llvm.org GIT mirror llvm / release_35@215010 lib / Target / AArch64 / AArch64RegisterInfo.cpp
release_35@215010

Tree @release_35@215010 (Download .tar.gz)

AArch64RegisterInfo.cpp @release_35@215010raw · 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
//===- AArch64RegisterInfo.cpp - AArch64 Register 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 AArch64 implementation of the TargetRegisterInfo
// class.
//
//===----------------------------------------------------------------------===//

#include "AArch64RegisterInfo.h"
#include "AArch64FrameLowering.h"
#include "AArch64InstrInfo.h"
#include "AArch64Subtarget.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/RegisterScavenging.h"
#include "llvm/IR/Function.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetFrameLowering.h"
#include "llvm/Target/TargetOptions.h"

using namespace llvm;

#define GET_REGINFO_TARGET_DESC
#include "AArch64GenRegisterInfo.inc"

AArch64RegisterInfo::AArch64RegisterInfo(const AArch64InstrInfo *tii,
                                         const AArch64Subtarget *sti)
    : AArch64GenRegisterInfo(AArch64::LR), TII(tii), STI(sti) {}

const MCPhysReg *
AArch64RegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
  assert(MF && "Invalid MachineFunction pointer.");
  if (MF->getFunction()->getCallingConv() == CallingConv::AnyReg)
    return CSR_AArch64_AllRegs_SaveList;
  else
    return CSR_AArch64_AAPCS_SaveList;
}

const uint32_t *
AArch64RegisterInfo::getCallPreservedMask(CallingConv::ID CC) const {
  if (CC == CallingConv::AnyReg)
    return CSR_AArch64_AllRegs_RegMask;
  else
    return CSR_AArch64_AAPCS_RegMask;
}

const uint32_t *AArch64RegisterInfo::getTLSCallPreservedMask() const {
  if (STI->isTargetDarwin())
    return CSR_AArch64_TLS_Darwin_RegMask;

  assert(STI->isTargetELF() && "only expect Darwin or ELF TLS");
  return CSR_AArch64_TLS_ELF_RegMask;
}

const uint32_t *
AArch64RegisterInfo::getThisReturnPreservedMask(CallingConv::ID) const {
  // This should return a register mask that is the same as that returned by
  // getCallPreservedMask but that additionally preserves the register used for
  // the first i64 argument (which must also be the register used to return a
  // single i64 return value)
  //
  // In case that the calling convention does not use the same register for
  // both, the function should return NULL (does not currently apply)
  return CSR_AArch64_AAPCS_ThisReturn_RegMask;
}

BitVector
AArch64RegisterInfo::getReservedRegs(const MachineFunction &MF) const {
  const TargetFrameLowering *TFI = MF.getTarget().getFrameLowering();

  // FIXME: avoid re-calculating this every time.
  BitVector Reserved(getNumRegs());
  Reserved.set(AArch64::SP);
  Reserved.set(AArch64::XZR);
  Reserved.set(AArch64::WSP);
  Reserved.set(AArch64::WZR);

  if (TFI->hasFP(MF) || STI->isTargetDarwin()) {
    Reserved.set(AArch64::FP);
    Reserved.set(AArch64::W29);
  }

  if (STI->isTargetDarwin()) {
    Reserved.set(AArch64::X18); // Platform register
    Reserved.set(AArch64::W18);
  }

  if (hasBasePointer(MF)) {
    Reserved.set(AArch64::X19);
    Reserved.set(AArch64::W19);
  }

  return Reserved;
}

bool AArch64RegisterInfo::isReservedReg(const MachineFunction &MF,
                                      unsigned Reg) const {
  const TargetFrameLowering *TFI = MF.getTarget().getFrameLowering();

  switch (Reg) {
  default:
    break;
  case AArch64::SP:
  case AArch64::XZR:
  case AArch64::WSP:
  case AArch64::WZR:
    return true;
  case AArch64::X18:
  case AArch64::W18:
    return STI->isTargetDarwin();
  case AArch64::FP:
  case AArch64::W29:
    return TFI->hasFP(MF) || STI->isTargetDarwin();
  case AArch64::W19:
  case AArch64::X19:
    return hasBasePointer(MF);
  }

