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
|
/*-
* Copyright (c) 2011 NetApp, Inc.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/time.h>
#include <machine/atomic.h>
#include <machine/segments.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <err.h>
#include <libgen.h>
#include <unistd.h>
#include <assert.h>
#include <errno.h>
#include <pthread.h>
#include <pthread_np.h>
#include <sysexits.h>
#include <stdbool.h>
#include <machine/vmm.h>
#include <vmmapi.h>
#include "bhyverun.h"
#include "acpi.h"
#include "inout.h"
#include "dbgport.h"
#include "fwctl.h"
#include "ioapic.h"
#include "mem.h"
#include "mevent.h"
#include "mptbl.h"
#include "pci_emul.h"
#include "pci_irq.h"
#include "pci_lpc.h"
#include "smbiostbl.h"
#include "xmsr.h"
#include "spinup_ap.h"
#include "rtc.h"
#define GUEST_NIO_PORT 0x488 /* guest upcalls via i/o port */
#define MB (1024UL * 1024)
#define GB (1024UL * MB)
typedef int (*vmexit_handler_t)(struct vmctx *, struct vm_exit *, int *vcpu);
extern int vmexit_task_switch(struct vmctx *, struct vm_exit *, int *vcpu);
char *vmname;
int guest_ncpus;
char *guest_uuid_str;
static int guest_vmexit_on_hlt, guest_vmexit_on_pause;
static int virtio_msix = 1;
static int x2apic_mode = 0; /* default is xAPIC */
static int strictio;
static int strictmsr = 1;
static int acpi;
static char *progname;
static const int BSP = 0;
static cpuset_t cpumask;
static void vm_loop(struct vmctx *ctx, int vcpu, uint64_t rip);
static struct vm_exit vmexit[VM_MAXCPU];
struct bhyvestats {
uint64_t vmexit_bogus;
uint64_t vmexit_reqidle;
uint64_t vmexit_hlt;
uint64_t vmexit_pause;
uint64_t vmexit_mtrap;
uint64_t vmexit_inst_emul;
uint64_t cpu_switch_rotate;
uint64_t cpu_switch_direct;
} stats;
struct mt_vmm_info {
pthread_t mt_thr;
struct vmctx *mt_ctx;
int mt_vcpu;
} mt_vmm_info[VM_MAXCPU];
static cpuset_t *vcpumap[VM_MAXCPU] = { NULL };
static void
usage(int code)
{
fprintf(stderr,
"Usage: %s [-abehuwxACHPSWY] [-c vcpus] [-g <gdb port>] [-l <lpc>]\n"
" %*s [-m mem] [-p vcpu:hostcpu] [-s <pci>] [-U uuid] <vm>\n"
" -a: local apic is in xAPIC mode (deprecated)\n"
" -A: create ACPI tables\n"
" -c: # cpus (default 1)\n"
" -C: include guest memory in core file\n"
" -e: exit on unhandled I/O access\n"
" -g: gdb port\n"
" -h: help\n"
" -H: vmexit from the guest on hlt\n"
" -l: LPC device configuration\n"
" -m: memory size in MB\n"
" -p: pin 'vcpu' to 'hostcpu'\n"
" -P: vmexit from the guest on pause\n"
" -s: <slot,driver,configinfo> PCI slot config\n"
" -S: guest memory cannot be swapped\n"
" -u: RTC keeps UTC time\n"
" -U: uuid\n"
" -w: ignore unimplemented MSRs\n"
" -W: force virtio to use single-vector MSI\n"
" -x: local apic is in x2APIC mode\n"
" -Y: disable MPtable generation\n",
progname, (int)strlen(progname), "");
exit(code);
}
static int
pincpu_parse(const char *opt)
{
int vcpu, pcpu;
if (sscanf(opt, "%d:%d", &vcpu, &pcpu) != 2) {
fprintf(stderr, "invalid format: %s\n", opt);
return (-1);
}
if (vcpu < 0 || vcpu >= VM_MAXCPU) {
fprintf(stderr, "vcpu '%d' outside valid range from 0 to %d\n",
vcpu, VM_MAXCPU - 1);
return (-1);
}
if (pcpu < 0 || pcpu >= CPU_SETSIZE) {
fprintf(stderr, "hostcpu '%d' outside valid range from "
"0 to %d\n", pcpu, CPU_SETSIZE - 1);
return (-1);
}
if (vcpumap[vcpu] == NULL) {
if ((vcpumap[vcpu] = malloc(sizeof(cpuset_t))) == NULL) {
