summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
blob: b4d8e1b01ee4f20f732585fce9aba72ccfed3d69 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */


#include "msm_gem.h"
#include "msm_mmu.h"
#include "msm_gpu_trace.h"
#include "a6xx_gpu.h"
#include "a6xx_gmu.xml.h"

#include <linux/bitfield.h>
#include <linux/devfreq.h>
#include <linux/nvmem-consumer.h>
#include <linux/soc/qcom/llcc-qcom.h>

#define GPU_PAS_ID 13

static inline bool _a6xx_check_idle(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

	/* Check that the GMU is idle */
	if (!a6xx_gmu_isidle(&a6xx_gpu->gmu))
		return false;

	/* Check tha the CX master is idle */
	if (gpu_read(gpu, REG_A6XX_RBBM_STATUS) &
			~A6XX_RBBM_STATUS_CP_AHB_BUSY_CX_MASTER)
		return false;

	return !(gpu_read(gpu, REG_A6XX_RBBM_INT_0_STATUS) &
		A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT);
}

static bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
{
	/* wait for CP to drain ringbuffer: */
	if (!adreno_idle(gpu, ring))
		return false;

	if (spin_until(_a6xx_check_idle(gpu))) {
		DRM_ERROR("%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X rptr/wptr %d/%d\n",
			gpu->name, __builtin_return_address(0),
			gpu_read(gpu, REG_A6XX_RBBM_STATUS),
			gpu_read(gpu, REG_A6XX_RBBM_INT_0_STATUS),
			gpu_read(gpu, REG_A6XX_CP_RB_RPTR),
			gpu_read(gpu, REG_A6XX_CP_RB_WPTR));
		return false;
	}

	return true;
}

static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	uint32_t wptr;
	unsigned long flags;

	/* Expanded APRIV doesn't need to issue the WHERE_AM_I opcode */
	if (a6xx_gpu->has_whereami && !adreno_gpu->base.hw_apriv) {
		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

		OUT_PKT7(ring, CP_WHERE_AM_I, 2);
		OUT_RING(ring, lower_32_bits(shadowptr(a6xx_gpu, ring)));
		OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring)));
	}

	spin_lock_irqsave(&ring->preempt_lock, flags);

	/* Copy the shadow to the actual register */
	ring->cur = ring->next;

	/* Make sure to wrap wptr if we need to */
	wptr = get_wptr(ring);

	spin_unlock_irqrestore(&ring->preempt_lock, flags);

	/* Make sure everything is posted before making a decision */
	mb();

	gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr);
}

static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
		u64 iova)
{
	OUT_PKT7(ring, CP_REG_TO_MEM, 3);
	OUT_RING(ring, CP_REG_TO_MEM_0_REG(counter) |
		CP_REG_TO_MEM_0_CNT(2) |
		CP_REG_TO_MEM_0_64B);
	OUT_RING(ring, lower_32_bits(iova));
	OUT_RING(ring, upper_32_bits(iova));
}

static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
		struct msm_ringbuffer *ring, struct msm_file_private *ctx)
{
	phys_addr_t ttbr;
	u32 asid;
	u64 memptr = rbmemptr(ring, ttbr0);

	if (ctx == a6xx_gpu->cur_ctx)
		return;

	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
		return;

	/* Execute the table update */
	OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4);
	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr)));

	OUT_RING(ring,
		CP_SMMU_TABLE_UPDATE_1_TTBR0_HI(upper_32_bits(ttbr)) |
		CP_SMMU_TABLE_UPDATE_1_ASID(asid));
	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_2_CONTEXTIDR(0));
	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK(0));

	/*
	 * Write the new TTBR0 to the memstore. This is good for debugging.
	 */
	OUT_PKT7(ring, CP_MEM_WRITE, 4);
	OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr)));
	OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr)));
	OUT_RING(ring, lower_32_bits(ttbr));
	OUT_RING(ring, (asid << 16) | upper_32_bits(ttbr));

	/*
	 * And finally, trigger a uche flush to be sure there isn't anything
	 * lingering in that part of the GPU
	 */

	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
	OUT_RING(ring, 0x31);

	a6xx_gpu->cur_ctx = ctx;
}

static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
	unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
	struct msm_drm_private *priv = gpu->dev->dev_private;
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	struct msm_ringbuffer *ring = submit->ring;
	unsigned int i;

	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);

	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
		rbmemptr_stats(ring, index, cpcycles_start));

	/*
	 * For PM4 the GMU register offsets are calculated from the base of the
	 * GPU registers so we need to add 0x1a800 to the register value on A630
	 * to get the right value from PM4.
	 */
	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
		rbmemptr_stats(ring, index, alwayson_start));

	/* Invalidate CCU depth and color */
	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(PC_CCU_INVALIDATE_DEPTH));

	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(PC_CCU_INVALIDATE_COLOR));

