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
|
// SPDX-License-Identifier: MIT
/*
* Copyright © 2021-2022 Intel Corporation
*/
#include <linux/types.h>
#include <drm/drm_print.h>
#include "gt/intel_engine_regs.h"
#include "gt/intel_gt.h"
#include "gt/intel_gt_mcr.h"
#include "gt/intel_gt_regs.h"
#include "gt/intel_lrc.h"
#include "guc_capture_fwif.h"
#include "intel_guc_capture.h"
#include "intel_guc_fwif.h"
#include "intel_guc_print.h"
#include "i915_drv.h"
#include "i915_gpu_error.h"
#include "i915_irq.h"
#include "i915_memcpy.h"
#include "i915_reg.h"
/*
* Define all device tables of GuC error capture register lists
* NOTE: For engine-registers, GuC only needs the register offsets
* from the engine-mmio-base
*/
#define COMMON_BASE_GLOBAL \
{ FORCEWAKE_MT, 0, 0, "FORCEWAKE" }
#define COMMON_GEN9BASE_GLOBAL \
{ ERROR_GEN6, 0, 0, "ERROR_GEN6" }, \
{ DONE_REG, 0, 0, "DONE_REG" }, \
{ HSW_GTT_CACHE_EN, 0, 0, "HSW_GTT_CACHE_EN" }
#define GEN9_GLOBAL \
{ GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \
{ GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" }
#define COMMON_GEN12BASE_GLOBAL \
{ GEN12_FAULT_TLB_DATA0, 0, 0, "GEN12_FAULT_TLB_DATA0" }, \
{ GEN12_FAULT_TLB_DATA1, 0, 0, "GEN12_FAULT_TLB_DATA1" }, \
{ GEN12_AUX_ERR_DBG, 0, 0, "AUX_ERR_DBG" }, \
{ GEN12_GAM_DONE, 0, 0, "GAM_DONE" }, \
{ GEN12_RING_FAULT_REG, 0, 0, "FAULT_REG" }
#define COMMON_BASE_ENGINE_INSTANCE \
{ RING_PSMI_CTL(0), 0, 0, "RC PSMI" }, \
{ RING_ESR(0), 0, 0, "ESR" }, \
{ RING_DMA_FADD(0), 0, 0, "RING_DMA_FADD_LDW" }, \
{ RING_DMA_FADD_UDW(0), 0, 0, "RING_DMA_FADD_UDW" }, \
{ RING_IPEIR(0), 0, 0, "IPEIR" }, \
{ RING_IPEHR(0), 0, 0, "IPEHR" }, \
{ RING_INSTPS(0), 0, 0, "INSTPS" }, \
{ RING_BBADDR(0), 0, 0, "RING_BBADDR_LOW32" }, \
{ RING_BBADDR_UDW(0), 0, 0, "RING_BBADDR_UP32" }, \
{ RING_BBSTATE(0), 0, 0, "BB_STATE" }, \
{ CCID(0), 0, 0, "CCID" }, \
{ RING_ACTHD(0), 0, 0, "ACTHD_LDW" }, \
{ RING_ACTHD_UDW(0), 0, 0, "ACTHD_UDW" }, \
{ RING_INSTPM(0), 0, 0, "INSTPM" }, \
{ RING_INSTDONE(0), 0, 0, "INSTDONE" }, \
{ RING_NOPID(0), 0, 0, "RING_NOPID" }, \
{ RING_START(0), 0, 0, "START" }, \
{ RING_HEAD(0), 0, 0, "HEAD" }, \
{ RING_TAIL(0), 0, 0, "TAIL" }, \
{ RING_CTL(0), 0, 0, "CTL" }, \
{ RING_MI_MODE(0), 0, 0, "MODE" }, \
{ RING_CONTEXT_CONTROL(0), 0, 0, "RING_CONTEXT_CONTROL" }, \
{ RING_HWS_PGA(0), 0, 0, "HWS" }, \
{ RING_MODE_GEN7(0), 0, 0, "GFX_MODE" }, \
{ GEN8_RING_PDP_LDW(0, 0), 0, 0, "PDP0_LDW" }, \
{ GEN8_RING_PDP_UDW(0, 0), 0, 0, "PDP0_UDW" }, \
{ GEN8_RING_PDP_LDW(0, 1), 0, 0, "PDP1_LDW" }, \
{ GEN8_RING_PDP_UDW(0, 1), 0, 0, "PDP1_UDW" }, \
{ GEN8_RING_PDP_LDW(0, 2), 0, 0, "PDP2_LDW" }, \
{ GEN8_RING_PDP_UDW(0, 2), 0, 0, "PDP2_UDW" }, \
{ GEN8_RING_PDP_LDW(0, 3), 0, 0, "PDP3_LDW" }, \
{ GEN8_RING_PDP_UDW(0, 3), 0, 0, "PDP3_UDW" }
#define COMMON_BASE_HAS_EU \
{ EIR, 0, 0, "EIR" }
#define COMMON_BASE_RENDER \
{ GEN7_SC_INSTDONE, 0, 0, "GEN7_SC_INSTDONE" }
#define COMMON_GEN12BASE_RENDER \
{ GEN12_SC_INSTDONE_EXTRA, 0, 0, "GEN12_SC_INSTDONE_EXTRA" }, \
{ GEN12_SC_INSTDONE_EXTRA2, 0, 0, "GEN12_SC_INSTDONE_EXTRA2" }
#define COMMON_GEN12BASE_VEC \
{ GEN12_SFC_DONE(0), 0, 0, "SFC_DONE[0]" }, \
{ GEN12_SFC_DONE(1), 0, 0, "SFC_DONE[1]" }, \
{ GEN12_SFC_DONE(2), 0, 0, "SFC_DONE[2]" }, \
{ GEN12_SFC_DONE(3), 0, 0, "SFC_DONE[3]" }
/* XE_LPD - Global */
static const struct __guc_mmio_reg_descr xe_lpd_global_regs[] = {
COMMON_BASE_GLOBAL,
COMMON_GEN9BASE_GLOBAL,
COMMON_GEN12BASE_GLOBAL,
};
/* XE_LPD - Render / Compute Per-Class */
static const struct __guc_mmio_reg_descr xe_lpd_rc_class_regs[] = {
COMMON_BASE_HAS_EU,
COMMON_BASE_RENDER,
COMMON_GEN12BASE_RENDER,
};
/* GEN9/XE_LPD - Render / Compute Per-Engine-Instance */
static const struct __guc_mmio_reg_descr xe_lpd_rc_inst_regs[] = {
COMMON_BASE_ENGINE_INSTANCE,
};
/* GEN9/XE_LPD - Media Decode/Encode Per-Engine-Instance */
static const struct __guc_mmio_reg_descr xe_lpd_vd_inst_regs[] = {
COMMON_BASE_ENGINE_INSTANCE,
};
/* XE_LPD - Video Enhancement Per-Class */
static const struct __guc_mmio_reg_descr xe_lpd_vec_class_regs[] = {
COMMON_GEN12BASE_VEC,
};
/* GEN9/XE_LPD - Video Enhancement Per-Engine-Instance */
static const struct __guc_mmio_reg_descr xe_lpd_vec_inst_regs[] = {
COMMON_BASE_ENGINE_INSTANCE,
};
/* GEN9/XE_LPD - Blitter Per-Engine-Instance */
static const struct __guc_mmio_reg_descr xe_lpd_blt_inst_regs[] = {
COMMON_BASE_ENGINE_INSTANCE,
};
/* XE_LPD - GSC Per-Engine-Instance */
static const struct __guc_mmio_reg_descr xe_lpd_gsc_inst_regs[] = {
COMMON_BASE_ENGINE_INSTANCE,
};
/* GEN9 - Global */
static const struct __guc_mmio_reg_descr default_global_regs[] = {
COMMON_BASE_GLOBAL,
COMMON_GEN9BASE_GLOBAL,
GEN9_GLOBAL,
};
static const struct __guc_mmio_reg_descr default_rc_class_regs[] = {
COMMON_BASE_HAS_EU,
COMMON_BASE_RENDER,
};
/*
* Empty lists:
* GEN9/XE_LPD - Blitter Per-Class
* GEN9/XE_LPD - Media Decode/Encode Per-Class
* GEN9 - VEC Class
*/
static const struct __guc_mmio_reg_descr empty_regs_list[] = {
};
#define TO_GCAP_DEF_OWNER(x) (GUC_CAPTURE_LIST_INDEX_##x)
#define TO_GCAP_DEF_TYPE(x) (GUC_CAPTURE_LIST_TYPE_##x)
#define MAKE_REGLIST(regslist, regsowner, regstype, class) \
{ \
regslist, \
ARRAY_SIZE(regslist), \
TO_GCAP_DEF_OWNER(regsowner), \
TO_GCAP_DEF_TYPE(regstype), \
class, \
NULL, \
}
/* List of lists */
static const struct __guc_mmio_reg_descr_group default_lists[] = {
MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0),
MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS),
MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS),
MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS),
MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS),
{}
};
