summaryrefslogtreecommitdiffstats
path: root/drivers/perf/arm-cmn.c
blob: 8b98ca9666d014d5a3ffaf7b4271db6d6dc152c6 (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
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2016-2020 Arm Limited
// CMN-600 Coherent Mesh Network PMU driver

#include <linux/acpi.h>
#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/sort.h>

/* Common register stuff */
#define CMN_NODE_INFO			0x0000
#define CMN_NI_NODE_TYPE		GENMASK_ULL(15, 0)
#define CMN_NI_NODE_ID			GENMASK_ULL(31, 16)
#define CMN_NI_LOGICAL_ID		GENMASK_ULL(47, 32)

#define CMN_NODEID_DEVID(reg)		((reg) & 3)
#define CMN_NODEID_PID(reg)		(((reg) >> 2) & 1)
#define CMN_NODEID_X(reg, bits)		((reg) >> (3 + (bits)))
#define CMN_NODEID_Y(reg, bits)		(((reg) >> 3) & ((1U << (bits)) - 1))

#define CMN_CHILD_INFO			0x0080
#define CMN_CI_CHILD_COUNT		GENMASK_ULL(15, 0)
#define CMN_CI_CHILD_PTR_OFFSET		GENMASK_ULL(31, 16)

#define CMN_CHILD_NODE_ADDR		GENMASK(27, 0)
#define CMN_CHILD_NODE_EXTERNAL		BIT(31)

#define CMN_MAX_DIMENSION		8
#define CMN_MAX_XPS			(CMN_MAX_DIMENSION * CMN_MAX_DIMENSION)
#define CMN_MAX_DTMS			CMN_MAX_XPS

/* The CFG node has one other useful purpose */
#define CMN_CFGM_PERIPH_ID_2		0x0010
#define CMN_CFGM_PID2_REVISION		GENMASK(7, 4)

/* PMU registers occupy the 3rd 4KB page of each node's 16KB space */
#define CMN_PMU_OFFSET			0x2000

/* For most nodes, this is all there is */
#define CMN_PMU_EVENT_SEL		0x000
#define CMN_PMU_EVENTn_ID_SHIFT(n)	((n) * 8)

/* DTMs live in the PMU space of XP registers */
#define CMN_DTM_WPn(n)			(0x1A0 + (n) * 0x18)
#define CMN_DTM_WPn_CONFIG(n)		(CMN_DTM_WPn(n) + 0x00)
#define CMN_DTM_WPn_CONFIG_WP_COMBINE	BIT(6)
#define CMN_DTM_WPn_CONFIG_WP_EXCLUSIVE	BIT(5)
#define CMN_DTM_WPn_CONFIG_WP_GRP	BIT(4)
#define CMN_DTM_WPn_CONFIG_WP_CHN_SEL	GENMASK_ULL(3, 1)
#define CMN_DTM_WPn_CONFIG_WP_DEV_SEL	BIT(0)
#define CMN_DTM_WPn_VAL(n)		(CMN_DTM_WPn(n) + 0x08)
#define CMN_DTM_WPn_MASK(n)		(CMN_DTM_WPn(n) + 0x10)

#define CMN_DTM_PMU_CONFIG		0x210
#define CMN__PMEVCNT0_INPUT_SEL		GENMASK_ULL(37, 32)
#define CMN__PMEVCNT0_INPUT_SEL_WP	0x00
#define CMN__PMEVCNT0_INPUT_SEL_XP	0x04
#define CMN__PMEVCNT0_INPUT_SEL_DEV	0x10
#define CMN__PMEVCNT0_GLOBAL_NUM	GENMASK_ULL(18, 16)
#define CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(n)	((n) * 4)
#define CMN__PMEVCNT_PAIRED(n)		BIT(4 + (n))
#define CMN__PMEVCNT23_COMBINED		BIT(2)
#define CMN__PMEVCNT01_COMBINED		BIT(1)
#define CMN_DTM_PMU_CONFIG_PMU_EN	BIT(0)

#define CMN_DTM_PMEVCNT			0x220

#define CMN_DTM_PMEVCNTSR		0x240

#define CMN_DTM_NUM_COUNTERS		4

/* The DTC node is where the magic happens */
#define CMN_DT_DTC_CTL			0x0a00
#define CMN_DT_DTC_CTL_DT_EN		BIT(0)

/* DTC counters are paired in 64-bit registers on a 16-byte stride. Yuck */
#define _CMN_DT_CNT_REG(n)		((((n) / 2) * 4 + (n) % 2) * 4)
#define CMN_DT_PMEVCNT(n)		(CMN_PMU_OFFSET + _CMN_DT_CNT_REG(n))
#define CMN_DT_PMCCNTR			(CMN_PMU_OFFSET + 0x40)

#define CMN_DT_PMEVCNTSR(n)		(CMN_PMU_OFFSET + 0x50 + _CMN_DT_CNT_REG(n))
#define CMN_DT_PMCCNTRSR		(CMN_PMU_OFFSET + 0x90)

#define CMN_DT_PMCR			(CMN_PMU_OFFSET + 0x100)
#define CMN_DT_PMCR_PMU_EN		BIT(0)
#define CMN_DT_PMCR_CNTR_RST		BIT(5)
#define CMN_DT_PMCR_OVFL_INTR_EN	BIT(6)

#define CMN_DT_PMOVSR			(CMN_PMU_OFFSET + 0x118)
#define CMN_DT_PMOVSR_CLR		(CMN_PMU_OFFSET + 0x120)

#define CMN_DT_PMSSR			(CMN_PMU_OFFSET + 0x128)
#define CMN_DT_PMSSR_SS_STATUS(n)	BIT(n)

#define CMN_DT_PMSRR			(CMN_PMU_OFFSET + 0x130)
#define CMN_DT_PMSRR_SS_REQ		BIT(0)

#define CMN_DT_NUM_COUNTERS		8
#define CMN_MAX_DTCS			4

/*
 * Even in the worst case a DTC counter can't wrap in fewer than 2^42 cycles,
 * so throwing away one bit to make overflow handling easy is no big deal.
 */
#define CMN_COUNTER_INIT		0x80000000
/* Similarly for the 40-bit cycle counter */
#define CMN_CC_INIT			0x8000000000ULL


/* Event attributes */
#define CMN_CONFIG_TYPE			GENMASK_ULL(15, 0)
#define CMN_CONFIG_EVENTID		GENMASK_ULL(23, 16)
#define CMN_CONFIG_OCCUPID		GENMASK_ULL(27, 24)
#define CMN_CONFIG_BYNODEID		BIT_ULL(31)
#define CMN_CONFIG_NODEID		GENMASK_ULL(47, 32)

#define CMN_EVENT_TYPE(event)		FIELD_GET(CMN_CONFIG_TYPE, (event)->attr.config)
#define CMN_EVENT_EVENTID(event)	FIELD_GET(CMN_CONFIG_EVENTID, (event)->attr.config)
#define CMN_EVENT_OCCUPID(event)	FIELD_GET(CMN_CONFIG_OCCUPID, (event)->attr.config)
#define CMN_EVENT_BYNODEID(event)	FIELD_GET(CMN_CONFIG_BYNODEID, (event)->attr.config)
#define CMN_EVENT_NODEID(event)		FIELD_GET(CMN_CONFIG_NODEID, (event)->attr.config)

#define CMN_CONFIG_WP_COMBINE		GENMASK_ULL(27, 24)
#define CMN_CONFIG_WP_DEV_SEL		BIT_ULL(48)
#define CMN_CONFIG_WP_CHN_SEL		GENMASK_ULL(50, 49)
#define CMN_CONFIG_WP_GRP		BIT_ULL(52)
#define CMN_CONFIG_WP_EXCLUSIVE		BIT_ULL(53)
#define CMN_CONFIG1_WP_VAL		GENMASK_ULL(63, 0)
#define CMN_CONFIG2_WP_MASK		GENMASK_ULL(63, 0)

