Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
//===- MemorySSA.cpp - Memory SSA Builder ---------------------------------===//
//
// 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 implements the MemorySSA class.
//
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/MemorySSA.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseMapInfo.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/DepthFirstIterator.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/iterator.h"
#include "llvm/ADT/iterator_range.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/IteratedDominanceFrontier.h"
#include "llvm/Analysis/MemoryLocation.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/IR/AssemblyAnnotationWriter.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/Use.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/AtomicOrdering.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cassert>
#include <cstdlib>
#include <iterator>
#include <memory>
#include <utility>

using namespace llvm;

#define DEBUG_TYPE "memoryssa"

INITIALIZE_PASS_BEGIN(MemorySSAWrapperPass, "memoryssa", "Memory SSA", false,
                      true)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
INITIALIZE_PASS_END(MemorySSAWrapperPass, "memoryssa", "Memory SSA", false,
                    true)

INITIALIZE_PASS_BEGIN(MemorySSAPrinterLegacyPass, "print-memoryssa",
                      "Memory SSA Printer", false, false)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
INITIALIZE_PASS_END(MemorySSAPrinterLegacyPass, "print-memoryssa",
                    "Memory SSA Printer", false, false)

static cl::opt<unsigned> MaxCheckLimit(
    "memssa-check-limit", cl::Hidden, cl::init(100),
    cl::desc("The maximum number of stores/phis MemorySSA"
             "will consider trying to walk past (default = 100)"));

// Always verify MemorySSA if expensive checking is enabled.
#ifdef EXPENSIVE_CHECKS
bool llvm::VerifyMemorySSA = true;
#else
bool llvm::VerifyMemorySSA = false;
#endif
/// Enables memory ssa as a dependency for loop passes in legacy pass manager.
cl::opt<bool> llvm::EnableMSSALoopDependency(
    "enable-mssa-loop-dependency", cl::Hidden, cl::init(true),
    cl::desc("Enable MemorySSA dependency for loop pass manager"));

static cl::opt<bool, true>
    VerifyMemorySSAX("verify-memoryssa", cl::location(VerifyMemorySSA),
                     cl::Hidden, cl::desc("Enable verification of MemorySSA."));

namespace llvm {

/// An assembly annotator class to print Memory SSA information in
/// comments.
class MemorySSAAnnotatedWriter : public AssemblyAnnotationWriter {
  friend class MemorySSA;

  const MemorySSA *MSSA;

public:
  MemorySSAAnnotatedWriter(const MemorySSA *M) : MSSA(M) {}

  void emitBasicBlockStartAnnot(const BasicBlock *BB,
                                formatted_raw_ostream &OS) override {
    if (MemoryAccess *MA = MSSA->getMemoryAccess(BB))
      OS << "; " << *MA << "\n";
  }

  void emitInstructionAnnot(const Instruction *I,
                            formatted_raw_ostream &OS) override {
    if (MemoryAccess *MA = MSSA->getMemoryAccess(I))
      OS << "; " << *MA << "\n";
  }
};

} // end namespace llvm

namespace {

/// Our current alias analysis API differentiates heavily between calls and
/// non-calls, and functions called on one usually assert on the other.
/// This class encapsulates the distinction to simplify other code that wants
/// "Memory affecting instructions and related data" to use as a key.
/// For example, this class is used as a densemap key in the use optimizer.
class MemoryLocOrCall {
public:
  bool IsCall = false;

  MemoryLocOrCall(MemoryUseOrDef *MUD)
      : MemoryLocOrCall(MUD->getMemoryInst()) {}
  MemoryLocOrCall(const MemoryUseOrDef *MUD)
      : MemoryLocOrCall(MUD->getMemoryInst()) {}

  MemoryLocOrCall(Instruction *Inst) {
    if (auto *C = dyn_cast<CallBase>(Inst)) {
      IsCall = true;
      Call = C;
    } else {
      IsCall = false;
      // There is no such thing as a memorylocation for a fence inst, and it is
      // unique in that regard.
      if (!isa<FenceInst>(Inst))
        Loc = MemoryLocation::get(Inst);
    }
  }

  explicit MemoryLocOrCall(const MemoryLocation &Loc) : Loc(Loc) {}

  const CallBase *getCall() const {
    assert(IsCall);
    return Call;
  }

  MemoryLocation getLoc() const {
    assert(!IsCall);
    return Loc;
  }

  bool operator==(const MemoryLocOrCall &Other) const {
    if (IsCall != Other.IsCall)
      return false;

    if (!IsCall)
      return Loc == Other.Loc;

    if (Call->getCalledOperand() != Other.Call->getCalledOperand())
      return false;

    return Call->arg_size() == Other.Call->arg_size() &&
           std::equal(Call->arg_begin(), Call->arg_end(),
                      Other.Call->arg_begin());
  }

private:
  union {
    const CallBase *Call;
    MemoryLocation Loc;
  };
};

} // end anonymous namespace

namespace llvm {

template <> struct DenseMapInfo<MemoryLocOrCall> {
  static inline MemoryLocOrCall getEmptyKey() {
    return MemoryLocOrCall(DenseMapInfo<MemoryLocation>::getEmptyKey());
  }

  static inline MemoryLocOrCall getTombstoneKey() {
    return MemoryLocOrCall(DenseMapInfo<MemoryLocation>::getTombstoneKey());
  }

  static unsigned getHashValue(const MemoryLocOrCall &MLOC) {
    if (!MLOC.IsCall)
      return hash_combine(
          MLOC.IsCall,
          DenseMapInfo<MemoryLocation>::getHashValue(MLOC.getLoc()));

    hash_code hash =
        hash_combine(MLOC.IsCall, DenseMapInfo<const Value *>::getHashValue(
                                      MLOC.getCall()->getCalledOperand()));

    for (const Value *Arg : MLOC.getCall()->args())
      hash = hash_combine(hash, DenseMapInfo<const Value *>::getHashValue(Arg));
    return hash;
  }

  static bool isEqual(const MemoryLocOrCall &LHS, const MemoryLocOrCall &RHS) {
    return LHS == RHS;
  }
};

} // end namespace llvm

/// This does one-way checks to see if Use could theoretically be hoisted above
/// MayClobber. This will not check the other way around.
///
/// This assumes that, for the purposes of MemorySSA, Use comes directly after
/// MayClobber, with no potentially clobbering operations in between them.
/// (Where potentially clobbering ops are memory barriers, aliased stores, etc.)
static bool areLoadsReorderable(const LoadInst *Use,
                                const LoadInst *MayClobber) {
  bool VolatileUse = Use->isVolatile();
  bool VolatileClobber = MayClobber->isVolatile();
  // Volatile operations may never be reordered with other volatile operations.
  if (VolatileUse && VolatileClobber)
    return false;
  // Otherwise, volatile doesn't matter here. From the language reference:
  // 'optimizers may change the order of volatile operations relative to
  // non-volatile operations.'"

  // If a load is seq_cst, it cannot be moved above other loads. If its ordering
  // is weaker, it can be moved above other loads. We just need to be sure that
  // MayClobber isn't an acquire load, because loads can't be moved above
  // acquire loads.
  //
  // Note that this explicitly *does* allow the free reordering of monotonic (or
  // weaker) loads of the same address.
  bool SeqCstUse = Use->getOrdering() == AtomicOrdering::SequentiallyConsistent;
  bool MayClobberIsAcquire = isAtLeastOrStrongerThan(MayClobber->getOrdering(),
                                                     AtomicOrdering::Acquire);
  return !(SeqCstUse || MayClobberIsAcquire);
}

namespace {

struct ClobberAlias {
  bool IsClobber;
  Optional<AliasResult> AR;
};

} // end anonymous namespace

// Return a pair of {IsClobber (bool), AR (AliasResult)}. It relies on AR being
// ignored if IsClobber = false.
template <typename AliasAnalysisType>
static ClobberAlias
instructionClobbersQuery(const MemoryDef *MD, const MemoryLocation &UseLoc,
                         const Instruction *UseInst, AliasAnalysisType &AA) {
  Instruction *DefInst = MD->getMemoryInst();
  assert(DefInst && "Defining instruction not actually an instruction");
  const auto *UseCall = dyn_cast<CallBase>(UseInst);
  Optional<AliasResult> AR;

  if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(DefInst)) {
    // These intrinsics will show up as affecting memory, but they are just
    // markers, mostly.
    //
    // FIXME: We probably don't actually want MemorySSA to model these at all
    // (including creating MemoryAccesses for them): we just end up inventing
    // clobbers where they don't really exist at all. Please see D43269 for
    // context.
    switch (II->getIntrinsicID()) {
    case Intrinsic::lifetime_start:
      if (UseCall)
        return {false, NoAlias};
      AR = AA.alias(MemoryLocation(II->getArgOperand(1)), UseLoc);
      return {AR != NoAlias, AR};
    case Intrinsic::lifetime_end:
    case Intrinsic::invariant_start:
    case Intrinsic::invariant_end:
    case Intrinsic::assume:
      return {false, NoAlias};
    case Intrinsic::dbg_addr:
    case Intrinsic::dbg_declare:
    case Intrinsic::dbg_label:
    case Intrinsic::dbg_value:
      llvm_unreachable("debuginfo shouldn't have associated defs!");
    default:
      break;
    }
  }

  if (UseCall) {
    ModRefInfo I = AA.getModRefInfo(DefInst, UseCall);
    AR = isMustSet(I) ? MustAlias : MayAlias;
    return {isModOrRefSet(I), AR};
  }

  if (auto *DefLoad = dyn_cast<LoadInst>(DefInst))
    if (auto *UseLoad = dyn_cast<LoadInst>(UseInst))
      return {!areLoadsReorderable(UseLoad, DefLoad), MayAlias};

  ModRefInfo I = AA.getModRefInfo(DefInst, UseLoc);
  AR = isMustSet(I) ? MustAlias : MayAlias;
  return {isModSet(I), AR};
}

template <typename AliasAnalysisType>
static ClobberAlias instructionClobbersQuery(MemoryDef *MD,
                                             const MemoryUseOrDef *MU,
                                             const MemoryLocOrCall &UseMLOC,
                                             AliasAnalysisType &AA) {
  // FIXME: This is a temporary hack to allow a single instructionClobbersQuery
  // to exist while MemoryLocOrCall is pushed through places.
  if (UseMLOC.IsCall)
    return instructionClobbersQuery(MD, MemoryLocation(), MU->getMemoryInst(),
                                    AA);
  return instructionClobbersQuery(MD, UseMLOC.getLoc(), MU->getMemoryInst(),
                                  AA);
}

// Return true when MD may alias MU, return false otherwise.
bool MemorySSAUtil::defClobbersUseOrDef(MemoryDef *MD, const MemoryUseOrDef *MU,
                                        AliasAnalysis &AA) {
  return instructionClobbersQuery(MD, MU, MemoryLocOrCall(MU), AA).IsClobber;
}

namespace {

struct UpwardsMemoryQuery {
  // True if our original query started off as a call
  bool IsCall = false;
  // The pointer location we started the query with. This will be empty if
  // IsCall is true.
  MemoryLocation StartingLoc;
  // This is the instruction we were querying about.
  const Instruction *Inst = nullptr;
  // The MemoryAccess we actually got called with, used to test local domination
  const MemoryAccess *OriginalAccess = nullptr;
  Optional<AliasResult> AR = MayAlias;
  bool SkipSelfAccess = false;

  UpwardsMemoryQuery() = default;

  UpwardsMemoryQuery(const Instruction *Inst, const MemoryAccess *Access)
      : IsCall(isa<CallBase>(Inst)), Inst(Inst), OriginalAccess(Access) {
    if (!IsCall)
      StartingLoc = MemoryLocation::get(Inst);
  }
};

