summaryrefslogtreecommitdiff
path: root/drivers/base/power/runtime.c
blob: 4244e22e4b403f7679d0958a15d9663e16b9d7c8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
// SPDX-License-Identifier: GPL-2.0
/*
 * drivers/base/power/runtime.c - Helper functions for device runtime PM
 *
 * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
 * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu>
 */
#include <linux/sched/mm.h>
#include <linux/ktime.h>
#include <linux/hrtimer.h>
#include <linux/export.h>
#include <linux/pm_runtime.h>
#include <linux/pm_wakeirq.h>
#include <trace/events/rpm.h>

#include "../base.h"
#include "power.h"

typedef int (*pm_callback_t)(struct device *);

static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
{
	pm_callback_t cb;
	const struct dev_pm_ops *ops;

	if (dev->pm_domain)
		ops = &dev->pm_domain->ops;
	else if (dev->type && dev->type->pm)
		ops = dev->type->pm;
	else if (dev->class && dev->class->pm)
		ops = dev->class->pm;
	else if (dev->bus && dev->bus->pm)
		ops = dev->bus->pm;
	else
		ops = NULL;

	if (ops)
		cb = *(pm_callback_t *)((void *)ops + cb_offset);
	else
		cb = NULL;

	if (!cb && dev->driver && dev->driver->pm)
		cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset);

	return cb;
}

#define RPM_GET_CALLBACK(dev, callback) \
		__rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback))

static int rpm_resume(struct device *dev, int rpmflags);
static int rpm_suspend(struct device *dev, int rpmflags);

/**
 * update_pm_runtime_accounting - Update the time accounting of power states
 * @dev: Device to update the accounting for
 *
 * In order to be able to have time accounting of the various power states
 * (as used by programs such as PowerTOP to show the effectiveness of runtime
 * PM), we need to track the time spent in each state.
 * update_pm_runtime_accounting must be called each time before the
 * runtime_status field is updated, to account the time in the old state
 * correctly.
 */
static void update_pm_runtime_accounting(struct device *dev)
{
	u64 now, last, delta;

	if (dev->power.disable_depth > 0)
		return;

	last = dev->power.accounting_timestamp;

	now = ktime_get_mono_fast_ns();
	dev->power.accounting_timestamp = now;

	/*
	 * Because ktime_get_mono_fast_ns() is not monotonic during
	 * timekeeping updates, ensure that 'now' is after the last saved
	 * timesptamp.
	 */
	if (now < last)
		return;

	delta = now - last;

	if (dev->power.runtime_status == RPM_SUSPENDED)
		dev->power.suspended_time += delta;
	else
		dev->power.active_time += delta;
}

static void __update_runtime_status(struct device *dev, enum rpm_status status)
{
	update_pm_runtime_accounting(dev);
	dev->power.runtime_status = status;
}

static u64 rpm_get_accounted_time(struct device *dev, bool suspended)
{
	u64 time;
	unsigned long flags;

	spin_lock_irqsave(&dev->power.lock, flags);

	update_pm_runtime_accounting(dev);
	time = suspended ? dev->power.suspended_time : dev->power.active_time;

	spin_unlock_irqrestore(&dev->power.lock, flags);

	return time;
}

u64 pm_runtime_active_time(struct device *dev)
{
	return rpm_get_accounted_time(dev, false);
}

u64 pm_runtime_suspended_time(struct device *dev)
{
	return rpm_get_accounted_time(dev, true);
}
EXPORT_SYMBOL_GPL(pm_runtime_suspended_time);

/**
 * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
 * @dev: Device to handle.
 */
static void pm_runtime_deactivate_timer(struct device *dev)
{
	if (dev->power.timer_expires > 0) {
		hrtimer_try_to_cancel(&dev->power.suspend_timer);
		dev->power.timer_expires = 0;
	}
}

/**
 * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests.
 * @dev: Device to handle.
 */
static void pm_runtime_cancel_pending(struct device *dev)
{
	pm_runtime_deactivate_timer(dev);
	/*
	 * In case there's a request pending, make sure its work function will
	 * return without doing anything.
	 */
	dev->power.request = RPM_REQ_NONE;
}

/*
 * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time.
 * @dev: Device to handle.
 *
 * Compute the autosuspend-delay expiration time based on the device's
 * power.last_busy time.  If the delay has already expired or is disabled
 * (negative) or the power.use_autosuspend flag isn't set, return 0.
 * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero).
 *
 * This function may be called either with or without dev->power.lock held.
 * Either way it can be racy, since power.last_busy may be updated at any time.
 */
u64 pm_runtime_autosuspend_expiration(struct device *dev)
{
	int autosuspend_delay;
	u64 expires;

	if (!dev->power.use_autosuspend)
		return 0;

	autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay);
	if (autosuspend_delay < 0)
		return 0;

	expires  = READ_ONCE(dev->power.last_busy);
	expires += (u64)autosuspend_delay * NSEC_PER_MSEC;
	if (expires > ktime_get_mono_fast_ns())
		return expires;	/* Expires in the future */

	return 0;
}
EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);

static int dev_memalloc_noio(struct device *dev, void *data)
{
	return dev->power.memalloc_noio;
}

/*
 * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
 * @dev: Device to handle.
 * @enable: True for setting the flag and False for clearing the flag.
 *
 * Set the flag for all devices in the path from the device to the
 * root device in the device tree if @enable is true, otherwise clear
 * the flag for devices in the path whose siblings don't set the flag.
 *
 * The function should only be called by block device, or network
 * device driver for solving the deadlock problem during runtime
 * resume/suspend:
 *
 *     If memory allocation with GFP_KERNEL is called inside runtime
 *     resume/suspend callback of any one of its ancestors(or the
 *     block device itself), the deadlock may be triggered inside the
 *     memory allocation since it might not complete until the block
 *     device becomes active and the involed page I/O finishes. The
 *     situation is pointed out first by Alan Stern. Network device
 *     are involved in iSCSI kind of situation.
 *
 * The lock of dev_hotplug_mutex is held in the function for handling
 * hotplug race because pm_runtime_set_memalloc_noio() may be called
 * in async probe().
 *
 * The function should be called between device_add() and device_del()
 * on the affected device(block/network device).
 */
void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
{
	static DEFINE_MUTEX(dev_hotplug_mutex);

	mutex_lock(&dev_hotplug_mutex);
	for (;;) {
		bool enabled;

		/* hold power lock since bitfield is not SMP-safe. */
		spin_lock_irq(&dev->power.lock);
		enabled = dev->power.memalloc_noio;
		dev->power.memalloc_noio = enable;
		spin_unlock_irq(&dev->power.lock);

		/*
		 * not need to enable ancestors any more if the device
		 * has been enabled.
		 */
		if (enabled && enable)
			break;

		dev = dev->parent;

