X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FCodeGen%2FPrologEpilogInserter.cpp;h=585c7edc0f0ad92c078aaeb69f8099cd9fd884be;hb=436444d569938cd75bd05f3abb65fe57bce0f067;hp=5a168dd244cbde7c4aad099947748ad6d3c9a02c;hpb=b6cfeb63f8192724362565567a4cb4aa642baa1d;p=oota-llvm.git diff --git a/lib/CodeGen/PrologEpilogInserter.cpp b/lib/CodeGen/PrologEpilogInserter.cpp index 5a168dd244c..585c7edc0f0 100644 --- a/lib/CodeGen/PrologEpilogInserter.cpp +++ b/lib/CodeGen/PrologEpilogInserter.cpp @@ -14,42 +14,103 @@ // This pass must be run after register allocation. After this pass is // executed, it is illegal to construct MO_FrameIndex operands. // -// This pass provides an optional shrink wrapping variant of prolog/epilog -// insertion, enabled via --shrink-wrap. See ShrinkWrapping.cpp. -// //===----------------------------------------------------------------------===// -#define DEBUG_TYPE "pei" -#include "PrologEpilogInserter.h" #include "llvm/ADT/IndexedMap.h" #include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/SetVector.h" #include "llvm/ADT/SmallSet.h" #include "llvm/ADT/Statistic.h" #include "llvm/CodeGen/MachineDominators.h" #include "llvm/CodeGen/MachineFrameInfo.h" #include "llvm/CodeGen/MachineInstr.h" #include "llvm/CodeGen/MachineLoopInfo.h" +#include "llvm/CodeGen/MachineModuleInfo.h" #include "llvm/CodeGen/MachineRegisterInfo.h" +#include "llvm/CodeGen/Passes.h" #include "llvm/CodeGen/RegisterScavenging.h" +#include "llvm/CodeGen/StackProtector.h" +#include "llvm/CodeGen/WinEHFuncInfo.h" +#include "llvm/IR/DiagnosticInfo.h" #include "llvm/IR/InlineAsm.h" +#include "llvm/IR/LLVMContext.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Compiler.h" #include "llvm/Support/Debug.h" +#include "llvm/Support/raw_ostream.h" #include "llvm/Target/TargetFrameLowering.h" #include "llvm/Target/TargetInstrInfo.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetRegisterInfo.h" +#include "llvm/Target/TargetSubtargetInfo.h" #include using namespace llvm; +#define DEBUG_TYPE "pei" + +namespace { +class PEI : public MachineFunctionPass { +public: + static char ID; + PEI() : MachineFunctionPass(ID) { + initializePEIPass(*PassRegistry::getPassRegistry()); + } + + void getAnalysisUsage(AnalysisUsage &AU) const override; + + /// runOnMachineFunction - Insert prolog/epilog code and replace abstract + /// frame indexes with appropriate references. + /// + bool runOnMachineFunction(MachineFunction &Fn) override; + +private: + RegScavenger *RS; + + // MinCSFrameIndex, MaxCSFrameIndex - Keeps the range of callee saved + // stack frame indexes. + unsigned MinCSFrameIndex, MaxCSFrameIndex; + + // Save and Restore blocks of the current function. Typically there is a + // single save block, unless Windows EH funclets are involved. + SmallVector SaveBlocks; + SmallVector RestoreBlocks; + + // Flag to control whether to use the register scavenger to resolve + // frame index materialization registers. Set according to + // TRI->requiresFrameIndexScavenging() for the current function. + bool FrameIndexVirtualScavenging; + + void calculateSets(MachineFunction &Fn); + void calculateCallsInformation(MachineFunction &Fn); + void assignCalleeSavedSpillSlots(MachineFunction &Fn, + const BitVector &SavedRegs); + void insertCSRSpillsAndRestores(MachineFunction &Fn); + void calculateFrameObjectOffsets(MachineFunction &Fn); + void replaceFrameIndices(MachineFunction &Fn); + void replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn, + int &SPAdj); + void scavengeFrameVirtualRegs(MachineFunction &Fn); + void insertPrologEpilogCode(MachineFunction &Fn); + + // Convenience for recognizing return blocks. + bool isReturnBlock(const MachineBasicBlock *MBB) const; +}; +} // namespace + char PEI::ID = 0; char &llvm::PrologEpilogCodeInserterID = PEI::ID; +static cl::opt +WarnStackSize("warn-stack-size", cl::Hidden, cl::init((unsigned)-1), + cl::desc("Warn for stack size bigger than the given" + " number")); + INITIALIZE_PASS_BEGIN(PEI, "prologepilog", "Prologue/Epilogue Insertion", false, false) INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo) INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree) +INITIALIZE_PASS_DEPENDENCY(StackProtector) INITIALIZE_PASS_DEPENDENCY(TargetPassConfig) INITIALIZE_PASS_END(PEI, "prologepilog", "Prologue/Epilogue Insertion & Frame Finalization", @@ -59,17 +120,64 @@ STATISTIC(NumScavengedRegs, "Number of frame index regs scavenged"); STATISTIC(NumBytesStackSpace, "Number of bytes used for stack in all functions"); +void PEI::getAnalysisUsage(AnalysisUsage &AU) const { + AU.setPreservesCFG(); + AU.addPreserved(); + AU.addPreserved(); + AU.addRequired(); + AU.addRequired(); + MachineFunctionPass::getAnalysisUsage(AU); +} + +bool PEI::isReturnBlock(const MachineBasicBlock* MBB) const { + return (MBB && !MBB->empty() && MBB->back().isReturn()); +} + +/// Compute the set of return blocks +void PEI::calculateSets(MachineFunction &Fn) { + const MachineFrameInfo *MFI = Fn.getFrameInfo(); + + // Even when we do not change any CSR, we still want to insert the + // prologue and epilogue of the function. + // So set the save points for those. + + // Use the points found by shrink-wrapping, if any. + if (MFI->getSavePoint()) { + SaveBlocks.push_back(MFI->getSavePoint()); + assert(MFI->getRestorePoint() && "Both restore and save must be set"); + MachineBasicBlock *RestoreBlock = MFI->getRestorePoint(); + // If RestoreBlock does not have any successor and is not a return block + // then the end point is unreachable and we do not need