IsFunctionStart = 1 << 2,
};
};
+
+enum class CodeViewContainer { ObjectFile, Pdb };
+
+inline uint32_t alignOf(CodeViewContainer Container) {
+ if (Container == CodeViewContainer::ObjectFile)
+ return 1;
+ return 4;
+}
}
}
Error mapByteVectorTail(ArrayRef<uint8_t> &Bytes);
Error mapByteVectorTail(std::vector<uint8_t> &Bytes);
+ Error padToAlignment(uint32_t Align);
Error skipPadding();
private:
class DebugSubsectionRecord {
public:
DebugSubsectionRecord();
- DebugSubsectionRecord(DebugSubsectionKind Kind, BinaryStreamRef Data);
+ DebugSubsectionRecord(DebugSubsectionKind Kind, BinaryStreamRef Data,
+ CodeViewContainer Container);
- static Error initialize(BinaryStreamRef Stream, DebugSubsectionRecord &Info);
+ static Error initialize(BinaryStreamRef Stream, DebugSubsectionRecord &Info,
+ CodeViewContainer Container);
uint32_t getRecordLength() const;
DebugSubsectionKind kind() const;
BinaryStreamRef getRecordData() const;
private:
+ CodeViewContainer Container;
DebugSubsectionKind Kind;
BinaryStreamRef Data;
};
class DebugSubsectionRecordBuilder {
public:
- DebugSubsectionRecordBuilder(DebugSubsectionKind Kind, DebugSubsection &Frag);
+ DebugSubsectionRecordBuilder(DebugSubsectionKind Kind, DebugSubsection &Frag,
+ CodeViewContainer Container);
uint32_t calculateSerializedLength();
Error commit(BinaryStreamWriter &Writer);
private:
+ CodeViewContainer Container;
DebugSubsectionKind Kind;
DebugSubsection &Frag;
};
static Error extract(BinaryStreamRef Stream, uint32_t &Length,
codeview::DebugSubsectionRecord &Info) {
- if (auto EC = codeview::DebugSubsectionRecord::initialize(Stream, Info))
+ // FIXME: We need to pass the container type through to this function, but
+ // VarStreamArray doesn't easily support stateful contexts. In practice
+ // this isn't super important since the subsection header describes its
+ // length and we can just skip it. It's more important when writing.
+ if (auto EC = codeview::DebugSubsectionRecord::initialize(
+ Stream, Info, codeview::CodeViewContainer::Pdb))
return EC;
Length = Info.getRecordLength();
return Error::success();
class SymbolVisitorDelegate;
class SymbolDeserializer : public SymbolVisitorCallbacks {
struct MappingInfo {
- explicit MappingInfo(ArrayRef<uint8_t> RecordData)
+ MappingInfo(ArrayRef<uint8_t> RecordData, CodeViewContainer Container)
: Stream(RecordData, llvm::support::little), Reader(Stream),
- Mapping(Reader) {}
+ Mapping(Reader, Container) {}
BinaryByteStream Stream;
BinaryStreamReader Reader;
public:
template <typename T> static Error deserializeAs(CVSymbol Symbol, T &Record) {
- SymbolDeserializer S(nullptr);
+ // If we're just deserializing one record, then don't worry about alignment
+ // as there's nothing that comes after.
