * support for Logical Ring Contexts and Aliasing PPGTT or better).
 *
 * Return: 1 if Execlists is supported and has to be enabled.
 */
int intel_sanitize_enable_execlists(struct drm_i915_private *dev_priv, int enable_execlists)
{
	/* On platforms with execlist available, vGPU will only
	 * support execlist mode, no ring buffer mode.
	 */
	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv) && intel_vgpu_active(dev_priv))
		return 1;

	if (INTEL_GEN(dev_priv) >= 9)
		return 1;

	if (enable_execlists == 0)
		return 0;

	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv) &&
	    USES_PPGTT(dev_priv) &&
	    i915.use_mmio_flip >= 0)
		return 1;

	return 0;
}

static void
logical_ring_init_platform_invariants(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;

	engine->disable_lite_restore_wa =
		(IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) ||
		 IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) &&
		(engine->id == VCS || engine->id == VCS2);

	engine->ctx_desc_template = GEN8_CTX_VALID;
	if (IS_GEN8(dev_priv))
		engine->ctx_desc_template |= GEN8_CTX_L3LLC_COHERENT;
	engine->ctx_desc_template |= GEN8_CTX_PRIVILEGE;

	/* TODO: WaDisableLiteRestore when we start using semaphore
	 * signalling between Command Streamers */
	/* ring->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE; */

	/* WaEnableForceRestoreInCtxtDescForVCS:skl */
	/* WaEnableForceRestoreInCtxtDescForVCS:bxt */
	if (engine->disable_lite_restore_wa)
		engine->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE;
}

/**
 * intel_lr_context_descriptor_update() - calculate & cache the descriptor
 * 					  descriptor for a pinned context
 * @ctx: Context to work on
 * @engine: Engine the descriptor will be used with
 *
 * 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
 *      bits 53-54:    mbz, reserved for use by hardware
 *      bits 55-63:    group ID, currently unused and set to 0
 */
static void
intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
				   struct intel_engine_cs *engine)
{
	struct intel_context *ce = &ctx->engine[engine->id];
	u64 desc;

	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (1<<GEN8_CTX_ID_WIDTH));

	desc = ctx->desc_template;				/* bits  3-4  */
	desc |= engine->ctx_desc_template;			/* bits  0-11 */
	desc |= i915_ggtt_offset(ce->state) + LRC_PPHWSP_PN * PAGE_SIZE;
								/* bits 12-31 */
	desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;		/* bits 32-52 */

	ce->lrc_desc = desc;
}

uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx,
				     struct intel_engine_cs *engine)
{
	return ctx->engine[engine->id].lrc_desc;
}

static inline void
execlists_context_status_change(struct drm_i915_gem_request *rq,
				unsigned long status)
{
	/*
	 * Only used when GVT-g is enabled now. When GVT-g is disabled,
	 * The compiler should eliminate this function as dead-code.
	 */
	if (!IS_ENABLED(CONFIG_DRM_I915_GVT))
		return;

	atomic_notifier_call_chain(&rq->ctx->status_notifier, status, rq);
}

static void
execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
{
	ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
	ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
	ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
	ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
}

static u64 execlists_update_context(struct drm_i915_gem_request *rq)
{
	struct intel_context *ce = &rq->ctx->engine[rq->engine->id];
	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
	u32 *reg_state = ce->lrc_reg_state;

	reg_state[CTX_RING_TAIL+1] = intel_ring_offset(rq->ring, rq->tail);

	/*
	 * True 32b PPGTT with dynamic page allocation: update PDP
	 * registers and point the unallocated PDPs to scratch page.
	 * PML4 is allocated during ppgtt init, so this is not needed
	 * in 48-bit mode.
	 */
	if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
		execlists_update_context_pdps(ppgtt, reg_state);

	/*
	 * Make sure the context image is complete before we submit it to HW.
	 *
	 * Ostensibly, writes (including the WCB) should be flushed prior to
	 * an uncached write such as our mmio register access, the empirical
	 * evidence (esp. on Braswell) suggests that the WC write into memory
	 * may not be visible to the HW prior to the completion of the UC
	 * register write and that we may begin execution from the context
	 * before its image is complete leading to invalid PD chasing.
	 *
	 * Furthermore, Braswell, at least, wants a full mb to be sure that
	 * the writes are coherent in memory (visible to the GPU) prior to
	 * execution, and not just visible to other CPUs (as is the result of
	 * wmb).
	 */
	mb();
	return ce->lrc_desc;
}

static void execlists_submit_ports(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	struct execlist_port *port = engine->execlist_port;
	u32 __iomem *elsp =
		dev_priv->regs + i915_mmio_reg_offset(RING_ELSP(engine));
	u64 desc[2];

	if (!port[0].count)
		execlists_context_status_change(port[0].request,
						INTEL_CONTEXT_SCHEDULE_IN);
	desc[0] = execlists_update_context(port[0].request);
	engine->preempt_wa = port[0].count++; /* bdw only? fixed on skl? */

	if (port[1].request) {
		GEM_BUG_ON(port[1].count);
		execlists_context_status_change(port[1].request,
						INTEL_CONTEXT_SCHEDULE_IN);
		desc[1] = execlists_update_context(port[1].request);
		port[1].count = 1;
	} else {
		desc[1] = 0;
	}
	GEM_BUG_ON(desc[0] == desc[1]);

	/* You must always write both descriptors in the order below. */
	writel(upper_32_bits(desc[1]), elsp);
	writel(lower_32_bits(desc[1]), elsp);

	writel(upper_32_bits(desc[0]), elsp);
	/* The context is automatically loaded after the following */
	writel(lower_32_bits(desc[0]), elsp);
}

static bool ctx_single_port_submission(const struct i915_gem_context *ctx)
{
	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
		ctx->execlists_force_single_submission);
}

static bool can_merge_ctx(const struct i915_gem_context *prev,
			  const struct i915_gem_context *next)
{
	if (prev != next)
		return false;

	if (ctx_single_port_submission(prev))
		return false;

	return true;
}

static void execlists_dequeue(struct intel_engine_cs *engine)
{
	struct drm_i915_gem_request *cursor, *last;
	struct execlist_port *port = engine->execlist_port;
	bool submit = false;

	last = port->request;
	if (last)
		/* WaIdleLiteRestore:bdw,skl
		 * Apply the wa NOOPs to prevent ring:HEAD == req:TAIL
		 * as we resubmit the request. See gen8_emit_request()
		 * for where we prepare the padding after the end of the
		 * request.
		 */
		last->tail = last->wa_tail;

	GEM_BUG_ON(port[1].request);

