summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
blob: 096be97ce9f961583d407afaa83320bfeadc74fb (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 <linux/clk.h>
#include <linux/interconnect.h>
#include <linux/pm_domain.h>
#include <linux/pm_opp.h>
#include <soc/qcom/cmd-db.h>
#include <drm/drm_gem.h>

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

static void a6xx_gmu_fault(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	struct drm_device *dev = gpu->dev;
	struct msm_drm_private *priv = dev->dev_private;

	/* FIXME: add a banner here */
	gmu->hung = true;

	/* Turn off the hangcheck timer while we are resetting */
	del_timer(&gpu->hangcheck_timer);

	/* Queue the GPU handler because we need to treat this as a recovery */
	queue_work(priv->wq, &gpu->recover_work);
}

static irqreturn_t a6xx_gmu_irq(int irq, void *data)
{
	struct a6xx_gmu *gmu = data;
	u32 status;

	status = gmu_read(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_STATUS);
	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, status);

	if (status & A6XX_GMU_AO_HOST_INTERRUPT_STATUS_WDOG_BITE) {
		dev_err_ratelimited(gmu->dev, "GMU watchdog expired\n");

		a6xx_gmu_fault(gmu);
	}

	if (status &  A6XX_GMU_AO_HOST_INTERRUPT_STATUS_HOST_AHB_BUS_ERROR)
		dev_err_ratelimited(gmu->dev, "GMU AHB bus error\n");

	if (status & A6XX_GMU_AO_HOST_INTERRUPT_STATUS_FENCE_ERR)
		dev_err_ratelimited(gmu->dev, "GMU fence error: 0x%x\n",
			gmu_read(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS));

	return IRQ_HANDLED;
}

static irqreturn_t a6xx_hfi_irq(int irq, void *data)
{
	struct a6xx_gmu *gmu = data;
	u32 status;

	status = gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO);
	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, status);

	if (status & A6XX_GMU_GMU2HOST_INTR_INFO_CM3_FAULT) {
		dev_err_ratelimited(gmu->dev, "GMU firmware fault\n");

		a6xx_gmu_fault(gmu);
	}

	return IRQ_HANDLED;
}

bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu)
{
	u32 val;

	/* This can be called from gpu state code so make sure GMU is valid */
	if (!gmu->initialized)
		return false;

	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);

	return !(val &
		(A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SPTPRAC_GDSC_POWER_OFF |
		A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SP_CLOCK_OFF));
}

/* Check to see if the GX rail is still powered */
bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
{
	u32 val;

	/* This can be called from gpu state code so make sure GMU is valid */
	if (!gmu->initialized)
		return false;

	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);

	return !(val &
		(A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF |
		A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_CLK_OFF));
}

static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	int ret;

	gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);

	gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
		((3 & 0xf) << 28) | index);

	/*
	 * Send an invalid index as a vote for the bus bandwidth and let the
	 * firmware decide on the right vote
	 */
	gmu_write(gmu, REG_A6XX_GMU_DCVS_BW_SETTING, 0xff);

	/* Set and clear the OOB for DCVS to trigger the GMU */
	a6xx_gmu_set_oob(gmu, GMU_OOB_DCVS_SET);
	a6xx_gmu_clear_oob(gmu, GMU_OOB_DCVS_SET);

	ret = gmu_read(gmu, REG_A6XX_GMU_DCVS_RETURN);
	if (ret)
		dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);

	/*
	 * Eventually we will want to scale the path vote with the frequency but
	 * for now leave it at max so that the performance is nominal.
	 */
	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
}

void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
{
	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;
	u32 perf_index = 0;

	if (freq == gmu->freq)
		return;

	for (perf_index = 0; perf_index < gmu->nr_gpu_freqs - 1; perf_index++)
		if (freq == gmu->gpu_freqs[perf_index])
			break;

	gmu->current_perf_index = perf_index;
	gmu->freq = gmu->gpu_freqs[perf_index];

	/*
	 * This can get called from devfreq while the hardware is idle. Don't
	 * bring up the power if it isn't already active
	 */
	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
		return;

	if (gmu->legacy)
		__a6xx_gmu_set_freq(gmu, perf_index);
	else
		a6xx_hfi_set_freq(gmu, perf_index);

	pm_runtime_put(gmu->dev);
}

unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
{
	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;

	return  gmu->freq;
}

static bool a6xx_gmu_check_idle_level(struct a6xx_gmu *gmu)
{
	u32 val;
	int local = gmu->idle_level;

	/* SPTP and IFPC both report as IFPC */
	if (gmu->idle_level == GMU_IDLE_STATE_SPTP)
		local = GMU_IDLE_STATE_IFPC;

	val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE);

	if (val == local) {
		if (gmu->idle_level != GMU_IDLE_STATE_IFPC ||
			!a6xx_gmu_gx_is_on(gmu))
			return true;
	}

	return false;
}

/* Wait for the GMU to get to its most idle state */
int a6xx_gmu_wait_for_idle(struct a6xx_gmu *gmu)
{
	return spin_until(a6xx_gmu_check_idle_level(gmu));
}

static int a6xx_gmu_start(struct a6xx_gmu *gmu)
{
	int ret;
	u32 val;

	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);

	/* Set the log wptr index
	 * note: downstream saves the value in poweroff and restores it here
	 */
	gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_RESP, 0);

	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0);

