summaryrefslogtreecommitdiffstats
path: root/kernel/irq/manage.c
blob: 425170d4439be5926a63ef9be50c71c1dd5878a9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
/*
 * linux/kernel/irq/manage.c
 *
 * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
 * Copyright (C) 2005-2006 Thomas Gleixner
 *
 * This file contains driver APIs to the irq subsystem.
 */

#define pr_fmt(fmt) "genirq: " fmt

#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
#include <uapi/linux/sched/types.h>
#include <linux/task_work.h>

#include "internals.h"

#ifdef CONFIG_IRQ_FORCED_THREADING
__read_mostly bool force_irqthreads;

static int __init setup_forced_irqthreads(char *arg)
{
	force_irqthreads = true;
	return 0;
}
early_param("threadirqs", setup_forced_irqthreads);
#endif

static void __synchronize_hardirq(struct irq_desc *desc)
{
	bool inprogress;

	do {
		unsigned long flags;

		/*
		 * Wait until we're out of the critical section.  This might
		 * give the wrong answer due to the lack of memory barriers.
		 */
		while (irqd_irq_inprogress(&desc->irq_data))
			cpu_relax();

		/* Ok, that indicated we're done: double-check carefully. */
		raw_spin_lock_irqsave(&desc->lock, flags);
		inprogress = irqd_irq_inprogress(&desc->irq_data);
		raw_spin_unlock_irqrestore(&desc->lock, flags);

		/* Oops, that failed? */
	} while (inprogress);
}

/**
 *	synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
 *	@irq: interrupt number to wait for
 *
 *	This function waits for any pending hard IRQ handlers for this
 *	interrupt to complete before returning. If you use this
 *	function while holding a resource the IRQ handler may need you
 *	will deadlock. It does not take associated threaded handlers
 *	into account.
 *
 *	Do not use this for shutdown scenarios where you must be sure
 *	that all parts (hardirq and threaded handler) have completed.
 *
 *	Returns: false if a threaded handler is active.
 *
 *	This function may be called - with care - from IRQ context.
 */
bool synchronize_hardirq(unsigned int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (desc) {
		__synchronize_hardirq(desc);
		return !atomic_read(&desc->threads_active);
	}

	return true;
}
EXPORT_SYMBOL(synchronize_hardirq);

/**
 *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
 *	@irq: interrupt number to wait for
 *
 *	This function waits for any pending IRQ handlers for this interrupt
 *	to complete before returning. If you use this function while
 *	holding a resource the IRQ handler may need you will deadlock.
 *
 *	This function may be called - with care - from IRQ context.
 */
void synchronize_irq(unsigned int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (desc) {
		__synchronize_hardirq(desc);
		/*
		 * We made sure that no hardirq handler is
		 * running. Now verify that no threaded handlers are
		 * active.
		 */
		wait_event(desc->wait_for_threads,
			   !atomic_read(&desc->threads_active));
	}
}
EXPORT_SYMBOL(synchronize_irq);

#ifdef CONFIG_SMP
cpumask_var_t irq_default_affinity;

static bool __irq_can_set_affinity(struct irq_desc *desc)
{
	if (!desc || !irqd_can_balance(&desc->irq_data) ||
	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
		return false;
	return true;
}

/**
 *	irq_can_set_affinity - Check if the affinity of a given irq can be set
 *	@irq:		Interrupt to check
 *
 */
int irq_can_set_affinity(unsigned int irq)
{
	return __irq_can_set_affinity(irq_to_desc(irq));
}

/**
 * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
 * @irq:	Interrupt to check
 *
 * Like irq_can_set_affinity() above, but additionally checks for the
 * AFFINITY_MANAGED flag.
 */
bool irq_can_set_affinity_usr(unsigned int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);

	return __irq_can_set_affinity(desc) &&
		!irqd_affinity_is_managed(&desc->irq_data);
}

/**
 *	irq_set_thread_affinity - Notify irq threads to adjust affinity
 *	@desc:		irq descriptor which has affitnity changed
 *
 *	We just set IRQTF_AFFINITY and delegate the affinity setting
 *	to the interrupt thread itself. We can not call
 *	set_cpus_allowed_ptr() here as we hold desc->lock and this
 *	code can be called from hard interrupt context.
 */
void irq_set_thread_affinity(struct irq_desc *desc)
{
	struct irqaction *action;

	for_each_action_of_desc(desc, action)
		if (action->thread)
			set_bit(IRQTF_AFFINITY, &action->thread_flags);
}

#ifdef CONFIG_GENERIC_PENDING_IRQ
static inline bool irq_can_move_pcntxt(struct irq_data *data)
{
	return irqd_can_move_in_process_context(data);
}
static inline bool irq_move_pending(struct irq_data *data)
{
	return irqd_is_setaffinity_pending(data);
}
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
{
	cpumask_copy(desc->pending_mask, mask);
}
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
{
	cpumask_copy(mask, desc->pending_mask);
}
#else
static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; }
static inline bool irq_move_pending(struct irq_data *data) { return false; }
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { }
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
#endif

int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
			bool force)
{
	struct irq_desc *desc = irq_data_to_desc(data);
	struct irq_chip *chip = irq_data_get_irq_chip(data);
	int ret;

	ret = chip->irq_set_affinity(data, mask, force);
	switch (ret) {
	case IRQ_SET_MASK_OK:
	case IRQ_SET_MASK_OK_DONE:
		cpumask_copy(desc->irq_common_data.affinity, mask);
	case IRQ_SET_MASK_OK_NOCOPY:
		irq_set_thread_affinity(desc);
		ret = 0;
	}

	return ret;
}

int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
			    bool force)
{
	struct irq_chip *chip = irq_data_get_irq_chip(data);
	struct irq_desc *desc = irq_data_to_desc(data);
	int ret = 0;

	if (!chip || !chip->irq_set_affinity)
		return -EINVAL;

	if (irq_can_move_pcntxt(data)) {
		ret = irq_do_set_affinity(data, mask, force);
	} else {
		irqd_set_move_pending(data);
		irq_copy_pending(desc, mask);
	}

	if (desc->affinity_notify) {
		kref_get(&desc->affinity_notify->kref);
		schedule_work(&desc->affinity_notify->work);
	}
	irqd_set(data, IRQD_AFFINITY_SET);

	return ret;
}

int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
{
	struct irq_desc *desc = irq_to_desc(irq);
	unsigned long flags;
	int ret;

	if (!desc)
		return -EINVAL;

	raw_spin_lock_irqsave(&desc->lock, flags);
	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	return ret;
}

int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

	if (!desc)
		return -EINVAL;
	desc->affinity_hint = m;
	irq_put_desc_unlock(desc, flags);
	/* set the initial affinity to prevent every interrupt being on CPU0 */
	if (m)
		__irq_set_affinity(irq, m, false);
	return 0;
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);

static void irq_affinity_notify(struct work_struct *work)
{
	struct irq_affinity_notify *notify =
		container_of(work, struct irq_affinity_notify, work);
	struct irq_desc *desc = irq_to_desc(notify->irq);
	cpumask_var_t cpumask;
	unsigned long flags;

	if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
		goto out;

	raw_spin_lock_irqsave(&desc->lock, flags);
	if (irq_move_pending(&desc->irq_data))
		irq_get_pending(cpumask, desc);
	else
		cpumask_copy(cpumask, desc->irq_common_data.affinity);
	raw_spin_unlock_irqrestore(&desc->lock, flags);

	notify->notify(notify, cpumask);

	free_cpumask_var(cpumask);
out:
	kref_put(&notify->kref, notify->release);
}

/**
 *	irq_set_affinity_notifier - control notification of IRQ affinity changes
 *	@irq:		Interrupt for which to enable/disable notification
 *	@notify:	Context for notification, or %NULL to disable
 *			notification.  Function pointers must be initialised;
 *			the other fields will be initialised by this function.
 *
 *	Must be called in process context.  Notification may only be enabled
 *	after the IRQ is allocated and must be disabled before the IRQ is
 *	freed using free_irq().
 */
int
irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irq_affinity_notify *old_notify;
	unsigned long flags;

