diff options
Diffstat (limited to 'contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp')
-rw-r--r-- | contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp | 228 |
1 files changed, 186 insertions, 42 deletions
diff --git a/contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp b/contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp index 7874240..c75998a 100644 --- a/contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp +++ b/contrib/llvm/lib/Target/Sparc/SparcFrameLowering.cpp @@ -26,7 +26,61 @@ using namespace llvm; +static cl::opt<bool> +DisableLeafProc("disable-sparc-leaf-proc", + cl::init(false), + cl::desc("Disable Sparc leaf procedure optimization."), + cl::Hidden); + + +void SparcFrameLowering::emitSPAdjustment(MachineFunction &MF, + MachineBasicBlock &MBB, + MachineBasicBlock::iterator MBBI, + int NumBytes, + unsigned ADDrr, + unsigned ADDri) const { + + DebugLoc dl = (MBBI != MBB.end()) ? MBBI->getDebugLoc() : DebugLoc(); + const SparcInstrInfo &TII = + *static_cast<const SparcInstrInfo*>(MF.getTarget().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) const { + SparcMachineFunctionInfo *FuncInfo = MF.getInfo<SparcMachineFunctionInfo>(); + MachineBasicBlock &MBB = MF.front(); MachineFrameInfo *MFI = MF.getFrameInfo(); const SparcInstrInfo &TII = @@ -37,43 +91,36 @@ void SparcFrameLowering::emitPrologue(MachineFunction &MF) const { // Get the number of bytes to allocate from the FrameInfo int NumBytes = (int) MFI->getStackSize(); - if (SubTarget.is64Bit()) { - // All 64-bit stack frames must be 16-byte aligned, and must reserve space - // for spilling the 16 window registers at %sp+BIAS..%sp+BIAS+128. - NumBytes += 128; - // Frames with calls must also reserve space for 6 outgoing arguments - // whether they are used or not. LowerCall_64 takes care of that. - assert(NumBytes % 16 == 0 && "Stack size not 16-byte aligned"); - } else { - // Emit the correct save instruction based on the number of bytes in - // the frame. Minimum stack frame size according to V8 ABI is: - // 16 words for register window spill - // 1 word for address of returned aggregate-value - // + 6 words for passing parameters on the stack - // ---------- - // 23 words * 4 bytes per word = 92 bytes - NumBytes += 92; - - // Round up to next doubleword boundary -- a double-word boundary - // is required by the ABI. - NumBytes = RoundUpToAlignment(NumBytes, 8); + unsigned SAVEri = SP::SAVEri; + unsigned SAVErr = SP::SAVErr; + if (FuncInfo->isLeafProc()) { + if (NumBytes == 0) + return; + SAVEri = SP::ADDri; + SAVErr = SP::ADDrr; } - NumBytes = -NumBytes; + NumBytes = - SubTarget.getAdjustedFrameSize(NumBytes); + emitSPAdjustment(MF, MBB, MBBI, NumBytes, SAVErr, SAVEri); - if (NumBytes >= -4096) { - BuildMI(MBB, MBBI, dl, TII.get(SP::SAVEri), SP::O6) - .addReg(SP::O6).addImm(NumBytes); - } else { - // Emit this the hard way. This clobbers G1 which we always know is - // available here. - unsigned OffHi = (unsigned)NumBytes >> 10U; - BuildMI(MBB, MBBI, dl, TII.get(SP::SETHIi), SP::G1).addImm(OffHi); - // Emit G1 = G1 + I6 - BuildMI(MBB, MBBI, dl, TII.get(SP::ORri), SP::G1) - .addReg(SP::G1).addImm(NumBytes & ((1 << 10)-1)); - BuildMI(MBB, MBBI, dl, TII.get(SP::SAVErr), SP::O6) - .addReg(SP::O6).addReg(SP::G1); - } + MachineModuleInfo &MMI = MF.getMMI(); + const MCRegisterInfo *MRI = MMI.getContext().getRegisterInfo(); + MCSymbol *FrameLabel = MMI.getContext().CreateTempSymbol(); + BuildMI(MBB, MBBI, dl, TII.get(SP::PROLOG_LABEL)).addSym(FrameLabel); + + unsigned regFP = MRI->getDwarfRegNum(SP::I6, true); + + // Emit ".cfi_def_cfa_register 30". + MMI.addFrameInst(MCCFIInstruction::createDefCfaRegister(FrameLabel, + regFP)); + // Emit ".cfi_window_save". + MMI.addFrameInst(MCCFIInstruction::createWindowSave(FrameLabel)); + + unsigned regInRA = MRI->getDwarfRegNum(SP::I7, true); + unsigned regOutRA = MRI->getDwarfRegNum(SP::O7, true); + // Emit ".cfi_register 15, 31". + MMI.addFrameInst(MCCFIInstruction::createRegister(FrameLabel, + regOutRA, + regInRA)); } void SparcFrameLowering:: @@ -81,15 +128,12 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB, MachineBasicBlock::iterator I) const { if (!hasReservedCallFrame(MF)) { MachineInstr &MI = *I; - DebugLoc DL = MI.getDebugLoc(); int Size = MI.getOperand(0).getImm(); if (MI.getOpcode() == SP::ADJCALLSTACKDOWN) Size = -Size; - const SparcInstrInfo &TII = - *static_cast<const SparcInstrInfo*>(MF.getTarget().getInstrInfo()); + if (Size) - BuildMI(MBB, I, DL, TII.get(SP::ADDri), SP::O6).addReg(SP::O6) - .addImm(Size); + emitSPAdjustment(MF, MBB, I, Size, SP::ADDrr, SP::ADDri); } MBB.erase(I); } @@ -97,12 +141,112 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB, 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.getTarget().getInstrInfo()); DebugLoc dl = MBBI->getDebugLoc(); assert(MBBI->getOpcode() == SP::RETL && "Can only put epilog before 'retl' instruction!"); - BuildMI(MBB, MBBI, dl, TII.get(SP::RESTORErr), SP::G0).addReg(SP::G0) - .addReg(SP::G0); + 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; + + NumBytes = SubTarget.getAdjustedFrameSize(NumBytes); + 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 MachineFrameInfo *MFI = MF.getFrameInfo(); + return MF.getTarget().Options.DisableFramePointerElim(MF) || + MFI->hasVarSizedObjects() || MFI->isFrameAddressTaken(); +} + + +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); + assert(!MRI.isPhysRegUsed(mapped_reg)); + + // Replace I register with O register. + MRI.replaceRegWith(reg, mapped_reg); + + // Mark the reg unused. + MRI.setPhysRegUnused(reg); + } + + // Rewrite MBB's Live-ins. + for (MachineFunction::iterator MBB = MF.begin(), E = MF.end(); + MBB != E; ++MBB) { + 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 XDEBUG + MF.verify(0, "After LeafProc Remapping"); +#endif +} + +void SparcFrameLowering::processFunctionBeforeCalleeSavedScan + (MachineFunction &MF, RegScavenger *RS) const { + + if (!DisableLeafProc && isLeafProc(MF)) { + SparcMachineFunctionInfo *MFI = MF.getInfo<SparcMachineFunctionInfo>(); + MFI->setLeafProc(true); + + remapRegsForLeafProc(MF); + } + } |