	/* Hardware submission is through 2 ports. Conceptually each port
	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
	 * static for a context, and unique to each, so we only execute
	 * requests belonging to a single context from each ring. RING_HEAD
	 * is maintained by the CS in the context image, it marks the place
	 * where it got up to last time, and through RING_TAIL we tell the CS
	 * where we want to execute up to this time.
	 *
	 * In this list the requests are in order of execution. Consecutive
	 * requests from the same context are adjacent in the ringbuffer. We
	 * can combine these requests into a single RING_TAIL update:
	 *
	 *              RING_HEAD...req1...req2
	 *                                    ^- RING_TAIL
	 * since to execute req2 the CS must first execute req1.
	 *
	 * Our goal then is to point each port to the end of a consecutive
	 * sequence of requests as being the most optimal (fewest wake ups
	 * and context switches) submission.
	 */

	spin_lock(&engine->execlist_lock);
	list_for_each_entry(cursor, &engine->execlist_queue, execlist_link) {
		/* Can we combine this request with the current port? It has to
		 * be the same context/ringbuffer and not have any exceptions
		 * (e.g. GVT saying never to combine contexts).
		 *
		 * If we can combine the requests, we can execute both by
		 * updating the RING_TAIL to point to the end of the second
		 * request, and so we never need to tell the hardware about
		 * the first.
		 */
		if (last && !can_merge_ctx(cursor->ctx, last->ctx)) {
			/* If we are on the second port and cannot combine
			 * this request with the last, then we are done.
			 */
			if (port != engine->execlist_port)
				break;

			/* If GVT overrides us we only ever submit port[0],
			 * leaving port[1] empty. Note that we also have
			 * to be careful that we don't queue the same
			 * context (even though a different request) to
			 * the second port.
			 */
			if (ctx_single_port_submission(cursor->ctx))
				break;

			GEM_BUG_ON(last->ctx == cursor->ctx);

			i915_gem_request_assign(&port->request, last);
			port++;
		}
		last = cursor;
		submit = true;
	}
	if (submit) {
		/* Decouple all the requests submitted from the queue */
		engine->execlist_queue.next = &cursor->execlist_link;
		cursor->execlist_link.prev = &engine->execlist_queue;

		i915_gem_request_assign(&port->request, last);
	}
	spin_unlock(&engine->execlist_lock);

	if (submit)
		execlists_submit_ports(engine);
}

static bool execlists_elsp_idle(struct intel_engine_cs *engine)
{
	return !engine->execlist_port[0].request;
}

static bool execlists_elsp_ready(struct intel_engine_cs *engine)
{
	int port;

	port = 1; /* wait for a free slot */
	if (engine->disable_lite_restore_wa || engine->preempt_wa)
		port = 0; /* wait for GPU to be idle before continuing */

	return !engine->execlist_port[port].request;
}

/*
 * Check the unread Context Status Buffers and manage the submission of new
 * contexts to the ELSP accordingly.
 */
static void intel_lrc_irq_handler(unsigned long data)
{
	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
	struct execlist_port *port = engine->execlist_port;
	struct drm_i915_private *dev_priv = engine->i915;

	intel_uncore_forcewake_get(dev_priv, engine->fw_domains);

	if (!execlists_elsp_idle(engine)) {
		u32 __iomem *csb_mmio =
			dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
		u32 __iomem *buf =
			dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0));
		unsigned int csb, head, tail;

		csb = readl(csb_mmio);
		head = GEN8_CSB_READ_PTR(csb);
		tail = GEN8_CSB_WRITE_PTR(csb);
		if (tail < head)
			tail += GEN8_CSB_ENTRIES;
		while (head < tail) {
			unsigned int idx = ++head % GEN8_CSB_ENTRIES;
			unsigned int status = readl(buf + 2 * idx);

			if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
				continue;

			GEM_BUG_ON(port[0].count == 0);
			if (--port[0].count == 0) {
				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
				execlists_context_status_change(port[0].request,
								INTEL_CONTEXT_SCHEDULE_OUT);

				i915_gem_request_put(port[0].request);
				port[0] = port[1];
				memset(&port[1], 0, sizeof(port[1]));

				engine->preempt_wa = false;
			}

			GEM_BUG_ON(port[0].count == 0 &&
				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
		}

		writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
				     GEN8_CSB_WRITE_PTR(csb) << 8),
		       csb_mmio);
	}

	if (execlists_elsp_ready(engine))
		execlists_dequeue(engine);

	intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
}

static void execlists_submit_request(struct drm_i915_gem_request *request)
{
	struct intel_engine_cs *engine = request->engine;
	unsigned long flags;

	spin_lock_irqsave(&engine->execlist_lock, flags);

	list_add_tail(&request->execlist_link, &engine->execlist_queue);
	if (execlists_elsp_idle(engine))
		tasklet_hi_schedule(&engine->irq_tasklet);

	spin_unlock_irqrestore(&engine->execlist_lock, flags);
}

int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request)
{
	struct intel_engine_cs *engine = request->engine;
	struct intel_context *ce = &request->ctx->engine[engine->id];
	int ret;

	/* Flush enough space to reduce the likelihood of waiting after
	 * we start building the request - in which case we will just
	 * have to repeat work.
	 */
	request->reserved_space += EXECLISTS_REQUEST_SIZE;

	if (!ce->state) {
		ret = execlists_context_deferred_alloc(request->ctx, engine);
		if (ret)
			return ret;
	}

	request->ring = ce->ring;

	ret = intel_lr_context_pin(request->ctx, engine);
	if (ret)
		return ret;

	if (i915.enable_guc_submission) {
		/*
		 * Check that the GuC has space for the request before
		 * going any further, as the i915_add_request() call
		 * later on mustn't fail ...
		 */
		ret = i915_guc_wq_reserve(request);
		if (ret)
			goto err_unpin;
	}

	ret = intel_ring_begin(request, 0);
	if (ret)
		goto err_unreserve;

	if (!ce->initialised) {
		ret = engine->init_context(request);
		if (ret)
			goto err_unreserve;

		ce->initialised = true;
	}

	/* Note that after this point, we have committed to using
	 * this request as it is being used to both track the
	 * state of engine initialisation and liveness of the
	 * golden renderstate above. Think twice before you try
	 * to cancel/unwind this request now.
	 */

	request->reserved_space -= EXECLISTS_REQUEST_SIZE;
	return 0;

err_unreserve:
	if (i915.enable_guc_submission)
		i915_guc_wq_unreserve(request);
err_unpin:
	intel_lr_context_unpin(request->ctx, engine);
	return ret;
}

/*
 * intel_logical_ring_advance() - advance the tail and prepare for submission
 * @request: Request to advance the logical ringbuffer of.
 *
 * The tail is updated in our logical ringbuffer struct, not in the actual context. What
 * really happens during submission is that the context and current tail will be placed
 * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
 * point, the tail *inside* the context is updated and the ELSP written to.
 */
static int
intel_logical_ring_advance(struct drm_i915_gem_request *request)
{
	struct intel_ring *ring = request->ring;
	struct intel_engine_cs *engine = request->engine;

	intel_ring_advance(ring);
	request->tail = ring->tail;

