aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Target/ARM/Thumb1FrameLowering.cpp
blob: 71a82a1e32715aeff71f86df9075ce118263d19d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
//===- Thumb1FrameLowering.cpp - Thumb1 Frame Information -----------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file contains the Thumb1 implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//

#include "Thumb1FrameLowering.h"
#include "ARMBaseInstrInfo.h"
#include "ARMBaseRegisterInfo.h"
#include "ARMMachineFunctionInfo.h"
#include "ARMSubtarget.h"
#include "Thumb1InstrInfo.h"
#include "ThumbRegisterInfo.h"
#include "Utils/ARMBaseInfo.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/CodeGen/LivePhysRegs.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetOpcodes.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include <bitset>
#include <cassert>
#include <iterator>
#include <vector>

using namespace llvm;

Thumb1FrameLowering::Thumb1FrameLowering(const ARMSubtarget &sti)
    : ARMFrameLowering(sti) {}

bool Thumb1FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const{
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  unsigned CFSize = MFI.getMaxCallFrameSize();
  // It's not always a good idea to include the call frame as part of the
  // stack frame. ARM (especially Thumb) has small immediate offset to
  // address the stack frame. So a large call frame can cause poor codegen
  // and may even makes it impossible to scavenge a register.
  if (CFSize >= ((1 << 8) - 1) * 4 / 2) // Half of imm8 * 4
    return false;

  return !MFI.hasVarSizedObjects();
}

static void
emitPrologueEpilogueSPUpdate(MachineBasicBlock &MBB,
                             MachineBasicBlock::iterator &MBBI,
                             const TargetInstrInfo &TII, const DebugLoc &dl,
                             const ThumbRegisterInfo &MRI, int NumBytes,
                             unsigned ScratchReg, unsigned MIFlags) {
  // If it would take more than three instructions to adjust the stack pointer
  // using tADDspi/tSUBspi, load an immediate instead.
  if (std::abs(NumBytes) > 508 * 3) {
    // We use a different codepath here from the normal
    // emitThumbRegPlusImmediate so we don't have to deal with register
    // scavenging. (Scavenging could try to use the emergency spill slot
    // before we've actually finished setting up the stack.)
    if (ScratchReg == ARM::NoRegister)
      report_fatal_error("Failed to emit Thumb1 stack adjustment");
    MachineFunction &MF = *MBB.getParent();
    const ARMSubtarget &ST = MF.getSubtarget<ARMSubtarget>();
    if (ST.genExecuteOnly()) {
      BuildMI(MBB, MBBI, dl, TII.get(ARM::t2MOVi32imm), ScratchReg)
        .addImm(NumBytes).setMIFlags(MIFlags);
    } else {
      MRI.emitLoadConstPool(MBB, MBBI, dl, ScratchReg, 0, NumBytes, ARMCC::AL,
                            0, MIFlags);
    }
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDhirr), ARM::SP)
        .addReg(ARM::SP)
        .addReg(ScratchReg, RegState::Kill)
        .add(predOps(ARMCC::AL))
        .setMIFlags(MIFlags);
    return;
  }
  // FIXME: This is assuming the heuristics in emitThumbRegPlusImmediate
  // won't change.
  emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::SP, ARM::SP, NumBytes, TII,
                            MRI, MIFlags);

}

static void emitCallSPUpdate(MachineBasicBlock &MBB,
                             MachineBasicBlock::iterator &MBBI,
                             const TargetInstrInfo &TII, const DebugLoc &dl,
                             const ThumbRegisterInfo &MRI, int NumBytes,
                             unsigned MIFlags = MachineInstr::NoFlags) {
  emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::SP, ARM::SP, NumBytes, TII,
                            MRI, MIFlags);
}


MachineBasicBlock::iterator Thumb1FrameLowering::
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
                              MachineBasicBlock::iterator I) const {
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());
  const ThumbRegisterInfo *RegInfo =
      static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
  if (!hasReservedCallFrame(MF)) {
    // If we have alloca, convert as follows:
    // ADJCALLSTACKDOWN -> sub, sp, sp, amount
    // ADJCALLSTACKUP   -> add, sp, sp, amount
    MachineInstr &Old = *I;
    DebugLoc dl = Old.getDebugLoc();
    unsigned Amount = TII.getFrameSize(Old);
    if (Amount != 0) {
      // We need to keep the stack aligned properly.  To do this, we round the
      // amount of space needed for the outgoing arguments up to the next
      // alignment boundary.
      Amount = alignTo(Amount, getStackAlign());

      // Replace the pseudo instruction with a new instruction...
      unsigned Opc = Old.getOpcode();
      if (Opc == ARM::ADJCALLSTACKDOWN || Opc == ARM::tADJCALLSTACKDOWN) {
        emitCallSPUpdate(MBB, I, TII, dl, *RegInfo, -Amount);
      } else {
        assert(Opc == ARM::ADJCALLSTACKUP || Opc == ARM::tADJCALLSTACKUP);
        emitCallSPUpdate(MBB, I, TII, dl, *RegInfo, Amount);
      }
    }
  }
  return MBB.erase(I);
}

void Thumb1FrameLowering::emitPrologue(MachineFunction &MF,
                                       MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.begin();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
  MachineModuleInfo &MMI = MF.getMMI();
  const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo();
  const ThumbRegisterInfo *RegInfo =
      static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());

  unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
  unsigned NumBytes = MFI.getStackSize();
  assert(NumBytes >= ArgRegsSaveSize &&
         "ArgRegsSaveSize is included in NumBytes");
  const std::vector<CalleeSavedInfo> &CSI = MFI.getCalleeSavedInfo();

