[PGO] Instrument only base constructors and destructors.

[sepavloff]

Summary

Constructors and destructors may be represented by several functions
in IR. Only the base structors correspond to source code, others
are small pieces of code and eventually call the base variant. In
this case instrumentation of non-base structors has little sense,
this fix remove it. Now profile data of a declaration correspond to
exactly one function in IR, it agrees with current logic of profile
data loading.

This change fixes PR24996.

[sepavloff]

Changes according to reviewer's notes.

cfe/trunk/lib/CodeGen/CGBlocks.cpp

CodeGenFunction::GenerateBlockFunction(GlobalDecl GD,
   // Save a spot to insert the debug information for all the DeclRefExprs.
   llvm::BasicBlock *entry = Builder.GetInsertBlock();
   llvm::BasicBlock::iterator entry_ptr = Builder.GetInsertPoint();
   --entry_ptr;
 
   if (IsLambdaConversionToBlock)
     EmitLambdaBlockInvokeBody();
   else {
-    PGO.assignRegionCounters(blockDecl, fn);
+    PGO.assignRegionCounters(GlobalDecl(blockDecl), fn);
     incrementProfileCounter(blockDecl->getBody());
     EmitStmt(blockDecl->getBody());
   }
 
   // Remember where we were...
   llvm::BasicBlock *resume = Builder.GetInsertBlock();
 
   // Go back to the entry.

cfe/trunk/lib/CodeGen/CGObjC.cpp

 
 static llvm::Value *emitARCRetainLoadOfScalar(CodeGenFunction &CGF,
                                               LValue lvalue, QualType type);
 
 /// Generate an Objective-C method.  An Objective-C method is a C function with
 /// its pointer, name, and types registered in the class struture.
 void CodeGenFunction::GenerateObjCMethod(const ObjCMethodDecl *OMD) {
   StartObjCMethod(OMD, OMD->getClassInterface());
-  PGO.assignRegionCounters(OMD, CurFn);
+  PGO.assignRegionCounters(GlobalDecl(OMD), CurFn);
   assert(isa<CompoundStmt>(OMD->getBody()));
   incrementProfileCounter(OMD->getBody());
   EmitCompoundStmtWithoutScope(*cast<CompoundStmt>(OMD->getBody()));
   FinishFunction(OMD->getBodyRBrace());
 }
 
 /// emitStructGetterCall - Call the runtime function to load a property
 /// into the return value slot.

cfe/trunk/lib/CodeGen/CGStmt.cpp

CodeGenFunction::GenerateCapturedStmtFunction(const CapturedStmt &S) {
 
   // If 'this' is captured, load it into CXXThisValue.
   if (CapturedStmtInfo->isCXXThisExprCaptured()) {
     FieldDecl *FD = CapturedStmtInfo->getThisFieldDecl();
     LValue ThisLValue = EmitLValueForField(Base, FD);
     CXXThisValue = EmitLoadOfLValue(ThisLValue, Loc).getScalarVal();
   }
 
-  PGO.assignRegionCounters(CD, F);
+  PGO.assignRegionCounters(GlobalDecl(CD), F);
   CapturedStmtInfo->EmitBody(*this, CD->getBody());
   FinishFunction(CD->getBodyRBrace());
 
   return F;
 }

cfe/trunk/lib/CodeGen/CGStmtOpenMP.cpp

if (FD->hasCapturedVLAType()) {
       // If 'this' is captured, load it into CXXThisValue.
       assert(I->capturesThis());
       CXXThisValue =
           EmitLoadOfLValue(ArgLVal, Args[Cnt]->getLocation()).getScalarVal();
     }
     ++Cnt, ++I;
   }
 
-  PGO.assignRegionCounters(CD, F);
+  PGO.assignRegionCounters(GlobalDecl(CD), F);
   CapturedStmtInfo->EmitBody(*this, CD->getBody());
   FinishFunction(CD->getBodyRBrace());
 
   return F;
 }
 
 //===----------------------------------------------------------------------===//
 //                              OpenMP Directive Emission

cfe/trunk/lib/CodeGen/CodeGenFunction.cpp

void CodeGenFunction::GenerateCode(GlobalDecl GD, llvm::Function *Fn,
   if (const FunctionDecl *SpecDecl = FD->getTemplateInstantiationPattern())
     if (SpecDecl->hasBody(SpecDecl))
       Loc = SpecDecl->getLocation();
 
