forked from TritonDataCenter/illumos-kvm
-
Notifications
You must be signed in to change notification settings - Fork 11
/
kvm_svm.c
2799 lines (2361 loc) · 66.1 KB
/
kvm_svm.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
*
* AMD SVM support
*
* Copyright (C) 2006 Qumranet, Inc.
*
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Copyright 2011 Joshua M. Clulow <josh@sysmgr.org>
* Copyright 2011 Richard Lowe
*/
#include <sys/sysmacros.h>
#include <sys/types.h>
#include <sys/mach_mmu.h>
#include <asm/cpu.h>
#include <sys/x86_archext.h>
#include <sys/xc_levels.h>
#include <sys/ddi.h>
#include <sys/sunddi.h>
#include "kvm_bitops.h"
#include "kvm_msr.h"
#include "kvm_cpuid.h"
#include "kvm_impl.h"
#include "kvm_x86impl.h"
#include "kvm_cache_regs.h"
#include "kvm_host.h"
#include "kvm_iodev.h"
#include "kvm_irq.h"
#include "kvm_mmu.h"
#include "kvm_svm.h"
#include "kvm_glue_alloc.h"
#define __ex(x) __kvm_handle_fault_on_reboot(x)
static kmem_cache_t *kvm_svm_vcpu_cache = NULL;
static kmem_cache_t *kvm_svm_vmcb_cache = NULL;
static kmem_cache_t *kvm_svm_msrpm_cache = NULL;
static kmem_cache_t *kvm_svm_cpudata_cache = NULL;
static kmem_cache_t *kvm_svm_savearea_cache = NULL;
/* per-CPU structure: */
static struct svm_cpu_data **kvm_svm_cpu_data;
#define IOPM_ALLOC_ORDER 2
#define MSRPM_ALLOC_ORDER 1
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
#define SVM_FEATURE_NPT (1 << 0)
#define SVM_FEATURE_LBRV (1 << 1)
#define SVM_FEATURE_SVML (1 << 2)
#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */
#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
static const uint32_t host_save_user_msrs[] = {
MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
MSR_FS_BASE,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
};
struct vmcb_control_area {
uint16_t intercept_cr_read;
uint16_t intercept_cr_write;
uint16_t intercept_dr_read;
uint16_t intercept_dr_write;
uint32_t intercept_exceptions;
uint64_t intercept;
uint8_t reserved_1[42];
uint16_t pause_filter_count;
uint64_t iopm_base_pa;
uint64_t msrpm_base_pa;
uint64_t tsc_offset;
uint32_t asid;
uint8_t tlb_ctl;
uint8_t reserved_2[3];
uint32_t int_ctl;
uint32_t int_vector;
uint32_t int_state;
uint8_t reserved_3[4];
uint32_t exit_code;
uint32_t exit_code_hi;
uint64_t exit_info_1;
uint64_t exit_info_2;
uint32_t exit_int_info;
uint32_t exit_int_info_err;
uint64_t nested_ctl;
uint8_t reserved_4[16];
uint32_t event_inj;
uint32_t event_inj_err;
uint64_t nested_cr3;
uint64_t lbr_ctl;
uint8_t reserved_5[832];
} __attribute__((__packed__));
struct vmcb_seg {
uint16_t selector;
uint16_t attrib;
uint32_t limit;
uint64_t base;
} __attribute__((__packed__));
struct vmcb_save_area {
struct vmcb_seg es;
struct vmcb_seg cs;
struct vmcb_seg ss;
struct vmcb_seg ds;
struct vmcb_seg fs;
struct vmcb_seg gs;
struct vmcb_seg gdtr;
struct vmcb_seg ldtr;
struct vmcb_seg idtr;
struct vmcb_seg tr;
uint8_t reserved_1[43];
uint8_t cpl;
uint8_t reserved_2[4];
uint64_t efer;
uint8_t reserved_3[112];
uint64_t cr4;
uint64_t cr3;
uint64_t cr0;
uint64_t dr7;
