[llvm][AsmPrinter] Emit call graph section

llvm/include/llvm/CodeGen/AsmPrinter.h

@@ -190,6 +190,36 @@ class LLVM_ABI AsmPrinter : public MachineFunctionPass {
   /// Emit comments in assembly output if this is true.
   bool VerboseAsm;
 
+  /// Store symbols and type identifiers used to create call graph section
+  /// entries related to a function.
+  struct FunctionInfo {
+    /// Numeric type identifier used in call graph section for indirect calls
+    /// and targets.
+    using CGTypeId = uint64_t;
+
+    /// Enumeration of function kinds, and their mapping to function kind values
+    /// stored in call graph section entries.
+    /// Must match the enum in llvm/tools/llvm-objdump/llvm-objdump.cpp.
+    enum class FunctionKind : uint64_t {
+      /// Function cannot be target to indirect calls.
+      NOT_INDIRECT_TARGET = 0,
+
+      /// Function may be target to indirect calls but its type id is unknown.
+      INDIRECT_TARGET_UNKNOWN_TID = 1,
+
+      /// Function may be target to indirect calls and its type id is known.
+      INDIRECT_TARGET_KNOWN_TID = 2,
+    };
+
+    /// Map type identifiers to callsite labels. Labels are only for indirect
+    /// calls and inclusive of all indirect calls of the function.
+    SmallVector<std::pair<CGTypeId, MCSymbol *>> CallSiteLabels;
+  };
+
+  enum CallGraphSectionFormatVersion : uint64_t {
+    V_0 = 0,
+  };
+
   /// Output stream for the stack usage file (i.e., .su file).
   std::unique_ptr<raw_fd_ostream> StackUsageStream;
 
@@ -355,6 +385,13 @@ class LLVM_ABI AsmPrinter : public MachineFunctionPass {
   /// are available. Returns empty string otherwise.
   StringRef getConstantSectionSuffix(const Constant *C) const;
 
+  /// Generate and emit labels for callees of the indirect callsites which will
+  /// be used to populate the .callgraph section.
+  void emitIndirectCalleeLabels(
+      FunctionInfo &FuncInfo,
+      const MachineFunction::CallSiteInfoMap &CallSitesInfoMap,
+      const MachineInstr &MI);
+
   //===------------------------------------------------------------------===//
   // XRay instrumentation implementation.
   //===------------------------------------------------------------------===//
@@ -442,6 +479,8 @@ class LLVM_ABI AsmPrinter : public MachineFunctionPass {
   void emitKCFITrapEntry(const MachineFunction &MF, const MCSymbol *Symbol);
   virtual void emitKCFITypeId(const MachineFunction &MF);
 
+  void emitCallGraphSection(const MachineFunction &MF, FunctionInfo &FuncInfo);
+
   void emitPseudoProbe(const MachineInstr &MI);
 
   void emitRemarksSection(remarks::RemarkStreamer &RS);

llvm/include/llvm/CodeGen/CommandFlags.h

@@ -133,6 +133,8 @@ LLVM_ABI bool getEnableStackSizeSection();
 
 LLVM_ABI bool getEnableAddrsig();
 
+LLVM_ABI bool getEnableCallGraphSection();
+
 LLVM_ABI bool getEmitCallSiteInfo();
 
 LLVM_ABI bool getEnableMachineFunctionSplitter();

llvm/include/llvm/CodeGen/MIRYamlMapping.h

@@ -482,6 +482,8 @@ struct CallSiteInfo {
 
   MachineInstrLoc CallLocation;
   std::vector<ArgRegPair> ArgForwardingRegs;
+  /// Numeric callee type identifiers for the callgraph section.
+  std::vector<uint64_t> CalleeTypeIds;
 
   bool operator==(const CallSiteInfo &Other) const {
     return CallLocation.BlockNum == Other.CallLocation.BlockNum &&
@@ -511,6 +513,7 @@ template <> struct MappingTraits<CallSiteInfo> {
     YamlIO.mapRequired("offset", CSInfo.CallLocation.Offset);
     YamlIO.mapOptional("fwdArgRegs", CSInfo.ArgForwardingRegs,
                        std::vector<CallSiteInfo::ArgRegPair>());
+    YamlIO.mapOptional("calleeTypeIds", CSInfo.CalleeTypeIds);
   }
 
