aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
blob: 651ad9ad4c83ff452d82dc8bcd48aceed6a00ac2 (plain) (blame)
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
//===- AArch64FrameLowering.cpp - AArch64 Frame Lowering -------*- C++ -*-====//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file contains the AArch64 implementation of TargetFrameLowering class.
//
// On AArch64, stack frames are structured as follows:
//
// The stack grows downward.
//
// All of the individual frame areas on the frame below are optional, i.e. it's
// possible to create a function so that the particular area isn't present
// in the frame.
//
// At function entry, the "frame" looks as follows:
//
// |                                   | Higher address
// |-----------------------------------|
// |                                   |
// | arguments passed on the stack     |
// |                                   |
// |-----------------------------------| <- sp
// |                                   | Lower address
//
//
// After the prologue has run, the frame has the following general structure.
// Note that this doesn't depict the case where a red-zone is used. Also,
// technically the last frame area (VLAs) doesn't get created until in the
// main function body, after the prologue is run. However, it's depicted here
// for completeness.
//
// |                                   | Higher address
// |-----------------------------------|
// |                                   |
// | arguments passed on the stack     |
// |                                   |
// |-----------------------------------|
// |                                   |
// | (Win64 only) varargs from reg     |
// |                                   |
// |-----------------------------------|
// |                                   |
// | callee-saved gpr registers        | <--.
// |                                   |    | On Darwin platforms these
// |- - - - - - - - - - - - - - - - - -|    | callee saves are swapped,
// |                                   |    | (frame record first)
// | prev_fp, prev_lr                  | <--'
// | (a.k.a. "frame record")           |
// |-----------------------------------| <- fp(=x29)
// |                                   |
// | callee-saved fp/simd/SVE regs     |
// |                                   |
// |-----------------------------------|
// |                                   |
// |        SVE stack objects          |
// |                                   |
// |-----------------------------------|
// |.empty.space.to.make.part.below....|
// |.aligned.in.case.it.needs.more.than| (size of this area is unknown at
// |.the.standard.16-byte.alignment....|  compile time; if present)
// |-----------------------------------|
// |                                   |
// | local variables of fixed size     |
// | including spill slots             |
// |-----------------------------------| <- bp(not defined by ABI,
// |.variable-sized.local.variables....|       LLVM chooses X19)
// |.(VLAs)............................| (size of this area is unknown at
// |...................................|  compile time)
// |-----------------------------------| <- sp
// |                                   | Lower address
//
//
// To access the data in a frame, at-compile time, a constant offset must be
// computable from one of the pointers (fp, bp, sp) to access it. The size
// of the areas with a dotted background cannot be computed at compile-time
// if they are present, making it required to have all three of fp, bp and
// sp to be set up to be able to access all contents in the frame areas,
// assuming all of the frame areas are non-empty.
//
// For most functions, some of the frame areas are empty. For those functions,
// it may not be necessary to set up fp or bp:
// * A base pointer is definitely needed when there are both VLAs and local
//   variables with more-than-default alignment requirements.
// * A frame pointer is definitely needed when there are local variables with
//   more-than-default alignment requirements.
//
// For Darwin platforms the frame-record (fp, lr) is stored at the top of the
// callee-saved area, since the unwind encoding does not allow for encoding
// this dynamically and existing tools depend on this layout. For other
// platforms, the frame-record is stored at the bottom of the (gpr) callee-saved
// area to allow SVE stack objects (allocated directly below the callee-saves,
// if available) to be accessed directly from the framepointer.
// The SVE spill/fill instructions have VL-scaled addressing modes such
// as:
//    ldr z8, [fp, #-7 mul vl]
// For SVE the size of the vector length (VL) is not known at compile-time, so
// '#-7 mul vl' is an offset that can only be evaluated at runtime. With this
// layout, we don't need to add an unscaled offset to the framepointer before
// accessing the SVE object in the frame.
//
// In some cases when a base pointer is not strictly needed, it is generated
// anyway when offsets from the frame pointer to access local variables become
// so large that the offset can't be encoded in the immediate fields of loads
// or stores.
//
// FIXME: also explain the redzone concept.
// FIXME: also explain the concept of reserved call frames.
//
//===----------------------------------------------------------------------===//

#include "AArch64FrameLowering.h"
#include "AArch64InstrInfo.h"
#include "AArch64MachineFunctionInfo.h"
#include "AArch64RegisterInfo.h"
#include "AArch64StackOffset.h"
#include "AArch64Subtarget.h"
#include "AArch64TargetMachine.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/CodeGen/LivePhysRegs.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/RegisterScavenging.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/CodeGen/WinEHFuncInfo.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include <cassert>
#include <cstdint>
#include <iterator>
#include <vector>

using namespace llvm;

#define DEBUG_TYPE "frame-info"

static cl::opt<bool> EnableRedZone("aarch64-redzone",
                                   cl::desc("enable use of redzone on AArch64"),
                                   cl::init(false), cl::Hidden);

static cl::opt<bool>
    ReverseCSRRestoreSeq("reverse-csr-restore-seq",
                         cl::desc("reverse the CSR restore sequence"),
                         cl::init(false), cl::Hidden);

STATISTIC(NumRedZoneFunctions, "Number of functions using red zone");

/// This is the biggest offset to the stack pointer we can encode in aarch64
/// instructions (without using a separate calculation and a temp register).
/// Note that the exception here are vector stores/loads which cannot encode any
/// displacements (see estimateRSStackSizeLimit(), isAArch64FrameOffsetLegal()).
static const unsigned DefaultSafeSPDisplacement = 255;

/// Look at each instruction that references stack frames and return the stack
/// size limit beyond which some of these instructions will require a scratch
/// register during their expansion later.
static unsigned estimateRSStackSizeLimit(MachineFunction &MF) {
  // FIXME: For now, just conservatively guestimate based on unscaled indexing
  // range. We'll end up allocating an unnecessary spill slot a lot, but
  // realistically that's not a big deal at this stage of the game.
  for (MachineBasicBlock &MBB : MF) {
    for (MachineInstr &MI : MBB) {
      if (MI.isDebugInstr() || MI.isPseudo() ||
          MI.getOpcode() == AArch64::ADDXri ||
          MI.getOpcode() == AArch64::ADDSXri)
        continue;

      for (const MachineOperand &MO : MI.operands()) {
        if (!MO.isFI())
          continue;

        StackOffset Offset;
        if (isAArch64FrameOffsetLegal(MI, Offset, nullptr, nullptr, nullptr) ==
            AArch64FrameOffsetCannotUpdate)
          return 0;
      }
    }
  }
  return DefaultSafeSPDisplacement;
}

TargetStackID::Value
AArch64FrameLowering::getStackIDForScalableVectors() const {
  return TargetStackID::SVEVector;
}

/// Returns the size of the fixed object area (allocated next to sp on entry)
/// On Win64 this may include a var args area and an UnwindHelp object for EH.
static unsigned getFixedObjectSize(const MachineFunction &MF,
                                   const AArch64FunctionInfo *AFI, bool IsWin64,
                                   bool IsFunclet) {
  if (!IsWin64 || IsFunclet) {
    // Only Win64 uses fixed objects, and then only for the function (not
    // funclets)
    return 0;
  } else {
    // Var args are stored here in the primary function.
    const unsigned VarArgsArea = AFI->getVarArgsGPRSize();
    // To support EH funclets we allocate an UnwindHelp object
    const unsigned UnwindHelpObject = (MF.hasEHFunclets() ? 8 : 0);
    return alignTo(VarArgsArea + UnwindHelpObject, 16);
  }
}

/// Returns the size of the entire SVE stackframe (calleesaves + spills).
static StackOffset getSVEStackSize(const MachineFunction &MF) {
  const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  return {(int64_t)AFI->getStackSizeSVE(), MVT::nxv1i8};
}

bool AArch64FrameLowering::canUseRedZone(const MachineFunction &MF) const {
  if (!EnableRedZone)
    return false;
  // Don't use the red zone if the function explicitly asks us not to.
  // This is typically used for kernel code.
  if (MF.getFunction().hasFnAttribute(Attribute::NoRedZone))
    return false;

  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  uint64_t NumBytes = AFI->getLocalStackSize();

  return !(MFI.hasCalls() || hasFP(MF) || NumBytes > 128 ||
           getSVEStackSize(MF));
}

/// hasFP - Return true if the specified function should have a dedicated frame
/// pointer register.
bool AArch64FrameLowering::hasFP(const MachineFunction &MF) const {
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();
  // Win64 EH requires a frame pointer if funclets are present, as the locals
  // are accessed off the frame pointer in both the parent function and the
  // funclets.
  if (MF.hasEHFunclets())
    return true;
  // Retain behavior of always omitting the FP for leaf functions when possible.
  if (MF.getTarget().Options.DisableFramePointerElim(MF))
    return true;
  if (MFI.hasVarSizedObjects() || MFI.isFrameAddressTaken() ||
      MFI.hasStackMap() || MFI.hasPatchPoint() ||
      RegInfo->needsStackRealignment(MF))
    return true;
  // With large callframes around we may need to use FP to access the scavenging
  // emergency spillslot.
  //
  // Unfortunately some calls to hasFP() like machine verifier ->
  // getReservedReg() -> hasFP in the middle of global isel are too early
  // to know the max call frame size. Hopefully conservatively returning "true"
  // in those cases is fine.
  // DefaultSafeSPDisplacement is fine as we only emergency spill GP regs.
  if (!MFI.isMaxCallFrameSizeComputed() ||
      MFI.getMaxCallFrameSize() > DefaultSafeSPDisplacement)
    return true;

  return false;
}

/// hasReservedCallFrame - Under normal circumstances, when a frame pointer is
/// not required, we reserve argument space for call sites in the function
/// immediately on entry to the current function.  This eliminates the need for
/// add/sub sp brackets around call sites.  Returns true if the call frame is
/// included as part of the stack frame.
bool
AArch64FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const {
  return !MF.getFrameInfo().hasVarSizedObjects();
}

MachineBasicBlock::iterator AArch64FrameLowering::eliminateCallFramePseudoInstr(
    MachineFunction &MF, MachineBasicBlock &MBB,
    MachineBasicBlock::iterator I) const {
  const AArch64InstrInfo *TII =
      static_cast<const AArch64InstrInfo *>(MF.getSubtarget().getInstrInfo());
  DebugLoc DL = I->getDebugLoc();
  unsigned Opc = I->getOpcode();
  bool IsDestroy = Opc == TII->getCallFrameDestroyOpcode();
  uint64_t CalleePopAmount = IsDestroy ? I->getOperand(1).getImm() : 0;

  if (!hasReservedCallFrame(MF)) {
    unsigned Align = getStackAlignment();

    int64_t Amount = I->getOperand(0).getImm();
    Amount = alignTo(Amount, Align);
    if (!IsDestroy)
      Amount = -Amount;

    // N.b. if CalleePopAmount is valid but zero (i.e. callee would pop, but it
    // doesn't have to pop anything), then the first operand will be zero too so
    // this adjustment is a no-op.
    if (CalleePopAmount == 0) {
      // FIXME: in-function stack adjustment for calls is limited to 24-bits
      // because there's no guaranteed temporary register available.
      //
      // ADD/SUB (immediate) has only LSL #0 and LSL #12 available.
      // 1) For offset <= 12-bit, we use LSL #0
      // 2) For 12-bit <= offset <= 24-bit, we use two instructions. One uses
      // LSL #0, and the other uses LSL #12.
      //
      // Most call frames will be allocated at the start of a function so
      // this is OK, but it is a limitation that needs dealing with.
      assert(Amount > -0xffffff && Amount < 0xffffff && "call frame too large");
      emitFrameOffset(MBB, I, DL, AArch64::SP, AArch64::SP, {Amount, MVT::i8},
                      TII);
    }
  } else if (CalleePopAmount != 0) {
    // If the calling convention demands that the callee pops arguments from the
    // stack, we want to add it back if we have a reserved call frame.
    assert(CalleePopAmount < 0xffffff && "call frame too large");
    emitFrameOffset(MBB, I, DL, AArch64::SP, AArch64::SP,
                    {-(int64_t)CalleePopAmount, MVT::i8}, TII);
  }
  return MBB.erase(I);
}

static bool ShouldSignReturnAddress(MachineFunction &MF) {
  // The function should be signed in the following situations:
  // - sign-return-address=all
  // - sign-return-address=non-leaf and the functions spills the LR

  const Function &F = MF.getFunction();
  if (!F.hasFnAttribute("sign-return-address"))
    return false;

  StringRef Scope = F.getFnAttribute("sign-return-address").getValueAsString();
  if (Scope.equals("none"))
    return false;

  if (Scope.equals("all"))
    return true;

  assert(Scope.equals("non-leaf") && "Expected all, none or non-leaf");

  for (const auto &Info : MF.getFrameInfo().getCalleeSavedInfo())
    if (Info.getReg() == AArch64::LR)
      return true;

  return false;
}

void AArch64FrameLowering::emitCalleeSavedFrameMoves(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI) const {
  MachineFunction &MF = *MBB.getParent();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  const TargetSubtargetInfo &STI = MF.getSubtarget();
  const MCRegisterInfo *MRI = STI.getRegisterInfo();
  const TargetInstrInfo *TII = STI.getInstrInfo();
  DebugLoc DL = MBB.findDebugLoc(MBBI);

  // Add callee saved registers to move list.
  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
  if (CSI.empty())
    return;

  for (const auto &Info : CSI) {
    unsigned Reg = Info.getReg();
    int64_t Offset =
        MFI.getObjectOffset(Info.getFrameIdx()) - getOffsetOfLocalArea();
    unsigned DwarfReg = MRI->getDwarfRegNum(Reg, true);
    unsigned CFIIndex = MF.addFrameInst(
        MCCFIInstruction::createOffset(nullptr, DwarfReg, Offset));
    BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }
}

