summaryrefslogtreecommitdiff
path: root/drivers/xen/events/events_base.c
blob: 3b9f080109d7e46da11e4efb73a46554d7ff416f (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
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Xen event channels
 *
 * Xen models interrupts with abstract event channels.  Because each
 * domain gets 1024 event channels, but NR_IRQ is not that large, we
 * must dynamically map irqs<->event channels.  The event channels
 * interface with the rest of the kernel by defining a xen interrupt
 * chip.  When an event is received, it is mapped to an irq and sent
 * through the normal interrupt processing path.
 *
 * There are four kinds of events which can be mapped to an event
 * channel:
 *
 * 1. Inter-domain notifications.  This includes all the virtual
 *    device events, since they're driven by front-ends in another domain
 *    (typically dom0).
 * 2. VIRQs, typically used for timers.  These are per-cpu events.
 * 3. IPIs.
 * 4. PIRQs - Hardware interrupts.
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/linkage.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/moduleparam.h>
#include <linux/string.h>
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/irqnr.h>
#include <linux/pci.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/cpuhotplug.h>
#include <linux/atomic.h>
#include <linux/ktime.h>

#ifdef CONFIG_X86
#include <asm/desc.h>
#include <asm/ptrace.h>
#include <asm/idtentry.h>
#include <asm/irq.h>
#include <asm/io_apic.h>
#include <asm/i8259.h>
#include <asm/xen/cpuid.h>
#include <asm/xen/pci.h>
#endif
#include <asm/sync_bitops.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <xen/page.h>

#include <xen/xen.h>
#include <xen/hvm.h>
#include <xen/xen-ops.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/hvm/params.h>
#include <xen/interface/physdev.h>
#include <xen/interface/sched.h>
#include <xen/interface/vcpu.h>
#include <xen/xenbus.h>
#include <asm/hw_irq.h>

#include "events_internal.h"

#undef MODULE_PARAM_PREFIX
#define MODULE_PARAM_PREFIX "xen."

/* Interrupt types. */
enum xen_irq_type {
	IRQT_UNBOUND = 0,
	IRQT_PIRQ,
	IRQT_VIRQ,
	IRQT_IPI,
	IRQT_EVTCHN
};

/*
 * Packed IRQ information:
 * type - enum xen_irq_type
 * event channel - irq->event channel mapping
 * cpu - cpu this event channel is bound to
 * index - type-specific information:
 *    PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM
 *           guest, or GSI (real passthrough IRQ) of the device.
 *    VIRQ - virq number
 *    IPI - IPI vector
 *    EVTCHN -
 */
struct irq_info {
	struct list_head list;
	struct list_head eoi_list;
	struct rcu_work rwork;
	short refcnt;
	u8 spurious_cnt;
	u8 is_accounted;
	short type;		/* type: IRQT_* */
	u8 mask_reason;		/* Why is event channel masked */
#define EVT_MASK_REASON_EXPLICIT	0x01
#define EVT_MASK_REASON_TEMPORARY	0x02
#define EVT_MASK_REASON_EOI_PENDING	0x04
	u8 is_active;		/* Is event just being handled? */
	unsigned irq;
	evtchn_port_t evtchn;   /* event channel */
	unsigned short cpu;     /* cpu bound */
	unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */
	unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
	u64 eoi_time;           /* Time in jiffies when to EOI. */
	raw_spinlock_t lock;
	bool is_static;           /* Is event channel static */

	union {
		unsigned short virq;
		enum ipi_vector ipi;
		struct {
			unsigned short pirq;
			unsigned short gsi;
			unsigned char vector;
			unsigned char flags;
			uint16_t domid;
		} pirq;
		struct xenbus_device *interdomain;
	} u;
};

#define PIRQ_NEEDS_EOI	(1 << 0)
#define PIRQ_SHAREABLE	(1 << 1)
#define PIRQ_MSI_GROUP	(1 << 2)

static uint __read_mostly event_loop_timeout = 2;
module_param(event_loop_timeout, uint, 0644);

static uint __read_mostly event_eoi_delay = 10;
module_param(event_eoi_delay, uint, 0644);

const struct evtchn_ops *evtchn_ops;

/*
 * This lock protects updates to the following mapping and reference-count
 * arrays. The lock does not need to be acquired to read the mapping tables.
 */
static DEFINE_MUTEX(irq_mapping_update_lock);

/*
 * Lock hierarchy:
 *
 * irq_mapping_update_lock
 *   IRQ-desc lock
 *     percpu eoi_list_lock
 *       irq_info->lock
 */

static LIST_HEAD(xen_irq_list_head);

/* IRQ <-> VIRQ mapping. */
static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};

/* IRQ <-> IPI mapping */
static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
/* Cache for IPI event channels - needed for hot cpu unplug (avoid RCU usage). */
static DEFINE_PER_CPU(evtchn_port_t [XEN_NR_IPIS], ipi_to_evtchn) = {[0 ... XEN_NR_IPIS-1] = 0};

/* Event channel distribution data */
static atomic_t channels_on_cpu[NR_CPUS];

static int **evtchn_to_irq;
#ifdef CONFIG_X86
static unsigned long *pirq_eoi_map;
#endif
static bool (*pirq_needs_eoi)(struct irq_info *info);

#define EVTCHN_ROW(e)  (e / (PAGE_SIZE/sizeof(**evtchn_to_irq)))
#define EVTCHN_COL(e)  (e % (PAGE_SIZE/sizeof(**evtchn_to_irq)))
#define EVTCHN_PER_ROW (PAGE_SIZE / sizeof(**evtchn_to_irq))

/* Xen will never allocate port zero for any purpose. */
#define VALID_EVTCHN(chn)	((chn) != 0)

static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY];

static struct irq_chip xen_dynamic_chip;
static struct irq_chip xen_lateeoi_chip;
static struct irq_chip xen_percpu_chip;
static struct irq_chip xen_pirq_chip;
static void enable_dynirq(struct irq_data *data);

static DEFINE_PER_CPU(unsigned int, irq_epoch);

static void clear_evtchn_to_irq_row(int *evtchn_row)
{
	unsigned col;

	for (col = 0; col < EVTCHN_PER_ROW; col++)
		WRITE_ONCE(evtchn_row[col], -1);
}

static void clear_evtchn_to_irq_all(void)
{
	unsigned row;

	for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) {
		if (evtchn_to_irq[row] == NULL)
			continue;
		clear_evtchn_to_irq_row(evtchn_to_irq[row]);
	}
}

static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq)
{
	unsigned row;
	unsigned col;
	int *evtchn_row;

	if (evtchn >= xen_evtchn_max_channels())
		return -EINVAL;

	row = EVTCHN_ROW(evtchn);
	col = EVTCHN_COL(evtchn);

	if (evtchn_to_irq[row] == NULL) {
		/* Unallocated irq entries return -1 anyway */
		if (irq == -1)
			return 0;

		evtchn_row = (int *) __get_free_pages(GFP_KERNEL, 0);
		if (evtchn_row == NULL)
			return -ENOMEM;

		clear_evtchn_to_irq_row(evtchn_row);

		/*
		 * We've prepared an empty row for the mapping. If a different
		 * thread was faster inserting it, we can drop ours.
		 */
		if (cmpxchg(&evtchn_to_irq[row], NULL, evtchn_row) != NULL)
			free_page((unsigned long) evtchn_row);
	}