  return false;
}

const TargetRegisterClass *
AArch64RegisterInfo::getPointerRegClass(const MachineFunction &MF,
                                      unsigned Kind) const {
  return &AArch64::GPR64RegClass;
}

const TargetRegisterClass *
AArch64RegisterInfo::getCrossCopyRegClass(const TargetRegisterClass *RC) const {
  if (RC == &AArch64::CCRRegClass)
    return &AArch64::GPR64RegClass; // Only MSR & MRS copy NZCV.
  return RC;
}

unsigned AArch64RegisterInfo::getBaseRegister() const { return AArch64::X19; }

bool AArch64RegisterInfo::hasBasePointer(const MachineFunction &MF) const {
  const MachineFrameInfo *MFI = MF.getFrameInfo();

  // In the presence of variable sized objects, if the fixed stack size is
  // large enough that referencing from the FP won't result in things being
  // in range relatively often, we can use a base pointer to allow access
  // from the other direction like the SP normally works.
  if (MFI->hasVarSizedObjects()) {
    // Conservatively estimate whether the negative offset from the frame
    // pointer will be sufficient to reach. If a function has a smallish
    // frame, it's less likely to have lots of spills and callee saved
    // space, so it's all more likely to be within range of the frame pointer.
    // If it's wrong, we'll materialize the constant and still get to the
    // object; it's just suboptimal. Negative offsets use the unscaled
    // load/store instructions, which have a 9-bit signed immediate.
    if (MFI->getLocalFrameSize() < 256)
      return false;
    return true;
  }

  return false;
}

unsigned
AArch64RegisterInfo::getFrameRegister(const MachineFunction &MF) const {
  const TargetFrameLowering *TFI = MF.getTarget().getFrameLowering();

  return TFI->hasFP(MF) ? AArch64::FP : AArch64::SP;
}

bool AArch64RegisterInfo::requiresRegisterScavenging(
    const MachineFunction &MF) const {
  return true;
}

bool AArch64RegisterInfo::requiresVirtualBaseRegisters(
    const MachineFunction &MF) const {
  return true;
}

bool
AArch64RegisterInfo::useFPForScavengingIndex(const MachineFunction &MF) const {
  const MachineFrameInfo *MFI = MF.getFrameInfo();
  // AArch64FrameLowering::resolveFrameIndexReference() can always fall back
  // to the stack pointer, so only put the emergency spill slot next to the
  // FP when there's no better way to access it (SP or base pointer).
  return MFI->hasVarSizedObjects() && !hasBasePointer(MF);
}

bool AArch64RegisterInfo::requiresFrameIndexScavenging(
    const MachineFunction &MF) const {
  return true;
}

bool
AArch64RegisterInfo::cannotEliminateFrame(const MachineFunction &MF) const {
  const MachineFrameInfo *MFI = MF.getFrameInfo();
  // Only consider eliminating leaf frames.
  if (MFI->hasCalls() || (MF.getTarget().Options.DisableFramePointerElim(MF) &&
                          MFI->adjustsStack()))
    return true;
  return MFI->hasVarSizedObjects() || MFI->isFrameAddressTaken();
}

/// needsFrameBaseReg - Returns true if the instruction's frame index
/// reference would be better served by a base register other than FP
/// or SP. Used by LocalStackFrameAllocation to determine which frame index
/// references it should create new base registers for.
bool AArch64RegisterInfo::needsFrameBaseReg(MachineInstr *MI,
                                            int64_t Offset) const {
  for (unsigned i = 0; !MI->getOperand(i).isFI(); ++i)
    assert(i < MI->getNumOperands() &&
           "Instr doesn't have FrameIndex operand!");

  // It's the load/store FI references that cause issues, as it can be difficult
  // to materialize the offset if it won't fit in the literal field. Estimate
  // based on the size of the local frame and some conservative assumptions
  // about the rest of the stack frame (note, this is pre-regalloc, so
  // we don't know everything for certain yet) whether this offset is likely
  // to be out of range of the immediate. Return true if so.

