summaryrefslogtreecommitdiffstats
path: root/lib/libvmmapi/vmmapi.c
blob: 6fec469ac92f3ec8a77b54ea062901c01a1254fe (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
/*-
 * 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/sysctl.h>
#include <sys/ioctl.h>
#include <sys/mman.h>

#include <machine/specialreg.h>

#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>

#include <libutil.h>

#include <machine/vmm.h>
#include <machine/vmm_dev.h>

#include "vmmapi.h"

#define	MB	(1024 * 1024UL)
#define	GB	(1024 * 1024 * 1024UL)

struct vmctx {
	int	fd;
	uint32_t lowmem_limit;
	enum vm_mmap_style vms;
	size_t	lowmem;
	char	*lowmem_addr;
	size_t	highmem;
	char	*highmem_addr;
	char	*name;
};

#define	CREATE(x)  sysctlbyname("hw.vmm.create", NULL, NULL, (x), strlen((x)))
#define	DESTROY(x) sysctlbyname("hw.vmm.destroy", NULL, NULL, (x), strlen((x)))

static int
vm_device_open(const char *name)
{
        int fd, len;
        char *vmfile;

	len = strlen("/dev/vmm/") + strlen(name) + 1;
	vmfile = malloc(len);
	assert(vmfile != NULL);
	snprintf(vmfile, len, "/dev/vmm/%s", name);

        /* Open the device file */
        fd = open(vmfile, O_RDWR, 0);

	free(vmfile);
        return (fd);
}

int
vm_create(const char *name)
{

	return (CREATE((char *)name));
}

struct vmctx *
vm_open(const char *name)
{
	struct vmctx *vm;

	vm = malloc(sizeof(struct vmctx) + strlen(name) + 1);
	assert(vm != NULL);

	vm->fd = -1;
	vm->lowmem_limit = 3 * GB;
	vm->name = (char *)(vm + 1);
	strcpy(vm->name, name);

	if ((vm->fd = vm_device_open(vm->name)) < 0)
		goto err;

	return (vm);
err:
	vm_destroy(vm);
	return (NULL);
}

void
vm_destroy(struct vmctx *vm)
{
	assert(vm != NULL);

	if (vm->fd >= 0)
		close(vm->fd);
	DESTROY(vm->name);

	free(vm);
}

int
vm_parse_memsize(const char *optarg, size_t *ret_memsize)
{
	char *endptr;
	size_t optval;
	int error;

	optval = strtoul(optarg, &endptr, 0);
	if (*optarg != '\0' && *endptr == '\0') {
		/*
		 * For the sake of backward compatibility if the memory size
		 * specified on the command line is less than a megabyte then
		 * it is interpreted as being in units of MB.
		 */
		if (optval < MB)
			optval *= MB;
		*ret_memsize = optval;
		error = 0;
	} else
		error = expand_number(optarg, ret_memsize);

	return (error);
}

int
vm_get_memory_seg(struct vmctx *ctx, vm_paddr_t gpa, size_t *ret_len,
		  int *wired)
{
	int error;
	struct vm_memory_segment seg;

	bzero(&seg, sizeof(seg));
	seg.gpa = gpa;
	error = ioctl(ctx->fd, VM_GET_MEMORY_SEG, &seg);
	*ret_len = seg.len;
	if (wired != NULL)
		*wired = seg.wired;
	return (error);
}

uint32_t
vm_get_lowmem_limit(struct vmctx *ctx)
{

	return (ctx->lowmem_limit);
}

void
vm_set_lowmem_limit(struct vmctx *ctx, uint32_t limit)
{

	ctx->lowmem_limit = limit;
}

static int
setup_memory_segment(struct vmctx *ctx, vm_paddr_t gpa, size_t len, char **addr)
{
	int error;
	struct vm_memory_segment seg;

	/*
	 * Create and optionally map 'len' bytes of memory at guest
	 * physical address 'gpa'
	 */
	bzero(&seg, sizeof(seg));
	seg.gpa = gpa;
	seg.len = len;
	error = ioctl(ctx->fd, VM_MAP_MEMORY, &seg);
	if (error == 0 && addr != NULL) {
		*addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_SHARED,
				ctx->fd, gpa);
	}
	return (error);
}

int
vm_setup_memory(struct vmctx *ctx, size_t memsize, enum vm_mmap_style vms)
{
	char **addr;
	int error;

	/* XXX VM_MMAP_SPARSE not implemented yet */
	assert(vms == VM_MMAP_NONE || vms == VM_MMAP_ALL);
	ctx->vms = vms;

