Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
/*	$NetBSD: intel_engine_cs.c,v 1.9 2021/12/19 12:40:43 riastradh Exp $	*/

/*
 * Copyright © 2016 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 */

#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: intel_engine_cs.c,v 1.9 2021/12/19 12:40:43 riastradh Exp $");

#include <drm/drm_print.h>

#include "gem/i915_gem_context.h"

#include "i915_drv.h"

#include "intel_context.h"
#include "intel_engine.h"
#include "intel_engine_pm.h"
#include "intel_engine_pool.h"
#include "intel_engine_user.h"
#include "intel_gt.h"
#include "intel_gt_requests.h"
#include "intel_lrc.h"
#include "intel_reset.h"
#include "intel_ring.h"

/* Haswell does have the CXT_SIZE register however it does not appear to be
 * valid. Now, docs explain in dwords what is in the context object. The full
 * size is 70720 bytes, however, the power context and execlist context will
 * never be saved (power context is stored elsewhere, and execlists don't work
 * on HSW) - so the final size, including the extra state required for the
 * Resource Streamer, is 66944 bytes, which rounds to 17 pages.
 */
#define HSW_CXT_TOTAL_SIZE		(17 * PAGE_SIZE)

#define DEFAULT_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_RENDER_SIZE	(20 * PAGE_SIZE)
#define GEN9_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
#define GEN10_LR_CONTEXT_RENDER_SIZE	(18 * PAGE_SIZE)
#define GEN11_LR_CONTEXT_RENDER_SIZE	(14 * PAGE_SIZE)

#define GEN8_LR_CONTEXT_OTHER_SIZE	( 2 * PAGE_SIZE)

#define MAX_MMIO_BASES 3
struct engine_info {
	unsigned int hw_id;
	u8 class;
	u8 instance;
	/* mmio bases table *must* be sorted in reverse gen order */
	struct engine_mmio_base {
		u32 gen : 8;
		u32 base : 24;
	} mmio_bases[MAX_MMIO_BASES];
};

static const struct engine_info intel_engines[] = {
	[RCS0] = {
		.hw_id = RCS0_HW,
		.class = RENDER_CLASS,
		.instance = 0,
		.mmio_bases = {
			{ .gen = 1, .base = RENDER_RING_BASE }
		},
	},
	[BCS0] = {
		.hw_id = BCS0_HW,
		.class = COPY_ENGINE_CLASS,
		.instance = 0,
		.mmio_bases = {
			{ .gen = 6, .base = BLT_RING_BASE }
		},
	},
	[VCS0] = {
		.hw_id = VCS0_HW,
		.class = VIDEO_DECODE_CLASS,
		.instance = 0,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_BSD_RING_BASE },
			{ .gen = 6, .base = GEN6_BSD_RING_BASE },
			{ .gen = 4, .base = BSD_RING_BASE }
		},
	},
	[VCS1] = {
		.hw_id = VCS1_HW,
		.class = VIDEO_DECODE_CLASS,
		.instance = 1,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_BSD2_RING_BASE },
			{ .gen = 8, .base = GEN8_BSD2_RING_BASE }
		},
	},
	[VCS2] = {
		.hw_id = VCS2_HW,
		.class = VIDEO_DECODE_CLASS,
		.instance = 2,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_BSD3_RING_BASE }
		},
	},
	[VCS3] = {
		.hw_id = VCS3_HW,
		.class = VIDEO_DECODE_CLASS,
		.instance = 3,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_BSD4_RING_BASE }
		},
	},
	[VECS0] = {
		.hw_id = VECS0_HW,
		.class = VIDEO_ENHANCEMENT_CLASS,
		.instance = 0,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_VEBOX_RING_BASE },
			{ .gen = 7, .base = VEBOX_RING_BASE }
		},
	},
	[VECS1] = {
		.hw_id = VECS1_HW,
		.class = VIDEO_ENHANCEMENT_CLASS,
		.instance = 1,
		.mmio_bases = {
			{ .gen = 11, .base = GEN11_VEBOX2_RING_BASE }
		},
	},
};

/**
 * intel_engine_context_size() - return the size of the context for an engine
 * @gt: the gt
 * @class: engine class
 *
 * Each engine class may require a different amount of space for a context
 * image.
 *
 * Return: size (in bytes) of an engine class 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.
 */
u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
{
	struct intel_uncore *uncore = gt->uncore;
	u32 cxt_size;

	BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE);

	switch (class) {
	case RENDER_CLASS:
		switch (INTEL_GEN(gt->i915)) {
		default:
			MISSING_CASE(INTEL_GEN(gt->i915));
			return DEFAULT_LR_CONTEXT_RENDER_SIZE;
		case 12:
		case 11:
			return GEN11_LR_CONTEXT_RENDER_SIZE;
		case 10:
			return GEN10_LR_CONTEXT_RENDER_SIZE;
		case 9:
			return GEN9_LR_CONTEXT_RENDER_SIZE;
		case 8:
			return GEN8_LR_CONTEXT_RENDER_SIZE;
		case 7:
			if (IS_HASWELL(gt->i915))
				return HSW_CXT_TOTAL_SIZE;

			cxt_size = intel_uncore_read(uncore, GEN7_CXT_SIZE);
			return round_up(GEN7_CXT_TOTAL_SIZE(cxt_size) * 64,
					PAGE_SIZE);
		case 6:
			cxt_size = intel_uncore_read(uncore, CXT_SIZE);
			return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64,
					PAGE_SIZE);
		case 5:
		case 4:
			/*
			 * There is a discrepancy here between the size reported
			 * by the register and the size of the context layout
			 * in the docs. Both are described as authorative!
			 *
			 * The discrepancy is on the order of a few cachelines,
			 * but the total is under one page (4k), which is our
			 * minimum allocation anyway so it should all come
			 * out in the wash.
			 */
			cxt_size = intel_uncore_read(uncore, CXT_SIZE) + 1;
			DRM_DEBUG_DRIVER("gen%d CXT_SIZE = %d bytes [0x%08x]\n",
					 INTEL_GEN(gt->i915),
					 cxt_size * 64,
					 cxt_size - 1);
			return round_up(cxt_size * 64, PAGE_SIZE);
		case 3:
		case 2:
		/* For the special day when i810 gets merged. */
		case 1:
			return 0;
		}
		break;
	default:
		MISSING_CASE(class);
		/* fall through */
	case VIDEO_DECODE_CLASS:
	case VIDEO_ENHANCEMENT_CLASS:
	case COPY_ENGINE_CLASS:
		if (INTEL_GEN(gt->i915) < 8)
			return 0;
		return GEN8_LR_CONTEXT_OTHER_SIZE;
	}
}

static u32 __engine_mmio_base(struct drm_i915_private *i915,
			      const struct engine_mmio_base *bases)
{
	int i;

	for (i = 0; i < MAX_MMIO_BASES; i++)
		if (INTEL_GEN(i915) >= bases[i].gen)
			break;

