[DebugInfo] Improvements to representation of enumeration types (PR36168)

This patch is the LLVM part of fixing the issues, described in
https://bugs.llvm.org/show_bug.cgi?id=36168

* The representation of enumerator values in the debug info metadata now
  contains a boolean flag isUnsigned, which determines how the bits of
  the value are interpreted.
* The DW_TAG_enumeration type DIE now always (for DWARF version >= 3)
  includes a DW_AT_type attribute, which refers to the underlying
  integer type, as suggested in DWARFv4 (5.7 Enumeration Type Entries).
* The debug info metadata for enumeration type contains (in flags)
  indication whether this is a C++11 "fixed enum".
* For C++11 enumeration with a fixed underlying type, the DIE also
  includes the DW_AT_enum_class attribute (for DWARF version >= 4).
* Encoding of enumerator constants uses DW_FORM_sdata for signed values
  and DW_FORM_udata for unsigned values, as suggested by DWARFv4 (7.5.4
  Attribute Encodings).

The changes should be backwards compatible:

* the isUnsigned attribute is optional and defaults to false.
* if the underlying type for the enumeration is not available, the
  enumerator values are considered signed.
* the FixedEnum flag defaults to clear.
* the bitcode format for DIEnumerator stores the unsigned flag bit #1 of
  the first record element, so the format does not change and the zero
  previously stored there is consistent with the false default for
  IsUnsigned.

Differential Revision: https://reviews.llvm.org/D42734

llvm-svn: 324489

8 files changed, 88 insertions, 26 deletions

diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 2833ef44fe9..209a834fed1 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -3636,6 +3636,22 @@ struct MDSignedOrMDField : MDEitherFieldImpl<MDSignedField, MDField> {
   }
 };
 
+struct MDSignedOrUnsignedField
+    : MDEitherFieldImpl<MDSignedField, MDUnsignedField> {
+  MDSignedOrUnsignedField() : ImplTy(MDSignedField(0), MDUnsignedField(0)) {}
+
+  bool isMDSignedField() const { return WhatIs == IsTypeA; }
+  bool isMDUnsignedField() const { return WhatIs == IsTypeB; }
+  int64_t getMDSignedValue() const {
+    assert(isMDSignedField() && "Wrong field type");
+    return A.Val;
+  }
+  uint64_t getMDUnsignedValue() const {
+    assert(isMDUnsignedField() && "Wrong field type");
+    return B.Val;
+  }
+};
+
 } // end anonymous namespace
 
 namespace llvm {
@@ -3913,6 +3929,27 @@ bool LLParser::ParseMDField(LocTy Loc, StringRef Name,
 }
 
 template <>
+bool LLParser::ParseMDField(LocTy Loc, StringRef Name,
+                            MDSignedOrUnsignedField &Result) {
+  if (Lex.getKind() != lltok::APSInt)
+    return false;
+
+  if (Lex.getAPSIntVal().isSigned()) {
+    MDSignedField Res = Result.A;
+    if (ParseMDField(Loc, Name, Res))
+      return true;
+    Result.assign(Res);
+    return false;
+  }
+
+  MDUnsignedField Res = Result.B;
+  if (ParseMDField(Loc, Name, Res))
+    return true;
+  Result.assign(Res);
+  return false;
+}
+
+template <>
 bool LLParser::ParseMDField(LocTy Loc, StringRef Name, MDStringField &Result) {
   LocTy ValueLoc = Lex.getLoc();
   std::string S;
@@ -4077,15 +4114,24 @@ bool LLParser::ParseDISubrange(MDNode *&Result, bool IsDistinct) {
 }
 
 /// ParseDIEnumerator:
-///   ::= !DIEnumerator(value: 30, name: "SomeKind")
+///   ::= !DIEnumerator(value: 30, isUnsigned: true, name: "SomeKind")
 bool LLParser::ParseDIEnumerator(MDNode *&Result, bool IsDistinct) {
 #define VISIT_MD_FIELDS(OPTIONAL, REQUIRED)                                    \
   REQUIRED(name, MDStringField, );                                             \
-  REQUIRED(value, MDSignedField, );
+  REQUIRED(value, MDSignedOrUnsignedField, );                                  \
+  OPTIONAL(isUnsigned, MDBoolField, (false));
   PARSE_MD_FIELDS();
 #undef VISIT_MD_FIELDS
 
