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
|
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright SUSE Linux Products GmbH 2010
*
* Authors: Alexander Graf <agraf@suse.de>
*/
/* Real mode helpers */
#if defined(CONFIG_PPC_BOOK3S_64)
#define GET_SHADOW_VCPU(reg) \
mr reg, r13
#define MTMSR_EERI(reg) mtmsrd (reg),1
#elif defined(CONFIG_PPC_BOOK3S_32)
#define GET_SHADOW_VCPU(reg) \
tophys(reg, r2); \
lwz reg, (THREAD + THREAD_KVM_SVCPU)(reg); \
tophys(reg, reg)
#define MTMSR_EERI(reg) mtmsr (reg)
#endif
/* Disable for nested KVM */
#define USE_QUICK_LAST_INST
/* Get helper functions for subarch specific functionality */
#if defined(CONFIG_PPC_BOOK3S_64)
#include "book3s_64_slb.S"
#elif defined(CONFIG_PPC_BOOK3S_32)
#include "book3s_32_sr.S"
#endif
/******************************************************************************
* *
* Entry code *
* *
*****************************************************************************/
.global kvmppc_handler_trampoline_enter
kvmppc_handler_trampoline_enter:
/* Required state:
*
* MSR = ~IR|DR
* R1 = host R1
* R2 = host R2
* R4 = guest shadow MSR
* R5 = normal host MSR
* R6 = current host MSR (EE, IR, DR off)
* LR = highmem guest exit code
* all other volatile GPRS = free
* SVCPU[CR] = guest CR
* SVCPU[XER] = guest XER
* SVCPU[CTR] = guest CTR
* SVCPU[LR] = guest LR
*/
/* r3 = shadow vcpu */
GET_SHADOW_VCPU(r3)
/* Save guest exit handler address and MSR */
mflr r0
PPC_STL r0, HSTATE_VMHANDLER(r3)
PPC_STL r5, HSTATE_HOST_MSR(r3)
/* Save R1/R2 in the PACA (64-bit) or shadow_vcpu (32-bit) */
PPC_STL r1, HSTATE_HOST_R1(r3)
PPC_STL r2, HSTATE_HOST_R2(r3)
/* Activate guest mode, so faults get handled by KVM */
li r11, KVM_GUEST_MODE_GUEST
stb r11, HSTATE_IN_GUEST(r3)
/* Switch to guest segment. This is subarch specific. */
LOAD_GUEST_SEGMENTS
#ifdef CONFIG_PPC_BOOK3S_64
/* Some guests may need to have dcbz set to 32 byte length.
*
* Usually we ensure that by patching the guest's instructions
* to trap on dcbz and emulate it in the hypervisor.
*
* If we can, we should tell the CPU to use 32 byte dcbz though,
* because that's a lot faster.
*/
lbz r0, HSTATE_RESTORE_HID5(r3)
cmpwi r0, 0
beq no_dcbz32_on
mfspr r0,SPRN_HID5
ori r0, r0, 0x80 /* XXX HID5_dcbz32 = 0x80 */
mtspr SPRN_HID5,r0
no_dcbz32_on:
#endif /* CONFIG_PPC_BOOK3S_64 */
/* Enter guest */
PPC_LL r8, SVCPU_CTR(r3)
PPC_LL r9, SVCPU_LR(r3)
lwz r10, SVCPU_CR(r3)
lwz r11, SVCPU_XER(r3)
mtctr r8
mtlr r9
mtcr r10
mtxer r11
/* Move SRR0 and SRR1 into the respective regs */
PPC_LL r9, SVCPU_PC(r3)
/* First clear RI in our current MSR value */
li r0, MSR_RI
andc r6, r6, r0
PPC_LL r0, SVCPU_R0(r3)
PPC_LL r1, SVCPU_R1(r3)
PPC_LL r2, SVCPU_R2(r3)
PPC_LL r5, SVCPU_R5(r3)
PPC_LL r7, SVCPU_R7(r3)
PPC_LL r8, SVCPU_R8(r3)
PPC_LL r10, SVCPU_R10(r3)
PPC_LL r11, SVCPU_R11(r3)
PPC_LL r12, SVCPU_R12(r3)
PPC_LL r13, SVCPU_R13(r3)
MTMSR_EERI(r6)
mtsrr0 r9
mtsrr1 r4
PPC_LL r4, SVCPU_R4(r3)
PPC_LL r6, SVCPU_R6(r3)
PPC_LL r9, SVCPU_R9(r3)
PPC_LL r3, (SVCPU_R3)(r3)
RFI
kvmppc_handler_trampoline_enter_end:
/******************************************************************************
* *
* Exit code *
* *
*****************************************************************************/
.global kvmppc_handler_trampoline_exit
kvmppc_handler_trampoline_exit:
.global kvmppc_interrupt
kvmppc_interrupt:
/* Register usage at this point:
*
* SPRG_SCRATCH0 = guest R13
* R12 = exit handler id
* R13 = shadow vcpu (32-bit) or PACA (64-bit)
* HSTATE.SCRATCH0 = guest R12
* HSTATE.SCRATCH1 = guest CR
*
*/
/* Save registers */
PPC_STL r0, SVCPU_R0(r13)
PPC_STL r1, SVCPU_R1(r13)
PPC_STL r2, SVCPU_R2(r13)
PPC_STL r3, SVCPU_R3(r13)
