forked from devos50/qemu-ios
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtcg.c
4738 lines (4207 loc) · 147 KB
/
tcg.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
/*
* Tiny Code Generator for QEMU
*
* Copyright (c) 2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
/* define it to use liveness analysis (better code) */
#define USE_TCG_OPTIMIZATIONS
#include "qemu/osdep.h"
/* Define to jump the ELF file used to communicate with GDB. */
#undef DEBUG_JIT
#include "qemu/error-report.h"
#include "qemu/cutils.h"
#include "qemu/host-utils.h"
#include "qemu/qemu-print.h"
#include "qemu/timer.h"
#include "qemu/cacheflush.h"
/* Note: the long term plan is to reduce the dependencies on the QEMU
CPU definitions. Currently they are used for qemu_ld/st
instructions */
#define NO_CPU_IO_DEFS
#include "exec/exec-all.h"
#include "tcg/tcg-op.h"
#if UINTPTR_MAX == UINT32_MAX
# define ELF_CLASS ELFCLASS32
#else
# define ELF_CLASS ELFCLASS64
#endif
#ifdef HOST_WORDS_BIGENDIAN
# define ELF_DATA ELFDATA2MSB
#else
# define ELF_DATA ELFDATA2LSB
#endif
#include "elf.h"
#include "exec/log.h"
#include "tcg/tcg-ldst.h"
#include "tcg-internal.h"
#ifdef CONFIG_TCG_INTERPRETER
#include <ffi.h>
#endif
/* Forward declarations for functions declared in tcg-target.c.inc and
used here. */
static void tcg_target_init(TCGContext *s);
static void tcg_target_qemu_prologue(TCGContext *s);
static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend);
/* The CIE and FDE header definitions will be common to all hosts. */
typedef struct {
uint32_t len __attribute__((aligned((sizeof(void *)))));
uint32_t id;
uint8_t version;
char augmentation[1];
uint8_t code_align;
uint8_t data_align;
uint8_t return_column;
} DebugFrameCIE;
typedef struct QEMU_PACKED {
uint32_t len __attribute__((aligned((sizeof(void *)))));
uint32_t cie_offset;
uintptr_t func_start;
uintptr_t func_len;
} DebugFrameFDEHeader;
typedef struct QEMU_PACKED {
DebugFrameCIE cie;
DebugFrameFDEHeader fde;
} DebugFrameHeader;
static void tcg_register_jit_int(const void *buf, size_t size,
const void *debug_frame,
size_t debug_frame_size)
__attribute__((unused));
/* Forward declarations for functions declared and used in tcg-target.c.inc. */
static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg1,
intptr_t arg2);
static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg);
static void tcg_out_movi(TCGContext *s, TCGType type,
TCGReg ret, tcg_target_long arg);
static void tcg_out_op(TCGContext *s, TCGOpcode opc,
const TCGArg args[TCG_MAX_OP_ARGS],
const int const_args[TCG_MAX_OP_ARGS]);
#if TCG_TARGET_MAYBE_vec
static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, TCGReg src);
static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, TCGReg base, intptr_t offset);
static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, int64_t arg);
static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
unsigned vecl, unsigned vece,
const TCGArg args[TCG_MAX_OP_ARGS],
const int const_args[TCG_MAX_OP_ARGS]);
#else
static inline bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, TCGReg src)
{
g_assert_not_reached();
}
static inline bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, TCGReg base, intptr_t offset)
{
g_assert_not_reached();
}
static inline void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
TCGReg dst, int64_t arg)
{
g_assert_not_reached();
}
static inline void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
unsigned vecl, unsigned vece,
const TCGArg args[TCG_MAX_OP_ARGS],
const int const_args[TCG_MAX_OP_ARGS])
{
g_assert_not_reached();
}
#endif
static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1,
intptr_t arg2);
static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val,
