aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/kvm/kvm_main.c
blob: 729573b844e5e860d4d108f68c5889f2d849ebc6 (plain) (blame)
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
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * Copyright (C) 2006 Qumranet, Inc.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "kvm.h"
#include "x86.h"
#include "irq.h"

#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
#include <linux/kvm_para.h>
#include <linux/pagemap.h>
#include <linux/mman.h>

#include <asm/processor.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
#include <asm/pgtable.h>

MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");

DEFINE_SPINLOCK(kvm_lock);
LIST_HEAD(vm_list);

static cpumask_t cpus_hardware_enabled;

struct kmem_cache *kvm_vcpu_cache;
EXPORT_SYMBOL_GPL(kvm_vcpu_cache);

static __read_mostly struct preempt_ops kvm_preempt_ops;

static struct dentry *debugfs_dir;

static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
			   unsigned long arg);

static inline int valid_vcpu(int n)
{
	return likely(n >= 0 && n < KVM_MAX_VCPUS);
}

/*
 * Switches to specified vcpu, until a matching vcpu_put()
 */
void vcpu_load(struct kvm_vcpu *vcpu)
{
	int cpu;

	mutex_lock(&vcpu->mutex);
	cpu = get_cpu();
	preempt_notifier_register(&vcpu->preempt_notifier);
	kvm_arch_vcpu_load(vcpu, cpu);
	put_cpu();
}

void vcpu_put(struct kvm_vcpu *vcpu)
{
	preempt_disable();
	kvm_arch_vcpu_put(vcpu);
	preempt_notifier_unregister(&vcpu->preempt_notifier);
	preempt_enable();
	mutex_unlock(&vcpu->mutex);
}

static void ack_flush(void *_completed)
{
}

void kvm_flush_remote_tlbs(struct kvm *kvm)
{
	int i, cpu;
	cpumask_t cpus;
	struct kvm_vcpu *vcpu;

	cpus_clear(cpus);
	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
		vcpu = kvm->vcpus[i];
		if (!vcpu)
			continue;
		if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
			continue;
		cpu = vcpu->cpu;
		if (cpu != -1 && cpu != raw_smp_processor_id())
			cpu_set(cpu, cpus);
	}
	smp_call_function_mask(cpus, ack_flush, NULL, 1);
}

int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
	struct page *page;
	int r;

	mutex_init(&vcpu->mutex);
	vcpu->cpu = -1;
	vcpu->kvm = kvm;
	vcpu->vcpu_id = id;
	init_waitqueue_head(&vcpu->wq);

	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
	if (!page) {
		r = -ENOMEM;
		goto fail;
	}
	vcpu->run = page_address(page);

	r = kvm_arch_vcpu_init(vcpu);
	if (r < 0)
		goto fail_free_run;
	return 0;

fail_free_run:
	free_page((unsigned long)vcpu->run);
fail:
	return r;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_init);

void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_uninit(vcpu);
	free_page((unsigned long)vcpu->run);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);

static struct kvm *kvm_create_vm(void)
{
	struct kvm *kvm = kvm_arch_create_vm();

	if (IS_ERR(kvm))
		goto out;

	kvm_io_bus_init(&kvm->pio_bus);
	mutex_init(&kvm->lock);
	kvm_io_bus_init(&kvm->mmio_bus);
	spin_lock(&kvm_lock);
	list_add(&kvm->vm_list, &vm_list);
	spin_unlock(&kvm_lock);
out:
	return kvm;
}

/*
 * Free any memory in @free but not in @dont.
 */
static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
				  struct kvm_memory_slot *dont)
{
	if (!dont || free->rmap != dont->rmap)
		vfree(free->rmap);

