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
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
|
/*
* Tiny Code Generator for QEMU
*
* Copyright (c) 2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "tcg-be-ldst.h"
#if defined _CALL_DARWIN || defined __APPLE__
#define TCG_TARGET_CALL_DARWIN
#endif
#ifdef _CALL_SYSV
# define TCG_TARGET_CALL_ALIGN_ARGS 1
#endif
/* For some memory operations, we need a scratch that isn't R0. For the AIX
calling convention, we can re-use the TOC register since we'll be reloading
it at every call. Otherwise R12 will do nicely as neither a call-saved
register nor a parameter register. */
#ifdef _CALL_AIX
# define TCG_REG_TMP1 TCG_REG_R2
#else
# define TCG_REG_TMP1 TCG_REG_R12
#endif
/* For the 64-bit target, we don't like the 5 insn sequence needed to build
full 64-bit addresses. Better to have a base register to which we can
apply a 32-bit displacement.
There are generally three items of interest:
(1) helper functions in the main executable,
(2) TranslationBlock data structures,
(3) the return address in the epilogue.
For user-only, we USE_STATIC_CODE_GEN_BUFFER, so the code_gen_buffer
will be inside the main executable, and thus near enough to make a
pointer to the epilogue be within 2GB of all helper functions.
For softmmu, we'll let the kernel choose the address of code_gen_buffer,
and odds are it'll be somewhere close to the main malloc arena, and so
a pointer to the epilogue will be within 2GB of the TranslationBlocks.
For --enable-pie, everything will be kinda near everything else,
somewhere in high memory.
Thus we choose to keep the return address in a call-saved register. */
#define TCG_REG_RA TCG_REG_R31
#define USE_REG_RA (TCG_TARGET_REG_BITS == 64)
/* Shorthand for size of a pointer. Avoid promotion to unsigned. */
#define SZP ((int)sizeof(void *))
/* Shorthand for size of a register. */
#define SZR (TCG_TARGET_REG_BITS / 8)
#define TCG_CT_CONST_S16 0x100
#define TCG_CT_CONST_U16 0x200
#define TCG_CT_CONST_S32 0x400
#define TCG_CT_CONST_U32 0x800
#define TCG_CT_CONST_ZERO 0x1000
#define TCG_CT_CONST_MONE 0x2000
static tcg_insn_unit *tb_ret_addr;
#ifndef GUEST_BASE
#define GUEST_BASE 0
#endif
#include "elf.h"
static bool have_isa_2_06;
#define HAVE_ISA_2_06 have_isa_2_06
#define HAVE_ISEL have_isa_2_06
#ifndef CONFIG_SOFTMMU
#define TCG_GUEST_BASE_REG 30
#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",
"r15",
"r16",
"r17",
"r18",
"r19",
"r20",
"r21",
"r22",
"r23",
"r24",
"r25",
"r26",
"r27",
"r28",
"r29",
"r30",
"r31"
};
#endif
static const int tcg_target_reg_alloc_order[] = {
TCG_REG_R14, /* call saved registers */
TCG_REG_R15,
TCG_REG_R16,
TCG_REG_R17,
TCG_REG_R18,
TCG_REG_R19,
TCG_REG_R20,
TCG_REG_R21,
TCG_REG_R22,
TCG_REG_R23,
TCG_REG_R24,
TCG_REG_R25,
TCG_REG_R26,
TCG_REG_R27,
TCG_REG_R28,
TCG_REG_R29,
TCG_REG_R30,
TCG_REG_R31,
TCG_REG_R12, /* call clobbered, non-arguments */
TCG_REG_R11,
TCG_REG_R2,
TCG_REG_R13,
TCG_REG_R10, /* call clobbered, arguments */
TCG_REG_R9,
TCG_REG_R8,
TCG_REG_R7,
TCG_REG_R6,
TCG_REG_R5,
TCG_REG_R4,
TCG_REG_R3,
};
static const int tcg_target_call_iarg_regs[] = {
TCG_REG_R3,
TCG_REG_R4,
TCG_REG_R5,
TCG_REG_R6,
TCG_REG_R7,
TCG_REG_R8,
TCG_REG_R9,
TCG_REG_R10
};
static const int tcg_target_call_oarg_regs[] = {
TCG_REG_R3,
TCG_REG_R4
};
static const int tcg_target_callee_save_regs[] = {
#ifdef TCG_TARGET_CALL_DARWIN
TCG_REG_R11,
#endif
TCG_REG_R14,
TCG_REG_R15,
TCG_REG_R16,
TCG_REG_R17,
TCG_REG_R18,
TCG_REG_R19,
TCG_REG_R20,
TCG_REG_R21,
TCG_REG_R22,
TCG_REG_R23,
TCG_REG_R24,
TCG_REG_R25,
TCG_REG_R26,
TCG_REG_R27, /* currently used for the global env */
TCG_REG_R28,
TCG_REG_R29,
TCG_REG_R30,
TCG_REG_R31
};
static inline bool in_range_b(tcg_target_long target)
{
return target == sextract64(target, 0, 26);
}
static uint32_t reloc_pc24_val(tcg_insn_unit *pc, tcg_insn_unit *target)
{
ptrdiff_t disp = tcg_ptr_byte_diff(target, pc);
assert(in_range_b(disp));
return disp & 0x3fffffc;
}
static void reloc_pc24(tcg_insn_unit *pc, tcg_insn_unit *target)
{
*pc = (*pc & ~0x3fffffc) | reloc_pc24_val(pc, target);
}
static uint16_t reloc_pc14_val(tcg_insn_unit *pc, tcg_insn_unit *target)
{
ptrdiff_t disp = tcg_ptr_byte_diff(target, pc);
assert(disp == (int16_t) disp);
return disp & 0xfffc;
}
static void reloc_pc14(tcg_insn_unit *pc, tcg_insn_unit *target)
{
*pc = (*pc & ~0xfffc) | reloc_pc14_val(pc, target);
}
static inline void tcg_out_b_noaddr(TCGContext *s, int insn)
{
unsigned retrans = *s->code_ptr & 0x3fffffc;
tcg_out32(s, insn | retrans);
}
static inline void tcg_out_bc_noaddr(TCGContext *s, int insn)
{
unsigned retrans = *s->code_ptr & 0xfffc;
tcg_out32(s, insn | retrans);
}
static void patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend)
{
tcg_insn_unit *target = (tcg_insn_unit *)value;
assert(addend == 0);
switch (type) {
case R_PPC_REL14:
reloc_pc14(code_ptr, target);
break;
case R_PPC_REL24:
reloc_pc24(code_ptr, target);
break;
default:
tcg_abort();
}
}
/* 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 'A': case 'B': case 'C': case 'D':
ct->ct |= TCG_CT_REG;
tcg_regset_set_reg(ct->u.regs, 3 + ct_str[0] - 'A');
break;
case 'r':
ct->ct |= TCG_CT_REG;
tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
break;
case 'L': /* qemu_ld constraint */
ct->ct |= TCG_CT_REG;
tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
#ifdef CONFIG_SOFTMMU
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R4);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R5);
#endif
break;
case 'S': /* qemu_st constraint */
ct->ct |= TCG_CT_REG;
tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
#ifdef CONFIG_SOFTMMU
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R4);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R5);
tcg_regset_reset_reg(ct->u.regs, TCG_REG_R6);
#endif
break;
case 'I':
ct->ct |= TCG_CT_CONST_S16;
break;
case 'J':
ct->ct |= TCG_CT_CONST_U16;
break;
case 'M':
ct->ct |= TCG_CT_CONST_MONE;
break;
case 'T':
ct->ct |= TCG_CT_CONST_S32;
break;
case 'U':
ct->ct |= TCG_CT_CONST_U32;
break;
case 'Z':
ct->ct |= TCG_CT_CONST_ZERO;
break;
default:
return -1;
}
ct_str++;
*pct_str = ct_str;
return 0;
}
/* test if a constant matches the constraint */
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;
}
/* The only 32-bit constraint we use aside from
TCG_CT_CONST is TCG_CT_CONST_S16. */
if (type == TCG_TYPE_I32) {
val = (int32_t)val;
}
if ((ct & TCG_CT_CONST_S16) && val == (int16_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_U16) && val == (uint16_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_S32) && val == (int32_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_U32) && val == (uint32_t)val) {
return 1;
} else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
return 1;
} else if ((ct & TCG_CT_CONST_MONE) && val == -1) {
return 1;
}
return 0;
}
#define OPCD(opc) ((opc)<<26)
#define XO19(opc) (OPCD(19)|((opc)<<1))
#define MD30(opc) (OPCD(30)|((opc)<<2))
#define MDS30(opc) (OPCD(30)|((opc)<<1))
#define XO31(opc) (OPCD(31)|((opc)<<1))
#define XO58(opc) (OPCD(58)|(opc))
#define XO62(opc) (OPCD(62)|(opc))
#define B OPCD( 18)
#define BC OPCD( 16)
#define LBZ OPCD( 34)
#define LHZ OPCD( 40)
#define LHA OPCD( 42)
#define LWZ OPCD( 32)
#define STB OPCD( 38)
#define STH OPCD( 44)
#define STW OPCD( 36)
#define STD XO62( 0)
#define STDU XO62( 1)
#define STDX XO31(149)
#define LD XO58( 0)
#define LDX XO31( 21)
#define LDU XO58( 1)
#define LWA XO58( 2)
#define LWAX XO31(341)
#define ADDIC OPCD( 12)
#define ADDI OPCD( 14)
#define ADDIS OPCD( 15)
#define ORI OPCD( 24)
#define ORIS OPCD( 25)
#define XORI OPCD( 26)
#define XORIS OPCD( 27)
#define ANDI OPCD( 28)
#define ANDIS OPCD( 29)
#define MULLI OPCD( 7)
#define CMPLI OPCD( 10)
#define CMPI OPCD( 11)
#define SUBFIC OPCD( 8)
#define LWZU OPCD( 33)
#define STWU OPCD( 37)
#define RLWIMI OPCD( 20)
#define RLWINM OPCD( 21)
#define RLWNM OPCD( 23)
#define RLDICL MD30( 0)
#define RLDICR MD30( 1)
#define RLDIMI MD30( 3)
#define RLDCL MDS30( 8)
#define BCLR XO19( 16)
#define BCCTR XO19(528)
#define CRAND XO19(257)
#define CRANDC XO19(129)
#define CRNAND XO19(225)