TCGReg base, intptr_t ofs);
#ifdef CONFIG_TCG_INTERPRETER
static void tcg_out_call(TCGContext *s, const tcg_insn_unit *target,
ffi_cif *cif);
#else
static void tcg_out_call(TCGContext *s, const tcg_insn_unit *target);
#endif
static bool tcg_target_const_match(int64_t val, TCGType type, int ct);
#ifdef TCG_TARGET_NEED_LDST_LABELS
static int tcg_out_ldst_finalize(TCGContext *s);
#endif
TCGContext tcg_init_ctx;
__thread TCGContext *tcg_ctx;
TCGContext **tcg_ctxs;
unsigned int tcg_cur_ctxs;
unsigned int tcg_max_ctxs;
TCGv_env cpu_env = 0;
const void *tcg_code_gen_epilogue;
uintptr_t tcg_splitwx_diff;
#ifndef CONFIG_TCG_INTERPRETER
tcg_prologue_fn *tcg_qemu_tb_exec;
#endif
static TCGRegSet tcg_target_available_regs[TCG_TYPE_COUNT];
static TCGRegSet tcg_target_call_clobber_regs;
#if TCG_TARGET_INSN_UNIT_SIZE == 1
static __attribute__((unused)) inline void tcg_out8(TCGContext *s, uint8_t v)
{
*s->code_ptr++ = v;
}
static __attribute__((unused)) inline void tcg_patch8(tcg_insn_unit *p,
uint8_t v)
{
*p = v;
}
#endif
#if TCG_TARGET_INSN_UNIT_SIZE <= 2
static __attribute__((unused)) inline void tcg_out16(TCGContext *s, uint16_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 2) {
*s->code_ptr++ = v;
} else {
tcg_insn_unit *p = s->code_ptr;
memcpy(p, &v, sizeof(v));
s->code_ptr = p + (2 / TCG_TARGET_INSN_UNIT_SIZE);
}
}
static __attribute__((unused)) inline void tcg_patch16(tcg_insn_unit *p,
uint16_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 2) {
*p = v;
} else {
memcpy(p, &v, sizeof(v));
}
}
#endif
#if TCG_TARGET_INSN_UNIT_SIZE <= 4
static __attribute__((unused)) inline void tcg_out32(TCGContext *s, uint32_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 4) {
*s->code_ptr++ = v;
} else {
tcg_insn_unit *p = s->code_ptr;
memcpy(p, &v, sizeof(v));
s->code_ptr = p + (4 / TCG_TARGET_INSN_UNIT_SIZE);
}
}
static __attribute__((unused)) inline void tcg_patch32(tcg_insn_unit *p,
uint32_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 4) {
*p = v;
} else {
memcpy(p, &v, sizeof(v));
}
}
#endif
#if TCG_TARGET_INSN_UNIT_SIZE <= 8
static __attribute__((unused)) inline void tcg_out64(TCGContext *s, uint64_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 8) {
*s->code_ptr++ = v;
} else {
tcg_insn_unit *p = s->code_ptr;
memcpy(p, &v, sizeof(v));
s->code_ptr = p + (8 / TCG_TARGET_INSN_UNIT_SIZE);
}
}
static __attribute__((unused)) inline void tcg_patch64(tcg_insn_unit *p,
uint64_t v)
{
if (TCG_TARGET_INSN_UNIT_SIZE == 8) {
*p = v;
} else {
memcpy(p, &v, sizeof(v));
}
}
#endif
/* label relocation processing */
static void tcg_out_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type,
TCGLabel *l, intptr_t addend)
{
TCGRelocation *r = tcg_malloc(sizeof(TCGRelocation));
r->type = type;
r->ptr = code_ptr;
r->addend = addend;
QSIMPLEQ_INSERT_TAIL(&l->relocs, r, next);
}
static void tcg_out_label(TCGContext *s, TCGLabel *l)
{
tcg_debug_assert(!l->has_value);
l->has_value = 1;
l->u.value_ptr = tcg_splitwx_to_rx(s->code_ptr);
}
TCGLabel *gen_new_label(void)
{
TCGContext *s = tcg_ctx;
TCGLabel *l = tcg_malloc(sizeof(TCGLabel));
memset(l, 0, sizeof(TCGLabel));
l->id = s->nb_labels++;
QSIMPLEQ_INIT(&l->relocs);
QSIMPLEQ_INSERT_TAIL(&s->labels, l, next);
return l;
}
static bool tcg_resolve_relocs(TCGContext *s)
{
TCGLabel *l;
QSIMPLEQ_FOREACH(l, &s->labels, next) {
TCGRelocation *r;
uintptr_t value = l->u.value;
QSIMPLEQ_FOREACH(r, &l->relocs, next) {
if (!patch_reloc(r->ptr, r->type, value, r->addend)) {
return false;
}
}
}
return true;
}
static void set_jmp_reset_offset(TCGContext *s, int which)
{
/*
* We will check for overflow at the end of the opcode loop in
* tcg_gen_code, where we bound tcg_current_code_size to UINT16_MAX.
