aboutsummaryrefslogtreecommitdiff
path: root/target/i386/hvf/hvf.c
blob: 3e5e9f9472b46a51cd00e6356e2a3ca0278f6e80 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
/* Copyright 2008 IBM Corporation
 *           2008 Red Hat, Inc.
 * Copyright 2011 Intel Corporation
 * Copyright 2016 Veertu, Inc.
 * Copyright 2017 The Android Open Source Project
 *
 * QEMU Hypervisor.framework support
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not, see <http://www.gnu.org/licenses/>.
 */
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/error-report.h"

#include "sysemu/hvf.h"
#include "hvf-i386.h"
#include "vmcs.h"
#include "vmx.h"
#include "x86.h"
#include "x86_descr.h"
#include "x86_mmu.h"
#include "x86_decode.h"
#include "x86_emu.h"
#include "x86_task.h"
#include "x86hvf.h"

#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>

#include "exec/address-spaces.h"
#include "exec/exec-all.h"
#include "exec/ioport.h"
#include "hw/i386/apic_internal.h"
#include "hw/boards.h"
#include "qemu/main-loop.h"
#include "strings.h"
#include "sysemu/accel.h"
#include "sysemu/sysemu.h"
#include "target/i386/cpu.h"

pthread_rwlock_t mem_lock = PTHREAD_RWLOCK_INITIALIZER;
HVFState *hvf_state;
int hvf_disabled = 1;

static void assert_hvf_ok(hv_return_t ret)
{
    if (ret == HV_SUCCESS) {
        return;
    }

    switch (ret) {
    case HV_ERROR:
        error_report("Error: HV_ERROR\n");
        break;
    case HV_BUSY:
        error_report("Error: HV_BUSY\n");
        break;
    case HV_BAD_ARGUMENT:
        error_report("Error: HV_BAD_ARGUMENT\n");
        break;
    case HV_NO_RESOURCES:
        error_report("Error: HV_NO_RESOURCES\n");
        break;
    case HV_NO_DEVICE:
        error_report("Error: HV_NO_DEVICE\n");
        break;
    case HV_UNSUPPORTED:
        error_report("Error: HV_UNSUPPORTED\n");
        break;
    default:
        error_report("Unknown Error\n");
    }

    abort();
}

/* Memory slots */
hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t end)
{
    hvf_slot *slot;
    int x;
    for (x = 0; x < hvf_state->num_slots; ++x) {
        slot = &hvf_state->slots[x];
        if (slot->size && start < (slot->start + slot->size) &&
            end > slot->start) {
            return slot;
        }
    }
    return NULL;
}

struct mac_slot {
    int present;
    uint64_t size;
    uint64_t gpa_start;
    uint64_t gva;
};

struct mac_slot mac_slots[32];
#define ALIGN(x, y)  (((x) + (y) - 1) & ~((y) - 1))

static int do_hvf_set_memory(hvf_slot *slot)
{
    struct mac_slot *macslot;
    hv_memory_flags_t flags;
    hv_return_t ret;

    macslot = &mac_slots[slot->slot_id];

    if (macslot->present) {
        if (macslot->size != slot->size) {
            macslot->present = 0;
            ret = hv_vm_unmap(macslot->gpa_start, macslot->size);
            assert_hvf_ok(ret);
        }
    }

    if (!slot->size) {
        return 0;
    }

    flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC;

    macslot->present = 1;
    macslot->gpa_start = slot->start;
    macslot->size = slot->size;
    ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags);
    assert_hvf_ok(ret);
    return 0;
}

void hvf_set_phys_mem(MemoryRegionSection *section, bool add)
{
    hvf_slot *mem;
    MemoryRegion *area = section->mr;

    if (!memory_region_is_ram(area)) {
        return;
    }

    mem = hvf_find_overlap_slot(
            section->offset_within_address_space,
            section->offset_within_address_space + int128_get64(section->size));

    if (mem && add) {
        if (mem->size == int128_get64(section->size) &&
            mem->start == section->offset_within_address_space &&
            mem->mem == (memory_region_get_ram_ptr(area) +
            section->offset_within_region)) {
            return; /* Same region was attempted to register, go away. */
        }
    }

