aboutsummaryrefslogtreecommitdiff
path: root/tcg/arm/tcg-target.c
blob: 980d0308a349fa0ddd02738c6e771c6a242acd0e (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
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
/*
 * Tiny Code Generator for QEMU
 *
 * Copyright (c) 2008 Andrzej Zaborowski
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "tcg-be-ldst.h"

/* The __ARM_ARCH define is provided by gcc 4.8.  Construct it otherwise.  */
#ifndef __ARM_ARCH
# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
     || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) \
     || defined(__ARM_ARCH_7EM__)
#  define __ARM_ARCH 7
# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \
       || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) \
       || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6T2__)
#  define __ARM_ARCH 6
# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5E__) \
       || defined(__ARM_ARCH_5T__) || defined(__ARM_ARCH_5TE__) \
       || defined(__ARM_ARCH_5TEJ__)
#  define __ARM_ARCH 5
# else
#  define __ARM_ARCH 4
# endif
#endif

static int arm_arch = __ARM_ARCH;

#if defined(__ARM_ARCH_5T__) \
    || defined(__ARM_ARCH_5TE__) || defined(__ARM_ARCH_5TEJ__)
# define use_armv5t_instructions 1
#else
# define use_armv5t_instructions use_armv6_instructions
#endif

#define use_armv6_instructions  (__ARM_ARCH >= 6 || arm_arch >= 6)
#define use_armv7_instructions  (__ARM_ARCH >= 7 || arm_arch >= 7)

#ifndef use_idiv_instructions
bool use_idiv_instructions;
#endif
#ifdef CONFIG_GETAUXVAL
# include <sys/auxv.h>
#endif

#ifndef NDEBUG
static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
    "%r0",
    "%r1",
    "%r2",
    "%r3",
    "%r4",
    "%r5",
    "%r6",
    "%r7",
    "%r8",
    "%r9",
    "%r10",
    "%r11",
    "%r12",
    "%r13",
    "%r14",
    "%pc",
};
#endif

static const int tcg_target_reg_alloc_order[] = {
    TCG_REG_R4,
    TCG_REG_R5,
    TCG_REG_R6,
    TCG_REG_R7,
    TCG_REG_R8,
    TCG_REG_R9,
    TCG_REG_R10,
    TCG_REG_R11,
    TCG_REG_R13,
    TCG_REG_R0,
    TCG_REG_R1,
    TCG_REG_R2,
    TCG_REG_R3,
    TCG_REG_R12,
    TCG_REG_R14,
};

static const int tcg_target_call_iarg_regs[4] = {
    TCG_REG_R0, TCG_REG_R1, TCG_REG_R2, TCG_REG_R3
};
static const int tcg_target_call_oarg_regs[2] = {
    TCG_REG_R0, TCG_REG_R1
};

#define TCG_REG_TMP  TCG_REG_R12

static inline void reloc_abs32(void *code_ptr, intptr_t target)
{
    *(uint32_t *) code_ptr = target;
}

static inline void reloc_pc24(void *code_ptr, intptr_t target)
{
    uint32_t offset = ((target - ((intptr_t)code_ptr + 8)) >> 2);

    *(uint32_t *) code_ptr = ((*(uint32_t *) code_ptr) & ~0xffffff)
                             | (offset & 0xffffff);
}

static void patch_reloc(uint8_t *code_ptr, int type,
                        intptr_t value, intptr_t addend)
{
    switch (type) {
    case R_ARM_ABS32:
        reloc_abs32(code_ptr, value);
        break;

    case R_ARM_CALL:
    case R_ARM_JUMP24:
    default:
        tcg_abort();

    case R_ARM_PC24:
        reloc_pc24(code_ptr, value);
        break;
    }
}

#define TCG_CT_CONST_ARM  0x100
#define TCG_CT_CONST_INV  0x200
#define TCG_CT_CONST_NEG  0x400
#define TCG_CT_CONST_ZERO 0x800

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

    ct_str = *pct_str;
    switch (ct_str[0]) {
    case 'I':
        ct->ct |= TCG_CT_CONST_ARM;
        break;
    case 'K':
        ct->ct |= TCG_CT_CONST_INV;
        break;
    case 'N': /* The gcc constraint letter is L, already used here.  */
        ct->ct |= TCG_CT_CONST_NEG;
        break;
    case 'Z':
        ct->ct |= TCG_CT_CONST_ZERO;
        break;

    case 'r':
        ct->ct |= TCG_CT_REG;
        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
        break;

    /* qemu_ld address */
    case 'l':
        ct->ct |= TCG_CT_REG;
        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
#ifdef CONFIG_SOFTMMU
        /* r0-r2,lr will be overwritten when reading the tlb entry,
           so don't use these. */
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R0);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R1);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R2);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R14);
#endif
        break;

    /* qemu_st address & data_reg */
    case 's':
        ct->ct |= TCG_CT_REG;
        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
        /* r0-r2 will be overwritten when reading the tlb entry (softmmu only)
           and r0-r1 doing the byte swapping, so don't use these. */
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R0);
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R1);
#if defined(CONFIG_SOFTMMU)
        /* Avoid clashes with registers being used for helper args */
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R2);
#if TARGET_LONG_BITS == 64
        /* Avoid clashes with registers being used for helper args */
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
#endif
        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R14);
#endif
        break;

    default:
        return -1;
    }
    ct_str++;
    *pct_str = ct_str;

    return 0;
}

static inline uint32_t rotl(uint32_t val, int n)
{
  return (val << n) | (val >> (32 - n));
}

/* ARM immediates for ALU instructions are made of an unsigned 8-bit
   right-rotated by an even amount between 0 and 30. */
static inline int encode_imm(uint32_t imm)
{
    int shift;

    /* simple case, only lower bits */
    if ((imm & ~0xff) == 0)
        return 0;
    /* then try a simple even shift */
    shift = ctz32(imm) & ~1;
    if (((imm >> shift) & ~0xff) == 0)
        return 32 - shift;
    /* now try harder with rotations */
    if ((rotl(imm, 2) & ~0xff) == 0)
        return 2;
    if ((rotl(imm, 4) & ~0xff) == 0)
        return 4;
    if ((rotl(imm, 6) & ~0xff) == 0)
        return 6;
    /* imm can't be encoded */
    return -1;
}

static inline int check_fit_imm(uint32_t imm)
{
    return encode_imm(imm) >= 0;
}

/* Test if a constant matches the constraint.
 * TODO: define constraints for:
 *
 * ldr/str offset:   between -0xfff and 0xfff
 * ldrh/strh offset: between -0xff and 0xff
 * mov operand2:     values represented with x << (2 * y), x < 0x100
 * add, sub, eor...: ditto
 */
static inline int tcg_target_const_match(tcg_target_long val,
                                         const TCGArgConstraint *arg_ct)
{
    int ct;
    ct = arg_ct->ct;
    if (ct & TCG_CT_CONST) {
        return 1;
    } else if ((ct & TCG_CT_CONST_ARM) && check_fit_imm(val)) {
        return 1;
    } else if ((ct & TCG_CT_CONST_INV) && check_fit_imm(~val)) {
        return 1;
    } else if ((ct & TCG_CT_CONST_NEG) && check_fit_imm(-val)) {
        return 1;
    } else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
        return 1;
    } else {
        return 0;
    }
}

#define TO_CPSR (1 << 20)

typedef enum {
    ARITH_AND = 0x0 << 21,
    ARITH_EOR = 0x1 << 21,
    ARITH_SUB = 0x2 << 21,
    ARITH_RSB = 0x3 << 21,
    ARITH_ADD = 0x4 << 21,
    ARITH_ADC = 0x5 << 21,
    ARITH_SBC = 0x6 << 21,
    ARITH_RSC = 0x7 << 21,
    ARITH_TST = 0x8 << 21 | TO_CPSR,
    ARITH_CMP = 0xa << 21 | TO_CPSR,
    ARITH_CMN = 0xb << 21 | TO_CPSR,
    ARITH_ORR = 0xc << 21,
    ARITH_MOV = 0xd << 21,
    ARITH_BIC = 0xe << 21,
    ARITH_MVN = 0xf << 21,

    INSN_LDR_IMM   = 0x04100000,
    INSN_LDR_REG   = 0x06100000,
    INSN_STR_IMM   = 0x04000000,
    INSN_STR_REG   = 0x06000000,

    INSN_LDRH_IMM  = 0x005000b0,
    INSN_LDRH_REG  = 0x001000b0,
    INSN_LDRSH_IMM = 0x005000f0,
    INSN_LDRSH_REG = 0x001000f0,
    INSN_STRH_IMM  = 0x004000b0,
    INSN_STRH_REG  = 0x000000b0,

    INSN_LDRB_IMM  = 0x04500000,
    INSN_LDRB_REG  = 0x06500000,
    INSN_LDRSB_IMM = 0x005000d0,
    INSN_LDRSB_REG = 0x001000d0,
    INSN_STRB_IMM  = 0x04400000,
    INSN_STRB_REG  = 0x06400000,

