summaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86FrameLowering.cpp
blob: f70be1d2c19fe18e29d3289e9c00b2dfb4a9b540 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
//===-- X86FrameLowering.cpp - X86 Frame Information ----------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains the X86 implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//

#include "X86FrameLowering.h"
#include "X86InstrBuilder.h"
#include "X86InstrInfo.h"
#include "X86MachineFunctionInfo.h"
#include "X86Subtarget.h"
#include "X86TargetMachine.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/DataLayout.h"
#include "llvm/Function.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetOptions.h"

using namespace llvm;

// FIXME: completely move here.
extern cl::opt<bool> ForceStackAlign;

bool X86FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const {
  return !MF.getFrameInfo()->hasVarSizedObjects();
}

/// hasFP - Return true if the specified function should have a dedicated frame
/// pointer register.  This is true if the function has variable sized allocas
/// or if frame pointer elimination is disabled.
bool X86FrameLowering::hasFP(const MachineFunction &MF) const {
  const MachineFrameInfo *MFI = MF.getFrameInfo();
  const MachineModuleInfo &MMI = MF.getMMI();
  const TargetRegisterInfo *RegInfo = TM.getRegisterInfo();

  return (MF.getTarget().Options.DisableFramePointerElim(MF) ||
          RegInfo->needsStackRealignment(MF) ||
          MFI->hasVarSizedObjects() ||
          MFI->isFrameAddressTaken() ||
          MF.getInfo<X86MachineFunctionInfo>()->getForceFramePointer() ||
          MMI.callsUnwindInit() || MMI.callsEHReturn());
}

static unsigned getSUBriOpcode(unsigned is64Bit, int64_t Imm) {
  if (is64Bit) {
    if (isInt<8>(Imm))
      return X86::SUB64ri8;
    return X86::SUB64ri32;
  } else {
    if (isInt<8>(Imm))
      return X86::SUB32ri8;
    return X86::SUB32ri;
  }
}

static unsigned getADDriOpcode(unsigned is64Bit, int64_t Imm) {
  if (is64Bit) {
    if (isInt<8>(Imm))
      return X86::ADD64ri8;
    return X86::ADD64ri32;
  } else {
    if (isInt<8>(Imm))
      return X86::ADD32ri8;
    return X86::ADD32ri;
  }
}

static unsigned getLEArOpcode(unsigned is64Bit) {
  return is64Bit ? X86::LEA64r : X86::LEA32r;
}

/// findDeadCallerSavedReg - Return a caller-saved register that isn't live
/// when it reaches the "return" instruction. We can then pop a stack object
/// to this register without worry about clobbering it.
static unsigned findDeadCallerSavedReg(MachineBasicBlock &MBB,
                                       MachineBasicBlock::iterator &MBBI,
                                       const TargetRegisterInfo &TRI,
                                       bool Is64Bit) {
  const MachineFunction *MF = MBB.getParent();
  const Function *F = MF->getFunction();
  if (!F || MF->getMMI().callsEHReturn())
    return 0;

  static const uint16_t CallerSavedRegs32Bit[] = {
    X86::EAX, X86::EDX, X86::ECX, 0
  };

  static const uint16_t CallerSavedRegs64Bit[] = {
    X86::RAX, X86::RDX, X86::RCX, X86::RSI, X86::RDI,
    X86::R8,  X86::R9,  X86::R10, X86::R11, 0
  };

  unsigned Opc = MBBI->getOpcode();
  switch (Opc) {
  default: return 0;
  case X86::RET:
  case X86::RETI:
  case X86::TCRETURNdi:
  case X86::TCRETURNri:
  case X86::TCRETURNmi:
  case X86::TCRETURNdi64:
  case X86::TCRETURNri64:
  case X86::TCRETURNmi64:
  case X86::EH_RETURN:
  case X86::EH_RETURN64: {
    SmallSet<uint16_t, 8> Uses;
    for (unsigned i = 0, e = MBBI->getNumOperands(); i != e; ++i) {
      MachineOperand &MO = MBBI->getOperand(i);
      if (!MO.isReg() || MO.isDef())
        continue;
      unsigned Reg = MO.getReg();
      if (!Reg)
        continue;
      for (MCRegAliasIterator AI(Reg, &TRI, true); AI.isValid(); ++AI)
        Uses.insert(*AI);
    }

    const uint16_t *CS = Is64Bit ? CallerSavedRegs64Bit : CallerSavedRegs32Bit;
    for (; *CS; ++CS)
      if (!Uses.count(*CS))
        return *CS;
  }
  }

  return 0;
}


/// emitSPUpdate - Emit a series of instructions to increment / decrement the
/// stack pointer by a constant value.
static
void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
                  unsigned StackPtr, int64_t NumBytes,
                  bool Is64Bit, bool UseLEA,
                  const TargetInstrInfo &TII, const TargetRegisterInfo &TRI) {
  bool isSub = NumBytes < 0;
  uint64_t Offset = isSub ? -NumBytes : NumBytes;
  unsigned Opc;
  if (UseLEA)
    Opc = getLEArOpcode(Is64Bit);
  else
    Opc = isSub
      ? getSUBriOpcode(Is64Bit, Offset)
      : getADDriOpcode(Is64Bit, Offset);

  uint64_t Chunk = (1LL << 31) - 1;
  DebugLoc DL = MBB.findDebugLoc(MBBI);

  while (Offset) {
    uint64_t ThisVal = (Offset > Chunk) ? Chunk : Offset;
    if (ThisVal == (Is64Bit ? 8 : 4)) {
      // Use push / pop instead.
      unsigned Reg = isSub
        ? (unsigned)(Is64Bit ? X86::RAX : X86::EAX)
        : findDeadCallerSavedReg(MBB, MBBI, TRI, Is64Bit);
      if (Reg) {
        Opc = isSub
          ? (Is64Bit ? X86::PUSH64r : X86::PUSH32r)
          : (Is64Bit ? X86::POP64r  : X86::POP32r);
        MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc))
          .addReg(Reg, getDefRegState(!isSub) | getUndefRegState(isSub));
        if (isSub)
          MI->setFlag(MachineInstr::FrameSetup);
        Offset -= ThisVal;
        continue;
      }
    }

    MachineInstr *MI = NULL;

    if (UseLEA) {
      MI =  addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr),
                          StackPtr, false, isSub ? -ThisVal : ThisVal);
    } else {
      MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
            .addReg(StackPtr)
            .addImm(ThisVal);
      MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
    }

    if (isSub)
      MI->setFlag(MachineInstr::FrameSetup);

    Offset -= ThisVal;
  }
}

/// mergeSPUpdatesUp - Merge two stack-manipulating instructions upper iterator.
static
void mergeSPUpdatesUp(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
                      unsigned StackPtr, uint64_t *NumBytes = NULL) {
  if (MBBI == MBB.begin()) return;

  MachineBasicBlock::iterator PI = prior(MBBI);
  unsigned Opc = PI->getOpcode();
  if ((Opc == X86::ADD64ri32 || Opc == X86::ADD64ri8 ||
       Opc == X86::ADD32ri || Opc == X86::ADD32ri8 ||
       Opc == X86::LEA32r || Opc == X86::LEA64_32r) &&
      PI->getOperand(0).getReg() == StackPtr) {
    if (NumBytes)
      *NumBytes += PI->getOperand(2).getImm();
    MBB.erase(PI);
  } else if ((Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
              Opc == X86::SUB32ri || Opc == X86::SUB32ri8) &&
             PI->getOperand(0).getReg() == StackPtr) {
    if (NumBytes)
      *NumBytes -= PI->getOperand(2).getImm();
    MBB.erase(PI);
  }
}

/// mergeSPUpdatesDown - Merge two stack-manipulating instructions lower iterator.
static
void mergeSPUpdatesDown(MachineBasicBlock &MBB,
                        MachineBasicBlock::iterator &MBBI,
                        unsigned StackPtr, uint64_t *NumBytes = NULL) {
  // FIXME:  THIS ISN'T RUN!!!
  return;

  if (MBBI == MBB.end()) return;