	/* Submit the commands */
	for (i = 0; i < submit->nr_cmds; i++) {
		switch (submit->cmd[i].type) {
		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
			break;
		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
			if (priv->lastctx == submit->queue->ctx)
				break;
			fallthrough;
		case MSM_SUBMIT_CMD_BUF:
			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
			OUT_RING(ring, submit->cmd[i].size);
			break;
		}
	}

	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
		rbmemptr_stats(ring, index, cpcycles_end));
	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
		rbmemptr_stats(ring, index, alwayson_end));

	/* Write the fence to the scratch register */
	OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1);
	OUT_RING(ring, submit->seqno);

	/*
	 * Execute a CACHE_FLUSH_TS event. This will ensure that the
	 * timestamp is written to the memory and then triggers the interrupt
	 */
	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
	OUT_RING(ring, CP_EVENT_WRITE_0_EVENT(CACHE_FLUSH_TS) |
		CP_EVENT_WRITE_0_IRQ);
	OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
	OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
	OUT_RING(ring, submit->seqno);

	trace_msm_gpu_submit_flush(submit,
		gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L,
			REG_A6XX_GMU_ALWAYS_ON_COUNTER_H));

	a6xx_flush(gpu, ring);
}

const struct adreno_reglist a630_hwcg[] = {
	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_SP1, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_SP2, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_SP3, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02022220},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP1, 0x02022220},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP2, 0x02022220},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP3, 0x02022220},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP1, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP2, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP3, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000f3cf},
	{REG_A6XX_RBBM_CLOCK_HYST_SP1, 0x0000f3cf},
	{REG_A6XX_RBBM_CLOCK_HYST_SP2, 0x0000f3cf},
	{REG_A6XX_RBBM_CLOCK_HYST_SP3, 0x0000f3cf},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP1, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP2, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP3, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP1, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP2, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP3, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP1, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP2, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP3, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP1, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP2, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP3, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST_TP1, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST_TP2, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST_TP3, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP1, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP2, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP3, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP1, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP2, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP3, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP1, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP2, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP3, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP1, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP2, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP3, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP1, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP2, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP3, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP1, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP2, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP3, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP1, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP2, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP3, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222},
	{REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004},
	{REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB1, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB2, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB3, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB1, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB2, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB3, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU1, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU2, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU3, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040f00},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU1, 0x00040f00},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU2, 0x00040f00},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU3, 0x00040f00},
	{REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x05022022},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555},
	{REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011},
	{REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044},
	{REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
	{REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222},
	{REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
	{REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
	{REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
	{REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002},
	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
	{},
};

const struct adreno_reglist a640_hwcg[] = {
	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040F00},
	{REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x05222022},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555},
	{REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011},
	{REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044},
	{REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
	{REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002},
	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
	{REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
	{REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_CNTL_TEX_FCHE, 0x00000222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TEX_FCHE, 0x00000111},
	{REG_A6XX_RBBM_CLOCK_HYST_TEX_FCHE, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004},
	{REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
	{REG_A6XX_RBBM_ISDB_CNT, 0x00000182},
	{REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000},
	{REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
	{},
};

const struct adreno_reglist a650_hwcg[] = {
	{REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
	{REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
	{REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
	{REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x02222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111},
	{REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111},
	{REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777},
	{REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777},
	{REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222},
	{REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220},
	{REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040F00},
	{REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x25222022},
	{REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555},
	{REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011},
	{REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044},
	{REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
	{REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002},
	{REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
	{REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
	{REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
	{REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
	{REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_CNTL_TEX_FCHE, 0x00000222},
	{REG_A6XX_RBBM_CLOCK_DELAY_TEX_FCHE, 0x00000111},
	{REG_A6XX_RBBM_CLOCK_HYST_TEX_FCHE, 0x00000777},
	{REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
	{REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004},
	{REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
	{REG_A6XX_RBBM_ISDB_CNT, 0x00000182},
	{REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000},
	{REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000},
	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
	{},
};

static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
	const struct adreno_reglist *reg;
	unsigned int i;
	u32 val, clock_cntl_on;

	if (!adreno_gpu->info->hwcg)
		return;

	if (adreno_is_a630(adreno_gpu))
		clock_cntl_on = 0x8aa8aa02;
	else
		clock_cntl_on = 0x8aa8aa82;

	val = gpu_read(gpu, REG_A6XX_RBBM_CLOCK_CNTL);

	/* Don't re-program the registers if they are already correct */
	if ((!state && !val) || (state && (val == clock_cntl_on)))
		return;

	/* Disable SP clock before programming HWCG registers */
	gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0);

	for (i = 0; (reg = &adreno_gpu->info->hwcg[i], reg->offset); i++)
		gpu_write(gpu, reg->offset, state ? reg->value : 0);

	/* Enable SP clock */
	gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1);