#define CROR XO19(449)
#define CRNOR XO19( 33)
#define EXTSB XO31(954)
#define EXTSH XO31(922)
#define EXTSW XO31(986)
#define ADD XO31(266)
#define ADDE XO31(138)
#define ADDME XO31(234)
#define ADDZE XO31(202)
#define ADDC XO31( 10)
#define AND XO31( 28)
#define SUBF XO31( 40)
#define SUBFC XO31( 8)
#define SUBFE XO31(136)
#define SUBFME XO31(232)
#define SUBFZE XO31(200)
#define OR XO31(444)
#define XOR XO31(316)
#define MULLW XO31(235)
#define MULHW XO31( 75)
#define MULHWU XO31( 11)
#define DIVW XO31(491)
#define DIVWU XO31(459)
#define CMP XO31( 0)
#define CMPL XO31( 32)
#define LHBRX XO31(790)
#define LWBRX XO31(534)
#define LDBRX XO31(532)
#define STHBRX XO31(918)
#define STWBRX XO31(662)
#define STDBRX XO31(660)
#define MFSPR XO31(339)
#define MTSPR XO31(467)
#define SRAWI XO31(824)
#define NEG XO31(104)
#define MFCR XO31( 19)
#define MFOCRF (MFCR | (1u << 20))
#define NOR XO31(124)
#define CNTLZW XO31( 26)
#define CNTLZD XO31( 58)
#define ANDC XO31( 60)
#define ORC XO31(412)
#define EQV XO31(284)
#define NAND XO31(476)
#define ISEL XO31( 15)
#define MULLD XO31(233)
#define MULHD XO31( 73)
#define MULHDU XO31( 9)
#define DIVD XO31(489)
#define DIVDU XO31(457)
#define LBZX XO31( 87)
#define LHZX XO31(279)
#define LHAX XO31(343)
#define LWZX XO31( 23)
#define STBX XO31(215)
#define STHX XO31(407)
#define STWX XO31(151)
#define SPR(a, b) ((((a)<<5)|(b))<<11)
#define LR SPR(8, 0)
#define CTR SPR(9, 0)
#define SLW XO31( 24)
#define SRW XO31(536)
#define SRAW XO31(792)
#define SLD XO31( 27)
#define SRD XO31(539)
#define SRAD XO31(794)
#define SRADI XO31(413<<1)
#define TW XO31( 4)
#define TRAP (TW | TO(31))
#define NOP ORI /* ori 0,0,0 */
#define RT(r) ((r)<<21)
#define RS(r) ((r)<<21)
#define RA(r) ((r)<<16)
#define RB(r) ((r)<<11)
#define TO(t) ((t)<<21)
#define SH(s) ((s)<<11)
#define MB(b) ((b)<<6)
#define ME(e) ((e)<<1)
#define BO(o) ((o)<<21)
#define MB64(b) ((b)<<5)
#define FXM(b) (1 << (19 - (b)))
#define LK 1
#define TAB(t, a, b) (RT(t) | RA(a) | RB(b))
#define SAB(s, a, b) (RS(s) | RA(a) | RB(b))
#define TAI(s, a, i) (RT(s) | RA(a) | ((i) & 0xffff))
#define SAI(s, a, i) (RS(s) | RA(a) | ((i) & 0xffff))
#define BF(n) ((n)<<23)
#define BI(n, c) (((c)+((n)*4))<<16)
#define BT(n, c) (((c)+((n)*4))<<21)
#define BA(n, c) (((c)+((n)*4))<<16)
#define BB(n, c) (((c)+((n)*4))<<11)
#define BC_(n, c) (((c)+((n)*4))<<6)
#define BO_COND_TRUE BO(12)
#define BO_COND_FALSE BO( 4)
#define BO_ALWAYS BO(20)
enum {
CR_LT,
CR_GT,
CR_EQ,
CR_SO
};
static const uint32_t tcg_to_bc[] = {
[TCG_COND_EQ] = BC | BI(7, CR_EQ) | BO_COND_TRUE,
[TCG_COND_NE] = BC | BI(7, CR_EQ) | BO_COND_FALSE,
[TCG_COND_LT] = BC | BI(7, CR_LT) | BO_COND_TRUE,
[TCG_COND_GE] = BC | BI(7, CR_LT) | BO_COND_FALSE,
[TCG_COND_LE] = BC | BI(7, CR_GT) | BO_COND_FALSE,
[TCG_COND_GT] = BC | BI(7, CR_GT) | BO_COND_TRUE,
[TCG_COND_LTU] = BC | BI(7, CR_LT) | BO_COND_TRUE,
[TCG_COND_GEU] = BC | BI(7, CR_LT) | BO_COND_FALSE,
[TCG_COND_LEU] = BC | BI(7, CR_GT) | BO_COND_FALSE,
[TCG_COND_GTU] = BC | BI(7, CR_GT) | BO_COND_TRUE,
};
/* The low bit here is set if the RA and RB fields must be inverted. */
static const uint32_t tcg_to_isel[] = {
[TCG_COND_EQ] = ISEL | BC_(7, CR_EQ),
[TCG_COND_NE] = ISEL | BC_(7, CR_EQ) | 1,
[TCG_COND_LT] = ISEL | BC_(7, CR_LT),
[TCG_COND_GE] = ISEL | BC_(7, CR_LT) | 1,
[TCG_COND_LE] = ISEL | BC_(7, CR_GT) | 1,
[TCG_COND_GT] = ISEL | BC_(7, CR_GT),
[TCG_COND_LTU] = ISEL | BC_(7, CR_LT),
[TCG_COND_GEU] = ISEL | BC_(7, CR_LT) | 1,
[TCG_COND_LEU] = ISEL | BC_(7, CR_GT) | 1,
[TCG_COND_GTU] = ISEL | BC_(7, CR_GT),
};
static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
TCGReg base, tcg_target_long offset);
static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
{
tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
if (ret != arg) {
tcg_out32(s, OR | SAB(arg, ret, arg));
}
}
static inline void tcg_out_rld(TCGContext *s, int op, TCGReg ra, TCGReg rs,
int sh, int mb)
{
assert(TCG_TARGET_REG_BITS == 64);
sh = SH(sh & 0x1f) | (((sh >> 5) & 1) << 1);
mb = MB64((mb >> 5) | ((mb << 1) & 0x3f));
tcg_out32(s, op | RA(ra) | RS(rs) | sh | mb);
}
static inline void tcg_out_rlw(TCGContext *s, int op, TCGReg ra, TCGReg rs,
int sh, int mb, int me)
{
tcg_out32(s, op | RA(ra) | RS(rs) | SH(sh) | MB(mb) | ME(me));
}
static inline void tcg_out_ext32u(TCGContext *s, TCGReg dst, TCGReg src)
{
tcg_out_rld(s, RLDICL, dst, src, 0, 32);
}
static inline void tcg_out_shli32(TCGContext *s, TCGReg dst, TCGReg src, int c)
{
tcg_out_rlw(s, RLWINM, dst, src, c, 0, 31 - c);
}
static inline void tcg_out_shli64(TCGContext *s, TCGReg dst, TCGReg src, int c)
{
tcg_out_rld(s, RLDICR, dst, src, c, 63 - c);
}
static inline void tcg_out_shri32(TCGContext *s, TCGReg dst, TCGReg src, int c)
{
tcg_out_rlw(s, RLWINM, dst, src, 32 - c, c, 31);
}
static inline void tcg_out_shri64(TCGContext *s, TCGReg dst, TCGReg src, int c)
{
tcg_out_rld(s, RLDICL, dst, src, 64 - c, c);
}
static void tcg_out_movi32(TCGContext *s, TCGReg ret, int32_t arg)
{
if (arg == (int16_t) arg) {
tcg_out32(s, ADDI | TAI(ret, 0, arg));
} else {
tcg_out32(s, ADDIS | TAI(ret, 0, arg >> 16));
if (arg & 0xffff) {
tcg_out32(s, ORI | SAI(ret, ret, arg));
}
}
}
static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret,
tcg_target_long arg)
{
tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
if (type == TCG_TYPE_I32 || arg == (int32_t)arg) {
tcg_out_movi32(s, ret, arg);
} else if (arg == (uint32_t)arg && !(arg & 0x8000)) {
tcg_out32(s, ADDI | TAI(ret, 0, arg));
tcg_out32(s, ORIS | SAI(ret, ret, arg >> 16));
} else {
int32_t high;
if (USE_REG_RA) {
intptr_t diff = arg - (intptr_t)tb_ret_addr;
if (diff == (int32_t)diff) {
tcg_out_mem_long(s, ADDI, ADD, ret, TCG_REG_RA, diff);
return;
}
}
high = arg >> 31 >> 1;
tcg_out_movi32(s, ret, high);
if (high) {
tcg_out_shli64(s, ret, ret, 32);
}
if (arg & 0xffff0000) {
tcg_out32(s, ORIS | SAI(ret, ret, arg >> 16));
}
if (arg & 0xffff) {
tcg_out32(s, ORI | SAI(ret, ret, arg));
}
}
}
static bool mask_operand(uint32_t c, int *mb, int *me)
{
uint32_t lsb, test;
/* Accept a bit pattern like:
0....01....1
1....10....0
0..01..10..0
Keep track of the transitions. */
if (c == 0 || c == -1) {
return false;
}
test = c;
lsb = test & -test;
test += lsb;
if (test & (test - 1)) {
return false;
}
*me = clz32(lsb);
*mb = test ? clz32(test & -test) + 1 : 0;
return true;
}
static bool mask64_operand(uint64_t c, int *mb, int *me)
{
uint64_t lsb;
if (c == 0) {
return false;
}
lsb = c & -c;
/* Accept 1..10..0. */
if (c == -lsb) {
*mb = 0;
*me = clz64(lsb);
return true;
}
/* Accept 0..01..1. */
if (lsb == 1 && (c & (c + 1)) == 0) {
*mb = clz64(c + 1) + 1;
*me = 63;
return true;
}
return false;
}
static void tcg_out_andi32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
{
int mb, me;
if ((c & 0xffff) == c) {
tcg_out32(s, ANDI | SAI(src, dst, c));
return;
} else if ((c & 0xffff0000) == c) {
tcg_out32(s, ANDIS | SAI(src, dst, c >> 16));
return;
} else if (mask_operand(c, &mb, &me)) {
tcg_out_rlw(s, RLWINM, dst, src, 0, mb, me);
} else {
tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_R0, c);
tcg_out32(s, AND | SAB(src, dst, TCG_REG_R0));
}
}
static void tcg_out_andi64(TCGContext *s, TCGReg dst, TCGReg src, uint64_t c)
{
int mb, me;
assert(TCG_TARGET_REG_BITS == 64);
if ((c & 0xffff) == c) {
tcg_out32(s, ANDI | SAI(src, dst, c));
return;
} else if ((c & 0xffff0000) == c) {
tcg_out32(s, ANDIS | SAI(src, dst, c >> 16));
return;
} else if (mask64_operand(c, &mb, &me)) {
if (mb == 0) {
tcg_out_rld(s, RLDICR, dst, src, 0, me);
} else {
tcg_out_rld(s, RLDICL, dst, src, 0, mb);
}
} else {
tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_R0, c);
tcg_out32(s, AND | SAB(src, dst, TCG_REG_R0));
}
}
static void tcg_out_zori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c,
int op_lo, int op_hi)
{
if (c >> 16) {
tcg_out32(s, op_hi | SAI(src, dst, c >> 16));
src = dst;
}
if (c & 0xffff) {
tcg_out32(s, op_lo | SAI(src, dst, c));
src = dst;
}
}
static void tcg_out_ori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
{
tcg_out_zori32(s, dst, src, c, ORI, ORIS);
}
static void tcg_out_xori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