	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val,
		val == 0xbabeface, 100, 10000);

	if (ret)
		DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n");

	return ret;
}

static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu)
{
	u32 val;
	int ret;

	gmu_write(gmu, REG_A6XX_GMU_HFI_CTRL_INIT, 1);

	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_HFI_CTRL_STATUS, val,
		val & 1, 100, 10000);
	if (ret)
		DRM_DEV_ERROR(gmu->dev, "Unable to start the HFI queues\n");

	return ret;
}

/* Trigger a OOB (out of band) request to the GMU */
int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
{
	int ret;
	u32 val;
	int request, ack;
	const char *name;

	switch (state) {
	case GMU_OOB_GPU_SET:
		if (gmu->legacy) {
			request = GMU_OOB_GPU_SET_REQUEST;
			ack = GMU_OOB_GPU_SET_ACK;
		} else {
			request = GMU_OOB_GPU_SET_REQUEST_NEW;
			ack = GMU_OOB_GPU_SET_ACK_NEW;
		}
		name = "GPU_SET";
		break;
	case GMU_OOB_BOOT_SLUMBER:
		request = GMU_OOB_BOOT_SLUMBER_REQUEST;
		ack = GMU_OOB_BOOT_SLUMBER_ACK;
		name = "BOOT_SLUMBER";
		break;
	case GMU_OOB_DCVS_SET:
		request = GMU_OOB_DCVS_REQUEST;
		ack = GMU_OOB_DCVS_ACK;
		name = "GPU_DCVS";
		break;
	default:
		return -EINVAL;
	}

	/* Trigger the equested OOB operation */
	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << request);

	/* Wait for the acknowledge interrupt */
	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val,
		val & (1 << ack), 100, 10000);

	if (ret)
		DRM_DEV_ERROR(gmu->dev,
			"Timeout waiting for GMU OOB set %s: 0x%x\n",
				name,
				gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO));

	/* Clear the acknowledge interrupt */
	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, 1 << ack);

	return ret;
}

/* Clear a pending OOB state in the GMU */
void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
{
	if (!gmu->legacy) {
		WARN_ON(state != GMU_OOB_GPU_SET);
		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
			1 << GMU_OOB_GPU_SET_CLEAR_NEW);
		return;
	}

	switch (state) {
	case GMU_OOB_GPU_SET:
		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
			1 << GMU_OOB_GPU_SET_CLEAR);
		break;
	case GMU_OOB_BOOT_SLUMBER:
		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
			1 << GMU_OOB_BOOT_SLUMBER_CLEAR);
		break;
	case GMU_OOB_DCVS_SET:
		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
			1 << GMU_OOB_DCVS_CLEAR);
		break;
	}
}

/* Enable CPU control of SPTP power power collapse */
static int a6xx_sptprac_enable(struct a6xx_gmu *gmu)
{
	int ret;
	u32 val;

	if (!gmu->legacy)
		return 0;

	gmu_write(gmu, REG_A6XX_GMU_GX_SPTPRAC_POWER_CONTROL, 0x778000);

	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS, val,
		(val & 0x38) == 0x28, 1, 100);

	if (ret) {
		DRM_DEV_ERROR(gmu->dev, "Unable to power on SPTPRAC: 0x%x\n",
			gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS));
	}

	return 0;
}

/* Disable CPU control of SPTP power power collapse */
static void a6xx_sptprac_disable(struct a6xx_gmu *gmu)
{
	u32 val;
	int ret;

	if (!gmu->legacy)
		return;

	/* Make sure retention is on */
	gmu_rmw(gmu, REG_A6XX_GPU_CC_GX_GDSCR, 0, (1 << 11));

	gmu_write(gmu, REG_A6XX_GMU_GX_SPTPRAC_POWER_CONTROL, 0x778001);

	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS, val,
		(val & 0x04), 100, 10000);

	if (ret)
		DRM_DEV_ERROR(gmu->dev, "failed to power off SPTPRAC: 0x%x\n",
			gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS));
}

/* Let the GMU know we are starting a boot sequence */
static int a6xx_gmu_gfx_rail_on(struct a6xx_gmu *gmu)
{
	u32 vote;

	/* Let the GMU know we are getting ready for boot */
	gmu_write(gmu, REG_A6XX_GMU_BOOT_SLUMBER_OPTION, 0);

	/* Choose the "default" power level as the highest available */
	vote = gmu->gx_arc_votes[gmu->nr_gpu_freqs - 1];

	gmu_write(gmu, REG_A6XX_GMU_GX_VOTE_IDX, vote & 0xff);
	gmu_write(gmu, REG_A6XX_GMU_MX_VOTE_IDX, (vote >> 8) & 0xff);

	/* Let the GMU know the boot sequence has started */
	return a6xx_gmu_set_oob(gmu, GMU_OOB_BOOT_SLUMBER);
}

/* Let the GMU know that we are about to go into slumber */
static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu)
{
	int ret;

	/* Disable the power counter so the GMU isn't busy */
	gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0);