#define CMN_EVENT_WP_COMBINE(event)	FIELD_GET(CMN_CONFIG_WP_COMBINE, (event)->attr.config)
#define CMN_EVENT_WP_DEV_SEL(event)	FIELD_GET(CMN_CONFIG_WP_DEV_SEL, (event)->attr.config)
#define CMN_EVENT_WP_CHN_SEL(event)	FIELD_GET(CMN_CONFIG_WP_CHN_SEL, (event)->attr.config)
#define CMN_EVENT_WP_GRP(event)		FIELD_GET(CMN_CONFIG_WP_GRP, (event)->attr.config)
#define CMN_EVENT_WP_EXCLUSIVE(event)	FIELD_GET(CMN_CONFIG_WP_EXCLUSIVE, (event)->attr.config)
#define CMN_EVENT_WP_VAL(event)		FIELD_GET(CMN_CONFIG1_WP_VAL, (event)->attr.config1)
#define CMN_EVENT_WP_MASK(event)	FIELD_GET(CMN_CONFIG2_WP_MASK, (event)->attr.config2)

/* Made-up event IDs for watchpoint direction */
#define CMN_WP_UP			0
#define CMN_WP_DOWN			2


/* r0px probably don't exist in silicon, thankfully */
enum cmn_revision {
	CMN600_R1P0,
	CMN600_R1P1,
	CMN600_R1P2,
	CMN600_R1P3,
	CMN600_R2P0,
	CMN600_R3P0,
};

enum cmn_node_type {
	CMN_TYPE_INVALID,
	CMN_TYPE_DVM,
	CMN_TYPE_CFG,
	CMN_TYPE_DTC,
	CMN_TYPE_HNI,
	CMN_TYPE_HNF,
	CMN_TYPE_XP,
	CMN_TYPE_SBSX,
	CMN_TYPE_RNI = 0xa,
	CMN_TYPE_RND = 0xd,
	CMN_TYPE_RNSAM = 0xf,
	CMN_TYPE_CXRA = 0x100,
	CMN_TYPE_CXHA = 0x101,
	CMN_TYPE_CXLA = 0x102,
	/* Not a real node type */
	CMN_TYPE_WP = 0x7770
};

struct arm_cmn_node {
	void __iomem *pmu_base;
	u16 id, logid;
	enum cmn_node_type type;

	int dtm;
	union {
		/* DN/HN-F/CXHA */
		struct {
			u8 occupid_val;
			u8 occupid_count;
		};
		/* XP */
		int dtc;
	};
	union {
		u8 event[4];
		__le32 event_sel;
	};
};

struct arm_cmn_dtm {
	void __iomem *base;
	u32 pmu_config_low;
	union {
		u8 input_sel[4];
		__le32 pmu_config_high;
	};
	s8 wp_event[4];
};

struct arm_cmn_dtc {
	void __iomem *base;
	int irq;
	int irq_friend;
	bool cc_active;

	struct perf_event *counters[CMN_DT_NUM_COUNTERS];
	struct perf_event *cycles;
};

#define CMN_STATE_DISABLED	BIT(0)
#define CMN_STATE_TXN		BIT(1)

struct arm_cmn {
	struct device *dev;
	void __iomem *base;

	enum cmn_revision rev;
	u8 mesh_x;
	u8 mesh_y;
	u16 num_xps;
	u16 num_dns;
	struct arm_cmn_node *xps;
	struct arm_cmn_node *dns;

	struct arm_cmn_dtm *dtms;
	struct arm_cmn_dtc *dtc;
	unsigned int num_dtcs;

	int cpu;
	struct hlist_node cpuhp_node;

	unsigned int state;
	struct pmu pmu;
};

#define to_cmn(p)	container_of(p, struct arm_cmn, pmu)

static int arm_cmn_hp_state;

struct arm_cmn_nodeid {
	u8 x;
	u8 y;
	u8 port;
	u8 dev;
};

static int arm_cmn_xyidbits(const struct arm_cmn *cmn)
{
	int dim = max(cmn->mesh_x, cmn->mesh_y);

	return dim > 4 ? 3 : 2;
}

static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn *cmn, u16 id)
{
	struct arm_cmn_nodeid nid;
	int bits = arm_cmn_xyidbits(cmn);

	nid.x = CMN_NODEID_X(id, bits);
	nid.y = CMN_NODEID_Y(id, bits);
	nid.port = CMN_NODEID_PID(id);
	nid.dev = CMN_NODEID_DEVID(id);

	return nid;
}

static struct arm_cmn_node *arm_cmn_node_to_xp(const struct arm_cmn *cmn,
					       const struct arm_cmn_node *dn)
{
	struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
	int xp_idx = cmn->mesh_x * nid.y + nid.x;

	return cmn->xps + xp_idx;
}
static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
					 enum cmn_node_type type)
{
	struct arm_cmn_node *dn;

	for (dn = cmn->dns; dn->type; dn++)
		if (dn->type == type)
			return dn;
	return NULL;
}

struct arm_cmn_hw_event {
	struct arm_cmn_node *dn;
	u64 dtm_idx[2];
	unsigned int dtc_idx;
	u8 dtcs_used;
	u8 num_dns;
};

#define for_each_hw_dn(hw, dn, i) \
	for (i = 0, dn = hw->dn; i < hw->num_dns; i++, dn++)

static struct arm_cmn_hw_event *to_cmn_hw(struct perf_event *event)
{
	BUILD_BUG_ON(sizeof(struct arm_cmn_hw_event) > offsetof(struct hw_perf_event, target));
	return (struct arm_cmn_hw_event *)&event->hw;
}

static void arm_cmn_set_index(u64 x[], unsigned int pos, unsigned int val)
{
	x[pos / 32] |= (u64)val << ((pos % 32) * 2);
}

static unsigned int arm_cmn_get_index(u64 x[], unsigned int pos)
{
	return (x[pos / 32] >> ((pos % 32) * 2)) & 3;
}

struct arm_cmn_event_attr {
	struct device_attribute attr;
	enum cmn_node_type type;
	u8 eventid;
	u8 occupid;
};

struct arm_cmn_format_attr {
	struct device_attribute attr;
	u64 field;
	int config;
};

#define CMN_EVENT_ATTR(_name, _type, _eventid, _occupid)		\
	(&((struct arm_cmn_event_attr[]) {{				\
		.attr = __ATTR(_name, 0444, arm_cmn_event_show, NULL),	\
		.type = _type,						\
		.eventid = _eventid,					\
		.occupid = _occupid,					\
	}})[0].attr.attr)

static bool arm_cmn_is_occup_event(enum cmn_node_type type, unsigned int id)
{
	return (type == CMN_TYPE_DVM && id == 0x05) ||
	       (type == CMN_TYPE_HNF && id == 0x0f);
}

static ssize_t arm_cmn_event_show(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	struct arm_cmn_event_attr *eattr;

	eattr = container_of(attr, typeof(*eattr), attr);

	if (eattr->type == CMN_TYPE_DTC)
		return sysfs_emit(buf, "type=0x%x\n", eattr->type);

	if (eattr->type == CMN_TYPE_WP)
		return sysfs_emit(buf,
				  "type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
				  eattr->type, eattr->eventid);

	if (arm_cmn_is_occup_event(eattr->type, eattr->eventid))
		return sysfs_emit(buf, "type=0x%x,eventid=0x%x,occupid=0x%x\n",
				  eattr->type, eattr->eventid, eattr->occupid);

	return sysfs_emit(buf, "type=0x%x,eventid=0x%x\n", eattr->type,
			  eattr->eventid);
}

static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
					     struct attribute *attr,
					     int unused)
{
	struct device *dev = kobj_to_dev(kobj);
	struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));
	struct arm_cmn_event_attr *eattr;
	enum cmn_node_type type;

	eattr = container_of(attr, typeof(*eattr), attr.attr);
	type = eattr->type;

	/* Watchpoints aren't nodes */
	if (type == CMN_TYPE_WP)
		type = CMN_TYPE_XP;

	/* Revision-specific differences */
	if (cmn->rev < CMN600_R1P2) {
		if (type == CMN_TYPE_HNF && eattr->eventid == 0x1b)
			return 0;
	}

	if (!arm_cmn_node(cmn, type))
		return 0;

	return attr->mode;
}

#define _CMN_EVENT_DVM(_name, _event, _occup)			\
	CMN_EVENT_ATTR(dn_##_name, CMN_TYPE_DVM, _event, _occup)
#define CMN_EVENT_DTC(_name)					\
	CMN_EVENT_ATTR(dtc_##_name, CMN_TYPE_DTC, 0, 0)
#define _CMN_EVENT_HNF(_name, _event, _occup)			\
	CMN_EVENT_ATTR(hnf_##_name, CMN_TYPE_HNF, _event, _occup)
#define CMN_EVENT_HNI(_name, _event)				\
	CMN_EVENT_ATTR(hni_##_name, CMN_TYPE_HNI, _event, 0)
#define __CMN_EVENT_XP(_name, _event)				\
	CMN_EVENT_ATTR(mxp_##_name, CMN_TYPE_XP, _event, 0)
#define CMN_EVENT_SBSX(_name, _event)				\
	CMN_EVENT_ATTR(sbsx_##_name, CMN_TYPE_SBSX, _event, 0)
#define CMN_EVENT_RNID(_name, _event)				\
	CMN_EVENT_ATTR(rnid_##_name, CMN_TYPE_RNI, _event, 0)

