aboutsummaryrefslogtreecommitdiff
path: root/tcg/aarch64/tcg-target.c
blob: b5f19ad493f68cf5e160588b60f376b58ed125d3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
/*
 * Initial TCG Implementation for aarch64
 *
 * Copyright (c) 2013 Huawei Technologies Duesseldorf GmbH
 * Written by Claudio Fontana
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or
 * (at your option) any later version.
 *
 * See the COPYING file in the top-level directory for details.
 */

#include "tcg-be-ldst.h"
#include "qemu/bitops.h"

/* We're going to re-use TCGType in setting of the SF bit, which controls
   the size of the operation performed.  If we know the values match, it
   makes things much cleaner.  */
QEMU_BUILD_BUG_ON(TCG_TYPE_I32 != 0 || TCG_TYPE_I64 != 1);

#ifndef NDEBUG
static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
    "%x0", "%x1", "%x2", "%x3", "%x4", "%x5", "%x6", "%x7",
    "%x8", "%x9", "%x10", "%x11", "%x12", "%x13", "%x14", "%x15",
    "%x16", "%x17", "%x18", "%x19", "%x20", "%x21", "%x22", "%x23",
    "%x24", "%x25", "%x26", "%x27", "%x28",
    "%fp", /* frame pointer */
    "%lr", /* link register */
    "%sp",  /* stack pointer */
};
#endif /* NDEBUG */

#ifdef TARGET_WORDS_BIGENDIAN
 #define TCG_LDST_BSWAP 1
#else
 #define TCG_LDST_BSWAP 0
#endif

static const int tcg_target_reg_alloc_order[] = {
    TCG_REG_X20, TCG_REG_X21, TCG_REG_X22, TCG_REG_X23,
    TCG_REG_X24, TCG_REG_X25, TCG_REG_X26, TCG_REG_X27,
    TCG_REG_X28, /* we will reserve this for GUEST_BASE if configured */

    TCG_REG_X9, TCG_REG_X10, TCG_REG_X11, TCG_REG_X12,
    TCG_REG_X13, TCG_REG_X14, TCG_REG_X15,
    TCG_REG_X16, TCG_REG_X17,

    TCG_REG_X18, TCG_REG_X19, /* will not use these, see tcg_target_init */

    TCG_REG_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7,

    TCG_REG_X8, /* will not use, see tcg_target_init */
};

static const int tcg_target_call_iarg_regs[8] = {
    TCG_REG_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7
};
static const int tcg_target_call_oarg_regs[1] = {
    TCG_REG_X0
};

#define TCG_REG_TMP TCG_REG_X8

#ifndef CONFIG_SOFTMMU
# if defined(CONFIG_USE_GUEST_BASE)
# define TCG_REG_GUEST_BASE TCG_REG_X28
# else
# define TCG_REG_GUEST_BASE TCG_REG_XZR
# endif
#endif

static inline void reloc_pc26(void *code_ptr, intptr_t target)
{
    intptr_t offset = (target - (intptr_t)code_ptr) / 4;
    /* read instruction, mask away previous PC_REL26 parameter contents,
       set the proper offset, then write back the instruction. */
    uint32_t insn = *(uint32_t *)code_ptr;
    insn = deposit32(insn, 0, 26, offset);
    *(uint32_t *)code_ptr = insn;
}

static inline void reloc_pc19(void *code_ptr, intptr_t target)
{
    intptr_t offset = (target - (intptr_t)code_ptr) / 4;
    /* read instruction, mask away previous PC_REL19 parameter contents,
       set the proper offset, then write back the instruction. */
    uint32_t insn = *(uint32_t *)code_ptr;
    insn = deposit32(insn, 5, 19, offset);
    *(uint32_t *)code_ptr = insn;
}

static inline void patch_reloc(uint8_t *code_ptr, int type,
                               intptr_t value, intptr_t addend)
{
    value += addend;

    switch (type) {
    case R_AARCH64_JUMP26:
    case R_AARCH64_CALL26:
        reloc_pc26(code_ptr, value);
        break;
    case R_AARCH64_CONDBR19:
        reloc_pc19(code_ptr, value);
        break;

    default:
        tcg_abort();
    }
}

/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct,
                                   const char **pct_str)
{
    const char *ct_str = *pct_str;

    switch (ct_str[0]) {
    case 'r':
        ct->ct |= TCG_CT_REG;
        tcg_regset_set32(ct->u.regs, 0, (1ULL << TCG_TARGET_NB_REGS) - 1);
        break;
    case 'l': /* qemu_ld / qemu_st address, data_reg */
        ct->ct |= TCG_CT_REG;
        tcg_regset_set32(ct->u.regs, 0, (1ULL << TCG_TARGET_NB_REGS) - 1);
#ifdef CONFIG_SOFTMMU
        /* x0 and x1 will be overwritten when reading the tlb entry,
           and x2, and x3 for helper args, better to avoid using them. */
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X0);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X1);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X2);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X3);
#endif
        break;
    default:
        return -1;
    }

    ct_str++;
    *pct_str = ct_str;
    return 0;
}

static inline int tcg_target_const_match(tcg_target_long val,
                                         const TCGArgConstraint *arg_ct)
{
    int ct = arg_ct->ct;

    if (ct & TCG_CT_CONST) {
        return 1;
    }

    return 0;
}

enum aarch64_cond_code {
    COND_EQ = 0x0,
    COND_NE = 0x1,
    COND_CS = 0x2,     /* Unsigned greater or equal */
    COND_HS = COND_CS, /* ALIAS greater or equal */
    COND_CC = 0x3,     /* Unsigned less than */
    COND_LO = COND_CC, /* ALIAS Lower */
    COND_MI = 0x4,     /* Negative */
    COND_PL = 0x5,     /* Zero or greater */
    COND_VS = 0x6,     /* Overflow */
    COND_VC = 0x7,     /* No overflow */
    COND_HI = 0x8,     /* Unsigned greater than */
    COND_LS = 0x9,     /* Unsigned less or equal */
    COND_GE = 0xa,
    COND_LT = 0xb,
    COND_GT = 0xc,
    COND_LE = 0xd,
    COND_AL = 0xe,
    COND_NV = 0xf, /* behaves like COND_AL here */
};

static const enum aarch64_cond_code tcg_cond_to_aarch64[] = {
    [TCG_COND_EQ] = COND_EQ,
    [TCG_COND_NE] = COND_NE,
    [TCG_COND_LT] = COND_LT,
    [TCG_COND_GE] = COND_GE,
    [TCG_COND_LE] = COND_LE,
    [TCG_COND_GT] = COND_GT,
    /* unsigned */
    [TCG_COND_LTU] = COND_LO,
    [TCG_COND_GTU] = COND_HI,
    [TCG_COND_GEU] = COND_HS,
    [TCG_COND_LEU] = COND_LS,
};

/* opcodes for LDR / STR instructions with base + simm9 addressing */
enum aarch64_ldst_op_data { /* size of the data moved */
    LDST_8 = 0x38,
    LDST_16 = 0x78,
    LDST_32 = 0xb8,
    LDST_64 = 0xf8,
};
enum aarch64_ldst_op_type { /* type of operation */
    LDST_ST = 0x0,    /* store */
    LDST_LD = 0x4,    /* load */
    LDST_LD_S_X = 0x8,  /* load and sign-extend into Xt */
    LDST_LD_S_W = 0xc,  /* load and sign-extend into Wt */
};

