summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/perf/imc-pmu.c
blob: 8664a7d297ad8188eb4842abd2ccc106005324fb (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
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * In-Memory Collection (IMC) Performance Monitor counter support.
 *
 * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation.
 *           (C) 2017 Anju T Sudhakar, IBM Corporation.
 *           (C) 2017 Hemant K Shaw, IBM Corporation.
 */
#include <linux/of.h>
#include <linux/perf_event.h>
#include <linux/slab.h>
#include <asm/opal.h>
#include <asm/imc-pmu.h>
#include <asm/cputhreads.h>
#include <asm/smp.h>
#include <linux/string.h>
#include <linux/spinlock.h>

/* Nest IMC data structures and variables */

/*
 * Used to avoid races in counting the nest-pmu units during hotplug
 * register and unregister
 */
static DEFINE_MUTEX(nest_init_lock);
static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
static struct imc_pmu **per_nest_pmu_arr;
static cpumask_t nest_imc_cpumask;
static struct imc_pmu_ref *nest_imc_refc;
static int nest_pmus;

/* Core IMC data structures and variables */

static cpumask_t core_imc_cpumask;
static struct imc_pmu_ref *core_imc_refc;
static struct imc_pmu *core_imc_pmu;

/* Thread IMC data structures and variables */

static DEFINE_PER_CPU(u64 *, thread_imc_mem);
static struct imc_pmu *thread_imc_pmu;
static int thread_imc_mem_size;

/* Trace IMC data structures */
static DEFINE_PER_CPU(u64 *, trace_imc_mem);
static struct imc_pmu_ref *trace_imc_refc;
static int trace_imc_mem_size;

/*
 * Global data structure used to avoid races between thread,
 * core and trace-imc
 */
static struct imc_pmu_ref imc_global_refc = {
	.lock = __SPIN_LOCK_UNLOCKED(imc_global_refc.lock),
	.id = 0,
	.refc = 0,
};

static struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
{
	return container_of(event->pmu, struct imc_pmu, pmu);
}

PMU_FORMAT_ATTR(event, "config:0-61");
PMU_FORMAT_ATTR(offset, "config:0-31");
PMU_FORMAT_ATTR(rvalue, "config:32");
PMU_FORMAT_ATTR(mode, "config:33-40");
static struct attribute *imc_format_attrs[] = {
	&format_attr_event.attr,
	&format_attr_offset.attr,
	&format_attr_rvalue.attr,
	&format_attr_mode.attr,
	NULL,
};

static const struct attribute_group imc_format_group = {
	.name = "format",
	.attrs = imc_format_attrs,
};

/* Format attribute for imc trace-mode */
PMU_FORMAT_ATTR(cpmc_reserved, "config:0-19");
PMU_FORMAT_ATTR(cpmc_event, "config:20-27");
PMU_FORMAT_ATTR(cpmc_samplesel, "config:28-29");
PMU_FORMAT_ATTR(cpmc_load, "config:30-61");
static struct attribute *trace_imc_format_attrs[] = {
	&format_attr_event.attr,
	&format_attr_cpmc_reserved.attr,
	&format_attr_cpmc_event.attr,
	&format_attr_cpmc_samplesel.attr,
	&format_attr_cpmc_load.attr,
	NULL,
};

static const struct attribute_group trace_imc_format_group = {
.name = "format",
.attrs = trace_imc_format_attrs,
};

/* Get the cpumask printed to a buffer "buf" */
static ssize_t imc_pmu_cpumask_get_attr(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct pmu *pmu = dev_get_drvdata(dev);
	struct imc_pmu *imc_pmu = container_of(pmu, struct imc_pmu, pmu);
	cpumask_t *active_mask;

	switch(imc_pmu->domain){
	case IMC_DOMAIN_NEST:
		active_mask = &nest_imc_cpumask;
		break;
	case IMC_DOMAIN_CORE:
		active_mask = &core_imc_cpumask;
		break;
	default:
		return 0;
	}

	return cpumap_print_to_pagebuf(true, buf, active_mask);
}

static DEVICE_ATTR(cpumask, S_IRUGO, imc_pmu_cpumask_get_attr, NULL);

static struct attribute *imc_pmu_cpumask_attrs[] = {
	&dev_attr_cpumask.attr,
	NULL,
};

static const struct attribute_group imc_pmu_cpumask_attr_group = {
	.attrs = imc_pmu_cpumask_attrs,
};

/* device_str_attr_create : Populate event "name" and string "str" in attribute */
static struct attribute *device_str_attr_create(const char *name, const char *str)
{
	struct perf_pmu_events_attr *attr;

	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
	if (!attr)
		return NULL;
	sysfs_attr_init(&attr->attr.attr);

	attr->event_str = str;
	attr->attr.attr.name = name;
	attr->attr.attr.mode = 0444;
	attr->attr.show = perf_event_sysfs_show;

	return &attr->attr.attr;
}

static int imc_parse_event(struct device_node *np, const char *scale,
				  const char *unit, const char *prefix,
				  u32 base, struct imc_events *event)
{
	const char *s;
	u32 reg;

	if (of_property_read_u32(np, "reg", &reg))
		goto error;
	/* Add the base_reg value to the "reg" */
	event->value = base + reg;

	if (of_property_read_string(np, "event-name", &s))
		goto error;

	event->name = kasprintf(GFP_KERNEL, "%s%s", prefix, s);
	if (!event->name)
		goto error;

	if (of_property_read_string(np, "scale", &s))
		s = scale;

	if (s) {
		event->scale = kstrdup(s, GFP_KERNEL);
		if (!event->scale)
			goto error;
	}

	if (of_property_read_string(np, "unit", &s))
		s = unit;

	if (s) {
		event->unit = kstrdup(s, GFP_KERNEL);
		if (!event->unit)
			goto error;
	}

	return 0;
error:
	kfree(event->unit);
	kfree(event->scale);
	kfree(event->name);
	return -EINVAL;
}

/*
 * imc_free_events: Function to cleanup the events list, having
 * 		    "nr_entries".
 */
static void imc_free_events(struct imc_events *events, int nr_entries)
{
	int i;

	/* Nothing to clean, return */
	if (!events)
		return;
	for (i = 0; i < nr_entries; i++) {
		kfree(events[i].unit);
		kfree(events[i].scale);
		kfree(events[i].name);
	}

	kfree(events);
}

/*
 * update_events_in_group: Update the "events" information in an attr_group
 *                         and assign the attr_group to the pmu "pmu".
 */
static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
{
	struct attribute_group *attr_group;
	struct attribute **attrs, *dev_str;
	struct device_node *np, *pmu_events;
	u32 handle, base_reg;
	int i = 0, j = 0, ct, ret;
	const char *prefix, *g_scale, *g_unit;
	const char *ev_val_str, *ev_scale_str, *ev_unit_str;

	if (!of_property_read_u32(node, "events", &handle))
		pmu_events = of_find_node_by_phandle(handle);
	else
		return 0;