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

  Register FramePtr = RegInfo->getFrameRegister(MF);
  Register BasePtr = RegInfo->getBaseRegister();
  int CFAOffset = 0;

  // Thumb add/sub sp, imm8 instructions implicitly multiply the offset by 4.
  NumBytes = (NumBytes + 3) & ~3;
  MFI.setStackSize(NumBytes);

  // Determine the sizes of each callee-save spill areas and record which frame
  // belongs to which callee-save spill areas.
  unsigned GPRCS1Size = 0, GPRCS2Size = 0, DPRCSSize = 0;
  int FramePtrSpillFI = 0;

  if (ArgRegsSaveSize) {
    emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize,
                                 ARM::NoRegister, MachineInstr::FrameSetup);
    CFAOffset += ArgRegsSaveSize;
    unsigned CFIIndex =
        MF.addFrameInst(MCCFIInstruction::cfiDefCfaOffset(nullptr, CFAOffset));
    BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }

  if (!AFI->hasStackFrame()) {
    if (NumBytes - ArgRegsSaveSize != 0) {
      emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo,
                                   -(NumBytes - ArgRegsSaveSize),
                                   ARM::NoRegister, MachineInstr::FrameSetup);
      CFAOffset += NumBytes - ArgRegsSaveSize;
      unsigned CFIIndex = MF.addFrameInst(
          MCCFIInstruction::cfiDefCfaOffset(nullptr, CFAOffset));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    }
    return;
  }

  for (const CalleeSavedInfo &I : CSI) {
    Register Reg = I.getReg();
    int FI = I.getFrameIdx();
    switch (Reg) {
    case ARM::R8:
    case ARM::R9:
    case ARM::R10:
    case ARM::R11:
      if (STI.splitFramePushPop(MF)) {
        GPRCS2Size += 4;
        break;
      }
      LLVM_FALLTHROUGH;
    case ARM::R4:
    case ARM::R5:
    case ARM::R6:
    case ARM::R7:
    case ARM::LR:
      if (Reg == FramePtr)
        FramePtrSpillFI = FI;
      GPRCS1Size += 4;
      break;
    default:
      DPRCSSize += 8;
    }
  }

  if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
    ++MBBI;
  }

  // Determine starting offsets of spill areas.
  unsigned DPRCSOffset  = NumBytes - ArgRegsSaveSize - (GPRCS1Size + GPRCS2Size + DPRCSSize);
  unsigned GPRCS2Offset = DPRCSOffset + DPRCSSize;
  unsigned GPRCS1Offset = GPRCS2Offset + GPRCS2Size;
  bool HasFP = hasFP(MF);
  if (HasFP)
    AFI->setFramePtrSpillOffset(MFI.getObjectOffset(FramePtrSpillFI) +
                                NumBytes);
  AFI->setGPRCalleeSavedArea1Offset(GPRCS1Offset);
  AFI->setGPRCalleeSavedArea2Offset(GPRCS2Offset);
  AFI->setDPRCalleeSavedAreaOffset(DPRCSOffset);
  NumBytes = DPRCSOffset;

  int FramePtrOffsetInBlock = 0;
  unsigned adjustedGPRCS1Size = GPRCS1Size;
  if (GPRCS1Size > 0 && GPRCS2Size == 0 &&
      tryFoldSPUpdateIntoPushPop(STI, MF, &*std::prev(MBBI), NumBytes)) {
    FramePtrOffsetInBlock = NumBytes;
    adjustedGPRCS1Size += NumBytes;
    NumBytes = 0;
  }

  if (adjustedGPRCS1Size) {
    CFAOffset += adjustedGPRCS1Size;
    unsigned CFIIndex =
        MF.addFrameInst(MCCFIInstruction::cfiDefCfaOffset(nullptr, CFAOffset));
    BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }
  for (const CalleeSavedInfo &I : CSI) {
    Register Reg = I.getReg();
    int FI = I.getFrameIdx();
    switch (Reg) {
    case ARM::R8:
    case ARM::R9:
    case ARM::R10:
    case ARM::R11:
    case ARM::R12:
      if (STI.splitFramePushPop(MF))
        break;
      LLVM_FALLTHROUGH;
    case ARM::R0:
    case ARM::R1:
    case ARM::R2:
    case ARM::R3:
    case ARM::R4:
    case ARM::R5:
    case ARM::R6:
    case ARM::R7:
    case ARM::LR:
      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createOffset(
          nullptr, MRI->getDwarfRegNum(Reg, true), MFI.getObjectOffset(FI)));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
      break;
    }
  }