		/*
		 * clear flag of the parent device only if all the
		 * children don't set the flag because ancestor's
		 * flag was set by any one of the descendants.
		 */
		if (!dev || (!enable &&
			     device_for_each_child(dev, NULL,
						   dev_memalloc_noio)))
			break;
	}
	mutex_unlock(&dev_hotplug_mutex);
}
EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);

/**
 * rpm_check_suspend_allowed - Test whether a device may be suspended.
 * @dev: Device to test.
 */
static int rpm_check_suspend_allowed(struct device *dev)
{
	int retval = 0;

	if (dev->power.runtime_error)
		retval = -EINVAL;
	else if (dev->power.disable_depth > 0)
		retval = -EACCES;
	else if (atomic_read(&dev->power.usage_count) > 0)
		retval = -EAGAIN;
	else if (!dev->power.ignore_children &&
			atomic_read(&dev->power.child_count))
		retval = -EBUSY;

	/* Pending resume requests take precedence over suspends. */
	else if ((dev->power.deferred_resume
			&& dev->power.runtime_status == RPM_SUSPENDING)
	    || (dev->power.request_pending
			&& dev->power.request == RPM_REQ_RESUME))
		retval = -EAGAIN;
	else if (__dev_pm_qos_resume_latency(dev) == 0)
		retval = -EPERM;
	else if (dev->power.runtime_status == RPM_SUSPENDED)
		retval = 1;

	return retval;
}

static int rpm_get_suppliers(struct device *dev)
{
	struct device_link *link;

	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
				device_links_read_lock_held()) {
		int retval;

		if (!(link->flags & DL_FLAG_PM_RUNTIME))
			continue;

		retval = pm_runtime_get_sync(link->supplier);
		/* Ignore suppliers with disabled runtime PM. */
		if (retval < 0 && retval != -EACCES) {
			pm_runtime_put_noidle(link->supplier);
			return retval;
		}
		refcount_inc(&link->rpm_active);
	}
	return 0;
}

static void rpm_put_suppliers(struct device *dev)
{
	struct device_link *link;

	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
				device_links_read_lock_held()) {

		while (refcount_dec_not_one(&link->rpm_active))
			pm_runtime_put(link->supplier);
	}
}

/**
 * __rpm_callback - Run a given runtime PM callback for a given device.
 * @cb: Runtime PM callback to run.
 * @dev: Device to run the callback for.
 */
static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
	__releases(&dev->power.lock) __acquires(&dev->power.lock)
{
	int retval, idx;
	bool use_links = dev->power.links_count > 0;

	if (dev->power.irq_safe) {
		spin_unlock(&dev->power.lock);
	} else {
		spin_unlock_irq(&dev->power.lock);

		/*
		 * Resume suppliers if necessary.
		 *
		 * The device's runtime PM status cannot change until this
		 * routine returns, so it is safe to read the status outside of
		 * the lock.
		 */
		if (use_links && dev->power.runtime_status == RPM_RESUMING) {
			idx = device_links_read_lock();

			retval = rpm_get_suppliers(dev);
			if (retval)
				goto fail;

			device_links_read_unlock(idx);
		}
	}

	retval = cb(dev);

	if (dev->power.irq_safe) {
		spin_lock(&dev->power.lock);
	} else {
		/*
		 * If the device is suspending and the callback has returned
		 * success, drop the usage counters of the suppliers that have
		 * been reference counted on its resume.
		 *
		 * Do that if resume fails too.
		 */
		if (use_links
		    && ((dev->power.runtime_status == RPM_SUSPENDING && !retval)
		    || (dev->power.runtime_status == RPM_RESUMING && retval))) {
			idx = device_links_read_lock();

 fail:
			rpm_put_suppliers(dev);

			device_links_read_unlock(idx);
		}

		spin_lock_irq(&dev->power.lock);
	}

	return retval;
}

/**
 * rpm_idle - Notify device bus type if the device can be suspended.
 * @dev: Device to notify the bus type about.
 * @rpmflags: Flag bits.
 *
 * Check if the device's runtime PM status allows it to be suspended.  If
 * another idle notification has been started earlier, return immediately.  If
 * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
 * run the ->runtime_idle() callback directly. If the ->runtime_idle callback
 * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag.
 *
 * This function must be called under dev->power.lock with interrupts disabled.
 */
static int rpm_idle(struct device *dev, int rpmflags)
{
	int (*callback)(struct device *);
	int retval;

	trace_rpm_idle_rcuidle(dev, rpmflags);
	retval = rpm_check_suspend_allowed(dev);
	if (retval < 0)
		;	/* Conditions are wrong. */

	/* Idle notifications are allowed only in the RPM_ACTIVE state. */
	else if (dev->power.runtime_status != RPM_ACTIVE)
		retval = -EAGAIN;

	/*
	 * Any pending request other than an idle notification takes
	 * precedence over us, except that the timer may be running.
	 */
	else if (dev->power.request_pending &&
	    dev->power.request > RPM_REQ_IDLE)
		retval = -EAGAIN;

	/* Act as though RPM_NOWAIT is always set. */
	else if (dev->power.idle_notification)
		retval = -EINPROGRESS;
	if (retval)
		goto out;

	/* Pending requests need to be canceled. */
	dev->power.request = RPM_REQ_NONE;

	if (dev->power.no_callbacks)
		goto out;

	/* Carry out an asynchronous or a synchronous idle notification. */
	if (rpmflags & RPM_ASYNC) {
		dev->power.request = RPM_REQ_IDLE;
		if (!dev->power.request_pending) {
			dev->power.request_pending = true;
			queue_work(pm_wq, &dev->power.work);
		}
		trace_rpm_return_int_rcuidle(dev, _THIS_IP_, 0);
		return 0;
	}

	dev->power.idle_notification = true;

	callback = RPM_GET_CALLBACK(dev, runtime_idle);

	if (callback)
		retval = __rpm_callback(callback, dev);

	dev->power.idle_notification = false;
	wake_up_all(&dev->power.wait_queue);

 out:
	trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
	return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO);
}

/**
 * rpm_callback - Run a given runtime PM callback for a given device.
 * @cb: Runtime PM callback to run.
 * @dev: Device to run the callback for.
 */
static int rpm_callback(int (*cb)(struct device *), struct device *dev)
{
	int retval;

	if (!cb)
		return -ENOSYS;

	if (dev->power.memalloc_noio) {
		unsigned int noio_flag;

