summaryrefslogtreecommitdiffstats
path: root/arch/x86/events/intel/uncore.c
blob: d5c6d3b340c503cebeab5d79d683a3739fb362fe (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
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>

#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "uncore.h"

static struct intel_uncore_type *empty_uncore[] = { NULL, };
struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
struct intel_uncore_type **uncore_mmio_uncores = empty_uncore;

static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
/* pci bus to socket mapping */
DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
struct pci_extra_dev *uncore_extra_pci_dev;
int __uncore_max_dies;

/* mask of cpus that collect uncore events */
static cpumask_t uncore_cpu_mask;

/* constraint for the fixed counter */
static struct event_constraint uncore_constraint_fixed =
	EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
struct event_constraint uncore_constraint_empty =
	EVENT_CONSTRAINT(0, 0, 0);

MODULE_LICENSE("GPL");

int uncore_pcibus_to_physid(struct pci_bus *bus)
{
	struct pci2phy_map *map;
	int phys_id = -1;

	raw_spin_lock(&pci2phy_map_lock);
	list_for_each_entry(map, &pci2phy_map_head, list) {
		if (map->segment == pci_domain_nr(bus)) {
			phys_id = map->pbus_to_physid[bus->number];
			break;
		}
	}
	raw_spin_unlock(&pci2phy_map_lock);

	return phys_id;
}

static void uncore_free_pcibus_map(void)
{
	struct pci2phy_map *map, *tmp;

	list_for_each_entry_safe(map, tmp, &pci2phy_map_head, list) {
		list_del(&map->list);
		kfree(map);
	}
}

struct pci2phy_map *__find_pci2phy_map(int segment)
{
	struct pci2phy_map *map, *alloc = NULL;
	int i;

	lockdep_assert_held(&pci2phy_map_lock);

lookup:
	list_for_each_entry(map, &pci2phy_map_head, list) {
		if (map->segment == segment)
			goto end;
	}

	if (!alloc) {
		raw_spin_unlock(&pci2phy_map_lock);
		alloc = kmalloc(sizeof(struct pci2phy_map), GFP_KERNEL);
		raw_spin_lock(&pci2phy_map_lock);

		if (!alloc)
			return NULL;

		goto lookup;
	}

	map = alloc;
	alloc = NULL;
	map->segment = segment;
	for (i = 0; i < 256; i++)
		map->pbus_to_physid[i] = -1;
	list_add_tail(&map->list, &pci2phy_map_head);

end:
	kfree(alloc);
	return map;
}

ssize_t uncore_event_show(struct kobject *kobj,
			  struct kobj_attribute *attr, char *buf)
{
	struct uncore_event_desc *event =
		container_of(attr, struct uncore_event_desc, attr);
	return sprintf(buf, "%s", event->config);
}

struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
	unsigned int dieid = topology_logical_die_id(cpu);

	/*
	 * The unsigned check also catches the '-1' return value for non
	 * existent mappings in the topology map.
	 */
	return dieid < uncore_max_dies() ? pmu->boxes[dieid] : NULL;
}

u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
{
	u64 count;

	rdmsrl(event->hw.event_base, count);

	return count;
}

void uncore_mmio_exit_box(struct intel_uncore_box *box)
{
	if (box->io_addr)
		iounmap(box->io_addr);
}

u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
			     struct perf_event *event)
{
	if (!box->io_addr)
		return 0;

	if (!uncore_mmio_is_valid_offset(box, event->hw.event_base))
		return 0;

	return readq(box->io_addr + event->hw.event_base);
}

/*
 * generic get constraint function for shared match/mask registers.
 */
struct event_constraint *
uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
{
	struct intel_uncore_extra_reg *er;
	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
	unsigned long flags;
	bool ok = false;

	/*
	 * reg->alloc can be set due to existing state, so for fake box we
	 * need to ignore this, otherwise we might fail to allocate proper
	 * fake state for this extra reg constraint.
	 */
	if (reg1->idx == EXTRA_REG_NONE ||
	    (!uncore_box_is_fake(box) && reg1->alloc))
		return NULL;

	er = &box->shared_regs[reg1->idx];
	raw_spin_lock_irqsave(&er->lock, flags);
	if (!atomic_read(&er->ref) ||
	    (er->config1 == reg1->config && er->config2 == reg2->config)) {
		atomic_inc(&er->ref);
		er->config1 = reg1->config;
		er->config2 = reg2->config;
		ok = true;
	}
	raw_spin_unlock_irqrestore(&er->lock, flags);

	if (ok) {
		if (!uncore_box_is_fake(box))
			reg1->alloc = 1;
		return NULL;
	}

	return &uncore_constraint_empty;
}

void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
{
	struct intel_uncore_extra_reg *er;
	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;