  // Adjust FP so it point to the stack slot that contains the previous FP.
  if (HasFP) {
    FramePtrOffsetInBlock +=
        MFI.getObjectOffset(FramePtrSpillFI) + GPRCS1Size + ArgRegsSaveSize;
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
        .addReg(ARM::SP)
        .addImm(FramePtrOffsetInBlock / 4)
        .setMIFlags(MachineInstr::FrameSetup)
        .add(predOps(ARMCC::AL));
    if(FramePtrOffsetInBlock) {
      CFAOffset -= FramePtrOffsetInBlock;
      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::cfiDefCfa(
          nullptr, MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    } else {
      unsigned CFIIndex =
          MF.addFrameInst(MCCFIInstruction::createDefCfaRegister(
              nullptr, MRI->getDwarfRegNum(FramePtr, true)));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    }
    if (NumBytes > 508)
      // If offset is > 508 then sp cannot be adjusted in a single instruction,
      // try restoring from fp instead.
      AFI->setShouldRestoreSPFromFP(true);
  }

  // Skip past the spilling of r8-r11, which could consist of multiple tPUSH
  // and tMOVr instructions. We don't need to add any call frame information
  // in-between these instructions, because they do not modify the high
  // registers.
  while (true) {
    MachineBasicBlock::iterator OldMBBI = MBBI;
    // Skip a run of tMOVr instructions
    while (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tMOVr)
      MBBI++;
    if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPUSH) {
      MBBI++;
    } else {
      // We have reached an instruction which is not a push, so the previous
      // run of tMOVr instructions (which may have been empty) was not part of
      // the prologue. Reset MBBI back to the last PUSH of the prologue.
      MBBI = OldMBBI;
      break;
    }
  }

  // Emit call frame information for the callee-saved high registers.
  for (auto &I : CSI) {
    Register Reg = I.getReg();
    int FI = I.getFrameIdx();
    switch (Reg) {
    case ARM::R8:
    case ARM::R9:
    case ARM::R10:
    case ARM::R11:
    case ARM::R12: {
      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::createOffset(
          nullptr, MRI->getDwarfRegNum(Reg, true), MFI.getObjectOffset(FI)));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
      break;
    }
    default:
      break;
    }
  }

  if (NumBytes) {
    // Insert it after all the callee-save spills.
    //
    // For a large stack frame, we might need a scratch register to store
    // the size of the frame.  We know all callee-save registers are free
    // at this point in the prologue, so pick one.
    unsigned ScratchRegister = ARM::NoRegister;
    for (auto &I : CSI) {
      Register Reg = I.getReg();
      if (isARMLowRegister(Reg) && !(HasFP && Reg == FramePtr)) {
        ScratchRegister = Reg;
        break;
      }
    }
    emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
                                 ScratchRegister, MachineInstr::FrameSetup);
    if (!HasFP) {
      CFAOffset += NumBytes;
      unsigned CFIIndex = MF.addFrameInst(
          MCCFIInstruction::cfiDefCfaOffset(nullptr, CFAOffset));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    }
  }

  if (STI.isTargetELF() && HasFP)
    MFI.setOffsetAdjustment(MFI.getOffsetAdjustment() -
                            AFI->getFramePtrSpillOffset());

  AFI->setGPRCalleeSavedArea1Size(GPRCS1Size);
  AFI->setGPRCalleeSavedArea2Size(GPRCS2Size);
  AFI->setDPRCalleeSavedAreaSize(DPRCSSize);

  if (RegInfo->hasStackRealignment(MF)) {
    const unsigned NrBitsToZero = Log2(MFI.getMaxAlign());
    // Emit the following sequence, using R4 as a temporary, since we cannot use
    // SP as a source or destination register for the shifts:
    // mov  r4, sp
    // lsrs r4, r4, #NrBitsToZero
    // lsls r4, r4, #NrBitsToZero
    // mov  sp, r4
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::R4)
      .addReg(ARM::SP, RegState::Kill)
      .add(predOps(ARMCC::AL));

    BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSRri), ARM::R4)
      .addDef(ARM::CPSR)
      .addReg(ARM::R4, RegState::Kill)
      .addImm(NrBitsToZero)
      .add(predOps(ARMCC::AL));

    BuildMI(MBB, MBBI, dl, TII.get(ARM::tLSLri), ARM::R4)
      .addDef(ARM::CPSR)
      .addReg(ARM::R4, RegState::Kill)
      .addImm(NrBitsToZero)
      .add(predOps(ARMCC::AL));

    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::SP)
      .addReg(ARM::R4, RegState::Kill)
      .add(predOps(ARMCC::AL));

    AFI->setShouldRestoreSPFromFP(true);
  }

  // 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))
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), BasePtr)
        .addReg(ARM::SP)
        .add(predOps(ARMCC::AL));

  // If the frame has variable sized objects then the epilogue must restore
  // the sp from fp. We can assume there's an FP here since hasFP already
  // checks for hasVarSizedObjects.
  if (MFI.hasVarSizedObjects())
    AFI->setShouldRestoreSPFromFP(true);