	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
}

static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	u32 lower_bit = 2;
	u32 amsbc = 0;
	u32 rgb565_predicator = 0;
	u32 uavflagprd_inv = 0;

	/* a618 is using the hw default values */
	if (adreno_is_a618(adreno_gpu))
		return;

	if (adreno_is_a640(adreno_gpu))
		amsbc = 1;

	if (adreno_is_a650(adreno_gpu)) {
		/* TODO: get ddr type from bootloader and use 2 for LPDDR4 */
		lower_bit = 3;
		amsbc = 1;
		rgb565_predicator = 1;
		uavflagprd_inv = 2;
	}

	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
		rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1);
	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1);
	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL,
		uavflagprd_inv >> 4 | lower_bit << 1);
	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, lower_bit << 21);
}

static int a6xx_cp_init(struct msm_gpu *gpu)
{
	struct msm_ringbuffer *ring = gpu->rb[0];

	OUT_PKT7(ring, CP_ME_INIT, 8);

	OUT_RING(ring, 0x0000002f);

	/* Enable multiple hardware contexts */
	OUT_RING(ring, 0x00000003);

	/* Enable error detection */
	OUT_RING(ring, 0x20000000);

	/* Don't enable header dump */
	OUT_RING(ring, 0x00000000);
	OUT_RING(ring, 0x00000000);

	/* No workarounds enabled */
	OUT_RING(ring, 0x00000000);

	/* Pad rest of the cmds with 0's */
	OUT_RING(ring, 0x00000000);
	OUT_RING(ring, 0x00000000);

	a6xx_flush(gpu, ring);
	return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
}

/*
 * Check that the microcode version is new enough to include several key
 * security fixes. Return true if the ucode is safe.
 */
static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
		struct drm_gem_object *obj)
{
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	u32 *buf = msm_gem_get_vaddr(obj);
	bool ret = false;

	if (IS_ERR(buf))
		return false;

	/*
	 * Targets up to a640 (a618, a630 and a640) need to check for a
	 * microcode version that is patched to support the whereami opcode or
	 * one that is new enough to include it by default.
	 */
	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
		adreno_is_a640(adreno_gpu)) {
		/*
		 * If the lowest nibble is 0xa that is an indication that this
		 * microcode has been patched. The actual version is in dword
		 * [3] but we only care about the patchlevel which is the lowest
		 * nibble of dword [3]
		 *
		 * Otherwise check that the firmware is greater than or equal
		 * to 1.90 which was the first version that had this fix built
		 * in
		 */
		if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) ||
			(buf[0] & 0xfff) >= 0x190) {
			a6xx_gpu->has_whereami = true;
			ret = true;
			goto out;
		}

		DRM_DEV_ERROR(&gpu->pdev->dev,
			"a630 SQE ucode is too old. Have version %x need at least %x\n",
			buf[0] & 0xfff, 0x190);
	}  else {
		/*
		 * a650 tier targets don't need whereami but still need to be
		 * equal to or newer than 0.95 for other security fixes
		 */
		if (adreno_is_a650(adreno_gpu)) {
			if ((buf[0] & 0xfff) >= 0x095) {
				ret = true;
				goto out;
			}

			DRM_DEV_ERROR(&gpu->pdev->dev,
				"a650 SQE ucode is too old. Have version %x need at least %x\n",
				buf[0] & 0xfff, 0x095);
		}

		/*
		 * When a660 is added those targets should return true here
		 * since those have all the critical security fixes built in
		 * from the start
		 */
	}
out:
	msm_gem_put_vaddr(obj);
	return ret;
}

static int a6xx_ucode_init(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

	if (!a6xx_gpu->sqe_bo) {
		a6xx_gpu->sqe_bo = adreno_fw_create_bo(gpu,
			adreno_gpu->fw[ADRENO_FW_SQE], &a6xx_gpu->sqe_iova);

		if (IS_ERR(a6xx_gpu->sqe_bo)) {
			int ret = PTR_ERR(a6xx_gpu->sqe_bo);

			a6xx_gpu->sqe_bo = NULL;
			DRM_DEV_ERROR(&gpu->pdev->dev,
				"Could not allocate SQE ucode: %d\n", ret);

			return ret;
		}

		msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
		if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) {
			msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
			drm_gem_object_put(a6xx_gpu->sqe_bo);

			a6xx_gpu->sqe_bo = NULL;
			return -EPERM;
		}
	}

	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
		REG_A6XX_CP_SQE_INSTR_BASE_HI, a6xx_gpu->sqe_iova);

	return 0;
}

static int a6xx_zap_shader_init(struct msm_gpu *gpu)
{
	static bool loaded;
	int ret;

	if (loaded)
		return 0;

	ret = adreno_zap_shader_load(gpu, GPU_PAS_ID);

	loaded = !ret;
	return ret;
}

#define A6XX_INT_MASK (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \
	  A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \
	  A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
	  A6XX_RBBM_INT_0_MASK_CP_IB2 | \
	  A6XX_RBBM_INT_0_MASK_CP_IB1 | \
	  A6XX_RBBM_INT_0_MASK_CP_RB | \
	  A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \
	  A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \
	  A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \
	  A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
	  A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)

static int a6xx_hw_init(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	int ret;

