summaryrefslogtreecommitdiff
path: root/arch/x86/xen/enlighten.c
blob: 30d12afe52ed173b2a81720cd5c89c24e667de2a (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
/*
 * Core of Xen paravirt_ops implementation.
 *
 * This file contains the xen_paravirt_ops structure itself, and the
 * implementations for:
 * - privileged instructions
 * - interrupt flags
 * - segment operations
 * - booting and setup
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/preempt.h>
#include <linux/hardirq.h>
#include <linux/percpu.h>
#include <linux/delay.h>
#include <linux/start_kernel.h>
#include <linux/sched.h>
#include <linux/kprobes.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/highmem.h>
#include <linux/console.h>
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/edd.h>

#include <xen/xen.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/version.h>
#include <xen/interface/physdev.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/memory.h>
#include <xen/interface/nmi.h>
#include <xen/interface/xen-mca.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/hvm.h>
#include <xen/hvc-console.h>
#include <xen/acpi.h>

#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/page.h>
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/msr-index.h>
#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
#include <asm/stackprotector.h>
#include <asm/hypervisor.h>
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
#include <asm/pat.h>

#ifdef CONFIG_ACPI
#include <linux/acpi.h>
#include <asm/acpi.h>
#include <acpi/pdc_intel.h>
#include <acpi/processor.h>
#include <xen/interface/platform.h>
#endif

#include "xen-ops.h"
#include "mmu.h"
#include "smp.h"
#include "multicalls.h"
#include "pmu.h"

EXPORT_SYMBOL_GPL(hypercall_page);

/*
 * Pointer to the xen_vcpu_info structure or
 * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
 * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
 * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point
 * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to
 * acknowledge pending events.
 * Also more subtly it is used by the patched version of irq enable/disable
 * e.g. xen_irq_enable_direct and xen_iret in PV mode.
 *
 * The desire to be able to do those mask/unmask operations as a single
 * instruction by using the per-cpu offset held in %gs is the real reason
 * vcpu info is in a per-cpu pointer and the original reason for this
 * hypercall.
 *
 */
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);

/*
 * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info
 * hypercall. This can be used both in PV and PVHVM mode. The structure
 * overrides the default per_cpu(xen_vcpu, cpu) value.
 */
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);

enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);

unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
EXPORT_SYMBOL(machine_to_phys_mapping);
unsigned long  machine_to_phys_nr;
EXPORT_SYMBOL(machine_to_phys_nr);

struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);

struct shared_info xen_dummy_shared_info;

void *xen_initial_gdt;

RESERVE_BRK(shared_info_page_brk, PAGE_SIZE);
__read_mostly int xen_have_vector_callback;
EXPORT_SYMBOL_GPL(xen_have_vector_callback);

/*
 * Point at some empty memory to start with. We map the real shared_info
 * page as soon as fixmap is up and running.
 */
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;

/*
 * Flag to determine whether vcpu info placement is available on all
 * VCPUs.  We assume it is to start with, and then set it to zero on
 * the first failure.  This is because it can succeed on some VCPUs
 * and not others, since it can involve hypervisor memory allocation,
 * or because the guest failed to guarantee all the appropriate
 * constraints on all VCPUs (ie buffer can't cross a page boundary).
 *
 * Note that any particular CPU may be using a placed vcpu structure,
 * but we can only optimise if the all are.
 *
 * 0: not available, 1: available
 */
static int have_vcpu_info_placement = 1;

struct tls_descs {
	struct desc_struct desc[3];
};

/*
 * Updating the 3 TLS descriptors in the GDT on every task switch is
 * surprisingly expensive so we avoid updating them if they haven't
 * changed.  Since Xen writes different descriptors than the one
 * passed in the update_descriptor hypercall we keep shadow copies to
 * compare against.
 */
static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);

static void clamp_max_cpus(void)
{
#ifdef CONFIG_SMP
	if (setup_max_cpus > MAX_VIRT_CPUS)
		setup_max_cpus = MAX_VIRT_CPUS;
#endif
}

static void xen_vcpu_setup(int cpu)
{
	struct vcpu_register_vcpu_info info;
	int err;
	struct vcpu_info *vcpup;

	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);

	/*
	 * This path is called twice on PVHVM - first during bootup via
	 * smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being
	 * hotplugged: cpu_up -> xen_hvm_cpu_notify.
	 * As we can only do the VCPUOP_register_vcpu_info once lets
	 * not over-write its result.
	 *
	 * For PV it is called during restore (xen_vcpu_restore) and bootup
	 * (xen_setup_vcpu_info_placement). The hotplug mechanism does not
	 * use this function.
	 */
	if (xen_hvm_domain()) {
		if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
			return;
	}
	if (cpu < MAX_VIRT_CPUS)
		per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];

	if (!have_vcpu_info_placement) {
		if (cpu >= MAX_VIRT_CPUS)
			clamp_max_cpus();
		return;
	}

	vcpup = &per_cpu(xen_vcpu_info, cpu);
	info.mfn = arbitrary_virt_to_mfn(vcpup);
	info.offset = offset_in_page(vcpup);

	/* Check to see if the hypervisor will put the vcpu_info
	   structure where we want it, which allows direct access via
	   a percpu-variable.
	   N.B. This hypercall can _only_ be called once per CPU. Subsequent
	   calls will error out with -EINVAL. This is due to the fact that
	   hypervisor has no unregister variant and this hypercall does not
	   allow to over-write info.mfn and info.offset.
	 */
	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);

	if (err) {
		printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
		have_vcpu_info_placement = 0;
		clamp_max_cpus();
	} else {
		/* This cpu is using the registered vcpu info, even if
		   later ones fail to. */
		per_cpu(xen_vcpu, cpu) = vcpup;
	}
}