{
tcg_out_zori32(s, dst, src, c, XORI, XORIS);
}
static void tcg_out_b(TCGContext *s, int mask, tcg_insn_unit *target)
{
ptrdiff_t disp = tcg_pcrel_diff(s, target);
if (in_range_b(disp)) {
tcg_out32(s, B | (disp & 0x3fffffc) | mask);
} else {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, (uintptr_t)target);
tcg_out32(s, MTSPR | RS(TCG_REG_R0) | CTR);
tcg_out32(s, BCCTR | BO_ALWAYS | mask);
}
}
static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
TCGReg base, tcg_target_long offset)
{
tcg_target_long orig = offset, l0, l1, extra = 0, align = 0;
bool is_store = false;
TCGReg rs = TCG_REG_TMP1;
switch (opi) {
case LD: case LWA:
align = 3;
/* FALLTHRU */
default:
if (rt != TCG_REG_R0) {
rs = rt;
break;
}
break;
case STD:
align = 3;
/* FALLTHRU */
case STB: case STH: case STW:
is_store = true;
break;
}
/* For unaligned, or very large offsets, use the indexed form. */
if (offset & align || offset != (int32_t)offset) {
if (rs == base) {
rs = TCG_REG_R0;
}
tcg_debug_assert(!is_store || rs != rt);
tcg_out_movi(s, TCG_TYPE_PTR, rs, orig);
tcg_out32(s, opx | TAB(rt, base, rs));
return;
}
l0 = (int16_t)offset;
offset = (offset - l0) >> 16;
l1 = (int16_t)offset;
if (l1 < 0 && orig >= 0) {
extra = 0x4000;
l1 = (int16_t)(offset - 0x4000);
}
if (l1) {
tcg_out32(s, ADDIS | TAI(rs, base, l1));
base = rs;
}
if (extra) {
tcg_out32(s, ADDIS | TAI(rs, base, extra));
base = rs;
}
if (opi != ADDI || base != rt || l0 != 0) {
tcg_out32(s, opi | TAI(rt, base, l0));
}
}
static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
TCGReg arg1, intptr_t arg2)
{
int opi, opx;
assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
if (type == TCG_TYPE_I32) {
opi = LWZ, opx = LWZX;
} else {
opi = LD, opx = LDX;
}
tcg_out_mem_long(s, opi, opx, ret, arg1, arg2);
}
static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
TCGReg arg1, intptr_t arg2)
{
int opi, opx;
assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
if (type == TCG_TYPE_I32) {
opi = STW, opx = STWX;
} else {
opi = STD, opx = STDX;
}
tcg_out_mem_long(s, opi, opx, arg, arg1, arg2);
}
static void tcg_out_cmp(TCGContext *s, int cond, TCGArg arg1, TCGArg arg2,
int const_arg2, int cr, TCGType type)
{
int imm;
uint32_t op;
tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
/* Simplify the comparisons below wrt CMPI. */
if (type == TCG_TYPE_I32) {
arg2 = (int32_t)arg2;
}
switch (cond) {
case TCG_COND_EQ:
case TCG_COND_NE:
if (const_arg2) {
if ((int16_t) arg2 == arg2) {
op = CMPI;
imm = 1;
break;
} else if ((uint16_t) arg2 == arg2) {
op = CMPLI;
imm = 1;
break;
}
}
op = CMPL;
imm = 0;
break;
case TCG_COND_LT:
case TCG_COND_GE:
case TCG_COND_LE:
case TCG_COND_GT:
if (const_arg2) {
if ((int16_t) arg2 == arg2) {
op = CMPI;
imm = 1;
break;
}
}
op = CMP;
imm = 0;
break;
case TCG_COND_LTU:
case TCG_COND_GEU:
case TCG_COND_LEU:
case TCG_COND_GTU:
if (const_arg2) {
if ((uint16_t) arg2 == arg2) {
op = CMPLI;
imm = 1;
break;
}
}
op = CMPL;
imm = 0;
break;
default:
tcg_abort();
}
op |= BF(cr) | ((type == TCG_TYPE_I64) << 21);
if (imm) {
tcg_out32(s, op | RA(arg1) | (arg2 & 0xffff));
} else {
if (const_arg2) {
tcg_out_movi(s, type, TCG_REG_R0, arg2);
arg2 = TCG_REG_R0;
}
tcg_out32(s, op | RA(arg1) | RB(arg2));
}
}
static void tcg_out_setcond_eq0(TCGContext *s, TCGType type,
TCGReg dst, TCGReg src)
{
if (type == TCG_TYPE_I32) {
tcg_out32(s, CNTLZW | RS(src) | RA(dst));
tcg_out_shri32(s, dst, dst, 5);
} else {
tcg_out32(s, CNTLZD | RS(src) | RA(dst));
tcg_out_shri64(s, dst, dst, 6);
}
}
static void tcg_out_setcond_ne0(TCGContext *s, TCGReg dst, TCGReg src)
{
/* X != 0 implies X + -1 generates a carry. Extra addition
trickery means: R = X-1 + ~X + C = X-1 + (-X+1) + C = C. */
if (dst != src) {
tcg_out32(s, ADDIC | TAI(dst, src, -1));
tcg_out32(s, SUBFE | TAB(dst, dst, src));
} else {
tcg_out32(s, ADDIC | TAI(TCG_REG_R0, src, -1));
tcg_out32(s, SUBFE | TAB(dst, TCG_REG_R0, src));
}
}
static TCGReg tcg_gen_setcond_xor(TCGContext *s, TCGReg arg1, TCGArg arg2,
bool const_arg2)
{
if (const_arg2) {
if ((uint32_t)arg2 == arg2) {
tcg_out_xori32(s, TCG_REG_R0, arg1, arg2);
} else {
tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_R0, arg2);
tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, TCG_REG_R0));
}
} else {
tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, arg2));
}
return TCG_REG_R0;
}
static void tcg_out_setcond(TCGContext *s, TCGType type, TCGCond cond,
TCGArg arg0, TCGArg arg1, TCGArg arg2,
int const_arg2)
{
int crop, sh;
assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
/* Ignore high bits of a potential constant arg2. */
if (type == TCG_TYPE_I32) {
arg2 = (uint32_t)arg2;
}
/* Handle common and trivial cases before handling anything else. */
if (arg2 == 0) {
switch (cond) {
case TCG_COND_EQ:
tcg_out_setcond_eq0(s, type, arg0, arg1);
return;
case TCG_COND_NE:
if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
tcg_out_ext32u(s, TCG_REG_R0, arg1);
arg1 = TCG_REG_R0;
}
tcg_out_setcond_ne0(s, arg0, arg1);
return;
case TCG_COND_GE:
tcg_out32(s, NOR | SAB(arg1, arg0, arg1));
arg1 = arg0;
/* FALLTHRU */
case TCG_COND_LT:
/* Extract the sign bit. */
if (type == TCG_TYPE_I32) {
tcg_out_shri32(s, arg0, arg1, 31);
} else {
tcg_out_shri64(s, arg0, arg1, 63);
}
return;
default:
break;
}
}
/* If we have ISEL, we can implement everything with 3 or 4 insns.
All other cases below are also at least 3 insns, so speed up the
code generator by not considering them and always using ISEL. */
if (HAVE_ISEL) {
int isel, tab;
tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
isel = tcg_to_isel[cond];
tcg_out_movi(s, type, arg0, 1);
if (isel & 1) {
/* arg0 = (bc ? 0 : 1) */
tab = TAB(arg0, 0, arg0);
isel &= ~1;
} else {
/* arg0 = (bc ? 1 : 0) */
tcg_out_movi(s, type, TCG_REG_R0, 0);
tab = TAB(arg0, arg0, TCG_REG_R0);
}
tcg_out32(s, isel | tab);
return;
}
switch (cond) {
case TCG_COND_EQ:
arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
tcg_out_setcond_eq0(s, type, arg0, arg1);
return;
case TCG_COND_NE:
arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
/* Discard the high bits only once, rather than both inputs. */
if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
tcg_out_ext32u(s, TCG_REG_R0, arg1);
arg1 = TCG_REG_R0;
}
tcg_out_setcond_ne0(s, arg0, arg1);
return;
case TCG_COND_GT:
case TCG_COND_GTU:
sh = 30;
crop = 0;
goto crtest;
case TCG_COND_LT:
case TCG_COND_LTU:
sh = 29;
crop = 0;
goto crtest;
case TCG_COND_GE:
case TCG_COND_GEU:
sh = 31;
crop = CRNOR | BT(7, CR_EQ) | BA(7, CR_LT) | BB(7, CR_LT);
goto crtest;
case TCG_COND_LE:
case TCG_COND_LEU:
sh = 31;
crop = CRNOR | BT(7, CR_EQ) | BA(7, CR_GT) | BB(7, CR_GT);
crtest:
tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
if (crop) {
tcg_out32(s, crop);
}
tcg_out32(s, MFOCRF | RT(TCG_REG_R0) | FXM(7));
tcg_out_rlw(s, RLWINM, arg0, TCG_REG_R0, sh, 31, 31);
break;
default:
tcg_abort();
}
}
static void tcg_out_bc(TCGContext *s, int bc, TCGLabel *l)
{
if (l->has_value) {
tcg_out32(s, bc | reloc_pc14_val(s->code_ptr, l->u.value_ptr));
} else {
tcg_out_reloc(s, s->code_ptr, R_PPC_REL14, l, 0);
tcg_out_bc_noaddr(s, bc);
}
}
static void tcg_out_brcond(TCGContext *s, TCGCond cond,
TCGArg arg1, TCGArg arg2, int const_arg2,
TCGLabel *l, TCGType type)
{
tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
tcg_out_bc(s, tcg_to_bc[cond], l);
}
static void tcg_out_movcond(TCGContext *s, TCGType type, TCGCond cond,
TCGArg dest, TCGArg c1, TCGArg c2, TCGArg v1,
TCGArg v2, bool const_c2)
{
/* If for some reason both inputs are zero, don't produce bad code. */
if (v1 == 0 && v2 == 0) {
tcg_out_movi(s, type, dest, 0);
return;
}
tcg_out_cmp(s, cond, c1, c2, const_c2, 7, type);
if (HAVE_ISEL) {
int isel = tcg_to_isel[cond];
/* Swap the V operands if the operation indicates inversion. */
if (isel & 1) {
int t = v1;
v1 = v2;
v2 = t;
isel &= ~1;
}
/* V1 == 0 is handled by isel; V2 == 0 must be handled by hand. */
if (v2 == 0) {
tcg_out_movi(s, type, TCG_REG_R0, 0);
}
tcg_out32(s, isel | TAB(dest, v1, v2));
} else {
if (dest == v2) {
cond = tcg_invert_cond(cond);
v2 = v1;
} else if (dest != v1) {