// Find a scratch register that we can use at the start of the prologue to
// re-align the stack pointer.  We avoid using callee-save registers since they
// may appear to be free when this is called from canUseAsPrologue (during
// shrink wrapping), but then no longer be free when this is called from
// emitPrologue.
//
// FIXME: This is a bit conservative, since in the above case we could use one
// of the callee-save registers as a scratch temp to re-align the stack pointer,
// but we would then have to make sure that we were in fact saving at least one
// callee-save register in the prologue, which is additional complexity that
// doesn't seem worth the benefit.
static unsigned findScratchNonCalleeSaveRegister(MachineBasicBlock *MBB) {
  MachineFunction *MF = MBB->getParent();

  // If MBB is an entry block, use X9 as the scratch register
  if (&MF->front() == MBB)
    return AArch64::X9;

  const AArch64Subtarget &Subtarget = MF->getSubtarget<AArch64Subtarget>();
  const AArch64RegisterInfo &TRI = *Subtarget.getRegisterInfo();
  LivePhysRegs LiveRegs(TRI);
  LiveRegs.addLiveIns(*MBB);

  // Mark callee saved registers as used so we will not choose them.
  const MCPhysReg *CSRegs = MF->getRegInfo().getCalleeSavedRegs();
  for (unsigned i = 0; CSRegs[i]; ++i)
    LiveRegs.addReg(CSRegs[i]);

  // Prefer X9 since it was historically used for the prologue scratch reg.
  const MachineRegisterInfo &MRI = MF->getRegInfo();
  if (LiveRegs.available(MRI, AArch64::X9))
    return AArch64::X9;

  for (unsigned Reg : AArch64::GPR64RegClass) {
    if (LiveRegs.available(MRI, Reg))
      return Reg;
  }
  return AArch64::NoRegister;
}

bool AArch64FrameLowering::canUseAsPrologue(
    const MachineBasicBlock &MBB) const {
  const MachineFunction *MF = MBB.getParent();
  MachineBasicBlock *TmpMBB = const_cast<MachineBasicBlock *>(&MBB);
  const AArch64Subtarget &Subtarget = MF->getSubtarget<AArch64Subtarget>();
  const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();

  // Don't need a scratch register if we're not going to re-align the stack.
  if (!RegInfo->needsStackRealignment(*MF))
    return true;
  // Otherwise, we can use any block as long as it has a scratch register
  // available.
  return findScratchNonCalleeSaveRegister(TmpMBB) != AArch64::NoRegister;
}

static bool windowsRequiresStackProbe(MachineFunction &MF,
                                      uint64_t StackSizeInBytes) {
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  if (!Subtarget.isTargetWindows())
    return false;
  const Function &F = MF.getFunction();
  // TODO: When implementing stack protectors, take that into account
  // for the probe threshold.
  unsigned StackProbeSize = 4096;
  if (F.hasFnAttribute("stack-probe-size"))
    F.getFnAttribute("stack-probe-size")
        .getValueAsString()
        .getAsInteger(0, StackProbeSize);
  return (StackSizeInBytes >= StackProbeSize) &&
         !F.hasFnAttribute("no-stack-arg-probe");
}

bool AArch64FrameLowering::shouldCombineCSRLocalStackBump(
    MachineFunction &MF, uint64_t StackBumpBytes) const {
  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();

  if (AFI->getLocalStackSize() == 0)
    return false;

  // 512 is the maximum immediate for stp/ldp that will be used for
  // callee-save save/restores
  if (StackBumpBytes >= 512 || windowsRequiresStackProbe(MF, StackBumpBytes))
    return false;

  if (MFI.hasVarSizedObjects())
    return false;

  if (RegInfo->needsStackRealignment(MF))
    return false;

  // This isn't strictly necessary, but it simplifies things a bit since the
  // current RedZone handling code assumes the SP is adjusted by the
  // callee-save save/restore code.
  if (canUseRedZone(MF))
    return false;

  // When there is an SVE area on the stack, always allocate the
  // callee-saves and spills/locals separately.
  if (getSVEStackSize(MF))
    return false;

  return true;
}

// Given a load or a store instruction, generate an appropriate unwinding SEH
// code on Windows.
static MachineBasicBlock::iterator InsertSEH(MachineBasicBlock::iterator MBBI,
                                             const TargetInstrInfo &TII,
                                             MachineInstr::MIFlag Flag) {
  unsigned Opc = MBBI->getOpcode();
  MachineBasicBlock *MBB = MBBI->getParent();
  MachineFunction &MF = *MBB->getParent();
  DebugLoc DL = MBBI->getDebugLoc();
  unsigned ImmIdx = MBBI->getNumOperands() - 1;
  int Imm = MBBI->getOperand(ImmIdx).getImm();
  MachineInstrBuilder MIB;
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();

  switch (Opc) {
  default:
    llvm_unreachable("No SEH Opcode for this instruction");
  case AArch64::LDPDpost:
    Imm = -Imm;
    LLVM_FALLTHROUGH;
  case AArch64::STPDpre: {
    unsigned Reg0 = RegInfo->getSEHRegNum(MBBI->getOperand(1).getReg());
    unsigned Reg1 = RegInfo->getSEHRegNum(MBBI->getOperand(2).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFRegP_X))
              .addImm(Reg0)
              .addImm(Reg1)
              .addImm(Imm * 8)
              .setMIFlag(Flag);
    break;
  }
  case AArch64::LDPXpost:
    Imm = -Imm;
    LLVM_FALLTHROUGH;
  case AArch64::STPXpre: {
    Register Reg0 = MBBI->getOperand(1).getReg();
    Register Reg1 = MBBI->getOperand(2).getReg();
    if (Reg0 == AArch64::FP && Reg1 == AArch64::LR)
      MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFPLR_X))
                .addImm(Imm * 8)
                .setMIFlag(Flag);
    else
      MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveRegP_X))
                .addImm(RegInfo->getSEHRegNum(Reg0))
                .addImm(RegInfo->getSEHRegNum(Reg1))
                .addImm(Imm * 8)
                .setMIFlag(Flag);
    break;
  }
  case AArch64::LDRDpost:
    Imm = -Imm;
    LLVM_FALLTHROUGH;
  case AArch64::STRDpre: {
    unsigned Reg = RegInfo->getSEHRegNum(MBBI->getOperand(1).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFReg_X))
              .addImm(Reg)
              .addImm(Imm)
              .setMIFlag(Flag);
    break;
  }
  case AArch64::LDRXpost:
    Imm = -Imm;
    LLVM_FALLTHROUGH;
  case AArch64::STRXpre: {
    unsigned Reg =  RegInfo->getSEHRegNum(MBBI->getOperand(1).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveReg_X))
              .addImm(Reg)
              .addImm(Imm)
              .setMIFlag(Flag);
    break;
  }
  case AArch64::STPDi:
  case AArch64::LDPDi: {
    unsigned Reg0 =  RegInfo->getSEHRegNum(MBBI->getOperand(0).getReg());
    unsigned Reg1 =  RegInfo->getSEHRegNum(MBBI->getOperand(1).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFRegP))
              .addImm(Reg0)
              .addImm(Reg1)
              .addImm(Imm * 8)
              .setMIFlag(Flag);
    break;
  }
  case AArch64::STPXi:
  case AArch64::LDPXi: {
    Register Reg0 = MBBI->getOperand(0).getReg();
    Register Reg1 = MBBI->getOperand(1).getReg();
    if (Reg0 == AArch64::FP && Reg1 == AArch64::LR)
      MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFPLR))
                .addImm(Imm * 8)
                .setMIFlag(Flag);
    else
      MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveRegP))
                .addImm(RegInfo->getSEHRegNum(Reg0))
                .addImm(RegInfo->getSEHRegNum(Reg1))
                .addImm(Imm * 8)
                .setMIFlag(Flag);
    break;
  }
  case AArch64::STRXui:
  case AArch64::LDRXui: {
    int Reg = RegInfo->getSEHRegNum(MBBI->getOperand(0).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveReg))
              .addImm(Reg)
              .addImm(Imm * 8)
              .setMIFlag(Flag);
    break;
  }
  case AArch64::STRDui:
  case AArch64::LDRDui: {
    unsigned Reg = RegInfo->getSEHRegNum(MBBI->getOperand(0).getReg());
    MIB = BuildMI(MF, DL, TII.get(AArch64::SEH_SaveFReg))
              .addImm(Reg)
              .addImm(Imm * 8)
              .setMIFlag(Flag);
    break;
  }
  }
  auto I = MBB->insertAfter(MBBI, MIB);
  return I;
}

// Fix up the SEH opcode associated with the save/restore instruction.
static void fixupSEHOpcode(MachineBasicBlock::iterator MBBI,
                           unsigned LocalStackSize) {
  MachineOperand *ImmOpnd = nullptr;
  unsigned ImmIdx = MBBI->getNumOperands() - 1;
  switch (MBBI->getOpcode()) {
  default:
    llvm_unreachable("Fix the offset in the SEH instruction");
  case AArch64::SEH_SaveFPLR:
  case AArch64::SEH_SaveRegP:
  case AArch64::SEH_SaveReg:
  case AArch64::SEH_SaveFRegP:
  case AArch64::SEH_SaveFReg:
    ImmOpnd = &MBBI->getOperand(ImmIdx);
    break;
  }
  if (ImmOpnd)
    ImmOpnd->setImm(ImmOpnd->getImm() + LocalStackSize);
}

// Convert callee-save register save/restore instruction to do stack pointer
// decrement/increment to allocate/deallocate the callee-save stack area by
// converting store/load to use pre/post increment version.
static MachineBasicBlock::iterator convertCalleeSaveRestoreToSPPrePostIncDec(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
    const DebugLoc &DL, const TargetInstrInfo *TII, int CSStackSizeInc,
    bool NeedsWinCFI, bool *HasWinCFI, bool InProlog = true) {
  // Ignore instructions that do not operate on SP, i.e. shadow call stack
  // instructions and associated CFI instruction.
  while (MBBI->getOpcode() == AArch64::STRXpost ||
         MBBI->getOpcode() == AArch64::LDRXpre ||
         MBBI->getOpcode() == AArch64::CFI_INSTRUCTION) {
    if (MBBI->getOpcode() != AArch64::CFI_INSTRUCTION)
      assert(MBBI->getOperand(0).getReg() != AArch64::SP);
    ++MBBI;
  }
  unsigned NewOpc;
  int Scale = 1;
  switch (MBBI->getOpcode()) {
  default:
    llvm_unreachable("Unexpected callee-save save/restore opcode!");
  case AArch64::STPXi:
    NewOpc = AArch64::STPXpre;
    Scale = 8;
    break;
  case AArch64::STPDi:
    NewOpc = AArch64::STPDpre;
    Scale = 8;
    break;
  case AArch64::STPQi:
    NewOpc = AArch64::STPQpre;
    Scale = 16;
    break;
  case AArch64::STRXui:
    NewOpc = AArch64::STRXpre;
    break;
  case AArch64::STRDui:
    NewOpc = AArch64::STRDpre;
    break;
  case AArch64::STRQui:
    NewOpc = AArch64::STRQpre;
    break;
  case AArch64::LDPXi:
    NewOpc = AArch64::LDPXpost;
    Scale = 8;
    break;
  case AArch64::LDPDi:
    NewOpc = AArch64::LDPDpost;
    Scale = 8;
    break;
  case AArch64::LDPQi:
    NewOpc = AArch64::LDPQpost;
    Scale = 16;
    break;
  case AArch64::LDRXui:
    NewOpc = AArch64::LDRXpost;
    break;
  case AArch64::LDRDui:
    NewOpc = AArch64::LDRDpost;
    break;
  case AArch64::LDRQui:
    NewOpc = AArch64::LDRQpost;
    break;
  }
  // Get rid of the SEH code associated with the old instruction.
  if (NeedsWinCFI) {
    auto SEH = std::next(MBBI);
    if (AArch64InstrInfo::isSEHInstruction(*SEH))
      SEH->eraseFromParent();
  }

  MachineInstrBuilder MIB = BuildMI(MBB, MBBI, DL, TII->get(NewOpc));
  MIB.addReg(AArch64::SP, RegState::Define);

  // Copy all operands other than the immediate offset.
  unsigned OpndIdx = 0;
  for (unsigned OpndEnd = MBBI->getNumOperands() - 1; OpndIdx < OpndEnd;
       ++OpndIdx)
    MIB.add(MBBI->getOperand(OpndIdx));

  assert(MBBI->getOperand(OpndIdx).getImm() == 0 &&
         "Unexpected immediate offset in first/last callee-save save/restore "
         "instruction!");
  assert(MBBI->getOperand(OpndIdx - 1).getReg() == AArch64::SP &&
         "Unexpected base register in callee-save save/restore instruction!");
  assert(CSStackSizeInc % Scale == 0);
  MIB.addImm(CSStackSizeInc / Scale);

  MIB.setMIFlags(MBBI->getFlags());
  MIB.setMemRefs(MBBI->memoperands());

  // Generate a new SEH code that corresponds to the new instruction.
  if (NeedsWinCFI) {
    *HasWinCFI = true;
    InsertSEH(*MIB, *TII,
              InProlog ? MachineInstr::FrameSetup : MachineInstr::FrameDestroy);
  }

  return std::prev(MBB.erase(MBBI));
}

// Fixup callee-save register save/restore instructions to take into account
// combined SP bump by adding the local stack size to the stack offsets.
static void fixupCalleeSaveRestoreStackOffset(MachineInstr &MI,
                                              uint64_t LocalStackSize,
                                              bool NeedsWinCFI,
                                              bool *HasWinCFI) {
  if (AArch64InstrInfo::isSEHInstruction(MI))
    return;

  unsigned Opc = MI.getOpcode();