	/* Make sure the GMU keeps the GPU on while we set it up */
	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);

	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0);

	/*
	 * Disable the trusted memory range - we don't actually supported secure
	 * memory rendering at this point in time and we don't want to block off
	 * part of the virtual memory space.
	 */
	gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO,
		REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);

	/* Turn on 64 bit addressing for all blocks */
	gpu_write(gpu, REG_A6XX_CP_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_VSC_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_GRAS_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_RB_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_PC_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_HLSQ_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_VFD_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_VPC_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_UCHE_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_SP_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);

	/* enable hardware clockgating */
	a6xx_set_hwcg(gpu, true);

	/* VBIF/GBIF start*/
	if (adreno_is_a640(adreno_gpu) || adreno_is_a650(adreno_gpu)) {
		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620);
		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620);
		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620);
		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE3, 0x00071620);
		gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE3, 0x00071620);
		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x3);
	} else {
		gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3);
	}

	if (adreno_is_a630(adreno_gpu))
		gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);

	/* Make all blocks contribute to the GPU BUSY perf counter */
	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff);

	/* Disable L2 bypass in the UCHE */
	gpu_write(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX_LO, 0xffffffc0);
	gpu_write(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX_HI, 0x0001ffff);
	gpu_write(gpu, REG_A6XX_UCHE_TRAP_BASE_LO, 0xfffff000);
	gpu_write(gpu, REG_A6XX_UCHE_TRAP_BASE_HI, 0x0001ffff);
	gpu_write(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE_LO, 0xfffff000);
	gpu_write(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE_HI, 0x0001ffff);

	if (!adreno_is_a650(adreno_gpu)) {
		/* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */
		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO,
			REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000);

		gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX_LO,
			REG_A6XX_UCHE_GMEM_RANGE_MAX_HI,
			0x00100000 + adreno_gpu->gmem - 1);
	}

	gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804);
	gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4);

	if (adreno_is_a640(adreno_gpu) || adreno_is_a650(adreno_gpu))
		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
	else
		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0);
	gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);

	/* Setting the mem pool size */
	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128);

	/* Setting the primFifo thresholds default values */
	if (adreno_is_a650(adreno_gpu))
		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300000);
	else if (adreno_is_a640(adreno_gpu))
		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200000);
	else
		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, (0x300 << 11));

	/* Set the AHB default slave response to "ERROR" */
	gpu_write(gpu, REG_A6XX_CP_AHB_CNTL, 0x1);

	/* Turn on performance counters */
	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_CNTL, 0x1);

	/* Select CP0 to always count cycles */
	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);

	a6xx_set_ubwc_config(gpu);

	/* Enable fault detection */
	gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,
		(1 << 30) | 0x1fffff);

	gpu_write(gpu, REG_A6XX_UCHE_CLIENT_PF, 1);

	/* Set weights for bicubic filtering */
	if (adreno_is_a650(adreno_gpu)) {
		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_0, 0);
		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_1,
			0x3fe05ff4);
		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_2,
			0x3fa0ebee);
		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_3,
			0x3f5193ed);
		gpu_write(gpu, REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE_4,
			0x3f0243f0);
	}

	/* Protect registers from the CP */
	gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, 0x00000003);

	gpu_write(gpu, REG_A6XX_CP_PROTECT(0),
		A6XX_PROTECT_RDONLY(0x600, 0x51));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(1), A6XX_PROTECT_RW(0xae50, 0x2));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(2), A6XX_PROTECT_RW(0x9624, 0x13));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(3), A6XX_PROTECT_RW(0x8630, 0x8));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(4), A6XX_PROTECT_RW(0x9e70, 0x1));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(5), A6XX_PROTECT_RW(0x9e78, 0x187));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(6), A6XX_PROTECT_RW(0xf000, 0x810));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(7),
		A6XX_PROTECT_RDONLY(0xfc00, 0x3));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(8), A6XX_PROTECT_RW(0x50e, 0x0));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(9), A6XX_PROTECT_RDONLY(0x50f, 0x0));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(10), A6XX_PROTECT_RW(0x510, 0x0));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(11),
		A6XX_PROTECT_RDONLY(0x0, 0x4f9));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(12),
		A6XX_PROTECT_RDONLY(0x501, 0xa));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(13),
		A6XX_PROTECT_RDONLY(0x511, 0x44));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(14), A6XX_PROTECT_RW(0xe00, 0xe));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(15), A6XX_PROTECT_RW(0x8e00, 0x0));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(16), A6XX_PROTECT_RW(0x8e50, 0xf));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(17), A6XX_PROTECT_RW(0xbe02, 0x0));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(18),
		A6XX_PROTECT_RW(0xbe20, 0x11f3));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(19), A6XX_PROTECT_RW(0x800, 0x82));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(20), A6XX_PROTECT_RW(0x8a0, 0x8));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(21), A6XX_PROTECT_RW(0x8ab, 0x19));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(22), A6XX_PROTECT_RW(0x900, 0x4d));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(23), A6XX_PROTECT_RW(0x98d, 0x76));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(24),
			A6XX_PROTECT_RDONLY(0x980, 0x4));
	gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));

