aboutsummaryrefslogtreecommitdiff
path: root/gdbserver/linux-aarch64-low.cc
blob: eb30c31f8f80d5d158daf857f882d6e6c838dfd0 (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
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
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
/* GNU/Linux/AArch64 specific low level interface, for the remote server for
   GDB.

   Copyright (C) 2009-2024 Free Software Foundation, Inc.
   Contributed by ARM Ltd.

   This file is part of GDB.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */

#include "linux-low.h"
#include "nat/aarch64-linux.h"
#include "nat/aarch64-linux-hw-point.h"
#include "arch/aarch64-insn.h"
#include "linux-aarch32-low.h"
#include "elf/common.h"
#include "ax.h"
#include "tracepoint.h"
#include "debug.h"

#include <signal.h>
#include <sys/user.h>
#include "nat/gdb_ptrace.h"
#include <asm/ptrace.h>
#include <inttypes.h>
#include <endian.h>
#include <sys/uio.h>

#include "gdb_proc_service.h"
#include "arch/aarch64.h"
#include "arch/aarch64-mte-linux.h"
#include "arch/aarch64-scalable-linux.h"
#include "linux-aarch32-tdesc.h"
#include "linux-aarch64-tdesc.h"
#include "nat/aarch64-mte-linux-ptrace.h"
#include "nat/aarch64-scalable-linux-ptrace.h"
#include "tdesc.h"

#ifdef HAVE_SYS_REG_H
#include <sys/reg.h>
#endif

#ifdef HAVE_GETAUXVAL
#include <sys/auxv.h>
#endif

/* Linux target op definitions for the AArch64 architecture.  */

class aarch64_target : public linux_process_target
{
public:

  const regs_info *get_regs_info () override;

  int breakpoint_kind_from_pc (CORE_ADDR *pcptr) override;

  int breakpoint_kind_from_current_state (CORE_ADDR *pcptr) override;

  const gdb_byte *sw_breakpoint_from_kind (int kind, int *size) override;

  bool supports_z_point_type (char z_type) override;

  bool supports_tracepoints () override;

  bool supports_fast_tracepoints () override;

  int install_fast_tracepoint_jump_pad
    (CORE_ADDR tpoint, CORE_ADDR tpaddr, CORE_ADDR collector,
     CORE_ADDR lockaddr, ULONGEST orig_size, CORE_ADDR *jump_entry,
     CORE_ADDR *trampoline, ULONGEST *trampoline_size,
     unsigned char *jjump_pad_insn, ULONGEST *jjump_pad_insn_size,
     CORE_ADDR *adjusted_insn_addr, CORE_ADDR *adjusted_insn_addr_end,
     char *err) override;

  int get_min_fast_tracepoint_insn_len () override;

  struct emit_ops *emit_ops () override;

  bool supports_memory_tagging () override;

  bool fetch_memtags (CORE_ADDR address, size_t len,
		      gdb::byte_vector &tags, int type) override;

  bool store_memtags (CORE_ADDR address, size_t len,
		      const gdb::byte_vector &tags, int type) override;

protected:

  void low_arch_setup () override;

  bool low_cannot_fetch_register (int regno) override;

  bool low_cannot_store_register (int regno) override;

  bool low_supports_breakpoints () override;

  CORE_ADDR low_get_pc (regcache *regcache) override;

  void low_set_pc (regcache *regcache, CORE_ADDR newpc) override;

  bool low_breakpoint_at (CORE_ADDR pc) override;

  int low_insert_point (raw_bkpt_type type, CORE_ADDR addr,
			int size, raw_breakpoint *bp) override;

  int low_remove_point (raw_bkpt_type type, CORE_ADDR addr,
			int size, raw_breakpoint *bp) override;

  bool low_stopped_by_watchpoint () override;

  CORE_ADDR low_stopped_data_address () override;

  bool low_siginfo_fixup (siginfo_t *native, gdb_byte *inf,
			  int direction) override;

  arch_process_info *low_new_process () override;

  void low_delete_process (arch_process_info *info) override;

  void low_new_thread (lwp_info *) override;

  void low_delete_thread (arch_lwp_info *) override;

  void low_new_fork (process_info *parent, process_info *child) override;

  void low_prepare_to_resume (lwp_info *lwp) override;

  int low_get_thread_area (int lwpid, CORE_ADDR *addrp) override;

  bool low_supports_range_stepping () override;

  bool low_supports_catch_syscall () override;

  void low_get_syscall_trapinfo (regcache *regcache, int *sysno) override;
};

/* The singleton target ops object.  */

static aarch64_target the_aarch64_target;

bool
aarch64_target::low_cannot_fetch_register (int regno)
{
  gdb_assert_not_reached ("linux target op low_cannot_fetch_register "
			  "is not implemented by the target");
}

bool
aarch64_target::low_cannot_store_register (int regno)
{
  gdb_assert_not_reached ("linux target op low_cannot_store_register "
			  "is not implemented by the target");
}

void
aarch64_target::low_prepare_to_resume (lwp_info *lwp)
{
  aarch64_linux_prepare_to_resume (lwp);
}

/* Per-process arch-specific data we want to keep.  */

struct arch_process_info
{
  /* Hardware breakpoint/watchpoint data.
     The reason for them to be per-process rather than per-thread is
     due to the lack of information in the gdbserver environment;
     gdbserver is not told that whether a requested hardware
     breakpoint/watchpoint is thread specific or not, so it has to set
     each hw bp/wp for every thread in the current process.  The
     higher level bp/wp management in gdb will resume a thread if a hw
     bp/wp trap is not expected for it.  Since the hw bp/wp setting is
     same for each thread, it is reasonable for the data to live here.
     */
  struct aarch64_debug_reg_state debug_reg_state;
};

/* Return true if the size of register 0 is 8 byte.  */

static int
is_64bit_tdesc (void)
{
  /* We may not have a current thread at this point, so go straight to
     the process's target description.  */
  return register_size (current_process ()->tdesc, 0) == 8;
}

static void
aarch64_fill_gregset (struct regcache *regcache, void *buf)
{
  struct user_pt_regs *regset = (struct user_pt_regs *) buf;
  int i;

  for (i = 0; i < AARCH64_X_REGS_NUM; i++)
    collect_register (regcache, AARCH64_X0_REGNUM + i, &regset->regs[i]);
  collect_register (regcache, AARCH64_SP_REGNUM, &regset->sp);
  collect_register (regcache, AARCH64_PC_REGNUM, &regset->pc);
  collect_register (regcache, AARCH64_CPSR_REGNUM, &regset->pstate);
}

static void
aarch64_store_gregset (struct regcache *regcache, const void *buf)
{
  const struct user_pt_regs *regset = (const struct user_pt_regs *) buf;
  int i;

  for (i = 0; i < AARCH64_X_REGS_NUM; i++)
    supply_register (regcache, AARCH64_X0_REGNUM + i, &regset->regs[i]);
  supply_register (regcache, AARCH64_SP_REGNUM, &regset->sp);
  supply_register (regcache, AARCH64_PC_REGNUM, &regset->pc);
  supply_register (regcache, AARCH64_CPSR_REGNUM, &regset->pstate);
}

static void
aarch64_fill_fpregset (struct regcache *regcache, void *buf)
{
  struct user_fpsimd_state *regset = (struct user_fpsimd_state *) buf;
  int i;

  for (i = 0; i < AARCH64_V_REGS_NUM; i++)
    collect_register (regcache, AARCH64_V0_REGNUM + i, &regset->vregs[i]);
  collect_register (regcache, AARCH64_FPSR_REGNUM, &regset->fpsr);
  collect_register (regcache, AARCH64_FPCR_REGNUM, &regset->fpcr);
}

static void
aarch64_store_fpregset (struct regcache *regcache, const void *buf)
{
  const struct user_fpsimd_state *regset
    = (const struct user_fpsimd_state *) buf;
  int i;

  for (i = 0; i < AARCH64_V_REGS_NUM; i++)
    supply_register (regcache, AARCH64_V0_REGNUM + i, &regset->vregs[i]);
  supply_register (regcache, AARCH64_FPSR_REGNUM, &regset->fpsr);
  supply_register (regcache, AARCH64_FPCR_REGNUM, &regset->fpcr);
}

/* Store the pauth registers to regcache.  */

static void
aarch64_store_pauthregset (struct regcache *regcache, const void *buf)
{
  uint64_t *pauth_regset = (uint64_t *) buf;
  int pauth_base = find_regno (regcache->tdesc, "pauth_dmask");

  if (pauth_base == 0)
    return;

  supply_register (regcache, AARCH64_PAUTH_DMASK_REGNUM (pauth_base),
		   &pauth_regset[0]);
  supply_register (regcache, AARCH64_PAUTH_CMASK_REGNUM (pauth_base),
		   &pauth_regset[1]);
}

/* Fill BUF with the MTE registers from the regcache.  */

static void
aarch64_fill_mteregset (struct regcache *regcache, void *buf)
{
  uint64_t *mte_regset = (uint64_t *) buf;
  int mte_base = find_regno (regcache->tdesc, "tag_ctl");

  collect_register (regcache, mte_base, mte_regset);
}

/* Store the MTE registers to regcache.  */

static void
aarch64_store_mteregset (struct regcache *regcache, const void *buf)
{
  uint64_t *mte_regset = (uint64_t *) buf;
  int mte_base = find_regno (regcache->tdesc, "tag_ctl");

  /* Tag Control register */
  supply_register (regcache, mte_base, mte_regset);
}

/* Fill BUF with TLS register from the regcache.  */

static void
aarch64_fill_tlsregset (struct regcache *regcache, void *buf)
{
  gdb_byte *tls_buf = (gdb_byte *) buf;
  int tls_regnum  = find_regno (regcache->tdesc, "tpidr");

  collect_register (regcache, tls_regnum, tls_buf);

  /* Read TPIDR2, if it exists.  */
  std::optional<int> regnum = find_regno_no_throw (regcache->tdesc, "tpidr2");

  if (regnum.has_value ())
    collect_register (regcache, *regnum, tls_buf + sizeof (uint64_t));
}

/* Store TLS register to regcache.  */

static void
aarch64_store_tlsregset (struct regcache *regcache, const void *buf)
{
  gdb_byte *tls_buf = (gdb_byte *) buf;
  int tls_regnum  = find_regno (regcache->tdesc, "tpidr");

  supply_register (regcache, tls_regnum, tls_buf);

  /* Write TPIDR2, if it exists.  */
  std::optional<int> regnum = find_regno_no_throw (regcache->tdesc, "tpidr2");

  if (regnum.has_value ())
    supply_register (regcache, *regnum, tls_buf + sizeof (uint64_t));
}

bool
aarch64_target::low_supports_breakpoints ()
{
  return true;
}

/* Implementation of linux target ops method "low_get_pc".  */

CORE_ADDR
aarch64_target::low_get_pc (regcache *regcache)
{
  if (register_size (regcache->tdesc, 0) == 8)
    return linux_get_pc_64bit (regcache);
  else
    return linux_get_pc_32bit (regcache);
}

/* Implementation of linux target ops method "low_set_pc".  */

void
aarch64_target::low_set_pc (regcache *regcache, CORE_ADDR pc)
{
  if (register_size (regcache->tdesc, 0) == 8)
    linux_set_pc_64bit (regcache, pc);
  else
    linux_set_pc_32bit (regcache, pc);
}

#define aarch64_breakpoint_len 4

/* AArch64 BRK software debug mode instruction.
   This instruction needs to match gdb/aarch64-tdep.c
   (aarch64_default_breakpoint).  */
static const gdb_byte aarch64_breakpoint[] = {0x00, 0x00, 0x20, 0xd4};