	/* The release function is promised process context */
	might_sleep();

	if (!desc)
		return -EINVAL;

	/* Complete initialisation of *notify */
	if (notify) {
		notify->irq = irq;
		kref_init(&notify->kref);
		INIT_WORK(&notify->work, irq_affinity_notify);
	}

	raw_spin_lock_irqsave(&desc->lock, flags);
	old_notify = desc->affinity_notify;
	desc->affinity_notify = notify;
	raw_spin_unlock_irqrestore(&desc->lock, flags);

	if (old_notify)
		kref_put(&old_notify->kref, old_notify->release);

	return 0;
}
EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);

#ifndef CONFIG_AUTO_IRQ_AFFINITY
/*
 * Generic version of the affinity autoselector.
 */
static int setup_affinity(struct irq_desc *desc, struct cpumask *mask)
{
	struct cpumask *set = irq_default_affinity;
	int node = irq_desc_get_node(desc);

	/* Excludes PER_CPU and NO_BALANCE interrupts */
	if (!__irq_can_set_affinity(desc))
		return 0;

	/*
	 * Preserve the managed affinity setting and a userspace affinity
	 * setup, but make sure that one of the targets is online.
	 */
	if (irqd_affinity_is_managed(&desc->irq_data) ||
	    irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
		if (cpumask_intersects(desc->irq_common_data.affinity,
				       cpu_online_mask))
			set = desc->irq_common_data.affinity;
		else
			irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
	}

	cpumask_and(mask, cpu_online_mask, set);
	if (node != NUMA_NO_NODE) {
		const struct cpumask *nodemask = cpumask_of_node(node);

		/* make sure at least one of the cpus in nodemask is online */
		if (cpumask_intersects(mask, nodemask))
			cpumask_and(mask, mask, nodemask);
	}
	irq_do_set_affinity(&desc->irq_data, mask, false);
	return 0;
}
#else
/* Wrapper for ALPHA specific affinity selector magic */
static inline int setup_affinity(struct irq_desc *d, struct cpumask *mask)
{
	return irq_select_affinity(irq_desc_get_irq(d));
}
#endif

/*
 * Called when affinity is set via /proc/irq
 */
int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
{
	struct irq_desc *desc = irq_to_desc(irq);
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&desc->lock, flags);
	ret = setup_affinity(desc, mask);
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	return ret;
}

#else
static inline int
setup_affinity(struct irq_desc *desc, struct cpumask *mask)
{
	return 0;
}
#endif

/**
 *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
 *	@irq: interrupt number to set affinity
 *	@vcpu_info: vCPU specific data
 *
 *	This function uses the vCPU specific data to set the vCPU
 *	affinity for an irq. The vCPU specific data is passed from
 *	outside, such as KVM. One example code path is as below:
 *	KVM -> IOMMU -> irq_set_vcpu_affinity().
 */
int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
	struct irq_data *data;
	struct irq_chip *chip;
	int ret = -ENOSYS;

	if (!desc)
		return -EINVAL;

	data = irq_desc_get_irq_data(desc);
	chip = irq_data_get_irq_chip(data);
	if (chip && chip->irq_set_vcpu_affinity)
		ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
	irq_put_desc_unlock(desc, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);

void __disable_irq(struct irq_desc *desc)
{
	if (!desc->depth++)
		irq_disable(desc);
}

static int __disable_irq_nosync(unsigned int irq)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

	if (!desc)
		return -EINVAL;
	__disable_irq(desc);
	irq_put_desc_busunlock(desc, flags);
	return 0;
}

/**
 *	disable_irq_nosync - disable an irq without waiting
 *	@irq: Interrupt to disable
 *
 *	Disable the selected interrupt line.  Disables and Enables are
 *	nested.
 *	Unlike disable_irq(), this function does not ensure existing
 *	instances of the IRQ handler have completed before returning.
 *
 *	This function may be called from IRQ context.
 */
void disable_irq_nosync(unsigned int irq)
{
	__disable_irq_nosync(irq);
}
EXPORT_SYMBOL(disable_irq_nosync);

/**
 *	disable_irq - disable an irq and wait for completion
 *	@irq: Interrupt to disable
 *
 *	Disable the selected interrupt line.  Enables and Disables are
 *	nested.
 *	This function waits for any pending IRQ handlers for this interrupt
 *	to complete before returning. If you use this function while
 *	holding a resource the IRQ handler may need you will deadlock.
 *
 *	This function may be called - with care - from IRQ context.
 */
void disable_irq(unsigned int irq)
{
	if (!__disable_irq_nosync(irq))
		synchronize_irq(irq);
}
EXPORT_SYMBOL(disable_irq);

/**
 *	disable_hardirq - disables an irq and waits for hardirq completion
 *	@irq: Interrupt to disable
 *
 *	Disable the selected interrupt line.  Enables and Disables are
 *	nested.
 *	This function waits for any pending hard IRQ handlers for this
 *	interrupt to complete before returning. If you use this function while
 *	holding a resource the hard IRQ handler may need you will deadlock.
 *
 *	When used to optimistically disable an interrupt from atomic context
 *	the return value must be checked.
 *
 *	Returns: false if a threaded handler is active.
 *
 *	This function may be called - with care - from IRQ context.
 */
bool disable_hardirq(unsigned int irq)
{
	if (!__disable_irq_nosync(irq))
		return synchronize_hardirq(irq);

	return false;
}
EXPORT_SYMBOL_GPL(disable_hardirq);

void __enable_irq(struct irq_desc *desc)
{
	switch (desc->depth) {
	case 0:
 err_out:
		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n",
		     irq_desc_get_irq(desc));
		break;
	case 1: {
		if (desc->istate & IRQS_SUSPENDED)
			goto err_out;
		/* Prevent probing on this irq: */
		irq_settings_set_noprobe(desc);
		irq_enable(desc);
		check_irq_resend(desc);
		/* fall-through */
	}
	default:
		desc->depth--;
	}
}