	/* Enable expanded apriv for targets that support it */
	if (gpu->hw_apriv) {
		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
			(1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1));
	}

	/* Enable interrupts */
	gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, A6XX_INT_MASK);

	ret = adreno_hw_init(gpu);
	if (ret)
		goto out;

	ret = a6xx_ucode_init(gpu);
	if (ret)
		goto out;

	/* Set the ringbuffer address */
	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
		gpu->rb[0]->iova);

	/* Targets that support extended APRIV can use the RPTR shadow from
	 * hardware but all the other ones need to disable the feature. Targets
	 * that support the WHERE_AM_I opcode can use that instead
	 */
	if (adreno_gpu->base.hw_apriv)
		gpu_write(gpu, REG_A6XX_CP_RB_CNTL, MSM_GPU_RB_CNTL_DEFAULT);
	else
		gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
			MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);

	/*
	 * Expanded APRIV and targets that support WHERE_AM_I both need a
	 * privileged buffer to store the RPTR shadow
	 */

	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) {
		if (!a6xx_gpu->shadow_bo) {
			a6xx_gpu->shadow = msm_gem_kernel_new_locked(gpu->dev,
				sizeof(u32) * gpu->nr_rings,
				MSM_BO_UNCACHED | MSM_BO_MAP_PRIV,
				gpu->aspace, &a6xx_gpu->shadow_bo,
				&a6xx_gpu->shadow_iova);

			if (IS_ERR(a6xx_gpu->shadow))
				return PTR_ERR(a6xx_gpu->shadow);
		}

		gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO,
			REG_A6XX_CP_RB_RPTR_ADDR_HI,
			shadowptr(a6xx_gpu, gpu->rb[0]));
	}

	/* Always come up on rb 0 */
	a6xx_gpu->cur_ring = gpu->rb[0];

	a6xx_gpu->cur_ctx = NULL;

	/* Enable the SQE_to start the CP engine */
	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);

	ret = a6xx_cp_init(gpu);
	if (ret)
		goto out;

	/*
	 * Try to load a zap shader into the secure world. If successful
	 * we can use the CP to switch out of secure mode. If not then we
	 * have no resource but to try to switch ourselves out manually. If we
	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
	 * be blocked and a permissions violation will soon follow.
	 */
	ret = a6xx_zap_shader_init(gpu);
	if (!ret) {
		OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1);
		OUT_RING(gpu->rb[0], 0x00000000);

		a6xx_flush(gpu, gpu->rb[0]);
		if (!a6xx_idle(gpu, gpu->rb[0]))
			return -EINVAL;
	} else if (ret == -ENODEV) {
		/*
		 * This device does not use zap shader (but print a warning
		 * just in case someone got their dt wrong.. hopefully they
		 * have a debug UART to realize the error of their ways...
		 * if you mess this up you are about to crash horribly)
		 */
		dev_warn_once(gpu->dev->dev,
			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
		ret = 0;
	} else {
		return ret;
	}

out:
	/*
	 * Tell the GMU that we are done touching the GPU and it can start power
	 * management
	 */
	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);

	if (a6xx_gpu->gmu.legacy) {
		/* Take the GMU out of its special boot mode */
		a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_BOOT_SLUMBER);
	}

	return ret;
}

static void a6xx_dump(struct msm_gpu *gpu)
{
	DRM_DEV_INFO(&gpu->pdev->dev, "status:   %08x\n",
			gpu_read(gpu, REG_A6XX_RBBM_STATUS));
	adreno_dump(gpu);
}

#define VBIF_RESET_ACK_TIMEOUT	100
#define VBIF_RESET_ACK_MASK	0x00f0

static void a6xx_recover(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	int i;

	adreno_dump_info(gpu);

	for (i = 0; i < 8; i++)
		DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i,
			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i)));

	if (hang_debug)
		a6xx_dump(gpu);

