diff options
Diffstat (limited to 'llvm/lib/Target')
-rw-r--r-- | llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp | 34 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMFrameLowering.cpp | 98 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp | 23 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMISelLowering.cpp | 3 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/Thumb1FrameLowering.cpp | 105 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ThumbRegisterInfo.cpp | 68 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ThumbRegisterInfo.h | 6 |
7 files changed, 217 insertions, 120 deletions
diff --git a/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp index 1662e4549b7..dc99b37742d 100644 --- a/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp +++ b/llvm/lib/Target/ARM/ARMBaseRegisterInfo.cpp @@ -370,29 +370,35 @@ bool ARMBaseRegisterInfo::hasBasePointer(const MachineFunction &MF) const { const ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>(); const ARMFrameLowering *TFI = getFrameLowering(MF); - // When outgoing call frames are so large that we adjust the stack pointer - // around the call, we can no longer use the stack pointer to reach the - // emergency spill slot. + // If we have stack realignment and VLAs, we have no pointer to use to + // access the stack. If we have stack realignment, and a large call frame, + // we have no place to allocate the emergency spill slot. if (needsStackRealignment(MF) && !TFI->hasReservedCallFrame(MF)) return true; // Thumb has trouble with negative offsets from the FP. Thumb2 has a limited // negative range for ldr/str (255), and thumb1 is positive offsets only. + // // It's going to be better to use the SP or Base Pointer instead. When there // are variable sized objects, we can't reference off of the SP, so we // reserve a Base Pointer. - if (AFI->isThumbFunction() && 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, the scavenger will still enable access to work, it just - // won't be optimal. - if (AFI->isThumb2Function() && MFI.getLocalFrameSize() < 128) - return false; + // + // For Thumb2, estimate whether a negative offset from the frame pointer + // will be sufficient to reach the whole stack frame. 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, the scavenger will still enable access to work, it just + // won't be optimal. (We should always be able to reach the emergency + // spill slot from the frame pointer.) + if (AFI->isThumb2Function() && MFI.hasVarSizedObjects() && + MFI.getLocalFrameSize() >= 128) + return true; + // For Thumb1, if sp moves, nothing is in range, so force a base pointer. + // This is necessary for correctness in cases where we need an emergency + // spill slot. (In Thumb1, we can't use a negative offset from the frame + // pointer.) + if (AFI->isThumb1OnlyFunction() && !TFI->hasReservedCallFrame(MF)) return true; - } - return false; } diff --git a/llvm/lib/Target/ARM/ARMFrameLowering.cpp b/llvm/lib/Target/ARM/ARMFrameLowering.cpp index 0e5740f55ea..bedb779bcba 100644 --- a/llvm/lib/Target/ARM/ARMFrameLowering.cpp +++ b/llvm/lib/Target/ARM/ARMFrameLowering.cpp @@ -344,6 +344,10 @@ static void emitAligningInstructions(MachineFunction &MF, ARMFunctionInfo *AFI, /// as assignCalleeSavedSpillSlots() hasn't run at this point. Instead we use /// this to produce a conservative estimate that we check in an assert() later. static int getMaxFPOffset(const Function &F, const ARMFunctionInfo &AFI) { + // For Thumb1, push.w isn't available, so the first push will always push + // r7 and lr onto the stack first. + if (AFI.isThumb1OnlyFunction()) + return -AFI.getArgRegsSaveSize() - (2 * 4); // This is a conservative estimation: Assume the frame pointer being r7 and // pc("r15") up to r8 getting spilled before (= 8 registers). return -AFI.getArgRegsSaveSize() - (8 * 4); @@ -954,8 +958,12 @@ ARMFrameLowering::ResolveFrameIndexReference(const MachineFunction &MF, } } // Use the base pointer if we have one. - if (RegInfo->hasBasePointer(MF)) + // FIXME: Maybe prefer sp on Thumb1 if it's legal and the