    INSN_LDRD_IMM  = 0x004000d0,
    INSN_LDRD_REG  = 0x000000d0,
    INSN_STRD_IMM  = 0x004000f0,
    INSN_STRD_REG  = 0x000000f0,
} ARMInsn;

#define SHIFT_IMM_LSL(im)	(((im) << 7) | 0x00)
#define SHIFT_IMM_LSR(im)	(((im) << 7) | 0x20)
#define SHIFT_IMM_ASR(im)	(((im) << 7) | 0x40)
#define SHIFT_IMM_ROR(im)	(((im) << 7) | 0x60)
#define SHIFT_REG_LSL(rs)	(((rs) << 8) | 0x10)
#define SHIFT_REG_LSR(rs)	(((rs) << 8) | 0x30)
#define SHIFT_REG_ASR(rs)	(((rs) << 8) | 0x50)
#define SHIFT_REG_ROR(rs)	(((rs) << 8) | 0x70)

enum arm_cond_code_e {
    COND_EQ = 0x0,
    COND_NE = 0x1,
    COND_CS = 0x2,	/* Unsigned greater or equal */
    COND_CC = 0x3,	/* Unsigned less than */
    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,
};

static const uint8_t tcg_cond_to_arm_cond[] = {
    [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_CC,
    [TCG_COND_GEU] = COND_CS,
    [TCG_COND_LEU] = COND_LS,
    [TCG_COND_GTU] = COND_HI,
};

static inline void tcg_out_bx(TCGContext *s, int cond, int rn)
{
    tcg_out32(s, (cond << 28) | 0x012fff10 | rn);
}

static inline void tcg_out_b(TCGContext *s, int cond, int32_t offset)
{
    tcg_out32(s, (cond << 28) | 0x0a000000 |
                    (((offset - 8) >> 2) & 0x00ffffff));
}

static inline void tcg_out_b_noaddr(TCGContext *s, int cond)
{
    /* We pay attention here to not modify the branch target by skipping
       the corresponding bytes. This ensure that caches and memory are
       kept coherent during retranslation. */
    s->code_ptr += 3;
    tcg_out8(s, (cond << 4) | 0x0a);
}

static inline void tcg_out_bl_noaddr(TCGContext *s, int cond)
{
    /* We pay attention here to not modify the branch target by skipping
       the corresponding bytes. This ensure that caches and memory are
       kept coherent during retranslation. */
    s->code_ptr += 3;
    tcg_out8(s, (cond << 4) | 0x0b);
}

static inline void tcg_out_bl(TCGContext *s, int cond, int32_t offset)
{
    tcg_out32(s, (cond << 28) | 0x0b000000 |
                    (((offset - 8) >> 2) & 0x00ffffff));
}

static inline void tcg_out_blx(TCGContext *s, int cond, int rn)
{
    tcg_out32(s, (cond << 28) | 0x012fff30 | rn);
}

static inline void tcg_out_blx_imm(TCGContext *s, int32_t offset)
{
    tcg_out32(s, 0xfa000000 | ((offset & 2) << 23) |
                (((offset - 8) >> 2) & 0x00ffffff));
}

static inline void tcg_out_dat_reg(TCGContext *s,
                int cond, int opc, int rd, int rn, int rm, int shift)
{
    tcg_out32(s, (cond << 28) | (0 << 25) | opc |
                    (rn << 16) | (rd << 12) | shift | rm);
}

static inline void tcg_out_nop(TCGContext *s)
{
    if (use_armv7_instructions) {
        /* Architected nop introduced in v6k.  */
        /* ??? This is an MSR (imm) 0,0,0 insn.  Anyone know if this
           also Just So Happened to do nothing on pre-v6k so that we
           don't need to conditionalize it?  */
        tcg_out32(s, 0xe320f000);
    } else {
        /* Prior to that the assembler uses mov r0, r0.  */
        tcg_out_dat_reg(s, COND_AL, ARITH_MOV, 0, 0, 0, SHIFT_IMM_LSL(0));
    }
}

static inline void tcg_out_mov_reg(TCGContext *s, int cond, int rd, int rm)
{
    /* Simple reg-reg move, optimising out the 'do nothing' case */
    if (rd != rm) {
        tcg_out_dat_reg(s, cond, ARITH_MOV, rd, 0, rm, SHIFT_IMM_LSL(0));
    }
}

static inline void tcg_out_dat_imm(TCGContext *s,
                int cond, int opc, int rd, int rn, int im)
{
    tcg_out32(s, (cond << 28) | (1 << 25) | opc |
                    (rn << 16) | (rd << 12) | im);
}

static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg)
{
    int rot, opc, rn;

    /* For armv7, make sure not to use movw+movt when mov/mvn would do.
       Speed things up by only checking when movt would be required.
       Prior to armv7, have one go at fully rotated immediates before
       doing the decomposition thing below.  */
    if (!use_armv7_instructions || (arg & 0xffff0000)) {
        rot = encode_imm(arg);
        if (rot >= 0) {
            tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0,
                            rotl(arg, rot) | (rot << 7));
            return;
        }
        rot = encode_imm(~arg);
        if (rot >= 0) {
            tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0,
                            rotl(~arg, rot) | (rot << 7));
            return;
        }
    }

    /* Use movw + movt.  */
    if (use_armv7_instructions) {
        /* movw */
        tcg_out32(s, (cond << 28) | 0x03000000 | (rd << 12)
                  | ((arg << 4) & 0x000f0000) | (arg & 0xfff));
        if (arg & 0xffff0000) {
            /* movt */
            tcg_out32(s, (cond << 28) | 0x03400000 | (rd << 12)
                      | ((arg >> 12) & 0x000f0000) | ((arg >> 16) & 0xfff));
        }
        return;
    }

    /* TODO: This is very suboptimal, we can easily have a constant
       pool somewhere after all the instructions.  */
    opc = ARITH_MOV;
    rn = 0;
    /* If we have lots of leading 1's, we can shorten the sequence by
       beginning with mvn and then clearing higher bits with eor.  */
    if (clz32(~arg) > clz32(arg)) {
        opc = ARITH_MVN, arg = ~arg;
    }
    do {
        int i = ctz32(arg) & ~1;
        rot = ((32 - i) << 7) & 0xf00;
        tcg_out_dat_imm(s, cond, opc, rd, rn, ((arg >> i) & 0xff) | rot);
        arg &= ~(0xff << i);

        opc = ARITH_EOR;
        rn = rd;
    } while (arg);
}

static inline void tcg_out_dat_rI(TCGContext *s, int cond, int opc, TCGArg dst,
                                  TCGArg lhs, TCGArg rhs, int rhs_is_const)
{
    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
     * rhs must satisfy the "rI" constraint.
     */
    if (rhs_is_const) {
        int rot = encode_imm(rhs);
        assert(rot >= 0);
        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
    } else {
        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
    }
}

static void tcg_out_dat_rIK(TCGContext *s, int cond, int opc, int opinv,
                            TCGReg dst, TCGReg lhs, TCGArg rhs,
                            bool rhs_is_const)
{
    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
     * rhs must satisfy the "rIK" constraint.
     */
    if (rhs_is_const) {
        int rot = encode_imm(rhs);
        if (rot < 0) {
            rhs = ~rhs;
            rot = encode_imm(rhs);
            assert(rot >= 0);
            opc = opinv;
        }
        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
    } else {
        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
    }
}

static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg,
                            TCGArg dst, TCGArg lhs, TCGArg rhs,
                            bool rhs_is_const)
{
    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
     * rhs must satisfy the "rIN" constraint.
     */
    if (rhs_is_const) {
        int rot = encode_imm(rhs);
        if (rot < 0) {
            rhs = -rhs;
            rot = encode_imm(rhs);
            assert(rot >= 0);
            opc = opneg;
        }
        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
    } else {
        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
    }
}

static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd,
                                 TCGReg rn, TCGReg rm)
{
    /* if ArchVersion() < 6 && d == n then UNPREDICTABLE;  */
    if (!use_armv6_instructions && rd == rn) {
        if (rd == rm) {
            /* rd == rn == rm; copy an input to tmp first.  */
            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
            rm = rn = TCG_REG_TMP;
        } else {
            rn = rm;
            rm = rd;
        }
    }
    /* mul */
    tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn);
}

static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0,
                                   TCGReg rd1, TCGReg rn, TCGReg rm)
{
    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
        if (rd0 == rm || rd1 == rm) {
            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
            rn = TCG_REG_TMP;
        } else {
            TCGReg t = rn;
            rn = rm;
            rm = t;
        }
    }
    /* umull */
    tcg_out32(s, (cond << 28) | 0x00800090 |
              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
}

static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0,
                                   TCGReg rd1, TCGReg rn, TCGReg rm)
{
    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
        if (rd0 == rm || rd1 == rm) {
            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
            rn = TCG_REG_TMP;
        } else {
            TCGReg t = rn;
            rn = rm;
            rm = t;
        }
    }
    /* smull */
    tcg_out32(s, (cond << 28) | 0x00c00090 |
              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
}

static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm)
{
    tcg_out32(s, 0x0710f010 | (cond << 28) | (rd << 16) | rn | (rm << 8));
}