/*
 * On restore, set the vcpu placement up again.
 * If it fails, then we're in a bad state, since
 * we can't back out from using it...
 */
void xen_vcpu_restore(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		bool other_cpu = (cpu != smp_processor_id());
		bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL);

		if (other_cpu && is_up &&
		    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
			BUG();

		xen_setup_runstate_info(cpu);

		if (have_vcpu_info_placement)
			xen_vcpu_setup(cpu);

		if (other_cpu && is_up &&
		    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
			BUG();
	}
}

static void __init xen_banner(void)
{
	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
	struct xen_extraversion extra;
	HYPERVISOR_xen_version(XENVER_extraversion, &extra);

	pr_info("Booting paravirtualized kernel %son %s\n",
		xen_feature(XENFEAT_auto_translated_physmap) ?
			"with PVH extensions " : "", pv_info.name);
	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
	       version >> 16, version & 0xffff, extra.extraversion,
	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
/* Check if running on Xen version (major, minor) or later */
bool
xen_running_on_version_or_later(unsigned int major, unsigned int minor)
{
	unsigned int version;

	if (!xen_domain())
		return false;

	version = HYPERVISOR_xen_version(XENVER_version, NULL);
	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
		((version >> 16) > major))
		return true;
	return false;
}

#define CPUID_THERM_POWER_LEAF 6
#define APERFMPERF_PRESENT 0

static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;

static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask;
static __read_mostly unsigned int cpuid_leaf5_ecx_val;
static __read_mostly unsigned int cpuid_leaf5_edx_val;

static void xen_cpuid(unsigned int *ax, unsigned int *bx,
		      unsigned int *cx, unsigned int *dx)
{
	unsigned maskebx = ~0;
	unsigned maskecx = ~0;
	unsigned maskedx = ~0;
	unsigned setecx = 0;
	/*
	 * Mask out inconvenient features, to try and disable as many
	 * unsupported kernel subsystems as possible.
	 */
	switch (*ax) {
	case 1:
		maskecx = cpuid_leaf1_ecx_mask;
		setecx = cpuid_leaf1_ecx_set_mask;
		maskedx = cpuid_leaf1_edx_mask;
		break;

	case CPUID_MWAIT_LEAF:
		/* Synthesize the values.. */
		*ax = 0;
		*bx = 0;
		*cx = cpuid_leaf5_ecx_val;
		*dx = cpuid_leaf5_edx_val;
		return;

	case CPUID_THERM_POWER_LEAF:
		/* Disabling APERFMPERF for kernel usage */
		maskecx = ~(1 << APERFMPERF_PRESENT);
		break;

	case 0xb:
		/* Suppress extended topology stuff */
		maskebx = 0;
		break;
	}

	asm(XEN_EMULATE_PREFIX "cpuid"
		: "=a" (*ax),
		  "=b" (*bx),
		  "=c" (*cx),
		  "=d" (*dx)
		: "0" (*ax), "2" (*cx));

	*bx &= maskebx;
	*cx &= maskecx;
	*cx |= setecx;
	*dx &= maskedx;

}

static bool __init xen_check_mwait(void)
{
#ifdef CONFIG_ACPI
	struct xen_platform_op op = {
		.cmd			= XENPF_set_processor_pminfo,
		.u.set_pminfo.id	= -1,
		.u.set_pminfo.type	= XEN_PM_PDC,
	};
	uint32_t buf[3];
	unsigned int ax, bx, cx, dx;
	unsigned int mwait_mask;

	/* We need to determine whether it is OK to expose the MWAIT
	 * capability to the kernel to harvest deeper than C3 states from ACPI
	 * _CST using the processor_harvest_xen.c module. For this to work, we
	 * need to gather the MWAIT_LEAF values (which the cstate.c code
	 * checks against). The hypervisor won't expose the MWAIT flag because
	 * it would break backwards compatibility; so we will find out directly
	 * from the hardware and hypercall.
	 */
	if (!xen_initial_domain())
		return false;

	/*
	 * When running under platform earlier than Xen4.2, do not expose
	 * mwait, to avoid the risk of loading native acpi pad driver
	 */
	if (!xen_running_on_version_or_later(4, 2))
		return false;

	ax = 1;
	cx = 0;

	native_cpuid(&ax, &bx, &cx, &dx);

	mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
		     (1 << (X86_FEATURE_MWAIT % 32));

	if ((cx & mwait_mask) != mwait_mask)
		return false;

	/* We need to emulate the MWAIT_LEAF and for that we need both
	 * ecx and edx. The hypercall provides only partial information.
	 */

	ax = CPUID_MWAIT_LEAF;
	bx = 0;
	cx = 0;
	dx = 0;

	native_cpuid(&ax, &bx, &cx, &dx);

	/* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
	 * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
	 */
	buf[0] = ACPI_PDC_REVISION_ID;
	buf[1] = 1;
	buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);

	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);

	if ((HYPERVISOR_dom0_op(&op) == 0) &&
	    (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
		cpuid_leaf5_ecx_val = cx;
		cpuid_leaf5_edx_val = dx;
	}
	return true;
#else
	return false;
#endif
}
static void __init xen_init_cpuid_mask(void)
{
	unsigned int ax, bx, cx, dx;
	unsigned int xsave_mask;

	cpuid_leaf1_edx_mask =
		~((1 << X86_FEATURE_MTRR) |  /* disable MTRR */
		  (1 << X86_FEATURE_ACC));   /* thermal monitoring */

	if (!xen_initial_domain())
		cpuid_leaf1_edx_mask &=
			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */

	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));

	ax = 1;
	cx = 0;
	cpuid(1, &ax, &bx, &cx, &dx);

	xsave_mask =
		(1 << (X86_FEATURE_XSAVE % 32)) |
		(1 << (X86_FEATURE_OSXSAVE % 32));

	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
	if ((cx & xsave_mask) != xsave_mask)
		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
	if (xen_check_mwait())
		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
}

static void xen_set_debugreg(int reg, unsigned long val)
{
	HYPERVISOR_set_debugreg(reg, val);
}

static unsigned long xen_get_debugreg(int reg)
{
	return HYPERVISOR_get_debugreg(reg);
}

static void xen_end_context_switch(struct task_struct *next)
{
	xen_mc_flush();
	paravirt_end_context_switch(next);
}

static unsigned long xen_store_tr(void)
{
	return 0;
}

/*
 * Set the page permissions for a particular virtual address.  If the
 * address is a vmalloc mapping (or other non-linear mapping), then
 * find the linear mapping of the page and also set its protections to
 * match.
 */
static void set_aliased_prot(void *v, pgprot_t prot)
{
	int level;
	pte_t *ptep;
	pte_t pte;
	unsigned long pfn;
	struct page *page;
	unsigned char dummy;

	ptep = lookup_address((unsigned long)v, &level);
	BUG_ON(ptep == NULL);

	pfn = pte_pfn(*ptep);
	page = pfn_to_page(pfn);

	pte = pfn_pte(pfn, prot);