		/*
		 * Deadlock might be caused if memory allocation with
		 * GFP_KERNEL happens inside runtime_suspend and
		 * runtime_resume callbacks of one block device's
		 * ancestor or the block device itself. Network
		 * device might be thought as part of iSCSI block
		 * device, so network device and its ancestor should
		 * be marked as memalloc_noio too.
		 */
		noio_flag = memalloc_noio_save();
		retval = __rpm_callback(cb, dev);
		memalloc_noio_restore(noio_flag);
	} else {
		retval = __rpm_callback(cb, dev);
	}

	dev->power.runtime_error = retval;
	return retval != -EACCES ? retval : -EIO;
}

/**
 * rpm_suspend - Carry out runtime suspend of given device.
 * @dev: Device to suspend.
 * @rpmflags: Flag bits.
 *
 * Check if the device's runtime PM status allows it to be suspended.
 * Cancel a pending idle notification, autosuspend or suspend. If
 * another suspend has been started earlier, either return immediately
 * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC
 * flags. If the RPM_ASYNC flag is set then queue a suspend request;
 * otherwise run the ->runtime_suspend() callback directly. When
 * ->runtime_suspend succeeded, if a deferred resume was requested while
 * the callback was running then carry it out, otherwise send an idle
 * notification for its parent (if the suspend succeeded and both
 * ignore_children of parent->power and irq_safe of dev->power are not set).
 * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO
 * flag is set and the next autosuspend-delay expiration time is in the
 * future, schedule another autosuspend attempt.
 *
 * This function must be called under dev->power.lock with interrupts disabled.
 */
static int rpm_suspend(struct device *dev, int rpmflags)
	__releases(&dev->power.lock) __acquires(&dev->power.lock)
{
	int (*callback)(struct device *);
	struct device *parent = NULL;
	int retval;

	trace_rpm_suspend_rcuidle(dev, rpmflags);

 repeat:
	retval = rpm_check_suspend_allowed(dev);

	if (retval < 0)
		;	/* Conditions are wrong. */

	/* Synchronous suspends are not allowed in the RPM_RESUMING state. */
	else if (dev->power.runtime_status == RPM_RESUMING &&
	    !(rpmflags & RPM_ASYNC))
		retval = -EAGAIN;
	if (retval)
		goto out;

	/* If the autosuspend_delay time hasn't expired yet, reschedule. */
	if ((rpmflags & RPM_AUTO)
	    && dev->power.runtime_status != RPM_SUSPENDING) {
		u64 expires = pm_runtime_autosuspend_expiration(dev);

		if (expires != 0) {
			/* Pending requests need to be canceled. */
			dev->power.request = RPM_REQ_NONE;

			/*
			 * Optimization: If the timer is already running and is
			 * set to expire at or before the autosuspend delay,
			 * avoid the overhead of resetting it.  Just let it
			 * expire; pm_suspend_timer_fn() will take care of the
			 * rest.
			 */
			if (!(dev->power.timer_expires &&
					dev->power.timer_expires <= expires)) {
				/*
				 * We add a slack of 25% to gather wakeups
				 * without sacrificing the granularity.
				 */
				u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) *
						    (NSEC_PER_MSEC >> 2);

				dev->power.timer_expires = expires;
				hrtimer_start_range_ns(&dev->power.suspend_timer,
						ns_to_ktime(expires),
						slack,
						HRTIMER_MODE_ABS);
			}
			dev->power.timer_autosuspends = 1;
			goto out;
		}
	}

	/* Other scheduled or pending requests need to be canceled. */
	pm_runtime_cancel_pending(dev);

	if (dev->power.runtime_status == RPM_SUSPENDING) {
		DEFINE_WAIT(wait);

		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
			retval = -EINPROGRESS;
			goto out;
		}

		if (dev->power.irq_safe) {
			spin_unlock(&dev->power.lock);

			cpu_relax();

			spin_lock(&dev->power.lock);
			goto repeat;
		}

		/* Wait for the other suspend running in parallel with us. */
		for (;;) {
			prepare_to_wait(&dev->power.wait_queue, &wait,
					TASK_UNINTERRUPTIBLE);
			if (dev->power.runtime_status != RPM_SUSPENDING)
				break;

			spin_unlock_irq(&dev->power.lock);

			schedule();

			spin_lock_irq(&dev->power.lock);
		}
		finish_wait(&dev->power.wait_queue, &wait);
		goto repeat;
	}

	if (dev->power.no_callbacks)
		goto no_callback;	/* Assume success. */

	/* Carry out an asynchronous or a synchronous suspend. */
	if (rpmflags & RPM_ASYNC) {
		dev->power.request = (rpmflags & RPM_AUTO) ?
		    RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND;
		if (!dev->power.request_pending) {
			dev->power.request_pending = true;
			queue_work(pm_wq, &dev->power.work);
		}
		goto out;
	}

	__update_runtime_status(dev, RPM_SUSPENDING);

	callback = RPM_GET_CALLBACK(dev, runtime_suspend);

	dev_pm_enable_wake_irq_check(dev, true);
	retval = rpm_callback(callback, dev);
	if (retval)
		goto fail;

 no_callback:
	__update_runtime_status(dev, RPM_SUSPENDED);
	pm_runtime_deactivate_timer(dev);

	if (dev->parent) {
		parent = dev->parent;
		atomic_add_unless(&parent->power.child_count, -1, 0);
	}
	wake_up_all(&dev->power.wait_queue);

	if (dev->power.deferred_resume) {
		dev->power.deferred_resume = false;
		rpm_resume(dev, 0);
		retval = -EAGAIN;
		goto out;
	}

	/* Maybe the parent is now able to suspend. */
	if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
		spin_unlock(&dev->power.lock);

		spin_lock(&parent->power.lock);
		rpm_idle(parent, RPM_ASYNC);
		spin_unlock(&parent->power.lock);

		spin_lock(&dev->power.lock);
	}

 out:
	trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);

	return retval;

 fail:
	dev_pm_disable_wake_irq_check(dev);
	__update_runtime_status(dev, RPM_ACTIVE);
	dev->power.deferred_resume = false;
	wake_up_all(&dev->power.wait_queue);

	if (retval == -EAGAIN || retval == -EBUSY) {
		dev->power.runtime_error = 0;

		/*
		 * If the callback routine failed an autosuspend, and
		 * if the last_busy time has been updated so that there
		 * is a new autosuspend expiration time, automatically
		 * reschedule another autosuspend.
		 */
		if ((rpmflags & RPM_AUTO) &&
		    pm_runtime_autosuspend_expiration(dev) != 0)
			goto repeat;
	} else {
		pm_runtime_cancel_pending(dev);
	}
	goto out;
}

