aboutsummaryrefslogtreecommitdiff
path: root/tcg/aarch64/tcg-target.inc.c
blob: a1e5dd2f0350dc348e9daf6b5815b94332d6f684 (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
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
/*
 * 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);

#ifdef CONFIG_DEBUG_TCG
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", "%x30", "%sp",
};
#endif /* CONFIG_DEBUG_TCG */

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_X8, 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_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7,

    /* X18 reserved by system */
    /* X19 reserved for AREG0 */
    /* X29 reserved as fp */
    /* X30 reserved as temporary */
};

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_X30

#ifndef CONFIG_SOFTMMU
/* Note that XZR cannot be encoded in the address base register slot,
   as that actaully encodes SP.  So if we need to zero-extend the guest
   address, via the address index register slot, we need to load even
   a zero guest base into a register.  */
#define USE_GUEST_BASE     (guest_base != 0 || TARGET_LONG_BITS == 32)
#define TCG_REG_GUEST_BASE TCG_REG_X28
#endif

static inline void reloc_pc26(tcg_insn_unit *code_ptr, tcg_insn_unit *target)
{
    ptrdiff_t offset = target - code_ptr;
    tcg_debug_assert(offset == sextract64(offset, 0, 26));
    /* read instruction, mask away previous PC_REL26 parameter contents,
       set the proper offset, then write back the instruction. */
    *code_ptr = deposit32(*code_ptr, 0, 26, offset);
}

static inline void reloc_pc26_atomic(tcg_insn_unit *code_ptr,
                                     tcg_insn_unit *target)
{
    ptrdiff_t offset = target - code_ptr;
    tcg_insn_unit insn;
    tcg_debug_assert(offset == sextract64(offset, 0, 26));
    /* read instruction, mask away previous PC_REL26 parameter contents,
       set the proper offset, then write back the instruction. */
    insn = atomic_read(code_ptr);
    atomic_set(code_ptr, deposit32(insn, 0, 26, offset));
}

static inline void reloc_pc19(tcg_insn_unit *code_ptr, tcg_insn_unit *target)
{
    ptrdiff_t offset = target - code_ptr;
    tcg_debug_assert(offset == sextract64(offset, 0, 19));
    *code_ptr = deposit32(*code_ptr, 5, 19, offset);
}

static inline void patch_reloc(tcg_insn_unit *code_ptr, int type,
                               intptr_t value, intptr_t addend)
{
    tcg_debug_assert(addend == 0);
    switch (type) {
    case R_AARCH64_JUMP26:
    case R_AARCH64_CALL26:
        reloc_pc26(code_ptr, (tcg_insn_unit *)value);
        break;
    case R_AARCH64_CONDBR19:
        reloc_pc19(code_ptr, (tcg_insn_unit *)value);
        break;
    default:
        tcg_abort();
    }
}

#define TCG_CT_CONST_AIMM 0x100
#define TCG_CT_CONST_LIMM 0x200
#define TCG_CT_CONST_ZERO 0x400
#define TCG_CT_CONST_MONE 0x800

/* parse target specific constraints */
static const char *target_parse_constraint(TCGArgConstraint *ct,
                                           const char *ct_str, TCGType type)
{
    switch (*ct_str++) {
    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;
    case 'A': /* Valid for arithmetic immediate (positive or negative).  */
        ct->ct |= TCG_CT_CONST_AIMM;
        break;
    case 'L': /* Valid for logical immediate.  */
        ct->ct |= TCG_CT_CONST_LIMM;
        break;
    case 'M': /* minus one */
        ct->ct |= TCG_CT_CONST_MONE;
        break;
    case 'Z': /* zero */
        ct->ct |= TCG_CT_CONST_ZERO;
        break;
    default:
        return NULL;
    }
    return ct_str;
}

static inline bool is_aimm(uint64_t val)
{
    return (val & ~0xfff) == 0 || (val & ~0xfff000) == 0;
}

static inline bool is_limm(uint64_t val)
{
    /* Taking a simplified view of the logical immediates for now, ignoring
       the replication that can happen across the field.  Match bit patterns
       of the forms
           0....01....1
           0..01..10..0
       and their inverses.  */

    /* Make things easier below, by testing the form with msb clear. */
    if ((int64_t)val < 0) {
        val = ~val;
    }
    if (val == 0) {
        return false;
    }
    val += val & -val;
    return (val & (val - 1)) == 0;
}

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

    if (ct & TCG_CT_CONST) {
        return 1;
    }
    if (type == TCG_TYPE_I32) {
        val = (int32_t)val;
    }
    if ((ct & TCG_CT_CONST_AIMM) && (is_aimm(val) || is_aimm(-val))) {
        return 1;
    }
    if ((ct & TCG_CT_CONST_LIMM) && is_limm(val)) {
        return 1;
    }
    if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
        return 1;
    }
    if ((ct & TCG_CT_CONST_MONE) && val == -1) {
        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,
};

typedef enum {
    LDST_ST = 0,    /* store */
    LDST_LD = 1,    /* load */
    LDST_LD_S_X = 2,  /* load and sign-extend into Xt */
    LDST_LD_S_W = 3,  /* load and sign-extend into Wt */
} AArch64LdstType;

/* 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 {
    /* Compare and branch (immediate).  */
    I3201_CBZ       = 0x34000000,
    I3201_CBNZ      = 0x35000000,

    /* Conditional branch (immediate).  */
    I3202_B_C       = 0x54000000,

    /* Unconditional branch (immediate).  */
    I3206_B         = 0x14000000,
    I3206_BL        = 0x94000000,

    /* Unconditional branch (register).  */
    I3207_BR        = 0xd61f0000,
    I3207_BLR       = 0xd63f0000,
    I3207_RET       = 0xd65f0000,

    /* Load literal for loading the address at pc-relative offset */
    I3305_LDR       = 0x58000000,
    /* Load/store register.  Described here as 3.3.12, but the helper
       that emits them can transform to 3.3.10 or 3.3.13.  */
    I3312_STRB      = 0x38000000 | LDST_ST << 22 | MO_8 << 30,
    I3312_STRH      = 0x38000000 | LDST_ST << 22 | MO_16 << 30,
    I3312_STRW      = 0x38000000 | LDST_ST << 22 | MO_32 << 30,
    I3312_STRX      = 0x38000000 | LDST_ST << 22 | MO_64 << 30,

    I3312_LDRB      = 0x38000000 | LDST_LD << 22 | MO_8 << 30,
    I3312_LDRH      = 0x38000000 | LDST_LD << 22 | MO_16 << 30,
    I3312_LDRW      = 0x38000000 | LDST_LD << 22 | MO_32 << 30,
    I3312_LDRX      = 0x38000000 | LDST_LD << 22 | MO_64 << 30,

    I3312_LDRSBW    = 0x38000000 | LDST_LD_S_W << 22 | MO_8 << 30,
    I3312_LDRSHW    = 0x38000000 | LDST_LD_S_W << 22 | MO_16 << 30,

    I3312_LDRSBX    = 0x38000000 | LDST_LD_S_X << 22 | MO_8 << 30,
    I3312_LDRSHX    = 0x38000000 | LDST_LD_S_X << 22 | MO_16 << 30,
    I3312_LDRSWX    = 0x38000000 | LDST_LD_S_X << 22 | MO_32 << 30,

    I3312_TO_I3310  = 0x00200800,
    I3312_TO_I3313  = 0x01000000,

    /* Load/store register pair instructions.  */
    I3314_LDP       = 0x28400000,
    I3314_STP       = 0x28000000,

    /* Add/subtract immediate instructions.  */
    I3401_ADDI      = 0x11000000,
    I3401_ADDSI     = 0x31000000,
    I3401_SUBI      = 0x51000000,
    I3401_SUBSI     = 0x71000000,

    /* Bitfield instructions.  */
    I3402_BFM       = 0x33000000,
    I3402_SBFM      = 0x13000000,
    I3402_UBFM      = 0x53000000,

