forked from panda-re/panda
-
Notifications
You must be signed in to change notification settings - Fork 0
/
translate.c
3033 lines (2772 loc) · 86.9 KB
/
translate.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
/*
* Alpha emulation cpu translation for qemu.
*
* Copyright (c) 2007 Jocelyn Mayer
*
* 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/>.
*/
#include "cpu.h"
#include "disas/disas.h"
#include "qemu/host-utils.h"
#include "tcg-op.h"
#include "exec/cpu_ldst.h"
#include "exec/helper-proto.h"
#include "exec/helper-gen.h"
#include "trace-tcg.h"
#undef ALPHA_DEBUG_DISAS
#define CONFIG_SOFTFLOAT_INLINE
#ifdef ALPHA_DEBUG_DISAS
# define LOG_DISAS(...) qemu_log_mask(CPU_LOG_TB_IN_ASM, ## __VA_ARGS__)
#else
# define LOG_DISAS(...) do { } while (0)
#endif
typedef struct DisasContext DisasContext;
struct DisasContext {
struct TranslationBlock *tb;
uint64_t pc;
#ifndef CONFIG_USER_ONLY
uint64_t palbr;
#endif
int mem_idx;
/* Current rounding mode for this TB. */
int tb_rm;
/* Current flush-to-zero setting for this TB. */
int tb_ftz;
/* implver value for this CPU. */
int implver;
/* The set of registers active in the current context. */
TCGv *ir;
/* Temporaries for $31 and $f31 as source and destination. */
TCGv zero;
TCGv sink;
/* Temporary for immediate constants. */
TCGv lit;
bool singlestep_enabled;
};
/* Return values from translate_one, indicating the state of the TB.
Note that zero indicates that we are not exiting the TB. */
typedef enum {
NO_EXIT,
/* We have emitted one or more goto_tb. No fixup required. */
EXIT_GOTO_TB,
/* We are not using a goto_tb (for whatever reason), but have updated
the PC (for whatever reason), so there's no need to do it again on
exiting the TB. */
EXIT_PC_UPDATED,
/* We are exiting the TB, but have neither emitted a goto_tb, nor
updated the PC for the next instruction to be executed. */
EXIT_PC_STALE,
/* We are ending the TB with a noreturn function call, e.g. longjmp.
No following code will be executed. */
EXIT_NORETURN,
} ExitStatus;
/* global register indexes */
static TCGv_ptr cpu_env;
static TCGv cpu_std_ir[31];
static TCGv cpu_fir[31];
static TCGv cpu_pc;
static TCGv cpu_lock_addr;
static TCGv cpu_lock_st_addr;
static TCGv cpu_lock_value;
#ifndef CONFIG_USER_ONLY
static TCGv cpu_pal_ir[31];
#endif
#include "exec/gen-icount.h"
void alpha_translate_init(void)
{
#define DEF_VAR(V) { &cpu_##V, #V, offsetof(CPUAlphaState, V) }
typedef struct { TCGv *var; const char *name; int ofs; } GlobalVar;
static const GlobalVar vars[] = {
DEF_VAR(pc),
DEF_VAR(lock_addr),
DEF_VAR(lock_st_addr),
DEF_VAR(lock_value),
};
#undef DEF_VAR
/* Use the symbolic register names that match the disassembler. */
static const char greg_names[31][4] = {
"v0", "t0", "t1", "t2", "t3", "t4", "t5", "t6",
"t7", "s0", "s1", "s2", "s3", "s4", "s5", "fp",
"a0", "a1", "a2", "a3", "a4", "a5", "t8", "t9",
