summaryrefslogtreecommitdiffstats
path: root/exec-all.h
blob: 898cf687c22fad0e144147d4e1eef9df8c8cd927 (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
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
/*
 * 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

/* 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
/* A Call op needs up to 6 + 2N parameters (N = number of arguments).  */
#define MAX_OPC_PARAM 10
#define OPC_BUF_SIZE 512
#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 regirster reloads.
   For now take a wild guess at 128 bytes, which should allow at least
   a couple of fixup instructions per argument.  */
#define TCG_MAX_OP_SIZE 128

#define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * MAX_OPC_PARAM)

extern target_ulong gen_opc_pc[OPC_BUF_SIZE];
extern target_ulong gen_opc_npc[OPC_BUF_SIZE];
extern uint8_t gen_opc_cc_op[OPC_BUF_SIZE];
extern uint8_t gen_opc_instr_start[OPC_BUF_SIZE];
extern target_ulong gen_opc_jump_pc[2];
extern uint32_t gen_opc_hflags[OPC_BUF_SIZE];

typedef void (GenOpFunc)(void);
typedef void (GenOpFunc1)(long);
typedef void (GenOpFunc2)(long, long);
typedef void (GenOpFunc3)(long, long, long);

#if defined(TARGET_I386)

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);
unsigned long code_gen_max_block_size(void);
void cpu_gen_init(void);
int cpu_gen_code(CPUState *env, struct TranslationBlock *tb,
                 int *gen_code_size_ptr);
int cpu_restore_state(struct TranslationBlock *tb,
                      CPUState *env, unsigned long searched_pc,
                      void *puc);
int cpu_gen_code_copy(CPUState *env, struct TranslationBlock *tb,
                      int max_code_size, int *gen_code_size_ptr);
int cpu_restore_state_copy(struct TranslationBlock *tb,
                           CPUState *env, unsigned long searched_pc,
                           void *puc);
void cpu_resume_from_signal(CPUState *env1, void *puc);
void cpu_exec_init(CPUState *env);
int page_unprotect(target_ulong address, unsigned long pc, void *puc);
void tb_invalidate_phys_page_range(target_ulong start, target_ulong end,
                                   int is_cpu_write_access);
void tb_invalidate_page_range(target_ulong start, target_ulong end);
void tlb_flush_page(CPUState *env, target_ulong addr);
void tlb_flush(CPUState *env, int flush_global);
int tlb_set_page_exec(CPUState *env, target_ulong vaddr,
                      target_phys_addr_t paddr, int prot,
                      int mmu_idx, int is_softmmu);
static inline int tlb_set_page(CPUState *env, target_ulong vaddr,
                               target_phys_addr_t paddr, int prot,
                               int mmu_idx, int is_softmmu)
{
    if (prot & PAGE_READ)
        prot |= PAGE_EXEC;
    return tlb_set_page_exec(env, vaddr, paddr, prot, mmu_idx, is_softmmu);
}

#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)

/* maximum total translate dcode allocated */

/* NOTE: the translated code area cannot be too big because on some
   archs the range of "fast" function calls is limited. Here is a
   summary of the ranges:

   i386  : signed 32 bits
   arm   : signed 26 bits
   ppc   : signed 24 bits
   sparc : signed 32 bits
   alpha : signed 23 bits
*/

#if defined(__alpha__)
#define CODE_GEN_BUFFER_SIZE     (2 * 1024 * 1024)
#elif defined(__ia64)
#define CODE_GEN_BUFFER_SIZE     (4 * 1024 * 1024)	/* range of addl */
#elif defined(__powerpc__)
#define CODE_GEN_BUFFER_SIZE     (6 * 1024 * 1024)
#else
/* XXX: make it dynamic on x86 */
#define CODE_GEN_BUFFER_SIZE     (16 * 1024 * 1024)
#endif

//#define CODE_GEN_BUFFER_SIZE     (128 * 1024)

/* 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

#define CODE_GEN_MAX_BLOCKS    (CODE_GEN_BUFFER_SIZE / CODE_GEN_AVG_BLOCK_SIZE)

#if defined(__powerpc__) || defined(__x86_64__)
#define USE_DIRECT_JUMP
#endif
#if defined(__i386__) && !defined(_WIN32)
#define USE_DIRECT_JUMP
#endif

typedef 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_CODE_COPY   0x0001 /* block was generated in code copy mode */
#define CF_TB_FP_USED  0x0002 /* fp ops are used in the TB */
#define CF_FP_USED     0x0004 /* fp ops are used in the TB or in a chained TB */
#define CF_SINGLE_INSN 0x0008 /* compile only a single instruction */