static const struct __guc_mmio_reg_descr_group xe_lpd_lists[] = {
MAKE_REGLIST(xe_lpd_global_regs, PF, GLOBAL, 0),
MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_COMPUTE_CLASS),
MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_COMPUTE_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
MAKE_REGLIST(xe_lpd_vec_class_regs, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS),
MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS),
MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS),
MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS),
{}
};
static const struct __guc_mmio_reg_descr_group *
guc_capture_get_one_list(const struct __guc_mmio_reg_descr_group *reglists,
u32 owner, u32 type, u32 id)
{
int i;
if (!reglists)
return NULL;
for (i = 0; reglists[i].list; ++i) {
if (reglists[i].owner == owner && reglists[i].type == type &&
(reglists[i].engine == id || reglists[i].type == GUC_CAPTURE_LIST_TYPE_GLOBAL))
return ®lists[i];
}
return NULL;
}
static struct __guc_mmio_reg_descr_group *
guc_capture_get_one_ext_list(struct __guc_mmio_reg_descr_group *reglists,
u32 owner, u32 type, u32 id)
{
int i;
if (!reglists)
return NULL;
for (i = 0; reglists[i].extlist; ++i) {
if (reglists[i].owner == owner && reglists[i].type == type &&
(reglists[i].engine == id || reglists[i].type == GUC_CAPTURE_LIST_TYPE_GLOBAL))
return ®lists[i];
}
return NULL;
}
static void guc_capture_free_extlists(struct __guc_mmio_reg_descr_group *reglists)
{
int i = 0;
if (!reglists)
return;
while (reglists[i].extlist)
kfree(reglists[i++].extlist);
}
struct __ext_steer_reg {
const char *name;
i915_mcr_reg_t reg;
};
static const struct __ext_steer_reg xe_extregs[] = {
{"GEN8_SAMPLER_INSTDONE", GEN8_SAMPLER_INSTDONE},
{"GEN8_ROW_INSTDONE", GEN8_ROW_INSTDONE}
};
static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
const struct __ext_steer_reg *extlist,
int slice_id, int subslice_id)
{
ext->reg = _MMIO(i915_mmio_reg_offset(extlist->reg));
ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
ext->regname = extlist->name;
}
static int
__alloc_ext_regs(struct __guc_mmio_reg_descr_group *newlist,
const struct __guc_mmio_reg_descr_group *rootlist, int num_regs)
{
struct __guc_mmio_reg_descr *list;
list = kcalloc(num_regs, sizeof(struct __guc_mmio_reg_descr), GFP_KERNEL);
if (!list)
return -ENOMEM;
newlist->extlist = list;
newlist->num_regs = num_regs;
newlist->owner = rootlist->owner;
newlist->engine = rootlist->engine;
newlist->type = rootlist->type;
return 0;
}
static void
guc_capture_alloc_steered_lists_xe_lpd(struct intel_guc *guc,
const struct __guc_mmio_reg_descr_group *lists)
{
struct intel_gt *gt = guc_to_gt(guc);
int slice, subslice, iter, i, num_steer_regs, num_tot_regs = 0;
const struct __guc_mmio_reg_descr_group *list;
struct __guc_mmio_reg_descr_group *extlists;
struct __guc_mmio_reg_descr *extarray;
struct sseu_dev_info *sseu;
/* In XE_LPD we only have steered registers for the render-class */
list = guc_capture_get_one_list(lists, GUC_CAPTURE_LIST_INDEX_PF,
GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, GUC_RENDER_CLASS);
/* skip if extlists was previously allocated */
if (!list || guc->capture->extlists)
return;
num_steer_regs = ARRAY_SIZE(xe_extregs);
sseu = >->info.sseu;
for_each_ss_steering(iter, gt, slice, subslice)
num_tot_regs += num_steer_regs;
if (!num_tot_regs)
return;
/* allocate an extra for an end marker */
extlists = kcalloc(2, sizeof(struct __guc_mmio_reg_descr_group), GFP_KERNEL);
if (!extlists)
return;
if (__alloc_ext_regs(&extlists[0], list, num_tot_regs)) {
kfree(extlists);
return;
}
extarray = extlists[0].extlist;
for_each_ss_steering(iter, gt, slice, subslice) {
for (i = 0; i < num_steer_regs; ++i) {
__fill_ext_reg(extarray, &xe_extregs[i], slice, subslice);
++extarray;
}
}
guc->capture->extlists = extlists;
}
static const struct __ext_steer_reg xehpg_extregs[] = {
{"XEHPG_INSTDONE_GEOM_SVG", XEHPG_INSTDONE_GEOM_SVG}
};
static bool __has_xehpg_extregs(u32 ipver)
{
return (ipver >= IP_VER(12, 55));
}
static void
guc_capture_alloc_steered_lists_xe_hpg(struct intel_guc *guc,
const struct __guc_mmio_reg_descr_group *lists,
u32 ipver)
{
struct intel_gt *gt = guc_to_gt(guc);
struct sseu_dev_info *sseu;
int slice, subslice, i, iter, num_steer_regs, num_tot_regs = 0;
const struct __guc_mmio_reg_descr_group *list;
struct __guc_mmio_reg_descr_group *extlists;
struct __guc_mmio_reg_descr *extarray;
/* In XE_LP / HPG we only have render-class steering registers during error-capture */
list = guc_capture_get_one_list(lists, GUC_CAPTURE_LIST_INDEX_PF,
GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, GUC_RENDER_CLASS);
/* skip if extlists was previously allocated */
if (!list || guc->capture->extlists)
return;
num_steer_regs = ARRAY_SIZE(xe_extregs);
if (__has_xehpg_extregs(ipver))
num_steer_regs += ARRAY_SIZE(xehpg_extregs);
sseu = >->info.sseu;
for_each_ss_steering(iter, gt, slice, subslice)
num_tot_regs += num_steer_regs;
if (!num_tot_regs)
return;
/* allocate an extra for an end marker */
extlists = kcalloc(2, sizeof(struct __guc_mmio_reg_descr_group), GFP_KERNEL);
if (!extlists)
return;
if (__alloc_ext_regs(&extlists[0], list, num_tot_regs)) {
kfree(extlists);
return;
}
extarray = extlists[0].extlist;
for_each_ss_steering(iter, gt, slice, subslice) {
for (i = 0; i < ARRAY_SIZE(xe_extregs); ++i) {
__fill_ext_reg(extarray, &xe_extregs[i], slice, subslice);
++extarray;
}
if (__has_xehpg_extregs(ipver)) {
for (i = 0; i < ARRAY_SIZE(xehpg_extregs); ++i) {
__fill_ext_reg(extarray, &xehpg_extregs[i], slice, subslice);
++extarray;
}
}
}
guc_dbg(guc, "capture found %d ext-regs.\n", num_tot_regs);
guc->capture->extlists = extlists;
}
static const struct __guc_mmio_reg_descr_group *