static inline void tcg_out_udiv(TCGContext *s, int cond, int rd, int rn, int rm)
{
    tcg_out32(s, 0x0730f010 | (cond << 28) | (rd << 16) | rn | (rm << 8));
}

static inline void tcg_out_ext8s(TCGContext *s, int cond,
                                 int rd, int rn)
{
    if (use_armv6_instructions) {
        /* sxtb */
        tcg_out32(s, 0x06af0070 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rn, SHIFT_IMM_LSL(24));
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rd, SHIFT_IMM_ASR(24));
    }
}

static inline void tcg_out_ext8u(TCGContext *s, int cond,
                                 int rd, int rn)
{
    tcg_out_dat_imm(s, cond, ARITH_AND, rd, rn, 0xff);
}

static inline void tcg_out_ext16s(TCGContext *s, int cond,
                                  int rd, int rn)
{
    if (use_armv6_instructions) {
        /* sxth */
        tcg_out32(s, 0x06bf0070 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rn, SHIFT_IMM_LSL(16));
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rd, SHIFT_IMM_ASR(16));
    }
}

static inline void tcg_out_ext16u(TCGContext *s, int cond,
                                  int rd, int rn)
{
    if (use_armv6_instructions) {
        /* uxth */
        tcg_out32(s, 0x06ff0070 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rn, SHIFT_IMM_LSL(16));
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rd, SHIFT_IMM_LSR(16));
    }
}

static inline void tcg_out_bswap16s(TCGContext *s, int cond, int rd, int rn)
{
    if (use_armv6_instructions) {
        /* revsh */
        tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_ASR(16));
        tcg_out_dat_reg(s, cond, ARITH_ORR,
                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
    }
}

static inline void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn)
{
    if (use_armv6_instructions) {
        /* rev16 */
        tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSR(16));
        tcg_out_dat_reg(s, cond, ARITH_ORR,
                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
    }
}

/* swap the two low bytes assuming that the two high input bytes and the
   two high output bit can hold any value. */
static inline void tcg_out_bswap16st(TCGContext *s, int cond, int rd, int rn)
{
    if (use_armv6_instructions) {
        /* rev16 */
        tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8));
        tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff);
        tcg_out_dat_reg(s, cond, ARITH_ORR,
                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8));
    }
}

static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
{
    if (use_armv6_instructions) {
        /* rev */
        tcg_out32(s, 0x06bf0f30 | (cond << 28) | (rd << 12) | rn);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_EOR,
                        TCG_REG_TMP, rn, rn, SHIFT_IMM_ROR(16));
        tcg_out_dat_imm(s, cond, ARITH_BIC,
                        TCG_REG_TMP, TCG_REG_TMP, 0xff | 0x800);
        tcg_out_dat_reg(s, cond, ARITH_MOV,
                        rd, 0, rn, SHIFT_IMM_ROR(8));
        tcg_out_dat_reg(s, cond, ARITH_EOR,
                        rd, rd, TCG_REG_TMP, SHIFT_IMM_LSR(8));
    }
}

bool tcg_target_deposit_valid(int ofs, int len)
{
    /* ??? Without bfi, we could improve over generic code by combining
       the right-shift from a non-zero ofs with the orr.  We do run into
       problems when rd == rs, and the mask generated from ofs+len doesn't
       fit into an immediate.  We would have to be careful not to pessimize
       wrt the optimizations performed on the expanded code.  */
    return use_armv7_instructions;
}

static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd,
                                   TCGArg a1, int ofs, int len, bool const_a1)
{
    if (const_a1) {
        /* bfi becomes bfc with rn == 15.  */
        a1 = 15;
    }
    /* bfi/bfc */
    tcg_out32(s, 0x07c00010 | (cond << 28) | (rd << 12) | a1
              | (ofs << 7) | ((ofs + len - 1) << 16));
}

/* Note that this routine is used for both LDR and LDRH formats, so we do
   not wish to include an immediate shift at this point.  */
static void tcg_out_memop_r(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
                            TCGReg rn, TCGReg rm, bool u, bool p, bool w)
{
    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24)
              | (w << 21) | (rn << 16) | (rt << 12) | rm);
}

static void tcg_out_memop_8(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
                            TCGReg rn, int imm8, bool p, bool w)
{
    bool u = 1;
    if (imm8 < 0) {
        imm8 = -imm8;
        u = 0;
    }
    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24) | (w << 21) |
              (rn << 16) | (rt << 12) | ((imm8 & 0xf0) << 4) | (imm8 & 0xf));
}

static void tcg_out_memop_12(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
                             TCGReg rn, int imm12, bool p, bool w)
{
    bool u = 1;
    if (imm12 < 0) {
        imm12 = -imm12;
        u = 0;
    }
    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24) | (w << 21) |
              (rn << 16) | (rt << 12) | imm12);
}

static inline void tcg_out_ld32_12(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm12)
{
    tcg_out_memop_12(s, cond, INSN_LDR_IMM, rt, rn, imm12, 1, 0);
}

static inline void tcg_out_st32_12(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm12)
{
    tcg_out_memop_12(s, cond, INSN_STR_IMM, rt, rn, imm12, 1, 0);
}

static inline void tcg_out_ld32_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_st32_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_ldrd_8(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_LDRD_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_ldrd_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDRD_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_strd_8(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_STRD_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_strd_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_STRD_REG, rt, rn, rm, 1, 1, 0);
}

/* Register pre-increment with base writeback.  */
static inline void tcg_out_ld32_rwb(TCGContext *s, int cond, TCGReg rt,
                                    TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 1);
}

static inline void tcg_out_st32_rwb(TCGContext *s, int cond, TCGReg rt,
                                    TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 1);
}

static inline void tcg_out_ld16u_8(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_LDRH_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_st16_8(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_STRH_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_ld16u_r(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDRH_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_st16_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_STRH_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_ld16s_8(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_LDRSH_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_ld16s_r(TCGContext *s, int cond, TCGReg rt,
                                   TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDRSH_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_ld8_12(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, int imm12)
{
    tcg_out_memop_12(s, cond, INSN_LDRB_IMM, rt, rn, imm12, 1, 0);
}

static inline void tcg_out_st8_12(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, int imm12)
{
    tcg_out_memop_12(s, cond, INSN_STRB_IMM, rt, rn, imm12, 1, 0);
}

static inline void tcg_out_ld8_r(TCGContext *s, int cond, TCGReg rt,
                                 TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDRB_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_st8_r(TCGContext *s, int cond, TCGReg rt,
                                 TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_STRB_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_ld8s_8(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, int imm8)
{
    tcg_out_memop_8(s, cond, INSN_LDRSB_IMM, rt, rn, imm8, 1, 0);
}

static inline void tcg_out_ld8s_r(TCGContext *s, int cond, TCGReg rt,
                                  TCGReg rn, TCGReg rm)
{
    tcg_out_memop_r(s, cond, INSN_LDRSB_REG, rt, rn, rm, 1, 1, 0);
}

static inline void tcg_out_ld32u(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xfff || offset < -0xfff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_ld32_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_ld32_12(s, cond, rd, rn, offset);
}

static inline void tcg_out_st32(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xfff || offset < -0xfff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_st32_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_st32_12(s, cond, rd, rn, offset);
}

static inline void tcg_out_ld16u(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xff || offset < -0xff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_ld16u_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_ld16u_8(s, cond, rd, rn, offset);
}

static inline void tcg_out_ld16s(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xff || offset < -0xff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_ld16s_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_ld16s_8(s, cond, rd, rn, offset);
}

static inline void tcg_out_st16(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xff || offset < -0xff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_st16_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_st16_8(s, cond, rd, rn, offset);
}

static inline void tcg_out_ld8u(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xfff || offset < -0xfff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_ld8_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_ld8_12(s, cond, rd, rn, offset);
}

static inline void tcg_out_ld8s(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xff || offset < -0xff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_ld8s_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_ld8s_8(s, cond, rd, rn, offset);
}

static inline void tcg_out_st8(TCGContext *s, int cond,
                int rd, int rn, int32_t offset)
{
    if (offset > 0xfff || offset < -0xfff) {
        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
        tcg_out_st8_r(s, cond, rd, rn, TCG_REG_TMP);
    } else
        tcg_out_st8_12(s, cond, rd, rn, offset);
}

/* The _goto case is normally between TBs within the same code buffer, and
 * with the code buffer limited to 16MB we wouldn't need the long case.
 * But we also use it for the tail-call to the qemu_ld/st helpers, which does.
 */
static inline void tcg_out_goto(TCGContext *s, int cond, uint32_t addr)
{
    int32_t disp = addr - (tcg_target_long) s->code_ptr;

    if ((addr & 1) == 0 && disp - 8 < 0x01fffffd && disp - 8 > -0x01fffffd) {
        tcg_out_b(s, cond, disp);
        return;
    }

    tcg_out_movi32(s, cond, TCG_REG_TMP, addr);
    if (use_armv5t_instructions) {
        tcg_out_bx(s, cond, TCG_REG_TMP);
    } else {
        if (addr & 1) {
            tcg_abort();
        }
        tcg_out_mov_reg(s, cond, TCG_REG_PC, TCG_REG_TMP);
    }
}