    /* Extract instruction.  */
    I3403_EXTR      = 0x13800000,

    /* Logical immediate instructions.  */
    I3404_ANDI      = 0x12000000,
    I3404_ORRI      = 0x32000000,
    I3404_EORI      = 0x52000000,

    /* Move wide immediate instructions.  */
    I3405_MOVN      = 0x12800000,
    I3405_MOVZ      = 0x52800000,
    I3405_MOVK      = 0x72800000,

    /* PC relative addressing instructions.  */
    I3406_ADR       = 0x10000000,
    I3406_ADRP      = 0x90000000,

    /* 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,

    /* Add/subtract with carry instructions.  */
    I3503_ADC       = 0x1a000000,
    I3503_SBC       = 0x5a000000,

    /* Conditional select instructions.  */
    I3506_CSEL      = 0x1a800000,
    I3506_CSINC     = 0x1a800400,
    I3506_CSINV     = 0x5a800000,
    I3506_CSNEG     = 0x5a800400,

    /* Data-processing (1 source) instructions.  */
    I3507_CLZ       = 0x5ac01000,
    I3507_RBIT      = 0x5ac00000,
    I3507_REV16     = 0x5ac00400,
    I3507_REV32     = 0x5ac00800,
    I3507_REV64     = 0x5ac00c00,

    /* Data-processing (2 source) instructions.  */
    I3508_LSLV      = 0x1ac02000,
    I3508_LSRV      = 0x1ac02400,
    I3508_ASRV      = 0x1ac02800,
    I3508_RORV      = 0x1ac02c00,
    I3508_SMULH     = 0x9b407c00,
    I3508_UMULH     = 0x9bc07c00,
    I3508_UDIV      = 0x1ac00800,
    I3508_SDIV      = 0x1ac00c00,

    /* Data-processing (3 source) instructions.  */
    I3509_MADD      = 0x1b000000,
    I3509_MSUB      = 0x1b008000,

    /* Logical shifted register instructions (without a shift).  */
    I3510_AND       = 0x0a000000,
    I3510_BIC       = 0x0a200000,
    I3510_ORR       = 0x2a000000,
    I3510_ORN       = 0x2a200000,
    I3510_EOR       = 0x4a000000,
    I3510_EON       = 0x4a200000,
    I3510_ANDS      = 0x6a000000,

    NOP             = 0xd503201f,
    /* System instructions.  */
    DMB_ISH         = 0xd50338bf,
    DMB_LD          = 0x00000100,
    DMB_ST          = 0x00000200,
} AArch64Insn;

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_3305(TCGContext *s, AArch64Insn insn, int imm19, TCGReg rt)
{
    tcg_out32(s, insn | (imm19 & 0x7ffff) << 5 | rt);
}

static void tcg_out_insn_3201(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rt, int imm19)
{
    tcg_out32(s, insn | ext << 31 | (imm19 & 0x7ffff) << 5 | rt);
}

static void tcg_out_insn_3202(TCGContext *s, AArch64Insn insn,
                              TCGCond c, int imm19)
{
    tcg_out32(s, insn | tcg_cond_to_aarch64[c] | (imm19 & 0x7ffff) << 5);
}

static void tcg_out_insn_3206(TCGContext *s, AArch64Insn insn, int imm26)
{
    tcg_out32(s, insn | (imm26 & 0x03ffffff));
}

static void tcg_out_insn_3207(TCGContext *s, AArch64Insn insn, TCGReg rn)
{
    tcg_out32(s, insn | rn << 5);
}

static void tcg_out_insn_3314(TCGContext *s, AArch64Insn insn,
                              TCGReg r1, TCGReg r2, TCGReg rn,
                              tcg_target_long ofs, bool pre, bool w)
{
    insn |= 1u << 31; /* ext */
    insn |= pre << 24;
    insn |= w << 23;

    tcg_debug_assert(ofs >= -0x200 && ofs < 0x200 && (ofs & 7) == 0);
    insn |= (ofs & (0x7f << 3)) << (15 - 3);

    tcg_out32(s, insn | r2 << 10 | rn << 5 | r1);
}

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

/* This function can be used for both 3.4.2 (Bitfield) and 3.4.4
   (Logical immediate).  Both insn groups have N, IMMR and IMMS fields
   that feed the DecodeBitMasks pseudo function.  */
static void tcg_out_insn_3402(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, int n, int immr, int imms)
{
    tcg_out32(s, insn | ext << 31 | n << 22 | immr << 16 | imms << 10
              | rn << 5 | rd);
}

#define tcg_out_insn_3404  tcg_out_insn_3402

static void tcg_out_insn_3403(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, TCGReg rm, int imms)
{
    tcg_out32(s, insn | ext << 31 | ext << 22 | rm << 16 | imms << 10
              | rn << 5 | rd);
}

/* This function is used for the Move (wide immediate) instruction group.
   Note that SHIFT is a full shift count, not the 2 bit HW field. */
static void tcg_out_insn_3405(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, uint16_t half, unsigned shift)
{
    tcg_debug_assert((shift & ~0x30) == 0);
    tcg_out32(s, insn | ext << 31 | shift << (21 - 4) | half << 5 | rd);
}

static void tcg_out_insn_3406(TCGContext *s, AArch64Insn insn,
                              TCGReg rd, int64_t disp)
{
    tcg_out32(s, insn | (disp & 3) << 29 | (disp & 0x1ffffc) << (5 - 2) | 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 void tcg_out_insn_3506(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, TCGReg rm, TCGCond c)
{
    tcg_out32(s, insn | ext << 31 | rm << 16 | rn << 5 | rd
              | tcg_cond_to_aarch64[c] << 12);
}

static void tcg_out_insn_3507(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn)
{
    tcg_out32(s, insn | ext << 31 | rn << 5 | rd);
}

static void tcg_out_insn_3509(TCGContext *s, AArch64Insn insn, TCGType ext,
                              TCGReg rd, TCGReg rn, TCGReg rm, TCGReg ra)
{
    tcg_out32(s, insn | ext << 31 | rm << 16 | ra << 10 | rn << 5 | rd);
}

static void tcg_out_insn_3310(TCGContext *s, AArch64Insn insn,
                              TCGReg rd, TCGReg base, TCGType ext,
                              TCGReg regoff)
{
    /* Note the AArch64Insn constants above are for C3.3.12.  Adjust.  */
    tcg_out32(s, insn | I3312_TO_I3310 | regoff << 16 |
              0x4000 | ext << 13 | base << 5 | rd);
}

static void tcg_out_insn_3312(TCGContext *s, AArch64Insn insn,
                              TCGReg rd, TCGReg rn, intptr_t offset)
{
    tcg_out32(s, insn | (offset & 0x1ff) << 12 | rn << 5 | rd);
}

static void tcg_out_insn_3313(TCGContext *s, AArch64Insn insn,
                              TCGReg rd, TCGReg rn, uintptr_t scaled_uimm)
{
    /* Note the AArch64Insn constants above are for C3.3.12.  Adjust.  */
    tcg_out32(s, insn | I3312_TO_I3313 | scaled_uimm << 10 | rn << 5 | rd);
}

/* Register to register move using ORR (shifted register with no shift). */
static void tcg_out_movr(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rm)
{
    tcg_out_insn(s, 3510, ORR, ext, rd, TCG_REG_XZR, rm);
}

/* Register to register move using ADDI (move to/from SP).  */
static void tcg_out_movr_sp(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rn)
{
    tcg_out_insn(s, 3401, ADDI, ext, rd, rn, 0);
}