/* We encode the format of the insn into the beginning of the name, so that
   we can have the preprocessor help "typecheck" the insn vs the output
   function.  Arm didn't provide us with nice names for the formats, so we
   use the section number of the architecture reference manual in which the
   instruction group is described.  */
typedef enum {
    /* Add/subtract immediate instructions.  */
    I3401_ADDI      = 0x11000000,
    I3401_ADDSI     = 0x31000000,
    I3401_SUBI      = 0x51000000,
    I3401_SUBSI     = 0x71000000,

    /* Add/subtract shifted register instructions (without a shift).  */
    I3502_ADD       = 0x0b000000,
    I3502_ADDS      = 0x2b000000,
    I3502_SUB       = 0x4b000000,
    I3502_SUBS      = 0x6b000000,

    /* Add/subtract shifted register instructions (with a shift).  */
    I3502S_ADD_LSL  = I3502_ADD,

    /* Data-processing (2 source) instructions.  */
    I3508_LSLV      = 0x1ac02000,
    I3508_LSRV      = 0x1ac02400,
    I3508_ASRV      = 0x1ac02800,
    I3508_RORV      = 0x1ac02c00,

    /* Logical shifted register instructions (without a shift).  */
    I3510_AND       = 0x0a000000,
    I3510_ORR       = 0x2a000000,
    I3510_EOR       = 0x4a000000,
    I3510_ANDS      = 0x6a000000,
} AArch64Insn;

static inline enum aarch64_ldst_op_data
aarch64_ldst_get_data(TCGOpcode tcg_op)
{
    switch (tcg_op) {
    case INDEX_op_ld8u_i32:
    case INDEX_op_ld8s_i32:
    case INDEX_op_ld8u_i64:
    case INDEX_op_ld8s_i64:
    case INDEX_op_st8_i32:
    case INDEX_op_st8_i64:
        return LDST_8;

    case INDEX_op_ld16u_i32:
    case INDEX_op_ld16s_i32:
    case INDEX_op_ld16u_i64:
    case INDEX_op_ld16s_i64:
    case INDEX_op_st16_i32:
    case INDEX_op_st16_i64:
        return LDST_16;

    case INDEX_op_ld_i32:
    case INDEX_op_st_i32:
    case INDEX_op_ld32u_i64:
    case INDEX_op_ld32s_i64:
    case INDEX_op_st32_i64:
        return LDST_32;

    case INDEX_op_ld_i64:
    case INDEX_op_st_i64:
        return LDST_64;

    default:
        tcg_abort();
    }
}

static inline enum aarch64_ldst_op_type
aarch64_ldst_get_type(TCGOpcode tcg_op)
{
    switch (tcg_op) {
    case INDEX_op_st8_i32:
    case INDEX_op_st16_i32:
    case INDEX_op_st8_i64:
    case INDEX_op_st16_i64:
    case INDEX_op_st_i32:
    case INDEX_op_st32_i64:
    case INDEX_op_st_i64:
        return LDST_ST;

    case INDEX_op_ld8u_i32:
    case INDEX_op_ld16u_i32:
    case INDEX_op_ld8u_i64:
    case INDEX_op_ld16u_i64:
    case INDEX_op_ld_i32:
    case INDEX_op_ld32u_i64:
    case INDEX_op_ld_i64:
        return LDST_LD;

    case INDEX_op_ld8s_i32:
    case INDEX_op_ld16s_i32:
        return LDST_LD_S_W;

    case INDEX_op_ld8s_i64:
    case INDEX_op_ld16s_i64:
    case INDEX_op_ld32s_i64:
        return LDST_LD_S_X;

    default:
        tcg_abort();
    }
}

static inline uint32_t tcg_in32(TCGContext *s)
{
    uint32_t v = *(uint32_t *)s->code_ptr;
    return v;
}

/* Emit an opcode with "type-checking" of the format.  */
#define tcg_out_insn(S, FMT, OP, ...) \
    glue(tcg_out_insn_,FMT)(S, glue(glue(glue(I,FMT),_),OP), ## __VA_ARGS__)

static void tcg_out_insn_3401(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, uint64_t aimm)
{
    if (aimm > 0xfff) {
        assert((aimm & 0xfff) == 0);
        aimm >>= 12;
        assert(aimm <= 0xfff);
        aimm |= 1 << 12;  /* apply LSL 12 */
    }
    tcg_out32(s, insn | ext << 31 | aimm << 10 | rn << 5 | rd);
}

/* This function is for both 3.5.2 (Add/Subtract shifted register), for
   the rare occasion when we actually want to supply a shift amount.  */
static inline void tcg_out_insn_3502S(TCGContext *s, AArch64Insn insn,
                                      TCGType ext, TCGReg rd, TCGReg rn,
                                      TCGReg rm, int imm6)
{
    tcg_out32(s, insn | ext << 31 | rm << 16 | imm6 << 10 | rn << 5 | rd);
}

/* This function is for 3.5.2 (Add/subtract shifted register),
   and 3.5.10 (Logical shifted register), for the vast majorty of cases
   when we don't want to apply a shift.  Thus it can also be used for
   3.5.3 (Add/subtract with carry) and 3.5.8 (Data processing 2 source).  */
static void tcg_out_insn_3502(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, TCGReg rm)
{
    tcg_out32(s, insn | ext << 31 | rm << 16 | rn << 5 | rd);
}

#define tcg_out_insn_3503  tcg_out_insn_3502
#define tcg_out_insn_3508  tcg_out_insn_3502
#define tcg_out_insn_3510  tcg_out_insn_3502


static inline void tcg_out_ldst_9(TCGContext *s,
                                  enum aarch64_ldst_op_data op_data,
                                  enum aarch64_ldst_op_type op_type,
                                  TCGReg rd, TCGReg rn, tcg_target_long offset)
{
    /* use LDUR with BASE register with 9bit signed unscaled offset */
    tcg_out32(s, op_data << 24 | op_type << 20
              | (offset & 0x1ff) << 12 | rn << 5 | rd);
}

/* tcg_out_ldst_12 expects a scaled unsigned immediate offset */
static inline void tcg_out_ldst_12(TCGContext *s,
                                   enum aarch64_ldst_op_data op_data,
                                   enum aarch64_ldst_op_type op_type,
                                   TCGReg rd, TCGReg rn,
                                   tcg_target_ulong scaled_uimm)
{
    tcg_out32(s, (op_data | 1) << 24
              | op_type << 20 | scaled_uimm << 10 | rn << 5 | rd);
}

static inline void tcg_out_movr(TCGContext *s, TCGType ext,
                                TCGReg rd, TCGReg src)
{
    /* register to register move using MOV (shifted register with no shift) */
    /* using MOV 0x2a0003e0 | (shift).. */
    unsigned int base = ext ? 0xaa0003e0 : 0x2a0003e0;
    tcg_out32(s, base | src << 16 | rd);
}

static inline void tcg_out_movi_aux(TCGContext *s,
                                    TCGReg rd, uint64_t value)
{
    uint32_t half, base, shift, movk = 0;
    /* construct halfwords of the immediate with MOVZ/MOVK with LSL */
    /* using MOVZ 0x52800000 | extended reg.. */
    base = (value > 0xffffffff) ? 0xd2800000 : 0x52800000;
    /* count trailing zeros in 16 bit steps, mapping 64 to 0. Emit the
       first MOVZ with the half-word immediate skipping the zeros, with a shift
       (LSL) equal to this number. Then morph all next instructions into MOVKs.
       Zero the processed half-word in the value, continue until empty.
       We build the final result 16bits at a time with up to 4 instructions,
       but do not emit instructions for 16bit zero holes. */
    do {
        shift = ctz64(value) & (63 & -16);
        half = (value >> shift) & 0xffff;
        tcg_out32(s, base | movk | shift << 17 | half << 5 | rd);
        movk = 0x20000000; /* morph next MOVZs into MOVKs */
        value &= ~(0xffffUL << shift);
    } while (value);
}

