[XRay] Merge instrumentation point table emission code into AsmPrinter.

[pelikan]

Summary

No need to have this per-architecture. While there, unify 32-bit ARM's
behaviour with what changed elsewhere and start function names lowercase
as per the coding standards. Individual entry emission code goes to the
entry's own class.

Fully tested on amd64, cross-builds on both ARMs and PowerPC.

[dberris]

LGTM -- thanks Martin!

include/llvm/CodeGen/AsmPrinter.h

public:
   // containing the sled, and what kind of sled (and whether they should always
   // be instrumented).
   struct XRayFunctionEntry {
     const MCSymbol *Sled;
     const MCSymbol *Function;
     SledKind Kind;
     bool AlwaysInstrument;
     const class Function *Fn;
+
+    void emit(int, MCStreamer *, const MCSymbol *) const;
   };
 
   // All the sleds to be emitted.
   std::vector<XRayFunctionEntry> Sleds;
 
   // Helper function to record a given XRay sled.
   void recordSled(MCSymbol *Sled, const MachineInstr &MI, SledKind Kind);
 
+  /// Emit a table with all XRay instrumentation points.
+  void emitXRayTable();
+
   //===------------------------------------------------------------------===//
   // MachineFunctionPass Implementation.
   //===------------------------------------------------------------------===//
 
   /// Record analysis usage.
   ///
   void getAnalysisUsage(AnalysisUsage &AU) const override;
 

lib/CodeGen/AsmPrinter/AsmPrinter.cpp

 #include "llvm/IR/Mangler.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCSection.h"
+#include "llvm/MC/MCSectionELF.h"
+#include "llvm/MC/MCSectionMachO.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSymbolELF.h"
 #include "llvm/MC/MCValue.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Support/Timer.h"
GCMetadataPrinter *AsmPrinter::GetOrCreateGCPrinter(GCStrategy &S) {
   report_fatal_error("no GCMetadataPrinter registered for GC: " + Twine(Name));
 }
 
 /// Pin vtable to this file.
 AsmPrinterHandler::~AsmPrinterHandler() {}
 
 void AsmPrinterHandler::markFunctionEnd() {}
 
+// In the binary's "xray_instr_map" section, an array of these function entries
+// describes each instrumentation point.  When XRay patches your code, the index
+// into this table will be given to your handler as a patch point identifier.
+void AsmPrinter::XRayFunctionEntry::emit(int Bytes, MCStreamer *Out,
+                                         const MCSymbol *CurrentFnSym) const {
+  Out->EmitSymbolValue(Sled, Bytes);
+  Out->EmitSymbolValue(CurrentFnSym, Bytes);
+  auto Kind8 = static_cast<uint8_t>(Kind);
+  Out->EmitBytes(StringRef(reinterpret_cast<const char *>(&Kind8), 1));
+  Out->EmitBytes(
+      StringRef(reinterpret_cast<const char *>(&AlwaysInstrument), 1));
+  Out->EmitZeros(2 * Bytes - 2);  // Pad the previous two entries
+}
+
+void AsmPrinter::emitXRayTable() {
+  if (Sleds.empty())
+    return;
+
+  auto PrevSection = OutStreamer->getCurrentSectionOnly();
+  auto Fn = MF->getFunction();
+  MCSection *Section = nullptr;
+  if (MF->getSubtarget().getTargetTriple().isOSBinFormatELF()) {
+    if (Fn->hasComdat()) {
+      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
+                                         ELF::SHF_ALLOC | ELF::SHF_GROUP, 0,
+                                         Fn->getComdat()->getName());
+    } else {
+      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
+                                         ELF::SHF_ALLOC);
+    }
+  } else if (MF->getSubtarget().getTargetTriple().isOSBinFormatMachO()) {
+    Section = OutContext.getMachOSection("__DATA", "xray_instr_map", 0,
+                                         SectionKind::getReadOnlyWithRel());
+  } else {
+    llvm_unreachable("Unsupported target");
+  }
+
+  // Before we switch over, we force a reference to a label inside the
+  // xray_instr_map section. Since this function is always called just
+  // before the function's end, we assume that this is happening after
+  // the last return instruction.
+
+  auto WordSizeBytes = TM.getPointerSize();
+  MCSymbol *Tmp = OutContext.createTempSymbol("xray_synthetic_", true);
+  OutStreamer->EmitCodeAlignment(16);
+  OutStreamer->EmitSymbolValue(Tmp, WordSizeBytes, false);
+  OutStreamer->SwitchSection(Section);
+  OutStreamer->EmitLabel(Tmp);
+  for (const auto &Sled : Sleds)
+    Sled.emit(WordSizeBytes, OutStreamer.get(), CurrentFnSym);
+
+  OutStreamer->SwitchSection(PrevSection);
+  Sleds.clear();
+}
+
 void AsmPrinter::recordSled(MCSymbol *Sled, const MachineInstr &MI,
   SledKind Kind) {
   auto Fn = MI.getParent()->getParent()->getFunction();
   auto Attr = Fn->getFnAttribute("function-instrument");
   bool AlwaysInstrument =
     Attr.isStringAttribute() && Attr.getValueAsString() == "xray-always";
   Sleds.emplace_back(
     XRayFunctionEntry{ Sled, CurrentFnSym, Kind, AlwaysInstrument, Fn });