	/* Did not find any node with a given phandle */
	if (!pmu_events)
		return 0;

	/* Get a count of number of child nodes */
	ct = of_get_child_count(pmu_events);

	/* Get the event prefix */
	if (of_property_read_string(node, "events-prefix", &prefix)) {
		of_node_put(pmu_events);
		return 0;
	}

	/* Get a global unit and scale data if available */
	if (of_property_read_string(node, "scale", &g_scale))
		g_scale = NULL;

	if (of_property_read_string(node, "unit", &g_unit))
		g_unit = NULL;

	/* "reg" property gives out the base offset of the counters data */
	of_property_read_u32(node, "reg", &base_reg);

	/* Allocate memory for the events */
	pmu->events = kcalloc(ct, sizeof(struct imc_events), GFP_KERNEL);
	if (!pmu->events) {
		of_node_put(pmu_events);
		return -ENOMEM;
	}

	ct = 0;
	/* Parse the events and update the struct */
	for_each_child_of_node(pmu_events, np) {
		ret = imc_parse_event(np, g_scale, g_unit, prefix, base_reg, &pmu->events[ct]);
		if (!ret)
			ct++;
	}

	of_node_put(pmu_events);

	/* Allocate memory for attribute group */
	attr_group = kzalloc(sizeof(*attr_group), GFP_KERNEL);
	if (!attr_group) {
		imc_free_events(pmu->events, ct);
		return -ENOMEM;
	}

	/*
	 * Allocate memory for attributes.
	 * Since we have count of events for this pmu, we also allocate
	 * memory for the scale and unit attribute for now.
	 * "ct" has the total event structs added from the events-parent node.
	 * So allocate three times the "ct" (this includes event, event_scale and
	 * event_unit).
	 */
	attrs = kcalloc(((ct * 3) + 1), sizeof(struct attribute *), GFP_KERNEL);
	if (!attrs) {
		kfree(attr_group);
		imc_free_events(pmu->events, ct);
		return -ENOMEM;
	}

	attr_group->name = "events";
	attr_group->attrs = attrs;
	do {
		ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value);
		if (!ev_val_str)
			continue;
		dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str);
		if (!dev_str)
			continue;

		attrs[j++] = dev_str;
		if (pmu->events[i].scale) {
			ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name);
			if (!ev_scale_str)
				continue;
			dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale);
			if (!dev_str)
				continue;

			attrs[j++] = dev_str;
		}

		if (pmu->events[i].unit) {
			ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name);
			if (!ev_unit_str)
				continue;
			dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit);
			if (!dev_str)
				continue;

			attrs[j++] = dev_str;
		}
	} while (++i < ct);

	/* Save the event attribute */
	pmu->attr_groups[IMC_EVENT_ATTR] = attr_group;

	return 0;
}

/* get_nest_pmu_ref: Return the imc_pmu_ref struct for the given node */
static struct imc_pmu_ref *get_nest_pmu_ref(int cpu)
{
	return per_cpu(local_nest_imc_refc, cpu);
}

static void nest_change_cpu_context(int old_cpu, int new_cpu)
{
	struct imc_pmu **pn = per_nest_pmu_arr;

	if (old_cpu < 0 || new_cpu < 0)
		return;

	while (*pn) {
		perf_pmu_migrate_context(&(*pn)->pmu, old_cpu, new_cpu);
		pn++;
	}
}

static int ppc_nest_imc_cpu_offline(unsigned int cpu)
{
	int nid, target = -1;
	const struct cpumask *l_cpumask;
	struct imc_pmu_ref *ref;

	/*
	 * Check in the designated list for this cpu. Dont bother
	 * if not one of them.
	 */
	if (!cpumask_test_and_clear_cpu(cpu, &nest_imc_cpumask))
		return 0;

	/*
	 * Check whether nest_imc is registered. We could end up here if the
	 * cpuhotplug callback registration fails. i.e, callback invokes the
	 * offline path for all successfully registered nodes. At this stage,
	 * nest_imc pmu will not be registered and we should return here.
	 *
	 * We return with a zero since this is not an offline failure. And
	 * cpuhp_setup_state() returns the actual failure reason to the caller,
	 * which in turn will call the cleanup routine.
	 */
	if (!nest_pmus)
		return 0;

	/*
	 * Now that this cpu is one of the designated,
	 * find a next cpu a) which is online and b) in same chip.
	 */
	nid = cpu_to_node(cpu);
	l_cpumask = cpumask_of_node(nid);
	target = cpumask_last(l_cpumask);

	/*
	 * If this(target) is the last cpu in the cpumask for this chip,
	 * check for any possible online cpu in the chip.
	 */
	if (unlikely(target == cpu))
		target = cpumask_any_but(l_cpumask, cpu);

	/*
	 * Update the cpumask with the target cpu and
	 * migrate the context if needed
	 */
	if (target >= 0 && target < nr_cpu_ids) {
		cpumask_set_cpu(target, &nest_imc_cpumask);
		nest_change_cpu_context(cpu, target);
	} else {
		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
				       get_hard_smp_processor_id(cpu));
		/*
		 * If this is the last cpu in this chip then, skip the reference
		 * count lock and make the reference count on this chip zero.
		 */
		ref = get_nest_pmu_ref(cpu);
		if (!ref)
			return -EINVAL;

		ref->refc = 0;
	}
	return 0;
}

static int ppc_nest_imc_cpu_online(unsigned int cpu)
{
	const struct cpumask *l_cpumask;
	static struct cpumask tmp_mask;
	int res;

	/* Get the cpumask of this node */
	l_cpumask = cpumask_of_node(cpu_to_node(cpu));

	/*
	 * If this is not the first online CPU on this node, then
	 * just return.
	 */
	if (cpumask_and(&tmp_mask, l_cpumask, &nest_imc_cpumask))
		return 0;

	/*
	 * If this is the first online cpu on this node
	 * disable the nest counters by making an OPAL call.
	 */
	res = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
				     get_hard_smp_processor_id(cpu));
	if (res)
		return res;

	/* Make this CPU the designated target for counter collection */
	cpumask_set_cpu(cpu, &nest_imc_cpumask);
	return 0;
}

static int nest_pmu_cpumask_init(void)
{
	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
				 "perf/powerpc/imc:online",
				 ppc_nest_imc_cpu_online,
				 ppc_nest_imc_cpu_offline);
}

static void nest_imc_counters_release(struct perf_event *event)
{
	int rc, node_id;
	struct imc_pmu_ref *ref;

	if (event->cpu < 0)
		return;

	node_id = cpu_to_node(event->cpu);

