[DWARFYAML] Implement debug_names support

llvm/include/llvm/ObjectYAML/DWARFEmitter.h

@@ -42,6 +42,7 @@ Error emitDebugAddr(raw_ostream &OS, const Data &DI);
 Error emitDebugStrOffsets(raw_ostream &OS, const Data &DI);
 Error emitDebugRnglists(raw_ostream &OS, const Data &DI);
 Error emitDebugLoclists(raw_ostream &OS, const Data &DI);
+Error emitDebugNames(raw_ostream &OS, const Data &DI);
 
 std::function<Error(raw_ostream &, const Data &)>
 getDWARFEmitterByName(StringRef SecName);

llvm/include/llvm/ObjectYAML/DWARFYAML.h

@@ -118,6 +118,28 @@ struct Unit {
   std::vector<Entry> Entries;
 };
 
+struct IdxForm {
+  dwarf::Index Idx;
+  dwarf::Form Form;
+};
+
+struct DebugNameAbbreviation {
+  yaml::Hex64 Code;
+  dwarf::Tag Tag;
+  std::vector<IdxForm> Indices;
+};
+
+struct DebugNameEntry {
+  yaml::Hex32 NameStrp;
+  yaml::Hex64 Code;
+  std::vector<yaml::Hex64> Values;
+};
+
+struct DebugNamesSection {
+  std::vector<DebugNameAbbreviation> Abbrevs;
+  std::vector<DebugNameEntry> Entries;
+};
+
 struct File {
   StringRef Name;
   uint64_t DirIdx;
@@ -228,6 +250,7 @@ struct Data {
   std::vector<LineTable> DebugLines;
   std::optional<std::vector<ListTable<RnglistEntry>>> DebugRnglists;
   std::optional<std::vector<ListTable<LoclistEntry>>> DebugLoclists;
+  std::optional<DebugNamesSection> DebugNames;
 
   bool isEmpty() const;
 
@@ -276,6 +299,9 @@ LLVM_YAML_IS_SEQUENCE_VECTOR(
     llvm::DWARFYAML::ListEntries<DWARFYAML::LoclistEntry>)
 LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::LoclistEntry)
 LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::DWARFOperation)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::DebugNameEntry)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::DebugNameAbbreviation)
+LLVM_YAML_IS_SEQUENCE_VECTOR(llvm::DWARFYAML::IdxForm)
 
 namespace llvm {
 namespace yaml {
@@ -324,6 +350,19 @@ template <> struct MappingTraits<DWARFYAML::Unit> {
   static void mapping(IO &IO, DWARFYAML::Unit &Unit);
 };
 
+template <> struct MappingTraits<DWARFYAML::DebugNamesSection> {
+  static void mapping(IO &IO, DWARFYAML::DebugNamesSection &);
+};
+template <> struct MappingTraits<DWARFYAML::DebugNameEntry> {
+  static void mapping(IO &IO, DWARFYAML::DebugNameEntry &);
+};
+template <> struct MappingTraits<DWARFYAML::DebugNameAbbreviation> {
+  static void mapping(IO &IO, DWARFYAML::DebugNameAbbreviation &);
+};
+template <> struct MappingTraits<DWARFYAML::IdxForm> {
+  static void mapping(IO &IO, DWARFYAML::IdxForm &);
+};
+
 template <> struct MappingTraits<DWARFYAML::Entry> {
   static void mapping(IO &IO, DWARFYAML::Entry &Entry);
 };
@@ -437,6 +476,16 @@ template <> struct ScalarEnumerationTraits<dwarf::Form> {
   }
 };
 
+#define HANDLE_DW_IDX(unused, name)                                            \
+  io.enumCase(value, "DW_IDX_" #name, dwarf::DW_IDX_##name);
+
+template <> struct ScalarEnumerationTraits<dwarf::Index> {
+  static void enumeration(IO &io, dwarf::Index &value) {
+#include "llvm/BinaryFormat/Dwarf.def"
+    io.enumFallback<Hex16>(value);
+  }
+};
+
 #define HANDLE_DW_UT(unused, name)                                             \
   io.enumCase(value, "DW_UT_" #name, dwarf::DW_UT_##name);
 

llvm/lib/ObjectYAML/DWARFEmitter.cpp

@@ -691,6 +691,194 @@ Error DWARFYAML::emitDebugStrOffsets(raw_ostream &OS, const Data &DI) {
   return Error::success();
 }
 