/**
 * rpm_resume - Carry out runtime resume of given device.
 * @dev: Device to resume.
 * @rpmflags: Flag bits.
 *
 * Check if the device's runtime PM status allows it to be resumed.  Cancel
 * any scheduled or pending requests.  If another resume has been started
 * earlier, either return immediately or wait for it to finish, depending on the
 * RPM_NOWAIT and RPM_ASYNC flags.  Similarly, if there's a suspend running in
 * parallel with this function, either tell the other process to resume after
 * suspending (deferred_resume) or wait for it to finish.  If the RPM_ASYNC
 * flag is set then queue a resume request; otherwise run the
 * ->runtime_resume() callback directly.  Queue an idle notification for the
 * device if the resume succeeded.
 *
 * This function must be called under dev->power.lock with interrupts disabled.
 */
static int rpm_resume(struct device *dev, int rpmflags)
	__releases(&dev->power.lock) __acquires(&dev->power.lock)
{
	int (*callback)(struct device *);
	struct device *parent = NULL;
	int retval = 0;

	trace_rpm_resume_rcuidle(dev, rpmflags);

 repeat:
	if (dev->power.runtime_error)
		retval = -EINVAL;
	else if (dev->power.disable_depth == 1 && dev->power.is_suspended
	    && dev->power.runtime_status == RPM_ACTIVE)
		retval = 1;
	else if (dev->power.disable_depth > 0)
		retval = -EACCES;
	if (retval)
		goto out;

	/*
	 * Other scheduled or pending requests need to be canceled.  Small
	 * optimization: If an autosuspend timer is running, leave it running
	 * rather than cancelling it now only to restart it again in the near
	 * future.
	 */
	dev->power.request = RPM_REQ_NONE;
	if (!dev->power.timer_autosuspends)
		pm_runtime_deactivate_timer(dev);

	if (dev->power.runtime_status == RPM_ACTIVE) {
		retval = 1;
		goto out;
	}

	if (dev->power.runtime_status == RPM_RESUMING
	    || dev->power.runtime_status == RPM_SUSPENDING) {
		DEFINE_WAIT(wait);

		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
			if (dev->power.runtime_status == RPM_SUSPENDING)
				dev->power.deferred_resume = true;
			else
				retval = -EINPROGRESS;
			goto out;
		}

		if (dev->power.irq_safe) {
			spin_unlock(&dev->power.lock);

			cpu_relax();

			spin_lock(&dev->power.lock);
			goto repeat;
		}

		/* Wait for the operation carried out in parallel with us. */
		for (;;) {
			prepare_to_wait(&dev->power.wait_queue, &wait,
					TASK_UNINTERRUPTIBLE);
			if (dev->power.runtime_status != RPM_RESUMING
			    && dev->power.runtime_status != RPM_SUSPENDING)
				break;

			spin_unlock_irq(&dev->power.lock);

			schedule();

			spin_lock_irq(&dev->power.lock);
		}
		finish_wait(&dev->power.wait_queue, &wait);
		goto repeat;
	}

	/*
	 * See if we can skip waking up the parent.  This is safe only if
	 * power.no_callbacks is set, because otherwise we don't know whether
	 * the resume will actually succeed.
	 */
	if (dev->power.no_callbacks && !parent && dev->parent) {
		spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING);
		if (dev->parent->power.disable_depth > 0
		    || dev->parent->power.ignore_children
		    || dev->parent->power.runtime_status == RPM_ACTIVE) {
			atomic_inc(&dev->parent->power.child_count);
			spin_unlock(&dev->parent->power.lock);
			retval = 1;
			goto no_callback;	/* Assume success. */
		}
		spin_unlock(&dev->parent->power.lock);
	}

	/* Carry out an asynchronous or a synchronous resume. */
	if (rpmflags & RPM_ASYNC) {
		dev->power.request = RPM_REQ_RESUME;
		if (!dev->power.request_pending) {
			dev->power.request_pending = true;
			queue_work(pm_wq, &dev->power.work);
		}
		retval = 0;
		goto out;
	}

	if (!parent && dev->parent) {
		/*
		 * Increment the parent's usage counter and resume it if
		 * necessary.  Not needed if dev is irq-safe; then the
		 * parent is permanently resumed.
		 */
		parent = dev->parent;
		if (dev->power.irq_safe)
			goto skip_parent;
		spin_unlock(&dev->power.lock);

		pm_runtime_get_noresume(parent);

		spin_lock(&parent->power.lock);
		/*
		 * Resume the parent if it has runtime PM enabled and not been
		 * set to ignore its children.
		 */
		if (!parent->power.disable_depth
		    && !parent->power.ignore_children) {
			rpm_resume(parent, 0);
			if (parent->power.runtime_status != RPM_ACTIVE)
				retval = -EBUSY;
		}
		spin_unlock(&parent->power.lock);

		spin_lock(&dev->power.lock);
		if (retval)
			goto out;
		goto repeat;
	}
 skip_parent:

	if (dev->power.no_callbacks)
		goto no_callback;	/* Assume success. */

	__update_runtime_status(dev, RPM_RESUMING);

	callback = RPM_GET_CALLBACK(dev, runtime_resume);

	dev_pm_disable_wake_irq_check(dev);
	retval = rpm_callback(callback, dev);
	if (retval) {
		__update_runtime_status(dev, RPM_SUSPENDED);
		pm_runtime_cancel_pending(dev);
		dev_pm_enable_wake_irq_check(dev, false);
	} else {
 no_callback:
		__update_runtime_status(dev, RPM_ACTIVE);
		pm_runtime_mark_last_busy(dev);
		if (parent)
			atomic_inc(&parent->power.child_count);
	}
	wake_up_all(&dev->power.wait_queue);

	if (retval >= 0)
		rpm_idle(dev, RPM_ASYNC);

 out:
	if (parent && !dev->power.irq_safe) {
		spin_unlock_irq(&dev->power.lock);

		pm_runtime_put(parent);

		spin_lock_irq(&dev->power.lock);
	}

	trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);

	return retval;
}

/**
 * pm_runtime_work - Universal runtime PM work function.
 * @work: Work structure used for scheduling the execution of this function.
 *
 * Use @work to get the device object the work is to be done for, determine what
 * is to be done and execute the appropriate runtime PM function.
 */
static void pm_runtime_work(struct work_struct *work)
{
	struct device *dev = container_of(work, struct device, power.work);
	enum rpm_request req;

	spin_lock_irq(&dev->power.lock);

	if (!dev->power.request_pending)
		goto out;

	req = dev->power.request;
	dev->power.request = RPM_REQ_NONE;
	dev->power.request_pending = false;

	switch (req) {
	case RPM_REQ_NONE:
		break;
	case RPM_REQ_IDLE:
		rpm_idle(dev, RPM_NOWAIT);
		break;
	case RPM_REQ_SUSPEND:
		rpm_suspend(dev, RPM_NOWAIT);
		break;
	case RPM_REQ_AUTOSUSPEND:
		rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO);
		break;
	case RPM_REQ_RESUME:
		rpm_resume(dev, RPM_NOWAIT);
		break;
	}