uint64_t dr6;
uint64_t rflags;
uint64_t rip;
uint8_t reserved_4[88];
uint64_t rsp;
uint8_t reserved_5[24];
uint64_t rax;
uint64_t star;
uint64_t lstar;
uint64_t cstar;
uint64_t sfmask;
uint64_t kernel_gs_base;
uint64_t sysenter_cs;
uint64_t sysenter_esp;
uint64_t sysenter_eip;
uint64_t cr2;
uint8_t reserved_6[32];
uint64_t g_pat;
uint64_t dbgctl;
uint64_t br_from;
uint64_t br_to;
uint64_t last_excp_from;
uint64_t last_excp_to;
} __attribute__((__packed__));
struct vmcb {
struct vmcb_control_area control;
struct vmcb_save_area save;
} __attribute__((__packed__));
struct kvm_vcpu;
#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
typedef struct vcpu_svm {
struct kvm_vcpu vcpu;
struct vmcb *vmcb;
uint64_t vmcb_pa; /* physical address of svm's vmcb */
struct svm_cpu_data *svm_data;
uint64_t asid_generation;
uint64_t sysenter_esp;
uint64_t sysenter_eip;
uint64_t next_rip;
uint64_t host_user_msrs[NR_HOST_SAVE_USER_MSRS];
uint64_t host_gs_base;
uint32_t *msrpm;
char nmi_singlestep;
} vcpu_svm_t;
static int kvm_svm_has_kvm_support_override = 0;
static char npt_enabled = 1;
static int npt = 1;
/* module_param(npt, int, S_IRUGO); */
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
static struct vcpu_svm *
to_svm(struct kvm_vcpu *vcpu)
{
return ((struct vcpu_svm *)((uintptr_t)vcpu -
offsetof(struct vcpu_svm, vcpu)));
}
static void
enable_gif(struct vcpu_svm *svm)
{
svm->vcpu.arch.hflags |= HF_GIF_MASK;
}
static void
disable_gif(struct vcpu_svm *svm)
{
svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
}
static char
gif_set(struct vcpu_svm *svm)
{
return (!!(svm->vcpu.arch.hflags & HF_GIF_MASK));
}
static unsigned long iopm_base;
static void *iopm_va;
struct svm_cpu_data {
int cpu;
uint64_t asid_generation;
uint32_t max_asid;
uint32_t next_asid;
void *save_area;
uint64_t save_area_pa;
};
static uint32_t svm_features;
struct svm_init_data {
int cpu;
int r;
};
static uint32_t msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
#define MAX_INST_SIZE 15
static char
svm_has(uint32_t feat)
{
return (!!(svm_features & feat));
}
static void
cpu_svm_disable(void)
{
uint64_t efer;
wrmsrl(MSR_VM_HSAVE_PA, 0);
rdmsrl(MSR_EFER, efer);
wrmsrl(MSR_EFER, efer & ~EFER_SVME);
}
static int
cpuid_ebx(unsigned int op)
{
struct cpuid_regs cp;
cp.cp_eax = op;
cp.cp_ecx = 0;
(void) __cpuid_insn(&cp);
return (cp.cp_ebx);
}
static int
cpuid_edx(unsigned int op)
{
struct cpuid_regs cp;
cp.cp_eax = op;
cp.cp_ecx = 0;
(void) __cpuid_insn(&cp);
return (cp.cp_edx);
}
/*
* CLGI: clear global interrupt flag
*/
static void
clgi(void)
{
__asm__ volatile(__ex(SVM_CLGI));
}
/*
* STGI: set global interrupt flag
*/
static void
stgi(void)
{
__asm__ volatile(__ex(SVM_STGI));
}
/*
* INVLPGA: invalidate TLB mapping for given virtual page + asid
*/
static void invlpga(unsigned long addr, uint32_t asid)
{
__asm__ volatile(__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
}
static void
force_new_asid(struct kvm_vcpu *vcpu)
{
to_svm(vcpu)->asid_generation--;
}
static void
flush_guest_tlb(struct kvm_vcpu *vcpu)