  // In some cases, virtual registers have been introduced, e.g. by uses of
  // emitThumbRegPlusImmInReg.
  MF.getProperties().reset(MachineFunctionProperties::Property::NoVRegs);
}

static bool isCSRestore(MachineInstr &MI, const MCPhysReg *CSRegs) {
  if (MI.getOpcode() == ARM::tLDRspi && MI.getOperand(1).isFI() &&
      isCalleeSavedRegister(MI.getOperand(0).getReg(), CSRegs))
    return true;
  else if (MI.getOpcode() == ARM::tPOP) {
    return true;
  } else if (MI.getOpcode() == ARM::tMOVr) {
    Register Dst = MI.getOperand(0).getReg();
    Register Src = MI.getOperand(1).getReg();
    return ((ARM::tGPRRegClass.contains(Src) || Src == ARM::LR) &&
            ARM::hGPRRegClass.contains(Dst));
  }
  return false;
}

void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
                                   MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
  DebugLoc dl = MBBI != MBB.end() ? MBBI->getDebugLoc() : DebugLoc();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
  const ThumbRegisterInfo *RegInfo =
      static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(STI.getInstrInfo());

  unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
  int NumBytes = (int)MFI.getStackSize();
  assert((unsigned)NumBytes >= ArgRegsSaveSize &&
         "ArgRegsSaveSize is included in NumBytes");
  const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&MF);
  Register FramePtr = RegInfo->getFrameRegister(MF);

  if (!AFI->hasStackFrame()) {
    if (NumBytes - ArgRegsSaveSize != 0)
      emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo,
                                   NumBytes - ArgRegsSaveSize, ARM::NoRegister,
                                   MachineInstr::NoFlags);
  } else {
    // Unwind MBBI to point to first LDR / VLDRD.
    if (MBBI != MBB.begin()) {
      do
        --MBBI;
      while (MBBI != MBB.begin() && isCSRestore(*MBBI, CSRegs));
      if (!isCSRestore(*MBBI, CSRegs))
        ++MBBI;
    }

    // Move SP to start of FP callee save spill area.
    NumBytes -= (AFI->getGPRCalleeSavedArea1Size() +
                 AFI->getGPRCalleeSavedArea2Size() +
                 AFI->getDPRCalleeSavedAreaSize() +
                 ArgRegsSaveSize);

    if (AFI->shouldRestoreSPFromFP()) {
      NumBytes = AFI->getFramePtrSpillOffset() - NumBytes;
      // Reset SP based on frame pointer only if the stack frame extends beyond
      // frame pointer stack slot, the target is ELF and the function has FP, or
      // the target uses var sized objects.
      if (NumBytes) {
        assert(!MFI.getPristineRegs(MF).test(ARM::R4) &&
               "No scratch register to restore SP from FP!");
        emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
                                  TII, *RegInfo);
        BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::SP)
            .addReg(ARM::R4)
            .add(predOps(ARMCC::AL));
      } else
        BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), ARM::SP)
            .addReg(FramePtr)
            .add(predOps(ARMCC::AL));
    } else {
      // For a large stack frame, we might need a scratch register to store
      // the size of the frame.  We know all callee-save registers are free
      // at this point in the epilogue, so pick one.
      unsigned ScratchRegister = ARM::NoRegister;
      bool HasFP = hasFP(MF);
      for (auto &I : MFI.getCalleeSavedInfo()) {
        Register Reg = I.getReg();
        if (isARMLowRegister(Reg) && !(HasFP && Reg == FramePtr)) {
          ScratchRegister = Reg;
          break;
        }
      }
      if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tBX_RET &&
          &MBB.front() != &*MBBI && std::prev(MBBI)->getOpcode() == ARM::tPOP) {
        MachineBasicBlock::iterator PMBBI = std::prev(MBBI);
        if (!tryFoldSPUpdateIntoPushPop(STI, MF, &*PMBBI, NumBytes))
          emitPrologueEpilogueSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes,
                                       ScratchRegister, MachineInstr::NoFlags);
      } else if (!tryFoldSPUpdateIntoPushPop(STI, MF, &*MBBI, NumBytes))
        emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes,
                                     ScratchRegister, MachineInstr::NoFlags);
    }
  }

  if (needPopSpecialFixUp(MF)) {
    bool Done = emitPopSpecialFixUp(MBB, /* DoIt */ true);
    (void)Done;
    assert(Done && "Emission of the special fixup failed!?");
  }
}

bool Thumb1FrameLowering::canUseAsEpilogue(const MachineBasicBlock &MBB) const {
  if (!needPopSpecialFixUp(*MBB.getParent()))
    return true;

  MachineBasicBlock *TmpMBB = const_cast<MachineBasicBlock *>(&MBB);
  return emitPopSpecialFixUp(*TmpMBB, /* DoIt */ false);
}

bool Thumb1FrameLowering::needPopSpecialFixUp(const MachineFunction &MF) const {
  ARMFunctionInfo *AFI =
      const_cast<MachineFunction *>(&MF)->getInfo<ARMFunctionInfo>();
  if (AFI->getArgRegsSaveSize())
    return true;