  // Ignore instructions that do not operate on SP, i.e. shadow call stack
  // instructions and associated CFI instruction.
  if (Opc == AArch64::STRXpost || Opc == AArch64::LDRXpre ||
      Opc == AArch64::CFI_INSTRUCTION) {
    if (Opc != AArch64::CFI_INSTRUCTION)
      assert(MI.getOperand(0).getReg() != AArch64::SP);
    return;
  }

  unsigned Scale;
  switch (Opc) {
  case AArch64::STPXi:
  case AArch64::STRXui:
  case AArch64::STPDi:
  case AArch64::STRDui:
  case AArch64::LDPXi:
  case AArch64::LDRXui:
  case AArch64::LDPDi:
  case AArch64::LDRDui:
    Scale = 8;
    break;
  case AArch64::STPQi:
  case AArch64::STRQui:
  case AArch64::LDPQi:
  case AArch64::LDRQui:
    Scale = 16;
    break;
  default:
    llvm_unreachable("Unexpected callee-save save/restore opcode!");
  }

  unsigned OffsetIdx = MI.getNumExplicitOperands() - 1;
  assert(MI.getOperand(OffsetIdx - 1).getReg() == AArch64::SP &&
         "Unexpected base register in callee-save save/restore instruction!");
  // Last operand is immediate offset that needs fixing.
  MachineOperand &OffsetOpnd = MI.getOperand(OffsetIdx);
  // All generated opcodes have scaled offsets.
  assert(LocalStackSize % Scale == 0);
  OffsetOpnd.setImm(OffsetOpnd.getImm() + LocalStackSize / Scale);

  if (NeedsWinCFI) {
    *HasWinCFI = true;
    auto MBBI = std::next(MachineBasicBlock::iterator(MI));
    assert(MBBI != MI.getParent()->end() && "Expecting a valid instruction");
    assert(AArch64InstrInfo::isSEHInstruction(*MBBI) &&
           "Expecting a SEH instruction");
    fixupSEHOpcode(MBBI, LocalStackSize);
  }
}

static void adaptForLdStOpt(MachineBasicBlock &MBB,
                            MachineBasicBlock::iterator FirstSPPopI,
                            MachineBasicBlock::iterator LastPopI) {
  // Sometimes (when we restore in the same order as we save), we can end up
  // with code like this:
  //
  // ldp      x26, x25, [sp]
  // ldp      x24, x23, [sp, #16]
  // ldp      x22, x21, [sp, #32]
  // ldp      x20, x19, [sp, #48]
  // add      sp, sp, #64
  //
  // In this case, it is always better to put the first ldp at the end, so
  // that the load-store optimizer can run and merge the ldp and the add into
  // a post-index ldp.
  // If we managed to grab the first pop instruction, move it to the end.
  if (ReverseCSRRestoreSeq)
    MBB.splice(FirstSPPopI, &MBB, LastPopI);
  // We should end up with something like this now:
  //
  // ldp      x24, x23, [sp, #16]
  // ldp      x22, x21, [sp, #32]
  // ldp      x20, x19, [sp, #48]
  // ldp      x26, x25, [sp]
  // add      sp, sp, #64
  //
  // and the load-store optimizer can merge the last two instructions into:
  //
  // ldp      x26, x25, [sp], #64
  //
}

static bool ShouldSignWithAKey(MachineFunction &MF) {
  const Function &F = MF.getFunction();
  if (!F.hasFnAttribute("sign-return-address-key"))
    return true;

  const StringRef Key =
      F.getFnAttribute("sign-return-address-key").getValueAsString();
  assert(Key.equals_lower("a_key") || Key.equals_lower("b_key"));
  return Key.equals_lower("a_key");
}

static bool needsWinCFI(const MachineFunction &MF) {
  const Function &F = MF.getFunction();
  return MF.getTarget().getMCAsmInfo()->usesWindowsCFI() &&
         F.needsUnwindTableEntry();
}

static bool isTargetDarwin(const MachineFunction &MF) {
  return MF.getSubtarget<AArch64Subtarget>().isTargetDarwin();
}

static bool isTargetWindows(const MachineFunction &MF) {
  return MF.getSubtarget<AArch64Subtarget>().isTargetWindows();
}

// Convenience function to determine whether I is an SVE callee save.
static bool IsSVECalleeSave(MachineBasicBlock::iterator I) {
  switch (I->getOpcode()) {
  default:
    return false;
  case AArch64::STR_ZXI:
  case AArch64::STR_PXI:
  case AArch64::LDR_ZXI:
  case AArch64::LDR_PXI:
    return I->getFlag(MachineInstr::FrameSetup) ||
           I->getFlag(MachineInstr::FrameDestroy);
  }
}

void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
                                        MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.begin();
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const Function &F = MF.getFunction();
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();
  const TargetInstrInfo *TII = Subtarget.getInstrInfo();
  MachineModuleInfo &MMI = MF.getMMI();
  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  bool needsFrameMoves =
      MF.needsFrameMoves() && !MF.getTarget().getMCAsmInfo()->usesWindowsCFI();
  bool HasFP = hasFP(MF);
  bool NeedsWinCFI = needsWinCFI(MF);
  bool HasWinCFI = false;
  auto Cleanup = make_scope_exit([&]() { MF.setHasWinCFI(HasWinCFI); });

  bool IsFunclet = MBB.isEHFuncletEntry();

  // At this point, we're going to decide whether or not the function uses a
  // redzone. In most cases, the function doesn't have a redzone so let's
  // assume that's false and set it to true in the case that there's a redzone.
  AFI->setHasRedZone(false);

  // Debug location must be unknown since the first debug location is used
  // to determine the end of the prologue.
  DebugLoc DL;

  if (ShouldSignReturnAddress(MF)) {
    if (ShouldSignWithAKey(MF))
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::PACIASP))
          .setMIFlag(MachineInstr::FrameSetup);
    else {
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::EMITBKEY))
          .setMIFlag(MachineInstr::FrameSetup);
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::PACIBSP))
          .setMIFlag(MachineInstr::FrameSetup);
    }

    unsigned CFIIndex =
        MF.addFrameInst(MCCFIInstruction::createNegateRAState(nullptr));
    BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }

  // All calls are tail calls in GHC calling conv, and functions have no
  // prologue/epilogue.
  if (MF.getFunction().getCallingConv() == CallingConv::GHC)
    return;

  // Set tagged base pointer to the bottom of the stack frame.
  // Ideally it should match SP value after prologue.
  AFI->setTaggedBasePointerOffset(MFI.getStackSize());

  const StackOffset &SVEStackSize = getSVEStackSize(MF);

  // getStackSize() includes all the locals in its size calculation. We don't
  // include these locals when computing the stack size of a funclet, as they
  // are allocated in the parent's stack frame and accessed via the frame
  // pointer from the funclet.  We only save the callee saved registers in the
  // funclet, which are really the callee saved registers of the parent
  // function, including the funclet.
  int64_t NumBytes = IsFunclet ? getWinEHFuncletFrameSize(MF)
                               : MFI.getStackSize();
  if (!AFI->hasStackFrame() && !windowsRequiresStackProbe(MF, NumBytes)) {
    assert(!HasFP && "unexpected function without stack frame but with FP");
    assert(!SVEStackSize &&
           "unexpected function without stack frame but with SVE objects");
    // All of the stack allocation is for locals.
    AFI->setLocalStackSize(NumBytes);
    if (!NumBytes)
      return;
    // REDZONE: If the stack size is less than 128 bytes, we don't need
    // to actually allocate.
    if (canUseRedZone(MF)) {
      AFI->setHasRedZone(true);
      ++NumRedZoneFunctions;
    } else {
      emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP,
                      {-NumBytes, MVT::i8}, TII, MachineInstr::FrameSetup,
                      false, NeedsWinCFI, &HasWinCFI);
      if (!NeedsWinCFI && needsFrameMoves) {
        // Label used to tie together the PROLOG_LABEL and the MachineMoves.
        MCSymbol *FrameLabel = MMI.getContext().createTempSymbol();
          // Encode the stack size of the leaf function.
          unsigned CFIIndex = MF.addFrameInst(
              MCCFIInstruction::createDefCfaOffset(FrameLabel, -NumBytes));
          BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
              .addCFIIndex(CFIIndex)
              .setMIFlags(MachineInstr::FrameSetup);
      }
    }

    if (NeedsWinCFI) {
      HasWinCFI = true;
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_PrologEnd))
          .setMIFlag(MachineInstr::FrameSetup);
    }

    return;
  }

  bool IsWin64 =
      Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());
  unsigned FixedObject = getFixedObjectSize(MF, AFI, IsWin64, IsFunclet);

  auto PrologueSaveSize = AFI->getCalleeSavedStackSize() + FixedObject;
  // All of the remaining stack allocations are for locals.
  AFI->setLocalStackSize(NumBytes - PrologueSaveSize);
  bool CombineSPBump = shouldCombineCSRLocalStackBump(MF, NumBytes);
  if (CombineSPBump) {
    assert(!SVEStackSize && "Cannot combine SP bump with SVE");
    emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP,
                    {-NumBytes, MVT::i8}, TII, MachineInstr::FrameSetup, false,
                    NeedsWinCFI, &HasWinCFI);
    NumBytes = 0;
  } else if (PrologueSaveSize != 0) {
    MBBI = convertCalleeSaveRestoreToSPPrePostIncDec(
        MBB, MBBI, DL, TII, -PrologueSaveSize, NeedsWinCFI, &HasWinCFI);
    NumBytes -= PrologueSaveSize;
  }
  assert(NumBytes >= 0 && "Negative stack allocation size!?");

  // Move past the saves of the callee-saved registers, fixing up the offsets
  // and pre-inc if we decided to combine the callee-save and local stack
  // pointer bump above.
  MachineBasicBlock::iterator End = MBB.end();
  while (MBBI != End && MBBI->getFlag(MachineInstr::FrameSetup) &&
         !IsSVECalleeSave(MBBI)) {
    if (CombineSPBump)
      fixupCalleeSaveRestoreStackOffset(*MBBI, AFI->getLocalStackSize(),
                                        NeedsWinCFI, &HasWinCFI);
    ++MBBI;
  }

  // For funclets the FP belongs to the containing function.
  if (!IsFunclet && HasFP) {
    // Only set up FP if we actually need to.
    int64_t FPOffset = isTargetDarwin(MF) ? (AFI->getCalleeSavedStackSize() - 16) : 0;

    if (CombineSPBump)
      FPOffset += AFI->getLocalStackSize();

    // Issue    sub fp, sp, FPOffset or
    //          mov fp,sp          when FPOffset is zero.
    // Note: All stores of callee-saved registers are marked as "FrameSetup".
    // This code marks the instruction(s) that set the FP also.
    emitFrameOffset(MBB, MBBI, DL, AArch64::FP, AArch64::SP,
                    {FPOffset, MVT::i8}, TII, MachineInstr::FrameSetup, false,
                    NeedsWinCFI, &HasWinCFI);
  }

  if (windowsRequiresStackProbe(MF, NumBytes)) {
    uint64_t NumWords = NumBytes >> 4;
    if (NeedsWinCFI) {
      HasWinCFI = true;
      // alloc_l can hold at most 256MB, so assume that NumBytes doesn't
      // exceed this amount.  We need to move at most 2^24 - 1 into x15.
      // This is at most two instructions, MOVZ follwed by MOVK.
      // TODO: Fix to use multiple stack alloc unwind codes for stacks
      // exceeding 256MB in size.
      if (NumBytes >= (1 << 28))
        report_fatal_error("Stack size cannot exceed 256MB for stack "
                            "unwinding purposes");

      uint32_t LowNumWords = NumWords & 0xFFFF;
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::MOVZXi), AArch64::X15)
            .addImm(LowNumWords)
            .addImm(AArch64_AM::getShifterImm(AArch64_AM::LSL, 0))
            .setMIFlag(MachineInstr::FrameSetup);
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
            .setMIFlag(MachineInstr::FrameSetup);
      if ((NumWords & 0xFFFF0000) != 0) {
          BuildMI(MBB, MBBI, DL, TII->get(AArch64::MOVKXi), AArch64::X15)
              .addReg(AArch64::X15)
              .addImm((NumWords & 0xFFFF0000) >> 16) // High half
              .addImm(AArch64_AM::getShifterImm(AArch64_AM::LSL, 16))
              .setMIFlag(MachineInstr::FrameSetup);
          BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
            .setMIFlag(MachineInstr::FrameSetup);
      }
    } else {
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::MOVi64imm), AArch64::X15)
          .addImm(NumWords)
          .setMIFlags(MachineInstr::FrameSetup);
    }

    switch (MF.getTarget().getCodeModel()) {
    case CodeModel::Tiny:
    case CodeModel::Small:
    case CodeModel::Medium:
    case CodeModel::Kernel:
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::BL))
          .addExternalSymbol("__chkstk")
          .addReg(AArch64::X15, RegState::Implicit)
          .addReg(AArch64::X16, RegState::Implicit | RegState::Define | RegState::Dead)
          .addReg(AArch64::X17, RegState::Implicit | RegState::Define | RegState::Dead)
          .addReg(AArch64::NZCV, RegState::Implicit | RegState::Define | RegState::Dead)
          .setMIFlags(MachineInstr::FrameSetup);
      if (NeedsWinCFI) {
        HasWinCFI = true;
        BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
            .setMIFlag(MachineInstr::FrameSetup);
      }
      break;
    case CodeModel::Large:
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::MOVaddrEXT))
          .addReg(AArch64::X16, RegState::Define)
          .addExternalSymbol("__chkstk")
          .addExternalSymbol("__chkstk")
          .setMIFlags(MachineInstr::FrameSetup);
      if (NeedsWinCFI) {
        HasWinCFI = true;
        BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
            .setMIFlag(MachineInstr::FrameSetup);
      }

