summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/xen.c
blob: d7af402402484bb008f253213a86c186224a34c1 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright © 2019 Oracle and/or its affiliates. All rights reserved.
 * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 *
 * KVM Xen emulation
 */

#include "x86.h"
#include "xen.h"
#include "hyperv.h"
#include "lapic.h"

#include <linux/eventfd.h>
#include <linux/kvm_host.h>
#include <linux/sched/stat.h>

#include <trace/events/kvm.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/version.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/sched.h>

#include "trace.h"

static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm);
static int kvm_xen_setattr_evtchn(struct kvm *kvm, struct kvm_xen_hvm_attr *data);
static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r);

DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ);

static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
{
	struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
	struct pvclock_wall_clock *wc;
	gpa_t gpa = gfn_to_gpa(gfn);
	u32 *wc_sec_hi;
	u32 wc_version;
	u64 wall_nsec;
	int ret = 0;
	int idx = srcu_read_lock(&kvm->srcu);

	if (gfn == GPA_INVALID) {
		kvm_gpc_deactivate(gpc);
		goto out;
	}

	do {
		ret = kvm_gpc_activate(gpc, gpa, PAGE_SIZE);
		if (ret)
			goto out;

		/*
		 * This code mirrors kvm_write_wall_clock() except that it writes
		 * directly through the pfn cache and doesn't mark the page dirty.
		 */
		wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm);

		/* It could be invalid again already, so we need to check */
		read_lock_irq(&gpc->lock);

		if (gpc->valid)
			break;

		read_unlock_irq(&gpc->lock);
	} while (1);

	/* Paranoia checks on the 32-bit struct layout */
	BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900);
	BUILD_BUG_ON(offsetof(struct compat_shared_info, arch.wc_sec_hi) != 0x924);
	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);

#ifdef CONFIG_X86_64
	/* Paranoia checks on the 64-bit struct layout */
	BUILD_BUG_ON(offsetof(struct shared_info, wc) != 0xc00);
	BUILD_BUG_ON(offsetof(struct shared_info, wc_sec_hi) != 0xc0c);

	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) {
		struct shared_info *shinfo = gpc->khva;

		wc_sec_hi = &shinfo->wc_sec_hi;
		wc = &shinfo->wc;
	} else
#endif
	{
		struct compat_shared_info *shinfo = gpc->khva;

		wc_sec_hi = &shinfo->arch.wc_sec_hi;
		wc = &shinfo->wc;
	}

	/* Increment and ensure an odd value */
	wc_version = wc->version = (wc->version + 1) | 1;
	smp_wmb();

	wc->nsec = do_div(wall_nsec,  1000000000);
	wc->sec = (u32)wall_nsec;
	*wc_sec_hi = wall_nsec >> 32;
	smp_wmb();

	wc->version = wc_version + 1;
	read_unlock_irq(&gpc->lock);

	kvm_make_all_cpus_request(kvm, KVM_REQ_MASTERCLOCK_UPDATE);

out:
	srcu_read_unlock(&kvm->srcu, idx);
	return ret;
}

void kvm_xen_inject_timer_irqs(struct kvm_vcpu *vcpu)
{
	if (atomic_read(&vcpu->arch.xen.timer_pending) > 0) {
		struct kvm_xen_evtchn e;

		e.vcpu_id = vcpu->vcpu_id;
		e.vcpu_idx = vcpu->vcpu_idx;
		e.port = vcpu->arch.xen.timer_virq;
		e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;

		kvm_xen_set_evtchn(&e, vcpu->kvm);

		vcpu->arch.xen.timer_expires = 0;
		atomic_set(&vcpu->arch.xen.timer_pending, 0);
	}
}

static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu = container_of(timer, struct kvm_vcpu,
					     arch.xen.timer);
	if (atomic_read(&vcpu->arch.xen.timer_pending))
		return HRTIMER_NORESTART;

	atomic_inc(&vcpu->arch.xen.timer_pending);
	kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
	kvm_vcpu_kick(vcpu);

	return HRTIMER_NORESTART;
}

static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns)
{
	atomic_set(&vcpu->arch.xen.timer_pending, 0);
	vcpu->arch.xen.timer_expires = guest_abs;

	if (delta_ns <= 0) {
		xen_timer_callback(&vcpu->arch.xen.timer);
	} else {
		ktime_t ktime_now = ktime_get();
		hrtimer_start(&vcpu->arch.xen.timer,
			      ktime_add_ns(ktime_now, delta_ns),
			      HRTIMER_MODE_ABS_HARD);
	}
}

static void kvm_xen_stop_timer(struct kvm_vcpu *vcpu)
{
	hrtimer_cancel(&vcpu->arch.xen.timer);
	vcpu->arch.xen.timer_expires = 0;
	atomic_set(&vcpu->arch.xen.timer_pending, 0);
}

static void kvm_xen_init_timer(struct kvm_vcpu *vcpu)
{
	hrtimer_init(&vcpu->arch.xen.timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_ABS_HARD);
	vcpu->arch.xen.timer.function = xen_timer_callback;
}

static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
{
	struct kvm_vcpu_xen *vx = &v->arch.xen;
	struct gfn_to_pfn_cache *gpc1 = &vx->runstate_cache;
	struct gfn_to_pfn_cache *gpc2 = &vx->runstate2_cache;
	size_t user_len, user_len1, user_len2;
	struct vcpu_runstate_info rs;
	unsigned long flags;
	size_t times_ofs;
	uint8_t *update_bit = NULL;
	uint64_t entry_time;
	uint64_t *rs_times;
	int *rs_state;

	/*
	 * The only difference between 32-bit and 64-bit versions of the
	 * runstate struct is the alignment of uint64_t in 32-bit, which
	 * means that the 64-bit version has an additional 4 bytes of
	 * padding after the first field 'state'. Let's be really really
	 * paranoid about that, and matching it with our internal data
	 * structures that we memcpy into it...
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0);
	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0);
	BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c);
#ifdef CONFIG_X86_64
	/*
	 * The 64-bit structure has 4 bytes of padding before 'state_entry_time'
	 * so each subsequent field is shifted by 4, and it's 4 bytes longer.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4);
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) !=
		     offsetof(struct compat_vcpu_runstate_info, time) + 4);
	BUILD_BUG_ON(sizeof(struct vcpu_runstate_info) != 0x2c + 4);
#endif
	/*
	 * The state field is in the same place at the start of both structs,
	 * and is the same size (int) as vx->current_runstate.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
		     offsetof(struct compat_vcpu_runstate_info, state));
	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
		     sizeof(vx->current_runstate));
	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
		     sizeof(vx->current_runstate));

	/*
	 * The state_entry_time field is 64 bits in both versions, and the
	 * XEN_RUNSTATE_UPDATE flag is in the top bit, which given that x86
	 * is little-endian means that it's in the last *byte* of the word.
	 * That detail is important later.
	 */
	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
		     sizeof(uint64_t));
	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
		     sizeof(uint64_t));
	BUILD_BUG_ON((XEN_RUNSTATE_UPDATE >> 56) != 0x80);

	/*
	 * The time array is four 64-bit quantities in both versions, matching
	 * the vx->runstate_times and immediately following state_entry_time.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct vcpu_runstate_info, time) - sizeof(uint64_t));
	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct compat_vcpu_runstate_info, time) - sizeof(uint64_t));
	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
		     sizeof_field(struct compat_vcpu_runstate_info, time));
	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
		     sizeof(vx->runstate_times));

	if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode) {
		user_len = sizeof(struct vcpu_runstate_info);
		times_ofs = offsetof(struct vcpu_runstate_info,
				     state_entry_time);
	} else {
		user_len = sizeof(struct compat_vcpu_runstate_info);
		times_ofs = offsetof(struct compat_vcpu_runstate_info,
				     state_entry_time);
	}