  MachineBasicBlock::iterator NI = llvm::next(MBBI);
  if (NI == MBB.end()) return;

  unsigned Opc = NI->getOpcode();
  if ((Opc == X86::ADD64ri32 || Opc == X86::ADD64ri8 ||
       Opc == X86::ADD32ri || Opc == X86::ADD32ri8) &&
      NI->getOperand(0).getReg() == StackPtr) {
    if (NumBytes)
      *NumBytes -= NI->getOperand(2).getImm();
    MBB.erase(NI);
    MBBI = NI;
  } else if ((Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
              Opc == X86::SUB32ri || Opc == X86::SUB32ri8) &&
             NI->getOperand(0).getReg() == StackPtr) {
    if (NumBytes)
      *NumBytes += NI->getOperand(2).getImm();
    MBB.erase(NI);
    MBBI = NI;
  }
}

/// mergeSPUpdates - Checks the instruction before/after the passed
/// instruction. If it is an ADD/SUB/LEA instruction it is deleted argument and the
/// stack adjustment is returned as a positive value for ADD/LEA and a negative for
/// SUB.
static int mergeSPUpdates(MachineBasicBlock &MBB,
                           MachineBasicBlock::iterator &MBBI,
                           unsigned StackPtr,
                           bool doMergeWithPrevious) {
  if ((doMergeWithPrevious && MBBI == MBB.begin()) ||
      (!doMergeWithPrevious && MBBI == MBB.end()))
    return 0;

  MachineBasicBlock::iterator PI = doMergeWithPrevious ? prior(MBBI) : MBBI;
  MachineBasicBlock::iterator NI = doMergeWithPrevious ? 0 : llvm::next(MBBI);
  unsigned Opc = PI->getOpcode();
  int Offset = 0;

  if ((Opc == X86::ADD64ri32 || Opc == X86::ADD64ri8 ||
       Opc == X86::ADD32ri || Opc == X86::ADD32ri8 ||
       Opc == X86::LEA32r || Opc == X86::LEA64_32r) &&
      PI->getOperand(0).getReg() == StackPtr){
    Offset += PI->getOperand(2).getImm();
    MBB.erase(PI);
    if (!doMergeWithPrevious) MBBI = NI;
  } else if ((Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
              Opc == X86::SUB32ri || Opc == X86::SUB32ri8) &&
             PI->getOperand(0).getReg() == StackPtr) {
    Offset -= PI->getOperand(2).getImm();
    MBB.erase(PI);
    if (!doMergeWithPrevious) MBBI = NI;
  }

  return Offset;
}

static bool isEAXLiveIn(MachineFunction &MF) {
  for (MachineRegisterInfo::livein_iterator II = MF.getRegInfo().livein_begin(),
       EE = MF.getRegInfo().livein_end(); II != EE; ++II) {
    unsigned Reg = II->first;

    if (Reg == X86::EAX || Reg == X86::AX ||
        Reg == X86::AH || Reg == X86::AL)
      return true;
  }

  return false;
}

void X86FrameLowering::emitCalleeSavedFrameMoves(MachineFunction &MF,
                                                 MCSymbol *Label,
                                                 unsigned FramePtr) const {
  MachineFrameInfo *MFI = MF.getFrameInfo();
  MachineModuleInfo &MMI = MF.getMMI();

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

  std::vector<MachineMove> &Moves = MMI.getFrameMoves();
  const X86RegisterInfo *RegInfo = TM.getRegisterInfo();
  bool HasFP = hasFP(MF);

  // Calculate amount of bytes used for return address storing.
  int stackGrowth = -RegInfo->getSlotSize();

  // FIXME: This is dirty hack. The code itself is pretty mess right now.
  // It should be rewritten from scratch and generalized sometimes.

  // Determine maximum offset (minimum due to stack growth).
  int64_t MaxOffset = 0;
  for (std::vector<CalleeSavedInfo>::const_iterator
         I = CSI.begin(), E = CSI.end(); I != E; ++I)
    MaxOffset = std::min(MaxOffset,
                         MFI->getObjectOffset(I->getFrameIdx()));

  // Calculate offsets.
  int64_t saveAreaOffset = (HasFP ? 3 : 2) * stackGrowth;
  for (std::vector<CalleeSavedInfo>::const_iterator
         I = CSI.begin(), E = CSI.end(); I != E; ++I) {
    int64_t Offset = MFI->getObjectOffset(I->getFrameIdx());
    unsigned Reg = I->getReg();
    Offset = MaxOffset - Offset + saveAreaOffset;

    // Don't output a new machine move if we're re-saving the frame
    // pointer. This happens when the PrologEpilogInserter has inserted an extra
    // "PUSH" of the frame pointer -- the "emitPrologue" method automatically
    // generates one when frame pointers are used. If we generate a "machine
    // move" for this extra "PUSH", the linker will lose track of the fact that
    // the frame pointer should have the value of the first "PUSH" when it's
    // trying to unwind.
    //
    // FIXME: This looks inelegant. It's possibly correct, but it's covering up
    //        another bug. I.e., one where we generate a prolog like this:
    //
    //          pushl  %ebp
    //          movl   %esp, %ebp
    //          pushl  %ebp
    //          pushl  %esi
    //           ...
    //
    //        The immediate re-push of EBP is unnecessary. At the least, it's an
    //        optimization bug. EBP can be used as a scratch register in certain
    //        cases, but probably not when we have a frame pointer.
    if (HasFP && FramePtr == Reg)
      continue;

    MachineLocation CSDst(MachineLocation::VirtualFP, Offset);
    MachineLocation CSSrc(Reg);
    Moves.push_back(MachineMove(Label, CSDst, CSSrc));
  }
}

/// getCompactUnwindRegNum - Get the compact unwind number for a given
/// register. The number corresponds to the enum lists in
/// compact_unwind_encoding.h.
static int getCompactUnwindRegNum(const uint16_t *CURegs, unsigned Reg) {
  for (int Idx = 1; *CURegs; ++CURegs, ++Idx)
    if (*CURegs == Reg)
      return Idx;

  return -1;
}

// Number of registers that can be saved in a compact unwind encoding.
#define CU_NUM_SAVED_REGS 6

/// encodeCompactUnwindRegistersWithoutFrame - Create the permutation encoding
/// used with frameless stacks. It is passed the number of registers to be saved
/// and an array of the registers saved.
static uint32_t
encodeCompactUnwindRegistersWithoutFrame(unsigned SavedRegs[CU_NUM_SAVED_REGS],
                                         unsigned RegCount, bool Is64Bit) {
  // The saved registers are numbered from 1 to 6. In order to encode the order
  // in which they were saved, we re-number them according to their place in the
  // register order. The re-numbering is relative to the last re-numbered
  // register. E.g., if we have registers {6, 2, 4, 5} saved in that order:
  //
  //    Orig  Re-Num
  //    ----  ------
  //     6       6
  //     2       2
  //     4       3
  //     5       3
  //
  static const uint16_t CU32BitRegs[] = {
    X86::EBX, X86::ECX, X86::EDX, X86::EDI, X86::ESI, X86::EBP, 0
  };
  static const uint16_t CU64BitRegs[] = {
    X86::RBX, X86::R12, X86::R13, X86::R14, X86::R15, X86::RBP, 0
  };
  const uint16_t *CURegs = (Is64Bit ? CU64BitRegs : CU32BitRegs);

  for (unsigned i = 0; i != CU_NUM_SAVED_REGS; ++i) {
    int CUReg = getCompactUnwindRegNum(CURegs, SavedRegs[i]);
    if (CUReg == -1) return ~0U;
    SavedRegs[i] = CUReg;
  }

  // Reverse the list.
  std::swap(SavedRegs[0], SavedRegs[5]);
  std::swap(SavedRegs[1], SavedRegs[4]);
  std::swap(SavedRegs[2], SavedRegs[3]);

  uint32_t RenumRegs[CU_NUM_SAVED_REGS];
  for (unsigned i = CU_NUM_SAVED_REGS - RegCount; i < CU_NUM_SAVED_REGS; ++i) {
    unsigned Countless = 0;
    for (unsigned j = CU_NUM_SAVED_REGS - RegCount; j < i; ++j)
      if (SavedRegs[j] < SavedRegs[i])
        ++Countless;