	WRITE_ONCE(evtchn_to_irq[row][col], irq);
	return 0;
}

/* Get info for IRQ */
static struct irq_info *info_for_irq(unsigned irq)
{
	if (irq < nr_legacy_irqs())
		return legacy_info_ptrs[irq];
	else
		return irq_get_chip_data(irq);
}

static void set_info_for_irq(unsigned int irq, struct irq_info *info)
{
	if (irq < nr_legacy_irqs())
		legacy_info_ptrs[irq] = info;
	else
		irq_set_chip_data(irq, info);
}

static struct irq_info *evtchn_to_info(evtchn_port_t evtchn)
{
	int irq;

	if (evtchn >= xen_evtchn_max_channels())
		return NULL;
	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
		return NULL;
	irq = READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);

	return (irq < 0) ? NULL : info_for_irq(irq);
}

/* Per CPU channel accounting */
static void channels_on_cpu_dec(struct irq_info *info)
{
	if (!info->is_accounted)
		return;

	info->is_accounted = 0;

	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
		return;

	WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], -1 , 0));
}

static void channels_on_cpu_inc(struct irq_info *info)
{
	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
		return;

	if (WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], 1,
					    INT_MAX)))
		return;

	info->is_accounted = 1;
}

static void xen_irq_free_desc(unsigned int irq)
{
	/* Legacy IRQ descriptors are managed by the arch. */
	if (irq >= nr_legacy_irqs())
		irq_free_desc(irq);
}

static void delayed_free_irq(struct work_struct *work)
{
	struct irq_info *info = container_of(to_rcu_work(work), struct irq_info,
					     rwork);
	unsigned int irq = info->irq;

	/* Remove the info pointer only now, with no potential users left. */
	set_info_for_irq(irq, NULL);

	kfree(info);

	xen_irq_free_desc(irq);
}

/* Constructors for packed IRQ information. */
static int xen_irq_info_common_setup(struct irq_info *info,
				     enum xen_irq_type type,
				     evtchn_port_t evtchn,
				     unsigned short cpu)
{
	int ret;

	BUG_ON(info->type != IRQT_UNBOUND && info->type != type);

	info->type = type;
	info->evtchn = evtchn;
	info->cpu = cpu;
	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
	raw_spin_lock_init(&info->lock);

	ret = set_evtchn_to_irq(evtchn, info->irq);
	if (ret < 0)
		return ret;

	irq_clear_status_flags(info->irq, IRQ_NOREQUEST | IRQ_NOAUTOEN);

	return xen_evtchn_port_setup(evtchn);
}

static int xen_irq_info_evtchn_setup(struct irq_info *info,
				     evtchn_port_t evtchn,
				     struct xenbus_device *dev)
{
	int ret;

	ret = xen_irq_info_common_setup(info, IRQT_EVTCHN, evtchn, 0);
	info->u.interdomain = dev;
	if (dev)
		atomic_inc(&dev->event_channels);

	return ret;
}

static int xen_irq_info_ipi_setup(struct irq_info *info, unsigned int cpu,
				  evtchn_port_t evtchn, enum ipi_vector ipi)
{
	info->u.ipi = ipi;

	per_cpu(ipi_to_irq, cpu)[ipi] = info->irq;
	per_cpu(ipi_to_evtchn, cpu)[ipi] = evtchn;

	return xen_irq_info_common_setup(info, IRQT_IPI, evtchn, 0);
}

static int xen_irq_info_virq_setup(struct irq_info *info, unsigned int cpu,
				   evtchn_port_t evtchn, unsigned int virq)
{
	info->u.virq = virq;

	per_cpu(virq_to_irq, cpu)[virq] = info->irq;

	return xen_irq_info_common_setup(info, IRQT_VIRQ, evtchn, 0);
}

static int xen_irq_info_pirq_setup(struct irq_info *info, evtchn_port_t evtchn,
				   unsigned int pirq, unsigned int gsi,
				   uint16_t domid, unsigned char flags)
{
	info->u.pirq.pirq = pirq;
	info->u.pirq.gsi = gsi;
	info->u.pirq.domid = domid;
	info->u.pirq.flags = flags;

	return xen_irq_info_common_setup(info, IRQT_PIRQ, evtchn, 0);
}

static void xen_irq_info_cleanup(struct irq_info *info)
{
	set_evtchn_to_irq(info->evtchn, -1);
	xen_evtchn_port_remove(info->evtchn, info->cpu);
	info->evtchn = 0;
	channels_on_cpu_dec(info);
}

/*
 * Accessors for packed IRQ information.
 */
static evtchn_port_t evtchn_from_irq(unsigned int irq)
{
	const struct irq_info *info = NULL;

	if (likely(irq < nr_irqs))
		info = info_for_irq(irq);
	if (!info)
		return 0;

	return info->evtchn;
}

unsigned int irq_from_evtchn(evtchn_port_t evtchn)
{
	struct irq_info *info = evtchn_to_info(evtchn);

	return info ? info->irq : -1;
}
EXPORT_SYMBOL_GPL(irq_from_evtchn);

int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq,
			 evtchn_port_t *evtchn)
{
	int irq = per_cpu(virq_to_irq, cpu)[virq];

	*evtchn = evtchn_from_irq(irq);

	return irq;
}

static enum ipi_vector ipi_from_irq(struct irq_info *info)
{
	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_IPI);

	return info->u.ipi;
}

static unsigned int virq_from_irq(struct irq_info *info)
{
	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_VIRQ);

	return info->u.virq;
}

static unsigned int pirq_from_irq(struct irq_info *info)
{
	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.pirq;
}

unsigned int cpu_from_evtchn(evtchn_port_t evtchn)
{
	struct irq_info *info = evtchn_to_info(evtchn);

	return info ? info->cpu : 0;
}

static void do_mask(struct irq_info *info, u8 reason)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&info->lock, flags);

	if (!info->mask_reason)
		mask_evtchn(info->evtchn);

	info->mask_reason |= reason;

	raw_spin_unlock_irqrestore(&info->lock, flags);
}

static void do_unmask(struct irq_info *info, u8 reason)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&info->lock, flags);

	info->mask_reason &= ~reason;

	if (!info->mask_reason)
		unmask_evtchn(info->evtchn);

	raw_spin_unlock_irqrestore(&info->lock, flags);
}

#ifdef CONFIG_X86
static bool pirq_check_eoi_map(struct irq_info *info)
{
	return test_bit(pirq_from_irq(info), pirq_eoi_map);
}
#endif

static bool pirq_needs_eoi_flag(struct irq_info *info)
{
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
}

static void bind_evtchn_to_cpu(struct irq_info *info, unsigned int cpu,
			       bool force_affinity)
{
	if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
		struct irq_data *data = irq_get_irq_data(info->irq);

		irq_data_update_affinity(data, cpumask_of(cpu));
		irq_data_update_effective_affinity(data, cpumask_of(cpu));
	}

	xen_evtchn_port_bind_to_cpu(info->evtchn, cpu, info->cpu);

	channels_on_cpu_dec(info);
	info->cpu = cpu;
	channels_on_cpu_inc(info);
}

/**
 * notify_remote_via_irq - send event to remote end of event channel via irq
 * @irq: irq of event channel to send event to
 *
 * Unlike notify_remote_via_evtchn(), this is safe to use across
 * save/restore. Notifications on a broken connection are silently
 * dropped.
 */
void notify_remote_via_irq(int irq)
{
	evtchn_port_t evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		notify_remote_via_evtchn(evtchn);
}
EXPORT_SYMBOL_GPL(notify_remote_via_irq);

struct lateeoi_work {
	struct delayed_work delayed;
	spinlock_t eoi_list_lock;
	struct list_head eoi_list;
};

static DEFINE_PER_CPU(struct lateeoi_work, lateeoi);

static void lateeoi_list_del(struct irq_info *info)
{
	struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu);
	unsigned long flags;