  // LR cannot be encoded with Thumb1, i.e., it requires a special fix-up.
  for (const CalleeSavedInfo &CSI : MF.getFrameInfo().getCalleeSavedInfo())
    if (CSI.getReg() == ARM::LR)
      return true;

  return false;
}

static void findTemporariesForLR(const BitVector &GPRsNoLRSP,
                                 const BitVector &PopFriendly,
                                 const LivePhysRegs &UsedRegs, unsigned &PopReg,
                                 unsigned &TmpReg, MachineRegisterInfo &MRI) {
  PopReg = TmpReg = 0;
  for (auto Reg : GPRsNoLRSP.set_bits()) {
    if (UsedRegs.available(MRI, Reg)) {
      // Remember the first pop-friendly register and exit.
      if (PopFriendly.test(Reg)) {
        PopReg = Reg;
        TmpReg = 0;
        break;
      }
      // Otherwise, remember that the register will be available to
      // save a pop-friendly register.
      TmpReg = Reg;
    }
  }
}

bool Thumb1FrameLowering::emitPopSpecialFixUp(MachineBasicBlock &MBB,
                                              bool DoIt) const {
  MachineFunction &MF = *MBB.getParent();
  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
  unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize();
  const TargetInstrInfo &TII = *STI.getInstrInfo();
  const ThumbRegisterInfo *RegInfo =
      static_cast<const ThumbRegisterInfo *>(STI.getRegisterInfo());

  // If MBBI is a return instruction, or is a tPOP followed by a return
  // instruction in the successor BB, we may be able to directly restore
  // LR in the PC.
  // This is only possible with v5T ops (v4T can't change the Thumb bit via
  // a POP PC instruction), and only if we do not need to emit any SP update.
  // Otherwise, we need a temporary register to pop the value
  // and copy that value into LR.
  auto MBBI = MBB.getFirstTerminator();
  bool CanRestoreDirectly = STI.hasV5TOps() && !ArgRegsSaveSize;
  if (CanRestoreDirectly) {
    if (MBBI != MBB.end() && MBBI->getOpcode() != ARM::tB)
      CanRestoreDirectly = (MBBI->getOpcode() == ARM::tBX_RET ||
                            MBBI->getOpcode() == ARM::tPOP_RET);
    else {
      auto MBBI_prev = MBBI;
      MBBI_prev--;
      assert(MBBI_prev->getOpcode() == ARM::tPOP);
      assert(MBB.succ_size() == 1);
      if ((*MBB.succ_begin())->begin()->getOpcode() == ARM::tBX_RET)
        MBBI = MBBI_prev; // Replace the final tPOP with a tPOP_RET.
      else
        CanRestoreDirectly = false;
    }
  }

  if (CanRestoreDirectly) {
    if (!DoIt || MBBI->getOpcode() == ARM::tPOP_RET)
      return true;
    MachineInstrBuilder MIB =
        BuildMI(MBB, MBBI, MBBI->getDebugLoc(), TII.get(ARM::tPOP_RET))
            .add(predOps(ARMCC::AL));
    // Copy implicit ops and popped registers, if any.
    for (auto MO: MBBI->operands())
      if (MO.isReg() && (MO.isImplicit() || MO.isDef()))
        MIB.add(MO);
    MIB.addReg(ARM::PC, RegState::Define);
    // Erase the old instruction (tBX_RET or tPOP).
    MBB.erase(MBBI);
    return true;
  }

  // Look for a temporary register to use.
  // First, compute the liveness information.
  const TargetRegisterInfo &TRI = *STI.getRegisterInfo();
  LivePhysRegs UsedRegs(TRI);
  UsedRegs.addLiveOuts(MBB);
  // The semantic of pristines changed recently and now,
  // the callee-saved registers that are touched in the function
  // are not part of the pristines set anymore.
  // Add those callee-saved now.
  const MCPhysReg *CSRegs = TRI.getCalleeSavedRegs(&MF);
  for (unsigned i = 0; CSRegs[i]; ++i)
    UsedRegs.addReg(CSRegs[i]);

  DebugLoc dl = DebugLoc();
  if (MBBI != MBB.end()) {
    dl = MBBI->getDebugLoc();
    auto InstUpToMBBI = MBB.end();
    while (InstUpToMBBI != MBBI)
      // The pre-decrement is on purpose here.
      // We want to have the liveness right before MBBI.
      UsedRegs.stepBackward(*--InstUpToMBBI);
  }

  // Look for a register that can be directly use in the POP.
  unsigned PopReg = 0;
  // And some temporary register, just in case.
  unsigned TemporaryReg = 0;
  BitVector PopFriendly =
      TRI.getAllocatableSet(MF, TRI.getRegClass(ARM::tGPRRegClassID));
  // R7 may be used as a frame pointer, hence marked as not generally
  // allocatable, however there's no reason to not use it as a temporary for
  // restoring LR.
  if (STI.getFramePointerReg() == ARM::R7)
    PopFriendly.set(ARM::R7);

  assert(PopFriendly.any() && "No allocatable pop-friendly register?!");
  // Rebuild the GPRs from the high registers because they are removed
  // form the GPR reg class for thumb1.
  BitVector GPRsNoLRSP =
      TRI.getAllocatableSet(MF, TRI.getRegClass(ARM::hGPRRegClassID));
  GPRsNoLRSP |= PopFriendly;
  GPRsNoLRSP.reset(ARM::LR);
  GPRsNoLRSP.reset(ARM::SP);
  GPRsNoLRSP.reset(ARM::PC);
  findTemporariesForLR(GPRsNoLRSP, PopFriendly, UsedRegs, PopReg, TemporaryReg,
                       MF.getRegInfo());