"t10", "t11", "ra", "t12", "at", "gp", "sp"
};
static const char freg_names[31][4] = {
"f0", "f1", "f2", "f3", "f4", "f5", "f6", "f7",
"f8", "f9", "f10", "f11", "f12", "f13", "f14", "f15",
"f16", "f17", "f18", "f19", "f20", "f21", "f22", "f23",
"f24", "f25", "f26", "f27", "f28", "f29", "f30"
};
#ifndef CONFIG_USER_ONLY
static const char shadow_names[8][8] = {
"pal_t7", "pal_s0", "pal_s1", "pal_s2",
"pal_s3", "pal_s4", "pal_s5", "pal_t11"
};
#endif
static bool done_init = 0;
int i;
if (done_init) {
return;
}
done_init = 1;
cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");
for (i = 0; i < 31; i++) {
cpu_std_ir[i] = tcg_global_mem_new_i64(TCG_AREG0,
offsetof(CPUAlphaState, ir[i]),
greg_names[i]);
}
for (i = 0; i < 31; i++) {
cpu_fir[i] = tcg_global_mem_new_i64(TCG_AREG0,
offsetof(CPUAlphaState, fir[i]),
freg_names[i]);
}
#ifndef CONFIG_USER_ONLY
memcpy(cpu_pal_ir, cpu_std_ir, sizeof(cpu_pal_ir));
for (i = 0; i < 8; i++) {
int r = (i == 7 ? 25 : i + 8);
cpu_pal_ir[r] = tcg_global_mem_new_i64(TCG_AREG0,
offsetof(CPUAlphaState,
shadow[i]),
shadow_names[i]);
}
#endif
for (i = 0; i < ARRAY_SIZE(vars); ++i) {
const GlobalVar *v = &vars[i];
*v->var = tcg_global_mem_new_i64(TCG_AREG0, v->ofs, v->name);
}
}
static TCGv load_zero(DisasContext *ctx)
{
if (TCGV_IS_UNUSED_I64(ctx->zero)) {
ctx->zero = tcg_const_i64(0);
}
return ctx->zero;
}
static TCGv dest_sink(DisasContext *ctx)
{
if (TCGV_IS_UNUSED_I64(ctx->sink)) {
ctx->sink = tcg_temp_new();
}
return ctx->sink;
}
static TCGv load_gpr(DisasContext *ctx, unsigned reg)
{
if (likely(reg < 31)) {
return ctx->ir[reg];
} else {
return load_zero(ctx);
}
}
static TCGv load_gpr_lit(DisasContext *ctx, unsigned reg,
uint8_t lit, bool islit)
{
if (islit) {
ctx->lit = tcg_const_i64(lit);
return ctx->lit;
} else if (likely(reg < 31)) {
return ctx->ir[reg];
} else {
return load_zero(ctx);
}
}
static TCGv dest_gpr(DisasContext *ctx, unsigned reg)
{
if (likely(reg < 31)) {
return ctx->ir[reg];
} else {
return dest_sink(ctx);
}
}
static TCGv load_fpr(DisasContext *ctx, unsigned reg)
{
if (likely(reg < 31)) {
return cpu_fir[reg];
} else {
return load_zero(ctx);
}
}
static TCGv dest_fpr(DisasContext *ctx, unsigned reg)
{
if (likely(reg < 31)) {
return cpu_fir[reg];
} else {
return dest_sink(ctx);
}
}
static void gen_excp_1(int exception, int error_code)
{
TCGv_i32 tmp1, tmp2;
tmp1 = tcg_const_i32(exception);
tmp2 = tcg_const_i32(error_code);
gen_helper_excp(cpu_env, tmp1, tmp2);
tcg_temp_free_i32(tmp2);
tcg_temp_free_i32(tmp1);
}
static ExitStatus gen_excp(DisasContext *ctx, int exception, int error_code)
{
tcg_gen_movi_i64(cpu_pc, ctx->pc);
gen_excp_1(exception, error_code);
return EXIT_NORETURN;
}
static inline ExitStatus gen_invalid(DisasContext *ctx)
{
return gen_excp(ctx, EXCP_OPCDEC, 0);
}
static inline void gen_qemu_ldf(TCGv t0, TCGv t1, int flags)
{