perror("malloc");
return (-1);
}
CPU_ZERO(vcpumap[vcpu]);
}
CPU_SET(pcpu, vcpumap[vcpu]);
return (0);
}
void
vm_inject_fault(void *arg, int vcpu, int vector, int errcode_valid,
int errcode)
{
struct vmctx *ctx;
int error, restart_instruction;
ctx = arg;
restart_instruction = 1;
error = vm_inject_exception(ctx, vcpu, vector, errcode_valid, errcode,
restart_instruction);
assert(error == 0);
}
void *
paddr_guest2host(struct vmctx *ctx, uintptr_t gaddr, size_t len)
{
return (vm_map_gpa(ctx, gaddr, len));
}
int
fbsdrun_vmexit_on_pause(void)
{
return (guest_vmexit_on_pause);
}
int
fbsdrun_vmexit_on_hlt(void)
{
return (guest_vmexit_on_hlt);
}
int
fbsdrun_virtio_msix(void)
{
return (virtio_msix);
}
static void *
fbsdrun_start_thread(void *param)
{
char tname[MAXCOMLEN + 1];
struct mt_vmm_info *mtp;
int vcpu;
mtp = param;
vcpu = mtp->mt_vcpu;
snprintf(tname, sizeof(tname), "vcpu %d", vcpu);
pthread_set_name_np(mtp->mt_thr, tname);
vm_loop(mtp->mt_ctx, vcpu, vmexit[vcpu].rip);
/* not reached */
exit(1);
return (NULL);
}
void
fbsdrun_addcpu(struct vmctx *ctx, int fromcpu, int newcpu, uint64_t rip)
{
int error;
assert(fromcpu == BSP);
/*
* The 'newcpu' must be activated in the context of 'fromcpu'. If
* vm_activate_cpu() is delayed until newcpu's pthread starts running
* then vmm.ko is out-of-sync with bhyve and this can create a race
* with vm_suspend().
*/
error = vm_activate_cpu(ctx, newcpu);
if (error != 0)
err(EX_OSERR, "could not activate CPU %d", newcpu);
CPU_SET_ATOMIC(newcpu, &cpumask);
/*
* Set up the vmexit struct to allow execution to start
* at the given RIP
*/
vmexit[newcpu].rip = rip;
vmexit[newcpu].inst_length = 0;
mt_vmm_info[newcpu].mt_ctx = ctx;
mt_vmm_info[newcpu].mt_vcpu = newcpu;
error = pthread_create(&mt_vmm_info[newcpu].mt_thr, NULL,
fbsdrun_start_thread, &mt_vmm_info[newcpu]);
assert(error == 0);
}
static int
fbsdrun_deletecpu(struct vmctx *ctx, int vcpu)
{
if (!CPU_ISSET(vcpu, &cpumask)) {
fprintf(stderr, "Attempting to delete unknown cpu %d\n", vcpu);
exit(1);
}
CPU_CLR_ATOMIC(vcpu, &cpumask);
return (CPU_EMPTY(&cpumask));
}
static int
vmexit_handle_notify(struct vmctx *ctx, struct vm_exit *vme, int *pvcpu,
uint32_t eax)
{
#if BHYVE_DEBUG
/*
* put guest-driven debug here
*/
#endif
return (VMEXIT_CONTINUE);
}
static int
vmexit_inout(struct vmctx *ctx, struct vm_exit *vme, int *pvcpu)
{
int error;
int bytes, port, in, out, string;
int vcpu;
vcpu = *pvcpu;
port = vme->u.inout.port;
bytes = vme->u.inout.bytes;
string = vme->u.inout.string;
in = vme->u.inout.in;
out = !in;
/* Extra-special case of host notifications */
if (out && port == GUEST_NIO_PORT) {
error = vmexit_handle_notify(ctx, vme, pvcpu, vme->u.inout.eax);
return (error);
}
error = emulate_inout(ctx, vcpu, vme, strictio);
if (error) {
fprintf(stderr, "Unhandled %s%c 0x%04x at 0x%lx\n",
in ? "in" : "out",
bytes == 1 ? 'b' : (bytes == 2 ? 'w' : 'l'),
port, vmexit->rip);
return (VMEXIT_ABORT);
} else {
return (VMEXIT_CONTINUE);
}
}
static int
vmexit_rdmsr(struct vmctx *ctx, struct vm_exit *vme, int *pvcpu)
{
uint64_t val;
uint32_t eax, edx;
int error;
val = 0;
error = emulate_rdmsr(ctx, *pvcpu, vme->u.msr.code, &val);
if (error != 0) {
fprintf(stderr, "rdmsr to register %#x on vcpu %d\n",
vme->u.msr.code, *pvcpu);
if (strictmsr) {
vm_inject_gp(ctx, *pvcpu);
return (VMEXIT_CONTINUE);
}
}
eax = val;