/**
 *	enable_irq - enable handling of an irq
 *	@irq: Interrupt to enable
 *
 *	Undoes the effect of one call to disable_irq().  If this
 *	matches the last disable, processing of interrupts on this
 *	IRQ line is re-enabled.
 *
 *	This function may be called from IRQ context only when
 *	desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
 */
void enable_irq(unsigned int irq)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

	if (!desc)
		return;
	if (WARN(!desc->irq_data.chip,
		 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
		goto out;

	__enable_irq(desc);
out:
	irq_put_desc_busunlock(desc, flags);
}
EXPORT_SYMBOL(enable_irq);

static int set_irq_wake_real(unsigned int irq, unsigned int on)
{
	struct irq_desc *desc = irq_to_desc(irq);
	int ret = -ENXIO;

	if (irq_desc_get_chip(desc)->flags &  IRQCHIP_SKIP_SET_WAKE)
		return 0;

	if (desc->irq_data.chip->irq_set_wake)
		ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);

	return ret;
}

/**
 *	irq_set_irq_wake - control irq power management wakeup
 *	@irq:	interrupt to control
 *	@on:	enable/disable power management wakeup
 *
 *	Enable/disable power management wakeup mode, which is
 *	disabled by default.  Enables and disables must match,
 *	just as they match for non-wakeup mode support.
 *
 *	Wakeup mode lets this IRQ wake the system from sleep
 *	states like "suspend to RAM".
 */
int irq_set_irq_wake(unsigned int irq, unsigned int on)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
	int ret = 0;

	if (!desc)
		return -EINVAL;

	/* wakeup-capable irqs can be shared between drivers that
	 * don't need to have the same sleep mode behaviors.
	 */
	if (on) {
		if (desc->wake_depth++ == 0) {
			ret = set_irq_wake_real(irq, on);
			if (ret)
				desc->wake_depth = 0;
			else
				irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
		}
	} else {
		if (desc->wake_depth == 0) {
			WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
		} else if (--desc->wake_depth == 0) {
			ret = set_irq_wake_real(irq, on);
			if (ret)
				desc->wake_depth = 1;
			else
				irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
		}
	}
	irq_put_desc_busunlock(desc, flags);
	return ret;
}
EXPORT_SYMBOL(irq_set_irq_wake);

/*
 * Internal function that tells the architecture code whether a
 * particular irq has been exclusively allocated or is available
 * for driver use.
 */
int can_request_irq(unsigned int irq, unsigned long irqflags)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
	int canrequest = 0;

	if (!desc)
		return 0;

	if (irq_settings_can_request(desc)) {
		if (!desc->action ||
		    irqflags & desc->action->flags & IRQF_SHARED)
			canrequest = 1;
	}
	irq_put_desc_unlock(desc, flags);
	return canrequest;
}

int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
{
	struct irq_chip *chip = desc->irq_data.chip;
	int ret, unmask = 0;

	if (!chip || !chip->irq_set_type) {
		/*
		 * IRQF_TRIGGER_* but the PIC does not support multiple
		 * flow-types?
		 */
		pr_debug("No set_type function for IRQ %d (%s)\n",
			 irq_desc_get_irq(desc),
			 chip ? (chip->name ? : "unknown") : "unknown");
		return 0;
	}

	if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
		if (!irqd_irq_masked(&desc->irq_data))
			mask_irq(desc);
		if (!irqd_irq_disabled(&desc->irq_data))
			unmask = 1;
	}

	/* Mask all flags except trigger mode */
	flags &= IRQ_TYPE_SENSE_MASK;
	ret = chip->irq_set_type(&desc->irq_data, flags);

	switch (ret) {
	case IRQ_SET_MASK_OK:
	case IRQ_SET_MASK_OK_DONE:
		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
		irqd_set(&desc->irq_data, flags);

	case IRQ_SET_MASK_OK_NOCOPY:
		flags = irqd_get_trigger_type(&desc->irq_data);
		irq_settings_set_trigger_mask(desc, flags);
		irqd_clear(&desc->irq_data, IRQD_LEVEL);
		irq_settings_clr_level(desc);
		if (flags & IRQ_TYPE_LEVEL_MASK) {
			irq_settings_set_level(desc);
			irqd_set(&desc->irq_data, IRQD_LEVEL);
		}

		ret = 0;
		break;
	default:
		pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n",
		       flags, irq_desc_get_irq(desc), chip->irq_set_type);
	}
	if (unmask)
		unmask_irq(desc);
	return ret;
}

#ifdef CONFIG_HARDIRQS_SW_RESEND
int irq_set_parent(int irq, int parent_irq)
{
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);

	if (!desc)
		return -EINVAL;

	desc->parent_irq = parent_irq;

	irq_put_desc_unlock(desc, flags);
	return 0;
}
EXPORT_SYMBOL_GPL(irq_set_parent);
#endif

/*
 * Default primary interrupt handler for threaded interrupts. Is
 * assigned as primary handler when request_threaded_irq is called
 * with handler == NULL. Useful for oneshot interrupts.
 */
static irqreturn_t irq_default_primary_handler(int irq, void *dev_id)
{
	return IRQ_WAKE_THREAD;
}

/*
 * Primary handler for nested threaded interrupts. Should never be
 * called.
 */
static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
{
	WARN(1, "Primary handler called for nested irq %d\n", irq);
	return IRQ_NONE;
}

static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
{
	WARN(1, "Secondary action handler called for irq %d\n", irq);
	return IRQ_NONE;
}

static int irq_wait_for_interrupt(struct irqaction *action)
{
	set_current_state(TASK_INTERRUPTIBLE);

	while (!kthread_should_stop()) {

		if (test_and_clear_bit(IRQTF_RUNTHREAD,
				       &action->thread_flags)) {
			__set_current_state(TASK_RUNNING);
			return 0;
		}
		schedule();
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return -1;
}

/*
 * Oneshot interrupts keep the irq line masked until the threaded
 * handler finished. unmask if the interrupt has not been disabled and
 * is marked MASKED.
 */
static void irq_finalize_oneshot(struct irq_desc *desc,
				 struct irqaction *action)
{
	if (!(desc->istate & IRQS_ONESHOT) ||
	    action->handler == irq_forced_secondary_handler)
		return;
again:
	chip_bus_lock(desc);
	raw_spin_lock_irq(&desc->lock);

	/*
	 * Implausible though it may be we need to protect us against
	 * the following scenario:
	 *
	 * The thread is faster done than the hard interrupt handler
	 * on the other CPU. If we unmask the irq line then the
	 * interrupt can come in again and masks the line, leaves due
	 * to IRQS_INPROGRESS and the irq line is masked forever.
	 *
	 * This also serializes the state of shared oneshot handlers
	 * versus "desc->threads_onehsot |= action->thread_mask;" in
	 * irq_wake_thread(). See the comment there which explains the
	 * serialization.
	 */
	if (unlikely(irqd_irq_inprogress(&desc->irq_data))) {
		raw_spin_unlock_irq(&desc->lock);
		chip_bus_sync_unlock(desc);
		cpu_relax();
		goto again;
	}

