llvm.org GIT mirror llvm / 1b27914 lib / Target / ARM / Thumb1FrameLowering.cpp
1b27914

Tree @1b27914 (Download .tar.gz)

Thumb1FrameLowering.cpp @1b27914raw · history · 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
//===-- Thumb1FrameLowering.cpp - Thumb1 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 Thumb1 implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//

#include "Thumb1FrameLowering.h"
#include "ARMMachineFunctionInfo.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"

using namespace llvm;

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

bool Thumb1FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const{
  const MachineFrameInfo *FFI = MF.getFrameInfo();
  unsigned CFSize = FFI->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 !MF.getFrameInfo()->hasVarSizedObjects();
}

static void
emitSPUpdate(MachineBasicBlock &MBB,
             MachineBasicBlock::iterator &MBBI,
             const TargetInstrInfo &TII, DebugLoc dl,
             const Thumb1RegisterInfo &MRI,
             int NumBytes, unsigned MIFlags = MachineInstr::NoFlags)  {
  emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::SP, ARM::SP, NumBytes, TII,
                            MRI, MIFlags);
}


void Thumb1FrameLowering::
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
                              MachineBasicBlock::iterator I) const {
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(MF.getSubtarget().getInstrInfo());
  const Thumb1RegisterInfo *RegInfo = static_cast<const Thumb1RegisterInfo *>(
      MF.getSubtarget().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 = Old->getOperand(0).getImm();
    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.
      unsigned Align = getStackAlignment();
      Amount = (Amount+Align-1)/Align*Align;

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

void Thumb1FrameLowering::emitPrologue(MachineFunction &MF) const {
  MachineBasicBlock &MBB = MF.front();
  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 Thumb1RegisterInfo *RegInfo = static_cast<const Thumb1RegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(MF.getSubtarget().getInstrInfo());

  unsigned Align = MF.getTarget()
                       .getSubtargetImpl()
                       ->getFrameLowering()
                       ->getStackAlignment();
  unsigned ArgRegsSaveSize = AFI->getArgRegsSaveSize(Align);
  unsigned NumBytes = MFI->getStackSize();
  assert(NumBytes >= ArgRegsSaveSize &&
         "ArgRegsSaveSize is included in NumBytes");
  const std::vector<CalleeSavedInfo> &CSI = MFI->getCalleeSavedInfo();
  DebugLoc dl = MBBI != MBB.end() ? MBBI->getDebugLoc() : DebugLoc();
  unsigned FramePtr = RegInfo->getFrameRegister(MF);
  unsigned 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) {
    emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize,
                 MachineInstr::FrameSetup);
    CFAOffset -= ArgRegsSaveSize;
    unsigned CFIIndex = MMI.addFrameInst(
        MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
    BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }

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

  for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
    unsigned Reg = CSI[i].getReg();
    int FI = CSI[i].getFrameIdx();
    switch (Reg) {
    case ARM::R8:
    case ARM::R9:
    case ARM::R10:
    case ARM::R11:
      if (STI.isTargetMachO()) {
        GPRCS2Size += 4;
        break;
      }
      // 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;
    if (MBBI != MBB.end())
      dl = MBBI->getDebugLoc();
  }

  // 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 (tryFoldSPUpdateIntoPushPop(STI, MF, std::prev(MBBI), NumBytes)) {
    FramePtrOffsetInBlock = NumBytes;
    adjustedGPRCS1Size += NumBytes;
    NumBytes = 0;
  }

  if (adjustedGPRCS1Size) {
    CFAOffset -= adjustedGPRCS1Size;
    unsigned CFIIndex = MMI.addFrameInst(
        MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset));
    BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
        .addCFIIndex(CFIIndex)
        .setMIFlags(MachineInstr::FrameSetup);
  }
  for (std::vector<CalleeSavedInfo>::const_iterator I = CSI.begin(),
         E = CSI.end(); I != E; ++I) {
    unsigned 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.isTargetMachO())
        break;
      // fallthough
    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 = MMI.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;
    AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tADDrSPi), FramePtr)
      .addReg(ARM::SP).addImm(FramePtrOffsetInBlock / 4)
      .setMIFlags(MachineInstr::FrameSetup));
    if(FramePtrOffsetInBlock) {
      CFAOffset += FramePtrOffsetInBlock;
      unsigned CFIIndex = MMI.addFrameInst(MCCFIInstruction::createDefCfa(
          nullptr, MRI->getDwarfRegNum(FramePtr, true), CFAOffset));
      BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
          .addCFIIndex(CFIIndex)
          .setMIFlags(MachineInstr::FrameSetup);
    } else {
      unsigned CFIIndex =
          MMI.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);
  }

  if (NumBytes) {
    // Insert it after all the callee-save spills.
    emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes,
                 MachineInstr::FrameSetup);
    if (!HasFP) {
      CFAOffset -= NumBytes;
      unsigned CFIIndex = MMI.addFrameInst(
          MCCFIInstruction::createDefCfaOffset(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);

  // Thumb1 does not currently support dynamic stack realignment.  Report a
  // fatal error rather then silently generate bad code.
  if (RegInfo->needsStackRealignment(MF))
      report_fatal_error("Dynamic stack realignment not supported for thumb1.");

  // 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))
    AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr), BasePtr)
                   .addReg(ARM::SP));