error = vm_set_register(ctx, *pvcpu, VM_REG_GUEST_RAX, eax);
assert(error == 0);
edx = val >> 32;
error = vm_set_register(ctx, *pvcpu, VM_REG_GUEST_RDX, edx);
assert(error == 0);
return (VMEXIT_CONTINUE);
}
static int
vmexit_wrmsr(struct vmctx *ctx, struct vm_exit *vme, int *pvcpu)
{
int error;
error = emulate_wrmsr(ctx, *pvcpu, vme->u.msr.code, vme->u.msr.wval);
if (error != 0) {
fprintf(stderr, "wrmsr to register %#x(%#lx) on vcpu %d\n",
vme->u.msr.code, vme->u.msr.wval, *pvcpu);
if (strictmsr) {
vm_inject_gp(ctx, *pvcpu);
return (VMEXIT_CONTINUE);
}
}
return (VMEXIT_CONTINUE);
}
static int
vmexit_spinup_ap(struct vmctx *ctx, struct vm_exit *vme, int *pvcpu)
{
int newcpu;
int retval = VMEXIT_CONTINUE;
newcpu = spinup_ap(ctx, *pvcpu,
vme->u.spinup_ap.vcpu, vme->u.spinup_ap.rip);
return (retval);
}
#define DEBUG_EPT_MISCONFIG
#ifdef DEBUG_EPT_MISCONFIG
#define EXIT_REASON_EPT_MISCONFIG 49
#define VMCS_GUEST_PHYSICAL_ADDRESS 0x00002400
#define VMCS_IDENT(x) ((x) | 0x80000000)
static uint64_t ept_misconfig_gpa, ept_misconfig_pte[4];
static int ept_misconfig_ptenum;
#endif
static int
vmexit_vmx(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
fprintf(stderr, "vm exit[%d]\n", *pvcpu);
fprintf(stderr, "\treason\t\tVMX\n");
fprintf(stderr, "\trip\t\t0x%016lx\n", vmexit->rip);
fprintf(stderr, "\tinst_length\t%d\n", vmexit->inst_length);
fprintf(stderr, "\tstatus\t\t%d\n", vmexit->u.vmx.status);
fprintf(stderr, "\texit_reason\t%u\n", vmexit->u.vmx.exit_reason);
fprintf(stderr, "\tqualification\t0x%016lx\n",
vmexit->u.vmx.exit_qualification);
fprintf(stderr, "\tinst_type\t\t%d\n", vmexit->u.vmx.inst_type);
fprintf(stderr, "\tinst_error\t\t%d\n", vmexit->u.vmx.inst_error);
#ifdef DEBUG_EPT_MISCONFIG
if (vmexit->u.vmx.exit_reason == EXIT_REASON_EPT_MISCONFIG) {
vm_get_register(ctx, *pvcpu,
VMCS_IDENT(VMCS_GUEST_PHYSICAL_ADDRESS),
&ept_misconfig_gpa);
vm_get_gpa_pmap(ctx, ept_misconfig_gpa, ept_misconfig_pte,
&ept_misconfig_ptenum);
fprintf(stderr, "\tEPT misconfiguration:\n");
fprintf(stderr, "\t\tGPA: %#lx\n", ept_misconfig_gpa);
fprintf(stderr, "\t\tPTE(%d): %#lx %#lx %#lx %#lx\n",
ept_misconfig_ptenum, ept_misconfig_pte[0],
ept_misconfig_pte[1], ept_misconfig_pte[2],
ept_misconfig_pte[3]);
}
#endif /* DEBUG_EPT_MISCONFIG */
return (VMEXIT_ABORT);
}
static int
vmexit_svm(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
fprintf(stderr, "vm exit[%d]\n", *pvcpu);
fprintf(stderr, "\treason\t\tSVM\n");
fprintf(stderr, "\trip\t\t0x%016lx\n", vmexit->rip);
fprintf(stderr, "\tinst_length\t%d\n", vmexit->inst_length);
fprintf(stderr, "\texitcode\t%#lx\n", vmexit->u.svm.exitcode);
fprintf(stderr, "\texitinfo1\t%#lx\n", vmexit->u.svm.exitinfo1);
fprintf(stderr, "\texitinfo2\t%#lx\n", vmexit->u.svm.exitinfo2);
return (VMEXIT_ABORT);
}
static int
vmexit_bogus(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
assert(vmexit->inst_length == 0);
stats.vmexit_bogus++;
return (VMEXIT_CONTINUE);
}
static int
vmexit_reqidle(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
assert(vmexit->inst_length == 0);
stats.vmexit_reqidle++;
return (VMEXIT_CONTINUE);
}
static int
vmexit_hlt(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
stats.vmexit_hlt++;
/*
* Just continue execution with the next instruction. We use
* the HLT VM exit as a way to be friendly with the host
* scheduler.
