[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/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>
@@ -517,18 +520,45 @@ class LLVM_ABI MachineFunction {
     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/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/SelectionDAG/ScheduleDAGSDNodes.cpp

@@ -888,7 +888,8 @@ EmitSchedule(MachineBasicBlock::iterator &InsertPos) {
     }
 
     if (MI->isCandidateForAdditionalCallInfo()) {
-      if (DAG->getTarget().Options.EmitCallSiteInfo)
+      if (DAG->getTarget().Options.EmitCallSiteInfo ||
+          DAG->getTarget().Options.EmitCallGraphSection)
         MF.addCallSiteInfo(MI, DAG->getCallSiteInfo(Node));
 
       if (auto CalledGlobal = DAG->getCalledGlobal(Node))

llvm/lib/MC/MCObjectFileInfo.cpp

@@ -537,6 +537,8 @@ void MCObjectFileInfo::initELFMCObjectFileInfo(const Triple &T, bool Large) {
   EHFrameSection =
       Ctx->getELFSection(".eh_frame", EHSectionType, EHSectionFlags);
 
+  CallGraphSection = Ctx->getELFSection(".callgraph", ELF::SHT_PROGBITS, 0);
+
   StackSizesSection = Ctx->getELFSection(".stack_sizes", ELF::SHT_PROGBITS, 0);
 
   PseudoProbeSection = Ctx->getELFSection(".pseudo_probe", DebugSecType, 0);
@@ -1120,6 +1122,24 @@ MCSection *MCObjectFileInfo::getDwarfComdatSection(const char *Name,
   llvm_unreachable("Unknown ObjectFormatType");
 }
 
+MCSection *
+MCObjectFileInfo::getCallGraphSection(const MCSection &TextSec) const {
+  if (Ctx->getObjectFileType() != MCContext::IsELF)
+    return CallGraphSection;
+
+  const MCSectionELF &ElfSec = static_cast<const MCSectionELF &>(TextSec);
+  unsigned Flags = ELF::SHF_LINK_ORDER;
+  StringRef GroupName;
+  if (const MCSymbol *Group = ElfSec.getGroup()) {
+    GroupName = Group->getName();
+    Flags |= ELF::SHF_GROUP;
+  }
+
+  return Ctx->getELFSection(".callgraph", ELF::SHT_PROGBITS, Flags, 0,
+                            GroupName, true, ElfSec.getUniqueID(),
+                            cast<MCSymbolELF>(TextSec.getBeginSymbol()));
+}
+
 MCSection *
 MCObjectFileInfo::getStackSizesSection(const MCSection &TextSec) const {
   if ((Ctx->getObjectFileType() != MCContext::IsELF) ||

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -8952,6 +8952,7 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
   bool &IsTailCall = CLI.IsTailCall;
   CallingConv::ID &CallConv = CLI.CallConv;
   bool IsVarArg = CLI.IsVarArg;
+  const CallBase *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   MachineFunction::CallSiteInfo CSInfo;
@@ -8991,6 +8992,10 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
                     *DAG.getContext());
   RetCCInfo.AnalyzeCallResult(Ins, RetCC);
 
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
+
   // Check callee args/returns for SVE registers and set calling convention
   // accordingly.
   if (CallConv == CallingConv::C || CallConv == CallingConv::Fast) {

llvm/lib/Target/ARM/ARMISelLowering.cpp

@@ -2423,6 +2423,7 @@ ARMTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   CallingConv::ID CallConv              = CLI.CallConv;
   bool doesNotRet                       = CLI.DoesNotReturn;
   bool isVarArg                         = CLI.IsVarArg;
+  const CallBase *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
@@ -2446,6 +2447,10 @@ ARMTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       !Subtarget->noBTIAtReturnTwice())
     GuardWithBTI = AFI->branchTargetEnforcement();
 
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
+
   // Determine whether this is a non-secure function call.
   if (CLI.CB && CLI.CB->getAttributes().hasFnAttr("cmse_nonsecure_call"))
     isCmseNSCall = true;

llvm/lib/Target/Mips/MipsISelLowering.cpp

@@ -3341,6 +3341,7 @@ MipsTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   bool &IsTailCall                      = CLI.IsTailCall;
   CallingConv::ID CallConv              = CLI.CallConv;
   bool IsVarArg                         = CLI.IsVarArg;
+  const CallBase *CB = CLI.CB;
 
   MachineFunction &MF = DAG.getMachineFunction();
   MachineFrameInfo &MFI = MF.getFrameInfo();
@@ -3397,8 +3398,11 @@ MipsTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   // Get a count of how many bytes are to be pushed on the stack.
   unsigned StackSize = CCInfo.getStackSize();
 
-  // Call site info for function parameters tracking.
+  // Call site info for function parameters tracking and call base type info.
   MachineFunction::CallSiteInfo CSInfo;
+  // Set type id for call site info.
+  if (MF.getTarget().Options.EmitCallGraphSection && CB && CB->isIndirectCall())
+    CSInfo = MachineFunction::CallSiteInfo(*CB);
 
   // Check if it's really possible to do a tail call. Restrict it to functions
   // that are part of this compilation unit.