    /* Region needs to be reset. set the size to 0 and remap it. */
    if (mem) {
        mem->size = 0;
        if (do_hvf_set_memory(mem)) {
            error_report("Failed to reset overlapping slot\n");
            abort();
        }
    }

    if (!add) {
        return;
    }

    /* Now make a new slot. */
    int x;

    for (x = 0; x < hvf_state->num_slots; ++x) {
        mem = &hvf_state->slots[x];
        if (!mem->size) {
            break;
        }
    }

    if (x == hvf_state->num_slots) {
        error_report("No free slots\n");
        abort();
    }

    mem->size = int128_get64(section->size);
    mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region;
    mem->start = section->offset_within_address_space;
    mem->region = area;

    if (do_hvf_set_memory(mem)) {
        error_report("Error registering new memory slot\n");
        abort();
    }
}

void vmx_update_tpr(CPUState *cpu)
{
    /* TODO: need integrate APIC handling */
    X86CPU *x86_cpu = X86_CPU(cpu);
    int tpr = cpu_get_apic_tpr(x86_cpu->apic_state) << 4;
    int irr = apic_get_highest_priority_irr(x86_cpu->apic_state);

    wreg(cpu->hvf_fd, HV_X86_TPR, tpr);
    if (irr == -1) {
        wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);
    } else {
        wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 :
              irr >> 4);
    }
}

void update_apic_tpr(CPUState *cpu)
{
    X86CPU *x86_cpu = X86_CPU(cpu);
    int tpr = rreg(cpu->hvf_fd, HV_X86_TPR) >> 4;
    cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
}

#define VECTORING_INFO_VECTOR_MASK     0xff

static void hvf_handle_interrupt(CPUState * cpu, int mask)
{
    cpu->interrupt_request |= mask;
    if (!qemu_cpu_is_self(cpu)) {
        qemu_cpu_kick(cpu);
    }
}

void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer,
                  int direction, int size, int count)
{
    int i;
    uint8_t *ptr = buffer;

    for (i = 0; i < count; i++) {
        address_space_rw(&address_space_io, port, MEMTXATTRS_UNSPECIFIED,
                         ptr, size,
                         direction);
        ptr += size;
    }
}

/* TODO: synchronize vcpu state */
static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
{
    CPUState *cpu_state = cpu;
    if (cpu_state->vcpu_dirty == 0) {
        hvf_get_registers(cpu_state);
    }

    cpu_state->vcpu_dirty = 1;
}

void hvf_cpu_synchronize_state(CPUState *cpu_state)
{
    if (cpu_state->vcpu_dirty == 0) {
        run_on_cpu(cpu_state, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL);
    }
}

static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg)
{
    CPUState *cpu_state = cpu;
    hvf_put_registers(cpu_state);
    cpu_state->vcpu_dirty = false;
}

void hvf_cpu_synchronize_post_reset(CPUState *cpu_state)
{
    run_on_cpu(cpu_state, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
}

void _hvf_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg)
{
    CPUState *cpu_state = cpu;
    hvf_put_registers(cpu_state);
    cpu_state->vcpu_dirty = false;
}

void hvf_cpu_synchronize_post_init(CPUState *cpu_state)
{
    run_on_cpu(cpu_state, _hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
}

static bool ept_emulation_fault(hvf_slot *slot, addr_t gpa, uint64_t ept_qual)
{
    int read, write;

    /* EPT fault on an instruction fetch doesn't make sense here */
    if (ept_qual & EPT_VIOLATION_INST_FETCH) {
        return false;
    }

    /* EPT fault must be a read fault or a write fault */
    read = ept_qual & EPT_VIOLATION_DATA_READ ? 1 : 0;
    write = ept_qual & EPT_VIOLATION_DATA_WRITE ? 1 : 0;
    if ((read | write) == 0) {
        return false;
    }

    if (write && slot) {
        if (slot->flags & HVF_SLOT_LOG) {
            memory_region_set_dirty(slot->region, gpa - slot->start, 1);
            hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
                          HV_MEMORY_READ | HV_MEMORY_WRITE);
        }
    }