  // 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);
}

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) {
    // The first two operands are predicates. The last two are
    // imp-def and imp-use of SP. Check everything in between.
    for (int i = 2, e = MI->getNumOperands() - 2; i != e; ++i)
      if (!isCalleeSavedRegister(MI->getOperand(i).getReg(), CSRegs))
        return false;
    return true;
  }
  return false;
}

void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF,
                                   MachineBasicBlock &MBB) const {
  MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
  assert((MBBI->getOpcode() == ARM::tBX_RET ||
          MBBI->getOpcode() == ARM::tPOP_RET) &&
         "Can only insert epilog into returning blocks");
  DebugLoc dl = MBBI->getDebugLoc();
  MachineFrameInfo *MFI = MF.getFrameInfo();
  ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
  const Thumb1RegisterInfo *RegInfo = static_cast<const Thumb1RegisterInfo *>(
      MF.getSubtarget().getRegisterInfo());
  const Thumb1InstrInfo &TII =
      *static_cast<const Thumb1InstrInfo *>(MF.getSubtarget().getInstrInfo());

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

  if (!AFI->hasStackFrame()) {
    if (NumBytes - ArgRegsSaveSize != 0)
      emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes - ArgRegsSaveSize);
  } 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(MF.getRegInfo().isPhysRegUsed(ARM::R4) &&
               "No scratch register to restore SP from FP!");
        emitThumbRegPlusImmediate(MBB, MBBI, dl, ARM::R4, FramePtr, -NumBytes,
                                  TII, *RegInfo);
        AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
                               ARM::SP)
          .addReg(ARM::R4));
      } else
        AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr),
                               ARM::SP)
          .addReg(FramePtr));
    } else {
      if (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))
          emitSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes);
      } else if (!tryFoldSPUpdateIntoPushPop(STI, MF, MBBI, NumBytes))
        emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes);
    }
  }

  bool IsV4PopReturn = false;
  for (const CalleeSavedInfo &CSI : MFI->getCalleeSavedInfo())
    if (CSI.getReg() == ARM::LR)
      IsV4PopReturn = true;
  IsV4PopReturn &= STI.hasV4TOps() && !STI.hasV5TOps();

  // Unlike T2 and ARM mode, the T1 pop instruction cannot restore
  // to LR, and we can't pop the value directly to the PC since
  // we need to update the SP after popping the value. So instead
  // we have to emit:
  //   POP {r3}
  //   ADD sp, #offset
  //   BX r3
  // If this would clobber a return value, then generate this sequence instead:
  //   MOV ip, r3
  //   POP {r3}
  //   ADD sp, #offset
  //   MOV lr, r3
  //   MOV r3, ip
  //   BX lr
  if (ArgRegsSaveSize || IsV4PopReturn) {
    // Get the last instruction, tBX_RET
    MBBI = MBB.getLastNonDebugInstr();
    assert (MBBI->getOpcode() == ARM::tBX_RET);
    DebugLoc dl = MBBI->getDebugLoc();

    if (AFI->getReturnRegsCount() <= 3) {
      // Epilogue: pop saved LR to R3 and branch off it. 
      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
        .addReg(ARM::R3, RegState::Define);

      emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);

      MachineInstrBuilder MIB =
        BuildMI(MBB, MBBI, dl, TII.get(ARM::tBX))
        .addReg(ARM::R3, RegState::Kill);
      AddDefaultPred(MIB);
      MIB.copyImplicitOps(&*MBBI);
      // erase the old tBX_RET instruction
      MBB.erase(MBBI);
    } else {
      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
        .addReg(ARM::R12, RegState::Define)
        .addReg(ARM::R3, RegState::Kill));

      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tPOP)))
        .addReg(ARM::R3, RegState::Define);

      emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize);

      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
        .addReg(ARM::LR, RegState::Define)
        .addReg(ARM::R3, RegState::Kill));

      AddDefaultPred(BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr))
        .addReg(ARM::R3, RegState::Define)
        .addReg(ARM::R12, RegState::Kill));
      // Keep the tBX_RET instruction
    }
  }
}

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

  DebugLoc DL;
  MachineFunction &MF = *MBB.getParent();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();

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

  MachineInstrBuilder MIB = BuildMI(MBB, MI, DL, TII.get(ARM::tPUSH));
  AddDefaultPred(MIB);
  for (unsigned i = CSI.size(); i != 0; --i) {
    unsigned Reg = CSI[i-1].getReg();
    bool isKill = true;

    // Add the callee-saved register as live-in unless it's LR and
    // @llvm.returnaddress is called. If LR is returned for @llvm.returnaddress
    // then it's already added to the function and entry block live-in sets.
    if (Reg == ARM::LR) {
      MachineFunction &MF = *MBB.getParent();
      if (MF.getFrameInfo()->isReturnAddressTaken() &&
          MF.getRegInfo().isLiveIn(Reg))
        isKill = false;
    }

    if (isKill)
      MBB.addLiveIn(Reg);

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

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

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

  bool isVarArg = AFI->getArgRegsSaveSize() > 0;
  DebugLoc DL = MI->getDebugLoc();
  MachineInstrBuilder MIB = BuildMI(MF, DL, TII.get(ARM::tPOP));
  AddDefaultPred(MIB);

  bool NumRegs = false;
  for (unsigned i = CSI.size(); i != 0; --i) {
    unsigned Reg = CSI[i-1].getReg();
    if (Reg == ARM::LR) {
      // Special epilogue for vararg functions. See emitEpilogue
      if (isVarArg)
        continue;
      // ARMv4T requires BX, see emitEpilogue
      if (STI.hasV4TOps() && !STI.hasV5TOps())
        continue;
      Reg = ARM::PC;
      (*MIB).setDesc(TII.get(ARM::tPOP_RET));
      MIB.copyImplicitOps(&*MI);
      MI = MBB.erase(MI);
    }
    MIB.addReg(Reg, getDefRegState(true));
    NumRegs = true;
  }

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

  return true;
}