/* This function is used for the Logical (immediate) instruction group.
   The value of LIMM must satisfy IS_LIMM.  See the comment above about
   only supporting simplified logical immediates.  */
static void tcg_out_logicali(TCGContext *s, AArch64Insn insn, TCGType ext,
                             TCGReg rd, TCGReg rn, uint64_t limm)
{
    unsigned h, l, r, c;

    tcg_debug_assert(is_limm(limm));

    h = clz64(limm);
    l = ctz64(limm);
    if (l == 0) {
        r = 0;                  /* form 0....01....1 */
        c = ctz64(~limm) - 1;
        if (h == 0) {
            r = clz64(~limm);   /* form 1..10..01..1 */
            c += r;
        }
    } else {
        r = 64 - l;             /* form 1....10....0 or 0..01..10..0 */
        c = r - h - 1;
    }
    if (ext == TCG_TYPE_I32) {
        r &= 31;
        c &= 31;
    }

    tcg_out_insn_3404(s, insn, ext, rd, rn, ext, r, c);
}

static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd,
                         tcg_target_long value)
{
    int i, wantinv, shift;
    tcg_target_long svalue = value;
    tcg_target_long ivalue = ~value;

    /* For 32-bit values, discard potential garbage in value.  For 64-bit
       values within [2**31, 2**32-1], we can create smaller sequences by
       interpreting this as a negative 32-bit number, while ensuring that
       the high 32 bits are cleared by setting SF=0.  */
    if (type == TCG_TYPE_I32 || (value & ~0xffffffffull) == 0) {
        svalue = (int32_t)value;
        value = (uint32_t)value;
        ivalue = (uint32_t)ivalue;
        type = TCG_TYPE_I32;
    }

    /* Speed things up by handling the common case of small positive
       and negative values specially.  */
    if ((value & ~0xffffull) == 0) {
        tcg_out_insn(s, 3405, MOVZ, type, rd, value, 0);
        return;
    } else if ((ivalue & ~0xffffull) == 0) {
        tcg_out_insn(s, 3405, MOVN, type, rd, ivalue, 0);
        return;
    }

    /* Check for bitfield immediates.  For the benefit of 32-bit quantities,
       use the sign-extended value.  That lets us match rotated values such
       as 0xff0000ff with the same 64-bit logic matching 0xffffffffff0000ff. */
    if (is_limm(svalue)) {
        tcg_out_logicali(s, I3404_ORRI, type, rd, TCG_REG_XZR, svalue);
        return;
    }

    /* Look for host pointer values within 4G of the PC.  This happens
       often when loading pointers to QEMU's own data structures.  */
    if (type == TCG_TYPE_I64) {
        tcg_target_long disp = value - (intptr_t)s->code_ptr;
        if (disp == sextract64(disp, 0, 21)) {
            tcg_out_insn(s, 3406, ADR, rd, disp);
            return;
        }
        disp = (value >> 12) - ((intptr_t)s->code_ptr >> 12);
        if (disp == sextract64(disp, 0, 21)) {
            tcg_out_insn(s, 3406, ADRP, rd, disp);
            if (value & 0xfff) {
                tcg_out_insn(s, 3401, ADDI, type, rd, rd, value & 0xfff);
            }
            return;
        }
    }

    /* Would it take fewer insns to begin with MOVN?  For the value and its
       inverse, count the number of 16-bit lanes that are 0.  */
    for (i = wantinv = 0; i < 64; i += 16) {
        tcg_target_long mask = 0xffffull << i;
        wantinv -= ((value & mask) == 0);
        wantinv += ((ivalue & mask) == 0);
    }

    if (wantinv <= 0) {
        /* Find the lowest lane that is not 0x0000.  */
        shift = ctz64(value) & (63 & -16);
        tcg_out_insn(s, 3405, MOVZ, type, rd, value >> shift, shift);
        /* Clear out the lane that we just set.  */
        value &= ~(0xffffUL << shift);
        /* Iterate until all non-zero lanes have been processed.  */
        while (value) {
            shift = ctz64(value) & (63 & -16);
            tcg_out_insn(s, 3405, MOVK, type, rd, value >> shift, shift);
            value &= ~(0xffffUL << shift);
        }
    } else {
        /* Like above, but with the inverted value and MOVN to start.  */
        shift = ctz64(ivalue) & (63 & -16);
        tcg_out_insn(s, 3405, MOVN, type, rd, ivalue >> shift, shift);
        ivalue &= ~(0xffffUL << shift);
        while (ivalue) {
            shift = ctz64(ivalue) & (63 & -16);
            /* Provide MOVK with the non-inverted value.  */
            tcg_out_insn(s, 3405, MOVK, type, rd, ~(ivalue >> shift), shift);
            ivalue &= ~(0xffffUL << shift);
        }
    }
}

/* Define something more legible for general use.  */
#define tcg_out_ldst_r  tcg_out_insn_3310

static void tcg_out_ldst(TCGContext *s, AArch64Insn insn,
                         TCGReg rd, TCGReg rn, intptr_t offset)
{
    TCGMemOp size = (uint32_t)insn >> 30;

    /* If the offset is naturally aligned and in range, then we can
       use the scaled uimm12 encoding */
    if (offset >= 0 && !(offset & ((1 << size) - 1))) {
        uintptr_t scaled_uimm = offset >> size;
        if (scaled_uimm <= 0xfff) {
            tcg_out_insn_3313(s, insn, rd, rn, scaled_uimm);
            return;
        }
    }

    /* Small signed offsets can use the unscaled encoding.  */
    if (offset >= -256 && offset < 256) {
        tcg_out_insn_3312(s, insn, rd, rn, offset);
        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, insn, rd, rn, TCG_TYPE_I64, TCG_REG_TMP);
}

static inline void tcg_out_mov(TCGContext *s,
                               TCGType type, TCGReg ret, TCGReg arg)
{
    if (ret != arg) {
        tcg_out_movr(s, type, 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_I32 ? I3312_LDRW : I3312_LDRX,
                 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_I32 ? I3312_STRW : I3312_STRX,
                 arg, arg1, arg2);
}

static inline bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val,
                               TCGReg base, intptr_t ofs)
{
    if (val == 0) {
        tcg_out_st(s, type, TCG_REG_XZR, base, ofs);
        return true;
    }
    return false;
}

static inline void tcg_out_bfm(TCGContext *s, TCGType ext, TCGReg rd,
                               TCGReg rn, unsigned int a, unsigned int b)
{
    tcg_out_insn(s, 3402, BFM, ext, rd, rn, ext, a, b);
}

static inline void tcg_out_ubfm(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, unsigned int a, unsigned int b)
{
    tcg_out_insn(s, 3402, UBFM, ext, rd, rn, ext, a, b);
}

static inline void tcg_out_sbfm(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, unsigned int a, unsigned int b)
{
    tcg_out_insn(s, 3402, SBFM, ext, rd, rn, ext, a, b);
}

static inline void tcg_out_extr(TCGContext *s, TCGType ext, TCGReg rd,
                                TCGReg rn, TCGReg rm, unsigned int a)
{
    tcg_out_insn(s, 3403, EXTR, ext, rd, rn, rm, a);
}

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

static inline void tcg_out_dep(TCGContext *s, TCGType ext, TCGReg rd,
                               TCGReg rn, unsigned lsb, unsigned width)
{
    unsigned size = ext ? 64 : 32;
    unsigned a = (size - lsb) & (size - 1);
    unsigned b = width - 1;
    tcg_out_bfm(s, ext, rd, rn, a, b);
}

static void tcg_out_cmp(TCGContext *s, TCGType ext, TCGReg a,
                        tcg_target_long b, bool const_b)
{
    if (const_b) {
        /* Using CMP or CMN aliases.  */
        if (b >= 0) {
            tcg_out_insn(s, 3401, SUBSI, ext, TCG_REG_XZR, a, b);
        } else {
            tcg_out_insn(s, 3401, ADDSI, ext, TCG_REG_XZR, a, -b);
        }
    } else {
        /* Using CMP alias SUBS wzr, Wn, Wm */
        tcg_out_insn(s, 3502, SUBS, ext, TCG_REG_XZR, a, b);
    }
}

static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target)
{
    ptrdiff_t offset = target - s->code_ptr;
    tcg_debug_assert(offset == sextract64(offset, 0, 26));
    tcg_out_insn(s, 3206, B, offset);
}

static inline void tcg_out_goto_long(TCGContext *s, tcg_insn_unit *target)
{
    ptrdiff_t offset = target - s->code_ptr;
    if (offset == sextract64(offset, 0, 26)) {
        tcg_out_insn(s, 3206, BL, offset);
    } else {
        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, (intptr_t)target);
        tcg_out_insn(s, 3207, BR, TCG_REG_TMP);
    }
}