      BuildMI(MBB, MBBI, DL, TII->get(AArch64::BLR))
          .addReg(AArch64::X16, RegState::Kill)
          .addReg(AArch64::X15, RegState::Implicit | RegState::Define)
          .addReg(AArch64::X16, RegState::Implicit | RegState::Define | RegState::Dead)
          .addReg(AArch64::X17, RegState::Implicit | RegState::Define | RegState::Dead)
          .addReg(AArch64::NZCV, RegState::Implicit | RegState::Define | RegState::Dead)
          .setMIFlags(MachineInstr::FrameSetup);
      if (NeedsWinCFI) {
        HasWinCFI = true;
        BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
            .setMIFlag(MachineInstr::FrameSetup);
      }
      break;
    }

    BuildMI(MBB, MBBI, DL, TII->get(AArch64::SUBXrx64), AArch64::SP)
        .addReg(AArch64::SP, RegState::Kill)
        .addReg(AArch64::X15, RegState::Kill)
        .addImm(AArch64_AM::getArithExtendImm(AArch64_AM::UXTX, 4))
        .setMIFlags(MachineInstr::FrameSetup);
    if (NeedsWinCFI) {
      HasWinCFI = true;
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_StackAlloc))
          .addImm(NumBytes)
          .setMIFlag(MachineInstr::FrameSetup);
    }
    NumBytes = 0;
  }

  StackOffset AllocateBefore = SVEStackSize, AllocateAfter = {};
  MachineBasicBlock::iterator CalleeSavesBegin = MBBI, CalleeSavesEnd = MBBI;

  // Process the SVE callee-saves to determine what space needs to be
  // allocated.
  if (AFI->getSVECalleeSavedStackSize()) {
    // Find callee save instructions in frame.
    CalleeSavesBegin = MBBI;
    assert(IsSVECalleeSave(CalleeSavesBegin) && "Unexpected instruction");
    while (IsSVECalleeSave(MBBI) && MBBI != MBB.getFirstTerminator())
      ++MBBI;
    CalleeSavesEnd = MBBI;

    int64_t OffsetToFirstCalleeSaveFromSP =
        MFI.getObjectOffset(AFI->getMaxSVECSFrameIndex());
    StackOffset OffsetToCalleeSavesFromSP =
        StackOffset(OffsetToFirstCalleeSaveFromSP, MVT::nxv1i8) + SVEStackSize;
    AllocateBefore -= OffsetToCalleeSavesFromSP;
    AllocateAfter = SVEStackSize - AllocateBefore;
  }

  // Allocate space for the callee saves (if any).
  emitFrameOffset(MBB, CalleeSavesBegin, DL, AArch64::SP, AArch64::SP,
                  -AllocateBefore, TII,
                  MachineInstr::FrameSetup);

  // Finally allocate remaining SVE stack space.
  emitFrameOffset(MBB, CalleeSavesEnd, DL, AArch64::SP, AArch64::SP,
                  -AllocateAfter, TII,
                  MachineInstr::FrameSetup);

  // Allocate space for the rest of the frame.
  if (NumBytes) {
    // Alignment is required for the parent frame, not the funclet
    const bool NeedsRealignment =
        !IsFunclet && RegInfo->needsStackRealignment(MF);
    unsigned scratchSPReg = AArch64::SP;

    if (NeedsRealignment) {
      scratchSPReg = findScratchNonCalleeSaveRegister(&MBB);
      assert(scratchSPReg != AArch64::NoRegister);
    }

    // If we're a leaf function, try using the red zone.
    if (!canUseRedZone(MF))
      // FIXME: in the case of dynamic re-alignment, NumBytes doesn't have
      // the correct value here, as NumBytes also includes padding bytes,
      // which shouldn't be counted here.
      emitFrameOffset(MBB, MBBI, DL, scratchSPReg, AArch64::SP,
                      {-NumBytes, MVT::i8}, TII, MachineInstr::FrameSetup,
                      false, NeedsWinCFI, &HasWinCFI);

    if (NeedsRealignment) {
      const unsigned Alignment = MFI.getMaxAlignment();
      const unsigned NrBitsToZero = countTrailingZeros(Alignment);
      assert(NrBitsToZero > 1);
      assert(scratchSPReg != AArch64::SP);

      // SUB X9, SP, NumBytes
      //   -- X9 is temporary register, so shouldn't contain any live data here,
      //   -- free to use. This is already produced by emitFrameOffset above.
      // AND SP, X9, 0b11111...0000
      // The logical immediates have a non-trivial encoding. The following
      // formula computes the encoded immediate with all ones but
      // NrBitsToZero zero bits as least significant bits.
      uint32_t andMaskEncoded = (1 << 12)                         // = N
                                | ((64 - NrBitsToZero) << 6)      // immr
                                | ((64 - NrBitsToZero - 1) << 0); // imms

      BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
          .addReg(scratchSPReg, RegState::Kill)
          .addImm(andMaskEncoded);
      AFI->setStackRealigned(true);
      if (NeedsWinCFI) {
        HasWinCFI = true;
        BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_StackAlloc))
            .addImm(NumBytes & andMaskEncoded)
            .setMIFlag(MachineInstr::FrameSetup);
      }
    }
  }

  // If we need a base pointer, set it up here. It's whatever the value of the
  // stack pointer is at this point. Any variable size objects will be allocated
  // after this, so we can still use the base pointer to reference locals.
  //
  // FIXME: Clarify FrameSetup flags here.
  // Note: Use emitFrameOffset() like above for FP if the FrameSetup flag is
  // needed.
  // For funclets the BP belongs to the containing function.
  if (!IsFunclet && RegInfo->hasBasePointer(MF)) {
    TII->copyPhysReg(MBB, MBBI, DL, RegInfo->getBaseRegister(), AArch64::SP,
                     false);
    if (NeedsWinCFI) {
      HasWinCFI = true;
      BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_Nop))
          .setMIFlag(MachineInstr::FrameSetup);
    }
  }

  // The very last FrameSetup instruction indicates the end of prologue. Emit a
  // SEH opcode indicating the prologue end.
  if (NeedsWinCFI && HasWinCFI) {
    BuildMI(MBB, MBBI, DL, TII->get(AArch64::SEH_PrologEnd))
        .setMIFlag(MachineInstr::FrameSetup);
  }

  // SEH funclets are passed the frame pointer in X1.  If the parent
  // function uses the base register, then the base register is used
  // directly, and is not retrieved from X1.
  if (IsFunclet && F.hasPersonalityFn()) {
    EHPersonality Per = classifyEHPersonality(F.getPersonalityFn());
    if (isAsynchronousEHPersonality(Per)) {
      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::COPY), AArch64::FP)
          .addReg(AArch64::X1)
          .setMIFlag(MachineInstr::FrameSetup);
      MBB.addLiveIn(AArch64::X1);
    }
  }

  if (needsFrameMoves) {
    const DataLayout &TD = MF.getDataLayout();
    const int StackGrowth = isTargetDarwin(MF)
                                ? (2 * -TD.getPointerSize(0))
                                : -AFI->getCalleeSavedStackSize();
    Register FramePtr = RegInfo->getFrameRegister(MF);
    // An example of the prologue:
    //
    //     .globl __foo
    //     .align 2
    //  __foo:
    // Ltmp0:
    //     .cfi_startproc
    //     .cfi_personality 155, ___gxx_personality_v0
    // Leh_func_begin:
    //     .cfi_lsda 16, Lexception33
    //
    //     stp  xa,bx, [sp, -#offset]!
    //     ...
    //     stp  x28, x27, [sp, #offset-32]
    //     stp  fp, lr, [sp, #offset-16]
    //     add  fp, sp, #offset - 16
    //     sub  sp, sp, #1360
    //
    // The Stack:
    //       +-------------------------------------------+
    // 10000 | ........ | ........ | ........ | ........ |
    // 10004 | ........ | ........ | ........ | ........ |
    //       +-------------------------------------------+
    // 10008 | ........ | ........ | ........ | ........ |
    // 1000c | ........ | ........ | ........ | ........ |
    //       +===========================================+
    // 10010 |                X28 Register               |
    // 10014 |                X28 Register               |
    //       +-------------------------------------------+
    // 10018 |                X27 Register               |
    // 1001c |                X27 Register               |
    //       +===========================================+
    // 10020 |                Frame Pointer              |
    // 10024 |                Frame Pointer              |
    //       +-------------------------------------------+
    // 10028 |                Link Register              |
    // 1002c |                Link Register              |
    //       +===========================================+
    // 10030 | ........ | ........ | ........ | ........ |
    // 10034 | ........ | ........ | ........ | ........ |
    //       +-------------------------------------------+
    // 10038 | ........ | ........ | ........ | ........ |
    // 1003c | ........ | ........ | ........ | ........ |
    //       +-------------------------------------------+
    //
    //     [sp] = 10030        ::    >>initial value<<
    //     sp = 10020          ::  stp fp, lr, [sp, #-16]!
    //     fp = sp == 10020    ::  mov fp, sp
    //     [sp] == 10020       ::  stp x28, x27, [sp, #-16]!
    //     sp == 10010         ::    >>final value<<
    //
    // The frame pointer (w29) points to address 10020. If we use an offset of
    // '16' from 'w29', we get the CFI offsets of -8 for w30, -16 for w29, -24
    // for w27, and -32 for w28:
    //
    //  Ltmp1:
    //     .cfi_def_cfa w29, 16
    //  Ltmp2:
    //     .cfi_offset w30, -8
    //  Ltmp3:
    //     .cfi_offset w29, -16
    //  Ltmp4:
    //     .cfi_offset w27, -24
    //  Ltmp5:
    //     .cfi_offset w28, -32

    if (HasFP) {
      // Define the current CFA rule to use the provided FP.
      unsigned Reg = RegInfo->getDwarfRegNum(FramePtr, true);
      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createDefCfa(
          nullptr, Reg, StackGrowth - FixedObject));
      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    } else {
      // Encode the stack size of the leaf function.
      unsigned CFIIndex = MF.addFrameInst(
          MCCFIInstruction::createDefCfaOffset(nullptr, -MFI.getStackSize()));
      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    }

    // Now emit the moves for whatever callee saved regs we have (including FP,
    // LR if those are saved).
    emitCalleeSavedFrameMoves(MBB, MBBI);
  }
}

static void InsertReturnAddressAuth(MachineFunction &MF,
                                    MachineBasicBlock &MBB) {
  if (!ShouldSignReturnAddress(MF))
    return;
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  const TargetInstrInfo *TII = Subtarget.getInstrInfo();

  MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
  DebugLoc DL;
  if (MBBI != MBB.end())
    DL = MBBI->getDebugLoc();

  // The AUTIASP instruction assembles to a hint instruction before v8.3a so
  // this instruction can safely used for any v8a architecture.
  // From v8.3a onwards there are optimised authenticate LR and return
  // instructions, namely RETA{A,B}, that can be used instead.
  if (Subtarget.hasV8_3aOps() && MBBI != MBB.end() &&
      MBBI->getOpcode() == AArch64::RET_ReallyLR) {
    BuildMI(MBB, MBBI, DL,
            TII->get(ShouldSignWithAKey(MF) ? AArch64::RETAA : AArch64::RETAB))
        .copyImplicitOps(*MBBI);
    MBB.erase(MBBI);
  } else {
    BuildMI(
        MBB, MBBI, DL,
        TII->get(ShouldSignWithAKey(MF) ? AArch64::AUTIASP : AArch64::AUTIBSP))
        .setMIFlag(MachineInstr::FrameDestroy);
  }
}

static bool isFuncletReturnInstr(const MachineInstr &MI) {
  switch (MI.getOpcode()) {
  default:
    return false;
  case AArch64::CATCHRET:
  case AArch64::CLEANUPRET:
    return true;
  }
}

void AArch64FrameLowering::emitEpilogue(MachineFunction &MF,
                                        MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  const TargetInstrInfo *TII = Subtarget.getInstrInfo();
  DebugLoc DL;
  bool IsTailCallReturn = false;
  bool NeedsWinCFI = needsWinCFI(MF);
  bool HasWinCFI = false;
  bool IsFunclet = false;
  auto WinCFI = make_scope_exit([&]() {
    if (!MF.hasWinCFI())
      MF.setHasWinCFI(HasWinCFI);
  });

  if (MBB.end() != MBBI) {
    DL = MBBI->getDebugLoc();
    unsigned RetOpcode = MBBI->getOpcode();
    IsTailCallReturn = RetOpcode == AArch64::TCRETURNdi ||
                       RetOpcode == AArch64::TCRETURNri ||
                       RetOpcode == AArch64::TCRETURNriBTI;
    IsFunclet = isFuncletReturnInstr(*MBBI);
  }

  int64_t NumBytes = IsFunclet ? getWinEHFuncletFrameSize(MF)
                               : MFI.getStackSize();
  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();

  // All calls are tail calls in GHC calling conv, and functions have no
  // prologue/epilogue.
  if (MF.getFunction().getCallingConv() == CallingConv::GHC)
    return;

  // Initial and residual are named for consistency with the prologue. Note that
  // in the epilogue, the residual adjustment is executed first.
  uint64_t ArgumentPopSize = 0;
  if (IsTailCallReturn) {
    MachineOperand &StackAdjust = MBBI->getOperand(1);

    // For a tail-call in a callee-pops-arguments environment, some or all of
    // the stack may actually be in use for the call's arguments, this is
    // calculated during LowerCall and consumed here...
    ArgumentPopSize = StackAdjust.getImm();
  } else {
    // ... otherwise the amount to pop is *all* of the argument space,
    // conveniently stored in the MachineFunctionInfo by
    // LowerFormalArguments. This will, of course, be zero for the C calling
    // convention.
    ArgumentPopSize = AFI->getArgumentStackToRestore();
  }