*/
s->tb_jmp_reset_offset[which] = tcg_current_code_size(s);
}
/* Signal overflow, starting over with fewer guest insns. */
static void QEMU_NORETURN tcg_raise_tb_overflow(TCGContext *s)
{
siglongjmp(s->jmp_trans, -2);
}
#define C_PFX1(P, A) P##A
#define C_PFX2(P, A, B) P##A##_##B
#define C_PFX3(P, A, B, C) P##A##_##B##_##C
#define C_PFX4(P, A, B, C, D) P##A##_##B##_##C##_##D
#define C_PFX5(P, A, B, C, D, E) P##A##_##B##_##C##_##D##_##E
#define C_PFX6(P, A, B, C, D, E, F) P##A##_##B##_##C##_##D##_##E##_##F
/* Define an enumeration for the various combinations. */
#define C_O0_I1(I1) C_PFX1(c_o0_i1_, I1),
#define C_O0_I2(I1, I2) C_PFX2(c_o0_i2_, I1, I2),
#define C_O0_I3(I1, I2, I3) C_PFX3(c_o0_i3_, I1, I2, I3),
#define C_O0_I4(I1, I2, I3, I4) C_PFX4(c_o0_i4_, I1, I2, I3, I4),
#define C_O1_I1(O1, I1) C_PFX2(c_o1_i1_, O1, I1),
#define C_O1_I2(O1, I1, I2) C_PFX3(c_o1_i2_, O1, I1, I2),
#define C_O1_I3(O1, I1, I2, I3) C_PFX4(c_o1_i3_, O1, I1, I2, I3),
#define C_O1_I4(O1, I1, I2, I3, I4) C_PFX5(c_o1_i4_, O1, I1, I2, I3, I4),
#define C_N1_I2(O1, I1, I2) C_PFX3(c_n1_i2_, O1, I1, I2),
#define C_O2_I1(O1, O2, I1) C_PFX3(c_o2_i1_, O1, O2, I1),
#define C_O2_I2(O1, O2, I1, I2) C_PFX4(c_o2_i2_, O1, O2, I1, I2),
#define C_O2_I3(O1, O2, I1, I2, I3) C_PFX5(c_o2_i3_, O1, O2, I1, I2, I3),
#define C_O2_I4(O1, O2, I1, I2, I3, I4) C_PFX6(c_o2_i4_, O1, O2, I1, I2, I3, I4),
typedef enum {
#include "tcg-target-con-set.h"
} TCGConstraintSetIndex;
static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode);
#undef C_O0_I1
#undef C_O0_I2
#undef C_O0_I3
#undef C_O0_I4
#undef C_O1_I1
#undef C_O1_I2
#undef C_O1_I3
#undef C_O1_I4
#undef C_N1_I2
#undef C_O2_I1
#undef C_O2_I2
#undef C_O2_I3
#undef C_O2_I4
/* Put all of the constraint sets into an array, indexed by the enum. */
#define C_O0_I1(I1) { .args_ct_str = { #I1 } },
#define C_O0_I2(I1, I2) { .args_ct_str = { #I1, #I2 } },
#define C_O0_I3(I1, I2, I3) { .args_ct_str = { #I1, #I2, #I3 } },
#define C_O0_I4(I1, I2, I3, I4) { .args_ct_str = { #I1, #I2, #I3, #I4 } },
#define C_O1_I1(O1, I1) { .args_ct_str = { #O1, #I1 } },
#define C_O1_I2(O1, I1, I2) { .args_ct_str = { #O1, #I1, #I2 } },
#define C_O1_I3(O1, I1, I2, I3) { .args_ct_str = { #O1, #I1, #I2, #I3 } },
#define C_O1_I4(O1, I1, I2, I3, I4) { .args_ct_str = { #O1, #I1, #I2, #I3, #I4 } },
#define C_N1_I2(O1, I1, I2) { .args_ct_str = { "&" #O1, #I1, #I2 } },