/* The call case is mostly used for helpers - so it's not unreasonable
 * for them to be beyond branch range */
static inline void tcg_out_call(TCGContext *s, uint32_t addr)
{
    int32_t val;

    val = addr - (tcg_target_long) s->code_ptr;
    if (val - 8 < 0x02000000 && val - 8 >= -0x02000000) {
        if (addr & 1) {
            /* Use BLX if the target is in Thumb mode */
            if (!use_armv5t_instructions) {
                tcg_abort();
            }
            tcg_out_blx_imm(s, val);
        } else {
            tcg_out_bl(s, COND_AL, val);
        }
    } else if (use_armv7_instructions) {
        tcg_out_movi32(s, COND_AL, TCG_REG_TMP, addr);
        tcg_out_blx(s, COND_AL, TCG_REG_TMP);
    } else {
        tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R14, TCG_REG_PC, 4);
        tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_PC, -4);
        tcg_out32(s, addr);
    }
}

static inline void tcg_out_callr(TCGContext *s, int cond, int arg)
{
    if (use_armv5t_instructions) {
        tcg_out_blx(s, cond, arg);
    } else {
        tcg_out_dat_reg(s, cond, ARITH_MOV, TCG_REG_R14, 0,
                        TCG_REG_PC, SHIFT_IMM_LSL(0));
        tcg_out_bx(s, cond, arg);
    }
}

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

    if (l->has_value) {
        tcg_out_goto(s, cond, l->u.value);
    } else {
        tcg_out_reloc(s, s->code_ptr, R_ARM_PC24, label_index, 31337);
        tcg_out_b_noaddr(s, cond);
    }
}

#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[8] = {
    helper_ret_ldub_mmu,
    helper_ret_lduw_mmu,
    helper_ret_ldul_mmu,
    helper_ret_ldq_mmu,

    helper_ret_ldsb_mmu,
    helper_ret_ldsw_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,
};

/* Helper routines for marshalling helper function arguments into
 * the correct registers and stack.
 * argreg is where we want to put this argument, arg is the argument itself.
 * Return value is the updated argreg ready for the next call.
 * Note that argreg 0..3 is real registers, 4+ on stack.
 *
 * We provide routines for arguments which are: immediate, 32 bit
 * value in register, 16 and 8 bit values in register (which must be zero
 * extended before use) and 64 bit value in a lo:hi register pair.
 */
#define DEFINE_TCG_OUT_ARG(NAME, ARGTYPE, MOV_ARG, EXT_ARG)                \
static TCGReg NAME(TCGContext *s, TCGReg argreg, ARGTYPE arg)              \
{                                                                          \
    if (argreg < 4) {                                                      \
        MOV_ARG(s, COND_AL, argreg, arg);                                  \
    } else {                                                               \
        int ofs = (argreg - 4) * 4;                                        \
        EXT_ARG;                                                           \
        assert(ofs + 4 <= TCG_STATIC_CALL_ARGS_SIZE);                      \
        tcg_out_st32_12(s, COND_AL, arg, TCG_REG_CALL_STACK, ofs);         \
    }                                                                      \
    return argreg + 1;                                                     \
}

DEFINE_TCG_OUT_ARG(tcg_out_arg_imm32, uint32_t, tcg_out_movi32,
    (tcg_out_movi32(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
DEFINE_TCG_OUT_ARG(tcg_out_arg_reg8, TCGReg, tcg_out_ext8u,
    (tcg_out_ext8u(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
DEFINE_TCG_OUT_ARG(tcg_out_arg_reg16, TCGReg, tcg_out_ext16u,
    (tcg_out_ext16u(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
DEFINE_TCG_OUT_ARG(tcg_out_arg_reg32, TCGReg, tcg_out_mov_reg, )

static TCGReg tcg_out_arg_reg64(TCGContext *s, TCGReg argreg,
                                TCGReg arglo, TCGReg arghi)
{
    /* 64 bit arguments must go in even/odd register pairs
     * and in 8-aligned stack slots.
     */
    if (argreg & 1) {
        argreg++;
    }
    if (use_armv6_instructions && argreg >= 4
        && (arglo & 1) == 0 && arghi == arglo + 1) {
        tcg_out_strd_8(s, COND_AL, arglo,
                       TCG_REG_CALL_STACK, (argreg - 4) * 4);
        return argreg + 2;
    } else {
        argreg = tcg_out_arg_reg32(s, argreg, arglo);
        argreg = tcg_out_arg_reg32(s, argreg, arghi);
        return argreg;
    }
}

#define TLB_SHIFT	(CPU_TLB_ENTRY_BITS + CPU_TLB_BITS)

/* We're expecting to use an 8-bit immediate and to mask.  */
QEMU_BUILD_BUG_ON(CPU_TLB_BITS > 8);

/* We're expecting to use an 8-bit immediate add + 8-bit ldrd offset.
   Using the offset of the second entry in the last tlb table ensures
   that we can index all of the elements of the first entry.  */
QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_table[NB_MMU_MODES - 1][1])
                  > 0xffff);

/* Load and compare a TLB entry, leaving the flags set.  Returns the register
   containing the addend of the tlb entry.  Clobbers R0, R1, R2, TMP.  */

static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi,
                               TCGMemOp s_bits, int mem_index, bool is_load)
{
    TCGReg base = TCG_AREG0;
    int cmp_off =
        (is_load
         ? offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
         : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
    int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);

    /* Should generate something like the following:
     *   shr    tmp, addr_reg, #TARGET_PAGE_BITS                  (1)
     *   add    r2, env, #high
     *   and    r0, tmp, #(CPU_TLB_SIZE - 1)                      (2)
     *   add    r2, r2, r0, lsl #CPU_TLB_ENTRY_BITS               (3)
     *   ldr    r0, [r2, #cmp]                                    (4)
     *   tst    addr_reg, #s_mask
     *   ldr    r1, [r2, #add]                                    (5)
     *   cmpeq  r0, tmp, lsl #TARGET_PAGE_BITS
     */
    tcg_out_dat_reg(s, COND_AL, ARITH_MOV, TCG_REG_TMP,
                    0, addrlo, SHIFT_IMM_LSR(TARGET_PAGE_BITS));

    /* We checked that the offset is contained within 16 bits above.  */
    if (add_off > 0xfff || (use_armv6_instructions && cmp_off > 0xff)) {
        tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R2, base,
                        (24 << 7) | (cmp_off >> 8));
        base = TCG_REG_R2;
        add_off -= cmp_off & 0xff00;
        cmp_off &= 0xff;
    }

    tcg_out_dat_imm(s, COND_AL, ARITH_AND,
                    TCG_REG_R0, TCG_REG_TMP, CPU_TLB_SIZE - 1);
    tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_R2, base,
                    TCG_REG_R0, SHIFT_IMM_LSL(CPU_TLB_ENTRY_BITS));

    /* Load the tlb comparator.  Use ldrd if needed and available,
       but due to how the pointer needs setting up, ldm isn't useful.
       Base arm5 doesn't have ldrd, but armv5te does.  */
    if (use_armv6_instructions && TARGET_LONG_BITS == 64) {
        tcg_out_ldrd_8(s, COND_AL, TCG_REG_R0, TCG_REG_R2, cmp_off);
    } else {
        tcg_out_ld32_12(s, COND_AL, TCG_REG_R0, TCG_REG_R2, cmp_off);
        if (TARGET_LONG_BITS == 64) {
            tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R2, cmp_off + 4);
        }
    }

    /* Check alignment.  */
    if (s_bits) {
        tcg_out_dat_imm(s, COND_AL, ARITH_TST,
                        0, addrlo, (1 << s_bits) - 1);
    }

    /* Load the tlb addend.  */
    tcg_out_ld32_12(s, COND_AL, TCG_REG_R2, TCG_REG_R2, add_off);

    tcg_out_dat_reg(s, (s_bits ? COND_EQ : COND_AL), ARITH_CMP, 0,
                    TCG_REG_R0, TCG_REG_TMP, SHIFT_IMM_LSL(TARGET_PAGE_BITS));

    if (TARGET_LONG_BITS == 64) {
        tcg_out_dat_reg(s, COND_EQ, ARITH_CMP, 0,
                        TCG_REG_R1, addrhi, SHIFT_IMM_LSL(0));
    }

    return TCG_REG_R2;
}

/* Record the context of a call to the out of line helper code for the slow
   path for a load or store, so that we can later generate the correct
   helper code.  */
static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOp opc,
                                int data_reg, int data_reg2, int addrlo_reg,
                                int addrhi_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->datahi_reg = data_reg2;
    label->addrlo_reg = addrlo_reg;
    label->addrhi_reg = addrhi_reg;
    label->mem_index = mem_index;
    label->raddr = raddr;
    label->label_ptr[0] = label_ptr;
}

static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    TCGReg argreg, data_reg, data_reg2;
    TCGMemOp opc = lb->opc & MO_SSIZE;
    uintptr_t func;

    reloc_pc24(lb->label_ptr[0], (tcg_target_long)s->code_ptr);

    argreg = tcg_out_arg_reg32(s, TCG_REG_R0, TCG_AREG0);
    if (TARGET_LONG_BITS == 64) {
        argreg = tcg_out_arg_reg64(s, argreg, lb->addrlo_reg, lb->addrhi_reg);
    } else {
        argreg = tcg_out_arg_reg32(s, argreg, lb->addrlo_reg);
    }
    argreg = tcg_out_arg_imm32(s, argreg, lb->mem_index);
    argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);