lib/Target/AArch64/AArch64AsmPrinter.cpp

void LowerSTACKMAP(MCStreamer &OutStreamer, StackMaps &SM,
                      const MachineInstr &MI);
   void LowerPATCHPOINT(MCStreamer &OutStreamer, StackMaps &SM,
                        const MachineInstr &MI);
 
   void LowerPATCHABLE_FUNCTION_ENTER(const MachineInstr &MI);
   void LowerPATCHABLE_FUNCTION_EXIT(const MachineInstr &MI);
   void LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI);
 
-  void EmitXRayTable();
   void EmitSled(const MachineInstr &MI, SledKind Kind);
 
   /// \brief tblgen'erated driver function for lowering simple MI->MC
   /// pseudo instructions.
   bool emitPseudoExpansionLowering(MCStreamer &OutStreamer,
                                    const MachineInstr *MI);
 
   void EmitInstruction(const MachineInstr *MI) override;
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AsmPrinter::getAnalysisUsage(AU);
     AU.setPreservesAll();
   }
 
   bool runOnMachineFunction(MachineFunction &F) override {
     AArch64FI = F.getInfo<AArch64FunctionInfo>();
     STI = static_cast<const AArch64Subtarget*>(&F.getSubtarget());
     bool Result = AsmPrinter::runOnMachineFunction(F);
-    EmitXRayTable();
+    emitXRayTable();
     return Result;
   }
 
 private:
   void printOperand(const MachineInstr *MI, unsigned OpNum, raw_ostream &O);
   bool printAsmMRegister(const MachineOperand &MO, char Mode, raw_ostream &O);
   bool printAsmRegInClass(const MachineOperand &MO,
                           const TargetRegisterClass *RC, bool isVector,
void AArch64AsmPrinter::LowerPATCHABLE_FUNCTION_EXIT(const MachineInstr &MI)
   EmitSled(MI, SledKind::FUNCTION_EXIT);
 }
 
 void AArch64AsmPrinter::LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI)
 {
   EmitSled(MI, SledKind::TAIL_CALL);
 }
 
-void AArch64AsmPrinter::EmitXRayTable()
-{
-  //TODO: merge the logic for ELF XRay sleds at a higher level, so to avoid
-  // code duplication as it is now for x86_64, ARM32 and AArch64.
-  if (Sleds.empty())
-    return;
-
-  auto PrevSection = OutStreamer->getCurrentSectionOnly();
-  auto Fn = MF->getFunction();
-  MCSection *Section;
-
-  if (STI->isTargetELF()) {
-    if (Fn->hasComdat())
-      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
-        ELF::SHF_ALLOC | ELF::SHF_GROUP, 0,
-        Fn->getComdat()->getName());
-    else
-      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
-        ELF::SHF_ALLOC);
-  } else if (STI->isTargetMachO()) {
-    Section = OutContext.getMachOSection("__DATA", "xray_instr_map", 0,
-                                         SectionKind::getReadOnlyWithRel());
-  } else {
-    llvm_unreachable("Unsupported target");
-  }
-
-  // Before we switch over, we force a reference to a label inside the
-  // xray_instr_map section. Since EmitXRayTable() is always called just
-  // before the function's end, we assume that this is happening after the
-  // last return instruction.
-  //
-  // We then align the reference to 16 byte boundaries, which we determined
-  // experimentally to be beneficial to avoid causing decoder stalls.
-  MCSymbol *Tmp = OutContext.createTempSymbol("xray_synthetic_", true);
-  OutStreamer->EmitCodeAlignment(16);
-  OutStreamer->EmitSymbolValue(Tmp, 8, false);
-  OutStreamer->SwitchSection(Section);
-  OutStreamer->EmitLabel(Tmp);
-  for (const auto &Sled : Sleds) {
-    OutStreamer->EmitSymbolValue(Sled.Sled, 8);
-    OutStreamer->EmitSymbolValue(CurrentFnSym, 8);
-    auto Kind = static_cast<uint8_t>(Sled.Kind);
-    OutStreamer->EmitBytes(
-      StringRef(reinterpret_cast<const char *>(&Kind), 1));
-    OutStreamer->EmitBytes(
-      StringRef(reinterpret_cast<const char *>(&Sled.AlwaysInstrument), 1));
-    OutStreamer->EmitZeros(14);
-  }
-  OutStreamer->SwitchSection(PrevSection);
-
-  Sleds.clear();
-}
-
 void AArch64AsmPrinter::EmitSled(const MachineInstr &MI, SledKind Kind)
 {
   static const int8_t NoopsInSledCount = 7;
   // We want to emit the following pattern:
   //
   // .Lxray_sled_N:
   //   ALIGN
   //   B #32