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 old = tcg_in32(s);
    tcg_out_insn(s, 3206, B, old);
}

static inline void tcg_out_goto_cond_noaddr(TCGContext *s, TCGCond c)
{
    /* See comments in tcg_out_goto_noaddr.  */
    uint32_t old = tcg_in32(s) >> 5;
    tcg_out_insn(s, 3202, B_C, c, old);
}

static inline void tcg_out_callr(TCGContext *s, TCGReg reg)
{
    tcg_out_insn(s, 3207, BLR, reg);
}

static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target)
{
    ptrdiff_t offset = target - s->code_ptr;
    if (offset == sextract64(offset, 0, 26)) {
        tcg_out_insn(s, 3206, BL, offset);
    } else {
        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, (intptr_t)target);
        tcg_out_callr(s, TCG_REG_TMP);
    }
}

void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
                              uintptr_t addr)
{
    tcg_insn_unit i1, i2;
    TCGType rt = TCG_TYPE_I64;
    TCGReg  rd = TCG_REG_TMP;
    uint64_t pair;

    ptrdiff_t offset = addr - jmp_addr;

    if (offset == sextract64(offset, 0, 26)) {
        i1 = I3206_B | ((offset >> 2) & 0x3ffffff);
        i2 = NOP;
    } else {
        offset = (addr >> 12) - (jmp_addr >> 12);

        /* patch ADRP */
        i1 = I3406_ADRP | (offset & 3) << 29 | (offset & 0x1ffffc) << (5 - 2) | rd;
        /* patch ADDI */
        i2 = I3401_ADDI | rt << 31 | (addr & 0xfff) << 10 | rd << 5 | rd;
    }
    pair = (uint64_t)i2 << 32 | i1;
    atomic_set((uint64_t *)jmp_addr, pair);
    flush_icache_range(jmp_addr, jmp_addr + 8);
}

static inline void tcg_out_goto_label(TCGContext *s, TCGLabel *l)
{
    if (!l->has_value) {
        tcg_out_reloc(s, s->code_ptr, R_AARCH64_JUMP26, l, 0);
        tcg_out_goto_noaddr(s);
    } else {
        tcg_out_goto(s, l->u.value_ptr);
    }
}

static void tcg_out_brcond(TCGContext *s, TCGType ext, TCGCond c, TCGArg a,
                           TCGArg b, bool b_const, TCGLabel *l)
{
    intptr_t offset;
    bool need_cmp;

    if (b_const && b == 0 && (c == TCG_COND_EQ || c == TCG_COND_NE)) {
        need_cmp = false;
    } else {
        need_cmp = true;
        tcg_out_cmp(s, ext, a, b, b_const);
    }

    if (!l->has_value) {
        tcg_out_reloc(s, s->code_ptr, R_AARCH64_CONDBR19, l, 0);
        offset = tcg_in32(s) >> 5;
    } else {
        offset = l->u.value_ptr - s->code_ptr;
        tcg_debug_assert(offset == sextract64(offset, 0, 19));
    }

    if (need_cmp) {
        tcg_out_insn(s, 3202, B_C, c, offset);
    } else if (c == TCG_COND_EQ) {
        tcg_out_insn(s, 3201, CBZ, ext, a, offset);
    } else {
        tcg_out_insn(s, 3201, CBNZ, ext, a, offset);
    }
}

static inline void tcg_out_rev64(TCGContext *s, TCGReg rd, TCGReg rn)
{
    tcg_out_insn(s, 3507, REV64, TCG_TYPE_I64, rd, rn);
}

static inline void tcg_out_rev32(TCGContext *s, TCGReg rd, TCGReg rn)
{
    tcg_out_insn(s, 3507, REV32, TCG_TYPE_I32, rd, rn);
}

static inline void tcg_out_rev16(TCGContext *s, TCGReg rd, TCGReg rn)
{
    tcg_out_insn(s, 3507, REV16, TCG_TYPE_I32, rd, rn);
}

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

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

static void tcg_out_addsubi(TCGContext *s, int ext, TCGReg rd,
                            TCGReg rn, int64_t aimm)
{
    if (aimm >= 0) {
        tcg_out_insn(s, 3401, ADDI, ext, rd, rn, aimm);
    } else {
        tcg_out_insn(s, 3401, SUBI, ext, rd, rn, -aimm);
    }
}

static inline void tcg_out_addsub2(TCGContext *s, TCGType ext, TCGReg rl,
                                   TCGReg rh, TCGReg al, TCGReg ah,
                                   tcg_target_long bl, tcg_target_long bh,
                                   bool const_bl, bool const_bh, bool sub)
{
    TCGReg orig_rl = rl;
    AArch64Insn insn;

    if (rl == ah || (!const_bh && rl == bh)) {
        rl = TCG_REG_TMP;
    }

    if (const_bl) {
        insn = I3401_ADDSI;
        if ((bl < 0) ^ sub) {
            insn = I3401_SUBSI;
            bl = -bl;
        }
        if (unlikely(al == TCG_REG_XZR)) {
            /* ??? We want to allow al to be zero for the benefit of
               negation via subtraction.  However, that leaves open the
               possibility of adding 0+const in the low part, and the
               immediate add instructions encode XSP not XZR.  Don't try
               anything more elaborate here than loading another zero.  */
            al = TCG_REG_TMP;
            tcg_out_movi(s, ext, al, 0);
        }
        tcg_out_insn_3401(s, insn, ext, rl, al, bl);
    } else {
        tcg_out_insn_3502(s, sub ? I3502_SUBS : I3502_ADDS, ext, rl, al, bl);
    }

    insn = I3503_ADC;
    if (const_bh) {
        /* Note that the only two constants we support are 0 and -1, and
           that SBC = rn + ~rm + c, so adc -1 is sbc 0, and vice-versa.  */
        if ((bh != 0) ^ sub) {
            insn = I3503_SBC;
        }
        bh = TCG_REG_XZR;
    } else if (sub) {
        insn = I3503_SBC;
    }
    tcg_out_insn_3503(s, insn, ext, rh, ah, bh);

    tcg_out_mov(s, ext, orig_rl, rl);
}

static inline void tcg_out_mb(TCGContext *s, TCGArg a0)
{
    static const uint32_t sync[] = {
        [0 ... TCG_MO_ALL]            = DMB_ISH | DMB_LD | DMB_ST,
        [TCG_MO_ST_ST]                = DMB_ISH | DMB_ST,
        [TCG_MO_LD_LD]                = DMB_ISH | DMB_LD,
        [TCG_MO_LD_ST]                = DMB_ISH | DMB_LD,
        [TCG_MO_LD_ST | TCG_MO_LD_LD] = DMB_ISH | DMB_LD,
    };
    tcg_out32(s, sync[a0 & TCG_MO_ALL]);
}

static void tcg_out_cltz(TCGContext *s, TCGType ext, TCGReg d,
                         TCGReg a0, TCGArg b, bool const_b, bool is_ctz)
{
    TCGReg a1 = a0;
    if (is_ctz) {
        a1 = TCG_REG_TMP;
        tcg_out_insn(s, 3507, RBIT, ext, a1, a0);
    }
    if (const_b && b == (ext ? 64 : 32)) {
        tcg_out_insn(s, 3507, CLZ, ext, d, a1);
    } else {
        AArch64Insn sel = I3506_CSEL;

        tcg_out_cmp(s, ext, a0, 0, 1);
        tcg_out_insn(s, 3507, CLZ, ext, TCG_REG_TMP, a1);

        if (const_b) {
            if (b == -1) {
                b = TCG_REG_XZR;
                sel = I3506_CSINV;
            } else if (b == 0) {
                b = TCG_REG_XZR;
            } else {
                tcg_out_movi(s, ext, d, b);
                b = d;
            }
        }
        tcg_out_insn_3506(s, sel, ext, d, TCG_REG_TMP, b, TCG_COND_NE);
    }
}

