forked from spotify/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathkvm_main.c
2404 lines (2057 loc) · 53.3 KB
/
kvm_main.c
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
/*
* 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 <[email protected]>
* Yaniv Kamay <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include "iodev.h"
#include <linux/kvm_host.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 <linux/swap.h>
#include <asm/processor.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
#include "coalesced_mmio.h"
#endif
#ifdef KVM_CAP_DEVICE_ASSIGNMENT
#include <linux/pci.h>
#include <linux/interrupt.h>
#include "irq.h"
#endif
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
static int msi2intx = 1;
module_param(msi2intx, bool, 0);
DEFINE_SPINLOCK(kvm_lock);
LIST_HEAD(vm_list);
static cpumask_var_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;
struct dentry *kvm_debugfs_dir;
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
static bool kvm_rebooting;
#ifdef KVM_CAP_DEVICE_ASSIGNMENT
static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
int assigned_dev_id)
{
struct list_head *ptr;
struct kvm_assigned_dev_kernel *match;
list_for_each(ptr, head) {
match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
if (match->assigned_dev_id == assigned_dev_id)
return match;
}
return NULL;
}
static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
{
struct kvm_assigned_dev_kernel *assigned_dev;
assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
interrupt_work);
/* This is taken to safely inject irq inside the guest. When
* the interrupt injection (or the ioapic code) uses a
* finer-grained lock, update this
*/
mutex_lock(&assigned_dev->kvm->lock);
kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
assigned_dev->guest_irq, 1);
if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) {
enable_irq(assigned_dev->host_irq);
assigned_dev->host_irq_disabled = false;
}
mutex_unlock(&assigned_dev->kvm->lock);
}
static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
{
struct kvm_assigned_dev_kernel *assigned_dev =
(struct kvm_assigned_dev_kernel *) dev_id;
schedule_work(&assigned_dev->interrupt_work);
disable_irq_nosync(irq);
assigned_dev->host_irq_disabled = true;
return IRQ_HANDLED;
}
/* Ack the irq line for an assigned device */
static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
{
struct kvm_assigned_dev_kernel *dev;
if (kian->gsi == -1)
return;
dev = container_of(kian, struct kvm_assigned_dev_kernel,
ack_notifier);
kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
/* The guest irq may be shared so this ack may be
* from another device.
*/
if (dev->host_irq_disabled) {
enable_irq(dev->host_irq);
dev->host_irq_disabled = false;
}
}
/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
static void kvm_free_assigned_irq(struct kvm *kvm,
struct kvm_assigned_dev_kernel *assigned_dev)
{
if (!irqchip_in_kernel(kvm))
return;
kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
if (assigned_dev->irq_source_id != -1)
kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
assigned_dev->irq_source_id = -1;
if (!assigned_dev->irq_requested_type)
return;
/*
* In kvm_free_device_irq, cancel_work_sync return true if:
* 1. work is scheduled, and then cancelled.
* 2. work callback is executed.
*
* The first one ensured that the irq is disabled and no more events
* would happen. But for the second one, the irq may be enabled (e.g.
* for MSI). So we disable irq here to prevent further events.
*
* Notice this maybe result in nested disable if the interrupt type is
* INTx, but it's OK for we are going to free it.
*
* If this function is a part of VM destroy, please ensure that till
* now, the kvm state is still legal for probably we also have to wait
* interrupt_work done.
*/
disable_irq_nosync(assigned_dev->host_irq);
cancel_work_sync(&assigned_dev->interrupt_work);
free_irq(assigned_dev->host_irq, (void *)assigned_dev);
if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
pci_disable_msi(assigned_dev->dev);
assigned_dev->irq_requested_type = 0;
}
static void kvm_free_assigned_device(struct kvm *kvm,
struct kvm_assigned_dev_kernel
*assigned_dev)
{
kvm_free_assigned_irq(kvm, assigned_dev);
pci_reset_function(assigned_dev->dev);
pci_release_regions(assigned_dev->dev);
pci_disable_device(assigned_dev->dev);
pci_dev_put(assigned_dev->dev);
list_del(&assigned_dev->list);
kfree(assigned_dev);
}
void kvm_free_all_assigned_devices(struct kvm *kvm)
{
struct list_head *ptr, *ptr2;
struct kvm_assigned_dev_kernel *assigned_dev;
list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
assigned_dev = list_entry(ptr,
struct kvm_assigned_dev_kernel,
list);
kvm_free_assigned_device(kvm, assigned_dev);
}
}
static int assigned_device_update_intx(struct kvm *kvm,
struct kvm_assigned_dev_kernel *adev,
struct kvm_assigned_irq *airq)
{
adev->guest_irq = airq->guest_irq;
adev->ack_notifier.gsi = airq->guest_irq;
if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX)
return 0;
if (irqchip_in_kernel(kvm)) {
if (!msi2intx &&
(adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) {
free_irq(adev->host_irq, (void *)adev);
pci_disable_msi(adev->dev);
}
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
if (airq->host_irq)
adev->host_irq = airq->host_irq;
else
adev->host_irq = adev->dev->irq;
/* Even though this is PCI, we don't want to use shared
* interrupts. Sharing host devices with guest-assigned devices
* on the same interrupt line is not a happy situation: there
* are going to be long delays in accepting, acking, etc.