if (v1 == 0) {
tcg_out_movi(s, type, dest, 0);
} else {
tcg_out_mov(s, type, dest, v1);
}
}
/* Branch forward over one insn */
tcg_out32(s, tcg_to_bc[cond] | 8);
if (v2 == 0) {
tcg_out_movi(s, type, dest, 0);
} else {
tcg_out_mov(s, type, dest, v2);
}
}
}
static void tcg_out_cmp2(TCGContext *s, const TCGArg *args,
const int *const_args)
{
static const struct { uint8_t bit1, bit2; } bits[] = {
[TCG_COND_LT ] = { CR_LT, CR_LT },
[TCG_COND_LE ] = { CR_LT, CR_GT },
[TCG_COND_GT ] = { CR_GT, CR_GT },
[TCG_COND_GE ] = { CR_GT, CR_LT },
[TCG_COND_LTU] = { CR_LT, CR_LT },
[TCG_COND_LEU] = { CR_LT, CR_GT },
[TCG_COND_GTU] = { CR_GT, CR_GT },
[TCG_COND_GEU] = { CR_GT, CR_LT },
};
TCGCond cond = args[4], cond2;
TCGArg al, ah, bl, bh;
int blconst, bhconst;
int op, bit1, bit2;
al = args[0];
ah = args[1];
bl = args[2];
bh = args[3];
blconst = const_args[2];
bhconst = const_args[3];
switch (cond) {
case TCG_COND_EQ:
op = CRAND;
goto do_equality;
case TCG_COND_NE:
op = CRNAND;
do_equality:
tcg_out_cmp(s, cond, al, bl, blconst, 6, TCG_TYPE_I32);
tcg_out_cmp(s, cond, ah, bh, bhconst, 7, TCG_TYPE_I32);
tcg_out32(s, op | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ));
break;
case TCG_COND_LT:
case TCG_COND_LE:
case TCG_COND_GT:
case TCG_COND_GE:
case TCG_COND_LTU:
case TCG_COND_LEU:
case TCG_COND_GTU:
case TCG_COND_GEU:
bit1 = bits[cond].bit1;
bit2 = bits[cond].bit2;
op = (bit1 != bit2 ? CRANDC : CRAND);
cond2 = tcg_unsigned_cond(cond);
tcg_out_cmp(s, cond, ah, bh, bhconst, 6, TCG_TYPE_I32);
tcg_out_cmp(s, cond2, al, bl, blconst, 7, TCG_TYPE_I32);
tcg_out32(s, op | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, bit2));
tcg_out32(s, CROR | BT(7, CR_EQ) | BA(6, bit1) | BB(7, CR_EQ));
break;
default:
tcg_abort();
}
}
static void tcg_out_setcond2(TCGContext *s, const TCGArg *args,
const int *const_args)
{
tcg_out_cmp2(s, args + 1, const_args + 1);
tcg_out32(s, MFOCRF | RT(TCG_REG_R0) | FXM(7));
tcg_out_rlw(s, RLWINM, args[0], TCG_REG_R0, 31, 31, 31);
}
static void tcg_out_brcond2 (TCGContext *s, const TCGArg *args,
const int *const_args)
{
tcg_out_cmp2(s, args, const_args);
tcg_out_bc(s, BC | BI(7, CR_EQ) | BO_COND_TRUE, arg_label(args[5]));
}
void ppc_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr)
{
TCGContext s;
s.code_buf = s.code_ptr = (tcg_insn_unit *)jmp_addr;
tcg_out_b(&s, 0, (tcg_insn_unit *)addr);
flush_icache_range(jmp_addr, jmp_addr + tcg_current_code_size(&s));
}
static void tcg_out_call(TCGContext *s, tcg_insn_unit *target)
{
#ifdef _CALL_AIX
/* Look through the descriptor. If the branch is in range, and we
don't have to spend too much effort on building the toc. */
void *tgt = ((void **)target)[0];
uintptr_t toc = ((uintptr_t *)target)[1];
intptr_t diff = tcg_pcrel_diff(s, tgt);
if (in_range_b(diff) && toc == (uint32_t)toc) {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP1, toc);
tcg_out_b(s, LK, tgt);
} else {
/* Fold the low bits of the constant into the addresses below. */
intptr_t arg = (intptr_t)target;
int ofs = (int16_t)arg;
if (ofs + 8 < 0x8000) {
arg -= ofs;
} else {
ofs = 0;
}
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP1, arg);
tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_TMP1, ofs);
tcg_out32(s, MTSPR | RA(TCG_REG_R0) | CTR);
tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R2, TCG_REG_TMP1, ofs + SZP);
tcg_out32(s, BCCTR | BO_ALWAYS | LK);
}
#elif defined(_CALL_ELF) && _CALL_ELF == 2
intptr_t diff;
/* In the ELFv2 ABI, we have to set up r12 to contain the destination
address, which the callee uses to compute its TOC address. */
/* FIXME: when the branch is in range, we could avoid r12 load if we
knew that the destination uses the same TOC, and what its local
entry point offset is. */
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R12, (intptr_t)target);
diff = tcg_pcrel_diff(s, target);
if (in_range_b(diff)) {
tcg_out_b(s, LK, target);
} else {
tcg_out32(s, MTSPR | RS(TCG_REG_R12) | CTR);
tcg_out32(s, BCCTR | BO_ALWAYS | LK);
}
#else
tcg_out_b(s, LK, target);
#endif
}
static const uint32_t qemu_ldx_opc[16] = {
[MO_UB] = LBZX,
[MO_UW] = LHZX,
[MO_UL] = LWZX,
[MO_Q] = LDX,
[MO_SW] = LHAX,
[MO_SL] = LWAX,
[MO_BSWAP | MO_UB] = LBZX,
[MO_BSWAP | MO_UW] = LHBRX,
[MO_BSWAP | MO_UL] = LWBRX,
[MO_BSWAP | MO_Q] = LDBRX,
};
static const uint32_t qemu_stx_opc[16] = {
[MO_UB] = STBX,
[MO_UW] = STHX,
[MO_UL] = STWX,
[MO_Q] = STDX,
[MO_BSWAP | MO_UB] = STBX,
[MO_BSWAP | MO_UW] = STHBRX,
[MO_BSWAP | MO_UL] = STWBRX,
[MO_BSWAP | MO_Q] = STDBRX,
};
static const uint32_t qemu_exts_opc[4] = {
EXTSB, EXTSH, EXTSW, 0
};
#if defined (CONFIG_SOFTMMU)
/* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr,
* int mmu_idx, 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_st_mmu(CPUState *env, target_ulong addr,
* uintxx_t val, int mmu_idx, 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,
};
/* Perform the TLB load and compare. Places the result of the comparison
in CR7, loads the addend of the TLB into R3, and returns the register
containing the guest address (zero-extended into R4). Clobbers R0 and R2. */
static TCGReg tcg_out_tlb_read(TCGContext *s, TCGMemOp opc,
TCGReg addrlo, TCGReg addrhi,
int mem_index, bool is_read)
{
int cmp_off
= (is_read
? 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);
TCGReg base = TCG_AREG0;
TCGMemOp s_bits = opc & MO_SIZE;
/* Extract the page index, shifted into place for tlb index. */
if (TCG_TARGET_REG_BITS == 64) {
if (TARGET_LONG_BITS == 32) {
/* Zero-extend the address into a place helpful for further use. */
tcg_out_ext32u(s, TCG_REG_R4, addrlo);
addrlo = TCG_REG_R4;
} else {
tcg_out_rld(s, RLDICL, TCG_REG_R3, addrlo,
64 - TARGET_PAGE_BITS, 64 - CPU_TLB_BITS);
}
}
/* Compensate for very large offsets. */
if (add_off >= 0x8000) {
/* Most target env are smaller than 32k; none are larger than 64k.
Simplify the logic here merely to offset by 0x7ff0, giving us a
range just shy of 64k. Check this assumption. */
QEMU_BUILD_BUG_ON(offsetof(CPUArchState,
tlb_table[NB_MMU_MODES - 1][1])
> 0x7ff0 + 0x7fff);
tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, base, 0x7ff0));
base = TCG_REG_TMP1;
cmp_off -= 0x7ff0;
add_off -= 0x7ff0;
}
/* Extraction and shifting, part 2. */
if (TCG_TARGET_REG_BITS == 32 || TARGET_LONG_BITS == 32) {
tcg_out_rlw(s, RLWINM, TCG_REG_R3, addrlo,
32 - (TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS),
32 - (CPU_TLB_BITS + CPU_TLB_ENTRY_BITS),
31 - CPU_TLB_ENTRY_BITS);
} else {
tcg_out_shli64(s, TCG_REG_R3, TCG_REG_R3, CPU_TLB_ENTRY_BITS);
}
tcg_out32(s, ADD | TAB(TCG_REG_R3, TCG_REG_R3, base));
/* Load the tlb comparator. */
if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_R4, TCG_REG_R3, cmp_off);
tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP1, TCG_REG_R3, cmp_off + 4);
} else {
tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP1, TCG_REG_R3, cmp_off);
}
/* Load the TLB addend for use on the fast path. Do this asap
to minimize any load use delay. */
tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R3, TCG_REG_R3, add_off);
/* Clear the non-page, non-alignment bits from the address */
if (TCG_TARGET_REG_BITS == 32 || TARGET_LONG_BITS == 32) {
/* We don't support unaligned accesses on 32-bits, preserve
* the bottom bits and thus trigger a comparison failure on
* unaligned accesses
*/
tcg_out_rlw(s, RLWINM, TCG_REG_R0, addrlo, 0,
(32 - s_bits) & 31, 31 - TARGET_PAGE_BITS);
} else if (s_bits) {
/* > byte access, we need to handle alignment */
if ((opc & MO_AMASK) == MO_ALIGN) {
/* Alignment required by the front-end, same as 32-bits */
tcg_out_rld(s, RLDICL, TCG_REG_R0, addrlo,
64 - TARGET_PAGE_BITS, TARGET_PAGE_BITS - s_bits);
tcg_out_rld(s, RLDICL, TCG_REG_R0, TCG_REG_R0, TARGET_PAGE_BITS, 0);
} else {
/* We support unaligned accesses, we need to make sure we fail
* if we cross a page boundary. The trick is to add the
* access_size-1 to the address before masking the low bits.
* That will make the address overflow to the next page if we
* cross a page boundary which will then force a mismatch of
* the TLB compare since the next page cannot possibly be in
* the same TLB index.