	/*
	 * Now check again, whether the thread should run. Otherwise
	 * we would clear the threads_oneshot bit of this thread which
	 * was just set.
	 */
	if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
		goto out_unlock;

	desc->threads_oneshot &= ~action->thread_mask;

	if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
	    irqd_irq_masked(&desc->irq_data))
		unmask_threaded_irq(desc);

out_unlock:
	raw_spin_unlock_irq(&desc->lock);
	chip_bus_sync_unlock(desc);
}

#ifdef CONFIG_SMP
/*
 * Check whether we need to change the affinity of the interrupt thread.
 */
static void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
{
	cpumask_var_t mask;
	bool valid = true;

	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
		return;

	/*
	 * In case we are out of memory we set IRQTF_AFFINITY again and
	 * try again next time
	 */
	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
		set_bit(IRQTF_AFFINITY, &action->thread_flags);
		return;
	}

	raw_spin_lock_irq(&desc->lock);
	/*
	 * This code is triggered unconditionally. Check the affinity
	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
	 */
	if (cpumask_available(desc->irq_common_data.affinity))
		cpumask_copy(mask, desc->irq_common_data.affinity);
	else
		valid = false;
	raw_spin_unlock_irq(&desc->lock);

	if (valid)
		set_cpus_allowed_ptr(current, mask);
	free_cpumask_var(mask);
}
#else
static inline void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif

/*
 * Interrupts which are not explicitely requested as threaded
 * interrupts rely on the implicit bh/preempt disable of the hard irq
 * context. So we need to disable bh here to avoid deadlocks and other
 * side effects.
 */
static irqreturn_t
irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
	irqreturn_t ret;

	local_bh_disable();
	ret = action->thread_fn(action->irq, action->dev_id);
	irq_finalize_oneshot(desc, action);
	local_bh_enable();
	return ret;
}

/*
 * Interrupts explicitly requested as threaded interrupts want to be
 * preemtible - many of them need to sleep and wait for slow busses to
 * complete.
 */
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
		struct irqaction *action)
{
	irqreturn_t ret;

	ret = action->thread_fn(action->irq, action->dev_id);
	irq_finalize_oneshot(desc, action);
	return ret;
}

static void wake_threads_waitq(struct irq_desc *desc)
{
	if (atomic_dec_and_test(&desc->threads_active))
		wake_up(&desc->wait_for_threads);
}

static void irq_thread_dtor(struct callback_head *unused)
{
	struct task_struct *tsk = current;
	struct irq_desc *desc;
	struct irqaction *action;

	if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
		return;

	action = kthread_data(tsk);

	pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
	       tsk->comm, tsk->pid, action->irq);


	desc = irq_to_desc(action->irq);
	/*
	 * If IRQTF_RUNTHREAD is set, we need to decrement
	 * desc->threads_active and wake possible waiters.
	 */
	if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
		wake_threads_waitq(desc);

	/* Prevent a stale desc->threads_oneshot */
	irq_finalize_oneshot(desc, action);
}

static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
{
	struct irqaction *secondary = action->secondary;

	if (WARN_ON_ONCE(!secondary))
		return;

	raw_spin_lock_irq(&desc->lock);
	__irq_wake_thread(desc, secondary);
	raw_spin_unlock_irq(&desc->lock);
}

/*
 * Interrupt handler thread
 */
static int irq_thread(void *data)
{
	struct callback_head on_exit_work;
	struct irqaction *action = data;
	struct irq_desc *desc = irq_to_desc(action->irq);
	irqreturn_t (*handler_fn)(struct irq_desc *desc,
			struct irqaction *action);

	if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD,
					&action->thread_flags))
		handler_fn = irq_forced_thread_fn;
	else
		handler_fn = irq_thread_fn;

	init_task_work(&on_exit_work, irq_thread_dtor);
	task_work_add(current, &on_exit_work, false);

	irq_thread_check_affinity(desc, action);

	while (!irq_wait_for_interrupt(action)) {
		irqreturn_t action_ret;

		irq_thread_check_affinity(desc, action);

		action_ret = handler_fn(desc, action);
		if (action_ret == IRQ_HANDLED)
			atomic_inc(&desc->threads_handled);
		if (action_ret == IRQ_WAKE_THREAD)
			irq_wake_secondary(desc, action);

		wake_threads_waitq(desc);
	}

	/*
	 * This is the regular exit path. __free_irq() is stopping the
	 * thread via kthread_stop() after calling
	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
	 * oneshot mask bit can be set. We cannot verify that as we
	 * cannot touch the oneshot mask at this point anymore as
	 * __setup_irq() might have given out currents thread_mask
	 * again.
	 */
	task_work_cancel(current, irq_thread_dtor);
	return 0;
}

/**
 *	irq_wake_thread - wake the irq thread for the action identified by dev_id
 *	@irq:		Interrupt line
 *	@dev_id:	Device identity for which the thread should be woken
 *
 */
void irq_wake_thread(unsigned int irq, void *dev_id)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irqaction *action;
	unsigned long flags;

	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
		return;

	raw_spin_lock_irqsave(&desc->lock, flags);
	for_each_action_of_desc(desc, action) {
		if (action->dev_id == dev_id) {
			if (action->thread)
				__irq_wake_thread(desc, action);
			break;
		}
	}
	raw_spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL_GPL(irq_wake_thread);

static int irq_setup_forced_threading(struct irqaction *new)
{
	if (!force_irqthreads)
		return 0;
	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
		return 0;

	new->flags |= IRQF_ONESHOT;

	/*
	 * Handle the case where we have a real primary handler and a
	 * thread handler. We force thread them as well by creating a
	 * secondary action.
	 */
	if (new->handler != irq_default_primary_handler && new->thread_fn) {
		/* Allocate the secondary action */
		new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
		if (!new->secondary)
			return -ENOMEM;
		new->secondary->handler = irq_forced_secondary_handler;
		new->secondary->thread_fn = new->thread_fn;
		new->secondary->dev_id = new->dev_id;
		new->secondary->irq = new->irq;
		new->secondary->name = new->name;
	}
	/* Deal with the primary handler */
	set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
	new->thread_fn = new->handler;
	new->handler = irq_default_primary_handler;
	return 0;
}

static int irq_request_resources(struct irq_desc *desc)
{
	struct irq_data *d = &desc->irq_data;
	struct irq_chip *c = d->chip;

	return c->irq_request_resources ? c->irq_request_resources(d) : 0;
}

static void irq_release_resources(struct irq_desc *desc)
{
	struct irq_data *d = &desc->irq_data;
	struct irq_chip *c = d->chip;

	if (c->irq_release_resources)
		c->irq_release_resources(d);
}

static int
setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
{
	struct task_struct *t;
	struct sched_param param = {
		.sched_priority = MAX_USER_RT_PRIO/2,
	};

	if (!secondary) {
		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
				   new->name);
	} else {
		t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq,
				   new->name);
		param.sched_priority -= 1;
	}

	if (IS_ERR(t))
		return PTR_ERR(t);

	sched_setscheduler_nocheck(t, SCHED_FIFO, &param);