    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];
    target_ulong 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[4]; /* offset of jump instruction */
#else
    unsigned long 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_jmp_cache_hash_page(target_ulong pc)
{
    target_ulong tmp;
    tmp = pc ^ (pc >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS));
    return (tmp >> 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 >> TB_JMP_PAGE_BITS) & TB_JMP_PAGE_MASK) |
	    (tmp & TB_JMP_ADDR_MASK));
}

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

TranslationBlock *tb_alloc(target_ulong pc);
void tb_flush(CPUState *env);
void tb_link_phys(TranslationBlock *tb,
                  target_ulong phys_pc, target_ulong phys_page2);

extern TranslationBlock *tb_phys_hash[CODE_GEN_PHYS_HASH_SIZE];

extern uint8_t code_gen_buffer[CODE_GEN_BUFFER_SIZE];
extern uint8_t *code_gen_ptr;

#if defined(USE_DIRECT_JUMP)

#if defined(__powerpc__)
static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr)
{
    uint32_t val, *ptr;

    /* patch the branch destination */
    ptr = (uint32_t *)jmp_addr;
    val = *ptr;
    val = (val & ~0x03fffffc) | ((addr - jmp_addr) & 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");
}
#elif defined(__i386__) || defined(__x86_64__)
static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr)
{
    /* patch the branch destination */
    *(uint32_t *)jmp_addr = addr - (jmp_addr + 4);
    /* no need to flush icache explicitely */
}
#endif

static inline void tb_set_jmp_target(TranslationBlock *tb,
                                     int n, unsigned long addr)
{
    unsigned long offset;

    offset = tb->tb_jmp_offset[n];
    tb_set_jmp_target1((unsigned long)(tb->tc_ptr + offset), addr);
    offset = tb->tb_jmp_offset[n + 2];
    if (offset != 0xffff)
        tb_set_jmp_target1((unsigned long)(tb->tc_ptr + offset), addr);
}

#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(_WIN32)
#define ASM_DATA_SECTION ".section \".data\"\n"
#define ASM_PREVIOUS_SECTION ".section .text\n"
#elif defined(__APPLE__)
#define ASM_DATA_SECTION ".data\n"
#define ASM_PREVIOUS_SECTION ".text\n"
#else
#define ASM_DATA_SECTION ".section \".data\"\n"
#define ASM_PREVIOUS_SECTION ".previous\n"
#endif

#define ASM_OP_LABEL_NAME(n, opname) \
    ASM_NAME(__op_label) #n "." ASM_NAME(opname)

extern CPUWriteMemoryFunc *io_mem_write[IO_MEM_NB_ENTRIES][4];
extern CPUReadMemoryFunc *io_mem_read[IO_MEM_NB_ENTRIES][4];
extern void *io_mem_opaque[IO_MEM_NB_ENTRIES];

#if defined(__hppa__)

typedef int spinlock_t[4];

#define SPIN_LOCK_UNLOCKED { 1, 1, 1, 1 }

static inline void resetlock (spinlock_t *p)
{
    (*p)[0] = (*p)[1] = (*p)[2] = (*p)[3] = 1;
}

#else

typedef int spinlock_t;

#define SPIN_LOCK_UNLOCKED 0

static inline void resetlock (spinlock_t *p)
{
    *p = SPIN_LOCK_UNLOCKED;
}

#endif

#if defined(__powerpc__)
static inline int testandset (int *p)
{
    int ret;
    __asm__ __volatile__ (
                          "0:    lwarx %0,0,%1\n"
                          "      xor. %0,%3,%0\n"
                          "      bne 1f\n"
                          "      stwcx. %2,0,%1\n"
                          "      bne- 0b\n"
                          "1:    "
                          : "=&r" (ret)
                          : "r" (p), "r" (1), "r" (0)
                          : "cr0", "memory");
    return ret;
}
#elif defined(__i386__)
static inline int testandset (int *p)
{
    long int readval = 0;

    __asm__ __volatile__ ("lock; cmpxchgl %2, %0"
                          : "+m" (*p), "+a" (readval)
                          : "r" (1)
                          : "cc");
    return readval;
}
#elif defined(__x86_64__)
static inline int testandset (int *p)
{
    long int readval = 0;

    __asm__ __volatile__ ("lock; cmpxchgl %2, %0"
                          : "+m" (*p), "+a" (readval)
                          : "r" (1)
                          : "cc");
    return readval;
}
#elif defined(__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;
}
#elif defined(__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;
}
#elif defined(__sparc__)
static inline int testandset (int *p)
{
	int ret;

	__asm__ __volatile__("ldstub	[%1], %0"
			     : "=r" (ret)
			     : "r" (p)
			     : "memory");

	return (ret ? 1 : 0);
}
#elif defined(__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;
}
#elif defined(__mc68000)
static inline int testandset (int *p)
{
    char ret;
    __asm__ __volatile__("tas %1; sne %0"
                         : "=r" (ret)
                         : "m" (p)
                         : "cc","memory");
    return ret;
}
#elif defined(__hppa__)