	GEM_BUG_ON(i == MAX_MMIO_BASES);
	GEM_BUG_ON(!bases[i].base);

	return bases[i].base;
}

static void __sprint_engine_name(struct intel_engine_cs *engine)
{
	/*
	 * Before we know what the uABI name for this engine will be,
	 * we still would like to keep track of this engine in the debug logs.
	 * We throw in a ' here as a reminder that this isn't its final name.
	 */
	GEM_WARN_ON(snprintf(engine->name, sizeof(engine->name), "%s'%u",
			     intel_engine_class_repr(engine->class),
			     engine->instance) >= sizeof(engine->name));
}

void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask)
{
	/*
	 * Though they added more rings on g4x/ilk, they did not add
	 * per-engine HWSTAM until gen6.
	 */
	if (INTEL_GEN(engine->i915) < 6 && engine->class != RENDER_CLASS)
		return;

	if (INTEL_GEN(engine->i915) >= 3)
		ENGINE_WRITE(engine, RING_HWSTAM, mask);
	else
		ENGINE_WRITE16(engine, RING_HWSTAM, mask);
}

static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine)
{
	/* Mask off all writes into the unknown HWSP */
	intel_engine_set_hwsp_writemask(engine, ~0u);
}

static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
{
	const struct engine_info *info = &intel_engines[id];
	struct intel_engine_cs *engine;

	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));

	if (GEM_DEBUG_WARN_ON(id >= ARRAY_SIZE(gt->engine)))
		return -EINVAL;

	if (GEM_DEBUG_WARN_ON(info->class > MAX_ENGINE_CLASS))
		return -EINVAL;

	if (GEM_DEBUG_WARN_ON(info->instance > MAX_ENGINE_INSTANCE))
		return -EINVAL;

	if (GEM_DEBUG_WARN_ON(gt->engine_class[info->class][info->instance]))
		return -EINVAL;

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

	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);

	engine->id = id;
	engine->legacy_idx = INVALID_ENGINE;
	engine->mask = BIT(id);
	engine->i915 = gt->i915;
	engine->gt = gt;
	engine->uncore = gt->uncore;
	engine->hw_id = engine->guc_id = info->hw_id;
	engine->mmio_base = __engine_mmio_base(gt->i915, info->mmio_bases);

	engine->class = info->class;
	engine->instance = info->instance;
	__sprint_engine_name(engine);

	engine->props.heartbeat_interval_ms =
		CONFIG_DRM_I915_HEARTBEAT_INTERVAL;
	engine->props.preempt_timeout_ms =
		CONFIG_DRM_I915_PREEMPT_TIMEOUT;
	engine->props.stop_timeout_ms =
		CONFIG_DRM_I915_STOP_TIMEOUT;
	engine->props.timeslice_duration_ms =
		CONFIG_DRM_I915_TIMESLICE_DURATION;

	engine->context_size = intel_engine_context_size(gt, engine->class);
	if (WARN_ON(engine->context_size > BIT(20)))
		engine->context_size = 0;
	if (engine->context_size)
		DRIVER_CAPS(gt->i915)->has_logical_contexts = true;

	/* Nothing to do here, execute in order of dependencies */
	engine->schedule = NULL;

	ewma__engine_latency_init(&engine->latency);
	seqlock_init(&engine->stats.lock);

	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);

	/* Scrub mmio state on takeover */
	intel_engine_sanitize_mmio(engine);

	gt->engine_class[info->class][info->instance] = engine;
	gt->engine[id] = engine;

	gt->i915->engine[id] = engine;

	return 0;
}

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

	if (engine->class == VIDEO_DECODE_CLASS) {
		/*
		 * HEVC support is present on first engine instance
		 * before Gen11 and on all instances afterwards.
		 */
		if (INTEL_GEN(i915) >= 11 ||
		    (INTEL_GEN(i915) >= 9 && engine->instance == 0))
			engine->uabi_capabilities |=
				I915_VIDEO_CLASS_CAPABILITY_HEVC;

		/*
		 * SFC block is present only on even logical engine
		 * instances.
		 */
		if ((INTEL_GEN(i915) >= 11 &&
		     RUNTIME_INFO(i915)->vdbox_sfc_access & engine->mask) ||
		    (INTEL_GEN(i915) >= 9 && engine->instance == 0))
			engine->uabi_capabilities |=
				I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
	} else if (engine->class == VIDEO_ENHANCEMENT_CLASS) {
		if (INTEL_GEN(i915) >= 9)
			engine->uabi_capabilities |=
				I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
	}
}

static void intel_setup_engine_capabilities(struct intel_gt *gt)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	for_each_engine(engine, gt, id)
		__setup_engine_capabilities(engine);
}

/**
 * intel_engines_release() - free the resources allocated for Command Streamers
 * @gt: pointer to struct intel_gt
 */
void intel_engines_release(struct intel_gt *gt)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	/* Decouple the backend; but keep the layout for late GPU resets */
	for_each_engine(engine, gt, id) {
		if (!engine->release)
			continue;

		engine->release(engine);
		engine->release = NULL;

		memset(&engine->reset, 0, sizeof(engine->reset));

		gt->i915->engine[id] = NULL;
	}
}

void intel_engines_free(struct intel_gt *gt)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	for_each_engine(engine, gt, id) {
		seqlock_destroy(&engine->stats.lock);
		kfree(engine);
		gt->engine[id] = NULL;
	}
}