#define C_O2_I1(O1, O2, I1) { .args_ct_str = { #O1, #O2, #I1 } },
#define C_O2_I2(O1, O2, I1, I2) { .args_ct_str = { #O1, #O2, #I1, #I2 } },
#define C_O2_I3(O1, O2, I1, I2, I3) { .args_ct_str = { #O1, #O2, #I1, #I2, #I3 } },
#define C_O2_I4(O1, O2, I1, I2, I3, I4) { .args_ct_str = { #O1, #O2, #I1, #I2, #I3, #I4 } },
static const TCGTargetOpDef constraint_sets[] = {
#include "tcg-target-con-set.h"
};
#undef C_O0_I1
#undef C_O0_I2
#undef C_O0_I3
#undef C_O0_I4
#undef C_O1_I1
#undef C_O1_I2
#undef C_O1_I3
#undef C_O1_I4
#undef C_N1_I2
#undef C_O2_I1
#undef C_O2_I2
#undef C_O2_I3
#undef C_O2_I4
/* Expand the enumerator to be returned from tcg_target_op_def(). */
#define C_O0_I1(I1) C_PFX1(c_o0_i1_, I1)
#define C_O0_I2(I1, I2) C_PFX2(c_o0_i2_, I1, I2)
#define C_O0_I3(I1, I2, I3) C_PFX3(c_o0_i3_, I1, I2, I3)
#define C_O0_I4(I1, I2, I3, I4) C_PFX4(c_o0_i4_, I1, I2, I3, I4)
#define C_O1_I1(O1, I1) C_PFX2(c_o1_i1_, O1, I1)
#define C_O1_I2(O1, I1, I2) C_PFX3(c_o1_i2_, O1, I1, I2)
#define C_O1_I3(O1, I1, I2, I3) C_PFX4(c_o1_i3_, O1, I1, I2, I3)
#define C_O1_I4(O1, I1, I2, I3, I4) C_PFX5(c_o1_i4_, O1, I1, I2, I3, I4)
#define C_N1_I2(O1, I1, I2) C_PFX3(c_n1_i2_, O1, I1, I2)
#define C_O2_I1(O1, O2, I1) C_PFX3(c_o2_i1_, O1, O2, I1)
#define C_O2_I2(O1, O2, I1, I2) C_PFX4(c_o2_i2_, O1, O2, I1, I2)
#define C_O2_I3(O1, O2, I1, I2, I3) C_PFX5(c_o2_i3_, O1, O2, I1, I2, I3)
#define C_O2_I4(O1, O2, I1, I2, I3, I4) C_PFX6(c_o2_i4_, O1, O2, I1, I2, I3, I4)
#include "tcg-target.c.inc"
static void alloc_tcg_plugin_context(TCGContext *s)
{
#ifdef CONFIG_PLUGIN
s->plugin_tb = g_new0(struct qemu_plugin_tb, 1);
s->plugin_tb->insns =
g_ptr_array_new_with_free_func(qemu_plugin_insn_cleanup_fn);
#endif
}
/*
* All TCG threads except the parent (i.e. the one that called tcg_context_init
* and registered the target's TCG globals) must register with this function
* before initiating translation.
*
* In user-mode we just point tcg_ctx to tcg_init_ctx. See the documentation
* of tcg_region_init() for the reasoning behind this.
*
* In softmmu each caller registers its context in tcg_ctxs[]. Note that in
* softmmu tcg_ctxs[] does not track tcg_ctx_init, since the initial context
* is not used anymore for translation once this function is called.
*
* Not tracking tcg_init_ctx in tcg_ctxs[] in softmmu keeps code that iterates
* over the array (e.g. tcg_code_size() the same for both softmmu and user-mode.