static inline void tcg_out_movi(TCGContext *s, TCGType type,
                                TCGReg rd, tcg_target_long value)
{
    if (type == TCG_TYPE_I64) {
        tcg_out_movi_aux(s, rd, value);
    } else {
        tcg_out_movi_aux(s, rd, value & 0xffffffff);
    }
}

static inline void tcg_out_ldst_r(TCGContext *s,
                                  enum aarch64_ldst_op_data op_data,
                                  enum aarch64_ldst_op_type op_type,
                                  TCGReg rd, TCGReg base, TCGReg regoff)
{
    /* load from memory to register using base + 64bit register offset */
    /* using f.e. STR Wt, [Xn, Xm] 0xb8600800|(regoff << 16)|(base << 5)|rd */
    /* the 0x6000 is for the "no extend field" */
    tcg_out32(s, 0x00206800
              | op_data << 24 | op_type << 20 | regoff << 16 | base << 5 | rd);
}

/* solve the whole ldst problem */
static inline void tcg_out_ldst(TCGContext *s, enum aarch64_ldst_op_data data,
                                enum aarch64_ldst_op_type type,
                                TCGReg rd, TCGReg rn, tcg_target_long offset)
{
    if (offset >= -256 && offset < 256) {
        tcg_out_ldst_9(s, data, type, rd, rn, offset);
        return;
    }

    if (offset >= 256) {
        /* if the offset is naturally aligned and in range,
           then we can use the scaled uimm12 encoding */
        unsigned int s_bits = data >> 6;
        if (!(offset & ((1 << s_bits) - 1))) {
            tcg_target_ulong scaled_uimm = offset >> s_bits;
            if (scaled_uimm <= 0xfff) {
                tcg_out_ldst_12(s, data, type, rd, rn, scaled_uimm);
                return;
            }
        }
    }

    /* worst-case scenario, move offset to temp register, use reg offset */
    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, offset);
    tcg_out_ldst_r(s, data, type, rd, rn, TCG_REG_TMP);
}

/* mov alias implemented with add immediate, useful to move to/from SP */
static inline void tcg_out_movr_sp(TCGContext *s, TCGType ext,
                                   TCGReg rd, TCGReg rn)
{
    /* using ADD 0x11000000 | (ext) | rn << 5 | rd */
    unsigned int base = ext ? 0x91000000 : 0x11000000;
    tcg_out32(s, base | rn << 5 | rd);
}

static inline void tcg_out_mov(TCGContext *s,
                               TCGType type, TCGReg ret, TCGReg arg)
{
    if (ret != arg) {
        tcg_out_movr(s, type == TCG_TYPE_I64, ret, arg);
    }
}

static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
                              TCGReg arg1, intptr_t arg2)
{
    tcg_out_ldst(s, (type == TCG_TYPE_I64) ? LDST_64 : LDST_32, LDST_LD,
                 arg, arg1, arg2);
}

static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
                              TCGReg arg1, intptr_t arg2)
{
    tcg_out_ldst(s, (type == TCG_TYPE_I64) ? LDST_64 : LDST_32, LDST_ST,
                 arg, arg1, arg2);
}

static inline void tcg_out_mul(TCGContext *s, TCGType ext,
                               TCGReg rd, TCGReg rn, TCGReg rm)
{
    /* Using MADD 0x1b000000 with Ra = wzr alias MUL 0x1b007c00 */
    unsigned int base = ext ? 0x9b007c00 : 0x1b007c00;
    tcg_out32(s, base | rm << 16 | rn << 5 | rd);
}

static inline void tcg_out_ubfm(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, unsigned int a, unsigned int b)
{
    /* Using UBFM 0x53000000 Wd, Wn, a, b */
    unsigned int base = ext ? 0xd3400000 : 0x53000000;
    tcg_out32(s, base | a << 16 | b << 10 | rn << 5 | rd);
}

static inline void tcg_out_sbfm(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, unsigned int a, unsigned int b)
{
    /* Using SBFM 0x13000000 Wd, Wn, a, b */
    unsigned int base = ext ? 0x93400000 : 0x13000000;
    tcg_out32(s, base | a << 16 | b << 10 | rn << 5 | rd);
}

static inline void tcg_out_extr(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, TCGReg rm, unsigned int a)
{
    /* Using EXTR 0x13800000 Wd, Wn, Wm, a */
    unsigned int base = ext ? 0x93c00000 : 0x13800000;
    tcg_out32(s, base | rm << 16 | a << 10 | rn << 5 | rd);
}

static inline void tcg_out_shl(TCGContext *s, TCGType ext,
                               TCGReg rd, TCGReg rn, unsigned int m)
{
    int bits, max;
    bits = ext ? 64 : 32;
    max = bits - 1;
    tcg_out_ubfm(s, ext, rd, rn, bits - (m & max), max - (m & max));
}

static inline void tcg_out_shr(TCGContext *s, TCGType ext,
                               TCGReg rd, TCGReg rn, unsigned int m)
{
    int max = ext ? 63 : 31;
    tcg_out_ubfm(s, ext, rd, rn, m & max, max);
}

static inline void tcg_out_sar(TCGContext *s, TCGType ext,
                               TCGReg rd, TCGReg rn, unsigned int m)
{
    int max = ext ? 63 : 31;
    tcg_out_sbfm(s, ext, rd, rn, m & max, max);
}

static inline void tcg_out_rotr(TCGContext *s, TCGType ext,
                                TCGReg rd, TCGReg rn, unsigned int m)
{
    int max = ext ? 63 : 31;
    tcg_out_extr(s, ext, rd, rn, rn, m & max);
}

static inline void tcg_out_rotl(TCGContext *s, TCGType ext,
                                TCGReg rd, TCGReg rn, unsigned int m)
{
    int bits, max;
    bits = ext ? 64 : 32;
    max = bits - 1;
    tcg_out_extr(s, ext, rd, rn, rn, bits - (m & max));
}

static void tcg_out_cmp(TCGContext *s, TCGType ext, TCGReg rn, TCGReg rm)
{
    /* Using CMP alias SUBS wzr, Wn, Wm */
    tcg_out_insn(s, 3502, SUBS, ext, TCG_REG_XZR, rn, rm);
}

static inline void tcg_out_cset(TCGContext *s, TCGType ext,
                                TCGReg rd, TCGCond c)
{
    /* Using CSET alias of CSINC 0x1a800400 Xd, XZR, XZR, invert(cond) */
    unsigned int base = ext ? 0x9a9f07e0 : 0x1a9f07e0;
    tcg_out32(s, base | tcg_cond_to_aarch64[tcg_invert_cond(c)] << 12 | rd);
}

static inline void tcg_out_goto(TCGContext *s, intptr_t target)
{
    intptr_t offset = (target - (intptr_t)s->code_ptr) / 4;

    if (offset < -0x02000000 || offset >= 0x02000000) {
        /* out of 26bit range */
        tcg_abort();
    }

