aboutsummaryrefslogtreecommitdiff
blob: 9f6c7d65592d4031fb6200a1c435ba370c63850e (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
//===-- SparcFrameLowering.cpp - Sparc 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 Sparc implementation of TargetFrameLowering class.
//
//===----------------------------------------------------------------------===//

#include "SparcFrameLowering.h"
#include "SparcInstrInfo.h"
#include "SparcMachineFunctionInfo.h"
#include "SparcSubtarget.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/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetOptions.h"

using namespace llvm;

static cl::opt<bool>
DisableLeafProc("disable-sparc-leaf-proc",
                cl::init(false),
                cl::desc("Disable Sparc leaf procedure optimization."),
                cl::Hidden);

SparcFrameLowering::SparcFrameLowering(const SparcSubtarget &ST)
    : TargetFrameLowering(TargetFrameLowering::StackGrowsDown,
                          ST.is64Bit() ? 16 : 8, 0, ST.is64Bit() ? 16 : 8) {}

void SparcFrameLowering::emitSPAdjustment(MachineFunction &MF,
                                          MachineBasicBlock &MBB,
                                          MachineBasicBlock::iterator MBBI,
                                          int NumBytes,
                                          unsigned ADDrr,
                                          unsigned ADDri) const {

  DebugLoc dl;
  const SparcInstrInfo &TII =
      *static_cast<const SparcInstrInfo *>(MF.getSubtarget().getInstrInfo());

  if (NumBytes >= -4096 && NumBytes < 4096) {
    BuildMI(MBB, MBBI, dl, TII.get(ADDri), SP::O6)
      .addReg(SP::O6).addImm(NumBytes);
    return;
  }

  // Emit this the hard way.  This clobbers G1 which we always know is
  // available here.
  if (NumBytes >= 0) {
    // Emit nonnegative numbers with sethi + or.
    // sethi %hi(NumBytes), %g1
    // or %g1, %lo(NumBytes), %g1
    // add %sp, %g1, %sp
    BuildMI(MBB, MBBI, dl, TII.get(SP::SETHIi), SP::G1)
      .addImm(HI22(NumBytes));
    BuildMI(MBB, MBBI, dl, TII.get(SP::ORri), SP::G1)
      .addReg(SP::G1).addImm(LO10(NumBytes));
    BuildMI(MBB, MBBI, dl, TII.get(ADDrr), SP::O6)
      .addReg(SP::O6).addReg(SP::G1);
    return ;
  }

  // Emit negative numbers with sethi + xor.
  // sethi %hix(NumBytes), %g1
  // xor %g1, %lox(NumBytes), %g1
  // add %sp, %g1, %sp
  BuildMI(MBB, MBBI, dl, TII.get(SP::SETHIi), SP::G1)
    .addImm(HIX22(NumBytes));
  BuildMI(MBB, MBBI, dl, TII.get(SP::XORri), SP::G1)
    .addReg(SP::G1).addImm(LOX10(NumBytes));
  BuildMI(MBB, MBBI, dl, TII.get(ADDrr), SP::O6)
    .addReg(SP::O6).addReg(SP::G1);
}

void SparcFrameLowering::emitPrologue(MachineFunction &MF,
                                      MachineBasicBlock &MBB) const {
  SparcMachineFunctionInfo *FuncInfo = MF.getInfo<SparcMachineFunctionInfo>();

  assert(&MF.front() == &MBB && "Shrink-wrapping not yet supported");
  MachineFrameInfo &MFI = MF.getFrameInfo();
  const SparcSubtarget &Subtarget = MF.getSubtarget<SparcSubtarget>();
  const SparcInstrInfo &TII =
      *static_cast<const SparcInstrInfo *>(Subtarget.getInstrInfo());
  const SparcRegisterInfo &RegInfo =
      *static_cast<const SparcRegisterInfo *>(Subtarget.getRegisterInfo());
  MachineBasicBlock::iterator MBBI = MBB.begin();
  // Debug location must be unknown since the first debug location is used
  // to determine the end of the prologue.
  DebugLoc dl;
  bool NeedsStackRealignment = RegInfo.needsStackRealignment(MF);