   static const bool flow = true;

llvm/include/llvm/CodeGen/MachineFunction.h

@@ -26,11 +26,14 @@
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineMemOperand.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/IR/EHPersonalities.h"
+#include "llvm/IR/Instructions.h"
 #include "llvm/Support/Allocator.h"
 #include "llvm/Support/ArrayRecycler.h"
 #include "llvm/Support/AtomicOrdering.h"
 #include "llvm/Support/Compiler.h"
+#include "llvm/Support/MD5.h"
 #include "llvm/Support/Recycler.h"
 #include "llvm/Target/TargetOptions.h"
 #include <bitset>
@@ -515,18 +518,47 @@ class LLVM_ABI MachineFunction {
   struct CallSiteInfo {
     /// Vector of call argument and its forwarding register.
     SmallVector<ArgRegPair, 1> ArgRegPairs;
+    /// Callee type ids.
+    SmallVector<ConstantInt *, 4> CalleeTypeIds;
+
+    CallSiteInfo() = default;
+
+    /// Extracts the numeric type id from the CallBase's callee_type Metadata,
+    /// and sets CalleeTypeIds. This is used as type id for the indirect call in
+    /// the call graph section.
+    CallSiteInfo(const CallBase &CB) {
+      // Call graph section needs numeric callee_type id only for indirect
+      // calls.
+      if (!CB.isIndirectCall())
+        return;
+
+      MDNode *CalleeTypeList = CB.getMetadata(LLVMContext::MD_callee_type);
+      if (!CalleeTypeList)
+        return;
+
+      for (const MDOperand &Op : CalleeTypeList->operands()) {
+        MDNode *TypeMD = cast<MDNode>(Op);
+        MDString *TypeIdStr = cast<MDString>(TypeMD->getOperand(1));
+        // Compute numeric type id from generalized type id string
+        uint64_t TypeIdVal = MD5Hash(TypeIdStr->getString());
+        IntegerType *Int64Ty = Type::getInt64Ty(CB.getContext());
+        CalleeTypeIds.push_back(
+            ConstantInt::get(Int64Ty, TypeIdVal, /*IsSigned=*/false));
+      }
+    }
   };
 
   struct CalledGlobalInfo {
     const GlobalValue *Callee;
     unsigned TargetFlags;
   };
 
+  using CallSiteInfoMap = DenseMap<const MachineInstr *, CallSiteInfo>;
+
 private:
   Delegate *TheDelegate = nullptr;
   GISelChangeObserver *Observer = nullptr;
 
-  using CallSiteInfoMap = DenseMap<const MachineInstr *, CallSiteInfo>;
   /// Map a call instruction to call site arguments forwarding info.
   CallSiteInfoMap CallSitesInfo;
 

llvm/include/llvm/MC/MCObjectFileInfo.h

@@ -69,6 +69,9 @@ class LLVM_ABI MCObjectFileInfo {
   /// Language Specific Data Area information is emitted to.
   MCSection *LSDASection = nullptr;
 
+  /// Section containing call graph metadata.
+  MCSection *CallGraphSection = nullptr;
+
   /// If exception handling is supported by the target and the target can
   /// support a compact representation of the CIE and FDE, this is the section
   /// to emit them into.
@@ -359,6 +362,8 @@ class LLVM_ABI MCObjectFileInfo {
   MCSection *getFaultMapSection() const { return FaultMapSection; }
   MCSection *getRemarksSection() const { return RemarksSection; }
 
+  MCSection *getCallGraphSection(const MCSection &TextSec) const;
+
   MCSection *getStackSizesSection(const MCSection &TextSec) const;
 
