aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/thermal/thermal_core.c
blob: cc8ee7c1b1aa43a7362a4434fde851d381960ad5 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  thermal.c - Generic Thermal Management Sysfs support.
 *
 *  Copyright (C) 2008 Intel Corp
 *  Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
 *  Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/kdev_t.h>
#include <linux/idr.h>
#include <linux/thermal.h>
#include <linux/reboot.h>
#include <linux/string.h>
#include <linux/of.h>
#include <net/netlink.h>
#include <net/genetlink.h>
#include <linux/suspend.h>

#define CREATE_TRACE_POINTS
#include <trace/events/thermal.h>

#include "thermal_core.h"
#include "thermal_hwmon.h"

MODULE_AUTHOR("Zhang Rui");
MODULE_DESCRIPTION("Generic thermal management sysfs support");
MODULE_LICENSE("GPL v2");

static DEFINE_IDA(thermal_tz_ida);
static DEFINE_IDA(thermal_cdev_ida);

static LIST_HEAD(thermal_tz_list);
static LIST_HEAD(thermal_cdev_list);
static LIST_HEAD(thermal_governor_list);

static DEFINE_MUTEX(thermal_list_lock);
static DEFINE_MUTEX(thermal_governor_lock);
static DEFINE_MUTEX(poweroff_lock);

static atomic_t in_suspend;
static bool power_off_triggered;

static struct thermal_governor *def_governor;

/*
 * Governor section: set of functions to handle thermal governors
 *
 * Functions to help in the life cycle of thermal governors within
 * the thermal core and by the thermal governor code.
 */

static struct thermal_governor *__find_governor(const char *name)
{
	struct thermal_governor *pos;

	if (!name || !name[0])
		return def_governor;

	list_for_each_entry(pos, &thermal_governor_list, governor_list)
		if (!strncasecmp(name, pos->name, THERMAL_NAME_LENGTH))
			return pos;

	return NULL;
}

/**
 * bind_previous_governor() - bind the previous governor of the thermal zone
 * @tz:		a valid pointer to a struct thermal_zone_device
 * @failed_gov_name:	the name of the governor that failed to register
 *
 * Register the previous governor of the thermal zone after a new
 * governor has failed to be bound.
 */
static void bind_previous_governor(struct thermal_zone_device *tz,
				   const char *failed_gov_name)
{
	if (tz->governor && tz->governor->bind_to_tz) {
		if (tz->governor->bind_to_tz(tz)) {
			dev_err(&tz->device,
				"governor %s failed to bind and the previous one (%s) failed to bind again, thermal zone %s has no governor\n",
				failed_gov_name, tz->governor->name, tz->type);
			tz->governor = NULL;
		}
	}
}

/**
 * thermal_set_governor() - Switch to another governor
 * @tz:		a valid pointer to a struct thermal_zone_device
 * @new_gov:	pointer to the new governor
 *
 * Change the governor of thermal zone @tz.
 *
 * Return: 0 on success, an error if the new governor's bind_to_tz() failed.
 */
static int thermal_set_governor(struct thermal_zone_device *tz,
				struct thermal_governor *new_gov)
{
	int ret = 0;

	if (tz->governor && tz->governor->unbind_from_tz)
		tz->governor->unbind_from_tz(tz);

	if (new_gov && new_gov->bind_to_tz) {
		ret = new_gov->bind_to_tz(tz);
		if (ret) {
			bind_previous_governor(tz, new_gov->name);

			return ret;
		}
	}

	tz->governor = new_gov;

	return ret;
}

int thermal_register_governor(struct thermal_governor *governor)
{
	int err;
	const char *name;
	struct thermal_zone_device *pos;

	if (!governor)
		return -EINVAL;

	mutex_lock(&thermal_governor_lock);

	err = -EBUSY;
	if (!__find_governor(governor->name)) {
		bool match_default;

		err = 0;
		list_add(&governor->governor_list, &thermal_governor_list);
		match_default = !strncmp(governor->name,
					 DEFAULT_THERMAL_GOVERNOR,
					 THERMAL_NAME_LENGTH);

		if (!def_governor && match_default)
			def_governor = governor;
	}

	mutex_lock(&thermal_list_lock);

	list_for_each_entry(pos, &thermal_tz_list, node) {
		/*
		 * only thermal zones with specified tz->tzp->governor_name
		 * may run with tz->govenor unset
		 */
		if (pos->governor)
			continue;

		name = pos->tzp->governor_name;

		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
			int ret;

			ret = thermal_set_governor(pos, governor);
			if (ret)
				dev_err(&pos->device,
					"Failed to set governor %s for thermal zone %s: %d\n",
					governor->name, pos->type, ret);
		}
	}

	mutex_unlock(&thermal_list_lock);
	mutex_unlock(&thermal_governor_lock);

	return err;
}

void thermal_unregister_governor(struct thermal_governor *governor)
{
	struct thermal_zone_device *pos;

	if (!governor)
		return;

	mutex_lock(&thermal_governor_lock);

	if (!__find_governor(governor->name))
		goto exit;

	mutex_lock(&thermal_list_lock);

	list_for_each_entry(pos, &thermal_tz_list, node) {
		if (!strncasecmp(pos->governor->name, governor->name,
				 THERMAL_NAME_LENGTH))
			thermal_set_governor(pos, NULL);
	}

	mutex_unlock(&thermal_list_lock);
	list_del(&governor->governor_list);
exit:
	mutex_unlock(&thermal_governor_lock);
}

int thermal_zone_device_set_policy(struct thermal_zone_device *tz,
				   char *policy)
{
	struct thermal_governor *gov;
	int ret = -EINVAL;

	mutex_lock(&thermal_governor_lock);
	mutex_lock(&tz->lock);

	gov = __find_governor(strim(policy));
	if (!gov)
		goto exit;

	ret = thermal_set_governor(tz, gov);

exit:
	mutex_unlock(&tz->lock);
	mutex_unlock(&thermal_governor_lock);

	return ret;
}

int thermal_build_list_of_policies(char *buf)
{
	struct thermal_governor *pos;
	ssize_t count = 0;
	ssize_t size = PAGE_SIZE;