  // FIXME: unfortunately, returning false from canRealignStack
  // actually just causes needsStackRealignment to return false,
  // rather than reporting an error, as would be sensible. This is
  // poor, but fixing that bogosity is going to be a large project.
  // For now, just see if it's lied, and report an error here.
  if (!NeedsStackRealignment && MFI.getMaxAlignment() > getStackAlignment())
    report_fatal_error("Function \"" + Twine(MF.getName()) + "\" required "
                       "stack re-alignment, but LLVM couldn't handle it "
                       "(probably because it has a dynamic alloca).");

  // Get the number of bytes to allocate from the FrameInfo
  int NumBytes = (int) MFI.getStackSize();

  unsigned SAVEri = SP::SAVEri;
  unsigned SAVErr = SP::SAVErr;
  if (FuncInfo->isLeafProc()) {
    if (NumBytes == 0)
      return;
    SAVEri = SP::ADDri;
    SAVErr = SP::ADDrr;
  }

  // The SPARC ABI is a bit odd in that it requires a reserved 92-byte
  // (128 in v9) area in the user's stack, starting at %sp. Thus, the
  // first part of the stack that can actually be used is located at
  // %sp + 92.
  //
  // We therefore need to add that offset to the total stack size
  // after all the stack objects are placed by
  // PrologEpilogInserter calculateFrameObjectOffsets. However, since the stack needs to be
  // aligned *after* the extra size is added, we need to disable
  // calculateFrameObjectOffsets's built-in stack alignment, by having
  // targetHandlesStackFrameRounding return true.


  // Add the extra call frame stack size, if needed. (This is the same
  // code as in PrologEpilogInserter, but also gets disabled by
  // targetHandlesStackFrameRounding)
  if (MFI.adjustsStack() && hasReservedCallFrame(MF))
    NumBytes += MFI.getMaxCallFrameSize();

  // Adds the SPARC subtarget-specific spill area to the stack
  // size. Also ensures target-required alignment.
  NumBytes = Subtarget.getAdjustedFrameSize(NumBytes);

  // Finally, ensure that the size is sufficiently aligned for the
  // data on the stack.
  if (MFI.getMaxAlignment() > 0) {
    NumBytes = alignTo(NumBytes, MFI.getMaxAlignment());
  }

  // Update stack size with corrected value.
  MFI.setStackSize(NumBytes);

  emitSPAdjustment(MF, MBB, MBBI, -NumBytes, SAVErr, SAVEri);

  unsigned regFP = RegInfo.getDwarfRegNum(SP::I6, true);

  // Emit ".cfi_def_cfa_register 30".
  unsigned CFIIndex =
      MF.addFrameInst(MCCFIInstruction::createDefCfaRegister(nullptr, regFP));
  BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
      .addCFIIndex(CFIIndex);

  // Emit ".cfi_window_save".
  CFIIndex = MF.addFrameInst(MCCFIInstruction::createWindowSave(nullptr));
  BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
      .addCFIIndex(CFIIndex);

  unsigned regInRA = RegInfo.getDwarfRegNum(SP::I7, true);
  unsigned regOutRA = RegInfo.getDwarfRegNum(SP::O7, true);
  // Emit ".cfi_register 15, 31".
  CFIIndex = MF.addFrameInst(
      MCCFIInstruction::createRegister(nullptr, regOutRA, regInRA));
  BuildMI(MBB, MBBI, dl, TII.get(TargetOpcode::CFI_INSTRUCTION))
      .addCFIIndex(CFIIndex);

  if (NeedsStackRealignment) {
    int64_t Bias = Subtarget.getStackPointerBias();
    unsigned regUnbiased;
    if (Bias) {
      // This clobbers G1 which we always know is available here.
      regUnbiased = SP::G1;
      // add %o6, BIAS, %g1
      BuildMI(MBB, MBBI, dl, TII.get(SP::ADDri), regUnbiased)
        .addReg(SP::O6).addImm(Bias);
    } else
      regUnbiased = SP::O6;