	/* Disable SPTP_PC if the CPU is responsible for it */
	if (gmu->idle_level < GMU_IDLE_STATE_SPTP)
		a6xx_sptprac_disable(gmu);

	if (!gmu->legacy) {
		ret = a6xx_hfi_send_prep_slumber(gmu);
		goto out;
	}

	/* Tell the GMU to get ready to slumber */
	gmu_write(gmu, REG_A6XX_GMU_BOOT_SLUMBER_OPTION, 1);

	ret = a6xx_gmu_set_oob(gmu, GMU_OOB_BOOT_SLUMBER);
	a6xx_gmu_clear_oob(gmu, GMU_OOB_BOOT_SLUMBER);

	if (!ret) {
		/* Check to see if the GMU really did slumber */
		if (gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE)
			!= 0x0f) {
			DRM_DEV_ERROR(gmu->dev, "The GMU did not go into slumber\n");
			ret = -ETIMEDOUT;
		}
	}

out:
	/* Put fence into allow mode */
	gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0);
	return ret;
}

static int a6xx_rpmh_start(struct a6xx_gmu *gmu)
{
	int ret;
	u32 val;

	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1 << 1);
	/* Wait for the register to finish posting */
	wmb();

	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val,
		val & (1 << 1), 100, 10000);
	if (ret) {
		DRM_DEV_ERROR(gmu->dev, "Unable to power on the GPU RSC\n");
		return ret;
	}

	ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_SEQ_BUSY_DRV0, val,
		!val, 100, 10000);

	if (ret) {
		DRM_DEV_ERROR(gmu->dev, "GPU RSC sequence stuck while waking up the GPU\n");
		return ret;
	}

	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0);

	/* Set up CX GMU counter 0 to count busy ticks */
	gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000);
	gmu_rmw(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, 0xff, 0x20);

	/* Enable the power counter */
	gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1);
	return 0;
}

static void a6xx_rpmh_stop(struct a6xx_gmu *gmu)
{
	int ret;
	u32 val;

	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1);

	ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0,
		val, val & (1 << 16), 100, 10000);
	if (ret)
		DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n");

	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0);
}

static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value)
{
	return msm_writel(value, ptr + (offset << 2));
}

static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
		const char *name);

static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct platform_device *pdev = to_platform_device(gmu->dev);
	void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc");
	void __iomem *seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq");
	uint32_t pdc_address_offset;

	if (!pdcptr || !seqptr)
		goto err;

	if (adreno_is_a618(adreno_gpu) || adreno_is_a640(adreno_gpu))
		pdc_address_offset = 0x30090;
	else if (adreno_is_a650(adreno_gpu))
		pdc_address_offset = 0x300a0;
	else
		pdc_address_offset = 0x30080;

	/* Disable SDE clock gating */
	gmu_write_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, BIT(24));

	/* Setup RSC PDC handshake for sleep and wakeup */
	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_SLAVE_ID_DRV0, 1);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 2, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 2, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_DATA + 4, 0x80000000);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_HIDDEN_TCS_CMD0_ADDR + 4, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_OVERRIDE_START_ADDR, 0);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_SEQ_START_ADDR, 0x4520);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_MATCH_VALUE_LO, 0x4510);
	gmu_write_rscc(gmu, REG_A6XX_RSCC_PDC_MATCH_VALUE_HI, 0x4514);

	/* Load RSC sequencer uCode for sleep and wakeup */
	if (adreno_is_a650(adreno_gpu)) {
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0, 0xeaaae5a0);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 1, 0xe1a1ebab);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 2, 0xa2e0a581);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 3, 0xecac82e2);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 4, 0x0020edad);
	} else {
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0, 0xa7a506a0);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 1, 0xa1e6a6e7);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 2, 0xa2e081e1);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 3, 0xe9a982e2);
		gmu_write_rscc(gmu, REG_A6XX_RSCC_SEQ_MEM_0_DRV0 + 4, 0x0020e8a8);
	}

	/* Load PDC sequencer uCode for power up and power down sequence */
	pdc_write(seqptr, REG_A6XX_PDC_GPU_SEQ_MEM_0, 0xfebea1e1);
	pdc_write(seqptr, REG_A6XX_PDC_GPU_SEQ_MEM_0 + 1, 0xa5a4a3a2);
	pdc_write(seqptr, REG_A6XX_PDC_GPU_SEQ_MEM_0 + 2, 0x8382a6e0);
	pdc_write(seqptr, REG_A6XX_PDC_GPU_SEQ_MEM_0 + 3, 0xbce3e284);
	pdc_write(seqptr, REG_A6XX_PDC_GPU_SEQ_MEM_0 + 4, 0x002081fc);

	/* Set TCS commands used by PDC sequence for low power modes */
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD_ENABLE_BANK, 7);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD_WAIT_FOR_CMPL_BANK, 0);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CONTROL, 0);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR, 0x30010);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA, 1);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 4, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 4, 0x30000);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 4, 0x0);

	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 8, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, pdc_address_offset);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 8, 0x0);

	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_ENABLE_BANK, 7);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_WAIT_FOR_CMPL_BANK, 0);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CONTROL, 0);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR, 0x30010);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA, 2);

	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000);
	if (adreno_is_a618(adreno_gpu) || adreno_is_a650(adreno_gpu))
		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2);
	else
		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 8, 0x10108);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, pdc_address_offset);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 8, 0x3);

	/* Setup GPU PDC */
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_SEQ_START_ADDR, 0);
	pdc_write(pdcptr, REG_A6XX_PDC_GPU_ENABLE_PDC, 0x80000001);

	/* ensure no writes happen before the uCode is fully written */
	wmb();

err:
	if (!IS_ERR_OR_NULL(pdcptr))
		iounmap(pdcptr);
	if (!IS_ERR_OR_NULL(seqptr))
		iounmap(seqptr);
}

