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
|
/*
* PowerPC implementation of KVM hooks
*
* Copyright IBM Corp. 2007
*
* Authors:
* Jerone Young <jyoung5@us.ibm.com>
* Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
* Hollis Blanchard <hollisb@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <linux/kvm.h>
#include "qemu-common.h"
#include "qemu-timer.h"
#include "sysemu.h"
#include "kvm.h"
#include "kvm_ppc.h"
#include "cpu.h"
#include "device_tree.h"
//#define DEBUG_KVM
#ifdef DEBUG_KVM
#define dprintf(fmt, ...) \
do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define dprintf(fmt, ...) \
do { } while (0)
#endif
/* XXX We have a race condition where we actually have a level triggered
* interrupt, but the infrastructure can't expose that yet, so the guest
* takes but ignores it, goes to sleep and never gets notified that there's
* still an interrupt pending.
*
* As a quick workaround, let's just wake up again 20 ms after we injected
* an interrupt. That way we can assure that we're always reinjecting
* interrupts in case the guest swallowed them.
*/
static QEMUTimer *idle_timer;
static void kvm_kick_env(void *env)
{
qemu_cpu_kick(env);
}
int kvm_arch_init(KVMState *s, int smp_cpus)
{
return 0;
}
int kvm_arch_init_vcpu(CPUState *cenv)
{
int ret = 0;
struct kvm_sregs sregs;
sregs.pvr = cenv->spr[SPR_PVR];
ret = kvm_vcpu_ioctl(cenv, KVM_SET_SREGS, &sregs);
idle_timer = qemu_new_timer(vm_clock, kvm_kick_env, cenv);
return ret;
}
void kvm_arch_reset_vcpu(CPUState *env)
{
}
int kvm_arch_put_registers(CPUState *env, int level)
{
struct kvm_regs regs;
int ret;
int i;
ret = kvm_vcpu_ioctl(env, KVM_GET_REGS, ®s);
if (ret < 0)
return ret;
regs.ctr = env->ctr;
regs.lr = env->lr;
regs.xer = env->xer;
regs.msr = env->msr;
regs.pc = env->nip;
regs.srr0 = env->spr[SPR_SRR0];
regs.srr1 = env->spr[SPR_SRR1];
regs.sprg0 = env->spr[SPR_SPRG0];
regs.sprg1 = env->spr[SPR_SPRG1];
regs.sprg2 = env->spr[SPR_SPRG2];
regs.sprg3 = env->spr[SPR_SPRG3];
regs.sprg4 = env->spr[SPR_SPRG4];
regs.sprg5 = env->spr[SPR_SPRG5];
regs.sprg6 = env->spr[SPR_SPRG6];
regs.sprg7 = env->spr[SPR_SPRG7];
for (i = 0;i < 32; i++)
regs.gpr[i] = env->gpr[i];
ret = kvm_vcpu_ioctl(env, KVM_SET_REGS, ®s);
if (ret < 0)
return ret;
return ret;
}
int kvm_arch_get_registers(CPUState *env)
{
struct kvm_regs regs;
struct kvm_sregs sregs;
uint32_t i, ret;
ret = kvm_vcpu_ioctl(env, KVM_GET_REGS, ®s);
if (ret < 0)
return ret;
ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);
if (ret < 0)
return ret;
env->ctr = regs.ctr;
env->lr = regs.lr;
env->xer = regs.xer;
env->msr = regs.msr;
env->nip = regs.pc;
env->spr[SPR_SRR0] = regs.srr0;
env->spr[SPR_SRR1] = regs.srr1;
env->spr[SPR_SPRG0] = regs.sprg0;
env->spr[SPR_SPRG1] = regs.sprg1;
env->spr[SPR_SPRG2] = regs.sprg2;
env->spr[SPR_SPRG3] = regs.sprg3;
env->spr[SPR_SPRG4] = regs.sprg4;
env->spr[SPR_SPRG5] = regs.sprg5;
env->spr[SPR_SPRG6] = regs.sprg6;
env->spr[SPR_SPRG7] = regs.sprg7;
for (i = 0;i < 32; i++)
env->gpr[i] = regs.gpr[i];
#ifdef KVM_CAP_PPC_SEGSTATE
if (kvm_check_extension(env->kvm_state, KVM_CAP_PPC_SEGSTATE)) {
env->sdr1 = sregs.u.s.sdr1;
/* Sync SLB */
#ifdef TARGET_PPC64
for (i = 0; i < 64; i++) {
ppc_store_slb(env, sregs.u.s.ppc64.slb[i].slbe,
sregs.u.s.ppc64.slb[i].slbv);
}
#endif
/* Sync SRs */
for (i = 0; i < 16; i++) {
env->sr[i] = sregs.u.s.ppc32.sr[i];
}
/* Sync BATs */
for (i = 0; i < 8; i++) {
env->DBAT[0][i] = sregs.u.s.ppc32.dbat[i] & 0xffffffff;
env->DBAT[1][i] = sregs.u.s.ppc32.dbat[i] >> 32;
env->IBAT[0][i] = sregs.u.s.ppc32.ibat[i] & 0xffffffff;
env->IBAT[1][i] = sregs.u.s.ppc32.ibat[i] >> 32;
}
}
#endif
return 0;
}
#if defined(TARGET_PPCEMB)
#define PPC_INPUT_INT PPC40x_INPUT_INT
#elif defined(TARGET_PPC64)
#define PPC_INPUT_INT PPC970_INPUT_INT
#else
#define PPC_INPUT_INT PPC6xx_INPUT_INT
#endif
int kvm_arch_pre_run(CPUState *env, struct kvm_run *run)
{
int r;
unsigned irq;
/* PowerPC Qemu tracks the various core input pins (interrupt, critical
* interrupt, reset, etc) in PPC-specific env->irq_input_state. */
if (run->ready_for_interrupt_injection &&
(env->interrupt_request & CPU_INTERRUPT_HARD) &&
(env->irq_input_state & (1<<PPC_INPUT_INT)))
{
/* For now KVM disregards the 'irq' argument. However, in the
* future KVM could cache it in-kernel to avoid a heavyweight exit
* when reading the UIC.