	/*
	 * See if we need to disable the nest PMU.
	 * If no events are currently in use, then we have to take a
	 * lock to ensure that we don't race with another task doing
	 * enable or disable the nest counters.
	 */
	ref = get_nest_pmu_ref(event->cpu);
	if (!ref)
		return;

	/* Take the lock for this node and then decrement the reference count */
	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		/*
		 * The scenario where this is true is, when perf session is
		 * started, followed by offlining of all cpus in a given node.
		 *
		 * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline()
		 * function set the ref->count to zero, if the cpu which is
		 * about to offline is the last cpu in a given node and make
		 * an OPAL call to disable the engine in that node.
		 *
		 */
		spin_unlock(&ref->lock);
		return;
	}
	ref->refc--;
	if (ref->refc == 0) {
		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
					    get_hard_smp_processor_id(event->cpu));
		if (rc) {
			spin_unlock(&ref->lock);
			pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id);
			return;
		}
	} else if (ref->refc < 0) {
		WARN(1, "nest-imc: Invalid event reference count\n");
		ref->refc = 0;
	}
	spin_unlock(&ref->lock);
}

static int nest_imc_event_init(struct perf_event *event)
{
	int chip_id, rc, node_id;
	u32 l_config, config = event->attr.config;
	struct imc_mem_info *pcni;
	struct imc_pmu *pmu;
	struct imc_pmu_ref *ref;
	bool flag = false;

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

	/* Sampling not supported */
	if (event->hw.sample_period)
		return -EINVAL;

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

	pmu = imc_event_to_pmu(event);

	/* Sanity check for config (event offset) */
	if ((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size)
		return -EINVAL;

	/*
	 * Nest HW counter memory resides in a per-chip reserve-memory (HOMER).
	 * Get the base memory address for this cpu.
	 */
	chip_id = cpu_to_chip_id(event->cpu);

	/* Return, if chip_id is not valid */
	if (chip_id < 0)
		return -ENODEV;

	pcni = pmu->mem_info;
	do {
		if (pcni->id == chip_id) {
			flag = true;
			break;
		}
		pcni++;
	} while (pcni->vbase);

	if (!flag)
		return -ENODEV;

	/*
	 * Add the event offset to the base address.
	 */
	l_config = config & IMC_EVENT_OFFSET_MASK;
	event->hw.event_base = (u64)pcni->vbase + l_config;
	node_id = cpu_to_node(event->cpu);

	/*
	 * Get the imc_pmu_ref struct for this node.
	 * Take the lock and then increment the count of nest pmu events inited.
	 */
	ref = get_nest_pmu_ref(event->cpu);
	if (!ref)
		return -EINVAL;

	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST,
					     get_hard_smp_processor_id(event->cpu));
		if (rc) {
			spin_unlock(&ref->lock);
			pr_err("nest-imc: Unable to start the counters for node %d\n",
									node_id);
			return rc;
		}
	}
	++ref->refc;
	spin_unlock(&ref->lock);

	event->destroy = nest_imc_counters_release;
	return 0;
}

/*
 * core_imc_mem_init : Initializes memory for the current core.
 *
 * Uses alloc_pages_node() and uses the returned address as an argument to
 * an opal call to configure the pdbar. The address sent as an argument is
 * converted to physical address before the opal call is made. This is the
 * base address at which the core imc counters are populated.
 */
static int core_imc_mem_init(int cpu, int size)
{
	int nid, rc = 0, core_id = (cpu / threads_per_core);
	struct imc_mem_info *mem_info;
	struct page *page;

	/*
	 * alloc_pages_node() will allocate memory for core in the
	 * local node only.
	 */
	nid = cpu_to_node(cpu);
	mem_info = &core_imc_pmu->mem_info[core_id];
	mem_info->id = core_id;

	/* We need only vbase for core counters */
	page = alloc_pages_node(nid,
				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
				__GFP_NOWARN, get_order(size));
	if (!page)
		return -ENOMEM;
	mem_info->vbase = page_address(page);

	core_imc_refc[core_id].id = core_id;
	spin_lock_init(&core_imc_refc[core_id].lock);

	rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE,
				__pa((void *)mem_info->vbase),
				get_hard_smp_processor_id(cpu));
	if (rc) {
		free_pages((u64)mem_info->vbase, get_order(size));
		mem_info->vbase = NULL;
	}

	return rc;
}

static bool is_core_imc_mem_inited(int cpu)
{
	struct imc_mem_info *mem_info;
	int core_id = (cpu / threads_per_core);

	mem_info = &core_imc_pmu->mem_info[core_id];
	if (!mem_info->vbase)
		return false;

	return true;
}

static int ppc_core_imc_cpu_online(unsigned int cpu)
{
	const struct cpumask *l_cpumask;
	static struct cpumask tmp_mask;
	int ret = 0;

	/* Get the cpumask for this core */
	l_cpumask = cpu_sibling_mask(cpu);

	/* If a cpu for this core is already set, then, don't do anything */
	if (cpumask_and(&tmp_mask, l_cpumask, &core_imc_cpumask))
		return 0;

	if (!is_core_imc_mem_inited(cpu)) {
		ret = core_imc_mem_init(cpu, core_imc_pmu->counter_mem_size);
		if (ret) {
			pr_info("core_imc memory allocation for cpu %d failed\n", cpu);
			return ret;
		}
	}

	/* set the cpu in the mask */
	cpumask_set_cpu(cpu, &core_imc_cpumask);
	return 0;
}

static int ppc_core_imc_cpu_offline(unsigned int cpu)
{
	unsigned int core_id;
	int ncpu;
	struct imc_pmu_ref *ref;

	/*
	 * clear this cpu out of the mask, if not present in the mask,
	 * don't bother doing anything.
	 */
	if (!cpumask_test_and_clear_cpu(cpu, &core_imc_cpumask))
		return 0;

	/*
	 * Check whether core_imc is registered. We could end up here
	 * if the cpuhotplug callback registration fails. i.e, callback
	 * invokes the offline path for all successfully registered cpus.
	 * At this stage, core_imc pmu will not be registered and we
	 * should return here.
	 *
	 * We return with a zero since this is not an offline failure.
	 * And cpuhp_setup_state() returns the actual failure reason
	 * to the caller, which inturn will call the cleanup routine.
	 */
	if (!core_imc_pmu->pmu.event_init)
		return 0;