TCGv_i32 tmp32 = tcg_temp_new_i32();
tcg_gen_qemu_ld_i32(tmp32, t1, flags, MO_LEUL);
gen_helper_memory_to_f(t0, tmp32);
tcg_temp_free_i32(tmp32);
}
static inline void gen_qemu_ldg(TCGv t0, TCGv t1, int flags)
{
TCGv tmp = tcg_temp_new();
tcg_gen_qemu_ld_i64(tmp, t1, flags, MO_LEQ);
gen_helper_memory_to_g(t0, tmp);
tcg_temp_free(tmp);
}
static inline void gen_qemu_lds(TCGv t0, TCGv t1, int flags)
{
TCGv_i32 tmp32 = tcg_temp_new_i32();
tcg_gen_qemu_ld_i32(tmp32, t1, flags, MO_LEUL);
gen_helper_memory_to_s(t0, tmp32);
tcg_temp_free_i32(tmp32);
}
static inline void gen_qemu_ldl_l(TCGv t0, TCGv t1, int flags)
{
tcg_gen_qemu_ld_i64(t0, t1, flags, MO_LESL);
tcg_gen_mov_i64(cpu_lock_addr, t1);
tcg_gen_mov_i64(cpu_lock_value, t0);
}
static inline void gen_qemu_ldq_l(TCGv t0, TCGv t1, int flags)
{
tcg_gen_qemu_ld_i64(t0, t1, flags, MO_LEQ);
tcg_gen_mov_i64(cpu_lock_addr, t1);
tcg_gen_mov_i64(cpu_lock_value, t0);
}
static inline void gen_load_mem(DisasContext *ctx,
void (*tcg_gen_qemu_load)(TCGv t0, TCGv t1,
int flags),
int ra, int rb, int32_t disp16, bool fp,
bool clear)
{
TCGv tmp, addr, va;
/* LDQ_U with ra $31 is UNOP. Other various loads are forms of
prefetches, which we can treat as nops. No worries about
missed exceptions here. */
if (unlikely(ra == 31)) {
return;
}
tmp = tcg_temp_new();
addr = load_gpr(ctx, rb);
if (disp16) {
tcg_gen_addi_i64(tmp, addr, disp16);
addr = tmp;
}
if (clear) {
tcg_gen_andi_i64(tmp, addr, ~0x7);
addr = tmp;
}
va = (fp ? cpu_fir[ra] : ctx->ir[ra]);
tcg_gen_qemu_load(va, addr, ctx->mem_idx);
tcg_temp_free(tmp);
}
static inline void gen_qemu_stf(TCGv t0, TCGv t1, int flags)
{
TCGv_i32 tmp32 = tcg_temp_new_i32();
gen_helper_f_to_memory(tmp32, t0);
tcg_gen_qemu_st_i32(tmp32, t1, flags, MO_LEUL);
tcg_temp_free_i32(tmp32);
}
static inline void gen_qemu_stg(TCGv t0, TCGv t1, int flags)
{
TCGv tmp = tcg_temp_new();
gen_helper_g_to_memory(tmp, t0);
tcg_gen_qemu_st_i64(tmp, t1, flags, MO_LEQ);
tcg_temp_free(tmp);
}
static inline void gen_qemu_sts(TCGv t0, TCGv t1, int flags)
{
TCGv_i32 tmp32 = tcg_temp_new_i32();
gen_helper_s_to_memory(tmp32, t0);
tcg_gen_qemu_st_i32(tmp32, t1, flags, MO_LEUL);
tcg_temp_free_i32(tmp32);
}
static inline void gen_store_mem(DisasContext *ctx,
void (*tcg_gen_qemu_store)(TCGv t0, TCGv t1,
int flags),
int ra, int rb, int32_t disp16, bool fp,
bool clear)
{
TCGv tmp, addr, va;
tmp = tcg_temp_new();
addr = load_gpr(ctx, rb);
if (disp16) {
tcg_gen_addi_i64(tmp, addr, disp16);
addr = tmp;
}
if (clear) {
tcg_gen_andi_i64(tmp, addr, ~0x7);
addr = tmp;
}
va = (fp ? load_fpr(ctx, ra) : load_gpr(ctx, ra));
tcg_gen_qemu_store(va, addr, ctx->mem_idx);
tcg_temp_free(tmp);
}
static ExitStatus gen_store_conditional(DisasContext *ctx, int ra, int rb,
int32_t disp16, int quad)
{
TCGv addr;
if (ra == 31) {
/* ??? Don't bother storing anything. The user can't tell