    // andn %regUnbiased, MaxAlign-1, %regUnbiased
    int MaxAlign = MFI.getMaxAlignment();
    BuildMI(MBB, MBBI, dl, TII.get(SP::ANDNri), regUnbiased)
      .addReg(regUnbiased).addImm(MaxAlign - 1);

    if (Bias) {
      // add %g1, -BIAS, %o6
      BuildMI(MBB, MBBI, dl, TII.get(SP::ADDri), SP::O6)
        .addReg(regUnbiased).addImm(-Bias);
    }
  }
}

MachineBasicBlock::iterator SparcFrameLowering::
eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
                              MachineBasicBlock::iterator I) const {
  if (!hasReservedCallFrame(MF)) {
    MachineInstr &MI = *I;
    int Size = MI.getOperand(0).getImm();
    if (MI.getOpcode() == SP::ADJCALLSTACKDOWN)
      Size = -Size;

    if (Size)
      emitSPAdjustment(MF, MBB, I, Size, SP::ADDrr, SP::ADDri);
  }
  return MBB.erase(I);
}


void SparcFrameLowering::emitEpilogue(MachineFunction &MF,
                                  MachineBasicBlock &MBB) const {
  SparcMachineFunctionInfo *FuncInfo = MF.getInfo<SparcMachineFunctionInfo>();
  MachineBasicBlock::iterator MBBI = MBB.getLastNonDebugInstr();
  const SparcInstrInfo &TII =
      *static_cast<const SparcInstrInfo *>(MF.getSubtarget().getInstrInfo());
  DebugLoc dl = MBBI->getDebugLoc();
  assert(MBBI->getOpcode() == SP::RETL &&
         "Can only put epilog before 'retl' instruction!");
  if (!FuncInfo->isLeafProc()) {
    BuildMI(MBB, MBBI, dl, TII.get(SP::RESTORErr), SP::G0).addReg(SP::G0)
      .addReg(SP::G0);
    return;
  }
  MachineFrameInfo &MFI = MF.getFrameInfo();

  int NumBytes = (int) MFI.getStackSize();
  if (NumBytes == 0)
    return;

  emitSPAdjustment(MF, MBB, MBBI, NumBytes, SP::ADDrr, SP::ADDri);
}

bool SparcFrameLowering::hasReservedCallFrame(const MachineFunction &MF) const {
  // Reserve call frame if there are no variable sized objects on the stack.
  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 SparcFrameLowering::hasFP(const MachineFunction &MF) const {
  const TargetRegisterInfo *RegInfo = MF.getSubtarget().getRegisterInfo();

  const MachineFrameInfo &MFI = MF.getFrameInfo();
  return MF.getTarget().Options.DisableFramePointerElim(MF) ||
      RegInfo->needsStackRealignment(MF) ||
      MFI.hasVarSizedObjects() ||
      MFI.isFrameAddressTaken();
}


int SparcFrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI,
                                               unsigned &FrameReg) const {
  const SparcSubtarget &Subtarget = MF.getSubtarget<SparcSubtarget>();
  const MachineFrameInfo &MFI = MF.getFrameInfo();
  const SparcRegisterInfo *RegInfo = Subtarget.getRegisterInfo();
  const SparcMachineFunctionInfo *FuncInfo = MF.getInfo<SparcMachineFunctionInfo>();
  bool isFixed = MFI.isFixedObjectIndex(FI);

  // Addressable stack objects are accessed using neg. offsets from
  // %fp, or positive offsets from %sp.
  bool UseFP;