    /*
     * The EPT violation must have been caused by accessing a
     * guest-physical address that is a translation of a guest-linear
     * address.
     */
    if ((ept_qual & EPT_VIOLATION_GLA_VALID) == 0 ||
        (ept_qual & EPT_VIOLATION_XLAT_VALID) == 0) {
        return false;
    }

    return !slot;
}

static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
{
    hvf_slot *slot;

    slot = hvf_find_overlap_slot(
            section->offset_within_address_space,
            section->offset_within_address_space + int128_get64(section->size));

    /* protect region against writes; begin tracking it */
    if (on) {
        slot->flags |= HVF_SLOT_LOG;
        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
                      HV_MEMORY_READ);
    /* stop tracking region*/
    } else {
        slot->flags &= ~HVF_SLOT_LOG;
        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
                      HV_MEMORY_READ | HV_MEMORY_WRITE);
    }
}

static void hvf_log_start(MemoryListener *listener,
                          MemoryRegionSection *section, int old, int new)
{
    if (old != 0) {
        return;
    }

    hvf_set_dirty_tracking(section, 1);
}

static void hvf_log_stop(MemoryListener *listener,
                         MemoryRegionSection *section, int old, int new)
{
    if (new != 0) {
        return;
    }

    hvf_set_dirty_tracking(section, 0);
}

static void hvf_log_sync(MemoryListener *listener,
                         MemoryRegionSection *section)
{
    /*
     * sync of dirty pages is handled elsewhere; just make sure we keep
     * tracking the region.
     */
    hvf_set_dirty_tracking(section, 1);
}

static void hvf_region_add(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    hvf_set_phys_mem(section, true);
}

static void hvf_region_del(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    hvf_set_phys_mem(section, false);
}

static MemoryListener hvf_memory_listener = {
    .priority = 10,
    .region_add = hvf_region_add,
    .region_del = hvf_region_del,
    .log_start = hvf_log_start,
    .log_stop = hvf_log_stop,
    .log_sync = hvf_log_sync,
};

void hvf_reset_vcpu(CPUState *cpu) {

    /* TODO: this shouldn't be needed; there is already a call to
     * cpu_synchronize_all_post_reset in vl.c
     */
    wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER, 0);
    macvm_set_cr0(cpu->hvf_fd, 0x60000010);

    wvmcs(cpu->hvf_fd, VMCS_CR4_MASK, CR4_VMXE_MASK);
    wvmcs(cpu->hvf_fd, VMCS_CR4_SHADOW, 0x0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CR4, CR4_VMXE_MASK);

    /* set VMCS guest state fields */
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_SELECTOR, 0xf000);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_ACCESS_RIGHTS, 0x9b);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CS_BASE, 0xffff0000);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_ACCESS_RIGHTS, 0x93);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_DS_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_ACCESS_RIGHTS, 0x93);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_ES_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_ACCESS_RIGHTS, 0x93);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_ACCESS_RIGHTS, 0x93);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_LIMIT, 0xffff);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_ACCESS_RIGHTS, 0x93);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_SS_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_ACCESS_RIGHTS, 0x10000);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_SELECTOR, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_LIMIT, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_ACCESS_RIGHTS, 0x83);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_TR_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE, 0);

    wvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_LIMIT, 0);
    wvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_BASE, 0);

    /*wvmcs(cpu->hvf_fd, VMCS_GUEST_CR2, 0x0);*/
    wvmcs(cpu->hvf_fd, VMCS_GUEST_CR3, 0x0);

    wreg(cpu->hvf_fd, HV_X86_RIP, 0xfff0);
    wreg(cpu->hvf_fd, HV_X86_RDX, 0x623);
    wreg(cpu->hvf_fd, HV_X86_RFLAGS, 0x2);
    wreg(cpu->hvf_fd, HV_X86_RSP, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RAX, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RBX, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RCX, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RSI, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RDI, 0x0);
    wreg(cpu->hvf_fd, HV_X86_RBP, 0x0);

    for (int i = 0; i < 8; i++) {
        wreg(cpu->hvf_fd, HV_X86_R8 + i, 0x0);
    }

    hv_vm_sync_tsc(0);
    cpu->halted = 0;
    hv_vcpu_invalidate_tlb(cpu->hvf_fd);
    hv_vcpu_flush(cpu->hvf_fd);
}

void hvf_vcpu_destroy(CPUState *cpu)
{
    hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd);
    assert_hvf_ok(ret);
}

static void dummy_signal(int sig)
{
}

int hvf_init_vcpu(CPUState *cpu)
{

    X86CPU *x86cpu = X86_CPU(cpu);
    CPUX86State *env = &x86cpu->env;
    int r;