	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
		vfree(free->dirty_bitmap);

	free->npages = 0;
	free->dirty_bitmap = NULL;
	free->rmap = NULL;
}

void kvm_free_physmem(struct kvm *kvm)
{
	int i;

	for (i = 0; i < kvm->nmemslots; ++i)
		kvm_free_physmem_slot(&kvm->memslots[i], NULL);
}

static void kvm_destroy_vm(struct kvm *kvm)
{
	spin_lock(&kvm_lock);
	list_del(&kvm->vm_list);
	spin_unlock(&kvm_lock);
	kvm_io_bus_destroy(&kvm->pio_bus);
	kvm_io_bus_destroy(&kvm->mmio_bus);
	kvm_arch_destroy_vm(kvm);
}

static int kvm_vm_release(struct inode *inode, struct file *filp)
{
	struct kvm *kvm = filp->private_data;

	kvm_destroy_vm(kvm);
	return 0;
}

/*
 * Allocate some memory and give it an address in the guest physical address
 * space.
 *
 * Discontiguous memory is allowed, mostly for framebuffers.
 *
 * Must be called holding kvm->lock.
 */
int __kvm_set_memory_region(struct kvm *kvm,
			    struct kvm_userspace_memory_region *mem,
			    int user_alloc)
{
	int r;
	gfn_t base_gfn;
	unsigned long npages;
	unsigned long i;
	struct kvm_memory_slot *memslot;
	struct kvm_memory_slot old, new;

	r = -EINVAL;
	/* General sanity checks */
	if (mem->memory_size & (PAGE_SIZE - 1))
		goto out;
	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
		goto out;
	if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
		goto out;
	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
		goto out;

	memslot = &kvm->memslots[mem->slot];
	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
	npages = mem->memory_size >> PAGE_SHIFT;

	if (!npages)
		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;

	new = old = *memslot;

	new.base_gfn = base_gfn;
	new.npages = npages;
	new.flags = mem->flags;

	/* Disallow changing a memory slot's size. */
	r = -EINVAL;
	if (npages && old.npages && npages != old.npages)
		goto out_free;

	/* Check for overlaps */
	r = -EEXIST;
	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
		struct kvm_memory_slot *s = &kvm->memslots[i];

		if (s == memslot)
			continue;
		if (!((base_gfn + npages <= s->base_gfn) ||
		      (base_gfn >= s->base_gfn + s->npages)))
			goto out_free;
	}

	/* Free page dirty bitmap if unneeded */
	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
		new.dirty_bitmap = NULL;

	r = -ENOMEM;

	/* Allocate if a slot is being created */
	if (npages && !new.rmap) {
		new.rmap = vmalloc(npages * sizeof(struct page *));

		if (!new.rmap)
			goto out_free;

		memset(new.rmap, 0, npages * sizeof(*new.rmap));

		new.user_alloc = user_alloc;
		if (user_alloc)
			new.userspace_addr = mem->userspace_addr;
		else {
			down_write(&current->mm->mmap_sem);
			new.userspace_addr = do_mmap(NULL, 0,
						     npages * PAGE_SIZE,
						     PROT_READ | PROT_WRITE,
						     MAP_SHARED | MAP_ANONYMOUS,
						     0);
			up_write(&current->mm->mmap_sem);

			if (IS_ERR((void *)new.userspace_addr))
				goto out_free;
		}
	} else {
		if (!old.user_alloc && old.rmap) {
			int ret;

			down_write(&current->mm->mmap_sem);
			ret = do_munmap(current->mm, old.userspace_addr,
					old.npages * PAGE_SIZE);
			up_write(&current->mm->mmap_sem);
			if (ret < 0)
				printk(KERN_WARNING
				       "kvm_vm_ioctl_set_memory_region: "
				       "failed to munmap memory\n");
		}
	}

	/* Allocate page dirty bitmap if needed */
	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
		unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8;

		new.dirty_bitmap = vmalloc(dirty_bytes);
		if (!new.dirty_bitmap)
			goto out_free;
		memset(new.dirty_bitmap, 0, dirty_bytes);
	}

	if (mem->slot >= kvm->nmemslots)
		kvm->nmemslots = mem->slot + 1;

	if (!kvm->n_requested_mmu_pages) {
		unsigned int n_pages;

		if (npages) {
			n_pages = npages * KVM_PERMILLE_MMU_PAGES / 1000;
			kvm_mmu_change_mmu_pages(kvm, kvm->n_alloc_mmu_pages +
						 n_pages);
		} else {
			unsigned int nr_mmu_pages;

			n_pages = old.npages * KVM_PERMILLE_MMU_PAGES / 1000;
			nr_mmu_pages = kvm->n_alloc_mmu_pages - n_pages;
			nr_mmu_pages = max(nr_mmu_pages,
				        (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
			kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
		}
	}