	/*
	 * There are basically no alignment constraints. The guest can set it
	 * up so it crosses from one page to the next, and at arbitrary byte
	 * alignment (and the 32-bit ABI doesn't align the 64-bit integers
	 * anyway, even if the overall struct had been 64-bit aligned).
	 */
	if ((gpc1->gpa & ~PAGE_MASK) + user_len >= PAGE_SIZE) {
		user_len1 = PAGE_SIZE - (gpc1->gpa & ~PAGE_MASK);
		user_len2 = user_len - user_len1;
	} else {
		user_len1 = user_len;
		user_len2 = 0;
	}
	BUG_ON(user_len1 + user_len2 != user_len);

 retry:
	/*
	 * Attempt to obtain the GPC lock on *both* (if there are two)
	 * gfn_to_pfn caches that cover the region.
	 */
	read_lock_irqsave(&gpc1->lock, flags);
	while (!kvm_gpc_check(gpc1, user_len1)) {
		read_unlock_irqrestore(&gpc1->lock, flags);

		/* When invoked from kvm_sched_out() we cannot sleep */
		if (atomic)
			return;

		if (kvm_gpc_refresh(gpc1, user_len1))
			return;

		read_lock_irqsave(&gpc1->lock, flags);
	}

	if (likely(!user_len2)) {
		/*
		 * Set up three pointers directly to the runstate_info
		 * struct in the guest (via the GPC).
		 *
		 *  • @rs_state   → state field
		 *  • @rs_times   → state_entry_time field.
		 *  • @update_bit → last byte of state_entry_time, which
		 *                  contains the XEN_RUNSTATE_UPDATE bit.
		 */
		rs_state = gpc1->khva;
		rs_times = gpc1->khva + times_ofs;
		if (v->kvm->arch.xen.runstate_update_flag)
			update_bit = ((void *)(&rs_times[1])) - 1;
	} else {
		/*
		 * The guest's runstate_info is split across two pages and we
		 * need to hold and validate both GPCs simultaneously. We can
		 * declare a lock ordering GPC1 > GPC2 because nothing else
		 * takes them more than one at a time.
		 */
		read_lock(&gpc2->lock);

		if (!kvm_gpc_check(gpc2, user_len2)) {
			read_unlock(&gpc2->lock);
			read_unlock_irqrestore(&gpc1->lock, flags);

			/* When invoked from kvm_sched_out() we cannot sleep */
			if (atomic)
				return;

			/*
			 * Use kvm_gpc_activate() here because if the runstate
			 * area was configured in 32-bit mode and only extends
			 * to the second page now because the guest changed to
			 * 64-bit mode, the second GPC won't have been set up.
			 */
			if (kvm_gpc_activate(gpc2, gpc1->gpa + user_len1,
					     user_len2))
				return;

			/*
			 * We dropped the lock on GPC1 so we have to go all the
			 * way back and revalidate that too.
			 */
			goto retry;
		}

		/*
		 * In this case, the runstate_info struct will be assembled on
		 * the kernel stack (compat or not as appropriate) and will
		 * be copied to GPC1/GPC2 with a dual memcpy. Set up the three
		 * rs pointers accordingly.
		 */
		rs_times = &rs.state_entry_time;

		/*
		 * The rs_state pointer points to the start of what we'll
		 * copy to the guest, which in the case of a compat guest
		 * is the 32-bit field that the compiler thinks is padding.
		 */
		rs_state = ((void *)rs_times) - times_ofs;

		/*
		 * The update_bit is still directly in the guest memory,
		 * via one GPC or the other.
		 */
		if (v->kvm->arch.xen.runstate_update_flag) {
			if (user_len1 >= times_ofs + sizeof(uint64_t))
				update_bit = gpc1->khva + times_ofs +
					sizeof(uint64_t) - 1;
			else
				update_bit = gpc2->khva + times_ofs +
					sizeof(uint64_t) - 1 - user_len1;
		}

#ifdef CONFIG_X86_64
		/*
		 * Don't leak kernel memory through the padding in the 64-bit
		 * version of the struct.
		 */
		memset(&rs, 0, offsetof(struct vcpu_runstate_info, state_entry_time));
#endif
	}

	/*
	 * First, set the XEN_RUNSTATE_UPDATE bit in the top bit of the
	 * state_entry_time field, directly in the guest. We need to set
	 * that (and write-barrier) before writing to the rest of the
	 * structure, and clear it last. Just as Xen does, we address the
	 * single *byte* in which it resides because it might be in a
	 * different cache line to the rest of the 64-bit word, due to
	 * the (lack of) alignment constraints.
	 */
	entry_time = vx->runstate_entry_time;
	if (update_bit) {
		entry_time |= XEN_RUNSTATE_UPDATE;
		*update_bit = (vx->runstate_entry_time | XEN_RUNSTATE_UPDATE) >> 56;
		smp_wmb();
	}

	/*
	 * Now assemble the actual structure, either on our kernel stack
	 * or directly in the guest according to how the rs_state and
	 * rs_times pointers were set up above.
	 */
	*rs_state = vx->current_runstate;
	rs_times[0] = entry_time;
	memcpy(rs_times + 1, vx->runstate_times, sizeof(vx->runstate_times));

	/* For the split case, we have to then copy it to the guest. */
	if (user_len2) {
		memcpy(gpc1->khva, rs_state, user_len1);
		memcpy(gpc2->khva, ((void *)rs_state) + user_len1, user_len2);
	}
	smp_wmb();

	/* Finally, clear the XEN_RUNSTATE_UPDATE bit. */
	if (update_bit) {
		entry_time &= ~XEN_RUNSTATE_UPDATE;
		*update_bit = entry_time >> 56;
		smp_wmb();
	}

	if (user_len2)
		read_unlock(&gpc2->lock);

	read_unlock_irqrestore(&gpc1->lock, flags);

	mark_page_dirty_in_slot(v->kvm, gpc1->memslot, gpc1->gpa >> PAGE_SHIFT);
	if (user_len2)
		mark_page_dirty_in_slot(v->kvm, gpc2->memslot, gpc2->gpa >> PAGE_SHIFT);
}

void kvm_xen_update_runstate(struct kvm_vcpu *v, int state)
{
	struct kvm_vcpu_xen *vx = &v->arch.xen;
	u64 now = get_kvmclock_ns(v->kvm);
	u64 delta_ns = now - vx->runstate_entry_time;
	u64 run_delay = current->sched_info.run_delay;

	if (unlikely(!vx->runstate_entry_time))
		vx->current_runstate = RUNSTATE_offline;

	/*
	 * Time waiting for the scheduler isn't "stolen" if the
	 * vCPU wasn't running anyway.
	 */
	if (vx->current_runstate == RUNSTATE_running) {
		u64 steal_ns = run_delay - vx->last_steal;

		delta_ns -= steal_ns;

		vx->runstate_times[RUNSTATE_runnable] += steal_ns;
	}
	vx->last_steal = run_delay;

	vx->runstate_times[vx->current_runstate] += delta_ns;
	vx->current_runstate = state;
	vx->runstate_entry_time = now;

	if (vx->runstate_cache.active)
		kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable);
}

static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v)
{
	struct kvm_lapic_irq irq = { };
	int r;

	irq.dest_id = v->vcpu_id;
	irq.vector = v->arch.xen.upcall_vector;
	irq.dest_mode = APIC_DEST_PHYSICAL;
	irq.shorthand = APIC_DEST_NOSHORT;
	irq.delivery_mode = APIC_DM_FIXED;
	irq.level = 1;