	mutex_lock(&thermal_governor_lock);

	list_for_each_entry(pos, &thermal_governor_list, governor_list) {
		size = PAGE_SIZE - count;
		count += scnprintf(buf + count, size, "%s ", pos->name);
	}
	count += scnprintf(buf + count, size, "\n");

	mutex_unlock(&thermal_governor_lock);

	return count;
}

static int __init thermal_register_governors(void)
{
	int result;

	result = thermal_gov_step_wise_register();
	if (result)
		return result;

	result = thermal_gov_fair_share_register();
	if (result)
		return result;

	result = thermal_gov_bang_bang_register();
	if (result)
		return result;

	result = thermal_gov_user_space_register();
	if (result)
		return result;

	return thermal_gov_power_allocator_register();
}

static void __init thermal_unregister_governors(void)
{
	thermal_gov_step_wise_unregister();
	thermal_gov_fair_share_unregister();
	thermal_gov_bang_bang_unregister();
	thermal_gov_user_space_unregister();
	thermal_gov_power_allocator_unregister();
}

/*
 * Zone update section: main control loop applied to each zone while monitoring
 *
 * in polling mode. The monitoring is done using a workqueue.
 * Same update may be done on a zone by calling thermal_zone_device_update().
 *
 * An update means:
 * - Non-critical trips will invoke the governor responsible for that zone;
 * - Hot trips will produce a notification to userspace;
 * - Critical trip point will cause a system shutdown.
 */
static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
					    int delay)
{
	if (delay > 1000)
		mod_delayed_work(system_freezable_power_efficient_wq,
				 &tz->poll_queue,
				 round_jiffies(msecs_to_jiffies(delay)));
	else if (delay)
		mod_delayed_work(system_freezable_power_efficient_wq,
				 &tz->poll_queue,
				 msecs_to_jiffies(delay));
	else
		cancel_delayed_work(&tz->poll_queue);
}

static void monitor_thermal_zone(struct thermal_zone_device *tz)
{
	mutex_lock(&tz->lock);

	if (tz->passive)
		thermal_zone_device_set_polling(tz, tz->passive_delay);
	else if (tz->polling_delay)
		thermal_zone_device_set_polling(tz, tz->polling_delay);
	else
		thermal_zone_device_set_polling(tz, 0);

	mutex_unlock(&tz->lock);
}

static void handle_non_critical_trips(struct thermal_zone_device *tz, int trip)
{
	tz->governor ? tz->governor->throttle(tz, trip) :
		       def_governor->throttle(tz, trip);
}

/**
 * thermal_emergency_poweroff_func - emergency poweroff work after a known delay
 * @work: work_struct associated with the emergency poweroff function
 *
 * This function is called in very critical situations to force
 * a kernel poweroff after a configurable timeout value.
 */
static void thermal_emergency_poweroff_func(struct work_struct *work)
{
	/*
	 * We have reached here after the emergency thermal shutdown
	 * Waiting period has expired. This means orderly_poweroff has
	 * not been able to shut off the system for some reason.
	 * Try to shut down the system immediately using kernel_power_off
	 * if populated
	 */
	WARN(1, "Attempting kernel_power_off: Temperature too high\n");
	kernel_power_off();

	/*
	 * Worst of the worst case trigger emergency restart
	 */
	WARN(1, "Attempting emergency_restart: Temperature too high\n");
	emergency_restart();
}

static DECLARE_DELAYED_WORK(thermal_emergency_poweroff_work,
			    thermal_emergency_poweroff_func);

/**
 * thermal_emergency_poweroff - Trigger an emergency system poweroff
 *
 * This may be called from any critical situation to trigger a system shutdown
 * after a known period of time. By default this is not scheduled.
 */
static void thermal_emergency_poweroff(void)
{
	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
	/*
	 * poweroff_delay_ms must be a carefully profiled positive value.
	 * Its a must for thermal_emergency_poweroff_work to be scheduled
	 */
	if (poweroff_delay_ms <= 0)
		return;
	schedule_delayed_work(&thermal_emergency_poweroff_work,
			      msecs_to_jiffies(poweroff_delay_ms));
}

static void handle_critical_trips(struct thermal_zone_device *tz,
				  int trip, enum thermal_trip_type trip_type)
{
	int trip_temp;

	tz->ops->get_trip_temp(tz, trip, &trip_temp);

	/* If we have not crossed the trip_temp, we do not care. */
	if (trip_temp <= 0 || tz->temperature < trip_temp)
		return;

	trace_thermal_zone_trip(tz, trip, trip_type);

	if (tz->ops->notify)
		tz->ops->notify(tz, trip, trip_type);

	if (trip_type == THERMAL_TRIP_CRITICAL) {
		dev_emerg(&tz->device,
			  "critical temperature reached (%d C), shutting down\n",
			  tz->temperature / 1000);
		mutex_lock(&poweroff_lock);
		if (!power_off_triggered) {
			/*
			 * Queue a backup emergency shutdown in the event of
			 * orderly_poweroff failure
			 */
			thermal_emergency_poweroff();
			orderly_poweroff(true);
			power_off_triggered = true;
		}
		mutex_unlock(&poweroff_lock);
	}
}

static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
{
	enum thermal_trip_type type;