    /* init cpu signals */
    sigset_t set;
    struct sigaction sigact;

    memset(&sigact, 0, sizeof(sigact));
    sigact.sa_handler = dummy_signal;
    sigaction(SIG_IPI, &sigact, NULL);

    pthread_sigmask(SIG_BLOCK, NULL, &set);
    sigdelset(&set, SIG_IPI);

    init_emu();
    init_decoder();

    hvf_state->hvf_caps = g_new0(struct hvf_vcpu_caps, 1);
    env->hvf_emul = g_new0(HVFX86EmulatorState, 1);

    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT);
    cpu->vcpu_dirty = 1;
    assert_hvf_ok(r);

    if (hv_vmx_read_capability(HV_VMX_CAP_PINBASED,
        &hvf_state->hvf_caps->vmx_cap_pinbased)) {
        abort();
    }
    if (hv_vmx_read_capability(HV_VMX_CAP_PROCBASED,
        &hvf_state->hvf_caps->vmx_cap_procbased)) {
        abort();
    }
    if (hv_vmx_read_capability(HV_VMX_CAP_PROCBASED2,
        &hvf_state->hvf_caps->vmx_cap_procbased2)) {
        abort();
    }
    if (hv_vmx_read_capability(HV_VMX_CAP_ENTRY,
        &hvf_state->hvf_caps->vmx_cap_entry)) {
        abort();
    }

    /* set VMCS control fields */
    wvmcs(cpu->hvf_fd, VMCS_PIN_BASED_CTLS,
          cap2ctrl(hvf_state->hvf_caps->vmx_cap_pinbased,
          VMCS_PIN_BASED_CTLS_EXTINT |
          VMCS_PIN_BASED_CTLS_NMI |
          VMCS_PIN_BASED_CTLS_VNMI));
    wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS,
          cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased,
          VMCS_PRI_PROC_BASED_CTLS_HLT |
          VMCS_PRI_PROC_BASED_CTLS_MWAIT |
          VMCS_PRI_PROC_BASED_CTLS_TSC_OFFSET |
          VMCS_PRI_PROC_BASED_CTLS_TPR_SHADOW) |
          VMCS_PRI_PROC_BASED_CTLS_SEC_CONTROL);
    wvmcs(cpu->hvf_fd, VMCS_SEC_PROC_BASED_CTLS,
          cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased2,
                   VMCS_PRI_PROC_BASED2_CTLS_APIC_ACCESSES));

    wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry,
          0));
    wvmcs(cpu->hvf_fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */

    wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);

    hvf_reset_vcpu(cpu);

    x86cpu = X86_CPU(cpu);
    x86cpu->env.kvm_xsave_buf = qemu_memalign(4096, 4096);

    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_STAR, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_LSTAR, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_CSTAR, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FMASK, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FSBASE, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_GSBASE, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_KERNELGSBASE, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_TSC_AUX, 1);
    /*hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_TSC, 1);*/
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_CS, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_EIP, 1);
    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_ESP, 1);

    return 0;
}

void hvf_disable(int shouldDisable)
{
    hvf_disabled = shouldDisable;
}

static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_info)
{
    X86CPU *x86_cpu = X86_CPU(cpu);
    CPUX86State *env = &x86_cpu->env;

