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
|
/*
* Copyright 2016 Advanced Micro Devices, Inc.
*
* 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 <linux/firmware.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <drm/amdgpu_drm.h>
#include "amdgpu.h"
#include "amdgpu_atombios.h"
#include "amdgpu_ih.h"
#include "amdgpu_uvd.h"
#include "amdgpu_vce.h"
#include "amdgpu_ucode.h"
#include "amdgpu_psp.h"
#include "atom.h"
#include "amd_pcie.h"
#include "uvd/uvd_7_0_offset.h"
#include "gc/gc_9_0_offset.h"
#include "gc/gc_9_0_sh_mask.h"
#include "sdma0/sdma0_4_0_offset.h"
#include "sdma1/sdma1_4_0_offset.h"
#include "nbio/nbio_7_0_default.h"
#include "nbio/nbio_7_0_offset.h"
#include "nbio/nbio_7_0_sh_mask.h"
#include "nbio/nbio_7_0_smn.h"
#include "mp/mp_9_0_offset.h"
#include "soc15.h"
#include "soc15_common.h"
#include "gfx_v9_0.h"
#include "gmc_v9_0.h"
#include "gfxhub_v1_0.h"
#include "mmhub_v1_0.h"
#include "df_v1_7.h"
#include "df_v3_6.h"
#include "nbio_v6_1.h"
#include "nbio_v7_0.h"
#include "nbio_v7_4.h"
#include "hdp_v4_0.h"
#include "vega10_ih.h"
#include "vega20_ih.h"
#include "navi10_ih.h"
#include "sdma_v4_0.h"
#include "uvd_v7_0.h"
#include "vce_v4_0.h"
#include "vcn_v1_0.h"
#include "vcn_v2_0.h"
#include "jpeg_v2_0.h"
#include "vcn_v2_5.h"
#include "jpeg_v2_5.h"
#include "smuio_v9_0.h"
#include "smuio_v11_0.h"
#include "smuio_v13_0.h"
#include "amdgpu_vkms.h"
#include "mxgpu_ai.h"
#include "amdgpu_ras.h"
#include "amdgpu_xgmi.h"
#include <uapi/linux/kfd_ioctl.h>
#define mmMP0_MISC_CGTT_CTRL0 0x01b9
#define mmMP0_MISC_CGTT_CTRL0_BASE_IDX 0
#define mmMP0_MISC_LIGHT_SLEEP_CTRL 0x01ba
#define mmMP0_MISC_LIGHT_SLEEP_CTRL_BASE_IDX 0
static const struct amd_ip_funcs soc15_common_ip_funcs;
/* Vega, Raven, Arcturus */
static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
{
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_encode =
{
.codec_count = ARRAY_SIZE(vega_video_codecs_encode_array),
.codec_array = vega_video_codecs_encode_array,
};
/* Vega */
static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
{
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_decode =
{
.codec_count = ARRAY_SIZE(vega_video_codecs_decode_array),
.codec_array = vega_video_codecs_decode_array,
};
/* Raven */
static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
{
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs rv_video_codecs_decode =
{
.codec_count = ARRAY_SIZE(rv_video_codecs_decode_array),
.codec_array = rv_video_codecs_decode_array,
};
/* Renoir, Arcturus */
static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
{
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs rn_video_codecs_decode =
{
.codec_count = ARRAY_SIZE(rn_video_codecs_decode_array),
.codec_array = rn_video_codecs_decode_array,
};
static const struct amdgpu_video_codec_info vcn_4_0_3_video_codecs_decode_array[] = {
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs vcn_4_0_3_video_codecs_decode = {
.codec_count = ARRAY_SIZE(vcn_4_0_3_video_codecs_decode_array),
.codec_array = vcn_4_0_3_video_codecs_decode_array,
};
static const struct amdgpu_video_codecs vcn_4_0_3_video_codecs_encode = {
.codec_count = 0,
.codec_array = NULL,
};
static int soc15_query_video_codecs(struct amdgpu_device *adev, bool encode,
const struct amdgpu_video_codecs **codecs)
{
if (amdgpu_ip_version(adev, VCE_HWIP, 0)) {
switch (amdgpu_ip_version(adev, VCE_HWIP, 0)) {
case IP_VERSION(4, 0, 0):
case IP_VERSION(4, 1, 0):
if (encode)
*codecs = &vega_video_codecs_encode;
else
*codecs = &vega_video_codecs_decode;
return 0;
default:
return -EINVAL;
}
} else {
switch (amdgpu_ip_version(adev, UVD_HWIP, 0)) {
case IP_VERSION(1, 0, 0):
case IP_VERSION(1, 0, 1):
if (encode)
*codecs = &vega_video_codecs_encode;
else
*codecs = &rv_video_codecs_decode;
return 0;
case IP_VERSION(2, 5, 0):
case IP_VERSION(2, 6, 0):
case IP_VERSION(2, 2, 0):
if (encode)
*codecs = &vega_video_codecs_encode;
else
*codecs = &rn_video_codecs_decode;
return 0;
case IP_VERSION(4, 0, 3):
if (encode)
*codecs = &vcn_4_0_3_video_codecs_encode;
else
*codecs = &vcn_4_0_3_video_codecs_decode;
return 0;
default:
return -EINVAL;
}
}
}
static u32 soc15_uvd_ctx_rreg(struct amdgpu_device *adev, u32 reg)
{
unsigned long flags, address, data;
u32 r;
address = SOC15_REG_OFFSET(UVD, 0, mmUVD_CTX_INDEX);
data = SOC15_REG_OFFSET(UVD, 0, mmUVD_CTX_DATA);
spin_lock_irqsave(&adev->uvd_ctx_idx_lock, flags);
WREG32(address, ((reg) & 0x1ff));
r = RREG32(data);
spin_unlock_irqrestore(&adev->uvd_ctx_idx_lock, flags);
return r;
}
static void soc15_uvd_ctx_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
{
unsigned long flags, address, data;
address = SOC15_REG_OFFSET(UVD, 0, mmUVD_CTX_INDEX);
data = SOC15_REG_OFFSET(UVD, 0, mmUVD_CTX_DATA);
spin_lock_irqsave(&adev->uvd_ctx_idx_lock, flags);
WREG32(address, ((reg) & 0x1ff));
WREG32(data, (v));
spin_unlock_irqrestore(&adev->uvd_ctx_idx_lock, flags);
}
static u32 soc15_didt_rreg(struct amdgpu_device *adev, u32 reg)
{
unsigned long flags, address, data;
u32 r;
address = SOC15_REG_OFFSET(GC, 0, mmDIDT_IND_INDEX);
data = SOC15_REG_OFFSET(GC, 0, mmDIDT_IND_DATA);
spin_lock_irqsave(&adev->didt_idx_lock, flags);
WREG32(address, (reg));
r = RREG32(data);
spin_unlock_irqrestore(&adev->didt_idx_lock, flags);
return r;
}