	*memslot = new;

	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
	kvm_flush_remote_tlbs(kvm);

	kvm_free_physmem_slot(&old, &new);
	return 0;

out_free:
	kvm_free_physmem_slot(&new, &old);
out:
	return r;

}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);

int kvm_set_memory_region(struct kvm *kvm,
			  struct kvm_userspace_memory_region *mem,
			  int user_alloc)
{
	int r;

	mutex_lock(&kvm->lock);
	r = __kvm_set_memory_region(kvm, mem, user_alloc);
	mutex_unlock(&kvm->lock);
	return r;
}
EXPORT_SYMBOL_GPL(kvm_set_memory_region);

int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
				   struct
				   kvm_userspace_memory_region *mem,
				   int user_alloc)
{
	if (mem->slot >= KVM_MEMORY_SLOTS)
		return -EINVAL;
	return kvm_set_memory_region(kvm, mem, user_alloc);
}

int kvm_get_dirty_log(struct kvm *kvm,
			struct kvm_dirty_log *log, int *is_dirty)
{
	struct kvm_memory_slot *memslot;
	int r, i;
	int n;
	unsigned long any = 0;

	r = -EINVAL;
	if (log->slot >= KVM_MEMORY_SLOTS)
		goto out;

	memslot = &kvm->memslots[log->slot];
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;

	for (i = 0; !any && i < n/sizeof(long); ++i)
		any = memslot->dirty_bitmap[i];

	r = -EFAULT;
	if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
		goto out;

	if (any)
		*is_dirty = 1;

	r = 0;
out:
	return r;
}

int is_error_page(struct page *page)
{
	return page == bad_page;
}
EXPORT_SYMBOL_GPL(is_error_page);

static inline unsigned long bad_hva(void)
{
	return PAGE_OFFSET;
}

int kvm_is_error_hva(unsigned long addr)
{
	return addr == bad_hva();
}
EXPORT_SYMBOL_GPL(kvm_is_error_hva);

gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
	int i;
	struct kvm_mem_alias *alias;

	for (i = 0; i < kvm->naliases; ++i) {
		alias = &kvm->aliases[i];
		if (gfn >= alias->base_gfn
		    && gfn < alias->base_gfn + alias->npages)
			return alias->target_gfn + gfn - alias->base_gfn;
	}
	return gfn;
}

static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
	int i;

	for (i = 0; i < kvm->nmemslots; ++i) {
		struct kvm_memory_slot *memslot = &kvm->memslots[i];

		if (gfn >= memslot->base_gfn
		    && gfn < memslot->base_gfn + memslot->npages)
			return memslot;
	}
	return NULL;
}

struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
	gfn = unalias_gfn(kvm, gfn);
	return __gfn_to_memslot(kvm, gfn);
}

int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
{
	int i;

	gfn = unalias_gfn(kvm, gfn);
	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
		struct kvm_memory_slot *memslot = &kvm->memslots[i];

		if (gfn >= memslot->base_gfn
		    && gfn < memslot->base_gfn + memslot->npages)
			return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);

static unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *slot;

	gfn = unalias_gfn(kvm, gfn);
	slot = __gfn_to_memslot(kvm, gfn);
	if (!slot)
		return bad_hva();
	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
}

/*
 * Requires current->mm->mmap_sem to be held
 */
static struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
	struct page *page[1];
	unsigned long addr;
	int npages;

	might_sleep();

	addr = gfn_to_hva(kvm, gfn);
	if (kvm_is_error_hva(addr)) {
		get_page(bad_page);
		return bad_page;
	}

	npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page,
				NULL);

	if (npages != 1) {
		get_page(bad_page);
		return bad_page;
	}

	return page[0];
}

struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
	struct page *page;

	down_read(&current->mm->mmap_sem);
	page = __gfn_to_page(kvm, gfn);
	up_read(&current->mm->mmap_sem);

	return page;
}

EXPORT_SYMBOL_GPL(gfn_to_page);

void kvm_release_page_clean(struct page *page)
{
	put_page(page);
}
EXPORT_SYMBOL_GPL(kvm_release_page_clean);

