This repository has been archived by the owner on Nov 15, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 148
/
translate-all.c
1864 lines (1646 loc) · 54.1 KB
/
translate-all.c
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
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Host code generation
*
* 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/>.
*/
#ifdef _WIN32
#include <winsock2.h>
#include <windows.h>
#else
#include <sys/types.h>
#include <sys/mman.h>
#endif
#include <stdarg.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <inttypes.h>
#include "config.h"
#include "qemu-common.h"
#define NO_CPU_IO_DEFS
#include "cpu.h"
#include "exec/exec-all.h"
#include "disas/disas.h"
#include "tcg.h"
#include "exec/cputlb.h"
#include "translate-all.h"
#include "qemu/timer.h"
//#define DEBUG_TB_INVALIDATE
//#define DEBUG_FLUSH
/* make various TB consistency checks */
//#define DEBUG_TB_CHECK
#if !defined(CONFIG_USER_ONLY)
/* TB consistency checks only implemented for usermode emulation. */
#undef DEBUG_TB_CHECK
#endif
#define SMC_BITMAP_USE_THRESHOLD 10
typedef struct PageDesc {
/* list of TBs intersecting this ram page */
TranslationBlock *first_tb;
/* in order to optimize self modifying code, we count the number
of lookups we do to a given page to use a bitmap */
unsigned int code_write_count;
uint8_t *code_bitmap;
#if defined(CONFIG_USER_ONLY)
unsigned long flags;
#endif
} PageDesc;
/* In system mode we want L1_MAP to be based on ram offsets,
while in user mode we want it to be based on virtual addresses. */
#if !defined(CONFIG_USER_ONLY)
#if HOST_LONG_BITS < TARGET_PHYS_ADDR_SPACE_BITS
# define L1_MAP_ADDR_SPACE_BITS HOST_LONG_BITS
#else
# define L1_MAP_ADDR_SPACE_BITS TARGET_PHYS_ADDR_SPACE_BITS
#endif
#else
# define L1_MAP_ADDR_SPACE_BITS TARGET_VIRT_ADDR_SPACE_BITS
#endif
/* The bits remaining after N lower levels of page tables. */
#define V_L1_BITS_REM \
((L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS) % L2_BITS)
#if V_L1_BITS_REM < 4
#define V_L1_BITS (V_L1_BITS_REM + L2_BITS)
#else
#define V_L1_BITS V_L1_BITS_REM
#endif
#define V_L1_SIZE ((target_ulong)1 << V_L1_BITS)
#define V_L1_SHIFT (L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS - V_L1_BITS)
uintptr_t qemu_real_host_page_size;
uintptr_t qemu_host_page_size;
uintptr_t qemu_host_page_mask;
/* This is a multi-level map on the virtual address space.
The bottom level has pointers to PageDesc. */
static void *l1_map[V_L1_SIZE];
static void* l1_phys_map[V_L1_SIZE];
/* code generation context */
TCGContext tcg_ctx;
/* XXX: suppress that */
unsigned long code_gen_max_block_size(void)
{
static unsigned long max;
if (max == 0) {
max = TCG_MAX_OP_SIZE;
#define DEF(name, iarg, oarg, carg, flags) DEF2((iarg) + (oarg) + (carg))
#define DEF2(copy_size) max = (copy_size > max) ? copy_size : max;
#include "tcg-opc.h"
#undef DEF
#undef DEF2
max *= OPC_MAX_SIZE;
}
return max;
}
static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
tb_page_addr_t phys_page2);
void cpu_gen_init(void)
{
tcg_context_init(&tcg_ctx);
}
/* return non zero if the very first instruction is invalid so that
the virtual CPU can trigger an exception.
'*gen_code_size_ptr' contains the size of the generated code (host
code).
