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
|
/*
* Copyright (C) 2016 Veertu Inc,
* Copyright (C) 2017 Google Inc,
* Based on Veertu vddh/vmm/vmx.h
*
* Interfaces to Hypervisor.framework to read/write X86 registers and VMCS.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* 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/>.
*
* This file contain code under public domain from the hvdos project:
* https://github.com/mist64/hvdos
*/
#ifndef VMX_H
#define VMX_H
#include <Hypervisor/hv.h>
#include <Hypervisor/hv_vmx.h>
#include "vmcs.h"
#include "cpu.h"
#include "x86.h"
#include "system/hvf.h"
#include "system/hvf_int.h"
#include "exec/address-spaces.h"
static inline uint64_t rreg(hv_vcpuid_t vcpu, hv_x86_reg_t reg)
{
uint64_t v;
if (hv_vcpu_read_register(vcpu, reg, &v)) {
abort();
}
return v;
}
/* write GPR */
static inline void wreg(hv_vcpuid_t vcpu, hv_x86_reg_t reg, uint64_t v)
{
if (hv_vcpu_write_register(vcpu, reg, v)) {
abort();
}
}
/* read VMCS field */
static inline uint64_t rvmcs(hv_vcpuid_t vcpu, uint32_t field)
{
uint64_t v;
hv_vmx_vcpu_read_vmcs(vcpu, field, &v);
return v;
}
/* write VMCS field */
static inline void wvmcs(hv_vcpuid_t vcpu, uint32_t field, uint64_t v)
{
hv_vmx_vcpu_write_vmcs(vcpu, field, v);
}
/* desired control word constrained by hardware/hypervisor capabilities */
static inline uint64_t cap2ctrl(uint64_t cap, uint64_t ctrl)
{
return (ctrl | (cap & 0xffffffff)) & (cap >> 32);
}
#define VM_ENTRY_GUEST_LMA (1LL << 9)
#define AR_TYPE_ACCESSES_MASK 1
#define AR_TYPE_READABLE_MASK (1 << 1)
#define AR_TYPE_WRITABLE_MASK (1 << 2)
#define AR_TYPE_CODE_MASK (1 << 3)
#define AR_TYPE_MASK 0x0f
#define AR_TYPE_BUSY_64_TSS 11
#define AR_TYPE_BUSY_32_TSS 11
#define AR_TYPE_BUSY_16_TSS 3
#define AR_TYPE_LDT 2
static void enter_long_mode(hv_vcpuid_t vcpu, uint64_t cr0, uint64_t efer)
{
uint64_t entry_ctls;
efer |= MSR_EFER_LMA;
wvmcs(vcpu, VMCS_GUEST_IA32_EFER, efer);
entry_ctls = rvmcs(vcpu, VMCS_ENTRY_CTLS);
wvmcs(vcpu, VMCS_ENTRY_CTLS, entry_ctls | VM_ENTRY_GUEST_LMA);
uint64_t guest_tr_ar = rvmcs(vcpu, VMCS_GUEST_TR_ACCESS_RIGHTS);
if ((efer & MSR_EFER_LME) &&
(guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
wvmcs(vcpu, VMCS_GUEST_TR_ACCESS_RIGHTS,
(guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS);
}
}
static void exit_long_mode(hv_vcpuid_t vcpu, uint64_t cr0, uint64_t efer)
{
uint64_t entry_ctls;
entry_ctls = rvmcs(vcpu, VMCS_ENTRY_CTLS);
wvmcs(vcpu, VMCS_ENTRY_CTLS, entry_ctls & ~VM_ENTRY_GUEST_LMA);
efer &= ~MSR_EFER_LMA;
wvmcs(vcpu, VMCS_GUEST_IA32_EFER, efer);
}
static inline void macvm_set_cr0(hv_vcpuid_t vcpu, uint64_t cr0)
{
int i;
uint64_t pdpte[4] = {0, 0, 0, 0};
uint64_t efer = rvmcs(vcpu, VMCS_GUEST_IA32_EFER);
uint64_t old_cr0 = rvmcs(vcpu, VMCS_GUEST_CR0);
uint64_t changed_cr0 = old_cr0 ^ cr0;
uint64_t mask = CR0_PG_MASK | CR0_CD_MASK | CR0_NW_MASK |
CR0_NE_MASK | CR0_ET_MASK;
uint64_t entry_ctls;
if ((cr0 & CR0_PG_MASK) && (rvmcs(vcpu, VMCS_GUEST_CR4) & CR4_PAE_MASK) &&