	/* Ignore disabled trip points */
	if (test_bit(trip, &tz->trips_disabled))
		return;

	tz->ops->get_trip_type(tz, trip, &type);

	if (type == THERMAL_TRIP_CRITICAL || type == THERMAL_TRIP_HOT)
		handle_critical_trips(tz, trip, type);
	else
		handle_non_critical_trips(tz, trip);
	/*
	 * Alright, we handled this trip successfully.
	 * So, start monitoring again.
	 */
	monitor_thermal_zone(tz);
}

static void update_temperature(struct thermal_zone_device *tz)
{
	int temp, ret;

	ret = thermal_zone_get_temp(tz, &temp);
	if (ret) {
		if (ret != -EAGAIN)
			dev_warn(&tz->device,
				 "failed to read out thermal zone (%d)\n",
				 ret);
		return;
	}

	mutex_lock(&tz->lock);
	tz->last_temperature = tz->temperature;
	tz->temperature = temp;
	mutex_unlock(&tz->lock);

	trace_thermal_temperature(tz);
	if (tz->last_temperature == THERMAL_TEMP_INVALID)
		dev_dbg(&tz->device, "last_temperature N/A, current_temperature=%d\n",
			tz->temperature);
	else
		dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n",
			tz->last_temperature, tz->temperature);
}

static void thermal_zone_device_init(struct thermal_zone_device *tz)
{
	struct thermal_instance *pos;
	tz->temperature = THERMAL_TEMP_INVALID;
	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
		pos->initialized = false;
}

static void thermal_zone_device_reset(struct thermal_zone_device *tz)
{
	tz->passive = 0;
	thermal_zone_device_init(tz);
}

void thermal_zone_device_update(struct thermal_zone_device *tz,
				enum thermal_notify_event event)
{
	int count;

	if (atomic_read(&in_suspend))
		return;

	if (!tz->ops->get_temp)
		return;

	update_temperature(tz);

	thermal_zone_set_trips(tz);

	tz->notify_event = event;

	for (count = 0; count < tz->trips; count++)
		handle_thermal_trip(tz, count);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_update);

/**
 * thermal_notify_framework - Sensor drivers use this API to notify framework
 * @tz:		thermal zone device
 * @trip:	indicates which trip point has been crossed
 *
 * This function handles the trip events from sensor drivers. It starts
 * throttling the cooling devices according to the policy configured.
 * For CRITICAL and HOT trip points, this notifies the respective drivers,
 * and does actual throttling for other trip points i.e ACTIVE and PASSIVE.
 * The throttling policy is based on the configured platform data; if no
 * platform data is provided, this uses the step_wise throttling policy.
 */
void thermal_notify_framework(struct thermal_zone_device *tz, int trip)
{
	handle_thermal_trip(tz, trip);
}
EXPORT_SYMBOL_GPL(thermal_notify_framework);

static void thermal_zone_device_check(struct work_struct *work)
{
	struct thermal_zone_device *tz = container_of(work, struct
						      thermal_zone_device,
						      poll_queue.work);
	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
}

/*
 * Power actor section: interface to power actors to estimate power
 *
 * Set of functions used to interact to cooling devices that know
 * how to estimate their devices power consumption.
 */

/**
 * power_actor_get_max_power() - get the maximum power that a cdev can consume
 * @cdev:	pointer to &thermal_cooling_device
 * @tz:		a valid thermal zone device pointer
 * @max_power:	pointer in which to store the maximum power
 *
 * Calculate the maximum power consumption in milliwats that the
 * cooling device can currently consume and store it in @max_power.
 *
 * Return: 0 on success, -EINVAL if @cdev doesn't support the
 * power_actor API or -E* on other error.
 */
int power_actor_get_max_power(struct thermal_cooling_device *cdev,
			      struct thermal_zone_device *tz, u32 *max_power)
{
	if (!cdev_is_power_actor(cdev))
		return -EINVAL;

	return cdev->ops->state2power(cdev, tz, 0, max_power);
}

/**
 * power_actor_get_min_power() - get the mainimum power that a cdev can consume
 * @cdev:	pointer to &thermal_cooling_device
 * @tz:		a valid thermal zone device pointer
 * @min_power:	pointer in which to store the minimum power
 *
 * Calculate the minimum power consumption in milliwatts that the
 * cooling device can currently consume and store it in @min_power.
 *
 * Return: 0 on success, -EINVAL if @cdev doesn't support the
 * power_actor API or -E* on other error.
 */
int power_actor_get_min_power(struct thermal_cooling_device *cdev,
			      struct thermal_zone_device *tz, u32 *min_power)
{
	unsigned long max_state;
	int ret;

	if (!cdev_is_power_actor(cdev))
		return -EINVAL;

	ret = cdev->ops->get_max_state(cdev, &max_state);
	if (ret)
		return ret;

	return cdev->ops->state2power(cdev, tz, max_state, min_power);
}

/**
 * power_actor_set_power() - limit the maximum power a cooling device consumes
 * @cdev:	pointer to &thermal_cooling_device
 * @instance:	thermal instance to update
 * @power:	the power in milliwatts
 *
 * Set the cooling device to consume at most @power milliwatts. The limit is
 * expected to be a cap at the maximum power consumption.
 *
 * Return: 0 on success, -EINVAL if the cooling device does not
 * implement the power actor API or -E* for other failures.
 */
int power_actor_set_power(struct thermal_cooling_device *cdev,
			  struct thermal_instance *instance, u32 power)
{
	unsigned long state;
	int ret;

	if (!cdev_is_power_actor(cdev))
		return -EINVAL;

	ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
	if (ret)
		return ret;

	instance->target = state;
	mutex_lock(&cdev->lock);
	cdev->updated = false;
	mutex_unlock(&cdev->lock);
	thermal_cdev_update(cdev);

	return 0;
}

void thermal_zone_device_rebind_exception(struct thermal_zone_device *tz,
					  const char *cdev_type, size_t size)
{
	struct thermal_cooling_device *cdev = NULL;

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(cdev, &thermal_cdev_list, node) {
		/* skip non matching cdevs */
		if (strncmp(cdev_type, cdev->type, size))
			continue;

		/* re binding the exception matching the type pattern */
		thermal_zone_bind_cooling_device(tz, THERMAL_TRIPS_NONE, cdev,
						 THERMAL_NO_LIMIT,
						 THERMAL_NO_LIMIT,
						 THERMAL_WEIGHT_DEFAULT);
	}
	mutex_unlock(&thermal_list_lock);
}

void thermal_zone_device_unbind_exception(struct thermal_zone_device *tz,
					  const char *cdev_type, size_t size)
{
	struct thermal_cooling_device *cdev = NULL;

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(cdev, &thermal_cdev_list, node) {
		/* skip non matching cdevs */
		if (strncmp(cdev_type, cdev->type, size))
			continue;
		/* unbinding the exception matching the type pattern */
		thermal_zone_unbind_cooling_device(tz, THERMAL_TRIPS_NONE,
						   cdev);
	}
	mutex_unlock(&thermal_list_lock);
}