-  Result = GET_OR_DISTINCT(DIEnumerator, (Context, value.Val, name.Val));
+  if (isUnsigned.Val && value.isMDSignedField())
+    return TokError("unsigned enumerator with negative value");
+
+  int64_t Value = value.isMDSignedField()
+                      ? value.getMDSignedValue()
+                      : static_cast<int64_t>(value.getMDUnsignedValue());
+  Result =
+      GET_OR_DISTINCT(DIEnumerator, (Context, Value, isUnsigned.Val, name.Val));
+
   return false;
 }
 
diff --git a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
index c0ec80e9c01..374e3152816 100644
--- a/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
+++ b/llvm/lib/Bitcode/Reader/MetadataLoader.cpp
@@ -1200,10 +1200,11 @@ Error MetadataLoader::MetadataLoaderImpl::parseOneMetadata(
     if (Record.size() != 3)
       return error("Invalid record");
 
-    IsDistinct = Record[0];
+    IsDistinct = Record[0] & 1;
+    bool IsUnsigned = Record[0] & 2;
     MetadataList.assignValue(
         GET_OR_DISTINCT(DIEnumerator, (Context, unrotateSign(Record[1]),
-                                       getMDString(Record[2]))),
+                                       IsUnsigned, getMDString(Record[2]))),
         NextMetadataNo);
     NextMetadataNo++;
     break;
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index fd9cde17847..8c65e951bfa 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -1457,7 +1457,7 @@ void ModuleBitcodeWriter::writeDISubrange(const DISubrange *N,
 void ModuleBitcodeWriter::writeDIEnumerator(const DIEnumerator *N,
                                             SmallVectorImpl<uint64_t> &Record,
                                             unsigned Abbrev) {
-  Record.push_back(N->isDistinct());
+  Record.push_back((N->isUnsigned() << 1) | N->isDistinct());
   Record.push_back(rotateSign(N->getValue()));
   Record.push_back(VE.getMetadataOrNullID(N->getRawName()));
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
index 0e6ed1c349f..939d13faec0 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
@@ -1427,6 +1427,15 @@ void DwarfUnit::constructArrayTypeDIE(DIE &Buffer, const DICompositeType *CTy) {
 }
 
 void DwarfUnit::constructEnumTypeDIE(DIE &Buffer, const DICompositeType *CTy) {
+  const DIType *DTy = resolve(CTy->getBaseType());
+  bool IsUnsigned = DTy && isUnsignedDIType(DD, DTy);
+  if (DTy && DD->getDwarfVersion() >= 3)
+    addType(Buffer, DTy);
+  if (DD->getDwarfVersion() >= 4 && (CTy->getFlags() & DINode::FlagFixedEnum)) {
+    assert(DTy);
+    addFlag(Buffer, dwarf::DW_AT_enum_class);
+  }
+
   DINodeArray Elements = CTy->getElements();
 
   // Add enumerators to enumeration type.
@@ -1436,16 +1445,10 @@ void DwarfUnit::constructEnumTypeDIE(DIE &Buffer, const DICompositeType *CTy) {
       DIE &Enumerator = createAndAddDIE(dwarf::DW_TAG_enumerator, Buffer);
       StringRef Name = Enum->getName();
       addString(Enumerator, dwarf::DW_AT_name, Name);
-      int64_t Value = Enum->getValue();
-      addSInt(Enumerator, dwarf::DW_AT_const_value, dwarf::DW_FORM_sdata,
-              Value);
+      auto Value = static_cast<uint64_t>(Enum->getValue());
+      addConstantValue(Enumerator, IsUnsigned, Value);
     }
   }
-  const DIType *DTy = resolve(CTy->getBaseType());
-  if (DTy) {
-    addType(Buffer, DTy);
-    addFlag(Buffer, dwarf::DW_AT_enum_class);
-  }
 }
 
 void DwarfUnit::constructContainingTypeDIEs() {
diff --git a/llvm/lib/IR/AsmWriter.cpp b/llvm/lib/IR/AsmWriter.cpp
index d641a63c21d..444a3419350 100644
--- a/llvm/lib/IR/AsmWriter.cpp
+++ b/llvm/lib/IR/AsmWriter.cpp
@@ -1629,7 +1629,13 @@ static void writeDIEnumerator(raw_ostream &Out, const DIEnumerator *N,
   Out << "!DIEnumerator(";
   MDFieldPrinter Printer(Out);
   Printer.printString("name", N->getName(), /* ShouldSkipEmpty */ false);
-  Printer.printInt("value", N->getValue(), /* ShouldSkipZero */ false);
+  if (N->isUnsigned()) {
+    auto Value = static_cast<uint64_t>(N->getValue());
+    Printer.printInt("value", Value, /* ShouldSkipZero */ false);
+    Printer.printBool("isUnsigned", true);
+  } else {
+    Printer.printInt("value", N->getValue(), /* ShouldSkipZero */ false);
+  }
   Out << ")";
 }
 
diff --git a/llvm/lib/IR/DIBuilder.cpp b/llvm/lib/IR/DIBuilder.cpp
index ed3e28144d1..f9aca8afec9 100644
--- a/llvm/lib/IR/DIBuilder.cpp
+++ b/llvm/lib/IR/DIBuilder.cpp
@@ -233,9 +233,10 @@ DIMacroFile *DIBuilder::createTempMacroFile(DIMacroFile *Parent,
   return MF;
 }
 
