[MachineOutliner] Define MachineOutliner support in TargetOptions

[paquette]

Summary

Targets should be able to define whether or not they support the outliner without the outliner being added to the pass pipeline. Before this, the outliner pass would be added, and ask the target whether or not it supports the outliner.

After this, it's possible to query the target in TargetPassConfig, before the outliner pass is created. This ensures that passing -enable-machine-outliner will not modify the pass pipeline of any target that does not support it.

[efriedma]

LGTM

[paquette]

Thanks!

Committed in r335872.

[paquette]

Argh. I accidentally pushed https://reviews.llvm.org/D48682 instead of this. I'll revert it and push this instead. I haven't had enough coffee this morning.

[paquette]

This was actually committed in r335887.

https://reviews.llvm.org/rL335887

include/llvm/CodeGen/TargetInstrInfo.h

public:
 
   /// True if the instruction is bound to the top of its basic block and no
   /// other instructions shall be inserted before it. This can be implemented
   /// to prevent register allocator to insert spills before such instructions.
   virtual bool isBasicBlockPrologue(const MachineInstr &MI) const {
     return false;
   }
 
-  /// Returns true if the target implements the MachineOutliner.
-  virtual bool useMachineOutliner() const { return false; }
-
   /// Returns a \p outliner::TargetCostInfo struct containing target-specific
   /// information for a set of outlining candidates.
   virtual outliner::TargetCostInfo getOutlininingCandidateInfo(
       std::vector<outliner::Candidate> &RepeatedSequenceLocs) const {
     llvm_unreachable(
         "Target didn't implement TargetInstrInfo::getOutliningCandidateInfo!");
   }
 

include/llvm/Target/TargetMachine.h

public:
 
   /// Overrides the optimization level.
   void setOptLevel(CodeGenOpt::Level Level);
 
   void setFastISel(bool Enable) { Options.EnableFastISel = Enable; }
   bool getO0WantsFastISel() { return O0WantsFastISel; }
   void setO0WantsFastISel(bool Enable) { O0WantsFastISel = Enable; }
   void setGlobalISel(bool Enable) { Options.EnableGlobalISel = Enable; }
+  void setMachineOutliner(bool Enable) {
+    Options.EnableMachineOutliner = Enable;
+  }
 
   bool shouldPrintMachineCode() const { return Options.PrintMachineCode; }
 
   bool getUniqueSectionNames() const { return Options.UniqueSectionNames; }
 
   /// Return true if data objects should be emitted into their own section,
   /// corresponds to -fdata-sections.
   bool getDataSections() const {

include/llvm/Target/TargetOptions.h

TargetOptions()
           NoSignedZerosFPMath(false),
           HonorSignDependentRoundingFPMathOption(false), NoZerosInBSS(false),
           GuaranteedTailCallOpt(false), StackSymbolOrdering(true),
           EnableFastISel(false), EnableGlobalISel(false), UseInitArray(false),
           DisableIntegratedAS(false), RelaxELFRelocations(false),
           FunctionSections(false), DataSections(false),
           UniqueSectionNames(true), TrapUnreachable(false),
           EmulatedTLS(false), ExplicitEmulatedTLS(false),
-          EnableIPRA(false), EmitStackSizeSection(false) {}
+          EnableIPRA(false), EmitStackSizeSection(false),
+          EnableMachineOutliner(false) {}
 
     /// PrintMachineCode - This flag is enabled when the -print-machineinstrs
     /// option is specified on the command line, and should enable debugging
     /// output from the code generator.
     unsigned PrintMachineCode : 1;
 
     /// DisableFramePointerElim - This returns true if frame pointer elimination
     /// optimization should be disabled for the given machine function.
public:
     unsigned ExplicitEmulatedTLS : 1;
 
     /// This flag enables InterProcedural Register Allocation (IPRA).
     unsigned EnableIPRA : 1;
 
     /// Emit section containing metadata on function stack sizes.
     unsigned EmitStackSizeSection : 1;
 
+    /// Enables the MachineOutliner pass.
+    unsigned EnableMachineOutliner : 1;
+
     /// FloatABIType - This setting is set by -float-abi=xxx option is specfied
     /// on the command line. This setting may either be Default, Soft, or Hard.
     /// Default selects the target's default behavior. Soft selects the ABI for
     /// software floating point, but does not indicate that FP hardware may not
     /// be used. Such a combination is unfortunately popular (e.g.
     /// arm-apple-darwin). Hard presumes that the normal FP ABI is used.
     FloatABI::ABIType FloatABIType = FloatABI::Default;
 

lib/CodeGen/MachineOutliner.cpp

if (M.empty())
     return false;
 
   MachineModuleInfo &MMI = getAnalysis<MachineModuleInfo>();
   const TargetSubtargetInfo &STI =
       MMI.getOrCreateMachineFunction(*M.begin()).getSubtarget();
   const TargetRegisterInfo *TRI = STI.getRegisterInfo();
   const TargetInstrInfo *TII = STI.getInstrInfo();
 
