//===- DbiStream.cpp - PDB Dbi Stream (Stream 3) Access -------------------===// // // The LLVM Compiler Infrastructure // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #include "llvm/DebugInfo/PDB/Raw/DbiStream.h" #include "llvm/DebugInfo/CodeView/StreamArray.h" #include "llvm/DebugInfo/CodeView/StreamReader.h" #include "llvm/DebugInfo/PDB/Raw/InfoStream.h" #include "llvm/DebugInfo/PDB/Raw/ModInfo.h" #include "llvm/DebugInfo/PDB/Raw/NameHashTable.h" #include "llvm/DebugInfo/PDB/Raw/PDBFile.h" #include "llvm/DebugInfo/PDB/Raw/RawConstants.h" #include "llvm/DebugInfo/PDB/Raw/RawError.h" using namespace llvm; using namespace llvm::pdb; using namespace llvm::support; namespace { // Some of the values are stored in bitfields. Since this needs to be portable // across compilers and architectures (big / little endian in particular) we // can't use the actual structures below, but must instead do the shifting // and masking ourselves. The struct definitions are provided for reference. // struct DbiFlags { // uint16_t IncrementalLinking : 1; // True if linked incrementally // uint16_t IsStripped : 1; // True if private symbols were stripped. // uint16_t HasCTypes : 1; // True if linked with /debug:ctypes. // uint16_t Reserved : 13; //}; const uint16_t FlagIncrementalMask = 0x0001; const uint16_t FlagStrippedMask = 0x0002; const uint16_t FlagHasCTypesMask = 0x0004; // struct DbiBuildNo { // uint16_t MinorVersion : 8; // uint16_t MajorVersion : 7; // uint16_t NewVersionFormat : 1; //}; const uint16_t BuildMinorMask = 0x00FF; const uint16_t BuildMinorShift = 0; const uint16_t BuildMajorMask = 0x7F00; const uint16_t BuildMajorShift = 8; } struct DbiStream::HeaderInfo { little32_t VersionSignature; ulittle32_t VersionHeader; ulittle32_t Age; // Should match InfoStream. ulittle16_t GlobalSymbolStreamIndex; // Global symbol stream # ulittle16_t BuildNumber; // See DbiBuildNo structure. ulittle16_t PublicSymbolStreamIndex; // Public symbols stream # ulittle16_t PdbDllVersion; // version of mspdbNNN.dll ulittle16_t SymRecordStreamIndex; // Symbol records stream # ulittle16_t PdbDllRbld; // rbld number of mspdbNNN.dll little32_t ModiSubstreamSize; // Size of module info stream little32_t SecContrSubstreamSize; // Size of sec. contribution stream little32_t SectionMapSize; // Size of sec. map substream little32_t FileInfoSize; // Size of file info substream little32_t TypeServerSize; // Size of type server map ulittle32_t MFCTypeServerIndex; // Index of MFC Type Server little32_t OptionalDbgHdrSize; // Size of DbgHeader info little32_t ECSubstreamSize; // Size of EC stream (what is EC?) ulittle16_t Flags; // See DbiFlags enum. ulittle16_t MachineType; // See PDB_MachineType enum. ulittle32_t Reserved; // Pad to 64 bytes }; DbiStream::DbiStream(PDBFile &File) : Pdb(File), Stream(StreamDBI, File), Header(nullptr) { static_assert(sizeof(HeaderInfo) == 64, "Invalid HeaderInfo size!"); } DbiStream::~DbiStream() {} Error DbiStream::reload() { codeview::StreamReader Reader(Stream); if (Stream.getLength() < sizeof(HeaderInfo)) return make_error(raw_error_code::corrupt_file, "DBI Stream does not contain a header."); if (auto EC = Reader.readObject(Header)) return make_error(raw_error_code::corrupt_file, "DBI Stream does not contain a header."); if (Header->VersionSignature != -1) return make_error(raw_error_code::corrupt_file, "Invalid DBI version signature."); // Require at least version 7, which should be present in all PDBs // produced in the last decade and allows us to avoid having to // special case all kinds of complicated arcane formats. if (Header->VersionHeader < PdbDbiV70) return