	/*
	 * If 'memsize' cannot fit entirely in the 'lowmem' segment then
	 * create another 'highmem' segment above 4GB for the remainder.
	 */
	if (memsize > ctx->lowmem_limit) {
		ctx->lowmem = ctx->lowmem_limit;
		ctx->highmem = memsize - ctx->lowmem;
	} else {
		ctx->lowmem = memsize;
		ctx->highmem = 0;
	}

	if (ctx->lowmem > 0) {
		addr = (vms == VM_MMAP_ALL) ? &ctx->lowmem_addr : NULL;
		error = setup_memory_segment(ctx, 0, ctx->lowmem, addr);
		if (error)
			return (error);
	}

	if (ctx->highmem > 0) {
		addr = (vms == VM_MMAP_ALL) ? &ctx->highmem_addr : NULL;
		error = setup_memory_segment(ctx, 4*GB, ctx->highmem, addr);
		if (error)
			return (error);
	}

	return (0);
}

void *
vm_map_gpa(struct vmctx *ctx, vm_paddr_t gaddr, size_t len)
{

	/* XXX VM_MMAP_SPARSE not implemented yet */
	assert(ctx->vms == VM_MMAP_ALL);

	if (gaddr < ctx->lowmem && gaddr + len <= ctx->lowmem)
		return ((void *)(ctx->lowmem_addr + gaddr));

	if (gaddr >= 4*GB) {
		gaddr -= 4*GB;
		if (gaddr < ctx->highmem && gaddr + len <= ctx->highmem)
			return ((void *)(ctx->highmem_addr + gaddr));
	}

	return (NULL);
}

int
vm_set_desc(struct vmctx *ctx, int vcpu, int reg,
	    uint64_t base, uint32_t limit, uint32_t access)
{
	int error;
	struct vm_seg_desc vmsegdesc;

	bzero(&vmsegdesc, sizeof(vmsegdesc));
	vmsegdesc.cpuid = vcpu;
	vmsegdesc.regnum = reg;
	vmsegdesc.desc.base = base;
	vmsegdesc.desc.limit = limit;
	vmsegdesc.desc.access = access;

	error = ioctl(ctx->fd, VM_SET_SEGMENT_DESCRIPTOR, &vmsegdesc);
	return (error);
}

int
vm_get_desc(struct vmctx *ctx, int vcpu, int reg,
	    uint64_t *base, uint32_t *limit, uint32_t *access)
{
	int error;
	struct vm_seg_desc vmsegdesc;

	bzero(&vmsegdesc, sizeof(vmsegdesc));
	vmsegdesc.cpuid = vcpu;
	vmsegdesc.regnum = reg;

	error = ioctl(ctx->fd, VM_GET_SEGMENT_DESCRIPTOR, &vmsegdesc);
	if (error == 0) {
		*base = vmsegdesc.desc.base;
		*limit = vmsegdesc.desc.limit;
		*access = vmsegdesc.desc.access;
	}
	return (error);
}

int
vm_set_register(struct vmctx *ctx, int vcpu, int reg, uint64_t val)
{
	int error;
	struct vm_register vmreg;

	bzero(&vmreg, sizeof(vmreg));
	vmreg.cpuid = vcpu;
	vmreg.regnum = reg;
	vmreg.regval = val;

	error = ioctl(ctx->fd, VM_SET_REGISTER, &vmreg);
	return (error);
}

int
vm_get_register(struct vmctx *ctx, int vcpu, int reg, uint64_t *ret_val)
{
	int error;
	struct vm_register vmreg;

	bzero(&vmreg, sizeof(vmreg));
	vmreg.cpuid = vcpu;
	vmreg.regnum = reg;

	error = ioctl(ctx->fd, VM_GET_REGISTER, &vmreg);
	*ret_val = vmreg.regval;
	return (error);
}

int
vm_run(struct vmctx *ctx, int vcpu, uint64_t rip, struct vm_exit *vmexit)
{
	int error;
	struct vm_run vmrun;

	bzero(&vmrun, sizeof(vmrun));
	vmrun.cpuid = vcpu;
	vmrun.rip = rip;

	error = ioctl(ctx->fd, VM_RUN, &vmrun);
	bcopy(&vmrun.vm_exit, vmexit, sizeof(struct vm_exit));
	return (error);
}

static int
vm_inject_event_real(struct vmctx *ctx, int vcpu, enum vm_event_type type,
		     int vector, int error_code, int error_code_valid)
{
	struct vm_event ev;

	bzero(&ev, sizeof(ev));
	ev.cpuid = vcpu;
	ev.type = type;
	ev.vector = vector;
	ev.error_code = error_code;
	ev.error_code_valid = error_code_valid;