guc_capture_get_device_reglist(struct intel_guc *guc)
{
struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
if (GRAPHICS_VER(i915) > 11) {
/*
* For certain engine classes, there are slice and subslice
* level registers requiring steering. We allocate and populate
* these at init time based on hw config add it as an extension
* list at the end of the pre-populated render list.
*/
if (IS_DG2(i915))
guc_capture_alloc_steered_lists_xe_hpg(guc, xe_lpd_lists, IP_VER(12, 55));
else if (IS_XEHPSDV(i915))
guc_capture_alloc_steered_lists_xe_hpg(guc, xe_lpd_lists, IP_VER(12, 50));
else
guc_capture_alloc_steered_lists_xe_lpd(guc, xe_lpd_lists);
return xe_lpd_lists;
}
/* if GuC submission is enabled on a non-POR platform, just use a common baseline */
return default_lists;
}
static const char *
__stringify_type(u32 type)
{
switch (type) {
case GUC_CAPTURE_LIST_TYPE_GLOBAL:
return "Global";
case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
return "Class";
case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
return "Instance";
default:
break;
}
return "unknown";
}
static const char *
__stringify_engclass(u32 class)
{
switch (class) {
case GUC_RENDER_CLASS:
return "Render";
case GUC_VIDEO_CLASS:
return "Video";
case GUC_VIDEOENHANCE_CLASS:
return "VideoEnhance";
case GUC_BLITTER_CLASS:
return "Blitter";
case GUC_COMPUTE_CLASS:
return "Compute";
case GUC_GSC_OTHER_CLASS:
return "GSC-Other";
default:
break;
}
return "unknown";
}
static int
guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
struct guc_mmio_reg *ptr, u16 num_entries)
{
u32 i = 0, j = 0;
const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists;
struct __guc_mmio_reg_descr_group *extlists = guc->capture->extlists;
const struct __guc_mmio_reg_descr_group *match;
struct __guc_mmio_reg_descr_group *matchext;
if (!reglists)
return -ENODEV;
match = guc_capture_get_one_list(reglists, owner, type, classid);
if (!match)
return -ENODATA;
for (i = 0; i < num_entries && i < match->num_regs; ++i) {
ptr[i].offset = match->list[i].reg.reg;
ptr[i].value = 0xDEADF00D;
ptr[i].flags = match->list[i].flags;
ptr[i].mask = match->list[i].mask;
}
matchext = guc_capture_get_one_ext_list(extlists, owner, type, classid);
if (matchext) {
for (i = match->num_regs, j = 0; i < num_entries &&
i < (match->num_regs + matchext->num_regs) &&
j < matchext->num_regs; ++i, ++j) {
ptr[i].offset = matchext->extlist[j].reg.reg;
ptr[i].value = 0xDEADF00D;
ptr[i].flags = matchext->extlist[j].flags;
ptr[i].mask = matchext->extlist[j].mask;
}
}
if (i < num_entries)
guc_dbg(guc, "Got short capture reglist init: %d out %d.\n", i, num_entries);
return 0;
}
static int
guc_cap_list_num_regs(struct intel_guc_state_capture *gc, u32 owner, u32 type, u32 classid)
{
const struct __guc_mmio_reg_descr_group *match;
struct __guc_mmio_reg_descr_group *matchext;
int num_regs;
match = guc_capture_get_one_list(gc->reglists, owner, type, classid);
if (!match)
return 0;
num_regs = match->num_regs;
matchext = guc_capture_get_one_ext_list(gc->extlists, owner, type, classid);
if (matchext)
num_regs += matchext->num_regs;
return num_regs;
}
static int
guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
size_t *size, bool is_purpose_est)
{
struct intel_guc_state_capture *gc = guc->capture;
struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid];
int num_regs;
if (!gc->reglists) {
guc_warn(guc, "No capture reglist for this device\n");
return -ENODEV;
}
if (cache->is_valid) {
*size = cache->size;
return cache->status;
}
if (!is_purpose_est && owner == GUC_CAPTURE_LIST_INDEX_PF &&
!guc_capture_get_one_list(gc->reglists, owner, type, classid)) {
if (type == GUC_CAPTURE_LIST_TYPE_GLOBAL)
guc_warn(guc, "Missing capture reglist: global!\n");
else
guc_warn(guc, "Missing capture reglist: %s(%u):%s(%u)!\n",
__stringify_type(type), type,
__stringify_engclass(classid), classid);
return -ENODATA;
}
num_regs = guc_cap_list_num_regs(gc, owner, type, classid);
/* intentional empty lists can exist depending on hw config */
if (!num_regs)
return -ENODATA;
if (size)
*size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
(num_regs * sizeof(struct guc_mmio_reg)));
return 0;
}
int
intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
size_t *size)
{
return guc_capture_getlistsize(guc, owner, type, classid, size, false);
}
static void guc_capture_create_prealloc_nodes(struct intel_guc *guc);
int
intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
void **outptr)
{
struct intel_guc_state_capture *gc = guc->capture;
struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid];
struct guc_debug_capture_list *listnode;
int ret, num_regs;
u8 *caplist, *tmp;
size_t size = 0;
if (!gc->reglists)
return -ENODEV;
if (cache->is_valid) {
*outptr = cache->ptr;
return cache->status;
}
/*
* ADS population of input registers is a good
* time to pre-allocate cachelist output nodes
*/
guc_capture_create_prealloc_nodes(guc);
ret = intel_guc_capture_getlistsize(guc, owner, type, classid, &size);
if (ret) {
cache->is_valid = true;
cache->ptr = NULL;
cache->size = 0;
cache->status = ret;
return ret;
}
caplist = kzalloc(size, GFP_KERNEL);
if (!caplist) {
guc_dbg(guc, "Failed to alloc cached register capture list");
return -ENOMEM;
}
/* populate capture list header */
tmp = caplist;
num_regs = guc_cap_list_num_regs(guc->capture, owner, type, classid);
listnode = (struct guc_debug_capture_list *)tmp;
listnode->header.info = FIELD_PREP(GUC_CAPTURELISTHDR_NUMDESCR, (u32)num_regs);
/* populate list of register descriptor */
tmp += sizeof(struct guc_debug_capture_list);
guc_capture_list_init(guc, owner, type, classid, (struct guc_mmio_reg *)tmp, num_regs);