	/* Find any online cpu in that core except the current "cpu" */
	ncpu = cpumask_last(cpu_sibling_mask(cpu));

	if (unlikely(ncpu == cpu))
		ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu);

	if (ncpu >= 0 && ncpu < nr_cpu_ids) {
		cpumask_set_cpu(ncpu, &core_imc_cpumask);
		perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu);
	} else {
		/*
		 * If this is the last cpu in this core then skip taking reference
		 * count lock for this core and directly zero "refc" for this core.
		 */
		opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
				       get_hard_smp_processor_id(cpu));
		core_id = cpu / threads_per_core;
		ref = &core_imc_refc[core_id];
		if (!ref)
			return -EINVAL;

		ref->refc = 0;
		/*
		 * Reduce the global reference count, if this is the
		 * last cpu in this core and core-imc event running
		 * in this cpu.
		 */
		spin_lock(&imc_global_refc.lock);
		if (imc_global_refc.id == IMC_DOMAIN_CORE)
			imc_global_refc.refc--;

		spin_unlock(&imc_global_refc.lock);
	}
	return 0;
}

static int core_imc_pmu_cpumask_init(void)
{
	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
				 "perf/powerpc/imc_core:online",
				 ppc_core_imc_cpu_online,
				 ppc_core_imc_cpu_offline);
}

static void reset_global_refc(struct perf_event *event)
{
		spin_lock(&imc_global_refc.lock);
		imc_global_refc.refc--;

		/*
		 * If no other thread is running any
		 * event for this domain(thread/core/trace),
		 * set the global id to zero.
		 */
		if (imc_global_refc.refc <= 0) {
			imc_global_refc.refc = 0;
			imc_global_refc.id = 0;
		}
		spin_unlock(&imc_global_refc.lock);
}

static void core_imc_counters_release(struct perf_event *event)
{
	int rc, core_id;
	struct imc_pmu_ref *ref;

	if (event->cpu < 0)
		return;
	/*
	 * See if we need to disable the IMC PMU.
	 * If no events are currently in use, then we have to take a
	 * lock to ensure that we don't race with another task doing
	 * enable or disable the core counters.
	 */
	core_id = event->cpu / threads_per_core;

	/* Take the lock and decrement the refernce count for this core */
	ref = &core_imc_refc[core_id];
	if (!ref)
		return;

	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		/*
		 * The scenario where this is true is, when perf session is
		 * started, followed by offlining of all cpus in a given core.
		 *
		 * In the cpuhotplug offline path, ppc_core_imc_cpu_offline()
		 * function set the ref->count to zero, if the cpu which is
		 * about to offline is the last cpu in a given core and make
		 * an OPAL call to disable the engine in that core.
		 *
		 */
		spin_unlock(&ref->lock);
		return;
	}
	ref->refc--;
	if (ref->refc == 0) {
		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
					    get_hard_smp_processor_id(event->cpu));
		if (rc) {
			spin_unlock(&ref->lock);
			pr_err("IMC: Unable to stop the counters for core %d\n", core_id);
			return;
		}
	} else if (ref->refc < 0) {
		WARN(1, "core-imc: Invalid event reference count\n");
		ref->refc = 0;
	}
	spin_unlock(&ref->lock);

	reset_global_refc(event);
}

static int core_imc_event_init(struct perf_event *event)
{
	int core_id, rc;
	u64 config = event->attr.config;
	struct imc_mem_info *pcmi;
	struct imc_pmu *pmu;
	struct imc_pmu_ref *ref;

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

	/* Sampling not supported */
	if (event->hw.sample_period)
		return -EINVAL;

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

	event->hw.idx = -1;
	pmu = imc_event_to_pmu(event);

	/* Sanity check for config (event offset) */
	if (((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size))
		return -EINVAL;

	if (!is_core_imc_mem_inited(event->cpu))
		return -ENODEV;

	core_id = event->cpu / threads_per_core;
	pcmi = &core_imc_pmu->mem_info[core_id];
	if ((!pcmi->vbase))
		return -ENODEV;

	ref = &core_imc_refc[core_id];
	if (!ref)
		return -EINVAL;

	/*
	 * Core pmu units are enabled only when it is used.
	 * See if this is triggered for the first time.
	 * If yes, take the lock and enable the core counters.
	 * If not, just increment the count in core_imc_refc struct.
	 */
	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
					     get_hard_smp_processor_id(event->cpu));
		if (rc) {
			spin_unlock(&ref->lock);
			pr_err("core-imc: Unable to start the counters for core %d\n",
									core_id);
			return rc;
		}
	}
	++ref->refc;
	spin_unlock(&ref->lock);

	/*
	 * Since the system can run either in accumulation or trace-mode
	 * of IMC at a time, core-imc events are allowed only if no other
	 * trace/thread imc events are enabled/monitored.
	 *
	 * Take the global lock, and check the refc.id
	 * to know whether any other trace/thread imc
	 * events are running.
	 */
	spin_lock(&imc_global_refc.lock);
	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
		/*
		 * No other trace/thread imc events are running in
		 * the system, so set the refc.id to core-imc.
		 */
		imc_global_refc.id = IMC_DOMAIN_CORE;
		imc_global_refc.refc++;
	} else {
		spin_unlock(&imc_global_refc.lock);
		return -EBUSY;
	}
	spin_unlock(&imc_global_refc.lock);

	event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
	event->destroy = core_imc_counters_release;
	return 0;
}

/*
 * Allocates a page of memory for each of the online cpus, and load
 * LDBAR with 0.
 * The physical base address of the page allocated for a cpu will be
 * written to the LDBAR for that cpu, when the thread-imc event
 * is added.
 *
 * LDBAR Register Layout:
 *
 *  0          4         8         12        16        20        24        28
 * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
 *   | |       [   ]    [                   Counter Address [8:50]
 *   | * Mode    |
 *   |           * PB Scope
 *   * Enable/Disable
 *
 *  32        36        40        44        48        52        56        60
 * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
 *           Counter Address [8:50]              ]
 *
 */
static int thread_imc_mem_alloc(int cpu_id, int size)
{
	u64 *local_mem = per_cpu(thread_imc_mem, cpu_id);
	int nid = cpu_to_node(cpu_id);

	if (!local_mem) {
		struct page *page;
		/*
		 * This case could happen only once at start, since we dont
		 * free the memory in cpu offline path.
		 */
		page = alloc_pages_node(nid,
				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
				  __GFP_NOWARN, get_order(size));
		if (!page)
			return -ENOMEM;
		local_mem = page_address(page);

		per_cpu(thread_imc_mem, cpu_id) = local_mem;
	}

	mtspr(SPRN_LDBAR, 0);
	return 0;
}

static int ppc_thread_imc_cpu_online(unsigned int cpu)
{
	return thread_imc_mem_alloc(cpu, thread_imc_mem_size);
}

static int ppc_thread_imc_cpu_offline(unsigned int cpu)
{
	/*
	 * Set the bit 0 of LDBAR to zero.
	 *
	 * If bit 0 of LDBAR is unset, it will stop posting
	 * the counter data to memory.
	 * For thread-imc, bit 0 of LDBAR will be set to 1 in the
	 * event_add function. So reset this bit here, to stop the updates
	 * to memory in the cpu_offline path.
	 */
	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));