/*
 * Device management section: cooling devices, zones devices, and binding
 *
 * Set of functions provided by the thermal core for:
 * - cooling devices lifecycle: registration, unregistration,
 *				binding, and unbinding.
 * - thermal zone devices lifecycle: registration, unregistration,
 *				     binding, and unbinding.
 */

/**
 * thermal_zone_bind_cooling_device() - bind a cooling device to a thermal zone
 * @tz:		pointer to struct thermal_zone_device
 * @trip:	indicates which trip point the cooling devices is
 *		associated with in this thermal zone.
 * @cdev:	pointer to struct thermal_cooling_device
 * @upper:	the Maximum cooling state for this trip point.
 *		THERMAL_NO_LIMIT means no upper limit,
 *		and the cooling device can be in max_state.
 * @lower:	the Minimum cooling state can be used for this trip point.
 *		THERMAL_NO_LIMIT means no lower limit,
 *		and the cooling device can be in cooling state 0.
 * @weight:	The weight of the cooling device to be bound to the
 *		thermal zone. Use THERMAL_WEIGHT_DEFAULT for the
 *		default value
 *
 * This interface function bind a thermal cooling device to the certain trip
 * point of a thermal zone device.
 * This function is usually called in the thermal zone device .bind callback.
 *
 * Return: 0 on success, the proper error value otherwise.
 */
int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
				     int trip,
				     struct thermal_cooling_device *cdev,
				     unsigned long upper, unsigned long lower,
				     unsigned int weight)
{
	struct thermal_instance *dev;
	struct thermal_instance *pos;
	struct thermal_zone_device *pos1;
	struct thermal_cooling_device *pos2;
	unsigned long max_state;
	int result, ret;

	if (trip >= tz->trips || (trip < 0 && trip != THERMAL_TRIPS_NONE))
		return -EINVAL;

	list_for_each_entry(pos1, &thermal_tz_list, node) {
		if (pos1 == tz)
			break;
	}
	list_for_each_entry(pos2, &thermal_cdev_list, node) {
		if (pos2 == cdev)
			break;
	}

	if (tz != pos1 || cdev != pos2)
		return -EINVAL;

	ret = cdev->ops->get_max_state(cdev, &max_state);
	if (ret)
		return ret;

	/* lower default 0, upper default max_state */
	lower = lower == THERMAL_NO_LIMIT ? 0 : lower;
	upper = upper == THERMAL_NO_LIMIT ? max_state : upper;

	if (lower > upper || upper > max_state)
		return -EINVAL;

	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
	if (!dev)
		return -ENOMEM;
	dev->tz = tz;
	dev->cdev = cdev;
	dev->trip = trip;
	dev->upper = upper;
	dev->lower = lower;
	dev->target = THERMAL_NO_TARGET;
	dev->weight = weight;

	result = ida_simple_get(&tz->ida, 0, 0, GFP_KERNEL);
	if (result < 0)
		goto free_mem;

	dev->id = result;
	sprintf(dev->name, "cdev%d", dev->id);
	result =
	    sysfs_create_link(&tz->device.kobj, &cdev->device.kobj, dev->name);
	if (result)
		goto release_ida;

	sprintf(dev->attr_name, "cdev%d_trip_point", dev->id);
	sysfs_attr_init(&dev->attr.attr);
	dev->attr.attr.name = dev->attr_name;
	dev->attr.attr.mode = 0444;
	dev->attr.show = trip_point_show;
	result = device_create_file(&tz->device, &dev->attr);
	if (result)
		goto remove_symbol_link;

	sprintf(dev->weight_attr_name, "cdev%d_weight", dev->id);
	sysfs_attr_init(&dev->weight_attr.attr);
	dev->weight_attr.attr.name = dev->weight_attr_name;
	dev->weight_attr.attr.mode = S_IWUSR | S_IRUGO;
	dev->weight_attr.show = weight_show;
	dev->weight_attr.store = weight_store;
	result = device_create_file(&tz->device, &dev->weight_attr);
	if (result)
		goto remove_trip_file;

	mutex_lock(&tz->lock);
	mutex_lock(&cdev->lock);
	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
			result = -EEXIST;
			break;
		}
	if (!result) {
		list_add_tail(&dev->tz_node, &tz->thermal_instances);
		list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
		atomic_set(&tz->need_update, 1);
	}
	mutex_unlock(&cdev->lock);
	mutex_unlock(&tz->lock);

	if (!result)
		return 0;

	device_remove_file(&tz->device, &dev->weight_attr);
remove_trip_file:
	device_remove_file(&tz->device, &dev->attr);
remove_symbol_link:
	sysfs_remove_link(&tz->device.kobj, dev->name);
release_ida:
	ida_simple_remove(&tz->ida, dev->id);
free_mem:
	kfree(dev);
	return result;
}
EXPORT_SYMBOL_GPL(thermal_zone_bind_cooling_device);

/**
 * thermal_zone_unbind_cooling_device() - unbind a cooling device from a
 *					  thermal zone.
 * @tz:		pointer to a struct thermal_zone_device.
 * @trip:	indicates which trip point the cooling devices is
 *		associated with in this thermal zone.
 * @cdev:	pointer to a struct thermal_cooling_device.
 *
 * This interface function unbind a thermal cooling device from the certain
 * trip point of a thermal zone device.
 * This function is usually called in the thermal zone device .unbind callback.
 *
 * Return: 0 on success, the proper error value otherwise.
 */
int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
				       int trip,
				       struct thermal_cooling_device *cdev)
{
	struct thermal_instance *pos, *next;

	mutex_lock(&tz->lock);
	mutex_lock(&cdev->lock);
	list_for_each_entry_safe(pos, next, &tz->thermal_instances, tz_node) {
		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
			list_del(&pos->tz_node);
			list_del(&pos->cdev_node);
			mutex_unlock(&cdev->lock);
			mutex_unlock(&tz->lock);
			goto unbind;
		}
	}
	mutex_unlock(&cdev->lock);
	mutex_unlock(&tz->lock);

	return -ENODEV;