*/
irq = -1U;
dprintf("injected interrupt %d\n", irq);
r = kvm_vcpu_ioctl(env, KVM_INTERRUPT, &irq);
if (r < 0)
printf("cpu %d fail inject %x\n", env->cpu_index, irq);
/* Always wake up soon in case the interrupt was level based */
qemu_mod_timer(idle_timer, qemu_get_clock(vm_clock) +
(get_ticks_per_sec() / 50));
}
/* We don't know if there are more interrupts pending after this. However,
* the guest will return to userspace in the course of handling this one
* anyways, so we will get a chance to deliver the rest. */
return 0;
}
int kvm_arch_post_run(CPUState *env, struct kvm_run *run)
{
return 0;
}
int kvm_arch_process_irqchip_events(CPUState *env)
{
return 0;
}
static int kvmppc_handle_halt(CPUState *env)
{
if (!(env->interrupt_request & CPU_INTERRUPT_HARD) && (msr_ee)) {
env->halted = 1;
env->exception_index = EXCP_HLT;
}
return 1;
}
/* map dcr access to existing qemu dcr emulation */
static int kvmppc_handle_dcr_read(CPUState *env, uint32_t dcrn, uint32_t *data)
{
if (ppc_dcr_read(env->dcr_env, dcrn, data) < 0)
fprintf(stderr, "Read to unhandled DCR (0x%x)\n", dcrn);
return 1;
}
static int kvmppc_handle_dcr_write(CPUState *env, uint32_t dcrn, uint32_t data)
{
if (ppc_dcr_write(env->dcr_env, dcrn, data) < 0)
fprintf(stderr, "Write to unhandled DCR (0x%x)\n", dcrn);
return 1;
}
int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
{
int ret = 0;
switch (run->exit_reason) {
case KVM_EXIT_DCR:
if (run->dcr.is_write) {
dprintf("handle dcr write\n");
ret = kvmppc_handle_dcr_write(env, run->dcr.dcrn, run->dcr.data);
} else {
dprintf("handle dcr read\n");
ret = kvmppc_handle_dcr_read(env, run->dcr.dcrn, &run->dcr.data);
}
break;
case KVM_EXIT_HLT:
dprintf("handle halt\n");
ret = kvmppc_handle_halt(env);
break;
}
return ret;
}
static int read_cpuinfo(const char *field, char *value, int len)
{
FILE *f;
int ret = -1;
int field_len = strlen(field);
char line[512];
f = fopen("/proc/cpuinfo", "r");
if (!f) {
return -1;
}
do {
if(!fgets(line, sizeof(line), f)) {
break;
}
if (!strncmp(line, field, field_len)) {
strncpy(value, line, len);
ret = 0;
break;
}
} while(*line);
fclose(f);
return ret;
}
uint32_t kvmppc_get_tbfreq(void)
{
char line[512];
char *ns;
uint32_t retval = get_ticks_per_sec();
if (read_cpuinfo("timebase", line, sizeof(line))) {
return retval;
}
if (!(ns = strchr(line, ':'))) {
return retval;
}
ns++;
retval = atoi(ns);
return retval;
}
int kvmppc_get_hypercall(CPUState *env, uint8_t *buf, int buf_len)
{
uint32_t *hc = (uint32_t*)buf;
#ifdef KVM_CAP_PPC_GET_PVINFO
struct kvm_ppc_pvinfo pvinfo;
if (kvm_check_extension(env->kvm_state, KVM_CAP_PPC_GET_PVINFO) &&
!kvm_vm_ioctl(env->kvm_state, KVM_PPC_GET_PVINFO, &pvinfo)) {
memcpy(buf, pvinfo.hcall, buf_len);
return 0;
}
#endif
/*
* Fallback to always fail hypercalls:
*
* li r3, -1
* nop
* nop
* nop
*/
hc[0] = 0x3860ffff;
hc[1] = 0x60000000;
hc[2] = 0x60000000;
hc[3] = 0x60000000;
return 0;
}
bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
return true;
}
|