} // end anonymous namespace

static bool lifetimeEndsAt(MemoryDef *MD, const MemoryLocation &Loc,
                           BatchAAResults &AA) {
  Instruction *Inst = MD->getMemoryInst();
  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst)) {
    switch (II->getIntrinsicID()) {
    case Intrinsic::lifetime_end:
      return AA.alias(MemoryLocation(II->getArgOperand(1)), Loc) == MustAlias;
    default:
      return false;
    }
  }
  return false;
}

template <typename AliasAnalysisType>
static bool isUseTriviallyOptimizableToLiveOnEntry(AliasAnalysisType &AA,
                                                   const Instruction *I) {
  // If the memory can't be changed, then loads of the memory can't be
  // clobbered.
  return isa<LoadInst>(I) && (I->hasMetadata(LLVMContext::MD_invariant_load) ||
                              AA.pointsToConstantMemory(MemoryLocation(
                                  cast<LoadInst>(I)->getPointerOperand())));
}

/// Verifies that `Start` is clobbered by `ClobberAt`, and that nothing
/// inbetween `Start` and `ClobberAt` can clobbers `Start`.
///
/// This is meant to be as simple and self-contained as possible. Because it
/// uses no cache, etc., it can be relatively expensive.
///
/// \param Start     The MemoryAccess that we want to walk from.
/// \param ClobberAt A clobber for Start.
/// \param StartLoc  The MemoryLocation for Start.
/// \param MSSA      The MemorySSA instance that Start and ClobberAt belong to.
/// \param Query     The UpwardsMemoryQuery we used for our search.
/// \param AA        The AliasAnalysis we used for our search.
/// \param AllowImpreciseClobber Always false, unless we do relaxed verify.

template <typename AliasAnalysisType>
LLVM_ATTRIBUTE_UNUSED static void
checkClobberSanity(const MemoryAccess *Start, MemoryAccess *ClobberAt,
                   const MemoryLocation &StartLoc, const MemorySSA &MSSA,
                   const UpwardsMemoryQuery &Query, AliasAnalysisType &AA,
                   bool AllowImpreciseClobber = false) {
  assert(MSSA.dominates(ClobberAt, Start) && "Clobber doesn't dominate start?");

  if (MSSA.isLiveOnEntryDef(Start)) {
    assert(MSSA.isLiveOnEntryDef(ClobberAt) &&
           "liveOnEntry must clobber itself");
    return;
  }

  bool FoundClobber = false;
  DenseSet<ConstMemoryAccessPair> VisitedPhis;
  SmallVector<ConstMemoryAccessPair, 8> Worklist;
  Worklist.emplace_back(Start, StartLoc);
  // Walk all paths from Start to ClobberAt, while looking for clobbers. If one
  // is found, complain.
  while (!Worklist.empty()) {
    auto MAP = Worklist.pop_back_val();
    // All we care about is that nothing from Start to ClobberAt clobbers Start.
    // We learn nothing from revisiting nodes.
    if (!VisitedPhis.insert(MAP).second)
      continue;

    for (const auto *MA : def_chain(MAP.first)) {
      if (MA == ClobberAt) {
        if (const auto *MD = dyn_cast<MemoryDef>(MA)) {
          // instructionClobbersQuery isn't essentially free, so don't use `|=`,
          // since it won't let us short-circuit.
          //
          // Also, note that this can't be hoisted out of the `Worklist` loop,
          // since MD may only act as a clobber for 1 of N MemoryLocations.
          FoundClobber = FoundClobber || MSSA.isLiveOnEntryDef(MD);
          if (!FoundClobber) {
            ClobberAlias CA =
                instructionClobbersQuery(MD, MAP.second, Query.Inst, AA);
            if (CA.IsClobber) {
              FoundClobber = true;
              // Not used: CA.AR;
            }
          }
        }
        break;
      }

      // We should never hit liveOnEntry, unless it's the clobber.
      assert(!MSSA.isLiveOnEntryDef(MA) && "Hit liveOnEntry before clobber?");

      if (const auto *MD = dyn_cast<MemoryDef>(MA)) {
        // If Start is a Def, skip self.
        if (MD == Start)
          continue;

        assert(!instructionClobbersQuery(MD, MAP.second, Query.Inst, AA)
                    .IsClobber &&
               "Found clobber before reaching ClobberAt!");
        continue;
      }

      if (const auto *MU = dyn_cast<MemoryUse>(MA)) {
        (void)MU;
        assert (MU == Start &&
                "Can only find use in def chain if Start is a use");
        continue;
      }

      assert(isa<MemoryPhi>(MA));
      Worklist.append(
          upward_defs_begin({const_cast<MemoryAccess *>(MA), MAP.second},
                            MSSA.getDomTree()),
          upward_defs_end());
    }
  }

  // If the verify is done following an optimization, it's possible that
  // ClobberAt was a conservative clobbering, that we can now infer is not a
  // true clobbering access. Don't fail the verify if that's the case.
  // We do have accesses that claim they're optimized, but could be optimized
  // further. Updating all these can be expensive, so allow it for now (FIXME).
  if (AllowImpreciseClobber)
    return;

  // If ClobberAt is a MemoryPhi, we can assume something above it acted as a
  // clobber. Otherwise, `ClobberAt` should've acted as a clobber at some point.
  assert((isa<MemoryPhi>(ClobberAt) || FoundClobber) &&
         "ClobberAt never acted as a clobber");
}

namespace {

/// Our algorithm for walking (and trying to optimize) clobbers, all wrapped up
/// in one class.
template <class AliasAnalysisType> class ClobberWalker {
  /// Save a few bytes by using unsigned instead of size_t.
  using ListIndex = unsigned;

  /// Represents a span of contiguous MemoryDefs, potentially ending in a
  /// MemoryPhi.
  struct DefPath {
    MemoryLocation Loc;
    // Note that, because we always walk in reverse, Last will always dominate
    // First. Also note that First and Last are inclusive.
    MemoryAccess *First;
    MemoryAccess *Last;
    Optional<ListIndex> Previous;

    DefPath(const MemoryLocation &Loc, MemoryAccess *First, MemoryAccess *Last,
            Optional<ListIndex> Previous)
        : Loc(Loc), First(First), Last(Last), Previous(Previous) {}

    DefPath(const MemoryLocation &Loc, MemoryAccess *Init,
            Optional<ListIndex> Previous)
        : DefPath(Loc, Init, Init, Previous) {}
  };

  const MemorySSA &MSSA;
  AliasAnalysisType &AA;
  DominatorTree &DT;
  UpwardsMemoryQuery *Query;
  unsigned *UpwardWalkLimit;

  // Phi optimization bookkeeping
  SmallVector<DefPath, 32> Paths;
  DenseSet<ConstMemoryAccessPair> VisitedPhis;

  /// Find the nearest def or phi that `From` can legally be optimized to.
  const MemoryAccess *getWalkTarget(const MemoryPhi *From) const {
    assert(From->getNumOperands() && "Phi with no operands?");

    BasicBlock *BB = From->getBlock();
    MemoryAccess *Result = MSSA.getLiveOnEntryDef();
    DomTreeNode *Node = DT.getNode(BB);
    while ((Node = Node->getIDom())) {
      auto *Defs = MSSA.getBlockDefs(Node->getBlock());
      if (Defs)
        return &*Defs->rbegin();
    }
    return Result;
  }

  /// Result of calling walkToPhiOrClobber.
  struct UpwardsWalkResult {
    /// The "Result" of the walk. Either a clobber, the last thing we walked, or
    /// both. Include alias info when clobber found.
    MemoryAccess *Result;
    bool IsKnownClobber;
    Optional<AliasResult> AR;
  };

  /// Walk to the next Phi or Clobber in the def chain starting at Desc.Last.
  /// This will update Desc.Last as it walks. It will (optionally) also stop at
  /// StopAt.
  ///
  /// This does not test for whether StopAt is a clobber
  UpwardsWalkResult
  walkToPhiOrClobber(DefPath &Desc, const MemoryAccess *StopAt = nullptr,
                     const MemoryAccess *SkipStopAt = nullptr) const {
    assert(!isa<MemoryUse>(Desc.Last) && "Uses don't exist in my world");
    assert(UpwardWalkLimit && "Need a valid walk limit");
    bool LimitAlreadyReached = false;
    // (*UpwardWalkLimit) may be 0 here, due to the loop in tryOptimizePhi. Set
    // it to 1. This will not do any alias() calls. It either returns in the
    // first iteration in the loop below, or is set back to 0 if all def chains
    // are free of MemoryDefs.
    if (!*UpwardWalkLimit) {
      *UpwardWalkLimit = 1;
      LimitAlreadyReached = true;
    }

    for (MemoryAccess *Current : def_chain(Desc.Last)) {
      Desc.Last = Current;
      if (Current == StopAt || Current == SkipStopAt)
        return {Current, false, MayAlias};

      if (auto *MD = dyn_cast<MemoryDef>(Current)) {
        if (MSSA.isLiveOnEntryDef(MD))
          return {MD, true, MustAlias};

        if (!--*UpwardWalkLimit)
          return {Current, true, MayAlias};

        ClobberAlias CA =
            instructionClobbersQuery(MD, Desc.Loc, Query->Inst, AA);
        if (CA.IsClobber)
          return {MD, true, CA.AR};
      }
    }

    if (LimitAlreadyReached)
      *UpwardWalkLimit = 0;

    assert(isa<MemoryPhi>(Desc.Last) &&
           "Ended at a non-clobber that's not a phi?");
    return {Desc.Last, false, MayAlias};
  }

  void addSearches(MemoryPhi *Phi, SmallVectorImpl<ListIndex> &PausedSearches,
                   ListIndex PriorNode) {
    auto UpwardDefs = make_range(
        upward_defs_begin({Phi, Paths[PriorNode].Loc}, DT), upward_defs_end());
    for (const MemoryAccessPair &P : UpwardDefs) {
      PausedSearches.push_back(Paths.size());
      Paths.emplace_back(P.second, P.first, PriorNode);
    }
  }

  /// Represents a search that terminated after finding a clobber. This clobber
  /// may or may not be present in the path of defs from LastNode..SearchStart,
  /// since it may have been retrieved from cache.
  struct TerminatedPath {
    MemoryAccess *Clobber;
    ListIndex LastNode;
  };

  /// Get an access that keeps us from optimizing to the given phi.
  ///
  /// PausedSearches is an array of indices into the Paths array. Its incoming
  /// value is the indices of searches that stopped at the last phi optimization
  /// target. It's left in an unspecified state.
  ///
  /// If this returns None, NewPaused is a vector of searches that terminated
  /// at StopWhere. Otherwise, NewPaused is left in an unspecified state.
  Optional<TerminatedPath>
  getBlockingAccess(const MemoryAccess *StopWhere,
                    SmallVectorImpl<ListIndex> &PausedSearches,
                    SmallVectorImpl<ListIndex> &NewPaused,
                    SmallVectorImpl<TerminatedPath> &Terminated) {
    assert(!PausedSearches.empty() && "No searches to continue?");

    // BFS vs DFS really doesn't make a difference here, so just do a DFS with
    // PausedSearches as our stack.
    while (!PausedSearches.empty()) {
      ListIndex PathIndex = PausedSearches.pop_back_val();
      DefPath &Node = Paths[PathIndex];

      // If we've already visited this path with this MemoryLocation, we don't
      // need to do so again.
      //
      // NOTE: That we just drop these paths on the ground makes caching
      // behavior sporadic. e.g. given a diamond:
      //  A
      // B C
      //  D
      //
      // ...If we walk D, B, A, C, we'll only cache the result of phi
      // optimization for A, B, and D; C will be skipped because it dies here.
      // This arguably isn't the worst thing ever, since:
      //   - We generally query things in a top-down order, so if we got below D
      //     without needing cache entries for {C, MemLoc}, then chances are
      //     that those cache entries would end up ultimately unused.
      //   - We still cache things for A, so C only needs to walk up a bit.
      // If this behavior becomes problematic, we can fix without a ton of extra
      // work.
      if (!VisitedPhis.insert({Node.Last, Node.Loc}).second)
        continue;

      const MemoryAccess *SkipStopWhere = nullptr;
      if (Query->SkipSelfAccess && Node.Loc == Query->StartingLoc) {
        assert(isa<MemoryDef>(Query->OriginalAccess));
        SkipStopWhere = Query->OriginalAccess;
      }