!(efer & MSR_EFER_LME)) {
address_space_read(&address_space_memory,
rvmcs(vcpu, VMCS_GUEST_CR3) & ~0x1f,
MEMTXATTRS_UNSPECIFIED, pdpte, 32);
/* Only set PDPTE when appropriate. */
for (i = 0; i < 4; i++) {
wvmcs(vcpu, VMCS_GUEST_PDPTE0 + i * 2, pdpte[i]);
}
}
wvmcs(vcpu, VMCS_CR0_MASK, mask);
wvmcs(vcpu, VMCS_CR0_SHADOW, cr0);
if (efer & MSR_EFER_LME) {
if (changed_cr0 & CR0_PG_MASK) {
if (cr0 & CR0_PG_MASK) {
enter_long_mode(vcpu, cr0, efer);
} else {
exit_long_mode(vcpu, cr0, efer);
}
}
} else {
entry_ctls = rvmcs(vcpu, VMCS_ENTRY_CTLS);
wvmcs(vcpu, VMCS_ENTRY_CTLS, entry_ctls & ~VM_ENTRY_GUEST_LMA);
}
/* Filter new CR0 after we are finished examining it above. */
cr0 = (cr0 & ~(mask & ~CR0_PG_MASK));
wvmcs(vcpu, VMCS_GUEST_CR0, cr0 | CR0_NE_MASK | CR0_ET_MASK);
hv_vcpu_invalidate_tlb(vcpu);
}
static inline void macvm_set_cr4(hv_vcpuid_t vcpu, uint64_t cr4)
{
uint64_t guest_cr4 = cr4 | CR4_VMXE_MASK;
wvmcs(vcpu, VMCS_GUEST_CR4, guest_cr4);
wvmcs(vcpu, VMCS_CR4_SHADOW, cr4);
wvmcs(vcpu, VMCS_CR4_MASK, CR4_VMXE_MASK);
hv_vcpu_invalidate_tlb(vcpu);
}
static inline void macvm_set_rip(CPUState *cpu, uint64_t rip)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
uint64_t val;
/* BUG, should take considering overlap.. */
wreg(cpu->accel->fd, HV_X86_RIP, rip);
env->eip = rip;
/* after moving forward in rip, we need to clean INTERRUPTABILITY */
val = rvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY);
if (val & (VMCS_INTERRUPTIBILITY_STI_BLOCKING |
VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
env->hflags &= ~HF_INHIBIT_IRQ_MASK;
wvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY,
val & ~(VMCS_INTERRUPTIBILITY_STI_BLOCKING |
VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING));
}
}
static inline void vmx_clear_nmi_blocking(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
env->hflags2 &= ~HF2_NMI_MASK;
uint32_t gi = (uint32_t) rvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY);
gi &= ~VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
wvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
}
static inline void vmx_set_nmi_blocking(CPUState *cpu)
{
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
env->hflags2 |= HF2_NMI_MASK;
uint32_t gi = (uint32_t)rvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY);
gi |= VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
wvmcs(cpu->accel->fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
}
static inline void vmx_set_nmi_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->accel->fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->accel->fd, VMCS_PRI_PROC_BASED_CTLS, val |
VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
}
static inline void vmx_clear_nmi_window_exiting(CPUState *cpu)
{
uint64_t val;
val = rvmcs(cpu->accel->fd, VMCS_PRI_PROC_BASED_CTLS);
wvmcs(cpu->accel->fd, VMCS_PRI_PROC_BASED_CTLS, val &
~VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
}
#endif
|