	/*
	 * Careful: update_va_mapping() will fail if the virtual address
	 * we're poking isn't populated in the page tables.  We don't
	 * need to worry about the direct map (that's always in the page
	 * tables), but we need to be careful about vmap space.  In
	 * particular, the top level page table can lazily propagate
	 * entries between processes, so if we've switched mms since we
	 * vmapped the target in the first place, we might not have the
	 * top-level page table entry populated.
	 *
	 * We disable preemption because we want the same mm active when
	 * we probe the target and when we issue the hypercall.  We'll
	 * have the same nominal mm, but if we're a kernel thread, lazy
	 * mm dropping could change our pgd.
	 *
	 * Out of an abundance of caution, this uses __get_user() to fault
	 * in the target address just in case there's some obscure case
	 * in which the target address isn't readable.
	 */

	preempt_disable();

	pagefault_disable();	/* Avoid warnings due to being atomic. */
	__get_user(dummy, (unsigned char __user __force *)v);
	pagefault_enable();

	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
		BUG();

	if (!PageHighMem(page)) {
		void *av = __va(PFN_PHYS(pfn));

		if (av != v)
			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
				BUG();
	} else
		kmap_flush_unused();

	preempt_enable();
}

static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
	int i;

	/*
	 * We need to mark the all aliases of the LDT pages RO.  We
	 * don't need to call vm_flush_aliases(), though, since that's
	 * only responsible for flushing aliases out the TLBs, not the
	 * page tables, and Xen will flush the TLB for us if needed.
	 *
	 * To avoid confusing future readers: none of this is necessary
	 * to load the LDT.  The hypervisor only checks this when the
	 * LDT is faulted in due to subsequent descriptor access.
	 */

	for(i = 0; i < entries; i += entries_per_page)
		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
}

static void xen_free_ldt(struct desc_struct *ldt, unsigned entries)
{
	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
	int i;

	for(i = 0; i < entries; i += entries_per_page)
		set_aliased_prot(ldt + i, PAGE_KERNEL);
}

static void xen_set_ldt(const void *addr, unsigned entries)
{
	struct mmuext_op *op;
	struct multicall_space mcs = xen_mc_entry(sizeof(*op));

	trace_xen_cpu_set_ldt(addr, entries);

	op = mcs.args;
	op->cmd = MMUEXT_SET_LDT;
	op->arg1.linear_addr = (unsigned long)addr;
	op->arg2.nr_ents = entries;

	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static void xen_load_gdt(const struct desc_ptr *dtr)
{
	unsigned long va = dtr->address;
	unsigned int size = dtr->size + 1;
	unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
	unsigned long frames[pages];
	int f;

	/*
	 * A GDT can be up to 64k in size, which corresponds to 8192
	 * 8-byte entries, or 16 4k pages..
	 */

	BUG_ON(size > 65536);
	BUG_ON(va & ~PAGE_MASK);

	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
		int level;
		pte_t *ptep;
		unsigned long pfn, mfn;
		void *virt;

		/*
		 * The GDT is per-cpu and is in the percpu data area.
		 * That can be virtually mapped, so we need to do a
		 * page-walk to get the underlying MFN for the
		 * hypercall.  The page can also be in the kernel's
		 * linear range, so we need to RO that mapping too.
		 */
		ptep = lookup_address(va, &level);
		BUG_ON(ptep == NULL);

		pfn = pte_pfn(*ptep);
		mfn = pfn_to_mfn(pfn);
		virt = __va(PFN_PHYS(pfn));

		frames[f] = mfn;

		make_lowmem_page_readonly((void *)va);
		make_lowmem_page_readonly(virt);
	}

	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
		BUG();
}

/*
 * load_gdt for early boot, when the gdt is only mapped once
 */
static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
{
	unsigned long va = dtr->address;
	unsigned int size = dtr->size + 1;
	unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
	unsigned long frames[pages];
	int f;

	/*
	 * A GDT can be up to 64k in size, which corresponds to 8192
	 * 8-byte entries, or 16 4k pages..
	 */

	BUG_ON(size > 65536);
	BUG_ON(va & ~PAGE_MASK);

	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
		pte_t pte;
		unsigned long pfn, mfn;

		pfn = virt_to_pfn(va);
		mfn = pfn_to_mfn(pfn);

		pte = pfn_pte(pfn, PAGE_KERNEL_RO);

		if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
			BUG();

		frames[f] = mfn;
	}

	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
		BUG();
}

static inline bool desc_equal(const struct desc_struct *d1,
			      const struct desc_struct *d2)
{
	return d1->a == d2->a && d1->b == d2->b;
}

static void load_TLS_descriptor(struct thread_struct *t,
				unsigned int cpu, unsigned int i)
{
	struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i];
	struct desc_struct *gdt;
	xmaddr_t maddr;
	struct multicall_space mc;

	if (desc_equal(shadow, &t->tls_array[i]))
		return;

	*shadow = t->tls_array[i];

	gdt = get_cpu_gdt_table(cpu);
	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
	mc = __xen_mc_entry(0);