      UpwardsWalkResult Res = walkToPhiOrClobber(Node,
                                                 /*StopAt=*/StopWhere,
                                                 /*SkipStopAt=*/SkipStopWhere);
      if (Res.IsKnownClobber) {
        assert(Res.Result != StopWhere && Res.Result != SkipStopWhere);

        // If this wasn't a cache hit, we hit a clobber when walking. That's a
        // failure.
        TerminatedPath Term{Res.Result, PathIndex};
        if (!MSSA.dominates(Res.Result, StopWhere))
          return Term;

        // Otherwise, it's a valid thing to potentially optimize to.
        Terminated.push_back(Term);
        continue;
      }

      if (Res.Result == StopWhere || Res.Result == SkipStopWhere) {
        // We've hit our target. Save this path off for if we want to continue
        // walking. If we are in the mode of skipping the OriginalAccess, and
        // we've reached back to the OriginalAccess, do not save path, we've
        // just looped back to self.
        if (Res.Result != SkipStopWhere)
          NewPaused.push_back(PathIndex);
        continue;
      }

      assert(!MSSA.isLiveOnEntryDef(Res.Result) && "liveOnEntry is a clobber");
      addSearches(cast<MemoryPhi>(Res.Result), PausedSearches, PathIndex);
    }

    return None;
  }

  template <typename T, typename Walker>
  struct generic_def_path_iterator
      : public iterator_facade_base<generic_def_path_iterator<T, Walker>,
                                    std::forward_iterator_tag, T *> {
    generic_def_path_iterator() {}
    generic_def_path_iterator(Walker *W, ListIndex N) : W(W), N(N) {}

    T &operator*() const { return curNode(); }

    generic_def_path_iterator &operator++() {
      N = curNode().Previous;
      return *this;
    }

    bool operator==(const generic_def_path_iterator &O) const {
      if (N.hasValue() != O.N.hasValue())
        return false;
      return !N.hasValue() || *N == *O.N;
    }

  private:
    T &curNode() const { return W->Paths[*N]; }

    Walker *W = nullptr;
    Optional<ListIndex> N = None;
  };

  using def_path_iterator = generic_def_path_iterator<DefPath, ClobberWalker>;
  using const_def_path_iterator =
      generic_def_path_iterator<const DefPath, const ClobberWalker>;

  iterator_range<def_path_iterator> def_path(ListIndex From) {
    return make_range(def_path_iterator(this, From), def_path_iterator());
  }

  iterator_range<const_def_path_iterator> const_def_path(ListIndex From) const {
    return make_range(const_def_path_iterator(this, From),
                      const_def_path_iterator());
  }

  struct OptznResult {
    /// The path that contains our result.
    TerminatedPath PrimaryClobber;
    /// The paths that we can legally cache back from, but that aren't
    /// necessarily the result of the Phi optimization.
    SmallVector<TerminatedPath, 4> OtherClobbers;
  };

  ListIndex defPathIndex(const DefPath &N) const {
    // The assert looks nicer if we don't need to do &N
    const DefPath *NP = &N;
    assert(!Paths.empty() && NP >= &Paths.front() && NP <= &Paths.back() &&
           "Out of bounds DefPath!");
    return NP - &Paths.front();
  }

  /// Try to optimize a phi as best as we can. Returns a SmallVector of Paths
  /// that act as legal clobbers. Note that this won't return *all* clobbers.
  ///
  /// Phi optimization algorithm tl;dr:
  ///   - Find the earliest def/phi, A, we can optimize to
  ///   - Find if all paths from the starting memory access ultimately reach A
  ///     - If not, optimization isn't possible.
  ///     - Otherwise, walk from A to another clobber or phi, A'.
  ///       - If A' is a def, we're done.
  ///       - If A' is a phi, try to optimize it.
  ///
  /// A path is a series of {MemoryAccess, MemoryLocation} pairs. A path
  /// terminates when a MemoryAccess that clobbers said MemoryLocation is found.
  OptznResult tryOptimizePhi(MemoryPhi *Phi, MemoryAccess *Start,
                             const MemoryLocation &Loc) {
    assert(Paths.empty() && VisitedPhis.empty() &&
           "Reset the optimization state.");

    Paths.emplace_back(Loc, Start, Phi, None);
    // Stores how many "valid" optimization nodes we had prior to calling
    // addSearches/getBlockingAccess. Necessary for caching if we had a blocker.
    auto PriorPathsSize = Paths.size();

    SmallVector<ListIndex, 16> PausedSearches;
    SmallVector<ListIndex, 8> NewPaused;
    SmallVector<TerminatedPath, 4> TerminatedPaths;

    addSearches(Phi, PausedSearches, 0);

    // Moves the TerminatedPath with the "most dominated" Clobber to the end of
    // Paths.
    auto MoveDominatedPathToEnd = [&](SmallVectorImpl<TerminatedPath> &Paths) {
      assert(!Paths.empty() && "Need a path to move");
      auto Dom = Paths.begin();
      for (auto I = std::next(Dom), E = Paths.end(); I != E; ++I)
        if (!MSSA.dominates(I->Clobber, Dom->Clobber))
          Dom = I;
      auto Last = Paths.end() - 1;
      if (Last != Dom)
        std::iter_swap(Last, Dom);
    };

    MemoryPhi *Current = Phi;
    while (true) {
      assert(!MSSA.isLiveOnEntryDef(Current) &&
             "liveOnEntry wasn't treated as a clobber?");

      const auto *Target = getWalkTarget(Current);
      // If a TerminatedPath doesn't dominate Target, then it wasn't a legal
      // optimization for the prior phi.
      assert(all_of(TerminatedPaths, [&](const TerminatedPath &P) {
        return MSSA.dominates(P.Clobber, Target);
      }));

      // FIXME: This is broken, because the Blocker may be reported to be
      // liveOnEntry, and we'll happily wait for that to disappear (read: never)
      // For the moment, this is fine, since we do nothing with blocker info.
      if (Optional<TerminatedPath> Blocker = getBlockingAccess(
              Target, PausedSearches, NewPaused, TerminatedPaths)) {

        // Find the node we started at. We can't search based on N->Last, since
        // we may have gone around a loop with a different MemoryLocation.
        auto Iter = find_if(def_path(Blocker->LastNode), [&](const DefPath &N) {
          return defPathIndex(N) < PriorPathsSize;
        });
        assert(Iter != def_path_iterator());

        DefPath &CurNode = *Iter;
        assert(CurNode.Last == Current);

        // Two things:
        // A. We can't reliably cache all of NewPaused back. Consider a case
        //    where we have two paths in NewPaused; one of which can't optimize
        //    above this phi, whereas the other can. If we cache the second path
        //    back, we'll end up with suboptimal cache entries. We can handle
        //    cases like this a bit better when we either try to find all
        //    clobbers that block phi optimization, or when our cache starts
        //    supporting unfinished searches.
        // B. We can't reliably cache TerminatedPaths back here without doing
        //    extra checks; consider a case like:
        //       T
        //      / \
        //     D   C
        //      \ /
        //       S
        //    Where T is our target, C is a node with a clobber on it, D is a
        //    diamond (with a clobber *only* on the left or right node, N), and
        //    S is our start. Say we walk to D, through the node opposite N
        //    (read: ignoring the clobber), and see a cache entry in the top
        //    node of D. That cache entry gets put into TerminatedPaths. We then
        //    walk up to C (N is later in our worklist), find the clobber, and
        //    quit. If we append TerminatedPaths to OtherClobbers, we'll cache
        //    the bottom part of D to the cached clobber, ignoring the clobber
        //    in N. Again, this problem goes away if we start tracking all
        //    blockers for a given phi optimization.
        TerminatedPath Result{CurNode.Last, defPathIndex(CurNode)};
        return {Result, {}};
      }

      // If there's nothing left to search, then all paths led to valid clobbers
      // that we got from our cache; pick the nearest to the start, and allow
      // the rest to be cached back.
      if (NewPaused.empty()) {
        MoveDominatedPathToEnd(TerminatedPaths);
        TerminatedPath Result = TerminatedPaths.pop_back_val();
        return {Result, std::move(TerminatedPaths)};
      }

      MemoryAccess *DefChainEnd = nullptr;
      SmallVector<TerminatedPath, 4> Clobbers;
      for (ListIndex Paused : NewPaused) {
        UpwardsWalkResult WR = walkToPhiOrClobber(Paths[Paused]);
        if (WR.IsKnownClobber)
          Clobbers.push_back({WR.Result, Paused});
        else
          // Micro-opt: If we hit the end of the chain, save it.
          DefChainEnd = WR.Result;
      }

      if (!TerminatedPaths.empty()) {
        // If we couldn't find the dominating phi/liveOnEntry in the above loop,
        // do it now.
        if (!DefChainEnd)
          for (auto *MA : def_chain(const_cast<MemoryAccess *>(Target)))
            DefChainEnd = MA;
        assert(DefChainEnd && "Failed to find dominating phi/liveOnEntry");

        // If any of the terminated paths don't dominate the phi we'll try to
        // optimize, we need to figure out what they are and quit.
        const BasicBlock *ChainBB = DefChainEnd->getBlock();
        for (const TerminatedPath &TP : TerminatedPaths) {
          // Because we know that DefChainEnd is as "high" as we can go, we
          // don't need local dominance checks; BB dominance is sufficient.
          if (DT.dominates(ChainBB, TP.Clobber->getBlock()))
            Clobbers.push_back(TP);
        }
      }

      // If we have clobbers in the def chain, find the one closest to Current
      // and quit.
      if (!Clobbers.empty()) {
        MoveDominatedPathToEnd(Clobbers);
        TerminatedPath Result = Clobbers.pop_back_val();
        return {Result, std::move(Clobbers)};
      }

      assert(all_of(NewPaused,
                    [&](ListIndex I) { return Paths[I].Last == DefChainEnd; }));

      // Because liveOnEntry is a clobber, this must be a phi.
      auto *DefChainPhi = cast<MemoryPhi>(DefChainEnd);

      PriorPathsSize = Paths.size();
      PausedSearches.clear();
      for (ListIndex I : NewPaused)
        addSearches(DefChainPhi, PausedSearches, I);
      NewPaused.clear();

      Current = DefChainPhi;
    }
  }

  void verifyOptResult(const OptznResult &R) const {
    assert(all_of(R.OtherClobbers, [&](const TerminatedPath &P) {
      return MSSA.dominates(P.Clobber, R.PrimaryClobber.Clobber);
    }));
  }

  void resetPhiOptznState() {
    Paths.clear();
    VisitedPhis.clear();
  }

public:
  ClobberWalker(const MemorySSA &MSSA, AliasAnalysisType &AA, DominatorTree &DT)
      : MSSA(MSSA), AA(AA), DT(DT) {}

  AliasAnalysisType *getAA() { return &AA; }
  /// Finds the nearest clobber for the given query, optimizing phis if
  /// possible.
  MemoryAccess *findClobber(MemoryAccess *Start, UpwardsMemoryQuery &Q,
                            unsigned &UpWalkLimit) {
    Query = &Q;
    UpwardWalkLimit = &UpWalkLimit;
    // Starting limit must be > 0.
    if (!UpWalkLimit)
      UpWalkLimit++;

    MemoryAccess *Current = Start;
    // This walker pretends uses don't exist. If we're handed one, silently grab
    // its def. (This has the nice side-effect of ensuring we never cache uses)
    if (auto *MU = dyn_cast<MemoryUse>(Start))
      Current = MU->getDefiningAccess();

    DefPath FirstDesc(Q.StartingLoc, Current, Current, None);
    // Fast path for the overly-common case (no crazy phi optimization
    // necessary)
    UpwardsWalkResult WalkResult = walkToPhiOrClobber(FirstDesc);
    MemoryAccess *Result;
    if (WalkResult.IsKnownClobber) {
      Result = WalkResult.Result;
      Q.AR = WalkResult.AR;
    } else {
      OptznResult OptRes = tryOptimizePhi(cast<MemoryPhi>(FirstDesc.Last),
                                          Current, Q.StartingLoc);
      verifyOptResult(OptRes);
      resetPhiOptznState();
      Result = OptRes.PrimaryClobber.Clobber;
    }