    RenumRegs[i] = SavedRegs[i] - Countless - 1;
  }

  // Take the renumbered values and encode them into a 10-bit number.
  uint32_t permutationEncoding = 0;
  switch (RegCount) {
  case 6:
    permutationEncoding |= 120 * RenumRegs[0] + 24 * RenumRegs[1]
                           + 6 * RenumRegs[2] +  2 * RenumRegs[3]
                           +     RenumRegs[4];
    break;
  case 5:
    permutationEncoding |= 120 * RenumRegs[1] + 24 * RenumRegs[2]
                           + 6 * RenumRegs[3] +  2 * RenumRegs[4]
                           +     RenumRegs[5];
    break;
  case 4:
    permutationEncoding |=  60 * RenumRegs[2] + 12 * RenumRegs[3]
                           + 3 * RenumRegs[4] +      RenumRegs[5];
    break;
  case 3:
    permutationEncoding |=  20 * RenumRegs[3] +  4 * RenumRegs[4]
                           +     RenumRegs[5];
    break;
  case 2:
    permutationEncoding |=   5 * RenumRegs[4] +      RenumRegs[5];
    break;
  case 1:
    permutationEncoding |=       RenumRegs[5];
    break;
  }

  assert((permutationEncoding & 0x3FF) == permutationEncoding &&
         "Invalid compact register encoding!");
  return permutationEncoding;
}

/// encodeCompactUnwindRegistersWithFrame - Return the registers encoded for a
/// compact encoding with a frame pointer.
static uint32_t
encodeCompactUnwindRegistersWithFrame(unsigned SavedRegs[CU_NUM_SAVED_REGS],
                                      bool Is64Bit) {
  static const uint16_t CU32BitRegs[] = {
    X86::EBX, X86::ECX, X86::EDX, X86::EDI, X86::ESI, X86::EBP, 0
  };
  static const uint16_t CU64BitRegs[] = {
    X86::RBX, X86::R12, X86::R13, X86::R14, X86::R15, X86::RBP, 0
  };
  const uint16_t *CURegs = (Is64Bit ? CU64BitRegs : CU32BitRegs);

  // Encode the registers in the order they were saved, 3-bits per register. The
  // registers are numbered from 1 to CU_NUM_SAVED_REGS.
  uint32_t RegEnc = 0;
  for (int I = CU_NUM_SAVED_REGS - 1, Idx = 0; I != -1; --I) {
    unsigned Reg = SavedRegs[I];
    if (Reg == 0) continue;

    int CURegNum = getCompactUnwindRegNum(CURegs, Reg);
    if (CURegNum == -1) return ~0U;

    // Encode the 3-bit register number in order, skipping over 3-bits for each
    // register.
    RegEnc |= (CURegNum & 0x7) << (Idx++ * 3);
  }

  assert((RegEnc & 0x3FFFF) == RegEnc && "Invalid compact register encoding!");
  return RegEnc;
}

uint32_t X86FrameLowering::getCompactUnwindEncoding(MachineFunction &MF) const {
  const X86RegisterInfo *RegInfo = TM.getRegisterInfo();
  unsigned FramePtr = RegInfo->getFrameRegister(MF);
  unsigned StackPtr = RegInfo->getStackRegister();

  bool Is64Bit = STI.is64Bit();
  bool HasFP = hasFP(MF);

  unsigned SavedRegs[CU_NUM_SAVED_REGS] = { 0, 0, 0, 0, 0, 0 };
  unsigned SavedRegIdx = 0;

  unsigned OffsetSize = (Is64Bit ? 8 : 4);

  unsigned PushInstr = (Is64Bit ? X86::PUSH64r : X86::PUSH32r);
  unsigned PushInstrSize = 1;
  unsigned MoveInstr = (Is64Bit ? X86::MOV64rr : X86::MOV32rr);
  unsigned MoveInstrSize = (Is64Bit ? 3 : 2);
  unsigned SubtractInstrIdx = (Is64Bit ? 3 : 2);

  unsigned StackDivide = (Is64Bit ? 8 : 4);

  unsigned InstrOffset = 0;
  unsigned StackAdjust = 0;
  unsigned StackSize = 0;

  MachineBasicBlock &MBB = MF.front(); // Prologue is in entry BB.
  bool ExpectEnd = false;
  for (MachineBasicBlock::iterator
         MBBI = MBB.begin(), MBBE = MBB.end(); MBBI != MBBE; ++MBBI) {
    MachineInstr &MI = *MBBI;
    unsigned Opc = MI.getOpcode();
    if (Opc == X86::PROLOG_LABEL) continue;
    if (!MI.getFlag(MachineInstr::FrameSetup)) break;

    // We don't exect any more prolog instructions.
    if (ExpectEnd) return 0;

    if (Opc == PushInstr) {
      // If there are too many saved registers, we cannot use compact encoding.
      if (SavedRegIdx >= CU_NUM_SAVED_REGS) return 0;

      SavedRegs[SavedRegIdx++] = MI.getOperand(0).getReg();
      StackAdjust += OffsetSize;
      InstrOffset += PushInstrSize;
    } else if (Opc == MoveInstr) {
      unsigned SrcReg = MI.getOperand(1).getReg();
      unsigned DstReg = MI.getOperand(0).getReg();

      if (DstReg != FramePtr || SrcReg != StackPtr)
        return 0;

      StackAdjust = 0;
      memset(SavedRegs, 0, sizeof(SavedRegs));
      SavedRegIdx = 0;
      InstrOffset += MoveInstrSize;
    } else if (Opc == X86::SUB64ri32 || Opc == X86::SUB64ri8 ||
               Opc == X86::SUB32ri || Opc == X86::SUB32ri8) {
      if (StackSize)
        // We already have a stack size.
        return 0;

      if (!MI.getOperand(0).isReg() ||
          MI.getOperand(0).getReg() != MI.getOperand(1).getReg() ||
          MI.getOperand(0).getReg() != StackPtr || !MI.getOperand(2).isImm())
        // We need this to be a stack adjustment pointer. Something like:
        //
        //   %RSP<def> = SUB64ri8 %RSP, 48
        return 0;

      StackSize = MI.getOperand(2).getImm() / StackDivide;
      SubtractInstrIdx += InstrOffset;
      ExpectEnd = true;
    }
  }

  // Encode that we are using EBP/RBP as the frame pointer.
  uint32_t CompactUnwindEncoding = 0;
  StackAdjust /= StackDivide;
  if (HasFP) {
    if ((StackAdjust & 0xFF) != StackAdjust)
      // Offset was too big for compact encoding.
      return 0;

    // Get the encoding of the saved registers when we have a frame pointer.
    uint32_t RegEnc = encodeCompactUnwindRegistersWithFrame(SavedRegs, Is64Bit);
    if (RegEnc == ~0U) return 0;

    CompactUnwindEncoding |= 0x01000000;
    CompactUnwindEncoding |= (StackAdjust & 0xFF) << 16;
    CompactUnwindEncoding |= RegEnc & 0x7FFF;
  } else {
    ++StackAdjust;
    uint32_t TotalStackSize = StackAdjust + StackSize;
    if ((TotalStackSize & 0xFF) == TotalStackSize) {
      // Frameless stack with a small stack size.
      CompactUnwindEncoding |= 0x02000000;

      // Encode the stack size.
      CompactUnwindEncoding |= (TotalStackSize & 0xFF) << 16;
    } else {
      if ((StackAdjust & 0x7) != StackAdjust)
        // The extra stack adjustments are too big for us to handle.
        return 0;

      // Frameless stack with an offset too large for us to encode compactly.
      CompactUnwindEncoding |= 0x03000000;

      // Encode the offset to the nnnnnn value in the 'subl $nnnnnn, ESP'
      // instruction.
      CompactUnwindEncoding |= (SubtractInstrIdx & 0xFF) << 16;

      // Encode any extra stack stack adjustments (done via push instructions).
      CompactUnwindEncoding |= (StackAdjust & 0x7) << 13;
    }

    // Encode the number of registers saved.
    CompactUnwindEncoding |= (SavedRegIdx & 0x7) << 10;

    // Get the encoding of the saved registers when we don't have a frame
    // pointer.
    uint32_t RegEnc =
      encodeCompactUnwindRegistersWithoutFrame(SavedRegs, SavedRegIdx,
                                               Is64Bit);
    if (RegEnc == ~0U) return 0;