    /* For armv6 we can use the canonical unsigned helpers and minimize
       icache usage.  For pre-armv6, use the signed helpers since we do
       not have a single insn sign-extend.  */
    if (use_armv6_instructions) {
        func = (uintptr_t)qemu_ld_helpers[opc & MO_SIZE];
    } else {
        func = (uintptr_t)qemu_ld_helpers[opc];
        if (opc & MO_SIGN) {
            opc = MO_UL;
        }
    }
    tcg_out_call(s, func);

    data_reg = lb->datalo_reg;
    data_reg2 = lb->datahi_reg;
    switch (opc) {
    case MO_SB:
        tcg_out_ext8s(s, COND_AL, data_reg, TCG_REG_R0);
        break;
    case MO_SW:
        tcg_out_ext16s(s, COND_AL, data_reg, TCG_REG_R0);
        break;
    default:
        tcg_out_mov_reg(s, COND_AL, data_reg, TCG_REG_R0);
        break;
    case MO_Q:
        if (data_reg != TCG_REG_R1) {
            tcg_out_mov_reg(s, COND_AL, data_reg, TCG_REG_R0);
            tcg_out_mov_reg(s, COND_AL, data_reg2, TCG_REG_R1);
        } else if (data_reg2 != TCG_REG_R0) {
            tcg_out_mov_reg(s, COND_AL, data_reg2, TCG_REG_R1);
            tcg_out_mov_reg(s, COND_AL, data_reg, TCG_REG_R0);
        } else {
            tcg_out_mov_reg(s, COND_AL, TCG_REG_TMP, TCG_REG_R0);
            tcg_out_mov_reg(s, COND_AL, data_reg2, TCG_REG_R1);
            tcg_out_mov_reg(s, COND_AL, data_reg, TCG_REG_TMP);
        }
        break;
    }

    tcg_out_goto(s, COND_AL, (tcg_target_long)lb->raddr);
}

static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
    TCGReg argreg, data_reg, data_reg2;
    TCGMemOp s_bits = lb->opc & MO_SIZE;

    reloc_pc24(lb->label_ptr[0], (tcg_target_long)s->code_ptr);

    argreg = TCG_REG_R0;
    argreg = tcg_out_arg_reg32(s, argreg, TCG_AREG0);
    if (TARGET_LONG_BITS == 64) {
        argreg = tcg_out_arg_reg64(s, argreg, lb->addrlo_reg, lb->addrhi_reg);
    } else {
        argreg = tcg_out_arg_reg32(s, argreg, lb->addrlo_reg);
    }

    data_reg = lb->datalo_reg;
    data_reg2 = lb->datahi_reg;
    switch (s_bits) {
    case MO_8:
        argreg = tcg_out_arg_reg8(s, argreg, data_reg);
        break;
    case MO_16:
        argreg = tcg_out_arg_reg16(s, argreg, data_reg);
        break;
    case MO_32:
    default:
        argreg = tcg_out_arg_reg32(s, argreg, data_reg);
        break;
    case MO_64:
        argreg = tcg_out_arg_reg64(s, argreg, data_reg, data_reg2);
        break;
    }

    argreg = tcg_out_arg_imm32(s, argreg, lb->mem_index);
    argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);

    /* Tail-call to the helper, which will return to the fast path.  */
    tcg_out_goto(s, COND_AL, (tcg_target_long) qemu_st_helpers[s_bits]);
}
#endif /* SOFTMMU */

static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, TCGMemOp opc)
{
    TCGReg addr_reg, data_reg, data_reg2;
    TCGMemOp bswap = opc & MO_BSWAP;
    TCGMemOp s_bits = opc & MO_SIZE;
#ifdef CONFIG_SOFTMMU
    int mem_index;
    TCGReg addr_reg2, addend;
    uint8_t *label_ptr;
#endif

    data_reg = *args++;
    data_reg2 = (s_bits == MO_64 ? *args++ : 0);
    addr_reg = *args++;
#ifdef CONFIG_SOFTMMU
    addr_reg2 = (TARGET_LONG_BITS == 64 ? *args++ : 0);
    mem_index = *args;

    addend = tcg_out_tlb_read(s, addr_reg, addr_reg2, s_bits, mem_index, 1);

    /* This a conditional BL only to load a pointer within this opcode into LR
       for the slow path.  We will not be using the value for a tail call.  */
    label_ptr = s->code_ptr;
    tcg_out_bl_noaddr(s, COND_NE);

    switch (opc & MO_SSIZE) {
    case MO_UB:
        tcg_out_ld8_r(s, COND_AL, data_reg, addr_reg, addend);
        break;
    case MO_SB:
        tcg_out_ld8s_r(s, COND_AL, data_reg, addr_reg, addend);
        break;
    case MO_UW:
        tcg_out_ld16u_r(s, COND_AL, data_reg, addr_reg, addend);
        if (bswap) {
            tcg_out_bswap16(s, COND_AL, data_reg, data_reg);
        }
        break;
    case MO_SW:
        if (bswap) {
            tcg_out_ld16u_r(s, COND_AL, data_reg, addr_reg, addend);
            tcg_out_bswap16s(s, COND_AL, data_reg, data_reg);
        } else {
            tcg_out_ld16s_r(s, COND_AL, data_reg, addr_reg, addend);
        }
        break;
    case MO_UL:
    default:
        tcg_out_ld32_r(s, COND_AL, data_reg, addr_reg, addend);
        if (bswap) {
            tcg_out_bswap32(s, COND_AL, data_reg, data_reg);
        }
        break;
    case MO_Q:
        {
            /* Be careful not to modify data_reg and data_reg2
               for the slow path below.  */
            TCGReg dl = (bswap ? data_reg2 : data_reg);
            TCGReg dh = (bswap ? data_reg : data_reg2);

            if (use_armv6_instructions && (dl & 1) == 0 && dh == dl + 1) {
                tcg_out_ldrd_r(s, COND_AL, dl, addr_reg, addend);
            } else if (dl != addend) {
                tcg_out_ld32_rwb(s, COND_AL, dl, addend, addr_reg);
                tcg_out_ld32_12(s, COND_AL, dh, addend, 4);
            } else {
                tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
                                addend, addr_reg, SHIFT_IMM_LSL(0));
                tcg_out_ld32_12(s, COND_AL, dl, TCG_REG_TMP, 0);
                tcg_out_ld32_12(s, COND_AL, dh, TCG_REG_TMP, 4);
            }
            if (bswap) {
                tcg_out_bswap32(s, COND_AL, dh, dh);
                tcg_out_bswap32(s, COND_AL, dl, dl);
            }
        }
        break;
    }

    add_qemu_ldst_label(s, 1, opc, data_reg, data_reg2, addr_reg, addr_reg2,
                        mem_index, s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    if (GUEST_BASE) {
        uint32_t offset = GUEST_BASE;
        int i, rot;

        while (offset) {
            i = ctz32(offset) & ~1;
            rot = ((32 - i) << 7) & 0xf00;

            tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_TMP, addr_reg,
                            ((offset >> i) & 0xff) | rot);
            addr_reg = TCG_REG_TMP;
            offset &= ~(0xff << i);
        }
    }
    switch (opc & MO_SSIZE) {
    case MO_UB:
        tcg_out_ld8_12(s, COND_AL, data_reg, addr_reg, 0);
        break;
    case MO_SB:
        tcg_out_ld8s_8(s, COND_AL, data_reg, addr_reg, 0);
        break;
    case MO_UW:
        tcg_out_ld16u_8(s, COND_AL, data_reg, addr_reg, 0);
        if (bswap) {
            tcg_out_bswap16(s, COND_AL, data_reg, data_reg);
        }
        break;
    case MO_SW:
        if (bswap) {
            tcg_out_ld16u_8(s, COND_AL, data_reg, addr_reg, 0);
            tcg_out_bswap16s(s, COND_AL, data_reg, data_reg);
        } else {
            tcg_out_ld16s_8(s, COND_AL, data_reg, addr_reg, 0);
        }
        break;
    case MO_UL:
    default:
        tcg_out_ld32_12(s, COND_AL, data_reg, addr_reg, 0);
        if (bswap) {
            tcg_out_bswap32(s, COND_AL, data_reg, data_reg);
        }
        break;
    case MO_Q:
        if (use_armv6_instructions && !bswap
            && (data_reg & 1) == 0 && data_reg2 == data_reg + 1) {
            tcg_out_ldrd_8(s, COND_AL, data_reg, addr_reg, 0);
        } else if (use_armv6_instructions && bswap
                   && (data_reg2 & 1) == 0 && data_reg == data_reg2 + 1) {
            tcg_out_ldrd_8(s, COND_AL, data_reg2, addr_reg, 0);
        } else if (data_reg == addr_reg) {
            tcg_out_ld32_12(s, COND_AL, data_reg2, addr_reg, bswap ? 0 : 4);
            tcg_out_ld32_12(s, COND_AL, data_reg, addr_reg, bswap ? 4 : 0);
        } else {
            tcg_out_ld32_12(s, COND_AL, data_reg, addr_reg, bswap ? 4 : 0);
            tcg_out_ld32_12(s, COND_AL, data_reg2, addr_reg, bswap ? 0 : 4);
        }
        if (bswap) {
            tcg_out_bswap32(s, COND_AL, data_reg, data_reg);
            tcg_out_bswap32(s, COND_AL, data_reg2, data_reg2);
        }
        break;
    }
#endif
}

