[hip][cuda] Fix the extended lambda name mangling issue.

Summary:
- HIP/CUDA host side needs to use device kernel symbol name to match the
  device side binaries. Without a consistent naming between host- and
  device-side compilations, it's risky that wrong device binaries are
  executed. Consistent naming is usually not an issue until unnamed
  types are used, especially the lambda. In this patch, the consistent
  name mangling is addressed for the extended lambdas, i.e. the lambdas
  annotated with `__device__`.
- In [Itanium C++ ABI][1], the mangling of the lambda is generally
  unspecified unless, in certain cases, ODR rule is required to ensure
  consisent naming cross TUs. The extended lambda is such a case as its
  name may be part of a device kernel function, e.g., the extended
  lambda is used as a template argument and etc. Thus, we need to force
  ODR for extended lambdas as they are referenced in both device- and
  host-side TUs. Furthermore, if a extended lambda is nested in other
  (extended or not) lambdas, those lambdas are required to follow ODR
  naming as well. This patch revises the current lambda mangle numbering
  to force ODR from an extended lambda to all its parent lambdas.
- On the other side, the aforementioned ODR naming should not change
  those lambdas' original linkages, i.e., we cannot replace the original
  `internal` with `linkonce_odr`; otherwise, we may violate ODR in
  general. This patch introduces a new field `HasKnownInternalLinkage`
  in lambda data to decouple the current linkage calculation based on
  mangling number assigned.

[1]: https://itanium-cxx-abi.github.io/cxx-abi/abi.html

Reviewers: tra, rsmith, yaxunl, martong, shafik

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D68818

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@375309 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 72 insertions, 24 deletions

diff --git a/lib/AST/ASTImporter.cpp b/lib/AST/ASTImporter.cpp
index a549cf9f89..54acca7dc6 100644
--- a/lib/AST/ASTImporter.cpp
+++ b/lib/AST/ASTImporter.cpp
@@ -2694,7 +2694,8 @@ ExpectedDecl ASTNodeImporter::VisitRecordDecl(RecordDecl *D) {
       ExpectedDecl CDeclOrErr = import(DCXX->getLambdaContextDecl());
       if (!CDeclOrErr)
         return CDeclOrErr.takeError();
-      D2CXX->setLambdaMangling(DCXX->getLambdaManglingNumber(), *CDeclOrErr);
+      D2CXX->setLambdaMangling(DCXX->getLambdaManglingNumber(), *CDeclOrErr,
+                               DCXX->hasKnownLambdaInternalLinkage());
     } else if (DCXX->isInjectedClassName()) {
       // We have to be careful to do a similar dance to the one in
       // Sema::ActOnStartCXXMemberDeclarations
diff --git a/lib/AST/Decl.cpp b/lib/AST/Decl.cpp
index 9ebf1c3262..80235d8496 100644
--- a/lib/AST/Decl.cpp
+++ b/lib/AST/Decl.cpp
@@ -1385,7 +1385,8 @@ LinkageInfo LinkageComputer::computeLVForDecl(const NamedDecl *D,
     case Decl::CXXRecord: {
       const auto *Record = cast<CXXRecordDecl>(D);
       if (Record->isLambda()) {
-        if (!Record->getLambdaManglingNumber()) {
+        if (Record->hasKnownLambdaInternalLinkage() ||
+            !Record->getLambdaManglingNumber()) {
           // This lambda has no mangling number, so it's internal.
           return getInternalLinkageFor(D);
         }
@@ -1402,7 +1403,8 @@ LinkageInfo LinkageComputer::computeLVForDecl(const NamedDecl *D,
         //  };
         const CXXRecordDecl *OuterMostLambda =
             getOutermostEnclosingLambda(Record);
-        if (!OuterMostLambda->getLambdaManglingNumber())
+        if (OuterMostLambda->hasKnownLambdaInternalLinkage() ||
+            !OuterMostLambda->getLambdaManglingNumber())
           return getInternalLinkageFor(D);
 
         return getLVForClosure(
diff --git a/lib/Sema/SemaLambda.cpp b/lib/Sema/SemaLambda.cpp
index df4f0ddc6c..749b0f2caa 100644
--- a/lib/Sema/SemaLambda.cpp
+++ b/lib/Sema/SemaLambda.cpp
@@ -335,7 +335,7 @@ Sema::getCurrentMangleNumberContext(const DeclContext *DC) {
   case StaticDataMember:
     //  -- the initializers of nonspecialized static members of template classes
     if (!IsInNonspecializedTemplate)
-      return std::make_tuple(nullptr, nullptr);
+      return std::make_tuple(nullptr, ManglingContextDecl);
     // Fall through to get the current context.
     LLVM_FALLTHROUGH;
 