/*
 * The lowest 16 bits of this value are the number of XO clock cycles for main
 * hysteresis which is set at 0x1680 cycles (300 us).  The higher 16 bits are
 * for the shorter hysteresis that happens after main - this is 0xa (.5 us)
 */

#define GMU_PWR_COL_HYST 0x000a1680

/* Set up the idle state for the GMU */
static void a6xx_gmu_power_config(struct a6xx_gmu *gmu)
{
	/* Disable GMU WB/RB buffer */
	gmu_write(gmu, REG_A6XX_GMU_SYS_BUS_CONFIG, 0x1);
	gmu_write(gmu, REG_A6XX_GMU_ICACHE_CONFIG, 0x1);
	gmu_write(gmu, REG_A6XX_GMU_DCACHE_CONFIG, 0x1);

	gmu_write(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0x9c40400);

	switch (gmu->idle_level) {
	case GMU_IDLE_STATE_IFPC:
		gmu_write(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_HYST,
			GMU_PWR_COL_HYST);
		gmu_rmw(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0,
			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_IFPC_ENABLE |
			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_HM_POWER_COLLAPSE_ENABLE);
		/* Fall through */
	case GMU_IDLE_STATE_SPTP:
		gmu_write(gmu, REG_A6XX_GMU_PWR_COL_SPTPRAC_HYST,
			GMU_PWR_COL_HYST);
		gmu_rmw(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0,
			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_IFPC_ENABLE |
			A6XX_GMU_PWR_COL_INTER_FRAME_CTRL_SPTPRAC_POWER_CONTROL_ENABLE);
	}

	/* Enable RPMh GPU client */
	gmu_rmw(gmu, REG_A6XX_GMU_RPMH_CTRL, 0,
		A6XX_GMU_RPMH_CTRL_RPMH_INTERFACE_ENABLE |
		A6XX_GMU_RPMH_CTRL_LLC_VOTE_ENABLE |
		A6XX_GMU_RPMH_CTRL_DDR_VOTE_ENABLE |
		A6XX_GMU_RPMH_CTRL_MX_VOTE_ENABLE |
		A6XX_GMU_RPMH_CTRL_CX_VOTE_ENABLE |
		A6XX_GMU_RPMH_CTRL_GFX_VOTE_ENABLE);
}

struct block_header {
	u32 addr;
	u32 size;
	u32 type;
	u32 value;
	u32 data[];
};

/* this should be a general kernel helper */
static int in_range(u32 addr, u32 start, u32 size)
{
	return addr >= start && addr < start + size;
}

static bool fw_block_mem(struct a6xx_gmu_bo *bo, const struct block_header *blk)
{
	if (!in_range(blk->addr, bo->iova, bo->size))
		return false;

	memcpy(bo->virt + blk->addr - bo->iova, blk->data, blk->size);
	return true;
}

static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	const struct firmware *fw_image = adreno_gpu->fw[ADRENO_FW_GMU];
	const struct block_header *blk;
	u32 reg_offset;

	u32 itcm_base = 0x00000000;
	u32 dtcm_base = 0x00040000;

	if (adreno_is_a650(adreno_gpu))
		dtcm_base = 0x10004000;

	if (gmu->legacy) {
		/* Sanity check the size of the firmware that was loaded */
		if (fw_image->size > 0x8000) {
			DRM_DEV_ERROR(gmu->dev,
				"GMU firmware is bigger than the available region\n");
			return -EINVAL;
		}

		gmu_write_bulk(gmu, REG_A6XX_GMU_CM3_ITCM_START,
			       (u32*) fw_image->data, fw_image->size);
		return 0;
	}


	for (blk = (const struct block_header *) fw_image->data;
	     (const u8*) blk < fw_image->data + fw_image->size;
	     blk = (const struct block_header *) &blk->data[blk->size >> 2]) {
		if (blk->size == 0)
			continue;

		if (in_range(blk->addr, itcm_base, SZ_16K)) {
			reg_offset = (blk->addr - itcm_base) >> 2;
			gmu_write_bulk(gmu,
				REG_A6XX_GMU_CM3_ITCM_START + reg_offset,
				blk->data, blk->size);
		} else if (in_range(blk->addr, dtcm_base, SZ_16K)) {
			reg_offset = (blk->addr - dtcm_base) >> 2;
			gmu_write_bulk(gmu,
				REG_A6XX_GMU_CM3_DTCM_START + reg_offset,
				blk->data, blk->size);
		} else if (!fw_block_mem(&gmu->icache, blk) &&
			   !fw_block_mem(&gmu->dcache, blk) &&
			   !fw_block_mem(&gmu->dummy, blk)) {
			DRM_DEV_ERROR(gmu->dev,
				"failed to match fw block (addr=%.8x size=%d data[0]=%.8x)\n",
				blk->addr, blk->size, blk->data[0]);
		}
	}

	return 0;
}

static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
{
	static bool rpmh_init;
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	int ret;
	u32 chipid;

	if (adreno_is_a650(adreno_gpu))
		gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1);

	if (state == GMU_WARM_BOOT) {
		ret = a6xx_rpmh_start(gmu);
		if (ret)
			return ret;
	} else {
		if (WARN(!adreno_gpu->fw[ADRENO_FW_GMU],
			"GMU firmware is not loaded\n"))
			return -ENOENT;

		/* Turn on register retention */
		gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1);