to insert any + // epilogue. + if (!RestoreBlock->succ_empty() || isReturnBlock(RestoreBlock)) + RestoreBlocks.push_back(RestoreBlock); + return; + } + + // Save refs to entry and return blocks. + SaveBlocks.push_back(Fn.begin()); + for (MachineBasicBlock &MBB : Fn) { + if (MBB.isEHFuncletEntry()) + SaveBlocks.push_back(&MBB); + if (isReturnBlock(&MBB)) + RestoreBlocks.push_back(&MBB); + } +} + +/// StackObjSet - A set of stack object indexes +typedef SmallSetVector StackObjSet; + /// runOnMachineFunction - Insert prolog/epilog code and replace abstract /// frame indexes with appropriate references. /// bool PEI::runOnMachineFunction(MachineFunction &Fn) { const Function* F = Fn.getFunction(); - const TargetRegisterInfo *TRI = Fn.getTarget().getRegisterInfo(); - const TargetFrameLowering *TFI = Fn.getTarget().getFrameLowering(); + const TargetRegisterInfo *TRI = Fn.getSubtarget().getRegisterInfo(); + const TargetFrameLowering *TFI = Fn.getSubtarget().getFrameLowering(); assert(!Fn.getRegInfo().getNumVirtRegs() && "Regalloc must assign all vregs"); - RS = TRI->requiresRegisterScavenging(Fn) ? new RegScavenger() : NULL; + RS = TRI->requiresRegisterScavenging(Fn) ? new RegScavenger() : nullptr; FrameIndexVirtualScavenging = TRI->requiresFrameIndexScavenging(Fn); // Calculate the MaxCallFrameSize and AdjustsStack variables for the @@ -77,25 +185,19 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) { // instructions. calculateCallsInformation(Fn); - // Allow the target machine to make some adjustments to the function - // e.g. UsedPhysRegs before calculateCalleeSavedRegisters. - TFI->processFunctionBeforeCalleeSavedScan(Fn, RS); + // Determine which of the registers in the callee save list should be saved. + BitVector SavedRegs; + TFI->determineCalleeSaves(Fn, SavedRegs, RS); - // Scan the function for modified callee saved registers and insert spill code - // for any callee saved registers that are modified. - calculateCalleeSavedRegisters(Fn); + // Insert spill code for any callee saved registers that are modified. + assignCalleeSavedSpillSlots(Fn, SavedRegs); // Determine placement of CSR spill/restore code: - // - With shrink wrapping, place spills and restores to tightly - // enclose regions in the Machine CFG of the function where - // they are used. - // - Without shink wrapping (default), place all spills in the - // entry block, all restores in return blocks. - placeCSRSpillsAndRestores(Fn); + // place all spills in the entry block, all restores in return blocks. + calculateSets(Fn); // Add the code to save and restore the callee saved registers - if (!F->getAttributes().hasAttribute(AttributeSet::FunctionIndex, - Attribute::Naked)) + if (!F->hasFnAttribute(Attribute::Naked)) insertCSRSpillsAndRestores(Fn); // Allow the target machine to make final modifications to the function @@ -110,8 +212,7 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) { // called functions. Because of this, calculateCalleeSavedRegisters() // must be called before this function in order to set the AdjustsStack // and MaxCallFrameSize variables. - if (!F->getAttributes().hasAttribute(AttributeSet::FunctionIndex, - Attribute::Naked)) + if (!F->hasFnAttribute(Attribute::Naked)) insertPrologEpilogCode(Fn); // Replace all MO_FrameIndex operands with physical register references @@ -120,7 +221,7 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) { replaceFrameIndices(Fn); // If register scavenging is needed, as we've enabled doing it as a - // post-pass, scavenge the virtual registers that frame index elimiation + // post-pass, scavenge the virtual registers that frame index elimination // inserted. if (TRI->requiresRegisterScavenging(Fn) && FrameIndexVirtualScavenging) scavengeFrameVirtualRegs(Fn); @@ -128,8 +229,17 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) { // Clear any vregs created by virtual scavenging. Fn.getRegInfo().clearVirtRegs(); + // Warn on stack size when we exceeds the given limit. + MachineFrameInfo *MFI = Fn.getFrameInfo(); + uint64_t StackSize = MFI->getStackSize(); + if (WarnStackSize.getNumOccurrences() > 0 && WarnStackSize < StackSize) { + DiagnosticInfoStackSize DiagStackSize(*F, StackSize); + F->getContext().diagnose(DiagStackSize); + } + delete RS; - clearAllSets(); + SaveBlocks.clear(); + RestoreBlocks.clear(); return true; } @@ -137,20 +247,20 @@ bool PEI::runOnMachineFunction(MachineFunction &Fn) { /// variables for the function's frame information and eliminate call frame /// pseudo instructions. void PEI::calculateCallsInformation(MachineFunction &Fn) { - const TargetInstrInfo &TII = *Fn.getTarget().getInstrInfo(); - const TargetFrameLowering *TFI = Fn.getTarget().getFrameLowering(); + const TargetInstrInfo &TII = *Fn.getSubtarget().getInstrInfo(); + const TargetFrameLowering *TFI = Fn.getSubtarget().getFrameLowering(); MachineFrameInfo *MFI = Fn.getFrameInfo(); unsigned MaxCallFrameSize = 0; bool AdjustsStack = MFI->adjustsStack(); // Get the function call frame set-up and tear-down instruction opcode - int FrameSetupOpcode = TII.getCallFrameSetupOpcode(); - int FrameDestroyOpcode = TII.getCallFrameDestroyOpcode(); + unsigned FrameSetupOpcode = TII.getCallFrameSetupOpcode(); + unsigned FrameDestroyOpcode = TII.getCallFrameDestroyOpcode(); // Early exit for targets which have no call frame setup/destroy pseudo // instructions. - if (FrameSetupOpcode == -1 && FrameDestroyOpcode == -1) + if (FrameSetupOpcode == ~0u && FrameDestroyOpcode == ~0u) return; std::vector FrameSDOps; @@ -187,91 +297,139 @@ void