  // If we couldn't find a pop-friendly register, try restoring LR before
  // popping the other callee-saved registers, so we could use one of them as a
  // temporary.
  bool UseLDRSP = false;
  if (!PopReg && MBBI != MBB.begin()) {
    auto PrevMBBI = MBBI;
    PrevMBBI--;
    if (PrevMBBI->getOpcode() == ARM::tPOP) {
      UsedRegs.stepBackward(*PrevMBBI);
      findTemporariesForLR(GPRsNoLRSP, PopFriendly, UsedRegs, PopReg,
                           TemporaryReg, MF.getRegInfo());
      if (PopReg) {
        MBBI = PrevMBBI;
        UseLDRSP = true;
      }
    }
  }

  if (!DoIt && !PopReg && !TemporaryReg)
    return false;

  assert((PopReg || TemporaryReg) && "Cannot get LR");

  if (UseLDRSP) {
    assert(PopReg && "Do not know how to get LR");
    // Load the LR via LDR tmp, [SP, #off]
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tLDRspi))
      .addReg(PopReg, RegState::Define)
      .addReg(ARM::SP)
      .addImm(MBBI->getNumExplicitOperands() - 2)
      .add(predOps(ARMCC::AL));
    // Move from the temporary register to the LR.
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
      .addReg(ARM::LR, RegState::Define)
      .addReg(PopReg, RegState::Kill)
      .add(predOps(ARMCC::AL));
    // Advance past the pop instruction.
    MBBI++;
    // Increment the SP.
    emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo,
                                 ArgRegsSaveSize + 4, ARM::NoRegister,
                                 MachineInstr::NoFlags);
    return true;
  }

  if (TemporaryReg) {
    assert(!PopReg && "Unnecessary MOV is about to be inserted");
    PopReg = PopFriendly.find_first();
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
        .addReg(TemporaryReg, RegState::Define)
        .addReg(PopReg, RegState::Kill)
        .add(predOps(ARMCC::AL));
  }

  if (MBBI != MBB.end() && MBBI->getOpcode() == ARM::tPOP_RET) {
    // We couldn't use the direct restoration above, so
    // perform the opposite conversion: tPOP_RET to tPOP.
    MachineInstrBuilder MIB =
        BuildMI(MBB, MBBI, MBBI->getDebugLoc(), TII.get(ARM::tPOP))
            .add(predOps(ARMCC::AL));
    bool Popped = false;
    for (auto MO: MBBI->operands())
      if (MO.isReg() && (MO.isImplicit() || MO.isDef()) &&
          MO.getReg() != ARM::PC) {
        MIB.add(MO);
        if (!MO.isImplicit())
          Popped = true;
      }
    // Is there anything left to pop?
    if (!Popped)
      MBB.erase(MIB.getInstr());
    // Erase the old instruction.
    MBB.erase(MBBI);
    MBBI = BuildMI(MBB, MBB.end(), dl, TII.get(ARM::tBX_RET))
               .add(predOps(ARMCC::AL));
  }

  assert(PopReg && "Do not know how to get LR");
  BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP))
      .add(predOps(ARMCC::AL))
      .addReg(PopReg, RegState::Define);

  emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize,
                               ARM::NoRegister, MachineInstr::NoFlags);

  BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
      .addReg(ARM::LR, RegState::Define)
      .addReg(PopReg, RegState::Kill)
      .add(predOps(ARMCC::AL));

  if (TemporaryReg)
    BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
        .addReg(PopReg, RegState::Define)
        .addReg(TemporaryReg, RegState::Kill)
        .add(predOps(ARMCC::AL));

  return true;
}

using ARMRegSet = std::bitset<ARM::NUM_TARGET_REGS>;

// Return the first iteraror after CurrentReg which is present in EnabledRegs,
// or OrderEnd if no further registers are in that set. This does not advance
// the iterator fiorst, so returns CurrentReg if it is in EnabledRegs.
static const unsigned *findNextOrderedReg(const unsigned *CurrentReg,
                                          const ARMRegSet &EnabledRegs,
                                          const unsigned *OrderEnd) {
  while (CurrentReg != OrderEnd && !EnabledRegs[*CurrentReg])
    ++CurrentReg;
  return CurrentReg;
}

bool Thumb1FrameLowering::spillCalleeSavedRegisters(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
    ArrayRef<CalleeSavedInfo> CSI, const TargetRegisterInfo *TRI) const {
  if (CSI.empty())
    return false;

  DebugLoc DL;
  const TargetInstrInfo &TII = *STI.getInstrInfo();
  MachineFunction &MF = *MBB.getParent();
  const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());

  ARMRegSet LoRegsToSave; // r0-r7, lr
  ARMRegSet HiRegsToSave; // r8-r11
  ARMRegSet CopyRegs;     // Registers which can be used after pushing
                          // LoRegs for saving HiRegs.

  for (const CalleeSavedInfo &I : llvm::reverse(CSI)) {
    Register Reg = I.getReg();

    if (ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR) {
      LoRegsToSave[Reg] = true;
    } else if (ARM::hGPRRegClass.contains(Reg) && Reg != ARM::LR) {
      HiRegsToSave[Reg] = true;
    } else {
      llvm_unreachable("callee-saved register of unexpected class");
    }

    if ((ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR) &&
        !MF.getRegInfo().isLiveIn(Reg) &&
        !(hasFP(MF) && Reg == RegInfo->getFrameRegister(MF)))
      CopyRegs[Reg] = true;
  }