*/
int cpu_gen_code(CPUArchState *env, TranslationBlock *tb, int *gen_code_size_ptr)
{
TCGContext *s = &tcg_ctx;
uint8_t *gen_code_buf;
int gen_code_size;
#ifdef CONFIG_PROFILER
int64_t ti;
#endif
#ifdef CONFIG_PROFILER
s->tb_count1++; /* includes aborted translations because of
exceptions */
ti = profile_getclock();
#endif
tcg_func_start(s);
gen_intermediate_code(env, tb);
/* generate machine code */
gen_code_buf = tb->tc_ptr;
tb->tb_next_offset[0] = 0xffff;
tb->tb_next_offset[1] = 0xffff;
s->tb_next_offset = tb->tb_next_offset;
#ifdef USE_DIRECT_JUMP
s->tb_jmp_offset = tb->tb_jmp_offset;
s->tb_next = NULL;
/* the following two entries are optional (only used for string ops) */
/* XXX: not used ? */
tb->tb_jmp_offset[2] = 0xffff;
tb->tb_jmp_offset[3] = 0xffff;
#else
s->tb_jmp_offset = NULL;
s->tb_next = tb->tb_next;
#endif
#ifdef CONFIG_PROFILER
s->tb_count++;
s->interm_time += profile_getclock() - ti;
s->code_time -= profile_getclock();
#endif
gen_code_size = tcg_gen_code(s, gen_code_buf);
*gen_code_size_ptr = gen_code_size;
#ifdef CONFIG_PROFILER
s->code_time += profile_getclock();
s->code_in_len += tb->size;
s->code_out_len += gen_code_size;
#endif
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM)) {
qemu_log("OUT: [size=%d]\n", *gen_code_size_ptr);
log_disas(tb->tc_ptr, *gen_code_size_ptr);
qemu_log("\n");
qemu_log_flush();
}
#endif
return 0;
}
/* The cpu state corresponding to 'searched_pc' is restored.
*/
static int cpu_restore_state_from_tb(TranslationBlock *tb, CPUArchState *env,
uintptr_t searched_pc)
{
TCGContext *s = &tcg_ctx;
int j;
uintptr_t tc_ptr;
#ifdef CONFIG_PROFILER
int64_t ti;
#endif
#ifdef CONFIG_PROFILER
ti = profile_getclock();
#endif
tcg_func_start(s);
gen_intermediate_code_pc(env, tb);
if (use_icount) {
/* Reset the cycle counter to the start of the block. */
env->icount_decr.u16.low += tb->icount;
/* Clear the IO flag. */
env->can_do_io = 0;
}
/* find opc index corresponding to search_pc */
tc_ptr = (uintptr_t)tb->tc_ptr;
if (searched_pc < tc_ptr)
return -1;
s->tb_next_offset = tb->tb_next_offset;
#ifdef USE_DIRECT_JUMP
s->tb_jmp_offset = tb->tb_jmp_offset;
s->tb_next = NULL;
#else
s->tb_jmp_offset = NULL;
s->tb_next = tb->tb_next;
#endif
j = tcg_gen_code_search_pc(s, (uint8_t *)tc_ptr, searched_pc - tc_ptr);
if (j < 0)
return -1;
/* now find start of instruction before */
while (s->gen_opc_instr_start[j] == 0) {
j--;
}
env->icount_decr.u16.low -= s->gen_opc_icount[j];
restore_state_to_opc(env, tb, j);
#ifdef CONFIG_PROFILER
s->restore_time += profile_getclock() - ti;
s->restore_count++;
#endif
return 0;
}
bool cpu_restore_state(CPUArchState *env, uintptr_t retaddr)
{
TranslationBlock *tb;
tb = tb_find_pc(retaddr);
if (tb) {
cpu_restore_state_from_tb(tb, env, retaddr);
return true;
}
return false;
}
#ifdef _WIN32
static inline void map_exec(void *addr, long size)
{
DWORD old_protect;
VirtualProtect(addr, size,
