summaryrefslogtreecommitdiff
path: root/exec-all.h
blob: e9b07cd9865700d27d23a04397f7c066d9537e02 (plain)
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
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
/*
 * 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, see <http://www.gnu.org/licenses/>.
 */

#ifndef _EXEC_ALL_H_
#define _EXEC_ALL_H_

#include "qemu-common.h"

/* allow to see translation results - the slowdown should be negligible, so we leave it */
#define DEBUG_DISAS

/* Page tracking code uses ram addresses in system mode, and virtual
   addresses in userspace mode.  Define tb_page_addr_t to be an appropriate
   type.  */
#if defined(CONFIG_USER_ONLY)
typedef abi_ulong tb_page_addr_t;
#else
typedef ram_addr_t tb_page_addr_t;
#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;
typedef struct TranslationBlock TranslationBlock;

/* XXX: make safe guess about sizes */
#define MAX_OP_PER_INSTR 208

#if HOST_LONG_BITS == 32
#define MAX_OPC_PARAM_PER_ARG 2
#else
#define MAX_OPC_PARAM_PER_ARG 1
#endif
#define MAX_OPC_PARAM_IARGS 5
#define MAX_OPC_PARAM_OARGS 1
#define MAX_OPC_PARAM_ARGS (MAX_OPC_PARAM_IARGS + MAX_OPC_PARAM_OARGS)

/* A Call op needs up to 4 + 2N parameters on 32-bit archs,
 * and up to 4 + N parameters on 64-bit archs
 * (N = number of input arguments + output arguments).  */
#define MAX_OPC_PARAM (4 + (MAX_OPC_PARAM_PER_ARG * MAX_OPC_PARAM_ARGS))
#define OPC_BUF_SIZE 640
#define OPC_MAX_SIZE (OPC_BUF_SIZE - MAX_OP_PER_INSTR)

/* Maximum size a TCG op can expand to.  This is complicated because a
   single op may require several host instructions and register reloads.
   For now take a wild guess at 192 bytes, which should allow at least
   a couple of fixup instructions per argument.  */
#define TCG_MAX_OP_SIZE 192

#define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * MAX_OPC_PARAM)

#include "qemu-log.h"

void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb);
void gen_intermediate_code_pc(CPUArchState *env, struct TranslationBlock *tb);
void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb,
                          int pc_pos);

void cpu_gen_init(void);
int cpu_gen_code(CPUArchState *env, struct TranslationBlock *tb,
                 int *gen_code_size_ptr);
bool cpu_restore_state(CPUArchState *env, uintptr_t searched_pc);

void QEMU_NORETURN cpu_resume_from_signal(CPUArchState *env1, void *puc);
void QEMU_NORETURN cpu_io_recompile(CPUArchState *env, uintptr_t retaddr);
TranslationBlock *tb_gen_code(CPUArchState *env, 
                              target_ulong pc, target_ulong cs_base, int flags,
                              int cflags);
void cpu_exec_init(CPUArchState *env);
void QEMU_NORETURN cpu_loop_exit(CPUArchState *env1);
int page_unprotect(target_ulong address, uintptr_t pc, void *puc);
void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
                                   int is_cpu_write_access);
void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end,
                              int is_cpu_write_access);
#if !defined(CONFIG_USER_ONLY)
/* cputlb.c */
void tlb_flush_page(CPUArchState *env, target_ulong addr);
void tlb_flush(CPUArchState *env, int flush_global);
void tlb_set_page(CPUArchState *env, target_ulong vaddr,
                  hwaddr paddr, int prot,
                  int mmu_idx, target_ulong size);
void tb_invalidate_phys_addr(hwaddr addr);
#else
static inline void tlb_flush_page(CPUArchState *env, target_ulong addr)
{
}

static inline void tlb_flush(CPUArchState *env, int flush_global)
{
}
#endif

#define CODE_GEN_ALIGN           16 /* must be >= of the size of a icache line */

#define CODE_GEN_PHYS_HASH_BITS     15
#define CODE_GEN_PHYS_HASH_SIZE     (1 << CODE_GEN_PHYS_HASH_BITS)

/* estimated block size for TB allocation */
/* XXX: use a per code average code fragment size and modulate it
   according to the host CPU */
#if defined(CONFIG_SOFTMMU)
#define CODE_GEN_AVG_BLOCK_SIZE 128
#else
#define CODE_GEN_AVG_BLOCK_SIZE 64
#endif