offset is cheaper? + // That can happen if we forced a base pointer for a large call frame. + if (RegInfo->hasBasePointer(MF)) { FrameReg = RegInfo->getBaseRegister(); + Offset -= SPAdj; + } return Offset; } @@ -1775,13 +1783,59 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, } EstimatedStackSize += 16; // For possible paddings. - unsigned EstimatedRSStackSizeLimit = estimateRSStackSizeLimit(MF, this); + unsigned EstimatedRSStackSizeLimit, EstimatedRSFixedSizeLimit; + if (AFI->isThumb1OnlyFunction()) { + // For Thumb1, don't bother to iterate over the function. The only + // instruction that requires an emergency spill slot is a store to a + // frame index. + // + // tSTRspi, which is used for sp-relative accesses, has an 8-bit unsigned + // immediate. tSTRi, which is used for bp- and fp-relative accesses, has + // a 5-bit unsigned immediate. + // + // We could try to check if the function actually contains a tSTRspi + // that might need the spill slot, but it's not really important. + // Functions with VLAs or extremely large call frames are rare, and + // if a function is allocating more than 1KB of stack, an extra 4-byte + // slot probably isn't relevant. + if (RegInfo->hasBasePointer(MF)) + EstimatedRSStackSizeLimit = (1U << 5) * 4; + else + EstimatedRSStackSizeLimit = (1U << 8) * 4; + EstimatedRSFixedSizeLimit = (1U << 5) * 4; + } else { + EstimatedRSStackSizeLimit = estimateRSStackSizeLimit(MF, this); + EstimatedRSFixedSizeLimit = EstimatedRSStackSizeLimit; + } + // Final estimate of whether sp or bp-relative accesses might require + // scavenging. + bool HasLargeStack = EstimatedStackSize > EstimatedRSStackSizeLimit; + + // If the stack pointer moves and we don't have a base pointer, the + // estimate logic doesn't work. The actual offsets might be larger when + // we're constructing a call frame, or we might need to use negative + // offsets from fp. + bool HasMovingSP = MFI.hasVarSizedObjects() || + (MFI.adjustsStack() && !canSimplifyCallFramePseudos(MF)); + bool HasBPOrFixedSP = RegInfo->hasBasePointer(MF) || !HasMovingSP; + + // If we have a frame pointer, we assume arguments will be accessed + // relative to the frame pointer. Check whether fp-relative accesses to + // arguments require scavenging. + // + // We could do slightly better on Thumb1; in some cases, an sp-relative + // offset would be legal even though an fp-relative offset is not. int MaxFPOffset = getMaxFPOffset(MF.getFunction(), *AFI); - bool BigFrameOffsets = EstimatedStackSize >= EstimatedRSStackSizeLimit || - MFI.hasVarSizedObjects() || - (MFI.adjustsStack() && !canSimplifyCallFramePseudos(MF)) || - // For large argument stacks fp relative addressed may overflow. - (HasFP && (MaxFixedOffset - MaxFPOffset) >= (int)EstimatedRSStackSizeLimit); + bool HasLargeArgumentList = + HasFP && (MaxFixedOffset - MaxFPOffset) > (int)EstimatedRSFixedSizeLimit; + + bool BigFrameOffsets = HasLargeStack || !HasBPOrFixedSP || + HasLargeArgumentList; + LLVM_DEBUG(dbgs() << "EstimatedLimit: " << EstimatedRSStackSizeLimit + << "; EstimatedStack" << EstimatedStackSize + << "; EstimatedFPStack" << MaxFixedOffset - MaxFPOffset + << "; BigFrameOffsets: " << BigFrameOffsets + << "\n"); if (BigFrameOffsets || !CanEliminateFrame || RegInfo->cannotEliminateFrame(MF)) { AFI->setHasStackFrame(true); @@ -1806,8 +1860,17 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, CS1Spilled = true; } - // This is true when we inserted a spill for an unused register that can now - // be used for register scavenging. + // This is true when we inserted a spill for a callee-save GPR which is + // not otherwise used by the function. This guaranteees it is possible + // to scavenge a register to hold the address of a stack slot. On Thumb1, + // the register must be a valid operand to tSTRi, i.e. r4-r7. For other + // subtargets, this is any GPR, i.e. r4-r11 or lr. + // + // If we don't insert a spill, we instead allocate an emergency spill + // slot, which can be used by scavenging to spill an arbitrary register. + // + // We currently don't try to figure out whether any