/* Implementation of linux target ops method "low_breakpoint_at".  */

bool
aarch64_target::low_breakpoint_at (CORE_ADDR where)
{
  if (is_64bit_tdesc ())
    {
      gdb_byte insn[aarch64_breakpoint_len];

      read_memory (where, (unsigned char *) &insn, aarch64_breakpoint_len);
      if (memcmp (insn, aarch64_breakpoint, aarch64_breakpoint_len) == 0)
	return true;

      return false;
    }
  else
    return arm_breakpoint_at (where);
}

static void
aarch64_init_debug_reg_state (struct aarch64_debug_reg_state *state)
{
  int i;

  for (i = 0; i < AARCH64_HBP_MAX_NUM; ++i)
    {
      state->dr_addr_bp[i] = 0;
      state->dr_ctrl_bp[i] = 0;
      state->dr_ref_count_bp[i] = 0;
    }

  for (i = 0; i < AARCH64_HWP_MAX_NUM; ++i)
    {
      state->dr_addr_wp[i] = 0;
      state->dr_ctrl_wp[i] = 0;
      state->dr_ref_count_wp[i] = 0;
    }
}

/* Return the pointer to the debug register state structure in the
   current process' arch-specific data area.  */

struct aarch64_debug_reg_state *
aarch64_get_debug_reg_state (pid_t pid)
{
  struct process_info *proc = find_process_pid (pid);

  return &proc->priv->arch_private->debug_reg_state;
}

/* Implementation of target ops method "supports_z_point_type".  */

bool
aarch64_target::supports_z_point_type (char z_type)
{
  switch (z_type)
    {
    case Z_PACKET_SW_BP:
    case Z_PACKET_HW_BP:
    case Z_PACKET_WRITE_WP:
    case Z_PACKET_READ_WP:
    case Z_PACKET_ACCESS_WP:
      return true;
    default:
      return false;
    }
}

/* Implementation of linux target ops method "low_insert_point".

   It actually only records the info of the to-be-inserted bp/wp;
   the actual insertion will happen when threads are resumed.  */

int
aarch64_target::low_insert_point (raw_bkpt_type type, CORE_ADDR addr,
				  int len, raw_breakpoint *bp)
{
  int ret;
  enum target_hw_bp_type targ_type;
  struct aarch64_debug_reg_state *state
    = aarch64_get_debug_reg_state (pid_of (current_thread));

  if (show_debug_regs)
    fprintf (stderr, "insert_point on entry (addr=0x%08lx, len=%d)\n",
	     (unsigned long) addr, len);

  /* Determine the type from the raw breakpoint type.  */
  targ_type = raw_bkpt_type_to_target_hw_bp_type (type);

  if (targ_type != hw_execute)
    {
      if (aarch64_region_ok_for_watchpoint (addr, len))
	ret = aarch64_handle_watchpoint (targ_type, addr, len,
					 1 /* is_insert */,
					 current_lwp_ptid (), state);
      else
	ret = -1;
    }
  else
    {
      if (len == 3)
	{
	  /* LEN is 3 means the breakpoint is set on a 32-bit thumb
	     instruction.   Set it to 2 to correctly encode length bit
	     mask in hardware/watchpoint control register.  */
	  len = 2;
	}
      ret = aarch64_handle_breakpoint (targ_type, addr, len,
				       1 /* is_insert */, current_lwp_ptid (),
				       state);
    }

  if (show_debug_regs)
    aarch64_show_debug_reg_state (state, "insert_point", addr, len,
				  targ_type);

  return ret;
}

/* Implementation of linux target ops method "low_remove_point".

   It actually only records the info of the to-be-removed bp/wp,
   the actual removal will be done when threads are resumed.  */

int
aarch64_target::low_remove_point (raw_bkpt_type type, CORE_ADDR addr,
				  int len, raw_breakpoint *bp)
{
  int ret;
  enum target_hw_bp_type targ_type;
  struct aarch64_debug_reg_state *state
    = aarch64_get_debug_reg_state (pid_of (current_thread));

  if (show_debug_regs)
    fprintf (stderr, "remove_point on entry (addr=0x%08lx, len=%d)\n",
	     (unsigned long) addr, len);

  /* Determine the type from the raw breakpoint type.  */
  targ_type = raw_bkpt_type_to_target_hw_bp_type (type);

  /* Set up state pointers.  */
  if (targ_type != hw_execute)
    ret =
      aarch64_handle_watchpoint (targ_type, addr, len, 0 /* is_insert */,
				 current_lwp_ptid (), state);
  else
    {
      if (len == 3)
	{
	  /* LEN is 3 means the breakpoint is set on a 32-bit thumb
	     instruction.   Set it to 2 to correctly encode length bit
	     mask in hardware/watchpoint control register.  */
	  len = 2;
	}
      ret = aarch64_handle_breakpoint (targ_type, addr, len,
				       0 /* is_insert */,  current_lwp_ptid (),
				       state);
    }

  if (show_debug_regs)
    aarch64_show_debug_reg_state (state, "remove_point", addr, len,
				  targ_type);

  return ret;
}

static CORE_ADDR
aarch64_remove_non_address_bits (CORE_ADDR pointer)
{
  /* By default, we assume TBI and discard the top 8 bits plus the
     VA range select bit (55).  */
  CORE_ADDR mask = AARCH64_TOP_BITS_MASK;

  /* Check if PAC is available for this target.  */
  if (tdesc_contains_feature (current_process ()->tdesc,
			      "org.gnu.gdb.aarch64.pauth"))
    {
      /* Fetch the PAC masks.  These masks are per-process, so we can just
	 fetch data from whatever thread we have at the moment.

	 Also, we have both a code mask and a data mask.  For now they are the
	 same, but this may change in the future.  */

      struct regcache *regs = get_thread_regcache (current_thread, 1);
      CORE_ADDR dmask = regcache_raw_get_unsigned_by_name (regs, "pauth_dmask");
      CORE_ADDR cmask = regcache_raw_get_unsigned_by_name (regs, "pauth_cmask");
      mask |= aarch64_mask_from_pac_registers (cmask, dmask);
    }

  return aarch64_remove_top_bits (pointer, mask);
}

/* Implementation of linux target ops method "low_stopped_data_address".  */

CORE_ADDR
aarch64_target::low_stopped_data_address ()
{
  siginfo_t siginfo;
  int pid;
  struct aarch64_debug_reg_state *state;

  pid = lwpid_of (current_thread);

  /* Get the siginfo.  */
  if (ptrace (PTRACE_GETSIGINFO, pid, NULL, &siginfo) != 0)
    return (CORE_ADDR) 0;

  /* Need to be a hardware breakpoint/watchpoint trap.  */
  if (siginfo.si_signo != SIGTRAP
      || (siginfo.si_code & 0xffff) != 0x0004 /* TRAP_HWBKPT */)
    return (CORE_ADDR) 0;

  /* Make sure to ignore the top byte, otherwise we may not recognize a
     hardware watchpoint hit.  The stopped data addresses coming from the
     kernel can potentially be tagged addresses.  */
  const CORE_ADDR addr_trap
    = aarch64_remove_non_address_bits ((CORE_ADDR) siginfo.si_addr);

  /* Check if the address matches any watched address.  */
  state = aarch64_get_debug_reg_state (pid_of (current_thread));
  CORE_ADDR result;
  if (aarch64_stopped_data_address (state, addr_trap, &result))
    return result;

  return (CORE_ADDR) 0;
}

/* Implementation of linux target ops method "low_stopped_by_watchpoint".  */

bool
aarch64_target::low_stopped_by_watchpoint ()
{
  return (low_stopped_data_address () != 0);
}

/* Fetch the thread-local storage pointer for libthread_db.  */

ps_err_e
ps_get_thread_area (struct ps_prochandle *ph,
		    lwpid_t lwpid, int idx, void **base)
{
  return aarch64_ps_get_thread_area (ph, lwpid, idx, base,
				     is_64bit_tdesc ());
}

/* Implementation of linux target ops method "low_siginfo_fixup".  */

bool
aarch64_target::low_siginfo_fixup (siginfo_t *native, gdb_byte *inf,
				   int direction)
{
  /* Is the inferior 32-bit?  If so, then fixup the siginfo object.  */
  if (!is_64bit_tdesc ())
    {
      if (direction == 0)
	aarch64_compat_siginfo_from_siginfo ((struct compat_siginfo *) inf,
					     native);
      else
	aarch64_siginfo_from_compat_siginfo (native,
					     (struct compat_siginfo *) inf);

      return true;
    }

  return false;
}

/* Implementation of linux target ops method "low_new_process".  */

arch_process_info *
aarch64_target::low_new_process ()
{
  struct arch_process_info *info = XCNEW (struct arch_process_info);

  aarch64_init_debug_reg_state (&info->debug_reg_state);

  return info;
}

/* Implementation of linux target ops method "low_delete_process".  */

void
aarch64_target::low_delete_process (arch_process_info *info)
{
  xfree (info);
}

void
aarch64_target::low_new_thread (lwp_info *lwp)
{
  aarch64_linux_new_thread (lwp);
}

void
aarch64_target::low_delete_thread (arch_lwp_info *arch_lwp)
{
  aarch64_linux_delete_thread (arch_lwp);
}

/* Implementation of linux target ops method "low_new_fork".  */

void
aarch64_target::low_new_fork (process_info *parent,
			      process_info *child)
{
  /* These are allocated by linux_add_process.  */
  gdb_assert (parent->priv != NULL
	      && parent->priv->arch_private != NULL);
  gdb_assert (child->priv != NULL
	      && child->priv->arch_private != NULL);

  /* Linux kernel before 2.6.33 commit
     72f674d203cd230426437cdcf7dd6f681dad8b0d
     will inherit hardware debug registers from parent
     on fork/vfork/clone.  Newer Linux kernels create such tasks with
     zeroed debug registers.

     GDB core assumes the child inherits the watchpoints/hw
     breakpoints of the parent, and will remove them all from the
     forked off process.  Copy the debug registers mirrors into the
     new process so that all breakpoints and watchpoints can be
     removed together.  The debug registers mirror will become zeroed
     in the end before detaching the forked off process, thus making
     this compatible with older Linux kernels too.  */

  *child->priv->arch_private = *parent->priv->arch_private;
}

/* Wrapper for aarch64_sve_regs_copy_to_reg_buf.  */

static void
aarch64_sve_regs_copy_to_regcache (struct regcache *regcache,
				   ATTRIBUTE_UNUSED const void *buf)
{
  /* BUF is unused here since we collect the data straight from a ptrace
     request in aarch64_sve_regs_copy_to_reg_buf, therefore bypassing
     gdbserver's own call to ptrace.  */

  int tid = lwpid_of (current_thread);

  /* Update the register cache.  aarch64_sve_regs_copy_to_reg_buf handles
     fetching the NT_ARM_SVE state from thread TID.  */
  aarch64_sve_regs_copy_to_reg_buf (tid, regcache);
}

/* Wrapper for aarch64_sve_regs_copy_from_reg_buf.  */

static void
aarch64_sve_regs_copy_from_regcache (struct regcache *regcache, void *buf)
{
  int tid = lwpid_of (current_thread);

  /* Update the thread SVE state.  aarch64_sve_regs_copy_from_reg_buf
     handles writing the SVE/FPSIMD state back to thread TID.  */
  aarch64_sve_regs_copy_from_reg_buf (tid, regcache);

  /* We need to return the expected data in BUF, so copy whatever the kernel
     already has to BUF.  */
  gdb::byte_vector sve_state = aarch64_fetch_sve_regset (tid);
  memcpy (buf, sve_state.data (), sve_state.size ());
}