  // Unused argument registers can be used for the high register saving.
  for (unsigned ArgReg : {ARM::R0, ARM::R1, ARM::R2, ARM::R3})
    if (!MF.getRegInfo().isLiveIn(ArgReg))
      CopyRegs[ArgReg] = true;

  // Push the low registers and lr
  const MachineRegisterInfo &MRI = MF.getRegInfo();
  if (!LoRegsToSave.none()) {
    MachineInstrBuilder MIB =
        BuildMI(MBB, MI, DL, TII.get(ARM::tPUSH)).add(predOps(ARMCC::AL));
    for (unsigned Reg : {ARM::R4, ARM::R5, ARM::R6, ARM::R7, ARM::LR}) {
      if (LoRegsToSave[Reg]) {
        bool isKill = !MRI.isLiveIn(Reg);
        if (isKill && !MRI.isReserved(Reg))
          MBB.addLiveIn(Reg);

        MIB.addReg(Reg, getKillRegState(isKill));
      }
    }
    MIB.setMIFlags(MachineInstr::FrameSetup);
  }

  // Push the high registers. There are no store instructions that can access
  // these registers directly, so we have to move them to low registers, and
  // push them. This might take multiple pushes, as it is possible for there to
  // be fewer low registers available than high registers which need saving.

  // These are in reverse order so that in the case where we need to use
  // multiple PUSH instructions, the order of the registers on the stack still
  // matches the unwind info. They need to be swicthed back to ascending order
  // before adding to the PUSH instruction.
  static const unsigned AllCopyRegs[] = {ARM::LR, ARM::R7, ARM::R6,
                                         ARM::R5, ARM::R4, ARM::R3,
                                         ARM::R2, ARM::R1, ARM::R0};
  static const unsigned AllHighRegs[] = {ARM::R11, ARM::R10, ARM::R9, ARM::R8};

  const unsigned *AllCopyRegsEnd = std::end(AllCopyRegs);
  const unsigned *AllHighRegsEnd = std::end(AllHighRegs);

  // Find the first register to save.
  const unsigned *HiRegToSave = findNextOrderedReg(
      std::begin(AllHighRegs), HiRegsToSave, AllHighRegsEnd);

  while (HiRegToSave != AllHighRegsEnd) {
    // Find the first low register to use.
    const unsigned *CopyReg =
        findNextOrderedReg(std::begin(AllCopyRegs), CopyRegs, AllCopyRegsEnd);

    // Create the PUSH, but don't insert it yet (the MOVs need to come first).
    MachineInstrBuilder PushMIB = BuildMI(MF, DL, TII.get(ARM::tPUSH))
                                      .add(predOps(ARMCC::AL))
                                      .setMIFlags(MachineInstr::FrameSetup);

    SmallVector<unsigned, 4> RegsToPush;
    while (HiRegToSave != AllHighRegsEnd && CopyReg != AllCopyRegsEnd) {
      if (HiRegsToSave[*HiRegToSave]) {
        bool isKill = !MRI.isLiveIn(*HiRegToSave);
        if (isKill && !MRI.isReserved(*HiRegToSave))
          MBB.addLiveIn(*HiRegToSave);

        // Emit a MOV from the high reg to the low reg.
        BuildMI(MBB, MI, DL, TII.get(ARM::tMOVr))
            .addReg(*CopyReg, RegState::Define)
            .addReg(*HiRegToSave, getKillRegState(isKill))
            .add(predOps(ARMCC::AL))
            .setMIFlags(MachineInstr::FrameSetup);

        // Record the register that must be added to the PUSH.
        RegsToPush.push_back(*CopyReg);

        CopyReg = findNextOrderedReg(++CopyReg, CopyRegs, AllCopyRegsEnd);
        HiRegToSave =
            findNextOrderedReg(++HiRegToSave, HiRegsToSave, AllHighRegsEnd);
      }
    }

    // Add the low registers to the PUSH, in ascending order.
    for (unsigned Reg : llvm::reverse(RegsToPush))
      PushMIB.addReg(Reg, RegState::Kill);

    // Insert the PUSH instruction after the MOVs.
    MBB.insert(MI, PushMIB);
  }

  return true;
}

bool Thumb1FrameLowering::restoreCalleeSavedRegisters(
    MachineBasicBlock &MBB, MachineBasicBlock::iterator MI,
    MutableArrayRef<CalleeSavedInfo> CSI, const TargetRegisterInfo *TRI) const {
  if (CSI.empty())
    return false;

  MachineFunction &MF = *MBB.getParent();
  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
  const TargetInstrInfo &TII = *STI.getInstrInfo();
  const ARMBaseRegisterInfo *RegInfo = static_cast<const ARMBaseRegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());

  bool isVarArg = AFI->getArgRegsSaveSize() > 0;
  DebugLoc DL = MI != MBB.end() ? MI->getDebugLoc() : DebugLoc();