#ifdef EXPENSIVE_CHECKS
    if (!Q.SkipSelfAccess && *UpwardWalkLimit > 0)
      checkClobberSanity(Current, Result, Q.StartingLoc, MSSA, Q, AA);
#endif
    return Result;
  }
};

struct RenamePassData {
  DomTreeNode *DTN;
  DomTreeNode::const_iterator ChildIt;
  MemoryAccess *IncomingVal;

  RenamePassData(DomTreeNode *D, DomTreeNode::const_iterator It,
                 MemoryAccess *M)
      : DTN(D), ChildIt(It), IncomingVal(M) {}

  void swap(RenamePassData &RHS) {
    std::swap(DTN, RHS.DTN);
    std::swap(ChildIt, RHS.ChildIt);
    std::swap(IncomingVal, RHS.IncomingVal);
  }
};

} // end anonymous namespace

namespace llvm {

template <class AliasAnalysisType> class MemorySSA::ClobberWalkerBase {
  ClobberWalker<AliasAnalysisType> Walker;
  MemorySSA *MSSA;

public:
  ClobberWalkerBase(MemorySSA *M, AliasAnalysisType *A, DominatorTree *D)
      : Walker(*M, *A, *D), MSSA(M) {}

  MemoryAccess *getClobberingMemoryAccessBase(MemoryAccess *,
                                              const MemoryLocation &,
                                              unsigned &);
  // Third argument (bool), defines whether the clobber search should skip the
  // original queried access. If true, there will be a follow-up query searching
  // for a clobber access past "self". Note that the Optimized access is not
  // updated if a new clobber is found by this SkipSelf search. If this
  // additional query becomes heavily used we may decide to cache the result.
  // Walker instantiations will decide how to set the SkipSelf bool.
  MemoryAccess *getClobberingMemoryAccessBase(MemoryAccess *, unsigned &, bool);
};

/// A MemorySSAWalker that does AA walks to disambiguate accesses. It no
/// longer does caching on its own, but the name has been retained for the
/// moment.
template <class AliasAnalysisType>
class MemorySSA::CachingWalker final : public MemorySSAWalker {
  ClobberWalkerBase<AliasAnalysisType> *Walker;

public:
  CachingWalker(MemorySSA *M, ClobberWalkerBase<AliasAnalysisType> *W)
      : MemorySSAWalker(M), Walker(W) {}
  ~CachingWalker() override = default;

  using MemorySSAWalker::getClobberingMemoryAccess;

  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA, unsigned &UWL) {
    return Walker->getClobberingMemoryAccessBase(MA, UWL, false);
  }
  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA,
                                          const MemoryLocation &Loc,
                                          unsigned &UWL) {
    return Walker->getClobberingMemoryAccessBase(MA, Loc, UWL);
  }

  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA) override {
    unsigned UpwardWalkLimit = MaxCheckLimit;
    return getClobberingMemoryAccess(MA, UpwardWalkLimit);
  }
  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA,
                                          const MemoryLocation &Loc) override {
    unsigned UpwardWalkLimit = MaxCheckLimit;
    return getClobberingMemoryAccess(MA, Loc, UpwardWalkLimit);
  }

  void invalidateInfo(MemoryAccess *MA) override {
    if (auto *MUD = dyn_cast<MemoryUseOrDef>(MA))
      MUD->resetOptimized();
  }
};

template <class AliasAnalysisType>
class MemorySSA::SkipSelfWalker final : public MemorySSAWalker {
  ClobberWalkerBase<AliasAnalysisType> *Walker;

public:
  SkipSelfWalker(MemorySSA *M, ClobberWalkerBase<AliasAnalysisType> *W)
      : MemorySSAWalker(M), Walker(W) {}
  ~SkipSelfWalker() override = default;

  using MemorySSAWalker::getClobberingMemoryAccess;

  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA, unsigned &UWL) {
    return Walker->getClobberingMemoryAccessBase(MA, UWL, true);
  }
  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA,
                                          const MemoryLocation &Loc,
                                          unsigned &UWL) {
    return Walker->getClobberingMemoryAccessBase(MA, Loc, UWL);
  }

  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA) override {
    unsigned UpwardWalkLimit = MaxCheckLimit;
    return getClobberingMemoryAccess(MA, UpwardWalkLimit);
  }
  MemoryAccess *getClobberingMemoryAccess(MemoryAccess *MA,
                                          const MemoryLocation &Loc) override {
    unsigned UpwardWalkLimit = MaxCheckLimit;
    return getClobberingMemoryAccess(MA, Loc, UpwardWalkLimit);
  }

  void invalidateInfo(MemoryAccess *MA) override {
    if (auto *MUD = dyn_cast<MemoryUseOrDef>(MA))
      MUD->resetOptimized();
  }
};

} // end namespace llvm

void MemorySSA::renameSuccessorPhis(BasicBlock *BB, MemoryAccess *IncomingVal,
                                    bool RenameAllUses) {
  // Pass through values to our successors
  for (const BasicBlock *S : successors(BB)) {
    auto It = PerBlockAccesses.find(S);
    // Rename the phi nodes in our successor block
    if (It == PerBlockAccesses.end() || !isa<MemoryPhi>(It->second->front()))
      continue;
    AccessList *Accesses = It->second.get();
    auto *Phi = cast<MemoryPhi>(&Accesses->front());
    if (RenameAllUses) {
      bool ReplacementDone = false;
      for (unsigned I = 0, E = Phi->getNumIncomingValues(); I != E; ++I)
        if (Phi->getIncomingBlock(I) == BB) {
          Phi->setIncomingValue(I, IncomingVal);
          ReplacementDone = true;
        }
      (void) ReplacementDone;
      assert(ReplacementDone && "Incomplete phi during partial rename");
    } else
      Phi->addIncoming(IncomingVal, BB);
  }
}

/// Rename a single basic block into MemorySSA form.
/// Uses the standard SSA renaming algorithm.
/// \returns The new incoming value.
MemoryAccess *MemorySSA::renameBlock(BasicBlock *BB, MemoryAccess *IncomingVal,
                                     bool RenameAllUses) {
  auto It = PerBlockAccesses.find(BB);
  // Skip most processing if the list is empty.
  if (It != PerBlockAccesses.end()) {
    AccessList *Accesses = It->second.get();
    for (MemoryAccess &L : *Accesses) {
      if (MemoryUseOrDef *MUD = dyn_cast<MemoryUseOrDef>(&L)) {
        if (MUD->getDefiningAccess() == nullptr || RenameAllUses)
          MUD->setDefiningAccess(IncomingVal);
        if (isa<MemoryDef>(&L))
          IncomingVal = &L;
      } else {
        IncomingVal = &L;
      }
    }
  }
  return IncomingVal;
}

/// This is the standard SSA renaming algorithm.
///
/// We walk the dominator tree in preorder, renaming accesses, and then filling
/// in phi nodes in our successors.
void MemorySSA::renamePass(DomTreeNode *Root, MemoryAccess *IncomingVal,
                           SmallPtrSetImpl<BasicBlock *> &Visited,
                           bool SkipVisited, bool RenameAllUses) {
  assert(Root && "Trying to rename accesses in an unreachable block");

  SmallVector<RenamePassData, 32> WorkStack;
  // Skip everything if we already renamed this block and we are skipping.
  // Note: You can't sink this into the if, because we need it to occur
  // regardless of whether we skip blocks or not.
  bool AlreadyVisited = !Visited.insert(Root->getBlock()).second;
  if (SkipVisited && AlreadyVisited)
    return;

  IncomingVal = renameBlock(Root->getBlock(), IncomingVal, RenameAllUses);
  renameSuccessorPhis(Root->getBlock(), IncomingVal, RenameAllUses);
  WorkStack.push_back({Root, Root->begin(), IncomingVal});

  while (!WorkStack.empty()) {
    DomTreeNode *Node = WorkStack.back().DTN;
    DomTreeNode::const_iterator ChildIt = WorkStack.back().ChildIt;
    IncomingVal = WorkStack.back().IncomingVal;

    if (ChildIt == Node->end()) {
      WorkStack.pop_back();
    } else {
      DomTreeNode *Child = *ChildIt;
      ++WorkStack.back().ChildIt;
      BasicBlock *BB = Child->getBlock();
      // Note: You can't sink this into the if, because we need it to occur
      // regardless of whether we skip blocks or not.
      AlreadyVisited = !Visited.insert(BB).second;
      if (SkipVisited && AlreadyVisited) {
        // We already visited this during our renaming, which can happen when
        // being asked to rename multiple blocks. Figure out the incoming val,
        // which is the last def.
        // Incoming value can only change if there is a block def, and in that
        // case, it's the last block def in the list.
        if (auto *BlockDefs = getWritableBlockDefs(BB))
          IncomingVal = &*BlockDefs->rbegin();
      } else
        IncomingVal = renameBlock(BB, IncomingVal, RenameAllUses);
      renameSuccessorPhis(BB, IncomingVal, RenameAllUses);
      WorkStack.push_back({Child, Child->begin(), IncomingVal});
    }
  }
}

/// This handles unreachable block accesses by deleting phi nodes in
/// unreachable blocks, and marking all other unreachable MemoryAccess's as
/// being uses of the live on entry definition.
void MemorySSA::markUnreachableAsLiveOnEntry(BasicBlock *BB) {
  assert(!DT->isReachableFromEntry(BB) &&
         "Reachable block found while handling unreachable blocks");

  // Make sure phi nodes in our reachable successors end up with a
  // LiveOnEntryDef for our incoming edge, even though our block is forward
  // unreachable.  We could just disconnect these blocks from the CFG fully,
  // but we do not right now.
  for (const BasicBlock *S : successors(BB)) {
    if (!DT->isReachableFromEntry(S))
      continue;
    auto It = PerBlockAccesses.find(S);
    // Rename the phi nodes in our successor block
    if (It == PerBlockAccesses.end() || !isa<MemoryPhi>(It->second->front()))
      continue;
    AccessList *Accesses = It->second.get();
    auto *Phi = cast<MemoryPhi>(&Accesses->front());
    Phi->addIncoming(LiveOnEntryDef.get(), BB);
  }

  auto It = PerBlockAccesses.find(BB);
  if (It == PerBlockAccesses.end())
    return;

  auto &Accesses = It->second;
  for (auto AI = Accesses->begin(), AE = Accesses->end(); AI != AE;) {
    auto Next = std::next(AI);
    // If we have a phi, just remove it. We are going to replace all
    // users with live on entry.
    if (auto *UseOrDef = dyn_cast<MemoryUseOrDef>(AI))
      UseOrDef->setDefiningAccess(LiveOnEntryDef.get());
    else
      Accesses->erase(AI);
    AI = Next;
  }
}

MemorySSA::MemorySSA(Function &Func, AliasAnalysis *AA, DominatorTree *DT)
    : AA(nullptr), DT(DT), F(Func), LiveOnEntryDef(nullptr), Walker(nullptr),
      SkipWalker(nullptr), NextID(0) {
  // Build MemorySSA using a batch alias analysis. This reuses the internal
  // state that AA collects during an alias()/getModRefInfo() call. This is
  // safe because there are no CFG changes while building MemorySSA and can
  // significantly reduce the time spent by the compiler in AA, because we will
  // make queries about all the instructions in the Function.
  assert(AA && "No alias analysis?");
  BatchAAResults BatchAA(*AA);
  buildMemorySSA(BatchAA);
  // Intentionally leave AA to nullptr while building so we don't accidently
  // use non-batch AliasAnalysis.
  this->AA = AA;
  // Also create the walker here.
  getWalker();
}

MemorySSA::~MemorySSA() {
  // Drop all our references
  for (const auto &Pair : PerBlockAccesses)
    for (MemoryAccess &MA : *Pair.second)
      MA.dropAllReferences();
}

MemorySSA::AccessList *MemorySSA::getOrCreateAccessList(const BasicBlock *BB) {
  auto Res = PerBlockAccesses.insert(std::make_pair(BB, nullptr));

  if (Res.second)
    Res.first->second = std::make_unique<AccessList>();
  return Res.first->second.get();
}