*/
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, (1 << s_bits) - 1));
tcg_out_rld(s, RLDICR, TCG_REG_R0, TCG_REG_R0,
0, 63 - TARGET_PAGE_BITS);
}
} else {
/* Byte access, just chop off the bits below the page index */
tcg_out_rld(s, RLDICR, TCG_REG_R0, addrlo, 0, 63 - TARGET_PAGE_BITS);
}
if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP1,
0, 7, TCG_TYPE_I32);
tcg_out_cmp(s, TCG_COND_EQ, addrhi, TCG_REG_R4, 0, 6, TCG_TYPE_I32);
tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ));
} else {
tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP1,
0, 7, TCG_TYPE_TL);
}
return addrlo;
}
/* 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, bool is_ld, TCGMemOpIdx oi,
TCGReg datalo_reg, TCGReg datahi_reg,
TCGReg addrlo_reg, TCGReg addrhi_reg,
tcg_insn_unit *raddr, tcg_insn_unit *lptr)
{
TCGLabelQemuLdst *label = new_ldst_label(s);
label->is_ld = is_ld;
label->oi = oi;
label->datalo_reg = datalo_reg;
label->datahi_reg = datahi_reg;
label->addrlo_reg = addrlo_reg;
label->addrhi_reg = addrhi_reg;
label->raddr = raddr;
label->label_ptr[0] = lptr;
}
static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
TCGMemOpIdx oi = lb->oi;
TCGMemOp opc = get_memop(oi);
TCGReg hi, lo, arg = TCG_REG_R3;
reloc_pc14(lb->label_ptr[0], s->code_ptr);
tcg_out_mov(s, TCG_TYPE_PTR, arg++, TCG_AREG0);
lo = lb->addrlo_reg;
hi = lb->addrhi_reg;
if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
arg |= 1;
#endif
tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
} else {
/* If the address needed to be zero-extended, we'll have already
placed it in R4. The only remaining case is 64-bit guest. */
tcg_out_mov(s, TCG_TYPE_TL, arg++, lo);
}
tcg_out_movi(s, TCG_TYPE_I32, arg++, oi);
tcg_out32(s, MFSPR | RT(arg) | LR);
tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
lo = lb->datalo_reg;
hi = lb->datahi_reg;
if (TCG_TARGET_REG_BITS == 32 && (opc & MO_SIZE) == MO_64) {
tcg_out_mov(s, TCG_TYPE_I32, lo, TCG_REG_R4);
tcg_out_mov(s, TCG_TYPE_I32, hi, TCG_REG_R3);
} else if (opc & MO_SIGN) {
uint32_t insn = qemu_exts_opc[opc & MO_SIZE];
tcg_out32(s, insn | RA(lo) | RS(TCG_REG_R3));
} else {
tcg_out_mov(s, TCG_TYPE_REG, lo, TCG_REG_R3);
}
tcg_out_b(s, 0, lb->raddr);
}
static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
{
TCGMemOpIdx oi = lb->oi;
TCGMemOp opc = get_memop(oi);
TCGMemOp s_bits = opc & MO_SIZE;
TCGReg hi, lo, arg = TCG_REG_R3;
reloc_pc14(lb->label_ptr[0], s->code_ptr);
tcg_out_mov(s, TCG_TYPE_PTR, arg++, TCG_AREG0);
lo = lb->addrlo_reg;
hi = lb->addrhi_reg;
if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
arg |= 1;
#endif
tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
} else {
/* If the address needed to be zero-extended, we'll have already
placed it in R4. The only remaining case is 64-bit guest. */
tcg_out_mov(s, TCG_TYPE_TL, arg++, lo);
}
lo = lb->datalo_reg;
hi = lb->datahi_reg;
if (TCG_TARGET_REG_BITS == 32) {
switch (s_bits) {
case MO_64:
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
arg |= 1;
#endif
tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
/* FALLTHRU */
case MO_32:
tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
break;
default:
tcg_out_rlw(s, RLWINM, arg++, lo, 0, 32 - (8 << s_bits), 31);
break;
}
} else {
if (s_bits == MO_64) {
tcg_out_mov(s, TCG_TYPE_I64, arg++, lo);
} else {
tcg_out_rld(s, RLDICL, arg++, lo, 0, 64 - (8 << s_bits));
}
}
tcg_out_movi(s, TCG_TYPE_I32, arg++, oi);
tcg_out32(s, MFSPR | RT(arg) | LR);
tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
tcg_out_b(s, 0, lb->raddr);
}
#endif /* SOFTMMU */
static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
{
TCGReg datalo, datahi, addrlo, rbase;
TCGReg addrhi __attribute__((unused));
TCGMemOpIdx oi;
TCGMemOp opc, s_bits;
#ifdef CONFIG_SOFTMMU
int mem_index;
tcg_insn_unit *label_ptr;
#endif
datalo = *args++;
datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
addrlo = *args++;
addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
oi = *args++;
opc = get_memop(oi);
s_bits = opc & MO_SIZE;
#ifdef CONFIG_SOFTMMU
mem_index = get_mmuidx(oi);
addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, mem_index, true);
/* Load a pointer into the current opcode w/conditional branch-link. */
label_ptr = s->code_ptr;
tcg_out_bc_noaddr(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK);
rbase = TCG_REG_R3;
#else /* !CONFIG_SOFTMMU */
rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
tcg_out_ext32u(s, TCG_REG_TMP1, addrlo);
addrlo = TCG_REG_TMP1;
}
#endif
if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) {
if (opc & MO_BSWAP) {
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo));
tcg_out32(s, LWBRX | TAB(datahi, rbase, TCG_REG_R0));
} else if (rbase != 0) {
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
tcg_out32(s, LWZX | TAB(datahi, rbase, addrlo));
tcg_out32(s, LWZX | TAB(datalo, rbase, TCG_REG_R0));
} else if (addrlo == datahi) {
tcg_out32(s, LWZ | TAI(datalo, addrlo, 4));
tcg_out32(s, LWZ | TAI(datahi, addrlo, 0));
} else {
tcg_out32(s, LWZ | TAI(datahi, addrlo, 0));
tcg_out32(s, LWZ | TAI(datalo, addrlo, 4));
}
} else {
uint32_t insn = qemu_ldx_opc[opc & (MO_BSWAP | MO_SSIZE)];
if (!HAVE_ISA_2_06 && insn == LDBRX) {
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo));
tcg_out32(s, LWBRX | TAB(TCG_REG_R0, rbase, TCG_REG_R0));
tcg_out_rld(s, RLDIMI, datalo, TCG_REG_R0, 32, 0);
} else if (insn) {
tcg_out32(s, insn | TAB(datalo, rbase, addrlo));
} else {
insn = qemu_ldx_opc[opc & (MO_SIZE | MO_BSWAP)];
tcg_out32(s, insn | TAB(datalo, rbase, addrlo));
insn = qemu_exts_opc[s_bits];
tcg_out32(s, insn | RA(datalo) | RS(datalo));
}
}
#ifdef CONFIG_SOFTMMU
add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi,
s->code_ptr, label_ptr);
#endif
}
static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
{
TCGReg datalo, datahi, addrlo, rbase;
TCGReg addrhi __attribute__((unused));
TCGMemOpIdx oi;
TCGMemOp opc, s_bits;
#ifdef CONFIG_SOFTMMU
int mem_index;
tcg_insn_unit *label_ptr;
#endif
datalo = *args++;
datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
addrlo = *args++;
addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
oi = *args++;
opc = get_memop(oi);
s_bits = opc & MO_SIZE;
#ifdef CONFIG_SOFTMMU
mem_index = get_mmuidx(oi);
addrlo = tcg_out_tlb_read(s, opc, addrlo, addrhi, mem_index, false);
/* Load a pointer into the current opcode w/conditional branch-link. */
label_ptr = s->code_ptr;
tcg_out_bc_noaddr(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK);
rbase = TCG_REG_R3;
#else /* !CONFIG_SOFTMMU */
rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
tcg_out_ext32u(s, TCG_REG_TMP1, addrlo);
addrlo = TCG_REG_TMP1;
}
#endif
if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) {
if (opc & MO_BSWAP) {
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo));
tcg_out32(s, STWBRX | SAB(datahi, rbase, TCG_REG_R0));
} else if (rbase != 0) {
tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
tcg_out32(s, STWX | SAB(datahi, rbase, addrlo));
tcg_out32(s, STWX | SAB(datalo, rbase, TCG_REG_R0));
} else {
tcg_out32(s, STW | TAI(datahi, addrlo, 0));
tcg_out32(s, STW | TAI(datalo, addrlo, 4));
}
} else {
uint32_t insn = qemu_stx_opc[opc & (MO_BSWAP | MO_SIZE)];
if (!HAVE_ISA_2_06 && insn == STDBRX) {
tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo));
tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, addrlo, 4));
tcg_out_shri64(s, TCG_REG_R0, datalo, 32);
tcg_out32(s, STWBRX | SAB(TCG_REG_R0, rbase, TCG_REG_TMP1));
} else {
tcg_out32(s, insn | SAB(datalo, rbase, addrlo));
}
}
#ifdef CONFIG_SOFTMMU
add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi,
s->code_ptr, label_ptr);
#endif
}
/* Parameters for function call generation, used in tcg.c. */
#define TCG_TARGET_STACK_ALIGN 16
#define TCG_TARGET_EXTEND_ARGS 1
#ifdef _CALL_AIX
# define LINK_AREA_SIZE (6 * SZR)
# define LR_OFFSET (1 * SZR)
# define TCG_TARGET_CALL_STACK_OFFSET (LINK_AREA_SIZE + 8 * SZR)
#elif defined(TCG_TARGET_CALL_DARWIN)
# define LINK_AREA_SIZE (6 * SZR)
# define LR_OFFSET (2 * SZR)
#elif TCG_TARGET_REG_BITS == 64
# if defined(_CALL_ELF) && _CALL_ELF == 2
# define LINK_AREA_SIZE (4 * SZR)
# define LR_OFFSET (1 * SZR)
# endif
#else /* TCG_TARGET_REG_BITS == 32 */
# if defined(_CALL_SYSV)
# define LINK_AREA_SIZE (2 * SZR)
# define LR_OFFSET (1 * SZR)
# endif
#endif
#ifndef LR_OFFSET
# error "Unhandled abi"
#endif
#ifndef TCG_TARGET_CALL_STACK_OFFSET
# define TCG_TARGET_CALL_STACK_OFFSET LINK_AREA_SIZE
#endif
#define CPU_TEMP_BUF_SIZE (CPU_TEMP_BUF_NLONGS * (int)sizeof(long))
#define REG_SAVE_SIZE ((int)ARRAY_SIZE(tcg_target_callee_save_regs) * SZR)
#define FRAME_SIZE ((TCG_TARGET_CALL_STACK_OFFSET \
+ TCG_STATIC_CALL_ARGS_SIZE \
+ CPU_TEMP_BUF_SIZE \
+ REG_SAVE_SIZE \
+ TCG_TARGET_STACK_ALIGN - 1) \
& -TCG_TARGET_STACK_ALIGN)
#define REG_SAVE_BOT (FRAME_SIZE - REG_SAVE_SIZE)
static void tcg_target_qemu_prologue(TCGContext *s)
{
int i;
#ifdef _CALL_AIX
void **desc = (void **)s->code_ptr;
desc[0] = desc + 2; /* entry point */
desc[1] = 0; /* environment pointer */
s->code_ptr = (void *)(desc + 2); /* skip over descriptor */
#endif
tcg_set_frame(s, TCG_REG_CALL_STACK, REG_SAVE_BOT - CPU_TEMP_BUF_SIZE,
CPU_TEMP_BUF_SIZE);
/* Prologue */
tcg_out32(s, MFSPR | RT(TCG_REG_R0) | LR);
tcg_out32(s, (SZR == 8 ? STDU : STWU)
| SAI(TCG_REG_R1, TCG_REG_R1, -FRAME_SIZE));
for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i) {
tcg_out_st(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
TCG_REG_R1, REG_SAVE_BOT + i * SZR);
}
tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_R1, FRAME_SIZE+LR_OFFSET);
#ifndef CONFIG_SOFTMMU
if (GUEST_BASE) {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, GUEST_BASE);
tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
}
#endif
tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
tcg_out32(s, MTSPR | RS(tcg_target_call_iarg_regs[1]) | CTR);
if (USE_REG_RA) {
#ifdef _CALL_AIX
/* Make the caller load the value as the TOC into R2. */
tb_ret_addr = s->code_ptr + 2;
desc[1] = tb_ret_addr;
tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_RA, TCG_REG_R2);
tcg_out32(s, BCCTR | BO_ALWAYS);
#elif defined(_CALL_ELF) && _CALL_ELF == 2
/* Compute from the incoming R12 value. */
tb_ret_addr = s->code_ptr + 2;
tcg_out32(s, ADDI | TAI(TCG_REG_RA, TCG_REG_R12,
tcg_ptr_byte_diff(tb_ret_addr, s->code_buf)));
tcg_out32(s, BCCTR | BO_ALWAYS);
#else
/* Reserve max 5 insns for the constant load. */
tb_ret_addr = s->code_ptr + 6;
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_RA, (intptr_t)tb_ret_addr);
tcg_out32(s, BCCTR | BO_ALWAYS);
while (s->code_ptr < tb_ret_addr) {
tcg_out32(s, NOP);
}
#endif
} else {
tcg_out32(s, BCCTR | BO_ALWAYS);
tb_ret_addr = s->code_ptr;
}
/* Epilogue */
assert(tb_ret_addr == s->code_ptr);
tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_R1, FRAME_SIZE+LR_OFFSET);
for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i) {
tcg_out_ld(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
TCG_REG_R1, REG_SAVE_BOT + i * SZR);
}
tcg_out32(s, MTSPR | RS(TCG_REG_R0) | LR);
tcg_out32(s, ADDI | TAI(TCG_REG_R1, TCG_REG_R1, FRAME_SIZE));
tcg_out32(s, BCLR | BO_ALWAYS);
}
static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
const int *const_args)
{
TCGArg a0, a1, a2;
int c;
switch (opc) {
case INDEX_op_exit_tb:
if (USE_REG_RA) {
ptrdiff_t disp = tcg_pcrel_diff(s, tb_ret_addr);
/* If we can use a direct branch, otherwise use the value in RA.