make_error(raw_error_code::corrupt_file, "Unsupported DBI version."); auto InfoStream = Pdb.getPDBInfoStream(); if (auto EC = InfoStream.takeError()) return EC; if (Header->Age != InfoStream.get().getAge()) return make_error(raw_error_code::corrupt_file, "DBI Age does not match PDB Age."); if (Stream.getLength() != sizeof(HeaderInfo) + Header->ModiSubstreamSize + Header->SecContrSubstreamSize + Header->SectionMapSize + Header->FileInfoSize + Header->TypeServerSize + Header->OptionalDbgHdrSize + Header->ECSubstreamSize) return make_error(raw_error_code::corrupt_file, "DBI Length does not equal sum of substreams."); // Only certain substreams are guaranteed to be aligned. Validate // them here. if (Header->ModiSubstreamSize % sizeof(uint32_t) != 0) return make_error(raw_error_code::corrupt_file, "DBI MODI substream not aligned."); if (Header->SecContrSubstreamSize % sizeof(uint32_t) != 0) return make_error( raw_error_code::corrupt_file, "DBI section contribution substream not aligned."); if (Header->SectionMapSize % sizeof(uint32_t) != 0) return make_error(raw_error_code::corrupt_file, "DBI section map substream not aligned."); if (Header->FileInfoSize % sizeof(uint32_t) != 0) return make_error(raw_error_code::corrupt_file, "DBI file info substream not aligned."); if (Header->TypeServerSize % sizeof(uint32_t) != 0) return make_error(raw_error_code::corrupt_file, "DBI type server substream not aligned."); // Since each ModInfo in the stream is a variable length, we have to iterate // them to know how many there actually are. codeview::VarStreamArray ModInfoArray; if (auto EC = Reader.readArray(ModInfoArray, Header->ModiSubstreamSize)) return EC; for (auto &Info : ModInfoArray) { ModuleInfos.emplace_back(Info); } if (auto EC = Reader.readStreamRef(SecContrSubstream, Header->SecContrSubstreamSize)) return EC; if (auto EC = Reader.readStreamRef(SecMapSubstream, Header->SectionMapSize)) return EC; if (auto EC = Reader.readStreamRef(FileInfoSubstream, Header->FileInfoSize)) return EC; if (auto EC = Reader.readStreamRef(TypeServerMapSubstream, Header->TypeServerSize)) return EC; if (auto EC = Reader.readStreamRef(ECSubstream, Header->ECSubstreamSize)) return EC; if (auto EC = Reader.readArray(DbgStreams, Header->OptionalDbgHdrSize / sizeof(ulittle16_t))) return EC; if (auto EC = initializeFileInfo()) return EC; if (Reader.bytesRemaining() > 0) return make_error(raw_error_code::corrupt_file, "Found unexpected bytes in DBI Stream."); codeview::StreamReader ECReader(ECSubstream); if (auto EC = ECNames.load(ECReader)) return EC; return Error::success(); } PdbRaw_DbiVer DbiStream::getDbiVersion() const { uint32_t Value = Header->VersionHeader; return static_cast(Value); } uint32_t DbiStream::getAge() const { return Header->Age; } uint16_t DbiStream::getPublicSymbolStreamIndex() const { return Header->PublicSymbolStreamIndex; } uint16_t DbiStream::getGlobalSymbolStreamIndex() const { return Header->GlobalSymbolStreamIndex; } bool DbiStream::isIncrementallyLinked() const { return (Header->Flags & FlagIncrementalMask) != 0; } bool DbiStream::hasCTypes() const { return (Header->Flags & FlagHasCTypesMask) != 0; } bool DbiStream::isStripped() const { return (Header->Flags & FlagStrippedMask) != 0; } uint16_t DbiStream::getBuildMajorVersion() const { return (Header->BuildNumber & BuildMajorMask) >> BuildMajorShift; } uint16_t DbiStream::getBuildMinorVersion() const { return (Header->BuildNumber & BuildMinorMask) >> BuildMinorShift; } uint32_t DbiStream::getPdbDllVersion() const { return Header->PdbDllVersion; } uint32_t DbiStream::getSymRecordStreamIndex() const { return Header->SymRecordStreamIndex; } PDB_Machine