	/*
	 * Only put constraint if extra reg was actually allocated. Also
	 * takes care of event which do not use an extra shared reg.
	 *
	 * Also, if this is a fake box we shouldn't touch any event state
	 * (reg->alloc) and we don't care about leaving inconsistent box
	 * state either since it will be thrown out.
	 */
	if (uncore_box_is_fake(box) || !reg1->alloc)
		return;

	er = &box->shared_regs[reg1->idx];
	atomic_dec(&er->ref);
	reg1->alloc = 0;
}

u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
{
	struct intel_uncore_extra_reg *er;
	unsigned long flags;
	u64 config;

	er = &box->shared_regs[idx];

	raw_spin_lock_irqsave(&er->lock, flags);
	config = er->config;
	raw_spin_unlock_irqrestore(&er->lock, flags);

	return config;
}

static void uncore_assign_hw_event(struct intel_uncore_box *box,
				   struct perf_event *event, int idx)
{
	struct hw_perf_event *hwc = &event->hw;

	hwc->idx = idx;
	hwc->last_tag = ++box->tags[idx];

	if (uncore_pmc_fixed(hwc->idx)) {
		hwc->event_base = uncore_fixed_ctr(box);
		hwc->config_base = uncore_fixed_ctl(box);
		return;
	}

	hwc->config_base = uncore_event_ctl(box, hwc->idx);
	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
}

void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
{
	u64 prev_count, new_count, delta;
	int shift;

	if (uncore_pmc_freerunning(event->hw.idx))
		shift = 64 - uncore_freerunning_bits(box, event);
	else if (uncore_pmc_fixed(event->hw.idx))
		shift = 64 - uncore_fixed_ctr_bits(box);
	else
		shift = 64 - uncore_perf_ctr_bits(box);

	/* the hrtimer might modify the previous event value */
again:
	prev_count = local64_read(&event->hw.prev_count);
	new_count = uncore_read_counter(box, event);
	if (local64_xchg(&event->hw.prev_count, new_count) != prev_count)
		goto again;

	delta = (new_count << shift) - (prev_count << shift);
	delta >>= shift;

	local64_add(delta, &event->count);
}

/*
 * The overflow interrupt is unavailable for SandyBridge-EP, is broken
 * for SandyBridge. So we use hrtimer to periodically poll the counter
 * to avoid overflow.
 */
static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
{
	struct intel_uncore_box *box;
	struct perf_event *event;
	unsigned long flags;
	int bit;

	box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
	if (!box->n_active || box->cpu != smp_processor_id())
		return HRTIMER_NORESTART;
	/*
	 * disable local interrupt to prevent uncore_pmu_event_start/stop
	 * to interrupt the update process
	 */
	local_irq_save(flags);

	/*
	 * handle boxes with an active event list as opposed to active
	 * counters
	 */
	list_for_each_entry(event, &box->active_list, active_entry) {
		uncore_perf_event_update(box, event);
	}

	for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
		uncore_perf_event_update(box, box->events[bit]);

	local_irq_restore(flags);

	hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
	return HRTIMER_RESTART;
}

void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
		      HRTIMER_MODE_REL_PINNED);
}

void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
{
	hrtimer_cancel(&box->hrtimer);
}

static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
{
	hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	box->hrtimer.function = uncore_pmu_hrtimer;
}

static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
						 int node)
{
	int i, size, numshared = type->num_shared_regs ;
	struct intel_uncore_box *box;

	size = sizeof(*box) + numshared * sizeof(struct intel_uncore_extra_reg);

	box = kzalloc_node(size, GFP_KERNEL, node);
	if (!box)
		return NULL;

	for (i = 0; i < numshared; i++)
		raw_spin_lock_init(&box->shared_regs[i].lock);

	uncore_pmu_init_hrtimer(box);
	box->cpu = -1;
	box->pci_phys_id = -1;
	box->dieid = -1;

	/* set default hrtimer timeout */
	box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;

	INIT_LIST_HEAD(&box->active_list);

	return box;
}

/*
 * Using uncore_pmu_event_init pmu event_init callback
 * as a detection point for uncore events.
 */
static int uncore_pmu_event_init(struct perf_event *event);

static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event)
{
	return &box->pmu->pmu == event->pmu;
}

static int
uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
		      bool dogrp)
{
	struct perf_event *event;
	int n, max_count;

	max_count = box->pmu->type->num_counters;
	if (box->pmu->type->fixed_ctl)
		max_count++;

	if (box->n_events >= max_count)
		return -EINVAL;

	n = box->n_events;

	if (is_box_event(box, leader)) {
		box->event_list[n] = leader;
		n++;
	}

	if (!dogrp)
		return n;

	for_each_sibling_event(event, leader) {
		if (!is_box_event(box, event) ||
		    event->state <= PERF_EVENT_STATE_OFF)
			continue;

		if (n >= max_count)
			return -EINVAL;

		box->event_list[n] = event;
		n++;
	}
	return n;
}

static struct event_constraint *
uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
{
	struct intel_uncore_type *type = box->pmu->type;
	struct event_constraint *c;

	if (type->ops->get_constraint) {
		c = type->ops->get_constraint(box, event);
		if (c)
			return c;
	}

	if (event->attr.config == UNCORE_FIXED_EVENT)
		return &uncore_constraint_fixed;

	if (type->constraints) {
		for_each_event_constraint(c, type->constraints) {
			if ((event->hw.config & c->cmask) == c->code)
				return c;
		}
	}

	return &type->unconstrainted;
}

static void uncore_put_event_constraint(struct intel_uncore_box *box,
					struct perf_event *event)
{
	if (box->pmu->type->ops->put_constraint)
		box->pmu->type->ops->put_constraint(box, event);
}

static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n)
{
	unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
	struct event_constraint *c;
	int i, wmin, wmax, ret = 0;
	struct hw_perf_event *hwc;

	bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);

	for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
		c = uncore_get_event_constraint(box, box->event_list[i]);
		box->event_constraint[i] = c;
		wmin = min(wmin, c->weight);
		wmax = max(wmax, c->weight);
	}