/**
 * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
 * @gt: pointer to struct intel_gt
 *
 * Return: non-zero if the initialization failed.
 */
int intel_engines_init_mmio(struct intel_gt *gt)
{
	struct drm_i915_private *i915 = gt->i915;
	struct intel_device_info *device_info = mkwrite_device_info(i915);
	const unsigned int engine_mask = INTEL_INFO(i915)->engine_mask;
	unsigned int mask = 0;
	unsigned int i;
	int err;

	WARN_ON(engine_mask == 0);
	WARN_ON(engine_mask &
		GENMASK(BITS_PER_TYPE(mask) - 1, I915_NUM_ENGINES));

	if (i915_inject_probe_failure(i915))
		return -ENODEV;

	for (i = 0; i < ARRAY_SIZE(intel_engines); i++) {
		if (!HAS_ENGINE(i915, i))
			continue;

		err = intel_engine_setup(gt, i);
		if (err)
			goto cleanup;

		mask |= BIT(i);
	}

	/*
	 * Catch failures to update intel_engines table when the new engines
	 * are added to the driver by a warning and disabling the forgotten
	 * engines.
	 */
	if (WARN_ON(mask != engine_mask))
		device_info->engine_mask = mask;

	RUNTIME_INFO(i915)->num_engines = hweight32(mask);

	intel_gt_check_and_clear_faults(gt);

	intel_setup_engine_capabilities(gt);

	return 0;

cleanup:
	intel_engines_free(gt);
	return err;
}

void intel_engine_init_execlists(struct intel_engine_cs *engine)
{
	struct intel_engine_execlists * const execlists = &engine->execlists;

	execlists->port_mask = 1;
	GEM_BUG_ON(!is_power_of_2(execlists_num_ports(execlists)));
	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);

	memset(execlists->pending, 0, sizeof(execlists->pending));
	execlists->active =
		memset(execlists->inflight, 0, sizeof(execlists->inflight));

	execlists->queue_priority_hint = INT_MIN;
	i915_sched_init(execlists);
}

static void cleanup_status_page(struct intel_engine_cs *engine)
{
	struct i915_vma *vma;

	/* Prevent writes into HWSP after returning the page to the system */
	intel_engine_set_hwsp_writemask(engine, ~0u);

	vma = fetch_and_zero(&engine->status_page.vma);
	if (!vma)
		return;

	if (!HWS_NEEDS_PHYSICAL(engine->i915))
		i915_vma_unpin(vma);

	i915_gem_object_unpin_map(vma->obj);
	i915_gem_object_put(vma->obj);
}

static int pin_ggtt_status_page(struct intel_engine_cs *engine,
				struct i915_vma *vma)
{
	unsigned int flags;

	flags = PIN_GLOBAL;
	if (!HAS_LLC(engine->i915) && i915_ggtt_has_aperture(engine->gt->ggtt))
		/*
		 * On g33, we cannot place HWS above 256MiB, so
		 * restrict its pinning to the low mappable arena.
		 * Though this restriction is not documented for
		 * gen4, gen5, or byt, they also behave similarly
		 * and hang if the HWS is placed at the top of the
		 * GTT. To generalise, it appears that all !llc
		 * platforms have issues with us placing the HWS
		 * above the mappable region (even though we never
		 * actually map it).
		 */
		flags |= PIN_MAPPABLE;
	else
		flags |= PIN_HIGH;

	return i915_vma_pin(vma, 0, 0, flags);
}

static int init_status_page(struct intel_engine_cs *engine)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	void *vaddr;
	int ret;

	/*
	 * Though the HWS register does support 36bit addresses, historically
	 * we have had hangs and corruption reported due to wild writes if
	 * the HWS is placed above 4G. We only allow objects to be allocated
	 * in GFP_DMA32 for i965, and no earlier physical address users had
	 * access to more than 4G.
	 */
	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
	if (IS_ERR(obj)) {
		DRM_ERROR("Failed to allocate status page\n");
		return PTR_ERR(obj);
	}

	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);

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

	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
	if (IS_ERR(vaddr)) {
		ret = PTR_ERR(vaddr);
		goto err;
	}

	engine->status_page.addr = memset(vaddr, 0, PAGE_SIZE);
	engine->status_page.vma = vma;

	if (!HWS_NEEDS_PHYSICAL(engine->i915)) {
		ret = pin_ggtt_status_page(engine, vma);
		if (ret)
			goto err_unpin;
	}

	return 0;

err_unpin:
	i915_gem_object_unpin_map(obj);
err:
	i915_gem_object_put(obj);
	return ret;
}

static int engine_setup_common(struct intel_engine_cs *engine)
{
	int err;

	init_llist_head(&engine->barrier_tasks);

	err = init_status_page(engine);
	if (err)
		return err;

	intel_engine_init_active(engine, ENGINE_PHYSICAL);
	intel_engine_init_breadcrumbs(engine);
	intel_engine_init_execlists(engine);
	intel_engine_init_cmd_parser(engine);
	intel_engine_init__pm(engine);
	intel_engine_init_retire(engine);

	intel_engine_pool_init(&engine->pool);

	/* Use the whole device by default */
	engine->sseu =
		intel_sseu_from_device_info(&RUNTIME_INFO(engine->i915)->sseu);

	intel_engine_init_workarounds(engine);
	intel_engine_init_whitelist(engine);
	intel_engine_init_ctx_wa(engine);

	return 0;
}

struct measure_breadcrumb {
	struct i915_request rq;
	struct intel_timeline timeline;
	struct intel_ring ring;
	u32 cs[1024];
};

static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
{
	struct measure_breadcrumb *frame;
	int dw = -ENOMEM;

	GEM_BUG_ON(!engine->gt->scratch);

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

	if (intel_timeline_init(&frame->timeline,
				engine->gt,
				engine->status_page.vma))
		goto out_frame;

	mutex_lock(&frame->timeline.mutex);

	frame->ring.vaddr = frame->cs;
	frame->ring.size = sizeof(frame->cs);
	frame->ring.effective_size = frame->ring.size;
	intel_ring_update_space(&frame->ring);

	frame->rq.i915 = engine->i915;
	frame->rq.engine = engine;
	frame->rq.ring = &frame->ring;
	rcu_assign_pointer(frame->rq.timeline, &frame->timeline);

	dw = intel_timeline_pin(&frame->timeline);
	if (dw < 0)
		goto out_timeline;

	spin_lock_irq(&engine->active.lock);
	dw = engine->emit_fini_breadcrumb(&frame->rq, frame->cs) - frame->cs;
	spin_unlock_irq(&engine->active.lock);