void kvm_release_page_dirty(struct page *page)
{
	if (!PageReserved(page))
		SetPageDirty(page);
	put_page(page);
}
EXPORT_SYMBOL_GPL(kvm_release_page_dirty);

static int next_segment(unsigned long len, int offset)
{
	if (len > PAGE_SIZE - offset)
		return PAGE_SIZE - offset;
	else
		return len;
}

int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
			int len)
{
	int r;
	unsigned long addr;

	addr = gfn_to_hva(kvm, gfn);
	if (kvm_is_error_hva(addr))
		return -EFAULT;
	r = copy_from_user(data, (void __user *)addr + offset, len);
	if (r)
		return -EFAULT;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page);

int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	int seg;
	int offset = offset_in_page(gpa);
	int ret;

	while ((seg = next_segment(len, offset)) != 0) {
		ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
		if (ret < 0)
			return ret;
		offset = 0;
		len -= seg;
		data += seg;
		++gfn;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest);

int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
			 int offset, int len)
{
	int r;
	unsigned long addr;

	addr = gfn_to_hva(kvm, gfn);
	if (kvm_is_error_hva(addr))
		return -EFAULT;
	r = copy_to_user((void __user *)addr + offset, data, len);
	if (r)
		return -EFAULT;
	mark_page_dirty(kvm, gfn);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest_page);

int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
		    unsigned long len)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	int seg;
	int offset = offset_in_page(gpa);
	int ret;

	while ((seg = next_segment(len, offset)) != 0) {
		ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
		if (ret < 0)
			return ret;
		offset = 0;
		len -= seg;
		data += seg;
		++gfn;
	}
	return 0;
}

int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
{
	return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_clear_guest_page);

int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	int seg;
	int offset = offset_in_page(gpa);
	int ret;

        while ((seg = next_segment(len, offset)) != 0) {
		ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
		if (ret < 0)
			return ret;
		offset = 0;
		len -= seg;
		++gfn;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);

void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *memslot;

	gfn = unalias_gfn(kvm, gfn);
	memslot = __gfn_to_memslot(kvm, gfn);
	if (memslot && memslot->dirty_bitmap) {
		unsigned long rel_gfn = gfn - memslot->base_gfn;

		/* avoid RMW */
		if (!test_bit(rel_gfn, memslot->dirty_bitmap))
			set_bit(rel_gfn, memslot->dirty_bitmap);
	}
}

/*
 * The vCPU has executed a HLT instruction with in-kernel mode enabled.
 */
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue(&vcpu->wq, &wait);

	/*
	 * We will block until either an interrupt or a signal wakes us up
	 */
	while (!kvm_cpu_has_interrupt(vcpu)
	       && !signal_pending(current)
	       && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE
	       && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) {
		set_current_state(TASK_INTERRUPTIBLE);
		vcpu_put(vcpu);
		schedule();
		vcpu_load(vcpu);
	}

	__set_current_state(TASK_RUNNING);
	remove_wait_queue(&vcpu->wq, &wait);
}

void kvm_resched(struct kvm_vcpu *vcpu)
{
	if (!need_resched())
		return;
	cond_resched();
}
EXPORT_SYMBOL_GPL(kvm_resched);

static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
				    struct kvm_interrupt *irq)
{
	if (irq->irq < 0 || irq->irq >= 256)
		return -EINVAL;
	if (irqchip_in_kernel(vcpu->kvm))
		return -ENXIO;
	vcpu_load(vcpu);

	set_bit(irq->irq, vcpu->irq_pending);
	set_bit(irq->irq / BITS_PER_LONG, &vcpu->irq_summary);

	vcpu_put(vcpu);

	return 0;
}

static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma,
				    unsigned long address,
				    int *type)
{
	struct kvm_vcpu *vcpu = vma->vm_file->private_data;
	unsigned long pgoff;
	struct page *page;

