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
|
/*
* internal execution defines for qemu
*
* Copyright (c) 2003 Fabrice Bellard
*
* This library 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 of the License, or (at your option) any later version.
*
* This library 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 library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/* allow to see translation results - the slowdown should be negligible, so we leave it */
#define DEBUG_DISAS
#ifndef glue
#define xglue(x, y) x ## y
#define glue(x, y) xglue(x, y)
#define stringify(s) tostring(s)
#define tostring(s) #s
#endif
#if GCC_MAJOR < 3
#define __builtin_expect(x, n) (x)
#endif
/* is_jmp field values */
#define DISAS_NEXT 0 /* next instruction can be analyzed */
#define DISAS_JUMP 1 /* only pc was modified dynamically */
#define DISAS_UPDATE 2 /* cpu state was modified dynamically */
#define DISAS_TB_JUMP 3 /* only pc was modified statically */
struct TranslationBlock;
/* XXX: make safe guess about sizes */
#define MAX_OP_PER_INSTR 32
#define OPC_BUF_SIZE 512
#define OPC_MAX_SIZE (OPC_BUF_SIZE - MAX_OP_PER_INSTR)
#define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * 3)
extern uint16_t gen_opc_buf[OPC_BUF_SIZE];
extern uint32_t gen_opparam_buf[OPPARAM_BUF_SIZE];
extern uint32_t gen_opc_pc[OPC_BUF_SIZE];
extern uint8_t gen_opc_cc_op[OPC_BUF_SIZE];
extern uint8_t gen_opc_instr_start[OPC_BUF_SIZE];
#if defined(TARGET_I386)
#define GEN_FLAG_CODE32_SHIFT 0
#define GEN_FLAG_ADDSEG_SHIFT 1
#define GEN_FLAG_SS32_SHIFT 2
#define GEN_FLAG_VM_SHIFT 3
#define GEN_FLAG_ST_SHIFT 4
#define GEN_FLAG_TF_SHIFT 8 /* same position as eflags */
#define GEN_FLAG_CPL_SHIFT 9
#define GEN_FLAG_SOFT_MMU_SHIFT 11
#define GEN_FLAG_IOPL_SHIFT 12 /* same position as eflags */
void optimize_flags_init(void);
#endif
extern FILE *logfile;
extern int loglevel;
int gen_intermediate_code(CPUState *env, struct TranslationBlock *tb);
int gen_intermediate_code_pc(CPUState *env, struct TranslationBlock *tb);
void dump_ops(const uint16_t *opc_buf, const uint32_t *opparam_buf);
int cpu_gen_code(CPUState *env, struct TranslationBlock *tb,
int max_code_size, int *gen_code_size_ptr);
int cpu_restore_state(struct TranslationBlock *tb,
CPUState *env, unsigned long searched_pc);
void cpu_exec_init(void);
int page_unprotect(unsigned long address);
void page_unmap(void);
void tlb_flush_page(CPUState *env, uint32_t addr);
void tlb_flush(CPUState *env);
#define CODE_GEN_MAX_SIZE 65536
#define CODE_GEN_ALIGN 16 /* must be >= of the size of a icache line */
#define CODE_GEN_HASH_BITS 15
#define CODE_GEN_HASH_SIZE (1 << CODE_GEN_HASH_BITS)
/* maximum total translate dcode allocated */
#define CODE_GEN_BUFFER_SIZE (2048 * 1024)
//#define CODE_GEN_BUFFER_SIZE (128 * 1024)
#if defined(__powerpc__)
#define USE_DIRECT_JUMP
#endif
typedef struct TranslationBlock {
unsigned long pc; /* simulated PC corresponding to this block (EIP + CS base) */
unsigned long cs_base; /* CS base for this block */
