aboutsummaryrefslogtreecommitdiff
path: root/include/exec/exec-all.h
blob: d900b0d078b6437cbf85012224e6aba3c42685f2 (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
/*
 * 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 266

#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)

#define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * MAX_OPC_PARAM)

#include "qemu/log.h"

void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb);
void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb,
                          target_ulong *data);

void cpu_gen_init(void);
bool cpu_restore_state(CPUState *cpu, uintptr_t searched_pc);

void QEMU_NORETURN cpu_resume_from_signal(CPUState *cpu, void *puc);
void QEMU_NORETURN cpu_io_recompile(CPUState *cpu, uintptr_t retaddr);
TranslationBlock *tb_gen_code(CPUState *cpu,
                              target_ulong pc, target_ulong cs_base, int flags,
                              int cflags);
void cpu_exec_init(CPUState *cpu, Error **errp);
void QEMU_NORETURN cpu_loop_exit(CPUState *cpu);
void QEMU_NORETURN cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc);

#if !defined(CONFIG_USER_ONLY)
void cpu_reloading_memory_map(void);
void tcg_cpu_address_space_init(CPUState *cpu, AddressSpace *as);
/* cputlb.c */
/**
 * tlb_flush_page:
 * @cpu: CPU whose TLB should be flushed
 * @addr: virtual address of page to be flushed
 *
 * Flush one page from the TLB of the specified CPU, for all
 * MMU indexes.
 */
void tlb_flush_page(CPUState *cpu, target_ulong addr);
/**
 * tlb_flush:
 * @cpu: CPU whose TLB should be flushed
 * @flush_global: ignored
 *
 * Flush the entire TLB for the specified CPU.
 * The flush_global flag is in theory an indicator of whether the whole
 * TLB should be flushed, or only those entries not marked global.
 * In practice QEMU does not implement any global/not global flag for
 * TLB entries, and the argument is ignored.
 */
void tlb_flush(CPUState *cpu, int flush_global);
/**
 * tlb_flush_page_by_mmuidx:
 * @cpu: CPU whose TLB should be flushed
 * @addr: virtual address of page to be flushed
 * @...: list of MMU indexes to flush, terminated by a negative value
 *
 * Flush one page from the TLB of the specified CPU, for the specified
 * MMU indexes.
 */
void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, ...);
/**
 * tlb_flush_by_mmuidx:
 * @cpu: CPU whose TLB should be flushed
 * @...: list of MMU indexes to flush, terminated by a negative value
 *
 * Flush all entries from the TLB of the specified CPU, for the specified
 * MMU indexes.
 */
void tlb_flush_by_mmuidx(CPUState *cpu, ...);
void tlb_set_page(CPUState *cpu, target_ulong vaddr,
                  hwaddr paddr, int prot,
                  int mmu_idx, target_ulong size);
void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
                             hwaddr paddr, MemTxAttrs attrs,
                             int prot, int mmu_idx, target_ulong size);
void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr);
void probe_write(CPUArchState *env, target_ulong addr, int mmu_idx,
                 uintptr_t retaddr);
#else
static inline void tlb_flush_page(CPUState *cpu, target_ulong addr)
{
}

static inline void tlb_flush(CPUState *cpu, int flush_global)
{
}

static inline void tlb_flush_page_by_mmuidx(CPUState *cpu,
                                            target_ulong addr, ...)
{
}

static inline void tlb_flush_by_mmuidx(CPUState *cpu, ...)
{
}
#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.  */
/* ??? The following is based on a 2015 survey of x86_64 host output.
   Better would seem to be some sort of dynamically sized TB array,
   adapting to the block sizes actually being produced.  */
#if defined(CONFIG_SOFTMMU)
#define CODE_GEN_AVG_BLOCK_SIZE 400
#else
#define CODE_GEN_AVG_BLOCK_SIZE 150
#endif