static void soc15_didt_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
{
unsigned long flags, address, data;
address = SOC15_REG_OFFSET(GC, 0, mmDIDT_IND_INDEX);
data = SOC15_REG_OFFSET(GC, 0, mmDIDT_IND_DATA);
spin_lock_irqsave(&adev->didt_idx_lock, flags);
WREG32(address, (reg));
WREG32(data, (v));
spin_unlock_irqrestore(&adev->didt_idx_lock, flags);
}
static u32 soc15_gc_cac_rreg(struct amdgpu_device *adev, u32 reg)
{
unsigned long flags;
u32 r;
spin_lock_irqsave(&adev->gc_cac_idx_lock, flags);
WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, (reg));
r = RREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA);
spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags);
return r;
}
static void soc15_gc_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
{
unsigned long flags;
spin_lock_irqsave(&adev->gc_cac_idx_lock, flags);
WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, (reg));
WREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA, (v));
spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags);
}
static u32 soc15_se_cac_rreg(struct amdgpu_device *adev, u32 reg)
{
unsigned long flags;
u32 r;
spin_lock_irqsave(&adev->se_cac_idx_lock, flags);
WREG32_SOC15(GC, 0, mmSE_CAC_IND_INDEX, (reg));
r = RREG32_SOC15(GC, 0, mmSE_CAC_IND_DATA);
spin_unlock_irqrestore(&adev->se_cac_idx_lock, flags);
return r;
}
static void soc15_se_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
{
unsigned long flags;
spin_lock_irqsave(&adev->se_cac_idx_lock, flags);
WREG32_SOC15(GC, 0, mmSE_CAC_IND_INDEX, (reg));
WREG32_SOC15(GC, 0, mmSE_CAC_IND_DATA, (v));
spin_unlock_irqrestore(&adev->se_cac_idx_lock, flags);
}
static u32 soc15_get_config_memsize(struct amdgpu_device *adev)
{
return adev->nbio.funcs->get_memsize(adev);
}
static u32 soc15_get_xclk(struct amdgpu_device *adev)
{
u32 reference_clock = adev->clock.spll.reference_freq;
if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(12, 0, 0) ||
amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(12, 0, 1) ||
amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 6))
return 10000;
if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(10, 0, 0) ||
amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(10, 0, 1))
return reference_clock / 4;
return reference_clock;
}
void soc15_grbm_select(struct amdgpu_device *adev,
u32 me, u32 pipe, u32 queue, u32 vmid, int xcc_id)
{
u32 grbm_gfx_cntl = 0;
grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, PIPEID, pipe);
grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, MEID, me);
grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, VMID, vmid);
grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, QUEUEID, queue);
WREG32_SOC15_RLC_SHADOW(GC, xcc_id, mmGRBM_GFX_CNTL, grbm_gfx_cntl);
}
static bool soc15_read_disabled_bios(struct amdgpu_device *adev)
{
/* todo */
return false;
}
static struct soc15_allowed_register_entry soc15_allowed_read_registers[] = {
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS)},
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS2)},
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE0)},
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE1)},
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE2)},
{ SOC15_REG_ENTRY(GC, 0, mmGRBM_STATUS_SE3)},
{ SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_STATUS_REG)},
{ SOC15_REG_ENTRY(SDMA1, 0, mmSDMA1_STATUS_REG)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_STAT)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT1)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT2)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_STALLED_STAT3)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_BUSY_STAT)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
{ SOC15_REG_ENTRY(GC, 0, mmDB_DEBUG2)},
};
static uint32_t soc15_read_indexed_register(struct amdgpu_device *adev, u32 se_num,
u32 sh_num, u32 reg_offset)
{
uint32_t val;
mutex_lock(&adev->grbm_idx_mutex);
if (se_num != 0xffffffff || sh_num != 0xffffffff)
amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff, 0);
val = RREG32(reg_offset);
if (se_num != 0xffffffff || sh_num != 0xffffffff)
amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0);
mutex_unlock(&adev->grbm_idx_mutex);
return val;
}
static uint32_t soc15_get_register_value(struct amdgpu_device *adev,
bool indexed, u32 se_num,
u32 sh_num, u32 reg_offset)
{
if (indexed) {
return soc15_read_indexed_register(adev, se_num, sh_num, reg_offset);
} else {
if (reg_offset == SOC15_REG_OFFSET(GC, 0, mmGB_ADDR_CONFIG))
return adev->gfx.config.gb_addr_config;
else if (reg_offset == SOC15_REG_OFFSET(GC, 0, mmDB_DEBUG2))
return adev->gfx.config.db_debug2;
return RREG32(reg_offset);
}
}
static int soc15_read_register(struct amdgpu_device *adev, u32 se_num,
u32 sh_num, u32 reg_offset, u32 *value)
{
uint32_t i;
struct soc15_allowed_register_entry *en;
*value = 0;
for (i = 0; i < ARRAY_SIZE(soc15_allowed_read_registers); i++) {
en = &soc15_allowed_read_registers[i];
if (!adev->reg_offset[en->hwip][en->inst])
continue;
else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg]
+ en->reg_offset))
continue;
*value = soc15_get_register_value(adev,
soc15_allowed_read_registers[i].grbm_indexed,
se_num, sh_num, reg_offset);
return 0;
}
return -EINVAL;
}
/**
* soc15_program_register_sequence - program an array of registers.