+ SymbolDeserializer S(nullptr, CodeViewContainer::ObjectFile);
if (auto EC = S.visitSymbolBegin(Symbol))
return EC;
if (auto EC = S.visitKnownRecord(Symbol, Record))
return Error::success();
}
- explicit SymbolDeserializer(SymbolVisitorDelegate *Delegate)
- : Delegate(Delegate) {}
+ explicit SymbolDeserializer(SymbolVisitorDelegate *Delegate,
+ CodeViewContainer Container)
+ : Delegate(Delegate), Container(Container) {}
Error visitSymbolBegin(CVSymbol &Record) override {
assert(!Mapping && "Already in a symbol mapping!");
- Mapping = llvm::make_unique<MappingInfo>(Record.content());
+ Mapping = llvm::make_unique<MappingInfo>(Record.content(), Container);
return Mapping->Mapping.visitSymbolBegin(Record);
}
Error visitSymbolEnd(CVSymbol &Record) override {
return Error::success();
}
+ CodeViewContainer Container;
SymbolVisitorDelegate *Delegate;
std::unique_ptr<MappingInfo> Mapping;
};
class CVSymbolDumper {
public:
CVSymbolDumper(ScopedPrinter &W, TypeCollection &Types,
+ CodeViewContainer Container,
std::unique_ptr<SymbolDumpDelegate> ObjDelegate,
bool PrintRecordBytes)
- : W(W), Types(Types), ObjDelegate(std::move(ObjDelegate)),
+ : W(W), Types(Types), Container(Container),
+ ObjDelegate(std::move(ObjDelegate)),
PrintRecordBytes(PrintRecordBytes) {}
/// Dumps one type record. Returns false if there was a type parsing error,
private:
ScopedPrinter &W;
TypeCollection &Types;
+ CodeViewContainer Container;
std::unique_ptr<SymbolDumpDelegate> ObjDelegate;
bool PrintRecordBytes;
namespace codeview {
class SymbolRecordMapping : public SymbolVisitorCallbacks {
public:
- explicit SymbolRecordMapping(BinaryStreamReader &Reader) : IO(Reader) {}
- explicit SymbolRecordMapping(BinaryStreamWriter &Writer) : IO(Writer) {}
+ explicit SymbolRecordMapping(BinaryStreamReader &Reader,
+ CodeViewContainer Container)
+ : IO(Reader), Container(Container) {}
+ explicit SymbolRecordMapping(BinaryStreamWriter &Writer,
+ CodeViewContainer Container)
+ : IO(Writer), Container(Container) {}
Error visitSymbolBegin(CVSymbol &Record) override;
Error visitSymbolEnd(CVSymbol &Record) override;
private:
Optional<SymbolKind> Kind;
+ CodeViewContainer Container;
CodeViewRecordIO IO;
};
}
public:
template <typename SymType>
- static CVSymbol writeOneSymbol(SymType &Sym, BumpPtrAllocator &Storage) {
+ static CVSymbol writeOneSymbol(SymType &Sym, BumpPtrAllocator &Storage,
+ CodeViewContainer Container) {
CVSymbol Result;
Result.Type = static_cast<SymbolKind>(Sym.Kind);
- SymbolSerializer Serializer(Storage);
+ SymbolSerializer Serializer(Storage, Container);
consumeError(Serializer.visitSymbolBegin(Result));
consumeError(Serializer.visitKnownRecord(Result, Sym));
consumeError(Serializer.visitSymbolEnd(Result));
return Result;
}
- explicit SymbolSerializer(BumpPtrAllocator &Storage);
+ SymbolSerializer(BumpPtrAllocator &Storage, CodeViewContainer Container);
virtual Error visitSymbolBegin(CVSymbol &Record) override;
virtual Error visitSymbolEnd(CVSymbol &Record) override;
struct SymbolRecord {
std::shared_ptr<detail::SymbolRecordBase> Symbol;
- codeview::CVSymbol toCodeViewSymbol(BumpPtrAllocator &Allocator) const;
+ codeview::CVSymbol
+ toCodeViewSymbol(BumpPtrAllocator &Allocator,
+ codeview::CodeViewContainer Container) const;
static Expected<SymbolRecord> fromCodeViewSymbol(codeview::CVSymbol Symbol);
};
Error CodeViewRecordIO::endRecord() {
assert(!Limits.empty() && "Not in a record!");
Limits.pop_back();
+ // We would like to assert that we actually read / wrote all the bytes that we
+ // expected to for this record, but unfortunately we can't do this. Some
+ // producers such as MASM over-allocate for certain types of records and
+ // commit the extraneous data, so when reading we can't be sure every byte
+ // will have been read. And when writing we over-allocate temporarily since
+ // we don't know how big the record is until we're finished writing it, so
+ // even though we don't commit the extraneous data, we still can't guarantee
+ // we're at the end of the allocated data.