	/*
	 * Here we add two extra NOOPs as padding to avoid
	 * lite restore of a context with HEAD==TAIL.
	 *
	 * Caller must reserve WA_TAIL_DWORDS for us!
	 */
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);
	request->wa_tail = ring->tail;

	/* We keep the previous context alive until we retire the following
	 * request. This ensures that any the context object is still pinned
	 * for any residual writes the HW makes into it on the context switch
	 * into the next object following the breadcrumb. Otherwise, we may
	 * retire the context too early.
	 */
	request->previous_context = engine->last_context;
	engine->last_context = request->ctx;
	return 0;
}

static int intel_lr_context_pin(struct i915_gem_context *ctx,
				struct intel_engine_cs *engine)
{
	struct intel_context *ce = &ctx->engine[engine->id];
	void *vaddr;
	int ret;

	lockdep_assert_held(&ctx->i915->drm.struct_mutex);

	if (ce->pin_count++)
		return 0;

	ret = i915_vma_pin(ce->state, 0, GEN8_LR_CONTEXT_ALIGN,
			   PIN_OFFSET_BIAS | GUC_WOPCM_TOP | PIN_GLOBAL);
	if (ret)
		goto err;

	vaddr = i915_gem_object_pin_map(ce->state->obj, I915_MAP_WB);
	if (IS_ERR(vaddr)) {
		ret = PTR_ERR(vaddr);
		goto unpin_vma;
	}

	ret = intel_ring_pin(ce->ring);
	if (ret)
		goto unpin_map;

	intel_lr_context_descriptor_update(ctx, engine);

	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
		i915_ggtt_offset(ce->ring->vma);

	ce->state->obj->dirty = true;

	/* Invalidate GuC TLB. */
	if (i915.enable_guc_submission) {
		struct drm_i915_private *dev_priv = ctx->i915;
		I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
	}

	i915_gem_context_get(ctx);
	return 0;

unpin_map:
	i915_gem_object_unpin_map(ce->state->obj);
unpin_vma:
	__i915_vma_unpin(ce->state);
err:
	ce->pin_count = 0;
	return ret;
}

void intel_lr_context_unpin(struct i915_gem_context *ctx,
			    struct intel_engine_cs *engine)
{
	struct intel_context *ce = &ctx->engine[engine->id];

	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
	GEM_BUG_ON(ce->pin_count == 0);

	if (--ce->pin_count)
		return;

	intel_ring_unpin(ce->ring);

	i915_gem_object_unpin_map(ce->state->obj);
	i915_vma_unpin(ce->state);

	i915_gem_context_put(ctx);
}

static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
	int ret, i;
	struct intel_ring *ring = req->ring;
	struct i915_workarounds *w = &req->i915->workarounds;

	if (w->count == 0)
		return 0;

	ret = req->engine->emit_flush(req, EMIT_BARRIER);
	if (ret)
		return ret;

	ret = intel_ring_begin(req, w->count * 2 + 2);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(w->count));
	for (i = 0; i < w->count; i++) {
		intel_ring_emit_reg(ring, w->reg[i].addr);
		intel_ring_emit(ring, w->reg[i].value);
	}
	intel_ring_emit(ring, MI_NOOP);

	intel_ring_advance(ring);

	ret = req->engine->emit_flush(req, EMIT_BARRIER);
	if (ret)
		return ret;

	return 0;
}

#define wa_ctx_emit(batch, index, cmd)					\
	do {								\
		int __index = (index)++;				\
		if (WARN_ON(__index >= (PAGE_SIZE / sizeof(uint32_t)))) { \
			return -ENOSPC;					\
		}							\
		batch[__index] = (cmd);					\
	} while (0)

#define wa_ctx_emit_reg(batch, index, reg) \
	wa_ctx_emit((batch), (index), i915_mmio_reg_offset(reg))

/*
 * 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 inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
						uint32_t *batch,
						uint32_t index)
{
	struct drm_i915_private *dev_priv = engine->i915;
	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);

	/*
	 * WaDisableLSQCROPERFforOCL:skl,kbl
	 * This WA is implemented in skl_init_clock_gating() but since
	 * this batch updates GEN8_L3SQCREG4 with default value we need to
	 * set this bit here to retain the WA during flush.
	 */
	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0))
		l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;

	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
				   MI_SRM_LRM_GLOBAL_GTT));
	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
	wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
	wa_ctx_emit(batch, index, 0);

	wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
	wa_ctx_emit(batch, index, l3sqc4_flush);

	wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
	wa_ctx_emit(batch, index, (PIPE_CONTROL_CS_STALL |
				   PIPE_CONTROL_DC_FLUSH_ENABLE));
	wa_ctx_emit(batch, index, 0);
	wa_ctx_emit(batch, index, 0);
	wa_ctx_emit(batch, index, 0);
	wa_ctx_emit(batch, index, 0);

	wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
				   MI_SRM_LRM_GLOBAL_GTT));
	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
	wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
	wa_ctx_emit(batch, index, 0);

	return index;
}

static inline uint32_t wa_ctx_start(struct i915_wa_ctx_bb *wa_ctx,
				    uint32_t offset,
				    uint32_t start_alignment)
{
	return wa_ctx->offset = ALIGN(offset, start_alignment);
}

static inline int wa_ctx_end(struct i915_wa_ctx_bb *wa_ctx,
			     uint32_t offset,
			     uint32_t size_alignment)
{
	wa_ctx->size = offset - wa_ctx->offset;

	WARN(wa_ctx->size % size_alignment,
	     "wa_ctx_bb failed sanity checks: size %d is not aligned to %d\n",
	     wa_ctx->size, size_alignment);
	return 0;
}

/*
 * 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 int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
				    struct i915_wa_ctx_bb *wa_ctx,
				    uint32_t *batch,
				    uint32_t *offset)
{
	uint32_t scratch_addr;
	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);

	/* WaDisableCtxRestoreArbitration:bdw,chv */
	wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);

	/* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */
	if (IS_BROADWELL(engine->i915)) {
		int rc = gen8_emit_flush_coherentl3_wa(engine, batch, index);
		if (rc < 0)
			return rc;
		index = rc;
	}

	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
	/* Actual scratch location is at 128 bytes offset */
	scratch_addr = i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;

	wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
	wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
				   PIPE_CONTROL_GLOBAL_GTT_IVB |
				   PIPE_CONTROL_CS_STALL |
				   PIPE_CONTROL_QW_WRITE));
	wa_ctx_emit(batch, index, scratch_addr);
	wa_ctx_emit(batch, index, 0);
	wa_ctx_emit(batch, index, 0);
	wa_ctx_emit(batch, index, 0);

	/* Pad to end of cacheline */
	while (index % CACHELINE_DWORDS)
		wa_ctx_emit(batch, index, 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 wa_ctx_end(wa_ctx, *offset = index, CACHELINE_DWORDS);
}