	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
	list_del_init(&info->eoi_list);
	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
}

static void lateeoi_list_add(struct irq_info *info)
{
	struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu);
	struct irq_info *elem;
	u64 now = get_jiffies_64();
	unsigned long delay;
	unsigned long flags;

	if (now < info->eoi_time)
		delay = info->eoi_time - now;
	else
		delay = 1;

	spin_lock_irqsave(&eoi->eoi_list_lock, flags);

	elem = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
					eoi_list);
	if (!elem || info->eoi_time < elem->eoi_time) {
		list_add(&info->eoi_list, &eoi->eoi_list);
		mod_delayed_work_on(info->eoi_cpu, system_wq,
				    &eoi->delayed, delay);
	} else {
		list_for_each_entry_reverse(elem, &eoi->eoi_list, eoi_list) {
			if (elem->eoi_time <= info->eoi_time)
				break;
		}
		list_add(&info->eoi_list, &elem->eoi_list);
	}

	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
}

static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
{
	evtchn_port_t evtchn;
	unsigned int cpu;
	unsigned int delay = 0;

	evtchn = info->evtchn;
	if (!VALID_EVTCHN(evtchn) || !list_empty(&info->eoi_list))
		return;

	if (spurious) {
		struct xenbus_device *dev = info->u.interdomain;
		unsigned int threshold = 1;

		if (dev && dev->spurious_threshold)
			threshold = dev->spurious_threshold;

		if ((1 << info->spurious_cnt) < (HZ << 2)) {
			if (info->spurious_cnt != 0xFF)
				info->spurious_cnt++;
		}
		if (info->spurious_cnt > threshold) {
			delay = 1 << (info->spurious_cnt - 1 - threshold);
			if (delay > HZ)
				delay = HZ;
			if (!info->eoi_time)
				info->eoi_cpu = smp_processor_id();
			info->eoi_time = get_jiffies_64() + delay;
			if (dev)
				atomic_add(delay, &dev->jiffies_eoi_delayed);
		}
		if (dev)
			atomic_inc(&dev->spurious_events);
	} else {
		info->spurious_cnt = 0;
	}

	cpu = info->eoi_cpu;
	if (info->eoi_time &&
	    (info->irq_epoch == per_cpu(irq_epoch, cpu) || delay)) {
		lateeoi_list_add(info);
		return;
	}

	info->eoi_time = 0;

	/* is_active hasn't been reset yet, do it now. */
	smp_store_release(&info->is_active, 0);
	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
}

static void xen_irq_lateeoi_worker(struct work_struct *work)
{
	struct lateeoi_work *eoi;
	struct irq_info *info;
	u64 now = get_jiffies_64();
	unsigned long flags;

	eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed);

	rcu_read_lock();

	while (true) {
		spin_lock_irqsave(&eoi->eoi_list_lock, flags);

		info = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
						eoi_list);

		if (info == NULL)
			break;

		if (now < info->eoi_time) {
			mod_delayed_work_on(info->eoi_cpu, system_wq,
					    &eoi->delayed,
					    info->eoi_time - now);
			break;
		}

		list_del_init(&info->eoi_list);

		spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);

		info->eoi_time = 0;

		xen_irq_lateeoi_locked(info, false);
	}

	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);

	rcu_read_unlock();
}

static void xen_cpu_init_eoi(unsigned int cpu)
{
	struct lateeoi_work *eoi = &per_cpu(lateeoi, cpu);

	INIT_DELAYED_WORK(&eoi->delayed, xen_irq_lateeoi_worker);
	spin_lock_init(&eoi->eoi_list_lock);
	INIT_LIST_HEAD(&eoi->eoi_list);
}

void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
{
	struct irq_info *info;

	rcu_read_lock();

	info = info_for_irq(irq);

	if (info)
		xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS);

	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(xen_irq_lateeoi);

static struct irq_info *xen_irq_init(unsigned int irq)
{
	struct irq_info *info;

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (info) {
		info->irq = irq;
		info->type = IRQT_UNBOUND;
		info->refcnt = -1;
		INIT_RCU_WORK(&info->rwork, delayed_free_irq);

		set_info_for_irq(irq, info);
		/*
		 * Interrupt affinity setting can be immediate. No point
		 * in delaying it until an interrupt is handled.
		 */
		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);

		INIT_LIST_HEAD(&info->eoi_list);
		list_add_tail(&info->list, &xen_irq_list_head);
	}

	return info;
}

static struct irq_info *xen_allocate_irq_dynamic(void)
{
	int irq = irq_alloc_desc_from(0, -1);
	struct irq_info *info = NULL;

	if (irq >= 0) {
		info = xen_irq_init(irq);
		if (!info)
			xen_irq_free_desc(irq);
	}

	return info;
}

static struct irq_info *xen_allocate_irq_gsi(unsigned int gsi)
{
	int irq;
	struct irq_info *info;

	/*
	 * A PV guest has no concept of a GSI (since it has no ACPI
	 * nor access to/knowledge of the physical APICs). Therefore
	 * all IRQs are dynamically allocated from the entire IRQ
	 * space.
	 */
	if (xen_pv_domain() && !xen_initial_domain())
		return xen_allocate_irq_dynamic();

	/* Legacy IRQ descriptors are already allocated by the arch. */
	if (gsi < nr_legacy_irqs())
		irq = gsi;
	else
		irq = irq_alloc_desc_at(gsi, -1);

	info = xen_irq_init(irq);
	if (!info)
		xen_irq_free_desc(irq);

	return info;
}

static void xen_free_irq(struct irq_info *info)
{
	if (WARN_ON(!info))
		return;

	if (!list_empty(&info->eoi_list))
		lateeoi_list_del(info);

	list_del(&info->list);

	WARN_ON(info->refcnt > 0);

	queue_rcu_work(system_wq, &info->rwork);
}

/* Not called for lateeoi events. */
static void event_handler_exit(struct irq_info *info)
{
	smp_store_release(&info->is_active, 0);
	clear_evtchn(info->evtchn);
}

static void pirq_query_unmask(struct irq_info *info)
{
	struct physdev_irq_status_query irq_status;

	irq_status.irq = pirq_from_irq(info);
	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
		irq_status.flags = 0;

	info->u.pirq.flags &= ~PIRQ_NEEDS_EOI;
	if (irq_status.flags & XENIRQSTAT_needs_eoi)
		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
}

static void do_eoi_pirq(struct irq_info *info)
{
	struct physdev_eoi eoi = { .irq = pirq_from_irq(info) };
	int rc = 0;

	if (!VALID_EVTCHN(info->evtchn))
		return;

	event_handler_exit(info);

	if (pirq_needs_eoi(info)) {
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
		WARN_ON(rc);
	}
}

static void eoi_pirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	do_eoi_pirq(info);
}