-  // Does the target implement the MachineOutliner? If it doesn't, quit here.
-  if (!TII->useMachineOutliner()) {
-    // No. So we're done.
-    LLVM_DEBUG(
-        dbgs()
-        << "Skipping pass: Target does not support the MachineOutliner.\n");
-    return false;
-  }
-
   // If the user specifies that they want to outline from linkonceodrs, set
   // it here.
   OutlineFromLinkOnceODRs = EnableLinkOnceODROutlining;
 
   InstructionMapper Mapper;
 
   // Build instruction mappings for each function in the module. Start by
   // iterating over each Function in M.

lib/CodeGen/TargetPassConfig.cpp

void TargetPassConfig::addMachinePasses() {
   addPass(&LiveDebugValuesID, false);
 
   // Insert before XRay Instrumentation.
   addPass(&FEntryInserterID, false);
 
   addPass(&XRayInstrumentationID, false);
   addPass(&PatchableFunctionID, false);
 
-  if (EnableMachineOutliner == AlwaysOutline)
+  if (TM->Options.EnableMachineOutliner &&
+      getOptLevel() != CodeGenOpt::None &&
+      EnableMachineOutliner == AlwaysOutline)
     addPass(createMachineOutlinerPass());
 
   // Add passes that directly emit MI after all other MI passes.
   addPreEmitPass2();
 
   AddingMachinePasses = false;
 }
 

lib/Target/AArch64/AArch64InstrInfo.h

public:
   decomposeMachineOperandsTargetFlags(unsigned TF) const override;
   ArrayRef<std::pair<unsigned, const char *>>
   getSerializableDirectMachineOperandTargetFlags() const override;
   ArrayRef<std::pair<unsigned, const char *>>
   getSerializableBitmaskMachineOperandTargetFlags() const override;
   ArrayRef<std::pair<MachineMemOperand::Flags, const char *>>
   getSerializableMachineMemOperandTargetFlags() const override;
 
-  /// AArch64 supports the MachineOutliner.
-  bool useMachineOutliner() const override { return true; }
   bool isFunctionSafeToOutlineFrom(MachineFunction &MF,
                                    bool OutlineFromLinkOnceODRs) const override;
   outliner::TargetCostInfo getOutlininingCandidateInfo(
       std::vector<outliner::Candidate> &RepeatedSequenceLocs) const override;
   outliner::InstrType
   getOutliningType(MachineBasicBlock::iterator &MIT, unsigned Flags) const override;
   unsigned getMachineOutlinerMBBFlags(MachineBasicBlock &MBB) const override;
   void buildOutlinedFrame(MachineBasicBlock &MBB, MachineFunction &MF,

lib/Target/AArch64/AArch64TargetMachine.cpp

AArch64TargetMachine::AArch64TargetMachine(const Target &T, const Triple &TT,
   initAsmInfo();
 
   if (TT.isOSBinFormatMachO())
     this->Options.TrapUnreachable = true;
 
   // Enable GlobalISel at or below EnableGlobalISelAt0.
   if (getOptLevel() <= EnableGlobalISelAtO)
     setGlobalISel(true);
+
+  // AArch64 supports the MachineOutliner.
+  setMachineOutliner(true);
 }
 
 AArch64TargetMachine::~AArch64TargetMachine() = default;
 
 const AArch64Subtarget *
 AArch64TargetMachine::getSubtargetImpl(const Function &F) const {
   Attribute CPUAttr = F.getFnAttribute("target-cpu");
   Attribute FSAttr = F.getFnAttribute("target-features");

lib/Target/X86/X86InstrInfo.h

MachineInstr *optimizeLoadInstr(MachineInstr &MI,
                                   MachineInstr *&DefMI) const override;
 
   std::pair<unsigned, unsigned>
   decomposeMachineOperandsTargetFlags(unsigned TF) const override;
 
   ArrayRef<std::pair<unsigned, const char *>>
   getSerializableDirectMachineOperandTargetFlags() const override;
 
-  /// X86 supports the MachineOutliner.
-  bool useMachineOutliner() const override { return true; }
-
   virtual outliner::TargetCostInfo getOutlininingCandidateInfo(
       std::vector<outliner::Candidate> &RepeatedSequenceLocs) const override;
 
   bool isFunctionSafeToOutlineFrom(MachineFunction &MF,
                                    bool OutlineFromLinkOnceODRs) const override;
 
   outliner::InstrType
   getOutliningType(MachineBasicBlock::iterator &MIT, unsigned Flags) const override;

lib/Target/X86/X86TargetMachine.cpp

X86TargetMachine::X86TargetMachine(const Target &T, const Triple &TT,
   // the calling function, and TrapUnreachable is an easy way to get that.
   // The check here for 64-bit windows is a bit icky, but as we're unlikely
   // to ever want to mix 32 and 64-bit windows code in a single module
   // this should be fine.
   if ((TT.isOSWindows() && TT.getArch() == Triple::x86_64) || TT.isPS4() ||
       TT.isOSBinFormatMachO())
     this->Options.TrapUnreachable = true;
 
+  // Outlining is available for x86-64.
+  if (TT.getArch() == Triple::x86_64)
+    setMachineOutliner(true);
+
   initAsmInfo();
 }
 
 X86TargetMachine::~X86TargetMachine() = default;
 
 const X86Subtarget *
 X86TargetMachine::getSubtargetImpl(const Function &F) const {
   Attribute CPUAttr = F.getFnAttribute("target-cpu");