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
|
/*
* Kernel-based Virtual Machine driver for Linux
*
* This header defines architecture specific interfaces, x86 version
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#ifndef _ASM_X86_KVM_HOST_H
#define _ASM_X86_KVM_HOST_H
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
#include <linux/kvm_types.h>
#include <asm/pvclock-abi.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#define KVM_MAX_VCPUS 16
#define KVM_MEMORY_SLOTS 32
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \
0xFFFFFF0000000000ULL)
#define KVM_GUEST_CR0_MASK \
(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
| X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON \
(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
| X86_CR0_MP)
#define KVM_GUEST_CR4_MASK \
(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
#define INVALID_PAGE (~(hpa_t)0)
#define UNMAPPED_GVA (~(gpa_t)0)
/* shadow tables are PAE even on non-PAE hosts */
#define KVM_HPAGE_SHIFT 21
#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
#define DE_VECTOR 0
#define DB_VECTOR 1
#define BP_VECTOR 3
#define OF_VECTOR 4
#define BR_VECTOR 5
#define UD_VECTOR 6
#define NM_VECTOR 7
#define DF_VECTOR 8
#define TS_VECTOR 10
#define NP_VECTOR 11
#define SS_VECTOR 12
#define GP_VECTOR 13
#define PF_VECTOR 14
#define MF_VECTOR 16
#define MC_VECTOR 18
#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03
#define IOPL_SHIFT 12
#define KVM_ALIAS_SLOTS 4
#define KVM_PERMILLE_MMU_PAGES 20
#define KVM_MIN_ALLOC_MMU_PAGES 64
#define KVM_MMU_HASH_SHIFT 10
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40
#define KVM_NR_FIXED_MTRR_REGION 88
#define KVM_NR_VAR_MTRR 8
extern spinlock_t kvm_lock;
extern struct list_head vm_list;
struct kvm_vcpu;
struct kvm;
enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
VCPU_REGS_RDX = 2,
VCPU_REGS_RBX = 3,
VCPU_REGS_RSP = 4,
VCPU_REGS_RBP = 5,
VCPU_REGS_RSI = 6,
VCPU_REGS_RDI = 7,
#ifdef CONFIG_X86_64
VCPU_REGS_R8 = 8,
VCPU_REGS_R9 = 9,
VCPU_REGS_R10 = 10,
VCPU_REGS_R11 = 11,
VCPU_REGS_R12 = 12,
VCPU_REGS_R13 = 13,
VCPU_REGS_R14 = 14,
VCPU_REGS_R15 = 15,
#endif
VCPU_REGS_RIP,
NR_VCPU_REGS
};
enum {
VCPU_SREG_ES,
VCPU_SREG_CS,
VCPU_SREG_SS,
VCPU_SREG_DS,
VCPU_SREG_FS,
VCPU_SREG_GS,
VCPU_SREG_TR,
VCPU_SREG_LDTR,
};
#include <asm/kvm_x86_emulate.h>
#define KVM_NR_MEM_OBJS 40
#define KVM_NR_DB_REGS 4
#define DR6_BD (1 << 13)
#define DR6_BS (1 << 14)
#define DR6_FIXED_1 0xffff0ff0
#define DR6_VOLATILE 0x0000e00f
#define DR7_BP_EN_MASK 0x000000ff
#define DR7_GE (1 << 9)
#define DR7_GD (1 << 13)
#define DR7_FIXED_1 0x00000400
#define DR7_VOLATILE 0xffff23ff
/*
* We don't want allocation failures within the mmu code, so we preallocate
* enough memory for a single page fault in a cache.
*/
struct kvm_mmu_memory_cache {
int nobjs;
void *objects[KVM_NR_MEM_OBJS];
};
#define NR_PTE_CHAIN_ENTRIES 5
struct kvm_pte_chain {
u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
struct hlist_node link;
};
/*
* kvm_mmu_page_role, below, is defined as:
*
* bits 0:3 - total guest paging levels (2-4, or zero for real mode)
* bits 4:7 - page table level for this shadow (1-4)
* bits 8:9 - page table quadrant for 2-level guests
* bit 16 - direct mapping of virtual to physical mapping at gfn
* used for real mode and two-dimensional paging
* bits 17:19 - common access permissions for all ptes in this shadow page
*/
union kvm_mmu_page_role {
unsigned word;
struct {
unsigned glevels:4;
unsigned level:4;
unsigned quadrant:2;
unsigned pad_for_nice_hex_output:6;
unsigned direct:1;
unsigned access:3;
unsigned invalid:1;
unsigned cr4_pge:1;
unsigned nxe:1;
};
};
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
struct list_head oos_link;
/*
* The following two entries are used to key the shadow page in the
* hash table.
*/
gfn_t gfn;
union kvm_mmu_page_role role;
u64 *spt;
/* hold the gfn of each spte inside spt */
gfn_t *gfns;
/*
* One bit set per slot which has memory
* in this shadow page.
*/
DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
int multimapped; /* More than one parent_pte? */
int root_count; /* Currently serving as active root */
bool unsync;
unsigned int unsync_children;
union {
u64 *parent_pte; /* !multimapped */
struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
};
DECLARE_BITMAP(unsync_child_bitmap, 512);
};
struct kvm_pv_mmu_op_buffer {
void *ptr;
unsigned len;
unsigned processed;
char buf[512] __aligned(sizeof(long));
};
struct kvm_pio_request {
unsigned long count;
int cur_count;
gva_t guest_gva;
int in;
int port;
int size;
int string;
int down;
int rep;
};
/*
* x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
* 32-bit). The kvm_mmu structure abstracts the details of the current mmu
* mode.
*/
struct kvm_mmu {
void (*new_cr3)(struct kvm_vcpu *vcpu);
int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
void (*free)(struct kvm_vcpu *vcpu);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
void (*prefetch_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *page);
int (*sync_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp);
void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
hpa_t root_hpa;
int root_level;
int shadow_root_level;
union kvm_mmu_page_role base_role;
u64 *pae_root;
u64 rsvd_bits_mask[2][4];
};
struct kvm_vcpu_arch {
u64 host_tsc;
/*
* rip and regs accesses must go through
* kvm_{register,rip}_{read,write} functions.
*/
unsigned long regs[NR_VCPU_REGS];
u32 regs_avail;
u32 regs_dirty;
unsigned long cr0;
unsigned long cr2;
unsigned long cr3;
unsigned long cr4;
unsigned long cr8;
u32 hflags;
u64 pdptrs[4]; /* pae */
u64 shadow_efer;
u64 apic_base;
struct kvm_lapic *apic; /* kernel irqchip context */
int32_t apic_arb_prio;
int mp_state;
int sipi_vector;
u64 ia32_misc_enable_msr;
bool tpr_access_reporting;
struct kvm_mmu mmu;
/* only needed in kvm_pv_mmu_op() path, but it's hot so
* put it here to avoid allocation */
struct
|