static void do_disable_dynirq(struct irq_info *info)
{
	if (VALID_EVTCHN(info->evtchn))
		do_mask(info, EVT_MASK_REASON_EXPLICIT);
}

static void disable_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	if (info)
		do_disable_dynirq(info);
}

static void mask_ack_pirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	if (info) {
		do_disable_dynirq(info);
		do_eoi_pirq(info);
	}
}

static unsigned int __startup_pirq(struct irq_info *info)
{
	struct evtchn_bind_pirq bind_pirq;
	evtchn_port_t evtchn = info->evtchn;
	int rc;

	if (VALID_EVTCHN(evtchn))
		goto out;

	bind_pirq.pirq = pirq_from_irq(info);
	/* NB. We are happy to share unless we are probing. */
	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
					BIND_PIRQ__WILL_SHARE : 0;
	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
	if (rc != 0) {
		pr_warn("Failed to obtain physical IRQ %d\n", info->irq);
		return 0;
	}
	evtchn = bind_pirq.port;

	pirq_query_unmask(info);

	rc = set_evtchn_to_irq(evtchn, info->irq);
	if (rc)
		goto err;

	info->evtchn = evtchn;
	bind_evtchn_to_cpu(info, 0, false);

	rc = xen_evtchn_port_setup(evtchn);
	if (rc)
		goto err;

out:
	do_unmask(info, EVT_MASK_REASON_EXPLICIT);

	do_eoi_pirq(info);

	return 0;

err:
	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", info->irq,
	       rc);
	xen_evtchn_close(evtchn);
	return 0;
}

static unsigned int startup_pirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	return __startup_pirq(info);
}

static void shutdown_pirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);
	evtchn_port_t evtchn = info->evtchn;

	BUG_ON(info->type != IRQT_PIRQ);

	if (!VALID_EVTCHN(evtchn))
		return;

	do_mask(info, EVT_MASK_REASON_EXPLICIT);
	xen_irq_info_cleanup(info);
	xen_evtchn_close(evtchn);
}

static void enable_pirq(struct irq_data *data)
{
	enable_dynirq(data);
}

static void disable_pirq(struct irq_data *data)
{
	disable_dynirq(data);
}

int xen_irq_from_gsi(unsigned gsi)
{
	struct irq_info *info;

	list_for_each_entry(info, &xen_irq_list_head, list) {
		if (info->type != IRQT_PIRQ)
			continue;

		if (info->u.pirq.gsi == gsi)
			return info->irq;
	}

	return -1;
}
EXPORT_SYMBOL_GPL(xen_irq_from_gsi);

static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
{
	evtchn_port_t evtchn;
	bool close_evtchn = false;

	if (!info) {
		xen_irq_free_desc(irq);
		return;
	}

	if (info->refcnt > 0) {
		info->refcnt--;
		if (info->refcnt != 0)
			return;
	}

	evtchn = info->evtchn;

	if (VALID_EVTCHN(evtchn)) {
		unsigned int cpu = info->cpu;
		struct xenbus_device *dev;

		if (!info->is_static)
			close_evtchn = true;

		switch (info->type) {
		case IRQT_VIRQ:
			per_cpu(virq_to_irq, cpu)[virq_from_irq(info)] = -1;
			break;
		case IRQT_IPI:
			per_cpu(ipi_to_irq, cpu)[ipi_from_irq(info)] = -1;
			per_cpu(ipi_to_evtchn, cpu)[ipi_from_irq(info)] = 0;
			break;
		case IRQT_EVTCHN:
			dev = info->u.interdomain;
			if (dev)
				atomic_dec(&dev->event_channels);
			break;
		default:
			break;
		}

		xen_irq_info_cleanup(info);

		if (close_evtchn)
			xen_evtchn_close(evtchn);
	}

	xen_free_irq(info);
}

/*
 * Do not make any assumptions regarding the relationship between the
 * IRQ number returned here and the Xen pirq argument.
 *
 * Note: We don't assign an event channel until the irq actually started
 * up.  Return an existing irq if we've already got one for the gsi.
 *
 * Shareable implies level triggered, not shareable implies edge
 * triggered here.
 */
int xen_bind_pirq_gsi_to_irq(unsigned gsi,
			     unsigned pirq, int shareable, char *name)
{
	struct irq_info *info;
	struct physdev_irq irq_op;
	int ret;

	mutex_lock(&irq_mapping_update_lock);

	ret = xen_irq_from_gsi(gsi);
	if (ret != -1) {
		pr_info("%s: returning irq %d for gsi %u\n",
			__func__, ret, gsi);
		goto out;
	}

	info = xen_allocate_irq_gsi(gsi);
	if (!info)
		goto out;

	irq_op.irq = info->irq;
	irq_op.vector = 0;

	/* Only the privileged domain can do this. For non-priv, the pcifront
	 * driver provides a PCI bus that does the call to do exactly
	 * this in the priv domain. */
	if (xen_initial_domain() &&
	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
		xen_free_irq(info);
		ret = -ENOSPC;
		goto out;
	}

	ret = xen_irq_info_pirq_setup(info, 0, pirq, gsi, DOMID_SELF,
			       shareable ? PIRQ_SHAREABLE : 0);
	if (ret < 0) {
		__unbind_from_irq(info, info->irq);
		goto out;
	}

	pirq_query_unmask(info);
	/* We try to use the handler with the appropriate semantic for the
	 * type of interrupt: if the interrupt is an edge triggered
	 * interrupt we use handle_edge_irq.
	 *
	 * On the other hand if the interrupt is level triggered we use
	 * handle_fasteoi_irq like the native code does for this kind of
	 * interrupts.
	 *
	 * Depending on the Xen version, pirq_needs_eoi might return true
	 * not only for level triggered interrupts but for edge triggered
	 * interrupts too. In any case Xen always honors the eoi mechanism,
	 * not injecting any more pirqs of the same kind if the first one
	 * hasn't received an eoi yet. Therefore using the fasteoi handler
	 * is the right choice either way.
	 */
	if (shareable)
		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
				handle_fasteoi_irq, name);
	else
		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
				handle_edge_irq, name);

	ret = info->irq;

out:
	mutex_unlock(&irq_mapping_update_lock);

	return ret;
}

#ifdef CONFIG_PCI_MSI
int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
	int rc;
	struct physdev_get_free_pirq op_get_free_pirq;

	op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);

	WARN_ONCE(rc == -ENOSYS,
		  "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");

	return rc ? -1 : op_get_free_pirq.pirq;
}

int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
			     int pirq, int nvec, const char *name, domid_t domid)
{
	int i, irq, ret;
	struct irq_info *info;

	mutex_lock(&irq_mapping_update_lock);

	irq = irq_alloc_descs(-1, 0, nvec, -1);
	if (irq < 0)
		goto out;

	for (i = 0; i < nvec; i++) {
		info = xen_irq_init(irq + i);
		if (!info) {
			ret = -ENOMEM;
			goto error_irq;
		}

		irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name);

		ret = xen_irq_info_pirq_setup(info, 0, pirq + i, 0, domid,
					      i == 0 ? 0 : PIRQ_MSI_GROUP);
		if (ret < 0)
			goto error_irq;
	}

	ret = irq_set_msi_desc(irq, msidesc);
	if (ret < 0)
		goto error_irq;
out:
	mutex_unlock(&irq_mapping_update_lock);
	return irq;

error_irq:
	while (nvec--) {
		info = info_for_irq(irq + nvec);
		__unbind_from_irq(info, irq + nvec);
	}
	mutex_unlock(&irq_mapping_update_lock);
	return ret;
}
#endif

int xen_destroy_irq(int irq)
{
	struct physdev_unmap_pirq unmap_irq;
	struct irq_info *info = info_for_irq(irq);
	int rc = -ENOENT;

	mutex_lock(&irq_mapping_update_lock);