PAGE_EXECUTE_READWRITE, &old_protect);
}
#else
static inline void map_exec(void *addr, long size)
{
unsigned long start, end, page_size;
page_size = getpagesize();
start = (unsigned long)addr;
start &= ~(page_size - 1);
end = (unsigned long)addr + size;
end += page_size - 1;
end &= ~(page_size - 1);
mprotect((void *)start, end - start,
PROT_READ | PROT_WRITE | PROT_EXEC);
}
#endif
static void page_init(void)
{
/* NOTE: we can always suppose that qemu_host_page_size >=
TARGET_PAGE_SIZE */
#ifdef _WIN32
{
SYSTEM_INFO system_info;
GetSystemInfo(&system_info);
qemu_real_host_page_size = system_info.dwPageSize;
}
#else
qemu_real_host_page_size = getpagesize();
#endif
if (qemu_host_page_size == 0) {
qemu_host_page_size = qemu_real_host_page_size;
}
if (qemu_host_page_size < TARGET_PAGE_SIZE) {
qemu_host_page_size = TARGET_PAGE_SIZE;
}
qemu_host_page_mask = ~(qemu_host_page_size - 1);
#if defined(CONFIG_BSD) && defined(CONFIG_USER_ONLY)
{
#ifdef HAVE_KINFO_GETVMMAP
struct kinfo_vmentry *freep;
int i, cnt;
freep = kinfo_getvmmap(getpid(), &cnt);
if (freep) {
mmap_lock();
for (i = 0; i < cnt; i++) {
unsigned long startaddr, endaddr;
startaddr = freep[i].kve_start;
endaddr = freep[i].kve_end;
if (h2g_valid(startaddr)) {
startaddr = h2g(startaddr) & TARGET_PAGE_MASK;
if (h2g_valid(endaddr)) {
endaddr = h2g(endaddr);
page_set_flags(startaddr, endaddr, PAGE_RESERVED);
} else {
#if TARGET_ABI_BITS <= L1_MAP_ADDR_SPACE_BITS
endaddr = ~0ul;
page_set_flags(startaddr, endaddr, PAGE_RESERVED);
#endif
}
}
}
free(freep);
mmap_unlock();
}
#else
FILE *f;
last_brk = (unsigned long)sbrk(0);
f = fopen("/compat/linux/proc/self/maps", "r");
if (f) {
mmap_lock();
do {
unsigned long startaddr, endaddr;
int n;
n = fscanf(f, "%lx-%lx %*[^\n]\n", &startaddr, &endaddr);
if (n == 2 && h2g_valid(startaddr)) {
startaddr = h2g(startaddr) & TARGET_PAGE_MASK;
if (h2g_valid(endaddr)) {
endaddr = h2g(endaddr);
} else {
endaddr = ~0ul;
}
page_set_flags(startaddr, endaddr, PAGE_RESERVED);
}
} while (!feof(f));
fclose(f);
mmap_unlock();
}
#endif
}
#endif
}
static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
{
PageDesc *pd;
void **lp;
int i;
#if defined(CONFIG_USER_ONLY)
/* We can't use g_malloc because it may recurse into a locked mutex. */
# define ALLOC(P, SIZE) \
do { \
P = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, \
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); \
} while (0)
#else
# define ALLOC(P, SIZE) \
do { P = g_malloc0(SIZE); } while (0)
#endif
/* Level 1. Always allocated. */
lp = l1_map + ((index >> V_L1_SHIFT) & (V_L1_SIZE - 1));
/* Level 2..N-1. */
for (i = V_L1_SHIFT / L2_BITS - 1; i > 0; i--) {
void **p = *lp;
if (p == NULL) {
if (!alloc) {
return NULL;
}
ALLOC(p, sizeof(void *) * L2_SIZE);
*lp = p;
}
lp = p + ((index >> (i * L2_BITS)) & (L2_SIZE - 1));
}
pd = *lp;
if (pd == NULL) {
if (!alloc) {
return NULL;
}
ALLOC(pd, sizeof(PageDesc) * L2_SIZE);