the difference, since the zero register always reads zero. */
return NO_EXIT;
}
#if defined(CONFIG_USER_ONLY)
addr = cpu_lock_st_addr;
#else
addr = tcg_temp_local_new();
#endif
tcg_gen_addi_i64(addr, load_gpr(ctx, rb), disp16);
#if defined(CONFIG_USER_ONLY)
/* ??? This is handled via a complicated version of compare-and-swap
in the cpu_loop. Hopefully one day we'll have a real CAS opcode
in TCG so that this isn't necessary. */
return gen_excp(ctx, quad ? EXCP_STQ_C : EXCP_STL_C, ra);
#else
/* ??? In system mode we are never multi-threaded, so CAS can be
implemented via a non-atomic load-compare-store sequence. */
{
TCGLabel *lab_fail, *lab_done;
TCGv val;
lab_fail = gen_new_label();
lab_done = gen_new_label();
tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_lock_addr, lab_fail);
val = tcg_temp_new();
tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, quad ? MO_LEQ : MO_LESL);
tcg_gen_brcond_i64(TCG_COND_NE, val, cpu_lock_value, lab_fail);
tcg_gen_qemu_st_i64(ctx->ir[ra], addr, ctx->mem_idx,
quad ? MO_LEQ : MO_LEUL);
tcg_gen_movi_i64(ctx->ir[ra], 1);
tcg_gen_br(lab_done);
gen_set_label(lab_fail);
tcg_gen_movi_i64(ctx->ir[ra], 0);
gen_set_label(lab_done);
tcg_gen_movi_i64(cpu_lock_addr, -1);
tcg_temp_free(addr);
return NO_EXIT;
}
#endif
}
static bool in_superpage(DisasContext *ctx, int64_t addr)
{
return ((ctx->tb->flags & TB_FLAGS_USER_MODE) == 0
&& addr < 0
&& ((addr >> 41) & 3) == 2
&& addr >> TARGET_VIRT_ADDR_SPACE_BITS == addr >> 63);
}
static bool use_goto_tb(DisasContext *ctx, uint64_t dest)
{
/* Suppress goto_tb in the case of single-steping and IO. */
if ((ctx->tb->cflags & CF_LAST_IO)
|| ctx->singlestep_enabled || singlestep) {
return false;
}
/* If the destination is in the superpage, the page perms can't change. */
if (in_superpage(ctx, dest)) {
return true;
}
/* Check for the dest on the same page as the start of the TB. */
return ((ctx->tb->pc ^ dest) & TARGET_PAGE_MASK) == 0;
}
static ExitStatus gen_bdirect(DisasContext *ctx, int ra, int32_t disp)
{
uint64_t dest = ctx->pc + (disp << 2);
if (ra != 31) {
tcg_gen_movi_i64(ctx->ir[ra], ctx->pc);
}
/* Notice branch-to-next; used to initialize RA with the PC. */
if (disp == 0) {
return 0;
} else if (use_goto_tb(ctx, dest)) {
tcg_gen_goto_tb(0);
tcg_gen_movi_i64(cpu_pc, dest);
tcg_gen_exit_tb((uintptr_t)ctx->tb);
return EXIT_GOTO_TB;
} else {
tcg_gen_movi_i64(cpu_pc, dest);
return EXIT_PC_UPDATED;
}
}
static ExitStatus gen_bcond_internal(DisasContext *ctx, TCGCond cond,
TCGv cmp, int32_t disp)
{
uint64_t dest = ctx->pc + (disp << 2);
TCGLabel *lab_true = gen_new_label();
if (use_goto_tb(ctx, dest)) {
tcg_gen_brcondi_i64(cond, cmp, 0, lab_true);
tcg_gen_goto_tb(0);
tcg_gen_movi_i64(cpu_pc, ctx->pc);
tcg_gen_exit_tb((uintptr_t)ctx->tb);
gen_set_label(lab_true);
tcg_gen_goto_tb(1);
tcg_gen_movi_i64(cpu_pc, dest);
tcg_gen_exit_tb((uintptr_t)ctx->tb + 1);