/* Wrapper for aarch64_za_regs_copy_to_reg_buf, to help copying NT_ARM_ZA
   state from the thread (BUF) to the register cache.  */

static void
aarch64_za_regs_copy_to_regcache (struct regcache *regcache,
				  ATTRIBUTE_UNUSED const void *buf)
{
  /* BUF is unused here since we collect the data straight from a ptrace
     request, therefore bypassing gdbserver's own call to ptrace.  */
  int tid = lwpid_of (current_thread);

  int za_regnum = find_regno (regcache->tdesc, "za");
  int svg_regnum = find_regno (regcache->tdesc, "svg");
  int svcr_regnum = find_regno (regcache->tdesc, "svcr");

  /* Update the register cache.  aarch64_za_regs_copy_to_reg_buf handles
     fetching the NT_ARM_ZA state from thread TID.  */
  aarch64_za_regs_copy_to_reg_buf (tid, regcache, za_regnum, svg_regnum,
				   svcr_regnum);
}

/* Wrapper for aarch64_za_regs_copy_from_reg_buf, to help copying NT_ARM_ZA
   state from the register cache to the thread (BUF).  */

static void
aarch64_za_regs_copy_from_regcache (struct regcache *regcache, void *buf)
{
  int tid = lwpid_of (current_thread);

  int za_regnum = find_regno (regcache->tdesc, "za");
  int svg_regnum = find_regno (regcache->tdesc, "svg");
  int svcr_regnum = find_regno (regcache->tdesc, "svcr");

  /* Update the thread NT_ARM_ZA state.  aarch64_za_regs_copy_from_reg_buf
     handles writing the ZA state back to thread TID.  */
  aarch64_za_regs_copy_from_reg_buf (tid, regcache, za_regnum, svg_regnum,
				     svcr_regnum);

  /* We need to return the expected data in BUF, so copy whatever the kernel
     already has to BUF.  */

  /* Obtain a dump of ZA from ptrace.  */
  gdb::byte_vector za_state = aarch64_fetch_za_regset (tid);
  memcpy (buf, za_state.data (), za_state.size ());
}

/* Wrapper for aarch64_zt_regs_copy_to_reg_buf, to help copying NT_ARM_ZT
   state from the thread (BUF) to the register cache.  */

static void
aarch64_zt_regs_copy_to_regcache (struct regcache *regcache,
				  ATTRIBUTE_UNUSED const void *buf)
{
  /* BUF is unused here since we collect the data straight from a ptrace
     request, therefore bypassing gdbserver's own call to ptrace.  */
  int tid = lwpid_of (current_thread);

  int zt_regnum = find_regno (regcache->tdesc, "zt0");

  /* Update the register cache.  aarch64_zt_regs_copy_to_reg_buf handles
     fetching the NT_ARM_ZT state from thread TID.  */
  aarch64_zt_regs_copy_to_reg_buf (tid, regcache, zt_regnum);
}

/* Wrapper for aarch64_zt_regs_copy_from_reg_buf, to help copying NT_ARM_ZT
   state from the register cache to the thread (BUF).  */

static void
aarch64_zt_regs_copy_from_regcache (struct regcache *regcache, void *buf)
{
  int tid = lwpid_of (current_thread);

  int zt_regnum = find_regno (regcache->tdesc, "zt0");

  /* Update the thread NT_ARM_ZT state.  aarch64_zt_regs_copy_from_reg_buf
     handles writing the ZT state back to thread TID.  */
  aarch64_zt_regs_copy_from_reg_buf (tid, regcache, zt_regnum);

  /* We need to return the expected data in BUF, so copy whatever the kernel
     already has to BUF.  */

  /* Obtain a dump of NT_ARM_ZT from ptrace.  */
  gdb::byte_vector zt_state = aarch64_fetch_zt_regset (tid);
  memcpy (buf, zt_state.data (), zt_state.size ());
}

/* Array containing all the possible register sets for AArch64/Linux.  During
   architecture setup, these will be checked against the HWCAP/HWCAP2 bits for
   validity and enabled/disabled accordingly.

   Their sizes are set to 0 here, but they will be adjusted later depending
   on whether each register set is available or not.  */
static struct regset_info aarch64_regsets[] =
{
  /* GPR registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_PRSTATUS,
    0, GENERAL_REGS,
    aarch64_fill_gregset, aarch64_store_gregset },
  /* Floating Point (FPU) registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_FPREGSET,
    0, FP_REGS,
    aarch64_fill_fpregset, aarch64_store_fpregset
  },
  /* Scalable Vector Extension (SVE) registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_SVE,
    0, EXTENDED_REGS,
    aarch64_sve_regs_copy_from_regcache, aarch64_sve_regs_copy_to_regcache
  },
  /* Scalable Matrix Extension (SME) ZA register.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_ZA,
    0, EXTENDED_REGS,
    aarch64_za_regs_copy_from_regcache, aarch64_za_regs_copy_to_regcache
  },
  /* Scalable Matrix Extension 2 (SME2) ZT registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_ZT,
    0, EXTENDED_REGS,
    aarch64_zt_regs_copy_from_regcache, aarch64_zt_regs_copy_to_regcache
  },
  /* PAC registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_PAC_MASK,
    0, OPTIONAL_REGS,
    nullptr, aarch64_store_pauthregset },
  /* Tagged address control / MTE registers.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_TAGGED_ADDR_CTRL,
    0, OPTIONAL_REGS,
    aarch64_fill_mteregset, aarch64_store_mteregset },
  /* TLS register.  */
  { PTRACE_GETREGSET, PTRACE_SETREGSET, NT_ARM_TLS,
    0, OPTIONAL_REGS,
    aarch64_fill_tlsregset, aarch64_store_tlsregset },
  NULL_REGSET
};

static struct regsets_info aarch64_regsets_info =
  {
    aarch64_regsets, /* regsets */
    0, /* num_regsets */
    nullptr, /* disabled_regsets */
  };

static struct regs_info regs_info_aarch64 =
  {
    nullptr, /* regset_bitmap */
    nullptr, /* usrregs */
    &aarch64_regsets_info,
  };

/* Given FEATURES, adjust the available register sets by setting their
   sizes.  A size of 0 means the register set is disabled and won't be
   used.  */

static void
aarch64_adjust_register_sets (const struct aarch64_features &features)
{
  struct regset_info *regset;

  for (regset = aarch64_regsets; regset->size >= 0; regset++)
    {
      switch (regset->nt_type)
	{
	case NT_PRSTATUS:
	  /* General purpose registers are always present.  */
	  regset->size = sizeof (struct user_pt_regs);
	  break;
	case NT_FPREGSET:
	  /* This is unavailable when SVE is present.  */
	  if (features.vq == 0)
	    regset->size = sizeof (struct user_fpsimd_state);
	  break;
	case NT_ARM_SVE:
	  if (features.vq > 0)
	    regset->size = SVE_PT_SIZE (AARCH64_MAX_SVE_VQ, SVE_PT_REGS_SVE);
	  break;
	case NT_ARM_PAC_MASK:
	  if (features.pauth)
	    regset->size = AARCH64_PAUTH_REGS_SIZE;
	  break;
	case NT_ARM_TAGGED_ADDR_CTRL:
	  if (features.mte)
	    regset->size = AARCH64_LINUX_SIZEOF_MTE;
	  break;
	case NT_ARM_TLS:
	  if (features.tls > 0)
	    regset->size = AARCH64_TLS_REGISTER_SIZE * features.tls;
	  break;
	case NT_ARM_ZA:
	  if (features.svq > 0)
	    regset->size = ZA_PT_SIZE (features.svq);
	  break;
	case NT_ARM_ZT:
	  if (features.sme2)
	    regset->size = AARCH64_SME2_ZT0_SIZE;
	  break;
	default:
	  gdb_assert_not_reached ("Unknown register set found.");
	}
    }
}

/* Matches HWCAP_PACA in kernel header arch/arm64/include/uapi/asm/hwcap.h.  */
#define AARCH64_HWCAP_PACA (1 << 30)

/* Implementation of linux target ops method "low_arch_setup".  */

void
aarch64_target::low_arch_setup ()
{
  unsigned int machine;
  int is_elf64;
  int tid;

  tid = lwpid_of (current_thread);

  is_elf64 = linux_pid_exe_is_elf_64_file (tid, &machine);

  if (is_elf64)
    {
      struct aarch64_features features;
      int pid = current_thread->id.pid ();

      features.vq = aarch64_sve_get_vq (tid);
      /* A-profile PAC is 64-bit only.  */
      features.pauth = linux_get_hwcap (pid, 8) & AARCH64_HWCAP_PACA;
      /* A-profile MTE is 64-bit only.  */
      features.mte = linux_get_hwcap2 (pid, 8) & HWCAP2_MTE;
      features.tls = aarch64_tls_register_count (tid);

      /* Scalable Matrix Extension feature and size check.  */
      if (linux_get_hwcap2 (pid, 8) & HWCAP2_SME)
	features.svq = aarch64_za_get_svq (tid);

      /* Scalable Matrix Extension 2 feature check.  */
      CORE_ADDR hwcap2 = linux_get_hwcap2 (pid, 8);
      if ((hwcap2 & HWCAP2_SME2) || (hwcap2 & HWCAP2_SME2P1))
	{
	  /* Make sure ptrace supports NT_ARM_ZT.  */
	  features.sme2 = supports_zt_registers (tid);
	}

      current_process ()->tdesc = aarch64_linux_read_description (features);

      /* Adjust the register sets we should use for this particular set of
	 features.  */
      aarch64_adjust_register_sets (features);
    }
  else
    current_process ()->tdesc = aarch32_linux_read_description ();

  aarch64_linux_get_debug_reg_capacity (lwpid_of (current_thread));
}

/* Implementation of linux target ops method "get_regs_info".  */

const regs_info *
aarch64_target::get_regs_info ()
{
  if (!is_64bit_tdesc ())
    return &regs_info_aarch32;

  /* AArch64 64-bit registers.  */
  return &regs_info_aarch64;
}

/* Implementation of target ops method "supports_tracepoints".  */

bool
aarch64_target::supports_tracepoints ()
{
  if (current_thread == NULL)
    return true;
  else
    {
      /* We don't support tracepoints on aarch32 now.  */
      return is_64bit_tdesc ();
    }
}

/* Implementation of linux target ops method "low_get_thread_area".  */

int
aarch64_target::low_get_thread_area (int lwpid, CORE_ADDR *addrp)
{
  struct iovec iovec;
  uint64_t reg;

  iovec.iov_base = &reg;
  iovec.iov_len = sizeof (reg);

  if (ptrace (PTRACE_GETREGSET, lwpid, NT_ARM_TLS, &iovec) != 0)
    return -1;

  *addrp = reg;

  return 0;
}

bool
aarch64_target::low_supports_catch_syscall ()
{
  return true;
}

/* Implementation of linux target ops method "low_get_syscall_trapinfo".  */

void
aarch64_target::low_get_syscall_trapinfo (regcache *regcache, int *sysno)
{
  int use_64bit = register_size (regcache->tdesc, 0) == 8;

  if (use_64bit)
    {
      long l_sysno;

      collect_register_by_name (regcache, "x8", &l_sysno);
      *sysno = (int) l_sysno;
    }
  else
    collect_register_by_name (regcache, "r7", sysno);
}

/* List of condition codes that we need.  */

enum aarch64_condition_codes
{
  EQ = 0x0,
  NE = 0x1,
  LO = 0x3,
  GE = 0xa,
  LT = 0xb,
  GT = 0xc,
  LE = 0xd,
};

enum aarch64_operand_type
{
  OPERAND_IMMEDIATE,
  OPERAND_REGISTER,
};

/* Representation of an operand.  At this time, it only supports register
   and immediate types.  */

struct aarch64_operand
{
  /* Type of the operand.  */
  enum aarch64_operand_type type;

  /* Value of the operand according to the type.  */
  union
    {
      uint32_t imm;
      struct aarch64_register reg;
    };
};

/* List of registers that we are currently using, we can add more here as
   we need to use them.  */

/* General purpose scratch registers (64 bit).  */
static const struct aarch64_register x0 = { 0, 1 };
static const struct aarch64_register x1 = { 1, 1 };
static const struct aarch64_register x2 = { 2, 1 };
static const struct aarch64_register x3 = { 3, 1 };
static const struct aarch64_register x4 = { 4, 1 };

/* General purpose scratch registers (32 bit).  */
static const struct aarch64_register w0 = { 0, 0 };
static const struct aarch64_register w2 = { 2, 0 };

/* Intra-procedure scratch registers.  */
static const struct aarch64_register ip0 = { 16, 1 };

/* Special purpose registers.  */
static const struct aarch64_register fp = { 29, 1 };
static const struct aarch64_register lr = { 30, 1 };
static const struct aarch64_register sp = { 31, 1 };
static const struct aarch64_register xzr = { 31, 1 };

/* Dynamically allocate a new register.  If we know the register
   statically, we should make it a global as above instead of using this
   helper function.  */

static struct aarch64_register
aarch64_register (unsigned num, int is64)
{
  return (struct aarch64_register) { num, is64 };
}

/* Helper function to create a register operand, for instructions with
   different types of operands.