	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	if (pgoff == 0)
		page = virt_to_page(vcpu->run);
	else if (pgoff == KVM_PIO_PAGE_OFFSET)
		page = virt_to_page(vcpu->pio_data);
	else
		return NOPAGE_SIGBUS;
	get_page(page);
	if (type != NULL)
		*type = VM_FAULT_MINOR;

	return page;
}

static struct vm_operations_struct kvm_vcpu_vm_ops = {
	.nopage = kvm_vcpu_nopage,
};

static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
{
	vma->vm_ops = &kvm_vcpu_vm_ops;
	return 0;
}

static int kvm_vcpu_release(struct inode *inode, struct file *filp)
{
	struct kvm_vcpu *vcpu = filp->private_data;

	fput(vcpu->kvm->filp);
	return 0;
}

static struct file_operations kvm_vcpu_fops = {
	.release        = kvm_vcpu_release,
	.unlocked_ioctl = kvm_vcpu_ioctl,
	.compat_ioctl   = kvm_vcpu_ioctl,
	.mmap           = kvm_vcpu_mmap,
};

/*
 * Allocates an inode for the vcpu.
 */
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
	int fd, r;
	struct inode *inode;
	struct file *file;

	r = anon_inode_getfd(&fd, &inode, &file,
			     "kvm-vcpu", &kvm_vcpu_fops, vcpu);
	if (r)
		return r;
	atomic_inc(&vcpu->kvm->filp->f_count);
	return fd;
}

/*
 * Creates some virtual cpus.  Good luck creating more than one.
 */
static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
{
	int r;
	struct kvm_vcpu *vcpu;

	if (!valid_vcpu(n))
		return -EINVAL;

	vcpu = kvm_arch_vcpu_create(kvm, n);
	if (IS_ERR(vcpu))
		return PTR_ERR(vcpu);

	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);

	mutex_lock(&kvm->lock);
	if (kvm->vcpus[n]) {
		r = -EEXIST;
		mutex_unlock(&kvm->lock);
		goto vcpu_destroy;
	}
	kvm->vcpus[n] = vcpu;
	mutex_unlock(&kvm->lock);

	/* Now it's all set up, let userspace reach it */
	r = create_vcpu_fd(vcpu);
	if (r < 0)
		goto unlink;
	return r;

unlink:
	mutex_lock(&kvm->lock);
	kvm->vcpus[n] = NULL;
	mutex_unlock(&kvm->lock);
vcpu_destroy:
	kvm_arch_vcpu_destroy(vcpu);
	return r;
}

static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
{
	if (sigset) {
		sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
		vcpu->sigset_active = 1;
		vcpu->sigset = *sigset;
	} else
		vcpu->sigset_active = 0;
	return 0;
}

static long kvm_vcpu_ioctl(struct file *filp,
			   unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;

	switch (ioctl) {
	case KVM_RUN:
		r = -EINVAL;
		if (arg)
			goto out;
		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
		break;
	case KVM_GET_REGS: {
		struct kvm_regs kvm_regs;

		memset(&kvm_regs, 0, sizeof kvm_regs);
		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_REGS: {
		struct kvm_regs kvm_regs;

		r = -EFAULT;
		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
			goto out;
		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_SREGS: {
		struct kvm_sregs kvm_sregs;

		memset(&kvm_sregs, 0, sizeof kvm_sregs);
		r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &kvm_sregs, sizeof kvm_sregs))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_SREGS: {
		struct kvm_sregs kvm_sregs;

		r = -EFAULT;
		if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
			goto out;
		r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_TRANSLATE: {
		struct kvm_translation tr;

		r = -EFAULT;
		if (copy_from_user(&tr, argp, sizeof tr))
			goto out;
		r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &tr, sizeof tr))
			goto out;
		r = 0;
		break;
	}
	case KVM_INTERRUPT: {
		struct kvm_interrupt irq;

		r = -EFAULT;
		if (copy_from_user(&irq, argp, sizeof irq))
			goto out;
		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_DEBUG_GUEST: {
		struct kvm_debug_guest dbg;

		r = -EFAULT;
		if (copy_from_user(&dbg, argp, sizeof dbg))
			goto out;
		r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
		if (r)
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_SIGNAL_MASK: {
		struct kvm_signal_mask __user *sigmask_arg = argp;
		struct kvm_signal_mask kvm_sigmask;
		sigset_t sigset, *p;