return EXIT_GOTO_TB;
} else {
TCGv_i64 z = tcg_const_i64(0);
TCGv_i64 d = tcg_const_i64(dest);
TCGv_i64 p = tcg_const_i64(ctx->pc);
tcg_gen_movcond_i64(cond, cpu_pc, cmp, z, d, p);
tcg_temp_free_i64(z);
tcg_temp_free_i64(d);
tcg_temp_free_i64(p);
return EXIT_PC_UPDATED;
}
}
static ExitStatus gen_bcond(DisasContext *ctx, TCGCond cond, int ra,
int32_t disp, int mask)
{
TCGv cmp_tmp;
if (mask) {
cmp_tmp = tcg_temp_new();
tcg_gen_andi_i64(cmp_tmp, load_gpr(ctx, ra), 1);
} else {
cmp_tmp = load_gpr(ctx, ra);
}
return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
}
/* Fold -0.0 for comparison with COND. */
static void gen_fold_mzero(TCGCond cond, TCGv dest, TCGv src)
{
uint64_t mzero = 1ull << 63;
switch (cond) {
case TCG_COND_LE:
case TCG_COND_GT:
/* For <= or >, the -0.0 value directly compares the way we want. */
tcg_gen_mov_i64(dest, src);
break;
case TCG_COND_EQ:
case TCG_COND_NE:
/* For == or !=, we can simply mask off the sign bit and compare. */
tcg_gen_andi_i64(dest, src, mzero - 1);
break;
case TCG_COND_GE:
case TCG_COND_LT:
/* For >= or <, map -0.0 to +0.0 via comparison and mask. */
tcg_gen_setcondi_i64(TCG_COND_NE, dest, src, mzero);
tcg_gen_neg_i64(dest, dest);
tcg_gen_and_i64(dest, dest, src);
break;
default:
abort();
}
}
static ExitStatus gen_fbcond(DisasContext *ctx, TCGCond cond, int ra,
int32_t disp)
{
TCGv cmp_tmp = tcg_temp_new();
gen_fold_mzero(cond, cmp_tmp, load_fpr(ctx, ra));
return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
}
static void gen_fcmov(DisasContext *ctx, TCGCond cond, int ra, int rb, int rc)
{
TCGv_i64 va, vb, z;
z = load_zero(ctx);
vb = load_fpr(ctx, rb);
va = tcg_temp_new();
gen_fold_mzero(cond, va, load_fpr(ctx, ra));
tcg_gen_movcond_i64(cond, dest_fpr(ctx, rc), va, z, vb, load_fpr(ctx, rc));
tcg_temp_free(va);
}
#define QUAL_RM_N 0x080 /* Round mode nearest even */
#define QUAL_RM_C 0x000 /* Round mode chopped */
#define QUAL_RM_M 0x040 /* Round mode minus infinity */
#define QUAL_RM_D 0x0c0 /* Round mode dynamic */
#define QUAL_RM_MASK 0x0c0
#define QUAL_U 0x100 /* Underflow enable (fp output) */
#define QUAL_V 0x100 /* Overflow enable (int output) */
#define QUAL_S 0x400 /* Software completion enable */
#define QUAL_I 0x200 /* Inexact detection enable */
static void gen_qual_roundmode(DisasContext *ctx, int fn11)
{
TCGv_i32 tmp;
fn11 &= QUAL_RM_MASK;
if (fn11 == ctx->tb_rm) {
return;
}
ctx->tb_rm = fn11;
tmp = tcg_temp_new_i32();
switch (fn11) {
case QUAL_RM_N:
tcg_gen_movi_i32(tmp, float_round_nearest_even);
break;
case QUAL_RM_C:
tcg_gen_movi_i32(tmp, float_round_to_zero);
break;
case QUAL_RM_M:
tcg_gen_movi_i32(tmp, float_round_down);
break;
case QUAL_RM_D:
tcg_gen_ld8u_i32(tmp, cpu_env,
offsetof(CPUAlphaState, fpcr_dyn_round));
break;
}
#if defined(CONFIG_SOFTFLOAT_INLINE)
/* ??? The "fpu/softfloat.h" interface is to call set_float_rounding_mode.