   For example:
   p += emit_mov (p, x0, register_operand (x1));  */

static struct aarch64_operand
register_operand (struct aarch64_register reg)
{
  struct aarch64_operand operand;

  operand.type = OPERAND_REGISTER;
  operand.reg = reg;

  return operand;
}

/* Helper function to create an immediate operand, for instructions with
   different types of operands.

   For example:
   p += emit_mov (p, x0, immediate_operand (12));  */

static struct aarch64_operand
immediate_operand (uint32_t imm)
{
  struct aarch64_operand operand;

  operand.type = OPERAND_IMMEDIATE;
  operand.imm = imm;

  return operand;
}

/* Helper function to create an offset memory operand.

   For example:
   p += emit_ldr (p, x0, sp, offset_memory_operand (16));  */

static struct aarch64_memory_operand
offset_memory_operand (int32_t offset)
{
  return (struct aarch64_memory_operand) { MEMORY_OPERAND_OFFSET, offset };
}

/* Helper function to create a pre-index memory operand.

   For example:
   p += emit_ldr (p, x0, sp, preindex_memory_operand (16));  */

static struct aarch64_memory_operand
preindex_memory_operand (int32_t index)
{
  return (struct aarch64_memory_operand) { MEMORY_OPERAND_PREINDEX, index };
}

/* Helper function to create a post-index memory operand.

   For example:
   p += emit_ldr (p, x0, sp, postindex_memory_operand (16));  */

static struct aarch64_memory_operand
postindex_memory_operand (int32_t index)
{
  return (struct aarch64_memory_operand) { MEMORY_OPERAND_POSTINDEX, index };
}

/* System control registers.  These special registers can be written and
   read with the MRS and MSR instructions.

   - NZCV: Condition flags.  GDB refers to this register under the CPSR
	   name.
   - FPSR: Floating-point status register.
   - FPCR: Floating-point control registers.
   - TPIDR_EL0: Software thread ID register.  */

enum aarch64_system_control_registers
{
  /*          op0           op1           crn          crm          op2  */
  NZCV =      (0x1 << 14) | (0x3 << 11) | (0x4 << 7) | (0x2 << 3) | 0x0,
  FPSR =      (0x1 << 14) | (0x3 << 11) | (0x4 << 7) | (0x4 << 3) | 0x1,
  FPCR =      (0x1 << 14) | (0x3 << 11) | (0x4 << 7) | (0x4 << 3) | 0x0,
  TPIDR_EL0 = (0x1 << 14) | (0x3 << 11) | (0xd << 7) | (0x0 << 3) | 0x2
};

/* Write a BLR instruction into *BUF.

     BLR rn

   RN is the register to branch to.  */

static int
emit_blr (uint32_t *buf, struct aarch64_register rn)
{
  return aarch64_emit_insn (buf, BLR | ENCODE (rn.num, 5, 5));
}

/* Write a RET instruction into *BUF.

     RET xn

   RN is the register to branch to.  */

static int
emit_ret (uint32_t *buf, struct aarch64_register rn)
{
  return aarch64_emit_insn (buf, RET | ENCODE (rn.num, 5, 5));
}

static int
emit_load_store_pair (uint32_t *buf, enum aarch64_opcodes opcode,
		      struct aarch64_register rt,
		      struct aarch64_register rt2,
		      struct aarch64_register rn,
		      struct aarch64_memory_operand operand)
{
  uint32_t opc;
  uint32_t pre_index;
  uint32_t write_back;

  if (rt.is64)
    opc = ENCODE (2, 2, 30);
  else
    opc = ENCODE (0, 2, 30);

  switch (operand.type)
    {
    case MEMORY_OPERAND_OFFSET:
      {
	pre_index = ENCODE (1, 1, 24);
	write_back = ENCODE (0, 1, 23);
	break;
      }
    case MEMORY_OPERAND_POSTINDEX:
      {
	pre_index = ENCODE (0, 1, 24);
	write_back = ENCODE (1, 1, 23);
	break;
      }
    case MEMORY_OPERAND_PREINDEX:
      {
	pre_index = ENCODE (1, 1, 24);
	write_back = ENCODE (1, 1, 23);
	break;
      }
    default:
      return 0;
    }

  return aarch64_emit_insn (buf, opcode | opc | pre_index | write_back
			    | ENCODE (operand.index >> 3, 7, 15)
			    | ENCODE (rt2.num, 5, 10)
			    | ENCODE (rn.num, 5, 5) | ENCODE (rt.num, 5, 0));
}

/* Write a STP instruction into *BUF.

     STP rt, rt2, [rn, #offset]
     STP rt, rt2, [rn, #index]!
     STP rt, rt2, [rn], #index

   RT and RT2 are the registers to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to a
   -512 .. 504 range (7 bits << 3).  */

static int
emit_stp (uint32_t *buf, struct aarch64_register rt,
	  struct aarch64_register rt2, struct aarch64_register rn,
	  struct aarch64_memory_operand operand)
{
  return emit_load_store_pair (buf, STP, rt, rt2, rn, operand);
}

/* Write a LDP instruction into *BUF.

     LDP rt, rt2, [rn, #offset]
     LDP rt, rt2, [rn, #index]!
     LDP rt, rt2, [rn], #index

   RT and RT2 are the registers to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to a
   -512 .. 504 range (7 bits << 3).  */

static int
emit_ldp (uint32_t *buf, struct aarch64_register rt,
	  struct aarch64_register rt2, struct aarch64_register rn,
	  struct aarch64_memory_operand operand)
{
  return emit_load_store_pair (buf, LDP, rt, rt2, rn, operand);
}

/* Write a LDP (SIMD&VFP) instruction using Q registers into *BUF.

     LDP qt, qt2, [rn, #offset]

   RT and RT2 are the Q registers to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to
   -1024 .. 1008 range (7 bits << 4).  */

static int
emit_ldp_q_offset (uint32_t *buf, unsigned rt, unsigned rt2,
		   struct aarch64_register rn, int32_t offset)
{
  uint32_t opc = ENCODE (2, 2, 30);
  uint32_t pre_index = ENCODE (1, 1, 24);

  return aarch64_emit_insn (buf, LDP_SIMD_VFP | opc | pre_index
			    | ENCODE (offset >> 4, 7, 15)
			    | ENCODE (rt2, 5, 10)
			    | ENCODE (rn.num, 5, 5) | ENCODE (rt, 5, 0));
}

/* Write a STP (SIMD&VFP) instruction using Q registers into *BUF.

     STP qt, qt2, [rn, #offset]

   RT and RT2 are the Q registers to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to
   -1024 .. 1008 range (7 bits << 4).  */

static int
emit_stp_q_offset (uint32_t *buf, unsigned rt, unsigned rt2,
		   struct aarch64_register rn, int32_t offset)
{
  uint32_t opc = ENCODE (2, 2, 30);
  uint32_t pre_index = ENCODE (1, 1, 24);

  return aarch64_emit_insn (buf, STP_SIMD_VFP | opc | pre_index
			    | ENCODE (offset >> 4, 7, 15)
			    | ENCODE (rt2, 5, 10)
			    | ENCODE (rn.num, 5, 5) | ENCODE (rt, 5, 0));
}

/* Write a LDRH instruction into *BUF.

     LDRH wt, [xn, #offset]
     LDRH wt, [xn, #index]!
     LDRH wt, [xn], #index

   RT is the register to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to
   0 .. 32760 range (12 bits << 3).  */

static int
emit_ldrh (uint32_t *buf, struct aarch64_register rt,
	   struct aarch64_register rn,
	   struct aarch64_memory_operand operand)
{
  return aarch64_emit_load_store (buf, 1, LDR, rt, rn, operand);
}

/* Write a LDRB instruction into *BUF.

     LDRB wt, [xn, #offset]
     LDRB wt, [xn, #index]!
     LDRB wt, [xn], #index

   RT is the register to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to
   0 .. 32760 range (12 bits << 3).  */

static int
emit_ldrb (uint32_t *buf, struct aarch64_register rt,
	   struct aarch64_register rn,
	   struct aarch64_memory_operand operand)
{
  return aarch64_emit_load_store (buf, 0, LDR, rt, rn, operand);
}



/* Write a STR instruction into *BUF.

     STR rt, [rn, #offset]
     STR rt, [rn, #index]!
     STR rt, [rn], #index

   RT is the register to store.
   RN is the base address register.
   OFFSET is the immediate to add to the base address.  It is limited to
   0 .. 32760 range (12 bits << 3).  */

static int
emit_str (uint32_t *buf, struct aarch64_register rt,
	  struct aarch64_register rn,
	  struct aarch64_memory_operand operand)
{
  return aarch64_emit_load_store (buf, rt.is64 ? 3 : 2, STR, rt, rn, operand);
}

/* Helper function emitting an exclusive load or store instruction.  */

static int
emit_load_store_exclusive (uint32_t *buf, uint32_t size,
			   enum aarch64_opcodes opcode,
			   struct aarch64_register rs,
			   struct aarch64_register rt,
			   struct aarch64_register rt2,
			   struct aarch64_register rn)
{
  return aarch64_emit_insn (buf, opcode | ENCODE (size, 2, 30)
			    | ENCODE (rs.num, 5, 16) | ENCODE (rt2.num, 5, 10)
			    | ENCODE (rn.num, 5, 5) | ENCODE (rt.num, 5, 0));
}

/* Write a LAXR instruction into *BUF.

     LDAXR rt, [xn]

   RT is the destination register.
   RN is the base address register.  */

static int
emit_ldaxr (uint32_t *buf, struct aarch64_register rt,
	    struct aarch64_register rn)
{
  return emit_load_store_exclusive (buf, rt.is64 ? 3 : 2, LDAXR, xzr, rt,
				    xzr, rn);
}

/* Write a STXR instruction into *BUF.

     STXR ws, rt, [xn]

   RS is the result register, it indicates if the store succeeded or not.
   RT is the destination register.
   RN is the base address register.  */

static int
emit_stxr (uint32_t *buf, struct aarch64_register rs,
	   struct aarch64_register rt, struct aarch64_register rn)
{
  return emit_load_store_exclusive (buf, rt.is64 ? 3 : 2, STXR, rs, rt,
				    xzr, rn);
}

/* Write a STLR instruction into *BUF.