#define CMN_EVENT_DVM(_name, _event)				\
	_CMN_EVENT_DVM(_name, _event, 0)
#define CMN_EVENT_HNF(_name, _event)				\
	_CMN_EVENT_HNF(_name, _event, 0)
#define _CMN_EVENT_XP(_name, _event)				\
	__CMN_EVENT_XP(e_##_name, (_event) | (0 << 2)),		\
	__CMN_EVENT_XP(w_##_name, (_event) | (1 << 2)),		\
	__CMN_EVENT_XP(n_##_name, (_event) | (2 << 2)),		\
	__CMN_EVENT_XP(s_##_name, (_event) | (3 << 2)),		\
	__CMN_EVENT_XP(p0_##_name, (_event) | (4 << 2)),	\
	__CMN_EVENT_XP(p1_##_name, (_event) | (5 << 2))

/* Good thing there are only 3 fundamental XP events... */
#define CMN_EVENT_XP(_name, _event)				\
	_CMN_EVENT_XP(req_##_name, (_event) | (0 << 5)),	\
	_CMN_EVENT_XP(rsp_##_name, (_event) | (1 << 5)),	\
	_CMN_EVENT_XP(snp_##_name, (_event) | (2 << 5)),	\
	_CMN_EVENT_XP(dat_##_name, (_event) | (3 << 5))


static struct attribute *arm_cmn_event_attrs[] = {
	CMN_EVENT_DTC(cycles),

	/*
	 * DVM node events conflict with HN-I events in the equivalent PMU
	 * slot, but our lazy short-cut of using the DTM counter index for
	 * the PMU index as well happens to avoid that by construction.
	 */
	CMN_EVENT_DVM(rxreq_dvmop,	0x01),
	CMN_EVENT_DVM(rxreq_dvmsync,	0x02),
	CMN_EVENT_DVM(rxreq_dvmop_vmid_filtered, 0x03),
	CMN_EVENT_DVM(rxreq_retried,	0x04),
	_CMN_EVENT_DVM(rxreq_trk_occupancy_all, 0x05, 0),
	_CMN_EVENT_DVM(rxreq_trk_occupancy_dvmop, 0x05, 1),
	_CMN_EVENT_DVM(rxreq_trk_occupancy_dvmsync, 0x05, 2),

	CMN_EVENT_HNF(cache_miss,	0x01),
	CMN_EVENT_HNF(slc_sf_cache_access, 0x02),
	CMN_EVENT_HNF(cache_fill,	0x03),
	CMN_EVENT_HNF(pocq_retry,	0x04),
	CMN_EVENT_HNF(pocq_reqs_recvd,	0x05),
	CMN_EVENT_HNF(sf_hit,		0x06),
	CMN_EVENT_HNF(sf_evictions,	0x07),
	CMN_EVENT_HNF(dir_snoops_sent,	0x08),
	CMN_EVENT_HNF(brd_snoops_sent,	0x09),
	CMN_EVENT_HNF(slc_eviction,	0x0a),
	CMN_EVENT_HNF(slc_fill_invalid_way, 0x0b),
	CMN_EVENT_HNF(mc_retries,	0x0c),
	CMN_EVENT_HNF(mc_reqs,		0x0d),
	CMN_EVENT_HNF(qos_hh_retry,	0x0e),
	_CMN_EVENT_HNF(qos_pocq_occupancy_all, 0x0f, 0),
	_CMN_EVENT_HNF(qos_pocq_occupancy_read, 0x0f, 1),
	_CMN_EVENT_HNF(qos_pocq_occupancy_write, 0x0f, 2),
	_CMN_EVENT_HNF(qos_pocq_occupancy_atomic, 0x0f, 3),
	_CMN_EVENT_HNF(qos_pocq_occupancy_stash, 0x0f, 4),
	CMN_EVENT_HNF(pocq_addrhaz,	0x10),
	CMN_EVENT_HNF(pocq_atomic_addrhaz, 0x11),
	CMN_EVENT_HNF(ld_st_swp_adq_full, 0x12),
	CMN_EVENT_HNF(cmp_adq_full,	0x13),
	CMN_EVENT_HNF(txdat_stall,	0x14),
	CMN_EVENT_HNF(txrsp_stall,	0x15),
	CMN_EVENT_HNF(seq_full,		0x16),
	CMN_EVENT_HNF(seq_hit,		0x17),
	CMN_EVENT_HNF(snp_sent,		0x18),
	CMN_EVENT_HNF(sfbi_dir_snp_sent, 0x19),
	CMN_EVENT_HNF(sfbi_brd_snp_sent, 0x1a),
	CMN_EVENT_HNF(snp_sent_untrk,	0x1b),
	CMN_EVENT_HNF(intv_dirty,	0x1c),
	CMN_EVENT_HNF(stash_snp_sent,	0x1d),
	CMN_EVENT_HNF(stash_data_pull,	0x1e),
	CMN_EVENT_HNF(snp_fwded,	0x1f),

	CMN_EVENT_HNI(rrt_rd_occ_cnt_ovfl, 0x20),
	CMN_EVENT_HNI(rrt_wr_occ_cnt_ovfl, 0x21),
	CMN_EVENT_HNI(rdt_rd_occ_cnt_ovfl, 0x22),
	CMN_EVENT_HNI(rdt_wr_occ_cnt_ovfl, 0x23),
	CMN_EVENT_HNI(wdb_occ_cnt_ovfl,	0x24),
	CMN_EVENT_HNI(rrt_rd_alloc,	0x25),
	CMN_EVENT_HNI(rrt_wr_alloc,	0x26),
	CMN_EVENT_HNI(rdt_rd_alloc,	0x27),
	CMN_EVENT_HNI(rdt_wr_alloc,	0x28),
	CMN_EVENT_HNI(wdb_alloc,	0x29),
	CMN_EVENT_HNI(txrsp_retryack,	0x2a),
	CMN_EVENT_HNI(arvalid_no_arready, 0x2b),
	CMN_EVENT_HNI(arready_no_arvalid, 0x2c),
	CMN_EVENT_HNI(awvalid_no_awready, 0x2d),
	CMN_EVENT_HNI(awready_no_awvalid, 0x2e),
	CMN_EVENT_HNI(wvalid_no_wready,	0x2f),
	CMN_EVENT_HNI(txdat_stall,	0x30),
	CMN_EVENT_HNI(nonpcie_serialization, 0x31),
	CMN_EVENT_HNI(pcie_serialization, 0x32),

	CMN_EVENT_XP(txflit_valid,	0x01),
	CMN_EVENT_XP(txflit_stall,	0x02),
	CMN_EVENT_XP(partial_dat_flit,	0x03),
	/* We treat watchpoints as a special made-up class of XP events */
	CMN_EVENT_ATTR(watchpoint_up, CMN_TYPE_WP, 0, 0),
	CMN_EVENT_ATTR(watchpoint_down, CMN_TYPE_WP, 2, 0),

	CMN_EVENT_SBSX(rd_req,		0x01),
	CMN_EVENT_SBSX(wr_req,		0x02),
	CMN_EVENT_SBSX(cmo_req,		0x03),
	CMN_EVENT_SBSX(txrsp_retryack,	0x04),
	CMN_EVENT_SBSX(txdat_flitv,	0x05),
	CMN_EVENT_SBSX(txrsp_flitv,	0x06),
	CMN_EVENT_SBSX(rd_req_trkr_occ_cnt_ovfl, 0x11),
	CMN_EVENT_SBSX(wr_req_trkr_occ_cnt_ovfl, 0x12),
	CMN_EVENT_SBSX(cmo_req_trkr_occ_cnt_ovfl, 0x13),
	CMN_EVENT_SBSX(wdb_occ_cnt_ovfl, 0x14),
	CMN_EVENT_SBSX(rd_axi_trkr_occ_cnt_ovfl, 0x15),
	CMN_EVENT_SBSX(cmo_axi_trkr_occ_cnt_ovfl, 0x16),
	CMN_EVENT_SBSX(arvalid_no_arready, 0x21),
	CMN_EVENT_SBSX(awvalid_no_awready, 0x22),
	CMN_EVENT_SBSX(wvalid_no_wready, 0x23),
	CMN_EVENT_SBSX(txdat_stall,	0x24),
	CMN_EVENT_SBSX(txrsp_stall,	0x25),