	/*
	 * We keep the reference to the task struct even if
	 * the thread dies to avoid that the interrupt code
	 * references an already freed task_struct.
	 */
	get_task_struct(t);
	new->thread = t;
	/*
	 * Tell the thread to set its affinity. This is
	 * important for shared interrupt handlers as we do
	 * not invoke setup_affinity() for the secondary
	 * handlers as everything is already set up. Even for
	 * interrupts marked with IRQF_NO_BALANCE this is
	 * correct as we want the thread to move to the cpu(s)
	 * on which the requesting code placed the interrupt.
	 */
	set_bit(IRQTF_AFFINITY, &new->thread_flags);
	return 0;
}

/*
 * Internal function to register an irqaction - typically used to
 * allocate special interrupts that are part of the architecture.
 */
static int
__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
{
	struct irqaction *old, **old_ptr;
	unsigned long flags, thread_mask = 0;
	int ret, nested, shared = 0;
	cpumask_var_t mask;

	if (!desc)
		return -EINVAL;

	if (desc->irq_data.chip == &no_irq_chip)
		return -ENOSYS;
	if (!try_module_get(desc->owner))
		return -ENODEV;

	new->irq = irq;

	/*
	 * If the trigger type is not specified by the caller,
	 * then use the default for this interrupt.
	 */
	if (!(new->flags & IRQF_TRIGGER_MASK))
		new->flags |= irqd_get_trigger_type(&desc->irq_data);

	/*
	 * Check whether the interrupt nests into another interrupt
	 * thread.
	 */
	nested = irq_settings_is_nested_thread(desc);
	if (nested) {
		if (!new->thread_fn) {
			ret = -EINVAL;
			goto out_mput;
		}
		/*
		 * Replace the primary handler which was provided from
		 * the driver for non nested interrupt handling by the
		 * dummy function which warns when called.
		 */
		new->handler = irq_nested_primary_handler;
	} else {
		if (irq_settings_can_thread(desc)) {
			ret = irq_setup_forced_threading(new);
			if (ret)
				goto out_mput;
		}
	}

	/*
	 * Create a handler thread when a thread function is supplied
	 * and the interrupt does not nest into another interrupt
	 * thread.
	 */
	if (new->thread_fn && !nested) {
		ret = setup_irq_thread(new, irq, false);
		if (ret)
			goto out_mput;
		if (new->secondary) {
			ret = setup_irq_thread(new->secondary, irq, true);
			if (ret)
				goto out_thread;
		}
	}

	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
		ret = -ENOMEM;
		goto out_thread;
	}

	/*
	 * Drivers are often written to work w/o knowledge about the
	 * underlying irq chip implementation, so a request for a
	 * threaded irq without a primary hard irq context handler
	 * requires the ONESHOT flag to be set. Some irq chips like
	 * MSI based interrupts are per se one shot safe. Check the
	 * chip flags, so we can avoid the unmask dance at the end of
	 * the threaded handler for those.
	 */
	if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)
		new->flags &= ~IRQF_ONESHOT;

	/*
	 * The following block of code has to be executed atomically
	 */
	raw_spin_lock_irqsave(&desc->lock, flags);
	old_ptr = &desc->action;
	old = *old_ptr;
	if (old) {
		/*
		 * Can't share interrupts unless both agree to and are
		 * the same type (level, edge, polarity). So both flag
		 * fields must have IRQF_SHARED set and the bits which
		 * set the trigger type must match. Also all must
		 * agree on ONESHOT.
		 */
		unsigned int oldtype = irqd_get_trigger_type(&desc->irq_data);

		if (!((old->flags & new->flags) & IRQF_SHARED) ||
		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)) ||
		    ((old->flags ^ new->flags) & IRQF_ONESHOT))
			goto mismatch;

		/* All handlers must agree on per-cpuness */
		if ((old->flags & IRQF_PERCPU) !=
		    (new->flags & IRQF_PERCPU))
			goto mismatch;

		/* add new interrupt at end of irq queue */
		do {
			/*
			 * Or all existing action->thread_mask bits,
			 * so we can find the next zero bit for this
			 * new action.
			 */
			thread_mask |= old->thread_mask;
			old_ptr = &old->next;
			old = *old_ptr;
		} while (old);
		shared = 1;
	}

	/*
	 * Setup the thread mask for this irqaction for ONESHOT. For
	 * !ONESHOT irqs the thread mask is 0 so we can avoid a
	 * conditional in irq_wake_thread().
	 */
	if (new->flags & IRQF_ONESHOT) {
		/*
		 * Unlikely to have 32 resp 64 irqs sharing one line,
		 * but who knows.
		 */
		if (thread_mask == ~0UL) {
			ret = -EBUSY;
			goto out_mask;
		}
		/*
		 * The thread_mask for the action is or'ed to
		 * desc->thread_active to indicate that the
		 * IRQF_ONESHOT thread handler has been woken, but not
		 * yet finished. The bit is cleared when a thread
		 * completes. When all threads of a shared interrupt
		 * line have completed desc->threads_active becomes
		 * zero and the interrupt line is unmasked. See
		 * handle.c:irq_wake_thread() for further information.
		 *
		 * If no thread is woken by primary (hard irq context)
		 * interrupt handlers, then desc->threads_active is
		 * also checked for zero to unmask the irq line in the
		 * affected hard irq flow handlers
		 * (handle_[fasteoi|level]_irq).
		 *
		 * The new action gets the first zero bit of
		 * thread_mask assigned. See the loop above which or's
		 * all existing action->thread_mask bits.
		 */
		new->thread_mask = 1 << ffz(thread_mask);

	} else if (new->handler == irq_default_primary_handler &&
		   !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
		/*
		 * The interrupt was requested with handler = NULL, so
		 * we use the default primary handler for it. But it
		 * does not have the oneshot flag set. In combination
		 * with level interrupts this is deadly, because the
		 * default primary handler just wakes the thread, then
		 * the irq lines is reenabled, but the device still
		 * has the level irq asserted. Rinse and repeat....
		 *
		 * While this works for edge type interrupts, we play
		 * it safe and reject unconditionally because we can't
		 * say for sure which type this interrupt really
		 * has. The type flags are unreliable as the
		 * underlying chip implementation can override them.
		 */
		pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
		       irq);
		ret = -EINVAL;
		goto out_mask;
	}

	if (!shared) {
		ret = irq_request_resources(desc);
		if (ret) {
			pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
			       new->name, irq, desc->irq_data.chip->name);
			goto out_mask;
		}

		init_waitqueue_head(&desc->wait_for_threads);

		/* Setup the type (level, edge polarity) if configured: */
		if (new->flags & IRQF_TRIGGER_MASK) {
			ret = __irq_set_trigger(desc,
						new->flags & IRQF_TRIGGER_MASK);

			if (ret) {
				irq_release_resources(desc);
				goto out_mask;
			}
		}

		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
				  IRQS_ONESHOT | IRQS_WAITING);
		irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);

		if (new->flags & IRQF_PERCPU) {
			irqd_set(&desc->irq_data, IRQD_PER_CPU);
			irq_settings_set_per_cpu(desc);
		}

		if (new->flags & IRQF_ONESHOT)
			desc->istate |= IRQS_ONESHOT;

		if (irq_settings_can_autoenable(desc))
			irq_startup(desc, true);
		else
			/* Undo nested disables: */
			desc->depth = 1;