{
force_new_asid(vcpu);
}
static void
svm_set_efer(struct kvm_vcpu *vcpu, uint64_t efer)
{
if (!npt_enabled && !(efer & EFER_LMA))
efer &= ~EFER_LME;
to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
vcpu->arch.efer = efer;
}
static void
svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
int has_error_code, uint32_t error_code)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.event_inj = nr
| SVM_EVTINJ_VALID
| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
| SVM_EVTINJ_TYPE_EXEPT;
svm->vmcb->control.event_inj_err = error_code;
}
static int
is_external_interrupt(uint32_t intr_info)
{
return ((intr_info & (SVM_EVTINJ_TYPE_MASK |
SVM_EVTINJ_VALID)) == (SVM_EVTINJ_VALID |
SVM_EVTINJ_TYPE_INTR));
}
static uint32_t
svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
struct vcpu_svm *svm = to_svm(vcpu);
uint32_t ret = 0;
if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
return (ret & mask);
}
static void
svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (mask == 0)
svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
else
svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
}
static void
skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
if (!svm->next_rip) {
if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
cmn_err(CE_NOTE, "%s: NOP\n", __func__);
return;
}
if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
cmn_err(CE_WARN, "%s: ip 0x%lx next 0x%llx\n",
__func__, kvm_rip_read(vcpu), (long long unsigned)svm->next_rip);
kvm_rip_write(vcpu, svm->next_rip);
svm_set_interrupt_shadow(vcpu, 0);
}
static int
kvm_svm_has_kvm_support(void)
{
if (kvm_svm_has_kvm_support_override)
return (kvm_svm_has_kvm_support_override > 0 ? 0 : -1);
if (is_x86_feature(x86_featureset, X86FSET_SVM))
return (0);
return (-1);
}
static void
svm_hardware_disable(void *garbage)
{
cpu_svm_disable();
}
static int
svm_hardware_enable(void *garbage)
{
struct svm_cpu_data *sd;
uint64_t efer;
int cpu = curthread->t_cpu->cpu_seqid;
rdmsrl(MSR_EFER, efer);
if (efer & EFER_SVME)
return (DDI_FAILURE);
sd = kvm_svm_cpu_data[cpu];
if (!sd) {
cmn_err(CE_WARN, "svm_hardware_enable: svm_data is "
"NULL on %d\n", cpu);
return (DDI_FAILURE);
}
sd->asid_generation = 1;
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
wrmsrl(MSR_EFER, efer | EFER_SVME);
wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa);
return (0);
}
static void
svm_cpu_uninit(int cpu)
{
struct svm_cpu_data *sd = kvm_svm_cpu_data[cpu];
if (!sd)
return;
kvm_svm_cpu_data[cpu] = NULL;
kmem_cache_free(kvm_svm_savearea_cache, sd->save_area);
kmem_cache_free(kvm_svm_cpudata_cache, sd);
}
static int
svm_cpu_init(int cpu)
{
struct svm_cpu_data *sd;
int r;
sd = kmem_cache_alloc(kvm_svm_cpudata_cache, KM_SLEEP);
if (!sd)
return (ENOMEM);
sd->cpu = cpu;
sd->save_area = kmem_cache_alloc(kvm_svm_savearea_cache, KM_SLEEP);
if (!sd->save_area) {
kmem_cache_free(kvm_svm_cpudata_cache, sd);
return (ENOMEM);
}
/*
* Store the physical address now so that we don't try and
* take locks we cannot hold in a crosscall later.