#if defined(__arm__) || defined(_ARCH_PPC) \
    || defined(__x86_64__) || defined(__i386__) \
    || defined(__sparc__) || defined(__aarch64__) \
    || defined(__s390x__) || defined(__mips__) \
    || 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 icount;
    uint32_t cflags;    /* compile flags */
#define CF_COUNT_MASK  0x7fff
#define CF_LAST_IO     0x8000 /* Last insn may be an IO access.  */
#define CF_NOCACHE     0x10000 /* To be freed after execution */
#define CF_USE_ICOUNT  0x20000
#define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */

    void *tc_ptr;    /* pointer to the translated code */
    uint8_t *tc_search;  /* pointer to search data */
    /* next matching tb for physical address. */
    struct TranslationBlock *phys_hash_next;
    /* original tb when cflags has CF_NOCACHE */
    struct TranslationBlock *orig_tb;
    /* 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;
};

#include "qemu/thread.h"

typedef struct TBContext TBContext;

struct TBContext {

    TranslationBlock *tbs;
    TranslationBlock *tb_phys_hash[CODE_GEN_PHYS_HASH_SIZE];
    int nb_tbs;
    /* any access to the tbs or the page table must use this lock */
    QemuMutex tb_lock;

    /* statistics */
    int tb_flush_count;
    int tb_phys_invalidate_count;

    int tb_invalidated_flag;
};

void tb_free(TranslationBlock *tb);
void tb_flush(CPUState *cpu);
void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr);

#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(uintptr_t jmp_addr, uintptr_t 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 */
    stl_le_p((void*)jmp_addr, addr - (jmp_addr + 4));
    /* no need to flush icache explicitly */
}
#elif defined(__s390x__)
static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
{
    /* patch the branch destination */
    intptr_t disp = addr - (jmp_addr - 2);
    stl_be_p((void*)jmp_addr, disp / 2);
    /* no need to flush icache explicitly */
}
#elif defined(__aarch64__)
void aarch64_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr);
#define tb_set_jmp_target1 aarch64_tb_set_jmp_target
#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__) || defined(__mips__)
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));
    }
}

/* GETRA is the true target of the return instruction that we'll execute,
   defined here for simplicity of defining the follow-up macros.  */
#if defined(CONFIG_TCG_INTERPRETER)
extern uintptr_t tci_tb_ptr;
# define GETRA() tci_tb_ptr
#else
# define GETRA() \
    ((uintptr_t)__builtin_extract_return_addr(__builtin_return_address(0)))
#endif

/* The true return address will often point to a host insn that is part of
   the next translated guest insn.  Adjust the address backward to point to
   the middle of the call insn.  Subtracting one would do the job except for
   several compressed mode architectures (arm, mips) which set the low bit
   to indicate the compressed mode; subtracting two works around that.  It
   is also the case that there are no host isas that contain a call insn
   smaller than 4 bytes, so we don't worry about special-casing this.  */
#define GETPC_ADJ   2

#define GETPC()  (GETRA() - GETPC_ADJ)

#if !defined(CONFIG_USER_ONLY)

struct MemoryRegion *iotlb_to_region(CPUState *cpu,
                                     hwaddr index);

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

#endif

#if defined(CONFIG_USER_ONLY)
void mmap_lock(void);
void mmap_unlock(void);

static inline tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
{
    return addr;
}
#else
static inline void mmap_lock(void) {}
static inline void mmap_unlock(void) {}

/* cputlb.c */
tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr);

void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length);
void tlb_set_dirty(CPUState *cpu, target_ulong vaddr);

/* exec.c */
void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr);

MemoryRegionSection *
address_space_translate_for_iotlb(CPUState *cpu, hwaddr addr, hwaddr *xlat,
                                  hwaddr *plen);
hwaddr memory_region_section_get_iotlb(CPUState *cpu,
                                       MemoryRegionSection *section,
                                       target_ulong vaddr,
                                       hwaddr paddr, hwaddr xlat,
                                       int prot,
                                       target_ulong *address);
bool memory_region_is_unassigned(MemoryRegion *mr);

#endif

/* vl.c */
extern int singlestep;

/* cpu-exec.c, accessed with atomic_mb_read/atomic_mb_set */
extern CPUState *tcg_current_cpu;
extern bool exit_request;

#endif