#if defined(__arm__) || defined(_ARCH_PPC) \
    || defined(__x86_64__) || defined(__i386__) \
    || defined(__sparc__) \
    || defined(CONFIG_TCG_INTERPRETER)
#define USE_DIRECT_JUMP
#endif

struct TranslationBlock {
    target_ulong pc;   /* simulated PC corresponding to this block (EIP + CS base) */
    target_ulong cs_base; /* CS base for this block */
    uint64_t 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) */
    uint16_t cflags;    /* compile flags */
#define CF_COUNT_MASK  0x7fff
#define CF_LAST_IO     0x8000 /* Last insn may be an IO access.  */

    uint8_t *tc_ptr;    /* pointer to the translated code */
    /* next matching tb for physical address. */
    struct TranslationBlock *phys_hash_next;
    /* first and second physical page containing code. The lower bit
       of the pointer tells the index in page_next[] */
    struct TranslationBlock *page_next[2];
    tb_page_addr_t page_addr[2];

    /* 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
    uintptr_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;
    uint32_t icount;
};

static inline unsigned int tb_jmp_cache_hash_page(target_ulong pc)
{
    target_ulong tmp;
    tmp = pc ^ (pc >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS));
    return (tmp >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS)) & TB_JMP_PAGE_MASK;
}

static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
{
    target_ulong tmp;
    tmp = pc ^ (pc >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS));
    return (((tmp >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS)) & TB_JMP_PAGE_MASK)
	    | (tmp & TB_JMP_ADDR_MASK));
}

static inline unsigned int tb_phys_hash_func(tb_page_addr_t pc)
{
    return (pc >> 2) & (CODE_GEN_PHYS_HASH_SIZE - 1);
}

void tb_free(TranslationBlock *tb);
void tb_flush(CPUArchState *env);
void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr);

extern TranslationBlock *tb_phys_hash[CODE_GEN_PHYS_HASH_SIZE];

#if defined(USE_DIRECT_JUMP)

#if defined(CONFIG_TCG_INTERPRETER)
static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
{
    /* patch the branch destination */
    *(uint32_t *)jmp_addr = addr - (jmp_addr + 4);
    /* no need to flush icache explicitly */
}
#elif defined(_ARCH_PPC)
void ppc_tb_set_jmp_target(unsigned long jmp_addr, unsigned long addr);
#define tb_set_jmp_target1 ppc_tb_set_jmp_target
#elif defined(__i386__) || defined(__x86_64__)
static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
{
    /* patch the branch destination */
    *(uint32_t *)jmp_addr = addr - (jmp_addr + 4);
    /* no need to flush icache explicitly */
}
#elif defined(__arm__)
static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
{
#if !QEMU_GNUC_PREREQ(4, 1)
    register unsigned long _beg __asm ("a1");
    register unsigned long _end __asm ("a2");
    register unsigned long _flg __asm ("a3");
#endif

    /* we could use a ldr pc, [pc, #-4] kind of branch and avoid the flush */
    *(uint32_t *)jmp_addr =
        (*(uint32_t *)jmp_addr & ~0xffffff)
        | (((addr - (jmp_addr + 8)) >> 2) & 0xffffff);

#if QEMU_GNUC_PREREQ(4, 1)
    __builtin___clear_cache((char *) jmp_addr, (char *) jmp_addr + 4);
#else
    /* flush icache */
    _beg = jmp_addr;
    _end = jmp_addr + 4;
    _flg = 0;
    __asm __volatile__ ("swi 0x9f0002" : : "r" (_beg), "r" (_end), "r" (_flg));
#endif
}
#elif defined(__sparc__)
void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr);
#else
#error tb_set_jmp_target1 is missing
#endif

static inline void tb_set_jmp_target(TranslationBlock *tb,
                                     int n, uintptr_t addr)
{
    uint16_t offset = tb->tb_jmp_offset[n];
    tb_set_jmp_target1((uintptr_t)(tb->tc_ptr + offset), addr);
}

#else

/* set the jump target */
static inline void tb_set_jmp_target(TranslationBlock *tb,
                                     int n, uintptr_t 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, (uintptr_t)tb_next->tc_ptr);

        /* add in TB jmp circular list */
        tb->jmp_next[n] = tb_next->jmp_first;
        tb_next->jmp_first = (TranslationBlock *)((uintptr_t)(tb) | (n));
    }
}

#include "qemu-lock.h"

extern spinlock_t tb_lock;

extern int tb_invalidated_flag;