	/* fastpath, try to reuse previous register */
	for (i = 0; i < n; i++) {
		hwc = &box->event_list[i]->hw;
		c = box->event_constraint[i];

		/* never assigned */
		if (hwc->idx == -1)
			break;

		/* constraint still honored */
		if (!test_bit(hwc->idx, c->idxmsk))
			break;

		/* not already used */
		if (test_bit(hwc->idx, used_mask))
			break;

		__set_bit(hwc->idx, used_mask);
		if (assign)
			assign[i] = hwc->idx;
	}
	/* slow path */
	if (i != n)
		ret = perf_assign_events(box->event_constraint, n,
					 wmin, wmax, n, assign);

	if (!assign || ret) {
		for (i = 0; i < n; i++)
			uncore_put_event_constraint(box, box->event_list[i]);
	}
	return ret ? -EINVAL : 0;
}

void uncore_pmu_event_start(struct perf_event *event, int flags)
{
	struct intel_uncore_box *box = uncore_event_to_box(event);
	int idx = event->hw.idx;

	if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
		return;

	/*
	 * Free running counter is read-only and always active.
	 * Use the current counter value as start point.
	 * There is no overflow interrupt for free running counter.
	 * Use hrtimer to periodically poll the counter to avoid overflow.
	 */
	if (uncore_pmc_freerunning(event->hw.idx)) {
		list_add_tail(&event->active_entry, &box->active_list);
		local64_set(&event->hw.prev_count,
			    uncore_read_counter(box, event));
		if (box->n_active++ == 0)
			uncore_pmu_start_hrtimer(box);
		return;
	}

	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
		return;

	event->hw.state = 0;
	box->events[idx] = event;
	box->n_active++;
	__set_bit(idx, box->active_mask);

	local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
	uncore_enable_event(box, event);

	if (box->n_active == 1)
		uncore_pmu_start_hrtimer(box);
}

void uncore_pmu_event_stop(struct perf_event *event, int flags)
{
	struct intel_uncore_box *box = uncore_event_to_box(event);
	struct hw_perf_event *hwc = &event->hw;

	/* Cannot disable free running counter which is read-only */
	if (uncore_pmc_freerunning(hwc->idx)) {
		list_del(&event->active_entry);
		if (--box->n_active == 0)
			uncore_pmu_cancel_hrtimer(box);
		uncore_perf_event_update(box, event);
		return;
	}

	if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
		uncore_disable_event(box, event);
		box->n_active--;
		box->events[hwc->idx] = NULL;
		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
		hwc->state |= PERF_HES_STOPPED;

		if (box->n_active == 0)
			uncore_pmu_cancel_hrtimer(box);
	}

	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
		/*
		 * Drain the remaining delta count out of a event
		 * that we are disabling:
		 */
		uncore_perf_event_update(box, event);
		hwc->state |= PERF_HES_UPTODATE;
	}
}

int uncore_pmu_event_add(struct perf_event *event, int flags)
{
	struct intel_uncore_box *box = uncore_event_to_box(event);
	struct hw_perf_event *hwc = &event->hw;
	int assign[UNCORE_PMC_IDX_MAX];
	int i, n, ret;

	if (!box)
		return -ENODEV;

	/*
	 * The free funning counter is assigned in event_init().
	 * The free running counter event and free running counter
	 * are 1:1 mapped. It doesn't need to be tracked in event_list.
	 */
	if (uncore_pmc_freerunning(hwc->idx)) {
		if (flags & PERF_EF_START)
			uncore_pmu_event_start(event, 0);
		return 0;
	}

	ret = n = uncore_collect_events(box, event, false);
	if (ret < 0)
		return ret;

	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
	if (!(flags & PERF_EF_START))
		hwc->state |= PERF_HES_ARCH;

	ret = uncore_assign_events(box, assign, n);
	if (ret)
		return ret;

	/* save events moving to new counters */
	for (i = 0; i < box->n_events; i++) {
		event = box->event_list[i];
		hwc = &event->hw;

		if (hwc->idx == assign[i] &&
			hwc->last_tag == box->tags[assign[i]])
			continue;
		/*
		 * Ensure we don't accidentally enable a stopped
		 * counter simply because we rescheduled.
		 */
		if (hwc->state & PERF_HES_STOPPED)
			hwc->state |= PERF_HES_ARCH;

		uncore_pmu_event_stop(event, PERF_EF_UPDATE);
	}

	/* reprogram moved events into new counters */
	for (i = 0; i < n; i++) {
		event = box->event_list[i];
		hwc = &event->hw;

		if (hwc->idx != assign[i] ||
			hwc->last_tag != box->tags[assign[i]])
			uncore_assign_hw_event(box, event, assign[i]);
		else if (i < box->n_events)
			continue;

		if (hwc->state & PERF_HES_ARCH)
			continue;

		uncore_pmu_event_start(event, 0);
	}
	box->n_events = n;

	return 0;
}

void uncore_pmu_event_del(struct perf_event *event, int flags)
{
	struct intel_uncore_box *box = uncore_event_to_box(event);
	int i;

	uncore_pmu_event_stop(event, PERF_EF_UPDATE);