   // Emit the standard function prologue.
   StartFunction(GD, ResTy, Fn, FnInfo, Args, Loc, BodyRange.getBegin());
 
   // Generate the body of the function.
-  PGO.checkGlobalDecl(GD);
-  PGO.assignRegionCounters(GD.getDecl(), CurFn);
+  PGO.assignRegionCounters(GD, CurFn);
   if (isa<CXXDestructorDecl>(FD))
     EmitDestructorBody(Args);
   else if (isa<CXXConstructorDecl>(FD))
     EmitConstructorBody(Args);
   else if (getLangOpts().CUDA &&
            !getLangOpts().CUDAIsDevice &&
            FD->hasAttr<CUDAGlobalAttr>())
     CGM.getCUDARuntime().emitDeviceStub(*this, Args);

cfe/trunk/lib/CodeGen/CodeGenPGO.h

public:
 
   /// If the execution count for the current statement is known, record that
   /// as the current count.
   void setCurrentStmt(const Stmt *S) {
     if (auto Count = getStmtCount(S))
       setCurrentRegionCount(*Count);
   }
 
-  /// Check if we need to emit coverage mapping for a given declaration
-  void checkGlobalDecl(GlobalDecl GD);
   /// Assign counters to regions and configure them for PGO of a given
   /// function. Does nothing if instrumentation is not enabled and either
   /// generates global variables or associates PGO data with each of the
   /// counters depending on whether we are generating or using instrumentation.
-  void assignRegionCounters(const Decl *D, llvm::Function *Fn);
+  void assignRegionCounters(GlobalDecl GD, llvm::Function *Fn);
   /// Emit a coverage mapping range with a counter zero
   /// for an unused declaration.
   void emitEmptyCounterMapping(const Decl *D, StringRef FuncName,
                                llvm::GlobalValue::LinkageTypes Linkage);
 private:
   void setFuncName(llvm::Function *Fn);
   void setFuncName(StringRef Name, llvm::GlobalValue::LinkageTypes Linkage);
   void mapRegionCounters(const Decl *D);

cfe/trunk/lib/CodeGen/CodeGenPGO.cpp

uint64_t PGOHash::finalize() {
 
   // Finalize the MD5 and return the hash.
   llvm::MD5::MD5Result Result;
   MD5.final(Result);
   using namespace llvm::support;
   return endian::read<uint64_t, little, unaligned>(Result);
 }
 
-void CodeGenPGO::checkGlobalDecl(GlobalDecl GD) {
-  // Make sure we only emit coverage mapping for one constructor/destructor.
-  // Clang emits several functions for the constructor and the destructor of
-  // a class. Every function is instrumented, but we only want to provide
-  // coverage for one of them. Because of that we only emit the coverage mapping
-  // for the base constructor/destructor.
-  if ((isa<CXXConstructorDecl>(GD.getDecl()) &&
-       GD.getCtorType() != Ctor_Base) ||
-      (isa<CXXDestructorDecl>(GD.getDecl()) &&
-       GD.getDtorType() != Dtor_Base)) {
-    SkipCoverageMapping = true;
-  }
-}
-
-void CodeGenPGO::assignRegionCounters(const Decl *D, llvm::Function *Fn) {
+void CodeGenPGO::assignRegionCounters(GlobalDecl GD, llvm::Function *Fn) {
+  const Decl *D = GD.getDecl();
   bool InstrumentRegions = CGM.getCodeGenOpts().ProfileInstrGenerate;
   llvm::IndexedInstrProfReader *PGOReader = CGM.getPGOReader();
   if (!InstrumentRegions && !PGOReader)
     return;
   if (D->isImplicit())
     return;
+  // Constructors and destructors may be represented by several functions in IR.
+  // If so, instrument only base variant, others are implemented by delegation
+  // to the base one, it would be counted twice otherwise.
+  if (CGM.getTarget().getCXXABI().hasConstructorVariants() &&
+      ((isa<CXXConstructorDecl>(GD.getDecl()) &&
+        GD.getCtorType() != Ctor_Base) ||
+       (isa<CXXDestructorDecl>(GD.getDecl()) &&
+        GD.getDtorType() != Dtor_Base))) {
+      return;
+  }
   CGM.ClearUnusedCoverageMapping(D);
   setFuncName(Fn);
 