*/
if (request_irq(adev->host_irq, kvm_assigned_dev_intr,
0, "kvm_assigned_intx_device", (void *)adev))
return -EIO;
}
adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX |
KVM_ASSIGNED_DEV_HOST_INTX;
return 0;
}
#ifdef CONFIG_X86
static int assigned_device_update_msi(struct kvm *kvm,
struct kvm_assigned_dev_kernel *adev,
struct kvm_assigned_irq *airq)
{
int r;
adev->guest_irq = airq->guest_irq;
if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
/* x86 don't care upper address of guest msi message addr */
adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI;
adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX;
adev->ack_notifier.gsi = -1;
} else if (msi2intx) {
adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX;
adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI;
adev->ack_notifier.gsi = airq->guest_irq;
} else {
/*
* Guest require to disable device MSI, we disable MSI and
* re-enable INTx by default again. Notice it's only for
* non-msi2intx.
*/
assigned_device_update_intx(kvm, adev, airq);
return 0;
}
if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
return 0;
if (irqchip_in_kernel(kvm)) {
if (!msi2intx) {
if (adev->irq_requested_type &
KVM_ASSIGNED_DEV_HOST_INTX)
free_irq(adev->host_irq, (void *)adev);
r = pci_enable_msi(adev->dev);
if (r)
return r;
}
adev->host_irq = adev->dev->irq;
if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0,
"kvm_assigned_msi_device", (void *)adev))
return -EIO;
}
if (!msi2intx)
adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI;
adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI;
return 0;
}
#endif
static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
struct kvm_assigned_irq
*assigned_irq)
{
int r = 0;
struct kvm_assigned_dev_kernel *match;
u32 current_flags = 0, changed_flags;
mutex_lock(&kvm->lock);
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
assigned_irq->assigned_dev_id);
if (!match) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
if (!match->irq_requested_type) {
INIT_WORK(&match->interrupt_work,
kvm_assigned_dev_interrupt_work_handler);
if (irqchip_in_kernel(kvm)) {
/* Register ack nofitier */
match->ack_notifier.gsi = -1;
match->ack_notifier.irq_acked =
kvm_assigned_dev_ack_irq;
kvm_register_irq_ack_notifier(kvm,
&match->ack_notifier);
/* Request IRQ source ID */
r = kvm_request_irq_source_id(kvm);
if (r < 0)
goto out_release;
else
match->irq_source_id = r;
#ifdef CONFIG_X86
/* Determine host device irq type, we can know the
* result from dev->msi_enabled */
if (msi2intx)
pci_enable_msi(match->dev);
#endif
}
}
if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) &&
(match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI))
current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI;
changed_flags = assigned_irq->flags ^ current_flags;
if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) ||
(msi2intx && match->dev->msi_enabled)) {
#ifdef CONFIG_X86
r = assigned_device_update_msi(kvm, match, assigned_irq);
if (r) {
printk(KERN_WARNING "kvm: failed to enable "
"MSI device!\n");
goto out_release;
}
#else
r = -ENOTTY;
#endif
} else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) {
/* Host device IRQ 0 means don't support INTx */
if (!msi2intx) {
printk(KERN_WARNING
"kvm: wait device to enable MSI!\n");
r = 0;
} else {
printk(KERN_WARNING
"kvm: failed to enable MSI device!\n");
r = -ENOTTY;
goto out_release;
}
} else {
/* Non-sharing INTx mode */
r = assigned_device_update_intx(kvm, match, assigned_irq);
if (r) {
printk(KERN_WARNING "kvm: failed to enable "
"INTx device!\n");
goto out_release;
}
}
mutex_unlock(&kvm->lock);
return r;
out_release:
mutex_unlock(&kvm->lock);
kvm_free_assigned_device(kvm, match);
return r;
}
static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
struct kvm_assigned_pci_dev *assigned_dev)
{
int r = 0;
struct kvm_assigned_dev_kernel *match;
struct pci_dev *dev;
down_read(&kvm->slots_lock);
mutex_lock(&kvm->lock);
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
assigned_dev->assigned_dev_id);
if (match) {
/* device already assigned */
r = -EINVAL;
goto out;
}
match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