	return (ioctl(ctx->fd, VM_INJECT_EVENT, &ev));
}

int
vm_inject_event(struct vmctx *ctx, int vcpu, enum vm_event_type type,
		int vector)
{

	return (vm_inject_event_real(ctx, vcpu, type, vector, 0, 0));
}

int
vm_inject_event2(struct vmctx *ctx, int vcpu, enum vm_event_type type,
		 int vector, int error_code)
{

	return (vm_inject_event_real(ctx, vcpu, type, vector, error_code, 1));
}

int
vm_apicid2vcpu(struct vmctx *ctx, int apicid)
{
	/*
	 * The apic id associated with the 'vcpu' has the same numerical value
	 * as the 'vcpu' itself.
	 */
	return (apicid);
}

int
vm_lapic_irq(struct vmctx *ctx, int vcpu, int vector)
{
	struct vm_lapic_irq vmirq;

	bzero(&vmirq, sizeof(vmirq));
	vmirq.cpuid = vcpu;
	vmirq.vector = vector;

	return (ioctl(ctx->fd, VM_LAPIC_IRQ, &vmirq));
}

int
vm_lapic_local_irq(struct vmctx *ctx, int vcpu, int vector)
{
	struct vm_lapic_irq vmirq;

	bzero(&vmirq, sizeof(vmirq));
	vmirq.cpuid = vcpu;
	vmirq.vector = vector;

	return (ioctl(ctx->fd, VM_LAPIC_LOCAL_IRQ, &vmirq));
}

int
vm_lapic_msi(struct vmctx *ctx, uint64_t addr, uint64_t msg)
{
	struct vm_lapic_msi vmmsi;

	bzero(&vmmsi, sizeof(vmmsi));
	vmmsi.addr = addr;
	vmmsi.msg = msg;

	return (ioctl(ctx->fd, VM_LAPIC_MSI, &vmmsi));
}

int
vm_ioapic_assert_irq(struct vmctx *ctx, int irq)
{
	struct vm_ioapic_irq ioapic_irq;

	bzero(&ioapic_irq, sizeof(struct vm_ioapic_irq));
	ioapic_irq.irq = irq;

	return (ioctl(ctx->fd, VM_IOAPIC_ASSERT_IRQ, &ioapic_irq));
}

int
vm_ioapic_deassert_irq(struct vmctx *ctx, int irq)
{
	struct vm_ioapic_irq ioapic_irq;

	bzero(&ioapic_irq, sizeof(struct vm_ioapic_irq));
	ioapic_irq.irq = irq;

	return (ioctl(ctx->fd, VM_IOAPIC_DEASSERT_IRQ, &ioapic_irq));
}

int
vm_ioapic_pulse_irq(struct vmctx *ctx, int irq)
{
	struct vm_ioapic_irq ioapic_irq;

	bzero(&ioapic_irq, sizeof(struct vm_ioapic_irq));
	ioapic_irq.irq = irq;

	return (ioctl(ctx->fd, VM_IOAPIC_PULSE_IRQ, &ioapic_irq));
}

int
vm_inject_nmi(struct vmctx *ctx, int vcpu)
{
	struct vm_nmi vmnmi;

	bzero(&vmnmi, sizeof(vmnmi));
	vmnmi.cpuid = vcpu;

	return (ioctl(ctx->fd, VM_INJECT_NMI, &vmnmi));
}

static struct {
	const char	*name;
	int		type;
} capstrmap[] = {
	{ "hlt_exit",		VM_CAP_HALT_EXIT },
	{ "mtrap_exit",		VM_CAP_MTRAP_EXIT },
	{ "pause_exit",		VM_CAP_PAUSE_EXIT },
	{ "unrestricted_guest",	VM_CAP_UNRESTRICTED_GUEST },
	{ "enable_invpcid",	VM_CAP_ENABLE_INVPCID },
	{ 0 }
};

int
vm_capability_name2type(const char *capname)
{
	int i;

	for (i = 0; capstrmap[i].name != NULL && capname != NULL; i++) {
		if (strcmp(capstrmap[i].name, capname) == 0)
			return (capstrmap[i].type);
	}

	return (-1);
}

const char *
vm_capability_type2name(int type)
{
	int i;

	for (i = 0; capstrmap[i].name != NULL; i++) {
		if (capstrmap[i].type == type)
			return (capstrmap[i].name);
	}

	return (NULL);
}

int
vm_get_capability(struct vmctx *ctx, int vcpu, enum vm_cap_type cap,
		  int *retval)
{
	int error;
	struct vm_capability vmcap;