    tcg_out32(s, 0x14000000 | (offset & 0x03ffffff));
}

static inline void tcg_out_goto_noaddr(TCGContext *s)
{
    /* We pay attention here to not modify the branch target by
       reading from the buffer. This ensure that caches and memory are
       kept coherent during retranslation.
       Mask away possible garbage in the high bits for the first translation,
       while keeping the offset bits for retranslation. */
    uint32_t insn;
    insn = (tcg_in32(s) & 0x03ffffff) | 0x14000000;
    tcg_out32(s, insn);
}

static inline void tcg_out_goto_cond_noaddr(TCGContext *s, TCGCond c)
{
    /* see comments in tcg_out_goto_noaddr */
    uint32_t insn;
    insn = tcg_in32(s) & (0x07ffff << 5);
    insn |= 0x54000000 | tcg_cond_to_aarch64[c];
    tcg_out32(s, insn);
}

static inline void tcg_out_goto_cond(TCGContext *s, TCGCond c, intptr_t target)
{
    intptr_t offset = (target - (intptr_t)s->code_ptr) / 4;

    if (offset < -0x40000 || offset >= 0x40000) {
        /* out of 19bit range */
        tcg_abort();
    }

    offset &= 0x7ffff;
    tcg_out32(s, 0x54000000 | tcg_cond_to_aarch64[c] | offset << 5);
}

static inline void tcg_out_callr(TCGContext *s, TCGReg reg)
{
    tcg_out32(s, 0xd63f0000 | reg << 5);
}

static inline void tcg_out_gotor(TCGContext *s, TCGReg reg)
{
    tcg_out32(s, 0xd61f0000 | reg << 5);
}

static inline void tcg_out_call(TCGContext *s, intptr_t target)
{
    intptr_t offset = (target - (intptr_t)s->code_ptr) / 4;

    if (offset < -0x02000000 || offset >= 0x02000000) { /* out of 26bit rng */
        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, target);
        tcg_out_callr(s, TCG_REG_TMP);
    } else {
        tcg_out32(s, 0x94000000 | (offset & 0x03ffffff));
    }
}

/* encode a logical immediate, mapping user parameter
   M=set bits pattern length to S=M-1 */
static inline unsigned int
aarch64_limm(unsigned int m, unsigned int r)
{
    assert(m > 0);
    return r << 16 | (m - 1) << 10;
}

/* test a register against an immediate bit pattern made of
   M set bits rotated right by R.
   Examples:
   to test a 32/64 reg against 0x00000007, pass M = 3,  R = 0.
   to test a 32/64 reg against 0x000000ff, pass M = 8,  R = 0.
   to test a 32bit reg against 0xff000000, pass M = 8,  R = 8.
   to test a 32bit reg against 0xff0000ff, pass M = 16, R = 8.
 */
static inline void tcg_out_tst(TCGContext *s, TCGType ext, TCGReg rn,
                               unsigned int m, unsigned int r)
{
    /* using TST alias of ANDS XZR, Xn,#bimm64 0x7200001f */
    unsigned int base = ext ? 0xf240001f : 0x7200001f;
    tcg_out32(s, base | aarch64_limm(m, r) | rn << 5);
}

/* and a register with a bit pattern, similarly to TST, no flags change */
static inline void tcg_out_andi(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, unsigned int m, unsigned int r)
{
    /* using AND 0x12000000 */
    unsigned int base = ext ? 0x92400000 : 0x12000000;
    tcg_out32(s, base | aarch64_limm(m, r) | rn << 5 | rd);
}

static inline void tcg_out_ret(TCGContext *s)
{
    /* emit RET { LR } */
    tcg_out32(s, 0xd65f03c0);
}

void aarch64_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr)
{
    intptr_t target = addr;
    intptr_t offset = (target - (intptr_t)jmp_addr) / 4;

    if (offset < -0x02000000 || offset >= 0x02000000) {
        /* out of 26bit range */
        tcg_abort();
    }

    patch_reloc((uint8_t *)jmp_addr, R_AARCH64_JUMP26, target, 0);
    flush_icache_range(jmp_addr, jmp_addr + 4);
}

static inline void tcg_out_goto_label(TCGContext *s, int label_index)
{
    TCGLabel *l = &s->labels[label_index];

    if (!l->has_value) {
        tcg_out_reloc(s, s->code_ptr, R_AARCH64_JUMP26, label_index, 0);
        tcg_out_goto_noaddr(s);
    } else {
        tcg_out_goto(s, l->u.value);
    }
}

static inline void tcg_out_goto_label_cond(TCGContext *s,
                                           TCGCond c, int label_index)
{
    TCGLabel *l = &s->labels[label_index];

    if (!l->has_value) {
        tcg_out_reloc(s, s->code_ptr, R_AARCH64_CONDBR19, label_index, 0);
        tcg_out_goto_cond_noaddr(s, c);
    } else {
        tcg_out_goto_cond(s, c, l->u.value);
    }
}

static inline void tcg_out_rev(TCGContext *s, TCGType ext,
                               TCGReg rd, TCGReg rm)
{
    /* using REV 0x5ac00800 */
    unsigned int base = ext ? 0xdac00c00 : 0x5ac00800;
    tcg_out32(s, base | rm << 5 | rd);
}

static inline void tcg_out_rev16(TCGContext *s, TCGType ext,
                                 TCGReg rd, TCGReg rm)
{
    /* using REV16 0x5ac00400 */
    unsigned int base = ext ? 0xdac00400 : 0x5ac00400;
    tcg_out32(s, base | rm << 5 | rd);
}

static inline void tcg_out_sxt(TCGContext *s, TCGType ext, int s_bits,
                               TCGReg rd, TCGReg rn)
{
    /* using ALIASes SXTB 0x13001c00, SXTH 0x13003c00, SXTW 0x93407c00
       of SBFM Xd, Xn, #0, #7|15|31 */
    int bits = 8 * (1 << s_bits) - 1;
    tcg_out_sbfm(s, ext, rd, rn, 0, bits);
}

static inline void tcg_out_uxt(TCGContext *s, int s_bits,
                               TCGReg rd, TCGReg rn)
{
    /* using ALIASes UXTB 0x53001c00, UXTH 0x53003c00
       of UBFM Wd, Wn, #0, #7|15 */
    int bits = 8 * (1 << s_bits) - 1;
    tcg_out_ubfm(s, 0, rd, rn, 0, bits);
}

#ifdef CONFIG_SOFTMMU
/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
 *                                     int mmu_idx, uintptr_t ra)
 */
static const void * const qemu_ld_helpers[4] = {
    helper_ret_ldub_mmu,
    helper_ret_lduw_mmu,
    helper_ret_ldul_mmu,
    helper_ret_ldq_mmu,
};