return Error::success();
}
return *Min;
}
+Error CodeViewRecordIO::padToAlignment(uint32_t Align) {
+ if (isReading())
+ return Reader->padToAlignment(Align);
+ return Writer->padToAlignment(Align);
+}
+
Error CodeViewRecordIO::skipPadding() {
assert(!isWriting() && "Cannot skip padding while writing!");
using namespace llvm::codeview;
DebugSubsectionRecord::DebugSubsectionRecord()
- : Kind(DebugSubsectionKind::None) {}
+ : Kind(DebugSubsectionKind::None),
+ Container(CodeViewContainer::ObjectFile) {}
DebugSubsectionRecord::DebugSubsectionRecord(DebugSubsectionKind Kind,
- BinaryStreamRef Data)
- : Kind(Kind), Data(Data) {}
+ BinaryStreamRef Data,
+ CodeViewContainer Container)
+ : Kind(Kind), Data(Data), Container(Container) {}
Error DebugSubsectionRecord::initialize(BinaryStreamRef Stream,
- DebugSubsectionRecord &Info) {
+ DebugSubsectionRecord &Info,
+ CodeViewContainer Container) {
const DebugSubsectionHeader *Header;
BinaryStreamReader Reader(Stream);
if (auto EC = Reader.readObject(Header))
}
if (auto EC = Reader.readStreamRef(Info.Data, Header->Length))
return EC;
+ Info.Container = Container;
Info.Kind = Kind;
return Error::success();
}
uint32_t DebugSubsectionRecord::getRecordLength() const {
uint32_t Result = sizeof(DebugSubsectionHeader) + Data.getLength();
- assert(Result % 4 == 0);
+ assert(Result % alignOf(Container) == 0);
return Result;
}
BinaryStreamRef DebugSubsectionRecord::getRecordData() const { return Data; }
DebugSubsectionRecordBuilder::DebugSubsectionRecordBuilder(
- DebugSubsectionKind Kind, DebugSubsection &Frag)
- : Kind(Kind), Frag(Frag) {}
+ DebugSubsectionKind Kind, DebugSubsection &Frag,
+ CodeViewContainer Container)
+ : Kind(Kind), Frag(Frag), Container(Container) {}
uint32_t DebugSubsectionRecordBuilder::calculateSerializedLength() {
uint32_t Size = sizeof(DebugSubsectionHeader) +
- alignTo(Frag.calculateSerializedSize(), 4);
+ alignTo(Frag.calculateSerializedSize(), alignOf(Container));
return Size;
}
Error DebugSubsectionRecordBuilder::commit(BinaryStreamWriter &Writer) {
+ assert(Writer.getOffset() % alignOf(Container) == 0 &&
+ "Debug Subsection not properly aligned");
+
DebugSubsectionHeader Header;
Header.Kind = uint32_t(Kind);
Header.Length = calculateSerializedLength() - sizeof(DebugSubsectionHeader);
return EC;
if (auto EC = Frag.commit(Writer))
return EC;
- if (auto EC = Writer.padToAlignment(4))
+ if (auto EC = Writer.padToAlignment(alignOf(Container)))
return EC;
return Error::success();
Error CVSymbolDumper::dump(CVRecord<SymbolKind> &Record) {
SymbolVisitorCallbackPipeline Pipeline;
- SymbolDeserializer Deserializer(ObjDelegate.get());
+ SymbolDeserializer Deserializer(ObjDelegate.get(), Container);
CVSymbolDumperImpl Dumper(Types, ObjDelegate.get(), W, PrintRecordBytes);
Pipeline.addCallbackToPipeline(Deserializer);
Error CVSymbolDumper::dump(const CVSymbolArray &Symbols) {
SymbolVisitorCallbackPipeline Pipeline;