	bzero(&vmcap, sizeof(vmcap));
	vmcap.cpuid = vcpu;
	vmcap.captype = cap;

	error = ioctl(ctx->fd, VM_GET_CAPABILITY, &vmcap);
	*retval = vmcap.capval;
	return (error);
}

int
vm_set_capability(struct vmctx *ctx, int vcpu, enum vm_cap_type cap, int val)
{
	struct vm_capability vmcap;

	bzero(&vmcap, sizeof(vmcap));
	vmcap.cpuid = vcpu;
	vmcap.captype = cap;
	vmcap.capval = val;
	
	return (ioctl(ctx->fd, VM_SET_CAPABILITY, &vmcap));
}

int
vm_assign_pptdev(struct vmctx *ctx, int bus, int slot, int func)
{
	struct vm_pptdev pptdev;

	bzero(&pptdev, sizeof(pptdev));
	pptdev.bus = bus;
	pptdev.slot = slot;
	pptdev.func = func;

	return (ioctl(ctx->fd, VM_BIND_PPTDEV, &pptdev));
}

int
vm_unassign_pptdev(struct vmctx *ctx, int bus, int slot, int func)
{
	struct vm_pptdev pptdev;

	bzero(&pptdev, sizeof(pptdev));
	pptdev.bus = bus;
	pptdev.slot = slot;
	pptdev.func = func;

	return (ioctl(ctx->fd, VM_UNBIND_PPTDEV, &pptdev));
}

int
vm_map_pptdev_mmio(struct vmctx *ctx, int bus, int slot, int func,
		   vm_paddr_t gpa, size_t len, vm_paddr_t hpa)
{
	struct vm_pptdev_mmio pptmmio;

	bzero(&pptmmio, sizeof(pptmmio));
	pptmmio.bus = bus;
	pptmmio.slot = slot;
	pptmmio.func = func;
	pptmmio.gpa = gpa;
	pptmmio.len = len;
	pptmmio.hpa = hpa;

	return (ioctl(ctx->fd, VM_MAP_PPTDEV_MMIO, &pptmmio));
}

int
vm_setup_pptdev_msi(struct vmctx *ctx, int vcpu, int bus, int slot, int func,
    uint64_t addr, uint64_t msg, int numvec)
{
	struct vm_pptdev_msi pptmsi;

	bzero(&pptmsi, sizeof(pptmsi));
	pptmsi.vcpu = vcpu;
	pptmsi.bus = bus;
	pptmsi.slot = slot;
	pptmsi.func = func;
	pptmsi.msg = msg;
	pptmsi.addr = addr;
	pptmsi.numvec = numvec;

	return (ioctl(ctx->fd, VM_PPTDEV_MSI, &pptmsi));
}

int	
vm_setup_pptdev_msix(struct vmctx *ctx, int vcpu, int bus, int slot, int func,
    int idx, uint64_t addr, uint64_t msg, uint32_t vector_control)
{
	struct vm_pptdev_msix pptmsix;

	bzero(&pptmsix, sizeof(pptmsix));
	pptmsix.vcpu = vcpu;
	pptmsix.bus = bus;
	pptmsix.slot = slot;
	pptmsix.func = func;
	pptmsix.idx = idx;
	pptmsix.msg = msg;
	pptmsix.addr = addr;
	pptmsix.vector_control = vector_control;

	return ioctl(ctx->fd, VM_PPTDEV_MSIX, &pptmsix);
}

uint64_t *
vm_get_stats(struct vmctx *ctx, int vcpu, struct timeval *ret_tv,
	     int *ret_entries)
{
	int error;

	static struct vm_stats vmstats;

	vmstats.cpuid = vcpu;

	error = ioctl(ctx->fd, VM_STATS, &vmstats);
	if (error == 0) {
		if (ret_entries)
			*ret_entries = vmstats.num_entries;
		if (ret_tv)
			*ret_tv = vmstats.tv;
		return (vmstats.statbuf);
	} else
		return (NULL);
}

const char *
vm_get_stat_desc(struct vmctx *ctx, int index)
{
	static struct vm_stat_desc statdesc;

	statdesc.index = index;
	if (ioctl(ctx->fd, VM_STAT_DESC, &statdesc) == 0)
		return (statdesc.desc);
	else
		return (NULL);
}

int
vm_get_x2apic_state(struct vmctx *ctx, int vcpu, enum x2apic_state *state)
{
	int error;
	struct vm_x2apic x2apic;

	bzero(&x2apic, sizeof(x2apic));
	x2apic.cpuid = vcpu;