  ARMRegSet LoRegsToRestore;
  ARMRegSet HiRegsToRestore;
  // Low registers (r0-r7) which can be used to restore the high registers.
  ARMRegSet CopyRegs;

  for (CalleeSavedInfo I : CSI) {
    Register Reg = I.getReg();

    if (ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR) {
      LoRegsToRestore[Reg] = true;
    } else if (ARM::hGPRRegClass.contains(Reg) && Reg != ARM::LR) {
      HiRegsToRestore[Reg] = true;
    } else {
      llvm_unreachable("callee-saved register of unexpected class");
    }

    // If this is a low register not used as the frame pointer, we may want to
    // use it for restoring the high registers.
    if ((ARM::tGPRRegClass.contains(Reg)) &&
        !(hasFP(MF) && Reg == RegInfo->getFrameRegister(MF)))
      CopyRegs[Reg] = true;
  }

  // If this is a return block, we may be able to use some unused return value
  // registers for restoring the high regs.
  auto Terminator = MBB.getFirstTerminator();
  if (Terminator != MBB.end() && Terminator->getOpcode() == ARM::tBX_RET) {
    CopyRegs[ARM::R0] = true;
    CopyRegs[ARM::R1] = true;
    CopyRegs[ARM::R2] = true;
    CopyRegs[ARM::R3] = true;
    for (auto Op : Terminator->implicit_operands()) {
      if (Op.isReg())
        CopyRegs[Op.getReg()] = false;
    }
  }

  static const unsigned AllCopyRegs[] = {ARM::R0, ARM::R1, ARM::R2, ARM::R3,
                                         ARM::R4, ARM::R5, ARM::R6, ARM::R7};
  static const unsigned AllHighRegs[] = {ARM::R8, ARM::R9, ARM::R10, ARM::R11};

  const unsigned *AllCopyRegsEnd = std::end(AllCopyRegs);
  const unsigned *AllHighRegsEnd = std::end(AllHighRegs);

  // Find the first register to restore.
  auto HiRegToRestore = findNextOrderedReg(std::begin(AllHighRegs),
                                           HiRegsToRestore, AllHighRegsEnd);

  while (HiRegToRestore != AllHighRegsEnd) {
    assert(!CopyRegs.none());
    // Find the first low register to use.
    auto CopyReg =
        findNextOrderedReg(std::begin(AllCopyRegs), CopyRegs, AllCopyRegsEnd);

    // Create the POP instruction.
    MachineInstrBuilder PopMIB =
        BuildMI(MBB, MI, DL, TII.get(ARM::tPOP)).add(predOps(ARMCC::AL));

    while (HiRegToRestore != AllHighRegsEnd && CopyReg != AllCopyRegsEnd) {
      // Add the low register to the POP.
      PopMIB.addReg(*CopyReg, RegState::Define);

      // Create the MOV from low to high register.
      BuildMI(MBB, MI, DL, TII.get(ARM::tMOVr))
          .addReg(*HiRegToRestore, RegState::Define)
          .addReg(*CopyReg, RegState::Kill)
          .add(predOps(ARMCC::AL));

      CopyReg = findNextOrderedReg(++CopyReg, CopyRegs, AllCopyRegsEnd);
      HiRegToRestore =
          findNextOrderedReg(++HiRegToRestore, HiRegsToRestore, AllHighRegsEnd);
    }
  }

  MachineInstrBuilder MIB =
      BuildMI(MF, DL, TII.get(ARM::tPOP)).add(predOps(ARMCC::AL));

  bool NeedsPop = false;
  for (CalleeSavedInfo &Info : llvm::reverse(CSI)) {
    Register Reg = Info.getReg();

    // High registers (excluding lr) have already been dealt with
    if (!(ARM::tGPRRegClass.contains(Reg) || Reg == ARM::LR))
      continue;

    if (Reg == ARM::LR) {
      Info.setRestored(false);
      if (!MBB.succ_empty() ||
          MI->getOpcode() == ARM::TCRETURNdi ||
          MI->getOpcode() == ARM::TCRETURNri)
        // LR may only be popped into PC, as part of return sequence.
        // If this isn't the return sequence, we'll need emitPopSpecialFixUp
        // to restore LR the hard way.
        // FIXME: if we don't pass any stack arguments it would be actually
        // advantageous *and* correct to do the conversion to an ordinary call
        // instruction here.
        continue;
      // Special epilogue for vararg functions. See emitEpilogue
      if (isVarArg)
        continue;
      // ARMv4T requires BX, see emitEpilogue
      if (!STI.hasV5TOps())
        continue;

      // CMSE entry functions must return via BXNS, see emitEpilogue.
      if (AFI->isCmseNSEntryFunction())
        continue;

      // Pop LR into PC.
      Reg = ARM::PC;
      (*MIB).setDesc(TII.get(ARM::tPOP_RET));
      if (MI != MBB.end())
        MIB.copyImplicitOps(*MI);
      MI = MBB.erase(MI);
    }
    MIB.addReg(Reg, getDefRegState(true));
    NeedsPop = true;
  }

  // It's illegal to emit pop instruction without operands.
  if (NeedsPop)
    MBB.insert(MI, &*MIB);
  else
    MF.deleteMachineInstr(MIB);

  return true;
}