*lp = pd;
}
#undef ALLOC
return pd + (index & (L2_SIZE - 1));
}
static inline PageDesc *page_find(tb_page_addr_t index)
{
return page_find_alloc(index, 0);
}
PhysPageDesc *phys_page_find_alloc(hwaddr index, int alloc)
{
void **lp;
PhysPageDesc *pd;
int i;
/* Level 1. Always allocated. */
lp = l1_phys_map + ((index >> V_L1_SHIFT) & (V_L1_SIZE - 1));
/* Level 2..N-1 */
for (i = V_L1_SHIFT / L2_BITS - 1; i > 0; i--) {
void **p = *lp;
if (p == NULL) {
if (!alloc) {
return NULL;
}
p = g_malloc0(sizeof(void *) * L2_SIZE);
*lp = p;
}
lp = p + ((index >> (i * L2_BITS)) & (L2_SIZE - 1));
}
pd = *lp;
if (pd == NULL) {
if (!alloc) {
return NULL;
}
pd = g_malloc(sizeof(PhysPageDesc) * L2_SIZE);
*lp = pd;
for (i = 0; i < L2_SIZE; i++) {
pd[i].phys_offset = IO_MEM_UNASSIGNED;
pd[i].region_offset = (index + i) << TARGET_PAGE_BITS;
}
}
return ((PhysPageDesc *)pd) + (index & (L2_SIZE - 1));
}
PhysPageDesc *phys_page_find(hwaddr index)
{
return phys_page_find_alloc(index, 0);
}
#if !defined(CONFIG_USER_ONLY)
#define mmap_lock() do { } while (0)
#define mmap_unlock() do { } while (0)
#endif
#if defined(CONFIG_USER_ONLY)
/* Currently it is not recommended to allocate big chunks of data in
user mode. It will change when a dedicated libc will be used. */
/* ??? 64-bit hosts ought to have no problem mmaping data outside the
region in which the guest needs to run. Revisit this. */
#define USE_STATIC_CODE_GEN_BUFFER
#endif
/* ??? Should configure for this, not list operating systems here. */
#if (defined(__linux__) \
|| defined(__FreeBSD__) || defined(__FreeBSD_kernel__) \
|| defined(__DragonFly__) || defined(__OpenBSD__) \
|| defined(__NetBSD__))
# define USE_MMAP
#endif
/* Minimum size of the code gen buffer. This number is randomly chosen,
but not so small that we can't have a fair number of TB's live. */
#define MIN_CODE_GEN_BUFFER_SIZE (1024u * 1024)
/* Maximum size of the code gen buffer we'd like to use. Unless otherwise
indicated, this is constrained by the range of direct branches on the
host cpu, as used by the TCG implementation of goto_tb. */
#if defined(__x86_64__)
# define MAX_CODE_GEN_BUFFER_SIZE (2ul * 1024 * 1024 * 1024)
#elif defined(__sparc__)
# define MAX_CODE_GEN_BUFFER_SIZE (2ul * 1024 * 1024 * 1024)
#elif defined(__aarch64__)
# define MAX_CODE_GEN_BUFFER_SIZE (128ul * 1024 * 1024)
#elif defined(__arm__)
# define MAX_CODE_GEN_BUFFER_SIZE (16u * 1024 * 1024)
#elif defined(__s390x__)
/* We have a +- 4GB range on the branches; leave some slop. */
# define MAX_CODE_GEN_BUFFER_SIZE (3ul * 1024 * 1024 * 1024)
#else
# define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1)
#endif
#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (32u * 1024 * 1024)
#define DEFAULT_CODE_GEN_BUFFER_SIZE \
(DEFAULT_CODE_GEN_BUFFER_SIZE_1 < MAX_CODE_GEN_BUFFER_SIZE \
? DEFAULT_CODE_GEN_BUFFER_SIZE_1 : MAX_CODE_GEN_BUFFER_SIZE)