     STLR rt, [xn]

   RT is the register to store.
   RN is the base address register.  */

static int
emit_stlr (uint32_t *buf, struct aarch64_register rt,
	   struct aarch64_register rn)
{
  return emit_load_store_exclusive (buf, rt.is64 ? 3 : 2, STLR, xzr, rt,
				    xzr, rn);
}

/* Helper function for data processing instructions with register sources.  */

static int
emit_data_processing_reg (uint32_t *buf, uint32_t opcode,
			  struct aarch64_register rd,
			  struct aarch64_register rn,
			  struct aarch64_register rm)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);

  return aarch64_emit_insn (buf, opcode | size | ENCODE (rm.num, 5, 16)
			    | ENCODE (rn.num, 5, 5) | ENCODE (rd.num, 5, 0));
}

/* Helper function for data processing instructions taking either a register
   or an immediate.  */

static int
emit_data_processing (uint32_t *buf, enum aarch64_opcodes opcode,
		      struct aarch64_register rd,
		      struct aarch64_register rn,
		      struct aarch64_operand operand)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);
  /* The opcode is different for register and immediate source operands.  */
  uint32_t operand_opcode;

  if (operand.type == OPERAND_IMMEDIATE)
    {
      /* xxx1 000x xxxx xxxx xxxx xxxx xxxx xxxx */
      operand_opcode = ENCODE (8, 4, 25);

      return aarch64_emit_insn (buf, opcode | operand_opcode | size
				| ENCODE (operand.imm, 12, 10)
				| ENCODE (rn.num, 5, 5)
				| ENCODE (rd.num, 5, 0));
    }
  else
    {
      /* xxx0 101x xxxx xxxx xxxx xxxx xxxx xxxx */
      operand_opcode = ENCODE (5, 4, 25);

      return emit_data_processing_reg (buf, opcode | operand_opcode, rd,
				       rn, operand.reg);
    }
}

/* Write an ADD instruction into *BUF.

     ADD rd, rn, #imm
     ADD rd, rn, rm

   This function handles both an immediate and register add.

   RD is the destination register.
   RN is the input register.
   OPERAND is the source operand, either of type OPERAND_IMMEDIATE or
   OPERAND_REGISTER.  */

static int
emit_add (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_operand operand)
{
  return emit_data_processing (buf, ADD, rd, rn, operand);
}

/* Write a SUB instruction into *BUF.

     SUB rd, rn, #imm
     SUB rd, rn, rm

   This function handles both an immediate and register sub.

   RD is the destination register.
   RN is the input register.
   IMM is the immediate to substract to RN.  */

static int
emit_sub (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_operand operand)
{
  return emit_data_processing (buf, SUB, rd, rn, operand);
}

/* Write a MOV instruction into *BUF.

     MOV rd, #imm
     MOV rd, rm

   This function handles both a wide immediate move and a register move,
   with the condition that the source register is not xzr.  xzr and the
   stack pointer share the same encoding and this function only supports
   the stack pointer.

   RD is the destination register.
   OPERAND is the source operand, either of type OPERAND_IMMEDIATE or
   OPERAND_REGISTER.  */

static int
emit_mov (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_operand operand)
{
  if (operand.type == OPERAND_IMMEDIATE)
    {
      uint32_t size = ENCODE (rd.is64, 1, 31);
      /* Do not shift the immediate.  */
      uint32_t shift = ENCODE (0, 2, 21);

      return aarch64_emit_insn (buf, MOV | size | shift
				| ENCODE (operand.imm, 16, 5)
				| ENCODE (rd.num, 5, 0));
    }
  else
    return emit_add (buf, rd, operand.reg, immediate_operand (0));
}

/* Write a MOVK instruction into *BUF.

     MOVK rd, #imm, lsl #shift

   RD is the destination register.
   IMM is the immediate.
   SHIFT is the logical shift left to apply to IMM.   */

static int
emit_movk (uint32_t *buf, struct aarch64_register rd, uint32_t imm,
	   unsigned shift)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);

  return aarch64_emit_insn (buf, MOVK | size | ENCODE (shift, 2, 21) |
			    ENCODE (imm, 16, 5) | ENCODE (rd.num, 5, 0));
}

/* Write instructions into *BUF in order to move ADDR into a register.
   ADDR can be a 64-bit value.

   This function will emit a series of MOV and MOVK instructions, such as:

     MOV  xd, #(addr)
     MOVK xd, #(addr >> 16), lsl #16
     MOVK xd, #(addr >> 32), lsl #32
     MOVK xd, #(addr >> 48), lsl #48  */

static int
emit_mov_addr (uint32_t *buf, struct aarch64_register rd, CORE_ADDR addr)
{
  uint32_t *p = buf;

  /* The MOV (wide immediate) instruction clears to top bits of the
     register.  */
  p += emit_mov (p, rd, immediate_operand (addr & 0xffff));

  if ((addr >> 16) != 0)
    p += emit_movk (p, rd, (addr >> 16) & 0xffff, 1);
  else
    return p - buf;

  if ((addr >> 32) != 0)
    p += emit_movk (p, rd, (addr >> 32) & 0xffff, 2);
  else
    return p - buf;

  if ((addr >> 48) != 0)
    p += emit_movk (p, rd, (addr >> 48) & 0xffff, 3);

  return p - buf;
}

/* Write a SUBS instruction into *BUF.

     SUBS rd, rn, rm

   This instruction update the condition flags.

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_subs (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, struct aarch64_operand operand)
{
  return emit_data_processing (buf, SUBS, rd, rn, operand);
}

/* Write a CMP instruction into *BUF.

     CMP rn, rm

   This instruction is an alias of SUBS xzr, rn, rm.

   RN and RM are the registers to compare.  */

static int
emit_cmp (uint32_t *buf, struct aarch64_register rn,
	      struct aarch64_operand operand)
{
  return emit_subs (buf, xzr, rn, operand);
}

/* Write a AND instruction into *BUF.

     AND rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_and (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, AND, rd, rn, rm);
}

/* Write a ORR instruction into *BUF.

     ORR rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_orr (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, ORR, rd, rn, rm);
}

/* Write a ORN instruction into *BUF.

     ORN rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_orn (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, ORN, rd, rn, rm);
}

/* Write a EOR instruction into *BUF.

     EOR rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_eor (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, EOR, rd, rn, rm);
}

/* Write a MVN instruction into *BUF.

     MVN rd, rm

   This is an alias for ORN rd, xzr, rm.

   RD is the destination register.
   RM is the source register.  */

static int
emit_mvn (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rm)
{
  return emit_orn (buf, rd, xzr, rm);
}

/* Write a LSLV instruction into *BUF.

     LSLV rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_lslv (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, LSLV, rd, rn, rm);
}

/* Write a LSRV instruction into *BUF.

     LSRV rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_lsrv (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, LSRV, rd, rn, rm);
}

/* Write a ASRV instruction into *BUF.

     ASRV rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_asrv (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, ASRV, rd, rn, rm);
}

/* Write a MUL instruction into *BUF.

     MUL rd, rn, rm

   RD is the destination register.
   RN and RM are the source registers.  */

static int
emit_mul (uint32_t *buf, struct aarch64_register rd,
	  struct aarch64_register rn, struct aarch64_register rm)
{
  return emit_data_processing_reg (buf, MUL, rd, rn, rm);
}

/* Write a MRS instruction into *BUF.  The register size is 64-bit.

     MRS xt, system_reg

   RT is the destination register.
   SYSTEM_REG is special purpose register to read.  */

static int
emit_mrs (uint32_t *buf, struct aarch64_register rt,
	  enum aarch64_system_control_registers system_reg)
{
  return aarch64_emit_insn (buf, MRS | ENCODE (system_reg, 15, 5)
			    | ENCODE (rt.num, 5, 0));
}

/* Write a MSR instruction into *BUF.  The register size is 64-bit.

     MSR system_reg, xt

   SYSTEM_REG is special purpose register to write.
   RT is the input register.  */

static int
emit_msr (uint32_t *buf, enum aarch64_system_control_registers system_reg,
	  struct aarch64_register rt)
{
  return aarch64_emit_insn (buf, MSR | ENCODE (system_reg, 15, 5)
			    | ENCODE (rt.num, 5, 0));
}

/* Write a SEVL instruction into *BUF.

   This is a hint instruction telling the hardware to trigger an event.  */

static int
emit_sevl (uint32_t *buf)
{
  return aarch64_emit_insn (buf, SEVL);
}

/* Write a WFE instruction into *BUF.

   This is a hint instruction telling the hardware to wait for an event.  */

static int
emit_wfe (uint32_t *buf)
{
  return aarch64_emit_insn (buf, WFE);
}

/* Write a SBFM instruction into *BUF.

     SBFM rd, rn, #immr, #imms

   This instruction moves the bits from #immr to #imms into the
   destination, sign extending the result.

   RD is the destination register.
   RN is the source register.
   IMMR is the bit number to start at (least significant bit).
   IMMS is the bit number to stop at (most significant bit).  */

static int
emit_sbfm (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, uint32_t immr, uint32_t imms)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);
  uint32_t n = ENCODE (rd.is64, 1, 22);

  return aarch64_emit_insn (buf, SBFM | size | n | ENCODE (immr, 6, 16)
			    | ENCODE (imms, 6, 10) | ENCODE (rn.num, 5, 5)
			    | ENCODE (rd.num, 5, 0));
}

/* Write a SBFX instruction into *BUF.

     SBFX rd, rn, #lsb, #width

   This instruction moves #width bits from #lsb into the destination, sign
   extending the result.  This is an alias for:

     SBFM rd, rn, #lsb, #(lsb + width - 1)

   RD is the destination register.
   RN is the source register.
   LSB is the bit number to start at (least significant bit).
   WIDTH is the number of bits to move.  */

static int
emit_sbfx (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, uint32_t lsb, uint32_t width)
{
  return emit_sbfm (buf, rd, rn, lsb, lsb + width - 1);
}

/* Write a UBFM instruction into *BUF.

     UBFM rd, rn, #immr, #imms

   This instruction moves the bits from #immr to #imms into the
   destination, extending the result with zeros.

   RD is the destination register.
   RN is the source register.
   IMMR is the bit number to start at (least significant bit).
   IMMS is the bit number to stop at (most significant bit).  */

static int
emit_ubfm (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, uint32_t immr, uint32_t imms)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);
  uint32_t n = ENCODE (rd.is64, 1, 22);

  return aarch64_emit_insn (buf, UBFM | size | n | ENCODE (immr, 6, 16)
			    | ENCODE (imms, 6, 10) | ENCODE (rn.num, 5, 5)
			    | ENCODE (rd.num, 5, 0));
}

/* Write a UBFX instruction into *BUF.

     UBFX rd, rn, #lsb, #width

   This instruction moves #width bits from #lsb into the destination,
   extending the result with zeros.  This is an alias for:

     UBFM rd, rn, #lsb, #(lsb + width - 1)

   RD is the destination register.
   RN is the source register.
   LSB is the bit number to start at (least significant bit).
   WIDTH is the number of bits to move.  */

static int
emit_ubfx (uint32_t *buf, struct aarch64_register rd,
	   struct aarch64_register rn, uint32_t lsb, uint32_t width)
{
  return emit_ubfm (buf, rd, rn, lsb, lsb + width - 1);
}

/* Write a CSINC instruction into *BUF.

     CSINC rd, rn, rm, cond

   This instruction conditionally increments rn or rm and places the result
   in rd.  rn is chosen is the condition is true.

   RD is the destination register.
   RN and RM are the source registers.
   COND is the encoded condition.  */

static int
emit_csinc (uint32_t *buf, struct aarch64_register rd,
	    struct aarch64_register rn, struct aarch64_register rm,
	    unsigned cond)
{
  uint32_t size = ENCODE (rd.is64, 1, 31);

  return aarch64_emit_insn (buf, CSINC | size | ENCODE (rm.num, 5, 16)
			    | ENCODE (cond, 4, 12) | ENCODE (rn.num, 5, 5)
			    | ENCODE (rd.num, 5, 0));
}

/* Write a CSET instruction into *BUF.