	/* Reduce the refc if thread-imc event running on this cpu */
	spin_lock(&imc_global_refc.lock);
	if (imc_global_refc.id == IMC_DOMAIN_THREAD)
		imc_global_refc.refc--;
	spin_unlock(&imc_global_refc.lock);

	return 0;
}

static int thread_imc_cpu_init(void)
{
	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
			  "perf/powerpc/imc_thread:online",
			  ppc_thread_imc_cpu_online,
			  ppc_thread_imc_cpu_offline);
}

static int thread_imc_event_init(struct perf_event *event)
{
	u32 config = event->attr.config;
	struct task_struct *target;
	struct imc_pmu *pmu;

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

	if (!perfmon_capable())
		return -EACCES;

	/* Sampling not supported */
	if (event->hw.sample_period)
		return -EINVAL;

	event->hw.idx = -1;
	pmu = imc_event_to_pmu(event);

	/* Sanity check for config offset */
	if (((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size))
		return -EINVAL;

	target = event->hw.target;
	if (!target)
		return -EINVAL;

	spin_lock(&imc_global_refc.lock);
	/*
	 * Check if any other trace/core imc events are running in the
	 * system, if not set the global id to thread-imc.
	 */
	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) {
		imc_global_refc.id = IMC_DOMAIN_THREAD;
		imc_global_refc.refc++;
	} else {
		spin_unlock(&imc_global_refc.lock);
		return -EBUSY;
	}
	spin_unlock(&imc_global_refc.lock);

	event->pmu->task_ctx_nr = perf_sw_context;
	event->destroy = reset_global_refc;
	return 0;
}

static bool is_thread_imc_pmu(struct perf_event *event)
{
	if (!strncmp(event->pmu->name, "thread_imc", strlen("thread_imc")))
		return true;

	return false;
}

static __be64 *get_event_base_addr(struct perf_event *event)
{
	u64 addr;

	if (is_thread_imc_pmu(event)) {
		addr = (u64)per_cpu(thread_imc_mem, smp_processor_id());
		return (__be64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK));
	}

	return (__be64 *)event->hw.event_base;
}

static void thread_imc_pmu_start_txn(struct pmu *pmu,
				     unsigned int txn_flags)
{
	if (txn_flags & ~PERF_PMU_TXN_ADD)
		return;
	perf_pmu_disable(pmu);
}

static void thread_imc_pmu_cancel_txn(struct pmu *pmu)
{
	perf_pmu_enable(pmu);
}

static int thread_imc_pmu_commit_txn(struct pmu *pmu)
{
	perf_pmu_enable(pmu);
	return 0;
}

static u64 imc_read_counter(struct perf_event *event)
{
	__be64 *addr;
	u64 data;

	/*
	 * In-Memory Collection (IMC) counters are free flowing counters.
	 * So we take a snapshot of the counter value on enable and save it
	 * to calculate the delta at later stage to present the event counter
	 * value.
	 */
	addr = get_event_base_addr(event);
	data = be64_to_cpu(READ_ONCE(*addr));
	local64_set(&event->hw.prev_count, data);

	return data;
}

static void imc_event_update(struct perf_event *event)
{
	u64 counter_prev, counter_new, final_count;

	counter_prev = local64_read(&event->hw.prev_count);
	counter_new = imc_read_counter(event);
	final_count = counter_new - counter_prev;

	/* Update the delta to the event count */
	local64_add(final_count, &event->count);
}

static void imc_event_start(struct perf_event *event, int flags)
{
	/*
	 * In Memory Counters are free flowing counters. HW or the microcode
	 * keeps adding to the counter offset in memory. To get event
	 * counter value, we snapshot the value here and we calculate
	 * delta at later point.
	 */
	imc_read_counter(event);
}

static void imc_event_stop(struct perf_event *event, int flags)
{
	/*
	 * Take a snapshot and calculate the delta and update
	 * the event counter values.
	 */
	imc_event_update(event);
}

static int imc_event_add(struct perf_event *event, int flags)
{
	if (flags & PERF_EF_START)
		imc_event_start(event, flags);

	return 0;
}

static int thread_imc_event_add(struct perf_event *event, int flags)
{
	int core_id;
	struct imc_pmu_ref *ref;
	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, smp_processor_id());

	if (flags & PERF_EF_START)
		imc_event_start(event, flags);

	if (!is_core_imc_mem_inited(smp_processor_id()))
		return -EINVAL;

	core_id = smp_processor_id() / threads_per_core;
	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE;
	mtspr(SPRN_LDBAR, ldbar_value);

	/*
	 * imc pmus are enabled only when it is used.
	 * See if this is triggered for the first time.
	 * If yes, take the lock and enable the counters.
	 * If not, just increment the count in ref count struct.
	 */
	ref = &core_imc_refc[core_id];
	if (!ref)
		return -EINVAL;

	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
		    get_hard_smp_processor_id(smp_processor_id()))) {
			spin_unlock(&ref->lock);
			pr_err("thread-imc: Unable to start the counter\
				for core %d\n", core_id);
			return -EINVAL;
		}
	}
	++ref->refc;
	spin_unlock(&ref->lock);
	return 0;
}

static void thread_imc_event_del(struct perf_event *event, int flags)
{

	int core_id;
	struct imc_pmu_ref *ref;

	core_id = smp_processor_id() / threads_per_core;
	ref = &core_imc_refc[core_id];
	if (!ref) {
		pr_debug("imc: Failed to get event reference count\n");
		return;
	}

	spin_lock(&ref->lock);
	ref->refc--;
	if (ref->refc == 0) {
		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
		    get_hard_smp_processor_id(smp_processor_id()))) {
			spin_unlock(&ref->lock);
			pr_err("thread-imc: Unable to stop the counters\
				for core %d\n", core_id);
			return;
		}
	} else if (ref->refc < 0) {
		ref->refc = 0;
	}
	spin_unlock(&ref->lock);

	/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));

	/*
	 * Take a snapshot and calculate the delta and update
	 * the event counter values.
	 */
	imc_event_update(event);
}