  // Sparc uses FP-based references in general, even when "hasFP" is
  // false. That function is rather a misnomer, because %fp is
  // actually always available, unless isLeafProc.
  if (FuncInfo->isLeafProc()) {
    // If there's a leaf proc, all offsets need to be %sp-based,
    // because we haven't caused %fp to actually point to our frame.
    UseFP = false;
  } else if (isFixed) {
    // Otherwise, argument access should always use %fp.
    UseFP = true;
  } else if (RegInfo->needsStackRealignment(MF)) {
    // If there is dynamic stack realignment, all local object
    // references need to be via %sp, to take account of the
    // re-alignment.
    UseFP = false;
  } else {
    // Finally, default to using %fp.
    UseFP = true;
  }

  int64_t FrameOffset = MF.getFrameInfo().getObjectOffset(FI) +
      Subtarget.getStackPointerBias();

  if (UseFP) {
    FrameReg = RegInfo->getFrameRegister(MF);
    return FrameOffset;
  } else {
    FrameReg = SP::O6; // %sp
    return FrameOffset + MF.getFrameInfo().getStackSize();
  }
}

static bool LLVM_ATTRIBUTE_UNUSED verifyLeafProcRegUse(MachineRegisterInfo *MRI)
{

  for (unsigned reg = SP::I0; reg <= SP::I7; ++reg)
    if (MRI->isPhysRegUsed(reg))
      return false;

  for (unsigned reg = SP::L0; reg <= SP::L7; ++reg)
    if (MRI->isPhysRegUsed(reg))
      return false;

  return true;
}

bool SparcFrameLowering::isLeafProc(MachineFunction &MF) const
{

  MachineRegisterInfo &MRI = MF.getRegInfo();
  MachineFrameInfo    &MFI = MF.getFrameInfo();

  return !(MFI.hasCalls()                  // has calls
           || MRI.isPhysRegUsed(SP::L0)    // Too many registers needed
           || MRI.isPhysRegUsed(SP::O6)    // %sp is used
           || hasFP(MF));                  // need %fp
}

void SparcFrameLowering::remapRegsForLeafProc(MachineFunction &MF) const {
  MachineRegisterInfo &MRI = MF.getRegInfo();
  // Remap %i[0-7] to %o[0-7].
  for (unsigned reg = SP::I0; reg <= SP::I7; ++reg) {
    if (!MRI.isPhysRegUsed(reg))
      continue;

    unsigned mapped_reg = reg - SP::I0 + SP::O0;

    // Replace I register with O register.
    MRI.replaceRegWith(reg, mapped_reg);

    // Also replace register pair super-registers.
    if ((reg - SP::I0) % 2 == 0) {
      unsigned preg = (reg - SP::I0) / 2 + SP::I0_I1;
      unsigned mapped_preg = preg - SP::I0_I1 + SP::O0_O1;
      MRI.replaceRegWith(preg, mapped_preg);
    }
  }

  // Rewrite MBB's Live-ins.
  for (MachineFunction::iterator MBB = MF.begin(), E = MF.end();
       MBB != E; ++MBB) {
    for (unsigned reg = SP::I0_I1; reg <= SP::I6_I7; ++reg) {
      if (!MBB->isLiveIn(reg))
        continue;
      MBB->removeLiveIn(reg);
      MBB->addLiveIn(reg - SP::I0_I1 + SP::O0_O1);
    }
    for (unsigned reg = SP::I0; reg <= SP::I7; ++reg) {
      if (!MBB->isLiveIn(reg))
        continue;
      MBB->removeLiveIn(reg);
      MBB->addLiveIn(reg - SP::I0 + SP::O0);
    }
  }

  assert(verifyLeafProcRegUse(&MRI));
#ifdef EXPENSIVE_CHECKS
  MF.verify(0, "After LeafProc Remapping");
#endif
}

void SparcFrameLowering::determineCalleeSaves(MachineFunction &MF,
                                              BitVector &SavedRegs,
                                              RegScavenger *RS) const {
  TargetFrameLowering::determineCalleeSaves(MF, SavedRegs, RS);
  if (!DisableLeafProc && isLeafProc(MF)) {
    SparcMachineFunctionInfo *MFI = MF.getInfo<SparcMachineFunctionInfo>();
    MFI->setLeafProc(true);

    remapRegsForLeafProc(MF);
  }

}