	/* The fast version will always work for physical unicast */
	WARN_ON_ONCE(!kvm_irq_delivery_to_apic_fast(v->kvm, NULL, &irq, &r, NULL));
}

/*
 * On event channel delivery, the vcpu_info may not have been accessible.
 * In that case, there are bits in vcpu->arch.xen.evtchn_pending_sel which
 * need to be marked into the vcpu_info (and evtchn_upcall_pending set).
 * Do so now that we can sleep in the context of the vCPU to bring the
 * page in, and refresh the pfn cache for it.
 */
void kvm_xen_inject_pending_events(struct kvm_vcpu *v)
{
	unsigned long evtchn_pending_sel = READ_ONCE(v->arch.xen.evtchn_pending_sel);
	struct gfn_to_pfn_cache *gpc = &v->arch.xen.vcpu_info_cache;
	unsigned long flags;

	if (!evtchn_pending_sel)
		return;

	/*
	 * Yes, this is an open-coded loop. But that's just what put_user()
	 * does anyway. Page it in and retry the instruction. We're just a
	 * little more honest about it.
	 */
	read_lock_irqsave(&gpc->lock, flags);
	while (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) {
		read_unlock_irqrestore(&gpc->lock, flags);

		if (kvm_gpc_refresh(gpc, sizeof(struct vcpu_info)))
			return;

		read_lock_irqsave(&gpc->lock, flags);
	}

	/* Now gpc->khva is a valid kernel address for the vcpu_info */
	if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode) {
		struct vcpu_info *vi = gpc->khva;

		asm volatile(LOCK_PREFIX "orq %0, %1\n"
			     "notq %0\n"
			     LOCK_PREFIX "andq %0, %2\n"
			     : "=r" (evtchn_pending_sel),
			       "+m" (vi->evtchn_pending_sel),
			       "+m" (v->arch.xen.evtchn_pending_sel)
			     : "0" (evtchn_pending_sel));
		WRITE_ONCE(vi->evtchn_upcall_pending, 1);
	} else {
		u32 evtchn_pending_sel32 = evtchn_pending_sel;
		struct compat_vcpu_info *vi = gpc->khva;

		asm volatile(LOCK_PREFIX "orl %0, %1\n"
			     "notl %0\n"
			     LOCK_PREFIX "andl %0, %2\n"
			     : "=r" (evtchn_pending_sel32),
			       "+m" (vi->evtchn_pending_sel),
			       "+m" (v->arch.xen.evtchn_pending_sel)
			     : "0" (evtchn_pending_sel32));
		WRITE_ONCE(vi->evtchn_upcall_pending, 1);
	}
	read_unlock_irqrestore(&gpc->lock, flags);

	/* For the per-vCPU lapic vector, deliver it as MSI. */
	if (v->arch.xen.upcall_vector)
		kvm_xen_inject_vcpu_vector(v);

	mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
}

int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
	struct gfn_to_pfn_cache *gpc = &v->arch.xen.vcpu_info_cache;
	unsigned long flags;
	u8 rc = 0;

	/*
	 * If the global upcall vector (HVMIRQ_callback_vector) is set and
	 * the vCPU's evtchn_upcall_pending flag is set, the IRQ is pending.
	 */

	/* No need for compat handling here */
	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
	BUILD_BUG_ON(sizeof(rc) !=
		     sizeof_field(struct vcpu_info, evtchn_upcall_pending));
	BUILD_BUG_ON(sizeof(rc) !=
		     sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));

	read_lock_irqsave(&gpc->lock, flags);
	while (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) {
		read_unlock_irqrestore(&gpc->lock, flags);

		/*
		 * This function gets called from kvm_vcpu_block() after setting the
		 * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
		 * from a HLT. So we really mustn't sleep. If the page ended up absent
		 * at that point, just return 1 in order to trigger an immediate wake,
		 * and we'll end up getting called again from a context where we *can*
		 * fault in the page and wait for it.
		 */
		if (in_atomic() || !task_is_running(current))
			return 1;

		if (kvm_gpc_refresh(gpc, sizeof(struct vcpu_info))) {
			/*
			 * If this failed, userspace has screwed up the
			 * vcpu_info mapping. No interrupts for you.
			 */
			return 0;
		}
		read_lock_irqsave(&gpc->lock, flags);
	}

	rc = ((struct vcpu_info *)gpc->khva)->evtchn_upcall_pending;
	read_unlock_irqrestore(&gpc->lock, flags);
	return rc;
}

int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
	int r = -ENOENT;


	switch (data->type) {
	case KVM_XEN_ATTR_TYPE_LONG_MODE:
		if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
			r = -EINVAL;
		} else {
			mutex_lock(&kvm->lock);
			kvm->arch.xen.long_mode = !!data->u.long_mode;
			mutex_unlock(&kvm->lock);
			r = 0;
		}
		break;

	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
		mutex_lock(&kvm->lock);
		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
		mutex_unlock(&kvm->lock);
		break;

	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
		if (data->u.vector && data->u.vector < 0x10)
			r = -EINVAL;
		else {
			mutex_lock(&kvm->lock);
			kvm->arch.xen.upcall_vector = data->u.vector;
			mutex_unlock(&kvm->lock);
			r = 0;
		}
		break;

	case KVM_XEN_ATTR_TYPE_EVTCHN:
		r = kvm_xen_setattr_evtchn(kvm, data);
		break;

	case KVM_XEN_ATTR_TYPE_XEN_VERSION:
		mutex_lock(&kvm->lock);
		kvm->arch.xen.xen_version = data->u.xen_version;
		mutex_unlock(&kvm->lock);
		r = 0;
		break;

	case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		mutex_lock(&kvm->lock);
		kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
		mutex_unlock(&kvm->lock);
		r = 0;
		break;

	default:
		break;
	}

	return r;
}

int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
	int r = -ENOENT;

	mutex_lock(&kvm->lock);

	switch (data->type) {
	case KVM_XEN_ATTR_TYPE_LONG_MODE:
		data->u.long_mode = kvm->arch.xen.long_mode;
		r = 0;
		break;

	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
		if (kvm->arch.xen.shinfo_cache.active)
			data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa);
		else
			data->u.shared_info.gfn = GPA_INVALID;
		r = 0;
		break;

	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
		data->u.vector = kvm->arch.xen.upcall_vector;
		r = 0;
		break;

	case KVM_XEN_ATTR_TYPE_XEN_VERSION:
		data->u.xen_version = kvm->arch.xen.xen_version;
		r = 0;
		break;

	case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		data->u.runstate_update_flag = kvm->arch.xen.runstate_update_flag;
		r = 0;
		break;

	default:
		break;
	}

	mutex_unlock(&kvm->lock);
	return r;
}

int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
	int idx, r = -ENOENT;

	mutex_lock(&vcpu->kvm->lock);
	idx = srcu_read_lock(&vcpu->kvm->srcu);

	switch (data->type) {
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
		/* No compat necessary here. */
		BUILD_BUG_ON(sizeof(struct vcpu_info) !=
			     sizeof(struct compat_vcpu_info));
		BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
			     offsetof(struct compat_vcpu_info, time));

		if (data->u.gpa == GPA_INVALID) {
			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
			r = 0;
			break;
		}

		r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache,
				     data->u.gpa, sizeof(struct vcpu_info));
		if (!r)
			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);

		break;

	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
		if (data->u.gpa == GPA_INVALID) {
			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);
			r = 0;
			break;
		}

		r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_time_info_cache,
				     data->u.gpa,
				     sizeof(struct pvclock_vcpu_time_info));
		if (!r)
			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: {
		size_t sz, sz1, sz2;

		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.gpa == GPA_INVALID) {
			r = 0;
		deactivate_out:
			kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache);
			kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache);
			break;
		}