/* The return address may point to the start of the next instruction.
   Subtracting one gets us the call instruction itself.  */
#if defined(CONFIG_TCG_INTERPRETER)
/* Softmmu, Alpha, MIPS, SH4 and SPARC user mode emulations call GETPC().
   For all others, GETPC remains undefined (which makes TCI a little faster. */
# if defined(CONFIG_SOFTMMU) || \
    defined(TARGET_ALPHA) || defined(TARGET_MIPS) || \
    defined(TARGET_SH4) || defined(TARGET_SPARC)
extern uintptr_t tci_tb_ptr;
#  define GETPC() tci_tb_ptr
# endif
#elif defined(__s390__) && !defined(__s390x__)
# define GETPC() \
    (((uintptr_t)__builtin_return_address(0) & 0x7fffffffUL) - 1)
#elif defined(__arm__)
/* Thumb return addresses have the low bit set, so we need to subtract two.
   This is still safe in ARM mode because instructions are 4 bytes.  */
# define GETPC() ((uintptr_t)__builtin_return_address(0) - 2)
#else
# define GETPC() ((uintptr_t)__builtin_return_address(0) - 1)
#endif

#if defined(CONFIG_QEMU_LDST_OPTIMIZATION) && defined(CONFIG_SOFTMMU)
/* qemu_ld/st optimization split code generation to fast and slow path, thus,
   it needs special handling for an MMU helper which is called from the slow
   path, to get the fast path's pc without any additional argument.
   It uses a tricky solution which embeds the fast path pc into the slow path.

   Code flow in slow path:
   (1) pre-process
   (2) call MMU helper
   (3) jump to (5)
   (4) fast path information (implementation specific)
   (5) post-process (e.g. stack adjust)
   (6) jump to corresponding code of the next of fast path
 */
# if defined(__i386__) || defined(__x86_64__)
/* To avoid broken disassembling, long jmp is used for embedding fast path pc,
   so that the destination is the next code of fast path, though this jmp is
   never executed.

   call MMU helper
   jmp POST_PROC (2byte)    <- GETRA()
   jmp NEXT_CODE (5byte)
   POST_PROCESS ...         <- GETRA() + 7
 */
#  define GETRA() ((uintptr_t)__builtin_return_address(0))
#  define GETPC_LDST() ((uintptr_t)(GETRA() + 7 + \
                                    *(int32_t *)((void *)GETRA() + 3) - 1))
# elif defined (_ARCH_PPC) && !defined (_ARCH_PPC64)
#  define GETRA() ((uintptr_t)__builtin_return_address(0))
#  define GETPC_LDST() ((uintptr_t) ((*(int32_t *)(GETRA() - 4)) - 1))
# else
#  error "CONFIG_QEMU_LDST_OPTIMIZATION needs GETPC_LDST() implementation!"
# endif
bool is_tcg_gen_code(uintptr_t pc_ptr);
# define GETPC_EXT() (is_tcg_gen_code(GETRA()) ? GETPC_LDST() : GETPC())
#else
# define GETPC_EXT() GETPC()
#endif

#if !defined(CONFIG_USER_ONLY)

struct MemoryRegion *iotlb_to_region(hwaddr index);
uint64_t io_mem_read(struct MemoryRegion *mr, hwaddr addr,
                     unsigned size);
void io_mem_write(struct MemoryRegion *mr, hwaddr addr,
                  uint64_t value, unsigned size);

void tlb_fill(CPUArchState *env1, target_ulong addr, int is_write, int mmu_idx,
              uintptr_t retaddr);

#include "softmmu_defs.h"

#define ACCESS_TYPE (NB_MMU_MODES + 1)
#define MEMSUFFIX _code

#define DATA_SIZE 1
#include "softmmu_header.h"

#define DATA_SIZE 2
#include "softmmu_header.h"

#define DATA_SIZE 4
#include "softmmu_header.h"

#define DATA_SIZE 8
#include "softmmu_header.h"

#undef ACCESS_TYPE
#undef MEMSUFFIX

#endif

#if defined(CONFIG_USER_ONLY)
static inline tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
{
    return addr;
}
#else
/* cputlb.c */
tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr);
#endif

typedef void (CPUDebugExcpHandler)(CPUArchState *env);

void cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler);

/* vl.c */
extern int singlestep;

/* cpu-exec.c */
extern volatile sig_atomic_t exit_request;

/* Deterministic execution requires that IO only be performed on the last
   instruction of a TB so that interrupts take effect immediately.  */
static inline int can_do_io(CPUArchState *env)
{
    if (!use_icount) {
        return 1;
    }
    /* If not executing code then assume we are ok.  */
    if (!env->current_tb) {
        return 1;
    }
    return env->can_do_io != 0;
}

#endif