	CMN_EVENT_RNID(s0_rdata_beats,	0x01),
	CMN_EVENT_RNID(s1_rdata_beats,	0x02),
	CMN_EVENT_RNID(s2_rdata_beats,	0x03),
	CMN_EVENT_RNID(rxdat_flits,	0x04),
	CMN_EVENT_RNID(txdat_flits,	0x05),
	CMN_EVENT_RNID(txreq_flits_total, 0x06),
	CMN_EVENT_RNID(txreq_flits_retried, 0x07),
	CMN_EVENT_RNID(rrt_occ_ovfl,	0x08),
	CMN_EVENT_RNID(wrt_occ_ovfl,	0x09),
	CMN_EVENT_RNID(txreq_flits_replayed, 0x0a),
	CMN_EVENT_RNID(wrcancel_sent,	0x0b),
	CMN_EVENT_RNID(s0_wdata_beats,	0x0c),
	CMN_EVENT_RNID(s1_wdata_beats,	0x0d),
	CMN_EVENT_RNID(s2_wdata_beats,	0x0e),
	CMN_EVENT_RNID(rrt_alloc,	0x0f),
	CMN_EVENT_RNID(wrt_alloc,	0x10),
	CMN_EVENT_RNID(rdb_unord,	0x11),
	CMN_EVENT_RNID(rdb_replay,	0x12),
	CMN_EVENT_RNID(rdb_hybrid,	0x13),
	CMN_EVENT_RNID(rdb_ord,		0x14),

	NULL
};

static const struct attribute_group arm_cmn_event_attrs_group = {
	.name = "events",
	.attrs = arm_cmn_event_attrs,
	.is_visible = arm_cmn_event_attr_is_visible,
};

static ssize_t arm_cmn_format_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct arm_cmn_format_attr *fmt = container_of(attr, typeof(*fmt), attr);
	int lo = __ffs(fmt->field), hi = __fls(fmt->field);

	if (lo == hi)
		return sysfs_emit(buf, "config:%d\n", lo);

	if (!fmt->config)
		return sysfs_emit(buf, "config:%d-%d\n", lo, hi);

	return sysfs_emit(buf, "config%d:%d-%d\n", fmt->config, lo, hi);
}

#define _CMN_FORMAT_ATTR(_name, _cfg, _fld)				\
	(&((struct arm_cmn_format_attr[]) {{				\
		.attr = __ATTR(_name, 0444, arm_cmn_format_show, NULL),	\
		.config = _cfg,						\
		.field = _fld,						\
	}})[0].attr.attr)
#define CMN_FORMAT_ATTR(_name, _fld)	_CMN_FORMAT_ATTR(_name, 0, _fld)

static struct attribute *arm_cmn_format_attrs[] = {
	CMN_FORMAT_ATTR(type, CMN_CONFIG_TYPE),
	CMN_FORMAT_ATTR(eventid, CMN_CONFIG_EVENTID),
	CMN_FORMAT_ATTR(occupid, CMN_CONFIG_OCCUPID),
	CMN_FORMAT_ATTR(bynodeid, CMN_CONFIG_BYNODEID),
	CMN_FORMAT_ATTR(nodeid, CMN_CONFIG_NODEID),

	CMN_FORMAT_ATTR(wp_dev_sel, CMN_CONFIG_WP_DEV_SEL),
	CMN_FORMAT_ATTR(wp_chn_sel, CMN_CONFIG_WP_CHN_SEL),
	CMN_FORMAT_ATTR(wp_grp, CMN_CONFIG_WP_GRP),
	CMN_FORMAT_ATTR(wp_exclusive, CMN_CONFIG_WP_EXCLUSIVE),
	CMN_FORMAT_ATTR(wp_combine, CMN_CONFIG_WP_COMBINE),

	_CMN_FORMAT_ATTR(wp_val, 1, CMN_CONFIG1_WP_VAL),
	_CMN_FORMAT_ATTR(wp_mask, 2, CMN_CONFIG2_WP_MASK),

	NULL
};

static const struct attribute_group arm_cmn_format_attrs_group = {
	.name = "format",
	.attrs = arm_cmn_format_attrs,
};

static ssize_t arm_cmn_cpumask_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));

	return cpumap_print_to_pagebuf(true, buf, cpumask_of(cmn->cpu));
}

static struct device_attribute arm_cmn_cpumask_attr =
		__ATTR(cpumask, 0444, arm_cmn_cpumask_show, NULL);

static struct attribute *arm_cmn_cpumask_attrs[] = {
	&arm_cmn_cpumask_attr.attr,
	NULL,
};

static const struct attribute_group arm_cmn_cpumask_attr_group = {
	.attrs = arm_cmn_cpumask_attrs,
};

static const struct attribute_group *arm_cmn_attr_groups[] = {
	&arm_cmn_event_attrs_group,
	&arm_cmn_format_attrs_group,
	&arm_cmn_cpumask_attr_group,
	NULL
};

static int arm_cmn_wp_idx(struct perf_event *event)
{
	return CMN_EVENT_EVENTID(event) + CMN_EVENT_WP_GRP(event);
}

static u32 arm_cmn_wp_config(struct perf_event *event)
{
	u32 config;
	u32 dev = CMN_EVENT_WP_DEV_SEL(event);
	u32 chn = CMN_EVENT_WP_CHN_SEL(event);
	u32 grp = CMN_EVENT_WP_GRP(event);
	u32 exc = CMN_EVENT_WP_EXCLUSIVE(event);
	u32 combine = CMN_EVENT_WP_COMBINE(event);

	config = FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_DEV_SEL, dev) |
		 FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_CHN_SEL, chn) |
		 FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_GRP, grp) |
		 FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_EXCLUSIVE, exc);
	if (combine && !grp)
		config |= CMN_DTM_WPn_CONFIG_WP_COMBINE;

	return config;
}

static void arm_cmn_set_state(struct arm_cmn *cmn, u32 state)
{
	if (!cmn->state)
		writel_relaxed(0, cmn->dtc[0].base + CMN_DT_PMCR);
	cmn->state |= state;
}

static void arm_cmn_clear_state(struct arm_cmn *cmn, u32 state)
{
	cmn->state &= ~state;
	if (!cmn->state)
		writel_relaxed(CMN_DT_PMCR_PMU_EN | CMN_DT_PMCR_OVFL_INTR_EN,
			       cmn->dtc[0].base + CMN_DT_PMCR);
}

static void arm_cmn_pmu_enable(struct pmu *pmu)
{
	arm_cmn_clear_state(to_cmn(pmu), CMN_STATE_DISABLED);
}

static void arm_cmn_pmu_disable(struct pmu *pmu)
{
	arm_cmn_set_state(to_cmn(pmu), CMN_STATE_DISABLED);
}

static u64 arm_cmn_read_dtm(struct arm_cmn *cmn, struct arm_cmn_hw_event *hw,
			    bool snapshot)
{
	struct arm_cmn_node *dn;
	unsigned int i, offset;
	u64 count = 0;

	offset = snapshot ? CMN_DTM_PMEVCNTSR : CMN_DTM_PMEVCNT;
	for_each_hw_dn(hw, dn, i) {
		struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm];
		int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i);
		u64 reg = readq_relaxed(dtm->base + offset);
		u16 dtm_count = reg >> (dtm_idx * 16);

		count += dtm_count;
	}
	return count;
}

static u64 arm_cmn_read_cc(struct arm_cmn_dtc *dtc)
{
	u64 val = readq_relaxed(dtc->base + CMN_DT_PMCCNTR);

	writeq_relaxed(CMN_CC_INIT, dtc->base + CMN_DT_PMCCNTR);
	return (val - CMN_CC_INIT) & ((CMN_CC_INIT << 1) - 1);
}