		/*
		 * If the guest switches to 64-bit mode after setting the runstate
		 * address, that's actually OK. kvm_xen_update_runstate_guest()
		 * will cope.
		 */
		if (IS_ENABLED(CONFIG_64BIT) && vcpu->kvm->arch.xen.long_mode)
			sz = sizeof(struct vcpu_runstate_info);
		else
			sz = sizeof(struct compat_vcpu_runstate_info);

		/* How much fits in the (first) page? */
		sz1 = PAGE_SIZE - (data->u.gpa & ~PAGE_MASK);
		r = kvm_gpc_activate(&vcpu->arch.xen.runstate_cache,
				     data->u.gpa, sz1);
		if (r)
			goto deactivate_out;

		/* Either map the second page, or deactivate the second GPC */
		if (sz1 >= sz) {
			kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache);
		} else {
			sz2 = sz - sz1;
			BUG_ON((data->u.gpa + sz1) & ~PAGE_MASK);
			r = kvm_gpc_activate(&vcpu->arch.xen.runstate2_cache,
					     data->u.gpa + sz1, sz2);
			if (r)
				goto deactivate_out;
		}

		kvm_xen_update_runstate_guest(vcpu, false);
		break;
	}
	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline) {
			r = -EINVAL;
			break;
		}

		kvm_xen_update_runstate(vcpu, data->u.runstate.state);
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline) {
			r = -EINVAL;
			break;
		}
		if (data->u.runstate.state_entry_time !=
		    (data->u.runstate.time_running +
		     data->u.runstate.time_runnable +
		     data->u.runstate.time_blocked +
		     data->u.runstate.time_offline)) {
			r = -EINVAL;
			break;
		}
		if (get_kvmclock_ns(vcpu->kvm) <
		    data->u.runstate.state_entry_time) {
			r = -EINVAL;
			break;
		}

		vcpu->arch.xen.current_runstate = data->u.runstate.state;
		vcpu->arch.xen.runstate_entry_time =
			data->u.runstate.state_entry_time;
		vcpu->arch.xen.runstate_times[RUNSTATE_running] =
			data->u.runstate.time_running;
		vcpu->arch.xen.runstate_times[RUNSTATE_runnable] =
			data->u.runstate.time_runnable;
		vcpu->arch.xen.runstate_times[RUNSTATE_blocked] =
			data->u.runstate.time_blocked;
		vcpu->arch.xen.runstate_times[RUNSTATE_offline] =
			data->u.runstate.time_offline;
		vcpu->arch.xen.last_steal = current->sched_info.run_delay;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline &&
		    data->u.runstate.state != (u64)-1) {
			r = -EINVAL;
			break;
		}
		/* The adjustment must add up */
		if (data->u.runstate.state_entry_time !=
		    (data->u.runstate.time_running +
		     data->u.runstate.time_runnable +
		     data->u.runstate.time_blocked +
		     data->u.runstate.time_offline)) {
			r = -EINVAL;
			break;
		}

		if (get_kvmclock_ns(vcpu->kvm) <
		    (vcpu->arch.xen.runstate_entry_time +
		     data->u.runstate.state_entry_time)) {
			r = -EINVAL;
			break;
		}

		vcpu->arch.xen.runstate_entry_time +=
			data->u.runstate.state_entry_time;
		vcpu->arch.xen.runstate_times[RUNSTATE_running] +=
			data->u.runstate.time_running;
		vcpu->arch.xen.runstate_times[RUNSTATE_runnable] +=
			data->u.runstate.time_runnable;
		vcpu->arch.xen.runstate_times[RUNSTATE_blocked] +=
			data->u.runstate.time_blocked;
		vcpu->arch.xen.runstate_times[RUNSTATE_offline] +=
			data->u.runstate.time_offline;

		if (data->u.runstate.state <= RUNSTATE_offline)
			kvm_xen_update_runstate(vcpu, data->u.runstate.state);
		else if (vcpu->arch.xen.runstate_cache.active)
			kvm_xen_update_runstate_guest(vcpu, false);
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID:
		if (data->u.vcpu_id >= KVM_MAX_VCPUS)
			r = -EINVAL;
		else {
			vcpu->arch.xen.vcpu_id = data->u.vcpu_id;
			r = 0;
		}
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_TIMER:
		if (data->u.timer.port &&
		    data->u.timer.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) {
			r = -EINVAL;
			break;
		}

		if (!vcpu->arch.xen.timer.function)
			kvm_xen_init_timer(vcpu);

		/* Stop the timer (if it's running) before changing the vector */
		kvm_xen_stop_timer(vcpu);
		vcpu->arch.xen.timer_virq = data->u.timer.port;

		/* Start the timer if the new value has a valid vector+expiry. */
		if (data->u.timer.port && data->u.timer.expires_ns)
			kvm_xen_start_timer(vcpu, data->u.timer.expires_ns,
					    data->u.timer.expires_ns -
					    get_kvmclock_ns(vcpu->kvm));

		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR:
		if (data->u.vector && data->u.vector < 0x10)
			r = -EINVAL;
		else {
			vcpu->arch.xen.upcall_vector = data->u.vector;
			r = 0;
		}
		break;

	default:
		break;
	}

	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	mutex_unlock(&vcpu->kvm->lock);
	return r;
}

int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
	int r = -ENOENT;

	mutex_lock(&vcpu->kvm->lock);

	switch (data->type) {
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
		if (vcpu->arch.xen.vcpu_info_cache.active)
			data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa;
		else
			data->u.gpa = GPA_INVALID;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
		if (vcpu->arch.xen.vcpu_time_info_cache.active)
			data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;
		else
			data->u.gpa = GPA_INVALID;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (vcpu->arch.xen.runstate_cache.active) {
			data->u.gpa = vcpu->arch.xen.runstate_cache.gpa;
			r = 0;
		}
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		data->u.runstate.state = vcpu->arch.xen.current_runstate;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		data->u.runstate.state = vcpu->arch.xen.current_runstate;
		data->u.runstate.state_entry_time =
			vcpu->arch.xen.runstate_entry_time;
		data->u.runstate.time_running =
			vcpu->arch.xen.runstate_times[RUNSTATE_running];
		data->u.runstate.time_runnable =
			vcpu->arch.xen.runstate_times[RUNSTATE_runnable];
		data->u.runstate.time_blocked =
			vcpu->arch.xen.runstate_times[RUNSTATE_blocked];
		data->u.runstate.time_offline =
			vcpu->arch.xen.runstate_times[RUNSTATE_offline];
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST:
		r = -EINVAL;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID:
		data->u.vcpu_id = vcpu->arch.xen.vcpu_id;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_TIMER:
		data->u.timer.port = vcpu->arch.xen.timer_virq;
		data->u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
		data->u.timer.expires_ns = vcpu->arch.xen.timer_expires;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR:
		data->u.vector = vcpu->arch.xen.upcall_vector;
		r = 0;
		break;

	default:
		break;
	}

	mutex_unlock(&vcpu->kvm->lock);
	return r;
}

int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u32 page_num = data & ~PAGE_MASK;
	u64 page_addr = data & PAGE_MASK;
	bool lm = is_long_mode(vcpu);

	/* Latch long_mode for shared_info pages etc. */
	vcpu->kvm->arch.xen.long_mode = lm;

	/*
	 * If Xen hypercall intercept is enabled, fill the hypercall
	 * page with VMCALL/VMMCALL instructions since that's what
	 * we catch. Else the VMM has provided the hypercall pages
	 * with instructions of its own choosing, so use those.
	 */
	if (kvm_xen_hypercall_enabled(kvm)) {
		u8 instructions[32];
		int i;

		if (page_num)
			return 1;