		/* Exclude IRQ from balancing if requested */
		if (new->flags & IRQF_NOBALANCING) {
			irq_settings_set_no_balancing(desc);
			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
		}

		/* Set default affinity mask once everything is setup */
		setup_affinity(desc, mask);

	} else if (new->flags & IRQF_TRIGGER_MASK) {
		unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
		unsigned int omsk = irqd_get_trigger_type(&desc->irq_data);

		if (nmsk != omsk)
			/* hope the handler works with current  trigger mode */
			pr_warn("irq %d uses trigger mode %u; requested %u\n",
				irq, omsk, nmsk);
	}

	*old_ptr = new;

	irq_pm_install_action(desc, new);

	/* Reset broken irq detection when installing new handler */
	desc->irq_count = 0;
	desc->irqs_unhandled = 0;

	/*
	 * Check whether we disabled the irq via the spurious handler
	 * before. Reenable it and give it another chance.
	 */
	if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
		desc->istate &= ~IRQS_SPURIOUS_DISABLED;
		__enable_irq(desc);
	}

	raw_spin_unlock_irqrestore(&desc->lock, flags);

	/*
	 * Strictly no need to wake it up, but hung_task complains
	 * when no hard interrupt wakes the thread up.
	 */
	if (new->thread)
		wake_up_process(new->thread);
	if (new->secondary)
		wake_up_process(new->secondary->thread);

	register_irq_proc(irq, desc);
	new->dir = NULL;
	register_handler_proc(irq, new);
	free_cpumask_var(mask);

	return 0;

mismatch:
	if (!(new->flags & IRQF_PROBE_SHARED)) {
		pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
		       irq, new->flags, new->name, old->flags, old->name);
#ifdef CONFIG_DEBUG_SHIRQ
		dump_stack();
#endif
	}
	ret = -EBUSY;

out_mask:
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	free_cpumask_var(mask);

out_thread:
	if (new->thread) {
		struct task_struct *t = new->thread;

		new->thread = NULL;
		kthread_stop(t);
		put_task_struct(t);
	}
	if (new->secondary && new->secondary->thread) {
		struct task_struct *t = new->secondary->thread;

		new->secondary->thread = NULL;
		kthread_stop(t);
		put_task_struct(t);
	}
out_mput:
	module_put(desc->owner);
	return ret;
}

/**
 *	setup_irq - setup an interrupt
 *	@irq: Interrupt line to setup
 *	@act: irqaction for the interrupt
 *
 * Used to statically setup interrupts in the early boot process.
 */
int setup_irq(unsigned int irq, struct irqaction *act)
{
	int retval;
	struct irq_desc *desc = irq_to_desc(irq);

	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
		return -EINVAL;

	retval = irq_chip_pm_get(&desc->irq_data);
	if (retval < 0)
		return retval;

	chip_bus_lock(desc);
	retval = __setup_irq(irq, desc, act);
	chip_bus_sync_unlock(desc);

	if (retval)
		irq_chip_pm_put(&desc->irq_data);

	return retval;
}
EXPORT_SYMBOL_GPL(setup_irq);

/*
 * Internal function to unregister an irqaction - used to free
 * regular and special interrupts that are part of the architecture.
 */
static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irqaction *action, **action_ptr;
	unsigned long flags;

	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);

	if (!desc)
		return NULL;

	chip_bus_lock(desc);
	raw_spin_lock_irqsave(&desc->lock, flags);

	/*
	 * There can be multiple actions per IRQ descriptor, find the right
	 * one based on the dev_id:
	 */
	action_ptr = &desc->action;
	for (;;) {
		action = *action_ptr;

		if (!action) {
			WARN(1, "Trying to free already-free IRQ %d\n", irq);
			raw_spin_unlock_irqrestore(&desc->lock, flags);
			chip_bus_sync_unlock(desc);
			return NULL;
		}

		if (action->dev_id == dev_id)
			break;
		action_ptr = &action->next;
	}

	/* Found it - now remove it from the list of entries: */
	*action_ptr = action->next;

	irq_pm_remove_action(desc, action);

	/* If this was the last handler, shut down the IRQ line: */
	if (!desc->action) {
		irq_settings_clr_disable_unlazy(desc);
		irq_shutdown(desc);
		irq_release_resources(desc);
	}

#ifdef CONFIG_SMP
	/* make sure affinity_hint is cleaned up */
	if (WARN_ON_ONCE(desc->affinity_hint))
		desc->affinity_hint = NULL;
#endif

	raw_spin_unlock_irqrestore(&desc->lock, flags);
	chip_bus_sync_unlock(desc);

	unregister_handler_proc(irq, action);

	/* Make sure it's not being used on another CPU: */
	synchronize_irq(irq);

#ifdef CONFIG_DEBUG_SHIRQ
	/*
	 * It's a shared IRQ -- the driver ought to be prepared for an IRQ
	 * event to happen even now it's being freed, so let's make sure that
	 * is so by doing an extra call to the handler ....
	 *
	 * ( We do this after actually deregistering it, to make sure that a
	 *   'real' IRQ doesn't run in * parallel with our fake. )
	 */
	if (action->flags & IRQF_SHARED) {
		local_irq_save(flags);
		action->handler(irq, dev_id);
		local_irq_restore(flags);
	}
#endif

	if (action->thread) {
		kthread_stop(action->thread);
		put_task_struct(action->thread);
		if (action->secondary && action->secondary->thread) {
			kthread_stop(action->secondary->thread);
			put_task_struct(action->secondary->thread);
		}
	}

	irq_chip_pm_put(&desc->irq_data);
	module_put(desc->owner);
	kfree(action->secondary);
	return action;
}

/**
 *	remove_irq - free an interrupt
 *	@irq: Interrupt line to free
 *	@act: irqaction for the interrupt
 *
 * Used to remove interrupts statically setup by the early boot process.
 */
void remove_irq(unsigned int irq, struct irqaction *act)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
		__free_irq(irq, act->dev_id);
}
EXPORT_SYMBOL_GPL(remove_irq);

/**
 *	free_irq - free an interrupt allocated with request_irq
 *	@irq: Interrupt line to free
 *	@dev_id: Device identity to free
 *
 *	Remove an interrupt handler. The handler is removed and if the
 *	interrupt line is no longer in use by any driver it is disabled.
 *	On a shared IRQ the caller must ensure the interrupt is disabled
 *	on the card it drives before calling this function. The function
 *	does not return until any executing interrupts for this IRQ
 *	have completed.
 *
 *	This function must not be called from interrupt context.
 *
 *	Returns the devname argument passed to request_irq.
 */
const void *free_irq(unsigned int irq, void *dev_id)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irqaction *action;
	const char *devname;

	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
		return NULL;

#ifdef CONFIG_SMP
	if (WARN_ON(desc->affinity_notify))
		desc->affinity_notify = NULL;
#endif

	action = __free_irq(irq, dev_id);
	devname = action->name;
	kfree(action);
	return devname;
}
EXPORT_SYMBOL(free_irq);