	GEM_BUG_ON(dw & 1); /* RING_TAIL must be qword aligned */

	intel_timeline_unpin(&frame->timeline);

out_timeline:
	mutex_unlock(&frame->timeline.mutex);
	intel_timeline_fini(&frame->timeline);
out_frame:
	kfree(frame);
	return dw;
}

void
intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
{
	INIT_LIST_HEAD(&engine->active.requests);
	INIT_LIST_HEAD(&engine->active.hold);

	spin_lock_init(&engine->active.lock);
	lockdep_set_subclass(&engine->active.lock, subclass);

	/*
	 * Due to an interesting quirk in lockdep's internal debug tracking,
	 * after setting a subclass we must ensure the lock is used. Otherwise,
	 * nr_unused_locks is incremented once too often.
	 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	local_irq_disable();
	lock_map_acquire(&engine->active.lock.dep_map);
	lock_map_release(&engine->active.lock.dep_map);
	local_irq_enable();
#endif
}

static struct intel_context *
create_kernel_context(struct intel_engine_cs *engine)
{
	static struct lock_class_key kernel;
	struct intel_context *ce;
	int err;

	ce = intel_context_create(engine);
	if (IS_ERR(ce))
		return ce;

	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);

	err = intel_context_pin(ce); /* perma-pin so it is always available */
	if (err) {
		intel_context_put(ce);
		return ERR_PTR(err);
	}

	/*
	 * Give our perma-pinned kernel timelines a separate lockdep class,
	 * so that we can use them from within the normal user timelines
	 * should we need to inject GPU operations during their request
	 * construction.
	 */
	lockdep_set_class(&ce->timeline->mutex, &kernel);

	return ce;
}

/**
 * intel_engines_init_common - initialize cengine state which might require hw access
 * @engine: Engine to initialize.
 *
 * Initializes @engine@ structure members shared between legacy and execlists
 * submission modes which do require hardware access.
 *
 * Typcally done at later stages of submission mode specific engine setup.
 *
 * Returns zero on success or an error code on failure.
 */
static int engine_init_common(struct intel_engine_cs *engine)
{
	struct intel_context *ce;
	int ret;

	engine->set_default_submission(engine);

	ret = measure_breadcrumb_dw(engine);
	if (ret < 0)
		return ret;

	engine->emit_fini_breadcrumb_dw = ret;

	/*
	 * We may need to do things with the shrinker which
	 * require us to immediately switch back to the default
	 * context. This can cause a problem as pinning the
	 * default context also requires GTT space which may not
	 * be available. To avoid this we always pin the default
	 * context.
	 */
	ce = create_kernel_context(engine);
	if (IS_ERR(ce))
		return PTR_ERR(ce);

	engine->kernel_context = ce;

	return 0;
}

int intel_engines_init(struct intel_gt *gt)
{
	int (*setup)(struct intel_engine_cs *engine);
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	int err;

	if (HAS_EXECLISTS(gt->i915))
		setup = intel_execlists_submission_setup;
	else
		setup = intel_ring_submission_setup;

	for_each_engine(engine, gt, id) {
		err = engine_setup_common(engine);
		if (err)
			return err;

		err = setup(engine);
		if (err)
			return err;

		err = engine_init_common(engine);
		if (err)
			return err;

		intel_engine_add_user(engine);
	}

	return 0;
}

/**
 * intel_engines_cleanup_common - cleans up the engine state created by
 *                                the common initiailizers.
 * @engine: Engine to cleanup.
 *
 * This cleans up everything created by the common helpers.
 */
void intel_engine_cleanup_common(struct intel_engine_cs *engine)
{
	GEM_BUG_ON(!list_empty(&engine->active.requests));
	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */

	cleanup_status_page(engine);

	intel_engine_fini_retire(engine);
	intel_engine_fini__pm(engine);
	intel_engine_pool_fini(&engine->pool);
	intel_engine_fini_breadcrumbs(engine);
	intel_engine_cleanup_cmd_parser(engine);

	if (engine->default_state)
		i915_gem_object_put(engine->default_state);

	if (engine->kernel_context) {
		intel_context_unpin(engine->kernel_context);
		intel_context_put(engine->kernel_context);
	}
	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));

	intel_wa_list_free(&engine->ctx_wa_list);
	intel_wa_list_free(&engine->wa_list);
	intel_wa_list_free(&engine->whitelist);

	spin_lock_destroy(&engine->active.lock);
}

u64 intel_engine_get_active_head(const struct intel_engine_cs *engine)
{
	struct drm_i915_private *i915 = engine->i915;

	u64 acthd;

	if (INTEL_GEN(i915) >= 8)
		acthd = ENGINE_READ64(engine, RING_ACTHD, RING_ACTHD_UDW);
	else if (INTEL_GEN(i915) >= 4)
		acthd = ENGINE_READ(engine, RING_ACTHD);
	else
		acthd = ENGINE_READ(engine, ACTHD);

	return acthd;
}

u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
{
	u64 bbaddr;

	if (INTEL_GEN(engine->i915) >= 8)
		bbaddr = ENGINE_READ64(engine, RING_BBADDR, RING_BBADDR_UDW);
	else
		bbaddr = ENGINE_READ(engine, RING_BBADDR);

	return bbaddr;
}

static unsigned long stop_timeout(const struct intel_engine_cs *engine)
{
	if (in_atomic() || irqs_disabled()) /* inside atomic preempt-reset? */
		return 0;

	/*
	 * If we are doing a normal GPU reset, we can take our time and allow
	 * the engine to quiesce. We've stopped submission to the engine, and
	 * if we wait long enough an innocent context should complete and
	 * leave the engine idle. So they should not be caught unaware by
	 * the forthcoming GPU reset (which usually follows the stop_cs)!
	 */
	return READ_ONCE(engine->props.stop_timeout_ms);
}

int intel_engine_stop_cs(struct intel_engine_cs *engine)
{
	struct intel_uncore *uncore = engine->uncore;
	const u32 base = engine->mmio_base;
	const i915_reg_t mode = RING_MI_MODE(base);
	int err;

	if (INTEL_GEN(engine->i915) < 3)
		return -ENODEV;