+namespace {
+/// Emits the header for a DebugNames section.
+void emitDebugNamesHeader(raw_ostream &OS, bool IsLittleEndian,
+                          uint32_t NameCount, uint32_t AbbrevSize,
+                          uint32_t CombinedSizeOtherParts) {
+  // Use the same AugmentationString as AsmPrinter.
+  StringRef AugmentationString = "LLVM0700";
+  size_t TotalSize = CombinedSizeOtherParts + 5 * sizeof(uint32_t) +
+                     2 * sizeof(uint16_t) + sizeof(NameCount) +
+                     sizeof(AbbrevSize) + AugmentationString.size();
+  writeInteger(uint32_t(TotalSize), OS, IsLittleEndian); // Unit length
+
+  // Everything below is included in total size.
+  writeInteger(uint16_t(5), OS, IsLittleEndian); // Version
+  writeInteger(uint16_t(0), OS, IsLittleEndian); // Padding
+  writeInteger(uint32_t(1), OS, IsLittleEndian); // Compilation Unit count
+  writeInteger(uint32_t(0), OS, IsLittleEndian); // Local Type Unit count
+  writeInteger(uint32_t(0), OS, IsLittleEndian); // Foreign Type Unit count
+  writeInteger(uint32_t(0), OS, IsLittleEndian); // Bucket count
+  writeInteger(NameCount, OS, IsLittleEndian);
+  writeInteger(AbbrevSize, OS, IsLittleEndian);
+  writeInteger(uint32_t(AugmentationString.size()), OS, IsLittleEndian);
+  OS.write(AugmentationString.data(), AugmentationString.size());
+  return;
+}
+
+/// Emits the abbreviations for a DebugNames section.
+std::string
+emitDebugNamesAbbrev(ArrayRef<DWARFYAML::DebugNameAbbreviation> Abbrevs) {
+  std::string Data;
+  raw_string_ostream OS(Data);
+  for (const DWARFYAML::DebugNameAbbreviation &Abbrev : Abbrevs) {
+    encodeULEB128(Abbrev.Code, OS);
+    encodeULEB128(Abbrev.Tag, OS);
+    for (auto [Idx, Form] : Abbrev.Indices) {
+      encodeULEB128(Idx, OS);
+      encodeULEB128(Form, OS);
+    }
+    encodeULEB128(0, OS);
+    encodeULEB128(0, OS);
+  }
+  encodeULEB128(0, OS);
+  return Data;
+}
+
+/// Emits a simple CU offsets list for a DebugNames section containing a single
+/// CU at offset 0.
+std::string emitDebugNamesCUOffsets(bool IsLittleEndian) {
+  std::string Data;
+  raw_string_ostream OS(Data);
+  writeInteger(uint32_t(0), OS, IsLittleEndian);
+  return Data;
+}
+
+/// Emits the "NameTable" for a DebugNames section; according to the spec, it
+/// consists of two arrays: an array of string offsets, followed immediately by
+/// an array of entry offsets. The string offsets are emitted in the order
+/// provided in `Entries`.
+std::string emitDebugNamesNameTable(
+    bool IsLittleEndian,
+    const DenseMap<uint32_t, std::vector<DWARFYAML::DebugNameEntry>> &Entries,
+    ArrayRef<uint32_t> EntryPoolOffsets) {
+  assert(Entries.size() == EntryPoolOffsets.size());
+
+  std::string Data;
+  raw_string_ostream OS(Data);
+
+  for (uint32_t Strp : make_first_range(Entries))
+    writeInteger(Strp, OS, IsLittleEndian);
+  for (uint32_t PoolOffset : EntryPoolOffsets)
+    writeInteger(PoolOffset, OS, IsLittleEndian);
+  return Data;
+}
+
+/// Groups entries based on their name (strp) code and returns a map.
+DenseMap<uint32_t, std::vector<DWARFYAML::DebugNameEntry>>
+groupEntries(ArrayRef<DWARFYAML::DebugNameEntry> Entries) {
+  DenseMap<uint32_t, std::vector<DWARFYAML::DebugNameEntry>> StrpToEntries;
+  for (const DWARFYAML::DebugNameEntry &Entry : Entries)
+    StrpToEntries[Entry.NameStrp].push_back(Entry);
+  return StrpToEntries;
+}
+
+/// Finds the abbreviation whose code is AbbrevCode and returns a list
+/// containing the expected size of all non-zero-length forms.
+Expected<SmallVector<uint8_t>>
+getNonZeroDataSizesFor(uint32_t AbbrevCode,
+                       ArrayRef<DWARFYAML::DebugNameAbbreviation> Abbrevs) {
+  const auto *AbbrevIt = find_if(Abbrevs, [&](const auto &Abbrev) {
+    return Abbrev.Code.value == AbbrevCode;
+  });
+  if (AbbrevIt == Abbrevs.end())
+    return createStringError(inconvertibleErrorCode(),
+                             "did not find an Abbreviation for this code");
+
+  SmallVector<uint8_t> DataSizes;
+  dwarf::FormParams Params{/*Version=*/5, /*AddrSize=*/4, dwarf::DWARF32};
+  for (auto [Idx, Form] : AbbrevIt->Indices) {