/**
 *	request_threaded_irq - allocate an interrupt line
 *	@irq: Interrupt line to allocate
 *	@handler: Function to be called when the IRQ occurs.
 *		  Primary handler for threaded interrupts
 *		  If NULL and thread_fn != NULL the default
 *		  primary handler is installed
 *	@thread_fn: Function called from the irq handler thread
 *		    If NULL, no irq thread is created
 *	@irqflags: Interrupt type flags
 *	@devname: An ascii name for the claiming device
 *	@dev_id: A cookie passed back to the handler function
 *
 *	This call allocates interrupt resources and enables the
 *	interrupt line and IRQ handling. From the point this
 *	call is made your handler function may be invoked. Since
 *	your handler function must clear any interrupt the board
 *	raises, you must take care both to initialise your hardware
 *	and to set up the interrupt handler in the right order.
 *
 *	If you want to set up a threaded irq handler for your device
 *	then you need to supply @handler and @thread_fn. @handler is
 *	still called in hard interrupt context and has to check
 *	whether the interrupt originates from the device. If yes it
 *	needs to disable the interrupt on the device and return
 *	IRQ_WAKE_THREAD which will wake up the handler thread and run
 *	@thread_fn. This split handler design is necessary to support
 *	shared interrupts.
 *
 *	Dev_id must be globally unique. Normally the address of the
 *	device data structure is used as the cookie. Since the handler
 *	receives this value it makes sense to use it.
 *
 *	If your interrupt is shared you must pass a non NULL dev_id
 *	as this is required when freeing the interrupt.
 *
 *	Flags:
 *
 *	IRQF_SHARED		Interrupt is shared
 *	IRQF_TRIGGER_*		Specify active edge(s) or level
 *
 */
int request_threaded_irq(unsigned int irq, irq_handler_t handler,
			 irq_handler_t thread_fn, unsigned long irqflags,
			 const char *devname, void *dev_id)
{
	struct irqaction *action;
	struct irq_desc *desc;
	int retval;

	if (irq == IRQ_NOTCONNECTED)
		return -ENOTCONN;

	/*
	 * Sanity-check: shared interrupts must pass in a real dev-ID,
	 * otherwise we'll have trouble later trying to figure out
	 * which interrupt is which (messes up the interrupt freeing
	 * logic etc).
	 *
	 * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
	 * it cannot be set along with IRQF_NO_SUSPEND.
	 */
	if (((irqflags & IRQF_SHARED) && !dev_id) ||
	    (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
	    ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
		return -EINVAL;

	desc = irq_to_desc(irq);
	if (!desc)
		return -EINVAL;

	if (!irq_settings_can_request(desc) ||
	    WARN_ON(irq_settings_is_per_cpu_devid(desc)))
		return -EINVAL;

	if (!handler) {
		if (!thread_fn)
			return -EINVAL;
		handler = irq_default_primary_handler;
	}

	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
	if (!action)
		return -ENOMEM;

	action->handler = handler;
	action->thread_fn = thread_fn;
	action->flags = irqflags;
	action->name = devname;
	action->dev_id = dev_id;

	retval = irq_chip_pm_get(&desc->irq_data);
	if (retval < 0) {
		kfree(action);
		return retval;
	}

	chip_bus_lock(desc);
	retval = __setup_irq(irq, desc, action);
	chip_bus_sync_unlock(desc);

	if (retval) {
		irq_chip_pm_put(&desc->irq_data);
		kfree(action->secondary);
		kfree(action);
	}

#ifdef CONFIG_DEBUG_SHIRQ_FIXME
	if (!retval && (irqflags & IRQF_SHARED)) {
		/*
		 * It's a shared IRQ -- the driver ought to be prepared for it
		 * to happen immediately, so let's make sure....
		 * We disable the irq to make sure that a 'real' IRQ doesn't
		 * run in parallel with our fake.
		 */
		unsigned long flags;

		disable_irq(irq);
		local_irq_save(flags);

		handler(irq, dev_id);

		local_irq_restore(flags);
		enable_irq(irq);
	}
#endif
	return retval;
}
EXPORT_SYMBOL(request_threaded_irq);

/**
 *	request_any_context_irq - allocate an interrupt line
 *	@irq: Interrupt line to allocate
 *	@handler: Function to be called when the IRQ occurs.
 *		  Threaded handler for threaded interrupts.
 *	@flags: Interrupt type flags
 *	@name: An ascii name for the claiming device
 *	@dev_id: A cookie passed back to the handler function
 *
 *	This call allocates interrupt resources and enables the
 *	interrupt line and IRQ handling. It selects either a
 *	hardirq or threaded handling method depending on the
 *	context.
 *
 *	On failure, it returns a negative value. On success,
 *	it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
 */
int request_any_context_irq(unsigned int irq, irq_handler_t handler,
			    unsigned long flags, const char *name, void *dev_id)
{
	struct irq_desc *desc;
	int ret;

	if (irq == IRQ_NOTCONNECTED)
		return -ENOTCONN;

	desc = irq_to_desc(irq);
	if (!desc)
		return -EINVAL;

	if (irq_settings_is_nested_thread(desc)) {
		ret = request_threaded_irq(irq, NULL, handler,
					   flags, name, dev_id);
		return !ret ? IRQC_IS_NESTED : ret;
	}

	ret = request_irq(irq, handler, flags, name, dev_id);
	return !ret ? IRQC_IS_HARDIRQ : ret;
}
EXPORT_SYMBOL_GPL(request_any_context_irq);

void enable_percpu_irq(unsigned int irq, unsigned int type)
{
	unsigned int cpu = smp_processor_id();
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);

	if (!desc)
		return;

	/*
	 * If the trigger type is not specified by the caller, then
	 * use the default for this interrupt.
	 */
	type &= IRQ_TYPE_SENSE_MASK;
	if (type == IRQ_TYPE_NONE)
		type = irqd_get_trigger_type(&desc->irq_data);

	if (type != IRQ_TYPE_NONE) {
		int ret;

		ret = __irq_set_trigger(desc, type);

		if (ret) {
			WARN(1, "failed to set type for IRQ%d\n", irq);
			goto out;
		}
	}

	irq_percpu_enable(desc, cpu);
out:
	irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(enable_percpu_irq);

/**
 * irq_percpu_is_enabled - Check whether the per cpu irq is enabled
 * @irq:	Linux irq number to check for
 *
 * Must be called from a non migratable context. Returns the enable
 * state of a per cpu interrupt on the current cpu.
 */
bool irq_percpu_is_enabled(unsigned int irq)
{
	unsigned int cpu = smp_processor_id();
	struct irq_desc *desc;
	unsigned long flags;
	bool is_enabled;

	desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
	if (!desc)
		return false;

	is_enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
	irq_put_desc_unlock(desc, flags);

	return is_enabled;
}
EXPORT_SYMBOL_GPL(irq_percpu_is_enabled);

void disable_percpu_irq(unsigned int irq)
{
	unsigned int cpu = smp_processor_id();
	unsigned long flags;
	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);

	if (!desc)
		return;

	irq_percpu_disable(desc, cpu);
	irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(disable_percpu_irq);