- SymbolDeserializer Deserializer(ObjDelegate.get());
+ SymbolDeserializer Deserializer(ObjDelegate.get(), Container);
CVSymbolDumperImpl Dumper(Types, ObjDelegate.get(), W, PrintRecordBytes);
Pipeline.addCallbackToPipeline(Deserializer);
}
Error SymbolRecordMapping::visitSymbolEnd(CVSymbol &Record) {
+ error(IO.padToAlignment(alignOf(Container)));
error(IO.endRecord());
return Error::success();
}
using namespace llvm;
using namespace llvm::codeview;
-SymbolSerializer::SymbolSerializer(BumpPtrAllocator &Allocator)
- : Storage(Allocator), RecordBuffer(MaxRecordLength), Stream(RecordBuffer, llvm::support::little),
- Writer(Stream), Mapping(Writer) { }
+SymbolSerializer::SymbolSerializer(BumpPtrAllocator &Allocator,
+ CodeViewContainer Container)
+ : Storage(Allocator), RecordBuffer(MaxRecordLength),
+ Stream(RecordBuffer, llvm::support::little), Writer(Stream),
+ Mapping(Writer, Container) {}
Error SymbolSerializer::visitSymbolBegin(CVSymbol &Record) {
assert(!CurrentSymbol.hasValue() && "Already in a symbol mapping!");
void DbiModuleDescriptorBuilder::addSymbol(CVSymbol Symbol) {
Symbols.push_back(Symbol);
- SymbolByteSize += Symbol.data().size();
+ // Symbols written to a PDB file are required to be 4 byte aligned. The same
+ // is not true of object files.
+ assert(Symbol.length() % alignOf(CodeViewContainer::Pdb) == 0 &&
+ "Invalid Symbol alignment!");
+ SymbolByteSize += Symbol.length();
}
void DbiModuleDescriptorBuilder::addSourceFile(StringRef Path) {
if (auto EC = SymbolWriter.writeStreamRef(RecordsRef))
return EC;
// TODO: Write C11 Line data
-
+ assert(SymbolWriter.getOffset() % alignOf(CodeViewContainer::Pdb) == 0 &&
+ "Invalid debug section alignment!");
for (const auto &Builder : C13Builders) {
assert(Builder && "Empty C13 Fragment Builder!");
if (auto EC = Builder->commit(SymbolWriter))
C13Builders.push_back(nullptr);
this->LineInfo.push_back(std::move(Lines));
- C13Builders.push_back(
- llvm::make_unique<DebugSubsectionRecordBuilder>(Frag.kind(), Frag));
+ C13Builders.push_back(llvm::make_unique<DebugSubsectionRecordBuilder>(
+ Frag.kind(), Frag, CodeViewContainer::Pdb));
}
void DbiModuleDescriptorBuilder::addC13Fragment(
C13Builders.push_back(nullptr);
this->Inlinees.push_back(std::move(Inlinees));
- C13Builders.push_back(
- llvm::make_unique<DebugSubsectionRecordBuilder>(Frag.kind(), Frag));
+ C13Builders.push_back(llvm::make_unique<DebugSubsectionRecordBuilder>(
+ Frag.kind(), Frag, CodeViewContainer::Pdb));
}
void DbiModuleDescriptorBuilder::setC13FileChecksums(
ChecksumInfo = std::move(Checksums);
C13Builders[0] = llvm::make_unique<DebugSubsectionRecordBuilder>(
- ChecksumInfo->kind(), *ChecksumInfo);
+ ChecksumInfo->kind(), *ChecksumInfo, CodeViewContainer::Pdb);
}
virtual ~SymbolRecordBase() {}
virtual void map(yaml::IO &io) = 0;
virtual codeview::CVSymbol
- toCodeViewSymbol(BumpPtrAllocator &Allocator) const = 0;
+ toCodeViewSymbol(BumpPtrAllocator &Allocator,
+ CodeViewContainer Container) const = 0;