static inline size_t size_code_gen_buffer(size_t tb_size)
{
/* Size the buffer. */
if (tb_size == 0) {
#ifdef USE_STATIC_CODE_GEN_BUFFER
tb_size = DEFAULT_CODE_GEN_BUFFER_SIZE;
#else
/* ??? Needs adjustments. */
/* ??? If we relax the requirement that CONFIG_USER_ONLY use the
static buffer, we could size this on RESERVED_VA, on the text
segment size of the executable, or continue to use the default. */
tb_size = (unsigned long)(ram_size / 4);
#endif
}
if (tb_size < MIN_CODE_GEN_BUFFER_SIZE) {
tb_size = MIN_CODE_GEN_BUFFER_SIZE;
}
if (tb_size > MAX_CODE_GEN_BUFFER_SIZE) {
tb_size = MAX_CODE_GEN_BUFFER_SIZE;
}
tcg_ctx.code_gen_buffer_size = tb_size;
return tb_size;
}
#ifdef USE_STATIC_CODE_GEN_BUFFER
static uint8_t static_code_gen_buffer[DEFAULT_CODE_GEN_BUFFER_SIZE]
__attribute__((aligned(CODE_GEN_ALIGN)));
static inline void *alloc_code_gen_buffer(void)
{
map_exec(static_code_gen_buffer, tcg_ctx.code_gen_buffer_size);
return static_code_gen_buffer;
}
#elif defined(USE_MMAP)
static inline void *alloc_code_gen_buffer(void)
{
int flags = MAP_PRIVATE | MAP_ANONYMOUS;
uintptr_t start = 0;
void *buf;
/* Constrain the position of the buffer based on the host cpu.
Note that these addresses are chosen in concert with the
addresses assigned in the relevant linker script file. */
# if defined(__PIE__) || defined(__PIC__)
/* Don't bother setting a preferred location if we're building
a position-independent executable. We're more likely to get
an address near the main executable if we let the kernel
choose the address. */
# elif defined(__x86_64__) && defined(MAP_32BIT)
/* Force the memory down into low memory with the executable.
Leave the choice of exact location with the kernel. */
flags |= MAP_32BIT;
/* Cannot expect to map more than 800MB in low memory. */
if (tcg_ctx.code_gen_buffer_size > 800u * 1024 * 1024) {
tcg_ctx.code_gen_buffer_size = 800u * 1024 * 1024;
}
# elif defined(__sparc__)
start = 0x40000000ul;
# elif defined(__s390x__)
start = 0x90000000ul;
# endif
buf = mmap((void *)start, tcg_ctx.code_gen_buffer_size,
PROT_WRITE | PROT_READ | PROT_EXEC, flags, -1, 0);
return buf == MAP_FAILED ? NULL : buf;
}
#else
static inline void *alloc_code_gen_buffer(void)
{
void *buf = g_malloc(tcg_ctx.code_gen_buffer_size);
if (buf) {
map_exec(buf, tcg_ctx.code_gen_buffer_size);
}
return buf;
}
#endif /* USE_STATIC_CODE_GEN_BUFFER, USE_MMAP */
static inline void code_gen_alloc(size_t tb_size)
{
tcg_ctx.code_gen_buffer_size = size_code_gen_buffer(tb_size);
tcg_ctx.code_gen_buffer = alloc_code_gen_buffer();
if (tcg_ctx.code_gen_buffer == NULL) {
fprintf(stderr, "Could not allocate dynamic translator buffer\n");
exit(1);
}
qemu_madvise(tcg_ctx.code_gen_buffer, tcg_ctx.code_gen_buffer_size,
QEMU_MADV_HUGEPAGE);
/* Steal room for the prologue at the end of the buffer. This ensures
(via the MAX_CODE_GEN_BUFFER_SIZE limits above) that direct branches
from TB's to the prologue are going to be in range. It also means