 out:
	spin_unlock_irq(&dev->power.lock);
}

/**
 * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
 * @data: Device pointer passed by pm_schedule_suspend().
 *
 * Check if the time is right and queue a suspend request.
 */
static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
{
	struct device *dev = container_of(timer, struct device, power.suspend_timer);
	unsigned long flags;
	u64 expires;

	spin_lock_irqsave(&dev->power.lock, flags);

	expires = dev->power.timer_expires;
	/*
	 * If 'expires' is after the current time, we've been called
	 * too early.
	 */
	if (expires > 0 && expires < ktime_get_mono_fast_ns()) {
		dev->power.timer_expires = 0;
		rpm_suspend(dev, dev->power.timer_autosuspends ?
		    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
	}

	spin_unlock_irqrestore(&dev->power.lock, flags);

	return HRTIMER_NORESTART;
}

/**
 * pm_schedule_suspend - Set up a timer to submit a suspend request in future.
 * @dev: Device to suspend.
 * @delay: Time to wait before submitting a suspend request, in milliseconds.
 */
int pm_schedule_suspend(struct device *dev, unsigned int delay)
{
	unsigned long flags;
	u64 expires;
	int retval;

	spin_lock_irqsave(&dev->power.lock, flags);

	if (!delay) {
		retval = rpm_suspend(dev, RPM_ASYNC);
		goto out;
	}

	retval = rpm_check_suspend_allowed(dev);
	if (retval)
		goto out;

	/* Other scheduled or pending requests need to be canceled. */
	pm_runtime_cancel_pending(dev);

	expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC;
	dev->power.timer_expires = expires;
	dev->power.timer_autosuspends = 0;
	hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS);

 out:
	spin_unlock_irqrestore(&dev->power.lock, flags);

	return retval;
}
EXPORT_SYMBOL_GPL(pm_schedule_suspend);

/**
 * __pm_runtime_idle - Entry point for runtime idle operations.
 * @dev: Device to send idle notification for.
 * @rpmflags: Flag bits.
 *
 * If the RPM_GET_PUT flag is set, decrement the device's usage count and
 * return immediately if it is larger than zero.  Then carry out an idle
 * notification, either synchronous or asynchronous.
 *
 * This routine may be called in atomic context if the RPM_ASYNC flag is set,
 * or if pm_runtime_irq_safe() has been called.
 */
int __pm_runtime_idle(struct device *dev, int rpmflags)
{
	unsigned long flags;
	int retval;

	if (rpmflags & RPM_GET_PUT) {
		if (!atomic_dec_and_test(&dev->power.usage_count))
			return 0;
	}

	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);

	spin_lock_irqsave(&dev->power.lock, flags);
	retval = rpm_idle(dev, rpmflags);
	spin_unlock_irqrestore(&dev->power.lock, flags);

	return retval;
}
EXPORT_SYMBOL_GPL(__pm_runtime_idle);

/**
 * __pm_runtime_suspend - Entry point for runtime put/suspend operations.
 * @dev: Device to suspend.
 * @rpmflags: Flag bits.
 *
 * If the RPM_GET_PUT flag is set, decrement the device's usage count and
 * return immediately if it is larger than zero.  Then carry out a suspend,
 * either synchronous or asynchronous.
 *
 * This routine may be called in atomic context if the RPM_ASYNC flag is set,
 * or if pm_runtime_irq_safe() has been called.
 */
int __pm_runtime_suspend(struct device *dev, int rpmflags)
{
	unsigned long flags;
	int retval;

	if (rpmflags & RPM_GET_PUT) {
		if (!atomic_dec_and_test(&dev->power.usage_count))
			return 0;
	}

	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);

	spin_lock_irqsave(&dev->power.lock, flags);
	retval = rpm_suspend(dev, rpmflags);
	spin_unlock_irqrestore(&dev->power.lock, flags);

	return retval;
}
EXPORT_SYMBOL_GPL(__pm_runtime_suspend);

/**
 * __pm_runtime_resume - Entry point for runtime resume operations.
 * @dev: Device to resume.
 * @rpmflags: Flag bits.
 *
 * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
 * carry out a resume, either synchronous or asynchronous.
 *
 * This routine may be called in atomic context if the RPM_ASYNC flag is set,
 * or if pm_runtime_irq_safe() has been called.
 */
int __pm_runtime_resume(struct device *dev, int rpmflags)
{
	unsigned long flags;
	int retval;

	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
			dev->power.runtime_status != RPM_ACTIVE);

	if (rpmflags & RPM_GET_PUT)
		atomic_inc(&dev->power.usage_count);

	spin_lock_irqsave(&dev->power.lock, flags);
	retval = rpm_resume(dev, rpmflags);
	spin_unlock_irqrestore(&dev->power.lock, flags);

	return retval;
}
EXPORT_SYMBOL_GPL(__pm_runtime_resume);

/**
 * pm_runtime_get_if_in_use - Conditionally bump up the device's usage counter.
 * @dev: Device to handle.
 *
 * Return -EINVAL if runtime PM is disabled for the device.
 *
 * If that's not the case and if the device's runtime PM status is RPM_ACTIVE
 * and the runtime PM usage counter is nonzero, increment the counter and
 * return 1.  Otherwise return 0 without changing the counter.
 */
int pm_runtime_get_if_in_use(struct device *dev)
{
	unsigned long flags;
	int retval;

	spin_lock_irqsave(&dev->power.lock, flags);
	retval = dev->power.disable_depth > 0 ? -EINVAL :
		dev->power.runtime_status == RPM_ACTIVE
			&& atomic_inc_not_zero(&dev->power.usage_count);
	spin_unlock_irqrestore(&dev->power.lock, flags);
	return retval;
}
EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use);

/**
 * __pm_runtime_set_status - Set runtime PM status of a device.
 * @dev: Device to handle.
 * @status: New runtime PM status of the device.
 *
 * If runtime PM of the device is disabled or its power.runtime_error field is
 * different from zero, the status may be changed either to RPM_ACTIVE, or to
 * RPM_SUSPENDED, as long as that reflects the actual state of the device.
 * However, if the device has a parent and the parent is not active, and the
 * parent's power.ignore_children flag is unset, the device's status cannot be
 * set to RPM_ACTIVE, so -EBUSY is returned in that case.
 *
 * If successful, __pm_runtime_set_status() clears the power.runtime_error field
 * and the device parent's counter of unsuspended children is modified to
 * reflect the new status.  If the new status is RPM_SUSPENDED, an idle
 * notification request for the parent is submitted.
 *
 * If @dev has any suppliers (as reflected by device links to them), and @status
 * is RPM_ACTIVE, they will be activated upfront and if the activation of one
 * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead
 * of the @status value) and the suppliers will be deacticated on exit.  The
 * error returned by the failing supplier activation will be returned in that
 * case.
 */
int __pm_runtime_set_status(struct device *dev, unsigned int status)
{
	struct device *parent = dev->parent;
	bool notify_parent = false;
	int error = 0;

	if (status != RPM_ACTIVE && status != RPM_SUSPENDED)
		return -EINVAL;

	spin_lock_irq(&dev->power.lock);