#ifdef CONFIG_SOFTMMU
/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
 *                                     TCGMemOpIdx oi, uintptr_t ra)
 */
static void * const qemu_ld_helpers[16] = {
    [MO_UB]   = helper_ret_ldub_mmu,
    [MO_LEUW] = helper_le_lduw_mmu,
    [MO_LEUL] = helper_le_ldul_mmu,
    [MO_LEQ]  = helper_le_ldq_mmu,
    [MO_BEUW] = helper_be_lduw_mmu,
    [MO_BEUL] = helper_be_ldul_mmu,
    [MO_BEQ]  = helper_be_ldq_mmu,
};

/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
 *                                     uintxx_t val, TCGMemOpIdx oi,
 *                                     uintptr_t ra)
 */
static void * const qemu_st_helpers[16] = {
    [MO_UB]   = helper_ret_stb_mmu,
    [MO_LEUW] = helper_le_stw_mmu,
    [MO_LEUL] = helper_le_stl_mmu,
    [MO_LEQ]  = helper_le_stq_mmu,
    [MO_BEUW] = helper_be_stw_mmu,
    [MO_BEUL] = helper_be_stl_mmu,
    [MO_BEQ]  = helper_be_stq_mmu,
};

static inline void tcg_out_adr(TCGContext *s, TCGReg rd, void *target)
{
    ptrdiff_t offset = tcg_pcrel_diff(s, target);
    tcg_debug_assert(offset == sextract64(offset, 0, 21));
    tcg_out_insn(s, 3406, ADR, rd, offset);
}

static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    TCGMemOpIdx oi = lb->oi;
    TCGMemOp opc = get_memop(oi);
    TCGMemOp size = opc & MO_SIZE;

    reloc_pc19(lb->label_ptr[0], s->code_ptr);

    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_X0, TCG_AREG0);
    tcg_out_mov(s, TARGET_LONG_BITS == 64, TCG_REG_X1, lb->addrlo_reg);
    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X2, oi);
    tcg_out_adr(s, TCG_REG_X3, lb->raddr);
    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
    if (opc & MO_SIGN) {
        tcg_out_sxt(s, lb->type, size, lb->datalo_reg, TCG_REG_X0);
    } else {
        tcg_out_mov(s, size == MO_64, lb->datalo_reg, TCG_REG_X0);
    }

    tcg_out_goto(s, lb->raddr);
}

static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    TCGMemOpIdx oi = lb->oi;
    TCGMemOp opc = get_memop(oi);
    TCGMemOp size = opc & MO_SIZE;

    reloc_pc19(lb->label_ptr[0], s->code_ptr);

    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_X0, TCG_AREG0);
    tcg_out_mov(s, TARGET_LONG_BITS == 64, TCG_REG_X1, lb->addrlo_reg);
    tcg_out_mov(s, size == MO_64, TCG_REG_X2, lb->datalo_reg);
    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X3, oi);
    tcg_out_adr(s, TCG_REG_X4, lb->raddr);
    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
    tcg_out_goto(s, lb->raddr);
}

static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
                                TCGType ext, TCGReg data_reg, TCGReg addr_reg,
                                tcg_insn_unit *raddr, tcg_insn_unit *label_ptr)
{
    TCGLabelQemuLdst *label = new_ldst_label(s);

    label->is_ld = is_ld;
    label->oi = oi;
    label->type = ext;
    label->datalo_reg = data_reg;
    label->addrlo_reg = addr_reg;
    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, TCGMemOp opc,
                             tcg_insn_unit **label_ptr, int mem_index,
                             bool is_read)
{
    int tlb_offset = is_read ?
        offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
        : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write);
    unsigned a_bits = get_alignment_bits(opc);
    unsigned s_bits = opc & MO_SIZE;
    unsigned a_mask = (1u << a_bits) - 1;
    unsigned s_mask = (1u << s_bits) - 1;
    TCGReg base = TCG_AREG0, x3;
    uint64_t tlb_mask;

    /* For aligned accesses, we check the first byte and include the alignment
       bits within the address.  For unaligned access, we check that we don't
       cross pages using the address of the last byte of the access.  */
    if (a_bits >= s_bits) {
        x3 = addr_reg;
    } else {
        tcg_out_insn(s, 3401, ADDI, TARGET_LONG_BITS == 64,
                     TCG_REG_X3, addr_reg, s_mask - a_mask);
        x3 = TCG_REG_X3;
    }
    tlb_mask = (uint64_t)TARGET_PAGE_MASK | a_mask;

    /* 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 into X3.  */
    tcg_out_logicali(s, I3404_ANDI, TARGET_LONG_BITS == 64,
                     TCG_REG_X3, x3, tlb_mask);

    /* 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) */
    if (tlb_offset & 0xfff000) {
        tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_X2, base,
                     tlb_offset & 0xfff000);
        base = TCG_REG_X2;
    }

    /* Merge the tlb index contribution into X2.
       X2 = X2 + (X0 << CPU_TLB_ENTRY_BITS) */
    tcg_out_insn(s, 3502S, ADD_LSL, TCG_TYPE_I64, TCG_REG_X2, base,
                 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 == 32 ? I3312_LDRW : I3312_LDRX,
                 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, I3312_LDRX, 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, 0);

    /* If not equal, we jump to the slow path. */
    *label_ptr = s->code_ptr;
    tcg_out_goto_cond_noaddr(s, TCG_COND_NE);
}

#endif /* CONFIG_SOFTMMU */

static void tcg_out_qemu_ld_direct(TCGContext *s, TCGMemOp memop, TCGType ext,
                                   TCGReg data_r, TCGReg addr_r,
                                   TCGType otype, TCGReg off_r)
{
    const TCGMemOp bswap = memop & MO_BSWAP;

    switch (memop & MO_SSIZE) {
    case MO_UB:
        tcg_out_ldst_r(s, I3312_LDRB, data_r, addr_r, otype, off_r);
        break;
    case MO_SB:
        tcg_out_ldst_r(s, ext ? I3312_LDRSBX : I3312_LDRSBW,
                       data_r, addr_r, otype, off_r);
        break;
    case MO_UW:
        tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
        if (bswap) {
            tcg_out_rev16(s, data_r, data_r);
        }
        break;
    case MO_SW:
        if (bswap) {
            tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
            tcg_out_rev16(s, data_r, data_r);
            tcg_out_sxt(s, ext, MO_16, data_r, data_r);
        } else {
            tcg_out_ldst_r(s, (ext ? I3312_LDRSHX : I3312_LDRSHW),
                           data_r, addr_r, otype, off_r);
        }
        break;
    case MO_UL:
        tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
        if (bswap) {
            tcg_out_rev32(s, data_r, data_r);
        }
        break;
    case MO_SL:
        if (bswap) {
            tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
            tcg_out_rev32(s, data_r, data_r);
            tcg_out_sxt(s, TCG_TYPE_I64, MO_32, data_r, data_r);
        } else {
            tcg_out_ldst_r(s, I3312_LDRSWX, data_r, addr_r, otype, off_r);
        }
        break;
    case MO_Q:
        tcg_out_ldst_r(s, I3312_LDRX, data_r, addr_r, otype, off_r);
        if (bswap) {
            tcg_out_rev64(s, data_r, data_r);
        }
        break;
    default:
        tcg_abort();
    }
}

static void tcg_out_qemu_st_direct(TCGContext *s, TCGMemOp memop,
                                   TCGReg data_r, TCGReg addr_r,
                                   TCGType otype, TCGReg off_r)
{
    const TCGMemOp bswap = memop & MO_BSWAP;