    env->exception_injected = -1;
    env->interrupt_injected = -1;
    env->nmi_injected = false;
    if (idtvec_info & VMCS_IDT_VEC_VALID) {
        switch (idtvec_info & VMCS_IDT_VEC_TYPE) {
        case VMCS_IDT_VEC_HWINTR:
        case VMCS_IDT_VEC_SWINTR:
            env->interrupt_injected = idtvec_info & VMCS_IDT_VEC_VECNUM;
            break;
        case VMCS_IDT_VEC_NMI:
            env->nmi_injected = true;
            break;
        case VMCS_IDT_VEC_HWEXCEPTION:
        case VMCS_IDT_VEC_SWEXCEPTION:
            env->exception_injected = idtvec_info & VMCS_IDT_VEC_VECNUM;
            break;
        case VMCS_IDT_VEC_PRIV_SWEXCEPTION:
        default:
            abort();
        }
        if ((idtvec_info & VMCS_IDT_VEC_TYPE) == VMCS_IDT_VEC_SWEXCEPTION ||
            (idtvec_info & VMCS_IDT_VEC_TYPE) == VMCS_IDT_VEC_SWINTR) {
            env->ins_len = ins_len;
        }
        if (idtvec_info & VMCS_INTR_DEL_ERRCODE) {
            env->has_error_code = true;
            env->error_code = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_ERROR);
        }
    }
    if ((rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
        VMCS_INTERRUPTIBILITY_NMI_BLOCKING)) {
        env->hflags2 |= HF2_NMI_MASK;
    } else {
        env->hflags2 &= ~HF2_NMI_MASK;
    }
    if (rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
         (VMCS_INTERRUPTIBILITY_STI_BLOCKING |
         VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
        env->hflags |= HF_INHIBIT_IRQ_MASK;
    } else {
        env->hflags &= ~HF_INHIBIT_IRQ_MASK;
    }
}

int hvf_vcpu_exec(CPUState *cpu)
{
    X86CPU *x86_cpu = X86_CPU(cpu);
    CPUX86State *env = &x86_cpu->env;
    int ret = 0;
    uint64_t rip = 0;

    cpu->halted = 0;

    if (hvf_process_events(cpu)) {
        return EXCP_HLT;
    }

    do {
        if (cpu->vcpu_dirty) {
            hvf_put_registers(cpu);
            cpu->vcpu_dirty = false;
        }

        if (hvf_inject_interrupts(cpu)) {
            return EXCP_INTERRUPT;
        }
        vmx_update_tpr(cpu);

        qemu_mutex_unlock_iothread();
        if (!cpu_is_bsp(X86_CPU(cpu)) && cpu->halted) {
            qemu_mutex_lock_iothread();
            return EXCP_HLT;
        }

        hv_return_t r  = hv_vcpu_run(cpu->hvf_fd);
        assert_hvf_ok(r);

        /* handle VMEXIT */
        uint64_t exit_reason = rvmcs(cpu->hvf_fd, VMCS_EXIT_REASON);
        uint64_t exit_qual = rvmcs(cpu->hvf_fd, VMCS_EXIT_QUALIFICATION);
        uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf_fd,
                                           VMCS_EXIT_INSTRUCTION_LENGTH);

        uint64_t idtvec_info = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);

        hvf_store_events(cpu, ins_len, idtvec_info);
        rip = rreg(cpu->hvf_fd, HV_X86_RIP);
        RFLAGS(env) = rreg(cpu->hvf_fd, HV_X86_RFLAGS);
        env->eflags = RFLAGS(env);

        qemu_mutex_lock_iothread();

        update_apic_tpr(cpu);
        current_cpu = cpu;

        ret = 0;
        switch (exit_reason) {
        case EXIT_REASON_HLT: {
            macvm_set_rip(cpu, rip + ins_len);
            if (!((cpu->interrupt_request & CPU_INTERRUPT_HARD) &&
                (EFLAGS(env) & IF_MASK))
                && !(cpu->interrupt_request & CPU_INTERRUPT_NMI) &&
                !(idtvec_info & VMCS_IDT_VEC_VALID)) {
                cpu->halted = 1;
                ret = EXCP_HLT;
            }
            ret = EXCP_INTERRUPT;
            break;
        }
        case EXIT_REASON_MWAIT: {
            ret = EXCP_INTERRUPT;
            break;
        }
            /* Need to check if MMIO or unmmaped fault */
        case EXIT_REASON_EPT_FAULT:
        {
            hvf_slot *slot;
            addr_t gpa = rvmcs(cpu->hvf_fd, VMCS_GUEST_PHYSICAL_ADDRESS);