	/*
	 * Prevent PM-runtime from being enabled for the device or return an
	 * error if it is enabled already and working.
	 */
	if (dev->power.runtime_error || dev->power.disable_depth)
		dev->power.disable_depth++;
	else
		error = -EAGAIN;

	spin_unlock_irq(&dev->power.lock);

	if (error)
		return error;

	/*
	 * If the new status is RPM_ACTIVE, the suppliers can be activated
	 * upfront regardless of the current status, because next time
	 * rpm_put_suppliers() runs, the rpm_active refcounts of the links
	 * involved will be dropped down to one anyway.
	 */
	if (status == RPM_ACTIVE) {
		int idx = device_links_read_lock();

		error = rpm_get_suppliers(dev);
		if (error)
			status = RPM_SUSPENDED;

		device_links_read_unlock(idx);
	}

	spin_lock_irq(&dev->power.lock);

	if (dev->power.runtime_status == status || !parent)
		goto out_set;

	if (status == RPM_SUSPENDED) {
		atomic_add_unless(&parent->power.child_count, -1, 0);
		notify_parent = !parent->power.ignore_children;
	} else {
		spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);

		/*
		 * It is invalid to put an active child under a parent that is
		 * not active, has runtime PM enabled and the
		 * 'power.ignore_children' flag unset.
		 */
		if (!parent->power.disable_depth
		    && !parent->power.ignore_children
		    && parent->power.runtime_status != RPM_ACTIVE) {
			dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n",
				dev_name(dev),
				dev_name(parent));
			error = -EBUSY;
		} else if (dev->power.runtime_status == RPM_SUSPENDED) {
			atomic_inc(&parent->power.child_count);
		}

		spin_unlock(&parent->power.lock);

		if (error) {
			status = RPM_SUSPENDED;
			goto out;
		}
	}

 out_set:
	__update_runtime_status(dev, status);
	if (!error)
		dev->power.runtime_error = 0;

 out:
	spin_unlock_irq(&dev->power.lock);

	if (notify_parent)
		pm_request_idle(parent);

	if (status == RPM_SUSPENDED) {
		int idx = device_links_read_lock();

		rpm_put_suppliers(dev);

		device_links_read_unlock(idx);
	}

	pm_runtime_enable(dev);

	return error;
}
EXPORT_SYMBOL_GPL(__pm_runtime_set_status);

/**
 * __pm_runtime_barrier - Cancel pending requests and wait for completions.
 * @dev: Device to handle.
 *
 * Flush all pending requests for the device from pm_wq and wait for all
 * runtime PM operations involving the device in progress to complete.
 *
 * Should be called under dev->power.lock with interrupts disabled.
 */
static void __pm_runtime_barrier(struct device *dev)
{
	pm_runtime_deactivate_timer(dev);

	if (dev->power.request_pending) {
		dev->power.request = RPM_REQ_NONE;
		spin_unlock_irq(&dev->power.lock);

		cancel_work_sync(&dev->power.work);

		spin_lock_irq(&dev->power.lock);
		dev->power.request_pending = false;
	}

	if (dev->power.runtime_status == RPM_SUSPENDING
	    || dev->power.runtime_status == RPM_RESUMING
	    || dev->power.idle_notification) {
		DEFINE_WAIT(wait);

		/* Suspend, wake-up or idle notification in progress. */
		for (;;) {
			prepare_to_wait(&dev->power.wait_queue, &wait,
					TASK_UNINTERRUPTIBLE);
			if (dev->power.runtime_status != RPM_SUSPENDING
			    && dev->power.runtime_status != RPM_RESUMING
			    && !dev->power.idle_notification)
				break;
			spin_unlock_irq(&dev->power.lock);

			schedule();

			spin_lock_irq(&dev->power.lock);
		}
		finish_wait(&dev->power.wait_queue, &wait);
	}
}

/**
 * pm_runtime_barrier - Flush pending requests and wait for completions.
 * @dev: Device to handle.
 *
 * Prevent the device from being suspended by incrementing its usage counter and
 * if there's a pending resume request for the device, wake the device up.
 * Next, make sure that all pending requests for the device have been flushed
 * from pm_wq and wait for all runtime PM operations involving the device in
 * progress to complete.
 *
 * Return value:
 * 1, if there was a resume request pending and the device had to be woken up,
 * 0, otherwise
 */
int pm_runtime_barrier(struct device *dev)
{
	int retval = 0;

	pm_runtime_get_noresume(dev);
	spin_lock_irq(&dev->power.lock);

	if (dev->power.request_pending
	    && dev->power.request == RPM_REQ_RESUME) {
		rpm_resume(dev, 0);
		retval = 1;
	}

	__pm_runtime_barrier(dev);

	spin_unlock_irq(&dev->power.lock);
	pm_runtime_put_noidle(dev);

	return retval;
}
EXPORT_SYMBOL_GPL(pm_runtime_barrier);

/**
 * __pm_runtime_disable - Disable runtime PM of a device.
 * @dev: Device to handle.
 * @check_resume: If set, check if there's a resume request for the device.
 *
 * Increment power.disable_depth for the device and if it was zero previously,
 * cancel all pending runtime PM requests for the device and wait for all
 * operations in progress to complete.  The device can be either active or
 * suspended after its runtime PM has been disabled.
 *
 * If @check_resume is set and there's a resume request pending when
 * __pm_runtime_disable() is called and power.disable_depth is zero, the
 * function will wake up the device before disabling its runtime PM.
 */
void __pm_runtime_disable(struct device *dev, bool check_resume)
{
	spin_lock_irq(&dev->power.lock);

	if (dev->power.disable_depth > 0) {
		dev->power.disable_depth++;
		goto out;
	}

	/*
	 * Wake up the device if there's a resume request pending, because that
	 * means there probably is some I/O to process and disabling runtime PM
	 * shouldn't prevent the device from processing the I/O.
	 */
	if (check_resume && dev->power.request_pending
	    && dev->power.request == RPM_REQ_RESUME) {
		/*
		 * Prevent suspends and idle notifications from being carried
		 * out after we have woken up the device.
		 */
		pm_runtime_get_noresume(dev);

		rpm_resume(dev, 0);

		pm_runtime_put_noidle(dev);
	}

	/* Update time accounting before disabling PM-runtime. */
	update_pm_runtime_accounting(dev);

	if (!dev->power.disable_depth++)
		__pm_runtime_barrier(dev);

 out:
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(__pm_runtime_disable);