With CONFIG_SOFTFLOAT that expands to an out-of-line call that just
sets the one field. */
tcg_gen_st8_i32(tmp, cpu_env,
offsetof(CPUAlphaState, fp_status.float_rounding_mode));
#else
gen_helper_setroundmode(tmp);
#endif
tcg_temp_free_i32(tmp);
}
static void gen_qual_flushzero(DisasContext *ctx, int fn11)
{
TCGv_i32 tmp;
fn11 &= QUAL_U;
if (fn11 == ctx->tb_ftz) {
return;
}
ctx->tb_ftz = fn11;
tmp = tcg_temp_new_i32();
if (fn11) {
/* Underflow is enabled, use the FPCR setting. */
tcg_gen_ld8u_i32(tmp, cpu_env,
offsetof(CPUAlphaState, fpcr_flush_to_zero));
} else {
/* Underflow is disabled, force flush-to-zero. */
tcg_gen_movi_i32(tmp, 1);
}
#if defined(CONFIG_SOFTFLOAT_INLINE)
tcg_gen_st8_i32(tmp, cpu_env,
offsetof(CPUAlphaState, fp_status.flush_to_zero));
#else
gen_helper_setflushzero(tmp);
#endif
tcg_temp_free_i32(tmp);
}
static TCGv gen_ieee_input(DisasContext *ctx, int reg, int fn11, int is_cmp)
{
TCGv val;
if (unlikely(reg == 31)) {
val = load_zero(ctx);
} else {
val = cpu_fir[reg];
if ((fn11 & QUAL_S) == 0) {
if (is_cmp) {
gen_helper_ieee_input_cmp(cpu_env, val);
} else {
gen_helper_ieee_input(cpu_env, val);
}
} else {
#ifndef CONFIG_USER_ONLY
/* In system mode, raise exceptions for denormals like real
hardware. In user mode, proceed as if the OS completion
handler is handling the denormal as per spec. */
gen_helper_ieee_input_s(cpu_env, val);
#endif
}
}
return val;
}
static void gen_fp_exc_raise(int rc, int fn11)
{
/* ??? We ought to be able to do something with imprecise exceptions.
E.g. notice we're still in the trap shadow of something within the
TB and do not generate the code to signal the exception; end the TB
when an exception is forced to arrive, either by consumption of a
register value or TRAPB or EXCB. */
TCGv_i32 reg, ign;
uint32_t ignore = 0;
if (!(fn11 & QUAL_U)) {
/* Note that QUAL_U == QUAL_V, so ignore either. */
ignore |= FPCR_UNF | FPCR_IOV;
}
if (!(fn11 & QUAL_I)) {
ignore |= FPCR_INE;
}
ign = tcg_const_i32(ignore);
/* ??? Pass in the regno of the destination so that the helper can
set EXC_MASK, which contains a bitmask of destination registers
that have caused arithmetic traps. A simple userspace emulation
does not require this. We do need it for a guest kernel's entArith,
or if we were to do something clever with imprecise exceptions. */
reg = tcg_const_i32(rc + 32);
if (fn11 & QUAL_S) {
gen_helper_fp_exc_raise_s(cpu_env, ign, reg);
} else {
gen_helper_fp_exc_raise(cpu_env, ign, reg);
}
tcg_temp_free_i32(reg);
tcg_temp_free_i32(ign);
}
static void gen_cvtlq(TCGv vc, TCGv vb)
{
TCGv tmp = tcg_temp_new();
/* The arithmetic right shift here, plus the sign-extended mask below
yields a sign-extended result without an explicit ext32s_i64. */
tcg_gen_sari_i64(tmp, vb, 32);
tcg_gen_shri_i64(vc, vb, 29);
tcg_gen_andi_i64(tmp, tmp, (int32_t)0xc0000000);
tcg_gen_andi_i64(vc, vc, 0x3fffffff);