static u32 arm_cmn_read_counter(struct arm_cmn_dtc *dtc, int idx)
{
	u32 val, pmevcnt = CMN_DT_PMEVCNT(idx);

	val = readl_relaxed(dtc->base + pmevcnt);
	writel_relaxed(CMN_COUNTER_INIT, dtc->base + pmevcnt);
	return val - CMN_COUNTER_INIT;
}

static void arm_cmn_init_counter(struct perf_event *event)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	unsigned int i, pmevcnt = CMN_DT_PMEVCNT(hw->dtc_idx);
	u64 count;

	for (i = 0; hw->dtcs_used & (1U << i); i++) {
		writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + pmevcnt);
		cmn->dtc[i].counters[hw->dtc_idx] = event;
	}

	count = arm_cmn_read_dtm(cmn, hw, false);
	local64_set(&event->hw.prev_count, count);
}

static void arm_cmn_event_read(struct perf_event *event)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	u64 delta, new, prev;
	unsigned long flags;
	unsigned int i;

	if (hw->dtc_idx == CMN_DT_NUM_COUNTERS) {
		i = __ffs(hw->dtcs_used);
		delta = arm_cmn_read_cc(cmn->dtc + i);
		local64_add(delta, &event->count);
		return;
	}
	new = arm_cmn_read_dtm(cmn, hw, false);
	prev = local64_xchg(&event->hw.prev_count, new);

	delta = new - prev;

	local_irq_save(flags);
	for (i = 0; hw->dtcs_used & (1U << i); i++) {
		new = arm_cmn_read_counter(cmn->dtc + i, hw->dtc_idx);
		delta += new << 16;
	}
	local_irq_restore(flags);
	local64_add(delta, &event->count);
}

static void arm_cmn_event_start(struct perf_event *event, int flags)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_node *dn;
	enum cmn_node_type type = CMN_EVENT_TYPE(event);
	int i;

	if (type == CMN_TYPE_DTC) {
		i = __ffs(hw->dtcs_used);
		writeq_relaxed(CMN_CC_INIT, cmn->dtc[i].base + CMN_DT_PMCCNTR);
		cmn->dtc[i].cc_active = true;
	} else if (type == CMN_TYPE_WP) {
		int wp_idx = arm_cmn_wp_idx(event);
		u64 val = CMN_EVENT_WP_VAL(event);
		u64 mask = CMN_EVENT_WP_MASK(event);

		for_each_hw_dn(hw, dn, i) {
			writeq_relaxed(val, dn->pmu_base + CMN_DTM_WPn_VAL(wp_idx));
			writeq_relaxed(mask, dn->pmu_base + CMN_DTM_WPn_MASK(wp_idx));
		}
	} else for_each_hw_dn(hw, dn, i) {
		int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i);

		dn->event[dtm_idx] = CMN_EVENT_EVENTID(event);
		writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL);
	}
}

static void arm_cmn_event_stop(struct perf_event *event, int flags)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_node *dn;
	enum cmn_node_type type = CMN_EVENT_TYPE(event);
	int i;

	if (type == CMN_TYPE_DTC) {
		i = __ffs(hw->dtcs_used);
		cmn->dtc[i].cc_active = false;
	} else if (type == CMN_TYPE_WP) {
		int wp_idx = arm_cmn_wp_idx(event);

		for_each_hw_dn(hw, dn, i) {
			writeq_relaxed(0, dn->pmu_base + CMN_DTM_WPn_MASK(wp_idx));
			writeq_relaxed(~0ULL, dn->pmu_base + CMN_DTM_WPn_VAL(wp_idx));
		}
	} else for_each_hw_dn(hw, dn, i) {
		int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i);

		dn->event[dtm_idx] = 0;
		writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL);
	}

	arm_cmn_event_read(event);
}

struct arm_cmn_val {
	u8 dtm_count[CMN_MAX_DTMS];
	u8 occupid[CMN_MAX_DTMS];
	u8 wp[CMN_MAX_DTMS][4];
	int dtc_count;
	bool cycles;
};

static void arm_cmn_val_add_event(struct arm_cmn_val *val, struct perf_event *event)
{
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_node *dn;
	enum cmn_node_type type;
	int i;
	u8 occupid;

	if (is_software_event(event))
		return;

	type = CMN_EVENT_TYPE(event);
	if (type == CMN_TYPE_DTC) {
		val->cycles = true;
		return;
	}

	val->dtc_count++;
	if (arm_cmn_is_occup_event(type, CMN_EVENT_EVENTID(event)))
		occupid = CMN_EVENT_OCCUPID(event) + 1;
	else
		occupid = 0;

	for_each_hw_dn(hw, dn, i) {
		int wp_idx, dtm = dn->dtm;

		val->dtm_count[dtm]++;
		val->occupid[dtm] = occupid;

		if (type != CMN_TYPE_WP)
			continue;

		wp_idx = arm_cmn_wp_idx(event);
		val->wp[dtm][wp_idx] = CMN_EVENT_WP_COMBINE(event) + 1;
	}
}

static int arm_cmn_validate_group(struct perf_event *event)
{
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_node *dn;
	struct perf_event *sibling, *leader = event->group_leader;
	enum cmn_node_type type;
	struct arm_cmn_val val;
	int i;
	u8 occupid;

	if (leader == event)
		return 0;

	if (event->pmu != leader->pmu && !is_software_event(leader))
		return -EINVAL;

	memset(&val, 0, sizeof(val));

	arm_cmn_val_add_event(&val, leader);
	for_each_sibling_event(sibling, leader)
		arm_cmn_val_add_event(&val, sibling);

	type = CMN_EVENT_TYPE(event);
	if (type == CMN_TYPE_DTC)
		return val.cycles ? -EINVAL : 0;

	if (val.dtc_count == CMN_DT_NUM_COUNTERS)
		return -EINVAL;

	if (arm_cmn_is_occup_event(type, CMN_EVENT_EVENTID(event)))
		occupid = CMN_EVENT_OCCUPID(event) + 1;
	else
		occupid = 0;

	for_each_hw_dn(hw, dn, i) {
		int wp_idx, wp_cmb, dtm = dn->dtm;

		if (val.dtm_count[dtm] == CMN_DTM_NUM_COUNTERS)
			return -EINVAL;

		if (occupid && val.occupid[dtm] && occupid != val.occupid[dtm])
			return -EINVAL;

		if (type != CMN_TYPE_WP)
			continue;

		wp_idx = arm_cmn_wp_idx(event);
		if (val.wp[dtm][wp_idx])
			return -EINVAL;

		wp_cmb = val.wp[dtm][wp_idx ^ 1];
		if (wp_cmb && wp_cmb != CMN_EVENT_WP_COMBINE(event) + 1)
			return -EINVAL;
	}

	return 0;
}

static int arm_cmn_event_init(struct perf_event *event)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_node *dn;
	enum cmn_node_type type;
	bool bynodeid;
	u16 nodeid, eventid;

	if (event->attr.type != event->pmu->type)
		return -ENOENT;

	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
		return -EINVAL;

	event->cpu = cmn->cpu;
	if (event->cpu < 0)
		return -EINVAL;

	type = CMN_EVENT_TYPE(event);
	/* DTC events (i.e. cycles) already have everything they need */
	if (type == CMN_TYPE_DTC)
		return 0;