  // We only generate virtual base registers for loads and stores, so
  // return false for everything else.
  if (!MI->mayLoad() && !MI->mayStore())
    return false;

  // Without a virtual base register, if the function has variable sized
  // objects, all fixed-size local references will be via the frame pointer,
  // Approximate the offset and see if it's legal for the instruction.
  // Note that the incoming offset is based on the SP value at function entry,
  // so it'll be negative.
  MachineFunction &MF = *MI->getParent()->getParent();
  const TargetFrameLowering *TFI = MF.getTarget().getFrameLowering();
  MachineFrameInfo *MFI = MF.getFrameInfo();

  // Estimate an offset from the frame pointer.
  // Conservatively assume all GPR callee-saved registers get pushed.
  // FP, LR, X19-X28, D8-D15. 64-bits each.
  int64_t FPOffset = Offset - 16 * 20;
  // Estimate an offset from the stack pointer.
  // The incoming offset is relating to the SP at the start of the function,
  // but when we access the local it'll be relative to the SP after local
  // allocation, so adjust our SP-relative offset by that allocation size.
  Offset += MFI->getLocalFrameSize();
  // Assume that we'll have at least some spill slots allocated.
  // FIXME: This is a total SWAG number. We should run some statistics
  //        and pick a real one.
  Offset += 128; // 128 bytes of spill slots

  // If there is a frame pointer, try using it.
  // The FP is only available if there is no dynamic realignment. We
  // don't know for sure yet whether we'll need that, so we guess based
  // on whether there are any local variables that would trigger it.
  if (TFI->hasFP(MF) && isFrameOffsetLegal(MI, FPOffset))
    return false;

  // If we can reference via the stack pointer or base pointer, try that.
  // FIXME: This (and the code that resolves the references) can be improved
  //        to only disallow SP relative references in the live range of
  //        the VLA(s). In practice, it's unclear how much difference that
  //        would make, but it may be worth doing.
  if (isFrameOffsetLegal(MI, Offset))
    return false;

  // The offset likely isn't legal; we want to allocate a virtual base register.
  return true;
}

bool AArch64RegisterInfo::isFrameOffsetLegal(const MachineInstr *MI,
                                             int64_t Offset) const {
  assert(Offset <= INT_MAX && "Offset too big to fit in int.");
  assert(MI && "Unable to get the legal offset for nil instruction.");
  int SaveOffset = Offset;
  return isAArch64FrameOffsetLegal(*MI, SaveOffset) & AArch64FrameOffsetIsLegal;
}

/// Insert defining instruction(s) for BaseReg to be a pointer to FrameIdx
/// at the beginning of the basic block.
void AArch64RegisterInfo::materializeFrameBaseRegister(MachineBasicBlock *MBB,
                                                       unsigned BaseReg,
                                                       int FrameIdx,
                                                       int64_t Offset) const {
  MachineBasicBlock::iterator Ins = MBB->begin();
  DebugLoc DL; // Defaults to "unknown"
  if (Ins != MBB->end())
    DL = Ins->getDebugLoc();

  const MCInstrDesc &MCID = TII->get(AArch64::ADDXri);
  MachineRegisterInfo &MRI = MBB->getParent()->getRegInfo();
  const MachineFunction &MF = *MBB->getParent();
  MRI.constrainRegClass(BaseReg, TII->getRegClass(MCID, 0, this, MF));
  unsigned Shifter = AArch64_AM::getShifterImm(AArch64_AM::LSL, 0);