/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
 *                                     uintxx_t val, int mmu_idx, uintptr_t ra)
 */
static const void * const qemu_st_helpers[4] = {
    helper_ret_stb_mmu,
    helper_ret_stw_mmu,
    helper_ret_stl_mmu,
    helper_ret_stq_mmu,
};

static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    reloc_pc19(lb->label_ptr[0], (intptr_t)s->code_ptr);

    tcg_out_movr(s, 1, TCG_REG_X0, TCG_AREG0);
    tcg_out_movr(s, (TARGET_LONG_BITS == 64), TCG_REG_X1, lb->addrlo_reg);
    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X2, lb->mem_index);
    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_X3, (tcg_target_long)lb->raddr);
    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP,
                 (tcg_target_long)qemu_ld_helpers[lb->opc & 3]);
    tcg_out_callr(s, TCG_REG_TMP);
    if (lb->opc & 0x04) {
        tcg_out_sxt(s, 1, lb->opc & 3, lb->datalo_reg, TCG_REG_X0);
    } else {
        tcg_out_movr(s, 1, lb->datalo_reg, TCG_REG_X0);
    }

    tcg_out_goto(s, (intptr_t)lb->raddr);
}

static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    reloc_pc19(lb->label_ptr[0], (intptr_t)s->code_ptr);

    tcg_out_movr(s, 1, TCG_REG_X0, TCG_AREG0);
    tcg_out_movr(s, (TARGET_LONG_BITS == 64), TCG_REG_X1, lb->addrlo_reg);
    tcg_out_movr(s, 1, TCG_REG_X2, lb->datalo_reg);
    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X3, lb->mem_index);
    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_X4, (intptr_t)lb->raddr);
    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP,
                 (intptr_t)qemu_st_helpers[lb->opc & 3]);
    tcg_out_callr(s, TCG_REG_TMP);
    tcg_out_goto(s, (tcg_target_long)lb->raddr);
}

static void add_qemu_ldst_label(TCGContext *s, int is_ld, int opc,
                                TCGReg data_reg, TCGReg addr_reg,
                                int mem_index,
                                uint8_t *raddr, uint8_t *label_ptr)
{
    TCGLabelQemuLdst *label = new_ldst_label(s);

    label->is_ld = is_ld;
    label->opc = opc;
    label->datalo_reg = data_reg;
    label->addrlo_reg = addr_reg;
    label->mem_index = mem_index;
    label->raddr = raddr;
    label->label_ptr[0] = label_ptr;
}

/* Load and compare a TLB entry, emitting the conditional jump to the
   slow path for the failure case, which will be patched later when finalizing
   the slow path. Generated code returns the host addend in X1,
   clobbers X0,X2,X3,TMP. */
static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg,
            int s_bits, uint8_t **label_ptr, int mem_index, int is_read)
{
    TCGReg base = TCG_AREG0;
    int tlb_offset = is_read ?
        offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
        : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write);
    /* Extract the TLB index from the address into X0.
       X0<CPU_TLB_BITS:0> =
       addr_reg<TARGET_PAGE_BITS+CPU_TLB_BITS:TARGET_PAGE_BITS> */
    tcg_out_ubfm(s, (TARGET_LONG_BITS == 64), TCG_REG_X0, addr_reg,
                 TARGET_PAGE_BITS, TARGET_PAGE_BITS + CPU_TLB_BITS);
    /* Store the page mask part of the address and the low s_bits into X3.
       Later this allows checking for equality and alignment at the same time.
       X3 = addr_reg & (PAGE_MASK | ((1 << s_bits) - 1)) */
    tcg_out_andi(s, (TARGET_LONG_BITS == 64), TCG_REG_X3, addr_reg,
                 (TARGET_LONG_BITS - TARGET_PAGE_BITS) + s_bits,
                 (TARGET_LONG_BITS - TARGET_PAGE_BITS));
    /* Add any "high bits" from the tlb offset to the env address into X2,
       to take advantage of the LSL12 form of the ADDI instruction.
       X2 = env + (tlb_offset & 0xfff000) */
    tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_X2, base,
                 tlb_offset & 0xfff000);
    /* Merge the tlb index contribution into X2.
       X2 = X2 + (X0 << CPU_TLB_ENTRY_BITS) */
    tcg_out_insn(s, 3502S, ADD_LSL, 1, TCG_REG_X2, TCG_REG_X2,
                 TCG_REG_X0, CPU_TLB_ENTRY_BITS);
    /* Merge "low bits" from tlb offset, load the tlb comparator into X0.
       X0 = load [X2 + (tlb_offset & 0x000fff)] */
    tcg_out_ldst(s, TARGET_LONG_BITS == 64 ? LDST_64 : LDST_32,
                 LDST_LD, TCG_REG_X0, TCG_REG_X2,
                 (tlb_offset & 0xfff));
    /* Load the tlb addend. Do that early to avoid stalling.
       X1 = load [X2 + (tlb_offset & 0xfff) + offsetof(addend)] */
    tcg_out_ldst(s, LDST_64, LDST_LD, TCG_REG_X1, TCG_REG_X2,
                 (tlb_offset & 0xfff) + (offsetof(CPUTLBEntry, addend)) -
                 (is_read ? offsetof(CPUTLBEntry, addr_read)
                  : offsetof(CPUTLBEntry, addr_write)));
    /* Perform the address comparison. */
    tcg_out_cmp(s, (TARGET_LONG_BITS == 64), TCG_REG_X0, TCG_REG_X3);
    *label_ptr = s->code_ptr;
    /* If not equal, we jump to the slow path. */
    tcg_out_goto_cond_noaddr(s, TCG_COND_NE);
}

#endif /* CONFIG_SOFTMMU */

static void tcg_out_qemu_ld_direct(TCGContext *s, int opc, TCGReg data_r,
                                   TCGReg addr_r, TCGReg off_r)
{
    switch (opc) {
    case 0:
        tcg_out_ldst_r(s, LDST_8, LDST_LD, data_r, addr_r, off_r);
        break;
    case 0 | 4:
        tcg_out_ldst_r(s, LDST_8, LDST_LD_S_X, data_r, addr_r, off_r);
        break;
    case 1:
        tcg_out_ldst_r(s, LDST_16, LDST_LD, data_r, addr_r, off_r);
        if (TCG_LDST_BSWAP) {
            tcg_out_rev16(s, 0, data_r, data_r);
        }
        break;
    case 1 | 4:
        if (TCG_LDST_BSWAP) {
            tcg_out_ldst_r(s, LDST_16, LDST_LD, data_r, addr_r, off_r);
            tcg_out_rev16(s, 0, data_r, data_r);
            tcg_out_sxt(s, 1, 1, data_r, data_r);
        } else {
            tcg_out_ldst_r(s, LDST_16, LDST_LD_S_X, data_r, addr_r, off_r);
        }
        break;
    case 2:
        tcg_out_ldst_r(s, LDST_32, LDST_LD, data_r, addr_r, off_r);
        if (TCG_LDST_BSWAP) {
            tcg_out_rev(s, 0, data_r, data_r);
        }
        break;
    case 2 | 4:
        if (TCG_LDST_BSWAP) {
            tcg_out_ldst_r(s, LDST_32, LDST_LD, data_r, addr_r, off_r);
            tcg_out_rev(s, 0, data_r, data_r);
            tcg_out_sxt(s, 1, 2, data_r, data_r);
        } else {
            tcg_out_ldst_r(s, LDST_32, LDST_LD_S_X, data_r, addr_r, off_r);
        }
        break;
    case 3:
        tcg_out_ldst_r(s, LDST_64, LDST_LD, data_r, addr_r, off_r);
        if (TCG_LDST_BSWAP) {
            tcg_out_rev(s, 1, data_r, data_r);
        }
        break;
    default:
        tcg_abort();
    }
}