		/* We only need to load the RPMh microcode once */
		if (!rpmh_init) {
			a6xx_gmu_rpmh_init(gmu);
			rpmh_init = true;
		} else {
			ret = a6xx_rpmh_start(gmu);
			if (ret)
				return ret;
		}

		ret = a6xx_gmu_fw_load(gmu);
		if (ret)
			return ret;
	}

	gmu_write(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, 0);
	gmu_write(gmu, REG_A6XX_GMU_CM3_BOOT_CONFIG, 0x02);

	/* Write the iova of the HFI table */
	gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_ADDR, gmu->hfi.iova);
	gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_INFO, 1);

	gmu_write(gmu, REG_A6XX_GMU_AHB_FENCE_RANGE_0,
		(1 << 31) | (0xa << 18) | (0xa0));

	chipid = adreno_gpu->rev.core << 24;
	chipid |= adreno_gpu->rev.major << 16;
	chipid |= adreno_gpu->rev.minor << 12;
	chipid |= adreno_gpu->rev.patchid << 8;

	gmu_write(gmu, REG_A6XX_GMU_HFI_SFR_ADDR, chipid);

	gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_MSG,
		  gmu->log.iova | (gmu->log.size / SZ_4K - 1));

	/* Set up the lowest idle level on the GMU */
	a6xx_gmu_power_config(gmu);

	ret = a6xx_gmu_start(gmu);
	if (ret)
		return ret;

	if (gmu->legacy) {
		ret = a6xx_gmu_gfx_rail_on(gmu);
		if (ret)
			return ret;
	}

	/* Enable SPTP_PC if the CPU is responsible for it */
	if (gmu->idle_level < GMU_IDLE_STATE_SPTP) {
		ret = a6xx_sptprac_enable(gmu);
		if (ret)
			return ret;
	}

	ret = a6xx_gmu_hfi_start(gmu);
	if (ret)
		return ret;

	/* FIXME: Do we need this wmb() here? */
	wmb();

	return 0;
}

#define A6XX_HFI_IRQ_MASK \
	(A6XX_GMU_GMU2HOST_INTR_INFO_CM3_FAULT)

#define A6XX_GMU_IRQ_MASK \
	(A6XX_GMU_AO_HOST_INTERRUPT_STATUS_WDOG_BITE | \
	 A6XX_GMU_AO_HOST_INTERRUPT_STATUS_HOST_AHB_BUS_ERROR | \
	 A6XX_GMU_AO_HOST_INTERRUPT_STATUS_FENCE_ERR)

static void a6xx_gmu_irq_disable(struct a6xx_gmu *gmu)
{
	disable_irq(gmu->gmu_irq);
	disable_irq(gmu->hfi_irq);

	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_MASK, ~0);
	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~0);
}

static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu)
{
	u32 val;

	/* Make sure there are no outstanding RPMh votes */
	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS0_DRV0_STATUS, val,
		(val & 1), 100, 10000);
	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS1_DRV0_STATUS, val,
		(val & 1), 100, 10000);
	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS2_DRV0_STATUS, val,
		(val & 1), 100, 10000);
	gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS, val,
		(val & 1), 100, 1000);
}

/* Force the GMU off in case it isn't responsive */
static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
{
	/* Flush all the queues */
	a6xx_hfi_stop(gmu);

	/* Stop the interrupts */
	a6xx_gmu_irq_disable(gmu);

	/* Force off SPTP in case the GMU is managing it */
	a6xx_sptprac_disable(gmu);

	/* Make sure there are no outstanding RPMh votes */
	a6xx_gmu_rpmh_off(gmu);
}

int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
{
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
	int status, ret;

	if (WARN(!gmu->initialized, "The GMU is not set up yet\n"))
		return 0;

	gmu->hung = false;

	/* Turn on the resources */
	pm_runtime_get_sync(gmu->dev);

	/* Use a known rate to bring up the GMU */
	clk_set_rate(gmu->core_clk, 200000000);
	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
	if (ret) {
		pm_runtime_put(gmu->dev);
		return ret;
	}

	/* Set the bus quota to a reasonable value for boot */
	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072));

	/* Enable the GMU interrupt */
	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0);
	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_MASK, ~A6XX_GMU_IRQ_MASK);
	enable_irq(gmu->gmu_irq);

	/* Check to see if we are doing a cold or warm boot */
	status = gmu_read(gmu, REG_A6XX_GMU_GENERAL_7) == 1 ?
		GMU_WARM_BOOT : GMU_COLD_BOOT;

	/*
	 * Warm boot path does not work on newer GPUs
	 * Presumably this is because icache/dcache regions must be restored
	 */
	if (!gmu->legacy)
		status = GMU_COLD_BOOT;

	ret = a6xx_gmu_fw_start(gmu, status);
	if (ret)
		goto out;

	ret = a6xx_hfi_start(gmu, status);
	if (ret)
		goto out;

	/*
	 * Turn on the GMU firmware fault interrupt after we know the boot
	 * sequence is successful
	 */
	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, ~0);
	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK);
	enable_irq(gmu->hfi_irq);

	/* Set the GPU to the current freq */
	if (gmu->legacy)
		__a6xx_gmu_set_freq(gmu, gmu->current_perf_index);
	else
		a6xx_hfi_set_freq(gmu, gmu->current_perf_index);