/*
 *  This batch is started immediately after indirect_ctx batch. Since we ensure
 *  that indirect_ctx ends on a cacheline this batch is aligned automatically.
 *
 *  The number of DWORDS written are returned using this field.
 *
 *  This batch is terminated with MI_BATCH_BUFFER_END and so we need not add padding
 *  to align it with cacheline as padding after MI_BATCH_BUFFER_END is redundant.
 */
static int gen8_init_perctx_bb(struct intel_engine_cs *engine,
			       struct i915_wa_ctx_bb *wa_ctx,
			       uint32_t *batch,
			       uint32_t *offset)
{
	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);

	/* WaDisableCtxRestoreArbitration:bdw,chv */
	wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE);

	wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END);

	return wa_ctx_end(wa_ctx, *offset = index, 1);
}

static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
				    struct i915_wa_ctx_bb *wa_ctx,
				    uint32_t *batch,
				    uint32_t *offset)
{
	int ret;
	struct drm_i915_private *dev_priv = engine->i915;
	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);

	/* WaDisableCtxRestoreArbitration:skl,bxt */
	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) ||
	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
		wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);

	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt */
	ret = gen8_emit_flush_coherentl3_wa(engine, batch, index);
	if (ret < 0)
		return ret;
	index = ret;

	/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl */
	wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
	wa_ctx_emit_reg(batch, index, COMMON_SLICE_CHICKEN2);
	wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(
			    GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE));
	wa_ctx_emit(batch, index, MI_NOOP);

	/* WaClearSlmSpaceAtContextSwitch:kbl */
	/* Actual scratch location is at 128 bytes offset */
	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
		u32 scratch_addr =
			i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;

		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
					   PIPE_CONTROL_GLOBAL_GTT_IVB |
					   PIPE_CONTROL_CS_STALL |
					   PIPE_CONTROL_QW_WRITE));
		wa_ctx_emit(batch, index, scratch_addr);
		wa_ctx_emit(batch, index, 0);
		wa_ctx_emit(batch, index, 0);
		wa_ctx_emit(batch, index, 0);
	}

	/* WaMediaPoolStateCmdInWABB:bxt */
	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.
		 */
		u32 eu_pool_config = 0x00777000;
		wa_ctx_emit(batch, index, GEN9_MEDIA_POOL_STATE);
		wa_ctx_emit(batch, index, GEN9_MEDIA_POOL_ENABLE);
		wa_ctx_emit(batch, index, eu_pool_config);
		wa_ctx_emit(batch, index, 0);
		wa_ctx_emit(batch, index, 0);
		wa_ctx_emit(batch, index, 0);
	}

	/* Pad to end of cacheline */
	while (index % CACHELINE_DWORDS)
		wa_ctx_emit(batch, index, MI_NOOP);

	return wa_ctx_end(wa_ctx, *offset = index, CACHELINE_DWORDS);
}

static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
			       struct i915_wa_ctx_bb *wa_ctx,
			       uint32_t *batch,
			       uint32_t *offset)
{
	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);

	/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
	if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_B0) ||
	    IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) {
		wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
		wa_ctx_emit_reg(batch, index, GEN9_SLICE_COMMON_ECO_CHICKEN0);
		wa_ctx_emit(batch, index,
			    _MASKED_BIT_ENABLE(DISABLE_PIXEL_MASK_CAMMING));
		wa_ctx_emit(batch, index, MI_NOOP);
	}

	/* WaClearTdlStateAckDirtyBits:bxt */
	if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_B0)) {
		wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(4));

		wa_ctx_emit_reg(batch, index, GEN8_STATE_ACK);
		wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));

		wa_ctx_emit_reg(batch, index, GEN9_STATE_ACK_SLICE1);
		wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));

		wa_ctx_emit_reg(batch, index, GEN9_STATE_ACK_SLICE2);
		wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));

		wa_ctx_emit_reg(batch, index, GEN7_ROW_CHICKEN2);
		/* dummy write to CS, mask bits are 0 to ensure the register is not modified */
		wa_ctx_emit(batch, index, 0x0);
		wa_ctx_emit(batch, index, MI_NOOP);
	}

	/* WaDisableCtxRestoreArbitration:skl,bxt */
	if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_D0) ||
	    IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1))
		wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE);

	wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END);

	return wa_ctx_end(wa_ctx, *offset = index, 1);
}

static int lrc_setup_wa_ctx_obj(struct intel_engine_cs *engine, u32 size)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	int err;

	obj = i915_gem_object_create(&engine->i915->drm, PAGE_ALIGN(size));
	if (IS_ERR(obj))
		return PTR_ERR(obj);

	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
	if (IS_ERR(vma)) {
		err = PTR_ERR(vma);
		goto err;
	}

	err = i915_vma_pin(vma, 0, PAGE_SIZE, PIN_GLOBAL | PIN_HIGH);
	if (err)
		goto err;

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

err:
	i915_gem_object_put(obj);
	return err;
}

static void lrc_destroy_wa_ctx_obj(struct intel_engine_cs *engine)
{
	i915_vma_unpin_and_release(&engine->wa_ctx.vma);
}

static int intel_init_workaround_bb(struct intel_engine_cs *engine)
{
	struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
	uint32_t *batch;
	uint32_t offset;
	struct page *page;
	int ret;

	WARN_ON(engine->id != RCS);

	/* update this when WA for higher Gen are added */
	if (INTEL_GEN(engine->i915) > 9) {
		DRM_ERROR("WA batch buffer is not initialized for Gen%d\n",
			  INTEL_GEN(engine->i915));
		return 0;
	}

	/* some WA perform writes to scratch page, ensure it is valid */
	if (!engine->scratch) {
		DRM_ERROR("scratch page not allocated for %s\n", engine->name);
		return -EINVAL;
	}

	ret = lrc_setup_wa_ctx_obj(engine, PAGE_SIZE);
	if (ret) {
		DRM_DEBUG_DRIVER("Failed to setup context WA page: %d\n", ret);
		return ret;
	}

	page = i915_gem_object_get_dirty_page(wa_ctx->vma->obj, 0);
	batch = kmap_atomic(page);
	offset = 0;

	if (IS_GEN8(engine->i915)) {
		ret = gen8_init_indirectctx_bb(engine,
					       &wa_ctx->indirect_ctx,
					       batch,
					       &offset);
		if (ret)
			goto out;

		ret = gen8_init_perctx_bb(engine,
					  &wa_ctx->per_ctx,
					  batch,
					  &offset);
		if (ret)
			goto out;
	} else if (IS_GEN9(engine->i915)) {
		ret = gen9_init_indirectctx_bb(engine,
					       &wa_ctx->indirect_ctx,
					       batch,
					       &offset);
		if (ret)
			goto out;

		ret = gen9_init_perctx_bb(engine,
					  &wa_ctx->per_ctx,
					  batch,
					  &offset);
		if (ret)
			goto out;
	}

out:
	kunmap_atomic(batch);
	if (ret)
		lrc_destroy_wa_ctx_obj(engine);

	return ret;
}

static void lrc_init_hws(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;