unsigned int flags; /* flags defining in which context the code was generated */
uint16_t size; /* size of target code for this block (1 <=
size <= TARGET_PAGE_SIZE) */
uint8_t *tc_ptr; /* pointer to the translated code */
struct TranslationBlock *hash_next; /* next matching block */
struct TranslationBlock *page_next[2]; /* next blocks in even/odd page */
/* the following data are used to directly call another TB from
the code of this one. */
uint16_t tb_next_offset[2]; /* offset of original jump target */
#ifdef USE_DIRECT_JUMP
uint16_t tb_jmp_offset[2]; /* offset of jump instruction */
#else
uint32_t tb_next[2]; /* address of jump generated code */
#endif
/* list of TBs jumping to this one. This is a circular list using
the two least significant bits of the pointers to tell what is
the next pointer: 0 = jmp_next[0], 1 = jmp_next[1], 2 =
jmp_first */
struct TranslationBlock *jmp_next[2];
struct TranslationBlock *jmp_first;
} TranslationBlock;
static inline unsigned int tb_hash_func(unsigned long pc)
{
return pc & (CODE_GEN_HASH_SIZE - 1);
}
TranslationBlock *tb_alloc(unsigned long pc);
void tb_flush(void);
void tb_link(TranslationBlock *tb);
extern TranslationBlock *tb_hash[CODE_GEN_HASH_SIZE];
extern uint8_t code_gen_buffer[CODE_GEN_BUFFER_SIZE];
extern uint8_t *code_gen_ptr;
/* find a translation block in the translation cache. If not found,
return NULL and the pointer to the last element of the list in pptb */
static inline TranslationBlock *tb_find(TranslationBlock ***pptb,
unsigned long pc,
unsigned long cs_base,
unsigned int flags)
{
TranslationBlock **ptb, *tb;
unsigned int h;
h = tb_hash_func(pc);
ptb = &tb_hash[h];
for(;;) {
tb = *ptb;
if (!tb)
break;
if (tb->pc == pc && tb->cs_base == cs_base && tb->flags == flags)
return tb;
ptb = &tb->hash_next;
}
*pptb = ptb;
return NULL;
}
#if defined(__powerpc__)
static inline void tb_set_jmp_target(TranslationBlock *tb,
int n, unsigned long addr)
{
uint32_t val, *ptr;
unsigned long offset;
offset = (unsigned long)(tb->tc_ptr + tb->tb_jmp_offset[n]);
/* patch the branch destination */
ptr = (uint32_t *)offset;
val = *ptr;
val = (val & ~0x03fffffc) | ((addr - offset) & 0x03fffffc);
*ptr = val;
/* flush icache */
asm volatile ("dcbst 0,%0" : : "r"(ptr) : "memory");
asm volatile ("sync" : : : "memory");
asm volatile ("icbi 0,%0" : : "r"(ptr) : "memory");
asm volatile ("sync" : : : "memory");
asm volatile ("isync" : : : "memory");
}
#else
/* set the jump target */
static inline void tb_set_jmp_target(TranslationBlock *tb,
int n, unsigned long addr)
{
tb->tb_next[n] = addr;
}
#endif
static inline void tb_add_jump(TranslationBlock *tb, int n,
TranslationBlock *tb_next)
{
/* NOTE: this test is only needed for thread safety */
if (!tb->jmp_next[n]) {
/* patch the native jump address */
tb_set_jmp_target(tb, n, (unsigned long)tb_next->tc_ptr);
/* add in TB jmp circular list */
tb->jmp_next[n] = tb_next->jmp_first;
tb_next->jmp_first = (TranslationBlock *)((long)(tb) | (n));
}
}
TranslationBlock *tb_find_pc(unsigned long pc_ptr);
#ifndef offsetof