specific instruction + // requires scavening an additional register. bool ExtraCSSpill = false; if (AFI->isThumb1OnlyFunction()) { @@ -1916,7 +1979,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, NumGPRSpills++; CS1Spilled = true; assert(!MRI.isReserved(Reg) && "Should not be reserved"); - if (!MRI.isPhysRegUsed(Reg)) + if (Reg != ARM::LR && !MRI.isPhysRegUsed(Reg)) ExtraCSSpill = true; UnspilledCS1GPRs.erase(llvm::find(UnspilledCS1GPRs, Reg)); if (Reg == ARM::LR) @@ -1941,7 +2004,8 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, UnspilledCS1GPRs.erase(LRPos); ForceLRSpill = false; - if (!MRI.isReserved(ARM::LR) && !MRI.isPhysRegUsed(ARM::LR)) + if (!MRI.isReserved(ARM::LR) && !MRI.isPhysRegUsed(ARM::LR) && + !AFI->isThumb1OnlyFunction()) ExtraCSSpill = true; } @@ -1963,7 +2027,8 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, SavedRegs.set(Reg); LLVM_DEBUG(dbgs() << "Spilling " << printReg(Reg, TRI) << " to make up alignment\n"); - if (!MRI.isReserved(Reg) && !MRI.isPhysRegUsed(Reg)) + if (!MRI.isReserved(Reg) && !MRI.isPhysRegUsed(Reg) && + !(Reg == ARM::LR && AFI->isThumb1OnlyFunction())) ExtraCSSpill = true; break; } @@ -1992,8 +2057,7 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, unsigned Reg = UnspilledCS1GPRs.back(); UnspilledCS1GPRs.pop_back(); if (!MRI.isReserved(Reg) && - (!AFI->isThumb1OnlyFunction() || isARMLowRegister(Reg) || - Reg == ARM::LR)) { + (!AFI->isThumb1OnlyFunction() || isARMLowRegister(Reg))) { Extras.push_back(Reg); NumExtras--; } @@ -2016,10 +2080,10 @@ void ARMFrameLowering::determineCalleeSaves(MachineFunction &MF, ExtraCSSpill = true; } } - if (!ExtraCSSpill && !AFI->isThumb1OnlyFunction()) { - // note: Thumb1 functions spill to R12, not the stack. Reserve a slot - // closest to SP or frame pointer. + if (!ExtraCSSpill) { + // Reserve a slot closest to SP or frame pointer. assert(RS && "Register scavenging not provided"); + LLVM_DEBUG(dbgs() << "Reserving emergency spill slot\n"); const TargetRegisterClass &RC = ARM::GPRRegClass; unsigned Size = TRI->getSpillSize(RC); unsigned Align = TRI->getSpillAlignment(RC); diff --git a/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp b/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp index 127d86c9138..c9a88823f5e 100644 --- a/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp +++ b/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp @@ -1150,15 +1150,22 @@ bool ARMDAGToDAGISel::SelectThumbAddrModeSP(SDValue N, if (isScaledConstantInRange(N.getOperand(1), /*Scale=*/4, 0, 256, RHSC)) { Base = N.getOperand(0); int FI = cast<FrameIndexSDNode>(Base)->getIndex(); - // For LHS+RHS to result in an offset that's a multiple of 4 the object - // indexed by the LHS must be 4-byte aligned. + // Make sure the offset is inside the object, or we might fail to + // allocate an emergency spill slot. (An out-of-range access is UB, but + // it could show up anyway.) MachineFrameInfo &MFI = MF->getFrameInfo(); - if (MFI.getObjectAlignment(FI) < 4) - MFI.setObjectAlignment(FI, 4); - Base = CurDAG->getTargetFrameIndex( - FI, TLI->getPointerTy(CurDAG->getDataLayout())); - OffImm = CurDAG->getTargetConstant(RHSC, SDLoc(N), MVT::i32); - return true; + if (RHSC * 4 < MFI.getObjectSize(FI)) { + // For LHS+RHS to result in an offset that's a multiple of 4 the object + // indexed by the LHS must be 4-byte aligned. + if (!MFI.isFixedObjectIndex(FI) && MFI.getObjectAlignment(FI) < 4) + MFI.setObjectAlignment(FI, 4); + if (MFI.getObjectAlignment(FI) >= 4) { + Base = CurDAG->getTargetFrameIndex( + FI, TLI->getPointerTy(CurDAG->getDataLayout())); + OffImm = CurDAG->getTargetConstant(RHSC, SDLoc(N), MVT::i32); + return true; + } + } } } diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp index edf5090cf54..7ff0846e1a0 100644 --- a/llvm/lib/Target/ARM/ARMISelLowering.cpp +++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp @@ -3652,7 +3652,8 @@ void ARMTargetLowering::VarArgStyleRegisters(CCState &CCInfo, SelectionDAG &DAG, // argument passed via stack. int FrameIndex = StoreByValRegs(CCInfo, DAG, dl, Chain, nullptr, CCInfo.getInRegsParamsCount(), - CCInfo.getNextStackOffset(), 