MemorySSA::DefsList *MemorySSA::getOrCreateDefsList(const BasicBlock *BB) {
  auto Res = PerBlockDefs.insert(std::make_pair(BB, nullptr));

  if (Res.second)
    Res.first->second = std::make_unique<DefsList>();
  return Res.first->second.get();
}

namespace llvm {

/// This class is a batch walker of all MemoryUse's in the program, and points
/// their defining access at the thing that actually clobbers them.  Because it
/// is a batch walker that touches everything, it does not operate like the
/// other walkers.  This walker is basically performing a top-down SSA renaming
/// pass, where the version stack is used as the cache.  This enables it to be
/// significantly more time and memory efficient than using the regular walker,
/// which is walking bottom-up.
class MemorySSA::OptimizeUses {
public:
  OptimizeUses(MemorySSA *MSSA, CachingWalker<BatchAAResults> *Walker,
               BatchAAResults *BAA, DominatorTree *DT)
      : MSSA(MSSA), Walker(Walker), AA(BAA), DT(DT) {}

  void optimizeUses();

private:
  /// This represents where a given memorylocation is in the stack.
  struct MemlocStackInfo {
    // This essentially is keeping track of versions of the stack. Whenever
    // the stack changes due to pushes or pops, these versions increase.
    unsigned long StackEpoch;
    unsigned long PopEpoch;
    // This is the lower bound of places on the stack to check. It is equal to
    // the place the last stack walk ended.
    // Note: Correctness depends on this being initialized to 0, which densemap
    // does
    unsigned long LowerBound;
    const BasicBlock *LowerBoundBlock;
    // This is where the last walk for this memory location ended.
    unsigned long LastKill;
    bool LastKillValid;
    Optional<AliasResult> AR;
  };

  void optimizeUsesInBlock(const BasicBlock *, unsigned long &, unsigned long &,
                           SmallVectorImpl<MemoryAccess *> &,
                           DenseMap<MemoryLocOrCall, MemlocStackInfo> &);

  MemorySSA *MSSA;
  CachingWalker<BatchAAResults> *Walker;
  BatchAAResults *AA;
  DominatorTree *DT;
};

} // end namespace llvm

/// Optimize the uses in a given block This is basically the SSA renaming
/// algorithm, with one caveat: We are able to use a single stack for all
/// MemoryUses.  This is because the set of *possible* reaching MemoryDefs is
/// the same for every MemoryUse.  The *actual* clobbering MemoryDef is just
/// going to be some position in that stack of possible ones.
///
/// We track the stack positions that each MemoryLocation needs
/// to check, and last ended at.  This is because we only want to check the
/// things that changed since last time.  The same MemoryLocation should
/// get clobbered by the same store (getModRefInfo does not use invariantness or
/// things like this, and if they start, we can modify MemoryLocOrCall to
/// include relevant data)
void MemorySSA::OptimizeUses::optimizeUsesInBlock(
    const BasicBlock *BB, unsigned long &StackEpoch, unsigned long &PopEpoch,
    SmallVectorImpl<MemoryAccess *> &VersionStack,
    DenseMap<MemoryLocOrCall, MemlocStackInfo> &LocStackInfo) {

  /// If no accesses, nothing to do.
  MemorySSA::AccessList *Accesses = MSSA->getWritableBlockAccesses(BB);
  if (Accesses == nullptr)
    return;

  // Pop everything that doesn't dominate the current block off the stack,
  // increment the PopEpoch to account for this.
  while (true) {
    assert(
        !VersionStack.empty() &&
        "Version stack should have liveOnEntry sentinel dominating everything");
    BasicBlock *BackBlock = VersionStack.back()->getBlock();
    if (DT->dominates(BackBlock, BB))
      break;
    while (VersionStack.back()->getBlock() == BackBlock)
      VersionStack.pop_back();
    ++PopEpoch;
  }

  for (MemoryAccess &MA : *Accesses) {
    auto *MU = dyn_cast<MemoryUse>(&MA);
    if (!MU) {
      VersionStack.push_back(&MA);
      ++StackEpoch;
      continue;
    }

    if (isUseTriviallyOptimizableToLiveOnEntry(*AA, MU->getMemoryInst())) {
      MU->setDefiningAccess(MSSA->getLiveOnEntryDef(), true, None);
      continue;
    }

    MemoryLocOrCall UseMLOC(MU);
    auto &LocInfo = LocStackInfo[UseMLOC];
    // If the pop epoch changed, it means we've removed stuff from top of
    // stack due to changing blocks. We may have to reset the lower bound or
    // last kill info.
    if (LocInfo.PopEpoch != PopEpoch) {
      LocInfo.PopEpoch = PopEpoch;
      LocInfo.StackEpoch = StackEpoch;
      // If the lower bound was in something that no longer dominates us, we
      // have to reset it.
      // We can't simply track stack size, because the stack may have had
      // pushes/pops in the meantime.
      // XXX: This is non-optimal, but only is slower cases with heavily
      // branching dominator trees.  To get the optimal number of queries would
      // be to make lowerbound and lastkill a per-loc stack, and pop it until
      // the top of that stack dominates us.  This does not seem worth it ATM.
      // A much cheaper optimization would be to always explore the deepest
      // branch of the dominator tree first. This will guarantee this resets on
      // the smallest set of blocks.
      if (LocInfo.LowerBoundBlock && LocInfo.LowerBoundBlock != BB &&
          !DT->dominates(LocInfo.LowerBoundBlock, BB)) {
        // Reset the lower bound of things to check.
        // TODO: Some day we should be able to reset to last kill, rather than
        // 0.
        LocInfo.LowerBound = 0;
        LocInfo.LowerBoundBlock = VersionStack[0]->getBlock();
        LocInfo.LastKillValid = false;
      }
    } else if (LocInfo.StackEpoch != StackEpoch) {
      // If all that has changed is the StackEpoch, we only have to check the
      // new things on the stack, because we've checked everything before.  In
      // this case, the lower bound of things to check remains the same.
      LocInfo.PopEpoch = PopEpoch;
      LocInfo.StackEpoch = StackEpoch;
    }
    if (!LocInfo.LastKillValid) {
      LocInfo.LastKill = VersionStack.size() - 1;
      LocInfo.LastKillValid = true;
      LocInfo.AR = MayAlias;
    }

    // At this point, we should have corrected last kill and LowerBound to be
    // in bounds.
    assert(LocInfo.LowerBound < VersionStack.size() &&
           "Lower bound out of range");
    assert(LocInfo.LastKill < VersionStack.size() &&
           "Last kill info out of range");
    // In any case, the new upper bound is the top of the stack.
    unsigned long UpperBound = VersionStack.size() - 1;

    if (UpperBound - LocInfo.LowerBound > MaxCheckLimit) {
      LLVM_DEBUG(dbgs() << "MemorySSA skipping optimization of " << *MU << " ("
                        << *(MU->getMemoryInst()) << ")"
                        << " because there are "
                        << UpperBound - LocInfo.LowerBound
                        << " stores to disambiguate\n");
      // Because we did not walk, LastKill is no longer valid, as this may
      // have been a kill.
      LocInfo.LastKillValid = false;
      continue;
    }
    bool FoundClobberResult = false;
    unsigned UpwardWalkLimit = MaxCheckLimit;
    while (UpperBound > LocInfo.LowerBound) {
      if (isa<MemoryPhi>(VersionStack[UpperBound])) {
        // For phis, use the walker, see where we ended up, go there
        MemoryAccess *Result =
            Walker->getClobberingMemoryAccess(MU, UpwardWalkLimit);
        // We are guaranteed to find it or something is wrong
        while (VersionStack[UpperBound] != Result) {
          assert(UpperBound != 0);
          --UpperBound;
        }
        FoundClobberResult = true;
        break;
      }

      MemoryDef *MD = cast<MemoryDef>(VersionStack[UpperBound]);
      // If the lifetime of the pointer ends at this instruction, it's live on
      // entry.
      if (!UseMLOC.IsCall && lifetimeEndsAt(MD, UseMLOC.getLoc(), *AA)) {
        // Reset UpperBound to liveOnEntryDef's place in the stack
        UpperBound = 0;
        FoundClobberResult = true;
        LocInfo.AR = MustAlias;
        break;
      }
      ClobberAlias CA = instructionClobbersQuery(MD, MU, UseMLOC, *AA);
      if (CA.IsClobber) {
        FoundClobberResult = true;
        LocInfo.AR = CA.AR;
        break;
      }
      --UpperBound;
    }

    // Note: Phis always have AliasResult AR set to MayAlias ATM.

    // At the end of this loop, UpperBound is either a clobber, or lower bound
    // PHI walking may cause it to be < LowerBound, and in fact, < LastKill.
    if (FoundClobberResult || UpperBound < LocInfo.LastKill) {
      // We were last killed now by where we got to
      if (MSSA->isLiveOnEntryDef(VersionStack[UpperBound]))
        LocInfo.AR = None;
      MU->setDefiningAccess(VersionStack[UpperBound], true, LocInfo.AR);
      LocInfo.LastKill = UpperBound;
    } else {
      // Otherwise, we checked all the new ones, and now we know we can get to
      // LastKill.
      MU->setDefiningAccess(VersionStack[LocInfo.LastKill], true, LocInfo.AR);
    }
    LocInfo.LowerBound = VersionStack.size() - 1;
    LocInfo.LowerBoundBlock = BB;
  }
}

/// Optimize uses to point to their actual clobbering definitions.
void MemorySSA::OptimizeUses::optimizeUses() {
  SmallVector<MemoryAccess *, 16> VersionStack;
  DenseMap<MemoryLocOrCall, MemlocStackInfo> LocStackInfo;
  VersionStack.push_back(MSSA->getLiveOnEntryDef());

  unsigned long StackEpoch = 1;
  unsigned long PopEpoch = 1;
  // We perform a non-recursive top-down dominator tree walk.
  for (const auto *DomNode : depth_first(DT->getRootNode()))
    optimizeUsesInBlock(DomNode->getBlock(), StackEpoch, PopEpoch, VersionStack,
                        LocStackInfo);
}

void MemorySSA::placePHINodes(
    const SmallPtrSetImpl<BasicBlock *> &DefiningBlocks) {
  // Determine where our MemoryPhi's should go
  ForwardIDFCalculator IDFs(*DT);
  IDFs.setDefiningBlocks(DefiningBlocks);
  SmallVector<BasicBlock *, 32> IDFBlocks;
  IDFs.calculate(IDFBlocks);

  // Now place MemoryPhi nodes.
  for (auto &BB : IDFBlocks)
    createMemoryPhi(BB);
}

void MemorySSA::buildMemorySSA(BatchAAResults &BAA) {
  // We create an access to represent "live on entry", for things like
  // arguments or users of globals, where the memory they use is defined before
  // the beginning of the function. We do not actually insert it into the IR.
  // We do not define a live on exit for the immediate uses, and thus our
  // semantics do *not* imply that something with no immediate uses can simply
  // be removed.
  BasicBlock &StartingPoint = F.getEntryBlock();
  LiveOnEntryDef.reset(new MemoryDef(F.getContext(), nullptr, nullptr,
                                     &StartingPoint, NextID++));

  // We maintain lists of memory accesses per-block, trading memory for time. We
  // could just look up the memory access for every possible instruction in the
  // stream.
  SmallPtrSet<BasicBlock *, 32> DefiningBlocks;
  // Go through each block, figure out where defs occur, and chain together all
  // the accesses.
  for (BasicBlock &B : F) {
    bool InsertIntoDef = false;
    AccessList *Accesses = nullptr;
    DefsList *Defs = nullptr;
    for (Instruction &I : B) {
      MemoryUseOrDef *MUD = createNewAccess(&I, &BAA);
      if (!MUD)
        continue;

      if (!Accesses)
        Accesses = getOrCreateAccessList(&B);
      Accesses->push_back(MUD);
      if (isa<MemoryDef>(MUD)) {
        InsertIntoDef = true;
        if (!Defs)
          Defs = getOrCreateDefsList(&B);
        Defs->push_back(*MUD);
      }
    }
    if (InsertIntoDef)
      DefiningBlocks.insert(&B);
  }
  placePHINodes(DefiningBlocks);