PEI::calculateCallsInformation(MachineFunction &Fn) { } } - -/// calculateCalleeSavedRegisters - Scan the function for modified callee saved -/// registers. -void PEI::calculateCalleeSavedRegisters(MachineFunction &F) { - const TargetRegisterInfo *RegInfo = F.getTarget().getRegisterInfo(); - const TargetFrameLowering *TFI = F.getTarget().getFrameLowering(); - MachineFrameInfo *MFI = F.getFrameInfo(); - - // Get the callee saved register list... - const uint16_t *CSRegs = RegInfo->getCalleeSavedRegs(&F); - +void PEI::assignCalleeSavedSpillSlots(MachineFunction &F, + const BitVector &SavedRegs) { // These are used to keep track the callee-save area. Initialize them. MinCSFrameIndex = INT_MAX; MaxCSFrameIndex = 0; - // Early exit for targets which have no callee saved registers. - if (CSRegs == 0 || CSRegs[0] == 0) + if (SavedRegs.empty()) return; - // In Naked functions we aren't going to save any registers. - if (F.getFunction()->getAttributes().hasAttribute(AttributeSet::FunctionIndex, - Attribute::Naked)) - return; + const TargetRegisterInfo *RegInfo = F.getSubtarget().getRegisterInfo(); + const MCPhysReg *CSRegs = RegInfo->getCalleeSavedRegs(&F); std::vector CSI; for (unsigned i = 0; CSRegs[i]; ++i) { unsigned Reg = CSRegs[i]; - if (F.getRegInfo().isPhysRegUsed(Reg)) { - // If the reg is modified, save it! + if (SavedRegs.test(Reg)) CSI.push_back(CalleeSavedInfo(Reg)); - } } - if (CSI.empty()) - return; // Early exit if no callee saved registers are modified! - - unsigned NumFixedSpillSlots; - const TargetFrameLowering::SpillSlot *FixedSpillSlots = - TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots); + const TargetFrameLowering *TFI = F.getSubtarget().getFrameLowering(); + MachineFrameInfo *MFI = F.getFrameInfo(); + if (!TFI->assignCalleeSavedSpillSlots(F, RegInfo, CSI)) { + // If target doesn't implement this, use generic code. + + if (CSI.empty()) + return; // Early exit if no callee saved registers are modified! + + unsigned NumFixedSpillSlots; + const TargetFrameLowering::SpillSlot *FixedSpillSlots = + TFI->getCalleeSavedSpillSlots(NumFixedSpillSlots); + + // Now that we know which registers need to be saved and restored, allocate + // stack slots for them. + for (std::vector::iterator I = CSI.begin(), E = CSI.end(); + I != E; ++I) { + unsigned Reg = I->getReg(); + const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg); + + int FrameIdx; + if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) { + I->setFrameIdx(FrameIdx); + continue; + } - // Now that we know which registers need to be saved and restored, allocate - // stack slots for them. - for (std::vector::iterator - I = CSI.begin(), E = CSI.end(); I != E; ++I) { - unsigned Reg = I->getReg(); - const TargetRegisterClass *RC = RegInfo->getMinimalPhysRegClass(Reg); + // Check to see if this physreg must be spilled to a particular stack slot + // on this target. + const TargetFrameLowering::SpillSlot *FixedSlot = FixedSpillSlots; + while (FixedSlot != FixedSpillSlots + NumFixedSpillSlots && + FixedSlot->Reg != Reg) + ++FixedSlot; + + if (FixedSlot == FixedSpillSlots + NumFixedSpillSlots) { + // Nope, just spill it anywhere convenient. + unsigned Align = RC->getAlignment(); + unsigned StackAlign = TFI->getStackAlignment(); + + // We may not be able to satisfy the desired alignment specification of + // the TargetRegisterClass if the stack alignment is smaller. Use the + // min. + Align = std::min(Align, StackAlign); + FrameIdx = MFI->CreateStackObject(RC->getSize(), Align, true); + if ((unsigned)FrameIdx < MinCSFrameIndex) MinCSFrameIndex = FrameIdx; + if ((unsigned)FrameIdx > MaxCSFrameIndex) MaxCSFrameIndex = FrameIdx; + } else { + // Spill it to the stack where we must. + FrameIdx = + MFI->CreateFixedSpillStackObject(RC->getSize(), FixedSlot->Offset); + } - int FrameIdx; - if (RegInfo->hasReservedSpillSlot(F, Reg, FrameIdx)) { I->setFrameIdx(FrameIdx); - continue; } + } - // Check to see if this physreg must be spilled to a particular stack slot - // on this target. - const TargetFrameLowering::SpillSlot *FixedSlot = FixedSpillSlots; - while (FixedSlot != FixedSpillSlots+NumFixedSpillSlots && - FixedSlot->Reg != Reg) - ++FixedSlot; - - if (FixedSlot == FixedSpillSlots + NumFixedSpillSlots) { - // Nope, just spill it anywhere convenient. - unsigned Align = RC->getAlignment(); - unsigned StackAlign = TFI->getStackAlignment(); - - // We may not be able to satisfy the desired alignment specification of - // the TargetRegisterClass if the stack alignment is smaller. Use the - // min. - Align = std::min(Align, StackAlign); - FrameIdx = MFI->CreateStackObject(RC->getSize(), Align, true); - if ((unsigned)FrameIdx < MinCSFrameIndex) MinCSFrameIndex = FrameIdx; - if ((unsigned)FrameIdx > MaxCSFrameIndex) MaxCSFrameIndex = FrameIdx; - } else { - // Spill it to the stack where we must. - FrameIdx = MFI->CreateFixedObject(RC->getSize(), FixedSlot->Offset, true); - } + MFI->setCalleeSavedInfo(CSI); +} - I->setFrameIdx(FrameIdx); +/// Helper function to update the liveness information for the callee-saved +/// registers. +static void updateLiveness(MachineFunction &MF) { + MachineFrameInfo *MFI = MF.getFrameInfo(); + // Visited will contain all the basic blocks that are in the region + // where the callee saved registers are alive: + // - Anything that is not Save or Restore -> LiveThrough. + // - Save -> LiveIn. + // - Restore -> LiveOut. + // The live-out is not attached to the block, so no need to keep + // Restore in this set. + SmallPtrSet Visited; + SmallVector WorkList; + MachineBasicBlock *Entry = &MF.front(); + MachineBasicBlock *Save = MFI->getSavePoint(); + + if (!Save) + Save = Entry; + + if (Entry != Save) { + WorkList.push_back(Entry); + Visited.insert(Entry); + } + Visited.insert(Save); + + MachineBasicBlock *Restore = MFI->getRestorePoint(); + if (Restore) + // By construction Restore cannot be visited, otherwise it + // means there exists a path to Restore that does not go + // through Save. + WorkList.push_back(Restore); + + while (!WorkList.empty()) { + const MachineBasicBlock *CurBB = WorkList.pop_back_val(); + // By construction, the region that is after the save point is + // dominated by the Save and post-dominated by the Restore. + if (CurBB == Save) + continue; + // Enqueue all the successors not already visited. + // Those are by construction either before Save or after Restore. + for (MachineBasicBlock *SuccBB : CurBB->successors()) + if (Visited.insert(SuccBB).second) + WorkList.push_back(SuccBB); } - MFI->setCalleeSavedInfo(CSI); + const std::vector &CSI = MFI->getCalleeSavedInfo(); + + for (unsigned i = 0, e = CSI.size(); i != e; ++i) { + for (MachineBasicBlock *MBB : Visited) + // Add the callee-saved register as live-in. + // It's killed at the spill. + MBB->addLiveIn(CSI[i].getReg()); + } } /// insertCSRSpillsAndRestores - Insert spill and restore code for -/// callee saved registers used in the function, handling shrink wrapping. +/// callee saved registers used in the function. /// void PEI::insertCSRSpillsAndRestores(MachineFunction &Fn) { // Get callee saved register information. @@ -284,138 +442,36 @@ void PEI::insertCSRSpillsAndRestores(MachineFunction &Fn) { if (CSI.empty()) return; - const TargetInstrInfo &TII = *Fn.getTarget().getInstrInfo(); - const TargetFrameLowering *TFI = Fn.getTarget().getFrameLowering(); - const TargetRegisterInfo *TRI = Fn.getTarget().getRegisterInfo(); + const TargetInstrInfo &TII = *Fn.getSubtarget().getInstrInfo(); + const TargetFrameLowering *TFI = Fn.getSubtarget().getFrameLowering(); + const TargetRegisterInfo *TRI = Fn.getSubtarget().getRegisterInfo(); MachineBasicBlock::iterator I; - if (!ShrinkWrapThisFunction) { - // Spill using target interface. - I = EntryBlock->begin(); - if (!TFI->spillCalleeSavedRegisters(*EntryBlock, I, CSI, TRI)) { + // Spill using target interface. + for (MachineBasicBlock *SaveBlock : SaveBlocks) { + I = SaveBlock->begin(); + if (!TFI->spillCalleeSavedRegisters(*SaveBlock, I, CSI, TRI)) { for (unsigned i = 0, e = CSI.size(); i != e; ++i) { - // Add the callee-saved register as live-in. - // It's killed at the spill. - EntryBlock->addLiveIn(CSI[i].getReg()); - // Insert the spill to the stack frame. unsigned Reg = CSI[i].getReg(); const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg); - TII.storeRegToStackSlot(*EntryBlock, I, Reg, true, - CSI[i].getFrameIdx(), RC, TRI); + TII.storeRegToStackSlot(*SaveBlock, I, Reg, true, CSI[i].getFrameIdx(), + RC, TRI); } } - - // Restore using target interface. - for (unsigned ri = 0, re = ReturnBlocks.size(); ri != re; ++ri) { - MachineBasicBlock* MBB = ReturnBlocks[ri]; - I = MBB->end(); --I; - - // Skip over all terminator instructions, which are part of the return - // sequence. - MachineBasicBlock::iterator I2 = I; - while (I2 != MBB->begin() && (--I2)->isTerminator()) - I = I2; - - bool AtStart = I == MBB->begin(); - MachineBasicBlock::iterator BeforeI = I; - if (!AtStart) - --BeforeI; - - // Restore all registers immediately before the return and any - // terminators that precede it. - if (!TFI->restoreCalleeSavedRegisters(*MBB, I, CSI, TRI)) { - for (unsigned i = 0, e = CSI.size(); i != e; ++i) { - unsigned Reg = CSI[i].getReg(); - const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg); - TII.loadRegFromStackSlot(*MBB, I, Reg, - CSI[i].getFrameIdx(), - RC, TRI); - assert(I != MBB->begin() && - "loadRegFromStackSlot didn't insert any code!"); - // Insert in reverse order. loadRegFromStackSlot can insert - // multiple instructions. - if (AtStart) - I = MBB->begin(); - else { - I = BeforeI; - ++I; - } - } - } - } - return; + // Update the live-in information of all the blocks up to the save point. + updateLiveness(Fn); } - // Insert spills. - std::vector blockCSI; - for (CSRegBlockMap::iterator BI = CSRSave.begin(), - BE = CSRSave.end(); BI != BE; ++BI) { - MachineBasicBlock* MBB = BI->first; - CSRegSet save = BI->second; - - if (save.empty()) - continue; - - blockCSI.clear(); - for (CSRegSet::iterator RI = save.begin(), - RE = save.end(); RI != RE; ++RI) { - blockCSI.push_back(CSI[*RI]); - } - assert(blockCSI.size() > 0 && - "Could not collect callee saved register info"); + // Restore using target interface. + for (MachineBasicBlock *MBB : RestoreBlocks) { + I = MBB->end(); - I = MBB->begin(); - - // When shrink wrapping, use stack slot stores/loads. - for (unsigned i = 0, e = blockCSI.size(); i != e; ++i) { - // Add the callee-saved register as live-in. - // It's killed at the spill. - MBB->addLiveIn(blockCSI[i].getReg()); - - // Insert the spill to the stack frame. - unsigned Reg = blockCSI[i].getReg(); - const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg); - TII.storeRegToStackSlot(*MBB, I, Reg, - true, - blockCSI[i].getFrameIdx(), - RC, TRI); - } - } - - for (CSRegBlockMap::iterator BI = CSRRestore.begin(), - BE = CSRRestore.end(); BI != BE; ++BI) { - MachineBasicBlock* MBB = BI->first; - CSRegSet restore = BI->second; - - if (restore.empty()) - continue; - - blockCSI.clear(); - for (CSRegSet::iterator RI = restore.begin(), - RE = restore.end(); RI != RE; ++RI) { - blockCSI.push_back(CSI[*RI]); - } - assert(blockCSI.size() > 0 && - "Could not find callee saved register info"); - - // If MBB is empty and needs restores, insert at the _beginning_. - if (MBB->empty()) { - I = MBB->begin(); - } else { - I = MBB->end(); - --I; - - // Skip over all terminator instructions, which are part of the - // return sequence. - if (! I->isTerminator()) { - ++I; - } else { - MachineBasicBlock::iterator I2 = I; - while (I2 != MBB->begin() && (--I2)->isTerminator()) - I = I2; - } - } + // Skip over all terminator instructions, which are part of the return + // sequence. + MachineBasicBlock::iterator I2 = I; + while (I2 != MBB->begin() && (--I2)->isTerminator()) + I = I2; bool AtStart = I == MBB->begin(); MachineBasicBlock::iterator BeforeI = I; @@ -424,21 +480,21 @@ void PEI::insertCSRSpillsAndRestores(MachineFunction &Fn) { // Restore all registers immediately before the return and any // terminators that precede it. - for (unsigned i = 0, e = blockCSI.size(); i != e; ++i) { - unsigned Reg = blockCSI[i].getReg(); - const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg); - TII.loadRegFromStackSlot(*MBB, I, Reg, - blockCSI[i].getFrameIdx(), - RC, TRI); - assert(I != MBB->begin() && - "loadRegFromStackSlot didn't insert any code!"); - // Insert in reverse order. loadRegFromStackSlot can insert - // multiple instructions. - if (AtStart) - I = MBB->begin(); - else { - I = BeforeI; - ++I; + if (!TFI->restoreCalleeSavedRegisters(*MBB, I, CSI, TRI)) { + for (unsigned i = 0, e = CSI.size(); i != e; ++i) { + unsigned Reg = CSI[i].getReg(); + const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg); + TII.loadRegFromStackSlot(*MBB, I, Reg, CSI[i].getFrameIdx(), RC, TRI); + assert(I != MBB->begin() && + "loadRegFromStackSlot didn't insert any code!"); + // Insert in reverse order. loadRegFromStackSlot can insert + // multiple instructions. + if (AtStart) + I = MBB->begin(); + else { + I = BeforeI; + ++I; + } } } } @@ -472,11 +528,28 @@ AdjustStackOffset(MachineFrameInfo *MFI, int FrameIdx, } } +/// AssignProtectedObjSet - Helper function to assign large stack objects (i.e., +/// those required to be close to the Stack Protector) to stack offsets. +static void +AssignProtectedObjSet(const StackObjSet &UnassignedObjs, + SmallSet &ProtectedObjs, + MachineFrameInfo *MFI, bool StackGrowsDown, + int64_t &Offset, unsigned &MaxAlign) { + + for (StackObjSet::const_iterator I = UnassignedObjs.begin(), + E = UnassignedObjs.end(); I != E; ++I) { + int i = *I; + AdjustStackOffset(MFI, i, StackGrowsDown, Offset, MaxAlign); + ProtectedObjs.insert(i); + } +} + /// calculateFrameObjectOffsets - Calculate actual frame offsets for all of the /// abstract stack objects. /// void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { - const TargetFrameLowering &TFI = *Fn.getTarget().getFrameLowering(); + const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering(); + StackProtector *SP = &getAnalysis(); bool StackGrowsDown = TFI.getStackGrowthDirection() == TargetFrameLowering::StackGrowsDown; @@ -524,7 +597,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { unsigned Align = MFI->getObjectAlignment(i); // Adjust to alignment boundary - Offset = (Offset+Align-1)/Align*Align; + Offset = RoundUpToAlignment(Offset, Align); MFI->setObjectOffset(i, -Offset); // Set the computed offset } @@ -533,7 +606,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { for (int i = MaxCSFI; i >= MinCSFI ; --i) { unsigned Align = MFI->getObjectAlignment(i); // Adjust to alignment boundary - Offset = (Offset+Align-1)/Align*Align; + Offset = RoundUpToAlignment(Offset, Align); MFI->setObjectOffset(i, Offset); Offset += MFI->getObjectSize(i); @@ -543,14 +616,18 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { unsigned MaxAlign = MFI->getMaxAlignment(); // Make sure the special register scavenging spill slot is closest to the - // frame pointer if a frame pointer is required. - const TargetRegisterInfo *RegInfo = Fn.getTarget().getRegisterInfo(); - if (RS && TFI.hasFP(Fn) && RegInfo->useFPForScavengingIndex(Fn) && - !RegInfo->needsStackRealignment(Fn)) { + // incoming stack pointer if a frame pointer is required and is closer + // to the incoming rather than the final stack pointer. + const TargetRegisterInfo *RegInfo = Fn.getSubtarget().getRegisterInfo(); + bool EarlyScavengingSlots = (TFI.hasFP(Fn) && + TFI.isFPCloseToIncomingSP() && + RegInfo->useFPForScavengingIndex(Fn) && + !RegInfo->needsStackRealignment(Fn)); + if (RS && EarlyScavengingSlots) { SmallVector SFIs; RS->getScavengingFrameIndices(SFIs); - for (SmallVector::iterator I = SFIs.begin(), - IE = SFIs.end(); I != IE; ++I) + for (SmallVectorImpl::iterator I = SFIs.begin(), + IE = SFIs.end(); I != IE; ++I) AdjustStackOffset(MFI, *I, StackGrowsDown, Offset, MaxAlign); } @@ -562,7 +639,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { unsigned Align = MFI->getLocalFrameMaxAlign(); // Adjust to alignment boundary. - Offset = (Offset + Align - 1) / Align * Align; + Offset = RoundUpToAlignment(Offset, Align); DEBUG(dbgs() << "Local frame base offset: " << Offset << "\n"); @@ -582,8 +659,12 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { // Make sure that the stack protector comes before the local variables on the // stack. - SmallSet LargeStackObjs; + SmallSet ProtectedObjs; if (MFI->getStackProtectorIndex() >= 0) { + StackObjSet LargeArrayObjs; + StackObjSet SmallArrayObjs; + StackObjSet AddrOfObjs; + AdjustStackOffset(MFI, MFI->getStackProtectorIndex(), StackGrowsDown, Offset, MaxAlign); @@ -600,12 +681,29 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { continue; if (MFI->getStackProtectorIndex() == (int)i) continue; - if (!MFI->MayNeedStackProtector(i)) - continue; - AdjustStackOffset(MFI, i, StackGrowsDown, Offset, MaxAlign); - LargeStackObjs.insert(i); + switch (SP->getSSPLayout(MFI->getObjectAllocation(i))) { + case StackProtector::SSPLK_None: + continue; + case StackProtector::SSPLK_SmallArray: + SmallArrayObjs.insert(i); + continue; + case StackProtector::SSPLK_AddrOf: + AddrOfObjs.insert(i); + continue; + case StackProtector::SSPLK_LargeArray: + LargeArrayObjs.insert(i); + continue; + } + llvm_unreachable("Unexpected SSPLayoutKind."); } + + AssignProtectedObjSet(LargeArrayObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); + AssignProtectedObjSet(SmallArrayObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); + AssignProtectedObjSet(AddrOfObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); } // Then assign frame offsets to stack objects that are not used to spill @@ -622,7 +720,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { continue; if (MFI->getStackProtectorIndex() == (int)i) continue; - if (LargeStackObjs.count(i)) + if (ProtectedObjs.count(i)) continue; AdjustStackOffset(MFI, i, StackGrowsDown, Offset, MaxAlign); @@ -630,12 +728,11 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { // Make sure the special register scavenging spill slot is closest to the // stack pointer. - if (RS && (!TFI.hasFP(Fn) || RegInfo->needsStackRealignment(Fn) || - !RegInfo->useFPForScavengingIndex(Fn))) { + if (RS && !EarlyScavengingSlots) { SmallVector SFIs; RS->getScavengingFrameIndices(SFIs); - for (SmallVector::iterator I = SFIs.begin(), - IE = SFIs.end(); I != IE; ++I) + for (SmallVectorImpl::iterator I = SFIs.begin(), + IE = SFIs.end(); I != IE; ++I) AdjustStackOffset(MFI, *I, StackGrowsDown, Offset, MaxAlign); } @@ -661,8 +758,7 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { // If the frame pointer is eliminated, all frame offsets will be relative to // SP not FP. Align to MaxAlign so this works. StackAlign = std::max(StackAlign, MaxAlign); - unsigned AlignMask = StackAlign - 1; - Offset = (Offset + AlignMask) & ~uint64_t(AlignMask); + Offset = RoundUpToAlignment(Offset, StackAlign); } // Update frame info to pretend that this is part of the stack... @@ -676,24 +772,24 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { /// prolog and epilog code to the function. /// void PEI::insertPrologEpilogCode(MachineFunction &Fn) { - const TargetFrameLowering &TFI = *Fn.getTarget().getFrameLowering(); + const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering(); // Add prologue to the function... - TFI.emitPrologue(Fn); + for (MachineBasicBlock *SaveBlock : SaveBlocks) + TFI.emitPrologue(Fn, *SaveBlock); - // Add epilogue to restore the callee-save registers in each exiting block - for (MachineFunction::iterator I = Fn.begin(), E = Fn.end(); I != E; ++I) { - // If last instruction is a return instruction, add an epilogue - if (!I->empty() && I->back().isReturn()) - TFI.emitEpilogue(Fn, *I); - } + // Add epilogue to restore the callee-save registers in each exiting block. + for (MachineBasicBlock *RestoreBlock : RestoreBlocks) + TFI.emitEpilogue(Fn, *RestoreBlock); // Emit additional code that is required to support segmented stacks, if // we've been asked for it. This, when linked with a runtime with support // for segmented stacks (libgcc is one), will result in allocating stack // space in small chunks instead of one large contiguous block. - if (Fn.getTarget().Options.EnableSegmentedStacks) - TFI.adjustForSegmentedStacks(Fn); + if (Fn.shouldSplitStack()) { + for (MachineBasicBlock *SaveBlock : SaveBlocks) + TFI.adjustForSegmentedStacks(Fn, *SaveBlock); + } // Emit additional code that is required to explicitly handle the stack in // HiPE native code (if needed) when loaded in the Erlang/OTP runtime. The @@ -701,108 +797,185 @@ void PEI::insertPrologEpilogCode(MachineFunction &Fn) { // different conditional check and another BIF for allocating more stack // space. if (Fn.getFunction()->getCallingConv() == CallingConv::HiPE) - TFI.adjustForHiPEPrologue(Fn); + for (MachineBasicBlock *SaveBlock : SaveBlocks) + TFI.adjustForHiPEPrologue(Fn, *SaveBlock); } /// replaceFrameIndices - Replace all MO_FrameIndex operands with physical /// register references and actual offsets. /// void PEI::replaceFrameIndices(MachineFunction &Fn) { - if (!Fn.getFrameInfo()->hasStackObjects()) return; // Nothing to do? + const TargetFrameLowering &TFI = *Fn.getSubtarget().getFrameLowering(); + if (!TFI.needsFrameIndexResolution(Fn)) return; + + MachineModuleInfo &MMI = Fn.getMMI(); + const Function *F = Fn.getFunction(); + const Function *ParentF = MMI.getWinEHParent(F); + unsigned FrameReg; + if (F == ParentF) { + WinEHFuncInfo &FuncInfo = MMI.getWinEHFuncInfo(Fn.getFunction()); + // FIXME: This should be unconditional but we have bugs in the preparation + // pass. + if (FuncInfo.UnwindHelpFrameIdx != INT_MAX) + FuncInfo.UnwindHelpFrameOffset = TFI.getFrameIndexReferenceFromSP( + Fn, FuncInfo.UnwindHelpFrameIdx, FrameReg); + for (WinEHTryBlockMapEntry &TBME : FuncInfo.TryBlockMap) { + for (WinEHHandlerType &H : TBME.HandlerArray) { + unsigned UnusedReg; + if (H.CatchObj.FrameIndex == INT_MAX) + H.CatchObj.FrameOffset = INT_MAX; + else + H.CatchObj.FrameOffset = + TFI.getFrameIndexReference(Fn, H.CatchObj.FrameIndex, UnusedReg); + } + } + } - const TargetMachine &TM = Fn.getTarget(); - assert(TM.getRegisterInfo() && "TM::getRegisterInfo() must be implemented!"); - const TargetInstrInfo &TII = *Fn.getTarget().getInstrInfo(); - const TargetRegisterInfo &TRI = *TM.getRegisterInfo(); - const TargetFrameLowering *TFI = TM.getFrameLowering(); - bool StackGrowsDown = - TFI->getStackGrowthDirection() == TargetFrameLowering::StackGrowsDown; - int FrameSetupOpcode = TII.getCallFrameSetupOpcode(); - int FrameDestroyOpcode = TII.getCallFrameDestroyOpcode(); + // Store SPAdj at exit of a basic block. + SmallVector SPState; + SPState.resize(Fn.getNumBlockIDs()); + SmallPtrSet Reachable; - for (MachineFunction::iterator BB = Fn.begin(), - E = Fn.end(); BB != E; ++BB) { -#ifndef NDEBUG - int SPAdjCount = 0; // frame setup / destroy count. -#endif - int SPAdj = 0; // SP offset due to call frame setup / destroy. - if (RS && !FrameIndexVirtualScavenging) RS->enterBasicBlock(BB); + // Iterate over the reachable blocks in DFS order. + for (auto DFI = df_ext_begin(&Fn, Reachable), DFE = df_ext_end(&Fn, Reachable); + DFI != DFE; ++DFI) { + int SPAdj = 0; + // Check the exit state of the DFS stack predecessor. + if (DFI.getPathLength() >= 2) { + MachineBasicBlock *StackPred = DFI.getPath(DFI.getPathLength() - 2); + assert(Reachable.count(StackPred) && + "DFS stack predecessor is already visited.\n"); + SPAdj = SPState[StackPred->getNumber()]; + } + MachineBasicBlock *BB = *DFI; + replaceFrameIndices(BB, Fn, SPAdj); + SPState[BB->getNumber()] = SPAdj; + } - for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ) { + // Handle the unreachable blocks. + for (MachineFunction::iterator BB = Fn.begin(), E = Fn.end(); BB != E; ++BB) { + if (Reachable.count(BB)) + // Already handled in DFS traversal. + continue; + int SPAdj = 0; + replaceFrameIndices(BB, Fn, SPAdj); + } +} - if (I->getOpcode() == FrameSetupOpcode || - I->getOpcode() == FrameDestroyOpcode) { -#ifndef NDEBUG - // Track whether we see even pairs of them - SPAdjCount += I->getOpcode() == FrameSetupOpcode ? 1 : -1; -#endif - // Remember how much SP has been adjusted to create the call - // frame. - int Size = I->getOperand(0).getImm(); - - if ((!StackGrowsDown && I->getOpcode() == FrameSetupOpcode) || - (StackGrowsDown && I->getOpcode() == FrameDestroyOpcode)) - Size = -Size; - - SPAdj += Size; - - MachineBasicBlock::iterator PrevI = BB->end(); - if (I != BB->begin()) PrevI = prior(I); - TFI->eliminateCallFramePseudoInstr(Fn, *BB, I); - - // Visit the instructions created by eliminateCallFramePseudoInstr(). - if (PrevI == BB->end()) - I = BB->begin(); // The replaced instr was the first in the block. - else - I = llvm::next(PrevI); - continue; - } +void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn, + int &SPAdj) { + assert(Fn.getSubtarget().getRegisterInfo() && + "getRegisterInfo() must be implemented!"); + const TargetInstrInfo &TII = *Fn.getSubtarget().getInstrInfo(); + const TargetRegisterInfo &TRI = *Fn.getSubtarget().getRegisterInfo(); + const TargetFrameLowering *TFI = Fn.getSubtarget().getFrameLowering(); + unsigned FrameSetupOpcode = TII.getCallFrameSetupOpcode(); + unsigned FrameDestroyOpcode = TII.getCallFrameDestroyOpcode(); - MachineInstr *MI = I; - bool DoIncr = true; - for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) { - if (!MI->getOperand(i).isFI()) - continue; + if (RS && !FrameIndexVirtualScavenging) RS->enterBasicBlock(BB); - // Some instructions (e.g. inline asm instructions) can have - // multiple frame indices and/or cause eliminateFrameIndex - // to insert more than one instruction. We need the register - // scavenger to go through all of these instructions so that - // it can update its register information. We keep the - // iterator at the point before insertion so that we can - // revisit them in full. - bool AtBeginning = (I == BB->begin()); - if (!AtBeginning) --I; - - // If this instruction has a FrameIndex operand, we need to - // use that target machine register info object to eliminate - // it. - TRI.eliminateFrameIndex(MI, SPAdj, i, - FrameIndexVirtualScavenging ? NULL : RS); - - // Reset the iterator if we were at the beginning of the BB. - if (AtBeginning) { - I = BB->begin(); - DoIncr = false; - } + bool InsideCallSequence = false; - MI = 0; - break; + for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ) { + + if (I->getOpcode() == FrameSetupOpcode || + I->getOpcode() == FrameDestroyOpcode) { + InsideCallSequence = (I->getOpcode() == FrameSetupOpcode); + SPAdj += TII.getSPAdjust(I); + + MachineBasicBlock::iterator PrevI = BB->end(); + if (I != BB->begin()) PrevI = std::prev(I); + TFI->eliminateCallFramePseudoInstr(Fn, *BB, I); + + // Visit the instructions created by eliminateCallFramePseudoInstr(). + if (PrevI == BB->end()) + I = BB->begin(); // The replaced instr was the first in the block. + else + I = std::next(PrevI); + continue; + } + + MachineInstr *MI = I; + bool DoIncr = true; + for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) { + if (!MI->getOperand(i).isFI()) + continue; + + // Frame indices in debug values are encoded in a target independent + // way with simply the frame index and offset rather than any + // target-specific addressing mode. + if (MI->isDebugValue()) { + assert(i == 0 && "Frame indices can only appear as the first " + "operand of a DBG_VALUE machine instruction"); + unsigned Reg; + MachineOperand &Offset = MI->getOperand(1); + Offset.setImm(Offset.getImm() + + TFI->getFrameIndexReference( + Fn, MI->getOperand(0).getIndex(), Reg)); + MI->getOperand(0).ChangeToRegister(Reg, false /*isDef*/); + continue; } - if (DoIncr && I != BB->end()) ++I; + // TODO: This code should be commoned with the code for + // PATCHPOINT. There's no good reason for the difference in + // implementation other than historical accident. The only + // remaining difference is the unconditional use of the stack + // pointer as the base register. + if (MI->getOpcode() == TargetOpcode::STATEPOINT) { + assert((!MI->isDebugValue() || i == 0) && + "Frame indicies can only appear as the first operand of a " + "DBG_VALUE machine instruction"); + unsigned Reg; + MachineOperand &Offset = MI->getOperand(i + 1); + const unsigned refOffset = + TFI->getFrameIndexReferenceFromSP(Fn, MI->getOperand(i).getIndex(), + Reg); + + Offset.setImm(Offset.getImm() + refOffset); + MI->getOperand(i).ChangeToRegister(Reg, false /*isDef*/); + continue; + } + + // Some instructions (e.g. inline asm instructions) can have + // multiple frame indices and/or cause eliminateFrameIndex + // to insert more than one instruction. We need the register + // scavenger to go through all of these instructions so that + // it can update its register information. We keep the + // iterator at the point before insertion so that we can + // revisit them in full. + bool AtBeginning = (I == BB->begin()); + if (!AtBeginning) --I; + + // If this instruction has a FrameIndex operand, we need to + // use that target machine register info object to eliminate + // it. + TRI.eliminateFrameIndex(MI, SPAdj, i, + FrameIndexVirtualScavenging ? nullptr : RS); + + // Reset the iterator if we were at the beginning of the BB. + if (AtBeginning) { + I = BB->begin(); + DoIncr = false; + } - // Update register states. - if (RS && !FrameIndexVirtualScavenging && MI) RS->forward(MI); + MI = nullptr; + break; } - // If we have evenly matched pairs of frame setup / destroy instructions, - // make sure the adjustments come out to zero. If we don't have matched - // pairs, we can't be sure the missing bit isn't in another basic block - // due to a custom inserter playing tricks, so just asserting SPAdj==0 - // isn't sufficient. See tMOVCC on Thumb1, for example. - assert((SPAdjCount || SPAdj == 0) && - "Unbalanced call frame setup / destroy pairs?"); + // If we are looking at a call sequence, we need to keep track of + // the SP adjustment made by each instruction in the sequence. + // This includes both the frame setup/destroy pseudos (handled above), + // as well as other instructions that have side effects w.r.t the SP. + // Note that this must come after eliminateFrameIndex, because + // if I itself referred to a frame index, we shouldn't count its own + // adjustment. + if (MI && InsideCallSequence) + SPAdj += TII.getSPAdjust(MI); + + if (DoIncr && I != BB->end()) ++I; + + // Update register states. + if (RS && !FrameIndexVirtualScavenging && MI) RS->forward(MI); } } @@ -813,7 +986,8 @@ void PEI::replaceFrameIndices(MachineFunction &Fn) { /// FIXME: Iterating over the instruction stream is unnecessary. We can simply /// iterate over the vreg use list, which at this point only contains machine /// operands for which eliminateFrameIndex need a new scratch reg. -void PEI::scavengeFrameVirtualRegs(MachineFunction &Fn) { +void +PEI::scavengeFrameVirtualRegs(MachineFunction &Fn) { // Run through the instructions and find any virtual registers. for (MachineFunction::iterator BB = Fn.begin(), E = Fn.end(); BB != E; ++BB) { @@ -824,8 +998,17 @@ void PEI::scavengeFrameVirtualRegs(MachineFunction &Fn) { // The instruction stream may change in the loop, so check BB->end() // directly. for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ) { + // We might end up here again with a NULL iterator if we scavenged a + // register for which we inserted spill code for definition by what was + // originally the first instruction in BB. + if (I == MachineBasicBlock::iterator(nullptr)) + I = BB->begin(); + MachineInstr *MI = I; - MachineBasicBlock::iterator J = llvm::next(I); + MachineBasicBlock::iterator J = std::next(I); + MachineBasicBlock::iterator P = + I == BB->begin() ? MachineBasicBlock::iterator(nullptr) + : std::prev(I); // RS should process this instruction before we might scavenge at this // location. This is because we might be replacing a virtual register @@ -856,11 +1039,11 @@ void PEI::scavengeFrameVirtualRegs(MachineFunction &Fn) { // scratch register. assert (ScratchReg && "Missing scratch register!"); Fn.getRegInfo().replaceRegWith(Reg, ScratchReg); - + // Because this instruction was processed by the RS before this // register was allocated, make sure that the RS now records the // register as being used. - RS->setUsed(ScratchReg); + RS->setRegUsed(ScratchReg); } } @@ -868,9 +1051,19 @@ void PEI::scavengeFrameVirtualRegs(MachineFunction &Fn) { // spill code will have been inserted in between I and J. This is a // problem because we need the spill code before I: Move I to just // prior to J. - if (I != llvm::prior(J)) { - BB->splice(J, BB, I++); - RS->skipTo(I == BB->begin() ? NULL : llvm::prior(I)); + if (I != std::prev(J)) { + BB->splice(J, BB, I); + + // Before we move I, we need to prepare the RS to visit I again. + // Specifically, RS will assert if it sees uses of registers that + // it believes are undefined. Because we have already processed + // register kills in I, when it visits I again, it will believe that + // those registers are undefined. To avoid this situation, unprocess + // the instruction I. + assert(RS->getCurrentPosition() == I && + "The register scavenger has an unexpected position"); + I = P; + RS->unprocess(P); } else ++I; }