+    std::optional<uint8_t> FormSize = dwarf::getFixedFormByteSize(Form, Params);
+    if (!FormSize)
+      return createStringError(inconvertibleErrorCode(),
+                               "unsupported Form for YAML debug_names emitter");
+    if (FormSize == 0)
+      continue;
+    DataSizes.push_back(*FormSize);
+  }
+  return DataSizes;
+}
+
+struct PoolOffsetsAndData {
+  std::string PoolData;
+  std::vector<uint32_t> PoolOffsets;
+};
+
+/// Emits the entry pool and returns an array of offsets containing the start
+/// offset for the entries of each unique name.
+/// Verifies that the provided number of data values match those expected by
+/// the abbreviation table.
+Expected<PoolOffsetsAndData> emitDebugNamesEntryPool(
+    bool IsLittleEndian,
+    const DenseMap<uint32_t, std::vector<DWARFYAML::DebugNameEntry>>
+        &StrpToEntries,
+    ArrayRef<DWARFYAML::DebugNameAbbreviation> Abbrevs) {
+  PoolOffsetsAndData Result;
+  raw_string_ostream OS(Result.PoolData);
+
+  for (ArrayRef<DWARFYAML::DebugNameEntry> EntriesWithSameName :
+       make_second_range(StrpToEntries)) {
+    Result.PoolOffsets.push_back(Result.PoolData.size());
+
+    for (const DWARFYAML::DebugNameEntry &Entry : EntriesWithSameName) {
+      encodeULEB128(Entry.Code, OS);
+
+      Expected<SmallVector<uint8_t>> DataSizes =
+          getNonZeroDataSizesFor(Entry.Code, Abbrevs);
+      if (!DataSizes)
+        return DataSizes.takeError();
+      if (DataSizes->size() != Entry.Values.size())
+        return createStringError(
+            inconvertibleErrorCode(),
+            "mismatch between provided and required number of values");
+
+      for (auto [Value, ValueSize] : zip_equal(Entry.Values, *DataSizes))
+        if (Error E =
+                writeVariableSizedInteger(Value, ValueSize, OS, IsLittleEndian))
+          return std::move(E);
+    }
+    encodeULEB128(0, OS);
+  }
+
+  return Result;
+}
+} // namespace
+
+Error DWARFYAML::emitDebugNames(raw_ostream &OS, const Data &DI) {
+  assert(DI.DebugNames && "unexpected emitDebugNames() call");
+  const DebugNamesSection DebugNames = DI.DebugNames.value();
+
+  DenseMap<uint32_t, std::vector<DebugNameEntry>> StrpToEntries =
+      groupEntries(DebugNames.Entries);
+
+  // Emit all sub-sections into individual strings so that we may compute
+  // relative offsets and sizes.
+  Expected<PoolOffsetsAndData> PoolInfo = emitDebugNamesEntryPool(
+      DI.IsLittleEndian, StrpToEntries, DebugNames.Abbrevs);
+  if (!PoolInfo)
+    return PoolInfo.takeError();
+  std::string NamesTableData = emitDebugNamesNameTable(
+      DI.IsLittleEndian, StrpToEntries, PoolInfo->PoolOffsets);
+
+  std::string AbbrevData = emitDebugNamesAbbrev(DebugNames.Abbrevs);
+  std::string CUOffsetsData = emitDebugNamesCUOffsets(DI.IsLittleEndian);
+
+  size_t TotalSize = PoolInfo->PoolData.size() + NamesTableData.size() +
+                     AbbrevData.size() + CUOffsetsData.size();
+
+  // Start real emission by combining all individual strings.
+  emitDebugNamesHeader(OS, DI.IsLittleEndian, StrpToEntries.size(),
+                       AbbrevData.size(), TotalSize);
+  OS.write(CUOffsetsData.data(), CUOffsetsData.size());
+  // No local TUs, no foreign TUs, no hash lookups table.
+  OS.write(NamesTableData.data(), NamesTableData.size());
+  OS.write(AbbrevData.data(), AbbrevData.size());
+  OS.write(PoolInfo->PoolData.data(), PoolInfo->PoolData.size());
+
+  return Error::success();
+}
+
 static Error checkOperandCount(StringRef EncodingString,
                                ArrayRef<yaml::Hex64> Values,
                                uint64_t ExpectedOperands) {
@@ -1024,6 +1212,7 @@ DWARFYAML::getDWARFEmitterByName(StringRef SecName) {
           .Case("debug_rnglists", DWARFYAML::emitDebugRnglists)
           .Case("debug_str", DWARFYAML::emitDebugStr)
           .Case("debug_str_offsets", DWARFYAML::emitDebugStrOffsets)
+          .Case("debug_names", DWARFYAML::emitDebugNames)
           .Default([&](raw_ostream &, const DWARFYAML::Data &) {
             return createStringError(errc::not_supported,
                                      SecName + " is not supported");