*
* @adev: amdgpu_device pointer
* @regs: pointer to the register array
* @array_size: size of the register array
*
* Programs an array or registers with and and or masks.
* This is a helper for setting golden registers.
*/
void soc15_program_register_sequence(struct amdgpu_device *adev,
const struct soc15_reg_golden *regs,
const u32 array_size)
{
const struct soc15_reg_golden *entry;
u32 tmp, reg;
int i;
for (i = 0; i < array_size; ++i) {
entry = ®s[i];
reg = adev->reg_offset[entry->hwip][entry->instance][entry->segment] + entry->reg;
if (entry->and_mask == 0xffffffff) {
tmp = entry->or_mask;
} else {
tmp = (entry->hwip == GC_HWIP) ?
RREG32_SOC15_IP(GC, reg) : RREG32(reg);
tmp &= ~(entry->and_mask);
tmp |= (entry->or_mask & entry->and_mask);
}
if (reg == SOC15_REG_OFFSET(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_3) ||
reg == SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE) ||
reg == SOC15_REG_OFFSET(GC, 0, mmPA_SC_ENHANCE_1) ||
reg == SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG))
WREG32_RLC(reg, tmp);
else
(entry->hwip == GC_HWIP) ?
WREG32_SOC15_IP(GC, reg, tmp) : WREG32(reg, tmp);
}
}
static int soc15_asic_baco_reset(struct amdgpu_device *adev)
{
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
int ret = 0;
/* avoid NBIF got stuck when do RAS recovery in BACO reset */
if (ras && adev->ras_enabled)
adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
ret = amdgpu_dpm_baco_reset(adev);
if (ret)
return ret;
/* re-enable doorbell interrupt after BACO exit */
if (ras && adev->ras_enabled)
adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
return 0;
}
static enum amd_reset_method
soc15_asic_reset_method(struct amdgpu_device *adev)
{
bool baco_reset = false;
bool connected_to_cpu = false;
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
if (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)
connected_to_cpu = true;
if (amdgpu_reset_method == AMD_RESET_METHOD_MODE1 ||
amdgpu_reset_method == AMD_RESET_METHOD_MODE2 ||
amdgpu_reset_method == AMD_RESET_METHOD_BACO ||
amdgpu_reset_method == AMD_RESET_METHOD_PCI) {
/* If connected to cpu, driver only support mode2 */
if (connected_to_cpu)
return AMD_RESET_METHOD_MODE2;
return amdgpu_reset_method;
}
if (amdgpu_reset_method != -1)
dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
amdgpu_reset_method);
switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
case IP_VERSION(10, 0, 0):
case IP_VERSION(10, 0, 1):
case IP_VERSION(12, 0, 0):
case IP_VERSION(12, 0, 1):
return AMD_RESET_METHOD_MODE2;
case IP_VERSION(9, 0, 0):
case IP_VERSION(11, 0, 2):
if (adev->asic_type == CHIP_VEGA20) {
if (adev->psp.sos.fw_version >= 0x80067)
baco_reset = amdgpu_dpm_is_baco_supported(adev);
/*
* 1. PMFW version > 0x284300: all cases use baco
* 2. PMFW version <= 0x284300: only sGPU w/o RAS use baco
*/
if (ras && adev->ras_enabled &&
adev->pm.fw_version <= 0x283400)
baco_reset = false;
} else {
baco_reset = amdgpu_dpm_is_baco_supported(adev);
}
break;
case IP_VERSION(13, 0, 2):
/*
* 1.connected to cpu: driver issue mode2 reset
* 2.discret gpu: driver issue mode1 reset
*/
if (connected_to_cpu)
return AMD_RESET_METHOD_MODE2;
break;
case IP_VERSION(13, 0, 6):
/* Use gpu_recovery param to target a reset method.
* Enable triggering of GPU reset only if specified
* by module parameter.