*/
sd->save_area_pa = kvm_va2pa((caddr_t)sd->save_area);
kvm_svm_cpu_data[cpu] = sd;
return (0);
}
static void
set_msr_interception(uint32_t *msrpm, unsigned msr, int read, int write)
{
int i;
for (i = 0; i < NUM_MSR_MAPS; i++) {
if (msr >= msrpm_ranges[i] &&
msr < msrpm_ranges[i] + MSRS_IN_RANGE) {
uint32_t msr_offset = (i * MSRS_IN_RANGE + msr -
msrpm_ranges[i]) * 2;
uint32_t *base = msrpm + (msr_offset / 32);
uint32_t msr_shift = msr_offset % 32;
uint32_t mask = ((write) ? 0 : 2) | ((read) ? 0 : 1);
*base = (*base & ~(0x3 << msr_shift)) |
(mask << msr_shift);
return;
}
}
cmn_err(CE_PANIC, "reached end of set_msr_interception()\n");
}
static void
svm_vcpu_init_msrpm(uint32_t *msrpm)
{
memset(msrpm, 0xff, SVM_ALLOC_MSRPM_SIZE);
set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
}
static void
svm_enable_lbrv(struct vcpu_svm *svm)
{
uint32_t *msrpm = svm->msrpm;
svm->vmcb->control.lbr_ctl = 1;
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
}
static void
svm_disable_lbrv(struct vcpu_svm *svm)
{
uint32_t *msrpm = svm->msrpm;
svm->vmcb->control.lbr_ctl = 0;
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
static int
svm_hardware_setup(void)
{
int cpu;
int r, i;
iopm_va = kvm_glue_alloc(SVM_ALLOC_IOPM_SIZE, SVM_ALLOC_IOPM_ALIGN, 0);
if (iopm_va == NULL)
return (ENOMEM);
memset(iopm_va, 0xff, SVM_ALLOC_IOPM_SIZE);
iopm_base = kvm_va2pa((caddr_t)iopm_va);
if (is_x86_feature(x86_featureset, X86FSET_NX))
kvm_enable_efer_bits(EFER_NX);
/* XXX figure this out */
#if 0
if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
kvm_enable_efer_bits(EFER_FFXSR);
#endif
kvm_svm_cpu_data = kmem_alloc(ncpus * sizeof (struct svm_cpu_data *),
KM_SLEEP);
for (i = 0; i < ncpus; i++) {
kvm_svm_cpu_data[i] = NULL;
}
for (i = 0; i < ncpus; i++) {
r = svm_cpu_init(i);
if (r) {
kvm_glue_free(iopm_va, SVM_ALLOC_IOPM_SIZE);
iopm_base = 0;
iopm_va = NULL;
return (r);
}
}
svm_features = cpuid_edx(SVM_CPUID_FUNC);
if (!svm_has(SVM_FEATURE_NPT))
npt_enabled = 0;
if (npt_enabled && !npt) {
npt_enabled = 0;
}
if (npt_enabled) {
kvm_enable_tdp();
} else
kvm_disable_tdp();
return (0);
}
static void
svm_hardware_unsetup(void)
{
int cpu;
for (cpu = 0; cpu < ncpus; cpu++) {
svm_cpu_uninit(cpu);
}
kvm_glue_free(iopm_va, SVM_ALLOC_IOPM_SIZE);
iopm_base = 0;
iopm_va = NULL;
}
static void
init_seg(struct vmcb_seg *seg)
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
seg->limit = 0xffff;
seg->base = 0;
}
static void
init_sys_seg(struct vmcb_seg *seg, uint32_t type)
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | type;
seg->limit = 0xffff;
seg->base = 0;
}
static void
init_vmcb(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
svm->vcpu.fpu_active = 1;
control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
control->intercept_cr_write = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK |
INTERCEPT_CR8_MASK;
control->intercept_dr_read = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
INTERCEPT_DR4_MASK |
INTERCEPT_DR5_MASK |
INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
control->intercept_dr_write = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
INTERCEPT_DR4_MASK |
INTERCEPT_DR5_MASK |
INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
control->intercept_exceptions = (1 << PF_VECTOR) |
(1 << UD_VECTOR) |
(1 << MC_VECTOR);
control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
(1ULL << INTERCEPT_SELECTIVE_CR0) |
(1ULL << INTERCEPT_CPUID) |
(1ULL << INTERCEPT_INVD) |
(1ULL << INTERCEPT_HLT) |
(1ULL << INTERCEPT_INVLPG) |
(1ULL << INTERCEPT_INVLPGA) |
(1ULL << INTERCEPT_IOIO_PROT) |
(1ULL << INTERCEPT_MSR_PROT) |
(1ULL << INTERCEPT_TASK_SWITCH) |
(1ULL << INTERCEPT_SHUTDOWN) |
(1ULL << INTERCEPT_VMRUN) |
(1ULL << INTERCEPT_VMMCALL) |