static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, TCGMemOp opc)
{
    TCGReg addr_reg, data_reg, data_reg2;
    TCGMemOp bswap = opc & MO_BSWAP;
    TCGMemOp s_bits = opc & MO_SIZE;
#ifdef CONFIG_SOFTMMU
    int mem_index;
    TCGReg addr_reg2, addend;
    uint8_t *label_ptr;
#endif
#ifdef TARGET_WORDS_BIGENDIAN
    bswap = 1;
#else
    bswap = 0;
#endif

    data_reg = *args++;
    data_reg2 = (s_bits == MO_64 ? *args++ : 0);
    addr_reg = *args++;
#ifdef CONFIG_SOFTMMU
    addr_reg2 = (TARGET_LONG_BITS == 64 ? *args++ : 0);
    mem_index = *args;

    addend = tcg_out_tlb_read(s, addr_reg, addr_reg2, s_bits, mem_index, 0);

    switch (s_bits) {
    case MO_8:
        tcg_out_st8_r(s, COND_EQ, data_reg, addr_reg, addend);
        break;
    case MO_16:
        if (bswap) {
            tcg_out_bswap16st(s, COND_EQ, TCG_REG_R0, data_reg);
            tcg_out_st16_r(s, COND_EQ, TCG_REG_R0, addr_reg, addend);
        } else {
            tcg_out_st16_r(s, COND_EQ, data_reg, addr_reg, addend);
        }
        break;
    case MO_32:
    default:
        if (bswap) {
            tcg_out_bswap32(s, COND_EQ, TCG_REG_R0, data_reg);
            tcg_out_st32_r(s, COND_EQ, TCG_REG_R0, addr_reg, addend);
        } else {
            tcg_out_st32_r(s, COND_EQ, data_reg, addr_reg, addend);
        }
        break;
    case MO_64:
        if (bswap) {
            tcg_out_bswap32(s, COND_EQ, TCG_REG_R0, data_reg2);
            tcg_out_st32_rwb(s, COND_EQ, TCG_REG_R0, addend, addr_reg);
            tcg_out_bswap32(s, COND_EQ, TCG_REG_R0, data_reg);
            tcg_out_st32_12(s, COND_EQ, TCG_REG_R0, addend, 4);
        } else if (use_armv6_instructions
                   && (data_reg & 1) == 0 && data_reg2 == data_reg + 1) {
            tcg_out_strd_r(s, COND_EQ, data_reg, addr_reg, addend);
        } else {
            tcg_out_st32_rwb(s, COND_EQ, data_reg, addend, addr_reg);
            tcg_out_st32_12(s, COND_EQ, data_reg2, addend, 4);
        }
        break;
    }

    /* The conditional call must come last, as we're going to return here.  */
    label_ptr = s->code_ptr;
    tcg_out_bl_noaddr(s, COND_NE);

    add_qemu_ldst_label(s, 0, opc, data_reg, data_reg2, addr_reg, addr_reg2,
                        mem_index, s->code_ptr, label_ptr);
#else /* !CONFIG_SOFTMMU */
    if (GUEST_BASE) {
        uint32_t offset = GUEST_BASE;
        int i;
        int rot;

        while (offset) {
            i = ctz32(offset) & ~1;
            rot = ((32 - i) << 7) & 0xf00;

            tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R1, addr_reg,
                            ((offset >> i) & 0xff) | rot);
            addr_reg = TCG_REG_R1;
            offset &= ~(0xff << i);
        }
    }
    switch (s_bits) {
    case MO_8:
        tcg_out_st8_12(s, COND_AL, data_reg, addr_reg, 0);
        break;
    case MO_16:
        if (bswap) {
            tcg_out_bswap16st(s, COND_AL, TCG_REG_R0, data_reg);
            tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addr_reg, 0);
        } else {
            tcg_out_st16_8(s, COND_AL, data_reg, addr_reg, 0);
        }
        break;
    case MO_32:
    default:
        if (bswap) {
            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, data_reg);
            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addr_reg, 0);
        } else {
            tcg_out_st32_12(s, COND_AL, data_reg, addr_reg, 0);
        }
        break;
    case MO_64:
        if (bswap) {
            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, data_reg2);
            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addr_reg, 0);
            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, data_reg);
            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addr_reg, 4);
        } else if (use_armv6_instructions
                   && (data_reg & 1) == 0 && data_reg2 == data_reg + 1) {
            tcg_out_strd_8(s, COND_AL, data_reg, addr_reg, 0);
        } else {
            tcg_out_st32_12(s, COND_AL, data_reg, addr_reg, 0);
            tcg_out_st32_12(s, COND_AL, data_reg2, addr_reg, 4);
        }
        break;
    }
#endif
}

static uint8_t *tb_ret_addr;

static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
                const TCGArg *args, const int *const_args)
{
    TCGArg a0, a1, a2, a3, a4, a5;
    int c;

    switch (opc) {
    case INDEX_op_exit_tb:
        if (use_armv7_instructions || check_fit_imm(args[0])) {
            tcg_out_movi32(s, COND_AL, TCG_REG_R0, args[0]);
            tcg_out_goto(s, COND_AL, (tcg_target_ulong) tb_ret_addr);
        } else {
            uint8_t *ld_ptr = s->code_ptr;
            tcg_out_ld32_12(s, COND_AL, TCG_REG_R0, TCG_REG_PC, 0);
            tcg_out_goto(s, COND_AL, (tcg_target_ulong) tb_ret_addr);
            *ld_ptr = (uint8_t) (s->code_ptr - ld_ptr) - 8;
            tcg_out32(s, args[0]);
        }
        break;
    case INDEX_op_goto_tb:
        if (s->tb_jmp_offset) {
            /* Direct jump method */
#if defined(USE_DIRECT_JUMP)
            s->tb_jmp_offset[args[0]] = s->code_ptr - s->code_buf;
            tcg_out_b_noaddr(s, COND_AL);
#else
            tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_PC, -4);
            s->tb_jmp_offset[args[0]] = s->code_ptr - s->code_buf;
            tcg_out32(s, 0);
#endif
        } else {
            /* Indirect jump method */
#if 1
            c = (int) (s->tb_next + args[0]) - ((int) s->code_ptr + 8);
            if (c > 0xfff || c < -0xfff) {
                tcg_out_movi32(s, COND_AL, TCG_REG_R0,
                                (tcg_target_long) (s->tb_next + args[0]));
                tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_R0, 0);
            } else
                tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_PC, c);
#else
            tcg_out_ld32_12(s, COND_AL, TCG_REG_R0, TCG_REG_PC, 0);
            tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_R0, 0);
            tcg_out32(s, (tcg_target_long) (s->tb_next + args[0]));
#endif
        }
        s->tb_next_offset[args[0]] = s->code_ptr - s->code_buf;
        break;
    case INDEX_op_call:
        if (const_args[0])
            tcg_out_call(s, args[0]);
        else
            tcg_out_callr(s, COND_AL, args[0]);
        break;
    case INDEX_op_br:
        tcg_out_goto_label(s, COND_AL, args[0]);
        break;

    case INDEX_op_ld8u_i32:
        tcg_out_ld8u(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_ld8s_i32:
        tcg_out_ld8s(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_ld16u_i32:
        tcg_out_ld16u(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_ld16s_i32:
        tcg_out_ld16s(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_ld_i32:
        tcg_out_ld32u(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_st8_i32:
        tcg_out_st8(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_st16_i32:
        tcg_out_st16(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_st_i32:
        tcg_out_st32(s, COND_AL, args[0], args[1], args[2]);
        break;