static void tcg_out_qemu_st_direct(TCGContext *s, int opc, TCGReg data_r,
                                   TCGReg addr_r, TCGReg off_r)
{
    switch (opc) {
    case 0:
        tcg_out_ldst_r(s, LDST_8, LDST_ST, data_r, addr_r, off_r);
        break;
    case 1:
        if (TCG_LDST_BSWAP) {
            tcg_out_rev16(s, 0, TCG_REG_TMP, data_r);
            tcg_out_ldst_r(s, LDST_16, LDST_ST, TCG_REG_TMP, addr_r, off_r);
        } else {
            tcg_out_ldst_r(s, LDST_16, LDST_ST, data_r, addr_r, off_r);
        }
        break;
    case 2:
        if (TCG_LDST_BSWAP) {
            tcg_out_rev(s, 0, TCG_REG_TMP, data_r);
            tcg_out_ldst_r(s, LDST_32, LDST_ST, TCG_REG_TMP, addr_r, off_r);
        } else {
            tcg_out_ldst_r(s, LDST_32, LDST_ST, data_r, addr_r, off_r);
        }
        break;
    case 3:
        if (TCG_LDST_BSWAP) {
            tcg_out_rev(s, 1, TCG_REG_TMP, data_r);
            tcg_out_ldst_r(s, LDST_64, LDST_ST, TCG_REG_TMP, addr_r, off_r);
        } else {
            tcg_out_ldst_r(s, LDST_64, LDST_ST, data_r, addr_r, off_r);
        }
        break;
    default:
        tcg_abort();
    }
}

static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, int opc)
{
    TCGReg addr_reg, data_reg;
#ifdef CONFIG_SOFTMMU
    int mem_index, s_bits;
    uint8_t *label_ptr;
#endif
    data_reg = args[0];
    addr_reg = args[1];

#ifdef CONFIG_SOFTMMU
    mem_index = args[2];
    s_bits = opc & 3;
    tcg_out_tlb_read(s, addr_reg, s_bits, &label_ptr, mem_index, 1);
    tcg_out_qemu_ld_direct(s, opc, data_reg, addr_reg, TCG_REG_X1);
    add_qemu_ldst_label(s, 1, opc, data_reg, addr_reg,
                        mem_index, s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    tcg_out_qemu_ld_direct(s, opc, data_reg, addr_reg,
                           GUEST_BASE ? TCG_REG_GUEST_BASE : TCG_REG_XZR);
#endif /* CONFIG_SOFTMMU */
}

static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, int opc)
{
    TCGReg addr_reg, data_reg;
#ifdef CONFIG_SOFTMMU
    int mem_index, s_bits;
    uint8_t *label_ptr;
#endif
    data_reg = args[0];
    addr_reg = args[1];

#ifdef CONFIG_SOFTMMU
    mem_index = args[2];
    s_bits = opc & 3;

    tcg_out_tlb_read(s, addr_reg, s_bits, &label_ptr, mem_index, 0);
    tcg_out_qemu_st_direct(s, opc, data_reg, addr_reg, TCG_REG_X1);
    add_qemu_ldst_label(s, 0, opc, data_reg, addr_reg,
                        mem_index, s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    tcg_out_qemu_st_direct(s, opc, data_reg, addr_reg,
                           GUEST_BASE ? TCG_REG_GUEST_BASE : TCG_REG_XZR);
#endif /* CONFIG_SOFTMMU */
}

static uint8_t *tb_ret_addr;

/* callee stack use example:
   stp     x29, x30, [sp,#-32]!
   mov     x29, sp
   stp     x1, x2, [sp,#16]
   ...
   ldp     x1, x2, [sp,#16]
   ldp     x29, x30, [sp],#32
   ret
*/

/* push r1 and r2, and alloc stack space for a total of
   alloc_n elements (1 element=16 bytes, must be between 1 and 31. */
static inline void tcg_out_push_pair(TCGContext *s, TCGReg addr,
                                     TCGReg r1, TCGReg r2, int alloc_n)
{
    /* using indexed scaled simm7 STP 0x28800000 | (ext) | 0x01000000 (pre-idx)
       | alloc_n * (-1) << 16 | r2 << 10 | addr << 5 | r1 */
    assert(alloc_n > 0 && alloc_n < 0x20);
    alloc_n = (-alloc_n) & 0x3f;
    tcg_out32(s, 0xa9800000 | alloc_n << 16 | r2 << 10 | addr << 5 | r1);
}

/* dealloc stack space for a total of alloc_n elements and pop r1, r2.  */
static inline void tcg_out_pop_pair(TCGContext *s, TCGReg addr,
                                    TCGReg r1, TCGReg r2, int alloc_n)
{
    /* using indexed scaled simm7 LDP 0x28c00000 | (ext) | nothing (post-idx)
       | alloc_n << 16 | r2 << 10 | addr << 5 | r1 */
    assert(alloc_n > 0 && alloc_n < 0x20);
    tcg_out32(s, 0xa8c00000 | alloc_n << 16 | r2 << 10 | addr << 5 | r1);
}

static inline void tcg_out_store_pair(TCGContext *s, TCGReg addr,
                                      TCGReg r1, TCGReg r2, int idx)
{
    /* using register pair offset simm7 STP 0x29000000 | (ext)
       | idx << 16 | r2 << 10 | addr << 5 | r1 */
    assert(idx > 0 && idx < 0x20);
    tcg_out32(s, 0xa9000000 | idx << 16 | r2 << 10 | addr << 5 | r1);
}

static inline void tcg_out_load_pair(TCGContext *s, TCGReg addr,
                                     TCGReg r1, TCGReg r2, int idx)
{
    /* using register pair offset simm7 LDP 0x29400000 | (ext)
       | idx << 16 | r2 << 10 | addr << 5 | r1 */
    assert(idx > 0 && idx < 0x20);
    tcg_out32(s, 0xa9400000 | idx << 16 | r2 << 10 | addr << 5 | r1);
}

static void tcg_out_op(TCGContext *s, TCGOpcode opc,
                       const TCGArg args[TCG_MAX_OP_ARGS],
                       const int const_args[TCG_MAX_OP_ARGS])
{
    /* 99% of the time, we can signal the use of extension registers
       by looking to see if the opcode handles 64-bit data.  */
    TCGType ext = (tcg_op_defs[opc].flags & TCG_OPF_64BIT) != 0;

    /* Hoist the loads of the most common arguments.  */
    TCGArg a0 = args[0];
    TCGArg a1 = args[1];
    TCGArg a2 = args[2];
    int c2 = const_args[2];

    switch (opc) {
    case INDEX_op_exit_tb:
        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
        tcg_out_goto(s, (intptr_t)tb_ret_addr);
        break;

    case INDEX_op_goto_tb:
#ifndef USE_DIRECT_JUMP
#error "USE_DIRECT_JUMP required for aarch64"
#endif
        assert(s->tb_jmp_offset != NULL); /* consistency for USE_DIRECT_JUMP */
        s->tb_jmp_offset[a0] = s->code_ptr - s->code_buf;
        /* actual branch destination will be patched by
           aarch64_tb_set_jmp_target later, beware retranslation. */
        tcg_out_goto_noaddr(s);
        s->tb_next_offset[a0] = s->code_ptr - s->code_buf;
        break;

    case INDEX_op_call:
        if (const_args[0]) {
            tcg_out_call(s, a0);
        } else {
            tcg_out_callr(s, a0);
        }
        break;

    case INDEX_op_br:
        tcg_out_goto_label(s, a0);
        break;

    case INDEX_op_ld_i32:
    case INDEX_op_ld_i64:
    case INDEX_op_st_i32:
    case INDEX_op_st_i64:
    case INDEX_op_ld8u_i32:
    case INDEX_op_ld8s_i32:
    case INDEX_op_ld16u_i32:
    case INDEX_op_ld16s_i32:
    case INDEX_op_ld8u_i64:
    case INDEX_op_ld8s_i64:
    case INDEX_op_ld16u_i64:
    case INDEX_op_ld16s_i64:
    case INDEX_op_ld32u_i64:
    case INDEX_op_ld32s_i64:
    case INDEX_op_st8_i32:
    case INDEX_op_st8_i64:
    case INDEX_op_st16_i32:
    case INDEX_op_st16_i64:
    case INDEX_op_st32_i64:
        tcg_out_ldst(s, aarch64_ldst_get_data(opc), aarch64_ldst_get_type(opc),
                     a0, a1, a2);
        break;