-DIEnumerator *DIBuilder::createEnumerator(StringRef Name, int64_t Val) {
+DIEnumerator *DIBuilder::createEnumerator(StringRef Name, int64_t Val,
+                                          bool IsUnsigned) {
   assert(!Name.empty() && "Unable to create enumerator without name");
-  return DIEnumerator::get(VMContext, Val, Name);
+  return DIEnumerator::get(VMContext, Val, IsUnsigned, Name);
 }
 
 DIBasicType *DIBuilder::createUnspecifiedType(StringRef Name) {
@@ -492,11 +493,12 @@ DISubroutineType *DIBuilder::createSubroutineType(DITypeRefArray ParameterTypes,
 DICompositeType *DIBuilder::createEnumerationType(
     DIScope *Scope, StringRef Name, DIFile *File, unsigned LineNumber,
     uint64_t SizeInBits, uint32_t AlignInBits, DINodeArray Elements,
-    DIType *UnderlyingType, StringRef UniqueIdentifier) {
+    DIType *UnderlyingType, StringRef UniqueIdentifier, bool IsFixed) {
   auto *CTy = DICompositeType::get(
       VMContext, dwarf::DW_TAG_enumeration_type, Name, File, LineNumber,
       getNonCompileUnitScope(Scope), UnderlyingType, SizeInBits, AlignInBits, 0,
-      DINode::FlagZero, Elements, 0, nullptr, nullptr, UniqueIdentifier);
+      IsFixed ? DINode::FlagFixedEnum : DINode::FlagZero, Elements, 0, nullptr,
+      nullptr, UniqueIdentifier);
   AllEnumTypes.push_back(CTy);
   trackIfUnresolved(CTy);
   return CTy;
diff --git a/llvm/lib/IR/DebugInfoMetadata.cpp b/llvm/lib/IR/DebugInfoMetadata.cpp
index db097e1487d..7c20ec86e34 100644
--- a/llvm/lib/IR/DebugInfoMetadata.cpp
+++ b/llvm/lib/IR/DebugInfoMetadata.cpp
@@ -263,12 +263,12 @@ DISubrange *DISubrange::getImpl(LLVMContext &Context, Metadata *CountNode,
 }
 
 DIEnumerator *DIEnumerator::getImpl(LLVMContext &Context, int64_t Value,
-                                    MDString *Name, StorageType Storage,
-                                    bool ShouldCreate) {
+                                    bool IsUnsigned, MDString *Name,
+                                    StorageType Storage, bool ShouldCreate) {
   assert(isCanonical(Name) && "Expected canonical MDString");
-  DEFINE_GETIMPL_LOOKUP(DIEnumerator, (Value, Name));
+  DEFINE_GETIMPL_LOOKUP(DIEnumerator, (Value, IsUnsigned, Name));
   Metadata *Ops[] = {Name};
-  DEFINE_GETIMPL_STORE(DIEnumerator, (Value), Ops);
+  DEFINE_GETIMPL_STORE(DIEnumerator, (Value, IsUnsigned), Ops);
 }
 
 DIBasicType *DIBasicType::getImpl(LLVMContext &Context, unsigned Tag,
diff --git a/llvm/lib/IR/LLVMContextImpl.h b/llvm/lib/IR/LLVMContextImpl.h
index db7f368230d..c4cd7850f79 100644
--- a/llvm/lib/IR/LLVMContextImpl.h
+++ b/llvm/lib/IR/LLVMContextImpl.h
@@ -354,13 +354,17 @@ template <> struct MDNodeKeyImpl<DISubrange> {
 template <> struct MDNodeKeyImpl<DIEnumerator> {
   int64_t Value;
   MDString *Name;
+  bool IsUnsigned;
 
-  MDNodeKeyImpl(int64_t Value, MDString *Name) : Value(Value), Name(Name) {}
+  MDNodeKeyImpl(int64_t Value, bool IsUnsigned, MDString *Name)
+      : Value(Value), Name(Name), IsUnsigned(IsUnsigned) {}
   MDNodeKeyImpl(const DIEnumerator *N)
-      : Value(N->getValue()), Name(N->getRawName()) {}
+      : Value(N->getValue()), Name(N->getRawName()),
+        IsUnsigned(N->isUnsigned()) {}
 
   bool isKeyOf(const DIEnumerator *RHS) const {
-    return Value == RHS->getValue() && Name == RHS->getRawName();
+    return Value == RHS->getValue() && IsUnsigned == RHS->isUnsigned() &&
+           Name == RHS->getRawName();
   }
 
   unsigned getHashValue() const { return hash_combine(Value, Name); }