/* cache this list */
cache->is_valid = true;
cache->ptr = caplist;
cache->size = size;
cache->status = 0;
*outptr = caplist;
return 0;
}
int
intel_guc_capture_getnullheader(struct intel_guc *guc,
void **outptr, size_t *size)
{
struct intel_guc_state_capture *gc = guc->capture;
int tmp = sizeof(u32) * 4;
void *null_header;
if (gc->ads_null_cache) {
*outptr = gc->ads_null_cache;
*size = tmp;
return 0;
}
null_header = kzalloc(tmp, GFP_KERNEL);
if (!null_header) {
guc_dbg(guc, "Failed to alloc cached register capture null list");
return -ENOMEM;
}
gc->ads_null_cache = null_header;
*outptr = null_header;
*size = tmp;
return 0;
}
static int
guc_capture_output_min_size_est(struct intel_guc *guc)
{
struct intel_gt *gt = guc_to_gt(guc);
struct intel_engine_cs *engine;
enum intel_engine_id id;
int worst_min_size = 0;
size_t tmp = 0;
if (!guc->capture)
return -ENODEV;
/*
* If every single engine-instance suffered a failure in quick succession but
* were all unrelated, then a burst of multiple error-capture events would dump
* registers for every one engine instance, one at a time. In this case, GuC
* would even dump the global-registers repeatedly.
*
* For each engine instance, there would be 1 x guc_state_capture_group_t output
* followed by 3 x guc_state_capture_t lists. The latter is how the register
* dumps are split across different register types (where the '3' are global vs class
* vs instance).
*/
for_each_engine(engine, gt, id) {
worst_min_size += sizeof(struct guc_state_capture_group_header_t) +
(3 * sizeof(struct guc_state_capture_header_t));
if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp, true))
worst_min_size += tmp;
if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
engine->class, &tmp, true)) {
worst_min_size += tmp;
}
if (!guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
engine->class, &tmp, true)) {
worst_min_size += tmp;
}
}
return worst_min_size;
}
/*
* Add on a 3x multiplier to allow for multiple back-to-back captures occurring
* before the i915 can read the data out and process it
*/
#define GUC_CAPTURE_OVERBUFFER_MULTIPLIER 3
static void check_guc_capture_size(struct intel_guc *guc)
{
int min_size = guc_capture_output_min_size_est(guc);
int spare_size = min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER;
u32 buffer_size = intel_guc_log_section_size_capture(&guc->log);
/*
* NOTE: min_size is much smaller than the capture region allocation (DG2: <80K vs 1MB)
* Additionally, its based on space needed to fit all engines getting reset at once
* within the same G2H handler task slot. This is very unlikely. However, if GuC really
* does run out of space for whatever reason, we will see an separate warning message
* when processing the G2H event capture-notification, search for:
* INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE.
*/
if (min_size < 0)
guc_warn(guc, "Failed to calculate error state capture buffer minimum size: %d!\n",
min_size);
else if (min_size > buffer_size)
guc_warn(guc, "Error state capture buffer maybe small: %d < %d\n",
buffer_size, min_size);
else if (spare_size > buffer_size)
guc_dbg(guc, "Error state capture buffer lacks spare size: %d < %d (min = %d)\n",
buffer_size, spare_size, min_size);
}
/*
* KMD Init time flows:
* --------------------
* --> alloc A: GuC input capture regs lists (registered to GuC via ADS).
* intel_guc_ads acquires the register lists by calling
* intel_guc_capture_list_size and intel_guc_capture_list_get 'n' times,
* where n = 1 for global-reg-list +
* num_engine_classes for class-reg-list +
* num_engine_classes for instance-reg-list
* (since all instances of the same engine-class type
* have an identical engine-instance register-list).
* ADS module also calls separately for PF vs VF.
*
* --> alloc B: GuC output capture buf (registered via guc_init_params(log_param))
* Size = #define CAPTURE_BUFFER_SIZE (warns if on too-small)
* Note2: 'x 3' to hold multiple capture groups
*
* GUC Runtime notify capture:
* --------------------------
* --> G2H STATE_CAPTURE_NOTIFICATION
* L--> intel_guc_capture_process
* L--> Loop through B (head..tail) and for each engine instance's
* err-state-captured register-list we find, we alloc 'C':
* --> alloc C: A capture-output-node structure that includes misc capture info along
* with 3 register list dumps (global, engine-class and engine-instance)
* This node is created from a pre-allocated list of blank nodes in
* guc->capture->cachelist and populated with the error-capture
* data from GuC and then it's added into guc->capture->outlist linked
* list. This list is used for matchup and printout by i915_gpu_coredump
* and err_print_gt, (when user invokes the error capture sysfs).
*
* GUC --> notify context reset:
* -----------------------------
* --> G2H CONTEXT RESET
* L--> guc_handle_context_reset --> i915_capture_error_state
* L--> i915_gpu_coredump(..IS_GUC_CAPTURE) --> gt_record_engines
* --> capture_engine(..IS_GUC_CAPTURE)
* L--> intel_guc_capture_get_matching_node is where
* detach C from internal linked list and add it into
* intel_engine_coredump struct (if the context and
* engine of the event notification matches a node
* in the link list).
*
* User Sysfs / Debugfs
* --------------------
* --> i915_gpu_coredump_copy_to_buffer->
* L--> err_print_to_sgl --> err_print_gt
* L--> error_print_guc_captures
* L--> intel_guc_capture_print_node prints the
* register lists values of the attached node
* on the error-engine-dump being reported.
* L--> i915_reset_error_state ... -->__i915_gpu_coredump_free
* L--> ... cleanup_gt -->
* L--> intel_guc_capture_free_node returns the
* capture-output-node back to the internal
* cachelist for reuse.