  // Now do regular SSA renaming on the MemoryDef/MemoryUse. Visited will get
  // filled in with all blocks.
  SmallPtrSet<BasicBlock *, 16> Visited;
  renamePass(DT->getRootNode(), LiveOnEntryDef.get(), Visited);

  ClobberWalkerBase<BatchAAResults> WalkerBase(this, &BAA, DT);
  CachingWalker<BatchAAResults> WalkerLocal(this, &WalkerBase);
  OptimizeUses(this, &WalkerLocal, &BAA, DT).optimizeUses();

  // Mark the uses in unreachable blocks as live on entry, so that they go
  // somewhere.
  for (auto &BB : F)
    if (!Visited.count(&BB))
      markUnreachableAsLiveOnEntry(&BB);
}

MemorySSAWalker *MemorySSA::getWalker() { return getWalkerImpl(); }

MemorySSA::CachingWalker<AliasAnalysis> *MemorySSA::getWalkerImpl() {
  if (Walker)
    return Walker.get();

  if (!WalkerBase)
    WalkerBase =
        std::make_unique<ClobberWalkerBase<AliasAnalysis>>(this, AA, DT);

  Walker =
      std::make_unique<CachingWalker<AliasAnalysis>>(this, WalkerBase.get());
  return Walker.get();
}

MemorySSAWalker *MemorySSA::getSkipSelfWalker() {
  if (SkipWalker)
    return SkipWalker.get();

  if (!WalkerBase)
    WalkerBase =
        std::make_unique<ClobberWalkerBase<AliasAnalysis>>(this, AA, DT);

  SkipWalker =
      std::make_unique<SkipSelfWalker<AliasAnalysis>>(this, WalkerBase.get());
  return SkipWalker.get();
 }


// This is a helper function used by the creation routines. It places NewAccess
// into the access and defs lists for a given basic block, at the given
// insertion point.
void MemorySSA::insertIntoListsForBlock(MemoryAccess *NewAccess,
                                        const BasicBlock *BB,
                                        InsertionPlace Point) {
  auto *Accesses = getOrCreateAccessList(BB);
  if (Point == Beginning) {
    // If it's a phi node, it goes first, otherwise, it goes after any phi
    // nodes.
    if (isa<MemoryPhi>(NewAccess)) {
      Accesses->push_front(NewAccess);
      auto *Defs = getOrCreateDefsList(BB);
      Defs->push_front(*NewAccess);
    } else {
      auto AI = find_if_not(
          *Accesses, [](const MemoryAccess &MA) { return isa<MemoryPhi>(MA); });
      Accesses->insert(AI, NewAccess);
      if (!isa<MemoryUse>(NewAccess)) {
        auto *Defs = getOrCreateDefsList(BB);
        auto DI = find_if_not(
            *Defs, [](const MemoryAccess &MA) { return isa<MemoryPhi>(MA); });
        Defs->insert(DI, *NewAccess);
      }
    }
  } else {
    Accesses->push_back(NewAccess);
    if (!isa<MemoryUse>(NewAccess)) {
      auto *Defs = getOrCreateDefsList(BB);
      Defs->push_back(*NewAccess);
    }
  }
  BlockNumberingValid.erase(BB);
}

void MemorySSA::insertIntoListsBefore(MemoryAccess *What, const BasicBlock *BB,
                                      AccessList::iterator InsertPt) {
  auto *Accesses = getWritableBlockAccesses(BB);
  bool WasEnd = InsertPt == Accesses->end();
  Accesses->insert(AccessList::iterator(InsertPt), What);
  if (!isa<MemoryUse>(What)) {
    auto *Defs = getOrCreateDefsList(BB);
    // If we got asked to insert at the end, we have an easy job, just shove it
    // at the end. If we got asked to insert before an existing def, we also get
    // an iterator. If we got asked to insert before a use, we have to hunt for
    // the next def.
    if (WasEnd) {
      Defs->push_back(*What);
    } else if (isa<MemoryDef>(InsertPt)) {
      Defs->insert(InsertPt->getDefsIterator(), *What);
    } else {
      while (InsertPt != Accesses->end() && !isa<MemoryDef>(InsertPt))
        ++InsertPt;
      // Either we found a def, or we are inserting at the end
      if (InsertPt == Accesses->end())
        Defs->push_back(*What);
      else
        Defs->insert(InsertPt->getDefsIterator(), *What);
    }
  }
  BlockNumberingValid.erase(BB);
}

void MemorySSA::prepareForMoveTo(MemoryAccess *What, BasicBlock *BB) {
  // Keep it in the lookup tables, remove from the lists
  removeFromLists(What, false);

  // Note that moving should implicitly invalidate the optimized state of a
  // MemoryUse (and Phis can't be optimized). However, it doesn't do so for a
  // MemoryDef.
  if (auto *MD = dyn_cast<MemoryDef>(What))
    MD->resetOptimized();
  What->setBlock(BB);
}

// Move What before Where in the IR.  The end result is that What will belong to
// the right lists and have the right Block set, but will not otherwise be
// correct. It will not have the right defining access, and if it is a def,
// things below it will not properly be updated.
void MemorySSA::moveTo(MemoryUseOrDef *What, BasicBlock *BB,
                       AccessList::iterator Where) {
  prepareForMoveTo(What, BB);
  insertIntoListsBefore(What, BB, Where);
}

void MemorySSA::moveTo(MemoryAccess *What, BasicBlock *BB,
                       InsertionPlace Point) {
  if (isa<MemoryPhi>(What)) {
    assert(Point == Beginning &&
           "Can only move a Phi at the beginning of the block");
    // Update lookup table entry
    ValueToMemoryAccess.erase(What->getBlock());
    bool Inserted = ValueToMemoryAccess.insert({BB, What}).second;
    (void)Inserted;
    assert(Inserted && "Cannot move a Phi to a block that already has one");
  }

  prepareForMoveTo(What, BB);
  insertIntoListsForBlock(What, BB, Point);
}

MemoryPhi *MemorySSA::createMemoryPhi(BasicBlock *BB) {
  assert(!getMemoryAccess(BB) && "MemoryPhi already exists for this BB");
  MemoryPhi *Phi = new MemoryPhi(BB->getContext(), BB, NextID++);
  // Phi's always are placed at the front of the block.
  insertIntoListsForBlock(Phi, BB, Beginning);
  ValueToMemoryAccess[BB] = Phi;
  return Phi;
}

MemoryUseOrDef *MemorySSA::createDefinedAccess(Instruction *I,
                                               MemoryAccess *Definition,
                                               const MemoryUseOrDef *Template,
                                               bool CreationMustSucceed) {
  assert(!isa<PHINode>(I) && "Cannot create a defined access for a PHI");
  MemoryUseOrDef *NewAccess = createNewAccess(I, AA, Template);
  if (CreationMustSucceed)
    assert(NewAccess != nullptr && "Tried to create a memory access for a "
                                   "non-memory touching instruction");
  if (NewAccess)
    NewAccess->setDefiningAccess(Definition);
  return NewAccess;
}

// Return true if the instruction has ordering constraints.
// Note specifically that this only considers stores and loads
// because others are still considered ModRef by getModRefInfo.
static inline bool isOrdered(const Instruction *I) {
  if (auto *SI = dyn_cast<StoreInst>(I)) {
    if (!SI->isUnordered())
      return true;
  } else if (auto *LI = dyn_cast<LoadInst>(I)) {
    if (!LI->isUnordered())
      return true;
  }
  return false;
}

/// Helper function to create new memory accesses
template <typename AliasAnalysisType>
MemoryUseOrDef *MemorySSA::createNewAccess(Instruction *I,
                                           AliasAnalysisType *AAP,
                                           const MemoryUseOrDef *Template) {
  // The assume intrinsic has a control dependency which we model by claiming
  // that it writes arbitrarily. Debuginfo intrinsics may be considered
  // clobbers when we have a nonstandard AA pipeline. Ignore these fake memory
  // dependencies here.
  // FIXME: Replace this special casing with a more accurate modelling of
  // assume's control dependency.
  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I))
    if (II->getIntrinsicID() == Intrinsic::assume)
      return nullptr;

  // Using a nonstandard AA pipelines might leave us with unexpected modref
  // results for I, so add a check to not model instructions that may not read
  // from or write to memory. This is necessary for correctness.
  if (!I->mayReadFromMemory() && !I->mayWriteToMemory())
    return nullptr;

  bool Def, Use;
  if (Template) {
    Def = dyn_cast_or_null<MemoryDef>(Template) != nullptr;
    Use = dyn_cast_or_null<MemoryUse>(Template) != nullptr;
#if !defined(NDEBUG)
    ModRefInfo ModRef = AAP->getModRefInfo(I, None);
    bool DefCheck, UseCheck;
    DefCheck = isModSet(ModRef) || isOrdered(I);
    UseCheck = isRefSet(ModRef);
    assert(Def == DefCheck && (Def || Use == UseCheck) && "Invalid template");
#endif
  } else {
    // Find out what affect this instruction has on memory.
    ModRefInfo ModRef = AAP->getModRefInfo(I, None);
    // The isOrdered check is used to ensure that volatiles end up as defs
    // (atomics end up as ModRef right now anyway).  Until we separate the
    // ordering chain from the memory chain, this enables people to see at least
    // some relative ordering to volatiles.  Note that getClobberingMemoryAccess
    // will still give an answer that bypasses other volatile loads.  TODO:
    // Separate memory aliasing and ordering into two different chains so that
    // we can precisely represent both "what memory will this read/write/is
    // clobbered by" and "what instructions can I move this past".
    Def = isModSet(ModRef) || isOrdered(I);
    Use = isRefSet(ModRef);
  }

  // It's possible for an instruction to not modify memory at all. During
  // construction, we ignore them.
  if (!Def && !Use)
    return nullptr;

  MemoryUseOrDef *MUD;
  if (Def)
    MUD = new MemoryDef(I->getContext(), nullptr, I, I->getParent(), NextID++);
  else
    MUD = new MemoryUse(I->getContext(), nullptr, I, I->getParent());
  ValueToMemoryAccess[I] = MUD;
  return MUD;
}

/// Returns true if \p Replacer dominates \p Replacee .
bool MemorySSA::dominatesUse(const MemoryAccess *Replacer,
                             const MemoryAccess *Replacee) const {
  if (isa<MemoryUseOrDef>(Replacee))
    return DT->dominates(Replacer->getBlock(), Replacee->getBlock());
  const auto *MP = cast<MemoryPhi>(Replacee);
  // For a phi node, the use occurs in the predecessor block of the phi node.
  // Since we may occur multiple times in the phi node, we have to check each
  // operand to ensure Replacer dominates each operand where Replacee occurs.
  for (const Use &Arg : MP->operands()) {
    if (Arg.get() != Replacee &&
        !DT->dominates(Replacer->getBlock(), MP->getIncomingBlock(Arg)))
      return false;
  }
  return true;
}

/// Properly remove \p MA from all of MemorySSA's lookup tables.
void MemorySSA::removeFromLookups(MemoryAccess *MA) {
  assert(MA->use_empty() &&
         "Trying to remove memory access that still has uses");
  BlockNumbering.erase(MA);
  if (auto *MUD = dyn_cast<MemoryUseOrDef>(MA))
    MUD->setDefiningAccess(nullptr);
  // Invalidate our walker's cache if necessary
  if (!isa<MemoryUse>(MA))
    getWalker()->invalidateInfo(MA);

  Value *MemoryInst;
  if (const auto *MUD = dyn_cast<MemoryUseOrDef>(MA))
    MemoryInst = MUD->getMemoryInst();
  else
    MemoryInst = MA->getBlock();

  auto VMA = ValueToMemoryAccess.find(MemoryInst);
  if (VMA->second == MA)
    ValueToMemoryAccess.erase(VMA);
}