    switch (memop & MO_SIZE) {
    case MO_8:
        tcg_out_ldst_r(s, I3312_STRB, data_r, addr_r, otype, off_r);
        break;
    case MO_16:
        if (bswap && data_r != TCG_REG_XZR) {
            tcg_out_rev16(s, TCG_REG_TMP, data_r);
            data_r = TCG_REG_TMP;
        }
        tcg_out_ldst_r(s, I3312_STRH, data_r, addr_r, otype, off_r);
        break;
    case MO_32:
        if (bswap && data_r != TCG_REG_XZR) {
            tcg_out_rev32(s, TCG_REG_TMP, data_r);
            data_r = TCG_REG_TMP;
        }
        tcg_out_ldst_r(s, I3312_STRW, data_r, addr_r, otype, off_r);
        break;
    case MO_64:
        if (bswap && data_r != TCG_REG_XZR) {
            tcg_out_rev64(s, TCG_REG_TMP, data_r);
            data_r = TCG_REG_TMP;
        }
        tcg_out_ldst_r(s, I3312_STRX, data_r, addr_r, otype, off_r);
        break;
    default:
        tcg_abort();
    }
}

static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
                            TCGMemOpIdx oi, TCGType ext)
{
    TCGMemOp memop = get_memop(oi);
    const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32;
#ifdef CONFIG_SOFTMMU
    unsigned mem_index = get_mmuidx(oi);
    tcg_insn_unit *label_ptr;

    tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, mem_index, 1);
    tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
                           TCG_REG_X1, otype, addr_reg);
    add_qemu_ldst_label(s, true, oi, ext, data_reg, addr_reg,
                        s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    if (USE_GUEST_BASE) {
        tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
                               TCG_REG_GUEST_BASE, otype, addr_reg);
    } else {
        tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
                               addr_reg, TCG_TYPE_I64, TCG_REG_XZR);
    }
#endif /* CONFIG_SOFTMMU */
}

static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
                            TCGMemOpIdx oi)
{
    TCGMemOp memop = get_memop(oi);
    const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32;
#ifdef CONFIG_SOFTMMU
    unsigned mem_index = get_mmuidx(oi);
    tcg_insn_unit *label_ptr;

    tcg_out_tlb_read(s, addr_reg, memop, &label_ptr, mem_index, 0);
    tcg_out_qemu_st_direct(s, memop, data_reg,
                           TCG_REG_X1, otype, addr_reg);
    add_qemu_ldst_label(s, false, oi, (memop & MO_SIZE)== MO_64,
                        data_reg, addr_reg, s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    if (USE_GUEST_BASE) {
        tcg_out_qemu_st_direct(s, memop, data_reg,
                               TCG_REG_GUEST_BASE, otype, addr_reg);
    } else {
        tcg_out_qemu_st_direct(s, memop, data_reg,
                               addr_reg, TCG_TYPE_I64, TCG_REG_XZR);
    }
#endif /* CONFIG_SOFTMMU */
}

static tcg_insn_unit *tb_ret_addr;

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];

    /* Some operands are defined with "rZ" constraint, a register or
       the zero register.  These need not actually test args[I] == 0.  */
#define REG0(I)  (const_args[I] ? TCG_REG_XZR : (TCGReg)args[I])

    switch (opc) {
    case INDEX_op_exit_tb:
        /* Reuse the zeroing that exists for goto_ptr.  */
        if (a0 == 0) {
            tcg_out_goto_long(s, s->code_gen_epilogue);
        } else {
            tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
            tcg_out_goto_long(s, tb_ret_addr);
        }
        break;

    case INDEX_op_goto_tb:
        if (s->tb_jmp_insn_offset != NULL) {
            /* TCG_TARGET_HAS_direct_jump */
            /* Ensure that ADRP+ADD are 8-byte aligned so that an atomic
               write can be used to patch the target address. */
            if ((uintptr_t)s->code_ptr & 7) {
                tcg_out32(s, NOP);
            }
            s->tb_jmp_insn_offset[a0] = tcg_current_code_size(s);
            /* actual branch destination will be patched by
               tb_target_set_jmp_target later. */
            tcg_out_insn(s, 3406, ADRP, TCG_REG_TMP, 0);
            tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_TMP, TCG_REG_TMP, 0);
        } else {
            /* !TCG_TARGET_HAS_direct_jump */
            tcg_debug_assert(s->tb_jmp_target_addr != NULL);
            intptr_t offset = tcg_pcrel_diff(s, (s->tb_jmp_target_addr + a0)) >> 2;
            tcg_out_insn(s, 3305, LDR, offset, TCG_REG_TMP);
        }
        tcg_out_insn(s, 3207, BR, TCG_REG_TMP);
        s->tb_jmp_reset_offset[a0] = tcg_current_code_size(s);
        break;

    case INDEX_op_goto_ptr:
        tcg_out_insn(s, 3207, BR, a0);
        break;

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

    case INDEX_op_ld8u_i32:
    case INDEX_op_ld8u_i64:
        tcg_out_ldst(s, I3312_LDRB, a0, a1, a2);
        break;
    case INDEX_op_ld8s_i32:
        tcg_out_ldst(s, I3312_LDRSBW, a0, a1, a2);
        break;
    case INDEX_op_ld8s_i64:
        tcg_out_ldst(s, I3312_LDRSBX, a0, a1, a2);
        break;
    case INDEX_op_ld16u_i32:
    case INDEX_op_ld16u_i64:
        tcg_out_ldst(s, I3312_LDRH, a0, a1, a2);
        break;
    case INDEX_op_ld16s_i32:
        tcg_out_ldst(s, I3312_LDRSHW, a0, a1, a2);
        break;
    case INDEX_op_ld16s_i64:
        tcg_out_ldst(s, I3312_LDRSHX, a0, a1, a2);
        break;
    case INDEX_op_ld_i32:
    case INDEX_op_ld32u_i64:
        tcg_out_ldst(s, I3312_LDRW, a0, a1, a2);
        break;
    case INDEX_op_ld32s_i64:
        tcg_out_ldst(s, I3312_LDRSWX, a0, a1, a2);
        break;
    case INDEX_op_ld_i64:
        tcg_out_ldst(s, I3312_LDRX, a0, a1, a2);
        break;

    case INDEX_op_st8_i32:
    case INDEX_op_st8_i64:
        tcg_out_ldst(s, I3312_STRB, REG0(0), a1, a2);
        break;
    case INDEX_op_st16_i32:
    case INDEX_op_st16_i64:
        tcg_out_ldst(s, I3312_STRH, REG0(0), a1, a2);
        break;
    case INDEX_op_st_i32:
    case INDEX_op_st32_i64:
        tcg_out_ldst(s, I3312_STRW, REG0(0), a1, a2);
        break;
    case INDEX_op_st_i64:
        tcg_out_ldst(s, I3312_STRX, REG0(0), a1, a2);
        break;

    case INDEX_op_add_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_add_i64:
        if (c2) {
            tcg_out_addsubi(s, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3502, ADD, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_sub_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_sub_i64:
        if (c2) {
            tcg_out_addsubi(s, ext, a0, a1, -a2);
        } else {
            tcg_out_insn(s, 3502, SUB, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_neg_i64:
    case INDEX_op_neg_i32:
        tcg_out_insn(s, 3502, SUB, ext, a0, TCG_REG_XZR, a1);
        break;

    case INDEX_op_and_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_and_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_ANDI, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3510, AND, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_andc_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_andc_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_ANDI, ext, a0, a1, ~a2);
        } else {
            tcg_out_insn(s, 3510, BIC, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_or_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_or_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_ORRI, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3510, ORR, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_orc_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_orc_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_ORRI, ext, a0, a1, ~a2);
        } else {
            tcg_out_insn(s, 3510, ORN, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_xor_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_xor_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_EORI, ext, a0, a1, a2);
        } else {
            tcg_out_insn(s, 3510, EOR, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_eqv_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_eqv_i64:
        if (c2) {
            tcg_out_logicali(s, I3404_EORI, ext, a0, a1, ~a2);
        } else {
            tcg_out_insn(s, 3510, EON, ext, a0, a1, a2);
        }
        break;