	/*
	 * The event for free running counter is not tracked by event_list.
	 * It doesn't need to force event->hw.idx = -1 to reassign the counter.
	 * Because the event and the free running counter are 1:1 mapped.
	 */
	if (uncore_pmc_freerunning(event->hw.idx))
		return;

	for (i = 0; i < box->n_events; i++) {
		if (event == box->event_list[i]) {
			uncore_put_event_constraint(box, event);

			for (++i; i < box->n_events; i++)
				box->event_list[i - 1] = box->event_list[i];

			--box->n_events;
			break;
		}
	}

	event->hw.idx = -1;
	event->hw.last_tag = ~0ULL;
}

void uncore_pmu_event_read(struct perf_event *event)
{
	struct intel_uncore_box *box = uncore_event_to_box(event);
	uncore_perf_event_update(box, event);
}

/*
 * validation ensures the group can be loaded onto the
 * PMU if it was the only group available.
 */
static int uncore_validate_group(struct intel_uncore_pmu *pmu,
				struct perf_event *event)
{
	struct perf_event *leader = event->group_leader;
	struct intel_uncore_box *fake_box;
	int ret = -EINVAL, n;

	/* The free running counter is always active. */
	if (uncore_pmc_freerunning(event->hw.idx))
		return 0;

	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
	if (!fake_box)
		return -ENOMEM;

	fake_box->pmu = pmu;
	/*
	 * the event is not yet connected with its
	 * siblings therefore we must first collect
	 * existing siblings, then add the new event
	 * before we can simulate the scheduling
	 */
	n = uncore_collect_events(fake_box, leader, true);
	if (n < 0)
		goto out;

	fake_box->n_events = n;
	n = uncore_collect_events(fake_box, event, false);
	if (n < 0)
		goto out;

	fake_box->n_events = n;

	ret = uncore_assign_events(fake_box, NULL, n);
out:
	kfree(fake_box);
	return ret;
}

static int uncore_pmu_event_init(struct perf_event *event)
{
	struct intel_uncore_pmu *pmu;
	struct intel_uncore_box *box;
	struct hw_perf_event *hwc = &event->hw;
	int ret;

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

	pmu = uncore_event_to_pmu(event);
	/* no device found for this pmu */
	if (pmu->func_id < 0)
		return -ENOENT;

	/* Sampling not supported yet */
	if (hwc->sample_period)
		return -EINVAL;

	/*
	 * Place all uncore events for a particular physical package
	 * onto a single cpu
	 */
	if (event->cpu < 0)
		return -EINVAL;
	box = uncore_pmu_to_box(pmu, event->cpu);
	if (!box || box->cpu < 0)
		return -EINVAL;
	event->cpu = box->cpu;
	event->pmu_private = box;

	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;

	event->hw.idx = -1;
	event->hw.last_tag = ~0ULL;
	event->hw.extra_reg.idx = EXTRA_REG_NONE;
	event->hw.branch_reg.idx = EXTRA_REG_NONE;

	if (event->attr.config == UNCORE_FIXED_EVENT) {
		/* no fixed counter */
		if (!pmu->type->fixed_ctl)
			return -EINVAL;
		/*
		 * if there is only one fixed counter, only the first pmu
		 * can access the fixed counter
		 */
		if (pmu->type->single_fixed && pmu->pmu_idx > 0)
			return -EINVAL;

		/* fixed counters have event field hardcoded to zero */
		hwc->config = 0ULL;
	} else if (is_freerunning_event(event)) {
		hwc->config = event->attr.config;
		if (!check_valid_freerunning_event(box, event))
			return -EINVAL;
		event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;
		/*
		 * The free running counter event and free running counter
		 * are always 1:1 mapped.
		 * The free running counter is always active.
		 * Assign the free running counter here.
		 */
		event->hw.event_base = uncore_freerunning_counter(box, event);
	} else {
		hwc->config = event->attr.config &
			      (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
		if (pmu->type->ops->hw_config) {
			ret = pmu->type->ops->hw_config(box, event);
			if (ret)
				return ret;
		}
	}

	if (event->group_leader != event)
		ret = uncore_validate_group(pmu, event);
	else
		ret = 0;

	return ret;
}

static void uncore_pmu_enable(struct pmu *pmu)
{
	struct intel_uncore_pmu *uncore_pmu;
	struct intel_uncore_box *box;

	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
	if (!uncore_pmu)
		return;

	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
	if (!box)
		return;

	if (uncore_pmu->type->ops->enable_box)
		uncore_pmu->type->ops->enable_box(box);
}

static void uncore_pmu_disable(struct pmu *pmu)
{
	struct intel_uncore_pmu *uncore_pmu;
	struct intel_uncore_box *box;

	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
	if (!uncore_pmu)
		return;