	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
}

static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
	/*
	 * XXX sleazy hack: If we're being called in a lazy-cpu zone
	 * and lazy gs handling is enabled, it means we're in a
	 * context switch, and %gs has just been saved.  This means we
	 * can zero it out to prevent faults on exit from the
	 * hypervisor if the next process has no %gs.  Either way, it
	 * has been saved, and the new value will get loaded properly.
	 * This will go away as soon as Xen has been modified to not
	 * save/restore %gs for normal hypercalls.
	 *
	 * On x86_64, this hack is not used for %gs, because gs points
	 * to KERNEL_GS_BASE (and uses it for PDA references), so we
	 * must not zero %gs on x86_64
	 *
	 * For x86_64, we need to zero %fs, otherwise we may get an
	 * exception between the new %fs descriptor being loaded and
	 * %fs being effectively cleared at __switch_to().
	 */
	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
#ifdef CONFIG_X86_32
		lazy_load_gs(0);
#else
		loadsegment(fs, 0);
#endif
	}

	xen_mc_batch();

	load_TLS_descriptor(t, cpu, 0);
	load_TLS_descriptor(t, cpu, 1);
	load_TLS_descriptor(t, cpu, 2);

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

#ifdef CONFIG_X86_64
static void xen_load_gs_index(unsigned int idx)
{
	if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
		BUG();
}
#endif

static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
				const void *ptr)
{
	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
	u64 entry = *(u64 *)ptr;

	trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);

	preempt_disable();

	xen_mc_flush();
	if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry))
		BUG();

	preempt_enable();
}

static int cvt_gate_to_trap(int vector, const gate_desc *val,
			    struct trap_info *info)
{
	unsigned long addr;

	if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
		return 0;

	info->vector = vector;

	addr = gate_offset(*val);
#ifdef CONFIG_X86_64
	/*
	 * Look for known traps using IST, and substitute them
	 * appropriately.  The debugger ones are the only ones we care
	 * about.  Xen will handle faults like double_fault,
	 * so we should never see them.  Warn if
	 * there's an unexpected IST-using fault handler.
	 */
	if (addr == (unsigned long)debug)
		addr = (unsigned long)xen_debug;
	else if (addr == (unsigned long)int3)
		addr = (unsigned long)xen_int3;
	else if (addr == (unsigned long)stack_segment)
		addr = (unsigned long)xen_stack_segment;
	else if (addr == (unsigned long)double_fault) {
		/* Don't need to handle these */
		return 0;
#ifdef CONFIG_X86_MCE
	} else if (addr == (unsigned long)machine_check) {
		/*
		 * when xen hypervisor inject vMCE to guest,
		 * use native mce handler to handle it
		 */
		;
#endif
	} else if (addr == (unsigned long)nmi)
		/*
		 * Use the native version as well.
		 */
		;
	else {
		/* Some other trap using IST? */
		if (WARN_ON(val->ist != 0))
			return 0;
	}
#endif	/* CONFIG_X86_64 */
	info->address = addr;

	info->cs = gate_segment(*val);
	info->flags = val->dpl;
	/* interrupt gates clear IF */
	if (val->type == GATE_INTERRUPT)
		info->flags |= 1 << 2;

	return 1;
}

/* Locations of each CPU's IDT */
static DEFINE_PER_CPU(struct desc_ptr, idt_desc);

/* Set an IDT entry.  If the entry is part of the current IDT, then
   also update Xen. */
static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
{
	unsigned long p = (unsigned long)&dt[entrynum];
	unsigned long start, end;

	trace_xen_cpu_write_idt_entry(dt, entrynum, g);

	preempt_disable();

	start = __this_cpu_read(idt_desc.address);
	end = start + __this_cpu_read(idt_desc.size) + 1;

	xen_mc_flush();

	native_write_idt_entry(dt, entrynum, g);

	if (p >= start && (p + 8) <= end) {
		struct trap_info info[2];

		info[1].address = 0;

		if (cvt_gate_to_trap(entrynum, g, &info[0]))
			if (HYPERVISOR_set_trap_table(info))
				BUG();
	}

	preempt_enable();
}

static void xen_convert_trap_info(const struct desc_ptr *desc,
				  struct trap_info *traps)
{
	unsigned in, out, count;

	count = (desc->size+1) / sizeof(gate_desc);
	BUG_ON(count > 256);

	for (in = out = 0; in < count; in++) {
		gate_desc *entry = (gate_desc*)(desc->address) + in;

		if (cvt_gate_to_trap(in, entry, &traps[out]))
			out++;
	}
	traps[out].address = 0;
}

void xen_copy_trap_info(struct trap_info *traps)
{
	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);

	xen_convert_trap_info(desc, traps);
}

/* Load a new IDT into Xen.  In principle this can be per-CPU, so we
   hold a spinlock to protect the static traps[] array (static because
   it avoids allocation, and saves stack space). */
static void xen_load_idt(const struct desc_ptr *desc)
{
	static DEFINE_SPINLOCK(lock);
	static struct trap_info traps[257];

	trace_xen_cpu_load_idt(desc);

	spin_lock(&lock);

	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));

	xen_convert_trap_info(desc, traps);

	xen_mc_flush();
	if (HYPERVISOR_set_trap_table(traps))
		BUG();

	spin_unlock(&lock);
}

/* Write a GDT descriptor entry.  Ignore LDT descriptors, since
   they're handled differently. */
static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
				const void *desc, int type)
{
	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);

	preempt_disable();

	switch (type) {
	case DESC_LDT:
	case DESC_TSS:
		/* ignore */
		break;

	default: {
		xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]);

		xen_mc_flush();
		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
			BUG();
	}

	}

	preempt_enable();
}

/*
 * Version of write_gdt_entry for use at early boot-time needed to
 * update an entry as simply as possible.
 */
static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
					    const void *desc, int type)
{
	trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);

	switch (type) {
	case DESC_LDT:
	case DESC_TSS:
		/* ignore */
		break;

	default: {
		xmaddr_t maddr = virt_to_machine(&dt[entry]);

		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
			dt[entry] = *(struct desc_struct *)desc;
	}

	}
}

static void xen_load_sp0(struct tss_struct *tss,
			 struct thread_struct *thread)
{
	struct multicall_space mcs;

	mcs = xen_mc_entry(0);
	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
	xen_mc_issue(PARAVIRT_LAZY_CPU);
	tss->x86_tss.sp0 = thread->sp0;
}

static void xen_set_iopl_mask(unsigned mask)
{
	struct physdev_set_iopl set_iopl;