/**
 * pm_runtime_enable - Enable runtime PM of a device.
 * @dev: Device to handle.
 */
void pm_runtime_enable(struct device *dev)
{
	unsigned long flags;

	spin_lock_irqsave(&dev->power.lock, flags);

	if (dev->power.disable_depth > 0) {
		dev->power.disable_depth--;

		/* About to enable runtime pm, set accounting_timestamp to now */
		if (!dev->power.disable_depth)
			dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
	} else {
		dev_warn(dev, "Unbalanced %s!\n", __func__);
	}

	WARN(!dev->power.disable_depth &&
	     dev->power.runtime_status == RPM_SUSPENDED &&
	     !dev->power.ignore_children &&
	     atomic_read(&dev->power.child_count) > 0,
	     "Enabling runtime PM for inactive device (%s) with active children\n",
	     dev_name(dev));

	spin_unlock_irqrestore(&dev->power.lock, flags);
}
EXPORT_SYMBOL_GPL(pm_runtime_enable);

/**
 * pm_runtime_forbid - Block runtime PM of a device.
 * @dev: Device to handle.
 *
 * Increase the device's usage count and clear its power.runtime_auto flag,
 * so that it cannot be suspended at run time until pm_runtime_allow() is called
 * for it.
 */
void pm_runtime_forbid(struct device *dev)
{
	spin_lock_irq(&dev->power.lock);
	if (!dev->power.runtime_auto)
		goto out;

	dev->power.runtime_auto = false;
	atomic_inc(&dev->power.usage_count);
	rpm_resume(dev, 0);

 out:
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(pm_runtime_forbid);

/**
 * pm_runtime_allow - Unblock runtime PM of a device.
 * @dev: Device to handle.
 *
 * Decrease the device's usage count and set its power.runtime_auto flag.
 */
void pm_runtime_allow(struct device *dev)
{
	spin_lock_irq(&dev->power.lock);
	if (dev->power.runtime_auto)
		goto out;

	dev->power.runtime_auto = true;
	if (atomic_dec_and_test(&dev->power.usage_count))
		rpm_idle(dev, RPM_AUTO | RPM_ASYNC);

 out:
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(pm_runtime_allow);

/**
 * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device.
 * @dev: Device to handle.
 *
 * Set the power.no_callbacks flag, which tells the PM core that this
 * device is power-managed through its parent and has no runtime PM
 * callbacks of its own.  The runtime sysfs attributes will be removed.
 */
void pm_runtime_no_callbacks(struct device *dev)
{
	spin_lock_irq(&dev->power.lock);
	dev->power.no_callbacks = 1;
	spin_unlock_irq(&dev->power.lock);
	if (device_is_registered(dev))
		rpm_sysfs_remove(dev);
}
EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks);

/**
 * pm_runtime_irq_safe - Leave interrupts disabled during callbacks.
 * @dev: Device to handle
 *
 * Set the power.irq_safe flag, which tells the PM core that the
 * ->runtime_suspend() and ->runtime_resume() callbacks for this device should
 * always be invoked with the spinlock held and interrupts disabled.  It also
 * causes the parent's usage counter to be permanently incremented, preventing
 * the parent from runtime suspending -- otherwise an irq-safe child might have
 * to wait for a non-irq-safe parent.
 */
void pm_runtime_irq_safe(struct device *dev)
{
	if (dev->parent)
		pm_runtime_get_sync(dev->parent);
	spin_lock_irq(&dev->power.lock);
	dev->power.irq_safe = 1;
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(pm_runtime_irq_safe);

/**
 * update_autosuspend - Handle a change to a device's autosuspend settings.
 * @dev: Device to handle.
 * @old_delay: The former autosuspend_delay value.
 * @old_use: The former use_autosuspend value.
 *
 * Prevent runtime suspend if the new delay is negative and use_autosuspend is
 * set; otherwise allow it.  Send an idle notification if suspends are allowed.
 *
 * This function must be called under dev->power.lock with interrupts disabled.
 */
static void update_autosuspend(struct device *dev, int old_delay, int old_use)
{
	int delay = dev->power.autosuspend_delay;

	/* Should runtime suspend be prevented now? */
	if (dev->power.use_autosuspend && delay < 0) {

		/* If it used to be allowed then prevent it. */
		if (!old_use || old_delay >= 0) {
			atomic_inc(&dev->power.usage_count);
			rpm_resume(dev, 0);
		}
	}

	/* Runtime suspend should be allowed now. */
	else {

		/* If it used to be prevented then allow it. */
		if (old_use && old_delay < 0)
			atomic_dec(&dev->power.usage_count);

		/* Maybe we can autosuspend now. */
		rpm_idle(dev, RPM_AUTO);
	}
}

/**
 * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value.
 * @dev: Device to handle.
 * @delay: Value of the new delay in milliseconds.
 *
 * Set the device's power.autosuspend_delay value.  If it changes to negative
 * and the power.use_autosuspend flag is set, prevent runtime suspends.  If it
 * changes the other way, allow runtime suspends.
 */
void pm_runtime_set_autosuspend_delay(struct device *dev, int delay)
{
	int old_delay, old_use;

	spin_lock_irq(&dev->power.lock);
	old_delay = dev->power.autosuspend_delay;
	old_use = dev->power.use_autosuspend;
	dev->power.autosuspend_delay = delay;
	update_autosuspend(dev, old_delay, old_use);
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay);

/**
 * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag.
 * @dev: Device to handle.
 * @use: New value for use_autosuspend.
 *
 * Set the device's power.use_autosuspend flag, and allow or prevent runtime
 * suspends as needed.
 */
void __pm_runtime_use_autosuspend(struct device *dev, bool use)
{
	int old_delay, old_use;

	spin_lock_irq(&dev->power.lock);
	old_delay = dev->power.autosuspend_delay;
	old_use = dev->power.use_autosuspend;
	dev->power.use_autosuspend = use;
	update_autosuspend(dev, old_delay, old_use);
	spin_unlock_irq(&dev->power.lock);
}
EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);