if (match == NULL) {
printk(KERN_INFO "%s: Couldn't allocate memory\n",
__func__);
r = -ENOMEM;
goto out;
}
dev = pci_get_bus_and_slot(assigned_dev->busnr,
assigned_dev->devfn);
if (!dev) {
printk(KERN_INFO "%s: host device not found\n", __func__);
r = -EINVAL;
goto out_free;
}
if (pci_enable_device(dev)) {
printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
r = -EBUSY;
goto out_put;
}
r = pci_request_regions(dev, "kvm_assigned_device");
if (r) {
printk(KERN_INFO "%s: Could not get access to device regions\n",
__func__);
goto out_disable;
}
pci_reset_function(dev);
match->assigned_dev_id = assigned_dev->assigned_dev_id;
match->host_busnr = assigned_dev->busnr;
match->host_devfn = assigned_dev->devfn;
match->flags = assigned_dev->flags;
match->dev = dev;
match->irq_source_id = -1;
match->kvm = kvm;
list_add(&match->list, &kvm->arch.assigned_dev_head);
if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
if (!kvm->arch.iommu_domain) {
r = kvm_iommu_map_guest(kvm);
if (r)
goto out_list_del;
}
r = kvm_assign_device(kvm, match);
if (r)
goto out_list_del;
}
out:
mutex_unlock(&kvm->lock);
up_read(&kvm->slots_lock);
return r;
out_list_del:
list_del(&match->list);
pci_release_regions(dev);
out_disable:
pci_disable_device(dev);
out_put:
pci_dev_put(dev);
out_free:
kfree(match);
mutex_unlock(&kvm->lock);
up_read(&kvm->slots_lock);
return r;
}
#endif
#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
struct kvm_assigned_pci_dev *assigned_dev)
{
int r = 0;
struct kvm_assigned_dev_kernel *match;
mutex_lock(&kvm->lock);
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
assigned_dev->assigned_dev_id);
if (!match) {
printk(KERN_INFO "%s: device hasn't been assigned before, "
"so cannot be deassigned\n", __func__);
r = -EINVAL;
goto out;
}
if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
kvm_deassign_device(kvm, match);
kvm_free_assigned_device(kvm, match);
out:
mutex_unlock(&kvm->lock);
return r;
}
#endif
static inline int valid_vcpu(int n)
{
return likely(n >= 0 && n < KVM_MAX_VCPUS);
}
inline int kvm_is_mmio_pfn(pfn_t pfn)
{
if (pfn_valid(pfn)) {
struct page *page = compound_head(pfn_to_page(pfn));
return PageReserved(page);
}
return true;
}
/*
* 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)
{
}
static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
int i, cpu, me;
cpumask_var_t cpus;
bool called = true;
struct kvm_vcpu *vcpu;
if (alloc_cpumask_var(&cpus, GFP_ATOMIC))
cpumask_clear(cpus);
me = get_cpu();
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
vcpu = kvm->vcpus[i];
if (!vcpu)
continue;
if (test_and_set_bit(req, &vcpu->requests))
continue;
cpu = vcpu->cpu;
if (cpus != NULL && cpu != -1 && cpu != me)
cpumask_set_cpu(cpu, cpus);
}
if (unlikely(cpus == NULL))
smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1);
else if (!cpumask_empty(cpus))
smp_call_function_many(cpus, ack_flush, NULL, 1);
else
called = false;
put_cpu();
free_cpumask_var(cpus);
return called;
}
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.remote_tlb_flush;
}
void kvm_reload_remote_mmus(struct kvm *kvm)
{
make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
}
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);
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
{
return container_of(mn, struct kvm, mmu_notifier);
}
static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int need_tlb_flush;
/*
* When ->invalidate_page runs, the linux pte has been zapped
* already but the page is still allocated until
* ->invalidate_page returns. So if we increase the sequence
* here the kvm page fault will notice if the spte can't be
* established because the page is going to be freed. If
* instead the kvm page fault establishes the spte before
* ->invalidate_page runs, kvm_unmap_hva will release it
* before returning.
*
* The sequence increase only need to be seen at spin_unlock
* time, and not at spin_lock time.
*
* Increasing the sequence after the spin_unlock would be
* unsafe because the kvm page fault could then establish the
* pte after kvm_unmap_hva returned, without noticing the page
* is going to be freed.