	/*
	 * If trying to remove a vector in a MSI group different
	 * than the first one skip the PIRQ unmap unless this vector
	 * is the first one in the group.
	 */
	if (xen_initial_domain() && !(info->u.pirq.flags & PIRQ_MSI_GROUP)) {
		unmap_irq.pirq = info->u.pirq.pirq;
		unmap_irq.domid = info->u.pirq.domid;
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
		/* If another domain quits without making the pci_disable_msix
		 * call, the Xen hypervisor takes care of freeing the PIRQs
		 * (free_domain_pirqs).
		 */
		if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
			pr_info("domain %d does not have %d anymore\n",
				info->u.pirq.domid, info->u.pirq.pirq);
		else if (rc) {
			pr_warn("unmap irq failed %d\n", rc);
			goto out;
		}
	}

	xen_free_irq(info);

out:
	mutex_unlock(&irq_mapping_update_lock);
	return rc;
}

int xen_pirq_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	return pirq_from_irq(info);
}
EXPORT_SYMBOL_GPL(xen_pirq_from_irq);

static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
				   struct xenbus_device *dev)
{
	int ret = -ENOMEM;
	struct irq_info *info;

	if (evtchn >= xen_evtchn_max_channels())
		return -ENOMEM;

	mutex_lock(&irq_mapping_update_lock);

	info = evtchn_to_info(evtchn);

	if (!info) {
		info = xen_allocate_irq_dynamic();
		if (!info)
			goto out;

		irq_set_chip_and_handler_name(info->irq, chip,
					      handle_edge_irq, "event");

		ret = xen_irq_info_evtchn_setup(info, evtchn, dev);
		if (ret < 0) {
			__unbind_from_irq(info, info->irq);
			goto out;
		}
		/*
		 * New interdomain events are initially bound to vCPU0 This
		 * is required to setup the event channel in the first
		 * place and also important for UP guests because the
		 * affinity setting is not invoked on them so nothing would
		 * bind the channel.
		 */
		bind_evtchn_to_cpu(info, 0, false);
	} else if (!WARN_ON(info->type != IRQT_EVTCHN)) {
		info->refcnt++;
	}

	ret = info->irq;

out:
	mutex_unlock(&irq_mapping_update_lock);

	return ret;
}

int bind_evtchn_to_irq(evtchn_port_t evtchn)
{
	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);

int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
{
	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);

static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	evtchn_port_t evtchn;
	struct irq_info *info;
	int ret;

	mutex_lock(&irq_mapping_update_lock);

	ret = per_cpu(ipi_to_irq, cpu)[ipi];

	if (ret == -1) {
		info = xen_allocate_irq_dynamic();
		if (!info)
			goto out;

		irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
					      handle_percpu_irq, "ipi");

		bind_ipi.vcpu = xen_vcpu_nr(cpu);
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		ret = xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
		if (ret < 0) {
			__unbind_from_irq(info, info->irq);
			goto out;
		}
		/*
		 * Force the affinity mask to the target CPU so proc shows
		 * the correct target.
		 */
		bind_evtchn_to_cpu(info, cpu, true);
		ret = info->irq;
	} else {
		info = info_for_irq(ret);
		WARN_ON(info == NULL || info->type != IRQT_IPI);
	}

 out:
	mutex_unlock(&irq_mapping_update_lock);
	return ret;
}

static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev,
					       evtchn_port_t remote_port,
					       struct irq_chip *chip)
{
	struct evtchn_bind_interdomain bind_interdomain;
	int err;

	bind_interdomain.remote_dom  = dev->otherend_id;
	bind_interdomain.remote_port = remote_port;

	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
					  &bind_interdomain);

	return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port,
					       chip, dev);
}

int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev,
					   evtchn_port_t remote_port)
{
	return bind_interdomain_evtchn_to_irq_chip(dev, remote_port,
						   &xen_lateeoi_chip);
}
EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi);

static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn)
{
	struct evtchn_status status;
	evtchn_port_t port;
	int rc = -ENOENT;

	memset(&status, 0, sizeof(status));
	for (port = 0; port < xen_evtchn_max_channels(); port++) {
		status.dom = DOMID_SELF;
		status.port = port;
		rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
		if (rc < 0)
			continue;
		if (status.status != EVTCHNSTAT_virq)
			continue;
		if (status.u.virq == virq && status.vcpu == xen_vcpu_nr(cpu)) {
			*evtchn = port;
			break;
		}
	}
	return rc;
}

/**
 * xen_evtchn_nr_channels - number of usable event channel ports
 *
 * This may be less than the maximum supported by the current
 * hypervisor ABI. Use xen_evtchn_max_channels() for the maximum
 * supported.
 */
unsigned xen_evtchn_nr_channels(void)
{
        return evtchn_ops->nr_channels();
}
EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels);

int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
{
	struct evtchn_bind_virq bind_virq;
	evtchn_port_t evtchn = 0;
	struct irq_info *info;
	int ret;

	mutex_lock(&irq_mapping_update_lock);

	ret = per_cpu(virq_to_irq, cpu)[virq];

	if (ret == -1) {
		info = xen_allocate_irq_dynamic();
		if (!info)
			goto out;

		if (percpu)
			irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
						      handle_percpu_irq, "virq");
		else
			irq_set_chip_and_handler_name(info->irq, &xen_dynamic_chip,
						      handle_edge_irq, "virq");

		bind_virq.virq = virq;
		bind_virq.vcpu = xen_vcpu_nr(cpu);
		ret = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq);
		if (ret == 0)
			evtchn = bind_virq.port;
		else {
			if (ret == -EEXIST)
				ret = find_virq(virq, cpu, &evtchn);
			BUG_ON(ret < 0);
		}

		ret = xen_irq_info_virq_setup(info, cpu, evtchn, virq);
		if (ret < 0) {
			__unbind_from_irq(info, info->irq);
			goto out;
		}

		/*
		 * Force the affinity mask for percpu interrupts so proc
		 * shows the correct target.
		 */
		bind_evtchn_to_cpu(info, cpu, percpu);
		ret = info->irq;
	} else {
		info = info_for_irq(ret);
		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
	}

out:
	mutex_unlock(&irq_mapping_update_lock);

	return ret;
}

static void unbind_from_irq(unsigned int irq)
{
	struct irq_info *info;

	mutex_lock(&irq_mapping_update_lock);
	info = info_for_irq(irq);
	__unbind_from_irq(info, irq);
	mutex_unlock(&irq_mapping_update_lock);
}

static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn,
					  irq_handler_t handler,
					  unsigned long irqflags,
					  const char *devname, void *dev_id,
					  struct irq_chip *chip)
{
	int irq, retval;

	irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL);
	if (irq < 0)
		return irq;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}

int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
			      irq_handler_t handler,
			      unsigned long irqflags,
			      const char *devname, void *dev_id)
{
	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
					      devname, dev_id,
					      &xen_dynamic_chip);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);

int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
				      irq_handler_t handler,
				      unsigned long irqflags,
				      const char *devname, void *dev_id)
{
	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
					      devname, dev_id,
					      &xen_lateeoi_chip);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi);

static int bind_interdomain_evtchn_to_irqhandler_chip(
		struct xenbus_device *dev, evtchn_port_t remote_port,
		irq_handler_t handler, unsigned long irqflags,
		const char *devname, void *dev_id, struct irq_chip *chip)
{
	int irq, retval;

	irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip);
	if (irq < 0)
		return irq;

