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
|
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <asm/asm.h>
#include <asm/asm-offsets.h>
#include <asm/bitsperlong.h>
#include <asm/frame.h>
#include <asm/nospec-branch.h>
#include "kvm-asm-offsets.h"
#include "vmenter.h"
#define SVM_vmcb01_pa (SVM_vmcb01 + KVM_VMCB_pa)
.section .noinstr.text, "ax"
.macro RESTORE_GUEST_SPEC_CTRL
/* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
ALTERNATIVE_2 "", \
"jmp 800f", X86_FEATURE_MSR_SPEC_CTRL, \
"", X86_FEATURE_V_SPEC_CTRL
.endm
.macro RESTORE_HOST_SPEC_CTRL
/* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
ALTERNATIVE_2 "", \
"jmp 900f", X86_FEATURE_MSR_SPEC_CTRL, \
"", X86_FEATURE_V_SPEC_CTRL
.endm
#define SVM_CLEAR_CPU_BUFFERS \
ALTERNATIVE "", __CLEAR_CPU_BUFFERS, X86_FEATURE_CLEAR_CPU_BUF_VM
/**
* __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode
* @svm: struct vcpu_svm *
* @enter_flags: u32
*/
SYM_FUNC_START(__svm_vcpu_run)
push %_ASM_BP
mov %_ASM_SP, %_ASM_BP
#ifdef CONFIG_X86_64
push %r15
push %r14
push %r13
push %r12
#else
push %edi
push %esi
#endif
push %_ASM_BX
/*
* Save variables needed after vmexit on the stack, in inverse
* order compared to when they are needed.
*/
/* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */
push %_ASM_ARG2
/* Needed to restore access to percpu variables. */
__ASM_SIZE(push) PER_CPU_VAR(svm_data + SD_save_area_pa)
/* Finally save @svm. */
push %_ASM_ARG1
.ifnc _ASM_ARG1, _ASM_DI
/*
* Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
* and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
*/
mov %_ASM_ARG1, %_ASM_DI
.endif
/* Clobbers RAX, RCX, RDX (and ESI on 32-bit), consumes RDI (@svm). */
RESTORE_GUEST_SPEC_CTRL
801:
/*
* Use a single vmcb (vmcb01 because it's always valid) for
* context switching guest state via VMLOAD/VMSAVE, that way
* the state doesn't need to be copied between vmcb01 and
* vmcb02 when switching vmcbs for nested virtualization.
*/
mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
1: vmload %_ASM_AX
2:
/* Get svm->current_vmcb->pa into RAX. */
mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
/*
* Load guest registers. Intentionally omit %_ASM_AX and %_ASM_SP as
* context switched by hardware
*/
LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, \
%_ASM_CX, %_ASM_DX, %_ASM_BX, %_ASM_BP, %_ASM_SI
#ifdef CONFIG_X86_64
LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, \
%r8, %r9, %r10, %r11, %r12, %r13, %r14, %r15
#endif
LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, %_ASM_DI
/* Clobbers EFLAGS.ZF */
SVM_CLEAR_CPU_BUFFERS
/* Enter guest mode */
3: vmrun %_ASM_AX
4:
/* Pop @svm to RAX while it's the only available register. */
pop %_ASM_AX
/*
* Save all guest registers. Intentionally omit %_ASM_AX and %_ASM_SP as
* context switched by hardware
*/
STORE_REGS %_ASM_AX, SVM_vcpu_arch_regs, \
%_ASM_CX, %_ASM_DX, %_ASM_BX, %_ASM_BP, %_ASM_SI, %_ASM_DI
#ifdef CONFIG_X86_64
STORE_REGS %_ASM_AX, SVM_vcpu_arch_regs, \
%r8, %r9, %r10, %r11, %r12, %r13, %r14, %r15
#endif
/* @svm can stay in RDI from now on. */
mov %_ASM_AX, %_ASM_DI
mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
5: vmsave %_ASM_AX
6:
/* Restores GSBASE among other things, allowing access to percpu data. */
pop %_ASM_AX
7: vmload %_ASM_AX
8:
/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
/*
* Clobbers RAX, RCX, RDX (and ESI, EDI on 32-bit), consumes RDI (@svm)
* and RSP (pointer to @spec_ctrl_intercepted).