*/
#ifdef CONFIG_USER_ONLY
void tcg_register_thread(void)
{
tcg_ctx = &tcg_init_ctx;
}
#else
void tcg_register_thread(void)
{
TCGContext *s = g_malloc(sizeof(*s));
unsigned int i, n;
*s = tcg_init_ctx;
/* Relink mem_base. */
for (i = 0, n = tcg_init_ctx.nb_globals; i < n; ++i) {
if (tcg_init_ctx.temps[i].mem_base) {
ptrdiff_t b = tcg_init_ctx.temps[i].mem_base - tcg_init_ctx.temps;
tcg_debug_assert(b >= 0 && b < n);
s->temps[i].mem_base = &s->temps[b];
}
}
/* Claim an entry in tcg_ctxs */
n = qatomic_fetch_inc(&tcg_cur_ctxs);
g_assert(n < tcg_max_ctxs);
qatomic_set(&tcg_ctxs[n], s);
if (n > 0) {
alloc_tcg_plugin_context(s);
tcg_region_initial_alloc(s);
}
tcg_ctx = s;
}
#endif /* !CONFIG_USER_ONLY */
/* pool based memory allocation */
void *tcg_malloc_internal(TCGContext *s, int size)
{
TCGPool *p;
int pool_size;
if (size > TCG_POOL_CHUNK_SIZE) {
/* big malloc: insert a new pool (XXX: could optimize) */
p = g_malloc(sizeof(TCGPool) + size);
p->size = size;
p->next = s->pool_first_large;
s->pool_first_large = p;
return p->data;
} else {
p = s->pool_current;
if (!p) {
p = s->pool_first;
if (!p)
goto new_pool;
} else {
if (!p->next) {
new_pool:
pool_size = TCG_POOL_CHUNK_SIZE;
p = g_malloc(sizeof(TCGPool) + pool_size);
p->size = pool_size;
p->next = NULL;
if (s->pool_current)
s->pool_current->next = p;
else
s->pool_first = p;
} else {
p = p->next;
}
}
}
s->pool_current = p;
s->pool_cur = p->data + size;
s->pool_end = p->data + p->size;
return p->data;
}
void tcg_pool_reset(TCGContext *s)
{
TCGPool *p, *t;
for (p = s->pool_first_large; p; p = t) {
t = p->next;
g_free(p);
}
s->pool_first_large = NULL;
s->pool_cur = s->pool_end = NULL;
s->pool_current = NULL;
}
#include "exec/helper-proto.h"
static const TCGHelperInfo all_helpers[] = {
#include "exec/helper-tcg.h"
};
static GHashTable *helper_table;
#ifdef CONFIG_TCG_INTERPRETER
static GHashTable *ffi_table;
static ffi_type * const typecode_to_ffi[8] = {
[dh_typecode_void] = &ffi_type_void,
[dh_typecode_i32] = &ffi_type_uint32,
[dh_typecode_s32] = &ffi_type_sint32,
[dh_typecode_i64] = &ffi_type_uint64,
[dh_typecode_s64] = &ffi_type_sint64,
[dh_typecode_ptr] = &ffi_type_pointer,
};
#endif
static int indirect_reg_alloc_order[ARRAY_SIZE(tcg_target_reg_alloc_order)];
static void process_op_defs(TCGContext *s);
static TCGTemp *tcg_global_reg_new_internal(TCGContext *s, TCGType type,
TCGReg reg, const char *name);
static void tcg_context_init(unsigned max_cpus)
{
TCGContext *s = &tcg_init_ctx;
int op, total_args, n, i;
TCGOpDef *def;
TCGArgConstraint *args_ct;
TCGTemp *ts;
memset(s, 0, sizeof(*s));
s->nb_globals = 0;
/* Count total number of arguments and allocate the corresponding
space */
total_args = 0;
for(op = 0; op < NB_OPS; op++) {
def = &tcg_op_defs[op];
n = def->nb_iargs + def->nb_oargs;
total_args += n;
}
args_ct = g_new0(TCGArgConstraint, total_args);