*/
return (VMEXIT_CONTINUE);
}
static int
vmexit_pause(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
stats.vmexit_pause++;
return (VMEXIT_CONTINUE);
}
static int
vmexit_mtrap(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
assert(vmexit->inst_length == 0);
stats.vmexit_mtrap++;
return (VMEXIT_CONTINUE);
}
static int
vmexit_inst_emul(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
int err, i;
struct vie *vie;
stats.vmexit_inst_emul++;
vie = &vmexit->u.inst_emul.vie;
err = emulate_mem(ctx, *pvcpu, vmexit->u.inst_emul.gpa,
vie, &vmexit->u.inst_emul.paging);
if (err) {
if (err == ESRCH) {
fprintf(stderr, "Unhandled memory access to 0x%lx\n",
vmexit->u.inst_emul.gpa);
}
fprintf(stderr, "Failed to emulate instruction [");
for (i = 0; i < vie->num_valid; i++) {
fprintf(stderr, "0x%02x%s", vie->inst[i],
i != (vie->num_valid - 1) ? " " : "");
}
fprintf(stderr, "] at 0x%lx\n", vmexit->rip);
return (VMEXIT_ABORT);
}
return (VMEXIT_CONTINUE);
}
static pthread_mutex_t resetcpu_mtx = PTHREAD_MUTEX_INITIALIZER;
static pthread_cond_t resetcpu_cond = PTHREAD_COND_INITIALIZER;
static int
vmexit_suspend(struct vmctx *ctx, struct vm_exit *vmexit, int *pvcpu)
{
enum vm_suspend_how how;
how = vmexit->u.suspended.how;
fbsdrun_deletecpu(ctx, *pvcpu);
if (*pvcpu != BSP) {
pthread_mutex_lock(&resetcpu_mtx);
pthread_cond_signal(&resetcpu_cond);
pthread_mutex_unlock(&resetcpu_mtx);
pthread_exit(NULL);
}
pthread_mutex_lock(&resetcpu_mtx);
while (!CPU_EMPTY(&cpumask)) {
pthread_cond_wait(&resetcpu_cond, &resetcpu_mtx);
}
pthread_mutex_unlock(&resetcpu_mtx);
switch (how) {
case VM_SUSPEND_RESET:
exit(0);
case VM_SUSPEND_POWEROFF:
exit(1);
case VM_SUSPEND_HALT:
exit(2);
case VM_SUSPEND_TRIPLEFAULT:
exit(3);
default:
fprintf(stderr, "vmexit_suspend: invalid reason %d\n", how);
exit(100);
}
return (0); /* NOTREACHED */
}
static vmexit_handler_t handler[VM_EXITCODE_MAX] = {
[VM_EXITCODE_INOUT] = vmexit_inout,
[VM_EXITCODE_INOUT_STR] = vmexit_inout,
[VM_EXITCODE_VMX] = vmexit_vmx,
[VM_EXITCODE_SVM] = vmexit_svm,
[VM_EXITCODE_BOGUS] = vmexit_bogus,
[VM_EXITCODE_REQIDLE] = vmexit_reqidle,
[VM_EXITCODE_RDMSR] = vmexit_rdmsr,
[VM_EXITCODE_WRMSR] = vmexit_wrmsr,
[VM_EXITCODE_MTRAP] = vmexit_mtrap,
[VM_EXITCODE_INST_EMUL] = vmexit_inst_emul,
[VM_EXITCODE_SPINUP_AP] = vmexit_spinup_ap,
[VM_EXITCODE_SUSPENDED] = vmexit_suspend,
[VM_EXITCODE_TASK_SWITCH] = vmexit_task_switch,
};
static void
vm_loop(struct vmctx *ctx, int vcpu, uint64_t startrip)
{
int error, rc, prevcpu;
enum vm_exitcode exitcode;
cpuset_t active_cpus;