that we don't need to mark (additional) portions of the data segment
as executable. */
tcg_ctx.code_gen_prologue = tcg_ctx.code_gen_buffer +
tcg_ctx.code_gen_buffer_size - 1024;
tcg_ctx.code_gen_buffer_size -= 1024;
tcg_ctx.code_gen_buffer_max_size = tcg_ctx.code_gen_buffer_size -
(TCG_MAX_OP_SIZE * OPC_BUF_SIZE);
tcg_ctx.code_gen_max_blocks = tcg_ctx.code_gen_buffer_size /
CODE_GEN_AVG_BLOCK_SIZE;
tcg_ctx.tb_ctx.tbs =
g_malloc(tcg_ctx.code_gen_max_blocks * sizeof(TranslationBlock));
}
/* Must be called before using the QEMU cpus. 'tb_size' is the size
(in bytes) allocated to the translation buffer. Zero means default
size. */
void tcg_exec_init(unsigned long tb_size)
{
cpu_gen_init();
code_gen_alloc(tb_size);
tcg_ctx.code_gen_ptr = tcg_ctx.code_gen_buffer;
page_init();
#if !defined(CONFIG_USER_ONLY) || !defined(CONFIG_USE_GUEST_BASE)
/* There's no guest base to take into account, so go ahead and
initialize the prologue now. */
tcg_prologue_init(&tcg_ctx);
#endif
}
bool tcg_enabled(void)
{
return tcg_ctx.code_gen_buffer != NULL;
}
/* Allocate a new translation block. Flush the translation buffer if
too many translation blocks or too much generated code. */
static TranslationBlock *tb_alloc(target_ulong pc)
{
TranslationBlock *tb;
if (tcg_ctx.tb_ctx.nb_tbs >= tcg_ctx.code_gen_max_blocks ||
(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer) >=
tcg_ctx.code_gen_buffer_max_size) {
return NULL;
}
tb = &tcg_ctx.tb_ctx.tbs[tcg_ctx.tb_ctx.nb_tbs++];
tb->pc = pc;
tb->cflags = 0;
return tb;
}
void tb_free(TranslationBlock *tb)
{
/* In practice this is mostly used for single use temporary TB
Ignore the hard cases and just back up if this TB happens to
be the last one generated. */
if (tcg_ctx.tb_ctx.nb_tbs > 0 &&
tb == &tcg_ctx.tb_ctx.tbs[tcg_ctx.tb_ctx.nb_tbs - 1]) {
tcg_ctx.code_gen_ptr = tb->tc_ptr;
tcg_ctx.tb_ctx.nb_tbs--;
}
}
static inline void invalidate_page_bitmap(PageDesc *p)
{
if (p->code_bitmap) {
g_free(p->code_bitmap);
p->code_bitmap = NULL;
}
p->code_write_count = 0;
}
/* Set to NULL all the 'first_tb' fields in all PageDescs. */
static void page_flush_tb_1(int level, void **lp)
{
int i;
if (*lp == NULL) {
return;
}
if (level == 0) {
PageDesc *pd = *lp;
for (i = 0; i < L2_SIZE; ++i) {
pd[i].first_tb = NULL;
invalidate_page_bitmap(pd + i);
}
} else {
void **pp = *lp;
for (i = 0; i < L2_SIZE; ++i) {
page_flush_tb_1(level - 1, pp + i);
}
}
}
static void page_flush_tb(void)
{
int i;
for (i = 0; i < V_L1_SIZE; i++) {
page_flush_tb_1(V_L1_SHIFT / L2_BITS - 1, l1_map + i);
}
}
/* flush all the translation blocks */
/* XXX: tb_flush is currently not thread safe */
void tb_flush(CPUArchState *env1)
{
CPUState *cpu;
#if defined(DEBUG_FLUSH)
printf("qemu: flush code_size=%ld nb_tbs=%d avg_tb_size=%ld\n",
(unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer),
tcg_ctx.tb_ctx.nb_tbs, tcg_ctx.tb_ctx.nb_tbs > 0 ?
((unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer)) /
tcg_ctx.tb_ctx.nb_tbs : 0);
#endif
if ((unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer)
> tcg_ctx.code_gen_buffer_size) {
cpu_abort(env1, "Internal error: code buffer overflow\n");
}
tcg_ctx.tb_ctx.nb_tbs = 0;
CPU_FOREACH(cpu) {
CPUArchState *env = cpu->env_ptr;
memset (env->tb_jmp_cache, 0, TB_JMP_CACHE_SIZE * sizeof (void *));
}
memset(tcg_ctx.tb_ctx.tb_phys_hash, 0,
CODE_GEN_PHYS_HASH_SIZE * sizeof(void *));
page_flush_tb();
tcg_ctx.code_gen_ptr = tcg_ctx.code_gen_buffer;
/* XXX: flush processor icache at this point if cache flush is
expensive */
tcg_ctx.tb_ctx.tb_flush_count++;
}
#ifdef DEBUG_TB_CHECK
static void tb_invalidate_check(target_ulong address)
{
TranslationBlock *tb;
int i;
address &= TARGET_PAGE_MASK;
for (i = 0; i < CODE_GEN_PHYS_HASH_SIZE; i++) {
for (tb = tb_ctx.tb_phys_hash[i]; tb != NULL; tb = tb->phys_hash_next) {
if (!(address + TARGET_PAGE_SIZE <= tb->pc ||
address >= tb->pc + tb->size)) {
printf("ERROR invalidate: address=" TARGET_FMT_lx
" PC=%08lx size=%04x\n",
address, (long)tb->pc, tb->size);
}
}
}
}
/* verify that all the pages have correct rights for code */
static void tb_page_check(void)
{
TranslationBlock *tb;
int i, flags1, flags2;
for (i = 0; i < CODE_GEN_PHYS_HASH_SIZE; i++) {
for (tb = tcg_ctx.tb_ctx.tb_phys_hash[i]; tb != NULL;
tb = tb->phys_hash_next) {
flags1 = page_get_flags(tb->pc);
flags2 = page_get_flags(tb->pc + tb->size - 1);
if ((flags1 & PAGE_WRITE) || (flags2 & PAGE_WRITE)) {
printf("ERROR page flags: PC=%08lx size=%04x f1=%x f2=%x\n",
(long)tb->pc, tb->size, flags1, flags2);
}
}
}
}
#endif
static inline void tb_hash_remove(TranslationBlock **ptb, TranslationBlock *tb)
{
TranslationBlock *tb1;
for (;;) {
tb1 = *ptb;
if (tb1 == tb) {
*ptb = tb1->phys_hash_next;
break;
}
ptb = &tb1->phys_hash_next;
}
}
static inline void tb_page_remove(TranslationBlock **ptb, TranslationBlock *tb)
{
TranslationBlock *tb1;
unsigned int n1;
for (;;) {
tb1 = *ptb;
n1 = (uintptr_t)tb1 & 3;
tb1 = (TranslationBlock *)((uintptr_t)tb1 & ~3);
if (tb1 == tb) {
*ptb = tb1->page_next[n1];
break;
}
ptb = &tb1->page_next[n1];
}
}
static inline void tb_jmp_remove(TranslationBlock *tb, int n)
{
TranslationBlock *tb1, **ptb;
unsigned int n1;
ptb = &tb->jmp_next[n];
tb1 = *ptb;
if (tb1) {
/* find tb(n) in circular list */
for (;;) {
tb1 = *ptb;
n1 = (uintptr_t)tb1 & 3;
tb1 = (TranslationBlock *)((uintptr_t)tb1 & ~3);
if (n1 == n && tb1 == tb) {
break;
}
if (n1 == 2) {
ptb = &tb1->jmp_first;
} else {
ptb = &tb1->jmp_next[n1];
}
}
/* now we can suppress tb(n) from the list */
*ptb = tb->jmp_next[n];
tb->jmp_next[n] = NULL;
}
}
/* reset the jump entry 'n' of a TB so that it is not chained to
another TB */
static inline void tb_reset_jump(TranslationBlock *tb, int n)
{
tb_set_jmp_target(tb, n, (uintptr_t)(tb->tc_ptr + tb->tb_next_offset[n]));
}
/* invalidate one TB */
void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
{
CPUState *cpu;