	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
		   engine->status_page.ggtt_offset);
	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
}

static int gen8_init_common_ring(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	int ret;

	ret = intel_mocs_init_engine(engine);
	if (ret)
		return ret;

	lrc_init_hws(engine);

	intel_engine_reset_breadcrumbs(engine);

	I915_WRITE(RING_HWSTAM(engine->mmio_base), 0xffffffff);

	I915_WRITE(RING_MODE_GEN7(engine),
		   _MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
		   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));

	DRM_DEBUG_DRIVER("Execlists enabled for %s\n", engine->name);

	intel_engine_init_hangcheck(engine);

	if (!execlists_elsp_idle(engine))
		execlists_submit_ports(engine);

	return 0;
}

static int gen8_init_render_ring(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	int ret;

	ret = gen8_init_common_ring(engine);
	if (ret)
		return ret;

	/* We need to disable the AsyncFlip performance optimisations in order
	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
	 * programmed to '1' on all products.
	 *
	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
	 */
	I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));

	I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));

	return init_workarounds_ring(engine);
}

static int gen9_init_render_ring(struct intel_engine_cs *engine)
{
	int ret;

	ret = gen8_init_common_ring(engine);
	if (ret)
		return ret;

	return init_workarounds_ring(engine);
}

static void reset_common_ring(struct intel_engine_cs *engine,
			      struct drm_i915_gem_request *request)
{
	struct drm_i915_private *dev_priv = engine->i915;
	struct execlist_port *port = engine->execlist_port;
	struct intel_context *ce = &request->ctx->engine[engine->id];

	/* We want a simple context + ring to execute the breadcrumb update.
	 * We cannot rely on the context being intact across the GPU hang,
	 * so clear it and rebuild just what we need for the breadcrumb.
	 * All pending requests for this context will be zapped, and any
	 * future request will be after userspace has had the opportunity
	 * to recreate its own state.
	 */
	execlists_init_reg_state(ce->lrc_reg_state,
				 request->ctx, engine, ce->ring);

	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
		i915_ggtt_offset(ce->ring->vma);
	ce->lrc_reg_state[CTX_RING_HEAD+1] = request->postfix;

	request->ring->head = request->postfix;
	request->ring->last_retired_head = -1;
	intel_ring_update_space(request->ring);

	if (i915.enable_guc_submission)
		return;

	/* Catch up with any missed context-switch interrupts */
	I915_WRITE(RING_CONTEXT_STATUS_PTR(engine), _MASKED_FIELD(0xffff, 0));
	if (request->ctx != port[0].request->ctx) {
		i915_gem_request_put(port[0].request);
		port[0] = port[1];
		memset(&port[1], 0, sizeof(port[1]));
	}

	/* CS is stopped, and we will resubmit both ports on resume */
	GEM_BUG_ON(request->ctx != port[0].request->ctx);
	port[0].count = 0;
	port[1].count = 0;

	/* Reset WaIdleLiteRestore:bdw,skl as well */
	request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
}

static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
{
	struct i915_hw_ppgtt *ppgtt = req->ctx->ppgtt;
	struct intel_ring *ring = req->ring;
	struct intel_engine_cs *engine = req->engine;
	const int num_lri_cmds = GEN8_LEGACY_PDPES * 2;
	int i, ret;

	ret = intel_ring_begin(req, num_lri_cmds * 2 + 2);
	if (ret)
		return ret;

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

		intel_ring_emit_reg(ring, GEN8_RING_PDP_UDW(engine, i));
		intel_ring_emit(ring, upper_32_bits(pd_daddr));
		intel_ring_emit_reg(ring, GEN8_RING_PDP_LDW(engine, i));
		intel_ring_emit(ring, lower_32_bits(pd_daddr));
	}

	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
			      u64 offset, u32 len,
			      unsigned int dispatch_flags)
{
	struct intel_ring *ring = req->ring;
	bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
	int ret;

	/* Don't rely in hw updating PDPs, specially in lite-restore.
	 * Ideally, we should set Force PD Restore in ctx descriptor,
	 * but we can't. Force Restore would be a second option, but
	 * it is unsafe in case of lite-restore (because the ctx is
	 * not idle). PML4 is allocated during ppgtt init so this is
	 * not needed in 48-bit.*/
	if (req->ctx->ppgtt &&
	    (intel_engine_flag(req->engine) & req->ctx->ppgtt->pd_dirty_rings)) {
		if (!USES_FULL_48BIT_PPGTT(req->i915) &&
		    !intel_vgpu_active(req->i915)) {
			ret = intel_logical_ring_emit_pdps(req);
			if (ret)
				return ret;
		}

		req->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(req->engine);
	}

	ret = intel_ring_begin(req, 4);
	if (ret)
		return ret;

	/* FIXME(BDW): Address space and security selectors. */
	intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 |
			(ppgtt<<8) |
			(dispatch_flags & I915_DISPATCH_RS ?
			 MI_BATCH_RESOURCE_STREAMER : 0));
	intel_ring_emit(ring, lower_32_bits(offset));
	intel_ring_emit(ring, upper_32_bits(offset));
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static void gen8_logical_ring_enable_irq(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	I915_WRITE_IMR(engine,
		       ~(engine->irq_enable_mask | engine->irq_keep_mask));
	POSTING_READ_FW(RING_IMR(engine->mmio_base));
}

static void gen8_logical_ring_disable_irq(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
}

static int gen8_emit_flush(struct drm_i915_gem_request *request, u32 mode)
{
	struct intel_ring *ring = request->ring;
	u32 cmd;
	int ret;

	ret = intel_ring_begin(request, 4);
	if (ret)
		return ret;

	cmd = MI_FLUSH_DW + 1;

	/* We always require a command barrier so that subsequent
	 * commands, such as breadcrumb interrupts, are strictly ordered
	 * wrt the contents of the write cache being flushed to memory
	 * (and thus being coherent from the CPU).
	 */
	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;

	if (mode & EMIT_INVALIDATE) {
		cmd |= MI_INVALIDATE_TLB;
		if (request->engine->id == VCS)
			cmd |= MI_INVALIDATE_BSD;
	}

	intel_ring_emit(ring, cmd);
	intel_ring_emit(ring,
			I915_GEM_HWS_SCRATCH_ADDR |
			MI_FLUSH_DW_USE_GTT);
	intel_ring_emit(ring, 0); /* upper addr */
	intel_ring_emit(ring, 0); /* value */
	intel_ring_advance(ring);

	return 0;
}

static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
				  u32 mode)
{
	struct intel_ring *ring = request->ring;
	struct intel_engine_cs *engine = request->engine;
	u32 scratch_addr =
		i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
	bool vf_flush_wa = false, dc_flush_wa = false;
	u32 flags = 0;
	int ret;
	int len;

	flags |= PIPE_CONTROL_CS_STALL;

	if (mode & EMIT_FLUSH) {
		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
		flags |= PIPE_CONTROL_FLUSH_ENABLE;
	}

	if (mode & EMIT_INVALIDATE) {
		flags |= PIPE_CONTROL_TLB_INVALIDATE;
		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
		flags |= PIPE_CONTROL_QW_WRITE;
		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;