	/* For watchpoints we need the actual XP node here */
	if (type == CMN_TYPE_WP) {
		type = CMN_TYPE_XP;
		/* ...and we need a "real" direction */
		eventid = CMN_EVENT_EVENTID(event);
		if (eventid != CMN_WP_UP && eventid != CMN_WP_DOWN)
			return -EINVAL;
	}

	bynodeid = CMN_EVENT_BYNODEID(event);
	nodeid = CMN_EVENT_NODEID(event);

	hw->dn = arm_cmn_node(cmn, type);
	if (!hw->dn)
		return -EINVAL;
	for (dn = hw->dn; dn->type == type; dn++) {
		if (!bynodeid) {
			hw->num_dns++;
		} else if (dn->id != nodeid) {
			hw->dn++;
		} else {
			hw->num_dns = 1;
			break;
		}
	}

	if (!hw->num_dns) {
		struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, nodeid);

		dev_dbg(cmn->dev, "invalid node 0x%x (%d,%d,%d,%d) type 0x%x\n",
			nodeid, nid.x, nid.y, nid.port, nid.dev, type);
		return -EINVAL;
	}
	/*
	 * By assuming events count in all DTC domains, we cunningly avoid
	 * needing to know anything about how XPs are assigned to domains.
	 */
	hw->dtcs_used = (1U << cmn->num_dtcs) - 1;

	return arm_cmn_validate_group(event);
}

static void arm_cmn_event_clear(struct arm_cmn *cmn, struct perf_event *event,
				int i)
{
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	enum cmn_node_type type = CMN_EVENT_TYPE(event);

	while (i--) {
		struct arm_cmn_dtm *dtm = &cmn->dtms[hw->dn[i].dtm];
		unsigned int dtm_idx = arm_cmn_get_index(hw->dtm_idx, i);

		if (type == CMN_TYPE_WP)
			dtm->wp_event[arm_cmn_wp_idx(event)] = -1;

		if (arm_cmn_is_occup_event(type, CMN_EVENT_EVENTID(event)))
			hw->dn[i].occupid_count--;

		dtm->pmu_config_low &= ~CMN__PMEVCNT_PAIRED(dtm_idx);
		writel_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG);
	}
	memset(hw->dtm_idx, 0, sizeof(hw->dtm_idx));

	for (i = 0; hw->dtcs_used & (1U << i); i++)
		cmn->dtc[i].counters[hw->dtc_idx] = NULL;
}

static int arm_cmn_event_add(struct perf_event *event, int flags)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	struct arm_cmn_dtc *dtc = &cmn->dtc[0];
	struct arm_cmn_node *dn;
	enum cmn_node_type type = CMN_EVENT_TYPE(event);
	unsigned int i, dtc_idx, input_sel;

	if (type == CMN_TYPE_DTC) {
		i = 0;
		while (cmn->dtc[i].cycles)
			if (++i == cmn->num_dtcs)
				return -ENOSPC;

		cmn->dtc[i].cycles = event;
		hw->dtc_idx = CMN_DT_NUM_COUNTERS;
		hw->dtcs_used = 1U << i;

		if (flags & PERF_EF_START)
			arm_cmn_event_start(event, 0);
		return 0;
	}

	/* Grab a free global counter first... */
	dtc_idx = 0;
	while (dtc->counters[dtc_idx])
		if (++dtc_idx == CMN_DT_NUM_COUNTERS)
			return -ENOSPC;

	hw->dtc_idx = dtc_idx;

	/* ...then the local counters to feed it. */
	for_each_hw_dn(hw, dn, i) {
		struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm];
		unsigned int dtm_idx, shift;
		u64 reg;

		dtm_idx = 0;
		while (dtm->pmu_config_low & CMN__PMEVCNT_PAIRED(dtm_idx))
			if (++dtm_idx == CMN_DTM_NUM_COUNTERS)
				goto free_dtms;

		if (type == CMN_TYPE_XP) {
			input_sel = CMN__PMEVCNT0_INPUT_SEL_XP + dtm_idx;
		} else if (type == CMN_TYPE_WP) {
			int tmp, wp_idx = arm_cmn_wp_idx(event);
			u32 cfg = arm_cmn_wp_config(event);

			if (dtm->wp_event[wp_idx] >= 0)
				goto free_dtms;

			tmp = dtm->wp_event[wp_idx ^ 1];
			if (tmp >= 0 && CMN_EVENT_WP_COMBINE(event) !=
					CMN_EVENT_WP_COMBINE(dtc->counters[tmp]))
				goto free_dtms;

			input_sel = CMN__PMEVCNT0_INPUT_SEL_WP + wp_idx;
			dtm->wp_event[wp_idx] = dtc_idx;
			writel_relaxed(cfg, dtm->base + CMN_DTM_WPn_CONFIG(wp_idx));
		} else {
			struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);

			input_sel = CMN__PMEVCNT0_INPUT_SEL_DEV + dtm_idx +
				    (nid.port << 4) + (nid.dev << 2);

			if (arm_cmn_is_occup_event(type, CMN_EVENT_EVENTID(event))) {
				u8 occupid = CMN_EVENT_OCCUPID(event);

				if (dn->occupid_count == 0) {
					dn->occupid_val = occupid;
					writel_relaxed(occupid,
						       dn->pmu_base + CMN_PMU_EVENT_SEL + 4);
				} else if (dn->occupid_val != occupid) {
					goto free_dtms;
				}
				dn->occupid_count++;
			}
		}

		arm_cmn_set_index(hw->dtm_idx, i, dtm_idx);

		dtm->input_sel[dtm_idx] = input_sel;
		shift = CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(dtm_idx);
		dtm->pmu_config_low &= ~(CMN__PMEVCNT0_GLOBAL_NUM << shift);
		dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, dtc_idx) << shift;
		dtm->pmu_config_low |= CMN__PMEVCNT_PAIRED(dtm_idx);
		reg = (u64)le32_to_cpu(dtm->pmu_config_high) << 32 | dtm->pmu_config_low;
		writeq_relaxed(reg, dtm->base + CMN_DTM_PMU_CONFIG);
	}

	/* Go go go! */
	arm_cmn_init_counter(event);

	if (flags & PERF_EF_START)
		arm_cmn_event_start(event, 0);

	return 0;

free_dtms:
	arm_cmn_event_clear(cmn, event, i);
	return -ENOSPC;
}

static void arm_cmn_event_del(struct perf_event *event, int flags)
{
	struct arm_cmn *cmn = to_cmn(event->pmu);
	struct arm_cmn_hw_event *hw = to_cmn_hw(event);
	enum cmn_node_type type = CMN_EVENT_TYPE(event);

	arm_cmn_event_stop(event, PERF_EF_UPDATE);

	if (type == CMN_TYPE_DTC)
		cmn->dtc[__ffs(hw->dtcs_used)].cycles = NULL;
	else
		arm_cmn_event_clear(cmn, event, hw->num_dns);
}

/*
 * We stop the PMU for both add and read, to avoid skew across DTM counters.
 * In theory we could use snapshots to read without stopping, but then it
 * becomes a lot trickier to deal with overlow and racing against interrupts,
 * plus it seems they don't work properly on some hardware anyway :(
 */
static void arm_cmn_start_txn(struct pmu *pmu, unsigned int flags)
{
	arm_cmn_set_state(to_cmn(pmu), CMN_STATE_TXN);
}

static void arm_cmn_end_txn(struct pmu *pmu)
{
	arm_cmn_clear_state(to_cmn(pmu), CMN_STATE_TXN);
}

static int arm_cmn_commit_txn(struct pmu *pmu)
{
	arm_cmn_end_txn(pmu);
	return 0;
}

static void arm_cmn_migrate(struct arm_cmn *cmn, unsigned int cpu)
{
	unsigned int i;

	perf_pmu_migrate_context(&cmn->pmu, cmn->cpu, cpu);
	for (i = 0; i < cmn->num_dtcs; i++)
		irq_set_affinity(cmn->dtc[i].irq, cpumask_of(cpu));
	cmn->cpu = cpu;
}

static int arm_cmn_pmu_online_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
{
	struct arm_cmn *cmn;
	int node;

	cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
	node = dev_to_node(cmn->dev);
	if (node != NUMA_NO_NODE && cpu_to_node(cmn->cpu) != node && cpu_to_node(cpu) == node)
		arm_cmn_migrate(cmn, cpu);
	return 0;
}

static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
{
	struct arm_cmn *cmn;
	unsigned int target;
	int node;
	cpumask_t mask;

	cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
	if (cpu != cmn->cpu)
		return 0;

	node = dev_to_node(cmn->dev);
	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
		target = cpumask_any(&mask);
	else
		target = cpumask_any_but(cpu_online_mask, cpu);
	if (target < nr_cpu_ids)
		arm_cmn_migrate(cmn, target);
	return 0;
}

static irqreturn_t arm_cmn_handle_irq(int irq, void *dev_id)
{
	struct arm_cmn_dtc *dtc = dev_id;
	irqreturn_t ret = IRQ_NONE;

	for (;;) {
		u32 status = readl_relaxed(dtc->base + CMN_DT_PMOVSR);
		u64 delta;
		int i;

		for (i = 0; i < CMN_DTM_NUM_COUNTERS; i++) {
			if (status & (1U << i)) {
				ret = IRQ_HANDLED;
				if (WARN_ON(!dtc->counters[i]))
					continue;
				delta = (u64)arm_cmn_read_counter(dtc, i) << 16;
				local64_add(delta, &dtc->counters[i]->count);
			}
		}