4); + CCInfo.getNextStackOffset(), + std::max(4U, TotalArgRegsSaveSize)); AFI->setVarArgsFrameIndex(FrameIndex); } diff --git a/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp b/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp index 077f6eeff13..1b32df2104a 100644 --- a/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp +++ b/llvm/lib/Target/ARM/Thumb1FrameLowering.cpp @@ -63,15 +63,52 @@ bool Thumb1FrameLowering::hasReservedCallFrame(const MachineFunction &MF) const{ return !MFI.hasVarSizedObjects(); } -static void emitSPUpdate(MachineBasicBlock &MBB, - MachineBasicBlock::iterator &MBBI, - const TargetInstrInfo &TII, const DebugLoc &dl, - const ThumbRegisterInfo &MRI, int NumBytes, - unsigned MIFlags = MachineInstr::NoFlags) { +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)); + 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 { @@ -95,10 +132,10 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB, // 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); + emitCallSPUpdate(MBB, I, TII, dl, *RegInfo, -Amount); } else { assert(Opc == ARM::ADJCALLSTACKUP || Opc == ARM::tADJCALLSTACKUP); - emitSPUpdate(MBB, I, TII, dl, *RegInfo, Amount); + emitCallSPUpdate(MBB, I, TII, dl, *RegInfo, Amount); } } } @@ -141,8 +178,8 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF, int FramePtrSpillFI = 0; if (ArgRegsSaveSize) { - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize, - MachineInstr::FrameSetup); + emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -ArgRegsSaveSize, + ARM::NoRegister, MachineInstr::FrameSetup); CFAOffset -= ArgRegsSaveSize; unsigned CFIIndex = MF.addFrameInst( MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset)); @@ -153,8 +190,9 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF, if (!AFI->hasStackFrame()) { if (NumBytes - ArgRegsSaveSize != 0) { - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -(NumBytes - ArgRegsSaveSize), - MachineInstr::FrameSetup); + emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, + -(NumBytes - ArgRegsSaveSize), + ARM::NoRegister, MachineInstr::FrameSetup); CFAOffset -= NumBytes - ArgRegsSaveSize; unsigned CFIIndex = MF.addFrameInst( MCCFIInstruction::createDefCfaOffset(nullptr, CFAOffset)); @@ -331,8 +369,20 @@ void Thumb1FrameLowering::emitPrologue(MachineFunction &MF, if (NumBytes) { // Insert it after all the callee-save spills. - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, -NumBytes, - MachineInstr::FrameSetup); + // + // 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) { + unsigned 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( @@ -437,7 +487,9 @@ void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF, if (!AFI->hasStackFrame()) { if (NumBytes - ArgRegsSaveSize != 0) - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes - ArgRegsSaveSize); + 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()) { @@ -472,13 +524,27 @@ void Thumb1FrameLowering::emitEpilogue(MachineFunction &MF, .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()) { + unsigned 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)) - emitSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes); + emitPrologueEpilogueSPUpdate(MBB, PMBBI, TII, dl, *RegInfo, NumBytes, + ScratchRegister, MachineInstr::NoFlags); } else if (!tryFoldSPUpdateIntoPushPop(STI, MF, &*MBBI, NumBytes)) - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes); + emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, NumBytes, + ScratchRegister, MachineInstr::NoFlags); } } @@ -665,7 +731,9 @@ bool Thumb1FrameLowering::emitPopSpecialFixUp(MachineBasicBlock &MBB, // Advance past the pop instruction. MBBI++; // Increment the SP. - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize + 4); + emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, + ArgRegsSaveSize + 4, ARM::NoRegister, + MachineInstr::NoFlags); return true; } @@ -706,7 +774,8 @@ bool Thumb1FrameLowering::emitPopSpecialFixUp(MachineBasicBlock &MBB, .add(predOps(ARMCC::AL)) .addReg(PopReg, RegState::Define); - emitSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize); + emitPrologueEpilogueSPUpdate(MBB, MBBI, TII, dl, *RegInfo, ArgRegsSaveSize, + ARM::NoRegister, MachineInstr::NoFlags); BuildMI(MBB, MBBI, dl, TII.get(ARM::tMOVr)) .addReg(ARM::LR, RegState::Define) diff --git a/llvm/lib/Target/ARM/ThumbRegisterInfo.cpp b/llvm/lib/Target/ARM/ThumbRegisterInfo.cpp index e485c79d3f3..a96417ffce4 100644 --- a/llvm/lib/Target/ARM/ThumbRegisterInfo.cpp +++ b/llvm/lib/Target/ARM/ThumbRegisterInfo.cpp @@ -446,63 +446,6 @@ void ThumbRegisterInfo::resolveFrameIndex(MachineInstr &MI, unsigned BaseReg, (void)Done; } -/// saveScavengerRegister - Spill the register so it can be used by the -/// register scavenger. Return true. -bool ThumbRegisterInfo::saveScavengerRegister( - MachineBasicBlock &MBB, MachineBasicBlock::iterator I, - MachineBasicBlock::iterator &UseMI, const TargetRegisterClass *RC, - unsigned Reg) const { - - const ARMSubtarget &STI = MBB.getParent()->getSubtarget<ARMSubtarget>(); - if (!STI.isThumb1Only()) - return ARMBaseRegisterInfo::saveScavengerRegister(MBB, I, UseMI, RC, Reg); - - // Thumb1 can't use the emergency spill slot on the stack because - // ldr/str immediate offsets must be positive, and if we're referencing - // off the frame pointer (if, for example, there are alloca() calls in - // the function, the offset will be negative. Use R12 instead since that's - // a call clobbered register that we know won't be used in Thumb1 mode. - const TargetInstrInfo &TII = *STI.getInstrInfo(); - DebugLoc DL; - BuildMI(MBB, I, DL, TII.get(ARM::tMOVr)) - .addReg(ARM::R12, RegState::Define) - .addReg(Reg, RegState::Kill) - .add(predOps(ARMCC::AL)); - - // The UseMI is where we would like to restore the register. If there's - // interference with R12 before then, however, we'll need to restore it - // before that instead and adjust the UseMI. - bool done = false; - for (MachineBasicBlock::iterator II = I; !done && II != UseMI ; ++II) { - if (II->isDebugInstr()) - continue; - // If this instruction affects R12, adjust our restore point. - for (unsigned i = 0, e = II->getNumOperands(); i != e; ++i) { - const MachineOperand &MO = II->getOperand(i); - if (MO.isRegMask() && MO.clobbersPhysReg(ARM::R12)) { - UseMI = II; - done = true; - break; - } - if (!MO.isReg() || MO.isUndef() || !MO.getReg() || - TargetRegisterInfo::isVirtualRegister(MO.getReg())) - continue; - if (MO.getReg() == ARM::R12) { - UseMI = II; - done = true; - break; - } - } - } - // Restore the register from R12 - BuildMI(MBB, UseMI, DL, TII.get(ARM::tMOVr)) - .addReg(Reg, RegState::Define) - .addReg(ARM::R12, RegState::Kill) - .add(predOps(ARMCC::AL)); - - return true; -} - void ThumbRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II, int SPAdj, unsigned FIOperandNum, RegScavenger *RS) const { @@ -618,3 +561,14 @@ void ThumbRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II, if (MI.isPredicable()) MIB.add(predOps(ARMCC::AL)); } + +bool +ThumbRegisterInfo::useFPForScavengingIndex(const MachineFunction &MF) const { + if (MF.getSubtarget<ARMSubtarget>().isThumb1Only()) { + // For Thumb1, the emergency spill slot must be some small positive + // offset from the base/stack pointer. + return false; + } + // For Thumb2, put the emergency spill slot next to FP. + return true; +} diff --git a/llvm/lib/Target/ARM/ThumbRegisterInfo.h b/llvm/lib/Target/ARM/ThumbRegisterInfo.h index 10017a7a0c6..08cf67284d4 100644 --- a/llvm/lib/Target/ARM/ThumbRegisterInfo.h +++ b/llvm/lib/Target/ARM/ThumbRegisterInfo.h @@ -51,14 +51,10 @@ public: const ARMBaseInstrInfo &TII) const; void resolveFrameIndex(MachineInstr &MI, unsigned BaseReg, int64_t Offset) const override; - bool saveScavengerRegister(MachineBasicBlock &MBB, - MachineBasicBlock::iterator I, - MachineBasicBlock::iterator &UseMI, - const TargetRegisterClass *RC, - unsigned Reg) const override; void eliminateFrameIndex(MachineBasicBlock::iterator II, int SPAdj, unsigned FIOperandNum, RegScavenger *RS = nullptr) const override; + bool useFPForScavengingIndex(const MachineFunction &MF) const override; }; } |