	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
	if (!box)
		return;

	if (uncore_pmu->type->ops->disable_box)
		uncore_pmu->type->ops->disable_box(box);
}

static ssize_t uncore_get_attr_cpumask(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask);
}

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

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

static const struct attribute_group uncore_pmu_attr_group = {
	.attrs = uncore_pmu_attrs,
};

static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
{
	int ret;

	if (!pmu->type->pmu) {
		pmu->pmu = (struct pmu) {
			.attr_groups	= pmu->type->attr_groups,
			.task_ctx_nr	= perf_invalid_context,
			.pmu_enable	= uncore_pmu_enable,
			.pmu_disable	= uncore_pmu_disable,
			.event_init	= uncore_pmu_event_init,
			.add		= uncore_pmu_event_add,
			.del		= uncore_pmu_event_del,
			.start		= uncore_pmu_event_start,
			.stop		= uncore_pmu_event_stop,
			.read		= uncore_pmu_event_read,
			.module		= THIS_MODULE,
			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
			.attr_update	= pmu->type->attr_update,
		};
	} else {
		pmu->pmu = *pmu->type->pmu;
		pmu->pmu.attr_groups = pmu->type->attr_groups;
		pmu->pmu.attr_update = pmu->type->attr_update;
	}

	if (pmu->type->num_boxes == 1) {
		if (strlen(pmu->type->name) > 0)
			sprintf(pmu->name, "uncore_%s", pmu->type->name);
		else
			sprintf(pmu->name, "uncore");
	} else {
		sprintf(pmu->name, "uncore_%s_%d", pmu->type->name,
			pmu->pmu_idx);
	}

	ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
	if (!ret)
		pmu->registered = true;
	return ret;
}

static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
{
	if (!pmu->registered)
		return;
	perf_pmu_unregister(&pmu->pmu);
	pmu->registered = false;
}

static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
	int die;

	for (die = 0; die < uncore_max_dies(); die++)
		kfree(pmu->boxes[die]);
	kfree(pmu->boxes);
}

static void uncore_type_exit(struct intel_uncore_type *type)
{
	struct intel_uncore_pmu *pmu = type->pmus;
	int i;

	if (type->cleanup_mapping)
		type->cleanup_mapping(type);

	if (pmu) {
		for (i = 0; i < type->num_boxes; i++, pmu++) {
			uncore_pmu_unregister(pmu);
			uncore_free_boxes(pmu);
		}
		kfree(type->pmus);
		type->pmus = NULL;
	}
	kfree(type->events_group);
	type->events_group = NULL;
}

static void uncore_types_exit(struct intel_uncore_type **types)
{
	for (; *types; types++)
		uncore_type_exit(*types);
}

static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
{
	struct intel_uncore_pmu *pmus;
	size_t size;
	int i, j;

	pmus = kcalloc(type->num_boxes, sizeof(*pmus), GFP_KERNEL);
	if (!pmus)
		return -ENOMEM;

	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);

	for (i = 0; i < type->num_boxes; i++) {
		pmus[i].func_id	= setid ? i : -1;
		pmus[i].pmu_idx	= i;
		pmus[i].type	= type;
		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
		if (!pmus[i].boxes)
			goto err;
	}

	type->pmus = pmus;
	type->unconstrainted = (struct event_constraint)
		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
				0, type->num_counters, 0, 0);

	if (type->event_descs) {
		struct {
			struct attribute_group group;
			struct attribute *attrs[];
		} *attr_group;
		for (i = 0; type->event_descs[i].attr.attr.name; i++);

		attr_group = kzalloc(struct_size(attr_group, attrs, i + 1),
								GFP_KERNEL);
		if (!attr_group)
			goto err;

		attr_group->group.name = "events";
		attr_group->group.attrs = attr_group->attrs;

		for (j = 0; j < i; j++)
			attr_group->attrs[j] = &type->event_descs[j].attr.attr;

		type->events_group = &attr_group->group;
	}

	type->pmu_group = &uncore_pmu_attr_group;

	if (type->set_mapping)
		type->set_mapping(type);

	return 0;

err:
	for (i = 0; i < type->num_boxes; i++)
		kfree(pmus[i].boxes);
	kfree(pmus);

	return -ENOMEM;
}

static int __init
uncore_types_init(struct intel_uncore_type **types, bool setid)
{
	int ret;

	for (; *types; types++) {
		ret = uncore_type_init(*types, setid);
		if (ret)
			return ret;
	}
	return 0;
}

/*
 * add a pci uncore device
 */
static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct intel_uncore_type *type;
	struct intel_uncore_pmu *pmu = NULL;
	struct intel_uncore_box *box;
	int phys_id, die, ret;

	phys_id = uncore_pcibus_to_physid(pdev->bus);
	if (phys_id < 0)
		return -ENODEV;

	die = (topology_max_die_per_package() > 1) ? phys_id :
					topology_phys_to_logical_pkg(phys_id);
	if (die < 0)
		return -EINVAL;

	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
		int idx = UNCORE_PCI_DEV_IDX(id->driver_data);

		uncore_extra_pci_dev[die].dev[idx] = pdev;
		pci_set_drvdata(pdev, NULL);
		return 0;
	}

	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];