		if (status & (1U << CMN_DT_NUM_COUNTERS)) {
			ret = IRQ_HANDLED;
			if (dtc->cc_active && !WARN_ON(!dtc->cycles)) {
				delta = arm_cmn_read_cc(dtc);
				local64_add(delta, &dtc->cycles->count);
			}
		}

		writel_relaxed(status, dtc->base + CMN_DT_PMOVSR_CLR);

		if (!dtc->irq_friend)
			return ret;
		dtc += dtc->irq_friend;
	}
}

/* We can reasonably accommodate DTCs of the same CMN sharing IRQs */
static int arm_cmn_init_irqs(struct arm_cmn *cmn)
{
	int i, j, irq, err;

	for (i = 0; i < cmn->num_dtcs; i++) {
		irq = cmn->dtc[i].irq;
		for (j = i; j--; ) {
			if (cmn->dtc[j].irq == irq) {
				cmn->dtc[j].irq_friend = i - j;
				goto next;
			}
		}
		err = devm_request_irq(cmn->dev, irq, arm_cmn_handle_irq,
				       IRQF_NOBALANCING | IRQF_NO_THREAD,
				       dev_name(cmn->dev), &cmn->dtc[i]);
		if (err)
			return err;

		err = irq_set_affinity(irq, cpumask_of(cmn->cpu));
		if (err)
			return err;
	next:
		; /* isn't C great? */
	}
	return 0;
}

static void arm_cmn_init_dtm(struct arm_cmn_dtm *dtm, struct arm_cmn_node *xp)
{
	int i;

	dtm->base = xp->pmu_base;
	dtm->pmu_config_low = CMN_DTM_PMU_CONFIG_PMU_EN;
	for (i = 0; i < 4; i++) {
		dtm->wp_event[i] = -1;
		writeq_relaxed(0, dtm->base + CMN_DTM_WPn_MASK(i));
		writeq_relaxed(~0ULL, dtm->base + CMN_DTM_WPn_VAL(i));
	}
}

static int arm_cmn_init_dtc(struct arm_cmn *cmn, struct arm_cmn_node *dn, int idx)
{
	struct arm_cmn_dtc *dtc = cmn->dtc + idx;

	dtc->base = dn->pmu_base - CMN_PMU_OFFSET;
	dtc->irq = platform_get_irq(to_platform_device(cmn->dev), idx);
	if (dtc->irq < 0)
		return dtc->irq;

	writel_relaxed(0, dtc->base + CMN_DT_PMCR);
	writel_relaxed(0x1ff, dtc->base + CMN_DT_PMOVSR_CLR);
	writel_relaxed(CMN_DT_PMCR_OVFL_INTR_EN, dtc->base + CMN_DT_PMCR);

	return 0;
}

static int arm_cmn_node_cmp(const void *a, const void *b)
{
	const struct arm_cmn_node *dna = a, *dnb = b;
	int cmp;

	cmp = dna->type - dnb->type;
	if (!cmp)
		cmp = dna->logid - dnb->logid;
	return cmp;
}

static int arm_cmn_init_dtcs(struct arm_cmn *cmn)
{
	struct arm_cmn_node *dn, *xp;
	int dtc_idx = 0;

	cmn->dtc = devm_kcalloc(cmn->dev, cmn->num_dtcs, sizeof(cmn->dtc[0]), GFP_KERNEL);
	if (!cmn->dtc)
		return -ENOMEM;

	sort(cmn->dns, cmn->num_dns, sizeof(cmn->dns[0]), arm_cmn_node_cmp, NULL);

	cmn->xps = arm_cmn_node(cmn, CMN_TYPE_XP);

	for (dn = cmn->dns; dn->type; dn++) {
		if (dn->type == CMN_TYPE_XP) {
			if (dn->dtc < 0 && cmn->num_dtcs == 1)
				dn->dtc = 0;
			continue;
		}

		xp = arm_cmn_node_to_xp(cmn, dn);
		dn->dtm = xp->dtm;

		if (dn->type == CMN_TYPE_DTC) {
			int err;
			/* We do at least know that a DTC's XP must be in that DTC's domain */
			if (xp->dtc < 0)
				xp->dtc = dtc_idx;
			err = arm_cmn_init_dtc(cmn, dn, dtc_idx++);
			if (err)
				return err;
		}

		/* To the PMU, RN-Ds don't add anything over RN-Is, so smoosh them together */
		if (dn->type == CMN_TYPE_RND)
			dn->type = CMN_TYPE_RNI;
	}

	writel_relaxed(CMN_DT_DTC_CTL_DT_EN, cmn->dtc[0].base + CMN_DT_DTC_CTL);

	return 0;
}

static void arm_cmn_init_node_info(struct arm_cmn *cmn, u32 offset, struct arm_cmn_node *node)
{
	int level;
	u64 reg = readq_relaxed(cmn->base + offset + CMN_NODE_INFO);

	node->type = FIELD_GET(CMN_NI_NODE_TYPE, reg);
	node->id = FIELD_GET(CMN_NI_NODE_ID, reg);
	node->logid = FIELD_GET(CMN_NI_LOGICAL_ID, reg);

	node->pmu_base = cmn->base + offset + CMN_PMU_OFFSET;

	if (node->type == CMN_TYPE_CFG)
		level = 0;
	else if (node->type == CMN_TYPE_XP)
		level = 1;
	else
		level = 2;

	dev_dbg(cmn->dev, "node%*c%#06hx%*ctype:%-#6x id:%-4hd off:%#x\n",
			(level * 2) + 1, ' ', node->id, 5 - (level * 2), ' ',
			node->type, node->logid, offset);
}

static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
{
	void __iomem *cfg_region;
	struct arm_cmn_node cfg, *dn;
	struct arm_cmn_dtm *dtm;
	u16 child_count, child_poff;
	u32 xp_offset[CMN_MAX_XPS];
	u64 reg;
	int i, j;
	size_t sz;

	cfg_region = cmn->base + rgn_offset;
	reg = readl_relaxed(cfg_region + CMN_CFGM_PERIPH_ID_2);
	cmn->rev = FIELD_GET(CMN_CFGM_PID2_REVISION, reg);
	dev_dbg(cmn->dev, "periph_id_2 revision: %d\n", cmn->rev);

	arm_cmn_init_node_info(cmn, rgn_offset, &cfg);
	if (cfg.type != CMN_TYPE_CFG)
		return -ENODEV;

	reg = readq_relaxed(cfg_region + CMN_CHILD_INFO);
	child_count = FIELD_GET(CMN_CI_CHILD_COUNT, reg);
	child_poff = FIELD_GET(CMN_CI_CHILD_PTR_OFFSET, reg);

	cmn->num_xps = child_count;
	cmn->num_dns = cmn->num_xps;

	/* Pass 1: visit the XPs, enumerate their children */
	for (i = 0; i < cmn->num_xps; i++) {
		reg = readq_relaxed(cfg_region + child_poff + i * 8);
		xp_offset[i] = reg & CMN_CHILD_NODE_ADDR;

		reg = readq_relaxed(cmn->base + xp_offset[i] + CMN_CHILD_INFO);
		cmn->num_dns += FIELD_GET(CMN_CI_CHILD_COUNT, reg);
	}

	/* Cheeky +1 to help terminate pointer-based iteration later */
	dn = devm_kcalloc(cmn->dev, cmn->num_dns + 1, sizeof(*dn), GFP_KERNEL);
	if (!dn)
		return -ENOMEM;

	dtm = devm_kcalloc(cmn->dev, cmn->num_xps, sizeof(*dtm), GFP_KERNEL);
	if (!dtm)
		return -ENOMEM;