	/* Force the change at ring 0. */
	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
}

static void xen_io_delay(void)
{
}

static void xen_clts(void)
{
	struct multicall_space mcs;

	mcs = xen_mc_entry(0);

	MULTI_fpu_taskswitch(mcs.mc, 0);

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static DEFINE_PER_CPU(unsigned long, xen_cr0_value);

static unsigned long xen_read_cr0(void)
{
	unsigned long cr0 = this_cpu_read(xen_cr0_value);

	if (unlikely(cr0 == 0)) {
		cr0 = native_read_cr0();
		this_cpu_write(xen_cr0_value, cr0);
	}

	return cr0;
}

static void xen_write_cr0(unsigned long cr0)
{
	struct multicall_space mcs;

	this_cpu_write(xen_cr0_value, cr0);

	/* Only pay attention to cr0.TS; everything else is
	   ignored. */
	mcs = xen_mc_entry(0);

	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static void xen_write_cr4(unsigned long cr4)
{
	cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE);

	native_write_cr4(cr4);
}
#ifdef CONFIG_X86_64
static inline unsigned long xen_read_cr8(void)
{
	return 0;
}
static inline void xen_write_cr8(unsigned long val)
{
	BUG_ON(val);
}
#endif

static u64 xen_read_msr_safe(unsigned int msr, int *err)
{
	u64 val;

	if (pmu_msr_read(msr, &val, err))
		return val;

	val = native_read_msr_safe(msr, err);
	switch (msr) {
	case MSR_IA32_APICBASE:
#ifdef CONFIG_X86_X2APIC
		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
#endif
			val &= ~X2APIC_ENABLE;
		break;
	}
	return val;
}

static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
	int ret;

	ret = 0;

	switch (msr) {
#ifdef CONFIG_X86_64
		unsigned which;
		u64 base;

	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;

	set:
		base = ((u64)high << 32) | low;
		if (HYPERVISOR_set_segment_base(which, base) != 0)
			ret = -EIO;
		break;
#endif

	case MSR_STAR:
	case MSR_CSTAR:
	case MSR_LSTAR:
	case MSR_SYSCALL_MASK:
	case MSR_IA32_SYSENTER_CS:
	case MSR_IA32_SYSENTER_ESP:
	case MSR_IA32_SYSENTER_EIP:
		/* Fast syscall setup is all done in hypercalls, so
		   these are all ignored.  Stub them out here to stop
		   Xen console noise. */

	default:
		if (!pmu_msr_write(msr, low, high, &ret))
			ret = native_write_msr_safe(msr, low, high);
	}

	return ret;
}

void xen_setup_shared_info(void)
{
	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
		set_fixmap(FIX_PARAVIRT_BOOTMAP,
			   xen_start_info->shared_info);

		HYPERVISOR_shared_info =
			(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
	} else
		HYPERVISOR_shared_info =
			(struct shared_info *)__va(xen_start_info->shared_info);

#ifndef CONFIG_SMP
	/* In UP this is as good a place as any to set up shared info */
	xen_setup_vcpu_info_placement();
#endif

	xen_setup_mfn_list_list();
}

/* This is called once we have the cpu_possible_mask */
void xen_setup_vcpu_info_placement(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		xen_vcpu_setup(cpu);

	/* xen_vcpu_setup managed to place the vcpu_info within the
	 * percpu area for all cpus, so make use of it. Note that for
	 * PVH we want to use native IRQ mechanism. */
	if (have_vcpu_info_placement && !xen_pvh_domain()) {
		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
		pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
		pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
	}
}

static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
			  unsigned long addr, unsigned len)
{
	char *start, *end, *reloc;
	unsigned ret;

	start = end = reloc = NULL;

#define SITE(op, x)							\
	case PARAVIRT_PATCH(op.x):					\
	if (have_vcpu_info_placement) {					\
		start = (char *)xen_##x##_direct;			\
		end = xen_##x##_direct_end;				\
		reloc = xen_##x##_direct_reloc;				\
	}								\
	goto patch_site

	switch (type) {
		SITE(pv_irq_ops, irq_enable);
		SITE(pv_irq_ops, irq_disable);
		SITE(pv_irq_ops, save_fl);
		SITE(pv_irq_ops, restore_fl);
#undef SITE

	patch_site:
		if (start == NULL || (end-start) > len)
			goto default_patch;

		ret = paravirt_patch_insns(insnbuf, len, start, end);

		/* Note: because reloc is assigned from something that
		   appears to be an array, gcc assumes it's non-null,
		   but doesn't know its relationship with start and
		   end. */
		if (reloc > start && reloc < end) {
			int reloc_off = reloc - start;
			long *relocp = (long *)(insnbuf + reloc_off);
			long delta = start - (char *)addr;

			*relocp += delta;
		}
		break;

	default_patch:
	default:
		ret = paravirt_patch_default(type, clobbers, insnbuf,
					     addr, len);
		break;
	}

	return ret;
}

static const struct pv_info xen_info __initconst = {
	.paravirt_enabled = 1,
	.shared_kernel_pmd = 0,

#ifdef CONFIG_X86_64
	.extra_user_64bit_cs = FLAT_USER_CS64,
#endif

	.name = "Xen",
};

static const struct pv_init_ops xen_init_ops __initconst = {
	.patch = xen_patch,
};

static const struct pv_cpu_ops xen_cpu_ops __initconst = {
	.cpuid = xen_cpuid,

	.set_debugreg = xen_set_debugreg,
	.get_debugreg = xen_get_debugreg,

	.clts = xen_clts,

	.read_cr0 = xen_read_cr0,
	.write_cr0 = xen_write_cr0,

	.read_cr4 = native_read_cr4,
	.read_cr4_safe = native_read_cr4_safe,
	.write_cr4 = xen_write_cr4,

#ifdef CONFIG_X86_64
	.read_cr8 = xen_read_cr8,
	.write_cr8 = xen_write_cr8,
#endif