unbind:
	device_remove_file(&tz->device, &pos->weight_attr);
	device_remove_file(&tz->device, &pos->attr);
	sysfs_remove_link(&tz->device.kobj, pos->name);
	ida_simple_remove(&tz->ida, pos->id);
	kfree(pos);
	return 0;
}
EXPORT_SYMBOL_GPL(thermal_zone_unbind_cooling_device);

static void thermal_release(struct device *dev)
{
	struct thermal_zone_device *tz;
	struct thermal_cooling_device *cdev;

	if (!strncmp(dev_name(dev), "thermal_zone",
		     sizeof("thermal_zone") - 1)) {
		tz = to_thermal_zone(dev);
		thermal_zone_destroy_device_groups(tz);
		kfree(tz);
	} else if (!strncmp(dev_name(dev), "cooling_device",
			    sizeof("cooling_device") - 1)) {
		cdev = to_cooling_device(dev);
		kfree(cdev);
	}
}

static struct class thermal_class = {
	.name = "thermal",
	.dev_release = thermal_release,
};

static inline
void print_bind_err_msg(struct thermal_zone_device *tz,
			struct thermal_cooling_device *cdev, int ret)
{
	dev_err(&tz->device, "binding zone %s with cdev %s failed:%d\n",
		tz->type, cdev->type, ret);
}

static void __bind(struct thermal_zone_device *tz, int mask,
		   struct thermal_cooling_device *cdev,
		   unsigned long *limits,
		   unsigned int weight)
{
	int i, ret;

	for (i = 0; i < tz->trips; i++) {
		if (mask & (1 << i)) {
			unsigned long upper, lower;

			upper = THERMAL_NO_LIMIT;
			lower = THERMAL_NO_LIMIT;
			if (limits) {
				lower = limits[i * 2];
				upper = limits[i * 2 + 1];
			}
			ret = thermal_zone_bind_cooling_device(tz, i, cdev,
							       upper, lower,
							       weight);
			if (ret)
				print_bind_err_msg(tz, cdev, ret);
		}
	}
}

static void bind_cdev(struct thermal_cooling_device *cdev)
{
	int i, ret;
	const struct thermal_zone_params *tzp;
	struct thermal_zone_device *pos = NULL;

	mutex_lock(&thermal_list_lock);

	list_for_each_entry(pos, &thermal_tz_list, node) {
		if (!pos->tzp && !pos->ops->bind)
			continue;

		if (pos->ops->bind) {
			ret = pos->ops->bind(pos, cdev);
			if (ret)
				print_bind_err_msg(pos, cdev, ret);
			continue;
		}

		tzp = pos->tzp;
		if (!tzp || !tzp->tbp)
			continue;

		for (i = 0; i < tzp->num_tbps; i++) {
			if (tzp->tbp[i].cdev || !tzp->tbp[i].match)
				continue;
			if (tzp->tbp[i].match(pos, cdev))
				continue;
			tzp->tbp[i].cdev = cdev;
			__bind(pos, tzp->tbp[i].trip_mask, cdev,
			       tzp->tbp[i].binding_limits,
			       tzp->tbp[i].weight);
		}
	}

	mutex_unlock(&thermal_list_lock);
}

/**
 * __thermal_cooling_device_register() - register a new thermal cooling device
 * @np:		a pointer to a device tree node.
 * @type:	the thermal cooling device type.
 * @devdata:	device private data.
 * @ops:		standard thermal cooling devices callbacks.
 *
 * This interface function adds a new thermal cooling device (fan/processor/...)
 * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
 * to all the thermal zone devices registered at the same time.
 * It also gives the opportunity to link the cooling device to a device tree
 * node, so that it can be bound to a thermal zone created out of device tree.
 *
 * Return: a pointer to the created struct thermal_cooling_device or an
 * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
 */
static struct thermal_cooling_device *
__thermal_cooling_device_register(struct device_node *np,
				  const char *type, void *devdata,
				  const struct thermal_cooling_device_ops *ops)
{
	struct thermal_cooling_device *cdev;
	struct thermal_zone_device *pos = NULL;
	int result;

	if (type && strlen(type) >= THERMAL_NAME_LENGTH)
		return ERR_PTR(-EINVAL);

	if (!ops || !ops->get_max_state || !ops->get_cur_state ||
	    !ops->set_cur_state)
		return ERR_PTR(-EINVAL);

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

	result = ida_simple_get(&thermal_cdev_ida, 0, 0, GFP_KERNEL);
	if (result < 0) {
		kfree(cdev);
		return ERR_PTR(result);
	}

	cdev->id = result;
	strlcpy(cdev->type, type ? : "", sizeof(cdev->type));
	mutex_init(&cdev->lock);
	INIT_LIST_HEAD(&cdev->thermal_instances);
	cdev->np = np;
	cdev->ops = ops;
	cdev->updated = false;
	cdev->device.class = &thermal_class;
	cdev->devdata = devdata;
	thermal_cooling_device_setup_sysfs(cdev);
	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
	result = device_register(&cdev->device);
	if (result) {
		ida_simple_remove(&thermal_cdev_ida, cdev->id);
		kfree(cdev);
		return ERR_PTR(result);
	}

	/* Add 'this' new cdev to the global cdev list */
	mutex_lock(&thermal_list_lock);
	list_add(&cdev->node, &thermal_cdev_list);
	mutex_unlock(&thermal_list_lock);

	/* Update binding information for 'this' new cdev */
	bind_cdev(cdev);

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(pos, &thermal_tz_list, node)
		if (atomic_cmpxchg(&pos->need_update, 1, 0))
			thermal_zone_device_update(pos,
						   THERMAL_EVENT_UNSPECIFIED);
	mutex_unlock(&thermal_list_lock);

	return cdev;
}

/**
 * thermal_cooling_device_register() - register a new thermal cooling device
 * @type:	the thermal cooling device type.
 * @devdata:	device private data.
 * @ops:		standard thermal cooling devices callbacks.
 *
 * This interface function adds a new thermal cooling device (fan/processor/...)
 * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
 * to all the thermal zone devices registered at the same time.
 *
 * Return: a pointer to the created struct thermal_cooling_device or an
 * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
 */
struct thermal_cooling_device *
thermal_cooling_device_register(const char *type, void *devdata,
				const struct thermal_cooling_device_ops *ops)
{
	return __thermal_cooling_device_register(NULL, type, devdata, ops);
}
EXPORT_SYMBOL_GPL(thermal_cooling_device_register);