    case INDEX_op_add_i64:
    case INDEX_op_add_i32:
        tcg_out_insn(s, 3502, ADD, ext, a0, a1, a2);
        break;

    case INDEX_op_sub_i64:
    case INDEX_op_sub_i32:
        tcg_out_insn(s, 3502, SUB, ext, a0, a1, a2);
        break;

    case INDEX_op_and_i64:
    case INDEX_op_and_i32:
        tcg_out_insn(s, 3510, AND, ext, a0, a1, a2);
        break;

    case INDEX_op_or_i64:
    case INDEX_op_or_i32:
        tcg_out_insn(s, 3510, ORR, ext, a0, a1, a2);
        break;

    case INDEX_op_xor_i64:
    case INDEX_op_xor_i32:
        tcg_out_insn(s, 3510, EOR, ext, a0, a1, a2);
        break;

    case INDEX_op_mul_i64:
    case INDEX_op_mul_i32:
        tcg_out_mul(s, ext, a0, a1, a2);
        break;

    case INDEX_op_shl_i64:
    case INDEX_op_shl_i32:
        if (c2) {
            tcg_out_shl(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3508, LSLV, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_shr_i64:
    case INDEX_op_shr_i32:
        if (c2) {
            tcg_out_shr(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3508, LSRV, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_sar_i64:
    case INDEX_op_sar_i32:
        if (c2) {
            tcg_out_sar(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3508, ASRV, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_rotr_i64:
    case INDEX_op_rotr_i32:
        if (c2) {
            tcg_out_rotr(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3508, RORV, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_rotl_i64:
    case INDEX_op_rotl_i32:
        if (c2) {
            tcg_out_rotl(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3502, SUB, 0, TCG_REG_TMP, TCG_REG_XZR, a2);
            tcg_out_insn(s, 3508, RORV, ext, a0, a1, TCG_REG_TMP);
        }
        break;

    case INDEX_op_brcond_i64:
    case INDEX_op_brcond_i32:
        tcg_out_cmp(s, ext, a0, a1);
        tcg_out_goto_label_cond(s, a2, args[3]);
        break;

    case INDEX_op_setcond_i64:
    case INDEX_op_setcond_i32:
        tcg_out_cmp(s, ext, a1, a2);
        tcg_out_cset(s, 0, a0, args[3]);
        break;

    case INDEX_op_qemu_ld8u:
        tcg_out_qemu_ld(s, args, 0 | 0);
        break;
    case INDEX_op_qemu_ld8s:
        tcg_out_qemu_ld(s, args, 4 | 0);
        break;
    case INDEX_op_qemu_ld16u:
        tcg_out_qemu_ld(s, args, 0 | 1);
        break;
    case INDEX_op_qemu_ld16s:
        tcg_out_qemu_ld(s, args, 4 | 1);
        break;
    case INDEX_op_qemu_ld32u:
        tcg_out_qemu_ld(s, args, 0 | 2);
        break;
    case INDEX_op_qemu_ld32s:
        tcg_out_qemu_ld(s, args, 4 | 2);
        break;
    case INDEX_op_qemu_ld32:
        tcg_out_qemu_ld(s, args, 0 | 2);
        break;
    case INDEX_op_qemu_ld64:
        tcg_out_qemu_ld(s, args, 0 | 3);
        break;
    case INDEX_op_qemu_st8:
        tcg_out_qemu_st(s, args, 0);
        break;
    case INDEX_op_qemu_st16:
        tcg_out_qemu_st(s, args, 1);
        break;
    case INDEX_op_qemu_st32:
        tcg_out_qemu_st(s, args, 2);
        break;
    case INDEX_op_qemu_st64:
        tcg_out_qemu_st(s, args, 3);
        break;

    case INDEX_op_bswap32_i64:
        /* Despite the _i64, this is a 32-bit bswap.  */
        ext = 0;
        /* FALLTHRU */
    case INDEX_op_bswap64_i64:
    case INDEX_op_bswap32_i32:
        tcg_out_rev(s, ext, a0, a1);
        break;
    case INDEX_op_bswap16_i64:
    case INDEX_op_bswap16_i32:
        tcg_out_rev16(s, 0, a0, a1);
        break;

    case INDEX_op_ext8s_i64:
    case INDEX_op_ext8s_i32:
        tcg_out_sxt(s, ext, 0, a0, a1);
        break;
    case INDEX_op_ext16s_i64:
    case INDEX_op_ext16s_i32:
        tcg_out_sxt(s, ext, 1, a0, a1);
        break;
    case INDEX_op_ext32s_i64:
        tcg_out_sxt(s, 1, 2, a0, a1);
        break;
    case INDEX_op_ext8u_i64:
    case INDEX_op_ext8u_i32:
        tcg_out_uxt(s, 0, a0, a1);
        break;
    case INDEX_op_ext16u_i64:
    case INDEX_op_ext16u_i32:
        tcg_out_uxt(s, 1, a0, a1);
        break;
    case INDEX_op_ext32u_i64:
        tcg_out_movr(s, 0, a0, a1);
        break;

    case INDEX_op_mov_i64:
    case INDEX_op_mov_i32:
    case INDEX_op_movi_i64:
    case INDEX_op_movi_i32:
        /* Always implemented with tcg_out_mov/i, never with tcg_out_op.  */
    default:
        /* Opcode not implemented.  */
        tcg_abort();
    }
}

static const TCGTargetOpDef aarch64_op_defs[] = {
    { INDEX_op_exit_tb, { } },
    { INDEX_op_goto_tb, { } },
    { INDEX_op_call, { "ri" } },
    { INDEX_op_br, { } },

    { INDEX_op_mov_i32, { "r", "r" } },
    { INDEX_op_mov_i64, { "r", "r" } },

    { INDEX_op_movi_i32, { "r" } },
    { INDEX_op_movi_i64, { "r" } },

    { INDEX_op_ld8u_i32, { "r", "r" } },
    { INDEX_op_ld8s_i32, { "r", "r" } },
    { INDEX_op_ld16u_i32, { "r", "r" } },
    { INDEX_op_ld16s_i32, { "r", "r" } },
    { INDEX_op_ld_i32, { "r", "r" } },
    { INDEX_op_ld8u_i64, { "r", "r" } },
    { INDEX_op_ld8s_i64, { "r", "r" } },
    { INDEX_op_ld16u_i64, { "r", "r" } },
    { INDEX_op_ld16s_i64, { "r", "r" } },
    { INDEX_op_ld32u_i64, { "r", "r" } },
    { INDEX_op_ld32s_i64, { "r", "r" } },
    { INDEX_op_ld_i64, { "r", "r" } },

    { INDEX_op_st8_i32, { "r", "r" } },
    { INDEX_op_st16_i32, { "r", "r" } },
    { INDEX_op_st_i32, { "r", "r" } },
    { INDEX_op_st8_i64, { "r", "r" } },
    { INDEX_op_st16_i64, { "r", "r" } },
    { INDEX_op_st32_i64, { "r", "r" } },
    { INDEX_op_st_i64, { "r", "r" } },