*/
if (amdgpu_gpu_recovery == 4 || amdgpu_gpu_recovery == 5)
return AMD_RESET_METHOD_MODE2;
else if (!(adev->flags & AMD_IS_APU))
return AMD_RESET_METHOD_MODE1;
else
return AMD_RESET_METHOD_MODE2;
default:
break;
}
if (baco_reset)
return AMD_RESET_METHOD_BACO;
else
return AMD_RESET_METHOD_MODE1;
}
static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
{
u32 sol_reg;
sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
/* Will reset for the following suspend abort cases.
* 1) Only reset limit on APU side, dGPU hasn't checked yet.
* 2) S3 suspend abort and TOS already launched.
*/
if (adev->flags & AMD_IS_APU && adev->in_s3 &&
!adev->suspend_complete &&
sol_reg)
return true;
return false;
}
static int soc15_asic_reset(struct amdgpu_device *adev)
{
/* original raven doesn't have full asic reset */
/* On the latest Raven, the GPU reset can be performed
* successfully. So now, temporarily enable it for the
* S3 suspend abort case.
*/
if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
(adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
!soc15_need_reset_on_resume(adev))
return 0;
switch (soc15_asic_reset_method(adev)) {
case AMD_RESET_METHOD_PCI:
dev_info(adev->dev, "PCI reset\n");
return amdgpu_device_pci_reset(adev);
case AMD_RESET_METHOD_BACO:
dev_info(adev->dev, "BACO reset\n");
return soc15_asic_baco_reset(adev);
case AMD_RESET_METHOD_MODE2:
dev_info(adev->dev, "MODE2 reset\n");
return amdgpu_dpm_mode2_reset(adev);
default:
dev_info(adev->dev, "MODE1 reset\n");
return amdgpu_device_mode1_reset(adev);
}
}
static bool soc15_supports_baco(struct amdgpu_device *adev)
{
switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
case IP_VERSION(9, 0, 0):
case IP_VERSION(11, 0, 2):
if (adev->asic_type == CHIP_VEGA20) {
if (adev->psp.sos.fw_version >= 0x80067)
return amdgpu_dpm_is_baco_supported(adev);
return false;
} else {
return amdgpu_dpm_is_baco_supported(adev);
}
break;
default:
return false;
}
}
/*static int soc15_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
u32 cntl_reg, u32 status_reg)
{
return 0;
}*/
static int soc15_set_uvd_clocks(struct amdgpu_device *adev, u32 vclk, u32 dclk)
{
/*int r;
r = soc15_set_uvd_clock(adev, vclk, ixCG_VCLK_CNTL, ixCG_VCLK_STATUS);
if (r)
return r;
r = soc15_set_uvd_clock(adev, dclk, ixCG_DCLK_CNTL, ixCG_DCLK_STATUS);
*/
return 0;
}
static int soc15_set_vce_clocks(struct amdgpu_device *adev, u32 evclk, u32 ecclk)
{
/* todo */
return 0;
}
static void soc15_program_aspm(struct amdgpu_device *adev)
{
if (!amdgpu_device_should_use_aspm(adev))
return;
if (adev->nbio.funcs->program_aspm)
adev->nbio.funcs->program_aspm(adev);
}
const struct amdgpu_ip_block_version vega10_common_ip_block =
{
.type = AMD_IP_BLOCK_TYPE_COMMON,
.major = 2,
.minor = 0,
.rev = 0,
.funcs = &soc15_common_ip_funcs,
};
static void soc15_reg_base_init(struct amdgpu_device *adev)
{
/* Set IP register base before any HW register access */
switch (adev->asic_type) {
case CHIP_VEGA10:
case CHIP_VEGA12:
case CHIP_RAVEN:
case CHIP_RENOIR:
vega10_reg_base_init(adev);
break;
case CHIP_VEGA20:
vega20_reg_base_init(adev);
break;
case CHIP_ARCTURUS:
arct_reg_base_init(adev);
break;
case CHIP_ALDEBARAN:
aldebaran_reg_base_init(adev);
break;
default:
DRM_ERROR("Unsupported asic type: %d!\n", adev->asic_type);
break;
}
}
void soc15_set_virt_ops(struct amdgpu_device *adev)
{
adev->virt.ops = &xgpu_ai_virt_ops;
/* init soc15 reg base early enough so we can
* request request full access for sriov before
* set_ip_blocks. */
soc15_reg_base_init(adev);
}
static bool soc15_need_full_reset(struct amdgpu_device *adev)
{
/* change this when we implement soft reset */
return true;
}
static void soc15_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0,
uint64_t *count1)
{
uint32_t perfctr = 0;
uint64_t cnt0_of, cnt1_of;
int tmp;
/* This reports 0 on APUs, so return to avoid writing/reading registers
* that may or may not be different from their GPU counterparts
*/
if (adev->flags & AMD_IS_APU)
return;
/* Set the 2 events that we wish to watch, defined above */
/* Reg 40 is # received msgs */
/* Reg 104 is # of posted requests sent */
perfctr = REG_SET_FIELD(perfctr, PCIE_PERF_CNTL_TXCLK, EVENT0_SEL, 40);
perfctr = REG_SET_FIELD(perfctr, PCIE_PERF_CNTL_TXCLK, EVENT1_SEL, 104);
/* Write to enable desired perf counters */
WREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK, perfctr);
/* Zero out and enable the perf counters
* Write 0x5:
* Bit 0 = Start all counters(1)
* Bit 2 = Global counter reset enable(1)