  // The stack frame should be like below,
  //
  //      ----------------------                     ---
  //      |                    |                      |
  //      | BytesInStackArgArea|              CalleeArgStackSize
  //      | (NumReusableBytes) |                (of tail call)
  //      |                    |                     ---
  //      |                    |                      |
  //      ---------------------|        ---           |
  //      |                    |         |            |
  //      |   CalleeSavedReg   |         |            |
  //      | (CalleeSavedStackSize)|      |            |
  //      |                    |         |            |
  //      ---------------------|         |         NumBytes
  //      |                    |     StackSize  (StackAdjustUp)
  //      |   LocalStackSize   |         |            |
  //      | (covering callee   |         |            |
  //      |       args)        |         |            |
  //      |                    |         |            |
  //      ----------------------        ---          ---
  //
  // So NumBytes = StackSize + BytesInStackArgArea - CalleeArgStackSize
  //             = StackSize + ArgumentPopSize
  //
  // AArch64TargetLowering::LowerCall figures out ArgumentPopSize and keeps
  // it as the 2nd argument of AArch64ISD::TC_RETURN.

  auto Cleanup = make_scope_exit([&] { InsertReturnAddressAuth(MF, MBB); });

  bool IsWin64 =
      Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());
  unsigned FixedObject = getFixedObjectSize(MF, AFI, IsWin64, IsFunclet);

  uint64_t AfterCSRPopSize = ArgumentPopSize;
  auto PrologueSaveSize = AFI->getCalleeSavedStackSize() + FixedObject;
  // We cannot rely on the local stack size set in emitPrologue if the function
  // has funclets, as funclets have different local stack size requirements, and
  // the current value set in emitPrologue may be that of the containing
  // function.
  if (MF.hasEHFunclets())
    AFI->setLocalStackSize(NumBytes - PrologueSaveSize);
  bool CombineSPBump = shouldCombineCSRLocalStackBump(MF, NumBytes);
  // Assume we can't combine the last pop with the sp restore.

  if (!CombineSPBump && PrologueSaveSize != 0) {
    MachineBasicBlock::iterator Pop = std::prev(MBB.getFirstTerminator());
    while (AArch64InstrInfo::isSEHInstruction(*Pop))
      Pop = std::prev(Pop);
    // Converting the last ldp to a post-index ldp is valid only if the last
    // ldp's offset is 0.
    const MachineOperand &OffsetOp = Pop->getOperand(Pop->getNumOperands() - 1);
    // If the offset is 0, convert it to a post-index ldp.
    if (OffsetOp.getImm() == 0)
      convertCalleeSaveRestoreToSPPrePostIncDec(
          MBB, Pop, DL, TII, PrologueSaveSize, NeedsWinCFI, &HasWinCFI, false);
    else {
      // If not, make sure to emit an add after the last ldp.
      // We're doing this by transfering the size to be restored from the
      // adjustment *before* the CSR pops to the adjustment *after* the CSR
      // pops.
      AfterCSRPopSize += PrologueSaveSize;
    }
  }

  // Move past the restores of the callee-saved registers.
  // If we plan on combining the sp bump of the local stack size and the callee
  // save stack size, we might need to adjust the CSR save and restore offsets.
  MachineBasicBlock::iterator LastPopI = MBB.getFirstTerminator();
  MachineBasicBlock::iterator Begin = MBB.begin();
  while (LastPopI != Begin) {
    --LastPopI;
    if (!LastPopI->getFlag(MachineInstr::FrameDestroy) ||
        IsSVECalleeSave(LastPopI)) {
      ++LastPopI;
      break;
    } else if (CombineSPBump)
      fixupCalleeSaveRestoreStackOffset(*LastPopI, AFI->getLocalStackSize(),
                                        NeedsWinCFI, &HasWinCFI);
  }

  if (NeedsWinCFI) {
    HasWinCFI = true;
    BuildMI(MBB, LastPopI, DL, TII->get(AArch64::SEH_EpilogStart))
        .setMIFlag(MachineInstr::FrameDestroy);
  }

  const StackOffset &SVEStackSize = getSVEStackSize(MF);

  // If there is a single SP update, insert it before the ret and we're done.
  if (CombineSPBump) {
    assert(!SVEStackSize && "Cannot combine SP bump with SVE");
    emitFrameOffset(MBB, MBB.getFirstTerminator(), DL, AArch64::SP, AArch64::SP,
                    {NumBytes + (int64_t)AfterCSRPopSize, MVT::i8}, TII,
                    MachineInstr::FrameDestroy, false, NeedsWinCFI, &HasWinCFI);
    if (NeedsWinCFI && HasWinCFI)
      BuildMI(MBB, MBB.getFirstTerminator(), DL,
              TII->get(AArch64::SEH_EpilogEnd))
          .setMIFlag(MachineInstr::FrameDestroy);
    return;
  }

  NumBytes -= PrologueSaveSize;
  assert(NumBytes >= 0 && "Negative stack allocation size!?");

  // Process the SVE callee-saves to determine what space needs to be
  // deallocated.
  StackOffset DeallocateBefore = {}, DeallocateAfter = SVEStackSize;
  MachineBasicBlock::iterator RestoreBegin = LastPopI, RestoreEnd = LastPopI;
  if (AFI->getSVECalleeSavedStackSize()) {
    RestoreBegin = std::prev(RestoreEnd);;
    while (IsSVECalleeSave(RestoreBegin) &&
           RestoreBegin != MBB.begin())
      --RestoreBegin;
    ++RestoreBegin;

    assert(IsSVECalleeSave(RestoreBegin) &&
           IsSVECalleeSave(std::prev(RestoreEnd)) && "Unexpected instruction");

    int64_t OffsetToFirstCalleeSaveFromSP =
        MFI.getObjectOffset(AFI->getMaxSVECSFrameIndex());
    StackOffset OffsetToCalleeSavesFromSP =
        StackOffset(OffsetToFirstCalleeSaveFromSP, MVT::nxv1i8) + SVEStackSize;
    DeallocateBefore = OffsetToCalleeSavesFromSP;
    DeallocateAfter = SVEStackSize - DeallocateBefore;
  }

  // Deallocate the SVE area.
  if (SVEStackSize) {
    if (AFI->isStackRealigned()) {
      if (AFI->getSVECalleeSavedStackSize())
        // Set SP to start of SVE area, from which the callee-save reloads
        // can be done. The code below will deallocate the stack space
        // space by moving FP -> SP.
        emitFrameOffset(MBB, RestoreBegin, DL, AArch64::SP, AArch64::FP,
                        -SVEStackSize, TII, MachineInstr::FrameDestroy);
    } else {
      if (AFI->getSVECalleeSavedStackSize()) {
        // Deallocate the non-SVE locals first before we can deallocate (and
        // restore callee saves) from the SVE area.
        emitFrameOffset(MBB, RestoreBegin, DL, AArch64::SP, AArch64::SP,
                        {NumBytes, MVT::i8}, TII, MachineInstr::FrameDestroy);
        NumBytes = 0;
      }

      emitFrameOffset(MBB, RestoreBegin, DL, AArch64::SP, AArch64::SP,
                      DeallocateBefore, TII, MachineInstr::FrameDestroy);

      emitFrameOffset(MBB, RestoreEnd, DL, AArch64::SP, AArch64::SP,
                      DeallocateAfter, TII, MachineInstr::FrameDestroy);
    }
  }

  if (!hasFP(MF)) {
    bool RedZone = canUseRedZone(MF);
    // If this was a redzone leaf function, we don't need to restore the
    // stack pointer (but we may need to pop stack args for fastcc).
    if (RedZone && AfterCSRPopSize == 0)
      return;

    bool NoCalleeSaveRestore = PrologueSaveSize == 0;
    int64_t StackRestoreBytes = RedZone ? 0 : NumBytes;
    if (NoCalleeSaveRestore)
      StackRestoreBytes += AfterCSRPopSize;

    // If we were able to combine the local stack pop with the argument pop,
    // then we're done.
    bool Done = NoCalleeSaveRestore || AfterCSRPopSize == 0;

    // If we're done after this, make sure to help the load store optimizer.
    if (Done)
      adaptForLdStOpt(MBB, MBB.getFirstTerminator(), LastPopI);

    emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::SP,
                    {StackRestoreBytes, MVT::i8}, TII,
                    MachineInstr::FrameDestroy, false, NeedsWinCFI, &HasWinCFI);
    if (Done) {
      if (NeedsWinCFI) {
        HasWinCFI = true;
        BuildMI(MBB, MBB.getFirstTerminator(), DL,
                TII->get(AArch64::SEH_EpilogEnd))
            .setMIFlag(MachineInstr::FrameDestroy);
      }
      return;
    }

    NumBytes = 0;
  }

  // Restore the original stack pointer.
  // FIXME: Rather than doing the math here, we should instead just use
  // non-post-indexed loads for the restores if we aren't actually going to
  // be able to save any instructions.
  if (!IsFunclet && (MFI.hasVarSizedObjects() || AFI->isStackRealigned())) {
    int64_t OffsetToFrameRecord =
        isTargetDarwin(MF) ? (-(int64_t)AFI->getCalleeSavedStackSize() + 16) : 0;
    emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::FP,
                    {OffsetToFrameRecord, MVT::i8},
                    TII, MachineInstr::FrameDestroy, false, NeedsWinCFI);
  } else if (NumBytes)
    emitFrameOffset(MBB, LastPopI, DL, AArch64::SP, AArch64::SP,
                    {NumBytes, MVT::i8}, TII, MachineInstr::FrameDestroy, false,
                    NeedsWinCFI);

  // This must be placed after the callee-save restore code because that code
  // assumes the SP is at the same location as it was after the callee-save save
  // code in the prologue.
  if (AfterCSRPopSize) {
    // Find an insertion point for the first ldp so that it goes before the
    // shadow call stack epilog instruction. This ensures that the restore of
    // lr from x18 is placed after the restore from sp.
    auto FirstSPPopI = MBB.getFirstTerminator();
    while (FirstSPPopI != Begin) {
      auto Prev = std::prev(FirstSPPopI);
      if (Prev->getOpcode() != AArch64::LDRXpre ||
          Prev->getOperand(0).getReg() == AArch64::SP)
        break;
      FirstSPPopI = Prev;
    }

    adaptForLdStOpt(MBB, FirstSPPopI, LastPopI);

    emitFrameOffset(MBB, FirstSPPopI, DL, AArch64::SP, AArch64::SP,
                    {(int64_t)AfterCSRPopSize, MVT::i8}, TII,
                    MachineInstr::FrameDestroy, false, NeedsWinCFI, &HasWinCFI);
  }
  if (NeedsWinCFI && HasWinCFI)
    BuildMI(MBB, MBB.getFirstTerminator(), DL, TII->get(AArch64::SEH_EpilogEnd))
        .setMIFlag(MachineInstr::FrameDestroy);

  MF.setHasWinCFI(HasWinCFI);
}

/// getFrameIndexReference - Provide a base+offset reference to an FI slot for
/// debug info.  It's the same as what we use for resolving the code-gen
/// references for now.  FIXME: This can go wrong when references are
/// SP-relative and simple call frames aren't used.
int AArch64FrameLowering::getFrameIndexReference(const MachineFunction &MF,
                                                 int FI,
                                                 unsigned &FrameReg) const {
  return resolveFrameIndexReference(
             MF, FI, FrameReg,
             /*PreferFP=*/
             MF.getFunction().hasFnAttribute(Attribute::SanitizeHWAddress),
             /*ForSimm=*/false)
      .getBytes();
}

int AArch64FrameLowering::getNonLocalFrameIndexReference(
  const MachineFunction &MF, int FI) const {
  return getSEHFrameIndexOffset(MF, FI);
}

static StackOffset getFPOffset(const MachineFunction &MF, int64_t ObjectOffset) {
  const auto *AFI = MF.getInfo<AArch64FunctionInfo>();
  const auto &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  bool IsWin64 =
      Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv());

  unsigned FixedObject =
      getFixedObjectSize(MF, AFI, IsWin64, /*IsFunclet=*/false);
  unsigned FPAdjust = isTargetDarwin(MF)
                        ? 16 : AFI->getCalleeSavedStackSize(MF.getFrameInfo());
  return {ObjectOffset + FixedObject + FPAdjust, MVT::i8};
}

static StackOffset getStackOffset(const MachineFunction &MF, int64_t ObjectOffset) {
  const auto &MFI = MF.getFrameInfo();
  return {ObjectOffset + (int64_t)MFI.getStackSize(), MVT::i8};
}

int AArch64FrameLowering::getSEHFrameIndexOffset(const MachineFunction &MF,
                                                 int FI) const {
  const auto *RegInfo = static_cast<const AArch64RegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());
  int ObjectOffset = MF.getFrameInfo().getObjectOffset(FI);
  return RegInfo->getLocalAddressRegister(MF) == AArch64::FP
             ? getFPOffset(MF, ObjectOffset).getBytes()
             : getStackOffset(MF, ObjectOffset).getBytes();
}

StackOffset AArch64FrameLowering::resolveFrameIndexReference(
    const MachineFunction &MF, int FI, unsigned &FrameReg, bool PreferFP,
    bool ForSimm) const {
  const auto &MFI = MF.getFrameInfo();
  int64_t ObjectOffset = MFI.getObjectOffset(FI);
  bool isFixed = MFI.isFixedObjectIndex(FI);
  bool isSVE = MFI.getStackID(FI) == TargetStackID::SVEVector;
  return resolveFrameOffsetReference(MF, ObjectOffset, isFixed, isSVE, FrameReg,
                                     PreferFP, ForSimm);
}

StackOffset AArch64FrameLowering::resolveFrameOffsetReference(
    const MachineFunction &MF, int64_t ObjectOffset, bool isFixed, bool isSVE,
    unsigned &FrameReg, bool PreferFP, bool ForSimm) const {
  const auto &MFI = MF.getFrameInfo();
  const auto *RegInfo = static_cast<const AArch64RegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());
  const auto *AFI = MF.getInfo<AArch64FunctionInfo>();
  const auto &Subtarget = MF.getSubtarget<AArch64Subtarget>();

  int64_t FPOffset = getFPOffset(MF, ObjectOffset).getBytes();
  int64_t Offset = getStackOffset(MF, ObjectOffset).getBytes();
  bool isCSR =
      !isFixed && ObjectOffset >= -((int)AFI->getCalleeSavedStackSize(MFI));

  const StackOffset &SVEStackSize = getSVEStackSize(MF);