    case INDEX_op_not_i64:
    case INDEX_op_not_i32:
        tcg_out_insn(s, 3510, ORN, ext, a0, TCG_REG_XZR, a1);
        break;

    case INDEX_op_mul_i64:
    case INDEX_op_mul_i32:
        tcg_out_insn(s, 3509, MADD, ext, a0, a1, a2, TCG_REG_XZR);
        break;

    case INDEX_op_div_i64:
    case INDEX_op_div_i32:
        tcg_out_insn(s, 3508, SDIV, ext, a0, a1, a2);
        break;
    case INDEX_op_divu_i64:
    case INDEX_op_divu_i32:
        tcg_out_insn(s, 3508, UDIV, ext, a0, a1, a2);
        break;

    case INDEX_op_rem_i64:
    case INDEX_op_rem_i32:
        tcg_out_insn(s, 3508, SDIV, ext, TCG_REG_TMP, a1, a2);
        tcg_out_insn(s, 3509, MSUB, ext, a0, TCG_REG_TMP, a2, a1);
        break;
    case INDEX_op_remu_i64:
    case INDEX_op_remu_i32:
        tcg_out_insn(s, 3508, UDIV, ext, TCG_REG_TMP, a1, a2);
        tcg_out_insn(s, 3509, MSUB, ext, a0, TCG_REG_TMP, a2, a1);
        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_clz_i64:
    case INDEX_op_clz_i32:
        tcg_out_cltz(s, ext, a0, a1, a2, c2, false);
        break;
    case INDEX_op_ctz_i64:
    case INDEX_op_ctz_i32:
        tcg_out_cltz(s, ext, a0, a1, a2, c2, true);
        break;

    case INDEX_op_brcond_i32:
        a1 = (int32_t)a1;
        /* FALLTHRU */
    case INDEX_op_brcond_i64:
        tcg_out_brcond(s, ext, a2, a0, a1, const_args[1], arg_label(args[3]));
        break;

    case INDEX_op_setcond_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_setcond_i64:
        tcg_out_cmp(s, ext, a1, a2, c2);
        /* Use CSET alias of CSINC Wd, WZR, WZR, invert(cond).  */
        tcg_out_insn(s, 3506, CSINC, TCG_TYPE_I32, a0, TCG_REG_XZR,
                     TCG_REG_XZR, tcg_invert_cond(args[3]));
        break;

    case INDEX_op_movcond_i32:
        a2 = (int32_t)a2;
        /* FALLTHRU */
    case INDEX_op_movcond_i64:
        tcg_out_cmp(s, ext, a1, a2, c2);
        tcg_out_insn(s, 3506, CSEL, ext, a0, REG0(3), REG0(4), args[5]);
        break;

    case INDEX_op_qemu_ld_i32:
    case INDEX_op_qemu_ld_i64:
        tcg_out_qemu_ld(s, a0, a1, a2, ext);
        break;
    case INDEX_op_qemu_st_i32:
    case INDEX_op_qemu_st_i64:
        tcg_out_qemu_st(s, REG0(0), a1, a2);
        break;

    case INDEX_op_bswap64_i64:
        tcg_out_rev64(s, a0, a1);
        break;
    case INDEX_op_bswap32_i64:
    case INDEX_op_bswap32_i32:
        tcg_out_rev32(s, a0, a1);
        break;
    case INDEX_op_bswap16_i64:
    case INDEX_op_bswap16_i32:
        tcg_out_rev16(s, a0, a1);
        break;

    case INDEX_op_ext8s_i64:
    case INDEX_op_ext8s_i32:
        tcg_out_sxt(s, ext, MO_8, a0, a1);
        break;
    case INDEX_op_ext16s_i64:
    case INDEX_op_ext16s_i32:
        tcg_out_sxt(s, ext, MO_16, a0, a1);
        break;
    case INDEX_op_ext_i32_i64:
    case INDEX_op_ext32s_i64:
        tcg_out_sxt(s, TCG_TYPE_I64, MO_32, a0, a1);
        break;
    case INDEX_op_ext8u_i64:
    case INDEX_op_ext8u_i32:
        tcg_out_uxt(s, MO_8, a0, a1);
        break;
    case INDEX_op_ext16u_i64:
    case INDEX_op_ext16u_i32:
        tcg_out_uxt(s, MO_16, a0, a1);
        break;
    case INDEX_op_extu_i32_i64:
    case INDEX_op_ext32u_i64:
        tcg_out_movr(s, TCG_TYPE_I32, a0, a1);
        break;

    case INDEX_op_deposit_i64:
    case INDEX_op_deposit_i32:
        tcg_out_dep(s, ext, a0, REG0(2), args[3], args[4]);
        break;

    case INDEX_op_extract_i64:
    case INDEX_op_extract_i32:
        tcg_out_ubfm(s, ext, a0, a1, a2, a2 + args[3] - 1);
        break;

    case INDEX_op_sextract_i64:
    case INDEX_op_sextract_i32:
        tcg_out_sbfm(s, ext, a0, a1, a2, a2 + args[3] - 1);
        break;

    case INDEX_op_add2_i32:
        tcg_out_addsub2(s, TCG_TYPE_I32, a0, a1, REG0(2), REG0(3),
                        (int32_t)args[4], args[5], const_args[4],
                        const_args[5], false);
        break;
    case INDEX_op_add2_i64:
        tcg_out_addsub2(s, TCG_TYPE_I64, a0, a1, REG0(2), REG0(3), args[4],
                        args[5], const_args[4], const_args[5], false);
        break;
    case INDEX_op_sub2_i32:
        tcg_out_addsub2(s, TCG_TYPE_I32, a0, a1, REG0(2), REG0(3),
                        (int32_t)args[4], args[5], const_args[4],
                        const_args[5], true);
        break;
    case INDEX_op_sub2_i64:
        tcg_out_addsub2(s, TCG_TYPE_I64, a0, a1, REG0(2), REG0(3), args[4],
                        args[5], const_args[4], const_args[5], true);
        break;

    case INDEX_op_muluh_i64:
        tcg_out_insn(s, 3508, UMULH, TCG_TYPE_I64, a0, a1, a2);
        break;
    case INDEX_op_mulsh_i64:
        tcg_out_insn(s, 3508, SMULH, TCG_TYPE_I64, a0, a1, a2);
        break;

    case INDEX_op_mb:
        tcg_out_mb(s, a0);
        break;

    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
    case INDEX_op_mov_i64:
    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
    case INDEX_op_movi_i64:
    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
    default:
        tcg_abort();
    }

#undef REG0
}

static const TCGTargetOpDef aarch64_op_defs[] = {
    { INDEX_op_exit_tb, { } },
    { INDEX_op_goto_tb, { } },
    { INDEX_op_br, { } },
    { INDEX_op_goto_ptr, { "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, { "rZ", "r" } },
    { INDEX_op_st16_i32, { "rZ", "r" } },
    { INDEX_op_st_i32, { "rZ", "r" } },
    { INDEX_op_st8_i64, { "rZ", "r" } },
    { INDEX_op_st16_i64, { "rZ", "r" } },
    { INDEX_op_st32_i64, { "rZ", "r" } },
    { INDEX_op_st_i64, { "rZ", "r" } },