		p = NULL;
		if (argp) {
			r = -EFAULT;
			if (copy_from_user(&kvm_sigmask, argp,
					   sizeof kvm_sigmask))
				goto out;
			r = -EINVAL;
			if (kvm_sigmask.len != sizeof sigset)
				goto out;
			r = -EFAULT;
			if (copy_from_user(&sigset, sigmask_arg->sigset,
					   sizeof sigset))
				goto out;
			p = &sigset;
		}
		r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
		break;
	}
	case KVM_GET_FPU: {
		struct kvm_fpu fpu;

		memset(&fpu, 0, sizeof fpu);
		r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, &fpu);
		if (r)
			goto out;
		r = -EFAULT;
		if (copy_to_user(argp, &fpu, sizeof fpu))
			goto out;
		r = 0;
		break;
	}
	case KVM_SET_FPU: {
		struct kvm_fpu fpu;

		r = -EFAULT;
		if (copy_from_user(&fpu, argp, sizeof fpu))
			goto out;
		r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, &fpu);
		if (r)
			goto out;
		r = 0;
		break;
	}
	default:
		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
	}
out:
	return r;
}

static long kvm_vm_ioctl(struct file *filp,
			   unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;

	switch (ioctl) {
	case KVM_CREATE_VCPU:
		r = kvm_vm_ioctl_create_vcpu(kvm, arg);
		if (r < 0)
			goto out;
		break;
	case KVM_SET_USER_MEMORY_REGION: {
		struct kvm_userspace_memory_region kvm_userspace_mem;

		r = -EFAULT;
		if (copy_from_user(&kvm_userspace_mem, argp,
						sizeof kvm_userspace_mem))
			goto out;

		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
		if (r)
			goto out;
		break;
	}
	case KVM_GET_DIRTY_LOG: {
		struct kvm_dirty_log log;

		r = -EFAULT;
		if (copy_from_user(&log, argp, sizeof log))
			goto out;
		r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
		if (r)
			goto out;
		break;
	}
	default:
		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
	}
out:
	return r;
}

static struct page *kvm_vm_nopage(struct vm_area_struct *vma,
				  unsigned long address,
				  int *type)
{
	struct kvm *kvm = vma->vm_file->private_data;
	unsigned long pgoff;
	struct page *page;

	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	if (!kvm_is_visible_gfn(kvm, pgoff))
		return NOPAGE_SIGBUS;
	/* current->mm->mmap_sem is already held so call lockless version */
	page = __gfn_to_page(kvm, pgoff);
	if (is_error_page(page)) {
		kvm_release_page_clean(page);
		return NOPAGE_SIGBUS;
	}
	if (type != NULL)
		*type = VM_FAULT_MINOR;

	return page;
}

static struct vm_operations_struct kvm_vm_vm_ops = {
	.nopage = kvm_vm_nopage,
};

static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
{
	vma->vm_ops = &kvm_vm_vm_ops;
	return 0;
}

static struct file_operations kvm_vm_fops = {
	.release        = kvm_vm_release,
	.unlocked_ioctl = kvm_vm_ioctl,
	.compat_ioctl   = kvm_vm_ioctl,
	.mmap           = kvm_vm_mmap,
};

static int kvm_dev_ioctl_create_vm(void)
{
	int fd, r;
	struct inode *inode;
	struct file *file;
	struct kvm *kvm;

	kvm = kvm_create_vm();
	if (IS_ERR(kvm))
		return PTR_ERR(kvm);
	r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm);
	if (r) {
		kvm_destroy_vm(kvm);
		return r;
	}

	kvm->filp = file;

	return fd;
}

static long kvm_dev_ioctl(struct file *filp,
			  unsigned int ioctl, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	long r = -EINVAL;

	switch (ioctl) {
	case KVM_GET_API_VERSION:
		r = -EINVAL;
		if (arg)
			goto out;
		r = KVM_API_VERSION;
		break;
	case KVM_CREATE_VM:
		r = -EINVAL;
		if (arg)
			goto out;
		r = kvm_dev_ioctl_create_vm();
		break;
	case KVM_CHECK_EXTENSION:
		r = kvm_dev_ioctl_check_extension((long)argp);
		break;
	case KVM_GET_VCPU_MMAP_SIZE:
		r = -EINVAL;
		if (arg)
			goto out;
		r = 2 * PAGE_SIZE;
		break;
	default:
		return kvm_arch_dev_ioctl(filp, ioctl, arg);
	}
out:
	return r;
}