llvm/lib/ObjectYAML/DWARFYAML.cpp

@@ -52,6 +52,8 @@ SetVector<StringRef> DWARFYAML::Data::getNonEmptySectionNames() const {
     SecNames.insert("debug_rnglists");
   if (DebugLoclists)
     SecNames.insert("debug_loclists");
+  if (DebugNames)
+    SecNames.insert("debug_names");
   return SecNames;
 }
 
@@ -105,6 +107,7 @@ void MappingTraits<DWARFYAML::Data>::mapping(IO &IO, DWARFYAML::Data &DWARF) {
   IO.mapOptional("debug_str_offsets", DWARF.DebugStrOffsets);
   IO.mapOptional("debug_rnglists", DWARF.DebugRnglists);
   IO.mapOptional("debug_loclists", DWARF.DebugLoclists);
+  IO.mapOptional("debug_names", DWARF.DebugNames);
   IO.setContext(OldContext);
 }
 
@@ -122,6 +125,32 @@ void MappingTraits<DWARFYAML::Abbrev>::mapping(IO &IO,
   IO.mapOptional("Attributes", Abbrev.Attributes);
 }
 
+void MappingTraits<DWARFYAML::IdxForm>::mapping(IO &IO,
+                                                DWARFYAML::IdxForm &IdxForm) {
+  IO.mapRequired("Idx", IdxForm.Idx);
+  IO.mapRequired("Form", IdxForm.Form);
+}
+
+void MappingTraits<DWARFYAML::DebugNameAbbreviation>::mapping(
+    IO &IO, DWARFYAML::DebugNameAbbreviation &DebugNameAbbreviation) {
+  IO.mapRequired("Code", DebugNameAbbreviation.Code);
+  IO.mapRequired("Tag", DebugNameAbbreviation.Tag);
+  IO.mapRequired("Indices", DebugNameAbbreviation.Indices);
+}
+
+void MappingTraits<DWARFYAML::DebugNameEntry>::mapping(
+    IO &IO, DWARFYAML::DebugNameEntry &DebugNameEntry) {
+  IO.mapRequired("Name", DebugNameEntry.NameStrp);
+  IO.mapRequired("Code", DebugNameEntry.Code);
+  IO.mapOptional("Values", DebugNameEntry.Values);
+}
+
+void MappingTraits<DWARFYAML::DebugNamesSection>::mapping(
+    IO &IO, DWARFYAML::DebugNamesSection &DebugNames) {
+  IO.mapRequired("Abbreviations", DebugNames.Abbrevs);
+  IO.mapRequired("Entries", DebugNames.Entries);
+}
+
 void MappingTraits<DWARFYAML::AttributeAbbrev>::mapping(
     IO &IO, DWARFYAML::AttributeAbbrev &AttAbbrev) {
   IO.mapRequired("Attribute", AttAbbrev.Attribute);