virtual Error fromCodeViewSymbol(codeview::CVSymbol Type) = 0;
};
void map(yaml::IO &io) override;
codeview::CVSymbol
- toCodeViewSymbol(BumpPtrAllocator &Allocator) const override {
- return SymbolSerializer::writeOneSymbol(Symbol, Allocator);
+ toCodeViewSymbol(BumpPtrAllocator &Allocator,
+ CodeViewContainer Container) const override {
+ return SymbolSerializer::writeOneSymbol(Symbol, Allocator, Container);
}
Error fromCodeViewSymbol(codeview::CVSymbol CVS) override {
return SymbolDeserializer::deserializeAs<T>(CVS, Symbol);
}
CVSymbol CodeViewYAML::SymbolRecord::toCodeViewSymbol(
- BumpPtrAllocator &Allocator) const {
- return Symbol->toCodeViewSymbol(Allocator);
+ BumpPtrAllocator &Allocator, CodeViewContainer Container) const {
+ return Symbol->toCodeViewSymbol(Allocator, Container);
}
namespace llvm {
; (for example if we don't write the entire stream)
;
; RUN: llvm-pdbdump pdb2yaml -stream-metadata -stream-directory \
-; RUN: -pdb-stream -tpi-stream %p/Inputs/empty.pdb > %t.1
+; RUN: -pdb-stream -tpi-stream -dbi-module-syms %p/Inputs/empty.pdb > %t.1
; RUN: llvm-pdbdump yaml2pdb -pdb=%t.2 %t.1
; RUN: llvm-pdbdump pdb2yaml -pdb-stream -tpi-stream \
-; RUN: -no-file-headers %p/Inputs/empty.pdb > %t.3
+; RUN: -dbi-module-syms -no-file-headers %p/Inputs/empty.pdb > %t.3
; RUN: llvm-pdbdump pdb2yaml -pdb-stream -tpi-stream \
-; RUN: -no-file-headers %t.2 > %t.4
+; RUN: -dbi-module-syms -no-file-headers %t.2 > %t.4
; RUN: diff %t.3 %t.4
auto &Types = *ExpectedTypes;
ListScope SS(P, "Symbols");
- codeview::CVSymbolDumper SD(P, Types, nullptr, false);
+ codeview::CVSymbolDumper SD(P, Types, CodeViewContainer::Pdb, nullptr,
+ false);
bool HadError = false;
for (auto S : ModS.symbols(&HadError)) {
DictScope LL(P, "");
return ExpectedTypes.takeError();
auto &Tpi = *ExpectedTypes;
- codeview::CVSymbolDumper SD(P, Tpi, nullptr, false);
+ codeview::CVSymbolDumper SD(P, Tpi, CodeViewContainer::Pdb, nullptr, false);
bool HadError = false;
for (auto S : Publics->getSymbols(&HadError)) {
DictScope DD(P, "");
ExitOnErr(DbiBuilder.addModuleSourceFile(MI.Mod, S));
if (MI.Modi.hasValue()) {
const auto &ModiStream = *MI.Modi;
- for (auto Symbol : ModiStream.Symbols)
- ModiBuilder.addSymbol(Symbol.toCodeViewSymbol(Allocator));
+ for (auto Symbol : ModiStream.Symbols) {
+ ModiBuilder.addSymbol(
+ Symbol.toCodeViewSymbol(Allocator, CodeViewContainer::Pdb));
+ }
}
if (MI.FileLineInfo.hasValue()) {
const auto &FLI = *MI.FileLineInfo;
Subsection.bytes_end());
auto CODD = llvm::make_unique<COFFObjectDumpDelegate>(*this, Section, Obj,
SectionContents);
- CVSymbolDumper CVSD(W, Types, std::move(CODD), opts::CodeViewSubsectionBytes);
+ CVSymbolDumper CVSD(W, Types, CodeViewContainer::ObjectFile, std::move(CODD),
+ opts::CodeViewSubsectionBytes);
CVSymbolArray Symbols;
BinaryStreamReader Reader(BinaryData, llvm::support::little);
if (auto EC = Reader.readArray(Symbols, Reader.getLength())) {