tcg_gen_or_i64(vc, vc, tmp);
tcg_temp_free(tmp);
}
static void gen_ieee_arith2(DisasContext *ctx,
void (*helper)(TCGv, TCGv_ptr, TCGv),
int rb, int rc, int fn11)
{
TCGv vb;
gen_qual_roundmode(ctx, fn11);
gen_qual_flushzero(ctx, fn11);
vb = gen_ieee_input(ctx, rb, fn11, 0);
helper(dest_fpr(ctx, rc), cpu_env, vb);
gen_fp_exc_raise(rc, fn11);
}
#define IEEE_ARITH2(name) \
static inline void glue(gen_, name)(DisasContext *ctx, \
int rb, int rc, int fn11) \
{ \
gen_ieee_arith2(ctx, gen_helper_##name, rb, rc, fn11); \
}
IEEE_ARITH2(sqrts)
IEEE_ARITH2(sqrtt)
IEEE_ARITH2(cvtst)
IEEE_ARITH2(cvtts)
static void gen_cvttq(DisasContext *ctx, int rb, int rc, int fn11)
{
TCGv vb, vc;
/* No need to set flushzero, since we have an integer output. */
vb = gen_ieee_input(ctx, rb, fn11, 0);
vc = dest_fpr(ctx, rc);
/* Almost all integer conversions use cropped rounding;
special case that. */
if ((fn11 & QUAL_RM_MASK) == QUAL_RM_C) {
gen_helper_cvttq_c(vc, cpu_env, vb);
} else {
gen_qual_roundmode(ctx, fn11);
gen_helper_cvttq(vc, cpu_env, vb);
}
gen_fp_exc_raise(rc, fn11);
}
static void gen_ieee_intcvt(DisasContext *ctx,
void (*helper)(TCGv, TCGv_ptr, TCGv),
int rb, int rc, int fn11)
{
TCGv vb, vc;
gen_qual_roundmode(ctx, fn11);
vb = load_fpr(ctx, rb);
vc = dest_fpr(ctx, rc);
/* The only exception that can be raised by integer conversion
is inexact. Thus we only need to worry about exceptions when
inexact handling is requested. */
if (fn11 & QUAL_I) {
helper(vc, cpu_env, vb);
gen_fp_exc_raise(rc, fn11);
} else {
helper(vc, cpu_env, vb);
}
}
#define IEEE_INTCVT(name) \
static inline void glue(gen_, name)(DisasContext *ctx, \
int rb, int rc, int fn11) \
{ \
gen_ieee_intcvt(ctx, gen_helper_##name, rb, rc, fn11); \
}
IEEE_INTCVT(cvtqs)
IEEE_INTCVT(cvtqt)
static void gen_cpy_mask(TCGv vc, TCGv va, TCGv vb, bool inv_a, uint64_t mask)
{
TCGv vmask = tcg_const_i64(mask);
TCGv tmp = tcg_temp_new_i64();
if (inv_a) {
tcg_gen_andc_i64(tmp, vmask, va);
} else {
tcg_gen_and_i64(tmp, va, vmask);
}
tcg_gen_andc_i64(vc, vb, vmask);
tcg_gen_or_i64(vc, vc, tmp);
tcg_temp_free(vmask);
tcg_temp_free(tmp);
}
static void gen_ieee_arith3(DisasContext *ctx,
void (*helper)(TCGv, TCGv_ptr, TCGv, TCGv),
int ra, int rb, int rc, int fn11)
{
TCGv va, vb, vc;
gen_qual_roundmode(ctx, fn11);
gen_qual_flushzero(ctx, fn11);
va = gen_ieee_input(ctx, ra, fn11, 0);
vb = gen_ieee_input(ctx, rb, fn11, 0);
vc = dest_fpr(ctx, rc);
helper(vc, cpu_env, va, vb);
gen_fp_exc_raise(rc, fn11);
}
#define IEEE_ARITH3(name) \
static inline void glue(gen_, name)(DisasContext *ctx, \
int ra, int rb, int rc, int fn11) \
{ \
gen_ieee_arith3(ctx, gen_helper_##name, ra, rb, rc, fn11); \
}
IEEE_ARITH3(adds)
IEEE_ARITH3(subs)
IEEE_ARITH3(muls)
IEEE_ARITH3(divs)
IEEE_ARITH3(addt)
IEEE_ARITH3(subt)
IEEE_ARITH3(mult)
IEEE_ARITH3(divt)
static void gen_ieee_compare(DisasContext *ctx,