  // Use frame pointer to reference fixed objects. Use it for locals if
  // there are VLAs or a dynamically realigned SP (and thus the SP isn't
  // reliable as a base). Make sure useFPForScavengingIndex() does the
  // right thing for the emergency spill slot.
  bool UseFP = false;
  if (AFI->hasStackFrame() && !isSVE) {
    // We shouldn't prefer using the FP when there is an SVE area
    // in between the FP and the non-SVE locals/spills.
    PreferFP &= !SVEStackSize;

    // Note: Keeping the following as multiple 'if' statements rather than
    // merging to a single expression for readability.
    //
    // Argument access should always use the FP.
    if (isFixed) {
      UseFP = hasFP(MF);
    } else if (isCSR && RegInfo->needsStackRealignment(MF)) {
      // References to the CSR area must use FP if we're re-aligning the stack
      // since the dynamically-sized alignment padding is between the SP/BP and
      // the CSR area.
      assert(hasFP(MF) && "Re-aligned stack must have frame pointer");
      UseFP = true;
    } else if (hasFP(MF) && !RegInfo->needsStackRealignment(MF)) {
      // If the FPOffset is negative and we're producing a signed immediate, we
      // have to keep in mind that the available offset range for negative
      // offsets is smaller than for positive ones. If an offset is available
      // via the FP and the SP, use whichever is closest.
      bool FPOffsetFits = !ForSimm || FPOffset >= -256;
      PreferFP |= Offset > -FPOffset;

      if (MFI.hasVarSizedObjects()) {
        // If we have variable sized objects, we can use either FP or BP, as the
        // SP offset is unknown. We can use the base pointer if we have one and
        // FP is not preferred. If not, we're stuck with using FP.
        bool CanUseBP = RegInfo->hasBasePointer(MF);
        if (FPOffsetFits && CanUseBP) // Both are ok. Pick the best.
          UseFP = PreferFP;
        else if (!CanUseBP) { // Can't use BP. Forced to use FP.
          assert(!SVEStackSize && "Expected BP to be available");
          UseFP = true;
        }
        // else we can use BP and FP, but the offset from FP won't fit.
        // That will make us scavenge registers which we can probably avoid by
        // using BP. If it won't fit for BP either, we'll scavenge anyway.
      } else if (FPOffset >= 0) {
        // Use SP or FP, whichever gives us the best chance of the offset
        // being in range for direct access. If the FPOffset is positive,
        // that'll always be best, as the SP will be even further away.
        UseFP = true;
      } else if (MF.hasEHFunclets() && !RegInfo->hasBasePointer(MF)) {
        // Funclets access the locals contained in the parent's stack frame
        // via the frame pointer, so we have to use the FP in the parent
        // function.
        (void) Subtarget;
        assert(
            Subtarget.isCallingConvWin64(MF.getFunction().getCallingConv()) &&
            "Funclets should only be present on Win64");
        UseFP = true;
      } else {
        // We have the choice between FP and (SP or BP).
        if (FPOffsetFits && PreferFP) // If FP is the best fit, use it.
          UseFP = true;
      }
    }
  }

  assert(((isFixed || isCSR) || !RegInfo->needsStackRealignment(MF) || !UseFP) &&
         "In the presence of dynamic stack pointer realignment, "
         "non-argument/CSR objects cannot be accessed through the frame pointer");

  if (isSVE) {
    int64_t OffsetToSVEArea =
        MFI.getStackSize() - AFI->getCalleeSavedStackSize();
    StackOffset FPOffset = {ObjectOffset, MVT::nxv1i8};
    StackOffset SPOffset = SVEStackSize +
                           StackOffset(ObjectOffset, MVT::nxv1i8) +
                           StackOffset(OffsetToSVEArea, MVT::i8);
    // Always use the FP for SVE spills if available and beneficial.
    if (hasFP(MF) &&
        (SPOffset.getBytes() ||
         FPOffset.getScalableBytes() < SPOffset.getScalableBytes() ||
         RegInfo->needsStackRealignment(MF))) {
      FrameReg = RegInfo->getFrameRegister(MF);
      return FPOffset;
    }

    FrameReg = RegInfo->hasBasePointer(MF) ? RegInfo->getBaseRegister()
                                           : (unsigned)AArch64::SP;
    return SPOffset;
  }

  StackOffset ScalableOffset = {};
  if (UseFP && !(isFixed || isCSR))
    ScalableOffset = -SVEStackSize;
  if (!UseFP && (isFixed || isCSR))
    ScalableOffset = SVEStackSize;

  if (UseFP) {
    FrameReg = RegInfo->getFrameRegister(MF);
    return StackOffset(FPOffset, MVT::i8) + ScalableOffset;
  }

  // Use the base pointer if we have one.
  if (RegInfo->hasBasePointer(MF))
    FrameReg = RegInfo->getBaseRegister();
  else {
    assert(!MFI.hasVarSizedObjects() &&
           "Can't use SP when we have var sized objects.");
    FrameReg = AArch64::SP;
    // If we're using the red zone for this function, the SP won't actually
    // be adjusted, so the offsets will be negative. They're also all
    // within range of the signed 9-bit immediate instructions.
    if (canUseRedZone(MF))
      Offset -= AFI->getLocalStackSize();
  }

  return StackOffset(Offset, MVT::i8) + ScalableOffset;
}

static unsigned getPrologueDeath(MachineFunction &MF, unsigned Reg) {
  // Do not set a kill flag on values that are also marked as live-in. This
  // happens with the @llvm-returnaddress intrinsic and with arguments passed in
  // callee saved registers.
  // Omitting the kill flags is conservatively correct even if the live-in
  // is not used after all.
  bool IsLiveIn = MF.getRegInfo().isLiveIn(Reg);
  return getKillRegState(!IsLiveIn);
}

static bool produceCompactUnwindFrame(MachineFunction &MF) {
  const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
  AttributeList Attrs = MF.getFunction().getAttributes();
  return Subtarget.isTargetMachO() &&
         !(Subtarget.getTargetLowering()->supportSwiftError() &&
           Attrs.hasAttrSomewhere(Attribute::SwiftError));
}

static bool invalidateWindowsRegisterPairing(unsigned Reg1, unsigned Reg2,
                                             bool NeedsWinCFI) {
  // If we are generating register pairs for a Windows function that requires
  // EH support, then pair consecutive registers only.  There are no unwind
  // opcodes for saves/restores of non-consectuve register pairs.
  // The unwind opcodes are save_regp, save_regp_x, save_fregp, save_frepg_x.
  // https://docs.microsoft.com/en-us/cpp/build/arm64-exception-handling

  // TODO: LR can be paired with any register.  We don't support this yet in
  // the MCLayer.  We need to add support for the save_lrpair unwind code.
  if (Reg2 == AArch64::FP)
    return true;
  if (!NeedsWinCFI)
    return false;
  if (Reg2 == Reg1 + 1)
    return false;
  return true;
}

/// Returns true if Reg1 and Reg2 cannot be paired using a ldp/stp instruction.
/// WindowsCFI requires that only consecutive registers can be paired.
/// LR and FP need to be allocated together when the frame needs to save
/// the frame-record. This means any other register pairing with LR is invalid.
static bool invalidateRegisterPairing(unsigned Reg1, unsigned Reg2,
                                      bool UsesWinAAPCS, bool NeedsWinCFI, bool NeedsFrameRecord) {
  if (UsesWinAAPCS)
    return invalidateWindowsRegisterPairing(Reg1, Reg2, NeedsWinCFI);

  // If we need to store the frame record, don't pair any register
  // with LR other than FP.
  if (NeedsFrameRecord)
    return Reg2 == AArch64::LR;

  return false;
}

namespace {

struct RegPairInfo {
  unsigned Reg1 = AArch64::NoRegister;
  unsigned Reg2 = AArch64::NoRegister;
  int FrameIdx;
  int Offset;
  enum RegType { GPR, FPR64, FPR128, PPR, ZPR } Type;

  RegPairInfo() = default;

  bool isPaired() const { return Reg2 != AArch64::NoRegister; }

  unsigned getScale() const {
    switch (Type) {
    case PPR:
      return 2;
    case GPR:
    case FPR64:
      return 8;
    case ZPR:
    case FPR128:
      return 16;
    }
    llvm_unreachable("Unsupported type");
  }

  bool isScalable() const { return Type == PPR || Type == ZPR; }
};

} // end anonymous namespace

static void computeCalleeSaveRegisterPairs(
    MachineFunction &MF, const std::vector<CalleeSavedInfo> &CSI,
    const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs,
    bool &NeedShadowCallStackProlog, bool NeedsFrameRecord) {

  if (CSI.empty())
    return;

  bool IsWindows = isTargetWindows(MF);
  bool NeedsWinCFI = needsWinCFI(MF);
  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  CallingConv::ID CC = MF.getFunction().getCallingConv();
  unsigned Count = CSI.size();
  (void)CC;
  // MachO's compact unwind format relies on all registers being stored in
  // pairs.
  assert((!produceCompactUnwindFrame(MF) ||
          CC == CallingConv::PreserveMost ||
          (Count & 1) == 0) &&
         "Odd number of callee-saved regs to spill!");
  int ByteOffset = AFI->getCalleeSavedStackSize();
  int ScalableByteOffset = AFI->getSVECalleeSavedStackSize();
  // On Linux, we will have either one or zero non-paired register.  On Windows
  // with CFI, we can have multiple unpaired registers in order to utilize the
  // available unwind codes.  This flag assures that the alignment fixup is done
  // only once, as intened.
  bool FixupDone = false;
  for (unsigned i = 0; i < Count; ++i) {
    RegPairInfo RPI;
    RPI.Reg1 = CSI[i].getReg();

    if (AArch64::GPR64RegClass.contains(RPI.Reg1))
      RPI.Type = RegPairInfo::GPR;
    else if (AArch64::FPR64RegClass.contains(RPI.Reg1))
      RPI.Type = RegPairInfo::FPR64;
    else if (AArch64::FPR128RegClass.contains(RPI.Reg1))
      RPI.Type = RegPairInfo::FPR128;
    else if (AArch64::ZPRRegClass.contains(RPI.Reg1))
      RPI.Type = RegPairInfo::ZPR;
    else if (AArch64::PPRRegClass.contains(RPI.Reg1))
      RPI.Type = RegPairInfo::PPR;
    else
      llvm_unreachable("Unsupported register class.");

    // Add the next reg to the pair if it is in the same register class.
    if (i + 1 < Count) {
      unsigned NextReg = CSI[i + 1].getReg();
      switch (RPI.Type) {
      case RegPairInfo::GPR:
        if (AArch64::GPR64RegClass.contains(NextReg) &&
            !invalidateRegisterPairing(RPI.Reg1, NextReg, IsWindows, NeedsWinCFI,
                                       NeedsFrameRecord))
          RPI.Reg2 = NextReg;
        break;
      case RegPairInfo::FPR64:
        if (AArch64::FPR64RegClass.contains(NextReg) &&
            !invalidateWindowsRegisterPairing(RPI.Reg1, NextReg, NeedsWinCFI))
          RPI.Reg2 = NextReg;
        break;
      case RegPairInfo::FPR128:
        if (AArch64::FPR128RegClass.contains(NextReg))
          RPI.Reg2 = NextReg;
        break;
      case RegPairInfo::PPR:
      case RegPairInfo::ZPR:
        break;
      }
    }

    // If either of the registers to be saved is the lr register, it means that
    // we also need to save lr in the shadow call stack.
    if ((RPI.Reg1 == AArch64::LR || RPI.Reg2 == AArch64::LR) &&
        MF.getFunction().hasFnAttribute(Attribute::ShadowCallStack)) {
      if (!MF.getSubtarget<AArch64Subtarget>().isXRegisterReserved(18))
        report_fatal_error("Must reserve x18 to use shadow call stack");
      NeedShadowCallStackProlog = true;
    }

    // GPRs and FPRs are saved in pairs of 64-bit regs. We expect the CSI
    // list to come in sorted by frame index so that we can issue the store
    // pair instructions directly. Assert if we see anything otherwise.
    //
    // The order of the registers in the list is controlled by
    // getCalleeSavedRegs(), so they will always be in-order, as well.
    assert((!RPI.isPaired() ||
            (CSI[i].getFrameIdx() + 1 == CSI[i + 1].getFrameIdx())) &&
           "Out of order callee saved regs!");

    assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg2 != AArch64::FP ||
            RPI.Reg1 == AArch64::LR) &&
           "FrameRecord must be allocated together with LR");

    // Windows AAPCS has FP and LR reversed.
    assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg1 != AArch64::FP ||
            RPI.Reg2 == AArch64::LR) &&
           "FrameRecord must be allocated together with LR");

    // MachO's compact unwind format relies on all registers being stored in
    // adjacent register pairs.
    assert((!produceCompactUnwindFrame(MF) ||
            CC == CallingConv::PreserveMost ||
            (RPI.isPaired() &&
             ((RPI.Reg1 == AArch64::LR && RPI.Reg2 == AArch64::FP) ||
              RPI.Reg1 + 1 == RPI.Reg2))) &&
           "Callee-save registers not saved as adjacent register pair!");

    RPI.FrameIdx = CSI[i].getFrameIdx();

    int Scale = RPI.getScale();
    if (RPI.isScalable())
      ScalableByteOffset -= Scale;
    else
      ByteOffset -= RPI.isPaired() ? 2 * Scale : Scale;

    assert(!(RPI.isScalable() && RPI.isPaired()) &&
           "Paired spill/fill instructions don't exist for SVE vectors");

