[CodeView] Don't output S_UDT symbols for forward decls.

S_UDT symbols are the debugger's "index" for all the structs,
typedefs, classes, and enums in a program.  If any of those
structs/classes don't have a complete declaration, or if there
is a typedef to something that doesn't have a complete definition,
then emitting the S_UDT is unhelpful because it doesn't give
the debugger enough information to do anything useful.  On the
other hand, it results in a huge size blow-up in the resulting
PDB, which is exacerbated by an order of magnitude when linking
with /DEBUG:FASTLINK.

With this patch, we drop S_UDT records for types that refer either
directly or indirectly (e.g. through a typedef, pointer, etc) to
a class/struct/union/enum without a complete definition.  This
brings us about 50% of the way towards parity with /DEBUG:FASTLINK
PDBs generated from cl-compiled object files.

Differential Revision: https://reviews.llvm.org/D37162

llvm-svn: 311904

2 files changed, 35 insertions, 16 deletions

diff --git a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
index 4346803738b..8879f6b1f3e 100644
--- a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.cpp
@@ -1099,10 +1099,25 @@ void CodeViewDebug::beginFunctionImpl(const MachineFunction *MF) {
   }
 }
 
-void CodeViewDebug::addToUDTs(const DIType *Ty, TypeIndex TI) {
+static bool shouldEmitUdt(const DIType *T) {
+  while (true) {
+    if (!T || T->isForwardDecl())
+      return false;
+
+    const DIDerivedType *DT = dyn_cast<DIDerivedType>(T);
+    if (!DT)
+      return true;
+    T = DT->getBaseType().resolve();
+  }
+  return true;
+}
+
+void CodeViewDebug::addToUDTs(const DIType *Ty) {
   // Don't record empty UDTs.
   if (Ty->getName().empty())
     return;
+  if (!shouldEmitUdt(Ty))
+    return;
 
   SmallVector<StringRef, 5> QualifiedNameComponents;
   const DISubprogram *ClosestSubprogram = getQualifiedNameComponents(
@@ -1111,10 +1126,11 @@ void CodeViewDebug::addToUDTs(const DIType *Ty, TypeIndex TI) {
   std::string FullyQualifiedName =
       getQualifiedName(QualifiedNameComponents, getPrettyScopeName(Ty));
 
-  if (ClosestSubprogram == nullptr)
-    GlobalUDTs.emplace_back(std::move(FullyQualifiedName), TI);
-  else if (ClosestSubprogram == CurrentSubprogram)
-    LocalUDTs.emplace_back(std::move(FullyQualifiedName), TI);
+  if (ClosestSubprogram == nullptr) {
+    GlobalUDTs.emplace_back(std::move(FullyQualifiedName), Ty);
+  } else if (ClosestSubprogram == CurrentSubprogram) {
+    LocalUDTs.emplace_back(std::move(FullyQualifiedName), Ty);
+  }
 
   // TODO: What if the ClosestSubprogram is neither null or the current
   // subprogram?  Currently, the UDT just gets dropped on the floor.
@@ -1172,7 +1188,7 @@ TypeIndex CodeViewDebug::lowerTypeAlias(const DIDerivedType *Ty) {
   TypeIndex UnderlyingTypeIndex = getTypeIndex(UnderlyingTypeRef);
   StringRef TypeName = Ty->getName();
 
-  addToUDTs(Ty, UnderlyingTypeIndex);
+  addToUDTs(Ty);
 
   if (UnderlyingTypeIndex == TypeIndex(SimpleTypeKind::Int32Long) &&
       TypeName == "HRESULT")
@@ -1764,7 +1780,7 @@ TypeIndex CodeViewDebug::lowerCompleteTypeClass(const DICompositeType *Ty) {
     TypeTable.writeKnownType(USLR);
   }
 
-  addToUDTs(Ty, ClassTI);
+  addToUDTs(Ty);
 
   return ClassTI;
 }
@@ -1803,7 +1819,7 @@ TypeIndex CodeViewDebug::lowerCompleteTypeUnion(const DICompositeType *Ty) {
   UdtSourceLineRecord USLR(UnionTI, SIRI, Ty->getLine());
   TypeTable.writeKnownType(USLR);
 
-  addToUDTs(Ty, UnionTI);
+  addToUDTs(Ty);
 
   return UnionTI;
 }
@@ -2203,8 +2219,11 @@ void CodeViewDebug::endCVSubsection(MCSymbol *EndLabel) {
 }
 
 void CodeViewDebug::emitDebugInfoForUDTs(
-    ArrayRef<std::pair<std::string, TypeIndex>> UDTs) {
-  for (const std::pair<std::string, codeview::TypeIndex> &UDT : UDTs) {
+    ArrayRef<std::pair<std::string, const DIType *>> UDTs) {
+  for (const auto &UDT : UDTs) {
+    const DIType *T = UDT.second;
+    assert(shouldEmitUdt(T));
+
     MCSymbol *UDTRecordBegin = MMI->getContext().createTempSymbol(),
              *UDTRecordEnd = MMI->getContext().createTempSymbol();
     OS.AddComment("Record length");
@@ -2215,7 +2234,7 @@ void CodeViewDebug::emitDebugInfoForUDTs(
     OS.EmitIntValue(unsigned(SymbolKind::S_UDT), 2);
 
     OS.AddComment("Type");
-    OS.EmitIntValue(UDT.second.getIndex(), 4);
+    OS.EmitIntValue(getCompleteTypeIndex(T).getIndex(), 4);
 
     emitNullTerminatedSymbolName(OS, UDT.first);
     OS.EmitLabel(UDTRecordEnd);
diff --git a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.h b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.h
index fd8f60425c2..91f691c635e 100644
--- a/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.h
+++ b/llvm/lib/CodeGen/AsmPrinter/CodeViewDebug.h
@@ -187,8 +187,8 @@ class LLVM_LIBRARY_VISIBILITY CodeViewDebug : public DebugHandlerBase {
 
   // The UDTs we have seen while processing types; each entry is a pair of type
   // index and type name.
-  std::vector<std::pair<std::string, codeview::TypeIndex>> LocalUDTs,
-      GlobalUDTs;
+  std::vector<std::pair<std::string, const DIType *>> LocalUDTs;
+  std::vector<std::pair<std::string, const DIType *>> GlobalUDTs;
 
   using FileToFilepathMapTy = std::map<const DIFile *, std::string>;
   FileToFilepathMapTy FileToFilepathMap;
@@ -222,8 +222,8 @@ class LLVM_LIBRARY_VISIBILITY CodeViewDebug : public DebugHandlerBase {
 
   void emitDebugInfoForRetainedTypes();
 
-  void emitDebugInfoForUDTs(
-      ArrayRef<std::pair<std::string, codeview::TypeIndex>> UDTs);
+  void
+  emitDebugInfoForUDTs(ArrayRef<std::pair<std::string, const DIType *>> UDTs);
 
   void emitDebugInfoForGlobal(const DIGlobalVariable *DIGV,
                               const GlobalVariable *GV, MCSymbol *GVSym);
@@ -266,7 +266,7 @@ class LLVM_LIBRARY_VISIBILITY CodeViewDebug : public DebugHandlerBase {
 
   codeview::TypeIndex getVBPTypeIndex();
 
-  void addToUDTs(const DIType *Ty, codeview::TypeIndex TI);
+  void addToUDTs(const DIType *Ty);
 
   codeview::TypeIndex lowerType(const DIType *Ty, const DIType *ClassTy);
   codeview::TypeIndex lowerTypeAlias(const DIDerivedType *Ty);