	/*
	 * Turn off keep alive that might have been enabled by the hang
	 * interrupt
	 */
	gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0);

	gpu->funcs->pm_suspend(gpu);
	gpu->funcs->pm_resume(gpu);

	msm_gpu_hw_init(gpu);
}

static int a6xx_fault_handler(void *arg, unsigned long iova, int flags)
{
	struct msm_gpu *gpu = arg;

	pr_warn_ratelimited("*** gpu fault: iova=%08lx, flags=%d (%u,%u,%u,%u)\n",
			iova, flags,
			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)),
			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)),
			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)),
			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)));

	return -EFAULT;
}

static void a6xx_cp_hw_err_irq(struct msm_gpu *gpu)
{
	u32 status = gpu_read(gpu, REG_A6XX_CP_INTERRUPT_STATUS);

	if (status & A6XX_CP_INT_CP_OPCODE_ERROR) {
		u32 val;

		gpu_write(gpu, REG_A6XX_CP_SQE_STAT_ADDR, 1);
		val = gpu_read(gpu, REG_A6XX_CP_SQE_STAT_DATA);
		dev_err_ratelimited(&gpu->pdev->dev,
			"CP | opcode error | possible opcode=0x%8.8X\n",
			val);
	}

	if (status & A6XX_CP_INT_CP_UCODE_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev,
			"CP ucode error interrupt\n");

	if (status & A6XX_CP_INT_CP_HW_FAULT_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev, "CP | HW fault | status=0x%8.8X\n",
			gpu_read(gpu, REG_A6XX_CP_HW_FAULT));

	if (status & A6XX_CP_INT_CP_REGISTER_PROTECTION_ERROR) {
		u32 val = gpu_read(gpu, REG_A6XX_CP_PROTECT_STATUS);

		dev_err_ratelimited(&gpu->pdev->dev,
			"CP | protected mode error | %s | addr=0x%8.8X | status=0x%8.8X\n",
			val & (1 << 20) ? "READ" : "WRITE",
			(val & 0x3ffff), val);
	}

	if (status & A6XX_CP_INT_CP_AHB_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev, "CP AHB error interrupt\n");

	if (status & A6XX_CP_INT_CP_VSD_PARITY_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev, "CP VSD decoder parity error\n");

	if (status & A6XX_CP_INT_CP_ILLEGAL_INSTR_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev, "CP illegal instruction error\n");

}

static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);

	/*
	 * Force the GPU to stay on until after we finish
	 * collecting information
	 */
	gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1);

	DRM_DEV_ERROR(&gpu->pdev->dev,
		"gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n",
		ring ? ring->id : -1, ring ? ring->seqno : 0,
		gpu_read(gpu, REG_A6XX_RBBM_STATUS),
		gpu_read(gpu, REG_A6XX_CP_RB_RPTR),
		gpu_read(gpu, REG_A6XX_CP_RB_WPTR),
		gpu_read64(gpu, REG_A6XX_CP_IB1_BASE, REG_A6XX_CP_IB1_BASE_HI),
		gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE),
		gpu_read64(gpu, REG_A6XX_CP_IB2_BASE, REG_A6XX_CP_IB2_BASE_HI),
		gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE));

	/* Turn off the hangcheck timer to keep it from bothering us */
	del_timer(&gpu->hangcheck_timer);

	kthread_queue_work(gpu->worker, &gpu->recover_work);
}

static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
{
	u32 status = gpu_read(gpu, REG_A6XX_RBBM_INT_0_STATUS);

	gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status);

	if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT)
		a6xx_fault_detect_irq(gpu);

	if (status & A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR)
		dev_err_ratelimited(&gpu->pdev->dev, "CP | AHB bus error\n");

	if (status & A6XX_RBBM_INT_0_MASK_CP_HW_ERROR)
		a6xx_cp_hw_err_irq(gpu);

	if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW)
		dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB ASYNC overflow\n");

	if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW)
		dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB bus overflow\n");

	if (status & A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS)
		dev_err_ratelimited(&gpu->pdev->dev, "UCHE | Out of bounds access\n");

	if (status & A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS)
		msm_gpu_retire(gpu);

	return IRQ_HANDLED;
}

static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask, u32 or)
{
	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
}

static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 value)
{
	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
}

static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
{
	llcc_slice_deactivate(a6xx_gpu->llc_slice);
	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
}

static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
{
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	u32 cntl1_regval = 0;

	if (IS_ERR(a6xx_gpu->llc_mmio))
		return;

	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);

		gpu_scid &= 0x1f;
		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
			       (gpu_scid << 15) | (gpu_scid << 20);
	}

	/*
	 * For targets with a MMU500, activate the slice but don't program the
	 * register.  The XBL will take care of that.
	 */
	if (!llcc_slice_activate(a6xx_gpu->htw_llc_slice)) {
		if (!a6xx_gpu->have_mmu500) {
			u32 gpuhtw_scid = llcc_get_slice_id(a6xx_gpu->htw_llc_slice);

			gpuhtw_scid &= 0x1f;
			cntl1_regval |= FIELD_PREP(GENMASK(29, 25), gpuhtw_scid);
		}
	}

	if (cntl1_regval) {
		/*
		 * Program the slice IDs for the various GPU blocks and GPU MMU
		 * pagetables
		 */
		if (a6xx_gpu->have_mmu500)
			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0),
				cntl1_regval);
		else {
			a6xx_llc_write(a6xx_gpu,
				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1, cntl1_regval);