	/*
	 * "enable" the GX power domain which won't actually do anything but it
	 * will make sure that the refcounting is correct in case we need to
	 * bring down the GX after a GMU failure
	 */
	if (!IS_ERR_OR_NULL(gmu->gxpd))
		pm_runtime_get(gmu->gxpd);

out:
	/* On failure, shut down the GMU to leave it in a good state */
	if (ret) {
		disable_irq(gmu->gmu_irq);
		a6xx_rpmh_stop(gmu);
		pm_runtime_put(gmu->dev);
	}

	return ret;
}

bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
{
	u32 reg;

	if (!gmu->initialized)
		return true;

	reg = gmu_read(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS);

	if (reg &  A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB)
		return false;

	return true;
}

#define GBIF_CLIENT_HALT_MASK             BIT(0)
#define GBIF_ARB_HALT_MASK                BIT(1)

static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
{
	struct msm_gpu *gpu = &adreno_gpu->base;

	if (!a6xx_has_gbif(adreno_gpu)) {
		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
								0xf) == 0xf);
		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);

		return;
	}

	/* Halt new client requests on GBIF */
	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);

	/* Halt all AXI requests on GBIF */
	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);

	/* The GBIF halt needs to be explicitly cleared */
	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
}

/* Gracefully try to shut down the GMU and by extension the GPU */
static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	u32 val;

	/*
	 * The GMU may still be in slumber unless the GPU started so check and
	 * skip putting it back into slumber if so
	 */
	val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE);

	if (val != 0xf) {
		int ret = a6xx_gmu_wait_for_idle(gmu);

		/* If the GMU isn't responding assume it is hung */
		if (ret) {
			a6xx_gmu_force_off(gmu);
			return;
		}

		a6xx_bus_clear_pending_transactions(adreno_gpu);

		/* tell the GMU we want to slumber */
		a6xx_gmu_notify_slumber(gmu);

		ret = gmu_poll_timeout(gmu,
			REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val,
			!(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB),
			100, 10000);

		/*
		 * Let the user know we failed to slumber but don't worry too
		 * much because we are powering down anyway
		 */

		if (ret)
			DRM_DEV_ERROR(gmu->dev,
				"Unable to slumber GMU: status = 0%x/0%x\n",
				gmu_read(gmu,
					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
				gmu_read(gmu,
					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2));
	}

	/* Turn off HFI */
	a6xx_hfi_stop(gmu);

	/* Stop the interrupts and mask the hardware */
	a6xx_gmu_irq_disable(gmu);

	/* Tell RPMh to power off the GPU */
	a6xx_rpmh_stop(gmu);
}


int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
{
	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
	struct msm_gpu *gpu = &a6xx_gpu->base.base;

	if (!pm_runtime_active(gmu->dev))
		return 0;

	/*
	 * Force the GMU off if we detected a hang, otherwise try to shut it
	 * down gracefully
	 */
	if (gmu->hung)
		a6xx_gmu_force_off(gmu);
	else
		a6xx_gmu_shutdown(gmu);

	/* Remove the bus vote */
	icc_set_bw(gpu->icc_path, 0, 0);

	/*
	 * Make sure the GX domain is off before turning off the GMU (CX)
	 * domain. Usually the GMU does this but only if the shutdown sequence
	 * was successful
	 */
	if (!IS_ERR_OR_NULL(gmu->gxpd))
		pm_runtime_put_sync(gmu->gxpd);

	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);

	pm_runtime_put_sync(gmu->dev);

	return 0;
}

static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu)
{
	msm_gem_kernel_put(gmu->hfi.obj, gmu->aspace, false);
	msm_gem_kernel_put(gmu->debug.obj, gmu->aspace, false);
	msm_gem_kernel_put(gmu->icache.obj, gmu->aspace, false);
	msm_gem_kernel_put(gmu->dcache.obj, gmu->aspace, false);
	msm_gem_kernel_put(gmu->dummy.obj, gmu->aspace, false);
	msm_gem_kernel_put(gmu->log.obj, gmu->aspace, false);

	gmu->aspace->mmu->funcs->detach(gmu->aspace->mmu);
	msm_gem_address_space_put(gmu->aspace);
}

static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo,
		size_t size, u64 iova)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct drm_device *dev = a6xx_gpu->base.base.dev;
	uint32_t flags = MSM_BO_WC;
	u64 range_start, range_end;
	int ret;

	size = PAGE_ALIGN(size);
	if (!iova) {
		/* no fixed address - use GMU's uncached range */
		range_start = 0x60000000 + PAGE_SIZE; /* skip dummy page */
		range_end = 0x80000000;
	} else {
		/* range for fixed address */
		range_start = iova;
		range_end = iova + size;
		/* use IOMMU_PRIV for icache/dcache */
		flags |= MSM_BO_MAP_PRIV;
	}

	bo->obj = msm_gem_new(dev, size, flags);
	if (IS_ERR(bo->obj))
		return PTR_ERR(bo->obj);

	ret = msm_gem_get_and_pin_iova_range(bo->obj, gmu->aspace, &bo->iova,
		range_start >> PAGE_SHIFT, range_end >> PAGE_SHIFT);
	if (ret) {
		drm_gem_object_put(bo->obj);
		return ret;
	}

	bo->virt = msm_gem_get_vaddr(bo->obj);
	bo->size = size;

	return 0;
}

static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
{
	struct iommu_domain *domain;
	struct msm_mmu *mmu;

	domain = iommu_domain_alloc(&platform_bus_type);
	if (!domain)
		return -ENODEV;

	mmu = msm_iommu_new(gmu->dev, domain);
	gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x7fffffff);
	if (IS_ERR(gmu->aspace)) {
		iommu_domain_free(domain);
		return PTR_ERR(gmu->aspace);
	}

	return 0;
}

/* Return the 'arc-level' for the given frequency */
static unsigned int a6xx_gmu_get_arc_level(struct device *dev,
					   unsigned long freq)
{
	struct dev_pm_opp *opp;
	unsigned int val;

	if (!freq)
		return 0;