/**
 * thermal_of_cooling_device_register() - register an OF thermal cooling device
 * @np:		a pointer to a device tree node.
 * @type:	the thermal cooling device type.
 * @devdata:	device private data.
 * @ops:		standard thermal cooling devices callbacks.
 *
 * This function will register a cooling device with device tree node reference.
 * This interface function adds a new thermal cooling device (fan/processor/...)
 * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
 * to all the thermal zone devices registered at the same time.
 *
 * Return: a pointer to the created struct thermal_cooling_device or an
 * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
 */
struct thermal_cooling_device *
thermal_of_cooling_device_register(struct device_node *np,
				   const char *type, void *devdata,
				   const struct thermal_cooling_device_ops *ops)
{
	return __thermal_cooling_device_register(np, type, devdata, ops);
}
EXPORT_SYMBOL_GPL(thermal_of_cooling_device_register);

static void thermal_cooling_device_release(struct device *dev, void *res)
{
	thermal_cooling_device_unregister(
				*(struct thermal_cooling_device **)res);
}

/**
 * devm_thermal_of_cooling_device_register() - register an OF thermal cooling
 *					       device
 * @dev:	a valid struct device pointer of a sensor device.
 * @np:		a pointer to a device tree node.
 * @type:	the thermal cooling device type.
 * @devdata:	device private data.
 * @ops:	standard thermal cooling devices callbacks.
 *
 * This function will register a cooling device with device tree node reference.
 * This interface function adds a new thermal cooling device (fan/processor/...)
 * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
 * to all the thermal zone devices registered at the same time.
 *
 * Return: a pointer to the created struct thermal_cooling_device or an
 * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
 */
struct thermal_cooling_device *
devm_thermal_of_cooling_device_register(struct device *dev,
				struct device_node *np,
				char *type, void *devdata,
				const struct thermal_cooling_device_ops *ops)
{
	struct thermal_cooling_device **ptr, *tcd;

	ptr = devres_alloc(thermal_cooling_device_release, sizeof(*ptr),
			   GFP_KERNEL);
	if (!ptr)
		return ERR_PTR(-ENOMEM);

	tcd = __thermal_cooling_device_register(np, type, devdata, ops);
	if (IS_ERR(tcd)) {
		devres_free(ptr);
		return tcd;
	}

	*ptr = tcd;
	devres_add(dev, ptr);

	return tcd;
}
EXPORT_SYMBOL_GPL(devm_thermal_of_cooling_device_register);

static void __unbind(struct thermal_zone_device *tz, int mask,
		     struct thermal_cooling_device *cdev)
{
	int i;

	for (i = 0; i < tz->trips; i++)
		if (mask & (1 << i))
			thermal_zone_unbind_cooling_device(tz, i, cdev);
}

/**
 * thermal_cooling_device_unregister - removes a thermal cooling device
 * @cdev:	the thermal cooling device to remove.
 *
 * thermal_cooling_device_unregister() must be called when a registered
 * thermal cooling device is no longer needed.
 */
void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
{
	int i;
	const struct thermal_zone_params *tzp;
	struct thermal_zone_device *tz;
	struct thermal_cooling_device *pos = NULL;

	if (!cdev)
		return;

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(pos, &thermal_cdev_list, node)
		if (pos == cdev)
			break;
	if (pos != cdev) {
		/* thermal cooling device not found */
		mutex_unlock(&thermal_list_lock);
		return;
	}
	list_del(&cdev->node);

	/* Unbind all thermal zones associated with 'this' cdev */
	list_for_each_entry(tz, &thermal_tz_list, node) {
		if (tz->ops->unbind) {
			tz->ops->unbind(tz, cdev);
			continue;
		}

		if (!tz->tzp || !tz->tzp->tbp)
			continue;

		tzp = tz->tzp;
		for (i = 0; i < tzp->num_tbps; i++) {
			if (tzp->tbp[i].cdev == cdev) {
				__unbind(tz, tzp->tbp[i].trip_mask, cdev);
				tzp->tbp[i].cdev = NULL;
			}
		}
	}

	mutex_unlock(&thermal_list_lock);

	ida_simple_remove(&thermal_cdev_ida, cdev->id);
	device_del(&cdev->device);
	thermal_cooling_device_destroy_sysfs(cdev);
	put_device(&cdev->device);
}
EXPORT_SYMBOL_GPL(thermal_cooling_device_unregister);

static void bind_tz(struct thermal_zone_device *tz)
{
	int i, ret;
	struct thermal_cooling_device *pos = NULL;
	const struct thermal_zone_params *tzp = tz->tzp;

	if (!tzp && !tz->ops->bind)
		return;

	mutex_lock(&thermal_list_lock);

	/* If there is ops->bind, try to use ops->bind */
	if (tz->ops->bind) {
		list_for_each_entry(pos, &thermal_cdev_list, node) {
			ret = tz->ops->bind(tz, pos);
			if (ret)
				print_bind_err_msg(tz, pos, ret);
		}
		goto exit;
	}

	if (!tzp || !tzp->tbp)
		goto exit;

	list_for_each_entry(pos, &thermal_cdev_list, node) {
		for (i = 0; i < tzp->num_tbps; i++) {
			if (tzp->tbp[i].cdev || !tzp->tbp[i].match)
				continue;
			if (tzp->tbp[i].match(tz, pos))
				continue;
			tzp->tbp[i].cdev = pos;
			__bind(tz, tzp->tbp[i].trip_mask, pos,
			       tzp->tbp[i].binding_limits,
			       tzp->tbp[i].weight);
		}
	}
exit:
	mutex_unlock(&thermal_list_lock);
}