			/*
			 * Program cacheability overrides to not allocate cache
			 * lines on a write miss
			 */
			a6xx_llc_rmw(a6xx_gpu,
				REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0, 0xF, 0x03);
		}
	}
}

static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
{
	llcc_slice_putd(a6xx_gpu->llc_slice);
	llcc_slice_putd(a6xx_gpu->htw_llc_slice);
}

static void a6xx_llc_slices_init(struct platform_device *pdev,
		struct a6xx_gpu *a6xx_gpu)
{
	struct device_node *phandle;

	/*
	 * There is a different programming path for targets with an mmu500
	 * attached, so detect if that is the case
	 */
	phandle = of_parse_phandle(pdev->dev.of_node, "iommus", 0);
	a6xx_gpu->have_mmu500 = (phandle &&
		of_device_is_compatible(phandle, "arm,mmu-500"));
	of_node_put(phandle);

	if (a6xx_gpu->have_mmu500)
		a6xx_gpu->llc_mmio = NULL;
	else
		a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");

	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);

	if (IS_ERR_OR_NULL(a6xx_gpu->llc_slice) && IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
		a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL);
}

static int a6xx_pm_resume(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	int ret;

	gpu->needs_hw_init = true;

	trace_msm_gpu_resume(0);

	ret = a6xx_gmu_resume(a6xx_gpu);
	if (ret)
		return ret;

	msm_gpu_resume_devfreq(gpu);

	a6xx_llc_activate(a6xx_gpu);

	return 0;
}

static int a6xx_pm_suspend(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	int i, ret;

	trace_msm_gpu_suspend(0);

	a6xx_llc_deactivate(a6xx_gpu);

	devfreq_suspend_device(gpu->devfreq.devfreq);

	ret = a6xx_gmu_stop(a6xx_gpu);
	if (ret)
		return ret;

	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami)
		for (i = 0; i < gpu->nr_rings; i++)
			a6xx_gpu->shadow[i] = 0;

	return 0;
}

static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	static DEFINE_MUTEX(perfcounter_oob);

	mutex_lock(&perfcounter_oob);

	/* Force the GPU power on so we can read this register */
	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);

	*value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
		REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);

	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
	mutex_unlock(&perfcounter_oob);
	return 0;
}

static struct msm_ringbuffer *a6xx_active_ring(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

	return a6xx_gpu->cur_ring;
}

static void a6xx_destroy(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

	if (a6xx_gpu->sqe_bo) {
		msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
		drm_gem_object_put(a6xx_gpu->sqe_bo);
	}

	if (a6xx_gpu->shadow_bo) {
		msm_gem_unpin_iova(a6xx_gpu->shadow_bo, gpu->aspace);
		drm_gem_object_put(a6xx_gpu->shadow_bo);
	}

	a6xx_llc_slices_destroy(a6xx_gpu);

	a6xx_gmu_remove(a6xx_gpu);

	adreno_gpu_cleanup(adreno_gpu);

	if (a6xx_gpu->opp_table)
		dev_pm_opp_put_supported_hw(a6xx_gpu->opp_table);

	kfree(a6xx_gpu);
}

static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	u64 busy_cycles, busy_time;


	/* Only read the gpu busy if the hardware is already active */
	if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
		return 0;

	busy_cycles = gmu_read64(&a6xx_gpu->gmu,
			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);

	busy_time = (busy_cycles - gpu->devfreq.busy_cycles) * 10;
	do_div(busy_time, 192);

	gpu->devfreq.busy_cycles = busy_cycles;

	pm_runtime_put(a6xx_gpu->gmu.dev);

	if (WARN_ON(busy_time > ~0LU))
		return ~0LU;

	return (unsigned long)busy_time;
}

static struct msm_gem_address_space *
a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
	struct iommu_domain *iommu;
	struct msm_mmu *mmu;
	struct msm_gem_address_space *aspace;
	u64 start, size;

	iommu = iommu_domain_alloc(&platform_bus_type);
	if (!iommu)
		return NULL;

	/*
	 * This allows GPU to set the bus attributes required to use system
	 * cache on behalf of the iommu page table walker.
	 */
	if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
		adreno_set_llc_attributes(iommu);

	mmu = msm_iommu_new(&pdev->dev, iommu);
	if (IS_ERR(mmu)) {
		iommu_domain_free(iommu);
		return ERR_CAST(mmu);
	}