    // Encode the register encoding.
    CompactUnwindEncoding |= RegEnc & 0x3FF;
  }

  return CompactUnwindEncoding;
}

/// usesTheStack - This function checks if any of the users of EFLAGS
/// copies the EFLAGS. We know that the code that lowers COPY of EFLAGS has
/// to use the stack, and if we don't adjust the stack we clobber the first
/// frame index.
/// See X86InstrInfo::copyPhysReg.
static bool usesTheStack(MachineFunction &MF) {
  MachineRegisterInfo &MRI = MF.getRegInfo();

  for (MachineRegisterInfo::reg_iterator ri = MRI.reg_begin(X86::EFLAGS),
       re = MRI.reg_end(); ri != re; ++ri)
    if (ri->isCopy())
      return true;

  return false;
}

/// emitPrologue - Push callee-saved registers onto the stack, which
/// automatically adjust the stack pointer. Adjust the stack pointer to allocate
/// space for local variables. Also emit labels used by the exception handler to
/// generate the exception handling frames.
void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
  MachineBasicBlock &MBB = MF.front(); // Prologue goes in entry BB.
  MachineBasicBlock::iterator MBBI = MBB.begin();
  MachineFrameInfo *MFI = MF.getFrameInfo();
  const Function *Fn = MF.getFunction();
  const X86RegisterInfo *RegInfo = TM.getRegisterInfo();
  const X86InstrInfo &TII = *TM.getInstrInfo();
  MachineModuleInfo &MMI = MF.getMMI();
  X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
  bool needsFrameMoves = MMI.hasDebugInfo() ||
    Fn->needsUnwindTableEntry();
  uint64_t MaxAlign  = MFI->getMaxAlignment(); // Desired stack alignment.
  uint64_t StackSize = MFI->getStackSize();    // Number of bytes to allocate.
  bool HasFP = hasFP(MF);
  bool Is64Bit = STI.is64Bit();
  bool IsWin64 = STI.isTargetWin64();
  bool UseLEA = STI.useLeaForSP();
  unsigned StackAlign = getStackAlignment();
  unsigned SlotSize = RegInfo->getSlotSize();
  unsigned FramePtr = RegInfo->getFrameRegister(MF);
  unsigned StackPtr = RegInfo->getStackRegister();
  unsigned BasePtr = RegInfo->getBaseRegister();
  DebugLoc DL;

  // If we're forcing a stack realignment we can't rely on just the frame
  // info, we need to know the ABI stack alignment as well in case we
  // have a call out.  Otherwise just make sure we have some alignment - we'll
  // go with the minimum SlotSize.
  if (ForceStackAlign) {
    if (MFI->hasCalls())
      MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
    else if (MaxAlign < SlotSize)
      MaxAlign = SlotSize;
  }

  // Add RETADDR move area to callee saved frame size.
  int TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
  if (TailCallReturnAddrDelta < 0)
    X86FI->setCalleeSavedFrameSize(
      X86FI->getCalleeSavedFrameSize() - TailCallReturnAddrDelta);

  // If this is x86-64 and the Red Zone is not disabled, if we are a leaf
  // function, and use up to 128 bytes of stack space, don't have a frame
  // pointer, calls, or dynamic alloca then we do not need to adjust the
  // stack pointer (we fit in the Red Zone). We also check that we don't
  // push and pop from the stack.
  if (Is64Bit && !Fn->getAttributes().hasAttribute(AttributeSet::FunctionIndex,
                                                   Attribute::NoRedZone) &&
      !RegInfo->needsStackRealignment(MF) &&
      !MFI->hasVarSizedObjects() &&                     // No dynamic alloca.
      !MFI->adjustsStack() &&                           // No calls.
      !IsWin64 &&                                       // Win64 has no Red Zone
      !usesTheStack(MF) &&                              // Don't push and pop.
      !MF.getTarget().Options.EnableSegmentedStacks) {  // Regular stack
    uint64_t MinSize = X86FI->getCalleeSavedFrameSize();
    if (HasFP) MinSize += SlotSize;
    StackSize = std::max(MinSize, StackSize > 128 ? StackSize - 128 : 0);
    MFI->setStackSize(StackSize);
  }

  // Insert stack pointer adjustment for later moving of return addr.  Only
  // applies to tail call optimized functions where the callee argument stack
  // size is bigger than the callers.
  if (TailCallReturnAddrDelta < 0) {
    MachineInstr *MI =
      BuildMI(MBB, MBBI, DL,
              TII.get(getSUBriOpcode(Is64Bit, -TailCallReturnAddrDelta)),
              StackPtr)
        .addReg(StackPtr)
        .addImm(-TailCallReturnAddrDelta)
        .setMIFlag(MachineInstr::FrameSetup);
    MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
  }

  // Mapping for machine moves:
  //
  //   DST: VirtualFP AND
  //        SRC: VirtualFP              => DW_CFA_def_cfa_offset
  //        ELSE                        => DW_CFA_def_cfa
  //
  //   SRC: VirtualFP AND
  //        DST: Register               => DW_CFA_def_cfa_register
  //
  //   ELSE
  //        OFFSET < 0                  => DW_CFA_offset_extended_sf
  //        REG < 64                    => DW_CFA_offset + Reg
  //        ELSE                        => DW_CFA_offset_extended

  std::vector<MachineMove> &Moves = MMI.getFrameMoves();
  uint64_t NumBytes = 0;
  int stackGrowth = -SlotSize;

  if (HasFP) {
    // Calculate required stack adjustment.
    uint64_t FrameSize = StackSize - SlotSize;
    if (RegInfo->needsStackRealignment(MF)) {
      // Callee-saved registers are pushed on stack before the stack
      // is realigned.
      FrameSize -= X86FI->getCalleeSavedFrameSize();
      NumBytes = (FrameSize + MaxAlign - 1) / MaxAlign * MaxAlign;
    } else {
      NumBytes = FrameSize - X86FI->getCalleeSavedFrameSize();
    }

    // Get the offset of the stack slot for the EBP register, which is
    // guaranteed to be the last slot by processFunctionBeforeFrameFinalized.
    // Update the frame offset adjustment.
    MFI->setOffsetAdjustment(-NumBytes);

    // Save EBP/RBP into the appropriate stack slot.
    BuildMI(MBB, MBBI, DL, TII.get(Is64Bit ? X86::PUSH64r : X86::PUSH32r))
      .addReg(FramePtr, RegState::Kill)
      .setMIFlag(MachineInstr::FrameSetup);

    if (needsFrameMoves) {
      // Mark the place where EBP/RBP was saved.
      MCSymbol *FrameLabel = MMI.getContext().CreateTempSymbol();
      BuildMI(MBB, MBBI, DL, TII.get(X86::PROLOG_LABEL))
        .addSym(FrameLabel);

      // Define the current CFA rule to use the provided offset.
      if (StackSize) {
        MachineLocation SPDst(MachineLocation::VirtualFP);
        MachineLocation SPSrc(MachineLocation::VirtualFP, 2 * stackGrowth);
        Moves.push_back(MachineMove(FrameLabel, SPDst, SPSrc));
      } else {
        MachineLocation SPDst(StackPtr);
        MachineLocation SPSrc(StackPtr, stackGrowth);
        Moves.push_back(MachineMove(FrameLabel, SPDst, SPSrc));
      }

      // Change the rule for the FramePtr to be an "offset" rule.
      MachineLocation FPDst(MachineLocation::VirtualFP, 2 * stackGrowth);
      MachineLocation FPSrc(FramePtr);
      Moves.push_back(MachineMove(FrameLabel, FPDst, FPSrc));
    }

    // Update EBP with the new base value.
    BuildMI(MBB, MBBI, DL,
            TII.get(Is64Bit ? X86::MOV64rr : X86::MOV32rr), FramePtr)
        .addReg(StackPtr)
        .setMIFlag(MachineInstr::FrameSetup);

    if (needsFrameMoves) {
      // Mark effective beginning of when frame pointer becomes valid.
      MCSymbol *FrameLabel = MMI.getContext().CreateTempSymbol();
      BuildMI(MBB, MBBI, DL, TII.get(X86::PROLOG_LABEL))
        .addSym(FrameLabel);

      // Define the current CFA to use the EBP/RBP register.
      MachineLocation FPDst(FramePtr);
      MachineLocation FPSrc(MachineLocation::VirtualFP);
      Moves.push_back(MachineMove(FrameLabel, FPDst, FPSrc));
    }

    // Mark the FramePtr as live-in in every block except the entry.
    for (MachineFunction::iterator I = llvm::next(MF.begin()), E = MF.end();
         I != E; ++I)
      I->addLiveIn(FramePtr);
  } else {
    NumBytes = StackSize - X86FI->getCalleeSavedFrameSize();
  }

  // Skip the callee-saved push instructions.
  bool PushedRegs = false;
  int StackOffset = 2 * stackGrowth;

  while (MBBI != MBB.end() &&
         (MBBI->getOpcode() == X86::PUSH32r ||
          MBBI->getOpcode() == X86::PUSH64r)) {
    PushedRegs = true;
    MBBI->setFlag(MachineInstr::FrameSetup);
    ++MBBI;

    if (!HasFP && needsFrameMoves) {
      // Mark callee-saved push instruction.
      MCSymbol *Label = MMI.getContext().CreateTempSymbol();
      BuildMI(MBB, MBBI, DL, TII.get(X86::PROLOG_LABEL)).addSym(Label);

      // Define the current CFA rule to use the provided offset.
      unsigned Ptr = StackSize ? MachineLocation::VirtualFP : StackPtr;
      MachineLocation SPDst(Ptr);
      MachineLocation SPSrc(Ptr, StackOffset);
      Moves.push_back(MachineMove(Label, SPDst, SPSrc));
      StackOffset += stackGrowth;
    }
  }

  // Realign stack after we pushed callee-saved registers (so that we'll be
  // able to calculate their offsets from the frame pointer).