/*
 * Allocate a page of memory for each cpu, and load LDBAR with 0.
 */
static int trace_imc_mem_alloc(int cpu_id, int size)
{
	u64 *local_mem = per_cpu(trace_imc_mem, cpu_id);
	int phys_id = cpu_to_node(cpu_id), rc = 0;
	int core_id = (cpu_id / threads_per_core);

	if (!local_mem) {
		struct page *page;

		page = alloc_pages_node(phys_id,
				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
				__GFP_NOWARN, get_order(size));
		if (!page)
			return -ENOMEM;
		local_mem = page_address(page);
		per_cpu(trace_imc_mem, cpu_id) = local_mem;

		/* Initialise the counters for trace mode */
		rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_TRACE, __pa((void *)local_mem),
					    get_hard_smp_processor_id(cpu_id));
		if (rc) {
			pr_info("IMC:opal init failed for trace imc\n");
			return rc;
		}
	}

	trace_imc_refc[core_id].id = core_id;
	spin_lock_init(&trace_imc_refc[core_id].lock);

	mtspr(SPRN_LDBAR, 0);
	return 0;
}

static int ppc_trace_imc_cpu_online(unsigned int cpu)
{
	return trace_imc_mem_alloc(cpu, trace_imc_mem_size);
}

static int ppc_trace_imc_cpu_offline(unsigned int cpu)
{
	/*
	 * No need to set bit 0 of LDBAR to zero, as
	 * it is set to zero for imc trace-mode
	 *
	 * Reduce the refc if any trace-imc event running
	 * on this cpu.
	 */
	spin_lock(&imc_global_refc.lock);
	if (imc_global_refc.id == IMC_DOMAIN_TRACE)
		imc_global_refc.refc--;
	spin_unlock(&imc_global_refc.lock);

	return 0;
}

static int trace_imc_cpu_init(void)
{
	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
			  "perf/powerpc/imc_trace:online",
			  ppc_trace_imc_cpu_online,
			  ppc_trace_imc_cpu_offline);
}

static u64 get_trace_imc_event_base_addr(void)
{
	return (u64)per_cpu(trace_imc_mem, smp_processor_id());
}

/*
 * Function to parse trace-imc data obtained
 * and to prepare the perf sample.
 */
static int trace_imc_prepare_sample(struct trace_imc_data *mem,
				    struct perf_sample_data *data,
				    u64 *prev_tb,
				    struct perf_event_header *header,
				    struct perf_event *event)
{
	/* Sanity checks for a valid record */
	if (be64_to_cpu(READ_ONCE(mem->tb1)) > *prev_tb)
		*prev_tb = be64_to_cpu(READ_ONCE(mem->tb1));
	else
		return -EINVAL;

	if ((be64_to_cpu(READ_ONCE(mem->tb1)) & IMC_TRACE_RECORD_TB1_MASK) !=
			 be64_to_cpu(READ_ONCE(mem->tb2)))
		return -EINVAL;

	/* Prepare perf sample */
	data->ip =  be64_to_cpu(READ_ONCE(mem->ip));
	data->period = event->hw.last_period;

	header->type = PERF_RECORD_SAMPLE;
	header->size = sizeof(*header) + event->header_size;
	header->misc = 0;

	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
		switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) {
		case 0:/* when MSR HV and PR not set in the trace-record */
			header->misc |= PERF_RECORD_MISC_GUEST_KERNEL;
			break;
		case 1: /* MSR HV is 0 and PR is 1 */
			header->misc |= PERF_RECORD_MISC_GUEST_USER;
			break;
		case 2: /* MSR HV is 1 and PR is 0 */
			header->misc |= PERF_RECORD_MISC_KERNEL;
			break;
		case 3: /* MSR HV is 1 and PR is 1 */
			header->misc |= PERF_RECORD_MISC_USER;
			break;
		default:
			pr_info("IMC: Unable to set the flag based on MSR bits\n");
			break;
		}
	} else {
		if (is_kernel_addr(data->ip))
			header->misc |= PERF_RECORD_MISC_KERNEL;
		else
			header->misc |= PERF_RECORD_MISC_USER;
	}
	perf_event_header__init_id(header, data, event);

	return 0;
}

static void dump_trace_imc_data(struct perf_event *event)
{
	struct trace_imc_data *mem;
	int i, ret;
	u64 prev_tb = 0;

	mem = (struct trace_imc_data *)get_trace_imc_event_base_addr();
	for (i = 0; i < (trace_imc_mem_size / sizeof(struct trace_imc_data));
		i++, mem++) {
		struct perf_sample_data data;
		struct perf_event_header header;

		ret = trace_imc_prepare_sample(mem, &data, &prev_tb, &header, event);
		if (ret) /* Exit, if not a valid record */
			break;
		else {
			/* If this is a valid record, create the sample */
			struct perf_output_handle handle;

			if (perf_output_begin(&handle, &data, event, header.size))
				return;

			perf_output_sample(&handle, &header, &data, event);
			perf_output_end(&handle);
		}
	}
}

static int trace_imc_event_add(struct perf_event *event, int flags)
{
	int core_id = smp_processor_id() / threads_per_core;
	struct imc_pmu_ref *ref = NULL;
	u64 local_mem, ldbar_value;

	/* Set trace-imc bit in ldbar and load ldbar with per-thread memory address */
	local_mem = get_trace_imc_event_base_addr();
	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE;

	/* trace-imc reference count */
	if (trace_imc_refc)
		ref = &trace_imc_refc[core_id];
	if (!ref) {
		pr_debug("imc: Failed to get the event reference count\n");
		return -EINVAL;
	}

	mtspr(SPRN_LDBAR, ldbar_value);
	spin_lock(&ref->lock);
	if (ref->refc == 0) {
		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
				get_hard_smp_processor_id(smp_processor_id()))) {
			spin_unlock(&ref->lock);
			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
			return -EINVAL;
		}
	}
	++ref->refc;
	spin_unlock(&ref->lock);
	return 0;
}

static void trace_imc_event_read(struct perf_event *event)
{
	return;
}

static void trace_imc_event_stop(struct perf_event *event, int flags)
{
	u64 local_mem = get_trace_imc_event_base_addr();
	dump_trace_imc_data(event);
	memset((void *)local_mem, 0, sizeof(u64));
}

static void trace_imc_event_start(struct perf_event *event, int flags)
{
	return;
}

static void trace_imc_event_del(struct perf_event *event, int flags)
{
	int core_id = smp_processor_id() / threads_per_core;
	struct imc_pmu_ref *ref = NULL;

	if (trace_imc_refc)
		ref = &trace_imc_refc[core_id];
	if (!ref) {
		pr_debug("imc: Failed to get event reference count\n");
		return;
	}

	spin_lock(&ref->lock);
	ref->refc--;
	if (ref->refc == 0) {
		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
				get_hard_smp_processor_id(smp_processor_id()))) {
			spin_unlock(&ref->lock);
			pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
			return;
		}
	} else if (ref->refc < 0) {
		ref->refc = 0;
	}
	spin_unlock(&ref->lock);

	trace_imc_event_stop(event, flags);
}

static int trace_imc_event_init(struct perf_event *event)
{
	if (event->attr.type != event->pmu->type)
		return -ENOENT;

	if (!perfmon_capable())
		return -EACCES;