	/*
	 * Use the aperture start or SZ_16M, whichever is greater. This will
	 * ensure that we align with the allocated pagetable range while still
	 * allowing room in the lower 32 bits for GMEM and whatnot
	 */
	start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
	size = iommu->geometry.aperture_end - start + 1;

	aspace = msm_gem_address_space_create(mmu, "gpu",
		start & GENMASK_ULL(48, 0), size);

	if (IS_ERR(aspace) && !IS_ERR(mmu))
		mmu->funcs->destroy(mmu);

	return aspace;
}

static struct msm_gem_address_space *
a6xx_create_private_address_space(struct msm_gpu *gpu)
{
	struct msm_mmu *mmu;

	mmu = msm_iommu_pagetable_create(gpu->aspace->mmu);

	if (IS_ERR(mmu))
		return ERR_CAST(mmu);

	return msm_gem_address_space_create(mmu,
		"gpu", 0x100000000ULL, 0x1ffffffffULL);
}

static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
{
	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);

	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami)
		return a6xx_gpu->shadow[ring->id];

	return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR);
}

static u32 a618_get_speed_bin(u32 fuse)
{
	if (fuse == 0)
		return 0;
	else if (fuse == 169)
		return 1;
	else if (fuse == 174)
		return 2;

	return UINT_MAX;
}

static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
{
	u32 val = UINT_MAX;

	if (revn == 618)
		val = a618_get_speed_bin(fuse);

	if (val == UINT_MAX) {
		DRM_DEV_ERROR(dev,
			"missing support for speed-bin: %u. Some OPPs may not be supported by hardware",
			fuse);
		return UINT_MAX;
	}

	return (1 << val);
}

static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
		u32 revn)
{
	struct opp_table *opp_table;
	u32 supp_hw = UINT_MAX;
	u16 speedbin;
	int ret;

	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
	/*
	 * -ENOENT means that the platform doesn't support speedbin which is
	 * fine
	 */
	if (ret == -ENOENT) {
		return 0;
	} else if (ret) {
		DRM_DEV_ERROR(dev,
			      "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
			      ret);
		goto done;
	}
	speedbin = le16_to_cpu(speedbin);

	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);

done:
	opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
	if (IS_ERR(opp_table))
		return PTR_ERR(opp_table);

	a6xx_gpu->opp_table = opp_table;
	return 0;
}

static const struct adreno_gpu_funcs funcs = {
	.base = {
		.get_param = adreno_get_param,
		.hw_init = a6xx_hw_init,
		.pm_suspend = a6xx_pm_suspend,
		.pm_resume = a6xx_pm_resume,
		.recover = a6xx_recover,
		.submit = a6xx_submit,
		.active_ring = a6xx_active_ring,
		.irq = a6xx_irq,
		.destroy = a6xx_destroy,
#if defined(CONFIG_DRM_MSM_GPU_STATE)
		.show = a6xx_show,
#endif
		.gpu_busy = a6xx_gpu_busy,
		.gpu_get_freq = a6xx_gmu_get_freq,
		.gpu_set_freq = a6xx_gmu_set_freq,
#if defined(CONFIG_DRM_MSM_GPU_STATE)
		.gpu_state_get = a6xx_gpu_state_get,
		.gpu_state_put = a6xx_gpu_state_put,
#endif
		.create_address_space = a6xx_create_address_space,
		.create_private_address_space = a6xx_create_private_address_space,
		.get_rptr = a6xx_get_rptr,
	},
	.get_timestamp = a6xx_get_timestamp,
};

struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
{
	struct msm_drm_private *priv = dev->dev_private;
	struct platform_device *pdev = priv->gpu_pdev;
	struct adreno_platform_config *config = pdev->dev.platform_data;
	const struct adreno_info *info;
	struct device_node *node;
	struct a6xx_gpu *a6xx_gpu;
	struct adreno_gpu *adreno_gpu;
	struct msm_gpu *gpu;
	int ret;

	a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL);
	if (!a6xx_gpu)
		return ERR_PTR(-ENOMEM);

	adreno_gpu = &a6xx_gpu->base;
	gpu = &adreno_gpu->base;

	adreno_gpu->registers = NULL;

	/*
	 * We need to know the platform type before calling into adreno_gpu_init
	 * so that the hw_apriv flag can be correctly set. Snoop into the info
	 * and grab the revision number
	 */
	info = adreno_info(config->rev);

	if (info && info->revn == 650)
		adreno_gpu->base.hw_apriv = true;

	a6xx_llc_slices_init(pdev, a6xx_gpu);

	ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
	if (ret) {
		a6xx_destroy(&(a6xx_gpu->base.base));
		return ERR_PTR(ret);
	}

	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
	if (ret) {
		a6xx_destroy(&(a6xx_gpu->base.base));
		return ERR_PTR(ret);
	}

	/* Check if there is a GMU phandle and set it up */
	node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0);

	/* FIXME: How do we gracefully handle this? */
	BUG_ON(!node);

	ret = a6xx_gmu_init(a6xx_gpu, node);
	if (ret) {
		a6xx_destroy(&(a6xx_gpu->base.base));
		return ERR_PTR(ret);
	}

	if (gpu->aspace)
		msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu,
				a6xx_fault_handler);

	return gpu;
}