lib/Target/ARM/ARMAsmPrinter.h

public:
   //===------------------------------------------------------------------===//
   // XRay implementation
   //===------------------------------------------------------------------===//
 public:
   // XRay-specific lowering for ARM.
   void LowerPATCHABLE_FUNCTION_ENTER(const MachineInstr &MI);
   void LowerPATCHABLE_FUNCTION_EXIT(const MachineInstr &MI);
   void LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI);
-  // Helper function that emits the XRay sleds we've collected for a particular
-  // function.
-  void EmitXRayTable();
 
 private:
   void EmitSled(const MachineInstr &MI, SledKind Kind);
 
   // Helpers for EmitStartOfAsmFile() and EmitEndOfAsmFile()
   void emitAttributes();
 
   // Generic helper used to emit e.g. ARMv5 mul pseudos

lib/Target/ARM/ARMAsmPrinter.cpp

if (Subtarget->isTargetCOFF()) {
     OutStreamer->EmitCOFFSymbolStorageClass(Scl);
     OutStreamer->EmitCOFFSymbolType(Type);
     OutStreamer->EndCOFFSymbolDef();
   }
 
   // Emit the rest of the function body.
   EmitFunctionBody();
 
-  // Emit the XRay table for this function.
-  EmitXRayTable();
-
   // If we need V4T thumb mode Register Indirect Jump pads, emit them.
   // These are created per function, rather than per TU, since it's
   // relatively easy to exceed the thumb branch range within a TU.
   if (! ThumbIndirectPads.empty()) {
     OutStreamer->EmitAssemblerFlag(MCAF_Code16);
     EmitAlignment(1);
     for (unsigned i = 0, e = ThumbIndirectPads.size(); i < e; i++) {
       OutStreamer->EmitLabel(ThumbIndirectPads[i].second);

lib/Target/ARM/ARMMCInstLower.cpp

 #include "MCTargetDesc/ARMBaseInfo.h"
 #include "MCTargetDesc/ARMMCExpr.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Mangler.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCContext.h"
-#include "llvm/MC/MCSymbolELF.h"
-#include "llvm/MC/MCSectionELF.h"
-#include "llvm/MC/MCSectionMachO.h"
 #include "llvm/MC/MCInstBuilder.h"
 #include "llvm/MC/MCStreamer.h"
 using namespace llvm;
 
 
 MCOperand ARMAsmPrinter::GetSymbolRef(const MachineOperand &MO,
                                       const MCSymbol *Symbol) {
   const MCExpr *Expr =

 {
   EmitSled(MI, SledKind::FUNCTION_EXIT);
 }
 
 void ARMAsmPrinter::LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI)
 {
   EmitSled(MI, SledKind::TAIL_CALL);
 }
-
-void ARMAsmPrinter::EmitXRayTable()
-{
-  if (Sleds.empty())
-    return;
-
-  MCSection *Section = nullptr;
-  if (Subtarget->isTargetELF()) {
-    Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
-                                       ELF::SHF_ALLOC | ELF::SHF_GROUP |
-                                           ELF::SHF_MERGE,
-                                       0, CurrentFnSym->getName());
-  } else if (Subtarget->isTargetMachO()) {
-    Section = OutContext.getMachOSection("__DATA", "xray_instr_map", 0,
-                                         SectionKind::getReadOnlyWithRel());
-  } else {
-    llvm_unreachable("Unsupported target");
-  }
-
-  auto PrevSection = OutStreamer->getCurrentSectionOnly();
-  OutStreamer->SwitchSection(Section);
-  for (const auto &Sled : Sleds) {
-    OutStreamer->EmitSymbolValue(Sled.Sled, 4);
-    OutStreamer->EmitSymbolValue(CurrentFnSym, 4);
-    auto Kind = static_cast<uint8_t>(Sled.Kind);
-    OutStreamer->EmitBytes(
-      StringRef(reinterpret_cast<const char *>(&Kind), 1));
-    OutStreamer->EmitBytes(
-      StringRef(reinterpret_cast<const char *>(&Sled.AlwaysInstrument), 1));
-    OutStreamer->EmitZeros(6);
-  }
-  OutStreamer->SwitchSection(PrevSection);
-
-  Sleds.clear();
-}