/// Properly remove \p MA from all of MemorySSA's lists.
///
/// Because of the way the intrusive list and use lists work, it is important to
/// do removal in the right order.
/// ShouldDelete defaults to true, and will cause the memory access to also be
/// deleted, not just removed.
void MemorySSA::removeFromLists(MemoryAccess *MA, bool ShouldDelete) {
  BasicBlock *BB = MA->getBlock();
  // The access list owns the reference, so we erase it from the non-owning list
  // first.
  if (!isa<MemoryUse>(MA)) {
    auto DefsIt = PerBlockDefs.find(BB);
    std::unique_ptr<DefsList> &Defs = DefsIt->second;
    Defs->remove(*MA);
    if (Defs->empty())
      PerBlockDefs.erase(DefsIt);
  }

  // The erase call here will delete it. If we don't want it deleted, we call
  // remove instead.
  auto AccessIt = PerBlockAccesses.find(BB);
  std::unique_ptr<AccessList> &Accesses = AccessIt->second;
  if (ShouldDelete)
    Accesses->erase(MA);
  else
    Accesses->remove(MA);

  if (Accesses->empty()) {
    PerBlockAccesses.erase(AccessIt);
    BlockNumberingValid.erase(BB);
  }
}

void MemorySSA::print(raw_ostream &OS) const {
  MemorySSAAnnotatedWriter Writer(this);
  F.print(OS, &Writer);
}

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MemorySSA::dump() const { print(dbgs()); }
#endif

void MemorySSA::verifyMemorySSA() const {
  verifyOrderingDominationAndDefUses(F);
  verifyDominationNumbers(F);
  verifyPrevDefInPhis(F);
  // Previously, the verification used to also verify that the clobberingAccess
  // cached by MemorySSA is the same as the clobberingAccess found at a later
  // query to AA. This does not hold true in general due to the current fragility
  // of BasicAA which has arbitrary caps on the things it analyzes before giving
  // up. As a result, transformations that are correct, will lead to BasicAA
  // returning different Alias answers before and after that transformation.
  // Invalidating MemorySSA is not an option, as the results in BasicAA can be so
  // random, in the worst case we'd need to rebuild MemorySSA from scratch after
  // every transformation, which defeats the purpose of using it. For such an
  // example, see test4 added in D51960.
}

void MemorySSA::verifyPrevDefInPhis(Function &F) const {
#if !defined(NDEBUG) && defined(EXPENSIVE_CHECKS)
  for (const BasicBlock &BB : F) {
    if (MemoryPhi *Phi = getMemoryAccess(&BB)) {
      for (unsigned I = 0, E = Phi->getNumIncomingValues(); I != E; ++I) {
        auto *Pred = Phi->getIncomingBlock(I);
        auto *IncAcc = Phi->getIncomingValue(I);
        // If Pred has no unreachable predecessors, get last def looking at
        // IDoms. If, while walkings IDoms, any of these has an unreachable
        // predecessor, then the incoming def can be any access.
        if (auto *DTNode = DT->getNode(Pred)) {
          while (DTNode) {
            if (auto *DefList = getBlockDefs(DTNode->getBlock())) {
              auto *LastAcc = &*(--DefList->end());
              assert(LastAcc == IncAcc &&
                     "Incorrect incoming access into phi.");
              break;
            }
            DTNode = DTNode->getIDom();
          }
        } else {
          // If Pred has unreachable predecessors, but has at least a Def, the
          // incoming access can be the last Def in Pred, or it could have been
          // optimized to LoE. After an update, though, the LoE may have been
          // replaced by another access, so IncAcc may be any access.
          // If Pred has unreachable predecessors and no Defs, incoming access
          // should be LoE; However, after an update, it may be any access.
        }
      }
    }
  }
#endif
}

/// Verify that all of the blocks we believe to have valid domination numbers
/// actually have valid domination numbers.
void MemorySSA::verifyDominationNumbers(const Function &F) const {
#ifndef NDEBUG
  if (BlockNumberingValid.empty())
    return;

  SmallPtrSet<const BasicBlock *, 16> ValidBlocks = BlockNumberingValid;
  for (const BasicBlock &BB : F) {
    if (!ValidBlocks.count(&BB))
      continue;

    ValidBlocks.erase(&BB);

    const AccessList *Accesses = getBlockAccesses(&BB);
    // It's correct to say an empty block has valid numbering.
    if (!Accesses)
      continue;

    // Block numbering starts at 1.
    unsigned long LastNumber = 0;
    for (const MemoryAccess &MA : *Accesses) {
      auto ThisNumberIter = BlockNumbering.find(&MA);
      assert(ThisNumberIter != BlockNumbering.end() &&
             "MemoryAccess has no domination number in a valid block!");

      unsigned long ThisNumber = ThisNumberIter->second;
      assert(ThisNumber > LastNumber &&
             "Domination numbers should be strictly increasing!");
      LastNumber = ThisNumber;
    }
  }

  assert(ValidBlocks.empty() &&
         "All valid BasicBlocks should exist in F -- dangling pointers?");
#endif
}

/// Verify ordering: the order and existence of MemoryAccesses matches the
/// order and existence of memory affecting instructions.
/// Verify domination: each definition dominates all of its uses.
/// Verify def-uses: the immediate use information - walk all the memory
/// accesses and verifying that, for each use, it appears in the appropriate
/// def's use list
void MemorySSA::verifyOrderingDominationAndDefUses(Function &F) const {
#if !defined(NDEBUG)
  // Walk all the blocks, comparing what the lookups think and what the access
  // lists think, as well as the order in the blocks vs the order in the access
  // lists.
  SmallVector<MemoryAccess *, 32> ActualAccesses;
  SmallVector<MemoryAccess *, 32> ActualDefs;
  for (BasicBlock &B : F) {
    const AccessList *AL = getBlockAccesses(&B);
    const auto *DL = getBlockDefs(&B);
    MemoryPhi *Phi = getMemoryAccess(&B);
    if (Phi) {
      // Verify ordering.
      ActualAccesses.push_back(Phi);
      ActualDefs.push_back(Phi);
      // Verify domination
      for (const Use &U : Phi->uses())
        assert(dominates(Phi, U) && "Memory PHI does not dominate it's uses");
#if defined(EXPENSIVE_CHECKS)
      // Verify def-uses.
      assert(Phi->getNumOperands() == static_cast<unsigned>(std::distance(
                                          pred_begin(&B), pred_end(&B))) &&
             "Incomplete MemoryPhi Node");
      for (unsigned I = 0, E = Phi->getNumIncomingValues(); I != E; ++I) {
        verifyUseInDefs(Phi->getIncomingValue(I), Phi);
        assert(find(predecessors(&B), Phi->getIncomingBlock(I)) !=
                   pred_end(&B) &&
               "Incoming phi block not a block predecessor");
      }
#endif
    }

    for (Instruction &I : B) {
      MemoryUseOrDef *MA = getMemoryAccess(&I);
      assert((!MA || (AL && (isa<MemoryUse>(MA) || DL))) &&
             "We have memory affecting instructions "
             "in this block but they are not in the "
             "access list or defs list");
      if (MA) {
        // Verify ordering.
        ActualAccesses.push_back(MA);
        if (MemoryAccess *MD = dyn_cast<MemoryDef>(MA)) {
          // Verify ordering.
          ActualDefs.push_back(MA);
          // Verify domination.
          for (const Use &U : MD->uses())
            assert(dominates(MD, U) &&
                   "Memory Def does not dominate it's uses");
        }
#if defined(EXPENSIVE_CHECKS)
        // Verify def-uses.
        verifyUseInDefs(MA->getDefiningAccess(), MA);
#endif
      }
    }
    // Either we hit the assert, really have no accesses, or we have both
    // accesses and an access list. Same with defs.
    if (!AL && !DL)
      continue;
    // Verify ordering.
    assert(AL->size() == ActualAccesses.size() &&
           "We don't have the same number of accesses in the block as on the "
           "access list");
    assert((DL || ActualDefs.size() == 0) &&
           "Either we should have a defs list, or we should have no defs");
    assert((!DL || DL->size() == ActualDefs.size()) &&
           "We don't have the same number of defs in the block as on the "
           "def list");
    auto ALI = AL->begin();
    auto AAI = ActualAccesses.begin();
    while (ALI != AL->end() && AAI != ActualAccesses.end()) {
      assert(&*ALI == *AAI && "Not the same accesses in the same order");
      ++ALI;
      ++AAI;
    }
    ActualAccesses.clear();
    if (DL) {
      auto DLI = DL->begin();
      auto ADI = ActualDefs.begin();
      while (DLI != DL->end() && ADI != ActualDefs.end()) {
        assert(&*DLI == *ADI && "Not the same defs in the same order");
        ++DLI;
        ++ADI;
      }
    }
    ActualDefs.clear();
  }
#endif
}

/// Verify the def-use lists in MemorySSA, by verifying that \p Use
/// appears in the use list of \p Def.
void MemorySSA::verifyUseInDefs(MemoryAccess *Def, MemoryAccess *Use) const {
#ifndef NDEBUG
  // The live on entry use may cause us to get a NULL def here
  if (!Def)
    assert(isLiveOnEntryDef(Use) &&
           "Null def but use not point to live on entry def");
  else
    assert(is_contained(Def->users(), Use) &&
           "Did not find use in def's use list");
#endif
}

/// Perform a local numbering on blocks so that instruction ordering can be
/// determined in constant time.
/// TODO: We currently just number in order.  If we numbered by N, we could
/// allow at least N-1 sequences of insertBefore or insertAfter (and at least
/// log2(N) sequences of mixed before and after) without needing to invalidate
/// the numbering.
void MemorySSA::renumberBlock(const BasicBlock *B) const {
  // The pre-increment ensures the numbers really start at 1.
  unsigned long CurrentNumber = 0;
  const AccessList *AL = getBlockAccesses(B);
  assert(AL != nullptr && "Asking to renumber an empty block");
  for (const auto &I : *AL)
    BlockNumbering[&I] = ++CurrentNumber;
  BlockNumberingValid.insert(B);
}

/// Determine, for two memory accesses in the same block,
/// whether \p Dominator dominates \p Dominatee.
/// \returns True if \p Dominator dominates \p Dominatee.
bool MemorySSA::locallyDominates(const MemoryAccess *Dominator,
                                 const MemoryAccess *Dominatee) const {
  const BasicBlock *DominatorBlock = Dominator->getBlock();

  assert((DominatorBlock == Dominatee->getBlock()) &&
         "Asking for local domination when accesses are in different blocks!");
  // A node dominates itself.
  if (Dominatee == Dominator)
    return true;

  // When Dominatee is defined on function entry, it is not dominated by another
  // memory access.
  if (isLiveOnEntryDef(Dominatee))
    return false;

  // When Dominator is defined on function entry, it dominates the other memory
  // access.
  if (isLiveOnEntryDef(Dominator))
    return true;

  if (!BlockNumberingValid.count(DominatorBlock))
    renumberBlock(DominatorBlock);

  unsigned long DominatorNum = BlockNumbering.lookup(Dominator);
  // All numbers start with 1
  assert(DominatorNum != 0 && "Block was not numbered properly");
  unsigned long DominateeNum = BlockNumbering.lookup(Dominatee);
  assert(DominateeNum != 0 && "Block was not numbered properly");
  return DominatorNum < DominateeNum;
}

bool MemorySSA::dominates(const MemoryAccess *Dominator,
                          const MemoryAccess *Dominatee) const {
  if (Dominator == Dominatee)
    return true;

  if (isLiveOnEntryDef(Dominatee))
    return false;

  if (Dominator->getBlock() != Dominatee->getBlock())
    return DT->dominates(Dominator->getBlock(), Dominatee->getBlock());
  return locallyDominates(Dominator, Dominatee);
}

bool MemorySSA::dominates(const MemoryAccess *Dominator,
                          const Use &Dominatee) const {
  if (MemoryPhi *MP = dyn_cast<MemoryPhi>(Dominatee.getUser())) {
    BasicBlock *UseBB = MP->getIncomingBlock(Dominatee);
    // The def must dominate the incoming block of the phi.
    if (UseBB != Dominator->getBlock())
      return DT->dominates(Dominator->getBlock(), UseBB);
    // If the UseBB and the DefBB are the same, compare locally.
    return locallyDominates(Dominator, cast<MemoryAccess>(Dominatee));
  }
  // If it's not a PHI node use, the normal dominates can already handle it.
  return dominates(Dominator, cast<MemoryAccess>(Dominatee.getUser()));
}

const static char LiveOnEntryStr[] = "liveOnEntry";

void MemoryAccess::print(raw_ostream &OS) const {
  switch (getValueID()) {
  case MemoryPhiVal: return static_cast<const MemoryPhi *>(this)->print(OS);
  case MemoryDefVal: return static_cast<const MemoryDef *>(this)->print(OS);
  case MemoryUseVal: return static_cast<const MemoryUse *>(this)->print(OS);
  }
  llvm_unreachable("invalid value id");
}

void MemoryDef::print(raw_ostream &OS) const {
  MemoryAccess *UO = getDefiningAccess();

  auto printID = [&OS](MemoryAccess *A) {
    if (A && A->getID())
      OS << A->getID();
    else
      OS << LiveOnEntryStr;
  };