   MCSection *getBBAddrMapSection(const MCSection &TextSec) const;

llvm/include/llvm/Target/TargetOptions.h

@@ -133,10 +133,11 @@ class TargetOptions {
         EmitStackSizeSection(false), EnableMachineOutliner(false),
         EnableMachineFunctionSplitter(false),
         EnableStaticDataPartitioning(false), SupportsDefaultOutlining(false),
-        EmitAddrsig(false), BBAddrMap(false), EmitCallSiteInfo(false),
-        SupportsDebugEntryValues(false), EnableDebugEntryValues(false),
-        ValueTrackingVariableLocations(false), ForceDwarfFrameSection(false),
-        XRayFunctionIndex(true), DebugStrictDwarf(false), Hotpatch(false),
+        EmitAddrsig(false), BBAddrMap(false), EmitCallGraphSection(false),
+        EmitCallSiteInfo(false), SupportsDebugEntryValues(false),
+        EnableDebugEntryValues(false), ValueTrackingVariableLocations(false),
+        ForceDwarfFrameSection(false), XRayFunctionIndex(true),
+        DebugStrictDwarf(false), Hotpatch(false),
         PPCGenScalarMASSEntries(false), JMCInstrument(false),
         EnableCFIFixup(false), MisExpect(false), XCOFFReadOnlyPointers(false),
         VerifyArgABICompliance(true),
@@ -319,6 +320,9 @@ class TargetOptions {
   /// to selectively generate basic block sections.
   std::shared_ptr<MemoryBuffer> BBSectionsFuncListBuf;
 
+  /// Emit section containing call graph metadata.
+  unsigned EmitCallGraphSection : 1;
+
   /// The flag enables call site info production. It is used only for debug
   /// info, and it is restricted only to optimized code. This can be used for
   /// something else, so that should be controlled in the frontend.

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -1654,6 +1654,88 @@ void AsmPrinter::emitStackUsage(const MachineFunction &MF) {
     *StackUsageStream << "static\n";
 }
 
+/// Extracts a generalized numeric type identifier of a Function's type from
+/// type metadata. Returns null if metadata cannot be found.
+static ConstantInt *extractNumericCGTypeId(const Function &F) {
+  SmallVector<MDNode *, 2> Types;
+  F.getMetadata(LLVMContext::MD_type, Types);
+  for (const auto &Type : Types) {
+    if (Type->hasGeneralizedMDString()) {
+      MDString *MDGeneralizedTypeId = cast<MDString>(Type->getOperand(1));
+      uint64_t TypeIdVal = llvm::MD5Hash(MDGeneralizedTypeId->getString());
+      IntegerType *Int64Ty = Type::getInt64Ty(F.getContext());
+      return ConstantInt::get(Int64Ty, TypeIdVal);
+    }
+  }
+  return nullptr;
+}
+
+/// Emits .callgraph section.
+void AsmPrinter::emitCallGraphSection(const MachineFunction &MF,
+                                      FunctionInfo &FuncInfo) {
+  if (!MF.getTarget().Options.EmitCallGraphSection)
+    return;
+
+  // Switch to the call graph section for the function
+  MCSection *FuncCGSection =
+      getObjFileLowering().getCallGraphSection(*getCurrentSection());
+  assert(FuncCGSection && "null callgraph section");
+  OutStreamer->pushSection();
+  OutStreamer->switchSection(FuncCGSection);
+
+  // Emit format version number.
+  OutStreamer->emitInt64(CallGraphSectionFormatVersion::V_0);
+
+  // Emit function's self information, which is composed of:
+  //  1) FunctionEntryPc
+  //  2) FunctionKind: Whether the function is indirect target, and if so,
+  //     whether its type id is known.
+  //  3) FunctionTypeId: Emit only when the function is an indirect target
+  //     and its type id is known.
+
+  // Emit function entry pc.
+  const MCSymbol *FunctionSymbol = getFunctionBegin();
+  OutStreamer->emitSymbolValue(FunctionSymbol, TM.getProgramPointerSize());
+
+  // If this function has external linkage or has its address taken and
+  // it is not a callback, then anything could call it.
+  const Function &F = MF.getFunction();
+  bool IsIndirectTarget =
+      !F.hasLocalLinkage() || F.hasAddressTaken(nullptr,
+                                                /*IgnoreCallbackUses=*/true,
+                                                /*IgnoreAssumeLikeCalls=*/true,
+                                                /*IgnoreLLVMUsed=*/false);
+
+  // FIXME: FunctionKind takes a few values but emitted as a 64-bit value.
+  // Can be optimized to occupy 2 bits instead.
+  // Emit function kind, and type id if available.
+  if (!IsIndirectTarget) {
+    OutStreamer->emitInt64(
+        static_cast<uint64_t>(FunctionInfo::FunctionKind::NOT_INDIRECT_TARGET));
+  } else {
+    if (const auto *TypeId = extractNumericCGTypeId(F)) {
+      OutStreamer->emitInt64(static_cast<uint64_t>(
+          FunctionInfo::FunctionKind::INDIRECT_TARGET_KNOWN_TID));
+      OutStreamer->emitInt64(TypeId->getZExtValue());
+    } else {
+      OutStreamer->emitInt64(static_cast<uint64_t>(
+          FunctionInfo::FunctionKind::INDIRECT_TARGET_UNKNOWN_TID));
+    }
+  }
+
+  // Emit callsite labels, where each element is a pair of type id and
+  // indirect callsite pc.
+  const auto &CallSiteLabels = FuncInfo.CallSiteLabels;
+  OutStreamer->emitInt64(CallSiteLabels.size());
+  for (const auto &[TypeId, Label] : CallSiteLabels) {
+    OutStreamer->emitInt64(TypeId);
+    OutStreamer->emitSymbolValue(Label, TM.getProgramPointerSize());
+  }
+  FuncInfo.CallSiteLabels.clear();
+
+  OutStreamer->popSection();
+}
+
 void AsmPrinter::emitPCSectionsLabel(const MachineFunction &MF,
                                      const MDNode &MD) {
   MCSymbol *S = MF.getContext().createTempSymbol("pcsection");
@@ -1784,6 +1866,23 @@ static StringRef getMIMnemonic(const MachineInstr &MI, MCStreamer &Streamer) {
   return Name;
 }
 