lib/Target/X86/X86AsmPrinter.cpp

OutStreamer->EmitCOFFSymbolType(COFF::IMAGE_SYM_DTYPE_FUNCTION
                                                << COFF::SCT_COMPLEX_TYPE_SHIFT);
     OutStreamer->EndCOFFSymbolDef();
   }
 
   // Emit the rest of the function body.
   EmitFunctionBody();
 
   // Emit the XRay table for this function.
-  EmitXRayTable();
+  emitXRayTable();
 
   // We didn't modify anything.
   return false;
 }
 
 /// printSymbolOperand - Print a raw symbol reference operand.  This handles
 /// jump tables, constant pools, global address and external symbols, all of
 /// which print to a label with various suffixes for relocation types etc.

lib/Target/X86/X86MCInstLower.cpp

void X86AsmPrinter::LowerPATCHABLE_TAIL_CALL(const MachineInstr &MI, X86MCInstLower &MCIL) {
   // indeed a tail call.
   OutStreamer->AddComment("TAILCALL");
   for (auto &MO : make_range(MI.operands_begin() + 1, MI.operands_end()))
     if (auto MaybeOperand = MCIL.LowerMachineOperand(&MI, MO))
       TC.addOperand(MaybeOperand.getValue());
   OutStreamer->EmitInstruction(TC, getSubtargetInfo());
 }
 
-void X86AsmPrinter::EmitXRayTable() {
-  if (Sleds.empty())
-    return;
-  
-  auto PrevSection = OutStreamer->getCurrentSectionOnly();
-  auto Fn = MF->getFunction();
-  MCSection *Section = nullptr;
-  if (Subtarget->isTargetELF()) {
-    if (Fn->hasComdat()) {
-      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
-                                         ELF::SHF_ALLOC | ELF::SHF_GROUP, 0,
-                                         Fn->getComdat()->getName());
-    } else {
-      Section = OutContext.getELFSection("xray_instr_map", ELF::SHT_PROGBITS,
-                                         ELF::SHF_ALLOC);
-    }
-  } else if (Subtarget->isTargetMachO()) {
-    Section = OutContext.getMachOSection("__DATA", "xray_instr_map", 0,
-                                         SectionKind::getReadOnlyWithRel());
-  } else {
-    llvm_unreachable("Unsupported target");
-  }
-
-  // Before we switch over, we force a reference to a label inside the
-  // xray_instr_map section. Since EmitXRayTable() is always called just
-  // before the function's end, we assume that this is happening after the
-  // last return instruction.
-  //
-  // We then align the reference to 16 byte boundaries, which we determined
-  // experimentally to be beneficial to avoid causing decoder stalls.
-  MCSymbol *Tmp = OutContext.createTempSymbol("xray_synthetic_", true);
-  OutStreamer->EmitCodeAlignment(16);
-  OutStreamer->EmitSymbolValue(Tmp, 8, false);
-  OutStreamer->SwitchSection(Section);
-  OutStreamer->EmitLabel(Tmp);
-  for (const auto &Sled : Sleds) {
-    OutStreamer->EmitSymbolValue(Sled.Sled, 8);
-    OutStreamer->EmitSymbolValue(CurrentFnSym, 8);
-    auto Kind = static_cast<uint8_t>(Sled.Kind);
-    OutStreamer->EmitBytes(
-        StringRef(reinterpret_cast<const char *>(&Kind), 1));
-    OutStreamer->EmitBytes(
-        StringRef(reinterpret_cast<const char *>(&Sled.AlwaysInstrument), 1));
-    OutStreamer->EmitZeros(14);
-  }
-  OutStreamer->SwitchSection(PrevSection);
-
-  Sleds.clear();
-}
-
 // Returns instruction preceding MBBI in MachineFunction.
 // If MBBI is the first instruction of the first basic block, returns null.
 static MachineBasicBlock::const_iterator
 PrevCrossBBInst(MachineBasicBlock::const_iterator MBBI) {
   const MachineBasicBlock *MBB = MBBI->getParent();
   while (MBBI == MBB->begin()) {
     if (MBB == &MBB->getParent()->front())
       return MachineBasicBlock::const_iterator();