	/*
	 * Some platforms, e.g.  Knights Landing, use a common PCI device ID
	 * for multiple instances of an uncore PMU device type. We should check
	 * PCI slot and func to indicate the uncore box.
	 */
	if (id->driver_data & ~0xffff) {
		struct pci_driver *pci_drv = pdev->driver;
		const struct pci_device_id *ids = pci_drv->id_table;
		unsigned int devfn;

		while (ids && ids->vendor) {
			if ((ids->vendor == pdev->vendor) &&
			    (ids->device == pdev->device)) {
				devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data),
						  UNCORE_PCI_DEV_FUNC(ids->driver_data));
				if (devfn == pdev->devfn) {
					pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)];
					break;
				}
			}
			ids++;
		}
		if (pmu == NULL)
			return -ENODEV;
	} else {
		/*
		 * for performance monitoring unit with multiple boxes,
		 * each box has a different function id.
		 */
		pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
	}

	if (WARN_ON_ONCE(pmu->boxes[die] != NULL))
		return -EINVAL;

	box = uncore_alloc_box(type, NUMA_NO_NODE);
	if (!box)
		return -ENOMEM;

	if (pmu->func_id < 0)
		pmu->func_id = pdev->devfn;
	else
		WARN_ON_ONCE(pmu->func_id != pdev->devfn);

	atomic_inc(&box->refcnt);
	box->pci_phys_id = phys_id;
	box->dieid = die;
	box->pci_dev = pdev;
	box->pmu = pmu;
	uncore_box_init(box);
	pci_set_drvdata(pdev, box);

	pmu->boxes[die] = box;
	if (atomic_inc_return(&pmu->activeboxes) > 1)
		return 0;

	/* First active box registers the pmu */
	ret = uncore_pmu_register(pmu);
	if (ret) {
		pci_set_drvdata(pdev, NULL);
		pmu->boxes[die] = NULL;
		uncore_box_exit(box);
		kfree(box);
	}
	return ret;
}

static void uncore_pci_remove(struct pci_dev *pdev)
{
	struct intel_uncore_box *box;
	struct intel_uncore_pmu *pmu;
	int i, phys_id, die;

	phys_id = uncore_pcibus_to_physid(pdev->bus);

	box = pci_get_drvdata(pdev);
	if (!box) {
		die = (topology_max_die_per_package() > 1) ? phys_id :
					topology_phys_to_logical_pkg(phys_id);
		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
			if (uncore_extra_pci_dev[die].dev[i] == pdev) {
				uncore_extra_pci_dev[die].dev[i] = NULL;
				break;
			}
		}
		WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX);
		return;
	}

	pmu = box->pmu;
	if (WARN_ON_ONCE(phys_id != box->pci_phys_id))
		return;

	pci_set_drvdata(pdev, NULL);
	pmu->boxes[box->dieid] = NULL;
	if (atomic_dec_return(&pmu->activeboxes) == 0)
		uncore_pmu_unregister(pmu);
	uncore_box_exit(box);
	kfree(box);
}

static int __init uncore_pci_init(void)
{
	size_t size;
	int ret;

	size = uncore_max_dies() * sizeof(struct pci_extra_dev);
	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
	if (!uncore_extra_pci_dev) {
		ret = -ENOMEM;
		goto err;
	}

	ret = uncore_types_init(uncore_pci_uncores, false);
	if (ret)
		goto errtype;

	uncore_pci_driver->probe = uncore_pci_probe;
	uncore_pci_driver->remove = uncore_pci_remove;

	ret = pci_register_driver(uncore_pci_driver);
	if (ret)
		goto errtype;

	pcidrv_registered = true;
	return 0;

errtype:
	uncore_types_exit(uncore_pci_uncores);
	kfree(uncore_extra_pci_dev);
	uncore_extra_pci_dev = NULL;
	uncore_free_pcibus_map();
err:
	uncore_pci_uncores = empty_uncore;
	return ret;
}

static void uncore_pci_exit(void)
{
	if (pcidrv_registered) {
		pcidrv_registered = false;
		pci_unregister_driver(uncore_pci_driver);
		uncore_types_exit(uncore_pci_uncores);
		kfree(uncore_extra_pci_dev);
		uncore_free_pcibus_map();
	}
}

static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
				   int new_cpu)
{
	struct intel_uncore_pmu *pmu = type->pmus;
	struct intel_uncore_box *box;
	int i, die;

	die = topology_logical_die_id(old_cpu < 0 ? new_cpu : old_cpu);
	for (i = 0; i < type->num_boxes; i++, pmu++) {
		box = pmu->boxes[die];
		if (!box)
			continue;

		if (old_cpu < 0) {
			WARN_ON_ONCE(box->cpu != -1);
			box->cpu = new_cpu;
			continue;
		}