(1ULL << INTERCEPT_VMLOAD) |
(1ULL << INTERCEPT_VMSAVE) |
(1ULL << INTERCEPT_STGI) |
(1ULL << INTERCEPT_CLGI) |
(1ULL << INTERCEPT_SKINIT) |
(1ULL << INTERCEPT_WBINVD) |
(1ULL << INTERCEPT_MONITOR) |
(1ULL << INTERCEPT_MWAIT);
control->iopm_base_pa = iopm_base;
control->msrpm_base_pa = kvm_va2pa((caddr_t)svm->msrpm);
control->tsc_offset = 0;
control->int_ctl = V_INTR_MASKING_MASK;
init_seg(&save->es);
init_seg(&save->ss);
init_seg(&save->ds);
init_seg(&save->fs);
init_seg(&save->gs);
save->cs.selector = 0xf000;
/* Executable/Readable Code Segment */
save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK |
SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK;
save->cs.limit = 0xffff;
/*
* cs.base should really be 0xffff0000, but vmx can't handle that, so
* be consistent with it.
*
* Replace when we have real mode working for vmx.
*/
save->cs.base = 0xf0000;
save->gdtr.limit = 0xffff;
save->idtr.limit = 0xffff;
init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
save->efer = EFER_SVME;
save->dr6 = 0xffff0ff0;
save->dr7 = 0x400;
save->rflags = 2;
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
/*
* This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0);
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
if (npt_enabled) {
/* Setup VMCB for Nested Paging */
control->nested_ctl = 1;
control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) |
(1ULL << INTERCEPT_INVLPG));
control->intercept_exceptions &= ~(1 << PF_VECTOR);
control->intercept_cr_read &= ~INTERCEPT_CR3_MASK;
control->intercept_cr_write &= ~INTERCEPT_CR3_MASK;
save->g_pat = 0x0007040600070406ULL;
save->cr3 = 0;
save->cr4 = 0;
}
force_new_asid(&svm->vcpu);
svm->vcpu.arch.hflags = 0;
if (svm_has(SVM_FEATURE_PAUSE_FILTER)) {
control->pause_filter_count = 3000;
control->intercept |= (1ULL << INTERCEPT_PAUSE);
}
enable_gif(svm);
}
static int
svm_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
init_vmcb(svm);
if (!kvm_vcpu_is_bsp(vcpu)) {
kvm_rip_write(vcpu, 0);
svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12;
svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8;
}
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
return (0);
}
static struct kvm_vcpu *
svm_create_vcpu(struct kvm *kvm, unsigned int id)
{
struct vcpu_svm *svm;
int err;
svm = kmem_cache_alloc(kvm_svm_vcpu_cache, KM_SLEEP);
if (!svm) {
return (NULL);
}
err = kvm_vcpu_init(&svm->vcpu, kvm, id);
if (err) {
kmem_cache_free(kvm_svm_vcpu_cache, svm);
return (NULL);
}
/* VMCBs need to be aligned on 4k boundaries */
svm->vmcb = kmem_cache_alloc(kvm_svm_vmcb_cache, KM_SLEEP);
if (!svm->vmcb) {
kvm_vcpu_uninit(&svm->vcpu);
kmem_cache_free(kvm_svm_vcpu_cache, svm);
return (NULL);
}
svm->vmcb_pa = kvm_va2pa((caddr_t)svm->vmcb);
svm->msrpm = kmem_cache_alloc(kvm_svm_msrpm_cache, KM_SLEEP);
if (!svm->msrpm) {
kmem_cache_free(kvm_svm_vmcb_cache, svm->vmcb);
kvm_vcpu_uninit(&svm->vcpu);
kmem_cache_free(kvm_svm_vcpu_cache, svm);
return (NULL);
}
svm_vcpu_init_msrpm(svm->msrpm);
svm->asid_generation = 0;
init_vmcb(svm);
fx_init(&svm->vcpu);
svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
return (&svm->vcpu);
}
static void
svm_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
kmem_cache_free(kvm_svm_vmcb_cache, svm->vmcb);
kmem_cache_free(kvm_svm_msrpm_cache, svm->msrpm);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_svm_vcpu_cache, svm);
}
static void
svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
int i;
uint64_t tsc_this, delta, new_offset;
if (cpu != vcpu->cpu) {
vcpu->cpu = cpu;
/* kvm_migrate_timers(vcpu); */
svm->asid_generation = 0;
/*
* XXX per-cpu TSS/GDT/IDT/GSBASE is, I believe,
* taken care of mostly by the VMRUN instruction
* but also by save/load behaviour in vcpu_run.