  BuildMI(*MBB, Ins, DL, MCID, BaseReg)
      .addFrameIndex(FrameIdx)
      .addImm(Offset)
      .addImm(Shifter);
}

void AArch64RegisterInfo::resolveFrameIndex(MachineInstr &MI, unsigned BaseReg,
                                            int64_t Offset) const {
  int Off = Offset; // ARM doesn't need the general 64-bit offsets
  unsigned i = 0;

  while (!MI.getOperand(i).isFI()) {
    ++i;
    assert(i < MI.getNumOperands() && "Instr doesn't have FrameIndex operand!");
  }
  bool Done = rewriteAArch64FrameIndex(MI, i, BaseReg, Off, TII);
  assert(Done && "Unable to resolve frame index!");
  (void)Done;
}

void AArch64RegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II,
                                              int SPAdj, unsigned FIOperandNum,
                                              RegScavenger *RS) const {
  assert(SPAdj == 0 && "Unexpected");

  MachineInstr &MI = *II;
  MachineBasicBlock &MBB = *MI.getParent();
  MachineFunction &MF = *MBB.getParent();
  const AArch64FrameLowering *TFI = static_cast<const AArch64FrameLowering *>(
      MF.getTarget().getFrameLowering());

  int FrameIndex = MI.getOperand(FIOperandNum).getIndex();
  unsigned FrameReg;
  int Offset;

  // Special handling of dbg_value, stackmap and patchpoint instructions.
  if (MI.isDebugValue() || MI.getOpcode() == TargetOpcode::STACKMAP ||
      MI.getOpcode() == TargetOpcode::PATCHPOINT) {
    Offset = TFI->resolveFrameIndexReference(MF, FrameIndex, FrameReg,
                                             /*PreferFP=*/true);
    Offset += MI.getOperand(FIOperandNum + 1).getImm();
    MI.getOperand(FIOperandNum).ChangeToRegister(FrameReg, false /*isDef*/);
    MI.getOperand(FIOperandNum + 1).ChangeToImmediate(Offset);
    return;
  }

  // Modify MI as necessary to handle as much of 'Offset' as possible
  Offset = TFI->resolveFrameIndexReference(MF, FrameIndex, FrameReg);
  if (rewriteAArch64FrameIndex(MI, FIOperandNum, FrameReg, Offset, TII))
    return;

  assert((!RS || !RS->isScavengingFrameIndex(FrameIndex)) &&
         "Emergency spill slot is out of reach");

  // If we get here, the immediate doesn't fit into the instruction.  We folded
  // as much as possible above.  Handle the rest, providing a register that is
  // SP+LargeImm.
  unsigned ScratchReg =
      MF.getRegInfo().createVirtualRegister(&AArch64::GPR64RegClass);
  emitFrameOffset(MBB, II, MI.getDebugLoc(), ScratchReg, FrameReg, Offset, TII);
  MI.getOperand(FIOperandNum).ChangeToRegister(ScratchReg, false, false, true);
}

namespace llvm {

unsigned AArch64RegisterInfo::getRegPressureLimit(const TargetRegisterClass *RC,
                                                  MachineFunction &MF) const {
  const TargetFrameLowering *TFI = MF.getTarget().getFrameLowering();

  switch (RC->getID()) {
  default:
    return 0;
  case AArch64::GPR32RegClassID:
  case AArch64::GPR32spRegClassID:
  case AArch64::GPR32allRegClassID:
  case AArch64::GPR64spRegClassID:
  case AArch64::GPR64allRegClassID:
  case AArch64::GPR64RegClassID:
  case AArch64::GPR32commonRegClassID:
  case AArch64::GPR64commonRegClassID:
    return 32 - 1                                      // XZR/SP
           - (TFI->hasFP(MF) || STI->isTargetDarwin()) // FP
           - STI->isTargetDarwin() // X18 reserved as platform register
           - hasBasePointer(MF);   // X19
  case AArch64::FPR8RegClassID:
  case AArch64::FPR16RegClassID:
  case AArch64::FPR32RegClassID:
  case AArch64::FPR64RegClassID:
  case AArch64::FPR128RegClassID:
    return 32;

  case AArch64::DDRegClassID:
  case AArch64::DDDRegClassID:
  case AArch64::DDDDRegClassID:
  case AArch64::QQRegClassID:
  case AArch64::QQQRegClassID:
  case AArch64::QQQQRegClassID:
    return 32;

  case AArch64::FPR128_loRegClassID:
    return 16;
  }
}

} // namespace llvm