    { INDEX_op_add_i32, { "r", "r", "r" } },
    { INDEX_op_add_i64, { "r", "r", "r" } },
    { INDEX_op_sub_i32, { "r", "r", "r" } },
    { INDEX_op_sub_i64, { "r", "r", "r" } },
    { INDEX_op_mul_i32, { "r", "r", "r" } },
    { INDEX_op_mul_i64, { "r", "r", "r" } },
    { INDEX_op_and_i32, { "r", "r", "r" } },
    { INDEX_op_and_i64, { "r", "r", "r" } },
    { INDEX_op_or_i32, { "r", "r", "r" } },
    { INDEX_op_or_i64, { "r", "r", "r" } },
    { INDEX_op_xor_i32, { "r", "r", "r" } },
    { INDEX_op_xor_i64, { "r", "r", "r" } },

    { INDEX_op_shl_i32, { "r", "r", "ri" } },
    { INDEX_op_shr_i32, { "r", "r", "ri" } },
    { INDEX_op_sar_i32, { "r", "r", "ri" } },
    { INDEX_op_rotl_i32, { "r", "r", "ri" } },
    { INDEX_op_rotr_i32, { "r", "r", "ri" } },
    { INDEX_op_shl_i64, { "r", "r", "ri" } },
    { INDEX_op_shr_i64, { "r", "r", "ri" } },
    { INDEX_op_sar_i64, { "r", "r", "ri" } },
    { INDEX_op_rotl_i64, { "r", "r", "ri" } },
    { INDEX_op_rotr_i64, { "r", "r", "ri" } },

    { INDEX_op_brcond_i32, { "r", "r" } },
    { INDEX_op_setcond_i32, { "r", "r", "r" } },
    { INDEX_op_brcond_i64, { "r", "r" } },
    { INDEX_op_setcond_i64, { "r", "r", "r" } },

    { INDEX_op_qemu_ld8u, { "r", "l" } },
    { INDEX_op_qemu_ld8s, { "r", "l" } },
    { INDEX_op_qemu_ld16u, { "r", "l" } },
    { INDEX_op_qemu_ld16s, { "r", "l" } },
    { INDEX_op_qemu_ld32u, { "r", "l" } },
    { INDEX_op_qemu_ld32s, { "r", "l" } },

    { INDEX_op_qemu_ld32, { "r", "l" } },
    { INDEX_op_qemu_ld64, { "r", "l" } },

    { INDEX_op_qemu_st8, { "l", "l" } },
    { INDEX_op_qemu_st16, { "l", "l" } },
    { INDEX_op_qemu_st32, { "l", "l" } },
    { INDEX_op_qemu_st64, { "l", "l" } },

    { INDEX_op_bswap16_i32, { "r", "r" } },
    { INDEX_op_bswap32_i32, { "r", "r" } },
    { INDEX_op_bswap16_i64, { "r", "r" } },
    { INDEX_op_bswap32_i64, { "r", "r" } },
    { INDEX_op_bswap64_i64, { "r", "r" } },

    { INDEX_op_ext8s_i32, { "r", "r" } },
    { INDEX_op_ext16s_i32, { "r", "r" } },
    { INDEX_op_ext8u_i32, { "r", "r" } },
    { INDEX_op_ext16u_i32, { "r", "r" } },

    { INDEX_op_ext8s_i64, { "r", "r" } },
    { INDEX_op_ext16s_i64, { "r", "r" } },
    { INDEX_op_ext32s_i64, { "r", "r" } },
    { INDEX_op_ext8u_i64, { "r", "r" } },
    { INDEX_op_ext16u_i64, { "r", "r" } },
    { INDEX_op_ext32u_i64, { "r", "r" } },

    { -1 },
};

static void tcg_target_init(TCGContext *s)
{
    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffffffff);
    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffffffff);

    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
                     (1 << TCG_REG_X0) | (1 << TCG_REG_X1) |
                     (1 << TCG_REG_X2) | (1 << TCG_REG_X3) |
                     (1 << TCG_REG_X4) | (1 << TCG_REG_X5) |
                     (1 << TCG_REG_X6) | (1 << TCG_REG_X7) |
                     (1 << TCG_REG_X8) | (1 << TCG_REG_X9) |
                     (1 << TCG_REG_X10) | (1 << TCG_REG_X11) |
                     (1 << TCG_REG_X12) | (1 << TCG_REG_X13) |
                     (1 << TCG_REG_X14) | (1 << TCG_REG_X15) |
                     (1 << TCG_REG_X16) | (1 << TCG_REG_X17) |
                     (1 << TCG_REG_X18));

    tcg_regset_clear(s->reserved_regs);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_FP);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_X18); /* platform register */

    tcg_add_target_add_op_defs(aarch64_op_defs);
}

static void tcg_target_qemu_prologue(TCGContext *s)
{
    /* NB: frame sizes are in 16 byte stack units! */
    int frame_size_callee_saved, frame_size_tcg_locals;
    TCGReg r;

    /* save pairs             (FP, LR) and (X19, X20) .. (X27, X28) */
    frame_size_callee_saved = (1) + (TCG_REG_X28 - TCG_REG_X19) / 2 + 1;

    /* frame size requirement for TCG local variables */
    frame_size_tcg_locals = TCG_STATIC_CALL_ARGS_SIZE
        + CPU_TEMP_BUF_NLONGS * sizeof(long)
        + (TCG_TARGET_STACK_ALIGN - 1);
    frame_size_tcg_locals &= ~(TCG_TARGET_STACK_ALIGN - 1);
    frame_size_tcg_locals /= TCG_TARGET_STACK_ALIGN;

    /* push (FP, LR) and update sp */
    tcg_out_push_pair(s, TCG_REG_SP,
                      TCG_REG_FP, TCG_REG_LR, frame_size_callee_saved);

    /* FP -> callee_saved */
    tcg_out_movr_sp(s, 1, TCG_REG_FP, TCG_REG_SP);

    /* store callee-preserved regs x19..x28 using FP -> callee_saved */
    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
        int idx = (r - TCG_REG_X19) / 2 + 1;
        tcg_out_store_pair(s, TCG_REG_FP, r, r + 1, idx);
    }

    /* Make stack space for TCG locals.  */
    tcg_out_insn(s, 3401, SUBI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
                 frame_size_tcg_locals * TCG_TARGET_STACK_ALIGN);

    /* inform TCG about how to find TCG locals with register, offset, size */
    tcg_set_frame(s, TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE,
                  CPU_TEMP_BUF_NLONGS * sizeof(long));

#if defined(CONFIG_USE_GUEST_BASE)
    if (GUEST_BASE) {
        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_GUEST_BASE, GUEST_BASE);
        tcg_regset_set_reg(s->reserved_regs, TCG_REG_GUEST_BASE);
    }
#endif

    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
    tcg_out_gotor(s, tcg_target_call_iarg_regs[1]);

    tb_ret_addr = s->code_ptr;

    /* Remove TCG locals stack space.  */
    tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
                 frame_size_tcg_locals * TCG_TARGET_STACK_ALIGN);

    /* restore registers x19..x28.
       FP must be preserved, so it still points to callee_saved area */
    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
        int idx = (r - TCG_REG_X19) / 2 + 1;
        tcg_out_load_pair(s, TCG_REG_FP, r, r + 1, idx);
    }

    /* pop (FP, LR), restore SP to previous frame, return */
    tcg_out_pop_pair(s, TCG_REG_SP,
                     TCG_REG_FP, TCG_REG_LR, frame_size_callee_saved);
    tcg_out_ret(s);
}