	ENGINE_TRACE(engine, "\n");

	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));

	err = 0;
	if (__intel_wait_for_register_fw(uncore,
					 mode, MODE_IDLE, MODE_IDLE,
					 1000, stop_timeout(engine),
					 NULL)) {
		ENGINE_TRACE(engine, "timed out on STOP_RING -> IDLE\n");
		err = -ETIMEDOUT;
	}

	/* A final mmio read to let GPU writes be hopefully flushed to memory */
	intel_uncore_posting_read_fw(uncore, mode);

	return err;
}

void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
{
	ENGINE_TRACE(engine, "\n");

	ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
}

const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
{
	switch (type) {
	case I915_CACHE_NONE: return " uncached";
	case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
	case I915_CACHE_L3_LLC: return " L3+LLC";
	case I915_CACHE_WT: return " WT";
	default: return "";
	}
}

static u32
read_subslice_reg(const struct intel_engine_cs *engine,
		  int slice, int subslice, i915_reg_t reg)
{
	struct drm_i915_private *i915 = engine->i915;
	struct intel_uncore *uncore = engine->uncore;
	u32 mcr_mask, mcr_ss, mcr, old_mcr, val;
	enum forcewake_domains fw_domains;

	if (INTEL_GEN(i915) >= 11) {
		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
		mcr_ss = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
	} else {
		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
		mcr_ss = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
	}

	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
						    FW_REG_READ);
	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
						     GEN8_MCR_SELECTOR,
						     FW_REG_READ | FW_REG_WRITE);

	spin_lock_irq(&uncore->lock);
	intel_uncore_forcewake_get__locked(uncore, fw_domains);

	old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);

	mcr &= ~mcr_mask;
	mcr |= mcr_ss;
	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);

	val = intel_uncore_read_fw(uncore, reg);

	mcr &= ~mcr_mask;
	mcr |= old_mcr & mcr_mask;

	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);

	intel_uncore_forcewake_put__locked(uncore, fw_domains);
	spin_unlock_irq(&uncore->lock);

	return val;
}

/* NB: please notice the memset */
void intel_engine_get_instdone(const struct intel_engine_cs *engine,
			       struct intel_instdone *instdone)
{
	struct drm_i915_private *i915 = engine->i915;
	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
	struct intel_uncore *uncore = engine->uncore;
	u32 mmio_base = engine->mmio_base;
	int slice;
	int subslice;

	memset(instdone, 0, sizeof(*instdone));

	switch (INTEL_GEN(i915)) {
	default:
		instdone->instdone =
			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));

		if (engine->id != RCS0)
			break;

		instdone->slice_common =
			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
		for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
			instdone->sampler[slice][subslice] =
				read_subslice_reg(engine, slice, subslice,
						  GEN7_SAMPLER_INSTDONE);
			instdone->row[slice][subslice] =
				read_subslice_reg(engine, slice, subslice,
						  GEN7_ROW_INSTDONE);
		}
		break;
	case 7:
		instdone->instdone =
			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));

		if (engine->id != RCS0)
			break;

		instdone->slice_common =
			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
		instdone->sampler[0][0] =
			intel_uncore_read(uncore, GEN7_SAMPLER_INSTDONE);
		instdone->row[0][0] =
			intel_uncore_read(uncore, GEN7_ROW_INSTDONE);

		break;
	case 6:
	case 5:
	case 4:
		instdone->instdone =
			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
		if (engine->id == RCS0)
			/* HACK: Using the wrong struct member */
			instdone->slice_common =
				intel_uncore_read(uncore, GEN4_INSTDONE1);
		break;
	case 3:
	case 2:
		instdone->instdone = intel_uncore_read(uncore, GEN2_INSTDONE);
		break;
	}
}

static bool ring_is_idle(struct intel_engine_cs *engine)
{
	bool idle = true;

	if (I915_SELFTEST_ONLY(!engine->mmio_base))
		return true;

	if (!intel_engine_pm_get_if_awake(engine))
		return true;

	/* First check that no commands are left in the ring */
	if ((ENGINE_READ(engine, RING_HEAD) & HEAD_ADDR) !=
	    (ENGINE_READ(engine, RING_TAIL) & TAIL_ADDR))
		idle = false;

	/* No bit for gen2, so assume the CS parser is idle */
	if (INTEL_GEN(engine->i915) > 2 &&
	    !(ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE))
		idle = false;

	intel_engine_pm_put(engine);

	return idle;
}

void intel_engine_flush_submission(struct intel_engine_cs *engine)
{
	struct tasklet_struct *t = &engine->execlists.tasklet;

	if (__tasklet_is_scheduled(t)) {
#ifdef __NetBSD__
		int s = splsoftserial();
#else
		local_bh_disable();
#endif
		if (tasklet_trylock(t)) {
			/* Must wait for any GPU reset in progress. */
			if (__tasklet_is_enabled(t))
				t->func(t->data);
			tasklet_unlock(t);
		}
#ifdef __NetBSD__
		splx(s);
#else
		local_bh_enable();
#endif
	}

	/* Otherwise flush the tasklet if it was running on another cpu */
	tasklet_unlock_wait(t);
}

/**
 * intel_engine_is_idle() - Report if the engine has finished process all work
 * @engine: the intel_engine_cs
 *
 * Return true if there are no requests pending, nothing left to be submitted
 * to hardware, and that the engine is idle.
 */
bool intel_engine_is_idle(struct intel_engine_cs *engine)
{
	/* More white lies, if wedged, hw state is inconsistent */
	if (intel_gt_is_wedged(engine->gt))
		return true;

	if (!intel_engine_pm_is_awake(engine))
		return true;

	/* Waiting to drain ELSP? */
	if (execlists_active(&engine->execlists)) {
#ifdef __NetBSD__
		xc_barrier(XC_HIGHPRI);
#else
		synchronize_hardirq(engine->i915->drm.pdev->irq);
#endif

		intel_engine_flush_submission(engine);

		if (execlists_active(&engine->execlists))
			return false;
	}

	/* ELSP is empty, but there are ready requests? E.g. after reset */
	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
		return false;