	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
	if (IS_ERR(opp))
		return 0;

	val = dev_pm_opp_get_level(opp);

	dev_pm_opp_put(opp);

	return val;
}

static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes,
		unsigned long *freqs, int freqs_count, const char *id)
{
	int i, j;
	const u16 *pri, *sec;
	size_t pri_count, sec_count;

	pri = cmd_db_read_aux_data(id, &pri_count);
	if (IS_ERR(pri))
		return PTR_ERR(pri);
	/*
	 * The data comes back as an array of unsigned shorts so adjust the
	 * count accordingly
	 */
	pri_count >>= 1;
	if (!pri_count)
		return -EINVAL;

	sec = cmd_db_read_aux_data("mx.lvl", &sec_count);
	if (IS_ERR(sec))
		return PTR_ERR(sec);

	sec_count >>= 1;
	if (!sec_count)
		return -EINVAL;

	/* Construct a vote for each frequency */
	for (i = 0; i < freqs_count; i++) {
		u8 pindex = 0, sindex = 0;
		unsigned int level = a6xx_gmu_get_arc_level(dev, freqs[i]);

		/* Get the primary index that matches the arc level */
		for (j = 0; j < pri_count; j++) {
			if (pri[j] >= level) {
				pindex = j;
				break;
			}
		}

		if (j == pri_count) {
			DRM_DEV_ERROR(dev,
				      "Level %u not found in the RPMh list\n",
				      level);
			DRM_DEV_ERROR(dev, "Available levels:\n");
			for (j = 0; j < pri_count; j++)
				DRM_DEV_ERROR(dev, "  %u\n", pri[j]);

			return -EINVAL;
		}

		/*
		 * Look for a level in in the secondary list that matches. If
		 * nothing fits, use the maximum non zero vote
		 */

		for (j = 0; j < sec_count; j++) {
			if (sec[j] >= level) {
				sindex = j;
				break;
			} else if (sec[j]) {
				sindex = j;
			}
		}

		/* Construct the vote */
		votes[i] = ((pri[pindex] & 0xffff) << 16) |
			(sindex << 8) | pindex;
	}

	return 0;
}

/*
 * The GMU votes with the RPMh for itself and on behalf of the GPU but we need
 * to construct the list of votes on the CPU and send it over. Query the RPMh
 * voltage levels and build the votes
 */

static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;
	int ret;

	/* Build the GX votes */
	ret = a6xx_gmu_rpmh_arc_votes_init(&gpu->pdev->dev, gmu->gx_arc_votes,
		gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl");

	/* Build the CX votes */
	ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes,
		gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl");

	return ret;
}

static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs,
		u32 size)
{
	int count = dev_pm_opp_get_opp_count(dev);
	struct dev_pm_opp *opp;
	int i, index = 0;
	unsigned long freq = 1;

	/*
	 * The OPP table doesn't contain the "off" frequency level so we need to
	 * add 1 to the table size to account for it
	 */

	if (WARN(count + 1 > size,
		"The GMU frequency table is being truncated\n"))
		count = size - 1;

	/* Set the "off" frequency */
	freqs[index++] = 0;

	for (i = 0; i < count; i++) {
		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
		if (IS_ERR(opp))
			break;

		dev_pm_opp_put(opp);
		freqs[index++] = freq++;
	}

	return index;
}

static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
{
	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct msm_gpu *gpu = &adreno_gpu->base;

	int ret = 0;

	/*
	 * The GMU handles its own frequency switching so build a list of
	 * available frequencies to send during initialization
	 */
	ret = dev_pm_opp_of_add_table(gmu->dev);
	if (ret) {
		DRM_DEV_ERROR(gmu->dev, "Unable to set the OPP table for the GMU\n");
		return ret;
	}

	gmu->nr_gmu_freqs = a6xx_gmu_build_freq_table(gmu->dev,
		gmu->gmu_freqs, ARRAY_SIZE(gmu->gmu_freqs));

	/*
	 * The GMU also handles GPU frequency switching so build a list
	 * from the GPU OPP table
	 */
	gmu->nr_gpu_freqs = a6xx_gmu_build_freq_table(&gpu->pdev->dev,
		gmu->gpu_freqs, ARRAY_SIZE(gmu->gpu_freqs));

	gmu->current_perf_index = gmu->nr_gpu_freqs - 1;