/**
 * thermal_zone_device_register() - register a new thermal zone device
 * @type:	the thermal zone device type
 * @trips:	the number of trip points the thermal zone support
 * @mask:	a bit string indicating the writeablility of trip points
 * @devdata:	private device data
 * @ops:	standard thermal zone device callbacks
 * @tzp:	thermal zone platform parameters
 * @passive_delay: number of milliseconds to wait between polls when
 *		   performing passive cooling
 * @polling_delay: number of milliseconds to wait between polls when checking
 *		   whether trip points have been crossed (0 for interrupt
 *		   driven systems)
 *
 * This interface function adds a new thermal zone device (sensor) to
 * /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
 * thermal cooling devices registered at the same time.
 * thermal_zone_device_unregister() must be called when the device is no
 * longer needed. The passive cooling depends on the .get_trend() return value.
 *
 * Return: a pointer to the created struct thermal_zone_device or an
 * in case of error, an ERR_PTR. Caller must check return value with
 * IS_ERR*() helpers.
 */
struct thermal_zone_device *
thermal_zone_device_register(const char *type, int trips, int mask,
			     void *devdata, struct thermal_zone_device_ops *ops,
			     struct thermal_zone_params *tzp, int passive_delay,
			     int polling_delay)
{
	struct thermal_zone_device *tz;
	enum thermal_trip_type trip_type;
	int trip_temp;
	int result;
	int count;
	struct thermal_governor *governor;

	if (!type || strlen(type) == 0)
		return ERR_PTR(-EINVAL);

	if (type && strlen(type) >= THERMAL_NAME_LENGTH)
		return ERR_PTR(-EINVAL);

	if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips)
		return ERR_PTR(-EINVAL);

	if (!ops)
		return ERR_PTR(-EINVAL);

	if (trips > 0 && (!ops->get_trip_type || !ops->get_trip_temp))
		return ERR_PTR(-EINVAL);

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

	INIT_LIST_HEAD(&tz->thermal_instances);
	ida_init(&tz->ida);
	mutex_init(&tz->lock);
	result = ida_simple_get(&thermal_tz_ida, 0, 0, GFP_KERNEL);
	if (result < 0)
		goto free_tz;

	tz->id = result;
	strlcpy(tz->type, type, sizeof(tz->type));
	tz->ops = ops;
	tz->tzp = tzp;
	tz->device.class = &thermal_class;
	tz->devdata = devdata;
	tz->trips = trips;
	tz->passive_delay = passive_delay;
	tz->polling_delay = polling_delay;

	/* sys I/F */
	/* Add nodes that are always present via .groups */
	result = thermal_zone_create_device_groups(tz, mask);
	if (result)
		goto remove_id;

	/* A new thermal zone needs to be updated anyway. */
	atomic_set(&tz->need_update, 1);

	dev_set_name(&tz->device, "thermal_zone%d", tz->id);
	result = device_register(&tz->device);
	if (result)
		goto remove_device_groups;

	for (count = 0; count < trips; count++) {
		if (tz->ops->get_trip_type(tz, count, &trip_type))
			set_bit(count, &tz->trips_disabled);
		if (tz->ops->get_trip_temp(tz, count, &trip_temp))
			set_bit(count, &tz->trips_disabled);
		/* Check for bogus trip points */
		if (trip_temp == 0)
			set_bit(count, &tz->trips_disabled);
	}

	/* Update 'this' zone's governor information */
	mutex_lock(&thermal_governor_lock);

	if (tz->tzp)
		governor = __find_governor(tz->tzp->governor_name);
	else
		governor = def_governor;

	result = thermal_set_governor(tz, governor);
	if (result) {
		mutex_unlock(&thermal_governor_lock);
		goto unregister;
	}

	mutex_unlock(&thermal_governor_lock);

	if (!tz->tzp || !tz->tzp->no_hwmon) {
		result = thermal_add_hwmon_sysfs(tz);
		if (result)
			goto unregister;
	}

	mutex_lock(&thermal_list_lock);
	list_add_tail(&tz->node, &thermal_tz_list);
	mutex_unlock(&thermal_list_lock);

	/* Bind cooling devices for this zone */
	bind_tz(tz);

	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);

	thermal_zone_device_reset(tz);
	/* Update the new thermal zone and mark it as already updated. */
	if (atomic_cmpxchg(&tz->need_update, 1, 0))
		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);

	return tz;

unregister:
	ida_simple_remove(&thermal_tz_ida, tz->id);
	device_unregister(&tz->device);
	return ERR_PTR(result);

remove_device_groups:
	thermal_zone_destroy_device_groups(tz);
remove_id:
	ida_simple_remove(&thermal_tz_ida, tz->id);
free_tz:
	kfree(tz);
	return ERR_PTR(result);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_register);

/**
 * thermal_device_unregister - removes the registered thermal zone device
 * @tz: the thermal zone device to remove
 */
void thermal_zone_device_unregister(struct thermal_zone_device *tz)
{
	int i;
	const struct thermal_zone_params *tzp;
	struct thermal_cooling_device *cdev;
	struct thermal_zone_device *pos = NULL;

	if (!tz)
		return;

	tzp = tz->tzp;

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(pos, &thermal_tz_list, node)
		if (pos == tz)
			break;
	if (pos != tz) {
		/* thermal zone device not found */
		mutex_unlock(&thermal_list_lock);
		return;
	}
	list_del(&tz->node);

	/* Unbind all cdevs associated with 'this' thermal zone */
	list_for_each_entry(cdev, &thermal_cdev_list, node) {
		if (tz->ops->unbind) {
			tz->ops->unbind(tz, cdev);
			continue;
		}

		if (!tzp || !tzp->tbp)
			break;

		for (i = 0; i < tzp->num_tbps; i++) {
			if (tzp->tbp[i].cdev == cdev) {
				__unbind(tz, tzp->tbp[i].trip_mask, cdev);
				tzp->tbp[i].cdev = NULL;
			}
		}
	}

	mutex_unlock(&thermal_list_lock);

	cancel_delayed_work_sync(&tz->poll_queue);

	thermal_set_governor(tz, NULL);

	thermal_remove_hwmon_sysfs(tz);
	ida_simple_remove(&thermal_tz_ida, tz->id);
	ida_destroy(&tz->ida);
	mutex_destroy(&tz->lock);
	device_unregister(&tz->device);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);