	/* Ring stopped? */
	return ring_is_idle(engine);
}

bool intel_engines_are_idle(struct intel_gt *gt)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	/*
	 * If the driver is wedged, HW state may be very inconsistent and
	 * report that it is still busy, even though we have stopped using it.
	 */
	if (intel_gt_is_wedged(gt))
		return true;

	/* Already parked (and passed an idleness test); must still be idle */
	if (!READ_ONCE(gt->awake))
		return true;

	for_each_engine(engine, gt, id) {
		if (!intel_engine_is_idle(engine))
			return false;
	}

	return true;
}

void intel_engines_reset_default_submission(struct intel_gt *gt)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	for_each_engine(engine, gt, id)
		engine->set_default_submission(engine);
}

bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
{
	switch (INTEL_GEN(engine->i915)) {
	case 2:
		return false; /* uses physical not virtual addresses */
	case 3:
		/* maybe only uses physical not virtual addresses */
		return !(IS_I915G(engine->i915) || IS_I915GM(engine->i915));
	case 4:
		return !IS_I965G(engine->i915); /* who knows! */
	case 6:
		return engine->class != VIDEO_DECODE_CLASS; /* b0rked */
	default:
		return true;
	}
}

static int print_sched_attr(struct drm_i915_private *i915,
			    const struct i915_sched_attr *attr,
			    char *buf, int x, int len)
{
	if (attr->priority == I915_PRIORITY_INVALID)
		return x;

	x += snprintf(buf + x, len - x,
		      " prio=%d", attr->priority);

	return x;
}

static void print_request(struct drm_printer *m,
			  struct i915_request *rq,
			  const char *prefix)
{
	const char *name = rq->fence.ops->get_timeline_name(&rq->fence);
	char buf[80] = "";
	int x = 0;

	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));

	drm_printf(m, "%s %"PRIx64":%"PRIx64"%s%s %s @ %dms: %s\n",
		   prefix,
		   (uint64_t)rq->fence.context, (uint64_t)rq->fence.seqno,
		   i915_request_completed(rq) ? "!" :
		   i915_request_started(rq) ? "*" :
		   "",
		   test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
			    &rq->fence.flags) ? "+" :
		   test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
			    &rq->fence.flags) ? "-" :
		   "",
		   buf,
		   jiffies_to_msecs(jiffies - rq->emitted_jiffies),
		   name);
}

#define	hexdump	intel_hexdump

static void hexdump(struct drm_printer *m, const void *buf, size_t len)
{
	const size_t rowsize = 8 * sizeof(u32);
	const void *prev = NULL;
	bool skip = false;
	size_t pos;

	for (pos = 0; pos < len; pos += rowsize) {
		char line[128];

		if (prev && !memcmp(prev, buf + pos, rowsize)) {
			if (!skip) {
				drm_printf(m, "*\n");
				skip = true;
			}
			continue;
		}

		WARN_ON_ONCE(hex_dump_to_buffer(buf + pos, len - pos,
						rowsize, sizeof(u32),
						line, sizeof(line),
						false) >= sizeof(line));
		drm_printf(m, "[%04zx] %s\n", pos, line);

		prev = buf + pos;
		skip = false;
	}
}

static struct intel_timeline *get_timeline(struct i915_request *rq)
{
	struct intel_timeline *tl;

	/*
	 * Even though we are holding the engine->active.lock here, there
	 * is no control over the submission queue per-se and we are
	 * inspecting the active state at a random point in time, with an
	 * unknown queue. Play safe and make sure the timeline remains valid.
	 * (Only being used for pretty printing, one extra kref shouldn't
	 * cause a camel stampede!)
	 */
	rcu_read_lock();
	tl = rcu_dereference(rq->timeline);
	if (!kref_get_unless_zero(&tl->kref))
		tl = NULL;
	rcu_read_unlock();

	return tl;
}

static const char *repr_timer(const struct timer_list *t)
{
#ifdef __NetBSD__
	if (!callout_active(__UNCONST(&t->tl_callout)))
		return "inactive";

	if (callout_pending(__UNCONST(&t->tl_callout)))
		return "pending";
#else
	if (!READ_ONCE(t->expires))
		return "inactive";

	if (timer_pending(t))
		return "active";
#endif

	return "expired";
}

static void intel_engine_print_registers(struct intel_engine_cs *engine,
					 struct drm_printer *m)
{
	struct drm_i915_private *dev_priv = engine->i915;
	struct intel_engine_execlists * const execlists = &engine->execlists;
	u64 addr;

	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
	drm_printf(m, "\tRING_START: 0x%08x\n",
		   ENGINE_READ(engine, RING_START));
	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
		   ENGINE_READ(engine, RING_HEAD) & HEAD_ADDR);
	drm_printf(m, "\tRING_TAIL:  0x%08x\n",
		   ENGINE_READ(engine, RING_TAIL) & TAIL_ADDR);
	drm_printf(m, "\tRING_CTL:   0x%08x%s\n",
		   ENGINE_READ(engine, RING_CTL),
		   ENGINE_READ(engine, RING_CTL) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? " [waiting]" : "");
	if (INTEL_GEN(engine->i915) > 2) {
		drm_printf(m, "\tRING_MODE:  0x%08x%s\n",
			   ENGINE_READ(engine, RING_MI_MODE),
			   ENGINE_READ(engine, RING_MI_MODE) & (MODE_IDLE) ? " [idle]" : "");
	}

	if (INTEL_GEN(dev_priv) >= 6) {
		drm_printf(m, "\tRING_IMR: %08x\n",
			   ENGINE_READ(engine, RING_IMR));
	}

	addr = intel_engine_get_active_head(engine);
	drm_printf(m, "\tACTHD:  0x%08x_%08x\n",
		   upper_32_bits(addr), lower_32_bits(addr));
	addr = intel_engine_get_last_batch_head(engine);
	drm_printf(m, "\tBBADDR: 0x%08x_%08x\n",
		   upper_32_bits(addr), lower_32_bits(addr));
	if (INTEL_GEN(dev_priv) >= 8)
		addr = ENGINE_READ64(engine, RING_DMA_FADD, RING_DMA_FADD_UDW);
	else if (INTEL_GEN(dev_priv) >= 4)
		addr = ENGINE_READ(engine, RING_DMA_FADD);
	else
		addr = ENGINE_READ(engine, DMA_FADD_I8XX);
	drm_printf(m, "\tDMA_FADDR: 0x%08x_%08x\n",
		   upper_32_bits(addr), lower_32_bits(addr));
	if (INTEL_GEN(dev_priv) >= 4) {
		drm_printf(m, "\tIPEIR: 0x%08x\n",
			   ENGINE_READ(engine, RING_IPEIR));
		drm_printf(m, "\tIPEHR: 0x%08x\n",
			   ENGINE_READ(engine, RING_IPEHR));
	} else {
		drm_printf(m, "\tIPEIR: 0x%08x\n", ENGINE_READ(engine, IPEIR));
		drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR));
	}