    // Round up size of non-pair to pair size if we need to pad the
    // callee-save area to ensure 16-byte alignment.
    if (AFI->hasCalleeSaveStackFreeSpace() && !FixupDone &&
        !RPI.isScalable() && RPI.Type != RegPairInfo::FPR128 &&
        !RPI.isPaired()) {
      FixupDone = true;
      ByteOffset -= 8;
      assert(ByteOffset % 16 == 0);
      assert(MFI.getObjectAlignment(RPI.FrameIdx) <= 16);
      MFI.setObjectAlignment(RPI.FrameIdx, 16);
    }

    int Offset = RPI.isScalable() ? ScalableByteOffset : ByteOffset;
    assert(Offset % Scale == 0);
    RPI.Offset = Offset / Scale;

    assert(((!RPI.isScalable() && RPI.Offset >= -64 && RPI.Offset <= 63) ||
            (RPI.isScalable() && RPI.Offset >= -256 && RPI.Offset <= 255)) &&
           "Offset out of bounds for LDP/STP immediate");

    RegPairs.push_back(RPI);
    if (RPI.isPaired())
      ++i;
  }
}

bool AArch64FrameLowering::spillCalleeSavedRegisters(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
    const std::vector<CalleeSavedInfo> &CSI,
    const TargetRegisterInfo *TRI) const {
  MachineFunction &MF = *MBB.getParent();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  bool NeedsWinCFI = needsWinCFI(MF);
  DebugLoc DL;
  SmallVector<RegPairInfo, 8> RegPairs;

  bool NeedShadowCallStackProlog = false;
  computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs,
                                 NeedShadowCallStackProlog, hasFP(MF));
  const MachineRegisterInfo &MRI = MF.getRegInfo();

  if (NeedShadowCallStackProlog) {
    // Shadow call stack prolog: str x30, [x18], #8
    BuildMI(MBB, MI, DL, TII.get(AArch64::STRXpost))
        .addReg(AArch64::X18, RegState::Define)
        .addReg(AArch64::LR)
        .addReg(AArch64::X18)
        .addImm(8)
        .setMIFlag(MachineInstr::FrameSetup);

    if (NeedsWinCFI)
      BuildMI(MBB, MI, DL, TII.get(AArch64::SEH_Nop))
          .setMIFlag(MachineInstr::FrameSetup);

    if (!MF.getFunction().hasFnAttribute(Attribute::NoUnwind)) {
      // Emit a CFI instruction that causes 8 to be subtracted from the value of
      // x18 when unwinding past this frame.
      static const char CFIInst[] = {
          dwarf::DW_CFA_val_expression,
          18, // register
          2,  // length
          static_cast<char>(unsigned(dwarf::DW_OP_breg18)),
          static_cast<char>(-8) & 0x7f, // addend (sleb128)
      };
      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createEscape(
          nullptr, StringRef(CFIInst, sizeof(CFIInst))));
      BuildMI(MBB, MI, DL, TII.get(AArch64::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlag(MachineInstr::FrameSetup);
    }

    // This instruction also makes x18 live-in to the entry block.
    MBB.addLiveIn(AArch64::X18);
  }

  for (auto RPII = RegPairs.rbegin(), RPIE = RegPairs.rend(); RPII != RPIE;
       ++RPII) {
    RegPairInfo RPI = *RPII;
    unsigned Reg1 = RPI.Reg1;
    unsigned Reg2 = RPI.Reg2;
    unsigned StrOpc;

    // Issue sequence of spills for cs regs.  The first spill may be converted
    // to a pre-decrement store later by emitPrologue if the callee-save stack
    // area allocation can't be combined with the local stack area allocation.
    // For example:
    //    stp     x22, x21, [sp, #0]     // addImm(+0)
    //    stp     x20, x19, [sp, #16]    // addImm(+2)
    //    stp     fp, lr, [sp, #32]      // addImm(+4)
    // Rationale: This sequence saves uop updates compared to a sequence of
    // pre-increment spills like stp xi,xj,[sp,#-16]!
    // Note: Similar rationale and sequence for restores in epilog.
    unsigned Size, Align;
    switch (RPI.Type) {
    case RegPairInfo::GPR:
       StrOpc = RPI.isPaired() ? AArch64::STPXi : AArch64::STRXui;
       Size = 8;
       Align = 8;
       break;
    case RegPairInfo::FPR64:
       StrOpc = RPI.isPaired() ? AArch64::STPDi : AArch64::STRDui;
       Size = 8;
       Align = 8;
       break;
    case RegPairInfo::FPR128:
       StrOpc = RPI.isPaired() ? AArch64::STPQi : AArch64::STRQui;
       Size = 16;
       Align = 16;
       break;
    case RegPairInfo::ZPR:
       StrOpc = AArch64::STR_ZXI;
       Size = 16;
       Align = 16;
       break;
    case RegPairInfo::PPR:
       StrOpc = AArch64::STR_PXI;
       Size = 2;
       Align = 2;
       break;
    }
    LLVM_DEBUG(dbgs() << "CSR spill: (" << printReg(Reg1, TRI);
               if (RPI.isPaired()) dbgs() << ", " << printReg(Reg2, TRI);
               dbgs() << ") -> fi#(" << RPI.FrameIdx;
               if (RPI.isPaired()) dbgs() << ", " << RPI.FrameIdx + 1;
               dbgs() << ")\n");

    assert((!NeedsWinCFI || !(Reg1 == AArch64::LR && Reg2 == AArch64::FP)) &&
           "Windows unwdinding requires a consecutive (FP,LR) pair");
    // Windows unwind codes require consecutive registers if registers are
    // paired.  Make the switch here, so that the code below will save (x,x+1)
    // and not (x+1,x).
    unsigned FrameIdxReg1 = RPI.FrameIdx;
    unsigned FrameIdxReg2 = RPI.FrameIdx + 1;
    if (NeedsWinCFI && RPI.isPaired()) {
      std::swap(Reg1, Reg2);
      std::swap(FrameIdxReg1, FrameIdxReg2);
    }
    MachineInstrBuilder MIB = BuildMI(MBB, MI, DL, TII.get(StrOpc));
    if (!MRI.isReserved(Reg1))
      MBB.addLiveIn(Reg1);
    if (RPI.isPaired()) {
      if (!MRI.isReserved(Reg2))
        MBB.addLiveIn(Reg2);
      MIB.addReg(Reg2, getPrologueDeath(MF, Reg2));
      MIB.addMemOperand(MF.getMachineMemOperand(
          MachinePointerInfo::getFixedStack(MF, FrameIdxReg2),
          MachineMemOperand::MOStore, Size, Align));
    }
    MIB.addReg(Reg1, getPrologueDeath(MF, Reg1))
        .addReg(AArch64::SP)
        .addImm(RPI.Offset) // [sp, #offset*scale],
                            // where factor*scale is implicit
        .setMIFlag(MachineInstr::FrameSetup);
    MIB.addMemOperand(MF.getMachineMemOperand(
        MachinePointerInfo::getFixedStack(MF,FrameIdxReg1),
        MachineMemOperand::MOStore, Size, Align));
    if (NeedsWinCFI)
      InsertSEH(MIB, TII, MachineInstr::FrameSetup);

    // Update the StackIDs of the SVE stack slots.
    MachineFrameInfo &MFI = MF.getFrameInfo();
    if (RPI.Type == RegPairInfo::ZPR || RPI.Type == RegPairInfo::PPR)
      MFI.setStackID(RPI.FrameIdx, TargetStackID::SVEVector);

  }
  return true;
}

bool AArch64FrameLowering::restoreCalleeSavedRegisters(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
    std::vector<CalleeSavedInfo> &CSI,
    const TargetRegisterInfo *TRI) const {
  MachineFunction &MF = *MBB.getParent();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  DebugLoc DL;
  SmallVector<RegPairInfo, 8> RegPairs;
  bool NeedsWinCFI = needsWinCFI(MF);

  if (MI != MBB.end())
    DL = MI->getDebugLoc();

  bool NeedShadowCallStackProlog = false;
  computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs,
                                 NeedShadowCallStackProlog, hasFP(MF));

  auto EmitMI = [&](const RegPairInfo &RPI) {
    unsigned Reg1 = RPI.Reg1;
    unsigned Reg2 = RPI.Reg2;

    // Issue sequence of restores for cs regs. The last restore may be converted
    // to a post-increment load later by emitEpilogue if the callee-save stack
    // area allocation can't be combined with the local stack area allocation.
    // For example:
    //    ldp     fp, lr, [sp, #32]       // addImm(+4)
    //    ldp     x20, x19, [sp, #16]     // addImm(+2)
    //    ldp     x22, x21, [sp, #0]      // addImm(+0)
    // Note: see comment in spillCalleeSavedRegisters()
    unsigned LdrOpc;
    unsigned Size, Align;
    switch (RPI.Type) {
    case RegPairInfo::GPR:
       LdrOpc = RPI.isPaired() ? AArch64::LDPXi : AArch64::LDRXui;
       Size = 8;
       Align = 8;
       break;
    case RegPairInfo::FPR64:
       LdrOpc = RPI.isPaired() ? AArch64::LDPDi : AArch64::LDRDui;
       Size = 8;
       Align = 8;
       break;
    case RegPairInfo::FPR128:
       LdrOpc = RPI.isPaired() ? AArch64::LDPQi : AArch64::LDRQui;
       Size = 16;
       Align = 16;
       break;
    case RegPairInfo::ZPR:
       LdrOpc = AArch64::LDR_ZXI;
       Size = 16;
       Align = 16;
       break;
    case RegPairInfo::PPR:
       LdrOpc = AArch64::LDR_PXI;
       Size = 2;
       Align = 2;
       break;
    }
    LLVM_DEBUG(dbgs() << "CSR restore: (" << printReg(Reg1, TRI);
               if (RPI.isPaired()) dbgs() << ", " << printReg(Reg2, TRI);
               dbgs() << ") -> fi#(" << RPI.FrameIdx;
               if (RPI.isPaired()) dbgs() << ", " << RPI.FrameIdx + 1;
               dbgs() << ")\n");

    // Windows unwind codes require consecutive registers if registers are
    // paired.  Make the switch here, so that the code below will save (x,x+1)
    // and not (x+1,x).
    unsigned FrameIdxReg1 = RPI.FrameIdx;
    unsigned FrameIdxReg2 = RPI.FrameIdx + 1;
    if (NeedsWinCFI && RPI.isPaired()) {
      std::swap(Reg1, Reg2);
      std::swap(FrameIdxReg1, FrameIdxReg2);
    }
    MachineInstrBuilder MIB = BuildMI(MBB, MI, DL, TII.get(LdrOpc));
    if (RPI.isPaired()) {
      MIB.addReg(Reg2, getDefRegState(true));
      MIB.addMemOperand(MF.getMachineMemOperand(
          MachinePointerInfo::getFixedStack(MF, FrameIdxReg2),
          MachineMemOperand::MOLoad, Size, Align));
    }
    MIB.addReg(Reg1, getDefRegState(true))
        .addReg(AArch64::SP)
        .addImm(RPI.Offset) // [sp, #offset*scale]
                            // where factor*scale is implicit
        .setMIFlag(MachineInstr::FrameDestroy);
    MIB.addMemOperand(MF.getMachineMemOperand(
        MachinePointerInfo::getFixedStack(MF, FrameIdxReg1),
        MachineMemOperand::MOLoad, Size, Align));
    if (NeedsWinCFI)
      InsertSEH(MIB, TII, MachineInstr::FrameDestroy);
  };

  // SVE objects are always restored in reverse order.
  for (const RegPairInfo &RPI : reverse(RegPairs))
    if (RPI.isScalable())
      EmitMI(RPI);

  if (ReverseCSRRestoreSeq) {
    for (const RegPairInfo &RPI : reverse(RegPairs))
      if (!RPI.isScalable())
        EmitMI(RPI);
  } else
    for (const RegPairInfo &RPI : RegPairs)
      if (!RPI.isScalable())
        EmitMI(RPI);

  if (NeedShadowCallStackProlog) {
    // Shadow call stack epilog: ldr x30, [x18, #-8]!
    BuildMI(MBB, MI, DL, TII.get(AArch64::LDRXpre))
        .addReg(AArch64::X18, RegState::Define)
        .addReg(AArch64::LR, RegState::Define)
        .addReg(AArch64::X18)
        .addImm(-8)
        .setMIFlag(MachineInstr::FrameDestroy);
  }

  return true;
}

void AArch64FrameLowering::determineCalleeSaves(MachineFunction &MF,
                                                BitVector &SavedRegs,
                                                RegScavenger *RS) const {
  // All calls are tail calls in GHC calling conv, and functions have no
  // prologue/epilogue.
  if (MF.getFunction().getCallingConv() == CallingConv::GHC)
    return;

  TargetFrameLowering::determineCalleeSaves(MF, SavedRegs, RS);
  const AArch64RegisterInfo *RegInfo = static_cast<const AArch64RegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());
  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  unsigned UnspilledCSGPR = AArch64::NoRegister;
  unsigned UnspilledCSGPRPaired = AArch64::NoRegister;

  MachineFrameInfo &MFI = MF.getFrameInfo();
  const MCPhysReg *CSRegs = MF.getRegInfo().getCalleeSavedRegs();

  unsigned BasePointerReg = RegInfo->hasBasePointer(MF)
                                ? RegInfo->getBaseRegister()
                                : (unsigned)AArch64::NoRegister;

  unsigned ExtraCSSpill = 0;
  // Figure out which callee-saved registers to save/restore.
  for (unsigned i = 0; CSRegs[i]; ++i) {
    const unsigned Reg = CSRegs[i];

    // Add the base pointer register to SavedRegs if it is callee-save.
    if (Reg == BasePointerReg)
      SavedRegs.set(Reg);

    bool RegUsed = SavedRegs.test(Reg);
    unsigned PairedReg = AArch64::NoRegister;
    if (AArch64::GPR64RegClass.contains(Reg) ||
        AArch64::FPR64RegClass.contains(Reg) ||
        AArch64::FPR128RegClass.contains(Reg))
      PairedReg = CSRegs[i ^ 1];

    if (!RegUsed) {
      if (AArch64::GPR64RegClass.contains(Reg) &&
          !RegInfo->isReservedReg(MF, Reg)) {
        UnspilledCSGPR = Reg;
        UnspilledCSGPRPaired = PairedReg;
      }
      continue;
    }