		WARN_ON_ONCE(box->cpu != old_cpu);
		box->cpu = -1;
		if (new_cpu < 0)
			continue;

		uncore_pmu_cancel_hrtimer(box);
		perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu);
		box->cpu = new_cpu;
	}
}

static void uncore_change_context(struct intel_uncore_type **uncores,
				  int old_cpu, int new_cpu)
{
	for (; *uncores; uncores++)
		uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}

static void uncore_box_unref(struct intel_uncore_type **types, int id)
{
	struct intel_uncore_type *type;
	struct intel_uncore_pmu *pmu;
	struct intel_uncore_box *box;
	int i;

	for (; *types; types++) {
		type = *types;
		pmu = type->pmus;
		for (i = 0; i < type->num_boxes; i++, pmu++) {
			box = pmu->boxes[id];
			if (box && atomic_dec_return(&box->refcnt) == 0)
				uncore_box_exit(box);
		}
	}
}

static int uncore_event_cpu_offline(unsigned int cpu)
{
	int die, target;

	/* Check if exiting cpu is used for collecting uncore events */
	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
		goto unref;
	/* Find a new cpu to collect uncore events */
	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);

	/* Migrate uncore events to the new target */
	if (target < nr_cpu_ids)
		cpumask_set_cpu(target, &uncore_cpu_mask);
	else
		target = -1;

	uncore_change_context(uncore_msr_uncores, cpu, target);
	uncore_change_context(uncore_mmio_uncores, cpu, target);
	uncore_change_context(uncore_pci_uncores, cpu, target);

unref:
	/* Clear the references */
	die = topology_logical_die_id(cpu);
	uncore_box_unref(uncore_msr_uncores, die);
	uncore_box_unref(uncore_mmio_uncores, die);
	return 0;
}

static int allocate_boxes(struct intel_uncore_type **types,
			 unsigned int die, unsigned int cpu)
{
	struct intel_uncore_box *box, *tmp;
	struct intel_uncore_type *type;
	struct intel_uncore_pmu *pmu;
	LIST_HEAD(allocated);
	int i;

	/* Try to allocate all required boxes */
	for (; *types; types++) {
		type = *types;
		pmu = type->pmus;
		for (i = 0; i < type->num_boxes; i++, pmu++) {
			if (pmu->boxes[die])
				continue;
			box = uncore_alloc_box(type, cpu_to_node(cpu));
			if (!box)
				goto cleanup;
			box->pmu = pmu;
			box->dieid = die;
			list_add(&box->active_list, &allocated);
		}
	}
	/* Install them in the pmus */
	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
		list_del_init(&box->active_list);
		box->pmu->boxes[die] = box;
	}
	return 0;

cleanup:
	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
		list_del_init(&box->active_list);
		kfree(box);
	}
	return -ENOMEM;
}

static int uncore_box_ref(struct intel_uncore_type **types,
			  int id, unsigned int cpu)
{
	struct intel_uncore_type *type;
	struct intel_uncore_pmu *pmu;
	struct intel_uncore_box *box;
	int i, ret;

	ret = allocate_boxes(types, id, cpu);
	if (ret)
		return ret;

	for (; *types; types++) {
		type = *types;
		pmu = type->pmus;
		for (i = 0; i < type->num_boxes; i++, pmu++) {
			box = pmu->boxes[id];
			if (box && atomic_inc_return(&box->refcnt) == 1)
				uncore_box_init(box);
		}
	}
	return 0;
}

static int uncore_event_cpu_online(unsigned int cpu)
{
	int die, target, msr_ret, mmio_ret;

	die = topology_logical_die_id(cpu);
	msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
	mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
	if (msr_ret && mmio_ret)
		return -ENOMEM;

	/*
	 * Check if there is an online cpu in the package
	 * which collects uncore events already.
	 */
	target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
	if (target < nr_cpu_ids)
		return 0;

	cpumask_set_cpu(cpu, &uncore_cpu_mask);

	if (!msr_ret)
		uncore_change_context(uncore_msr_uncores, -1, cpu);
	if (!mmio_ret)
		uncore_change_context(uncore_mmio_uncores, -1, cpu);
	uncore_change_context(uncore_pci_uncores, -1, cpu);
	return 0;
}

static int __init type_pmu_register(struct intel_uncore_type *type)
{
	int i, ret;

	for (i = 0; i < type->num_boxes; i++) {
		ret = uncore_pmu_register(&type->pmus[i]);
		if (ret)
			return ret;
	}
	return 0;
}

static int __init uncore_msr_pmus_register(void)
{
	struct intel_uncore_type **types = uncore_msr_uncores;
	int ret;

	for (; *types; types++) {
		ret = type_pmu_register(*types);
		if (ret)
			return ret;
	}
	return 0;
}

static int __init uncore_cpu_init(void)
{
	int ret;

	ret = uncore_types_init(uncore_msr_uncores, true);
	if (ret)
		goto err;

	ret = uncore_msr_pmus_register();
	if (ret)
		goto err;
	return 0;
err:
	uncore_types_exit(uncore_msr_uncores);
	uncore_msr_uncores = empty_uncore;
	return ret;
}

static int __init uncore_mmio_init(void)
{
	struct intel_uncore_type **types = uncore_mmio_uncores;
	int ret;

	ret = uncore_types_init(types, true);
	if (ret)
		goto err;

	for (; *types; types++) {
		ret = type_pmu_register(*types);
		if (ret)
			goto err;
	}
	return 0;
err:
	uncore_types_exit(uncore_mmio_uncores);
	uncore_mmio_uncores = empty_uncore;
	return ret;
}