		/* mov imm32, %eax */
		instructions[0] = 0xb8;

		/* vmcall / vmmcall */
		static_call(kvm_x86_patch_hypercall)(vcpu, instructions + 5);

		/* ret */
		instructions[8] = 0xc3;

		/* int3 to pad */
		memset(instructions + 9, 0xcc, sizeof(instructions) - 9);

		for (i = 0; i < PAGE_SIZE / sizeof(instructions); i++) {
			*(u32 *)&instructions[1] = i;
			if (kvm_vcpu_write_guest(vcpu,
						 page_addr + (i * sizeof(instructions)),
						 instructions, sizeof(instructions)))
				return 1;
		}
	} else {
		/*
		 * Note, truncation is a non-issue as 'lm' is guaranteed to be
		 * false for a 32-bit kernel, i.e. when hva_t is only 4 bytes.
		 */
		hva_t blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64
				     : kvm->arch.xen_hvm_config.blob_addr_32;
		u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
				  : kvm->arch.xen_hvm_config.blob_size_32;
		u8 *page;

		if (page_num >= blob_size)
			return 1;

		blob_addr += page_num * PAGE_SIZE;

		page = memdup_user((u8 __user *)blob_addr, PAGE_SIZE);
		if (IS_ERR(page))
			return PTR_ERR(page);

		if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
			kfree(page);
			return 1;
		}
	}
	return 0;
}

int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
{
	/* Only some feature flags need to be *enabled* by userspace */
	u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
		KVM_XEN_HVM_CONFIG_EVTCHN_SEND;

	if (xhc->flags & ~permitted_flags)
		return -EINVAL;

	/*
	 * With hypercall interception the kernel generates its own
	 * hypercall page so it must not be provided.
	 */
	if ((xhc->flags & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) &&
	    (xhc->blob_addr_32 || xhc->blob_addr_64 ||
	     xhc->blob_size_32 || xhc->blob_size_64))
		return -EINVAL;

	mutex_lock(&kvm->lock);

	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
		static_branch_inc(&kvm_xen_enabled.key);
	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
		static_branch_slow_dec_deferred(&kvm_xen_enabled);

	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));

	mutex_unlock(&kvm->lock);
	return 0;
}

static int kvm_xen_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
{
	kvm_rax_write(vcpu, result);
	return kvm_skip_emulated_instruction(vcpu);
}

static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;

	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.xen.hypercall_rip)))
		return 1;

	return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result);
}

static inline int max_evtchn_port(struct kvm *kvm)
{
	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
		return EVTCHN_2L_NR_CHANNELS;
	else
		return COMPAT_EVTCHN_2L_NR_CHANNELS;
}

static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports,
			       evtchn_port_t *ports)
{
	struct kvm *kvm = vcpu->kvm;
	struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
	unsigned long *pending_bits;
	unsigned long flags;
	bool ret = true;
	int idx, i;

	idx = srcu_read_lock(&kvm->srcu);
	read_lock_irqsave(&gpc->lock, flags);
	if (!kvm_gpc_check(gpc, PAGE_SIZE))
		goto out_rcu;

	ret = false;
	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) {
		struct shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
	} else {
		struct compat_shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
	}

	for (i = 0; i < nr_ports; i++) {
		if (test_bit(ports[i], pending_bits)) {
			ret = true;
			break;
		}
	}

 out_rcu:
	read_unlock_irqrestore(&gpc->lock, flags);
	srcu_read_unlock(&kvm->srcu, idx);

	return ret;
}

static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
				 u64 param, u64 *r)
{
	int idx, i;
	struct sched_poll sched_poll;
	evtchn_port_t port, *ports;
	gpa_t gpa;

	if (!lapic_in_kernel(vcpu) ||
	    !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
		return false;

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	if (!gpa) {
		*r = -EFAULT;
		return true;
	}

	if (IS_ENABLED(CONFIG_64BIT) && !longmode) {
		struct compat_sched_poll sp32;

		/* Sanity check that the compat struct definition is correct */
		BUILD_BUG_ON(sizeof(sp32) != 16);

		if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) {
			*r = -EFAULT;
			return true;
		}

		/*
		 * This is a 32-bit pointer to an array of evtchn_port_t which
		 * are uint32_t, so once it's converted no further compat
		 * handling is needed.
		 */
		sched_poll.ports = (void *)(unsigned long)(sp32.ports);
		sched_poll.nr_ports = sp32.nr_ports;
		sched_poll.timeout = sp32.timeout;
	} else {
		if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll,
					sizeof(sched_poll))) {
			*r = -EFAULT;
			return true;
		}
	}

	if (unlikely(sched_poll.nr_ports > 1)) {
		/* Xen (unofficially) limits number of pollers to 128 */
		if (sched_poll.nr_ports > 128) {
			*r = -EINVAL;
			return true;
		}

		ports = kmalloc_array(sched_poll.nr_ports,
				      sizeof(*ports), GFP_KERNEL);
		if (!ports) {
			*r = -ENOMEM;
			return true;
		}
	} else
		ports = &port;

	for (i = 0; i < sched_poll.nr_ports; i++) {
		idx = srcu_read_lock(&vcpu->kvm->srcu);
		gpa = kvm_mmu_gva_to_gpa_system(vcpu,
						(gva_t)(sched_poll.ports + i),
						NULL);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);

		if (!gpa || kvm_vcpu_read_guest(vcpu, gpa,
						&ports[i], sizeof(port))) {
			*r = -EFAULT;
			goto out;
		}
		if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
			*r = -EINVAL;
			goto out;
		}
	}

	if (sched_poll.nr_ports == 1)
		vcpu->arch.xen.poll_evtchn = port;
	else
		vcpu->arch.xen.poll_evtchn = -1;

	set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.xen.poll_mask);

	if (!wait_pending_event(vcpu, sched_poll.nr_ports, ports)) {
		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;

		if (sched_poll.timeout)
			mod_timer(&vcpu->arch.xen.poll_timer,
				  jiffies + nsecs_to_jiffies(sched_poll.timeout));

		kvm_vcpu_halt(vcpu);

		if (sched_poll.timeout)
			del_timer(&vcpu->arch.xen.poll_timer);

		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
	}

	vcpu->arch.xen.poll_evtchn = 0;
	*r = 0;
out:
	/* Really, this is only needed in case of timeout */
	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.xen.poll_mask);

	if (unlikely(sched_poll.nr_ports > 1))
		kfree(ports);
	return true;
}

static void cancel_evtchn_poll(struct timer_list *t)
{
	struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.xen.poll_timer);

	kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
	kvm_vcpu_kick(vcpu);
}

static bool kvm_xen_hcall_sched_op(struct kvm_vcpu *vcpu, bool longmode,
				   int cmd, u64 param, u64 *r)
{
	switch (cmd) {
	case SCHEDOP_poll:
		if (kvm_xen_schedop_poll(vcpu, longmode, param, r))
			return true;
		fallthrough;
	case SCHEDOP_yield:
		kvm_vcpu_on_spin(vcpu, true);
		*r = 0;
		return true;
	default:
		break;
	}

	return false;
}

struct compat_vcpu_set_singleshot_timer {
    uint64_t timeout_abs_ns;
    uint32_t flags;
} __attribute__((packed));

static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd,
				  int vcpu_id, u64 param, u64 *r)
{
	struct vcpu_set_singleshot_timer oneshot;
	s64 delta;
	gpa_t gpa;
	int idx;

	if (!kvm_xen_timer_enabled(vcpu))
		return false;

	switch (cmd) {
	case VCPUOP_set_singleshot_timer:
		if (vcpu->arch.xen.vcpu_id != vcpu_id) {
			*r = -EINVAL;
			return true;
		}
		idx = srcu_read_lock(&vcpu->kvm->srcu);
		gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
		srcu_read_unlock(&vcpu->kvm->srcu, idx);