    case INDEX_op_mov_i32:
        tcg_out_dat_reg(s, COND_AL, ARITH_MOV,
                        args[0], 0, args[1], SHIFT_IMM_LSL(0));
        break;
    case INDEX_op_movi_i32:
        tcg_out_movi32(s, COND_AL, args[0], args[1]);
        break;
    case INDEX_op_movcond_i32:
        /* Constraints mean that v2 is always in the same register as dest,
         * so we only need to do "if condition passed, move v1 to dest".
         */
        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
                        args[1], args[2], const_args[2]);
        tcg_out_dat_rIK(s, tcg_cond_to_arm_cond[args[5]], ARITH_MOV,
                        ARITH_MVN, args[0], 0, args[3], const_args[3]);
        break;
    case INDEX_op_add_i32:
        tcg_out_dat_rIN(s, COND_AL, ARITH_ADD, ARITH_SUB,
                        args[0], args[1], args[2], const_args[2]);
        break;
    case INDEX_op_sub_i32:
        if (const_args[1]) {
            if (const_args[2]) {
                tcg_out_movi32(s, COND_AL, args[0], args[1] - args[2]);
            } else {
                tcg_out_dat_rI(s, COND_AL, ARITH_RSB,
                               args[0], args[2], args[1], 1);
            }
        } else {
            tcg_out_dat_rIN(s, COND_AL, ARITH_SUB, ARITH_ADD,
                            args[0], args[1], args[2], const_args[2]);
        }
        break;
    case INDEX_op_and_i32:
        tcg_out_dat_rIK(s, COND_AL, ARITH_AND, ARITH_BIC,
                        args[0], args[1], args[2], const_args[2]);
        break;
    case INDEX_op_andc_i32:
        tcg_out_dat_rIK(s, COND_AL, ARITH_BIC, ARITH_AND,
                        args[0], args[1], args[2], const_args[2]);
        break;
    case INDEX_op_or_i32:
        c = ARITH_ORR;
        goto gen_arith;
    case INDEX_op_xor_i32:
        c = ARITH_EOR;
        /* Fall through.  */
    gen_arith:
        tcg_out_dat_rI(s, COND_AL, c, args[0], args[1], args[2], const_args[2]);
        break;
    case INDEX_op_add2_i32:
        a0 = args[0], a1 = args[1], a2 = args[2];
        a3 = args[3], a4 = args[4], a5 = args[5];
        if (a0 == a3 || (a0 == a5 && !const_args[5])) {
            a0 = TCG_REG_TMP;
        }
        tcg_out_dat_rIN(s, COND_AL, ARITH_ADD | TO_CPSR, ARITH_SUB | TO_CPSR,
                        a0, a2, a4, const_args[4]);
        tcg_out_dat_rIK(s, COND_AL, ARITH_ADC, ARITH_SBC,
                        a1, a3, a5, const_args[5]);
        tcg_out_mov_reg(s, COND_AL, args[0], a0);
        break;
    case INDEX_op_sub2_i32:
        a0 = args[0], a1 = args[1], a2 = args[2];
        a3 = args[3], a4 = args[4], a5 = args[5];
        if ((a0 == a3 && !const_args[3]) || (a0 == a5 && !const_args[5])) {
            a0 = TCG_REG_TMP;
        }
        if (const_args[2]) {
            if (const_args[4]) {
                tcg_out_movi32(s, COND_AL, a0, a4);
                a4 = a0;
            }
            tcg_out_dat_rI(s, COND_AL, ARITH_RSB | TO_CPSR, a0, a4, a2, 1);
        } else {
            tcg_out_dat_rIN(s, COND_AL, ARITH_SUB | TO_CPSR,
                            ARITH_ADD | TO_CPSR, a0, a2, a4, const_args[4]);
        }
        if (const_args[3]) {
            if (const_args[5]) {
                tcg_out_movi32(s, COND_AL, a1, a5);
                a5 = a1;
            }
            tcg_out_dat_rI(s, COND_AL, ARITH_RSC, a1, a5, a3, 1);
        } else {
            tcg_out_dat_rIK(s, COND_AL, ARITH_SBC, ARITH_ADC,
                            a1, a3, a5, const_args[5]);
        }
        tcg_out_mov_reg(s, COND_AL, args[0], a0);
        break;
    case INDEX_op_neg_i32:
        tcg_out_dat_imm(s, COND_AL, ARITH_RSB, args[0], args[1], 0);
        break;
    case INDEX_op_not_i32:
        tcg_out_dat_reg(s, COND_AL,
                        ARITH_MVN, args[0], 0, args[1], SHIFT_IMM_LSL(0));
        break;
    case INDEX_op_mul_i32:
        tcg_out_mul32(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_mulu2_i32:
        tcg_out_umull32(s, COND_AL, args[0], args[1], args[2], args[3]);
        break;
    case INDEX_op_muls2_i32:
        tcg_out_smull32(s, COND_AL, args[0], args[1], args[2], args[3]);
        break;
    /* XXX: Perhaps args[2] & 0x1f is wrong */
    case INDEX_op_shl_i32:
        c = const_args[2] ?
                SHIFT_IMM_LSL(args[2] & 0x1f) : SHIFT_REG_LSL(args[2]);
        goto gen_shift32;
    case INDEX_op_shr_i32:
        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_LSR(args[2] & 0x1f) :
                SHIFT_IMM_LSL(0) : SHIFT_REG_LSR(args[2]);
        goto gen_shift32;
    case INDEX_op_sar_i32:
        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_ASR(args[2] & 0x1f) :
                SHIFT_IMM_LSL(0) : SHIFT_REG_ASR(args[2]);
        goto gen_shift32;
    case INDEX_op_rotr_i32:
        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_ROR(args[2] & 0x1f) :
                SHIFT_IMM_LSL(0) : SHIFT_REG_ROR(args[2]);
        /* Fall through.  */
    gen_shift32:
        tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1], c);
        break;

    case INDEX_op_rotl_i32:
        if (const_args[2]) {
            tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1],
                            ((0x20 - args[2]) & 0x1f) ?
                            SHIFT_IMM_ROR((0x20 - args[2]) & 0x1f) :
                            SHIFT_IMM_LSL(0));
        } else {
            tcg_out_dat_imm(s, COND_AL, ARITH_RSB, TCG_REG_TMP, args[1], 0x20);
            tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1],
                            SHIFT_REG_ROR(TCG_REG_TMP));
        }
        break;

    case INDEX_op_brcond_i32:
        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
                       args[0], args[1], const_args[1]);
        tcg_out_goto_label(s, tcg_cond_to_arm_cond[args[2]], args[3]);
        break;
    case INDEX_op_brcond2_i32:
        /* The resulting conditions are:
         * TCG_COND_EQ    -->  a0 == a2 && a1 == a3,
         * TCG_COND_NE    --> (a0 != a2 && a1 == a3) ||  a1 != a3,
         * TCG_COND_LT(U) --> (a0 <  a2 && a1 == a3) ||  a1 <  a3,
         * TCG_COND_GE(U) --> (a0 >= a2 && a1 == a3) || (a1 >= a3 && a1 != a3),
         * TCG_COND_LE(U) --> (a0 <= a2 && a1 == a3) || (a1 <= a3 && a1 != a3),
         * TCG_COND_GT(U) --> (a0 >  a2 && a1 == a3) ||  a1 >  a3,
         */
        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
                        args[1], args[3], const_args[3]);
        tcg_out_dat_rIN(s, COND_EQ, ARITH_CMP, ARITH_CMN, 0,
                        args[0], args[2], const_args[2]);
        tcg_out_goto_label(s, tcg_cond_to_arm_cond[args[4]], args[5]);
        break;
    case INDEX_op_setcond_i32:
        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
                        args[1], args[2], const_args[2]);
        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[args[3]],
                        ARITH_MOV, args[0], 0, 1);
        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[tcg_invert_cond(args[3])],
                        ARITH_MOV, args[0], 0, 0);
        break;
    case INDEX_op_setcond2_i32:
        /* See brcond2_i32 comment */
        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
                        args[2], args[4], const_args[4]);
        tcg_out_dat_rIN(s, COND_EQ, ARITH_CMP, ARITH_CMN, 0,
                        args[1], args[3], const_args[3]);
        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[args[5]],
                        ARITH_MOV, args[0], 0, 1);
        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[tcg_invert_cond(args[5])],
                        ARITH_MOV, args[0], 0, 0);
        break;

    case INDEX_op_qemu_ld8u:
        tcg_out_qemu_ld(s, args, MO_UB);
        break;
    case INDEX_op_qemu_ld8s:
        tcg_out_qemu_ld(s, args, MO_SB);
        break;
    case INDEX_op_qemu_ld16u:
        tcg_out_qemu_ld(s, args, MO_TEUW);
        break;
    case INDEX_op_qemu_ld16s:
        tcg_out_qemu_ld(s, args, MO_TESW);
        break;
    case INDEX_op_qemu_ld32:
        tcg_out_qemu_ld(s, args, MO_TEUL);
        break;
    case INDEX_op_qemu_ld64:
        tcg_out_qemu_ld(s, args, MO_TEQ);
        break;

    case INDEX_op_qemu_st8:
        tcg_out_qemu_st(s, args, MO_UB);
        break;
    case INDEX_op_qemu_st16:
        tcg_out_qemu_st(s, args, MO_TEUW);
        break;
    case INDEX_op_qemu_st32:
        tcg_out_qemu_st(s, args, MO_TEUL);
        break;
    case INDEX_op_qemu_st64:
        tcg_out_qemu_st(s, args, MO_TEQ);
        break;

    case INDEX_op_bswap16_i32:
        tcg_out_bswap16(s, COND_AL, args[0], args[1]);
        break;
    case INDEX_op_bswap32_i32:
        tcg_out_bswap32(s, COND_AL, args[0], args[1]);
        break;

    case INDEX_op_ext8s_i32:
        tcg_out_ext8s(s, COND_AL, args[0], args[1]);
        break;
    case INDEX_op_ext16s_i32:
        tcg_out_ext16s(s, COND_AL, args[0], args[1]);
        break;
    case INDEX_op_ext16u_i32:
        tcg_out_ext16u(s, COND_AL, args[0], args[1]);
        break;

    case INDEX_op_deposit_i32:
        tcg_out_deposit(s, COND_AL, args[0], args[2],
                        args[3], args[4], const_args[2]);
        break;

    case INDEX_op_div_i32:
        tcg_out_sdiv(s, COND_AL, args[0], args[1], args[2]);
        break;
    case INDEX_op_divu_i32:
        tcg_out_udiv(s, COND_AL, args[0], args[1], args[2]);
        break;

    default:
        tcg_abort();
    }
}

static const TCGTargetOpDef arm_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_movi_i32, { "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_st8_i32, { "r", "r" } },
    { INDEX_op_st16_i32, { "r", "r" } },
    { INDEX_op_st_i32, { "r", "r" } },