if (vcpumap[vcpu] != NULL) {
error = pthread_setaffinity_np(pthread_self(),
sizeof(cpuset_t), vcpumap[vcpu]);
assert(error == 0);
}
error = vm_active_cpus(ctx, &active_cpus);
assert(CPU_ISSET(vcpu, &active_cpus));
error = vm_set_register(ctx, vcpu, VM_REG_GUEST_RIP, startrip);
assert(error == 0);
while (1) {
error = vm_run(ctx, vcpu, &vmexit[vcpu]);
if (error != 0)
break;
prevcpu = vcpu;
exitcode = vmexit[vcpu].exitcode;
if (exitcode >= VM_EXITCODE_MAX || handler[exitcode] == NULL) {
fprintf(stderr, "vm_loop: unexpected exitcode 0x%x\n",
exitcode);
exit(1);
}
rc = (*handler[exitcode])(ctx, &vmexit[vcpu], &vcpu);
switch (rc) {
case VMEXIT_CONTINUE:
break;
case VMEXIT_ABORT:
abort();
default:
exit(1);
}
}
fprintf(stderr, "vm_run error %d, errno %d\n", error, errno);
}
static int
num_vcpus_allowed(struct vmctx *ctx)
{
int tmp, error;
error = vm_get_capability(ctx, BSP, VM_CAP_UNRESTRICTED_GUEST, &tmp);
/*
* The guest is allowed to spinup more than one processor only if the
* UNRESTRICTED_GUEST capability is available.
*/
if (error == 0)
return (VM_MAXCPU);
else
return (1);
}
void
fbsdrun_set_capabilities(struct vmctx *ctx, int cpu)
{
int err, tmp;
if (fbsdrun_vmexit_on_hlt()) {
err = vm_get_capability(ctx, cpu, VM_CAP_HALT_EXIT, &tmp);
if (err < 0) {
fprintf(stderr, "VM exit on HLT not supported\n");
exit(1);
}
vm_set_capability(ctx, cpu, VM_CAP_HALT_EXIT, 1);
if (cpu == BSP)
handler[VM_EXITCODE_HLT] = vmexit_hlt;
}
if (fbsdrun_vmexit_on_pause()) {
/*
* pause exit support required for this mode
*/
err = vm_get_capability(ctx, cpu, VM_CAP_PAUSE_EXIT, &tmp);
if (err < 0) {
fprintf(stderr,
"SMP mux requested, no pause support\n");
exit(1);
}
vm_set_capability(ctx, cpu, VM_CAP_PAUSE_EXIT, 1);
if (cpu == BSP)
handler[VM_EXITCODE_PAUSE] = vmexit_pause;
}
if (x2apic_mode)
err = vm_set_x2apic_state(ctx, cpu, X2APIC_ENABLED);
else
err = vm_set_x2apic_state(ctx, cpu, X2APIC_DISABLED);
if (err) {
fprintf(stderr, "Unable to set x2apic state (%d)\n", err);
exit(1);
}
vm_set_capability(ctx, cpu, VM_CAP_ENABLE_INVPCID, 1);
}
static struct vmctx *
do_open(const char *vmname)
{
struct vmctx *ctx;
int error;
bool reinit, romboot;
reinit = romboot = false;
if (lpc_bootrom())
romboot = true;
error = vm_create(vmname);
if (error) {
if (errno == EEXIST) {
if (romboot) {
reinit = true;
} else {
/*
* The virtual machine has been setup by the
* userspace bootloader.
*/
}
} else {
perror("vm_create");
exit(1);
}
} else {
if (!romboot) {
/*
* If the virtual machine was just created then a
* bootrom must be configured to boot it.