*/
WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000005);
msleep(1000);
/* Load the shadow and disable the perf counters
* Write 0x2:
* Bit 0 = Stop counters(0)
* Bit 1 = Load the shadow counters(1)
*/
WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000002);
/* Read register values to get any >32bit overflow */
tmp = RREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK);
cnt0_of = REG_GET_FIELD(tmp, PCIE_PERF_CNTL_TXCLK, COUNTER0_UPPER);
cnt1_of = REG_GET_FIELD(tmp, PCIE_PERF_CNTL_TXCLK, COUNTER1_UPPER);
/* Get the values and add the overflow */
*count0 = RREG32_PCIE(smnPCIE_PERF_COUNT0_TXCLK) | (cnt0_of << 32);
*count1 = RREG32_PCIE(smnPCIE_PERF_COUNT1_TXCLK) | (cnt1_of << 32);
}
static void vega20_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0,
uint64_t *count1)
{
uint32_t perfctr = 0;
uint64_t cnt0_of, cnt1_of;
int tmp;
/* This reports 0 on APUs, so return to avoid writing/reading registers
* that may or may not be different from their GPU counterparts
*/
if (adev->flags & AMD_IS_APU)
return;
/* Set the 2 events that we wish to watch, defined above */
/* Reg 40 is # received msgs */
/* Reg 108 is # of posted requests sent on VG20 */
perfctr = REG_SET_FIELD(perfctr, PCIE_PERF_CNTL_TXCLK3,
EVENT0_SEL, 40);
perfctr = REG_SET_FIELD(perfctr, PCIE_PERF_CNTL_TXCLK3,
EVENT1_SEL, 108);
/* Write to enable desired perf counters */
WREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK3, perfctr);
/* Zero out and enable the perf counters
* Write 0x5:
* Bit 0 = Start all counters(1)
* Bit 2 = Global counter reset enable(1)
*/
WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000005);
msleep(1000);
/* Load the shadow and disable the perf counters
* Write 0x2:
* Bit 0 = Stop counters(0)
* Bit 1 = Load the shadow counters(1)
*/
WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000002);
/* Read register values to get any >32bit overflow */
tmp = RREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK3);
cnt0_of = REG_GET_FIELD(tmp, PCIE_PERF_CNTL_TXCLK3, COUNTER0_UPPER);
cnt1_of = REG_GET_FIELD(tmp, PCIE_PERF_CNTL_TXCLK3, COUNTER1_UPPER);
/* Get the values and add the overflow */
*count0 = RREG32_PCIE(smnPCIE_PERF_COUNT0_TXCLK3) | (cnt0_of << 32);
*count1 = RREG32_PCIE(smnPCIE_PERF_COUNT1_TXCLK3) | (cnt1_of << 32);
}
static bool soc15_need_reset_on_init(struct amdgpu_device *adev)
{
u32 sol_reg;
/* CP hangs in IGT reloading test on RN, reset to WA */
if (adev->asic_type == CHIP_RENOIR)
return true;
/* Just return false for soc15 GPUs. Reset does not seem to
* be necessary.
*/
if (!amdgpu_passthrough(adev))
return false;
if (adev->flags & AMD_IS_APU)
return false;
/* Check sOS sign of life register to confirm sys driver and sOS
* are already been loaded.
*/
sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
if (sol_reg)
return true;
return false;
}
static uint64_t soc15_get_pcie_replay_count(struct amdgpu_device *adev)
{
uint64_t nak_r, nak_g;
/* Get the number of NAKs received and generated */
nak_r = RREG32_PCIE(smnPCIE_RX_NUM_NAK);
nak_g = RREG32_PCIE(smnPCIE_RX_NUM_NAK_GENERATED);
/* Add the total number of NAKs, i.e the number of replays */
return (nak_r + nak_g);
}
static void soc15_pre_asic_init(struct amdgpu_device *adev)
{
gmc_v9_0_restore_registers(adev);
}
static const struct amdgpu_asic_funcs soc15_asic_funcs =
{
.read_disabled_bios = &soc15_read_disabled_bios,
.read_bios_from_rom = &amdgpu_soc15_read_bios_from_rom,
.read_register = &soc15_read_register,
.reset = &soc15_asic_reset,
.reset_method = &soc15_asic_reset_method,
.get_xclk = &soc15_get_xclk,
.set_uvd_clocks = &soc15_set_uvd_clocks,
.set_vce_clocks = &soc15_set_vce_clocks,
.get_config_memsize = &soc15_get_config_memsize,
.need_full_reset = &soc15_need_full_reset,
.init_doorbell_index = &vega10_doorbell_index_init,
.get_pcie_usage = &soc15_get_pcie_usage,
.need_reset_on_init = &soc15_need_reset_on_init,
.get_pcie_replay_count = &soc15_get_pcie_replay_count,
.supports_baco = &soc15_supports_baco,
.pre_asic_init = &soc15_pre_asic_init,
.query_video_codecs = &soc15_query_video_codecs,
};
static const struct amdgpu_asic_funcs vega20_asic_funcs =
{
.read_disabled_bios = &soc15_read_disabled_bios,
.read_bios_from_rom = &amdgpu_soc15_read_bios_from_rom,
.read_register = &soc15_read_register,
.reset = &soc15_asic_reset,
.reset_method = &soc15_asic_reset_method,
.get_xclk = &soc15_get_xclk,
.set_uvd_clocks = &soc15_set_uvd_clocks,
.set_vce_clocks = &soc15_set_vce_clocks,
.get_config_memsize = &soc15_get_config_memsize,