     CSET rd, cond

   This instruction conditionally write 1 or 0 in the destination register.
   1 is written if the condition is true.  This is an alias for:

     CSINC rd, xzr, xzr, !cond

   Note that the condition needs to be inverted.

   RD is the destination register.
   RN and RM are the source registers.
   COND is the encoded condition.  */

static int
emit_cset (uint32_t *buf, struct aarch64_register rd, unsigned cond)
{
  /* The least significant bit of the condition needs toggling in order to
     invert it.  */
  return emit_csinc (buf, rd, xzr, xzr, cond ^ 0x1);
}

/* Write LEN instructions from BUF into the inferior memory at *TO.

   Note instructions are always little endian on AArch64, unlike data.  */

static void
append_insns (CORE_ADDR *to, size_t len, const uint32_t *buf)
{
  size_t byte_len = len * sizeof (uint32_t);
#if (__BYTE_ORDER == __BIG_ENDIAN)
  uint32_t *le_buf = (uint32_t *) xmalloc (byte_len);
  size_t i;

  for (i = 0; i < len; i++)
    le_buf[i] = htole32 (buf[i]);

  target_write_memory (*to, (const unsigned char *) le_buf, byte_len);

  xfree (le_buf);
#else
  target_write_memory (*to, (const unsigned char *) buf, byte_len);
#endif

  *to += byte_len;
}

/* Sub-class of struct aarch64_insn_data, store information of
   instruction relocation for fast tracepoint.  Visitor can
   relocate an instruction from BASE.INSN_ADDR to NEW_ADDR and save
   the relocated instructions in buffer pointed by INSN_PTR.  */

struct aarch64_insn_relocation_data
{
  struct aarch64_insn_data base;

  /* The new address the instruction is relocated to.  */
  CORE_ADDR new_addr;
  /* Pointer to the buffer of relocated instruction(s).  */
  uint32_t *insn_ptr;
};

/* Implementation of aarch64_insn_visitor method "b".  */

static void
aarch64_ftrace_insn_reloc_b (const int is_bl, const int32_t offset,
			     struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  int64_t new_offset
    = insn_reloc->base.insn_addr - insn_reloc->new_addr + offset;

  if (can_encode_int32 (new_offset, 28))
    insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, is_bl, new_offset);
}

/* Implementation of aarch64_insn_visitor method "b_cond".  */

static void
aarch64_ftrace_insn_reloc_b_cond (const unsigned cond, const int32_t offset,
				  struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  int64_t new_offset
    = insn_reloc->base.insn_addr - insn_reloc->new_addr + offset;

  if (can_encode_int32 (new_offset, 21))
    {
      insn_reloc->insn_ptr += emit_bcond (insn_reloc->insn_ptr, cond,
					  new_offset);
    }
  else if (can_encode_int32 (new_offset, 28))
    {
      /* The offset is out of range for a conditional branch
	 instruction but not for a unconditional branch.  We can use
	 the following instructions instead:

	 B.COND TAKEN    ; If cond is true, then jump to TAKEN.
	 B NOT_TAKEN     ; Else jump over TAKEN and continue.
	 TAKEN:
	 B #(offset - 8)
	 NOT_TAKEN:

      */

      insn_reloc->insn_ptr += emit_bcond (insn_reloc->insn_ptr, cond, 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0, 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0, new_offset - 8);
    }
}

/* Implementation of aarch64_insn_visitor method "cb".  */

static void
aarch64_ftrace_insn_reloc_cb (const int32_t offset, const int is_cbnz,
			      const unsigned rn, int is64,
			      struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  int64_t new_offset
    = insn_reloc->base.insn_addr - insn_reloc->new_addr + offset;

  if (can_encode_int32 (new_offset, 21))
    {
      insn_reloc->insn_ptr += emit_cb (insn_reloc->insn_ptr, is_cbnz,
				       aarch64_register (rn, is64), new_offset);
    }
  else if (can_encode_int32 (new_offset, 28))
    {
      /* The offset is out of range for a compare and branch
	 instruction but not for a unconditional branch.  We can use
	 the following instructions instead:

	 CBZ xn, TAKEN   ; xn == 0, then jump to TAKEN.
	 B NOT_TAKEN     ; Else jump over TAKEN and continue.
	 TAKEN:
	 B #(offset - 8)
	 NOT_TAKEN:

      */
      insn_reloc->insn_ptr += emit_cb (insn_reloc->insn_ptr, is_cbnz,
				       aarch64_register (rn, is64), 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0, 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0, new_offset - 8);
    }
}

/* Implementation of aarch64_insn_visitor method "tb".  */

static void
aarch64_ftrace_insn_reloc_tb (const int32_t offset, int is_tbnz,
			      const unsigned rt, unsigned bit,
			      struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  int64_t new_offset
    = insn_reloc->base.insn_addr - insn_reloc->new_addr + offset;

  if (can_encode_int32 (new_offset, 16))
    {
      insn_reloc->insn_ptr += emit_tb (insn_reloc->insn_ptr, is_tbnz, bit,
				       aarch64_register (rt, 1), new_offset);
    }
  else if (can_encode_int32 (new_offset, 28))
    {
      /* The offset is out of range for a test bit and branch
	 instruction but not for a unconditional branch.  We can use
	 the following instructions instead:

	 TBZ xn, #bit, TAKEN ; xn[bit] == 0, then jump to TAKEN.
	 B NOT_TAKEN         ; Else jump over TAKEN and continue.
	 TAKEN:
	 B #(offset - 8)
	 NOT_TAKEN:

      */
      insn_reloc->insn_ptr += emit_tb (insn_reloc->insn_ptr, is_tbnz, bit,
				       aarch64_register (rt, 1), 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0, 8);
      insn_reloc->insn_ptr += emit_b (insn_reloc->insn_ptr, 0,
				      new_offset - 8);
    }
}

/* Implementation of aarch64_insn_visitor method "adr".  */

static void
aarch64_ftrace_insn_reloc_adr (const int32_t offset, const unsigned rd,
			       const int is_adrp,
			       struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  /* We know exactly the address the ADR{P,} instruction will compute.
     We can just write it to the destination register.  */
  CORE_ADDR address = data->insn_addr + offset;

  if (is_adrp)
    {
      /* Clear the lower 12 bits of the offset to get the 4K page.  */
      insn_reloc->insn_ptr += emit_mov_addr (insn_reloc->insn_ptr,
					     aarch64_register (rd, 1),
					     address & ~0xfff);
    }
  else
    insn_reloc->insn_ptr += emit_mov_addr (insn_reloc->insn_ptr,
					   aarch64_register (rd, 1), address);
}

/* Implementation of aarch64_insn_visitor method "ldr_literal".  */

static void
aarch64_ftrace_insn_reloc_ldr_literal (const int32_t offset, const int is_sw,
				       const unsigned rt, const int is64,
				       struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;
  CORE_ADDR address = data->insn_addr + offset;

  insn_reloc->insn_ptr += emit_mov_addr (insn_reloc->insn_ptr,
					 aarch64_register (rt, 1), address);

  /* We know exactly what address to load from, and what register we
     can use:

     MOV xd, #(oldloc + offset)
     MOVK xd, #((oldloc + offset) >> 16), lsl #16
     ...

     LDR xd, [xd] ; or LDRSW xd, [xd]

  */

  if (is_sw)
    insn_reloc->insn_ptr += emit_ldrsw (insn_reloc->insn_ptr,
					aarch64_register (rt, 1),
					aarch64_register (rt, 1),
					offset_memory_operand (0));
  else
    insn_reloc->insn_ptr += emit_ldr (insn_reloc->insn_ptr,
				      aarch64_register (rt, is64),
				      aarch64_register (rt, 1),
				      offset_memory_operand (0));
}

/* Implementation of aarch64_insn_visitor method "others".  */

static void
aarch64_ftrace_insn_reloc_others (const uint32_t insn,
				  struct aarch64_insn_data *data)
{
  struct aarch64_insn_relocation_data *insn_reloc
    = (struct aarch64_insn_relocation_data *) data;

  /* The instruction is not PC relative.  Just re-emit it at the new
     location.  */
  insn_reloc->insn_ptr += aarch64_emit_insn (insn_reloc->insn_ptr, insn);
}

static const struct aarch64_insn_visitor visitor =
{
  aarch64_ftrace_insn_reloc_b,
  aarch64_ftrace_insn_reloc_b_cond,
  aarch64_ftrace_insn_reloc_cb,
  aarch64_ftrace_insn_reloc_tb,
  aarch64_ftrace_insn_reloc_adr,
  aarch64_ftrace_insn_reloc_ldr_literal,
  aarch64_ftrace_insn_reloc_others,
};

bool
aarch64_target::supports_fast_tracepoints ()
{
  return true;
}

/* Implementation of target ops method
   "install_fast_tracepoint_jump_pad".  */

int
aarch64_target::install_fast_tracepoint_jump_pad
  (CORE_ADDR tpoint, CORE_ADDR tpaddr, CORE_ADDR collector,
   CORE_ADDR lockaddr, ULONGEST orig_size, CORE_ADDR *jump_entry,
   CORE_ADDR *trampoline, ULONGEST *trampoline_size,
   unsigned char *jjump_pad_insn, ULONGEST *jjump_pad_insn_size,
   CORE_ADDR *adjusted_insn_addr, CORE_ADDR *adjusted_insn_addr_end,
   char *err)
{
  uint32_t buf[256];
  uint32_t *p = buf;
  int64_t offset;
  int i;
  uint32_t insn;
  CORE_ADDR buildaddr = *jump_entry;
  struct aarch64_insn_relocation_data insn_data;

  /* We need to save the current state on the stack both to restore it
     later and to collect register values when the tracepoint is hit.

     The saved registers are pushed in a layout that needs to be in sync
     with aarch64_ft_collect_regmap (see linux-aarch64-ipa.c).  Later on
     the supply_fast_tracepoint_registers function will fill in the
     register cache from a pointer to saved registers on the stack we build
     here.

     For simplicity, we set the size of each cell on the stack to 16 bytes.
     This way one cell can hold any register type, from system registers
     to the 128 bit SIMD&FP registers.  Furthermore, the stack pointer
     has to be 16 bytes aligned anyway.

     Note that the CPSR register does not exist on AArch64.  Instead we
     can access system bits describing the process state with the
     MRS/MSR instructions, namely the condition flags.  We save them as
     if they are part of a CPSR register because that's how GDB
     interprets these system bits.  At the moment, only the condition
     flags are saved in CPSR (NZCV).

     Stack layout, each cell is 16 bytes (descending):

     High *-------- SIMD&FP registers from 31 down to 0. --------*
	  | q31                                                  |
	  .                                                      .
	  .                                                      . 32 cells
	  .                                                      .
	  | q0                                                   |
	  *---- General purpose registers from 30 down to 0. ----*
	  | x30                                                  |
	  .                                                      .
	  .                                                      . 31 cells
	  .                                                      .
	  | x0                                                   |
	  *------------- Special purpose registers. -------------*
	  | SP                                                   |
	  | PC                                                   |
	  | CPSR (NZCV)                                          | 5 cells
	  | FPSR                                                 |
	  | FPCR                                                 | <- SP + 16
	  *------------- collecting_t object --------------------*
	  | TPIDR_EL0               | struct tracepoint *        |
     Low  *------------------------------------------------------*

     After this stack is set up, we issue a call to the collector, passing
     it the saved registers at (SP + 16).  */

  /* Push SIMD&FP registers on the stack:

       SUB sp, sp, #(32 * 16)

       STP q30, q31, [sp, #(30 * 16)]
       ...
       STP q0, q1, [sp]

     */
  p += emit_sub (p, sp, sp, immediate_operand (32 * 16));
  for (i = 30; i >= 0; i -= 2)
    p += emit_stp_q_offset (p, i, i + 1, sp, i * 16);

  /* Push general purpose registers on the stack.  Note that we do not need
     to push x31 as it represents the xzr register and not the stack
     pointer in a STR instruction.