	if (HAS_EXECLISTS(dev_priv)) {
		struct i915_request * const *port, *rq;
		const u32 *hws =
			&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
		const u8 num_entries = execlists->csb_size;
		unsigned int idx;
		u8 read, write;

		drm_printf(m, "\tExeclist tasklet queued? %s (%s), preempt? %s, timeslice? %s\n",
#ifdef __NetBSD__		/* XXX sigh */
			   "<abstraction violation>",
			   "<abstraction violation>",
#else
			   yesno(test_bit(TASKLET_STATE_SCHED,
					  &engine->execlists.tasklet.state)),
			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)),
#endif
			   repr_timer(&engine->execlists.preempt),
			   repr_timer(&engine->execlists.timer));

		read = execlists->csb_head;
		write = READ_ONCE(*execlists->csb_write);

		drm_printf(m, "\tExeclist status: 0x%08x %08x; CSB read:%d, write:%d, entries:%d\n",
			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO),
			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI),
			   read, write, num_entries);

		if (read >= num_entries)
			read = 0;
		if (write >= num_entries)
			write = 0;
		if (read > write)
			write += num_entries;
		while (read < write) {
			idx = ++read % num_entries;
			drm_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n",
				   idx, hws[idx * 2], hws[idx * 2 + 1]);
		}

#ifdef __NetBSD__
		int s = execlists_active_lock_bh(execlists);
#else
		execlists_active_lock_bh(execlists);
#endif
		rcu_read_lock();
		for (port = execlists->active; (rq = *port); port++) {
			char hdr[80];
			int len;

			len = snprintf(hdr, sizeof(hdr),
				       "\t\tActive[%d]: ",
				       (int)(port - execlists->active));
			if (!i915_request_signaled(rq)) {
				struct intel_timeline *tl = get_timeline(rq);

				len += snprintf(hdr + len, sizeof(hdr) - len,
						"ring:{start:%08x, hwsp:%08x, seqno:%08x}, ",
						i915_ggtt_offset(rq->ring->vma),
						tl ? tl->hwsp_offset : 0,
						hwsp_seqno(rq));

				if (tl)
					intel_timeline_put(tl);
			}
			snprintf(hdr + len, sizeof(hdr) - len, "rq: ");
			print_request(m, rq, hdr);
		}
		for (port = execlists->pending; (rq = *port); port++) {
			struct intel_timeline *tl = get_timeline(rq);
			char hdr[80];

			snprintf(hdr, sizeof(hdr),
				 "\t\tPending[%d] ring:{start:%08x, hwsp:%08x, seqno:%08x}, rq: ",
				 (int)(port - execlists->pending),
				 i915_ggtt_offset(rq->ring->vma),
				 tl ? tl->hwsp_offset : 0,
				 hwsp_seqno(rq));
			print_request(m, rq, hdr);

			if (tl)
				intel_timeline_put(tl);
		}
		rcu_read_unlock();
#ifdef __NetBSD__
		execlists_active_unlock_bh(execlists, s);
#else
		execlists_active_unlock_bh(execlists);
#endif
	} else if (INTEL_GEN(dev_priv) > 6) {
		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
			   ENGINE_READ(engine, RING_PP_DIR_BASE));
		drm_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n",
			   ENGINE_READ(engine, RING_PP_DIR_BASE_READ));
		drm_printf(m, "\tPP_DIR_DCLV: 0x%08x\n",
			   ENGINE_READ(engine, RING_PP_DIR_DCLV));
	}
}

static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
{
	void *ring;
	int size;

	drm_printf(m,
		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
		   rq->head, rq->postfix, rq->tail,
		   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
		   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);

	size = rq->tail - rq->head;
	if (rq->tail < rq->head)
		size += rq->ring->size;

	ring = kmalloc(size, GFP_ATOMIC);
	if (ring) {
		const void *vaddr = rq->ring->vaddr;
		unsigned int head = rq->head;
		unsigned int len = 0;

		if (rq->tail < head) {
			len = rq->ring->size - head;
			memcpy(ring, vaddr + head, len);
			head = 0;
		}
		memcpy(ring + len, vaddr + head, size - len);

		hexdump(m, ring, size);
		kfree(ring);
	}
}

static unsigned long list_count(struct list_head *list)
{
	struct list_head *pos;
	unsigned long count = 0;

	list_for_each(pos, list)
		count++;

	return count;
}

void intel_engine_dump(struct intel_engine_cs *engine,
		       struct drm_printer *m,
		       const char *header, ...)
{
	struct i915_gpu_error * const error = &engine->i915->gpu_error;
	struct i915_request *rq;
	intel_wakeref_t wakeref;
	unsigned long flags;

	if (header) {
		va_list ap;

		va_start(ap, header);
		drm_vprintf(m, header, &ap);
		va_end(ap);
	}

	if (intel_gt_is_wedged(engine->gt))
		drm_printf(m, "*** WEDGED ***\n");

	drm_printf(m, "\tAwake? %d\n", atomic_read(&engine->wakeref.count));
	drm_printf(m, "\tBarriers?: %s\n",
		   yesno(!llist_empty(&engine->barrier_tasks)));
	drm_printf(m, "\tLatency: %luus\n",
		   ewma__engine_latency_read(&engine->latency));

	rcu_read_lock();
	rq = READ_ONCE(engine->heartbeat.systole);
	if (rq)
		drm_printf(m, "\tHeartbeat: %d ms ago\n",
			   jiffies_to_msecs(jiffies - rq->emitted_jiffies));
	rcu_read_unlock();
	drm_printf(m, "\tReset count: %d (global %d)\n",
		   i915_reset_engine_count(error, engine),
		   i915_reset_count(error));