#define offsetof(type, field) ((size_t) &((type *)0)->field)
#endif
#if defined(__powerpc__)
/* on PowerPC we patch the jump instruction directly */
#define JUMP_TB(tbparam, n, eip)\
do {\
static void __attribute__((unused)) *__op_label ## n = &&label ## n;\
asm volatile ("b %0" : : "i" (&__op_jmp ## n));\
label ## n:\
T0 = (long)(tbparam) + (n);\
EIP = eip;\
} while (0)
#else
/* jump to next block operations (more portable code, does not need
cache flushing, but slower because of indirect jump) */
#define JUMP_TB(tbparam, n, eip)\
do {\
static void __attribute__((unused)) *__op_label ## n = &&label ## n;\
static void __attribute__((unused)) *dummy ## n = &&dummy_label ## n;\
goto *(void *)(((TranslationBlock *)tbparam)->tb_next[n]);\
label ## n:\
T0 = (long)(tbparam) + (n);\
EIP = eip;\
dummy_label ## n:\
EXIT_TB();\
} while (0)
#endif
/* physical memory access */
#define IO_MEM_NB_ENTRIES 256
#define TLB_INVALID_MASK (1 << 3)
#define IO_MEM_SHIFT 4
#define IO_MEM_UNASSIGNED (1 << IO_MEM_SHIFT)
unsigned long physpage_find(unsigned long page);
extern CPUWriteMemoryFunc *io_mem_write[IO_MEM_NB_ENTRIES][4];
extern CPUReadMemoryFunc *io_mem_read[IO_MEM_NB_ENTRIES][4];
#ifdef __powerpc__
static inline int testandset (int *p)
{
int ret;
__asm__ __volatile__ (
"0: lwarx %0,0,%1 ;"
" xor. %0,%3,%0;"
" bne 1f;"
" stwcx. %2,0,%1;"
" bne- 0b;"
"1: "
: "=&r" (ret)
: "r" (p), "r" (1), "r" (0)
: "cr0", "memory");
return ret;
}
#endif
#ifdef __i386__
static inline int testandset (int *p)
{
char ret;
long int readval;
__asm__ __volatile__ ("lock; cmpxchgl %3, %1; sete %0"
: "=q" (ret), "=m" (*p), "=a" (readval)
: "r" (1), "m" (*p), "a" (0)
: "memory");
return ret;
}
#endif
#ifdef __s390__
static inline int testandset (int *p)
{
int ret;
__asm__ __volatile__ ("0: cs %0,%1,0(%2)\n"
" jl 0b"
: "=&d" (ret)
: "r" (1), "a" (p), "0" (*p)
: "cc", "memory" );
return ret;
}
#endif
#ifdef __alpha__
static inline int testandset (int *p)
{
int ret;
unsigned long one;
__asm__ __volatile__ ("0: mov 1,%2\n"
" ldl_l %0,%1\n"
" stl_c %2,%1\n"
" beq %2,1f\n"
".subsection 2\n"
"1: br 0b\n"
".previous"
: "=r" (ret), "=m" (*p), "=r" (one)
: "m" (*p));
return ret;
}
#endif
#ifdef __sparc__
static inline int testandset (int *p)
{
int ret;
__asm__ __volatile__("ldstub [%1], %0"
: "=r" (ret)
: "r" (p)
: "memory");
return (ret ? 1 : 0);
}
#endif
#ifdef __arm__
static inline int testandset (int *spinlock)
{
register unsigned int ret;
__asm__ __volatile__("swp %0, %1, [%2]"
: "=r"(ret)
: "0"(1), "r"(spinlock));
return ret;
}
#endif
typedef int spinlock_t;
#define SPIN_LOCK_UNLOCKED 0
#if 1
static inline void spin_lock(spinlock_t *lock)
{
while (testandset(lock));
}
static inline void spin_unlock(spinlock_t *lock)
{
*lock = 0;
}
static inline int spin_trylock(spinlock_t *lock)
{
return !testandset(lock);
}
#else
static inline void spin_lock(spinlock_t *lock)
{
}
static inline void spin_unlock(spinlock_t *lock)
{
}
static inline int spin_trylock(spinlock_t *lock)
{
return 1;
}
#endif
extern spinlock_t tb_lock;
|