		/*
		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
		 * pipe control.
		 */
		if (IS_GEN9(request->i915))
			vf_flush_wa = true;

		/* WaForGAMHang:kbl */
		if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0))
			dc_flush_wa = true;
	}

	len = 6;

	if (vf_flush_wa)
		len += 6;

	if (dc_flush_wa)
		len += 12;

	ret = intel_ring_begin(request, len);
	if (ret)
		return ret;

	if (vf_flush_wa) {
		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(6));
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
	}

	if (dc_flush_wa) {
		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(6));
		intel_ring_emit(ring, PIPE_CONTROL_DC_FLUSH_ENABLE);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
	}

	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(6));
	intel_ring_emit(ring, flags);
	intel_ring_emit(ring, scratch_addr);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, 0);

	if (dc_flush_wa) {
		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(6));
		intel_ring_emit(ring, PIPE_CONTROL_CS_STALL);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
		intel_ring_emit(ring, 0);
	}

	intel_ring_advance(ring);

	return 0;
}

static void bxt_a_seqno_barrier(struct intel_engine_cs *engine)
{
	/*
	 * On BXT A steppings there is a HW coherency issue whereby the
	 * MI_STORE_DATA_IMM storing the completed request's seqno
	 * occasionally doesn't invalidate the CPU cache. Work around this by
	 * clflushing the corresponding cacheline whenever the caller wants
	 * the coherency to be guaranteed. Note that this cacheline is known
	 * to be clean at this point, since we only write it in
	 * bxt_a_set_seqno(), where we also do a clflush after the write. So
	 * this clflush in practice becomes an invalidate operation.
	 */
	intel_flush_status_page(engine, I915_GEM_HWS_INDEX);
}

/*
 * Reserve space for 2 NOOPs at the end of each request to be
 * used as a workaround for not being allowed to do lite
 * restore with HEAD==TAIL (WaIdleLiteRestore).
 */

static int gen8_emit_request(struct drm_i915_gem_request *request)
{
	struct intel_ring *ring = request->ring;
	int ret;

	ret = intel_ring_begin(request, 6 + WA_TAIL_DWORDS);
	if (ret)
		return ret;

	/* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */
	BUILD_BUG_ON(I915_GEM_HWS_INDEX_ADDR & (1 << 5));

	intel_ring_emit(ring, (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW);
	intel_ring_emit(ring,
			intel_hws_seqno_address(request->engine) |
			MI_FLUSH_DW_USE_GTT);
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, request->fence.seqno);
	intel_ring_emit(ring, MI_USER_INTERRUPT);
	intel_ring_emit(ring, MI_NOOP);
	return intel_logical_ring_advance(request);
}

static int gen8_emit_request_render(struct drm_i915_gem_request *request)
{
	struct intel_ring *ring = request->ring;
	int ret;

	ret = intel_ring_begin(request, 8 + WA_TAIL_DWORDS);
	if (ret)
		return ret;

	/* We're using qword write, seqno should be aligned to 8 bytes. */
	BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1);

	/* w/a for post sync ops following a GPGPU operation we
	 * need a prior CS_STALL, which is emitted by the flush
	 * following the batch.
	 */
	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(6));
	intel_ring_emit(ring,
			(PIPE_CONTROL_GLOBAL_GTT_IVB |
			 PIPE_CONTROL_CS_STALL |
			 PIPE_CONTROL_QW_WRITE));
	intel_ring_emit(ring, intel_hws_seqno_address(request->engine));
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, i915_gem_request_get_seqno(request));
	/* We're thrashing one dword of HWS. */
	intel_ring_emit(ring, 0);
	intel_ring_emit(ring, MI_USER_INTERRUPT);
	intel_ring_emit(ring, MI_NOOP);
	return intel_logical_ring_advance(request);
}

static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
{
	int ret;

	ret = intel_logical_ring_workarounds_emit(req);
	if (ret)
		return ret;

	ret = intel_rcs_context_init_mocs(req);
	/*
	 * Failing to program the MOCS is non-fatal.The system will not
	 * run at peak performance. So generate an error and carry on.
	 */
	if (ret)
		DRM_ERROR("MOCS failed to program: expect performance issues.\n");

	return i915_gem_render_state_init(req);
}

/**
 * intel_logical_ring_cleanup() - deallocate the Engine Command Streamer
 * @engine: Engine Command Streamer.
 */
void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv;

	if (!intel_engine_initialized(engine))
		return;

	/*
	 * Tasklet cannot be active at this point due intel_mark_active/idle
	 * so this is just for documentation.
	 */
	if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->irq_tasklet.state)))
		tasklet_kill(&engine->irq_tasklet);

	dev_priv = engine->i915;

	if (engine->buffer) {
		WARN_ON((I915_READ_MODE(engine) & MODE_IDLE) == 0);
	}

	if (engine->cleanup)
		engine->cleanup(engine);

	intel_engine_cleanup_common(engine);

	if (engine->status_page.vma) {
		i915_gem_object_unpin_map(engine->status_page.vma->obj);
		engine->status_page.vma = NULL;
	}
	intel_lr_context_unpin(dev_priv->kernel_context, engine);

	lrc_destroy_wa_ctx_obj(engine);
	engine->i915 = NULL;
}

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

	for_each_engine(engine, dev_priv)
		engine->submit_request = execlists_submit_request;
}

static void
logical_ring_default_vfuncs(struct intel_engine_cs *engine)
{
	/* Default vfuncs which can be overriden by each engine. */
	engine->init_hw = gen8_init_common_ring;
	engine->reset_hw = reset_common_ring;
	engine->emit_flush = gen8_emit_flush;
	engine->emit_request = gen8_emit_request;
	engine->submit_request = execlists_submit_request;

	engine->irq_enable = gen8_logical_ring_enable_irq;
	engine->irq_disable = gen8_logical_ring_disable_irq;
	engine->emit_bb_start = gen8_emit_bb_start;
	if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1))
		engine->irq_seqno_barrier = bxt_a_seqno_barrier;
}

static inline void
logical_ring_default_irqs(struct intel_engine_cs *engine)
{
	unsigned shift = engine->irq_shift;
	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
}

static int
lrc_setup_hws(struct intel_engine_cs *engine, struct i915_vma *vma)
{
	const int hws_offset = LRC_PPHWSP_PN * PAGE_SIZE;
	void *hws;

	/* The HWSP is part of the default context object in LRC mode. */
	hws = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
	if (IS_ERR(hws))
		return PTR_ERR(hws);

	engine->status_page.page_addr = hws + hws_offset;
	engine->status_page.ggtt_offset = i915_ggtt_offset(vma) + hws_offset;
	engine->status_page.vma = vma;

	return 0;
}

static void
logical_ring_setup(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	enum forcewake_domains fw_domains;

	intel_engine_setup_common(engine);