	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}

int bind_interdomain_evtchn_to_irqhandler_lateeoi(struct xenbus_device *dev,
						  evtchn_port_t remote_port,
						  irq_handler_t handler,
						  unsigned long irqflags,
						  const char *devname,
						  void *dev_id)
{
	return bind_interdomain_evtchn_to_irqhandler_chip(dev,
				remote_port, handler, irqflags, devname,
				dev_id, &xen_lateeoi_chip);
}
EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi);

int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
			    irq_handler_t handler,
			    unsigned long irqflags, const char *devname, void *dev_id)
{
	int irq, retval;

	irq = bind_virq_to_irq(virq, cpu, irqflags & IRQF_PERCPU);
	if (irq < 0)
		return irq;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);

int bind_ipi_to_irqhandler(enum ipi_vector ipi,
			   unsigned int cpu,
			   irq_handler_t handler,
			   unsigned long irqflags,
			   const char *devname,
			   void *dev_id)
{
	int irq, retval;

	irq = bind_ipi_to_irq(ipi, cpu);
	if (irq < 0)
		return irq;

	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME | IRQF_EARLY_RESUME;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}

void unbind_from_irqhandler(unsigned int irq, void *dev_id)
{
	struct irq_info *info = info_for_irq(irq);

	if (WARN_ON(!info))
		return;
	free_irq(irq, dev_id);
	unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(unbind_from_irqhandler);

/**
 * xen_set_irq_priority() - set an event channel priority.
 * @irq:irq bound to an event channel.
 * @priority: priority between XEN_IRQ_PRIORITY_MAX and XEN_IRQ_PRIORITY_MIN.
 */
int xen_set_irq_priority(unsigned irq, unsigned priority)
{
	struct evtchn_set_priority set_priority;

	set_priority.port = evtchn_from_irq(irq);
	set_priority.priority = priority;

	return HYPERVISOR_event_channel_op(EVTCHNOP_set_priority,
					   &set_priority);
}
EXPORT_SYMBOL_GPL(xen_set_irq_priority);

int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static)
{
	struct irq_info *info = evtchn_to_info(evtchn);

	if (!info)
		return -ENOENT;

	WARN_ON(info->refcnt != -1);

	info->refcnt = 1;
	info->is_static = is_static;

	return 0;
}
EXPORT_SYMBOL_GPL(evtchn_make_refcounted);

int evtchn_get(evtchn_port_t evtchn)
{
	struct irq_info *info;
	int err = -ENOENT;

	if (evtchn >= xen_evtchn_max_channels())
		return -EINVAL;

	mutex_lock(&irq_mapping_update_lock);

	info = evtchn_to_info(evtchn);

	if (!info)
		goto done;

	err = -EINVAL;
	if (info->refcnt <= 0 || info->refcnt == SHRT_MAX)
		goto done;

	info->refcnt++;
	err = 0;
 done:
	mutex_unlock(&irq_mapping_update_lock);

	return err;
}
EXPORT_SYMBOL_GPL(evtchn_get);

void evtchn_put(evtchn_port_t evtchn)
{
	struct irq_info *info = evtchn_to_info(evtchn);

	if (WARN_ON(!info))
		return;
	unbind_from_irq(info->irq);
}
EXPORT_SYMBOL_GPL(evtchn_put);

void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
{
	evtchn_port_t evtchn;

#ifdef CONFIG_X86
	if (unlikely(vector == XEN_NMI_VECTOR)) {
		int rc =  HYPERVISOR_vcpu_op(VCPUOP_send_nmi, xen_vcpu_nr(cpu),
					     NULL);
		if (rc < 0)
			printk(KERN_WARNING "Sending nmi to CPU%d failed (rc:%d)\n", cpu, rc);
		return;
	}
#endif
	evtchn = per_cpu(ipi_to_evtchn, cpu)[vector];
	BUG_ON(evtchn == 0);
	notify_remote_via_evtchn(evtchn);
}

struct evtchn_loop_ctrl {
	ktime_t timeout;
	unsigned count;
	bool defer_eoi;
};

void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
{
	struct irq_info *info = evtchn_to_info(port);
	struct xenbus_device *dev;

	if (!info)
		return;

	/*
	 * Check for timeout every 256 events.
	 * We are setting the timeout value only after the first 256
	 * events in order to not hurt the common case of few loop
	 * iterations. The 256 is basically an arbitrary value.
	 *
	 * In case we are hitting the timeout we need to defer all further
	 * EOIs in order to ensure to leave the event handling loop rather
	 * sooner than later.
	 */
	if (!ctrl->defer_eoi && !(++ctrl->count & 0xff)) {
		ktime_t kt = ktime_get();

		if (!ctrl->timeout) {
			kt = ktime_add_ms(kt,
					  jiffies_to_msecs(event_loop_timeout));
			ctrl->timeout = kt;
		} else if (kt > ctrl->timeout) {
			ctrl->defer_eoi = true;
		}
	}

	if (xchg_acquire(&info->is_active, 1))
		return;

	dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL;
	if (dev)
		atomic_inc(&dev->events);

	if (ctrl->defer_eoi) {
		info->eoi_cpu = smp_processor_id();
		info->irq_epoch = __this_cpu_read(irq_epoch);
		info->eoi_time = get_jiffies_64() + event_eoi_delay;
	}

	generic_handle_irq(info->irq);
}

int xen_evtchn_do_upcall(void)
{
	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
	int ret = vcpu_info->evtchn_upcall_pending ? IRQ_HANDLED : IRQ_NONE;
	int cpu = smp_processor_id();
	struct evtchn_loop_ctrl ctrl = { 0 };

	/*
	 * When closing an event channel the associated IRQ must not be freed
	 * until all cpus have left the event handling loop. This is ensured
	 * by taking the rcu_read_lock() while handling events, as freeing of
	 * the IRQ is handled via queue_rcu_work() _after_ closing the event
	 * channel.
	 */
	rcu_read_lock();

	do {
		vcpu_info->evtchn_upcall_pending = 0;

		xen_evtchn_handle_events(cpu, &ctrl);

		BUG_ON(!irqs_disabled());

		virt_rmb(); /* Hypervisor can set upcall pending. */

	} while (vcpu_info->evtchn_upcall_pending);

	rcu_read_unlock();

	/*
	 * Increment irq_epoch only now to defer EOIs only for
	 * xen_irq_lateeoi() invocations occurring from inside the loop
	 * above.
	 */
	__this_cpu_inc(irq_epoch);

	return ret;
}
EXPORT_SYMBOL_GPL(xen_evtchn_do_upcall);

/* Rebind a new event channel to an existing irq. */
void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
{
	struct irq_info *info = info_for_irq(irq);

	if (WARN_ON(!info))
		return;

	/* Make sure the irq is masked, since the new event channel
	   will also be masked. */
	disable_irq(irq);

	mutex_lock(&irq_mapping_update_lock);