.need_full_reset = &soc15_need_full_reset,
.init_doorbell_index = &vega20_doorbell_index_init,
.get_pcie_usage = &vega20_get_pcie_usage,
.need_reset_on_init = &soc15_need_reset_on_init,
.get_pcie_replay_count = &soc15_get_pcie_replay_count,
.supports_baco = &soc15_supports_baco,
.pre_asic_init = &soc15_pre_asic_init,
.query_video_codecs = &soc15_query_video_codecs,
};
static const struct amdgpu_asic_funcs aqua_vanjaram_asic_funcs =
{
.read_disabled_bios = &soc15_read_disabled_bios,
.read_bios_from_rom = &amdgpu_soc15_read_bios_from_rom,
.read_register = &soc15_read_register,
.reset = &soc15_asic_reset,
.reset_method = &soc15_asic_reset_method,
.get_xclk = &soc15_get_xclk,
.set_uvd_clocks = &soc15_set_uvd_clocks,
.set_vce_clocks = &soc15_set_vce_clocks,
.get_config_memsize = &soc15_get_config_memsize,
.need_full_reset = &soc15_need_full_reset,
.init_doorbell_index = &aqua_vanjaram_doorbell_index_init,
.need_reset_on_init = &soc15_need_reset_on_init,
.get_pcie_replay_count = &amdgpu_nbio_get_pcie_replay_count,
.supports_baco = &soc15_supports_baco,
.pre_asic_init = &soc15_pre_asic_init,
.query_video_codecs = &soc15_query_video_codecs,
.encode_ext_smn_addressing = &aqua_vanjaram_encode_ext_smn_addressing,
.get_reg_state = &aqua_vanjaram_get_reg_state,
};
static int soc15_common_early_init(void *handle)
{
#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (!amdgpu_sriov_vf(adev)) {
adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
}
adev->smc_rreg = NULL;
adev->smc_wreg = NULL;
adev->pcie_rreg = &amdgpu_device_indirect_rreg;
adev->pcie_wreg = &amdgpu_device_indirect_wreg;
adev->pcie_rreg_ext = &amdgpu_device_indirect_rreg_ext;
adev->pcie_wreg_ext = &amdgpu_device_indirect_wreg_ext;
adev->pcie_rreg64 = &amdgpu_device_indirect_rreg64;
adev->pcie_wreg64 = &amdgpu_device_indirect_wreg64;
adev->pcie_rreg64_ext = &amdgpu_device_indirect_rreg64_ext;
adev->pcie_wreg64_ext = &amdgpu_device_indirect_wreg64_ext;
adev->uvd_ctx_rreg = &soc15_uvd_ctx_rreg;
adev->uvd_ctx_wreg = &soc15_uvd_ctx_wreg;
adev->didt_rreg = &soc15_didt_rreg;
adev->didt_wreg = &soc15_didt_wreg;
adev->gc_cac_rreg = &soc15_gc_cac_rreg;
adev->gc_cac_wreg = &soc15_gc_cac_wreg;
adev->se_cac_rreg = &soc15_se_cac_rreg;
adev->se_cac_wreg = &soc15_se_cac_wreg;
adev->rev_id = amdgpu_device_get_rev_id(adev);
adev->external_rev_id = 0xFF;
/* TODO: split the GC and PG flags based on the relevant IP version for which
* they are relevant.
*/
switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
case IP_VERSION(9, 0, 1):
adev->asic_funcs = &soc15_asic_funcs;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_RLC_LS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_BIF_MGCG |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_DRM_MGCG |
AMD_CG_SUPPORT_DRM_LS |
AMD_CG_SUPPORT_ROM_MGCG |
AMD_CG_SUPPORT_DF_MGCG |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS;
adev->pg_flags = 0;
adev->external_rev_id = 0x1;
break;
case IP_VERSION(9, 2, 1):
adev->asic_funcs = &soc15_asic_funcs;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_BIF_MGCG |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_MGCG |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_ROM_MGCG |
AMD_CG_SUPPORT_VCE_MGCG |
AMD_CG_SUPPORT_UVD_MGCG;
adev->pg_flags = 0;
adev->external_rev_id = adev->rev_id + 0x14;
break;
case IP_VERSION(9, 4, 0):
adev->asic_funcs = &vega20_asic_funcs;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_BIF_MGCG |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_MGCG |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_ROM_MGCG |
AMD_CG_SUPPORT_VCE_MGCG |
AMD_CG_SUPPORT_UVD_MGCG;
adev->pg_flags = 0;
adev->external_rev_id = adev->rev_id + 0x28;
break;
case IP_VERSION(9, 1, 0):
case IP_VERSION(9, 2, 2):
adev->asic_funcs = &soc15_asic_funcs;
if (adev->rev_id >= 0x8)
adev->apu_flags |= AMD_APU_IS_RAVEN2;
if (adev->apu_flags & AMD_APU_IS_RAVEN2)
adev->external_rev_id = adev->rev_id + 0x79;
else if (adev->apu_flags & AMD_APU_IS_PICASSO)
adev->external_rev_id = adev->rev_id + 0x41;
else if (adev->rev_id == 1)
adev->external_rev_id = adev->rev_id + 0x20;
else
adev->external_rev_id = adev->rev_id + 0x01;
if (adev->apu_flags & AMD_APU_IS_RAVEN2) {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_VCN_MGCG;
adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
} else if (adev->apu_flags & AMD_APU_IS_PICASSO) {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_VCN_MGCG;
/*
* MMHUB PG needs to be disabled for Picasso for
* stability reasons.