*
*/
static int guc_capture_buf_cnt(struct __guc_capture_bufstate *buf)
{
if (buf->wr >= buf->rd)
return (buf->wr - buf->rd);
return (buf->size - buf->rd) + buf->wr;
}
static int guc_capture_buf_cnt_to_end(struct __guc_capture_bufstate *buf)
{
if (buf->rd > buf->wr)
return (buf->size - buf->rd);
return (buf->wr - buf->rd);
}
/*
* GuC's error-capture output is a ring buffer populated in a byte-stream fashion:
*
* The GuC Log buffer region for error-capture is managed like a ring buffer.
* The GuC firmware dumps error capture logs into this ring in a byte-stream flow.
* Additionally, as per the current and foreseeable future, all packed error-
* capture output structures are dword aligned.
*
* That said, if the GuC firmware is in the midst of writing a structure that is larger
* than one dword but the tail end of the err-capture buffer-region has lesser space left,
* we would need to extract that structure one dword at a time straddled across the end,
* onto the start of the ring.
*
* Below function, guc_capture_log_remove_dw is a helper for that. All callers of this
* function would typically do a straight-up memcpy from the ring contents and will only
* call this helper if their structure-extraction is straddling across the end of the
* ring. GuC firmware does not add any padding. The reason for the no-padding is to ease
* scalability for future expansion of output data types without requiring a redesign
* of the flow controls.
*/
static int
guc_capture_log_remove_dw(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
u32 *dw)
{
int tries = 2;
int avail = 0;
u32 *src_data;
if (!guc_capture_buf_cnt(buf))
return 0;
while (tries--) {
avail = guc_capture_buf_cnt_to_end(buf);
if (avail >= sizeof(u32)) {
src_data = (u32 *)(buf->data + buf->rd);
*dw = *src_data;
buf->rd += 4;
return 4;
}
if (avail)
guc_dbg(guc, "Register capture log not dword aligned, skipping.\n");
buf->rd = 0;
}
return 0;
}
static bool
guc_capture_data_extracted(struct __guc_capture_bufstate *b,
int size, void *dest)
{
if (guc_capture_buf_cnt_to_end(b) >= size) {
memcpy(dest, (b->data + b->rd), size);
b->rd += size;
return true;
}
return false;
}
static int
guc_capture_log_get_group_hdr(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
struct guc_state_capture_group_header_t *ghdr)
{
int read = 0;
int fullsize = sizeof(struct guc_state_capture_group_header_t);
if (fullsize > guc_capture_buf_cnt(buf))
return -1;
if (guc_capture_data_extracted(buf, fullsize, (void *)ghdr))
return 0;
read += guc_capture_log_remove_dw(guc, buf, &ghdr->owner);
read += guc_capture_log_remove_dw(guc, buf, &ghdr->info);
if (read != fullsize)
return -1;
return 0;
}
static int
guc_capture_log_get_data_hdr(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
struct guc_state_capture_header_t *hdr)
{
int read = 0;
int fullsize = sizeof(struct guc_state_capture_header_t);
if (fullsize > guc_capture_buf_cnt(buf))
return -1;
if (guc_capture_data_extracted(buf, fullsize, (void *)hdr))
return 0;
read += guc_capture_log_remove_dw(guc, buf, &hdr->owner);
read += guc_capture_log_remove_dw(guc, buf, &hdr->info);
read += guc_capture_log_remove_dw(guc, buf, &hdr->lrca);
read += guc_capture_log_remove_dw(guc, buf, &hdr->guc_id);
read += guc_capture_log_remove_dw(guc, buf, &hdr->num_mmios);
if (read != fullsize)
return -1;
return 0;
}
static int
guc_capture_log_get_register(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
struct guc_mmio_reg *reg)
{
int read = 0;
int fullsize = sizeof(struct guc_mmio_reg);
if (fullsize > guc_capture_buf_cnt(buf))
return -1;
if (guc_capture_data_extracted(buf, fullsize, (void *)reg))
return 0;
read += guc_capture_log_remove_dw(guc, buf, ®->offset);
read += guc_capture_log_remove_dw(guc, buf, ®->value);
read += guc_capture_log_remove_dw(guc, buf, ®->flags);
read += guc_capture_log_remove_dw(guc, buf, ®->mask);
if (read != fullsize)
return -1;
return 0;
}
static void
guc_capture_delete_one_node(struct intel_guc *guc, struct __guc_capture_parsed_output *node)
{
int i;
for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i)
kfree(node->reginfo[i].regs);
list_del(&node->link);
kfree(node);
}
static void
guc_capture_delete_prealloc_nodes(struct intel_guc *guc)
{
struct __guc_capture_parsed_output *n, *ntmp;
/*
* NOTE: At the end of driver operation, we must assume that we
* have prealloc nodes in both the cachelist as well as outlist
* if unclaimed error capture events occurred prior to shutdown.
*/
list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link)
guc_capture_delete_one_node(guc, n);
list_for_each_entry_safe(n, ntmp, &guc->capture->cachelist, link)
guc_capture_delete_one_node(guc, n);
}
static void
guc_capture_add_node_to_list(struct __guc_capture_parsed_output *node,
struct list_head *list)
{
list_add_tail(&node->link, list);
}
static void
guc_capture_add_node_to_outlist(struct intel_guc_state_capture *gc,
struct __guc_capture_parsed_output *node)
{
guc_capture_add_node_to_list(node, &gc->outlist);
}
static void
guc_capture_add_node_to_cachelist(struct intel_guc_state_capture *gc,
struct __guc_capture_parsed_output *node)
{
guc_capture_add_node_to_list(node, &gc->cachelist);
}
static void
guc_capture_init_node(struct intel_guc *guc, struct __guc_capture_parsed_output *node)
{
struct guc_mmio_reg *tmp[GUC_CAPTURE_LIST_TYPE_MAX];
int i;
for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
tmp[i] = node->reginfo[i].regs;
memset(tmp[i], 0, sizeof(struct guc_mmio_reg) *
guc->capture->max_mmio_per_node);
}
memset(node, 0, sizeof(*node));
for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i)
node->reginfo[i].regs = tmp[i];
INIT_LIST_HEAD(&node->link);
}
static struct __guc_capture_parsed_output *
guc_capture_get_prealloc_node(struct intel_guc *guc)
{
struct __guc_capture_parsed_output *found = NULL;
if (!list_empty(&guc->capture->cachelist)) {
struct __guc_capture_parsed_output *n, *ntmp;
/* get first avail node from the cache list */
list_for_each_entry_safe(n, ntmp, &guc->capture->cachelist, link) {
found = n;
list_del(&n->link);
break;
}
} else {
struct __guc_capture_parsed_output *n, *ntmp;
/* traverse down and steal back the oldest node already allocated */
list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link) {
found = n;
}
if (found)
list_del(&found->link);
}
if (found)
guc_capture_init_node(guc, found);
return found;
}
static struct __guc_capture_parsed_output *