	/* After resume the irq<->evtchn mappings are all cleared out */
	BUG_ON(evtchn_to_info(evtchn));
	/* Expect irq to have been bound before,
	   so there should be a proper type */
	BUG_ON(info->type == IRQT_UNBOUND);

	info->irq = irq;
	(void)xen_irq_info_evtchn_setup(info, evtchn, NULL);

	mutex_unlock(&irq_mapping_update_lock);

	bind_evtchn_to_cpu(info, info->cpu, false);

	/* Unmask the event channel. */
	enable_irq(irq);
}

/* Rebind an evtchn so that it gets delivered to a specific cpu */
static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
{
	struct evtchn_bind_vcpu bind_vcpu;
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (!VALID_EVTCHN(evtchn))
		return -1;

	if (!xen_support_evtchn_rebind())
		return -1;

	/* Send future instances of this interrupt to other vcpu. */
	bind_vcpu.port = evtchn;
	bind_vcpu.vcpu = xen_vcpu_nr(tcpu);

	/*
	 * Mask the event while changing the VCPU binding to prevent
	 * it being delivered on an unexpected VCPU.
	 */
	do_mask(info, EVT_MASK_REASON_TEMPORARY);

	/*
	 * If this fails, it usually just indicates that we're dealing with a
	 * virq or IPI channel, which don't actually need to be rebound. Ignore
	 * it, but don't do the xenlinux-level rebind in that case.
	 */
	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
		bind_evtchn_to_cpu(info, tcpu, false);

	do_unmask(info, EVT_MASK_REASON_TEMPORARY);

	return 0;
}

/*
 * Find the CPU within @dest mask which has the least number of channels
 * assigned. This is not precise as the per cpu counts can be modified
 * concurrently.
 */
static unsigned int select_target_cpu(const struct cpumask *dest)
{
	unsigned int cpu, best_cpu = UINT_MAX, minch = UINT_MAX;

	for_each_cpu_and(cpu, dest, cpu_online_mask) {
		unsigned int curch = atomic_read(&channels_on_cpu[cpu]);

		if (curch < minch) {
			minch = curch;
			best_cpu = cpu;
		}
	}

	/*
	 * Catch the unlikely case that dest contains no online CPUs. Can't
	 * recurse.
	 */
	if (best_cpu == UINT_MAX)
		return select_target_cpu(cpu_online_mask);

	return best_cpu;
}

static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
			    bool force)
{
	unsigned int tcpu = select_target_cpu(dest);
	int ret;

	ret = xen_rebind_evtchn_to_cpu(info_for_irq(data->irq), tcpu);
	if (!ret)
		irq_data_update_effective_affinity(data, cpumask_of(tcpu));

	return ret;
}

static void enable_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (VALID_EVTCHN(evtchn))
		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
}

static void do_ack_dynirq(struct irq_info *info)
{
	evtchn_port_t evtchn = info->evtchn;

	if (VALID_EVTCHN(evtchn))
		event_handler_exit(info);
}

static void ack_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	if (info)
		do_ack_dynirq(info);
}

static void mask_ack_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);

	if (info) {
		do_disable_dynirq(info);
		do_ack_dynirq(info);
	}
}

static void lateeoi_ack_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (VALID_EVTCHN(evtchn)) {
		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
		/*
		 * Don't call event_handler_exit().
		 * Need to keep is_active non-zero in order to ignore re-raised
		 * events after cpu affinity changes while a lateeoi is pending.
		 */
		clear_evtchn(evtchn);
	}
}

static void lateeoi_mask_ack_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (VALID_EVTCHN(evtchn)) {
		do_mask(info, EVT_MASK_REASON_EXPLICIT);
		event_handler_exit(info);
	}
}

static int retrigger_dynirq(struct irq_data *data)
{
	struct irq_info *info = info_for_irq(data->irq);
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (!VALID_EVTCHN(evtchn))
		return 0;

	do_mask(info, EVT_MASK_REASON_TEMPORARY);
	set_evtchn(evtchn);
	do_unmask(info, EVT_MASK_REASON_TEMPORARY);

	return 1;
}

static void restore_pirqs(void)
{
	int pirq, rc, irq, gsi;
	struct physdev_map_pirq map_irq;
	struct irq_info *info;

	list_for_each_entry(info, &xen_irq_list_head, list) {
		if (info->type != IRQT_PIRQ)
			continue;

		pirq = info->u.pirq.pirq;
		gsi = info->u.pirq.gsi;
		irq = info->irq;

		/* save/restore of PT devices doesn't work, so at this point the
		 * only devices present are GSI based emulated devices */
		if (!gsi)
			continue;

		map_irq.domid = DOMID_SELF;
		map_irq.type = MAP_PIRQ_TYPE_GSI;
		map_irq.index = gsi;
		map_irq.pirq = pirq;

		rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
		if (rc) {
			pr_warn("xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
				gsi, irq, pirq, rc);
			xen_free_irq(info);
			continue;
		}

		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);

		__startup_pirq(info);
	}
}

static void restore_cpu_virqs(unsigned int cpu)
{
	struct evtchn_bind_virq bind_virq;
	evtchn_port_t evtchn;
	struct irq_info *info;
	int virq, irq;

	for (virq = 0; virq < NR_VIRQS; virq++) {
		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
			continue;
		info = info_for_irq(irq);

		BUG_ON(virq_from_irq(info) != virq);

		/* Get a new binding from Xen. */
		bind_virq.virq = virq;
		bind_virq.vcpu = xen_vcpu_nr(cpu);
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq) != 0)
			BUG();
		evtchn = bind_virq.port;

		/* Record the new mapping. */
		xen_irq_info_virq_setup(info, cpu, evtchn, virq);
		/* The affinity mask is still valid */
		bind_evtchn_to_cpu(info, cpu, false);
	}
}

static void restore_cpu_ipis(unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	evtchn_port_t evtchn;
	struct irq_info *info;
	int ipi, irq;

	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
			continue;
		info = info_for_irq(irq);

		BUG_ON(ipi_from_irq(info) != ipi);

		/* Get a new binding from Xen. */
		bind_ipi.vcpu = xen_vcpu_nr(cpu);
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		/* Record the new mapping. */
		xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
		/* The affinity mask is still valid */
		bind_evtchn_to_cpu(info, cpu, false);
	}
}

/* Clear an irq's pending state, in preparation for polling on it */
void xen_clear_irq_pending(int irq)
{
	struct irq_info *info = info_for_irq(irq);
	evtchn_port_t evtchn = info ? info->evtchn : 0;

	if (VALID_EVTCHN(evtchn))
		event_handler_exit(info);
}
EXPORT_SYMBOL(xen_clear_irq_pending);

bool xen_test_irq_pending(int irq)
{
	evtchn_port_t evtchn = evtchn_from_irq(irq);
	bool ret = false;

	if (VALID_EVTCHN(evtchn))
		ret = test_evtchn(evtchn);

	return ret;
}

/* Poll waiting for an irq to become pending with timeout.  In the usual case,
 * the irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq_timeout(int irq, u64 timeout)
{
	evtchn_port_t evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn)) {
		struct sched_poll poll;

		poll.nr_ports = 1;
		poll.timeout = timeout;
		set_xen_guest_handle(poll.ports, &evtchn);

		if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
			BUG();
	}
}
EXPORT_SYMBOL(xen_poll_irq_timeout);
/* Poll waiting for an irq to become pending.  In the usual case, the
 * irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq(int irq)
{
	xen_poll_irq_timeout(irq, 0 /* no timeout */);
}