	/* Return if this is a couting event */
	if (event->attr.sample_period == 0)
		return -ENOENT;

	/*
	 * Take the global lock, and make sure
	 * no other thread is running any core/thread imc
	 * events
	 */
	spin_lock(&imc_global_refc.lock);
	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
		/*
		 * No core/thread imc events are running in the
		 * system, so set the refc.id to trace-imc.
		 */
		imc_global_refc.id = IMC_DOMAIN_TRACE;
		imc_global_refc.refc++;
	} else {
		spin_unlock(&imc_global_refc.lock);
		return -EBUSY;
	}
	spin_unlock(&imc_global_refc.lock);

	event->hw.idx = -1;

	/*
	 * There can only be a single PMU for perf_hw_context events which is assigned to
	 * core PMU. Hence use "perf_sw_context" for trace_imc.
	 */
	event->pmu->task_ctx_nr = perf_sw_context;
	event->destroy = reset_global_refc;
	return 0;
}

/* update_pmu_ops : Populate the appropriate operations for "pmu" */
static int update_pmu_ops(struct imc_pmu *pmu)
{
	pmu->pmu.task_ctx_nr = perf_invalid_context;
	pmu->pmu.add = imc_event_add;
	pmu->pmu.del = imc_event_stop;
	pmu->pmu.start = imc_event_start;
	pmu->pmu.stop = imc_event_stop;
	pmu->pmu.read = imc_event_update;
	pmu->pmu.attr_groups = pmu->attr_groups;
	pmu->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
	pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group;

	switch (pmu->domain) {
	case IMC_DOMAIN_NEST:
		pmu->pmu.event_init = nest_imc_event_init;
		pmu->attr_groups[IMC_CPUMASK_ATTR] = &imc_pmu_cpumask_attr_group;
		break;
	case IMC_DOMAIN_CORE:
		pmu->pmu.event_init = core_imc_event_init;
		pmu->attr_groups[IMC_CPUMASK_ATTR] = &imc_pmu_cpumask_attr_group;
		break;
	case IMC_DOMAIN_THREAD:
		pmu->pmu.event_init = thread_imc_event_init;
		pmu->pmu.add = thread_imc_event_add;
		pmu->pmu.del = thread_imc_event_del;
		pmu->pmu.start_txn = thread_imc_pmu_start_txn;
		pmu->pmu.cancel_txn = thread_imc_pmu_cancel_txn;
		pmu->pmu.commit_txn = thread_imc_pmu_commit_txn;
		break;
	case IMC_DOMAIN_TRACE:
		pmu->pmu.event_init = trace_imc_event_init;
		pmu->pmu.add = trace_imc_event_add;
		pmu->pmu.del = trace_imc_event_del;
		pmu->pmu.start = trace_imc_event_start;
		pmu->pmu.stop = trace_imc_event_stop;
		pmu->pmu.read = trace_imc_event_read;
		pmu->attr_groups[IMC_FORMAT_ATTR] = &trace_imc_format_group;
		break;
	default:
		break;
	}

	return 0;
}

/* init_nest_pmu_ref: Initialize the imc_pmu_ref struct for all the nodes */
static int init_nest_pmu_ref(void)
{
	int nid, i, cpu;

	nest_imc_refc = kcalloc(num_possible_nodes(), sizeof(*nest_imc_refc),
								GFP_KERNEL);

	if (!nest_imc_refc)
		return -ENOMEM;

	i = 0;
	for_each_node(nid) {
		/*
		 * Take the lock to avoid races while tracking the number of
		 * sessions using the chip's nest pmu units.
		 */
		spin_lock_init(&nest_imc_refc[i].lock);

		/*
		 * Loop to init the "id" with the node_id. Variable "i" initialized to
		 * 0 and will be used as index to the array. "i" will not go off the
		 * end of the array since the "for_each_node" loops for "N_POSSIBLE"
		 * nodes only.
		 */
		nest_imc_refc[i++].id = nid;
	}

	/*
	 * Loop to init the per_cpu "local_nest_imc_refc" with the proper
	 * "nest_imc_refc" index. This makes get_nest_pmu_ref() alot simple.
	 */
	for_each_possible_cpu(cpu) {
		nid = cpu_to_node(cpu);
		for (i = 0; i < num_possible_nodes(); i++) {
			if (nest_imc_refc[i].id == nid) {
				per_cpu(local_nest_imc_refc, cpu) = &nest_imc_refc[i];
				break;
			}
		}
	}
	return 0;
}

static void cleanup_all_core_imc_memory(void)
{
	int i, nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
	struct imc_mem_info *ptr = core_imc_pmu->mem_info;
	int size = core_imc_pmu->counter_mem_size;

	/* mem_info will never be NULL */
	for (i = 0; i < nr_cores; i++) {
		if (ptr[i].vbase)
			free_pages((u64)ptr[i].vbase, get_order(size));
	}

	kfree(ptr);
	kfree(core_imc_refc);
}

static void thread_imc_ldbar_disable(void *dummy)
{
	/*
	 * By setting 0th bit of LDBAR to zero, we disable thread-imc
	 * updates to memory.
	 */
	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
}

void thread_imc_disable(void)
{
	on_each_cpu(thread_imc_ldbar_disable, NULL, 1);
}

static void cleanup_all_thread_imc_memory(void)
{
	int i, order = get_order(thread_imc_mem_size);

	for_each_online_cpu(i) {
		if (per_cpu(thread_imc_mem, i))
			free_pages((u64)per_cpu(thread_imc_mem, i), order);

	}
}

static void cleanup_all_trace_imc_memory(void)
{
	int i, order = get_order(trace_imc_mem_size);

	for_each_online_cpu(i) {
		if (per_cpu(trace_imc_mem, i))
			free_pages((u64)per_cpu(trace_imc_mem, i), order);

	}
	kfree(trace_imc_refc);
}

/* Function to free the attr_groups which are dynamically allocated */
static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
{
	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR])
		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
}

