[clang] All Clang Changes

This patch adds clang CodeGen option to emit callgraph section.
The `-fcall-graph-section` Driver flag is introduced to control
the `CallGraphSection` CodeGen option.

Author: Prabhuk

clang/include/clang/Basic/CodeGenOptions.def

@@ -72,6 +72,8 @@ CODEGENOPT(EnableNoundefAttrs, 1, 0, Benign) ///< Enable emitting `noundef` attr
 CODEGENOPT(DebugPassManager, 1, 0, Benign) ///< Prints debug information for the new
                                            ///< pass manager.
 CODEGENOPT(DisableRedZone    , 1, 0, Benign) ///< Set when -mno-red-zone is enabled.
+CODEGENOPT(CallGraphSection, 1, 0, Benign) ///< Emit a call graph section into the
+                                           ///< object file.
 CODEGENOPT(EmitCallSiteInfo, 1, 0, Benign) ///< Emit call site info only in the case of
                                            ///< '-g' + 'O>0' level.
 CODEGENOPT(IndirectTlsSegRefs, 1, 0, Benign) ///< Set when -mno-tls-direct-seg-refs

clang/include/clang/Driver/Options.td

@@ -4512,6 +4512,12 @@ defm data_sections : BoolFOption<"data-sections",
   PosFlag<SetTrue, [], [ClangOption, CC1Option],
           "Place each data in its own section">,
   NegFlag<SetFalse>>;
+defm experimental_call_graph_section
+    : BoolFOption<"experimental-call-graph-section", CodeGenOpts<"CallGraphSection">,
+                  DefaultFalse,
+                  PosFlag<SetTrue, [], [ClangOption, CC1Option],
+                          "Emit a call graph section">,
+                  NegFlag<SetFalse>>;
 defm stack_size_section : BoolFOption<"stack-size-section",
   CodeGenOpts<"StackSizeSection">, DefaultFalse,
   PosFlag<SetTrue, [], [ClangOption, CC1Option],

clang/lib/CodeGen/BackendUtil.cpp

@@ -463,6 +463,7 @@ static bool initTargetOptions(const CompilerInstance &CI,
   Options.StackUsageOutput = CodeGenOpts.StackUsageOutput;
   Options.EmitAddrsig = CodeGenOpts.Addrsig;
   Options.ForceDwarfFrameSection = CodeGenOpts.ForceDwarfFrameSection;
+  Options.EmitCallGraphSection = CodeGenOpts.CallGraphSection;
   Options.EmitCallSiteInfo = CodeGenOpts.EmitCallSiteInfo;
   Options.EnableAIXExtendedAltivecABI = LangOpts.EnableAIXExtendedAltivecABI;
   Options.XRayFunctionIndex = CodeGenOpts.XRayFunctionIndex;

clang/lib/CodeGen/CGCall.cpp

@@ -5945,8 +5945,24 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
       CI->getCalledFunction()->getName().starts_with("_Z4sqrt")) {
     SetSqrtFPAccuracy(CI);
   }
-  if (callOrInvoke)
+  if (callOrInvoke) {
     *callOrInvoke = CI;
+    if (CGM.getCodeGenOpts().CallGraphSection) {
+      QualType CST;
+      if (TargetDecl && TargetDecl->getFunctionType())
+        CST = QualType(TargetDecl->getFunctionType(), 0);
+      else if (const auto *FPT =
+                   Callee.getAbstractInfo().getCalleeFunctionProtoType())
+        CST = QualType(FPT, 0);
+      else
+        llvm_unreachable(
+            "Cannot find the callee type to generate callee_type metadata.");
+
+      // Set type identifier metadata of indirect calls for call graph section.
+      if (!CST.isNull())
+        CGM.createCalleeTypeMetadataForIcall(CST, *callOrInvoke);
+    }
+  }
 
   // If this is within a function that has the guard(nocf) attribute and is an
   // indirect call, add the "guard_nocf" attribute to this call to indicate that

clang/lib/CodeGen/CodeGenModule.cpp

@@ -2836,8 +2836,9 @@ void CodeGenModule::SetLLVMFunctionAttributesForDefinition(const Decl *D,
 
   // In the cross-dso CFI mode with canonical jump tables, we want !type
   // attributes on definitions only.
-  if (CodeGenOpts.SanitizeCfiCrossDso &&
-      CodeGenOpts.SanitizeCfiCanonicalJumpTables) {
+  if ((CodeGenOpts.SanitizeCfiCrossDso &&
+       CodeGenOpts.SanitizeCfiCanonicalJumpTables) ||
+      CodeGenOpts.CallGraphSection) {
     if (auto *FD = dyn_cast<FunctionDecl>(D)) {
       // Skip available_externally functions. They won't be codegen'ed in the
       // current module anyway.
@@ -3049,9 +3050,21 @@ static void setLinkageForGV(llvm::GlobalValue *GV, const NamedDecl *ND) {
     GV->setLinkage(llvm::GlobalValue::ExternalWeakLinkage);
 }
 