    /* TODO: "r", "r", "ri" */
    { INDEX_op_add_i32, { "r", "r", "rIN" } },
    { INDEX_op_sub_i32, { "r", "rI", "rIN" } },
    { INDEX_op_mul_i32, { "r", "r", "r" } },
    { INDEX_op_mulu2_i32, { "r", "r", "r", "r" } },
    { INDEX_op_muls2_i32, { "r", "r", "r", "r" } },
    { INDEX_op_and_i32, { "r", "r", "rIK" } },
    { INDEX_op_andc_i32, { "r", "r", "rIK" } },
    { INDEX_op_or_i32, { "r", "r", "rI" } },
    { INDEX_op_xor_i32, { "r", "r", "rI" } },
    { INDEX_op_neg_i32, { "r", "r" } },
    { INDEX_op_not_i32, { "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_brcond_i32, { "r", "rIN" } },
    { INDEX_op_setcond_i32, { "r", "r", "rIN" } },
    { INDEX_op_movcond_i32, { "r", "r", "rIN", "rIK", "0" } },

    { INDEX_op_add2_i32, { "r", "r", "r", "r", "rIN", "rIK" } },
    { INDEX_op_sub2_i32, { "r", "r", "rI", "rI", "rIN", "rIK" } },
    { INDEX_op_brcond2_i32, { "r", "r", "rIN", "rIN" } },
    { INDEX_op_setcond2_i32, { "r", "r", "r", "rIN", "rIN" } },

#if TARGET_LONG_BITS == 32
    { 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_ld32, { "r", "l" } },
    { INDEX_op_qemu_ld64, { "r", "r", "l" } },

    { INDEX_op_qemu_st8, { "s", "s" } },
    { INDEX_op_qemu_st16, { "s", "s" } },
    { INDEX_op_qemu_st32, { "s", "s" } },
    { INDEX_op_qemu_st64, { "s", "s", "s" } },
#else
    { INDEX_op_qemu_ld8u, { "r", "l", "l" } },
    { INDEX_op_qemu_ld8s, { "r", "l", "l" } },
    { INDEX_op_qemu_ld16u, { "r", "l", "l" } },
    { INDEX_op_qemu_ld16s, { "r", "l", "l" } },
    { INDEX_op_qemu_ld32, { "r", "l", "l" } },
    { INDEX_op_qemu_ld64, { "r", "r", "l", "l" } },

    { INDEX_op_qemu_st8, { "s", "s", "s" } },
    { INDEX_op_qemu_st16, { "s", "s", "s" } },
    { INDEX_op_qemu_st32, { "s", "s", "s" } },
    { INDEX_op_qemu_st64, { "s", "s", "s", "s" } },
#endif

    { INDEX_op_bswap16_i32, { "r", "r" } },
    { INDEX_op_bswap32_i32, { "r", "r" } },

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

    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },

    { INDEX_op_div_i32, { "r", "r", "r" } },
    { INDEX_op_divu_i32, { "r", "r", "r" } },

    { -1 },
};

static void tcg_target_init(TCGContext *s)
{
#if defined(CONFIG_GETAUXVAL)
    /* Only probe for the platform and capabilities if we havn't already
       determined maximum values at compile time.  */
# if !defined(use_idiv_instructions)
    {
        unsigned long hwcap = getauxval(AT_HWCAP);
        use_idiv_instructions = (hwcap & HWCAP_ARM_IDIVA) != 0;
    }
# endif
    if (__ARM_ARCH < 7) {
        const char *pl = (const char *)getauxval(AT_PLATFORM);
        if (pl != NULL && pl[0] == 'v' && pl[1] >= '4' && pl[1] <= '9') {
            arm_arch = pl[1] - '0';
        }
    }
#endif /* GETAUXVAL */

    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff);
    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
                     (1 << TCG_REG_R0) |
                     (1 << TCG_REG_R1) |
                     (1 << TCG_REG_R2) |
                     (1 << TCG_REG_R3) |
                     (1 << TCG_REG_R12) |
                     (1 << TCG_REG_R14));

    tcg_regset_clear(s->reserved_regs);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_CALL_STACK);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP);
    tcg_regset_set_reg(s->reserved_regs, TCG_REG_PC);

    tcg_add_target_add_op_defs(arm_op_defs);
}

static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
                              TCGReg arg1, intptr_t arg2)
{
    tcg_out_ld32u(s, COND_AL, arg, arg1, arg2);
}

static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
                              TCGReg arg1, intptr_t arg2)
{
    tcg_out_st32(s, COND_AL, arg, arg1, arg2);
}

static inline void tcg_out_mov(TCGContext *s, TCGType type,
                               TCGReg ret, TCGReg arg)
{
    tcg_out_dat_reg(s, COND_AL, ARITH_MOV, ret, 0, arg, SHIFT_IMM_LSL(0));
}

static inline void tcg_out_movi(TCGContext *s, TCGType type,
                                TCGReg ret, tcg_target_long arg)
{
    tcg_out_movi32(s, COND_AL, ret, arg);
}

/* Compute frame size via macros, to share between tcg_target_qemu_prologue
   and tcg_register_jit.  */

#define PUSH_SIZE  ((11 - 4 + 1 + 1) * sizeof(tcg_target_long))

#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)

static void tcg_target_qemu_prologue(TCGContext *s)
{
    int stack_addend;

    /* Calling convention requires us to save r4-r11 and lr.  */
    /* stmdb sp!, { r4 - r11, lr } */
    tcg_out32(s, (COND_AL << 28) | 0x092d4ff0);

    /* Reserve callee argument and tcg temp space.  */
    stack_addend = FRAME_SIZE - PUSH_SIZE;

    tcg_out_dat_rI(s, COND_AL, ARITH_SUB, TCG_REG_CALL_STACK,
                   TCG_REG_CALL_STACK, stack_addend, 1);
    tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
                  CPU_TEMP_BUF_NLONGS * sizeof(long));

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

    tcg_out_bx(s, COND_AL, tcg_target_call_iarg_regs[1]);
    tb_ret_addr = s->code_ptr;

    /* Epilogue.  We branch here via tb_ret_addr.  */
    tcg_out_dat_rI(s, COND_AL, ARITH_ADD, TCG_REG_CALL_STACK,
                   TCG_REG_CALL_STACK, stack_addend, 1);

    /* ldmia sp!, { r4 - r11, pc } */
    tcg_out32(s, (COND_AL << 28) | 0x08bd8ff0);
}

typedef struct {
    DebugFrameCIE cie;
    DebugFrameFDEHeader fde;
    uint8_t fde_def_cfa[4];
    uint8_t fde_reg_ofs[18];
} DebugFrame;

#define ELF_HOST_MACHINE EM_ARM

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

static DebugFrame debug_frame = {
    .cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
    .cie.id = -1,
    .cie.version = 1,
    .cie.code_align = 1,
    .cie.data_align = 0x7c,             /* sleb128 -4 */
    .cie.return_column = 14,

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

    .fde_def_cfa = {
        12, 13,                         /* DW_CFA_def_cfa sp, ... */
        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
        (FRAME_SIZE >> 7)
    },
    .fde_reg_ofs = {
        /* The following must match the stmdb in the prologue.  */
        0x8e, 1,                        /* DW_CFA_offset, lr, -4 */
        0x8b, 2,                        /* DW_CFA_offset, r11, -8 */
        0x8a, 3,                        /* DW_CFA_offset, r10, -12 */
        0x89, 4,                        /* DW_CFA_offset, r9, -16 */
        0x88, 5,                        /* DW_CFA_offset, r8, -20 */
        0x87, 6,                        /* DW_CFA_offset, r7, -24 */
        0x86, 7,                        /* DW_CFA_offset, r6, -28 */
        0x85, 8,                        /* DW_CFA_offset, r5, -32 */
        0x84, 9,                        /* DW_CFA_offset, r4, -36 */
    }
};

void tcg_register_jit(void *buf, size_t buf_size)
{
    debug_frame.fde.func_start = (tcg_target_long) buf;
    debug_frame.fde.func_len = buf_size;

    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
}