/*
 * Common function to unregister cpu hotplug callback and
 * free the memory.
 * TODO: Need to handle pmu unregistering, which will be
 * done in followup series.
 */
static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
{
	if (pmu_ptr->domain == IMC_DOMAIN_NEST) {
		mutex_lock(&nest_init_lock);
		if (nest_pmus == 1) {
			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
			kfree(nest_imc_refc);
			kfree(per_nest_pmu_arr);
			per_nest_pmu_arr = NULL;
		}

		if (nest_pmus > 0)
			nest_pmus--;
		mutex_unlock(&nest_init_lock);
	}

	/* Free core_imc memory */
	if (pmu_ptr->domain == IMC_DOMAIN_CORE) {
		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE);
		cleanup_all_core_imc_memory();
	}

	/* Free thread_imc memory */
	if (pmu_ptr->domain == IMC_DOMAIN_THREAD) {
		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE);
		cleanup_all_thread_imc_memory();
	}

	if (pmu_ptr->domain == IMC_DOMAIN_TRACE) {
		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE);
		cleanup_all_trace_imc_memory();
	}
}

/*
 * Function to unregister thread-imc if core-imc
 * is not registered.
 */
void unregister_thread_imc(void)
{
	imc_common_cpuhp_mem_free(thread_imc_pmu);
	imc_common_mem_free(thread_imc_pmu);
	perf_pmu_unregister(&thread_imc_pmu->pmu);
}

/*
 * imc_mem_init : Function to support memory allocation for core imc.
 */
static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent,
								int pmu_index)
{
	const char *s;
	int nr_cores, cpu, res = -ENOMEM;

	if (of_property_read_string(parent, "name", &s))
		return -ENODEV;

	switch (pmu_ptr->domain) {
	case IMC_DOMAIN_NEST:
		/* Update the pmu name */
		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s_imc", "nest_", s);
		if (!pmu_ptr->pmu.name)
			goto err;

		/* Needed for hotplug/migration */
		if (!per_nest_pmu_arr) {
			per_nest_pmu_arr = kcalloc(get_max_nest_dev() + 1,
						sizeof(struct imc_pmu *),
						GFP_KERNEL);
			if (!per_nest_pmu_arr)
				goto err;
		}
		per_nest_pmu_arr[pmu_index] = pmu_ptr;
		break;
	case IMC_DOMAIN_CORE:
		/* Update the pmu name */
		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc");
		if (!pmu_ptr->pmu.name)
			goto err;

		nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
		pmu_ptr->mem_info = kcalloc(nr_cores, sizeof(struct imc_mem_info),
								GFP_KERNEL);

		if (!pmu_ptr->mem_info)
			goto err;

		core_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref),
								GFP_KERNEL);

		if (!core_imc_refc) {
			kfree(pmu_ptr->mem_info);
			goto err;
		}

		core_imc_pmu = pmu_ptr;
		break;
	case IMC_DOMAIN_THREAD:
		/* Update the pmu name */
		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc");
		if (!pmu_ptr->pmu.name)
			goto err;

		thread_imc_mem_size = pmu_ptr->counter_mem_size;
		for_each_online_cpu(cpu) {
			res = thread_imc_mem_alloc(cpu, pmu_ptr->counter_mem_size);
			if (res) {
				cleanup_all_thread_imc_memory();
				goto err;
			}
		}

		thread_imc_pmu = pmu_ptr;
		break;
	case IMC_DOMAIN_TRACE:
		/* Update the pmu name */
		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc");
		if (!pmu_ptr->pmu.name)
			return -ENOMEM;

		nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
		trace_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref),
								GFP_KERNEL);
		if (!trace_imc_refc)
			return -ENOMEM;

		trace_imc_mem_size = pmu_ptr->counter_mem_size;
		for_each_online_cpu(cpu) {
			res = trace_imc_mem_alloc(cpu, trace_imc_mem_size);
			if (res) {
				cleanup_all_trace_imc_memory();
				goto err;
			}
		}
		break;
	default:
		return -EINVAL;
	}

	return 0;
err:
	return res;
}

/*
 * init_imc_pmu : Setup and register the IMC pmu device.
 *
 * @parent:	Device tree unit node
 * @pmu_ptr:	memory allocated for this pmu
 * @pmu_idx:	Count of nest pmc registered
 *
 * init_imc_pmu() setup pmu cpumask and registers for a cpu hotplug callback.
 * Handles failure cases and accordingly frees memory.
 */
int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_idx)
{
	int ret;

	ret = imc_mem_init(pmu_ptr, parent, pmu_idx);
	if (ret)
		goto err_free_mem;

	switch (pmu_ptr->domain) {
	case IMC_DOMAIN_NEST:
		/*
		* Nest imc pmu need only one cpu per chip, we initialize the
		* cpumask for the first nest imc pmu and use the same for the
		* rest. To handle the cpuhotplug callback unregister, we track
		* the number of nest pmus in "nest_pmus".
		*/
		mutex_lock(&nest_init_lock);
		if (nest_pmus == 0) {
			ret = init_nest_pmu_ref();
			if (ret) {
				mutex_unlock(&nest_init_lock);
				kfree(per_nest_pmu_arr);
				per_nest_pmu_arr = NULL;
				goto err_free_mem;
			}
			/* Register for cpu hotplug notification. */
			ret = nest_pmu_cpumask_init();
			if (ret) {
				mutex_unlock(&nest_init_lock);
				kfree(nest_imc_refc);
				kfree(per_nest_pmu_arr);
				per_nest_pmu_arr = NULL;
				goto err_free_mem;
			}
		}
		nest_pmus++;
		mutex_unlock(&nest_init_lock);
		break;
	case IMC_DOMAIN_CORE:
		ret = core_imc_pmu_cpumask_init();
		if (ret) {
			cleanup_all_core_imc_memory();
			goto err_free_mem;
		}

		break;
	case IMC_DOMAIN_THREAD:
		ret = thread_imc_cpu_init();
		if (ret) {
			cleanup_all_thread_imc_memory();
			goto err_free_mem;
		}

		break;
	case IMC_DOMAIN_TRACE:
		ret = trace_imc_cpu_init();
		if (ret) {
			cleanup_all_trace_imc_memory();
			goto err_free_mem;
		}

		break;
	default:
		return  -EINVAL;	/* Unknown domain */
	}

	ret = update_events_in_group(parent, pmu_ptr);
	if (ret)
		goto err_free_cpuhp_mem;

	ret = update_pmu_ops(pmu_ptr);
	if (ret)
		goto err_free_cpuhp_mem;

	ret = perf_pmu_register(&pmu_ptr->pmu, pmu_ptr->pmu.name, -1);
	if (ret)
		goto err_free_cpuhp_mem;

	pr_debug("%s performance monitor hardware support registered\n",
							pmu_ptr->pmu.name);

	return 0;

err_free_cpuhp_mem:
	imc_common_cpuhp_mem_free(pmu_ptr);
err_free_mem:
	imc_common_mem_free(pmu_ptr);
	return ret;
}