/**
 * thermal_zone_get_zone_by_name() - search for a zone and returns its ref
 * @name: thermal zone name to fetch the temperature
 *
 * When only one zone is found with the passed name, returns a reference to it.
 *
 * Return: On success returns a reference to an unique thermal zone with
 * matching name equals to @name, an ERR_PTR otherwise (-EINVAL for invalid
 * paramenters, -ENODEV for not found and -EEXIST for multiple matches).
 */
struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name)
{
	struct thermal_zone_device *pos = NULL, *ref = ERR_PTR(-EINVAL);
	unsigned int found = 0;

	if (!name)
		goto exit;

	mutex_lock(&thermal_list_lock);
	list_for_each_entry(pos, &thermal_tz_list, node)
		if (!strncasecmp(name, pos->type, THERMAL_NAME_LENGTH)) {
			found++;
			ref = pos;
		}
	mutex_unlock(&thermal_list_lock);

	/* nothing has been found, thus an error code for it */
	if (found == 0)
		ref = ERR_PTR(-ENODEV);
	else if (found > 1)
	/* Success only when an unique zone is found */
		ref = ERR_PTR(-EEXIST);

exit:
	return ref;
}
EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);

#ifdef CONFIG_NET
static const struct genl_multicast_group thermal_event_mcgrps[] = {
	{ .name = THERMAL_GENL_MCAST_GROUP_NAME, },
};

static struct genl_family thermal_event_genl_family __ro_after_init = {
	.module = THIS_MODULE,
	.name = THERMAL_GENL_FAMILY_NAME,
	.version = THERMAL_GENL_VERSION,
	.maxattr = THERMAL_GENL_ATTR_MAX,
	.mcgrps = thermal_event_mcgrps,
	.n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps),
};

int thermal_generate_netlink_event(struct thermal_zone_device *tz,
				   enum events event)
{
	struct sk_buff *skb;
	struct nlattr *attr;
	struct thermal_genl_event *thermal_event;
	void *msg_header;
	int size;
	int result;
	static unsigned int thermal_event_seqnum;

	if (!tz)
		return -EINVAL;

	/* allocate memory */
	size = nla_total_size(sizeof(struct thermal_genl_event)) +
	       nla_total_size(0);

	skb = genlmsg_new(size, GFP_ATOMIC);
	if (!skb)
		return -ENOMEM;

	/* add the genetlink message header */
	msg_header = genlmsg_put(skb, 0, thermal_event_seqnum++,
				 &thermal_event_genl_family, 0,
				 THERMAL_GENL_CMD_EVENT);
	if (!msg_header) {
		nlmsg_free(skb);
		return -ENOMEM;
	}

	/* fill the data */
	attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT,
			   sizeof(struct thermal_genl_event));

	if (!attr) {
		nlmsg_free(skb);
		return -EINVAL;
	}

	thermal_event = nla_data(attr);
	if (!thermal_event) {
		nlmsg_free(skb);
		return -EINVAL;
	}

	memset(thermal_event, 0, sizeof(struct thermal_genl_event));

	thermal_event->orig = tz->id;
	thermal_event->event = event;

	/* send multicast genetlink message */
	genlmsg_end(skb, msg_header);

	result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
				   0, GFP_ATOMIC);
	if (result)
		dev_err(&tz->device, "Failed to send netlink event:%d", result);

	return result;
}
EXPORT_SYMBOL_GPL(thermal_generate_netlink_event);

static int __init genetlink_init(void)
{
	return genl_register_family(&thermal_event_genl_family);
}

static void genetlink_exit(void)
{
	genl_unregister_family(&thermal_event_genl_family);
}
#else /* !CONFIG_NET */
static inline int genetlink_init(void) { return 0; }
static inline void genetlink_exit(void) {}
#endif /* !CONFIG_NET */

static int thermal_pm_notify(struct notifier_block *nb,
			     unsigned long mode, void *_unused)
{
	struct thermal_zone_device *tz;
	enum thermal_device_mode tz_mode;

	switch (mode) {
	case PM_HIBERNATION_PREPARE:
	case PM_RESTORE_PREPARE:
	case PM_SUSPEND_PREPARE:
		atomic_set(&in_suspend, 1);
		break;
	case PM_POST_HIBERNATION:
	case PM_POST_RESTORE:
	case PM_POST_SUSPEND:
		atomic_set(&in_suspend, 0);
		list_for_each_entry(tz, &thermal_tz_list, node) {
			tz_mode = THERMAL_DEVICE_ENABLED;
			if (tz->ops->get_mode)
				tz->ops->get_mode(tz, &tz_mode);

			if (tz_mode == THERMAL_DEVICE_DISABLED)
				continue;

			thermal_zone_device_init(tz);
			thermal_zone_device_update(tz,
						   THERMAL_EVENT_UNSPECIFIED);
		}
		break;
	default:
		break;
	}
	return 0;
}

static struct notifier_block thermal_pm_nb = {
	.notifier_call = thermal_pm_notify,
};

static int __init thermal_init(void)
{
	int result;

	mutex_init(&poweroff_lock);
	result = thermal_register_governors();
	if (result)
		goto error;

	result = class_register(&thermal_class);
	if (result)
		goto unregister_governors;

	result = genetlink_init();
	if (result)
		goto unregister_class;

	result = of_parse_thermal_zones();
	if (result)
		goto exit_netlink;

	result = register_pm_notifier(&thermal_pm_nb);
	if (result)
		pr_warn("Thermal: Can not register suspend notifier, return %d\n",
			result);

	return 0;

exit_netlink:
	genetlink_exit();
unregister_class:
	class_unregister(&thermal_class);
unregister_governors:
	thermal_unregister_governors();
error:
	ida_destroy(&thermal_tz_ida);
	ida_destroy(&thermal_cdev_ida);
	mutex_destroy(&thermal_list_lock);
	mutex_destroy(&thermal_governor_lock);
	mutex_destroy(&poweroff_lock);
	return result;
}
fs_initcall(thermal_init);