   mapRegionCounters(D);
   if (CGM.getCodeGenOpts().CoverageMapping)
     emitCounterRegionMapping(D);
   if (PGOReader) {
     SourceManager &SM = CGM.getContext().getSourceManager();

cfe/trunk/test/Profile/cxx-structors.cpp

+// Tests for instrumentation of C++ constructors and destructors.
+//
+// RUN: %clang_cc1 -triple x86_64-apple-macosx10.11.0 -x c++ %s -o - -emit-llvm -fprofile-instr-generate | FileCheck %s
+
+struct Foo {
+  Foo() {}
+  Foo(int) {}
+  ~Foo() {}
+};
+
+struct Bar : public Foo {
+  Bar() {}
+  Bar(int x) : Foo(x) {}
+  ~Bar();
+};
+
+Foo foo;
+Foo foo2(1);
+Bar bar;
+
+// Profile data for complete constructors and destructors must absent.
+
+// CHECK-NOT: @__llvm_profile_name__ZN3FooC1Ev
+// CHECK-NOT: @__llvm_profile_name__ZN3FooC1Ei
+// CHECK-NOT: @__llvm_profile_name__ZN3FooD1Ev
+// CHECK-NOT: @__llvm_profile_name__ZN3BarC1Ev
+// CHECK-NOT: @__llvm_profile_name__ZN3BarD1Ev
+// CHECK-NOT: @__llvm_profile_counters__ZN3FooD1Ev
+// CHECK-NOT: @__llvm_profile_data__ZN3FooD1Ev
+
+int main() {
+}

cfe/trunk/test/Profile/cxx-virtual-destructor-calls.cpp

 // RUN: %clang_cc1 -triple %itanium_abi_triple -emit-llvm -main-file-name cxx-virtual-destructor-calls.cpp %s -o - -fprofile-instr-generate | FileCheck %s
 
 struct Member {
   ~Member();
 };
 
 struct A {
   virtual ~A();
 };
 
 struct B : A {
   Member m;
   virtual ~B();
 };
 
-// Complete dtor
-// CHECK: @__llvm_profile_name__ZN1BD1Ev = private constant [9 x i8] c"_ZN1BD1Ev"
+// Base dtor
+// CHECK: @__llvm_profile_name__ZN1BD2Ev = private constant [9 x i8] c"_ZN1BD2Ev"
 
-// Deleting dtor
-// CHECK: @__llvm_profile_name__ZN1BD0Ev = private constant [9 x i8] c"_ZN1BD0Ev"
+// Complete dtor must not be instrumented
+// CHECK-NOT: @__llvm_profile_name__ZN1BD1Ev = private constant [9 x i8] c"_ZN1BD1Ev"
 
-// Complete dtor counters and profile data
-// CHECK: @__llvm_profile_counters__ZN1BD1Ev = private global [1 x i64] zeroinitializer
-// CHECK: @__llvm_profile_data__ZN1BD1Ev =
-
-// Deleting dtor counters and profile data
-// CHECK: @__llvm_profile_counters__ZN1BD0Ev = private global [1 x i64] zeroinitializer
-// CHECK: @__llvm_profile_data__ZN1BD0Ev =
+// Deleting dtor must not be instrumented
+// CHECK-NOT: @__llvm_profile_name__ZN1BD0Ev = private constant [9 x i8] c"_ZN1BD0Ev"
+
+// Base dtor counters and profile data
+// CHECK: @__llvm_profile_counters__ZN1BD2Ev = private global [1 x i64] zeroinitializer
+// CHECK: @__llvm_profile_data__ZN1BD2Ev =
+
+// Complete dtor counters and profile data must absent
+// CHECK-NOT: @__llvm_profile_counters__ZN1BD1Ev = private global [1 x i64] zeroinitializer
+// CHECK-NOT: @__llvm_profile_data__ZN1BD1Ev =
+
+// Deleting dtor counters and profile data must absent
+// CHECK-NOT: @__llvm_profile_counters__ZN1BD0Ev = private global [1 x i64] zeroinitializer
+// CHECK-NOT: @__llvm_profile_data__ZN1BD0Ev =
 
 B::~B() { }