    { INDEX_op_add_i32, { "r", "r", "rA" } },
    { INDEX_op_add_i64, { "r", "r", "rA" } },
    { INDEX_op_sub_i32, { "r", "r", "rA" } },
    { INDEX_op_sub_i64, { "r", "r", "rA" } },
    { INDEX_op_mul_i32, { "r", "r", "r" } },
    { INDEX_op_mul_i64, { "r", "r", "r" } },
    { INDEX_op_div_i32, { "r", "r", "r" } },
    { INDEX_op_div_i64, { "r", "r", "r" } },
    { INDEX_op_divu_i32, { "r", "r", "r" } },
    { INDEX_op_divu_i64, { "r", "r", "r" } },
    { INDEX_op_rem_i32, { "r", "r", "r" } },
    { INDEX_op_rem_i64, { "r", "r", "r" } },
    { INDEX_op_remu_i32, { "r", "r", "r" } },
    { INDEX_op_remu_i64, { "r", "r", "r" } },
    { INDEX_op_and_i32, { "r", "r", "rL" } },
    { INDEX_op_and_i64, { "r", "r", "rL" } },
    { INDEX_op_or_i32, { "r", "r", "rL" } },
    { INDEX_op_or_i64, { "r", "r", "rL" } },
    { INDEX_op_xor_i32, { "r", "r", "rL" } },
    { INDEX_op_xor_i64, { "r", "r", "rL" } },
    { INDEX_op_andc_i32, { "r", "r", "rL" } },
    { INDEX_op_andc_i64, { "r", "r", "rL" } },
    { INDEX_op_orc_i32, { "r", "r", "rL" } },
    { INDEX_op_orc_i64, { "r", "r", "rL" } },
    { INDEX_op_eqv_i32, { "r", "r", "rL" } },
    { INDEX_op_eqv_i64, { "r", "r", "rL" } },

    { INDEX_op_neg_i32, { "r", "r" } },
    { INDEX_op_neg_i64, { "r", "r" } },
    { INDEX_op_not_i32, { "r", "r" } },
    { INDEX_op_not_i64, { "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_clz_i32, { "r", "r", "rAL" } },
    { INDEX_op_ctz_i32, { "r", "r", "rAL" } },
    { 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_clz_i64, { "r", "r", "rAL" } },
    { INDEX_op_ctz_i64, { "r", "r", "rAL" } },

    { INDEX_op_brcond_i32, { "r", "rA" } },
    { INDEX_op_brcond_i64, { "r", "rA" } },
    { INDEX_op_setcond_i32, { "r", "r", "rA" } },
    { INDEX_op_setcond_i64, { "r", "r", "rA" } },
    { INDEX_op_movcond_i32, { "r", "r", "rA", "rZ", "rZ" } },
    { INDEX_op_movcond_i64, { "r", "r", "rA", "rZ", "rZ" } },

    { INDEX_op_qemu_ld_i32, { "r", "l" } },
    { INDEX_op_qemu_ld_i64, { "r", "l" } },
    { INDEX_op_qemu_st_i32, { "lZ", "l" } },
    { INDEX_op_qemu_st_i64, { "lZ", "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" } },
    { INDEX_op_ext_i32_i64, { "r", "r" } },
    { INDEX_op_extu_i32_i64, { "r", "r" } },

    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
    { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
    { INDEX_op_extract_i32, { "r", "r" } },
    { INDEX_op_extract_i64, { "r", "r" } },
    { INDEX_op_sextract_i32, { "r", "r" } },
    { INDEX_op_sextract_i64, { "r", "r" } },

    { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
    { INDEX_op_add2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
    { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
    { INDEX_op_sub2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },

    { INDEX_op_muluh_i64, { "r", "r", "r" } },
    { INDEX_op_mulsh_i64, { "r", "r", "r" } },

    { INDEX_op_mb, { } },
    { -1 },
};

static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
{
    int i, n = ARRAY_SIZE(aarch64_op_defs);

    for (i = 0; i < n; ++i) {
        if (aarch64_op_defs[i].op == op) {
            return &aarch64_op_defs[i];
        }
    }
    return NULL;
}

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) | (1 << TCG_REG_X30));

    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 */
}

/* Saving pairs: (X19, X20) .. (X27, X28), (X29(fp), X30(lr)).  */
#define PUSH_SIZE  ((30 - 19 + 1) * 8)

#define FRAME_SIZE \
    ((PUSH_SIZE \
      + TCG_STATIC_CALL_ARGS_SIZE \
      + CPU_TEMP_BUF_NLONGS * sizeof(long) \
      + TCG_TARGET_STACK_ALIGN - 1) \
     & ~(TCG_TARGET_STACK_ALIGN - 1))

/* We're expecting a 2 byte uleb128 encoded value.  */
QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));

/* We're expecting to use a single ADDI insn.  */
QEMU_BUILD_BUG_ON(FRAME_SIZE - PUSH_SIZE > 0xfff);

static void tcg_target_qemu_prologue(TCGContext *s)
{
    TCGReg r;

    /* Push (FP, LR) and allocate space for all saved registers.  */
    tcg_out_insn(s, 3314, STP, TCG_REG_FP, TCG_REG_LR,
                 TCG_REG_SP, -PUSH_SIZE, 1, 1);

    /* Set up frame pointer for canonical unwinding.  */
    tcg_out_movr_sp(s, TCG_TYPE_I64, TCG_REG_FP, TCG_REG_SP);

    /* Store callee-preserved regs x19..x28.  */
    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
        int ofs = (r - TCG_REG_X19 + 2) * 8;
        tcg_out_insn(s, 3314, STP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
    }

    /* Make stack space for TCG locals.  */
    tcg_out_insn(s, 3401, SUBI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
                 FRAME_SIZE - PUSH_SIZE);

    /* 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_SOFTMMU)
    if (USE_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_insn(s, 3207, BR, tcg_target_call_iarg_regs[1]);

    /*
     * Return path for goto_ptr. Set return value to 0, a-la exit_tb,
     * and fall through to the rest of the epilogue.
     */
    s->code_gen_epilogue = s->code_ptr;
    tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_X0, 0);

    /* TB epilogue */
    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 - PUSH_SIZE);

    /* Restore registers x19..x28.  */
    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
        int ofs = (r - TCG_REG_X19 + 2) * 8;
        tcg_out_insn(s, 3314, LDP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
    }

    /* Pop (FP, LR), restore SP to previous frame.  */
    tcg_out_insn(s, 3314, LDP, TCG_REG_FP, TCG_REG_LR,
                 TCG_REG_SP, PUSH_SIZE, 0, 1);
    tcg_out_insn(s, 3207, RET, TCG_REG_LR);
}

typedef struct {
    DebugFrameHeader h;
    uint8_t fde_def_cfa[4];
    uint8_t fde_reg_ofs[24];
} DebugFrame;

#define ELF_HOST_MACHINE EM_AARCH64

static const DebugFrame debug_frame = {
    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
    .h.cie.id = -1,
    .h.cie.version = 1,
    .h.cie.code_align = 1,
    .h.cie.data_align = 0x78,             /* sleb128 -8 */
    .h.cie.return_column = TCG_REG_LR,

    /* Total FDE size does not include the "len" member.  */
    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),

    .fde_def_cfa = {
        12, TCG_REG_SP,                 /* DW_CFA_def_cfa sp, ... */
        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
        (FRAME_SIZE >> 7)
    },
    .fde_reg_ofs = {
        0x80 + 28, 1,                   /* DW_CFA_offset, x28,  -8 */
        0x80 + 27, 2,                   /* DW_CFA_offset, x27, -16 */
        0x80 + 26, 3,                   /* DW_CFA_offset, x26, -24 */
        0x80 + 25, 4,                   /* DW_CFA_offset, x25, -32 */
        0x80 + 24, 5,                   /* DW_CFA_offset, x24, -40 */
        0x80 + 23, 6,                   /* DW_CFA_offset, x23, -48 */
        0x80 + 22, 7,                   /* DW_CFA_offset, x22, -56 */
        0x80 + 21, 8,                   /* DW_CFA_offset, x21, -64 */
        0x80 + 20, 9,                   /* DW_CFA_offset, x20, -72 */
        0x80 + 19, 10,                  /* DW_CFA_offset, x1p, -80 */
        0x80 + 30, 11,                  /* DW_CFA_offset,  lr, -88 */
        0x80 + 29, 12,                  /* DW_CFA_offset,  fp, -96 */
    }
};

void tcg_register_jit(void *buf, size_t buf_size)
{
    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
}