       SUB sp, sp, #(31 * 16)

       STR x30, [sp, #(30 * 16)]
       ...
       STR x0, [sp]

     */
  p += emit_sub (p, sp, sp, immediate_operand (31 * 16));
  for (i = 30; i >= 0; i -= 1)
    p += emit_str (p, aarch64_register (i, 1), sp,
		   offset_memory_operand (i * 16));

  /* Make space for 5 more cells.

       SUB sp, sp, #(5 * 16)

     */
  p += emit_sub (p, sp, sp, immediate_operand (5 * 16));


  /* Save SP:

       ADD x4, sp, #((32 + 31 + 5) * 16)
       STR x4, [sp, #(4 * 16)]

     */
  p += emit_add (p, x4, sp, immediate_operand ((32 + 31 + 5) * 16));
  p += emit_str (p, x4, sp, offset_memory_operand (4 * 16));

  /* Save PC (tracepoint address):

       MOV  x3, #(tpaddr)
       ...

       STR x3, [sp, #(3 * 16)]

     */

  p += emit_mov_addr (p, x3, tpaddr);
  p += emit_str (p, x3, sp, offset_memory_operand (3 * 16));

  /* Save CPSR (NZCV), FPSR and FPCR:

       MRS x2, nzcv
       MRS x1, fpsr
       MRS x0, fpcr

       STR x2, [sp, #(2 * 16)]
       STR x1, [sp, #(1 * 16)]
       STR x0, [sp, #(0 * 16)]

     */
  p += emit_mrs (p, x2, NZCV);
  p += emit_mrs (p, x1, FPSR);
  p += emit_mrs (p, x0, FPCR);
  p += emit_str (p, x2, sp, offset_memory_operand (2 * 16));
  p += emit_str (p, x1, sp, offset_memory_operand (1 * 16));
  p += emit_str (p, x0, sp, offset_memory_operand (0 * 16));

  /* Push the collecting_t object.  It consist of the address of the
     tracepoint and an ID for the current thread.  We get the latter by
     reading the tpidr_el0 system register.  It corresponds to the
     NT_ARM_TLS register accessible with ptrace.

       MOV x0, #(tpoint)
       ...

       MRS x1, tpidr_el0

       STP x0, x1, [sp, #-16]!

     */

  p += emit_mov_addr (p, x0, tpoint);
  p += emit_mrs (p, x1, TPIDR_EL0);
  p += emit_stp (p, x0, x1, sp, preindex_memory_operand (-16));

  /* Spin-lock:

     The shared memory for the lock is at lockaddr.  It will hold zero
     if no-one is holding the lock, otherwise it contains the address of
     the collecting_t object on the stack of the thread which acquired it.

     At this stage, the stack pointer points to this thread's collecting_t
     object.

     We use the following registers:
     - x0: Address of the lock.
     - x1: Pointer to collecting_t object.
     - x2: Scratch register.

       MOV x0, #(lockaddr)
       ...
       MOV x1, sp

       ; Trigger an event local to this core.  So the following WFE
       ; instruction is ignored.
       SEVL
     again:
       ; Wait for an event.  The event is triggered by either the SEVL
       ; or STLR instructions (store release).
       WFE

       ; Atomically read at lockaddr.  This marks the memory location as
       ; exclusive.  This instruction also has memory constraints which
       ; make sure all previous data reads and writes are done before
       ; executing it.
       LDAXR x2, [x0]

       ; Try again if another thread holds the lock.
       CBNZ x2, again

       ; We can lock it!  Write the address of the collecting_t object.
       ; This instruction will fail if the memory location is not marked
       ; as exclusive anymore.  If it succeeds, it will remove the
       ; exclusive mark on the memory location.  This way, if another
       ; thread executes this instruction before us, we will fail and try
       ; all over again.
       STXR w2, x1, [x0]
       CBNZ w2, again

     */

  p += emit_mov_addr (p, x0, lockaddr);
  p += emit_mov (p, x1, register_operand (sp));

  p += emit_sevl (p);
  p += emit_wfe (p);
  p += emit_ldaxr (p, x2, x0);
  p += emit_cb (p, 1, w2, -2 * 4);
  p += emit_stxr (p, w2, x1, x0);
  p += emit_cb (p, 1, x2, -4 * 4);

  /* Call collector (struct tracepoint *, unsigned char *):

       MOV x0, #(tpoint)
       ...

       ; Saved registers start after the collecting_t object.
       ADD x1, sp, #16

       ; We use an intra-procedure-call scratch register.
       MOV ip0, #(collector)
       ...

       ; And call back to C!
       BLR ip0

     */

  p += emit_mov_addr (p, x0, tpoint);
  p += emit_add (p, x1, sp, immediate_operand (16));

  p += emit_mov_addr (p, ip0, collector);
  p += emit_blr (p, ip0);

  /* Release the lock.

       MOV x0, #(lockaddr)
       ...

       ; This instruction is a normal store with memory ordering
       ; constraints.  Thanks to this we do not have to put a data
       ; barrier instruction to make sure all data read and writes are done
       ; before this instruction is executed.  Furthermore, this instruction
       ; will trigger an event, letting other threads know they can grab
       ; the lock.
       STLR xzr, [x0]

     */
  p += emit_mov_addr (p, x0, lockaddr);
  p += emit_stlr (p, xzr, x0);

  /* Free collecting_t object:

       ADD sp, sp, #16

     */
  p += emit_add (p, sp, sp, immediate_operand (16));

  /* Restore CPSR (NZCV), FPSR and FPCR.  And free all special purpose
     registers from the stack.

       LDR x2, [sp, #(2 * 16)]
       LDR x1, [sp, #(1 * 16)]
       LDR x0, [sp, #(0 * 16)]

       MSR NZCV, x2
       MSR FPSR, x1
       MSR FPCR, x0

       ADD sp, sp #(5 * 16)

     */
  p += emit_ldr (p, x2, sp, offset_memory_operand (2 * 16));
  p += emit_ldr (p, x1, sp, offset_memory_operand (1 * 16));
  p += emit_ldr (p, x0, sp, offset_memory_operand (0 * 16));
  p += emit_msr (p, NZCV, x2);
  p += emit_msr (p, FPSR, x1);
  p += emit_msr (p, FPCR, x0);

  p += emit_add (p, sp, sp, immediate_operand (5 * 16));

  /* Pop general purpose registers:

       LDR x0, [sp]
       ...
       LDR x30, [sp, #(30 * 16)]

       ADD sp, sp, #(31 * 16)

     */
  for (i = 0; i <= 30; i += 1)
    p += emit_ldr (p, aarch64_register (i, 1), sp,
		   offset_memory_operand (i * 16));
  p += emit_add (p, sp, sp, immediate_operand (31 * 16));

  /* Pop SIMD&FP registers:

       LDP q0, q1, [sp]
       ...
       LDP q30, q31, [sp, #(30 * 16)]

       ADD sp, sp, #(32 * 16)

     */
  for (i = 0; i <= 30; i += 2)
    p += emit_ldp_q_offset (p, i, i + 1, sp, i * 16);
  p += emit_add (p, sp, sp, immediate_operand (32 * 16));

  /* Write the code into the inferior memory.  */
  append_insns (&buildaddr, p - buf, buf);

  /* Now emit the relocated instruction.  */
  *adjusted_insn_addr = buildaddr;
  target_read_uint32 (tpaddr, &insn);

  insn_data.base.insn_addr = tpaddr;
  insn_data.new_addr = buildaddr;
  insn_data.insn_ptr = buf;

  aarch64_relocate_instruction (insn, &visitor,
				(struct aarch64_insn_data *) &insn_data);

  /* We may not have been able to relocate the instruction.  */
  if (insn_data.insn_ptr == buf)
    {
      sprintf (err,
	       "E.Could not relocate instruction from %s to %s.",
	       core_addr_to_string_nz (tpaddr),
	       core_addr_to_string_nz (buildaddr));
      return 1;
    }
  else
    append_insns (&buildaddr, insn_data.insn_ptr - buf, buf);
  *adjusted_insn_addr_end = buildaddr;

  /* Go back to the start of the buffer.  */
  p = buf;

  /* Emit a branch back from the jump pad.  */
  offset = (tpaddr + orig_size - buildaddr);
  if (!can_encode_int32 (offset, 28))
    {
      sprintf (err,
	       "E.Jump back from jump pad too far from tracepoint "
	       "(offset 0x%" PRIx64 " cannot be encoded in 28 bits).",
	       offset);
      return 1;
    }

  p += emit_b (p, 0, offset);
  append_insns (&buildaddr, p - buf, buf);

  /* Give the caller a branch instruction into the jump pad.  */
  offset = (*jump_entry - tpaddr);
  if (!can_encode_int32 (offset, 28))
    {
      sprintf (err,
	       "E.Jump pad too far from tracepoint "
	       "(offset 0x%" PRIx64 " cannot be encoded in 28 bits).",
	       offset);
      return 1;
    }

  emit_b ((uint32_t *) jjump_pad_insn, 0, offset);
  *jjump_pad_insn_size = 4;

  /* Return the end address of our pad.  */
  *jump_entry = buildaddr;

  return 0;
}

/* Helper function writing LEN instructions from START into
   current_insn_ptr.  */

static void
emit_ops_insns (const uint32_t *start, int len)
{
  CORE_ADDR buildaddr = current_insn_ptr;

  threads_debug_printf ("Adding %d instructions at %s",
			len, paddress (buildaddr));

  append_insns (&buildaddr, len, start);
  current_insn_ptr = buildaddr;
}

/* Pop a register from the stack.  */

static int
emit_pop (uint32_t *buf, struct aarch64_register rt)
{
  return emit_ldr (buf, rt, sp, postindex_memory_operand (1 * 16));
}

/* Push a register on the stack.  */

static int
emit_push (uint32_t *buf, struct aarch64_register rt)
{
  return emit_str (buf, rt, sp, preindex_memory_operand (-1 * 16));
}

/* Implementation of emit_ops method "emit_prologue".  */

static void
aarch64_emit_prologue (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* This function emit a prologue for the following function prototype:

     enum eval_result_type f (unsigned char *regs,
			      ULONGEST *value);

     The first argument is a buffer of raw registers.  The second
     argument is the result of
     evaluating the expression, which will be set to whatever is on top of
     the stack at the end.

     The stack set up by the prologue is as such:

     High *------------------------------------------------------*
	  | LR                                                   |
	  | FP                                                   | <- FP
	  | x1  (ULONGEST *value)                                |
	  | x0  (unsigned char *regs)                            |
     Low  *------------------------------------------------------*

     As we are implementing a stack machine, each opcode can expand the
     stack so we never know how far we are from the data saved by this
     prologue.  In order to be able refer to value and regs later, we save
     the current stack pointer in the frame pointer.  This way, it is not
     clobbered when calling C functions.