	error = ioctl(ctx->fd, VM_GET_X2APIC_STATE, &x2apic);
	*state = x2apic.state;
	return (error);
}

int
vm_set_x2apic_state(struct vmctx *ctx, int vcpu, enum x2apic_state state)
{
	int error;
	struct vm_x2apic x2apic;

	bzero(&x2apic, sizeof(x2apic));
	x2apic.cpuid = vcpu;
	x2apic.state = state;

	error = ioctl(ctx->fd, VM_SET_X2APIC_STATE, &x2apic);

	return (error);
}

/*
 * From Intel Vol 3a:
 * Table 9-1. IA-32 Processor States Following Power-up, Reset or INIT
 */
int
vcpu_reset(struct vmctx *vmctx, int vcpu)
{
	int error;
	uint64_t rflags, rip, cr0, cr4, zero, desc_base, rdx;
	uint32_t desc_access, desc_limit;
	uint16_t sel;

	zero = 0;

	rflags = 0x2;
	error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RFLAGS, rflags);
	if (error)
		goto done;

	rip = 0xfff0;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RIP, rip)) != 0)
		goto done;

	cr0 = CR0_NE;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_CR0, cr0)) != 0)
		goto done;

	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_CR3, zero)) != 0)
		goto done;
	
	cr4 = 0;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_CR4, cr4)) != 0)
		goto done;

	/*
	 * CS: present, r/w, accessed, 16-bit, byte granularity, usable
	 */
	desc_base = 0xffff0000;
	desc_limit = 0xffff;
	desc_access = 0x0093;
	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_CS,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	sel = 0xf000;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_CS, sel)) != 0)
		goto done;

	/*
	 * SS,DS,ES,FS,GS: present, r/w, accessed, 16-bit, byte granularity
	 */
	desc_base = 0;
	desc_limit = 0xffff;
	desc_access = 0x0093;
	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_SS,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_DS,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_ES,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_FS,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_GS,
			    desc_base, desc_limit, desc_access);
	if (error)
		goto done;

	sel = 0;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_SS, sel)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_DS, sel)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_ES, sel)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_FS, sel)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_GS, sel)) != 0)
		goto done;

	/* General purpose registers */
	rdx = 0xf00;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RAX, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RBX, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RCX, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RDX, rdx)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RSI, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RDI, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RBP, zero)) != 0)
		goto done;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_RSP, zero)) != 0)
		goto done;

	/* GDTR, IDTR */
	desc_base = 0;
	desc_limit = 0xffff;
	desc_access = 0;
	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_GDTR,
			    desc_base, desc_limit, desc_access);
	if (error != 0)
		goto done;

	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_IDTR,
			    desc_base, desc_limit, desc_access);
	if (error != 0)
		goto done;

	/* TR */
	desc_base = 0;
	desc_limit = 0xffff;
	desc_access = 0x0000008b;
	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_TR, 0, 0, desc_access);
	if (error)
		goto done;

	sel = 0;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_TR, sel)) != 0)
		goto done;

	/* LDTR */
	desc_base = 0;
	desc_limit = 0xffff;
	desc_access = 0x00000082;
	error = vm_set_desc(vmctx, vcpu, VM_REG_GUEST_LDTR, desc_base,
			    desc_limit, desc_access);
	if (error)
		goto done;

	sel = 0;
	if ((error = vm_set_register(vmctx, vcpu, VM_REG_GUEST_LDTR, 0)) != 0)
		goto done;

	/* XXX cr2, debug registers */

	error = 0;
done:
	return (error);
}

int
vm_get_gpa_pmap(struct vmctx *ctx, uint64_t gpa, uint64_t *pte, int *num)
{
	int error, i;
	struct vm_gpa_pte gpapte;

	bzero(&gpapte, sizeof(gpapte));
	gpapte.gpa = gpa;

	error = ioctl(ctx->fd, VM_GET_GPA_PMAP, &gpapte);

	if (error == 0) {
		*num = gpapte.ptenum;
		for (i = 0; i < gpapte.ptenum; i++)
			pte[i] = gpapte.pte[i];
	}

	return (error);
}

int
vm_get_hpet_capabilities(struct vmctx *ctx, uint32_t *capabilities)
{
	int error;
	struct vm_hpet_cap cap;

	bzero(&cap, sizeof(struct vm_hpet_cap));
	error = ioctl(ctx->fd, VM_GET_HPET_CAPABILITIES, &cap);
	if (capabilities != NULL)
		*capabilities = cap.capabilities;
	return (error);
}
OpenPOWER on IntegriCloud