Note that the direct branch is always forward. If it's in
range now, it'll still be in range after the movi. Don't
bother about the 20 bytes where the test here fails but it
would succeed below. */
if (!in_range_b(disp)) {
tcg_out32(s, MTSPR | RS(TCG_REG_RA) | CTR);
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R3, args[0]);
tcg_out32(s, BCCTR | BO_ALWAYS);
break;
}
}
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R3, args[0]);
tcg_out_b(s, 0, tb_ret_addr);
break;
case INDEX_op_goto_tb:
if (s->tb_jmp_offset) {
/* Direct jump method. */
s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
s->code_ptr += 7;
} else {
/* Indirect jump method. */
tcg_abort();
}
s->tb_next_offset[args[0]] = tcg_current_code_size(s);
break;
case INDEX_op_br:
{
TCGLabel *l = arg_label(args[0]);
if (l->has_value) {
tcg_out_b(s, 0, l->u.value_ptr);
} else {
tcg_out_reloc(s, s->code_ptr, R_PPC_REL24, l, 0);
tcg_out_b_noaddr(s, B);
}
}
break;
case INDEX_op_ld8u_i32:
case INDEX_op_ld8u_i64:
tcg_out_mem_long(s, LBZ, LBZX, args[0], args[1], args[2]);
break;
case INDEX_op_ld8s_i32:
case INDEX_op_ld8s_i64:
tcg_out_mem_long(s, LBZ, LBZX, args[0], args[1], args[2]);
tcg_out32(s, EXTSB | RS(args[0]) | RA(args[0]));
break;
case INDEX_op_ld16u_i32:
case INDEX_op_ld16u_i64:
tcg_out_mem_long(s, LHZ, LHZX, args[0], args[1], args[2]);
break;
case INDEX_op_ld16s_i32:
case INDEX_op_ld16s_i64:
tcg_out_mem_long(s, LHA, LHAX, args[0], args[1], args[2]);
break;
case INDEX_op_ld_i32:
case INDEX_op_ld32u_i64:
tcg_out_mem_long(s, LWZ, LWZX, args[0], args[1], args[2]);
break;
case INDEX_op_ld32s_i64:
tcg_out_mem_long(s, LWA, LWAX, args[0], args[1], args[2]);
break;
case INDEX_op_ld_i64:
tcg_out_mem_long(s, LD, LDX, args[0], args[1], args[2]);
break;
case INDEX_op_st8_i32:
case INDEX_op_st8_i64:
tcg_out_mem_long(s, STB, STBX, args[0], args[1], args[2]);
break;
case INDEX_op_st16_i32:
case INDEX_op_st16_i64:
tcg_out_mem_long(s, STH, STHX, args[0], args[1], args[2]);
break;
case INDEX_op_st_i32:
case INDEX_op_st32_i64:
tcg_out_mem_long(s, STW, STWX, args[0], args[1], args[2]);
break;
case INDEX_op_st_i64:
tcg_out_mem_long(s, STD, STDX, args[0], args[1], args[2]);
break;
case INDEX_op_add_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
do_addi_32:
tcg_out_mem_long(s, ADDI, ADD, a0, a1, (int32_t)a2);
} else {
tcg_out32(s, ADD | TAB(a0, a1, a2));
}
break;
case INDEX_op_sub_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[1]) {
if (const_args[2]) {
tcg_out_movi(s, TCG_TYPE_I32, a0, a1 - a2);
} else {
tcg_out32(s, SUBFIC | TAI(a0, a2, a1));
}
} else if (const_args[2]) {
a2 = -a2;
goto do_addi_32;
} else {
tcg_out32(s, SUBF | TAB(a0, a2, a1));
}
break;
case INDEX_op_and_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_andi32(s, a0, a1, a2);
} else {
tcg_out32(s, AND | SAB(a1, a0, a2));
}
break;
case INDEX_op_and_i64:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_andi64(s, a0, a1, a2);
} else {
tcg_out32(s, AND | SAB(a1, a0, a2));
}
break;
case INDEX_op_or_i64:
case INDEX_op_or_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_ori32(s, a0, a1, a2);
} else {
tcg_out32(s, OR | SAB(a1, a0, a2));
}
break;
case INDEX_op_xor_i64:
case INDEX_op_xor_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_xori32(s, a0, a1, a2);
} else {
tcg_out32(s, XOR | SAB(a1, a0, a2));
}
break;
case INDEX_op_andc_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_andi32(s, a0, a1, ~a2);
} else {
tcg_out32(s, ANDC | SAB(a1, a0, a2));
}
break;
case INDEX_op_andc_i64:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out_andi64(s, a0, a1, ~a2);
} else {
tcg_out32(s, ANDC | SAB(a1, a0, a2));
}
break;
case INDEX_op_orc_i32:
if (const_args[2]) {
tcg_out_ori32(s, args[0], args[1], ~args[2]);
break;
}
/* FALLTHRU */
case INDEX_op_orc_i64:
tcg_out32(s, ORC | SAB(args[1], args[0], args[2]));
break;
case INDEX_op_eqv_i32:
if (const_args[2]) {
tcg_out_xori32(s, args[0], args[1], ~args[2]);
break;
}
/* FALLTHRU */
case INDEX_op_eqv_i64:
tcg_out32(s, EQV | SAB(args[1], args[0], args[2]));
break;
case INDEX_op_nand_i32:
case INDEX_op_nand_i64:
tcg_out32(s, NAND | SAB(args[1], args[0], args[2]));
break;
case INDEX_op_nor_i32:
case INDEX_op_nor_i64:
tcg_out32(s, NOR | SAB(args[1], args[0], args[2]));
break;
case INDEX_op_mul_i32:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out32(s, MULLI | TAI(a0, a1, a2));
} else {
tcg_out32(s, MULLW | TAB(a0, a1, a2));
}
break;
case INDEX_op_div_i32:
tcg_out32(s, DIVW | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_divu_i32:
tcg_out32(s, DIVWU | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_shl_i32:
if (const_args[2]) {
tcg_out_shli32(s, args[0], args[1], args[2]);
} else {
tcg_out32(s, SLW | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_shr_i32:
if (const_args[2]) {
tcg_out_shri32(s, args[0], args[1], args[2]);
} else {
tcg_out32(s, SRW | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_sar_i32:
if (const_args[2]) {
tcg_out32(s, SRAWI | RS(args[1]) | RA(args[0]) | SH(args[2]));
} else {
tcg_out32(s, SRAW | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_rotl_i32:
if (const_args[2]) {
tcg_out_rlw(s, RLWINM, args[0], args[1], args[2], 0, 31);
} else {
tcg_out32(s, RLWNM | SAB(args[1], args[0], args[2])
| MB(0) | ME(31));
}
break;
case INDEX_op_rotr_i32:
if (const_args[2]) {
tcg_out_rlw(s, RLWINM, args[0], args[1], 32 - args[2], 0, 31);
} else {
tcg_out32(s, SUBFIC | TAI(TCG_REG_R0, args[2], 32));
tcg_out32(s, RLWNM | SAB(args[1], args[0], TCG_REG_R0)
| MB(0) | ME(31));
}
break;
case INDEX_op_brcond_i32:
tcg_out_brcond(s, args[2], args[0], args[1], const_args[1],
arg_label(args[3]), TCG_TYPE_I32);
break;
case INDEX_op_brcond_i64:
tcg_out_brcond(s, args[2], args[0], args[1], const_args[1],
arg_label(args[3]), TCG_TYPE_I64);
break;
case INDEX_op_brcond2_i32:
tcg_out_brcond2(s, args, const_args);
break;
case INDEX_op_neg_i32:
case INDEX_op_neg_i64:
tcg_out32(s, NEG | RT(args[0]) | RA(args[1]));
break;
case INDEX_op_not_i32:
case INDEX_op_not_i64:
tcg_out32(s, NOR | SAB(args[1], args[0], args[1]));
break;
case INDEX_op_add_i64:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
do_addi_64:
tcg_out_mem_long(s, ADDI, ADD, a0, a1, a2);
} else {
tcg_out32(s, ADD | TAB(a0, a1, a2));
}
break;
case INDEX_op_sub_i64:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[1]) {
if (const_args[2]) {
tcg_out_movi(s, TCG_TYPE_I64, a0, a1 - a2);
} else {
tcg_out32(s, SUBFIC | TAI(a0, a2, a1));
}
} else if (const_args[2]) {
a2 = -a2;
goto do_addi_64;
} else {
tcg_out32(s, SUBF | TAB(a0, a2, a1));
}
break;
case INDEX_op_shl_i64:
if (const_args[2]) {
tcg_out_shli64(s, args[0], args[1], args[2]);
} else {
tcg_out32(s, SLD | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_shr_i64:
if (const_args[2]) {
tcg_out_shri64(s, args[0], args[1], args[2]);
} else {
tcg_out32(s, SRD | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_sar_i64:
if (const_args[2]) {
int sh = SH(args[2] & 0x1f) | (((args[2] >> 5) & 1) << 1);
tcg_out32(s, SRADI | RA(args[0]) | RS(args[1]) | sh);
} else {
tcg_out32(s, SRAD | SAB(args[1], args[0], args[2]));
}
break;
case INDEX_op_rotl_i64:
if (const_args[2]) {
tcg_out_rld(s, RLDICL, args[0], args[1], args[2], 0);
} else {
tcg_out32(s, RLDCL | SAB(args[1], args[0], args[2]) | MB64(0));
}
break;
case INDEX_op_rotr_i64:
if (const_args[2]) {
tcg_out_rld(s, RLDICL, args[0], args[1], 64 - args[2], 0);
} else {
tcg_out32(s, SUBFIC | TAI(TCG_REG_R0, args[2], 64));
tcg_out32(s, RLDCL | SAB(args[1], args[0], TCG_REG_R0) | MB64(0));
}
break;
case INDEX_op_mul_i64:
a0 = args[0], a1 = args[1], a2 = args[2];
if (const_args[2]) {
tcg_out32(s, MULLI | TAI(a0, a1, a2));
} else {
tcg_out32(s, MULLD | TAB(a0, a1, a2));
}
break;
case INDEX_op_div_i64:
tcg_out32(s, DIVD | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_divu_i64:
tcg_out32(s, DIVDU | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_qemu_ld_i32:
tcg_out_qemu_ld(s, args, false);
break;
case INDEX_op_qemu_ld_i64:
tcg_out_qemu_ld(s, args, true);
break;
case INDEX_op_qemu_st_i32:
tcg_out_qemu_st(s, args, false);
break;
case INDEX_op_qemu_st_i64:
tcg_out_qemu_st(s, args, true);
break;
case INDEX_op_ext8s_i32:
case INDEX_op_ext8s_i64:
c = EXTSB;
goto gen_ext;
case INDEX_op_ext16s_i32:
case INDEX_op_ext16s_i64:
c = EXTSH;
goto gen_ext;
case INDEX_op_ext_i32_i64:
case INDEX_op_ext32s_i64:
c = EXTSW;
goto gen_ext;
gen_ext:
tcg_out32(s, c | RS(args[1]) | RA(args[0]));
break;
case INDEX_op_extu_i32_i64:
tcg_out_ext32u(s, args[0], args[1]);
break;
case INDEX_op_setcond_i32:
tcg_out_setcond(s, TCG_TYPE_I32, args[3], args[0], args[1], args[2],
const_args[2]);
break;
case INDEX_op_setcond_i64:
tcg_out_setcond(s, TCG_TYPE_I64, args[3], args[0], args[1], args[2],
const_args[2]);
break;
case INDEX_op_setcond2_i32:
tcg_out_setcond2(s, args, const_args);
break;
case INDEX_op_bswap16_i32:
case INDEX_op_bswap16_i64:
a0 = args[0], a1 = args[1];
/* a1 = abcd */
if (a0 != a1) {
/* a0 = (a1 r<< 24) & 0xff # 000c */
tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
/* a0 = (a0 & ~0xff00) | (a1 r<< 8) & 0xff00 # 00dc */
tcg_out_rlw(s, RLWIMI, a0, a1, 8, 16, 23);
} else {
/* r0 = (a1 r<< 8) & 0xff00 # 00d0 */
tcg_out_rlw(s, RLWINM, TCG_REG_R0, a1, 8, 16, 23);
/* a0 = (a1 r<< 24) & 0xff # 000c */
tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
/* a0 = a0 | r0 # 00dc */
tcg_out32(s, OR | SAB(TCG_REG_R0, a0, a0));
}
break;
case INDEX_op_bswap32_i32:
case INDEX_op_bswap32_i64:
/* Stolen from gcc's builtin_bswap32 */
a1 = args[1];
a0 = args[0] == a1 ? TCG_REG_R0 : args[0];
/* a1 = args[1] # abcd */
/* a0 = rotate_left (a1, 8) # bcda */
tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
/* a0 = (a0 & ~0xff000000) | ((a1 r<< 24) & 0xff000000) # dcda */
tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
/* a0 = (a0 & ~0x0000ff00) | ((a1 r<< 24) & 0x0000ff00) # dcba */
tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
if (a0 == TCG_REG_R0) {
tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
}
break;
case INDEX_op_bswap64_i64:
a0 = args[0], a1 = args[1], a2 = TCG_REG_R0;
if (a0 == a1) {
a0 = TCG_REG_R0;
a2 = a1;
}
/* a1 = # abcd efgh */
/* a0 = rl32(a1, 8) # 0000 fghe */
tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
/* a0 = dep(a0, rl32(a1, 24), 0xff000000) # 0000 hghe */
tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
/* a0 = dep(a0, rl32(a1, 24), 0x0000ff00) # 0000 hgfe */
tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
/* a0 = rl64(a0, 32) # hgfe 0000 */
/* a2 = rl64(a1, 32) # efgh abcd */
tcg_out_rld(s, RLDICL, a0, a0, 32, 0);
tcg_out_rld(s, RLDICL, a2, a1, 32, 0);
/* a0 = dep(a0, rl32(a2, 8), 0xffffffff) # hgfe bcda */
tcg_out_rlw(s, RLWIMI, a0, a2, 8, 0, 31);
/* a0 = dep(a0, rl32(a2, 24), 0xff000000) # hgfe dcda */
tcg_out_rlw(s, RLWIMI, a0, a2, 24, 0, 7);
/* a0 = dep(a0, rl32(a2, 24), 0x0000ff00) # hgfe dcba */
tcg_out_rlw(s, RLWIMI, a0, a2, 24, 16, 23);
if (a0 == 0) {
tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
}
break;
case INDEX_op_deposit_i32:
if (const_args[2]) {
uint32_t mask = ((2u << (args[4] - 1)) - 1) << args[3];
tcg_out_andi32(s, args[0], args[0], ~mask);
} else {
tcg_out_rlw(s, RLWIMI, args[0], args[2], args[3],
32 - args[3] - args[4], 31 - args[3]);
}
break;
case INDEX_op_deposit_i64:
if (const_args[2]) {
uint64_t mask = ((2ull << (args[4] - 1)) - 1) << args[3];
tcg_out_andi64(s, args[0], args[0], ~mask);
} else {
tcg_out_rld(s, RLDIMI, args[0], args[2], args[3],
64 - args[3] - args[4]);
}
break;
case INDEX_op_movcond_i32:
tcg_out_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1], args[2],
args[3], args[4], const_args[2]);
break;
case INDEX_op_movcond_i64:
tcg_out_movcond(s, TCG_TYPE_I64, args[5], args[0], args[1], args[2],
args[3], args[4], const_args[2]);
break;
#if TCG_TARGET_REG_BITS == 64
case INDEX_op_add2_i64:
#else
case INDEX_op_add2_i32:
#endif
/* Note that the CA bit is defined based on the word size of the
environment. So in 64-bit mode it's always carry-out of bit 63.