*/
spin_lock(&kvm->mmu_lock);
kvm->mmu_notifier_seq++;
need_tlb_flush = kvm_unmap_hva(kvm, address);
spin_unlock(&kvm->mmu_lock);
/* we've to flush the tlb before the pages can be freed */
if (need_tlb_flush)
kvm_flush_remote_tlbs(kvm);
}
static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int need_tlb_flush = 0;
spin_lock(&kvm->mmu_lock);
/*
* The count increase must become visible at unlock time as no
* spte can be established without taking the mmu_lock and
* count is also read inside the mmu_lock critical section.
*/
kvm->mmu_notifier_count++;
for (; start < end; start += PAGE_SIZE)
need_tlb_flush |= kvm_unmap_hva(kvm, start);
spin_unlock(&kvm->mmu_lock);
/* we've to flush the tlb before the pages can be freed */
if (need_tlb_flush)
kvm_flush_remote_tlbs(kvm);
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
spin_lock(&kvm->mmu_lock);
/*
* This sequence increase will notify the kvm page fault that
* the page that is going to be mapped in the spte could have
* been freed.
*/
kvm->mmu_notifier_seq++;
/*
* The above sequence increase must be visible before the
* below count decrease but both values are read by the kvm
* page fault under mmu_lock spinlock so we don't need to add
* a smb_wmb() here in between the two.
*/
kvm->mmu_notifier_count--;
spin_unlock(&kvm->mmu_lock);
BUG_ON(kvm->mmu_notifier_count < 0);
}
static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int young;
spin_lock(&kvm->mmu_lock);
young = kvm_age_hva(kvm, address);
spin_unlock(&kvm->mmu_lock);
if (young)
kvm_flush_remote_tlbs(kvm);
return young;
}
static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
kvm_arch_flush_shadow(kvm);
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
.invalidate_page = kvm_mmu_notifier_invalidate_page,
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
.release = kvm_mmu_notifier_release,
};
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kvm_arch_create_vm();
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
struct page *page;
#endif
if (IS_ERR(kvm))
goto out;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
INIT_LIST_HEAD(&kvm->irq_routing);
INIT_HLIST_HEAD(&kvm->mask_notifier_list);
#endif
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page) {
kfree(kvm);
return ERR_PTR(-ENOMEM);
}
kvm->coalesced_mmio_ring =
(struct kvm_coalesced_mmio_ring *)page_address(page);
#endif
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
{
int err;
kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;
err = mmu_notifier_register(&kvm->mmu_notifier, current->mm);
if (err) {
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
put_page(page);
#endif
kfree(kvm);
return ERR_PTR(err);
}
}
#endif
kvm->mm = current->mm;
atomic_inc(&kvm->mm->mm_count);
spin_lock_init(&kvm->mmu_lock);
kvm_io_bus_init(&kvm->pio_bus);
mutex_init(&kvm->lock);
kvm_io_bus_init(&kvm->mmio_bus);
init_rwsem(&kvm->slots_lock);
atomic_set(&kvm->users_count, 1);
spin_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
spin_unlock(&kvm_lock);
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
kvm_coalesced_mmio_init(kvm);
#endif
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);
if (!dont || free->lpage_info != dont->lpage_info)
vfree(free->lpage_info);
free->npages = 0;
free->dirty_bitmap = NULL;
free->rmap = NULL;
free->lpage_info = 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)
{
struct mm_struct *mm = kvm->mm;
kvm_arch_sync_events(kvm);
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
kvm_free_irq_routing(kvm);
kvm_io_bus_destroy(&kvm->pio_bus);
kvm_io_bus_destroy(&kvm->mmio_bus);
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
if (kvm->coalesced_mmio_ring != NULL)
free_page((unsigned long)kvm->coalesced_mmio_ring);
#endif
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
#endif
kvm_arch_destroy_vm(kvm);
mmdrop(mm);
}
void kvm_get_kvm(struct kvm *kvm)
{
atomic_inc(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm);
void kvm_put_kvm(struct kvm *kvm)
{
if (atomic_dec_and_test(&kvm->users_count))
kvm_destroy_vm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_put_kvm);
static int kvm_vm_release(struct inode *inode, struct file *filp)
{
struct kvm *kvm = filp->private_data;
kvm_put_kvm(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 mmap_sem for write.
*/
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 (user_alloc && (mem->userspace_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 */
#ifndef CONFIG_S390
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;
/*
* hva_to_rmmap() serialzies with the mmu_lock and to be
* safe it has to ignore memslots with !user_alloc &&
* !userspace_addr.
*/
if (user_alloc)
new.userspace_addr = mem->userspace_addr;
else
new.userspace_addr = 0;
}
if (npages && !new.lpage_info) {
int largepages = npages / KVM_PAGES_PER_HPAGE;
if (npages % KVM_PAGES_PER_HPAGE)
largepages++;