+void AsmPrinter::emitIndirectCalleeLabels(
+    FunctionInfo &FuncInfo,
+    const MachineFunction::CallSiteInfoMap &CallSitesInfoMap,
+    const MachineInstr &MI) {
+  // Only indirect calls have type identifiers set.
+  const auto &CallSiteInfo = CallSitesInfoMap.find(&MI);
+  if (CallSiteInfo == CallSitesInfoMap.end())
+    return;
+
+  for (ConstantInt *CalleeTypeId : CallSiteInfo->second.CalleeTypeIds) {
+    MCSymbol *S = MF->getContext().createTempSymbol();
+    OutStreamer->emitLabel(S);
+    uint64_t CalleeTypeIdVal = CalleeTypeId->getZExtValue();
+    FuncInfo.CallSiteLabels.emplace_back(CalleeTypeIdVal, S);
+  }
+}
+
 /// EmitFunctionBody - This method emits the body and trailer for a
 /// function.
 void AsmPrinter::emitFunctionBody() {
@@ -1830,6 +1929,8 @@ void AsmPrinter::emitFunctionBody() {
     MBBSectionRanges[MF->front().getSectionID()] =
         MBBSectionRange{CurrentFnBegin, nullptr};
 
+  FunctionInfo FuncInfo;
+  const auto &CallSitesInfoMap = MF->getCallSitesInfo();
   for (auto &MBB : *MF) {
     // Print a label for the basic block.
     emitBasicBlockStart(MBB);
@@ -1963,6 +2064,9 @@ void AsmPrinter::emitFunctionBody() {
         break;
       }
 
+      if (TM.Options.EmitCallGraphSection && MI.isCall())
+        emitIndirectCalleeLabels(FuncInfo, CallSitesInfoMap, MI);
+
       // If there is a post-instruction symbol, emit a label for it here.
       if (MCSymbol *S = MI.getPostInstrSymbol())
         OutStreamer->emitLabel(S);
@@ -2142,6 +2246,9 @@ void AsmPrinter::emitFunctionBody() {
   // Emit section containing stack size metadata.
   emitStackSizeSection(*MF);
 