*/
adev->pg_flags = AMD_PG_SUPPORT_SDMA |
AMD_PG_SUPPORT_VCN;
} else {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_RLC_LS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_BIF_MGCG |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_MGCG |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_DRM_MGCG |
AMD_CG_SUPPORT_DRM_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_VCN_MGCG;
adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
}
break;
case IP_VERSION(9, 4, 1):
adev->asic_funcs = &vega20_asic_funcs;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_HDP_MGCG |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_IH_CG |
AMD_CG_SUPPORT_VCN_MGCG |
AMD_CG_SUPPORT_JPEG_MGCG;
adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG;
adev->external_rev_id = adev->rev_id + 0x32;
break;
case IP_VERSION(9, 3, 0):
adev->asic_funcs = &soc15_asic_funcs;
if (adev->apu_flags & AMD_APU_IS_RENOIR)
adev->external_rev_id = adev->rev_id + 0x91;
else
adev->external_rev_id = adev->rev_id + 0xa1;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_CG_SUPPORT_GFX_3D_CGLS |
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_MC_MGCG |
AMD_CG_SUPPORT_MC_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_VCN_MGCG |
AMD_CG_SUPPORT_JPEG_MGCG |
AMD_CG_SUPPORT_IH_CG |
AMD_CG_SUPPORT_ATHUB_LS |
AMD_CG_SUPPORT_ATHUB_MGCG |
AMD_CG_SUPPORT_DF_MGCG;
adev->pg_flags = AMD_PG_SUPPORT_SDMA |
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_JPEG |
AMD_PG_SUPPORT_VCN_DPG;
break;
case IP_VERSION(9, 4, 2):
adev->asic_funcs = &vega20_asic_funcs;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_HDP_LS |
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_IH_CG |
AMD_CG_SUPPORT_VCN_MGCG | AMD_CG_SUPPORT_JPEG_MGCG;
adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG;
adev->external_rev_id = adev->rev_id + 0x3c;
break;
case IP_VERSION(9, 4, 3):
adev->asic_funcs = &aqua_vanjaram_asic_funcs;
adev->cg_flags =
AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_GFX_FGCG | AMD_CG_SUPPORT_REPEATER_FGCG |
AMD_CG_SUPPORT_VCN_MGCG | AMD_CG_SUPPORT_JPEG_MGCG |
AMD_CG_SUPPORT_IH_CG;
adev->pg_flags =
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
adev->external_rev_id = adev->rev_id + 0x46;
/* GC 9.4.3 uses MMIO register region hole at a different offset */
if (!amdgpu_sriov_vf(adev)) {
adev->rmmio_remap.reg_offset = 0x1A000;
adev->rmmio_remap.bus_addr = adev->rmmio_base + 0x1A000;
}
break;
default:
/* FIXME: not supported yet */
return -EINVAL;
}
if (amdgpu_sriov_vf(adev)) {
amdgpu_virt_init_setting(adev);
xgpu_ai_mailbox_set_irq_funcs(adev);
}
return 0;
}
static int soc15_common_late_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (amdgpu_sriov_vf(adev))
xgpu_ai_mailbox_get_irq(adev);
/* Enable selfring doorbell aperture late because doorbell BAR
* aperture will change if resize BAR successfully in gmc sw_init.
*/
adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true);
return 0;
}
static int soc15_common_sw_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (amdgpu_sriov_vf(adev))
xgpu_ai_mailbox_add_irq_id(adev);
if (adev->df.funcs &&
adev->df.funcs->sw_init)
adev->df.funcs->sw_init(adev);
return 0;
}
static int soc15_common_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (adev->df.funcs &&
adev->df.funcs->sw_fini)
adev->df.funcs->sw_fini(adev);
return 0;
}
static void soc15_sdma_doorbell_range_init(struct amdgpu_device *adev)
{
int i;
/* sdma doorbell range is programed by hypervisor */
if (!amdgpu_sriov_vf(adev)) {
for (i = 0; i < adev->sdma.num_instances; i++) {
adev->nbio.funcs->sdma_doorbell_range(adev, i,
true, adev->doorbell_index.sdma_engine[i] << 1,
adev->doorbell_index.sdma_doorbell_range);
}
}
}
static int soc15_common_hw_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* enable aspm */
soc15_program_aspm(adev);
/* setup nbio registers */
adev->nbio.funcs->init_registers(adev);
/* remap HDP registers to a hole in mmio space,
* for the purpose of expose those registers
* to process space
*/
if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
adev->nbio.funcs->remap_hdp_registers(adev);
/* enable the doorbell aperture */
adev->nbio.funcs->enable_doorbell_aperture(adev, true);
/* HW doorbell routing policy: doorbell writing not
* in SDMA/IH/MM/ACV range will be routed to CP. So
* we need to init SDMA doorbell range prior
* to CP ip block init and ring test. IH already
* happens before CP.
*/
soc15_sdma_doorbell_range_init(adev);
return 0;
}
static int soc15_common_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* Disable the doorbell aperture and selfring doorbell aperture
* separately in hw_fini because soc15_enable_doorbell_aperture
* has been removed and there is no need to delay disabling
* selfring doorbell.