	drm_printf(m, "\tRequests:\n");

	spin_lock_irqsave(&engine->active.lock, flags);
	rq = intel_engine_find_active_request(engine);
	if (rq) {
		struct intel_timeline *tl = get_timeline(rq);

		print_request(m, rq, "\t\tactive ");

		drm_printf(m, "\t\tring->start:  0x%08x\n",
			   i915_ggtt_offset(rq->ring->vma));
		drm_printf(m, "\t\tring->head:   0x%08x\n",
			   rq->ring->head);
		drm_printf(m, "\t\tring->tail:   0x%08x\n",
			   rq->ring->tail);
		drm_printf(m, "\t\tring->emit:   0x%08x\n",
			   rq->ring->emit);
		drm_printf(m, "\t\tring->space:  0x%08x\n",
			   rq->ring->space);

		if (tl) {
			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
				   tl->hwsp_offset);
			intel_timeline_put(tl);
		}

		print_request_ring(m, rq);

		if (rq->context->lrc_reg_state) {
			drm_printf(m, "Logical Ring Context:\n");
			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
		}
	}
	drm_printf(m, "\tOn hold?: %lu\n", list_count(&engine->active.hold));
	spin_unlock_irqrestore(&engine->active.lock, flags);

	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
	wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
	if (wakeref) {
		intel_engine_print_registers(engine, m);
		intel_runtime_pm_put(engine->uncore->rpm, wakeref);
	} else {
		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
	}

	intel_execlists_show_requests(engine, m, print_request, 8);

	drm_printf(m, "HWSP:\n");
	hexdump(m, engine->status_page.addr, PAGE_SIZE);

	drm_printf(m, "Idle? %s\n", yesno(intel_engine_is_idle(engine)));

	intel_engine_print_breadcrumbs(engine, m);
}

/**
 * intel_enable_engine_stats() - Enable engine busy tracking on engine
 * @engine: engine to enable stats collection
 *
 * Start collecting the engine busyness data for @engine.
 *
 * Returns 0 on success or a negative error code.
 */
int intel_enable_engine_stats(struct intel_engine_cs *engine)
{
	struct intel_engine_execlists *execlists = &engine->execlists;
	unsigned long flags;
	int err = 0;

	if (!intel_engine_supports_stats(engine))
		return -ENODEV;

#ifdef __NetBSD__
	int s = execlists_active_lock_bh(execlists);
#else
	execlists_active_lock_bh(execlists);
#endif
	write_seqlock_irqsave(&engine->stats.lock, flags);

	if (unlikely(engine->stats.enabled == ~0)) {
		err = -EBUSY;
		goto unlock;
	}

	if (engine->stats.enabled++ == 0) {
		struct i915_request * const *port;
		struct i915_request *rq;

		engine->stats.enabled_at = ktime_get();

		/* XXX submission method oblivious? */
		for (port = execlists->active; (rq = *port); port++)
			engine->stats.active++;

		for (port = execlists->pending; (rq = *port); port++) {
			/* Exclude any contexts already counted in active */
			if (!intel_context_inflight_count(rq->context))
				engine->stats.active++;
		}

		if (engine->stats.active)
			engine->stats.start = engine->stats.enabled_at;
	}

unlock:
	write_sequnlock_irqrestore(&engine->stats.lock, flags);
#ifdef __NetBSD__
	execlists_active_unlock_bh(execlists, s);
#else
	execlists_active_unlock_bh(execlists);
#endif

	return err;
}

static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
{
	ktime_t total = engine->stats.total;

	/*
	 * If the engine is executing something at the moment
	 * add it to the total.
	 */
	if (engine->stats.active)
		total = ktime_add(total,
				  ktime_sub(ktime_get(), engine->stats.start));

	return total;
}

/**
 * intel_engine_get_busy_time() - Return current accumulated engine busyness
 * @engine: engine to report on
 *
 * Returns accumulated time @engine was busy since engine stats were enabled.
 */
ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
{
	unsigned int seq;
	ktime_t total;

	do {
		seq = read_seqbegin(&engine->stats.lock);
		total = __intel_engine_get_busy_time(engine);
	} while (read_seqretry(&engine->stats.lock, seq));

	return total;
}

/**
 * intel_disable_engine_stats() - Disable engine busy tracking on engine
 * @engine: engine to disable stats collection
 *
 * Stops collecting the engine busyness data for @engine.
 */
void intel_disable_engine_stats(struct intel_engine_cs *engine)
{
	unsigned long flags;

	if (!intel_engine_supports_stats(engine))
		return;

	write_seqlock_irqsave(&engine->stats.lock, flags);
	WARN_ON_ONCE(engine->stats.enabled == 0);
	if (--engine->stats.enabled == 0) {
		engine->stats.total = __intel_engine_get_busy_time(engine);
		engine->stats.active = 0;
	}
	write_sequnlock_irqrestore(&engine->stats.lock, flags);
}

static bool match_ring(struct i915_request *rq)
{
	u32 ring = ENGINE_READ(rq->engine, RING_START);

	return ring == i915_ggtt_offset(rq->ring->vma);
}

struct i915_request *
intel_engine_find_active_request(struct intel_engine_cs *engine)
{
	struct i915_request *request, *active = NULL;

	/*
	 * We are called by the error capture, reset and to dump engine
	 * state at random points in time. In particular, note that neither is
	 * crucially ordered with an interrupt. After a hang, the GPU is dead
	 * and we assume that no more writes can happen (we waited long enough
	 * for all writes that were in transaction to be flushed) - adding an
	 * extra delay for a recent interrupt is pointless. Hence, we do
	 * not need an engine->irq_seqno_barrier() before the seqno reads.
	 * At all other times, we must assume the GPU is still running, but
	 * we only care about the snapshot of this moment.
	 */
	lockdep_assert_held(&engine->active.lock);
	list_for_each_entry(request, &engine->active.requests, sched.link) {
		if (i915_request_completed(request))
			continue;

		if (!i915_request_started(request))
			continue;

		/* More than one preemptible request may match! */
		if (!match_ring(request))
			continue;

		active = request;
		break;
	}

	return active;
}

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "mock_engine.c"
#include "selftest_engine.c"
#include "selftest_engine_cs.c"
#endif