*/
fprintf(stderr, "virtual machine cannot be booted\n");
exit(1);
}
}
ctx = vm_open(vmname);
if (ctx == NULL) {
perror("vm_open");
exit(1);
}
if (reinit) {
error = vm_reinit(ctx);
if (error) {
perror("vm_reinit");
exit(1);
}
}
return (ctx);
}
int
main(int argc, char *argv[])
{
int c, error, gdb_port, err, bvmcons;
int max_vcpus, mptgen, memflags;
int rtc_localtime;
struct vmctx *ctx;
uint64_t rip;
size_t memsize;
char *optstr;
bvmcons = 0;
progname = basename(argv[0]);
gdb_port = 0;
guest_ncpus = 1;
memsize = 256 * MB;
mptgen = 1;
rtc_localtime = 1;
memflags = 0;
optstr = "abehuwxACHIPSWYp:g:c:s:m:l:U:";
while ((c = getopt(argc, argv, optstr)) != -1) {
switch (c) {
case 'a':
x2apic_mode = 0;
break;
case 'A':
acpi = 1;
break;
case 'b':
bvmcons = 1;
break;
case 'p':
if (pincpu_parse(optarg) != 0) {
errx(EX_USAGE, "invalid vcpu pinning "
"configuration '%s'", optarg);
}
break;
case 'c':
guest_ncpus = atoi(optarg);
break;
case 'C':
memflags |= VM_MEM_F_INCORE;
break;
case 'g':
gdb_port = atoi(optarg);
break;
case 'l':
if (lpc_device_parse(optarg) != 0) {
errx(EX_USAGE, "invalid lpc device "
"configuration '%s'", optarg);
}
break;
case 's':
if (pci_parse_slot(optarg) != 0)
exit(1);
else
break;
case 'S':
memflags |= VM_MEM_F_WIRED;
break;
case 'm':
error = vm_parse_memsize(optarg, &memsize);
if (error)
errx(EX_USAGE, "invalid memsize '%s'", optarg);
break;
case 'H':
guest_vmexit_on_hlt = 1;
break;
case 'I':
/*
* The "-I" option was used to add an ioapic to the
* virtual machine.
*
* An ioapic is now provided unconditionally for each
* virtual machine and this option is now deprecated.
*/
break;
case 'P':
guest_vmexit_on_pause = 1;
break;
case 'e':
strictio = 1;
break;
case 'u':
rtc_localtime = 0;
break;
case 'U':
guest_uuid_str = optarg;
break;
case 'w':
strictmsr = 0;
break;
case 'W':
virtio_msix = 0;
break;
case 'x':
x2apic_mode = 1;
break;
case 'Y':
mptgen = 0;
break;
case 'h':
usage(0);
default:
usage(1);
}
}
argc -= optind;
argv += optind;
if (argc != 1)
usage(1);
vmname = argv[0];
ctx = do_open(vmname);
if (guest_ncpus < 1) {
fprintf(stderr, "Invalid guest vCPUs (%d)\n", guest_ncpus);
exit(1);
}
max_vcpus = num_vcpus_allowed(ctx);
if (guest_ncpus > max_vcpus) {
fprintf(stderr, "%d vCPUs requested but only %d available\n",
guest_ncpus, max_vcpus);
exit(1);
}
fbsdrun_set_capabilities(ctx, BSP);
vm_set_memflags(ctx, memflags);
err = vm_setup_memory(ctx, memsize, VM_MMAP_ALL);
if (err) {
fprintf(stderr, "Unable to setup memory (%d)\n", errno);
exit(1);
}
error = init_msr();
if (error) {
fprintf(stderr, "init_msr error %d", error);
exit(1);
}
init_mem();
init_inout();
pci_irq_init(ctx);
ioapic_init(ctx);
rtc_init(ctx, rtc_localtime);
sci_init(ctx);
/*
* Exit if a device emulation finds an error in it's initilization
*/
if (init_pci(ctx) != 0)
exit(1);
if (gdb_port != 0)
init_dbgport(gdb_port);
if (bvmcons)
init_bvmcons();
if (lpc_bootrom()) {
if (vm_set_capability(ctx, BSP, VM_CAP_UNRESTRICTED_GUEST, 1)) {
fprintf(stderr, "ROM boot failed: unrestricted guest "
"capability not available\n");
exit(1);
}
error = vcpu_reset(ctx, BSP);
assert(error == 0);
}
error = vm_get_register(ctx, BSP, VM_REG_GUEST_RIP, &rip);
assert(error == 0);
/*
* build the guest tables, MP etc.
*/
if (mptgen) {
error = mptable_build(ctx, guest_ncpus);
if (error)
exit(1);
}
error = smbios_build(ctx);
assert(error == 0);
if (acpi) {
error = acpi_build(ctx, guest_ncpus);
assert(error == 0);
}
if (lpc_bootrom())
fwctl_init();
/*
* Change the proc title to include the VM name.
*/
setproctitle("%s", vmname);
/*
* Add CPU 0
*/
fbsdrun_addcpu(ctx, BSP, BSP, rip);
/*
* Head off to the main event dispatch loop
*/
mevent_dispatch();
exit(1);
}
|