+  // Emit section containing call graph metadata.
+  emitCallGraphSection(*MF, FuncInfo);
+
   // Emit .su file containing function stack size information.
   emitStackUsage(*MF);
 
@@ -2841,6 +2948,7 @@ void AsmPrinter::SetupMachineFunction(MachineFunction &MF) {
       F.hasFnAttribute("xray-instruction-threshold") ||
       needFuncLabels(MF, *this) || NeedsLocalForSize ||
       MF.getTarget().Options.EmitStackSizeSection ||
+      MF.getTarget().Options.EmitCallGraphSection ||
       MF.getTarget().Options.BBAddrMap) {
     CurrentFnBegin = createTempSymbol("func_begin");
     if (NeedsLocalForSize)

llvm/lib/CodeGen/CommandFlags.cpp

@@ -101,6 +101,7 @@ CGOPT(EABI, EABIVersion)
 CGOPT(DebuggerKind, DebuggerTuningOpt)
 CGOPT(bool, EnableStackSizeSection)
 CGOPT(bool, EnableAddrsig)
+CGOPT(bool, EnableCallGraphSection)
 CGOPT(bool, EmitCallSiteInfo)
 CGOPT(bool, EnableMachineFunctionSplitter)
 CGOPT(bool, EnableStaticDataPartitioning)
@@ -461,6 +462,11 @@ codegen::RegisterCodeGenFlags::RegisterCodeGenFlags() {
       cl::init(false));
   CGBINDOPT(EnableAddrsig);
 
+  static cl::opt<bool> EnableCallGraphSection(
+      "call-graph-section", cl::desc("Emit a call graph section"),
+      cl::init(false));
+  CGBINDOPT(EnableCallGraphSection);
+
   static cl::opt<bool> EmitCallSiteInfo(
       "emit-call-site-info",
       cl::desc(
@@ -595,6 +601,7 @@ codegen::InitTargetOptionsFromCodeGenFlags(const Triple &TheTriple) {
   Options.EnableMachineFunctionSplitter = getEnableMachineFunctionSplitter();
   Options.EnableStaticDataPartitioning = getEnableStaticDataPartitioning();
   Options.EmitAddrsig = getEnableAddrsig();
+  Options.EmitCallGraphSection = getEnableCallGraphSection();
   Options.EmitCallSiteInfo = getEmitCallSiteInfo();
   Options.EnableDebugEntryValues = getEnableDebugEntryValues();
   Options.ForceDwarfFrameSection = getForceDwarfFrameSection();

llvm/lib/CodeGen/MIRParser/MIRParser.cpp

@@ -504,13 +504,21 @@ bool MIRParserImpl::initializeCallSiteInfo(
         return error(Error, ArgRegPair.Reg.SourceRange);
       CSInfo.ArgRegPairs.emplace_back(Reg, ArgRegPair.ArgNo);
     }
+    if (!YamlCSInfo.CalleeTypeIds.empty()) {
+      for (auto CalleeTypeId : YamlCSInfo.CalleeTypeIds) {
+        IntegerType *Int64Ty = Type::getInt64Ty(Context);
+        CSInfo.CalleeTypeIds.push_back(ConstantInt::get(Int64Ty, CalleeTypeId,
+                                                        /*isSigned=*/false));
+      }
+    }
 
-    if (TM.Options.EmitCallSiteInfo)
+    if (TM.Options.EmitCallSiteInfo || TM.Options.EmitCallGraphSection)
       MF.addCallSiteInfo(&*CallI, std::move(CSInfo));
   }
 
-  if (YamlMF.CallSitesInfo.size() && !TM.Options.EmitCallSiteInfo)
-    return error(Twine("Call site info provided but not used"));
+  if (!YamlMF.CallSitesInfo.empty() &&
+      !(TM.Options.EmitCallSiteInfo || TM.Options.EmitCallGraphSection))
+    return error("call site info provided but not used");
   return false;
 }