static struct file_operations kvm_chardev_ops = {
	.unlocked_ioctl = kvm_dev_ioctl,
	.compat_ioctl   = kvm_dev_ioctl,
};

static struct miscdevice kvm_dev = {
	KVM_MINOR,
	"kvm",
	&kvm_chardev_ops,
};

static void hardware_enable(void *junk)
{
	int cpu = raw_smp_processor_id();

	if (cpu_isset(cpu, cpus_hardware_enabled))
		return;
	cpu_set(cpu, cpus_hardware_enabled);
	kvm_arch_hardware_enable(NULL);
}

static void hardware_disable(void *junk)
{
	int cpu = raw_smp_processor_id();

	if (!cpu_isset(cpu, cpus_hardware_enabled))
		return;
	cpu_clear(cpu, cpus_hardware_enabled);
	decache_vcpus_on_cpu(cpu);
	kvm_arch_hardware_disable(NULL);
}

static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
			   void *v)
{
	int cpu = (long)v;

	val &= ~CPU_TASKS_FROZEN;
	switch (val) {
	case CPU_DYING:
		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
		       cpu);
		hardware_disable(NULL);
		break;
	case CPU_UP_CANCELED:
		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
		       cpu);
		smp_call_function_single(cpu, hardware_disable, NULL, 0, 1);
		break;
	case CPU_ONLINE:
		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
		       cpu);
		smp_call_function_single(cpu, hardware_enable, NULL, 0, 1);
		break;
	}
	return NOTIFY_OK;
}

static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
		      void *v)
{
	if (val == SYS_RESTART) {
		/*
		 * Some (well, at least mine) BIOSes hang on reboot if
		 * in vmx root mode.
		 */
		printk(KERN_INFO "kvm: exiting hardware virtualization\n");
		on_each_cpu(hardware_disable, NULL, 0, 1);
	}
	return NOTIFY_OK;
}

static struct notifier_block kvm_reboot_notifier = {
	.notifier_call = kvm_reboot,
	.priority = 0,
};

void kvm_io_bus_init(struct kvm_io_bus *bus)
{
	memset(bus, 0, sizeof(*bus));
}

void kvm_io_bus_destroy(struct kvm_io_bus *bus)
{
	int i;

	for (i = 0; i < bus->dev_count; i++) {
		struct kvm_io_device *pos = bus->devs[i];

		kvm_iodevice_destructor(pos);
	}
}

struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr)
{
	int i;

	for (i = 0; i < bus->dev_count; i++) {
		struct kvm_io_device *pos = bus->devs[i];

		if (pos->in_range(pos, addr))
			return pos;
	}

	return NULL;
}

void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev)
{
	BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1));

	bus->devs[bus->dev_count++] = dev;
}

static struct notifier_block kvm_cpu_notifier = {
	.notifier_call = kvm_cpu_hotplug,
	.priority = 20, /* must be > scheduler priority */
};

static u64 vm_stat_get(void *_offset)
{
	unsigned offset = (long)_offset;
	u64 total = 0;
	struct kvm *kvm;

	spin_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list)
		total += *(u32 *)((void *)kvm + offset);
	spin_unlock(&kvm_lock);
	return total;
}

DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n");

static u64 vcpu_stat_get(void *_offset)
{
	unsigned offset = (long)_offset;
	u64 total = 0;
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	int i;

	spin_lock(&kvm_lock);
	list_for_each_entry(kvm, &vm_list, vm_list)
		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
			vcpu = kvm->vcpus[i];
			if (vcpu)
				total += *(u32 *)((void *)vcpu + offset);
		}
	spin_unlock(&kvm_lock);
	return total;
}

DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n");

static struct file_operations *stat_fops[] = {
	[KVM_STAT_VCPU] = &vcpu_stat_fops,
	[KVM_STAT_VM]   = &vm_stat_fops,
};

static void kvm_init_debug(void)
{
	struct kvm_stats_debugfs_item *p;

	debugfs_dir = debugfs_create_dir("kvm", NULL);
	for (p = debugfs_entries; p->name; ++p)
		p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir,
						(void *)(long)p->offset,
						stat_fops[p->kind]);
}

static void kvm_exit_debug(void)
{
	struct kvm_stats_debugfs_item *p;

	for (p = debugfs_entries; p->name; ++p)
		debugfs_remove(p->dentry);
	debugfs_remove(debugfs_dir);
}

static int kvm_suspend(struct sys_device *dev, pm_message_t state)
{
	hardware_disable(NULL);
	return 0;
}

static int kvm_resume(struct sys_device *dev)
{
	hardware_enable(NULL);
	return 0;
}

static struct sysdev_class kvm_sysdev_class = {
	.name = "kvm",
	.suspend = kvm_suspend,
	.resume = kvm_resume,
};

static struct sys_device kvm_sysdev = {
	.id = 0,
	.cls = &kvm_sysdev_class,
};

struct page *bad_page;

static inline
struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
{
	return container_of(pn, struct kvm_vcpu, preempt_notifier);
}

static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
{
	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);

	kvm_arch_vcpu_load(vcpu, cpu);
}

static void kvm_sched_out(struct preempt_notifier *pn,
			  struct task_struct *next)
{
	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);

	kvm_arch_vcpu_put(vcpu);
}

int kvm_init(void *opaque, unsigned int vcpu_size,
		  struct module *module)
{
	int r;
	int cpu;

	kvm_init_debug();

	r = kvm_arch_init(opaque);
	if (r)
		goto out4;

	bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO);

	if (bad_page == NULL) {
		r = -ENOMEM;
		goto out;
	}

	r = kvm_arch_hardware_setup();
	if (r < 0)
		goto out;

	for_each_online_cpu(cpu) {
		smp_call_function_single(cpu,
				kvm_arch_check_processor_compat,
				&r, 0, 1);
		if (r < 0)
			goto out_free_0;
	}

	on_each_cpu(hardware_enable, NULL, 0, 1);
	r = register_cpu_notifier(&kvm_cpu_notifier);
	if (r)
		goto out_free_1;
	register_reboot_notifier(&kvm_reboot_notifier);

	r = sysdev_class_register(&kvm_sysdev_class);
	if (r)
		goto out_free_2;

	r = sysdev_register(&kvm_sysdev);
	if (r)
		goto out_free_3;

	/* A kmem cache lets us meet the alignment requirements of fx_save. */
	kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size,
					   __alignof__(struct kvm_vcpu),
					   0, NULL);
	if (!kvm_vcpu_cache) {
		r = -ENOMEM;
		goto out_free_4;
	}

	kvm_chardev_ops.owner = module;

	r = misc_register(&kvm_dev);
	if (r) {
		printk(KERN_ERR "kvm: misc device register failed\n");
		goto out_free;
	}

	kvm_preempt_ops.sched_in = kvm_sched_in;
	kvm_preempt_ops.sched_out = kvm_sched_out;

	return 0;

out_free:
	kmem_cache_destroy(kvm_vcpu_cache);
out_free_4:
	sysdev_unregister(&kvm_sysdev);
out_free_3:
	sysdev_class_unregister(&kvm_sysdev_class);
out_free_2:
	unregister_reboot_notifier(&kvm_reboot_notifier);
	unregister_cpu_notifier(&kvm_cpu_notifier);
out_free_1:
	on_each_cpu(hardware_disable, NULL, 0, 1);
out_free_0:
	kvm_arch_hardware_unsetup();
out:
	kvm_arch_exit();
	kvm_exit_debug();
out4:
	return r;
}
EXPORT_SYMBOL_GPL(kvm_init);

void kvm_exit(void)
{
	misc_deregister(&kvm_dev);
	kmem_cache_destroy(kvm_vcpu_cache);
	sysdev_unregister(&kvm_sysdev);
	sysdev_class_unregister(&kvm_sysdev_class);
	unregister_reboot_notifier(&kvm_reboot_notifier);
	unregister_cpu_notifier(&kvm_cpu_notifier);
	on_each_cpu(hardware_disable, NULL, 0, 1);
	kvm_arch_hardware_unsetup();
	kvm_arch_exit();
	kvm_exit_debug();
	__free_page(bad_page);
}
EXPORT_SYMBOL_GPL(kvm_exit);