/*
 * Internal function to unregister a percpu irqaction.
 */
static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irqaction *action;
	unsigned long flags;

	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);

	if (!desc)
		return NULL;

	raw_spin_lock_irqsave(&desc->lock, flags);

	action = desc->action;
	if (!action || action->percpu_dev_id != dev_id) {
		WARN(1, "Trying to free already-free IRQ %d\n", irq);
		goto bad;
	}

	if (!cpumask_empty(desc->percpu_enabled)) {
		WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
		     irq, cpumask_first(desc->percpu_enabled));
		goto bad;
	}

	/* Found it - now remove it from the list of entries: */
	desc->action = NULL;

	raw_spin_unlock_irqrestore(&desc->lock, flags);

	unregister_handler_proc(irq, action);

	irq_chip_pm_put(&desc->irq_data);
	module_put(desc->owner);
	return action;

bad:
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	return NULL;
}

/**
 *	remove_percpu_irq - free a per-cpu interrupt
 *	@irq: Interrupt line to free
 *	@act: irqaction for the interrupt
 *
 * Used to remove interrupts statically setup by the early boot process.
 */
void remove_percpu_irq(unsigned int irq, struct irqaction *act)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (desc && irq_settings_is_per_cpu_devid(desc))
	    __free_percpu_irq(irq, act->percpu_dev_id);
}

/**
 *	free_percpu_irq - free an interrupt allocated with request_percpu_irq
 *	@irq: Interrupt line to free
 *	@dev_id: Device identity to free
 *
 *	Remove a percpu interrupt handler. The handler is removed, but
 *	the interrupt line is not disabled. This must be done on each
 *	CPU before calling this function. The function does not return
 *	until any executing interrupts for this IRQ have completed.
 *
 *	This function must not be called from interrupt context.
 */
void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (!desc || !irq_settings_is_per_cpu_devid(desc))
		return;

	chip_bus_lock(desc);
	kfree(__free_percpu_irq(irq, dev_id));
	chip_bus_sync_unlock(desc);
}
EXPORT_SYMBOL_GPL(free_percpu_irq);

/**
 *	setup_percpu_irq - setup a per-cpu interrupt
 *	@irq: Interrupt line to setup
 *	@act: irqaction for the interrupt
 *
 * Used to statically setup per-cpu interrupts in the early boot process.
 */
int setup_percpu_irq(unsigned int irq, struct irqaction *act)
{
	struct irq_desc *desc = irq_to_desc(irq);
	int retval;

	if (!desc || !irq_settings_is_per_cpu_devid(desc))
		return -EINVAL;

	retval = irq_chip_pm_get(&desc->irq_data);
	if (retval < 0)
		return retval;

	chip_bus_lock(desc);
	retval = __setup_irq(irq, desc, act);
	chip_bus_sync_unlock(desc);

	if (retval)
		irq_chip_pm_put(&desc->irq_data);

	return retval;
}

/**
 *	request_percpu_irq - allocate a percpu interrupt line
 *	@irq: Interrupt line to allocate
 *	@handler: Function to be called when the IRQ occurs.
 *	@devname: An ascii name for the claiming device
 *	@dev_id: A percpu cookie passed back to the handler function
 *
 *	This call allocates interrupt resources and enables the
 *	interrupt on the local CPU. If the interrupt is supposed to be
 *	enabled on other CPUs, it has to be done on each CPU using
 *	enable_percpu_irq().
 *
 *	Dev_id must be globally unique. It is a per-cpu variable, and
 *	the handler gets called with the interrupted CPU's instance of
 *	that variable.
 */
int request_percpu_irq(unsigned int irq, irq_handler_t handler,
		       const char *devname, void __percpu *dev_id)
{
	struct irqaction *action;
	struct irq_desc *desc;
	int retval;

	if (!dev_id)
		return -EINVAL;

	desc = irq_to_desc(irq);
	if (!desc || !irq_settings_can_request(desc) ||
	    !irq_settings_is_per_cpu_devid(desc))
		return -EINVAL;

	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
	if (!action)
		return -ENOMEM;

	action->handler = handler;
	action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
	action->name = devname;
	action->percpu_dev_id = dev_id;

	retval = irq_chip_pm_get(&desc->irq_data);
	if (retval < 0) {
		kfree(action);
		return retval;
	}

	chip_bus_lock(desc);
	retval = __setup_irq(irq, desc, action);
	chip_bus_sync_unlock(desc);

	if (retval) {
		irq_chip_pm_put(&desc->irq_data);
		kfree(action);
	}

	return retval;
}
EXPORT_SYMBOL_GPL(request_percpu_irq);

/**
 *	irq_get_irqchip_state - returns the irqchip state of a interrupt.
 *	@irq: Interrupt line that is forwarded to a VM
 *	@which: One of IRQCHIP_STATE_* the caller wants to know about
 *	@state: a pointer to a boolean where the state is to be storeed
 *
 *	This call snapshots the internal irqchip state of an
 *	interrupt, returning into @state the bit corresponding to
 *	stage @which
 *
 *	This function should be called with preemption disabled if the
 *	interrupt controller has per-cpu registers.
 */
int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
			  bool *state)
{
	struct irq_desc *desc;
	struct irq_data *data;
	struct irq_chip *chip;
	unsigned long flags;
	int err = -EINVAL;

	desc = irq_get_desc_buslock(irq, &flags, 0);
	if (!desc)
		return err;

	data = irq_desc_get_irq_data(desc);

	do {
		chip = irq_data_get_irq_chip(data);
		if (chip->irq_get_irqchip_state)
			break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
		data = data->parent_data;
#else
		data = NULL;
#endif
	} while (data);

	if (data)
		err = chip->irq_get_irqchip_state(data, which, state);

	irq_put_desc_busunlock(desc, flags);
	return err;
}
EXPORT_SYMBOL_GPL(irq_get_irqchip_state);

/**
 *	irq_set_irqchip_state - set the state of a forwarded interrupt.
 *	@irq: Interrupt line that is forwarded to a VM
 *	@which: State to be restored (one of IRQCHIP_STATE_*)
 *	@val: Value corresponding to @which
 *
 *	This call sets the internal irqchip state of an interrupt,
 *	depending on the value of @which.
 *
 *	This function should be called with preemption disabled if the
 *	interrupt controller has per-cpu registers.
 */
int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
			  bool val)
{
	struct irq_desc *desc;
	struct irq_data *data;
	struct irq_chip *chip;
	unsigned long flags;
	int err = -EINVAL;

	desc = irq_get_desc_buslock(irq, &flags, 0);
	if (!desc)
		return err;

	data = irq_desc_get_irq_data(desc);

	do {
		chip = irq_data_get_irq_chip(data);
		if (chip->irq_set_irqchip_state)
			break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
		data = data->parent_data;
#else
		data = NULL;
#endif
	} while (data);

	if (data)
		err = chip->irq_set_irqchip_state(data, which, val);

	irq_put_desc_busunlock(desc, flags);
	return err;
}
EXPORT_SYMBOL_GPL(irq_set_irqchip_state);