+static bool hasExistingGeneralizedTypeMD(llvm::Function *F) {
+  llvm::MDNode *MD = F->getMetadata(llvm::LLVMContext::MD_type);
+  return MD && MD->hasGeneralizedMDString();
+}
+
 void CodeGenModule::createFunctionTypeMetadataForIcall(const FunctionDecl *FD,
                                                        llvm::Function *F) {
-  // Only if we are checking indirect calls.
+  if (CodeGenOpts.CallGraphSection && !hasExistingGeneralizedTypeMD(F) &&
+      (!F->hasLocalLinkage() ||
+       F->getFunction().hasAddressTaken(nullptr, /*IgnoreCallbackUses=*/true,
+                                        /*IgnoreAssumeLikeCalls=*/true,
+                                        /*IgnoreLLVMUsed=*/false)))
+    F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(FD->getType()));
+
+  // Add additional metadata only if we are checking indirect calls with CFI.
   if (!LangOpts.Sanitize.has(SanitizerKind::CFIICall))
     return;
 
@@ -3064,17 +3077,34 @@ void CodeGenModule::createFunctionTypeMetadataForIcall(const FunctionDecl *FD,
                                            /*GeneralizePointers=*/false);
   llvm::Metadata *MD = CreateMetadataIdentifierForType(FnType);
   F->addTypeMetadata(0, MD);
-
-  QualType GenPtrFnType = GeneralizeFunctionType(getContext(), FD->getType(),
-                                                 /*GeneralizePointers=*/true);
-  F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(GenPtrFnType));
+  // Add the generalized identifier if not added already.
+  if (!hasExistingGeneralizedTypeMD(F)) {
+    QualType GenPtrFnType = GeneralizeFunctionType(getContext(), FD->getType(),
+                                                  /*GeneralizePointers=*/true);
+    F->addTypeMetadata(0, CreateMetadataIdentifierGeneralized(GenPtrFnType));
+  }
 
   // Emit a hash-based bit set entry for cross-DSO calls.
   if (CodeGenOpts.SanitizeCfiCrossDso)
     if (auto CrossDsoTypeId = CreateCrossDsoCfiTypeId(MD))
       F->addTypeMetadata(0, llvm::ConstantAsMetadata::get(CrossDsoTypeId));
 }
 
+void CodeGenModule::createCalleeTypeMetadataForIcall(const QualType &QT,
+                                                     llvm::CallBase *CB) {
+  // Only if needed for call graph section and only for indirect calls.
+  if (!CodeGenOpts.CallGraphSection || !CB->isIndirectCall())
+    return;
+
+  llvm::Metadata *TypeIdMD = CreateMetadataIdentifierGeneralized(QT);
+  llvm::MDTuple *TypeTuple = llvm::MDTuple::get(
+      getLLVMContext(), {llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(
+                             llvm::Type::getInt64Ty(getLLVMContext()), 0)),
+                         TypeIdMD});
+  llvm::MDTuple *MDN = llvm::MDNode::get(getLLVMContext(), {TypeTuple});
+  CB->setMetadata(llvm::LLVMContext::MD_callee_type, MDN);
+}
+
 void CodeGenModule::setKCFIType(const FunctionDecl *FD, llvm::Function *F) {
   llvm::LLVMContext &Ctx = F->getContext();
   llvm::MDBuilder MDB(Ctx);

clang/lib/CodeGen/CodeGenModule.h

@@ -1644,6 +1644,9 @@ class CodeGenModule : public CodeGenTypeCache {
   void createFunctionTypeMetadataForIcall(const FunctionDecl *FD,
                                           llvm::Function *F);
 
+  /// Create and attach type metadata to the given call.
+  void createCalleeTypeMetadataForIcall(const QualType &QT, llvm::CallBase *CB);
+
   /// Set type metadata to the given function.
   void setKCFIType(const FunctionDecl *FD, llvm::Function *F);
 

clang/lib/Driver/ToolChains/Clang.cpp

@@ -6447,6 +6447,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back(A->getValue());
   }
 