for(op = 0; op < NB_OPS; op++) {
def = &tcg_op_defs[op];
def->args_ct = args_ct;
n = def->nb_iargs + def->nb_oargs;
args_ct += n;
}
/* Register helpers. */
/* Use g_direct_hash/equal for direct pointer comparisons on func. */
helper_table = g_hash_table_new(NULL, NULL);
for (i = 0; i < ARRAY_SIZE(all_helpers); ++i) {
g_hash_table_insert(helper_table, (gpointer)all_helpers[i].func,
(gpointer)&all_helpers[i]);
}
#ifdef CONFIG_TCG_INTERPRETER
/* g_direct_hash/equal for direct comparisons on uint32_t. */
ffi_table = g_hash_table_new(NULL, NULL);
for (i = 0; i < ARRAY_SIZE(all_helpers); ++i) {
struct {
ffi_cif cif;
ffi_type *args[];
} *ca;
uint32_t typemask = all_helpers[i].typemask;
gpointer hash = (gpointer)(uintptr_t)typemask;
ffi_status status;
int nargs;
if (g_hash_table_lookup(ffi_table, hash)) {
continue;
}
/* Ignoring the return type, find the last non-zero field. */
nargs = 32 - clz32(typemask >> 3);
nargs = DIV_ROUND_UP(nargs, 3);
ca = g_malloc0(sizeof(*ca) + nargs * sizeof(ffi_type *));
ca->cif.rtype = typecode_to_ffi[typemask & 7];
ca->cif.nargs = nargs;
if (nargs != 0) {
ca->cif.arg_types = ca->args;
for (i = 0; i < nargs; ++i) {
int typecode = extract32(typemask, (i + 1) * 3, 3);
ca->args[i] = typecode_to_ffi[typecode];
}
}
status = ffi_prep_cif(&ca->cif, FFI_DEFAULT_ABI, nargs,
ca->cif.rtype, ca->cif.arg_types);
assert(status == FFI_OK);
g_hash_table_insert(ffi_table, hash, (gpointer)&ca->cif);
}
#endif
tcg_target_init(s);
process_op_defs(s);
/* Reverse the order of the saved registers, assuming they're all at
the start of tcg_target_reg_alloc_order. */
for (n = 0; n < ARRAY_SIZE(tcg_target_reg_alloc_order); ++n) {
int r = tcg_target_reg_alloc_order[n];
if (tcg_regset_test_reg(tcg_target_call_clobber_regs, r)) {
break;
}
}
for (i = 0; i < n; ++i) {
indirect_reg_alloc_order[i] = tcg_target_reg_alloc_order[n - 1 - i];
}
for (; i < ARRAY_SIZE(tcg_target_reg_alloc_order); ++i) {
indirect_reg_alloc_order[i] = tcg_target_reg_alloc_order[i];
}
alloc_tcg_plugin_context(s);
tcg_ctx = s;
/*
* In user-mode we simply share the init context among threads, since we
* use a single region. See the documentation tcg_region_init() for the
* reasoning behind this.
* In softmmu we will have at most max_cpus TCG threads.
*/
#ifdef CONFIG_USER_ONLY
tcg_ctxs = &tcg_ctx;
tcg_cur_ctxs = 1;
tcg_max_ctxs = 1;
#else
tcg_max_ctxs = max_cpus;
tcg_ctxs = g_new0(TCGContext *, max_cpus);
#endif
tcg_debug_assert(!tcg_regset_test_reg(s->reserved_regs, TCG_AREG0));
ts = tcg_global_reg_new_internal(s, TCG_TYPE_PTR, TCG_AREG0, "env");
cpu_env = temp_tcgv_ptr(ts);
}
void tcg_init(size_t tb_size, int splitwx, unsigned max_cpus)
{
tcg_context_init(max_cpus);
tcg_region_init(tb_size, splitwx, max_cpus);
}
/*
* Allocate TBs right before their corresponding translated code, making
* sure that TBs and code are on different cache lines.