	.wbinvd = native_wbinvd,

	.read_msr = xen_read_msr_safe,
	.write_msr = xen_write_msr_safe,

	.read_pmc = xen_read_pmc,

	.iret = xen_iret,
#ifdef CONFIG_X86_64
	.usergs_sysret32 = xen_sysret32,
	.usergs_sysret64 = xen_sysret64,
#else
	.irq_enable_sysexit = xen_sysexit,
#endif

	.load_tr_desc = paravirt_nop,
	.set_ldt = xen_set_ldt,
	.load_gdt = xen_load_gdt,
	.load_idt = xen_load_idt,
	.load_tls = xen_load_tls,
#ifdef CONFIG_X86_64
	.load_gs_index = xen_load_gs_index,
#endif

	.alloc_ldt = xen_alloc_ldt,
	.free_ldt = xen_free_ldt,

	.store_idt = native_store_idt,
	.store_tr = xen_store_tr,

	.write_ldt_entry = xen_write_ldt_entry,
	.write_gdt_entry = xen_write_gdt_entry,
	.write_idt_entry = xen_write_idt_entry,
	.load_sp0 = xen_load_sp0,

	.set_iopl_mask = xen_set_iopl_mask,
	.io_delay = xen_io_delay,

	/* Xen takes care of %gs when switching to usermode for us */
	.swapgs = paravirt_nop,

	.start_context_switch = paravirt_start_context_switch,
	.end_context_switch = xen_end_context_switch,
};

static const struct pv_apic_ops xen_apic_ops __initconst = {
#ifdef CONFIG_X86_LOCAL_APIC
	.startup_ipi_hook = paravirt_nop,
#endif
};

static void xen_reboot(int reason)
{
	struct sched_shutdown r = { .reason = reason };
	int cpu;

	for_each_online_cpu(cpu)
		xen_pmu_finish(cpu);

	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
		BUG();
}

static void xen_restart(char *msg)
{
	xen_reboot(SHUTDOWN_reboot);
}

static void xen_emergency_restart(void)
{
	xen_reboot(SHUTDOWN_reboot);
}

static void xen_machine_halt(void)
{
	xen_reboot(SHUTDOWN_poweroff);
}

static void xen_machine_power_off(void)
{
	if (pm_power_off)
		pm_power_off();
	xen_reboot(SHUTDOWN_poweroff);
}

static void xen_crash_shutdown(struct pt_regs *regs)
{
	xen_reboot(SHUTDOWN_crash);
}

static int
xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	xen_reboot(SHUTDOWN_crash);
	return NOTIFY_DONE;
}

static struct notifier_block xen_panic_block = {
	.notifier_call= xen_panic_event,
	.priority = INT_MIN
};

int xen_panic_handler_init(void)
{
	atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block);
	return 0;
}

static const struct machine_ops xen_machine_ops __initconst = {
	.restart = xen_restart,
	.halt = xen_machine_halt,
	.power_off = xen_machine_power_off,
	.shutdown = xen_machine_halt,
	.crash_shutdown = xen_crash_shutdown,
	.emergency_restart = xen_emergency_restart,
};

static unsigned char xen_get_nmi_reason(void)
{
	unsigned char reason = 0;

	/* Construct a value which looks like it came from port 0x61. */
	if (test_bit(_XEN_NMIREASON_io_error,
		     &HYPERVISOR_shared_info->arch.nmi_reason))
		reason |= NMI_REASON_IOCHK;
	if (test_bit(_XEN_NMIREASON_pci_serr,
		     &HYPERVISOR_shared_info->arch.nmi_reason))
		reason |= NMI_REASON_SERR;

	return reason;
}

static void __init xen_boot_params_init_edd(void)
{
#if IS_ENABLED(CONFIG_EDD)
	struct xen_platform_op op;
	struct edd_info *edd_info;
	u32 *mbr_signature;
	unsigned nr;
	int ret;

	edd_info = boot_params.eddbuf;
	mbr_signature = boot_params.edd_mbr_sig_buffer;

	op.cmd = XENPF_firmware_info;

	op.u.firmware_info.type = XEN_FW_DISK_INFO;
	for (nr = 0; nr < EDDMAXNR; nr++) {
		struct edd_info *info = edd_info + nr;

		op.u.firmware_info.index = nr;
		info->params.length = sizeof(info->params);
		set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
				     &info->params);
		ret = HYPERVISOR_dom0_op(&op);
		if (ret)
			break;

#define C(x) info->x = op.u.firmware_info.u.disk_info.x
		C(device);
		C(version);
		C(interface_support);
		C(legacy_max_cylinder);
		C(legacy_max_head);
		C(legacy_sectors_per_track);
#undef C
	}
	boot_params.eddbuf_entries = nr;

	op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
	for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
		op.u.firmware_info.index = nr;
		ret = HYPERVISOR_dom0_op(&op);
		if (ret)
			break;
		mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
	}
	boot_params.edd_mbr_sig_buf_entries = nr;
#endif
}

/*
 * Set up the GDT and segment registers for -fstack-protector.  Until
 * we do this, we have to be careful not to call any stack-protected
 * function, which is most of the kernel.
 *
 * Note, that it is __ref because the only caller of this after init
 * is PVH which is not going to use xen_load_gdt_boot or other
 * __init functions.
 */
static void __ref xen_setup_gdt(int cpu)
{
	if (xen_feature(XENFEAT_auto_translated_physmap)) {
#ifdef CONFIG_X86_64
		unsigned long dummy;

		load_percpu_segment(cpu); /* We need to access per-cpu area */
		switch_to_new_gdt(cpu); /* GDT and GS set */

		/* We are switching of the Xen provided GDT to our HVM mode
		 * GDT. The new GDT has  __KERNEL_CS with CS.L = 1
		 * and we are jumping to reload it.
		 */
		asm volatile ("pushq %0\n"
			      "leaq 1f(%%rip),%0\n"
			      "pushq %0\n"
			      "lretq\n"
			      "1:\n"
			      : "=&r" (dummy) : "0" (__KERNEL_CS));