*/
/*
* Make sure the time stamp counter is monotonic.
*/
rdtscll(tsc_this);
if (tsc_this < vcpu->arch.host_tsc) {
delta = vcpu->arch.host_tsc - tsc_this;
svm->vmcb->control.tsc_offset += delta;
}
}
for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
}
}
static void
svm_vcpu_put(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
int i;
KVM_VCPU_KSTAT_INC(vcpu, kvmvs_host_state_reload);
for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
}
rdtscll(vcpu->arch.host_tsc);
}
static unsigned long
svm_get_rflags(struct kvm_vcpu *vcpu)
{
return (to_svm(vcpu)->vmcb->save.rflags);
}
static void
svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
to_svm(vcpu)->vmcb->save.rflags = rflags;
}
static void
svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
switch (reg) {
case VCPU_EXREG_PDPTR:
if (!npt_enabled)
cmn_err(CE_PANIC, "had !npt_enabled in "
"svm_cache_reg()\n");
load_pdptrs(vcpu, vcpu->arch.cr3);
break;
default:
cmn_err(CE_PANIC, "fell through switch in svm_cache_reg()\n");
}
}
static void
svm_set_vintr(struct vcpu_svm *svm)
{
svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR;
}
static void
svm_clear_vintr(struct vcpu_svm *svm)
{
svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR);
}
static struct vmcb_seg *
svm_seg(struct kvm_vcpu *vcpu, int seg)
{
struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
switch (seg) {
case VCPU_SREG_CS: return (&save->cs);
case VCPU_SREG_DS: return (&save->ds);
case VCPU_SREG_ES: return (&save->es);
case VCPU_SREG_FS: return (&save->fs);
case VCPU_SREG_GS: return (&save->gs);
case VCPU_SREG_SS: return (&save->ss);
case VCPU_SREG_TR: return (&save->tr);
case VCPU_SREG_LDTR: return (&save->ldtr);
}
cmn_err(CE_PANIC, "fell through switch in svm_seg()\n");
return (NULL);
}
static uint64_t
svm_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct vmcb_seg *s = svm_seg(vcpu, seg);
return (s->base);
}
static void
svm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
{
struct vmcb_seg *s = svm_seg(vcpu, seg);
var->base = s->base;
var->limit = s->limit;
var->selector = s->selector;
var->type = s->attrib & SVM_SELECTOR_TYPE_MASK;
var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1;
var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1;
var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1;
var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
/*
* AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
var->unusable = !var->present || (var->type == 0);
switch (seg) {
case VCPU_SREG_CS:
/*
* SVM always stores 0 for the 'G' bit in the CS selector in
* the VMCB on a VMEXIT. This hurts cross-vendor migration:
* Intel's VMENTRY has a check on the 'G' bit.
*/
var->g = s->limit > 0xfffff;