     Finally, throughout every operation, we are using register x0 as the
     top of the stack, and x1 as a scratch register.  */

  p += emit_stp (p, x0, x1, sp, preindex_memory_operand (-2 * 16));
  p += emit_str (p, lr, sp, offset_memory_operand (3 * 8));
  p += emit_str (p, fp, sp, offset_memory_operand (2 * 8));

  p += emit_add (p, fp, sp, immediate_operand (2 * 8));


  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_epilogue".  */

static void
aarch64_emit_epilogue (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* Store the result of the expression (x0) in *value.  */
  p += emit_sub (p, x1, fp, immediate_operand (1 * 8));
  p += emit_ldr (p, x1, x1, offset_memory_operand (0));
  p += emit_str (p, x0, x1, offset_memory_operand (0));

  /* Restore the previous state.  */
  p += emit_add (p, sp, fp, immediate_operand (2 * 8));
  p += emit_ldp (p, fp, lr, fp, offset_memory_operand (0));

  /* Return expr_eval_no_error.  */
  p += emit_mov (p, x0, immediate_operand (expr_eval_no_error));
  p += emit_ret (p, lr);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_add".  */

static void
aarch64_emit_add (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_add (p, x0, x1, register_operand (x0));

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_sub".  */

static void
aarch64_emit_sub (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_sub (p, x0, x1, register_operand (x0));

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_mul".  */

static void
aarch64_emit_mul (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_mul (p, x0, x1, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_lsh".  */

static void
aarch64_emit_lsh (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_lslv (p, x0, x1, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_rsh_signed".  */

static void
aarch64_emit_rsh_signed (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_asrv (p, x0, x1, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_rsh_unsigned".  */

static void
aarch64_emit_rsh_unsigned (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_lsrv (p, x0, x1, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_ext".  */

static void
aarch64_emit_ext (int arg)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_sbfx (p, x0, x0, 0, arg);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_log_not".  */

static void
aarch64_emit_log_not (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* If the top of the stack is 0, replace it with 1.  Else replace it with
     0.  */

  p += emit_cmp (p, x0, immediate_operand (0));
  p += emit_cset (p, x0, EQ);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_bit_and".  */

static void
aarch64_emit_bit_and (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_and (p, x0, x0, x1);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_bit_or".  */

static void
aarch64_emit_bit_or (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_orr (p, x0, x0, x1);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_bit_xor".  */

static void
aarch64_emit_bit_xor (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_eor (p, x0, x0, x1);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_bit_not".  */

static void
aarch64_emit_bit_not (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_mvn (p, x0, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_equal".  */

static void
aarch64_emit_equal (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x0, register_operand (x1));
  p += emit_cset (p, x0, EQ);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_less_signed".  */

static void
aarch64_emit_less_signed (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  p += emit_cset (p, x0, LT);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_less_unsigned".  */

static void
aarch64_emit_less_unsigned (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  p += emit_cset (p, x0, LO);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_ref".  */

static void
aarch64_emit_ref (int size)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  switch (size)
    {
    case 1:
      p += emit_ldrb (p, w0, x0, offset_memory_operand (0));
      break;
    case 2:
      p += emit_ldrh (p, w0, x0, offset_memory_operand (0));
      break;
    case 4:
      p += emit_ldr (p, w0, x0, offset_memory_operand (0));
      break;
    case 8:
      p += emit_ldr (p, x0, x0, offset_memory_operand (0));
      break;
    default:
      /* Unknown size, bail on compilation.  */
      emit_error = 1;
      break;
    }

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_if_goto".  */

static void
aarch64_emit_if_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* The Z flag is set or cleared here.  */
  p += emit_cmp (p, x0, immediate_operand (0));
  /* This instruction must not change the Z flag.  */
  p += emit_pop (p, x0);
  /* Branch over the next instruction if x0 == 0.  */
  p += emit_bcond (p, EQ, 8);

  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_goto".  */

static void
aarch64_emit_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = 0;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "write_goto_address".  */

static void
aarch64_write_goto_address (CORE_ADDR from, CORE_ADDR to, int size)
{
  uint32_t insn;

  emit_b (&insn, 0, to - from);
  append_insns (&from, 1, &insn);
}

/* Implementation of emit_ops method "emit_const".  */

static void
aarch64_emit_const (LONGEST num)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_mov_addr (p, x0, num);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_call".  */

static void
aarch64_emit_call (CORE_ADDR fn)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_mov_addr (p, ip0, fn);
  p += emit_blr (p, ip0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_reg".  */

static void
aarch64_emit_reg (int reg)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* Set x0 to unsigned char *regs.  */
  p += emit_sub (p, x0, fp, immediate_operand (2 * 8));
  p += emit_ldr (p, x0, x0, offset_memory_operand (0));
  p += emit_mov (p, x1, immediate_operand (reg));

  emit_ops_insns (buf, p - buf);

  aarch64_emit_call (get_raw_reg_func_addr ());
}

/* Implementation of emit_ops method "emit_pop".  */

static void
aarch64_emit_pop (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_stack_flush".  */

static void
aarch64_emit_stack_flush (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_push (p, x0);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_zero_ext".  */

static void
aarch64_emit_zero_ext (int arg)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_ubfx (p, x0, x0, 0, arg);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_swap".  */

static void
aarch64_emit_swap (void)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_ldr (p, x1, sp, offset_memory_operand (0 * 16));
  p += emit_str (p, x0, sp, offset_memory_operand (0 * 16));
  p += emit_mov (p, x0, register_operand (x1));

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_stack_adjust".  */

static void
aarch64_emit_stack_adjust (int n)
{
  /* This is not needed with our design.  */
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_add (p, sp, sp, immediate_operand (n * 16));

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_int_call_1".  */

static void
aarch64_emit_int_call_1 (CORE_ADDR fn, int arg1)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_mov (p, x0, immediate_operand (arg1));

  emit_ops_insns (buf, p - buf);

  aarch64_emit_call (fn);
}

/* Implementation of emit_ops method "emit_void_call_2".  */

static void
aarch64_emit_void_call_2 (CORE_ADDR fn, int arg1)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  /* Push x0 on the stack.  */
  aarch64_emit_stack_flush ();

  /* Setup arguments for the function call:

     x0: arg1
     x1: top of the stack

       MOV x1, x0
       MOV x0, #arg1  */

  p += emit_mov (p, x1, register_operand (x0));
  p += emit_mov (p, x0, immediate_operand (arg1));

  emit_ops_insns (buf, p - buf);

  aarch64_emit_call (fn);

  /* Restore x0.  */
  aarch64_emit_pop ();
}

/* Implementation of emit_ops method "emit_eq_goto".  */

static void
aarch64_emit_eq_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 != x1.  */
  p += emit_bcond (p, NE, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_ne_goto".  */

static void
aarch64_emit_ne_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 == x1.  */
  p += emit_bcond (p, EQ, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_lt_goto".  */

static void
aarch64_emit_lt_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 >= x1.  */
  p += emit_bcond (p, GE, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_le_goto".  */

static void
aarch64_emit_le_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 > x1.  */
  p += emit_bcond (p, GT, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_gt_goto".  */

static void
aarch64_emit_gt_goto (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 <= x1.  */
  p += emit_bcond (p, LE, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

/* Implementation of emit_ops method "emit_ge_got".  */

static void
aarch64_emit_ge_got (int *offset_p, int *size_p)
{
  uint32_t buf[16];
  uint32_t *p = buf;

  p += emit_pop (p, x1);
  p += emit_cmp (p, x1, register_operand (x0));
  /* Branch over the next instruction if x0 <= x1.  */
  p += emit_bcond (p, LT, 8);
  /* The NOP instruction will be patched with an unconditional branch.  */
  if (offset_p)
    *offset_p = (p - buf) * 4;
  if (size_p)
    *size_p = 4;
  p += emit_nop (p);

  emit_ops_insns (buf, p - buf);
}

static struct emit_ops aarch64_emit_ops_impl =
{
  aarch64_emit_prologue,
  aarch64_emit_epilogue,
  aarch64_emit_add,
  aarch64_emit_sub,
  aarch64_emit_mul,
  aarch64_emit_lsh,
  aarch64_emit_rsh_signed,
  aarch64_emit_rsh_unsigned,
  aarch64_emit_ext,
  aarch64_emit_log_not,
  aarch64_emit_bit_and,
  aarch64_emit_bit_or,
  aarch64_emit_bit_xor,
  aarch64_emit_bit_not,
  aarch64_emit_equal,
  aarch64_emit_less_signed,
  aarch64_emit_less_unsigned,
  aarch64_emit_ref,
  aarch64_emit_if_goto,
  aarch64_emit_goto,
  aarch64_write_goto_address,
  aarch64_emit_const,
  aarch64_emit_call,
  aarch64_emit_reg,
  aarch64_emit_pop,
  aarch64_emit_stack_flush,
  aarch64_emit_zero_ext,
  aarch64_emit_swap,
  aarch64_emit_stack_adjust,
  aarch64_emit_int_call_1,
  aarch64_emit_void_call_2,
  aarch64_emit_eq_goto,
  aarch64_emit_ne_goto,
  aarch64_emit_lt_goto,
  aarch64_emit_le_goto,
  aarch64_emit_gt_goto,
  aarch64_emit_ge_got,
};

/* Implementation of target ops method "emit_ops".  */

emit_ops *
aarch64_target::emit_ops ()
{
  return &aarch64_emit_ops_impl;
}

/* Implementation of target ops method
   "get_min_fast_tracepoint_insn_len".  */

int
aarch64_target::get_min_fast_tracepoint_insn_len ()
{
  return 4;
}

/* Implementation of linux target ops method "low_supports_range_stepping".  */

bool
aarch64_target::low_supports_range_stepping ()
{
  return true;
}

/* Implementation of target ops method "sw_breakpoint_from_kind".  */

const gdb_byte *
aarch64_target::sw_breakpoint_from_kind (int kind, int *size)
{
  if (is_64bit_tdesc ())
    {
      *size = aarch64_breakpoint_len;
      return aarch64_breakpoint;
    }
  else
    return arm_sw_breakpoint_from_kind (kind, size);
}

/* Implementation of target ops method "breakpoint_kind_from_pc".  */

int
aarch64_target::breakpoint_kind_from_pc (CORE_ADDR *pcptr)
{
  if (is_64bit_tdesc ())
    return aarch64_breakpoint_len;
  else
    return arm_breakpoint_kind_from_pc (pcptr);
}

/* Implementation of the target ops method
   "breakpoint_kind_from_current_state".  */

int
aarch64_target::breakpoint_kind_from_current_state (CORE_ADDR *pcptr)
{
  if (is_64bit_tdesc ())
    return aarch64_breakpoint_len;
  else
    return arm_breakpoint_kind_from_current_state (pcptr);
}

/* Returns true if memory tagging is supported.  */
bool
aarch64_target::supports_memory_tagging ()
{
  if (current_thread == NULL)
    {
      /* We don't have any processes running, so don't attempt to
	 use linux_get_hwcap2 as it will try to fetch the current
	 thread id.  Instead, just fetch the auxv from the self
	 PID.  */
#ifdef HAVE_GETAUXVAL
      return (getauxval (AT_HWCAP2) & HWCAP2_MTE) != 0;
#else
      return true;
#endif
    }

  return (linux_get_hwcap2 (current_thread->id.pid (), 8) & HWCAP2_MTE) != 0;
}

bool
aarch64_target::fetch_memtags (CORE_ADDR address, size_t len,
			       gdb::byte_vector &tags, int type)
{
  /* Allocation tags are per-process, so any tid is fine.  */
  int tid = lwpid_of (current_thread);

  /* Allocation tag?  */
  if (type == static_cast <int> (aarch64_memtag_type::mte_allocation))
    return aarch64_mte_fetch_memtags (tid, address, len, tags);

  return false;
}

bool
aarch64_target::store_memtags (CORE_ADDR address, size_t len,
			       const gdb::byte_vector &tags, int type)
{
  /* Allocation tags are per-process, so any tid is fine.  */
  int tid = lwpid_of (current_thread);

  /* Allocation tag?  */
  if (type == static_cast <int> (aarch64_memtag_type::mte_allocation))
    return aarch64_mte_store_memtags (tid, address, len, tags);

  return false;
}

/* The linux target ops object.  */

linux_process_target *the_linux_target = &the_aarch64_target;

void
initialize_low_arch (void)
{
  initialize_low_arch_aarch32 ();

  initialize_regsets_info (&aarch64_regsets_info);
}