	/* Build the list of RPMh votes that we'll send to the GMU */
	return a6xx_gmu_rpmh_votes_init(gmu);
}

static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu)
{
	int ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks);

	if (ret < 1)
		return ret;

	gmu->nr_clocks = ret;

	gmu->core_clk = msm_clk_bulk_get_clock(gmu->clocks,
		gmu->nr_clocks, "gmu");

	return 0;
}

static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
		const char *name)
{
	void __iomem *ret;
	struct resource *res = platform_get_resource_byname(pdev,
			IORESOURCE_MEM, name);

	if (!res) {
		DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name);
		return ERR_PTR(-EINVAL);
	}

	ret = ioremap(res->start, resource_size(res));
	if (!ret) {
		DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name);
		return ERR_PTR(-EINVAL);
	}

	return ret;
}

static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev,
		const char *name, irq_handler_t handler)
{
	int irq, ret;

	irq = platform_get_irq_byname(pdev, name);

	ret = request_irq(irq, handler, IRQF_TRIGGER_HIGH, name, gmu);
	if (ret) {
		DRM_DEV_ERROR(&pdev->dev, "Unable to get interrupt %s %d\n",
			      name, ret);
		return ret;
	}

	disable_irq(irq);

	return irq;
}

void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
{
	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
	struct platform_device *pdev = to_platform_device(gmu->dev);

	if (!gmu->initialized)
		return;

	pm_runtime_force_suspend(gmu->dev);

	if (!IS_ERR_OR_NULL(gmu->gxpd)) {
		pm_runtime_disable(gmu->gxpd);
		dev_pm_domain_detach(gmu->gxpd, false);
	}

	iounmap(gmu->mmio);
	if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc"))
		iounmap(gmu->rscc);
	gmu->mmio = NULL;
	gmu->rscc = NULL;

	a6xx_gmu_memory_free(gmu);

	free_irq(gmu->gmu_irq, gmu);
	free_irq(gmu->hfi_irq, gmu);

	/* Drop reference taken in of_find_device_by_node */
	put_device(gmu->dev);

	gmu->initialized = false;
}

int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
{
	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
	struct platform_device *pdev = of_find_device_by_node(node);
	int ret;

	if (!pdev)
		return -ENODEV;

	gmu->dev = &pdev->dev;

	of_dma_configure(gmu->dev, node, true);

	/* Fow now, don't do anything fancy until we get our feet under us */
	gmu->idle_level = GMU_IDLE_STATE_ACTIVE;

	pm_runtime_enable(gmu->dev);

	/* Get the list of clocks */
	ret = a6xx_gmu_clocks_probe(gmu);
	if (ret)
		goto err_put_device;

	ret = a6xx_gmu_memory_probe(gmu);
	if (ret)
		goto err_put_device;

	/* Allocate memory for the GMU dummy page */
	ret = a6xx_gmu_memory_alloc(gmu, &gmu->dummy, SZ_4K, 0x60000000);
	if (ret)
		goto err_memory;

	if (adreno_is_a650(adreno_gpu)) {
		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
			SZ_16M - SZ_16K, 0x04000);
		if (ret)
			goto err_memory;
	} else if (adreno_is_a640(adreno_gpu)) {
		ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache,
			SZ_256K - SZ_16K, 0x04000);
		if (ret)
			goto err_memory;

		ret = a6xx_gmu_memory_alloc(gmu, &gmu->dcache,
			SZ_256K - SZ_16K, 0x44000);
		if (ret)
			goto err_memory;
	} else {
		/* HFI v1, has sptprac */
		gmu->legacy = true;

		/* Allocate memory for the GMU debug region */
		ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_16K, 0);
		if (ret)
			goto err_memory;
	}

	/* Allocate memory for for the HFI queues */
	ret = a6xx_gmu_memory_alloc(gmu, &gmu->hfi, SZ_16K, 0);
	if (ret)
		goto err_memory;

	/* Allocate memory for the GMU log region */
	ret = a6xx_gmu_memory_alloc(gmu, &gmu->log, SZ_4K, 0);
	if (ret)
		goto err_memory;

	/* Map the GMU registers */
	gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu");
	if (IS_ERR(gmu->mmio)) {
		ret = PTR_ERR(gmu->mmio);
		goto err_memory;
	}

	if (adreno_is_a650(adreno_gpu)) {
		gmu->rscc = a6xx_gmu_get_mmio(pdev, "rscc");
		if (IS_ERR(gmu->rscc))
			goto err_mmio;
	} else {
		gmu->rscc = gmu->mmio + 0x23000;
	}

	/* Get the HFI and GMU interrupts */
	gmu->hfi_irq = a6xx_gmu_get_irq(gmu, pdev, "hfi", a6xx_hfi_irq);
	gmu->gmu_irq = a6xx_gmu_get_irq(gmu, pdev, "gmu", a6xx_gmu_irq);

	if (gmu->hfi_irq < 0 || gmu->gmu_irq < 0)
		goto err_mmio;

	/*
	 * Get a link to the GX power domain to reset the GPU in case of GMU
	 * crash
	 */
	gmu->gxpd = dev_pm_domain_attach_by_name(gmu->dev, "gx");

	/* Get the power levels for the GMU and GPU */
	a6xx_gmu_pwrlevels_probe(gmu);

	/* Set up the HFI queues */
	a6xx_hfi_init(gmu);

	gmu->initialized = true;

	return 0;

err_mmio:
	iounmap(gmu->mmio);
	if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc"))
		iounmap(gmu->rscc);
	free_irq(gmu->gmu_irq, gmu);
	free_irq(gmu->hfi_irq, gmu);

	ret = -ENODEV;

err_memory:
	a6xx_gmu_memory_free(gmu);
err_put_device:
	/* Drop reference taken in of_find_device_by_node */
	put_device(gmu->dev);

	return ret;
}