*/
RESTORE_HOST_SPEC_CTRL
901:
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
* untrained as soon as we exit the VM and are back to the
* kernel. This should be done before re-enabling interrupts
* because interrupt handlers won't sanitize 'ret' if the return is
* from the kernel.
*/
UNTRAIN_RET_VM
/*
* Clear all general purpose registers except RSP and RAX to prevent
* speculative use of the guest's values, even those that are reloaded
* via the stack. In theory, an L1 cache miss when restoring registers
* could lead to speculative execution with the guest's values.
* Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
* free. RSP and RAX are exempt as they are restored by hardware
* during VM-Exit.
*/
CLEAR_REGS %ecx, %edx, %ebx, %ebp, %esi, %edi
#ifdef CONFIG_X86_64
CLEAR_REGS %r8d, %r9d, %r10d, %r11d, %r12d, %r13d, %r14d, %r15d
#endif
/* "Pop" @enter_flags. */
pop %_ASM_BX
pop %_ASM_BX
#ifdef CONFIG_X86_64
pop %r12
pop %r13
pop %r14
pop %r15
#else
pop %esi
pop %edi
#endif
pop %_ASM_BP
RET
800:
RESTORE_GUEST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), 801b
jmp 801b
900:
RESTORE_HOST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), (%_ASM_SP), 901b
jmp 901b
10: cmpb $0, _ASM_RIP(virt_rebooting)
jne 2b
ud2
30: cmpb $0, _ASM_RIP(virt_rebooting)
jne 4b
ud2
50: cmpb $0, _ASM_RIP(virt_rebooting)
jne 6b
ud2
70: cmpb $0, _ASM_RIP(virt_rebooting)
jne 8b
ud2
_ASM_EXTABLE(1b, 10b)
_ASM_EXTABLE(3b, 30b)
_ASM_EXTABLE(5b, 50b)
_ASM_EXTABLE(7b, 70b)
SYM_FUNC_END(__svm_vcpu_run)
#ifdef CONFIG_KVM_AMD_SEV
#define SEV_ES_GPRS_BASE 0x300
/**
* __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
* @svm: struct vcpu_svm *
* @enter_flags: u32
*/
SYM_FUNC_START(__svm_sev_es_vcpu_run)
FRAME_BEGIN
/*
* Save non-volatile (callee-saved) registers to the host save area.
* Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not
* saved on VMRUN.
*/
STORE_REGS %rdx, SEV_ES_GPRS_BASE, %rbp, %r15, %r14, %r13, %r12, %rbx
/*
* Save volatile registers that hold arguments that are needed after
* #VMEXIT (RDI=@svm and RSI=@enter_flags).
*/
STORE_REGS %rdx, SEV_ES_GPRS_BASE, %rdi, %rsi
/* Clobbers RAX, RCX, and RDX (@hostsa), consumes RDI (@svm). */
RESTORE_GUEST_SPEC_CTRL
801:
/* Get svm->current_vmcb->pa into RAX. */
mov SVM_current_vmcb(%rdi), %rax
mov KVM_VMCB_pa(%rax), %rax
/* Clobbers EFLAGS.ZF */
SVM_CLEAR_CPU_BUFFERS
/* Enter guest mode */
1: vmrun %rax
2:
/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
/* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@enter_flags). */
RESTORE_HOST_SPEC_CTRL
901:
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
* untrained as soon as we exit the VM and are back to the
* kernel. This should be done before re-enabling interrupts
* because interrupt handlers won't sanitize RET if the return is
* from the kernel.
*/
UNTRAIN_RET_VM
FRAME_END
RET
800:
RESTORE_GUEST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), 801b
jmp 801b
900:
RESTORE_HOST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), %esi, 901b
jmp 901b
3: cmpb $0, virt_rebooting(%rip)
jne 2b
ud2
_ASM_EXTABLE(1b, 3b)
SYM_FUNC_END(__svm_sev_es_vcpu_run)
#endif /* CONFIG_KVM_AMD_SEV */
|