guc_capture_alloc_one_node(struct intel_guc *guc)
{
struct __guc_capture_parsed_output *new;
int i;
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return NULL;
for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
new->reginfo[i].regs = kcalloc(guc->capture->max_mmio_per_node,
sizeof(struct guc_mmio_reg), GFP_KERNEL);
if (!new->reginfo[i].regs) {
while (i)
kfree(new->reginfo[--i].regs);
kfree(new);
return NULL;
}
}
guc_capture_init_node(guc, new);
return new;
}
static struct __guc_capture_parsed_output *
guc_capture_clone_node(struct intel_guc *guc, struct __guc_capture_parsed_output *original,
u32 keep_reglist_mask)
{
struct __guc_capture_parsed_output *new;
int i;
new = guc_capture_get_prealloc_node(guc);
if (!new)
return NULL;
if (!original)
return new;
new->is_partial = original->is_partial;
/* copy reg-lists that we want to clone */
for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
if (keep_reglist_mask & BIT(i)) {
GEM_BUG_ON(original->reginfo[i].num_regs >
guc->capture->max_mmio_per_node);
memcpy(new->reginfo[i].regs, original->reginfo[i].regs,
original->reginfo[i].num_regs * sizeof(struct guc_mmio_reg));
new->reginfo[i].num_regs = original->reginfo[i].num_regs;
new->reginfo[i].vfid = original->reginfo[i].vfid;
if (i == GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS) {
new->eng_class = original->eng_class;
} else if (i == GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE) {
new->eng_inst = original->eng_inst;
new->guc_id = original->guc_id;
new->lrca = original->lrca;
}
}
}
return new;
}
static void
__guc_capture_create_prealloc_nodes(struct intel_guc *guc)
{
struct __guc_capture_parsed_output *node = NULL;
int i;
for (i = 0; i < PREALLOC_NODES_MAX_COUNT; ++i) {
node = guc_capture_alloc_one_node(guc);
if (!node) {
guc_warn(guc, "Register capture pre-alloc-cache failure\n");
/* dont free the priors, use what we got and cleanup at shutdown */
return;
}
guc_capture_add_node_to_cachelist(guc->capture, node);
}
}
static int
guc_get_max_reglist_count(struct intel_guc *guc)
{
int i, j, k, tmp, maxregcount = 0;
for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; ++i) {
for (j = 0; j < GUC_CAPTURE_LIST_TYPE_MAX; ++j) {
for (k = 0; k < GUC_MAX_ENGINE_CLASSES; ++k) {
if (j == GUC_CAPTURE_LIST_TYPE_GLOBAL && k > 0)
continue;
tmp = guc_cap_list_num_regs(guc->capture, i, j, k);
if (tmp > maxregcount)
maxregcount = tmp;
}
}
}
if (!maxregcount)
maxregcount = PREALLOC_NODES_DEFAULT_NUMREGS;
return maxregcount;
}
static void
guc_capture_create_prealloc_nodes(struct intel_guc *guc)
{
/* skip if we've already done the pre-alloc */
if (guc->capture->max_mmio_per_node)
return;
guc->capture->max_mmio_per_node = guc_get_max_reglist_count(guc);
__guc_capture_create_prealloc_nodes(guc);
}
static int
guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstate *buf)
{
struct guc_state_capture_group_header_t ghdr = {0};
struct guc_state_capture_header_t hdr = {0};
struct __guc_capture_parsed_output *node = NULL;
struct guc_mmio_reg *regs = NULL;
int i, numlists, numregs, ret = 0;
enum guc_capture_type datatype;
struct guc_mmio_reg tmp;
bool is_partial = false;
i = guc_capture_buf_cnt(buf);
if (!i)
return -ENODATA;
if (i % sizeof(u32)) {
guc_warn(guc, "Got mis-aligned register capture entries\n");
ret = -EIO;
goto bailout;
}
/* first get the capture group header */
if (guc_capture_log_get_group_hdr(guc, buf, &ghdr)) {
ret = -EIO;
goto bailout;
}
/*
* we would typically expect a layout as below where n would be expected to be
* anywhere between 3 to n where n > 3 if we are seeing multiple dependent engine
* instances being reset together.
* ____________________________________________
* | Capture Group |
* | ________________________________________ |
* | | Capture Group Header: | |
* | | - num_captures = 5 | |
* | |______________________________________| |
* | ________________________________________ |
* | | Capture1: | |
* | | Hdr: GLOBAL, numregs=a | |
* | | ____________________________________ | |
* | | | Reglist | | |
* | | | - reg1, reg2, ... rega | | |
* | | |__________________________________| | |
* | |______________________________________| |
* | ________________________________________ |
* | | Capture2: | |
* | | Hdr: CLASS=RENDER/COMPUTE, numregs=b| |
* | | ____________________________________ | |
* | | | Reglist | | |
* | | | - reg1, reg2, ... regb | | |
* | | |__________________________________| | |
* | |______________________________________| |
* | ________________________________________ |
* | | Capture3: | |
* | | Hdr: INSTANCE=RCS, numregs=c | |
* | | ____________________________________ | |
* | | | Reglist | | |
* | | | - reg1, reg2, ... regc | | |
* | | |__________________________________| | |
* | |______________________________________| |
* | ________________________________________ |
* | | Capture4: | |
* | | Hdr: CLASS=RENDER/COMPUTE, numregs=d| |
* | | ____________________________________ | |
* | | | Reglist | | |
* | | | - reg1, reg2, ... regd | | |
* | | |__________________________________| | |
* | |______________________________________| |
* | ________________________________________ |
* | | Capture5: | |
* | | Hdr: INSTANCE=CCS0, numregs=e | |
* | | ____________________________________ | |
* | | | Reglist | | |
* | | | - reg1, reg2, ... rege | | |
* | | |__________________________________| | |
* | |______________________________________| |
* |__________________________________________|
*/
is_partial = FIELD_GET(CAP_GRP_HDR_CAPTURE_TYPE, ghdr.info);
numlists = FIELD_GET(CAP_GRP_HDR_NUM_CAPTURES, ghdr.info);
while (numlists--) {
if (guc_capture_log_get_data_hdr(guc, buf, &hdr)) {
ret = -EIO;
break;
}
datatype = FIELD_GET(CAP_HDR_CAPTURE_TYPE, hdr.info);
if (datatype > GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE) {
/* unknown capture type - skip over to next capture set */
numregs = FIELD_GET(CAP_HDR_NUM_MMIOS, hdr.num_mmios);
while (numregs--) {
if (guc_capture_log_get_register(guc, buf, &tmp)) {
ret = -EIO;
break;
}
}
continue;
} else if (node) {
/*
* Based on the current capture type and what we have so far,
* decide if we should add the current node into the internal
* linked list for match-up when i915_gpu_coredump calls later
* (and alloc a blank node for the next set of reglists)
* or continue with the same node or clone the current node
* but only retain the global or class registers (such as the
* case of dependent engine resets).