*/
TranslationBlock *tcg_tb_alloc(TCGContext *s)
{
uintptr_t align = qemu_icache_linesize;
TranslationBlock *tb;
void *next;
retry:
tb = (void *)ROUND_UP((uintptr_t)s->code_gen_ptr, align);
next = (void *)ROUND_UP((uintptr_t)(tb + 1), align);
if (unlikely(next > s->code_gen_highwater)) {
if (tcg_region_alloc(s)) {
return NULL;
}
goto retry;
}
qatomic_set(&s->code_gen_ptr, next);
s->data_gen_ptr = NULL;
return tb;
}
void tcg_prologue_init(TCGContext *s)
{
size_t prologue_size;
s->code_ptr = s->code_gen_ptr;
s->code_buf = s->code_gen_ptr;
s->data_gen_ptr = NULL;
#ifndef CONFIG_TCG_INTERPRETER
tcg_qemu_tb_exec = (tcg_prologue_fn *)tcg_splitwx_to_rx(s->code_ptr);
#endif
#ifdef TCG_TARGET_NEED_POOL_LABELS
s->pool_labels = NULL;
#endif
qemu_thread_jit_write();
/* Generate the prologue. */
tcg_target_qemu_prologue(s);
#ifdef TCG_TARGET_NEED_POOL_LABELS
/* Allow the prologue to put e.g. guest_base into a pool entry. */
{
int result = tcg_out_pool_finalize(s);
tcg_debug_assert(result == 0);
}
#endif
prologue_size = tcg_current_code_size(s);
#ifndef CONFIG_TCG_INTERPRETER
flush_idcache_range((uintptr_t)tcg_splitwx_to_rx(s->code_buf),
(uintptr_t)s->code_buf, prologue_size);
#endif
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM)) {
FILE *logfile = qemu_log_lock();
qemu_log("PROLOGUE: [size=%zu]\n", prologue_size);
if (s->data_gen_ptr) {
size_t code_size = s->data_gen_ptr - s->code_gen_ptr;
size_t data_size = prologue_size - code_size;
size_t i;
log_disas(s->code_gen_ptr, code_size);
for (i = 0; i < data_size; i += sizeof(tcg_target_ulong)) {
if (sizeof(tcg_target_ulong) == 8) {
qemu_log("0x%08" PRIxPTR ": .quad 0x%016" PRIx64 "\n",
(uintptr_t)s->data_gen_ptr + i,
*(uint64_t *)(s->data_gen_ptr + i));
} else {
qemu_log("0x%08" PRIxPTR ": .long 0x%08x\n",
(uintptr_t)s->data_gen_ptr + i,
*(uint32_t *)(s->data_gen_ptr + i));
}
}
} else {
log_disas(s->code_gen_ptr, prologue_size);
}
qemu_log("\n");
qemu_log_flush();
qemu_log_unlock(logfile);
}
#endif
#ifndef CONFIG_TCG_INTERPRETER
/*
* Assert that goto_ptr is implemented completely, setting an epilogue.
* For tci, we use NULL as the signal to return from the interpreter,
* so skip this check.
*/
tcg_debug_assert(tcg_code_gen_epilogue != NULL);
#endif
tcg_region_prologue_set(s);
}
void tcg_func_start(TCGContext *s)
{
tcg_pool_reset(s);
s->nb_temps = s->nb_globals;
/* No temps have been previously allocated for size or locality. */
memset(s->free_temps, 0, sizeof(s->free_temps));
/* No constant temps have been previously allocated. */
for (int i = 0; i < TCG_TYPE_COUNT; ++i) {
if (s->const_table[i]) {
g_hash_table_remove_all(s->const_table[i]);
}
}
s->nb_ops = 0;
s->nb_labels = 0;
s->current_frame_offset = s->frame_start;
#ifdef CONFIG_DEBUG_TCG
s->goto_tb_issue_mask = 0;
#endif
QTAILQ_INIT(&s->ops);
QTAILQ_INIT(&s->free_ops);
QSIMPLEQ_INIT(&s->labels);
}
static TCGTemp *tcg_temp_alloc(TCGContext *s)
{
int n = s->nb_temps++;
if (n >= TCG_MAX_TEMPS) {
tcg_raise_tb_overflow(s);
}
return memset(&s->temps[n], 0, sizeof(TCGTemp));
}
static TCGTemp *tcg_global_alloc(TCGContext *s)
{
TCGTemp *ts;
tcg_debug_assert(s->nb_globals == s->nb_temps);
tcg_debug_assert(s->nb_globals < TCG_MAX_TEMPS);
s->nb_globals++;
ts = tcg_temp_alloc(s);
ts->kind = TEMP_GLOBAL;
return ts;
}
static TCGTemp *tcg_global_reg_new_internal(TCGContext *s, TCGType type,