DbiStream::getMachineType() const { uint16_t Machine = Header->MachineType; return static_cast(Machine); } ArrayRef DbiStream::modules() const { return ModuleInfos; } Error DbiStream::initializeFileInfo() { struct FileInfoSubstreamHeader { ulittle16_t NumModules; // Total # of modules, should match number of // records in the ModuleInfo substream. ulittle16_t NumSourceFiles; // Total # of source files. This value is not // accurate because PDB actually supports more // than 64k source files, so we ignore it and // compute the value from other stream fields. }; // The layout of the FileInfoSubstream is like this: // struct { // ulittle16_t NumModules; // ulittle16_t NumSourceFiles; // ulittle16_t ModIndices[NumModules]; // ulittle16_t ModFileCounts[NumModules]; // ulittle32_t FileNameOffsets[NumSourceFiles]; // char Names[][NumSourceFiles]; // }; // with the caveat that `NumSourceFiles` cannot be trusted, so // it is computed by summing `ModFileCounts`. // const FileInfoSubstreamHeader *FH; codeview::StreamReader FISR(FileInfoSubstream); if (auto EC = FISR.readObject(FH)) return EC; // The number of modules in the stream should be the same as reported by // the FileInfoSubstreamHeader. if (FH->NumModules != ModuleInfos.size()) return make_error(raw_error_code::corrupt_file, "FileInfo substream count doesn't match DBI."); codeview::FixedStreamArray ModIndexArray; codeview::FixedStreamArray ModFileCountArray; codeview::FixedStreamArray FileNameOffsets; // First is an array of `NumModules` module indices. This is not used for the // same reason that `NumSourceFiles` is not used. It's an array of uint16's, // but it's possible there are more than 64k source files, which would imply // more than 64k modules (e.g. object files) as well. So we ignore this // field. if (auto EC = FISR.readArray(ModIndexArray, ModuleInfos.size())) return EC; if (auto EC = FISR.readArray(ModFileCountArray, ModuleInfos.size())) return EC; // Compute the real number of source files. uint32_t NumSourceFiles = 0; for (auto Count : ModFileCountArray) NumSourceFiles += Count; // This is the array that in the reference implementation corresponds to // `ModInfo::FileLayout::FileNameOffs`, which is commented there as being a // pointer. Due to the mentioned problems of pointers causing difficulty // when reading from the file on 64-bit systems, we continue to ignore that // field in `ModInfo`, and instead build a vector of StringRefs and stores // them in `ModuleInfoEx`. The value written to and read from the file is // not used anyway, it is only there as a way to store the offsets for the // purposes of later accessing the names at runtime. if (auto EC = FISR.readArray(FileNameOffsets, NumSourceFiles)) return EC; codeview::StreamRef NamesBufferRef; if (auto EC = FISR.readStreamRef(NamesBufferRef)) return EC; codeview::StreamReader Names(NamesBufferRef); // We go through each ModuleInfo, determine the number N of source files for // that module, and then get the next N offsets from the Offsets array, using // them to get the corresponding N names from the Names buffer and associating // each one with the corresponding module. uint32_t NextFileIndex = 0; for (size_t I = 0; I < ModuleInfos.size(); ++I) { uint32_t NumFiles = ModFileCountArray[I]; ModuleInfos[I].SourceFiles.resize(NumFiles); for (size_t J = 0; J < NumFiles; ++J, ++NextFileIndex) { uint32_t FileOffset = FileNameOffsets[NextFileIndex]; Names.setOffset(FileOffset); if (auto EC = Names.readZeroString(ModuleInfos[I].SourceFiles[J])) return EC; } } return Error::success(); } uint32_t DbiStream::getDebugStreamIndex(DbgHeaderType Type) const { return DbgStreams[static_cast(Type)]; }