/* Because malloc only guarantees 8-byte alignment for malloc'd data,
   and GCC only guarantees 8-byte alignment for stack locals, we can't
   be assured of 16-byte alignment for atomic lock data even if we
   specify "__attribute ((aligned(16)))" in the type declaration.  So,
   we use a struct containing an array of four ints for the atomic lock
   type and dynamically select the 16-byte aligned int from the array
   for the semaphore.  */
#define __PA_LDCW_ALIGNMENT 16
static inline void *ldcw_align (void *p) {
    unsigned long a = (unsigned long)p;
    a = (a + __PA_LDCW_ALIGNMENT - 1) & ~(__PA_LDCW_ALIGNMENT - 1);
    return (void *)a;
}

static inline int testandset (spinlock_t *p)
{
    unsigned int ret;
    p = ldcw_align(p);
    __asm__ __volatile__("ldcw 0(%1),%0"
                         : "=r" (ret)
                         : "r" (p)
                         : "memory" );
    return !ret;
}

#elif defined(__ia64)

#include <ia64intrin.h>

static inline int testandset (int *p)
{
    return __sync_lock_test_and_set (p, 1);
}
#elif defined(__mips__)
static inline int testandset (int *p)
{
    int ret;

    __asm__ __volatile__ (
	"	.set push		\n"
	"	.set noat		\n"
	"	.set mips2		\n"
	"1:	li	$1, 1		\n"
	"	ll	%0, %1		\n"
	"	sc	$1, %1		\n"
	"	beqz	$1, 1b		\n"
	"	.set pop		"
	: "=r" (ret), "+R" (*p)
	:
	: "memory");

    return ret;
}
#else
#error unimplemented CPU support
#endif

#if defined(CONFIG_USER_ONLY)
static inline void spin_lock(spinlock_t *lock)
{
    while (testandset(lock));
}

static inline void spin_unlock(spinlock_t *lock)
{
    resetlock(lock);
}

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;

extern int tb_invalidated_flag;

#if !defined(CONFIG_USER_ONLY)

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

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

#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
#undef env

#endif

#if defined(CONFIG_USER_ONLY)
static inline target_ulong get_phys_addr_code(CPUState *env, target_ulong addr)
{
    return addr;
}
#else
/* NOTE: this function can trigger an exception */
/* NOTE2: the returned address is not exactly the physical address: it
   is the offset relative to phys_ram_base */
static inline target_ulong get_phys_addr_code(CPUState *env, target_ulong addr)
{
    int mmu_idx, index, pd;

    index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
    mmu_idx = cpu_mmu_index(env);
    if (__builtin_expect(env->tlb_table[mmu_idx][index].addr_code !=
                         (addr & TARGET_PAGE_MASK), 0)) {
        ldub_code(addr);
    }
    pd = env->tlb_table[mmu_idx][index].addr_code & ~TARGET_PAGE_MASK;
    if (pd > IO_MEM_ROM && !(pd & IO_MEM_ROMD)) {
#if defined(TARGET_SPARC) || defined(TARGET_MIPS)
        do_unassigned_access(addr, 0, 1, 0);
#else
        cpu_abort(env, "Trying to execute code outside RAM or ROM at 0x" TARGET_FMT_lx "\n", addr);
#endif
    }
    return addr + env->tlb_table[mmu_idx][index].addend - (unsigned long)phys_ram_base;
}
#endif

#ifdef USE_KQEMU
#define KQEMU_MODIFY_PAGE_MASK (0xff & ~(VGA_DIRTY_FLAG | CODE_DIRTY_FLAG))

int kqemu_init(CPUState *env);
int kqemu_cpu_exec(CPUState *env);
void kqemu_flush_page(CPUState *env, target_ulong addr);
void kqemu_flush(CPUState *env, int global);
void kqemu_set_notdirty(CPUState *env, ram_addr_t ram_addr);
void kqemu_modify_page(CPUState *env, ram_addr_t ram_addr);
void kqemu_cpu_interrupt(CPUState *env);
void kqemu_record_dump(void);

static inline int kqemu_is_ok(CPUState *env)
{
    return(env->kqemu_enabled &&
           (env->cr[0] & CR0_PE_MASK) &&
           !(env->hflags & HF_INHIBIT_IRQ_MASK) &&
           (env->eflags & IF_MASK) &&
           !(env->eflags & VM_MASK) &&
           (env->kqemu_enabled == 2 ||
            ((env->hflags & HF_CPL_MASK) == 3 &&
             (env->eflags & IOPL_MASK) != IOPL_MASK)));
}

#endif
OpenPOWER on IntegriCloud