Index: llvm/lib/CodeGen/MachineOutliner.cpp =================================================================== --- llvm/lib/CodeGen/MachineOutliner.cpp +++ llvm/lib/CodeGen/MachineOutliner.cpp @@ -56,6 +56,7 @@ //===----------------------------------------------------------------------===// #include "llvm/CodeGen/MachineOutliner.h" #include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/SmallSet.h" #include "llvm/ADT/Statistic.h" #include "llvm/ADT/Twine.h" #include "llvm/CodeGen/MachineFunction.h" @@ -1245,31 +1246,53 @@ // make sure that the ranges we yank things out of aren't wrong. if (MBB.getParent()->getProperties().hasProperty( MachineFunctionProperties::Property::TracksLiveness)) { - // Helper lambda for adding implicit def operands to the call + // The following code is to add implicit def operands to the call // instruction. It also updates call site information for moved // code. - auto CopyDefsAndUpdateCalls = [&CallInst](MachineInstr &MI) { - for (MachineOperand &MOP : MI.operands()) { - // Skip over anything that isn't a register. - if (!MOP.isReg()) - continue; - - // If it's a def, add it to the call instruction. - if (MOP.isDef()) - CallInst->addOperand(MachineOperand::CreateReg( - MOP.getReg(), true, /* isDef = true */ - true /* isImp = true */)); - } - if (MI.isCandidateForCallSiteEntry()) - MI.getMF()->eraseCallSiteInfo(&MI); - }; + SmallSet UseRegs, DefRegs; // Copy over the defs in the outlined range. // First inst in outlined range <-- Anything that's defined in this // ... .. range has to be added as an // implicit Last inst in outlined range <-- def to the call // instruction. Also remove call site information for outlined block - // of code. - std::for_each(CallInst, std::next(EndIt), CopyDefsAndUpdateCalls); + // of code. The exposed uses need to be copied in the outlined range. + for (MachineBasicBlock::reverse_iterator Iter = EndIt.getReverse(), + Last = std::next(CallInst.getReverse()); + Iter != Last; Iter++) { + MachineInstr *MI = &*Iter; + for (MachineOperand &MOP : MI->operands()) { + // Skip over anything that isn't a register. + if (!MOP.isReg()) + continue; + + if (MOP.isDef()) { + // Introduce DefRegs set to skip the redundant register. + DefRegs.insert(MOP.getReg()); + if (UseRegs.count(MOP.getReg())) + // Since the regiester is modeled as defined, + // it is not necessary to be put in use register set. + UseRegs.erase(MOP.getReg()); + } else if (!MOP.isUndef()) { + // Any register which is not undefined should + // be put in the use register set. + UseRegs.insert(MOP.getReg()); + } + } + if (MI->isCandidateForCallSiteEntry()) + MI->getMF()->eraseCallSiteInfo(MI); + } + + for (const Register &I : DefRegs) + // If it's a def, add it to the call instruction. + CallInst->addOperand(MachineOperand::CreateReg( + I, true, /* isDef = true */ + true /* isImp = true */)); + + for (const Register &I : UseRegs) + // If it's a exposed use, add it to the call instruction. + CallInst->addOperand( + MachineOperand::CreateReg(I, false, /* isDef = false */ + true /* isImp = true */)); } // Erase from the point after where the call was inserted up to, and Index: llvm/test/CodeGen/AArch64/machine-outliner-side-effect.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/AArch64/machine-outliner-side-effect.mir @@ -0,0 +1,32 @@ +# RUN: llc -mtriple=aarch64 -run-pass=machine-outliner -verify-machineinstrs %s -o - | FileCheck %s + +# The test checks whether the compiler updates the side effect of function @OUTLINED_FUNCTION_0 by adding the use of register x20. + +--- | + declare void @spam() local_unnamed_addr + define void @baz() optsize minsize noredzone { ret void } +... +--- +name: baz +tracksRegLiveness: true +body: | + bb.0: + liveins: $x0, $x20 + + $x0 = COPY renamable $x20 + BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0 + renamable $x21 = COPY $x0 + + $x0 = COPY renamable $x20 + BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0 + renamable $x22 = COPY $x0 + + $x0 = COPY killed renamable $x20 + BL @spam, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0 + renamable $x3 = COPY $x0 + + RET_ReallyLR + +... + +# CHECK: BL @OUTLINED_FUNCTION_0, {{.*}}, implicit $x20, {{.*}}