		/*
		 * While not needed, we also set the %es, %ds, and %fs
		 * to zero. We don't care about %ss as it is NULL.
		 * Strictly speaking this is not needed as Xen zeros those
		 * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE)
		 *
		 * Linux zeros them in cpu_init() and in secondary_startup_64
		 * (for BSP).
		 */
		loadsegment(es, 0);
		loadsegment(ds, 0);
		loadsegment(fs, 0);
#else
		/* PVH: TODO Implement. */
		BUG();
#endif
		return; /* PVH does not need any PV GDT ops. */
	}
	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
	pv_cpu_ops.load_gdt = xen_load_gdt_boot;

	setup_stack_canary_segment(0);
	switch_to_new_gdt(0);

	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry;
	pv_cpu_ops.load_gdt = xen_load_gdt;
}

#ifdef CONFIG_XEN_PVH
/*
 * A PV guest starts with default flags that are not set for PVH, set them
 * here asap.
 */
static void xen_pvh_set_cr_flags(int cpu)
{

	/* Some of these are setup in 'secondary_startup_64'. The others:
	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);

	if (!cpu)
		return;
	/*
	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
	*/
	if (cpu_has_pse)
		cr4_set_bits_and_update_boot(X86_CR4_PSE);

	if (cpu_has_pge)
		cr4_set_bits_and_update_boot(X86_CR4_PGE);
}

/*
 * Note, that it is ref - because the only caller of this after init
 * is PVH which is not going to use xen_load_gdt_boot or other
 * __init functions.
 */
void __ref xen_pvh_secondary_vcpu_init(int cpu)
{
	xen_setup_gdt(cpu);
	xen_pvh_set_cr_flags(cpu);
}

static void __init xen_pvh_early_guest_init(void)
{
	if (!xen_feature(XENFEAT_auto_translated_physmap))
		return;

	if (!xen_feature(XENFEAT_hvm_callback_vector))
		return;

	xen_have_vector_callback = 1;

	xen_pvh_early_cpu_init(0, false);
	xen_pvh_set_cr_flags(0);

#ifdef CONFIG_X86_32
	BUG(); /* PVH: Implement proper support. */
#endif
}
#endif    /* CONFIG_XEN_PVH */

/* First C function to be called on Xen boot */
asmlinkage __visible void __init xen_start_kernel(void)
{
	struct physdev_set_iopl set_iopl;
	unsigned long initrd_start = 0;
	u64 pat;
	int rc;

	if (!xen_start_info)
		return;

	xen_domain_type = XEN_PV_DOMAIN;

	xen_setup_features();
#ifdef CONFIG_XEN_PVH
	xen_pvh_early_guest_init();
#endif
	xen_setup_machphys_mapping();

	/* Install Xen paravirt ops */
	pv_info = xen_info;
	pv_init_ops = xen_init_ops;
	pv_apic_ops = xen_apic_ops;
	if (!xen_pvh_domain()) {
		pv_cpu_ops = xen_cpu_ops;

		x86_platform.get_nmi_reason = xen_get_nmi_reason;
	}

	if (xen_feature(XENFEAT_auto_translated_physmap))
		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
	else
		x86_init.resources.memory_setup = xen_memory_setup;
	x86_init.oem.arch_setup = xen_arch_setup;
	x86_init.oem.banner = xen_banner;

	xen_init_time_ops();

	/*
	 * Set up some pagetable state before starting to set any ptes.
	 */

	xen_init_mmu_ops();

	/* Prevent unwanted bits from being set in PTEs. */
	__supported_pte_mask &= ~_PAGE_GLOBAL;

	/*
	 * Prevent page tables from being allocated in highmem, even
	 * if CONFIG_HIGHPTE is enabled.
	 */
	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;

	/* Work out if we support NX */
	x86_configure_nx();

	/* Get mfn list */
	xen_build_dynamic_phys_to_machine();

	/*
	 * Set up kernel GDT and segment registers, mainly so that
	 * -fstack-protector code can be executed.
	 */
	xen_setup_gdt(0);

	xen_init_irq_ops();
	xen_init_cpuid_mask();

#ifdef CONFIG_X86_LOCAL_APIC
	/*
	 * set up the basic apic ops.
	 */
	xen_init_apic();
#endif

	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
	}

	machine_ops = xen_machine_ops;

	/*
	 * The only reliable way to retain the initial address of the
	 * percpu gdt_page is to remember it here, so we can go and
	 * mark it RW later, when the initial percpu area is freed.
	 */
	xen_initial_gdt = &per_cpu(gdt_page, 0);

	xen_smp_init();

#ifdef CONFIG_ACPI_NUMA
	/*
	 * The pages we from Xen are not related to machine pages, so
	 * any NUMA information the kernel tries to get from ACPI will
	 * be meaningless.  Prevent it from trying.
	 */
	acpi_numa = -1;
#endif
	/* Don't do the full vcpu_info placement stuff until we have a
	   possible map and a non-dummy shared_info. */
	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];

	local_irq_disable();
	early_boot_irqs_disabled = true;

	xen_raw_console_write("mapping kernel into physical memory\n");
	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
				   xen_start_info->nr_pages);
	xen_reserve_special_pages();

	/*
	 * Modify the cache mode translation tables to match Xen's PAT
	 * configuration.
	 */
	rdmsrl(MSR_IA32_CR_PAT, pat);
	pat_init_cache_modes(pat);

	/* keep using Xen gdt for now; no urgent need to change it */

#ifdef CONFIG_X86_32
	pv_info.kernel_rpl = 1;
	if (xen_feature(XENFEAT_supervisor_mode_kernel))
		pv_info.kernel_rpl = 0;
#else
	pv_info.kernel_rpl = 0;
#endif
	/* set the limit of our address space */
	xen_reserve_top();

	/* PVH: runs at default kernel iopl of 0 */
	if (!xen_pvh_domain()) {
		/*
		 * We used to do this in xen_arch_setup, but that is too late
		 * on AMD were early_cpu_init (run before ->arch_setup()) calls
		 * early_amd_init which pokes 0xcf8 port.
		 */
		set_iopl.iopl = 1;
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
		if (rc != 0)
			xen_raw_printk("physdev_op failed %d\n", rc);
	}