PageDesc *p;
unsigned int h, n1;
tb_page_addr_t phys_pc;
TranslationBlock *tb1, *tb2;
/* remove the TB from the hash list */
phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
h = tb_phys_hash_func(phys_pc);
tb_hash_remove(&tcg_ctx.tb_ctx.tb_phys_hash[h], tb);
/* remove the TB from the page list */
if (tb->page_addr[0] != page_addr) {
p = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS);
tb_page_remove(&p->first_tb, tb);
invalidate_page_bitmap(p);
}
if (tb->page_addr[1] != -1 && tb->page_addr[1] != page_addr) {
p = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS);
tb_page_remove(&p->first_tb, tb);
invalidate_page_bitmap(p);
}
tcg_ctx.tb_ctx.tb_invalidated_flag = 1;
/* remove the TB from the hash list */
h = tb_jmp_cache_hash_func(tb->pc);
CPU_FOREACH(cpu) {
CPUArchState *env = cpu->env_ptr;
if (env->tb_jmp_cache[h] == tb) {
env->tb_jmp_cache[h] = NULL;
}
}
/* suppress this TB from the two jump lists */
tb_jmp_remove(tb, 0);
tb_jmp_remove(tb, 1);
/* suppress any remaining jumps to this TB */
tb1 = tb->jmp_first;
for (;;) {
n1 = (uintptr_t)tb1 & 3;
if (n1 == 2) {
break;
}
tb1 = (TranslationBlock *)((uintptr_t)tb1 & ~3);
tb2 = tb1->jmp_next[n1];
tb_reset_jump(tb1, n1);
tb1->jmp_next[n1] = NULL;
tb1 = tb2;
}
tb->jmp_first = (TranslationBlock *)((uintptr_t)tb | 2); /* fail safe */
tcg_ctx.tb_ctx.tb_phys_invalidate_count++;
}
static inline void set_bits(uint8_t *tab, int start, int len)
{
int end, mask, end1;
end = start + len;
tab += start >> 3;
mask = 0xff << (start & 7);
if ((start & ~7) == (end & ~7)) {
if (start < end) {
mask &= ~(0xff << (end & 7));
*tab |= mask;
}
} else {
*tab++ |= mask;
start = (start + 8) & ~7;
end1 = end & ~7;
while (start < end1) {
*tab++ = 0xff;
start += 8;
}
if (start < end) {
mask = ~(0xff << (end & 7));
*tab |= mask;
}
}
}
static void build_page_bitmap(PageDesc *p)
{
int n, tb_start, tb_end;
TranslationBlock *tb;
p->code_bitmap = g_malloc0(TARGET_PAGE_SIZE / 8);
tb = p->first_tb;
while (tb != NULL) {
n = (uintptr_t)tb & 3;
tb = (TranslationBlock *)((uintptr_t)tb & ~3);
/* NOTE: this is subtle as a TB may span two physical pages */
if (n == 0) {
/* NOTE: tb_end may be after the end of the page, but
it is not a problem */
tb_start = tb->pc & ~TARGET_PAGE_MASK;
tb_end = tb_start + tb->size;
if (tb_end > TARGET_PAGE_SIZE) {
tb_end = TARGET_PAGE_SIZE;
}
} else {
tb_start = 0;
tb_end = ((tb->pc + tb->size) & ~TARGET_PAGE_MASK);
}
set_bits(p->code_bitmap, tb_start, tb_end - tb_start);
tb = tb->page_next[n];
}
}
TranslationBlock *tb_gen_code(CPUArchState *env,
target_ulong pc, target_ulong cs_base,
int flags, int cflags)
{
TranslationBlock *tb;
uint8_t *tc_ptr;
tb_page_addr_t phys_pc, phys_page2;
target_ulong virt_page2;
int code_gen_size;
phys_pc = get_page_addr_code(env, pc);
tb = tb_alloc(pc);
if (!tb) {
/* flush must be done */
tb_flush(env);
/* cannot fail at this point */
tb = tb_alloc(pc);
/* Don't forget to invalidate previous TB info. */
tcg_ctx.tb_ctx.tb_invalidated_flag = 1;