		/*
		 * The only difference for 32-bit compat is the 4 bytes of
		 * padding after the interesting part of the structure. So
		 * for a faithful emulation of Xen we have to *try* to copy
		 * the padding and return -EFAULT if we can't. Otherwise we
		 * might as well just have copied the 12-byte 32-bit struct.
		 */
		BUILD_BUG_ON(offsetof(struct compat_vcpu_set_singleshot_timer, timeout_abs_ns) !=
			     offsetof(struct vcpu_set_singleshot_timer, timeout_abs_ns));
		BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, timeout_abs_ns) !=
			     sizeof_field(struct vcpu_set_singleshot_timer, timeout_abs_ns));
		BUILD_BUG_ON(offsetof(struct compat_vcpu_set_singleshot_timer, flags) !=
			     offsetof(struct vcpu_set_singleshot_timer, flags));
		BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) !=
			     sizeof_field(struct vcpu_set_singleshot_timer, flags));

		if (!gpa ||
		    kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) :
					sizeof(struct compat_vcpu_set_singleshot_timer))) {
			*r = -EFAULT;
			return true;
		}

		delta = oneshot.timeout_abs_ns - get_kvmclock_ns(vcpu->kvm);
		if ((oneshot.flags & VCPU_SSHOTTMR_future) && delta < 0) {
			*r = -ETIME;
			return true;
		}

		kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta);
		*r = 0;
		return true;

	case VCPUOP_stop_singleshot_timer:
		if (vcpu->arch.xen.vcpu_id != vcpu_id) {
			*r = -EINVAL;
			return true;
		}
		kvm_xen_stop_timer(vcpu);
		*r = 0;
		return true;
	}

	return false;
}

static bool kvm_xen_hcall_set_timer_op(struct kvm_vcpu *vcpu, uint64_t timeout,
				       u64 *r)
{
	if (!kvm_xen_timer_enabled(vcpu))
		return false;

	if (timeout) {
		uint64_t guest_now = get_kvmclock_ns(vcpu->kvm);
		int64_t delta = timeout - guest_now;

		/* Xen has a 'Linux workaround' in do_set_timer_op() which
		 * checks for negative absolute timeout values (caused by
		 * integer overflow), and for values about 13 days in the
		 * future (2^50ns) which would be caused by jiffies
		 * overflow. For those cases, it sets the timeout 100ms in
		 * the future (not *too* soon, since if a guest really did
		 * set a long timeout on purpose we don't want to keep
		 * churning CPU time by waking it up).
		 */
		if (unlikely((int64_t)timeout < 0 ||
			     (delta > 0 && (uint32_t) (delta >> 50) != 0))) {
			delta = 100 * NSEC_PER_MSEC;
			timeout = guest_now + delta;
		}

		kvm_xen_start_timer(vcpu, timeout, delta);
	} else {
		kvm_xen_stop_timer(vcpu);
	}

	*r = 0;
	return true;
}

int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
{
	bool longmode;
	u64 input, params[6], r = -ENOSYS;
	bool handled = false;
	u8 cpl;

	input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX);

	/* Hyper-V hypercalls get bit 31 set in EAX */
	if ((input & 0x80000000) &&
	    kvm_hv_hypercall_enabled(vcpu))
		return kvm_hv_hypercall(vcpu);

	longmode = is_64_bit_hypercall(vcpu);
	if (!longmode) {
		params[0] = (u32)kvm_rbx_read(vcpu);
		params[1] = (u32)kvm_rcx_read(vcpu);
		params[2] = (u32)kvm_rdx_read(vcpu);
		params[3] = (u32)kvm_rsi_read(vcpu);
		params[4] = (u32)kvm_rdi_read(vcpu);
		params[5] = (u32)kvm_rbp_read(vcpu);
	}
#ifdef CONFIG_X86_64
	else {
		params[0] = (u64)kvm_rdi_read(vcpu);
		params[1] = (u64)kvm_rsi_read(vcpu);
		params[2] = (u64)kvm_rdx_read(vcpu);
		params[3] = (u64)kvm_r10_read(vcpu);
		params[4] = (u64)kvm_r8_read(vcpu);
		params[5] = (u64)kvm_r9_read(vcpu);
	}
#endif
	cpl = static_call(kvm_x86_get_cpl)(vcpu);
	trace_kvm_xen_hypercall(cpl, input, params[0], params[1], params[2],
				params[3], params[4], params[5]);

	/*
	 * Only allow hypercall acceleration for CPL0. The rare hypercalls that
	 * are permitted in guest userspace can be handled by the VMM.
	 */
	if (unlikely(cpl > 0))
		goto handle_in_userspace;

	switch (input) {
	case __HYPERVISOR_xen_version:
		if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) {
			r = vcpu->kvm->arch.xen.xen_version;
			handled = true;
		}
		break;
	case __HYPERVISOR_event_channel_op:
		if (params[0] == EVTCHNOP_send)
			handled = kvm_xen_hcall_evtchn_send(vcpu, params[1], &r);
		break;
	case __HYPERVISOR_sched_op:
		handled = kvm_xen_hcall_sched_op(vcpu, longmode, params[0],
						 params[1], &r);
		break;
	case __HYPERVISOR_vcpu_op:
		handled = kvm_xen_hcall_vcpu_op(vcpu, longmode, params[0], params[1],
						params[2], &r);
		break;
	case __HYPERVISOR_set_timer_op: {
		u64 timeout = params[0];
		/* In 32-bit mode, the 64-bit timeout is in two 32-bit params. */
		if (!longmode)
			timeout |= params[1] << 32;
		handled = kvm_xen_hcall_set_timer_op(vcpu, timeout, &r);
		break;
	}
	default:
		break;
	}

	if (handled)
		return kvm_xen_hypercall_set_result(vcpu, r);

handle_in_userspace:
	vcpu->run->exit_reason = KVM_EXIT_XEN;
	vcpu->run->xen.type = KVM_EXIT_XEN_HCALL;
	vcpu->run->xen.u.hcall.longmode = longmode;
	vcpu->run->xen.u.hcall.cpl = cpl;
	vcpu->run->xen.u.hcall.input = input;
	vcpu->run->xen.u.hcall.params[0] = params[0];
	vcpu->run->xen.u.hcall.params[1] = params[1];
	vcpu->run->xen.u.hcall.params[2] = params[2];
	vcpu->run->xen.u.hcall.params[3] = params[3];
	vcpu->run->xen.u.hcall.params[4] = params[4];
	vcpu->run->xen.u.hcall.params[5] = params[5];
	vcpu->arch.xen.hypercall_rip = kvm_get_linear_rip(vcpu);
	vcpu->arch.complete_userspace_io =
		kvm_xen_hypercall_complete_userspace;

	return 0;
}

static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port)
{
	int poll_evtchn = vcpu->arch.xen.poll_evtchn;

	if ((poll_evtchn == port || poll_evtchn == -1) &&
	    test_and_clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.xen.poll_mask)) {
		kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
		kvm_vcpu_kick(vcpu);
	}
}