@@ -356,14 +356,15 @@ Sema::getCurrentMangleNumberContext(const DeclContext *DC) {
   llvm_unreachable("unexpected context");
 }
 
-CXXMethodDecl *Sema::startLambdaDefinition(
-    CXXRecordDecl *Class, SourceRange IntroducerRange,
-    TypeSourceInfo *MethodTypeInfo, SourceLocation EndLoc,
-    ArrayRef<ParmVarDecl *> Params, ConstexprSpecKind ConstexprKind,
-    Optional<std::pair<unsigned, Decl *>> Mangling) {
+CXXMethodDecl *Sema::startLambdaDefinition(CXXRecordDecl *Class,
+                                           SourceRange IntroducerRange,
+                                           TypeSourceInfo *MethodTypeInfo,
+                                           SourceLocation EndLoc,
+                                           ArrayRef<ParmVarDecl *> Params,
+                                           ConstexprSpecKind ConstexprKind) {
   QualType MethodType = MethodTypeInfo->getType();
   TemplateParameterList *TemplateParams =
-            getGenericLambdaTemplateParameterList(getCurLambda(), *this);
+      getGenericLambdaTemplateParameterList(getCurLambda(), *this);
   // If a lambda appears in a dependent context or is a generic lambda (has
   // template parameters) and has an 'auto' return type, deduce it to a
   // dependent type.
@@ -425,20 +426,55 @@ CXXMethodDecl *Sema::startLambdaDefinition(
       P->setOwningFunction(Method);
   }
 
+  return Method;
+}
+
+void Sema::handleLambdaNumbering(
+    CXXRecordDecl *Class, CXXMethodDecl *Method,
+    Optional<std::tuple<unsigned, bool, Decl *>> Mangling) {
   if (Mangling) {
-    Class->setLambdaMangling(Mangling->first, Mangling->second);
-  } else {
-    MangleNumberingContext *MCtx;
+    unsigned ManglingNumber;
+    bool HasKnownInternalLinkage;
     Decl *ManglingContextDecl;
-    std::tie(MCtx, ManglingContextDecl) =
-        getCurrentMangleNumberContext(Class->getDeclContext());
-    if (MCtx) {
-      unsigned ManglingNumber = MCtx->getManglingNumber(Method);
-      Class->setLambdaMangling(ManglingNumber, ManglingContextDecl);
-    }
+    std::tie(ManglingNumber, HasKnownInternalLinkage, ManglingContextDecl) =
+        Mangling.getValue();
+    Class->setLambdaMangling(ManglingNumber, ManglingContextDecl,
+                             HasKnownInternalLinkage);
+    return;
   }
 
-  return Method;
+  auto getMangleNumberingContext =
+      [this](CXXRecordDecl *Class, Decl *ManglingContextDecl) -> MangleNumberingContext * {
+    // Get mangle numbering context if there's any extra decl context.
+    if (ManglingContextDecl)
+      return &Context.getManglingNumberContext(
+          ASTContext::NeedExtraManglingDecl, ManglingContextDecl);
+    // Otherwise, from that lambda's decl context.
+    auto DC = Class->getDeclContext();
+    while (auto *CD = dyn_cast<CapturedDecl>(DC))
+      DC = CD->getParent();
+    return &Context.getManglingNumberContext(DC);
+  };
+
+  MangleNumberingContext *MCtx;
+  Decl *ManglingContextDecl;
+  std::tie(MCtx, ManglingContextDecl) =
+      getCurrentMangleNumberContext(Class->getDeclContext());
+  bool HasKnownInternalLinkage = false;
+  if (!MCtx && getLangOpts().CUDA) {
+    // Force lambda numbering in CUDA/HIP as we need to name lambdas following
+    // ODR. Both device- and host-compilation need to have a consistent naming
+    // on kernel functions. As lambdas are potential part of these `__global__`
+    // function names, they needs numbering following ODR.
+    MCtx = getMangleNumberingContext(Class, ManglingContextDecl);
+    assert(MCtx && "Retrieving mangle numbering context failed!");
+    HasKnownInternalLinkage = true;
+  }
+  if (MCtx) {
+    unsigned ManglingNumber = MCtx->getManglingNumber(Method);
+    Class->setLambdaMangling(ManglingNumber, ManglingContextDecl,
+                             HasKnownInternalLinkage);
+  }
 }
 
 void Sema::buildLambdaScope(LambdaScopeInfo *LSI,
@@ -951,6 +987,9 @@ void Sema::ActOnStartOfLambdaDefinition(LambdaIntroducer &Intro,
   if (getLangOpts().CUDA)
     CUDASetLambdaAttrs(Method);
 