	/* Intentionally left blank. */
	engine->buffer = NULL;

	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
						    RING_ELSP(engine),
						    FW_REG_WRITE);

	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
						     RING_CONTEXT_STATUS_PTR(engine),
						     FW_REG_READ | FW_REG_WRITE);

	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
						     RING_CONTEXT_STATUS_BUF_BASE(engine),
						     FW_REG_READ);

	engine->fw_domains = fw_domains;

	tasklet_init(&engine->irq_tasklet,
		     intel_lrc_irq_handler, (unsigned long)engine);

	logical_ring_init_platform_invariants(engine);
	logical_ring_default_vfuncs(engine);
	logical_ring_default_irqs(engine);
}

static int
logical_ring_init(struct intel_engine_cs *engine)
{
	struct i915_gem_context *dctx = engine->i915->kernel_context;
	int ret;

	ret = intel_engine_init_common(engine);
	if (ret)
		goto error;

	ret = execlists_context_deferred_alloc(dctx, engine);
	if (ret)
		goto error;

	/* As this is the default context, always pin it */
	ret = intel_lr_context_pin(dctx, engine);
	if (ret) {
		DRM_ERROR("Failed to pin context for %s: %d\n",
			  engine->name, ret);
		goto error;
	}

	/* And setup the hardware status page. */
	ret = lrc_setup_hws(engine, dctx->engine[engine->id].state);
	if (ret) {
		DRM_ERROR("Failed to set up hws %s: %d\n", engine->name, ret);
		goto error;
	}

	return 0;

error:
	intel_logical_ring_cleanup(engine);
	return ret;
}

int logical_render_ring_init(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	int ret;

	logical_ring_setup(engine);

	if (HAS_L3_DPF(dev_priv))
		engine->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;

	/* Override some for render ring. */
	if (INTEL_GEN(dev_priv) >= 9)
		engine->init_hw = gen9_init_render_ring;
	else
		engine->init_hw = gen8_init_render_ring;
	engine->init_context = gen8_init_rcs_context;
	engine->emit_flush = gen8_emit_flush_render;
	engine->emit_request = gen8_emit_request_render;

	ret = intel_engine_create_scratch(engine, 4096);
	if (ret)
		return ret;

	ret = intel_init_workaround_bb(engine);
	if (ret) {
		/*
		 * 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_ERROR("WA batch buffer initialization failed: %d\n",
			  ret);
	}

	ret = logical_ring_init(engine);
	if (ret) {
		lrc_destroy_wa_ctx_obj(engine);
	}

	return ret;
}

int logical_xcs_ring_init(struct intel_engine_cs *engine)
{
	logical_ring_setup(engine);

	return logical_ring_init(engine);
}

static u32
make_rpcs(struct drm_i915_private *dev_priv)
{
	u32 rpcs = 0;

	/*
	 * No explicit RPCS request is needed to ensure full
	 * slice/subslice/EU enablement prior to Gen9.
	*/
	if (INTEL_GEN(dev_priv) < 9)
		return 0;

	/*
	 * Starting in Gen9, render power gating can leave
	 * slice/subslice/EU in a partially enabled state. We
	 * must make an explicit request through RPCS for full
	 * enablement.
	*/
	if (INTEL_INFO(dev_priv)->sseu.has_slice_pg) {
		rpcs |= GEN8_RPCS_S_CNT_ENABLE;
		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.slice_mask) <<
			GEN8_RPCS_S_CNT_SHIFT;
		rpcs |= GEN8_RPCS_ENABLE;
	}

	if (INTEL_INFO(dev_priv)->sseu.has_subslice_pg) {
		rpcs |= GEN8_RPCS_SS_CNT_ENABLE;
		rpcs |= hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask) <<
			GEN8_RPCS_SS_CNT_SHIFT;
		rpcs |= GEN8_RPCS_ENABLE;
	}

	if (INTEL_INFO(dev_priv)->sseu.has_eu_pg) {
		rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
			GEN8_RPCS_EU_MIN_SHIFT;
		rpcs |= INTEL_INFO(dev_priv)->sseu.eu_per_subslice <<
			GEN8_RPCS_EU_MAX_SHIFT;
		rpcs |= GEN8_RPCS_ENABLE;
	}

	return rpcs;
}

static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
{
	u32 indirect_ctx_offset;

	switch (INTEL_GEN(engine->i915)) {
	default:
		MISSING_CASE(INTEL_GEN(engine->i915));
		/* fall through */
	case 9:
		indirect_ctx_offset =
			GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
		break;
	case 8:
		indirect_ctx_offset =
			GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
		break;
	}

	return indirect_ctx_offset;
}

static void execlists_init_reg_state(u32 *reg_state,
				     struct i915_gem_context *ctx,
				     struct intel_engine_cs *engine,
				     struct intel_ring *ring)
{
	struct drm_i915_private *dev_priv = engine->i915;
	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: dev_priv->mm.aliasing_ppgtt;

	/* 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). */
	reg_state[CTX_LRI_HEADER_0] =
		MI_LOAD_REGISTER_IMM(engine->id == RCS ? 14 : 11) | MI_LRI_FORCE_POSTED;
	ASSIGN_CTX_REG(reg_state, CTX_CONTEXT_CONTROL,
		       RING_CONTEXT_CONTROL(engine),
		       _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
					  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
					  (HAS_RESOURCE_STREAMER(dev_priv) ?
					   CTX_CTRL_RS_CTX_ENABLE : 0)));
	ASSIGN_CTX_REG(reg_state, CTX_RING_HEAD, RING_HEAD(engine->mmio_base),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_RING_TAIL, RING_TAIL(engine->mmio_base),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_RING_BUFFER_START,
		       RING_START(engine->mmio_base), 0);
	ASSIGN_CTX_REG(reg_state, CTX_RING_BUFFER_CONTROL,
		       RING_CTL(engine->mmio_base),
		       ((ring->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID);
	ASSIGN_CTX_REG(reg_state, CTX_BB_HEAD_U,
		       RING_BBADDR_UDW(engine->mmio_base), 0);
	ASSIGN_CTX_REG(reg_state, CTX_BB_HEAD_L,
		       RING_BBADDR(engine->mmio_base), 0);
	ASSIGN_CTX_REG(reg_state, CTX_BB_STATE,
		       RING_BBSTATE(engine->mmio_base),
		       RING_BB_PPGTT);
	ASSIGN_CTX_REG(reg_state, CTX_SECOND_BB_HEAD_U,
		       RING_SBBADDR_UDW(engine->mmio_base), 0);
	ASSIGN_CTX_REG(reg_state, CTX_SECOND_BB_HEAD_L,
		       RING_SBBADDR(engine->mmio_base), 0);
	ASSIGN_CTX_REG(reg_state, CTX_SECOND_BB_STATE,
		       RING_SBBSTATE(engine->mmio_base), 0);
	if (engine->id == RCS) {
		ASSIGN_CTX_REG(reg_state, CTX_BB_PER_CTX_PTR,
			       RING_BB_PER_CTX_PTR(engine->mmio_base), 0);
		ASSIGN_CTX_REG(reg_state, CTX_RCS_INDIRECT_CTX,
			       RING_INDIRECT_CTX(engine->mmio_base), 0);
		ASSIGN_CTX_REG(reg_state, CTX_RCS_INDIRECT_CTX_OFFSET,
			       RING_INDIRECT_CTX_OFFSET(engine->mmio_base), 0);
		if (engine->wa_ctx.vma) {
			struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
			u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);