            if (((idtvec_info & VMCS_IDT_VEC_VALID) == 0) &&
                ((exit_qual & EXIT_QUAL_NMIUDTI) != 0)) {
                vmx_set_nmi_blocking(cpu);
            }

            slot = hvf_find_overlap_slot(gpa, gpa);
            /* mmio */
            if (ept_emulation_fault(slot, gpa, exit_qual)) {
                struct x86_decode decode;

                load_regs(cpu);
                env->hvf_emul->fetch_rip = rip;

                decode_instruction(env, &decode);
                exec_instruction(env, &decode);
                store_regs(cpu);
                break;
            }
            break;
        }
        case EXIT_REASON_INOUT:
        {
            uint32_t in = (exit_qual & 8) != 0;
            uint32_t size =  (exit_qual & 7) + 1;
            uint32_t string =  (exit_qual & 16) != 0;
            uint32_t port =  exit_qual >> 16;
            /*uint32_t rep = (exit_qual & 0x20) != 0;*/

            if (!string && in) {
                uint64_t val = 0;
                load_regs(cpu);
                hvf_handle_io(env, port, &val, 0, size, 1);
                if (size == 1) {
                    AL(env) = val;
                } else if (size == 2) {
                    AX(env) = val;
                } else if (size == 4) {
                    RAX(env) = (uint32_t)val;
                } else {
                    VM_PANIC("size");
                }
                RIP(env) += ins_len;
                store_regs(cpu);
                break;
            } else if (!string && !in) {
                RAX(env) = rreg(cpu->hvf_fd, HV_X86_RAX);
                hvf_handle_io(env, port, &RAX(env), 1, size, 1);
                macvm_set_rip(cpu, rip + ins_len);
                break;
            }
            struct x86_decode decode;

            load_regs(cpu);
            env->hvf_emul->fetch_rip = rip;

            decode_instruction(env, &decode);
            VM_PANIC_ON(ins_len != decode.len);
            exec_instruction(env, &decode);
            store_regs(cpu);

            break;
        }
        case EXIT_REASON_CPUID: {
            uint32_t rax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
            uint32_t rbx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RBX);
            uint32_t rcx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
            uint32_t rdx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);

            cpu_x86_cpuid(env, rax, rcx, &rax, &rbx, &rcx, &rdx);

            wreg(cpu->hvf_fd, HV_X86_RAX, rax);
            wreg(cpu->hvf_fd, HV_X86_RBX, rbx);
            wreg(cpu->hvf_fd, HV_X86_RCX, rcx);
            wreg(cpu->hvf_fd, HV_X86_RDX, rdx);

            macvm_set_rip(cpu, rip + ins_len);
            break;
        }
        case EXIT_REASON_XSETBV: {
            X86CPU *x86_cpu = X86_CPU(cpu);
            CPUX86State *env = &x86_cpu->env;
            uint32_t eax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
            uint32_t ecx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
            uint32_t edx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);

            if (ecx) {
                macvm_set_rip(cpu, rip + ins_len);
                break;
            }
            env->xcr0 = ((uint64_t)edx << 32) | eax;
            wreg(cpu->hvf_fd, HV_X86_XCR0, env->xcr0 | 1);
            macvm_set_rip(cpu, rip + ins_len);
            break;
        }
        case EXIT_REASON_INTR_WINDOW:
            vmx_clear_int_window_exiting(cpu);
            ret = EXCP_INTERRUPT;
            break;
        case EXIT_REASON_NMI_WINDOW:
            vmx_clear_nmi_window_exiting(cpu);
            ret = EXCP_INTERRUPT;
            break;
        case EXIT_REASON_EXT_INTR:
            /* force exit and allow io handling */
            ret = EXCP_INTERRUPT;
            break;
        case EXIT_REASON_RDMSR:
        case EXIT_REASON_WRMSR:
        {
            load_regs(cpu);
            if (exit_reason == EXIT_REASON_RDMSR) {
                simulate_rdmsr(cpu);
            } else {
                simulate_wrmsr(cpu);
            }
            RIP(env) += rvmcs(cpu->hvf_fd, VMCS_EXIT_INSTRUCTION_LENGTH);
            store_regs(cpu);
            break;
        }
        case EXIT_REASON_CR_ACCESS: {
            int cr;
            int reg;