The fallback code using deposit works just as well for 32-bit. */
a0 = args[0], a1 = args[1];
if (a0 == args[3] || (!const_args[5] && a0 == args[5])) {
a0 = TCG_REG_R0;
}
if (const_args[4]) {
tcg_out32(s, ADDIC | TAI(a0, args[2], args[4]));
} else {
tcg_out32(s, ADDC | TAB(a0, args[2], args[4]));
}
if (const_args[5]) {
tcg_out32(s, (args[5] ? ADDME : ADDZE) | RT(a1) | RA(args[3]));
} else {
tcg_out32(s, ADDE | TAB(a1, args[3], args[5]));
}
if (a0 != args[0]) {
tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
}
break;
#if TCG_TARGET_REG_BITS == 64
case INDEX_op_sub2_i64:
#else
case INDEX_op_sub2_i32:
#endif
a0 = args[0], a1 = args[1];
if (a0 == args[5] || (!const_args[3] && a0 == args[3])) {
a0 = TCG_REG_R0;
}
if (const_args[2]) {
tcg_out32(s, SUBFIC | TAI(a0, args[4], args[2]));
} else {
tcg_out32(s, SUBFC | TAB(a0, args[4], args[2]));
}
if (const_args[3]) {
tcg_out32(s, (args[3] ? SUBFME : SUBFZE) | RT(a1) | RA(args[5]));
} else {
tcg_out32(s, SUBFE | TAB(a1, args[5], args[3]));
}
if (a0 != args[0]) {
tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
}
break;
case INDEX_op_muluh_i32:
tcg_out32(s, MULHWU | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_mulsh_i32:
tcg_out32(s, MULHW | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_muluh_i64:
tcg_out32(s, MULHDU | TAB(args[0], args[1], args[2]));
break;
case INDEX_op_mulsh_i64:
tcg_out32(s, MULHD | TAB(args[0], args[1], args[2]));
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();
}
}
static const TCGTargetOpDef ppc_op_defs[] = {
{ INDEX_op_exit_tb, { } },
{ INDEX_op_goto_tb, { } },
{ INDEX_op_br, { } },
{ 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" } },
{ INDEX_op_add_i32, { "r", "r", "ri" } },
{ INDEX_op_mul_i32, { "r", "r", "rI" } },
{ INDEX_op_div_i32, { "r", "r", "r" } },
{ INDEX_op_divu_i32, { "r", "r", "r" } },
{ INDEX_op_sub_i32, { "r", "rI", "ri" } },
{ INDEX_op_and_i32, { "r", "r", "ri" } },
{ INDEX_op_or_i32, { "r", "r", "ri" } },
{ INDEX_op_xor_i32, { "r", "r", "ri" } },
{ INDEX_op_andc_i32, { "r", "r", "ri" } },
{ INDEX_op_orc_i32, { "r", "r", "ri" } },
{ INDEX_op_eqv_i32, { "r", "r", "ri" } },
{ INDEX_op_nand_i32, { "r", "r", "r" } },
{ INDEX_op_nor_i32, { "r", "r", "r" } },
{ INDEX_op_shl_i32, { "r", "r", "ri" } },
{ INDEX_op_shr_i32, { "r", "r", "ri" } },
{ INDEX_op_sar_i32, { "r", "r", "ri" } },
{ INDEX_op_rotl_i32, { "r", "r", "ri" } },
{ INDEX_op_rotr_i32, { "r", "r", "ri" } },
{ INDEX_op_neg_i32, { "r", "r" } },
{ INDEX_op_not_i32, { "r", "r" } },
{ INDEX_op_ext8s_i32, { "r", "r" } },
{ INDEX_op_ext16s_i32, { "r", "r" } },
{ INDEX_op_bswap16_i32, { "r", "r" } },
{ INDEX_op_bswap32_i32, { "r", "r" } },
{ INDEX_op_brcond_i32, { "r", "ri" } },
{ INDEX_op_setcond_i32, { "r", "r", "ri" } },
{ INDEX_op_movcond_i32, { "r", "r", "ri", "rZ", "rZ" } },
{ INDEX_op_deposit_i32, { "r", "0", "rZ" } },
{ INDEX_op_muluh_i32, { "r", "r", "r" } },
{ INDEX_op_mulsh_i32, { "r", "r", "r" } },
#if TCG_TARGET_REG_BITS == 64
{ 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_i64, { "r", "r" } },
{ INDEX_op_st16_i64, { "r", "r" } },
{ INDEX_op_st32_i64, { "r", "r" } },
{ INDEX_op_st_i64, { "r", "r" } },
{ INDEX_op_add_i64, { "r", "r", "rT" } },
{ INDEX_op_sub_i64, { "r", "rI", "rT" } },
{ INDEX_op_and_i64, { "r", "r", "ri" } },
{ INDEX_op_or_i64, { "r", "r", "rU" } },
{ INDEX_op_xor_i64, { "r", "r", "rU" } },
{ INDEX_op_andc_i64, { "r", "r", "ri" } },
{ INDEX_op_orc_i64, { "r", "r", "r" } },
{ INDEX_op_eqv_i64, { "r", "r", "r" } },
{ INDEX_op_nand_i64, { "r", "r", "r" } },
{ INDEX_op_nor_i64, { "r", "r", "r" } },
{ 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_mul_i64, { "r", "r", "rI" } },
{ INDEX_op_div_i64, { "r", "r", "r" } },
{ INDEX_op_divu_i64, { "r", "r", "r" } },
{ INDEX_op_neg_i64, { "r", "r" } },
{ INDEX_op_not_i64, { "r", "r" } },
{ INDEX_op_ext8s_i64, { "r", "r" } },
{ INDEX_op_ext16s_i64, { "r", "r" } },
{ INDEX_op_ext32s_i64, { "r", "r" } },
{ INDEX_op_ext_i32_i64, { "r", "r" } },
{ INDEX_op_extu_i32_i64, { "r", "r" } },
{ INDEX_op_bswap16_i64, { "r", "r" } },
{ INDEX_op_bswap32_i64, { "r", "r" } },
{ INDEX_op_bswap64_i64, { "r", "r" } },
{ INDEX_op_brcond_i64, { "r", "ri" } },
{ INDEX_op_setcond_i64, { "r", "r", "ri" } },
{ INDEX_op_movcond_i64, { "r", "r", "ri", "rZ", "rZ" } },
{ INDEX_op_deposit_i64, { "r", "0", "rZ" } },
{ INDEX_op_mulsh_i64, { "r", "r", "r" } },
{ INDEX_op_muluh_i64, { "r", "r", "r" } },
#endif
#if TCG_TARGET_REG_BITS == 32
{ INDEX_op_brcond2_i32, { "r", "r", "ri", "ri" } },
{ INDEX_op_setcond2_i32, { "r", "r", "r", "ri", "ri" } },
#endif
#if TCG_TARGET_REG_BITS == 64
{ INDEX_op_add2_i64, { "r", "r", "r", "r", "rI", "rZM" } },
{ INDEX_op_sub2_i64, { "r", "r", "rI", "rZM", "r", "r" } },
#else
{ INDEX_op_add2_i32, { "r", "r", "r", "r", "rI", "rZM" } },
{ INDEX_op_sub2_i32, { "r", "r", "rI", "rZM", "r", "r" } },
#endif
#if TCG_TARGET_REG_BITS == 64
{ INDEX_op_qemu_ld_i32, { "r", "L" } },
{ INDEX_op_qemu_st_i32, { "S", "S" } },
{ INDEX_op_qemu_ld_i64, { "r", "L" } },
{ INDEX_op_qemu_st_i64, { "S", "S" } },
#elif TARGET_LONG_BITS == 32
{ INDEX_op_qemu_ld_i32, { "r", "L" } },
{ INDEX_op_qemu_st_i32, { "S", "S" } },
{ INDEX_op_qemu_ld_i64, { "L", "L", "L" } },
{ INDEX_op_qemu_st_i64, { "S", "S", "S" } },
#else
{ INDEX_op_qemu_ld_i32, { "r", "L", "L" } },
{ INDEX_op_qemu_st_i32, { "S", "S", "S" } },
{ INDEX_op_qemu_ld_i64, { "L", "L", "L", "L" } },
{ INDEX_op_qemu_st_i64, { "S", "S", "S", "S" } },
#endif
{ -1 },
};
static void tcg_target_init(TCGContext *s)
{
unsigned long hwcap = qemu_getauxval(AT_HWCAP);
if (hwcap & PPC_FEATURE_ARCH_2_06) {
have_isa_2_06 = true;
}
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_R0) |
(1 << TCG_REG_R2) |
(1 << TCG_REG_R3) |
(1 << TCG_REG_R4) |
(1 << TCG_REG_R5) |
(1 << TCG_REG_R6) |
(1 << TCG_REG_R7) |
(1 << TCG_REG_R8) |
(1 << TCG_REG_R9) |
(1 << TCG_REG_R10) |
(1 << TCG_REG_R11) |
(1 << TCG_REG_R12));
tcg_regset_clear(s->reserved_regs);
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R0); /* tcg temp */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R1); /* stack pointer */
#if defined(_CALL_SYSV)
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R2); /* toc pointer */
#endif
#if defined(_CALL_SYSV) || TCG_TARGET_REG_BITS == 64
tcg_regset_set_reg(s->reserved_regs, TCG_REG_R13); /* thread pointer */
#endif
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP1); /* mem temp */
if (USE_REG_RA) {
tcg_regset_set_reg(s->reserved_regs, TCG_REG_RA); /* return addr */
}
tcg_add_target_add_op_defs(ppc_op_defs);
}
#ifdef __ELF__
typedef struct {
DebugFrameCIE cie;
DebugFrameFDEHeader fde;
uint8_t fde_def_cfa[4];
uint8_t fde_reg_ofs[ARRAY_SIZE(tcg_target_callee_save_regs) * 2 + 3];
} DebugFrame;
/* We're expecting a 2 byte uleb128 encoded value. */
QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
#if TCG_TARGET_REG_BITS == 64
# define ELF_HOST_MACHINE EM_PPC64
#else
# define ELF_HOST_MACHINE EM_PPC
#endif
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 = (-SZR & 0x7f), /* sleb128 -SZR */
.cie.return_column = 65,
/* Total FDE size does not include the "len" member. */
.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, fde.cie_offset),
.fde_def_cfa = {
12, TCG_REG_R1, /* DW_CFA_def_cfa r1, ... */
(FRAME_SIZE & 0x7f) | 0x80, /* ... uleb128 FRAME_SIZE */
(FRAME_SIZE >> 7)
},
.fde_reg_ofs = {
/* DW_CFA_offset_extended_sf, lr, LR_OFFSET */
0x11, 65, (LR_OFFSET / -SZR) & 0x7f,
}
};
void tcg_register_jit(void *buf, size_t buf_size)
{
uint8_t *p = &debug_frame.fde_reg_ofs[3];
int i;
for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i, p += 2) {
p[0] = 0x80 + tcg_target_callee_save_regs[i];
p[1] = (FRAME_SIZE - (REG_SAVE_BOT + i * SZR)) / SZR;
}
debug_frame.fde.func_start = (uintptr_t)buf;
debug_frame.fde.func_len = buf_size;
tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
}
#endif /* __ELF__ */
static size_t dcache_bsize = 16;
static size_t icache_bsize = 16;
void flush_icache_range(uintptr_t start, uintptr_t stop)
{
uintptr_t p, start1, stop1;
size_t dsize = dcache_bsize;
size_t isize = icache_bsize;
start1 = start & ~(dsize - 1);
stop1 = (stop + dsize - 1) & ~(dsize - 1);
for (p = start1; p < stop1; p += dsize) {
asm volatile ("dcbst 0,%0" : : "r"(p) : "memory");
}
asm volatile ("sync" : : : "memory");
start &= start & ~(isize - 1);
stop1 = (stop + isize - 1) & ~(isize - 1);
for (p = start1; p < stop1; p += isize) {
asm volatile ("icbi 0,%0" : : "r"(p) : "memory");
}
asm volatile ("sync" : : : "memory");
asm volatile ("isync" : : : "memory");
}
#if defined _AIX
#include <sys/systemcfg.h>
static void __attribute__((constructor)) tcg_cache_init(void)
{
icache_bsize = _system_configuration.icache_line;
dcache_bsize = _system_configuration.dcache_line;
}
#elif defined __linux__
static void __attribute__((constructor)) tcg_cache_init(void)
{
unsigned long dsize = qemu_getauxval(AT_DCACHEBSIZE);
unsigned long isize = qemu_getauxval(AT_ICACHEBSIZE);
if (dsize == 0 || isize == 0) {
if (dsize == 0) {
fprintf(stderr, "getauxval AT_DCACHEBSIZE failed\n");
}
if (isize == 0) {
fprintf(stderr, "getauxval AT_ICACHEBSIZE failed\n");
}
exit(1);
}
dcache_bsize = dsize;
icache_bsize = isize;
}
#elif defined __APPLE__
#include <stdio.h>
#include <sys/types.h>
#include <sys/sysctl.h>
static void __attribute__((constructor)) tcg_cache_init(void)
{
size_t len;
unsigned cacheline;
int name[2] = { CTL_HW, HW_CACHELINE };
len = sizeof(cacheline);
if (sysctl(name, 2, &cacheline, &len, NULL, 0)) {
perror("sysctl CTL_HW HW_CACHELINE failed");
exit(1);
}
dcache_bsize = cacheline;
icache_bsize = cacheline;
}
#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/sysctl.h>
static void __attribute__((constructor)) tcg_cache_init(void)
{
size_t len = 4;
unsigned cacheline;
if (sysctlbyname ("machdep.cacheline_size", &cacheline, &len, NULL, 0)) {
fprintf(stderr, "sysctlbyname machdep.cacheline_size failed: %s\n",
strerror(errno));
exit(1);
}
dcache_bsize = cacheline;
icache_bsize = cacheline;
}
#endif
|