			reg_state[CTX_RCS_INDIRECT_CTX+1] =
				(ggtt_offset + wa_ctx->indirect_ctx.offset * sizeof(uint32_t)) |
				(wa_ctx->indirect_ctx.size / CACHELINE_DWORDS);

			reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] =
				intel_lr_indirect_ctx_offset(engine) << 6;

			reg_state[CTX_BB_PER_CTX_PTR+1] =
				(ggtt_offset + wa_ctx->per_ctx.offset * sizeof(uint32_t)) |
				0x01;
		}
	}
	reg_state[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9) | MI_LRI_FORCE_POSTED;
	ASSIGN_CTX_REG(reg_state, CTX_CTX_TIMESTAMP,
		       RING_CTX_TIMESTAMP(engine->mmio_base), 0);
	/* PDP values well be assigned later if needed */
	ASSIGN_CTX_REG(reg_state, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(engine, 3),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(engine, 3),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(engine, 2),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(engine, 2),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(engine, 1),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(engine, 1),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(engine, 0),
		       0);
	ASSIGN_CTX_REG(reg_state, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(engine, 0),
		       0);

	if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
		/* 64b PPGTT (48bit canonical)
		 * PDP0_DESCRIPTOR contains the base address to PML4 and
		 * other PDP Descriptors are ignored.
		 */
		ASSIGN_CTX_PML4(ppgtt, reg_state);
	} else {
		/* 32b PPGTT
		 * PDP*_DESCRIPTOR contains the base address of space supported.
		 * With dynamic page allocation, PDPs may not be allocated at
		 * this point. Point the unallocated PDPs to the scratch page
		 */
		execlists_update_context_pdps(ppgtt, reg_state);
	}

	if (engine->id == RCS) {
		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
		ASSIGN_CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
			       make_rpcs(dev_priv));
	}
}

static int
populate_lr_context(struct i915_gem_context *ctx,
		    struct drm_i915_gem_object *ctx_obj,
		    struct intel_engine_cs *engine,
		    struct intel_ring *ring)
{
	void *vaddr;
	int ret;

	ret = i915_gem_object_set_to_cpu_domain(ctx_obj, true);
	if (ret) {
		DRM_DEBUG_DRIVER("Could not set to CPU domain\n");
		return ret;
	}

	vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB);
	if (IS_ERR(vaddr)) {
		ret = PTR_ERR(vaddr);
		DRM_DEBUG_DRIVER("Could not map object pages! (%d)\n", ret);
		return ret;
	}
	ctx_obj->dirty = true;

	/* The second page of the context object contains some fields which must
	 * be set up prior to the first execution. */

	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
				 ctx, engine, ring);

	i915_gem_object_unpin_map(ctx_obj);

	return 0;
}

/**
 * intel_lr_context_size() - return the size of the context for an engine
 * @engine: which engine to find the context size for
 *
 * Each engine may require a different amount of space for a context image,
 * so when allocating (or copying) an image, this function can be used to
 * find the right size for the specific engine.
 *
 * Return: size (in bytes) of an engine-specific context image
 *
 * Note: this size includes the HWSP, which is part of the context image
 * in LRC mode, but does not include the "shared data page" used with
 * GuC submission. The caller should account for this if using the GuC.
 */
uint32_t intel_lr_context_size(struct intel_engine_cs *engine)
{
	int ret = 0;

	WARN_ON(INTEL_GEN(engine->i915) < 8);

	switch (engine->id) {
	case RCS:
		if (INTEL_GEN(engine->i915) >= 9)
			ret = GEN9_LR_CONTEXT_RENDER_SIZE;
		else
			ret = GEN8_LR_CONTEXT_RENDER_SIZE;
		break;
	case VCS:
	case BCS:
	case VECS:
	case VCS2:
		ret = GEN8_LR_CONTEXT_OTHER_SIZE;
		break;
	}

	return ret;
}

static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
					    struct intel_engine_cs *engine)
{
	struct drm_i915_gem_object *ctx_obj;
	struct intel_context *ce = &ctx->engine[engine->id];
	struct i915_vma *vma;
	uint32_t context_size;
	struct intel_ring *ring;
	int ret;

	WARN_ON(ce->state);

	context_size = round_up(intel_lr_context_size(engine), 4096);

	/* One extra page as the sharing data between driver and GuC */
	context_size += PAGE_SIZE * LRC_PPHWSP_PN;

	ctx_obj = i915_gem_object_create(&ctx->i915->drm, context_size);
	if (IS_ERR(ctx_obj)) {
		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n");
		return PTR_ERR(ctx_obj);
	}

	vma = i915_vma_create(ctx_obj, &ctx->i915->ggtt.base, NULL);
	if (IS_ERR(vma)) {
		ret = PTR_ERR(vma);
		goto error_deref_obj;
	}

	ring = intel_engine_create_ring(engine, ctx->ring_size);
	if (IS_ERR(ring)) {
		ret = PTR_ERR(ring);
		goto error_deref_obj;
	}

	ret = populate_lr_context(ctx, ctx_obj, engine, ring);
	if (ret) {
		DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
		goto error_ring_free;
	}

	ce->ring = ring;
	ce->state = vma;
	ce->initialised = engine->init_context == NULL;

	return 0;

error_ring_free:
	intel_ring_free(ring);
error_deref_obj:
	i915_gem_object_put(ctx_obj);
	return ret;
}

void intel_lr_context_resume(struct drm_i915_private *dev_priv)
{
	struct i915_gem_context *ctx = dev_priv->kernel_context;
	struct intel_engine_cs *engine;

	for_each_engine(engine, dev_priv) {
		struct intel_context *ce = &ctx->engine[engine->id];
		void *vaddr;
		uint32_t *reg_state;

		if (!ce->state)
			continue;

		vaddr = i915_gem_object_pin_map(ce->state->obj, I915_MAP_WB);
		if (WARN_ON(IS_ERR(vaddr)))
			continue;

		reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;

		reg_state[CTX_RING_HEAD+1] = 0;
		reg_state[CTX_RING_TAIL+1] = 0;

		ce->state->obj->dirty = true;
		i915_gem_object_unpin_map(ce->state->obj);

		ce->ring->head = 0;
		ce->ring->tail = 0;
	}
}