/*
 * The return value from this function is propagated to kvm_set_irq() API,
 * so it returns:
 *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
 *  = 0   Interrupt was coalesced (previous irq is still pending)
 *  > 0   Number of CPUs interrupt was delivered to
 *
 * It is also called directly from kvm_arch_set_irq_inatomic(), where the
 * only check on its return value is a comparison with -EWOULDBLOCK'.
 */
int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm)
{
	struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
	struct kvm_vcpu *vcpu;
	unsigned long *pending_bits, *mask_bits;
	unsigned long flags;
	int port_word_bit;
	bool kick_vcpu = false;
	int vcpu_idx, idx, rc;

	vcpu_idx = READ_ONCE(xe->vcpu_idx);
	if (vcpu_idx >= 0)
		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
	else {
		vcpu = kvm_get_vcpu_by_id(kvm, xe->vcpu_id);
		if (!vcpu)
			return -EINVAL;
		WRITE_ONCE(xe->vcpu_idx, vcpu->vcpu_idx);
	}

	if (!vcpu->arch.xen.vcpu_info_cache.active)
		return -EINVAL;

	if (xe->port >= max_evtchn_port(kvm))
		return -EINVAL;

	rc = -EWOULDBLOCK;

	idx = srcu_read_lock(&kvm->srcu);

	read_lock_irqsave(&gpc->lock, flags);
	if (!kvm_gpc_check(gpc, PAGE_SIZE))
		goto out_rcu;

	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) {
		struct shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
		port_word_bit = xe->port / 64;
	} else {
		struct compat_shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
		port_word_bit = xe->port / 32;
	}

	/*
	 * If this port wasn't already set, and if it isn't masked, then
	 * we try to set the corresponding bit in the in-kernel shadow of
	 * evtchn_pending_sel for the target vCPU. And if *that* wasn't
	 * already set, then we kick the vCPU in question to write to the
	 * *real* evtchn_pending_sel in its own guest vcpu_info struct.
	 */
	if (test_and_set_bit(xe->port, pending_bits)) {
		rc = 0; /* It was already raised */
	} else if (test_bit(xe->port, mask_bits)) {
		rc = -ENOTCONN; /* Masked */
		kvm_xen_check_poller(vcpu, xe->port);
	} else {
		rc = 1; /* Delivered to the bitmap in shared_info. */
		/* Now switch to the vCPU's vcpu_info to set the index and pending_sel */
		read_unlock_irqrestore(&gpc->lock, flags);
		gpc = &vcpu->arch.xen.vcpu_info_cache;

		read_lock_irqsave(&gpc->lock, flags);
		if (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) {
			/*
			 * Could not access the vcpu_info. Set the bit in-kernel
			 * and prod the vCPU to deliver it for itself.
			 */
			if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel))
				kick_vcpu = true;
			goto out_rcu;
		}

		if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) {
			struct vcpu_info *vcpu_info = gpc->khva;
			if (!test_and_set_bit(port_word_bit, &vcpu_info->evtchn_pending_sel)) {
				WRITE_ONCE(vcpu_info->evtchn_upcall_pending, 1);
				kick_vcpu = true;
			}
		} else {
			struct compat_vcpu_info *vcpu_info = gpc->khva;
			if (!test_and_set_bit(port_word_bit,
					      (unsigned long *)&vcpu_info->evtchn_pending_sel)) {
				WRITE_ONCE(vcpu_info->evtchn_upcall_pending, 1);
				kick_vcpu = true;
			}
		}

		/* For the per-vCPU lapic vector, deliver it as MSI. */
		if (kick_vcpu && vcpu->arch.xen.upcall_vector) {
			kvm_xen_inject_vcpu_vector(vcpu);
			kick_vcpu = false;
		}
	}

 out_rcu:
	read_unlock_irqrestore(&gpc->lock, flags);
	srcu_read_unlock(&kvm->srcu, idx);

	if (kick_vcpu) {
		kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
		kvm_vcpu_kick(vcpu);
	}

	return rc;
}

static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
{
	bool mm_borrowed = false;
	int rc;

	rc = kvm_xen_set_evtchn_fast(xe, kvm);
	if (rc != -EWOULDBLOCK)
		return rc;

	if (current->mm != kvm->mm) {
		/*
		 * If not on a thread which already belongs to this KVM,
		 * we'd better be in the irqfd workqueue.
		 */
		if (WARN_ON_ONCE(current->mm))
			return -EINVAL;

		kthread_use_mm(kvm->mm);
		mm_borrowed = true;
	}

	/*
	 * For the irqfd workqueue, using the main kvm->lock mutex is
	 * fine since this function is invoked from kvm_set_irq() with
	 * no other lock held, no srcu. In future if it will be called
	 * directly from a vCPU thread (e.g. on hypercall for an IPI)
	 * then it may need to switch to using a leaf-node mutex for
	 * serializing the shared_info mapping.
	 */
	mutex_lock(&kvm->lock);

	/*
	 * It is theoretically possible for the page to be unmapped
	 * and the MMU notifier to invalidate the shared_info before
	 * we even get to use it. In that case, this looks like an
	 * infinite loop. It was tempting to do it via the userspace
	 * HVA instead... but that just *hides* the fact that it's
	 * an infinite loop, because if a fault occurs and it waits
	 * for the page to come back, it can *still* immediately
	 * fault and have to wait again, repeatedly.
	 *
	 * Conversely, the page could also have been reinstated by
	 * another thread before we even obtain the mutex above, so
	 * check again *first* before remapping it.
	 */
	do {
		struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
		int idx;

		rc = kvm_xen_set_evtchn_fast(xe, kvm);
		if (rc != -EWOULDBLOCK)
			break;

		idx = srcu_read_lock(&kvm->srcu);
		rc = kvm_gpc_refresh(gpc, PAGE_SIZE);
		srcu_read_unlock(&kvm->srcu, idx);
	} while(!rc);

	mutex_unlock(&kvm->lock);

	if (mm_borrowed)
		kthread_unuse_mm(kvm->mm);

	return rc;
}

/* This is the version called from kvm_set_irq() as the .set function */
static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
			 int irq_source_id, int level, bool line_status)
{
	if (!level)
		return -EINVAL;

	return kvm_xen_set_evtchn(&e->xen_evtchn, kvm);
}

/*
 * Set up an event channel interrupt from the KVM IRQ routing table.
 * Used for e.g. PIRQ from passed through physical devices.
 */
int kvm_xen_setup_evtchn(struct kvm *kvm,
			 struct kvm_kernel_irq_routing_entry *e,
			 const struct kvm_irq_routing_entry *ue)

{
	struct kvm_vcpu *vcpu;

	if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
		return -EINVAL;

	/* We only support 2 level event channels for now */
	if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
		return -EINVAL;

	/*
	 * Xen gives us interesting mappings from vCPU index to APIC ID,
	 * which means kvm_get_vcpu_by_id() has to iterate over all vCPUs
	 * to find it. Do that once at setup time, instead of every time.
	 * But beware that on live update / live migration, the routing
	 * table might be reinstated before the vCPU threads have finished
	 * recreating their vCPUs.
	 */
	vcpu = kvm_get_vcpu_by_id(kvm, ue->u.xen_evtchn.vcpu);
	if (vcpu)
		e->xen_evtchn.vcpu_idx = vcpu->vcpu_idx;
	else
		e->xen_evtchn.vcpu_idx = -1;

	e->xen_evtchn.port = ue->u.xen_evtchn.port;
	e->xen_evtchn.vcpu_id = ue->u.xen_evtchn.vcpu;
	e->xen_evtchn.priority = ue->u.xen_evtchn.priority;
	e->set = evtchn_set_fn;

	return 0;
}

/*
 * Explicit event sending from userspace with KVM_XEN_HVM_EVTCHN_SEND ioctl.
 */
int kvm_xen_hvm_evtchn_send(struct kvm *kvm, struct kvm_irq_routing_xen_evtchn *uxe)
{
	struct kvm_xen_evtchn e;
	int ret;

	if (!uxe->port || uxe->port >= max_evtchn_port(kvm))
		return -EINVAL;