	/* Pass 2: now we can actually populate the nodes */
	cmn->dns = dn;
	cmn->dtms = dtm;
	for (i = 0; i < cmn->num_xps; i++) {
		void __iomem *xp_region = cmn->base + xp_offset[i];
		struct arm_cmn_node *xp = dn++;

		arm_cmn_init_node_info(cmn, xp_offset[i], xp);
		/*
		 * Thanks to the order in which XP logical IDs seem to be
		 * assigned, we can handily infer the mesh X dimension by
		 * looking out for the XP at (0,1) without needing to know
		 * the exact node ID format, which we can later derive.
		 */
		if (xp->id == (1 << 3))
			cmn->mesh_x = xp->logid;

		xp->dtc = -1;
		xp->dtm = dtm - cmn->dtms;
		arm_cmn_init_dtm(dtm++, xp);

		reg = readq_relaxed(xp_region + CMN_CHILD_INFO);
		child_count = FIELD_GET(CMN_CI_CHILD_COUNT, reg);
		child_poff = FIELD_GET(CMN_CI_CHILD_PTR_OFFSET, reg);

		for (j = 0; j < child_count; j++) {
			reg = readq_relaxed(xp_region + child_poff + j * 8);
			/*
			 * Don't even try to touch anything external, since in general
			 * we haven't a clue how to power up arbitrary CHI requesters.
			 * As of CMN-600r1 these could only be RN-SAMs or CXLAs,
			 * neither of which have any PMU events anyway.
			 * (Actually, CXLAs do seem to have grown some events in r1p2,
			 * but they don't go to regular XP DTMs, and they depend on
			 * secure configuration which we can't easily deal with)
			 */
			if (reg & CMN_CHILD_NODE_EXTERNAL) {
				dev_dbg(cmn->dev, "ignoring external node %llx\n", reg);
				continue;
			}

			arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);

			switch (dn->type) {
			case CMN_TYPE_DTC:
				cmn->num_dtcs++;
				dn++;
				break;
			/* These guys have PMU events */
			case CMN_TYPE_DVM:
			case CMN_TYPE_HNI:
			case CMN_TYPE_HNF:
			case CMN_TYPE_SBSX:
			case CMN_TYPE_RNI:
			case CMN_TYPE_RND:
			case CMN_TYPE_CXRA:
			case CMN_TYPE_CXHA:
				dn++;
				break;
			/* Nothing to see here */
			case CMN_TYPE_RNSAM:
			case CMN_TYPE_CXLA:
				break;
			/* Something has gone horribly wrong */
			default:
				dev_err(cmn->dev, "invalid device node type: 0x%x\n", dn->type);
				return -ENODEV;
			}
		}
	}

	/* Correct for any nodes we skipped */
	cmn->num_dns = dn - cmn->dns;

	sz = (void *)(dn + 1) - (void *)cmn->dns;
	dn = devm_krealloc(cmn->dev, cmn->dns, sz, GFP_KERNEL);
	if (dn)
		cmn->dns = dn;

	/*
	 * If mesh_x wasn't set during discovery then we never saw
	 * an XP at (0,1), thus we must have an Nx1 configuration.
	 */
	if (!cmn->mesh_x)
		cmn->mesh_x = cmn->num_xps;
	cmn->mesh_y = cmn->num_xps / cmn->mesh_x;

	dev_dbg(cmn->dev, "mesh %dx%d, ID width %d\n",
		cmn->mesh_x, cmn->mesh_y, arm_cmn_xyidbits(cmn));

	return 0;
}

static int arm_cmn_acpi_probe(struct platform_device *pdev, struct arm_cmn *cmn)
{
	struct resource *cfg, *root;

	cfg = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (!cfg)
		return -EINVAL;

	root = platform_get_resource(pdev, IORESOURCE_MEM, 1);
	if (!root)
		return -EINVAL;

	if (!resource_contains(cfg, root))
		swap(cfg, root);
	/*
	 * Note that devm_ioremap_resource() is dumb and won't let the platform
	 * device claim cfg when the ACPI companion device has already claimed
	 * root within it. But since they *are* already both claimed in the
	 * appropriate name, we don't really need to do it again here anyway.
	 */
	cmn->base = devm_ioremap(cmn->dev, cfg->start, resource_size(cfg));
	if (!cmn->base)
		return -ENOMEM;

	return root->start - cfg->start;
}

static int arm_cmn_of_probe(struct platform_device *pdev, struct arm_cmn *cmn)
{
	struct device_node *np = pdev->dev.of_node;
	u32 rootnode;
	int ret;

	cmn->base = devm_platform_ioremap_resource(pdev, 0);
	if (IS_ERR(cmn->base))
		return PTR_ERR(cmn->base);

	ret = of_property_read_u32(np, "arm,root-node", &rootnode);
	if (ret)
		return ret;

	return rootnode;
}

static int arm_cmn_probe(struct platform_device *pdev)
{
	struct arm_cmn *cmn;
	const char *name;
	static atomic_t id;
	int err, rootnode;

	cmn = devm_kzalloc(&pdev->dev, sizeof(*cmn), GFP_KERNEL);
	if (!cmn)
		return -ENOMEM;

	cmn->dev = &pdev->dev;
	platform_set_drvdata(pdev, cmn);

	if (has_acpi_companion(cmn->dev))
		rootnode = arm_cmn_acpi_probe(pdev, cmn);
	else
		rootnode = arm_cmn_of_probe(pdev, cmn);
	if (rootnode < 0)
		return rootnode;

	err = arm_cmn_discover(cmn, rootnode);
	if (err)
		return err;

	err = arm_cmn_init_dtcs(cmn);
	if (err)
		return err;

	err = arm_cmn_init_irqs(cmn);
	if (err)
		return err;

	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
	cmn->pmu = (struct pmu) {
		.module = THIS_MODULE,
		.attr_groups = arm_cmn_attr_groups,
		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
		.task_ctx_nr = perf_invalid_context,
		.pmu_enable = arm_cmn_pmu_enable,
		.pmu_disable = arm_cmn_pmu_disable,
		.event_init = arm_cmn_event_init,
		.add = arm_cmn_event_add,
		.del = arm_cmn_event_del,
		.start = arm_cmn_event_start,
		.stop = arm_cmn_event_stop,
		.read = arm_cmn_event_read,
		.start_txn = arm_cmn_start_txn,
		.commit_txn = arm_cmn_commit_txn,
		.cancel_txn = arm_cmn_end_txn,
	};

	name = devm_kasprintf(cmn->dev, GFP_KERNEL, "arm_cmn_%d", atomic_fetch_inc(&id));
	if (!name)
		return -ENOMEM;

	err = cpuhp_state_add_instance(arm_cmn_hp_state, &cmn->cpuhp_node);
	if (err)
		return err;

	err = perf_pmu_register(&cmn->pmu, name, -1);
	if (err)
		cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node);

	return err;
}

static int arm_cmn_remove(struct platform_device *pdev)
{
	struct arm_cmn *cmn = platform_get_drvdata(pdev);

	writel_relaxed(0, cmn->dtc[0].base + CMN_DT_DTC_CTL);

	perf_pmu_unregister(&cmn->pmu);
	cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node);
	return 0;
}

#ifdef CONFIG_OF
static const struct of_device_id arm_cmn_of_match[] = {
	{ .compatible = "arm,cmn-600", },
	{}
};
MODULE_DEVICE_TABLE(of, arm_cmn_of_match);
#endif

#ifdef CONFIG_ACPI
static const struct acpi_device_id arm_cmn_acpi_match[] = {
	{ "ARMHC600", },
	{}
};
MODULE_DEVICE_TABLE(acpi, arm_cmn_acpi_match);
#endif

static struct platform_driver arm_cmn_driver = {
	.driver = {
		.name = "arm-cmn",
		.of_match_table = of_match_ptr(arm_cmn_of_match),
		.acpi_match_table = ACPI_PTR(arm_cmn_acpi_match),
	},
	.probe = arm_cmn_probe,
	.remove = arm_cmn_remove,
};

static int __init arm_cmn_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
				      "perf/arm/cmn:online",
				      arm_cmn_pmu_online_cpu,
				      arm_cmn_pmu_offline_cpu);
	if (ret < 0)
		return ret;

	arm_cmn_hp_state = ret;
	ret = platform_driver_register(&arm_cmn_driver);
	if (ret)
		cpuhp_remove_multi_state(arm_cmn_hp_state);
	return ret;
}

static void __exit arm_cmn_exit(void)
{
	platform_driver_unregister(&arm_cmn_driver);
	cpuhp_remove_multi_state(arm_cmn_hp_state);
}

module_init(arm_cmn_init);
module_exit(arm_cmn_exit);

MODULE_AUTHOR("Robin Murphy <robin.murphy@arm.com>");
MODULE_DESCRIPTION("Arm CMN-600 PMU driver");
MODULE_LICENSE("GPL v2");