+  // Number the lambda for linkage purposes if necessary.
+  handleLambdaNumbering(Class, Method);
+
   // Introduce the function call operator as the current declaration context.
   PushDeclContext(CurScope, Method);
 
diff --git a/lib/Sema/TreeTransform.h b/lib/Sema/TreeTransform.h
index 89a7b8cc84..4b3a670871 100644
--- a/lib/Sema/TreeTransform.h
+++ b/lib/Sema/TreeTransform.h
@@ -11497,17 +11497,18 @@ TreeTransform<Derived>::TransformLambdaExpr(LambdaExpr *E) {
                                         E->getCaptureDefault());
   getDerived().transformedLocalDecl(OldClass, {Class});
 
-  Optional<std::pair<unsigned, Decl*>> Mangling;
+  Optional<std::tuple<unsigned, bool, Decl *>> Mangling;
   if (getDerived().ReplacingOriginal())
-    Mangling = std::make_pair(OldClass->getLambdaManglingNumber(),
-                              OldClass->getLambdaContextDecl());
+    Mangling = std::make_tuple(OldClass->getLambdaManglingNumber(),
+                               OldClass->hasKnownLambdaInternalLinkage(),
+                               OldClass->getLambdaContextDecl());
 
   // Build the call operator.
   CXXMethodDecl *NewCallOperator = getSema().startLambdaDefinition(
       Class, E->getIntroducerRange(), NewCallOpTSI,
       E->getCallOperator()->getEndLoc(),
       NewCallOpTSI->getTypeLoc().castAs<FunctionProtoTypeLoc>().getParams(),
-      E->getCallOperator()->getConstexprKind(), Mangling);
+      E->getCallOperator()->getConstexprKind());
 
   LSI->CallOperator = NewCallOperator;
 
@@ -11527,6 +11528,9 @@ TreeTransform<Derived>::TransformLambdaExpr(LambdaExpr *E) {
   getDerived().transformAttrs(E->getCallOperator(), NewCallOperator);
   getDerived().transformedLocalDecl(E->getCallOperator(), {NewCallOperator});
 
+  // Number the lambda for linkage purposes if necessary.
+  getSema().handleLambdaNumbering(Class, NewCallOperator, Mangling);
+
   // Introduce the context of the call operator.
   Sema::ContextRAII SavedContext(getSema(), NewCallOperator,
                                  /*NewThisContext*/false);
diff --git a/lib/Serialization/ASTReaderDecl.cpp b/lib/Serialization/ASTReaderDecl.cpp
index 65d62524e2..9aa8c77c62 100644
--- a/lib/Serialization/ASTReaderDecl.cpp
+++ b/lib/Serialization/ASTReaderDecl.cpp
@@ -1690,6 +1690,7 @@ void ASTDeclReader::ReadCXXDefinitionData(
     Lambda.CaptureDefault = Record.readInt();
     Lambda.NumCaptures = Record.readInt();
     Lambda.NumExplicitCaptures = Record.readInt();
+    Lambda.HasKnownInternalLinkage = Record.readInt();
     Lambda.ManglingNumber = Record.readInt();
     Lambda.ContextDecl = ReadDeclID();
     Lambda.Captures = (Capture *)Reader.getContext().Allocate(
diff --git a/lib/Serialization/ASTWriter.cpp b/lib/Serialization/ASTWriter.cpp
index c6b05c9a17..28affedbbb 100644
--- a/lib/Serialization/ASTWriter.cpp
+++ b/lib/Serialization/ASTWriter.cpp
@@ -6224,6 +6224,7 @@ void ASTRecordWriter::AddCXXDefinitionData(const CXXRecordDecl *D) {
     Record->push_back(Lambda.CaptureDefault);
     Record->push_back(Lambda.NumCaptures);
     Record->push_back(Lambda.NumExplicitCaptures);
+    Record->push_back(Lambda.HasKnownInternalLinkage);
     Record->push_back(Lambda.ManglingNumber);
     AddDeclRef(D->getLambdaContextDecl());
     AddTypeSourceInfo(Lambda.MethodTyInfo);