*/
adev->nbio.funcs->enable_doorbell_aperture(adev, false);
adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false);
if (amdgpu_sriov_vf(adev))
xgpu_ai_mailbox_put_irq(adev);
if ((!amdgpu_sriov_vf(adev)) &&
adev->nbio.ras_if &&
amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
if (adev->nbio.ras &&
adev->nbio.ras->init_ras_controller_interrupt)
amdgpu_irq_put(adev, &adev->nbio.ras_controller_irq, 0);
if (adev->nbio.ras &&
adev->nbio.ras->init_ras_err_event_athub_interrupt)
amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0);
}
return 0;
}
static int soc15_common_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
return soc15_common_hw_fini(adev);
}
static int soc15_common_resume(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (soc15_need_reset_on_resume(adev)) {
dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
soc15_asic_reset(adev);
}
return soc15_common_hw_init(adev);
}
static bool soc15_common_is_idle(void *handle)
{
return true;
}
static int soc15_common_wait_for_idle(void *handle)
{
return 0;
}
static int soc15_common_soft_reset(void *handle)
{
return 0;
}
static void soc15_update_drm_clock_gating(struct amdgpu_device *adev, bool enable)
{
uint32_t def, data;
def = data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DRM_MGCG))
data &= ~(0x01000000 |
0x02000000 |
0x04000000 |
0x08000000 |
0x10000000 |
0x20000000 |
0x40000000 |
0x80000000);
else
data |= (0x01000000 |
0x02000000 |
0x04000000 |
0x08000000 |
0x10000000 |
0x20000000 |
0x40000000 |
0x80000000);
if (def != data)
WREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0), data);
}
static void soc15_update_drm_light_sleep(struct amdgpu_device *adev, bool enable)
{
uint32_t def, data;
def = data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_LIGHT_SLEEP_CTRL));
if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DRM_LS))
data |= 1;
else
data &= ~1;
if (def != data)
WREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_LIGHT_SLEEP_CTRL), data);
}
static int soc15_common_set_clockgating_state(void *handle,
enum amd_clockgating_state state)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
if (amdgpu_sriov_vf(adev))
return 0;
switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
case IP_VERSION(6, 1, 0):
case IP_VERSION(6, 2, 0):
case IP_VERSION(7, 4, 0):
adev->nbio.funcs->update_medium_grain_clock_gating(adev,
state == AMD_CG_STATE_GATE);
adev->nbio.funcs->update_medium_grain_light_sleep(adev,
state == AMD_CG_STATE_GATE);
adev->hdp.funcs->update_clock_gating(adev,
state == AMD_CG_STATE_GATE);
soc15_update_drm_clock_gating(adev,
state == AMD_CG_STATE_GATE);
soc15_update_drm_light_sleep(adev,
state == AMD_CG_STATE_GATE);
adev->smuio.funcs->update_rom_clock_gating(adev,
state == AMD_CG_STATE_GATE);
adev->df.funcs->update_medium_grain_clock_gating(adev,
state == AMD_CG_STATE_GATE);
break;
case IP_VERSION(7, 0, 0):
case IP_VERSION(7, 0, 1):
case IP_VERSION(2, 5, 0):
adev->nbio.funcs->update_medium_grain_clock_gating(adev,
state == AMD_CG_STATE_GATE);
adev->nbio.funcs->update_medium_grain_light_sleep(adev,
state == AMD_CG_STATE_GATE);
adev->hdp.funcs->update_clock_gating(adev,
state == AMD_CG_STATE_GATE);
soc15_update_drm_clock_gating(adev,
state == AMD_CG_STATE_GATE);
soc15_update_drm_light_sleep(adev,
state == AMD_CG_STATE_GATE);
break;
case IP_VERSION(7, 4, 1):
case IP_VERSION(7, 4, 4):
adev->hdp.funcs->update_clock_gating(adev,
state == AMD_CG_STATE_GATE);
break;
default:
break;
}
return 0;
}
static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int data;
if (amdgpu_sriov_vf(adev))
*flags = 0;
if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state)
adev->nbio.funcs->get_clockgating_state(adev, flags);
if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state)
adev->hdp.funcs->get_clock_gating_state(adev, flags);
if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) &&
(amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))) {
/* AMD_CG_SUPPORT_DRM_MGCG */
data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
if (!(data & 0x01000000))
*flags |= AMD_CG_SUPPORT_DRM_MGCG;
/* AMD_CG_SUPPORT_DRM_LS */
data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_LIGHT_SLEEP_CTRL));
if (data & 0x1)
*flags |= AMD_CG_SUPPORT_DRM_LS;
}
/* AMD_CG_SUPPORT_ROM_MGCG */
if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state)
adev->smuio.funcs->get_clock_gating_state(adev, flags);
if (adev->df.funcs && adev->df.funcs->get_clockgating_state)
adev->df.funcs->get_clockgating_state(adev, flags);
}
static int soc15_common_set_powergating_state(void *handle,
enum amd_powergating_state state)
{
/* todo */
return 0;
}
static const struct amd_ip_funcs soc15_common_ip_funcs = {
.name = "soc15_common",
.early_init = soc15_common_early_init,
.late_init = soc15_common_late_init,
.sw_init = soc15_common_sw_init,
.sw_fini = soc15_common_sw_fini,
.hw_init = soc15_common_hw_init,
.hw_fini = soc15_common_hw_fini,
.suspend = soc15_common_suspend,
.resume = soc15_common_resume,
.is_idle = soc15_common_is_idle,
.wait_for_idle = soc15_common_wait_for_idle,
.soft_reset = soc15_common_soft_reset,
.set_clockgating_state = soc15_common_set_clockgating_state,
.set_powergating_state = soc15_common_set_powergating_state,
.get_clockgating_state= soc15_common_get_clockgating_state,
};
|