*/
if (datatype == GUC_CAPTURE_LIST_TYPE_GLOBAL) {
guc_capture_add_node_to_outlist(guc->capture, node);
node = NULL;
} else if (datatype == GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS &&
node->reginfo[GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS].num_regs) {
/* Add to list, clone node and duplicate global list */
guc_capture_add_node_to_outlist(guc->capture, node);
node = guc_capture_clone_node(guc, node,
GCAP_PARSED_REGLIST_INDEX_GLOBAL);
} else if (datatype == GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE &&
node->reginfo[GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE].num_regs) {
/* Add to list, clone node and duplicate global + class lists */
guc_capture_add_node_to_outlist(guc->capture, node);
node = guc_capture_clone_node(guc, node,
(GCAP_PARSED_REGLIST_INDEX_GLOBAL |
GCAP_PARSED_REGLIST_INDEX_ENGCLASS));
}
}
if (!node) {
node = guc_capture_get_prealloc_node(guc);
if (!node) {
ret = -ENOMEM;
break;
}
if (datatype != GUC_CAPTURE_LIST_TYPE_GLOBAL)
guc_dbg(guc, "Register capture missing global dump: %08x!\n",
datatype);
}
node->is_partial = is_partial;
node->reginfo[datatype].vfid = FIELD_GET(CAP_HDR_CAPTURE_VFID, hdr.owner);
switch (datatype) {
case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
node->eng_class = FIELD_GET(CAP_HDR_ENGINE_CLASS, hdr.info);
node->eng_inst = FIELD_GET(CAP_HDR_ENGINE_INSTANCE, hdr.info);
node->lrca = hdr.lrca;
node->guc_id = hdr.guc_id;
break;
case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
node->eng_class = FIELD_GET(CAP_HDR_ENGINE_CLASS, hdr.info);
break;
default:
break;
}
numregs = FIELD_GET(CAP_HDR_NUM_MMIOS, hdr.num_mmios);
if (numregs > guc->capture->max_mmio_per_node) {
guc_dbg(guc, "Register capture list extraction clipped by prealloc!\n");
numregs = guc->capture->max_mmio_per_node;
}
node->reginfo[datatype].num_regs = numregs;
regs = node->reginfo[datatype].regs;
i = 0;
while (numregs--) {
if (guc_capture_log_get_register(guc, buf, ®s[i++])) {
ret = -EIO;
break;
}
}
}
bailout:
if (node) {
/* If we have data, add to linked list for match-up when i915_gpu_coredump calls */
for (i = GUC_CAPTURE_LIST_TYPE_GLOBAL; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
if (node->reginfo[i].regs) {
guc_capture_add_node_to_outlist(guc->capture, node);
node = NULL;
break;
}
}
if (node) /* else return it back to cache list */
guc_capture_add_node_to_cachelist(guc->capture, node);
}
return ret;
}
static int __guc_capture_flushlog_complete(struct intel_guc *guc)
{
u32 action[] = {
INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE,
GUC_CAPTURE_LOG_BUFFER
};
return intel_guc_send_nb(guc, action, ARRAY_SIZE(action), 0);
}
static void __guc_capture_process_output(struct intel_guc *guc)
{
unsigned int buffer_size, read_offset, write_offset, full_count;
struct intel_uc *uc = container_of(guc, typeof(*uc), guc);
struct guc_log_buffer_state log_buf_state_local;
struct guc_log_buffer_state *log_buf_state;
struct __guc_capture_bufstate buf;
void *src_data = NULL;
bool new_overflow;
int ret;
log_buf_state = guc->log.buf_addr +
(sizeof(struct guc_log_buffer_state) * GUC_CAPTURE_LOG_BUFFER);
src_data = guc->log.buf_addr +
intel_guc_get_log_buffer_offset(&guc->log, GUC_CAPTURE_LOG_BUFFER);
/*
* Make a copy of the state structure, inside GuC log buffer
* (which is uncached mapped), on the stack to avoid reading
* from it multiple times.
*/
memcpy(&log_buf_state_local, log_buf_state, sizeof(struct guc_log_buffer_state));
buffer_size = intel_guc_get_log_buffer_size(&guc->log, GUC_CAPTURE_LOG_BUFFER);
read_offset = log_buf_state_local.read_ptr;
write_offset = log_buf_state_local.sampled_write_ptr;
full_count = log_buf_state_local.buffer_full_cnt;
/* Bookkeeping stuff */
guc->log.stats[GUC_CAPTURE_LOG_BUFFER].flush += log_buf_state_local.flush_to_file;
new_overflow = intel_guc_check_log_buf_overflow(&guc->log, GUC_CAPTURE_LOG_BUFFER,
full_count);
/* Now copy the actual logs. */
if (unlikely(new_overflow)) {
/* copy the whole buffer in case of overflow */
read_offset = 0;
write_offset = buffer_size;
} else if (unlikely((read_offset > buffer_size) ||
(write_offset > buffer_size))) {
guc_err(guc, "Register capture buffer in invalid state: read = 0x%X, size = 0x%X!\n",
read_offset, buffer_size);
/* copy whole buffer as offsets are unreliable */
read_offset = 0;
write_offset = buffer_size;
}
buf.size = buffer_size;
buf.rd = read_offset;
buf.wr = write_offset;
buf.data = src_data;
if (!uc->reset_in_progress) {
do {
ret = guc_capture_extract_reglists(guc, &buf);
} while (ret >= 0);
}
/* Update the state of log buffer err-cap state */
log_buf_state->read_ptr = write_offset;
log_buf_state->flush_to_file = 0;
__guc_capture_flushlog_complete(guc);
}
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
static const char *
guc_capture_reg_to_str(const struct intel_guc *guc, u32 owner, u32 type,
u32 class, u32 id, u32 offset, u32 *is_ext)
{
const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists;
struct __guc_mmio_reg_descr_group *extlists = guc->capture->extlists;
const struct __guc_mmio_reg_descr_group *match;
struct __guc_mmio_reg_descr_group *matchext;
int j;
*is_ext = 0;
if (!reglists)
return NULL;
match = guc_capture_get_one_list(reglists, owner, type, id);
if (!match)
return NULL;
for (j = 0; j < match->num_regs; ++j) {
if (offset == match->list[j].reg.reg)
return match->list[j].regname;
}
if (extlists) {
matchext = guc_capture_get_one_ext_list(extlists, owner, type, id);
if (!matchext)
return NULL;
for (j = 0; j < matchext->num_regs; ++j) {
if (offset == matchext->extlist[j].reg.reg) {
*is_ext = 1;
return matchext->extlist[j].regname;
}
}
}
return NULL;
}
#define GCAP_PRINT_INTEL_ENG_INFO(ebuf, eng) \
do { \
i915_error_printf(ebuf, " i915-Eng-Name: %s command stream\n", \
(eng)->name); \