  // NOTE: We push the registers before realigning the stack, so
  // vector callee-saved (xmm) registers may be saved w/o proper
  // alignment in this way. However, currently these regs are saved in
  // stack slots (see X86FrameLowering::spillCalleeSavedRegisters()), so
  // this shouldn't be a problem.
  if (RegInfo->needsStackRealignment(MF)) {
    assert(HasFP && "There should be a frame pointer if stack is realigned.");
    MachineInstr *MI =
      BuildMI(MBB, MBBI, DL,
              TII.get(Is64Bit ? X86::AND64ri32 : X86::AND32ri), StackPtr)
      .addReg(StackPtr)
      .addImm(-MaxAlign)
      .setMIFlag(MachineInstr::FrameSetup);

    // The EFLAGS implicit def is dead.
    MI->getOperand(3).setIsDead();
  }

  // If there is an SUB32ri of ESP immediately before this instruction, merge
  // the two. This can be the case when tail call elimination is enabled and
  // the callee has more arguments then the caller.
  NumBytes -= mergeSPUpdates(MBB, MBBI, StackPtr, true);

  // If there is an ADD32ri or SUB32ri of ESP immediately after this
  // instruction, merge the two instructions.
  mergeSPUpdatesDown(MBB, MBBI, StackPtr, &NumBytes);

  // Adjust stack pointer: ESP -= numbytes.

  // Windows and cygwin/mingw require a prologue helper routine when allocating
  // more than 4K bytes on the stack.  Windows uses __chkstk and cygwin/mingw
  // uses __alloca.  __alloca and the 32-bit version of __chkstk will probe the
  // stack and adjust the stack pointer in one go.  The 64-bit version of
  // __chkstk is only responsible for probing the stack.  The 64-bit prologue is
  // responsible for adjusting the stack pointer.  Touching the stack at 4K
  // increments is necessary to ensure that the guard pages used by the OS
  // virtual memory manager are allocated in correct sequence.
  if (NumBytes >= 4096 && STI.isTargetCOFF() && !STI.isTargetEnvMacho()) {
    const char *StackProbeSymbol;
    bool isSPUpdateNeeded = false;

    if (Is64Bit) {
      if (STI.isTargetCygMing())
        StackProbeSymbol = "___chkstk";
      else {
        StackProbeSymbol = "__chkstk";
        isSPUpdateNeeded = true;
      }
    } else if (STI.isTargetCygMing())
      StackProbeSymbol = "_alloca";
    else
      StackProbeSymbol = "_chkstk";

    // Check whether EAX is livein for this function.
    bool isEAXAlive = isEAXLiveIn(MF);

    if (isEAXAlive) {
      // Sanity check that EAX is not livein for this function.
      // It should not be, so throw an assert.
      assert(!Is64Bit && "EAX is livein in x64 case!");

      // Save EAX
      BuildMI(MBB, MBBI, DL, TII.get(X86::PUSH32r))
        .addReg(X86::EAX, RegState::Kill)
        .setMIFlag(MachineInstr::FrameSetup);
    }

    if (Is64Bit) {
      // Handle the 64-bit Windows ABI case where we need to call __chkstk.
      // Function prologue is responsible for adjusting the stack pointer.
      BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::RAX)
        .addImm(NumBytes)
        .setMIFlag(MachineInstr::FrameSetup);
    } else {
      // Allocate NumBytes-4 bytes on stack in case of isEAXAlive.
      // We'll also use 4 already allocated bytes for EAX.
      BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
        .addImm(isEAXAlive ? NumBytes - 4 : NumBytes)
        .setMIFlag(MachineInstr::FrameSetup);
    }

    BuildMI(MBB, MBBI, DL,
            TII.get(Is64Bit ? X86::W64ALLOCA : X86::CALLpcrel32))
      .addExternalSymbol(StackProbeSymbol)
      .addReg(StackPtr,    RegState::Define | RegState::Implicit)
      .addReg(X86::EFLAGS, RegState::Define | RegState::Implicit)
      .setMIFlag(MachineInstr::FrameSetup);

    // MSVC x64's __chkstk needs to adjust %rsp.
    // FIXME: %rax preserves the offset and should be available.
    if (isSPUpdateNeeded)
      emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit,
                   UseLEA, TII, *RegInfo);

    if (isEAXAlive) {
        // Restore EAX
        MachineInstr *MI = addRegOffset(BuildMI(MF, DL, TII.get(X86::MOV32rm),
                                                X86::EAX),
                                        StackPtr, false, NumBytes - 4);
        MI->setFlag(MachineInstr::FrameSetup);
        MBB.insert(MBBI, MI);
    }
  } else if (NumBytes)
    emitSPUpdate(MBB, MBBI, StackPtr, -(int64_t)NumBytes, Is64Bit,
                 UseLEA, TII, *RegInfo);

  // If we need a base pointer, set it up here. It's whatever the value
  // of the stack pointer is at this point. Any variable size objects
  // will be allocated after this, so we can still use the base pointer
  // to reference locals.
  if (RegInfo->hasBasePointer(MF)) {
    // Update the frame pointer with the current stack pointer.
    unsigned Opc = Is64Bit ? X86::MOV64rr : X86::MOV32rr;
    BuildMI(MBB, MBBI, DL, TII.get(Opc), BasePtr)
      .addReg(StackPtr)
      .setMIFlag(MachineInstr::FrameSetup);
  }

  if (( (!HasFP && NumBytes) || PushedRegs) && needsFrameMoves) {
    // Mark end of stack pointer adjustment.
    MCSymbol *Label = MMI.getContext().CreateTempSymbol();
    BuildMI(MBB, MBBI, DL, TII.get(X86::PROLOG_LABEL))
      .addSym(Label);

    if (!HasFP && NumBytes) {
      // Define the current CFA rule to use the provided offset.
      if (StackSize) {
        MachineLocation SPDst(MachineLocation::VirtualFP);
        MachineLocation SPSrc(MachineLocation::VirtualFP,
                              -StackSize + stackGrowth);
        Moves.push_back(MachineMove(Label, SPDst, SPSrc));
      } else {
        MachineLocation SPDst(StackPtr);
        MachineLocation SPSrc(StackPtr, stackGrowth);
        Moves.push_back(MachineMove(Label, SPDst, SPSrc));
      }
    }

    // Emit DWARF info specifying the offsets of the callee-saved registers.
    if (PushedRegs)
      emitCalleeSavedFrameMoves(MF, Label, HasFP ? FramePtr : StackPtr);
  }

  // Darwin 10.7 and greater has support for compact unwind encoding.
  if (STI.getTargetTriple().isMacOSX() &&
      !STI.getTargetTriple().isMacOSXVersionLT(10, 7))
    MMI.setCompactUnwindEncoding(getCompactUnwindEncoding(MF));
}

void X86FrameLowering::emitEpilogue(MachineFunction &MF,
                                    MachineBasicBlock &MBB) const {
  const MachineFrameInfo *MFI = MF.getFrameInfo();
  X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
  const X86RegisterInfo *RegInfo = TM.getRegisterInfo();
  const X86InstrInfo &TII = *TM.getInstrInfo();
  MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
  assert(MBBI != MBB.end() && "Returning block has no instructions");
  unsigned RetOpcode = MBBI->getOpcode();
  DebugLoc DL = MBBI->getDebugLoc();
  bool Is64Bit = STI.is64Bit();
  bool UseLEA = STI.useLeaForSP();
  unsigned StackAlign = getStackAlignment();
  unsigned SlotSize = RegInfo->getSlotSize();
  unsigned FramePtr = RegInfo->getFrameRegister(MF);
  unsigned StackPtr = RegInfo->getStackRegister();

  switch (RetOpcode) {
  default:
    llvm_unreachable("Can only insert epilog into returning blocks");
  case X86::RET:
  case X86::RETI:
  case X86::TCRETURNdi:
  case X86::TCRETURNri:
  case X86::TCRETURNmi:
  case X86::TCRETURNdi64:
  case X86::TCRETURNri64:
  case X86::TCRETURNmi64:
  case X86::EH_RETURN:
  case X86::EH_RETURN64:
    break;  // These are ok
  }