void (*helper)(TCGv, TCGv_ptr, TCGv, TCGv),
int ra, int rb, int rc, int fn11)
{
TCGv va, vb, vc;
va = gen_ieee_input(ctx, ra, fn11, 1);
vb = gen_ieee_input(ctx, rb, fn11, 1);
vc = dest_fpr(ctx, rc);
helper(vc, cpu_env, va, vb);
gen_fp_exc_raise(rc, fn11);
}
#define IEEE_CMP3(name) \
static inline void glue(gen_, name)(DisasContext *ctx, \
int ra, int rb, int rc, int fn11) \
{ \
gen_ieee_compare(ctx, gen_helper_##name, ra, rb, rc, fn11); \
}
IEEE_CMP3(cmptun)
IEEE_CMP3(cmpteq)
IEEE_CMP3(cmptlt)
IEEE_CMP3(cmptle)
static inline uint64_t zapnot_mask(uint8_t lit)
{
uint64_t mask = 0;
int i;
for (i = 0; i < 8; ++i) {
if ((lit >> i) & 1) {
mask |= 0xffull << (i * 8);
}
}
return mask;
}
/* Implement zapnot with an immediate operand, which expands to some
form of immediate AND. This is a basic building block in the
definition of many of the other byte manipulation instructions. */
static void gen_zapnoti(TCGv dest, TCGv src, uint8_t lit)
{
switch (lit) {
case 0x00:
tcg_gen_movi_i64(dest, 0);
break;
case 0x01:
tcg_gen_ext8u_i64(dest, src);
break;
case 0x03:
tcg_gen_ext16u_i64(dest, src);
break;
case 0x0f:
tcg_gen_ext32u_i64(dest, src);
break;
case 0xff:
tcg_gen_mov_i64(dest, src);
break;
default:
tcg_gen_andi_i64(dest, src, zapnot_mask(lit));
break;
}
}
/* EXTWH, EXTLH, EXTQH */
static void gen_ext_h(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
if (islit) {
tcg_gen_shli_i64(vc, va, (64 - lit * 8) & 0x3f);
} else {
TCGv tmp = tcg_temp_new();
tcg_gen_shli_i64(tmp, load_gpr(ctx, rb), 3);
tcg_gen_neg_i64(tmp, tmp);
tcg_gen_andi_i64(tmp, tmp, 0x3f);
tcg_gen_shl_i64(vc, va, tmp);
tcg_temp_free(tmp);
}
gen_zapnoti(vc, vc, byte_mask);
}
/* EXTBL, EXTWL, EXTLL, EXTQL */
static void gen_ext_l(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
if (islit) {
tcg_gen_shri_i64(vc, va, (lit & 7) * 8);
} else {
TCGv tmp = tcg_temp_new();
tcg_gen_andi_i64(tmp, load_gpr(ctx, rb), 7);
tcg_gen_shli_i64(tmp, tmp, 3);
tcg_gen_shr_i64(vc, va, tmp);
tcg_temp_free(tmp);
}
gen_zapnoti(vc, vc, byte_mask);
}
/* INSWH, INSLH, INSQH */
static void gen_ins_h(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
TCGv tmp = tcg_temp_new();
/* The instruction description has us left-shift the byte mask and extract
bits <15:8> and apply that zap at the end. This is equivalent to simply
performing the zap first and shifting afterward. */
gen_zapnoti(tmp, va, byte_mask);
if (islit) {
lit &= 7;
if (unlikely(lit == 0)) {
tcg_gen_movi_i64(vc, 0);
} else {
tcg_gen_shri_i64(vc, tmp, 64 - lit * 8);
}
} else {
TCGv shift = tcg_temp_new();
/* If (B & 7) == 0, we need to shift by 64 and leave a zero. Do this
portably by splitting the shift into two parts: shift_count-1 and 1.
Arrange for the -1 by using ones-complement instead of
twos-complement in the negation: ~(B * 8) & 63. */
tcg_gen_shli_i64(shift, load_gpr(ctx, rb), 3);
tcg_gen_not_i64(shift, shift);