PPC_STL r4, SVCPU_R4(r13)
PPC_STL r5, SVCPU_R5(r13)
PPC_STL r6, SVCPU_R6(r13)
PPC_STL r7, SVCPU_R7(r13)
PPC_STL r8, SVCPU_R8(r13)
PPC_STL r9, SVCPU_R9(r13)
PPC_STL r10, SVCPU_R10(r13)
PPC_STL r11, SVCPU_R11(r13)
/* Restore R1/R2 so we can handle faults */
PPC_LL r1, HSTATE_HOST_R1(r13)
PPC_LL r2, HSTATE_HOST_R2(r13)
/* Save guest PC and MSR */
#ifdef CONFIG_PPC64
BEGIN_FTR_SECTION
andi. r0,r12,0x2
beq 1f
mfspr r3,SPRN_HSRR0
mfspr r4,SPRN_HSRR1
andi. r12,r12,0x3ffd
b 2f
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
#endif
1: mfsrr0 r3
mfsrr1 r4
2:
PPC_STL r3, SVCPU_PC(r13)
PPC_STL r4, SVCPU_SHADOW_SRR1(r13)
/* Get scratch'ed off registers */
GET_SCRATCH0(r9)
PPC_LL r8, HSTATE_SCRATCH0(r13)
lwz r7, HSTATE_SCRATCH1(r13)
PPC_STL r9, SVCPU_R13(r13)
PPC_STL r8, SVCPU_R12(r13)
stw r7, SVCPU_CR(r13)
/* Save more register state */
mfxer r5
mfdar r6
mfdsisr r7
mfctr r8
mflr r9
stw r5, SVCPU_XER(r13)
PPC_STL r6, SVCPU_FAULT_DAR(r13)
stw r7, SVCPU_FAULT_DSISR(r13)
PPC_STL r8, SVCPU_CTR(r13)
PPC_STL r9, SVCPU_LR(r13)
/*
* In order for us to easily get the last instruction,
* we got the #vmexit at, we exploit the fact that the
* virtual layout is still the same here, so we can just
* ld from the guest's PC address
*/
/* We only load the last instruction when it's safe */
cmpwi r12, BOOK3S_INTERRUPT_DATA_STORAGE
beq ld_last_inst
cmpwi r12, BOOK3S_INTERRUPT_PROGRAM
beq ld_last_inst
cmpwi r12, BOOK3S_INTERRUPT_SYSCALL
beq ld_last_prev_inst
cmpwi r12, BOOK3S_INTERRUPT_ALIGNMENT
beq- ld_last_inst
b no_ld_last_inst
ld_last_prev_inst:
addi r3, r3, -4
ld_last_inst:
/* Save off the guest instruction we're at */
/* In case lwz faults */
li r0, KVM_INST_FETCH_FAILED
#ifdef USE_QUICK_LAST_INST
/* Set guest mode to 'jump over instruction' so if lwz faults
* we'll just continue at the next IP. */
li r9, KVM_GUEST_MODE_SKIP
stb r9, HSTATE_IN_GUEST(r13)
/* 1) enable paging for data */
mfmsr r9
ori r11, r9, MSR_DR /* Enable paging for data */
mtmsr r11
sync
/* 2) fetch the instruction */
lwz r0, 0(r3)
/* 3) disable paging again */
mtmsr r9
sync
#endif
stw r0, SVCPU_LAST_INST(r13)
no_ld_last_inst:
/* Unset guest mode */
li r9, KVM_GUEST_MODE_NONE
stb r9, HSTATE_IN_GUEST(r13)
/* Switch back to host MMU */
LOAD_HOST_SEGMENTS
#ifdef CONFIG_PPC_BOOK3S_64
lbz r5, HSTATE_RESTORE_HID5(r13)
cmpwi r5, 0
beq no_dcbz32_off
li r4, 0
mfspr r5,SPRN_HID5
rldimi r5,r4,6,56
mtspr SPRN_HID5,r5
no_dcbz32_off:
#endif /* CONFIG_PPC_BOOK3S_64 */
/*
* For some interrupts, we need to call the real Linux
* handler, so it can do work for us. This has to happen
* as if the interrupt arrived from the kernel though,
* so let's fake it here where most state is restored.
*
* Having set up SRR0/1 with the address where we want
* to continue with relocation on (potentially in module
* space), we either just go straight there with rfi[d],
* or we jump to an interrupt handler with bctr if there
* is an interrupt to be handled first. In the latter
* case, the rfi[d] at the end of the interrupt handler
* will get us back to where we want to continue.
*/
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
beq 1f
cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER
beq 1f
cmpwi r12, BOOK3S_INTERRUPT_PERFMON
1: mtctr r12
/* Register usage at this point:
*
* R1 = host R1
* R2 = host R2
* R12 = exit handler id
* R13 = shadow vcpu (32-bit) or PACA (64-bit)
* SVCPU.* = guest *
*
*/
PPC_LL r6, HSTATE_HOST_MSR(r13)
PPC_LL r8, HSTATE_VMHANDLER(r13)
/* Restore host msr -> SRR1 */
mtsrr1 r6
/* Load highmem handler address */
mtsrr0 r8
/* RFI into the highmem handler, or jump to interrupt handler */
beqctr
RFI
kvmppc_handler_trampoline_exit_end:
|