  // Get the number of bytes to allocate from the FrameInfo.
  uint64_t StackSize = MFI->getStackSize();
  uint64_t MaxAlign  = MFI->getMaxAlignment();
  unsigned CSSize = X86FI->getCalleeSavedFrameSize();
  uint64_t NumBytes = 0;

  // If we're forcing a stack realignment we can't rely on just the frame
  // info, we need to know the ABI stack alignment as well in case we
  // have a call out.  Otherwise just make sure we have some alignment - we'll
  // go with the minimum.
  if (ForceStackAlign) {
    if (MFI->hasCalls())
      MaxAlign = (StackAlign > MaxAlign) ? StackAlign : MaxAlign;
    else
      MaxAlign = MaxAlign ? MaxAlign : 4;
  }

  if (hasFP(MF)) {
    // Calculate required stack adjustment.
    uint64_t FrameSize = StackSize - SlotSize;
    if (RegInfo->needsStackRealignment(MF)) {
      // Callee-saved registers were pushed on stack before the stack
      // was realigned.
      FrameSize -= CSSize;
      NumBytes = (FrameSize + MaxAlign - 1) / MaxAlign * MaxAlign;
    } else {
      NumBytes = FrameSize - CSSize;
    }

    // Pop EBP.
    BuildMI(MBB, MBBI, DL,
            TII.get(Is64Bit ? X86::POP64r : X86::POP32r), FramePtr);
  } else {
    NumBytes = StackSize - CSSize;
  }

  // Skip the callee-saved pop instructions.
  while (MBBI != MBB.begin()) {
    MachineBasicBlock::iterator PI = prior(MBBI);
    unsigned Opc = PI->getOpcode();

    if (Opc != X86::POP32r && Opc != X86::POP64r && Opc != X86::DBG_VALUE &&
        !PI->isTerminator())
      break;

    --MBBI;
  }
  MachineBasicBlock::iterator FirstCSPop = MBBI;

  DL = MBBI->getDebugLoc();

  // If there is an ADD32ri or SUB32ri of ESP immediately before this
  // instruction, merge the two instructions.
  if (NumBytes || MFI->hasVarSizedObjects())
    mergeSPUpdatesUp(MBB, MBBI, StackPtr, &NumBytes);

  // If dynamic alloca is used, then reset esp to point to the last callee-saved
  // slot before popping them off! Same applies for the case, when stack was
  // realigned.
  if (RegInfo->needsStackRealignment(MF) || MFI->hasVarSizedObjects()) {
    if (RegInfo->needsStackRealignment(MF))
      MBBI = FirstCSPop;
    if (CSSize != 0) {
      unsigned Opc = getLEArOpcode(Is64Bit);
      addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr),
                   FramePtr, false, -CSSize);
    } else {
      unsigned Opc = (Is64Bit ? X86::MOV64rr : X86::MOV32rr);
      BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
        .addReg(FramePtr);
    }
  } else if (NumBytes) {
    // Adjust stack pointer back: ESP += numbytes.
    emitSPUpdate(MBB, MBBI, StackPtr, NumBytes, Is64Bit, UseLEA, TII, *RegInfo);
  }

  // We're returning from function via eh_return.
  if (RetOpcode == X86::EH_RETURN || RetOpcode == X86::EH_RETURN64) {
    MBBI = MBB.getLastNonDebugInstr();
    MachineOperand &DestAddr  = MBBI->getOperand(0);
    assert(DestAddr.isReg() && "Offset should be in register!");
    BuildMI(MBB, MBBI, DL,
            TII.get(Is64Bit ? X86::MOV64rr : X86::MOV32rr),
            StackPtr).addReg(DestAddr.getReg());
  } else if (RetOpcode == X86::TCRETURNri || RetOpcode == X86::TCRETURNdi ||
             RetOpcode == X86::TCRETURNmi ||
             RetOpcode == X86::TCRETURNri64 || RetOpcode == X86::TCRETURNdi64 ||
             RetOpcode == X86::TCRETURNmi64) {
    bool isMem = RetOpcode == X86::TCRETURNmi || RetOpcode == X86::TCRETURNmi64;
    // Tail call return: adjust the stack pointer and jump to callee.
    MBBI = MBB.getLastNonDebugInstr();
    MachineOperand &JumpTarget = MBBI->getOperand(0);
    MachineOperand &StackAdjust = MBBI->getOperand(isMem ? 5 : 1);
    assert(StackAdjust.isImm() && "Expecting immediate value.");

    // Adjust stack pointer.
    int StackAdj = StackAdjust.getImm();
    int MaxTCDelta = X86FI->getTCReturnAddrDelta();
    int Offset = 0;
    assert(MaxTCDelta <= 0 && "MaxTCDelta should never be positive");

    // Incoporate the retaddr area.
    Offset = StackAdj-MaxTCDelta;
    assert(Offset >= 0 && "Offset should never be negative");

    if (Offset) {
      // Check for possible merge with preceding ADD instruction.
      Offset += mergeSPUpdates(MBB, MBBI, StackPtr, true);
      emitSPUpdate(MBB, MBBI, StackPtr, Offset, Is64Bit, UseLEA, TII, *RegInfo);
    }

    // Jump to label or value in register.
    if (RetOpcode == X86::TCRETURNdi || RetOpcode == X86::TCRETURNdi64) {
      MachineInstrBuilder MIB =
        BuildMI(MBB, MBBI, DL, TII.get((RetOpcode == X86::TCRETURNdi)
                                       ? X86::TAILJMPd : X86::TAILJMPd64));
      if (JumpTarget.isGlobal())
        MIB.addGlobalAddress(JumpTarget.getGlobal(), JumpTarget.getOffset(),
                             JumpTarget.getTargetFlags());
      else {
        assert(JumpTarget.isSymbol());
        MIB.addExternalSymbol(JumpTarget.getSymbolName(),
                              JumpTarget.getTargetFlags());
      }
    } else if (RetOpcode == X86::TCRETURNmi || RetOpcode == X86::TCRETURNmi64) {
      MachineInstrBuilder MIB =
        BuildMI(MBB, MBBI, DL, TII.get((RetOpcode == X86::TCRETURNmi)
                                       ? X86::TAILJMPm : X86::TAILJMPm64));
      for (unsigned i = 0; i != 5; ++i)
        MIB.addOperand(MBBI->getOperand(i));
    } else if (RetOpcode == X86::TCRETURNri64) {
      BuildMI(MBB, MBBI, DL, TII.get(X86::TAILJMPr64)).
        addReg(JumpTarget.getReg(), RegState::Kill);
    } else {
      BuildMI(MBB, MBBI, DL, TII.get(X86::TAILJMPr)).
        addReg(JumpTarget.getReg(), RegState::Kill);
    }

    MachineInstr *NewMI = prior(MBBI);
    NewMI->copyImplicitOps(MF, MBBI);

    // Delete the pseudo instruction TCRETURN.
    MBB.erase(MBBI);
  } else if ((RetOpcode == X86::RET || RetOpcode == X86::RETI) &&
             (X86FI->getTCReturnAddrDelta() < 0)) {
    // Add the return addr area delta back since we are not tail calling.
    int delta = -1*X86FI->getTCReturnAddrDelta();
    MBBI = MBB.getLastNonDebugInstr();