TCGReg reg, const char *name)
{
TCGTemp *ts;
if (TCG_TARGET_REG_BITS == 32 && type != TCG_TYPE_I32) {
tcg_abort();
}
ts = tcg_global_alloc(s);
ts->base_type = type;
ts->type = type;
ts->kind = TEMP_FIXED;
ts->reg = reg;
ts->name = name;
tcg_regset_set_reg(s->reserved_regs, reg);
return ts;
}
void tcg_set_frame(TCGContext *s, TCGReg reg, intptr_t start, intptr_t size)
{
s->frame_start = start;
s->frame_end = start + size;
s->frame_temp
= tcg_global_reg_new_internal(s, TCG_TYPE_PTR, reg, "_frame");
}
TCGTemp *tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
intptr_t offset, const char *name)
{
TCGContext *s = tcg_ctx;
TCGTemp *base_ts = tcgv_ptr_temp(base);
TCGTemp *ts = tcg_global_alloc(s);
int indirect_reg = 0, bigendian = 0;
#ifdef HOST_WORDS_BIGENDIAN
bigendian = 1;
#endif
switch (base_ts->kind) {
case TEMP_FIXED:
break;
case TEMP_GLOBAL:
/* We do not support double-indirect registers. */
tcg_debug_assert(!base_ts->indirect_reg);
base_ts->indirect_base = 1;
s->nb_indirects += (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64
? 2 : 1);
indirect_reg = 1;
break;
default:
g_assert_not_reached();
}
if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
TCGTemp *ts2 = tcg_global_alloc(s);
char buf[64];
ts->base_type = TCG_TYPE_I64;
ts->type = TCG_TYPE_I32;
ts->indirect_reg = indirect_reg;
ts->mem_allocated = 1;
ts->mem_base = base_ts;
ts->mem_offset = offset + bigendian * 4;
pstrcpy(buf, sizeof(buf), name);
pstrcat(buf, sizeof(buf), "_0");
ts->name = strdup(buf);
tcg_debug_assert(ts2 == ts + 1);
ts2->base_type = TCG_TYPE_I64;
ts2->type = TCG_TYPE_I32;
ts2->indirect_reg = indirect_reg;
ts2->mem_allocated = 1;
ts2->mem_base = base_ts;
ts2->mem_offset = offset + (1 - bigendian) * 4;
pstrcpy(buf, sizeof(buf), name);
pstrcat(buf, sizeof(buf), "_1");
ts2->name = strdup(buf);
} else {
ts->base_type = type;
ts->type = type;
ts->indirect_reg = indirect_reg;
ts->mem_allocated = 1;
ts->mem_base = base_ts;
ts->mem_offset = offset;
ts->name = name;
}
return ts;
}
TCGTemp *tcg_temp_new_internal(TCGType type, bool temp_local)
{
TCGContext *s = tcg_ctx;
TCGTempKind kind = temp_local ? TEMP_LOCAL : TEMP_NORMAL;
TCGTemp *ts;
int idx, k;
k = type + (temp_local ? TCG_TYPE_COUNT : 0);
idx = find_first_bit(s->free_temps[k].l, TCG_MAX_TEMPS);
if (idx < TCG_MAX_TEMPS) {
/* There is already an available temp with the right type. */
clear_bit(idx, s->free_temps[k].l);
ts = &s->temps[idx];
ts->temp_allocated = 1;
tcg_debug_assert(ts->base_type == type);
tcg_debug_assert(ts->kind == kind);
} else {
ts = tcg_temp_alloc(s);
if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
TCGTemp *ts2 = tcg_temp_alloc(s);
ts->base_type = type;
ts->type = TCG_TYPE_I32;
ts->temp_allocated = 1;
ts->kind = kind;
tcg_debug_assert(ts2 == ts + 1);
ts2->base_type = TCG_TYPE_I64;
ts2->type = TCG_TYPE_I32;
ts2->temp_allocated = 1;
ts2->kind = kind;
} else {
ts->base_type = type;
ts->type = type;
ts->temp_allocated = 1;
ts->kind = kind;
}
}
#if defined(CONFIG_DEBUG_TCG)
s->temps_in_use++;
#endif
return ts;
}
TCGv_vec tcg_temp_new_vec(TCGType type)
{
TCGTemp *t;
#ifdef CONFIG_DEBUG_TCG
switch (type) {
case TCG_TYPE_V64:
assert(TCG_TARGET_HAS_v64);
break;
case TCG_TYPE_V128:
assert(TCG_TARGET_HAS_v128);
break;
case TCG_TYPE_V256:
assert(TCG_TARGET_HAS_v256);
break;