	/* We only support 2 level event channels for now */
	if (uxe->priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
		return -EINVAL;

	e.port = uxe->port;
	e.vcpu_id = uxe->vcpu;
	e.vcpu_idx = -1;
	e.priority = uxe->priority;

	ret = kvm_xen_set_evtchn(&e, kvm);

	/*
	 * None of that 'return 1 if it actually got delivered' nonsense.
	 * We don't care if it was masked (-ENOTCONN) either.
	 */
	if (ret > 0 || ret == -ENOTCONN)
		ret = 0;

	return ret;
}

/*
 * Support for *outbound* event channel events via the EVTCHNOP_send hypercall.
 */
struct evtchnfd {
	u32 send_port;
	u32 type;
	union {
		struct kvm_xen_evtchn port;
		struct {
			u32 port; /* zero */
			struct eventfd_ctx *ctx;
		} eventfd;
	} deliver;
};

/*
 * Update target vCPU or priority for a registered sending channel.
 */
static int kvm_xen_eventfd_update(struct kvm *kvm,
				  struct kvm_xen_hvm_attr *data)
{
	u32 port = data->u.evtchn.send_port;
	struct evtchnfd *evtchnfd;

	if (!port || port >= max_evtchn_port(kvm))
		return -EINVAL;

	mutex_lock(&kvm->lock);
	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
	mutex_unlock(&kvm->lock);

	if (!evtchnfd)
		return -ENOENT;

	/* For an UPDATE, nothing may change except the priority/vcpu */
	if (evtchnfd->type != data->u.evtchn.type)
		return -EINVAL;

	/*
	 * Port cannot change, and if it's zero that was an eventfd
	 * which can't be changed either.
	 */
	if (!evtchnfd->deliver.port.port ||
	    evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port)
		return -EINVAL;

	/* We only support 2 level event channels for now */
	if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
		return -EINVAL;

	mutex_lock(&kvm->lock);
	evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
	if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) {
		evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu;
		evtchnfd->deliver.port.vcpu_idx = -1;
	}
	mutex_unlock(&kvm->lock);
	return 0;
}

/*
 * Configure the target (eventfd or local port delivery) for sending on
 * a given event channel.
 */
static int kvm_xen_eventfd_assign(struct kvm *kvm,
				  struct kvm_xen_hvm_attr *data)
{
	u32 port = data->u.evtchn.send_port;
	struct eventfd_ctx *eventfd = NULL;
	struct evtchnfd *evtchnfd = NULL;
	int ret = -EINVAL;

	if (!port || port >= max_evtchn_port(kvm))
		return -EINVAL;

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

	switch(data->u.evtchn.type) {
	case EVTCHNSTAT_ipi:
		/* IPI  must map back to the same port# */
		if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port)
			goto out_noeventfd; /* -EINVAL */
		break;

	case EVTCHNSTAT_interdomain:
		if (data->u.evtchn.deliver.port.port) {
			if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm))
				goto out_noeventfd; /* -EINVAL */
		} else {
			eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd);
			if (IS_ERR(eventfd)) {
				ret = PTR_ERR(eventfd);
				goto out_noeventfd;
			}
		}
		break;

	case EVTCHNSTAT_virq:
	case EVTCHNSTAT_closed:
	case EVTCHNSTAT_unbound:
	case EVTCHNSTAT_pirq:
	default: /* Unknown event channel type */
		goto out; /* -EINVAL */
	}

	evtchnfd->send_port = data->u.evtchn.send_port;
	evtchnfd->type = data->u.evtchn.type;
	if (eventfd) {
		evtchnfd->deliver.eventfd.ctx = eventfd;
	} else {
		/* We only support 2 level event channels for now */
		if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
			goto out; /* -EINVAL; */

		evtchnfd->deliver.port.port = data->u.evtchn.deliver.port.port;
		evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu;
		evtchnfd->deliver.port.vcpu_idx = -1;
		evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
	}

	mutex_lock(&kvm->lock);
	ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
			GFP_KERNEL);
	mutex_unlock(&kvm->lock);
	if (ret >= 0)
		return 0;

	if (ret == -ENOSPC)
		ret = -EEXIST;
out:
	if (eventfd)
		eventfd_ctx_put(eventfd);
out_noeventfd:
	kfree(evtchnfd);
	return ret;
}

static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port)
{
	struct evtchnfd *evtchnfd;

	mutex_lock(&kvm->lock);
	evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
	mutex_unlock(&kvm->lock);

	if (!evtchnfd)
		return -ENOENT;

	if (kvm)
		synchronize_srcu(&kvm->srcu);
	if (!evtchnfd->deliver.port.port)
		eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
	kfree(evtchnfd);
	return 0;
}

static int kvm_xen_eventfd_reset(struct kvm *kvm)
{
	struct evtchnfd *evtchnfd;
	int i;

	mutex_lock(&kvm->lock);
	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
		synchronize_srcu(&kvm->srcu);
		if (!evtchnfd->deliver.port.port)
			eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
		kfree(evtchnfd);
	}
	mutex_unlock(&kvm->lock);

	return 0;
}

static int kvm_xen_setattr_evtchn(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
	u32 port = data->u.evtchn.send_port;

	if (data->u.evtchn.flags == KVM_XEN_EVTCHN_RESET)
		return kvm_xen_eventfd_reset(kvm);

	if (!port || port >= max_evtchn_port(kvm))
		return -EINVAL;

	if (data->u.evtchn.flags == KVM_XEN_EVTCHN_DEASSIGN)
		return kvm_xen_eventfd_deassign(kvm, port);
	if (data->u.evtchn.flags == KVM_XEN_EVTCHN_UPDATE)
		return kvm_xen_eventfd_update(kvm, data);
	if (data->u.evtchn.flags)
		return -EINVAL;

	return kvm_xen_eventfd_assign(kvm, data);
}

static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r)
{
	struct evtchnfd *evtchnfd;
	struct evtchn_send send;
	gpa_t gpa;
	int idx;

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
	srcu_read_unlock(&vcpu->kvm->srcu, idx);

	if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) {
		*r = -EFAULT;
		return true;
	}

	/* The evtchn_ports idr is protected by vcpu->kvm->srcu */
	evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port);
	if (!evtchnfd)
		return false;

	if (evtchnfd->deliver.port.port) {
		int ret = kvm_xen_set_evtchn(&evtchnfd->deliver.port, vcpu->kvm);
		if (ret < 0 && ret != -ENOTCONN)
			return false;
	} else {
		eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1);
	}

	*r = 0;
	return true;
}

void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
{
	vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx;
	vcpu->arch.xen.poll_evtchn = 0;

	timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0);

	kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm, NULL,
		     KVM_HOST_USES_PFN);
	kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm, NULL,
		     KVM_HOST_USES_PFN);
	kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm, NULL,
		     KVM_HOST_USES_PFN);
	kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm, NULL,
		     KVM_HOST_USES_PFN);
}

void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
{
	if (kvm_xen_timer_enabled(vcpu))
		kvm_xen_stop_timer(vcpu);

	kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache);
	kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache);
	kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
	kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);

	del_timer_sync(&vcpu->arch.xen.poll_timer);
}

void kvm_xen_init_vm(struct kvm *kvm)
{
	idr_init(&kvm->arch.xen.evtchn_ports);
	kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
}

void kvm_xen_destroy_vm(struct kvm *kvm)
{
	struct evtchnfd *evtchnfd;
	int i;

	kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache);

	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
		if (!evtchnfd->deliver.port.port)
			eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
		kfree(evtchnfd);
	}
	idr_destroy(&kvm->arch.xen.evtchn_ports);

	if (kvm->arch.xen_hvm_config.msr)
		static_branch_slow_dec_deferred(&kvm_xen_enabled);
}