  OS << getID() << " = MemoryDef(";
  printID(UO);
  OS << ")";

  if (isOptimized()) {
    OS << "->";
    printID(getOptimized());

    if (Optional<AliasResult> AR = getOptimizedAccessType())
      OS << " " << *AR;
  }
}

void MemoryPhi::print(raw_ostream &OS) const {
  bool First = true;
  OS << getID() << " = MemoryPhi(";
  for (const auto &Op : operands()) {
    BasicBlock *BB = getIncomingBlock(Op);
    MemoryAccess *MA = cast<MemoryAccess>(Op);
    if (!First)
      OS << ',';
    else
      First = false;

    OS << '{';
    if (BB->hasName())
      OS << BB->getName();
    else
      BB->printAsOperand(OS, false);
    OS << ',';
    if (unsigned ID = MA->getID())
      OS << ID;
    else
      OS << LiveOnEntryStr;
    OS << '}';
  }
  OS << ')';
}

void MemoryUse::print(raw_ostream &OS) const {
  MemoryAccess *UO = getDefiningAccess();
  OS << "MemoryUse(";
  if (UO && UO->getID())
    OS << UO->getID();
  else
    OS << LiveOnEntryStr;
  OS << ')';

  if (Optional<AliasResult> AR = getOptimizedAccessType())
    OS << " " << *AR;
}

void MemoryAccess::dump() const {
// Cannot completely remove virtual function even in release mode.
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
  print(dbgs());
  dbgs() << "\n";
#endif
}

char MemorySSAPrinterLegacyPass::ID = 0;

MemorySSAPrinterLegacyPass::MemorySSAPrinterLegacyPass() : FunctionPass(ID) {
  initializeMemorySSAPrinterLegacyPassPass(*PassRegistry::getPassRegistry());
}

void MemorySSAPrinterLegacyPass::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.setPreservesAll();
  AU.addRequired<MemorySSAWrapperPass>();
}

bool MemorySSAPrinterLegacyPass::runOnFunction(Function &F) {
  auto &MSSA = getAnalysis<MemorySSAWrapperPass>().getMSSA();
  MSSA.print(dbgs());
  if (VerifyMemorySSA)
    MSSA.verifyMemorySSA();
  return false;
}

AnalysisKey MemorySSAAnalysis::Key;

MemorySSAAnalysis::Result MemorySSAAnalysis::run(Function &F,
                                                 FunctionAnalysisManager &AM) {
  auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
  auto &AA = AM.getResult<AAManager>(F);
  return MemorySSAAnalysis::Result(std::make_unique<MemorySSA>(F, &AA, &DT));
}

bool MemorySSAAnalysis::Result::invalidate(
    Function &F, const PreservedAnalyses &PA,
    FunctionAnalysisManager::Invalidator &Inv) {
  auto PAC = PA.getChecker<MemorySSAAnalysis>();
  return !(PAC.preserved() || PAC.preservedSet<AllAnalysesOn<Function>>()) ||
         Inv.invalidate<AAManager>(F, PA) ||
         Inv.invalidate<DominatorTreeAnalysis>(F, PA);
}

PreservedAnalyses MemorySSAPrinterPass::run(Function &F,
                                            FunctionAnalysisManager &AM) {
  OS << "MemorySSA for function: " << F.getName() << "\n";
  AM.getResult<MemorySSAAnalysis>(F).getMSSA().print(OS);

  return PreservedAnalyses::all();
}

PreservedAnalyses MemorySSAVerifierPass::run(Function &F,
                                             FunctionAnalysisManager &AM) {
  AM.getResult<MemorySSAAnalysis>(F).getMSSA().verifyMemorySSA();

  return PreservedAnalyses::all();
}

char MemorySSAWrapperPass::ID = 0;

MemorySSAWrapperPass::MemorySSAWrapperPass() : FunctionPass(ID) {
  initializeMemorySSAWrapperPassPass(*PassRegistry::getPassRegistry());
}

void MemorySSAWrapperPass::releaseMemory() { MSSA.reset(); }

void MemorySSAWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.setPreservesAll();
  AU.addRequiredTransitive<DominatorTreeWrapperPass>();
  AU.addRequiredTransitive<AAResultsWrapperPass>();
}

bool MemorySSAWrapperPass::runOnFunction(Function &F) {
  auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  auto &AA = getAnalysis<AAResultsWrapperPass>().getAAResults();
  MSSA.reset(new MemorySSA(F, &AA, &DT));
  return false;
}

void MemorySSAWrapperPass::verifyAnalysis() const {
  if (VerifyMemorySSA)
    MSSA->verifyMemorySSA();
}

void MemorySSAWrapperPass::print(raw_ostream &OS, const Module *M) const {
  MSSA->print(OS);
}

MemorySSAWalker::MemorySSAWalker(MemorySSA *M) : MSSA(M) {}

/// Walk the use-def chains starting at \p StartingAccess and find
/// the MemoryAccess that actually clobbers Loc.
///
/// \returns our clobbering memory access
template <typename AliasAnalysisType>
MemoryAccess *
MemorySSA::ClobberWalkerBase<AliasAnalysisType>::getClobberingMemoryAccessBase(
    MemoryAccess *StartingAccess, const MemoryLocation &Loc,
    unsigned &UpwardWalkLimit) {
  if (isa<MemoryPhi>(StartingAccess))
    return StartingAccess;

  auto *StartingUseOrDef = cast<MemoryUseOrDef>(StartingAccess);
  if (MSSA->isLiveOnEntryDef(StartingUseOrDef))
    return StartingUseOrDef;

  Instruction *I = StartingUseOrDef->getMemoryInst();

  // Conservatively, fences are always clobbers, so don't perform the walk if we
  // hit a fence.
  if (!isa<CallBase>(I) && I->isFenceLike())
    return StartingUseOrDef;

  UpwardsMemoryQuery Q;
  Q.OriginalAccess = StartingUseOrDef;
  Q.StartingLoc = Loc;
  Q.Inst = I;
  Q.IsCall = false;

  // Unlike the other function, do not walk to the def of a def, because we are
  // handed something we already believe is the clobbering access.
  // We never set SkipSelf to true in Q in this method.
  MemoryAccess *DefiningAccess = isa<MemoryUse>(StartingUseOrDef)
                                     ? StartingUseOrDef->getDefiningAccess()
                                     : StartingUseOrDef;

  MemoryAccess *Clobber =
      Walker.findClobber(DefiningAccess, Q, UpwardWalkLimit);
  LLVM_DEBUG(dbgs() << "Starting Memory SSA clobber for " << *I << " is ");
  LLVM_DEBUG(dbgs() << *StartingUseOrDef << "\n");
  LLVM_DEBUG(dbgs() << "Final Memory SSA clobber for " << *I << " is ");
  LLVM_DEBUG(dbgs() << *Clobber << "\n");
  return Clobber;
}

template <typename AliasAnalysisType>
MemoryAccess *
MemorySSA::ClobberWalkerBase<AliasAnalysisType>::getClobberingMemoryAccessBase(
    MemoryAccess *MA, unsigned &UpwardWalkLimit, bool SkipSelf) {
  auto *StartingAccess = dyn_cast<MemoryUseOrDef>(MA);
  // If this is a MemoryPhi, we can't do anything.
  if (!StartingAccess)
    return MA;

  bool IsOptimized = false;

  // If this is an already optimized use or def, return the optimized result.
  // Note: Currently, we store the optimized def result in a separate field,
  // since we can't use the defining access.
  if (StartingAccess->isOptimized()) {
    if (!SkipSelf || !isa<MemoryDef>(StartingAccess))
      return StartingAccess->getOptimized();
    IsOptimized = true;
  }

  const Instruction *I = StartingAccess->getMemoryInst();
  // We can't sanely do anything with a fence, since they conservatively clobber
  // all memory, and have no locations to get pointers from to try to
  // disambiguate.
  if (!isa<CallBase>(I) && I->isFenceLike())
    return StartingAccess;

  UpwardsMemoryQuery Q(I, StartingAccess);

  if (isUseTriviallyOptimizableToLiveOnEntry(*Walker.getAA(), I)) {
    MemoryAccess *LiveOnEntry = MSSA->getLiveOnEntryDef();
    StartingAccess->setOptimized(LiveOnEntry);
    StartingAccess->setOptimizedAccessType(None);
    return LiveOnEntry;
  }

  MemoryAccess *OptimizedAccess;
  if (!IsOptimized) {
    // Start with the thing we already think clobbers this location
    MemoryAccess *DefiningAccess = StartingAccess->getDefiningAccess();

    // At this point, DefiningAccess may be the live on entry def.
    // If it is, we will not get a better result.
    if (MSSA->isLiveOnEntryDef(DefiningAccess)) {
      StartingAccess->setOptimized(DefiningAccess);
      StartingAccess->setOptimizedAccessType(None);
      return DefiningAccess;
    }

    OptimizedAccess = Walker.findClobber(DefiningAccess, Q, UpwardWalkLimit);
    StartingAccess->setOptimized(OptimizedAccess);
    if (MSSA->isLiveOnEntryDef(OptimizedAccess))
      StartingAccess->setOptimizedAccessType(None);
    else if (Q.AR == MustAlias)
      StartingAccess->setOptimizedAccessType(MustAlias);
  } else
    OptimizedAccess = StartingAccess->getOptimized();

  LLVM_DEBUG(dbgs() << "Starting Memory SSA clobber for " << *I << " is ");
  LLVM_DEBUG(dbgs() << *StartingAccess << "\n");
  LLVM_DEBUG(dbgs() << "Optimized Memory SSA clobber for " << *I << " is ");
  LLVM_DEBUG(dbgs() << *OptimizedAccess << "\n");

  MemoryAccess *Result;
  if (SkipSelf && isa<MemoryPhi>(OptimizedAccess) &&
      isa<MemoryDef>(StartingAccess) && UpwardWalkLimit) {
    assert(isa<MemoryDef>(Q.OriginalAccess));
    Q.SkipSelfAccess = true;
    Result = Walker.findClobber(OptimizedAccess, Q, UpwardWalkLimit);
  } else
    Result = OptimizedAccess;

  LLVM_DEBUG(dbgs() << "Result Memory SSA clobber [SkipSelf = " << SkipSelf);
  LLVM_DEBUG(dbgs() << "] for " << *I << " is " << *Result << "\n");

  return Result;
}

MemoryAccess *
DoNothingMemorySSAWalker::getClobberingMemoryAccess(MemoryAccess *MA) {
  if (auto *Use = dyn_cast<MemoryUseOrDef>(MA))
    return Use->getDefiningAccess();
  return MA;
}

MemoryAccess *DoNothingMemorySSAWalker::getClobberingMemoryAccess(
    MemoryAccess *StartingAccess, const MemoryLocation &) {
  if (auto *Use = dyn_cast<MemoryUseOrDef>(StartingAccess))
    return Use->getDefiningAccess();
  return StartingAccess;
}

void MemoryPhi::deleteMe(DerivedUser *Self) {
  delete static_cast<MemoryPhi *>(Self);
}

void MemoryDef::deleteMe(DerivedUser *Self) {
  delete static_cast<MemoryDef *>(Self);
}

void MemoryUse::deleteMe(DerivedUser *Self) {
  delete static_cast<MemoryUse *>(Self);
}