/* Check whether the IRQ line is shared with other guests. */
int xen_test_irq_shared(int irq)
{
	struct irq_info *info = info_for_irq(irq);
	struct physdev_irq_status_query irq_status;

	if (WARN_ON(!info))
		return -ENOENT;

	irq_status.irq = info->u.pirq.pirq;

	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
		return 0;
	return !(irq_status.flags & XENIRQSTAT_shared);
}
EXPORT_SYMBOL_GPL(xen_test_irq_shared);

void xen_irq_resume(void)
{
	unsigned int cpu;
	struct irq_info *info;

	/* New event-channel space is not 'live' yet. */
	xen_evtchn_resume();

	/* No IRQ <-> event-channel mappings. */
	list_for_each_entry(info, &xen_irq_list_head, list) {
		/* Zap event-channel binding */
		info->evtchn = 0;
		/* Adjust accounting */
		channels_on_cpu_dec(info);
	}

	clear_evtchn_to_irq_all();

	for_each_possible_cpu(cpu) {
		restore_cpu_virqs(cpu);
		restore_cpu_ipis(cpu);
	}

	restore_pirqs();
}

static struct irq_chip xen_dynamic_chip __read_mostly = {
	.name			= "xen-dyn",

	.irq_disable		= disable_dynirq,
	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= ack_dynirq,
	.irq_mask_ack		= mask_ack_dynirq,

	.irq_set_affinity	= set_affinity_irq,
	.irq_retrigger		= retrigger_dynirq,
};

static struct irq_chip xen_lateeoi_chip __read_mostly = {
	/* The chip name needs to contain "xen-dyn" for irqbalance to work. */
	.name			= "xen-dyn-lateeoi",

	.irq_disable		= disable_dynirq,
	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= lateeoi_ack_dynirq,
	.irq_mask_ack		= lateeoi_mask_ack_dynirq,

	.irq_set_affinity	= set_affinity_irq,
	.irq_retrigger		= retrigger_dynirq,
};

static struct irq_chip xen_pirq_chip __read_mostly = {
	.name			= "xen-pirq",

	.irq_startup		= startup_pirq,
	.irq_shutdown		= shutdown_pirq,
	.irq_enable		= enable_pirq,
	.irq_disable		= disable_pirq,

	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= eoi_pirq,
	.irq_eoi		= eoi_pirq,
	.irq_mask_ack		= mask_ack_pirq,

	.irq_set_affinity	= set_affinity_irq,

	.irq_retrigger		= retrigger_dynirq,
};

static struct irq_chip xen_percpu_chip __read_mostly = {
	.name			= "xen-percpu",

	.irq_disable		= disable_dynirq,
	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= ack_dynirq,
};

#ifdef CONFIG_X86
#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
 * channel notifications because we can receive vector callbacks on any
 * vcpu and we don't need PCI support or APIC interactions. */
void xen_setup_callback_vector(void)
{
	uint64_t callback_via;

	if (xen_have_vector_callback) {
		callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR);
		if (xen_set_callback_via(callback_via)) {
			pr_err("Request for Xen HVM callback vector failed\n");
			xen_have_vector_callback = false;
		}
	}
}

/*
 * Setup per-vCPU vector-type callbacks. If this setup is unavailable,
 * fallback to the global vector-type callback.
 */
static __init void xen_init_setup_upcall_vector(void)
{
	if (!xen_have_vector_callback)
		return;

	if ((cpuid_eax(xen_cpuid_base() + 4) & XEN_HVM_CPUID_UPCALL_VECTOR) &&
	    !xen_set_upcall_vector(0))
		xen_percpu_upcall = true;
	else if (xen_feature(XENFEAT_hvm_callback_vector))
		xen_setup_callback_vector();
	else
		xen_have_vector_callback = false;
}

int xen_set_upcall_vector(unsigned int cpu)
{
	int rc;
	xen_hvm_evtchn_upcall_vector_t op = {
		.vector = HYPERVISOR_CALLBACK_VECTOR,
		.vcpu = per_cpu(xen_vcpu_id, cpu),
	};

	rc = HYPERVISOR_hvm_op(HVMOP_set_evtchn_upcall_vector, &op);
	if (rc)
		return rc;

	/* Trick toolstack to think we are enlightened. */
	if (!cpu)
		rc = xen_set_callback_via(1);

	return rc;
}

static __init void xen_alloc_callback_vector(void)
{
	if (!xen_have_vector_callback)
		return;

	pr_info("Xen HVM callback vector for event delivery is enabled\n");
	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_xen_hvm_callback);
}
#else
void xen_setup_callback_vector(void) {}
static inline void xen_init_setup_upcall_vector(void) {}
int xen_set_upcall_vector(unsigned int cpu) {}
static inline void xen_alloc_callback_vector(void) {}
#endif /* CONFIG_XEN_PVHVM */
#endif /* CONFIG_X86 */

bool xen_fifo_events = true;
module_param_named(fifo_events, xen_fifo_events, bool, 0);

static int xen_evtchn_cpu_prepare(unsigned int cpu)
{
	int ret = 0;

	xen_cpu_init_eoi(cpu);

	if (evtchn_ops->percpu_init)
		ret = evtchn_ops->percpu_init(cpu);

	return ret;
}

static int xen_evtchn_cpu_dead(unsigned int cpu)
{
	int ret = 0;

	if (evtchn_ops->percpu_deinit)
		ret = evtchn_ops->percpu_deinit(cpu);

	return ret;
}

void __init xen_init_IRQ(void)
{
	int ret = -EINVAL;
	evtchn_port_t evtchn;

	if (xen_fifo_events)
		ret = xen_evtchn_fifo_init();
	if (ret < 0) {
		xen_evtchn_2l_init();
		xen_fifo_events = false;
	}

	xen_cpu_init_eoi(smp_processor_id());

	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
				  "xen/evtchn:prepare",
				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);

	evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()),
				sizeof(*evtchn_to_irq), GFP_KERNEL);
	BUG_ON(!evtchn_to_irq);

	/* No event channels are 'live' right now. */
	for (evtchn = 0; evtchn < xen_evtchn_nr_channels(); evtchn++)
		mask_evtchn(evtchn);

	pirq_needs_eoi = pirq_needs_eoi_flag;

#ifdef CONFIG_X86
	if (xen_pv_domain()) {
		if (xen_initial_domain())
			pci_xen_initial_domain();
	}
	xen_init_setup_upcall_vector();
	xen_alloc_callback_vector();


	if (xen_hvm_domain()) {
		native_init_IRQ();
		/* pci_xen_hvm_init must be called after native_init_IRQ so that
		 * __acpi_register_gsi can point at the right function */
		pci_xen_hvm_init();
	} else {
		int rc;
		struct physdev_pirq_eoi_gmfn eoi_gmfn;

		pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
		eoi_gmfn.gmfn = virt_to_gfn(pirq_eoi_map);
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn);
		if (rc != 0) {
			free_page((unsigned long) pirq_eoi_map);
			pirq_eoi_map = NULL;
		} else
			pirq_needs_eoi = pirq_check_eoi_map;
	}
#endif
}