            load_regs(cpu);
            cr = exit_qual & 15;
            reg = (exit_qual >> 8) & 15;

            switch (cr) {
            case 0x0: {
                macvm_set_cr0(cpu->hvf_fd, RRX(env, reg));
                break;
            }
            case 4: {
                macvm_set_cr4(cpu->hvf_fd, RRX(env, reg));
                break;
            }
            case 8: {
                X86CPU *x86_cpu = X86_CPU(cpu);
                if (exit_qual & 0x10) {
                    RRX(env, reg) = cpu_get_apic_tpr(x86_cpu->apic_state);
                } else {
                    int tpr = RRX(env, reg);
                    cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
                    ret = EXCP_INTERRUPT;
                }
                break;
            }
            default:
                error_report("Unrecognized CR %d\n", cr);
                abort();
            }
            RIP(env) += ins_len;
            store_regs(cpu);
            break;
        }
        case EXIT_REASON_APIC_ACCESS: { /* TODO */
            struct x86_decode decode;

            load_regs(cpu);
            env->hvf_emul->fetch_rip = rip;

            decode_instruction(env, &decode);
            exec_instruction(env, &decode);
            store_regs(cpu);
            break;
        }
        case EXIT_REASON_TPR: {
            ret = 1;
            break;
        }
        case EXIT_REASON_TASK_SWITCH: {
            uint64_t vinfo = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);
            x68_segment_selector sel = {.sel = exit_qual & 0xffff};
            vmx_handle_task_switch(cpu, sel, (exit_qual >> 30) & 0x3,
             vinfo & VMCS_INTR_VALID, vinfo & VECTORING_INFO_VECTOR_MASK, vinfo
             & VMCS_INTR_T_MASK);
            break;
        }
        case EXIT_REASON_TRIPLE_FAULT: {
            qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
            ret = EXCP_INTERRUPT;
            break;
        }
        case EXIT_REASON_RDPMC:
            wreg(cpu->hvf_fd, HV_X86_RAX, 0);
            wreg(cpu->hvf_fd, HV_X86_RDX, 0);
            macvm_set_rip(cpu, rip + ins_len);
            break;
        case VMX_REASON_VMCALL:
            env->exception_injected = EXCP0D_GPF;
            env->has_error_code = true;
            env->error_code = 0;
            break;
        default:
            error_report("%llx: unhandled exit %llx\n", rip, exit_reason);
        }
    } while (ret == 0);

    return ret;
}

static bool hvf_allowed;

static int hvf_accel_init(MachineState *ms)
{
    int x;
    hv_return_t ret;
    HVFState *s;

    hvf_disable(0);
    ret = hv_vm_create(HV_VM_DEFAULT);
    assert_hvf_ok(ret);

    s = g_new0(HVFState, 1);
 
    s->num_slots = 32;
    for (x = 0; x < s->num_slots; ++x) {
        s->slots[x].size = 0;
        s->slots[x].slot_id = x;
    }
  
    hvf_state = s;
    cpu_interrupt_handler = hvf_handle_interrupt;
    memory_listener_register(&hvf_memory_listener, &address_space_memory);
    return 0;
}

static void hvf_accel_class_init(ObjectClass *oc, void *data)
{
    AccelClass *ac = ACCEL_CLASS(oc);
    ac->name = "HVF";
    ac->init_machine = hvf_accel_init;
    ac->allowed = &hvf_allowed;
}

static const TypeInfo hvf_accel_type = {
    .name = TYPE_HVF_ACCEL,
    .parent = TYPE_ACCEL,
    .class_init = hvf_accel_class_init,
};

static void hvf_type_init(void)
{
    type_register_static(&hvf_accel_type);
}

type_init(hvf_type_init);