    // MachO's compact unwind format relies on all registers being stored in
    // pairs.
    // FIXME: the usual format is actually better if unwinding isn't needed.
    if (produceCompactUnwindFrame(MF) && PairedReg != AArch64::NoRegister &&
        !SavedRegs.test(PairedReg)) {
      SavedRegs.set(PairedReg);
      if (AArch64::GPR64RegClass.contains(PairedReg) &&
          !RegInfo->isReservedReg(MF, PairedReg))
        ExtraCSSpill = PairedReg;
    }
  }

  // Calculates the callee saved stack size.
  unsigned CSStackSize = 0;
  unsigned SVECSStackSize = 0;
  const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();
  const MachineRegisterInfo &MRI = MF.getRegInfo();
  for (unsigned Reg : SavedRegs.set_bits()) {
    auto RegSize = TRI->getRegSizeInBits(Reg, MRI) / 8;
    if (AArch64::PPRRegClass.contains(Reg) ||
        AArch64::ZPRRegClass.contains(Reg))
      SVECSStackSize += RegSize;
    else
      CSStackSize += RegSize;
  }

  // Save number of saved regs, so we can easily update CSStackSize later.
  unsigned NumSavedRegs = SavedRegs.count();

  // The frame record needs to be created by saving the appropriate registers
  uint64_t EstimatedStackSize = MFI.estimateStackSize(MF);
  if (hasFP(MF) ||
      windowsRequiresStackProbe(MF, EstimatedStackSize + CSStackSize + 16)) {
    SavedRegs.set(AArch64::FP);
    SavedRegs.set(AArch64::LR);
  }

  LLVM_DEBUG(dbgs() << "*** determineCalleeSaves\nSaved CSRs:";
             for (unsigned Reg
                  : SavedRegs.set_bits()) dbgs()
             << ' ' << printReg(Reg, RegInfo);
             dbgs() << "\n";);

  // If any callee-saved registers are used, the frame cannot be eliminated.
  int64_t SVEStackSize =
      alignTo(SVECSStackSize + estimateSVEStackObjectOffsets(MFI), 16);
  bool CanEliminateFrame = (SavedRegs.count() == 0) && !SVEStackSize;

  // The CSR spill slots have not been allocated yet, so estimateStackSize
  // won't include them.
  unsigned EstimatedStackSizeLimit = estimateRSStackSizeLimit(MF);

  // Conservatively always assume BigStack when there are SVE spills.
  bool BigStack = SVEStackSize ||
                  (EstimatedStackSize + CSStackSize) > EstimatedStackSizeLimit;
  if (BigStack || !CanEliminateFrame || RegInfo->cannotEliminateFrame(MF))
    AFI->setHasStackFrame(true);

  // Estimate if we might need to scavenge a register at some point in order
  // to materialize a stack offset. If so, either spill one additional
  // callee-saved register or reserve a special spill slot to facilitate
  // register scavenging. If we already spilled an extra callee-saved register
  // above to keep the number of spills even, we don't need to do anything else
  // here.
  if (BigStack) {
    if (!ExtraCSSpill && UnspilledCSGPR != AArch64::NoRegister) {
      LLVM_DEBUG(dbgs() << "Spilling " << printReg(UnspilledCSGPR, RegInfo)
                        << " to get a scratch register.\n");
      SavedRegs.set(UnspilledCSGPR);
      // MachO's compact unwind format relies on all registers being stored in
      // pairs, so if we need to spill one extra for BigStack, then we need to
      // store the pair.
      if (produceCompactUnwindFrame(MF))
        SavedRegs.set(UnspilledCSGPRPaired);
      ExtraCSSpill = UnspilledCSGPR;
    }

    // If we didn't find an extra callee-saved register to spill, create
    // an emergency spill slot.
    if (!ExtraCSSpill || MF.getRegInfo().isPhysRegUsed(ExtraCSSpill)) {
      const TargetRegisterInfo *TRI = MF.getSubtarget().getRegisterInfo();
      const TargetRegisterClass &RC = AArch64::GPR64RegClass;
      unsigned Size = TRI->getSpillSize(RC);
      unsigned Align = TRI->getSpillAlignment(RC);
      int FI = MFI.CreateStackObject(Size, Align, false);
      RS->addScavengingFrameIndex(FI);
      LLVM_DEBUG(dbgs() << "No available CS registers, allocated fi#" << FI
                        << " as the emergency spill slot.\n");
    }
  }

  // Adding the size of additional 64bit GPR saves.
  CSStackSize += 8 * (SavedRegs.count() - NumSavedRegs);
  uint64_t AlignedCSStackSize = alignTo(CSStackSize, 16);
  LLVM_DEBUG(dbgs() << "Estimated stack frame size: "
               << EstimatedStackSize + AlignedCSStackSize
               << " bytes.\n");

  assert((!MFI.isCalleeSavedInfoValid() ||
          AFI->getCalleeSavedStackSize() == AlignedCSStackSize) &&
         "Should not invalidate callee saved info");

  // Round up to register pair alignment to avoid additional SP adjustment
  // instructions.
  AFI->setCalleeSavedStackSize(AlignedCSStackSize);
  AFI->setCalleeSaveStackHasFreeSpace(AlignedCSStackSize != CSStackSize);
  AFI->setSVECalleeSavedStackSize(alignTo(SVECSStackSize, 16));
}

bool AArch64FrameLowering::enableStackSlotScavenging(
    const MachineFunction &MF) const {
  const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  return AFI->hasCalleeSaveStackFreeSpace();
}

/// returns true if there are any SVE callee saves.
static bool getSVECalleeSaveSlotRange(const MachineFrameInfo &MFI,
                                      int &Min, int &Max) {
  Min = std::numeric_limits<int>::max();
  Max = std::numeric_limits<int>::min();

  if (!MFI.isCalleeSavedInfoValid())
    return false;

  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();
  for (auto &CS : CSI) {
    if (AArch64::ZPRRegClass.contains(CS.getReg()) ||
        AArch64::PPRRegClass.contains(CS.getReg())) {
      assert((Max == std::numeric_limits<int>::min() ||
              Max + 1 == CS.getFrameIdx()) &&
             "SVE CalleeSaves are not consecutive");

      Min = std::min(Min, CS.getFrameIdx());
      Max = std::max(Max, CS.getFrameIdx());
    }
  }
  return Min != std::numeric_limits<int>::max();
}

// Process all the SVE stack objects and determine offsets for each
// object. If AssignOffsets is true, the offsets get assigned.
// Fills in the first and last callee-saved frame indices into
// Min/MaxCSFrameIndex, respectively.
// Returns the size of the stack.
static int64_t determineSVEStackObjectOffsets(MachineFrameInfo &MFI,
                                              int &MinCSFrameIndex,
                                              int &MaxCSFrameIndex,
                                              bool AssignOffsets) {
  // First process all fixed stack objects.
  int64_t Offset = 0;
  for (int I = MFI.getObjectIndexBegin(); I != 0; ++I)
    if (MFI.getStackID(I) == TargetStackID::SVEVector) {
      int64_t FixedOffset = -MFI.getObjectOffset(I);
      if (FixedOffset > Offset)
        Offset = FixedOffset;
    }

  auto Assign = [&MFI](int FI, int64_t Offset) {
    LLVM_DEBUG(dbgs() << "alloc FI(" << FI << ") at SP[" << Offset << "]\n");
    MFI.setObjectOffset(FI, Offset);
  };

  // Then process all callee saved slots.
  if (getSVECalleeSaveSlotRange(MFI, MinCSFrameIndex, MaxCSFrameIndex)) {
    // Make sure to align the last callee save slot.
    MFI.setObjectAlignment(MaxCSFrameIndex, 16U);

    // Assign offsets to the callee save slots.
    for (int I = MinCSFrameIndex; I <= MaxCSFrameIndex; ++I) {
      Offset += MFI.getObjectSize(I);
      Offset = alignTo(Offset, MFI.getObjectAlignment(I));
      if (AssignOffsets)
        Assign(I, -Offset);
    }
  }

  // Create a buffer of SVE objects to allocate and sort it.
  SmallVector<int, 8> ObjectsToAllocate;
  for (int I = 0, E = MFI.getObjectIndexEnd(); I != E; ++I) {
    unsigned StackID = MFI.getStackID(I);
    if (StackID != TargetStackID::SVEVector)
      continue;
    if (MaxCSFrameIndex >= I && I >= MinCSFrameIndex)
      continue;
    if (MFI.isDeadObjectIndex(I))
      continue;

    ObjectsToAllocate.push_back(I);
  }

  // Allocate all SVE locals and spills
  for (unsigned FI : ObjectsToAllocate) {
    unsigned Align = MFI.getObjectAlignment(FI);
    // FIXME: Given that the length of SVE vectors is not necessarily a power of
    // two, we'd need to align every object dynamically at runtime if the
    // alignment is larger than 16. This is not yet supported.
    if (Align > 16)
      report_fatal_error(
          "Alignment of scalable vectors > 16 bytes is not yet supported");

    Offset = alignTo(Offset + MFI.getObjectSize(FI), Align);
    if (AssignOffsets)
      Assign(FI, -Offset);
  }

  return Offset;
}

int64_t AArch64FrameLowering::estimateSVEStackObjectOffsets(
    MachineFrameInfo &MFI) const {
  int MinCSFrameIndex, MaxCSFrameIndex;
  return determineSVEStackObjectOffsets(MFI, MinCSFrameIndex, MaxCSFrameIndex, false);
}

int64_t AArch64FrameLowering::assignSVEStackObjectOffsets(
    MachineFrameInfo &MFI, int &MinCSFrameIndex, int &MaxCSFrameIndex) const {
  return determineSVEStackObjectOffsets(MFI, MinCSFrameIndex, MaxCSFrameIndex,
                                        true);
}

void AArch64FrameLowering::processFunctionBeforeFrameFinalized(
    MachineFunction &MF, RegScavenger *RS) const {
  MachineFrameInfo &MFI = MF.getFrameInfo();

  assert(getStackGrowthDirection() == TargetFrameLowering::StackGrowsDown &&
         "Upwards growing stack unsupported");

  int MinCSFrameIndex, MaxCSFrameIndex;
  int64_t SVEStackSize =
      assignSVEStackObjectOffsets(MFI, MinCSFrameIndex, MaxCSFrameIndex);

  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
  AFI->setStackSizeSVE(alignTo(SVEStackSize, 16U));
  AFI->setMinMaxSVECSFrameIndex(MinCSFrameIndex, MaxCSFrameIndex);

  // If this function isn't doing Win64-style C++ EH, we don't need to do
  // anything.
  if (!MF.hasEHFunclets())
    return;
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  WinEHFuncInfo &EHInfo = *MF.getWinEHFuncInfo();

  MachineBasicBlock &MBB = MF.front();
  auto MBBI = MBB.begin();
  while (MBBI != MBB.end() && MBBI->getFlag(MachineInstr::FrameSetup))
    ++MBBI;

  // Create an UnwindHelp object.
  // The UnwindHelp object is allocated at the start of the fixed object area
  int64_t FixedObject =
      getFixedObjectSize(MF, AFI, /*IsWin64*/ true, /*IsFunclet*/ false);
  int UnwindHelpFI = MFI.CreateFixedObject(/*Size*/ 8,
                                           /*SPOffset*/ -FixedObject,
                                           /*IsImmutable=*/false);
  EHInfo.UnwindHelpFrameIdx = UnwindHelpFI;

  // We need to store -2 into the UnwindHelp object at the start of the
  // function.
  DebugLoc DL;
  RS->enterBasicBlockEnd(MBB);
  RS->backward(std::prev(MBBI));
  unsigned DstReg = RS->FindUnusedReg(&AArch64::GPR64commonRegClass);
  assert(DstReg && "There must be a free register after frame setup");
  BuildMI(MBB, MBBI, DL, TII.get(AArch64::MOVi64imm), DstReg).addImm(-2);
  BuildMI(MBB, MBBI, DL, TII.get(AArch64::STURXi))
      .addReg(DstReg, getKillRegState(true))
      .addFrameIndex(UnwindHelpFI)
      .addImm(0);
}

/// For Win64 AArch64 EH, the offset to the Unwind object is from the SP before
/// the update.  This is easily retrieved as it is exactly the offset that is set
/// in processFunctionBeforeFrameFinalized.
int AArch64FrameLowering::getFrameIndexReferencePreferSP(
    const MachineFunction &MF, int FI, unsigned &FrameReg,
    bool IgnoreSPUpdates) const {
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  if (IgnoreSPUpdates) {
    LLVM_DEBUG(dbgs() << "Offset from the SP for " << FI << " is "
                      << MFI.getObjectOffset(FI) << "\n");
    FrameReg = AArch64::SP;
    return MFI.getObjectOffset(FI);
  }

  return getFrameIndexReference(MF, FI, FrameReg);
}

/// The parent frame offset (aka dispFrame) is only used on X86_64 to retrieve
/// the parent's frame pointer
unsigned AArch64FrameLowering::getWinEHParentFrameOffset(
    const MachineFunction &MF) const {
  return 0;
}

/// Funclets only need to account for space for the callee saved registers,
/// as the locals are accounted for in the parent's stack frame.
unsigned AArch64FrameLowering::getWinEHFuncletFrameSize(
    const MachineFunction &MF) const {
  // This is the size of the pushed CSRs.
  unsigned CSSize =
      MF.getInfo<AArch64FunctionInfo>()->getCalleeSavedStackSize();
  // This is the amount of stack a funclet needs to allocate.
  return alignTo(CSSize + MF.getFrameInfo().getMaxCallFrameSize(),
                 getStackAlignment());
}