struct intel_uncore_init_fun {
	void	(*cpu_init)(void);
	int	(*pci_init)(void);
	void	(*mmio_init)(void);
};

static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
	.cpu_init = nhm_uncore_cpu_init,
};

static const struct intel_uncore_init_fun snb_uncore_init __initconst = {
	.cpu_init = snb_uncore_cpu_init,
	.pci_init = snb_uncore_pci_init,
};

static const struct intel_uncore_init_fun ivb_uncore_init __initconst = {
	.cpu_init = snb_uncore_cpu_init,
	.pci_init = ivb_uncore_pci_init,
};

static const struct intel_uncore_init_fun hsw_uncore_init __initconst = {
	.cpu_init = snb_uncore_cpu_init,
	.pci_init = hsw_uncore_pci_init,
};

static const struct intel_uncore_init_fun bdw_uncore_init __initconst = {
	.cpu_init = snb_uncore_cpu_init,
	.pci_init = bdw_uncore_pci_init,
};

static const struct intel_uncore_init_fun snbep_uncore_init __initconst = {
	.cpu_init = snbep_uncore_cpu_init,
	.pci_init = snbep_uncore_pci_init,
};

static const struct intel_uncore_init_fun nhmex_uncore_init __initconst = {
	.cpu_init = nhmex_uncore_cpu_init,
};

static const struct intel_uncore_init_fun ivbep_uncore_init __initconst = {
	.cpu_init = ivbep_uncore_cpu_init,
	.pci_init = ivbep_uncore_pci_init,
};

static const struct intel_uncore_init_fun hswep_uncore_init __initconst = {
	.cpu_init = hswep_uncore_cpu_init,
	.pci_init = hswep_uncore_pci_init,
};

static const struct intel_uncore_init_fun bdx_uncore_init __initconst = {
	.cpu_init = bdx_uncore_cpu_init,
	.pci_init = bdx_uncore_pci_init,
};

static const struct intel_uncore_init_fun knl_uncore_init __initconst = {
	.cpu_init = knl_uncore_cpu_init,
	.pci_init = knl_uncore_pci_init,
};

static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
	.cpu_init = skl_uncore_cpu_init,
	.pci_init = skl_uncore_pci_init,
};

static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
	.cpu_init = skx_uncore_cpu_init,
	.pci_init = skx_uncore_pci_init,
};

static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
	.cpu_init = icl_uncore_cpu_init,
	.pci_init = skl_uncore_pci_init,
};

static const struct intel_uncore_init_fun tgl_uncore_init __initconst = {
	.cpu_init = icl_uncore_cpu_init,
	.mmio_init = tgl_uncore_mmio_init,
};

static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = {
	.cpu_init = icl_uncore_cpu_init,
	.mmio_init = tgl_l_uncore_mmio_init,
};

static const struct intel_uncore_init_fun icx_uncore_init __initconst = {
	.cpu_init = icx_uncore_cpu_init,
	.pci_init = icx_uncore_pci_init,
	.mmio_init = icx_uncore_mmio_init,
};

static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
	.cpu_init = snr_uncore_cpu_init,
	.pci_init = snr_uncore_pci_init,
	.mmio_init = snr_uncore_mmio_init,
};

static const struct x86_cpu_id intel_uncore_match[] __initconst = {
	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&nhm_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE,		&nhm_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP,		&nhm_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&snb_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&ivb_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&hsw_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&hsw_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&hsw_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&bdw_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&bdw_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&snbep_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX,		&nhmex_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX,		&nhmex_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&ivbep_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&hswep_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&bdx_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&bdx_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&knl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&knl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&skx_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&skl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&icx_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&icx_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&tgl_l_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&tgl_uncore_init),
	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
	{},
};
MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);

static int __init intel_uncore_init(void)
{
	const struct x86_cpu_id *id;
	struct intel_uncore_init_fun *uncore_init;
	int pret = 0, cret = 0, mret = 0, ret;

	id = x86_match_cpu(intel_uncore_match);
	if (!id)
		return -ENODEV;

	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
		return -ENODEV;

	__uncore_max_dies =
		topology_max_packages() * topology_max_die_per_package();

	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
	if (uncore_init->pci_init) {
		pret = uncore_init->pci_init();
		if (!pret)
			pret = uncore_pci_init();
	}

	if (uncore_init->cpu_init) {
		uncore_init->cpu_init();
		cret = uncore_cpu_init();
	}

	if (uncore_init->mmio_init) {
		uncore_init->mmio_init();
		mret = uncore_mmio_init();
	}

	if (cret && pret && mret)
		return -ENODEV;

	/* Install hotplug callbacks to setup the targets for each package */
	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
				"perf/x86/intel/uncore:online",
				uncore_event_cpu_online,
				uncore_event_cpu_offline);
	if (ret)
		goto err;
	return 0;

err:
	uncore_types_exit(uncore_msr_uncores);
	uncore_types_exit(uncore_mmio_uncores);
	uncore_pci_exit();
	return ret;
}
module_init(intel_uncore_init);

static void __exit intel_uncore_exit(void)
{
	cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
	uncore_types_exit(uncore_msr_uncores);
	uncore_types_exit(uncore_mmio_uncores);
	uncore_pci_exit();
}
module_exit(intel_uncore_exit);