+  if (Args.hasFlag(options::OPT_fexperimental_call_graph_section,
+                   options::OPT_fno_experimental_call_graph_section, false))
+    CmdArgs.push_back("-fexperimental-call-graph-section");
+
   Args.addOptInFlag(CmdArgs, options::OPT_fstack_size_section,
                     options::OPT_fno_stack_size_section);
 

clang/lib/Driver/ToolChains/CommonArgs.cpp

@@ -1272,6 +1272,11 @@ void tools::addLTOOptions(const ToolChain &ToolChain, const ArgList &Args,
     CmdArgs.push_back(
         Args.MakeArgString(Twine(PluginOptPrefix) + "-stack-size-section"));
 
+  if (Args.hasFlag(options::OPT_fexperimental_call_graph_section,
+                   options::OPT_fno_experimental_call_graph_section, false))
+    CmdArgs.push_back(
+        Args.MakeArgString(Twine(PluginOptPrefix) + "-call-graph-section"));
+
   // Setup statistics file output.
   SmallString<128> StatsFile = getStatsFileName(Args, Output, *Input, D);
   if (!StatsFile.empty())

clang/test/CodeGen/call-graph-section-templates.cpp

@@ -0,0 +1,114 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets
+// specifically for C++ templates.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fexperimental-call-graph-section \
+// RUN: -emit-llvm -o %t %s
+// RUN: FileCheck --check-prefix=FT    %s < %t
+// RUN: FileCheck --check-prefix=CST   %s < %t
+
+////////////////////////////////////////////////////////////////////////////////
+// Class definitions and template classes (check for indirect target metadata)
+
+class Cls1 {};
+
+// Cls2 is instantiated with T=Cls1 in foo(). Following checks are for this
+// instantiation.
+template <class T>
+class Cls2 {
+public:
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f1Ev({{.*}} !type [[F_TCLS2F1:![0-9]+]]
+  void f1() {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f2ES0_({{.*}} !type [[F_TCLS2F2:![0-9]+]]
+  void f2(T a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f3EPS0_({{.*}} !type [[F_TCLS2F3:![0-9]+]]
+  void f3(T *a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f4EPKS0_({{.*}} !type [[F_TCLS2F4:![0-9]+]]
+  void f4(const T *a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f5ERS0_({{.*}} !type [[F_TCLS2F5:![0-9]+]]
+  void f5(T &a) {}
+
+  // FT: define {{.*}} void @_ZN4Cls2I4Cls1E2f6ERKS0_({{.*}} !type [[F_TCLS2F6:![0-9]+]]
+  void f6(const T &a) {}
+
+  // Mixed type function pointer member
+  T *(*fp)(T a, T *b, const T *c, T &d, const T &e);
+};
+
+// FT-DAG: [[F_TCLS2F1]] = !{i64 0, !"_ZTSFvvE.generalized"}
+// FT-DAG: [[F_TCLS2F2]] = !{i64 0, !"_ZTSFv4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F3]] = !{i64 0, !"_ZTSFvPvE.generalized"}
+// FT-DAG: [[F_TCLS2F4]] = !{i64 0, !"_ZTSFvPKvE.generalized"}
+// FT-DAG: [[F_TCLS2F5]] = !{i64 0, !"_ZTSFvR4Cls1E.generalized"}
+// FT-DAG: [[F_TCLS2F6]] = !{i64 0, !"_ZTSFvRK4Cls1E.generalized"}
+
+////////////////////////////////////////////////////////////////////////////////
+// Callsites (check for indirect callsite operand bundles)
+
+template <class T>
+T *T_func(T a, T *b, const T *c, T &d, const T &e) { return b; }
+
+// CST-LABEL: define {{.*}} @_Z3foov
+void foo() {
+  // Methods for Cls2<Cls1> is checked above within the template description.
+  Cls2<Cls1> Obj;
+
+  Obj.fp = T_func<Cls1>;
+  Cls1 Cls1Obj;
+  
+  // CST: call noundef ptr %{{.*}}, !callee_type [[F_TFUNC_CLS1_CT:![0-9]+]]
+  Obj.fp(Cls1Obj, &Cls1Obj, &Cls1Obj, Cls1Obj, Cls1Obj);
+
+  // Make indirect calls to Cls2's member methods
+  auto fp_f1 = &Cls2<Cls1>::f1;
+  auto fp_f2 = &Cls2<Cls1>::f2;
+  auto fp_f3 = &Cls2<Cls1>::f3;
+  auto fp_f4 = &Cls2<Cls1>::f4;
+  auto fp_f5 = &Cls2<Cls1>::f5;
+  auto fp_f6 = &Cls2<Cls1>::f6;
+
+  auto *Obj2Ptr = &Obj;
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F1_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f1)();
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F2_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f2)(Cls1Obj);
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F3_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f3)(&Cls1Obj);
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F4_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f4)(&Cls1Obj);
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F5_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f5)(Cls1Obj);
+
+  // CST: call void %{{.*}}, !callee_type [[F_TCLS2F6_CT:![0-9]+]]
+  (Obj2Ptr->*fp_f6)(Cls1Obj);
+}
+
+// CST: define {{.*}} @_Z6T_funcI4Cls1EPT_S1_S2_PKS1_RS1_RS3_({{.*}} !type [[F_TFUNC_CLS1:![0-9]+]]
+// CST-DAG: [[F_TFUNC_CLS1_CT]] = !{[[F_TFUNC_CLS1:![0-9]+]]}
+// CST-DAG: [[F_TFUNC_CLS1]] = !{i64 0, !"_ZTSFPv4Cls1S_PKvRS0_RKS0_E.generalized"}
+
+// CST-DAG: [[F_TCLS2F1_CT]] = !{[[F_TCLS2F1:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F1]] = !{i64 0, !"_ZTSFvvE.generalized"}
+
+// CST-DAG: [[F_TCLS2F2_CT]] = !{[[F_TCLS2F2:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F2]] = !{i64 0, !"_ZTSFv4Cls1E.generalized"}
+
+// CST-DAG: [[F_TCLS2F3_CT]] = !{[[F_TCLS2F3:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F3]] = !{i64 0, !"_ZTSFvPvE.generalized"}
+
+// CST-DAG: [[F_TCLS2F4_CT]] = !{[[F_TCLS2F4:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F4]] = !{i64 0, !"_ZTSFvPKvE.generalized"}
+
+// CST-DAG: [[F_TCLS2F5_CT]] = !{[[F_TCLS2F5:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F5]] = !{i64 0, !"_ZTSFvR4Cls1E.generalized"}
+
+// CST-DAG: [[F_TCLS2F6_CT]] = !{[[F_TCLS2F6:![0-9]+]]}
+// CST-DAG: [[F_TCLS2F6]] = !{i64 0, !"_ZTSFvRK4Cls1E.generalized"}