i915_error_printf(ebuf, " i915-Eng-Inst-Class: 0x%02x\n", (eng)->class); \
i915_error_printf(ebuf, " i915-Eng-Inst-Id: 0x%02x\n", (eng)->instance); \
i915_error_printf(ebuf, " i915-Eng-LogicalMask: 0x%08x\n", \
(eng)->logical_mask); \
} while (0)
#define GCAP_PRINT_GUC_INST_INFO(ebuf, node) \
do { \
i915_error_printf(ebuf, " GuC-Engine-Inst-Id: 0x%08x\n", \
(node)->eng_inst); \
i915_error_printf(ebuf, " GuC-Context-Id: 0x%08x\n", (node)->guc_id); \
i915_error_printf(ebuf, " LRCA: 0x%08x\n", (node)->lrca); \
} while (0)
int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf,
const struct intel_engine_coredump *ee)
{
const char *grptype[GUC_STATE_CAPTURE_GROUP_TYPE_MAX] = {
"full-capture",
"partial-capture"
};
const char *datatype[GUC_CAPTURE_LIST_TYPE_MAX] = {
"Global",
"Engine-Class",
"Engine-Instance"
};
struct intel_guc_state_capture *cap;
struct __guc_capture_parsed_output *node;
struct intel_engine_cs *eng;
struct guc_mmio_reg *regs;
struct intel_guc *guc;
const char *str;
int numregs, i, j;
u32 is_ext;
if (!ebuf || !ee)
return -EINVAL;
cap = ee->guc_capture;
if (!cap || !ee->engine)
return -ENODEV;
guc = &ee->engine->gt->uc.guc;
i915_error_printf(ebuf, "global --- GuC Error Capture on %s command stream:\n",
ee->engine->name);
node = ee->guc_capture_node;
if (!node) {
i915_error_printf(ebuf, " No matching ee-node\n");
return 0;
}
i915_error_printf(ebuf, "Coverage: %s\n", grptype[node->is_partial]);
for (i = GUC_CAPTURE_LIST_TYPE_GLOBAL; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
i915_error_printf(ebuf, " RegListType: %s\n",
datatype[i % GUC_CAPTURE_LIST_TYPE_MAX]);
i915_error_printf(ebuf, " Owner-Id: %d\n", node->reginfo[i].vfid);
switch (i) {
case GUC_CAPTURE_LIST_TYPE_GLOBAL:
default:
break;
case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
i915_error_printf(ebuf, " GuC-Eng-Class: %d\n", node->eng_class);
i915_error_printf(ebuf, " i915-Eng-Class: %d\n",
guc_class_to_engine_class(node->eng_class));
break;
case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
eng = intel_guc_lookup_engine(guc, node->eng_class, node->eng_inst);
if (eng)
GCAP_PRINT_INTEL_ENG_INFO(ebuf, eng);
else
i915_error_printf(ebuf, " i915-Eng-Lookup Fail!\n");
GCAP_PRINT_GUC_INST_INFO(ebuf, node);
break;
}
numregs = node->reginfo[i].num_regs;
i915_error_printf(ebuf, " NumRegs: %d\n", numregs);
j = 0;
while (numregs--) {
regs = node->reginfo[i].regs;
str = guc_capture_reg_to_str(guc, GUC_CAPTURE_LIST_INDEX_PF, i,
node->eng_class, 0, regs[j].offset, &is_ext);
if (!str)
i915_error_printf(ebuf, " REG-0x%08x", regs[j].offset);
else
i915_error_printf(ebuf, " %s", str);
if (is_ext)
i915_error_printf(ebuf, "[%ld][%ld]",
FIELD_GET(GUC_REGSET_STEERING_GROUP, regs[j].flags),
FIELD_GET(GUC_REGSET_STEERING_INSTANCE, regs[j].flags));
i915_error_printf(ebuf, ": 0x%08x\n", regs[j].value);
++j;
}
}
return 0;
}
#endif //CONFIG_DRM_I915_CAPTURE_ERROR
static void guc_capture_find_ecode(struct intel_engine_coredump *ee)
{
struct gcap_reg_list_info *reginfo;
struct guc_mmio_reg *regs;
i915_reg_t reg_ipehr = RING_IPEHR(0);
i915_reg_t reg_instdone = RING_INSTDONE(0);
int i;
if (!ee->guc_capture_node)
return;
reginfo = ee->guc_capture_node->reginfo + GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE;
regs = reginfo->regs;
for (i = 0; i < reginfo->num_regs; i++) {
if (regs[i].offset == reg_ipehr.reg)
ee->ipehr = regs[i].value;
else if (regs[i].offset == reg_instdone.reg)
ee->instdone.instdone = regs[i].value;
}
}
void intel_guc_capture_free_node(struct intel_engine_coredump *ee)
{
if (!ee || !ee->guc_capture_node)
return;
guc_capture_add_node_to_cachelist(ee->guc_capture, ee->guc_capture_node);
ee->guc_capture = NULL;
ee->guc_capture_node = NULL;
}
void intel_guc_capture_get_matching_node(struct intel_gt *gt,
struct intel_engine_coredump *ee,
struct intel_context *ce)
{
struct __guc_capture_parsed_output *n, *ntmp;
struct intel_guc *guc;
if (!gt || !ee || !ce)
return;
guc = >->uc.guc;
if (!guc->capture)
return;
GEM_BUG_ON(ee->guc_capture_node);
/*
* Look for a matching GuC reported error capture node from
* the internal output link-list based on lrca, guc-id and engine
* identification.
*/
list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link) {
if (n->eng_inst == GUC_ID_TO_ENGINE_INSTANCE(ee->engine->guc_id) &&
n->eng_class == GUC_ID_TO_ENGINE_CLASS(ee->engine->guc_id) &&
n->guc_id == ce->guc_id.id &&
(n->lrca & CTX_GTT_ADDRESS_MASK) == (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) {
list_del(&n->link);
ee->guc_capture_node = n;
ee->guc_capture = guc->capture;
guc_capture_find_ecode(ee);
return;
}
}
guc_warn(guc, "No register capture node found for 0x%04X / 0x%08X\n",
ce->guc_id.id, ce->lrc.lrca);
}
void intel_guc_capture_process(struct intel_guc *guc)
{
if (guc->capture)
__guc_capture_process_output(guc);
}
static void
guc_capture_free_ads_cache(struct intel_guc_state_capture *gc)
{
int i, j, k;
struct __guc_capture_ads_cache *cache;
for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; ++i) {
for (j = 0; j < GUC_CAPTURE_LIST_TYPE_MAX; ++j) {
for (k = 0; k < GUC_MAX_ENGINE_CLASSES; ++k) {
cache = &gc->ads_cache[i][j][k];
if (cache->is_valid)
kfree(cache->ptr);
}
}
}
kfree(gc->ads_null_cache);
}
void intel_guc_capture_destroy(struct intel_guc *guc)
{
if (!guc->capture)
return;
guc_capture_free_ads_cache(guc->capture);
guc_capture_delete_prealloc_nodes(guc);
guc_capture_free_extlists(guc->capture->extlists);
kfree(guc->capture->extlists);
kfree(guc->capture);
guc->capture = NULL;
}
int intel_guc_capture_init(struct intel_guc *guc)
{
guc->capture = kzalloc(sizeof(*guc->capture), GFP_KERNEL);
if (!guc->capture)
return -ENOMEM;
guc->capture->reglists = guc_capture_get_device_reglist(guc);
INIT_LIST_HEAD(&guc->capture->outlist);
INIT_LIST_HEAD(&guc->capture->cachelist);
check_guc_capture_size(guc);
return 0;
}
|