    // Check for possible merge with preceding ADD instruction.
    delta += mergeSPUpdates(MBB, MBBI, StackPtr, true);
    emitSPUpdate(MBB, MBBI, StackPtr, delta, Is64Bit, UseLEA, TII, *RegInfo);
  }
}

int X86FrameLowering::getFrameIndexOffset(const MachineFunction &MF, int FI) const {
  const X86RegisterInfo *RegInfo =
    static_cast<const X86RegisterInfo*>(MF.getTarget().getRegisterInfo());
  const MachineFrameInfo *MFI = MF.getFrameInfo();
  int Offset = MFI->getObjectOffset(FI) - getOffsetOfLocalArea();
  uint64_t StackSize = MFI->getStackSize();

  if (RegInfo->hasBasePointer(MF)) {
    assert (hasFP(MF) && "VLAs and dynamic stack realign, but no FP?!");
    if (FI < 0) {
      // Skip the saved EBP.
      return Offset + RegInfo->getSlotSize();
    } else {
      assert((-(Offset + StackSize)) % MFI->getObjectAlignment(FI) == 0);
      return Offset + StackSize;
    }
  } else if (RegInfo->needsStackRealignment(MF)) {
    if (FI < 0) {
      // Skip the saved EBP.
      return Offset + RegInfo->getSlotSize();
    } else {
      assert((-(Offset + StackSize)) % MFI->getObjectAlignment(FI) == 0);
      return Offset + StackSize;
    }
    // FIXME: Support tail calls
  } else {
    if (!hasFP(MF))
      return Offset + StackSize;

    // Skip the saved EBP.
    Offset += RegInfo->getSlotSize();

    // Skip the RETADDR move area
    const X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
    int TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();
    if (TailCallReturnAddrDelta < 0)
      Offset -= TailCallReturnAddrDelta;
  }

  return Offset;
}

int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
                                             unsigned &FrameReg) const {
  const X86RegisterInfo *RegInfo =
      static_cast<const X86RegisterInfo*>(MF.getTarget().getRegisterInfo());
  // We can't calculate offset from frame pointer if the stack is realigned,
  // so enforce usage of stack/base pointer.  The base pointer is used when we
  // have dynamic allocas in addition to dynamic realignment.
  if (RegInfo->hasBasePointer(MF))
    FrameReg = RegInfo->getBaseRegister();
  else if (RegInfo->needsStackRealignment(MF))
    FrameReg = RegInfo->getStackRegister();
  else
    FrameReg = RegInfo->getFrameRegister(MF);
  return getFrameIndexOffset(MF, FI);
}

bool X86FrameLowering::spillCalleeSavedRegisters(MachineBasicBlock &MBB,
                                             MachineBasicBlock::iterator MI,
                                        const std::vector<CalleeSavedInfo> &CSI,
                                          const TargetRegisterInfo *TRI) const {
  if (CSI.empty())
    return false;

  DebugLoc DL = MBB.findDebugLoc(MI);

  MachineFunction &MF = *MBB.getParent();

  unsigned SlotSize = STI.is64Bit() ? 8 : 4;
  unsigned FPReg = TRI->getFrameRegister(MF);
  unsigned CalleeFrameSize = 0;

  const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();
  X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();

  // Push GPRs. It increases frame size.
  unsigned Opc = STI.is64Bit() ? X86::PUSH64r : X86::PUSH32r;
  for (unsigned i = CSI.size(); i != 0; --i) {
    unsigned Reg = CSI[i-1].getReg();
    if (!X86::GR64RegClass.contains(Reg) &&
        !X86::GR32RegClass.contains(Reg))
      continue;
    // Add the callee-saved register as live-in. It's killed at the spill.
    MBB.addLiveIn(Reg);
    if (Reg == FPReg)
      // X86RegisterInfo::emitPrologue will handle spilling of frame register.
      continue;
    CalleeFrameSize += SlotSize;
    BuildMI(MBB, MI, DL, TII.get(Opc)).addReg(Reg, RegState::Kill)
      .setMIFlag(MachineInstr::FrameSetup);
  }

  X86FI->setCalleeSavedFrameSize(CalleeFrameSize);

  // Make XMM regs spilled. X86 does not have ability of push/pop XMM.
  // It can be done by spilling XMMs to stack frame.
  // Note that only Win64 ABI might spill XMMs.
  for (unsigned i = CSI.size(); i != 0; --i) {
    unsigned Reg = CSI[i-1].getReg();
    if (X86::GR64RegClass.contains(Reg) ||
        X86::GR32RegClass.contains(Reg))
      continue;
    // Add the callee-saved register as live-in. It's killed at the spill.
    MBB.addLiveIn(Reg);
    const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
    TII.storeRegToStackSlot(MBB, MI, Reg, true, CSI[i-1].getFrameIdx(),
                            RC, TRI);
  }

  return true;
}

bool X86FrameLowering::restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
                                               MachineBasicBlock::iterator MI,
                                        const std::vector<CalleeSavedInfo> &CSI,
                                          const TargetRegisterInfo *TRI) const {
  if (CSI.empty())
    return false;

  DebugLoc DL = MBB.findDebugLoc(MI);

  MachineFunction &MF = *MBB.getParent();
  const TargetInstrInfo &TII = *MF.getTarget().getInstrInfo();

  // Reload XMMs from stack frame.
  for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
    unsigned Reg = CSI[i].getReg();
    if (X86::GR64RegClass.contains(Reg) ||
        X86::GR32RegClass.contains(Reg))
      continue;
    const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
    TII.loadRegFromStackSlot(MBB, MI, Reg, CSI[i].getFrameIdx(),
                             RC, TRI);
  }

  // POP GPRs.
  unsigned FPReg = TRI->getFrameRegister(MF);
  unsigned Opc = STI.is64Bit() ? X86::POP64r : X86::POP32r;
  for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
    unsigned Reg = CSI[i].getReg();
    if (!X86::GR64RegClass.contains(Reg) &&
        !X86::GR32RegClass.contains(Reg))
      continue;
    if (Reg == FPReg)
      // X86RegisterInfo::emitEpilogue will handle restoring of frame register.
      continue;
    BuildMI(MBB, MI, DL, TII.get(Opc), Reg);
  }
  return true;
}

void
X86FrameLowering::processFunctionBeforeCalleeSavedScan(MachineFunction &MF,
                                                   RegScavenger *RS) const {
  MachineFrameInfo *MFI = MF.getFrameInfo();
  const X86RegisterInfo *RegInfo = TM.getRegisterInfo();
  unsigned SlotSize = RegInfo->getSlotSize();

  X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
  int32_t TailCallReturnAddrDelta = X86FI->getTCReturnAddrDelta();

  if (TailCallReturnAddrDelta < 0) {
    // create RETURNADDR area
    //   arg
    //   arg
    //   RETADDR
    //   { ...
    //     RETADDR area
    //     ...
    //   }
    //   [EBP]
    MFI->CreateFixedObject(-TailCallReturnAddrDelta,
                           (-1U*SlotSize)+TailCallReturnAddrDelta, true);
  }

  if (hasFP(MF)) {
    assert((TailCallReturnAddrDelta <= 0) &&
           "The Delta should always be zero or negative");
    const TargetFrameLowering &TFI = *MF.getTarget().getFrameLowering();

    // Create a frame entry for the EBP register that must be saved.
    int FrameIdx = MFI->CreateFixedObject(SlotSize,
                                          -(int)SlotSize +
                                          TFI.getOffsetOfLocalArea() +
                                          TailCallReturnAddrDelta,
                                          true);
    assert(FrameIdx == MFI->getObjectIndexBegin() &&
           "Slot for EBP register must be last in order to be found!");
    (void)FrameIdx;
  }

  // Spill the BasePtr if it's used.
  if (RegInfo->hasBasePointer(MF))
    MF.getRegInfo().setPhysRegUsed(RegInfo->getBaseRegister());
}

static bool
HasNestArgument(const MachineFunction *MF) {
  const Function *F = MF->getFunction();
  for (Function::const_arg_iterator I = F->arg_begin(), E = F->arg_end();
       I != E; I++) {
    if (I->hasNestAttr())
      return true;
  }
  return false;
}


/// GetScratchRegister - Get a register for performing work in the segmented
/// stack prologue. Depending on platform and the properties of the function
/// either one or two registers will be needed. Set primary to true for
/// the first register, false for the second.
static unsigned
GetScratchRegister(bool Is64Bit, const MachineFunction &MF, bool Primary) {
  if (Is64Bit)
    return Primary ? X86::R11 : X86::R12;

  CallingConv::ID CallingConvention = MF.getFunction()->getCallingConv();
  bool IsNested = HasNestArgument(&MF);

  if (CallingConvention == CallingConv::X86_FastCall ||
      CallingConvention == CallingConv::Fast) {
    if (IsNested)
      report_fatal_error("Segmented stacks does not support fastcall with "
                         "nested function.");
    return Primary ? X86::EAX : X86::ECX;
  }
  if (IsNested)
    return Primary ? X86::EDX : X86::EAX;
  return Primary ? X86::ECX : X86::EAX;
}