#ifdef CONFIG_X86_32
	/* set up basic CPUID stuff */
	cpu_detect(&new_cpu_data);
	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
	new_cpu_data.wp_works_ok = 1;
	new_cpu_data.x86_capability[0] = cpuid_edx(1);
#endif

	if (xen_start_info->mod_start) {
	    if (xen_start_info->flags & SIF_MOD_START_PFN)
		initrd_start = PFN_PHYS(xen_start_info->mod_start);
	    else
		initrd_start = __pa(xen_start_info->mod_start);
	}

	/* Poke various useful things into boot_params */
	boot_params.hdr.type_of_loader = (9 << 4) | 0;
	boot_params.hdr.ramdisk_image = initrd_start;
	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);

	if (!xen_initial_domain()) {
		add_preferred_console("xenboot", 0, NULL);
		add_preferred_console("tty", 0, NULL);
		add_preferred_console("hvc", 0, NULL);
		if (pci_xen)
			x86_init.pci.arch_init = pci_xen_init;
	} else {
		const struct dom0_vga_console_info *info =
			(void *)((char *)xen_start_info +
				 xen_start_info->console.dom0.info_off);
		struct xen_platform_op op = {
			.cmd = XENPF_firmware_info,
			.interface_version = XENPF_INTERFACE_VERSION,
			.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
		};

		xen_init_vga(info, xen_start_info->console.dom0.info_size);
		xen_start_info->console.domU.mfn = 0;
		xen_start_info->console.domU.evtchn = 0;

		if (HYPERVISOR_dom0_op(&op) == 0)
			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;

		/* Make sure ACS will be enabled */
		pci_request_acs();

		xen_acpi_sleep_register();

		/* Avoid searching for BIOS MP tables */
		x86_init.mpparse.find_smp_config = x86_init_noop;
		x86_init.mpparse.get_smp_config = x86_init_uint_noop;

		xen_boot_params_init_edd();
	}
#ifdef CONFIG_PCI
	/* PCI BIOS service won't work from a PV guest. */
	pci_probe &= ~PCI_PROBE_BIOS;
#endif
	xen_raw_console_write("about to get started...\n");

	xen_setup_runstate_info(0);

	xen_efi_init();

	/* Start the world */
#ifdef CONFIG_X86_32
	i386_start_kernel();
#else
	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
#endif
}

void __ref xen_hvm_init_shared_info(void)
{
	int cpu;
	struct xen_add_to_physmap xatp;
	static struct shared_info *shared_info_page = 0;

	if (!shared_info_page)
		shared_info_page = (struct shared_info *)
			extend_brk(PAGE_SIZE, PAGE_SIZE);
	xatp.domid = DOMID_SELF;
	xatp.idx = 0;
	xatp.space = XENMAPSPACE_shared_info;
	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
		BUG();

	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;

	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
	 * page, we use it in the event channel upcall and in some pvclock
	 * related functions. We don't need the vcpu_info placement
	 * optimizations because we don't use any pv_mmu or pv_irq op on
	 * HVM.
	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
	 * online but xen_hvm_init_shared_info is run at resume time too and
	 * in that case multiple vcpus might be online. */
	for_each_online_cpu(cpu) {
		/* Leave it to be NULL. */
		if (cpu >= MAX_VIRT_CPUS)
			continue;
		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
	}
}

#ifdef CONFIG_XEN_PVHVM
static void __init init_hvm_pv_info(void)
{
	int major, minor;
	uint32_t eax, ebx, ecx, edx, pages, msr, base;
	u64 pfn;

	base = xen_cpuid_base();
	cpuid(base + 1, &eax, &ebx, &ecx, &edx);

	major = eax >> 16;
	minor = eax & 0xffff;
	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);

	cpuid(base + 2, &pages, &msr, &ecx, &edx);

	pfn = __pa(hypercall_page);
	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));

	xen_setup_features();

	pv_info.name = "Xen HVM";

	xen_domain_type = XEN_HVM_DOMAIN;
}

static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
			      void *hcpu)
{
	int cpu = (long)hcpu;
	switch (action) {
	case CPU_UP_PREPARE:
		xen_vcpu_setup(cpu);
		if (xen_have_vector_callback) {
			if (xen_feature(XENFEAT_hvm_safe_pvclock))
				xen_setup_timer(cpu);
		}
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block xen_hvm_cpu_notifier = {
	.notifier_call	= xen_hvm_cpu_notify,
};

static void __init xen_hvm_guest_init(void)
{
	if (xen_pv_domain())
		return;

	init_hvm_pv_info();

	xen_hvm_init_shared_info();

	xen_panic_handler_init();

	if (xen_feature(XENFEAT_hvm_callback_vector))
		xen_have_vector_callback = 1;
	xen_hvm_smp_init();
	register_cpu_notifier(&xen_hvm_cpu_notifier);
	xen_unplug_emulated_devices();
	x86_init.irqs.intr_init = xen_init_IRQ;
	xen_hvm_init_time_ops();
	xen_hvm_init_mmu_ops();
}
#endif

static bool xen_nopv = false;
static __init int xen_parse_nopv(char *arg)
{
       xen_nopv = true;
       return 0;
}
early_param("xen_nopv", xen_parse_nopv);

static uint32_t __init xen_platform(void)
{
	if (xen_nopv)
		return 0;

	return xen_cpuid_base();
}

bool xen_hvm_need_lapic(void)
{
	if (xen_nopv)
		return false;
	if (xen_pv_domain())
		return false;
	if (!xen_hvm_domain())
		return false;
	if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
		return false;
	return true;
}
EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);

static void xen_set_cpu_features(struct cpuinfo_x86 *c)
{
	if (xen_pv_domain())
		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
}

const struct hypervisor_x86 x86_hyper_xen = {
	.name			= "Xen",
	.detect			= xen_platform,
#ifdef CONFIG_XEN_PVHVM
	.init_platform		= xen_hvm_guest_init,
#endif
	.x2apic_available	= xen_x2apic_para_available,
	.set_cpu_features       = xen_set_cpu_features,
};
EXPORT_SYMBOL(x86_hyper_xen);