/**
 * pm_runtime_init - Initialize runtime PM fields in given device object.
 * @dev: Device object to initialize.
 */
void pm_runtime_init(struct device *dev)
{
	dev->power.runtime_status = RPM_SUSPENDED;
	dev->power.idle_notification = false;

	dev->power.disable_depth = 1;
	atomic_set(&dev->power.usage_count, 0);

	dev->power.runtime_error = 0;

	atomic_set(&dev->power.child_count, 0);
	pm_suspend_ignore_children(dev, false);
	dev->power.runtime_auto = true;

	dev->power.request_pending = false;
	dev->power.request = RPM_REQ_NONE;
	dev->power.deferred_resume = false;
	INIT_WORK(&dev->power.work, pm_runtime_work);

	dev->power.timer_expires = 0;
	hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	dev->power.suspend_timer.function = pm_suspend_timer_fn;

	init_waitqueue_head(&dev->power.wait_queue);
}

/**
 * pm_runtime_reinit - Re-initialize runtime PM fields in given device object.
 * @dev: Device object to re-initialize.
 */
void pm_runtime_reinit(struct device *dev)
{
	if (!pm_runtime_enabled(dev)) {
		if (dev->power.runtime_status == RPM_ACTIVE)
			pm_runtime_set_suspended(dev);
		if (dev->power.irq_safe) {
			spin_lock_irq(&dev->power.lock);
			dev->power.irq_safe = 0;
			spin_unlock_irq(&dev->power.lock);
			if (dev->parent)
				pm_runtime_put(dev->parent);
		}
	}
}

/**
 * pm_runtime_remove - Prepare for removing a device from device hierarchy.
 * @dev: Device object being removed from device hierarchy.
 */
void pm_runtime_remove(struct device *dev)
{
	__pm_runtime_disable(dev, false);
	pm_runtime_reinit(dev);
}

/**
 * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
 * @dev: Device whose driver is going to be removed.
 *
 * Check links from this device to any consumers and if any of them have active
 * runtime PM references to the device, drop the usage counter of the device
 * (as many times as needed).
 *
 * Links with the DL_FLAG_MANAGED flag unset are ignored.
 *
 * Since the device is guaranteed to be runtime-active at the point this is
 * called, nothing else needs to be done here.
 *
 * Moreover, this is called after device_links_busy() has returned 'false', so
 * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
 * therefore rpm_active can't be manipulated concurrently.
 */
void pm_runtime_clean_up_links(struct device *dev)
{
	struct device_link *link;
	int idx;

	idx = device_links_read_lock();

	list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
				device_links_read_lock_held()) {
		if (!(link->flags & DL_FLAG_MANAGED))
			continue;

		while (refcount_dec_not_one(&link->rpm_active))
			pm_runtime_put_noidle(dev);
	}

	device_links_read_unlock(idx);
}

/**
 * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
 * @dev: Consumer device.
 */
void pm_runtime_get_suppliers(struct device *dev)
{
	struct device_link *link;
	int idx;

	idx = device_links_read_lock();

	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
				device_links_read_lock_held())
		if (link->flags & DL_FLAG_PM_RUNTIME) {
			link->supplier_preactivated = true;
			refcount_inc(&link->rpm_active);
			pm_runtime_get_sync(link->supplier);
		}

	device_links_read_unlock(idx);
}

/**
 * pm_runtime_put_suppliers - Drop references to supplier devices.
 * @dev: Consumer device.
 */
void pm_runtime_put_suppliers(struct device *dev)
{
	struct device_link *link;
	int idx;

	idx = device_links_read_lock();

	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
				device_links_read_lock_held())
		if (link->supplier_preactivated) {
			link->supplier_preactivated = false;
			if (refcount_dec_not_one(&link->rpm_active))
				pm_runtime_put(link->supplier);
		}

	device_links_read_unlock(idx);
}

void pm_runtime_new_link(struct device *dev)
{
	spin_lock_irq(&dev->power.lock);
	dev->power.links_count++;
	spin_unlock_irq(&dev->power.lock);
}

void pm_runtime_drop_link(struct device *dev)
{
	spin_lock_irq(&dev->power.lock);
	WARN_ON(dev->power.links_count == 0);
	dev->power.links_count--;
	spin_unlock_irq(&dev->power.lock);
}

static bool pm_runtime_need_not_resume(struct device *dev)
{
	return atomic_read(&dev->power.usage_count) <= 1 &&
		(atomic_read(&dev->power.child_count) == 0 ||
		 dev->power.ignore_children);
}

/**
 * pm_runtime_force_suspend - Force a device into suspend state if needed.
 * @dev: Device to suspend.
 *
 * Disable runtime PM so we safely can check the device's runtime PM status and
 * if it is active, invoke its ->runtime_suspend callback to suspend it and
 * change its runtime PM status field to RPM_SUSPENDED.  Also, if the device's
 * usage and children counters don't indicate that the device was in use before
 * the system-wide transition under way, decrement its parent's children counter
 * (if there is a parent).  Keep runtime PM disabled to preserve the state
 * unless we encounter errors.
 *
 * Typically this function may be invoked from a system suspend callback to make
 * sure the device is put into low power state and it should only be used during
 * system-wide PM transitions to sleep states.  It assumes that the analogous
 * pm_runtime_force_resume() will be used to resume the device.
 */
int pm_runtime_force_suspend(struct device *dev)
{
	int (*callback)(struct device *);
	int ret;

	pm_runtime_disable(dev);
	if (pm_runtime_status_suspended(dev))
		return 0;

	callback = RPM_GET_CALLBACK(dev, runtime_suspend);

	ret = callback ? callback(dev) : 0;
	if (ret)
		goto err;

	/*
	 * If the device can stay in suspend after the system-wide transition
	 * to the working state that will follow, drop the children counter of
	 * its parent, but set its status to RPM_SUSPENDED anyway in case this
	 * function will be called again for it in the meantime.
	 */
	if (pm_runtime_need_not_resume(dev))
		pm_runtime_set_suspended(dev);
	else
		__update_runtime_status(dev, RPM_SUSPENDED);

	return 0;

err:
	pm_runtime_enable(dev);
	return ret;
}
EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);

/**
 * pm_runtime_force_resume - Force a device into resume state if needed.
 * @dev: Device to resume.
 *
 * Prior invoking this function we expect the user to have brought the device
 * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
 * those actions and bring the device into full power, if it is expected to be
 * used on system resume.  In the other case, we defer the resume to be managed
 * via runtime PM.
 *
 * Typically this function may be invoked from a system resume callback.
 */
int pm_runtime_force_resume(struct device *dev)
{
	int (*callback)(struct device *);
	int ret = 0;

	if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev))
		goto out;

	/*
	 * The value of the parent's children counter is correct already, so
	 * just update the status of the device.
	 */
	__update_runtime_status(dev, RPM_ACTIVE);

	callback = RPM_GET_CALLBACK(dev, runtime_resume);

	ret = callback ? callback(dev) : 0;
	if (ret) {
		pm_runtime_set_suspended(dev);
		goto out;
	}

	pm_runtime_mark_last_busy(dev);
out:
	pm_runtime_enable(dev);
	return ret;
}
EXPORT_SYMBOL_GPL(pm_runtime_force_resume);