// The stack limit in the TCB is set to this many bytes above the actual stack
// limit.
static const uint64_t kSplitStackAvailable = 256;

void
X86FrameLowering::adjustForSegmentedStacks(MachineFunction &MF) const {
  MachineBasicBlock &prologueMBB = MF.front();
  MachineFrameInfo *MFI = MF.getFrameInfo();
  const X86InstrInfo &TII = *TM.getInstrInfo();
  uint64_t StackSize;
  bool Is64Bit = STI.is64Bit();
  unsigned TlsReg, TlsOffset;
  DebugLoc DL;
  const X86Subtarget *ST = &MF.getTarget().getSubtarget<X86Subtarget>();

  unsigned ScratchReg = GetScratchRegister(Is64Bit, MF, true);
  assert(!MF.getRegInfo().isLiveIn(ScratchReg) &&
         "Scratch register is live-in");

  if (MF.getFunction()->isVarArg())
    report_fatal_error("Segmented stacks do not support vararg functions.");
  if (!ST->isTargetLinux() && !ST->isTargetDarwin() &&
      !ST->isTargetWin32() && !ST->isTargetFreeBSD())
    report_fatal_error("Segmented stacks not supported on this platform.");

  MachineBasicBlock *allocMBB = MF.CreateMachineBasicBlock();
  MachineBasicBlock *checkMBB = MF.CreateMachineBasicBlock();
  X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
  bool IsNested = false;

  // We need to know if the function has a nest argument only in 64 bit mode.
  if (Is64Bit)
    IsNested = HasNestArgument(&MF);

  // The MOV R10, RAX needs to be in a different block, since the RET we emit in
  // allocMBB needs to be last (terminating) instruction.

  for (MachineBasicBlock::livein_iterator i = prologueMBB.livein_begin(),
         e = prologueMBB.livein_end(); i != e; i++) {
    allocMBB->addLiveIn(*i);
    checkMBB->addLiveIn(*i);
  }

  if (IsNested)
    allocMBB->addLiveIn(X86::R10);

  MF.push_front(allocMBB);
  MF.push_front(checkMBB);

  // Eventually StackSize will be calculated by a link-time pass; which will
  // also decide whether checking code needs to be injected into this particular
  // prologue.
  StackSize = MFI->getStackSize();

  // When the frame size is less than 256 we just compare the stack
  // boundary directly to the value of the stack pointer, per gcc.
  bool CompareStackPointer = StackSize < kSplitStackAvailable;

  // Read the limit off the current stacklet off the stack_guard location.
  if (Is64Bit) {
    if (ST->isTargetLinux()) {
      TlsReg = X86::FS;
      TlsOffset = 0x70;
    } else if (ST->isTargetDarwin()) {
      TlsReg = X86::GS;
      TlsOffset = 0x60 + 90*8; // See pthread_machdep.h. Steal TLS slot 90.
    } else if (ST->isTargetFreeBSD()) {
      TlsReg = X86::FS;
      TlsOffset = 0x18;
    } else {
      report_fatal_error("Segmented stacks not supported on this platform.");
    }

    if (CompareStackPointer)
      ScratchReg = X86::RSP;
    else
      BuildMI(checkMBB, DL, TII.get(X86::LEA64r), ScratchReg).addReg(X86::RSP)
        .addImm(1).addReg(0).addImm(-StackSize).addReg(0);

    BuildMI(checkMBB, DL, TII.get(X86::CMP64rm)).addReg(ScratchReg)
      .addReg(0).addImm(1).addReg(0).addImm(TlsOffset).addReg(TlsReg);
  } else {
    if (ST->isTargetLinux()) {
      TlsReg = X86::GS;
      TlsOffset = 0x30;
    } else if (ST->isTargetDarwin()) {
      TlsReg = X86::GS;
      TlsOffset = 0x48 + 90*4;
    } else if (ST->isTargetWin32()) {
      TlsReg = X86::FS;
      TlsOffset = 0x14; // pvArbitrary, reserved for application use
    } else if (ST->isTargetFreeBSD()) {
      report_fatal_error("Segmented stacks not supported on FreeBSD i386.");
    } else {
      report_fatal_error("Segmented stacks not supported on this platform.");
    }

    if (CompareStackPointer)
      ScratchReg = X86::ESP;
    else
      BuildMI(checkMBB, DL, TII.get(X86::LEA32r), ScratchReg).addReg(X86::ESP)
        .addImm(1).addReg(0).addImm(-StackSize).addReg(0);

    if (ST->isTargetLinux() || ST->isTargetWin32()) {
      BuildMI(checkMBB, DL, TII.get(X86::CMP32rm)).addReg(ScratchReg)
        .addReg(0).addImm(0).addReg(0).addImm(TlsOffset).addReg(TlsReg);
    } else if (ST->isTargetDarwin()) {

      // TlsOffset doesn't fit into a mod r/m byte so we need an extra register
      unsigned ScratchReg2;
      bool SaveScratch2;
      if (CompareStackPointer) {
        // The primary scratch register is available for holding the TLS offset
        ScratchReg2 = GetScratchRegister(Is64Bit, MF, true);
        SaveScratch2 = false;
      } else {
        // Need to use a second register to hold the TLS offset
        ScratchReg2 = GetScratchRegister(Is64Bit, MF, false);

        // Unfortunately, with fastcc the second scratch register may hold an arg
        SaveScratch2 = MF.getRegInfo().isLiveIn(ScratchReg2);
      }

      // If Scratch2 is live-in then it needs to be saved
      assert((!MF.getRegInfo().isLiveIn(ScratchReg2) || SaveScratch2) &&
             "Scratch register is live-in and not saved");

      if (SaveScratch2)
        BuildMI(checkMBB, DL, TII.get(X86::PUSH32r))
          .addReg(ScratchReg2, RegState::Kill);

      BuildMI(checkMBB, DL, TII.get(X86::MOV32ri), ScratchReg2)
        .addImm(TlsOffset);
      BuildMI(checkMBB, DL, TII.get(X86::CMP32rm))
        .addReg(ScratchReg)
        .addReg(ScratchReg2).addImm(1).addReg(0)
        .addImm(0)
        .addReg(TlsReg);

      if (SaveScratch2)
        BuildMI(checkMBB, DL, TII.get(X86::POP32r), ScratchReg2);
    }
  }

  // This jump is taken if SP >= (Stacklet Limit + Stack Space required).
  // It jumps to normal execution of the function body.
  BuildMI(checkMBB, DL, TII.get(X86::JA_4)).addMBB(&prologueMBB);

  // On 32 bit we first push the arguments size and then the frame size. On 64
  // bit, we pass the stack frame size in r10 and the argument size in r11.
  if (Is64Bit) {
    // Functions with nested arguments use R10, so it needs to be saved across
    // the call to _morestack

    if (IsNested)
      BuildMI(allocMBB, DL, TII.get(X86::MOV64rr), X86::RAX).addReg(X86::R10);

    BuildMI(allocMBB, DL, TII.get(X86::MOV64ri), X86::R10)
      .addImm(StackSize);
    BuildMI(allocMBB, DL, TII.get(X86::MOV64ri), X86::R11)
      .addImm(X86FI->getArgumentStackSize());
    MF.getRegInfo().setPhysRegUsed(X86::R10);
    MF.getRegInfo().setPhysRegUsed(X86::R11);
  } else {
    BuildMI(allocMBB, DL, TII.get(X86::PUSHi32))
      .addImm(X86FI->getArgumentStackSize());
    BuildMI(allocMBB, DL, TII.get(X86::PUSHi32))
      .addImm(StackSize);
  }

  // __morestack is in libgcc
  if (Is64Bit)
    BuildMI(allocMBB, DL, TII.get(X86::CALL64pcrel32))
      .addExternalSymbol("__morestack");
  else
    BuildMI(allocMBB, DL, TII.get(X86::CALLpcrel32))
      .addExternalSymbol("__morestack");

  if (IsNested)
    BuildMI(allocMBB, DL, TII.get(X86::MORESTACK_RET_RESTORE_R10));
  else
    BuildMI(allocMBB, DL, TII.get(X86::MORESTACK_RET));

  allocMBB->addSuccessor(&prologueMBB);

  checkMBB->addSuccessor(allocMBB);
  checkMBB->addSuccessor(&prologueMBB);

#ifdef XDEBUG
  MF.verify();
#endif
}