clang/test/CodeGen/call-graph-section-virtual-methods.cpp

@@ -0,0 +1,55 @@
+// Tests that we assign appropriate identifiers to indirect calls and targets
+// specifically for virtual methods.
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux -fexperimental-call-graph-section \
+// RUN: -emit-llvm -o %t %s
+// RUN: FileCheck --check-prefix=FT %s < %t
+// RUN: FileCheck --check-prefix=CST %s < %t
+
+////////////////////////////////////////////////////////////////////////////////
+// Class definitions (check for indirect target metadata)
+
+class Base {
+  public:
+    // FT-DAG: define {{.*}} @_ZN4Base2vfEPc({{.*}} !type [[F_TVF:![0-9]+]]
+    virtual int vf(char *a) { return 0; };
+  };
+  
+  class Derived : public Base {
+  public:
+    // FT-DAG: define {{.*}} @_ZN7Derived2vfEPc({{.*}} !type [[F_TVF]]
+    int vf(char *a) override { return 1; };
+  };
+  
+  // FT-DAG: [[F_TVF]] = !{i64 0, !"_ZTSFiPvE.generalized"}
+  
+  ////////////////////////////////////////////////////////////////////////////////
+  // Callsites (check for indirect callsite operand bundles)
+  
+  // CST-LABEL: define {{.*}} @_Z3foov
+  void foo() {
+    auto B = Base();
+    auto D = Derived();
+  
+    Base *Bptr = &B;
+    Base *BptrToD = &D;
+    Derived *Dptr = &D;
+  
+    auto FpBaseVf = &Base::vf;
+    auto FpDerivedVf = &Derived::vf;
+  
+    // CST: call noundef i32 %{{.*}}, !callee_type [[F_TVF_CT:![0-9]+]]
+    (Bptr->*FpBaseVf)(0);
+  
+    // CST: call noundef i32 %{{.*}}, !callee_type [[F_TVF_CT:![0-9]+]]
+    (BptrToD->*FpBaseVf)(0);
+  
+    // CST: call noundef i32 %{{.*}}, !callee_type [[F_TVF_CT:![0-9]+]]
+    (Dptr->*FpBaseVf)(0);
+  
+    // CST: call noundef i32 %{{.*}}, !callee_type [[F_TVF_CT:![0-9]+]]
+    (Dptr->*FpDerivedVf)(0);
+  }
+
+  // CST-DAG: [[F_TVF_CT]] = !{[[F_TVF:![0-9]+]]}
+  // CST-DAG: [[F_TVF]] = !{i64 0, !"_ZTSFiPvE.generalized"}