diff options
Diffstat (limited to 'lib/Bitcode/Reader/BitcodeReader.cpp')
| -rw-r--r-- | lib/Bitcode/Reader/BitcodeReader.cpp | 1931 |
1 files changed, 1589 insertions, 342 deletions
diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp index c04e8b9f1f37d..2e670d584ecc0 100644 --- a/lib/Bitcode/Reader/BitcodeReader.cpp +++ b/lib/Bitcode/Reader/BitcodeReader.cpp @@ -27,6 +27,7 @@ #include "llvm/IR/Module.h" #include "llvm/IR/OperandTraits.h" #include "llvm/IR/Operator.h" +#include "llvm/IR/FunctionInfo.h" #include "llvm/IR/ValueHandle.h" #include "llvm/Support/DataStream.h" #include "llvm/Support/ManagedStatic.h" @@ -93,35 +94,35 @@ public: void resolveConstantForwardRefs(); }; -class BitcodeReaderMDValueList { +class BitcodeReaderMetadataList { unsigned NumFwdRefs; bool AnyFwdRefs; unsigned MinFwdRef; unsigned MaxFwdRef; - std::vector<TrackingMDRef> MDValuePtrs; + std::vector<TrackingMDRef> MetadataPtrs; LLVMContext &Context; public: - BitcodeReaderMDValueList(LLVMContext &C) + BitcodeReaderMetadataList(LLVMContext &C) : NumFwdRefs(0), AnyFwdRefs(false), Context(C) {} // vector compatibility methods - unsigned size() const { return MDValuePtrs.size(); } - void resize(unsigned N) { MDValuePtrs.resize(N); } - void push_back(Metadata *MD) { MDValuePtrs.emplace_back(MD); } - void clear() { MDValuePtrs.clear(); } - Metadata *back() const { return MDValuePtrs.back(); } - void pop_back() { MDValuePtrs.pop_back(); } - bool empty() const { return MDValuePtrs.empty(); } + unsigned size() const { return MetadataPtrs.size(); } + void resize(unsigned N) { MetadataPtrs.resize(N); } + void push_back(Metadata *MD) { MetadataPtrs.emplace_back(MD); } + void clear() { MetadataPtrs.clear(); } + Metadata *back() const { return MetadataPtrs.back(); } + void pop_back() { MetadataPtrs.pop_back(); } + bool empty() const { return MetadataPtrs.empty(); } Metadata *operator[](unsigned i) const { - assert(i < MDValuePtrs.size()); - return MDValuePtrs[i]; + assert(i < MetadataPtrs.size()); + return MetadataPtrs[i]; } void shrinkTo(unsigned N) { assert(N <= size() && "Invalid shrinkTo request!"); - MDValuePtrs.resize(N); + MetadataPtrs.resize(N); } Metadata *getValueFwdRef(unsigned Idx); @@ -131,17 +132,27 @@ public: class BitcodeReader : public GVMaterializer { LLVMContext &Context; - DiagnosticHandlerFunction DiagnosticHandler; Module *TheModule = nullptr; std::unique_ptr<MemoryBuffer> Buffer; std::unique_ptr<BitstreamReader> StreamFile; BitstreamCursor Stream; + // Next offset to start scanning for lazy parsing of function bodies. uint64_t NextUnreadBit = 0; + // Last function offset found in the VST. + uint64_t LastFunctionBlockBit = 0; bool SeenValueSymbolTable = false; + uint64_t VSTOffset = 0; + // Contains an arbitrary and optional string identifying the bitcode producer + std::string ProducerIdentification; + // Number of module level metadata records specified by the + // MODULE_CODE_METADATA_VALUES record. + unsigned NumModuleMDs = 0; + // Support older bitcode without the MODULE_CODE_METADATA_VALUES record. + bool SeenModuleValuesRecord = false; std::vector<Type*> TypeList; BitcodeReaderValueList ValueList; - BitcodeReaderMDValueList MDValueList; + BitcodeReaderMetadataList MetadataList; std::vector<Comdat *> ComdatList; SmallVector<Instruction *, 64> InstructionList; @@ -157,7 +168,7 @@ class BitcodeReader : public GVMaterializer { /// is thus not represented here. As such all indices are off by one. std::vector<AttributeSet> MAttributes; - /// \brief The set of attribute groups. + /// The set of attribute groups. std::map<unsigned, AttributeSet> MAttributeGroups; /// While parsing a function body, this is a list of the basic blocks for the @@ -208,23 +219,24 @@ class BitcodeReader : public GVMaterializer { /// (e.g.) blockaddress forward references. bool WillMaterializeAllForwardRefs = false; - /// Functions that have block addresses taken. This is usually empty. - SmallPtrSet<const Function *, 4> BlockAddressesTaken; - /// True if any Metadata block has been materialized. bool IsMetadataMaterialized = false; bool StripDebugInfo = false; + /// Functions that need to be matched with subprograms when upgrading old + /// metadata. + SmallDenseMap<Function *, DISubprogram *, 16> FunctionsWithSPs; + + std::vector<std::string> BundleTags; + public: std::error_code error(BitcodeError E, const Twine &Message); std::error_code error(BitcodeError E); std::error_code error(const Twine &Message); - BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler); - BitcodeReader(LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler); + BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context); + BitcodeReader(LLVMContext &Context); ~BitcodeReader() override { freeState(); } std::error_code materializeForwardReferencedFunctions(); @@ -233,11 +245,9 @@ public: void releaseBuffer(); - bool isDematerializable(const GlobalValue *GV) const override; std::error_code materialize(GlobalValue *GV) override; - std::error_code materializeModule(Module *M) override; + std::error_code materializeModule() override; std::vector<StructType *> getIdentifiedStructTypes() const override; - void dematerialize(GlobalValue *GV) override; /// \brief Main interface to parsing a bitcode buffer. /// \returns true if an error occurred. @@ -249,6 +259,9 @@ public: /// \returns true if an error occurred. ErrorOr<std::string> parseTriple(); + /// Cheap mechanism to just extract the identification block out of bitcode. + ErrorOr<std::string> parseIdentificationBlock(); + static uint64_t decodeSignRotatedValue(uint64_t V); /// Materialize any deferred Metadata block. @@ -256,7 +269,20 @@ public: void setStripDebugInfo() override; + /// Save the mapping between the metadata values and the corresponding + /// value id that were recorded in the MetadataList during parsing. If + /// OnlyTempMD is true, then only record those entries that are still + /// temporary metadata. This interface is used when metadata linking is + /// performed as a postpass, such as during function importing. + void saveMetadataList(DenseMap<const Metadata *, unsigned> &MetadataToIDs, + bool OnlyTempMD) override; + private: + /// Parse the "IDENTIFICATION_BLOCK_ID" block, populate the + // ProducerIdentification data member, and do some basic enforcement on the + // "epoch" encoded in the bitcode. + std::error_code parseBitcodeVersion(); + std::vector<StructType *> IdentifiedStructTypes; StructType *createIdentifiedStructType(LLVMContext &Context, StringRef Name); StructType *createIdentifiedStructType(LLVMContext &Context); @@ -268,7 +294,7 @@ private: return ValueList.getValueFwdRef(ID, Ty); } Metadata *getFnMetadataByID(unsigned ID) { - return MDValueList.getValueFwdRef(ID); + return MetadataList.getValueFwdRef(ID); } BasicBlock *getBasicBlock(unsigned ID) const { if (ID >= FunctionBBs.size()) return nullptr; // Invalid ID @@ -351,21 +377,28 @@ private: /// a corresponding error code. std::error_code parseAlignmentValue(uint64_t Exponent, unsigned &Alignment); std::error_code parseAttrKind(uint64_t Code, Attribute::AttrKind *Kind); - std::error_code parseModule(bool Resume, bool ShouldLazyLoadMetadata = false); + std::error_code parseModule(uint64_t ResumeBit, + bool ShouldLazyLoadMetadata = false); std::error_code parseAttributeBlock(); std::error_code parseAttributeGroupBlock(); std::error_code parseTypeTable(); std::error_code parseTypeTableBody(); + std::error_code parseOperandBundleTags(); - std::error_code parseValueSymbolTable(); + ErrorOr<Value *> recordValue(SmallVectorImpl<uint64_t> &Record, + unsigned NameIndex, Triple &TT); + std::error_code parseValueSymbolTable(uint64_t Offset = 0); std::error_code parseConstants(); + std::error_code rememberAndSkipFunctionBodies(); std::error_code rememberAndSkipFunctionBody(); /// Save the positions of the Metadata blocks and skip parsing the blocks. std::error_code rememberAndSkipMetadata(); std::error_code parseFunctionBody(Function *F); std::error_code globalCleanup(); std::error_code resolveGlobalAndAliasInits(); - std::error_code parseMetadata(); + std::error_code parseMetadata(bool ModuleLevel = false); + std::error_code parseMetadataKinds(); + std::error_code parseMetadataKindRecord(SmallVectorImpl<uint64_t> &Record); std::error_code parseMetadataAttachment(Function &F); ErrorOr<std::string> parseModuleTriple(); std::error_code parseUseLists(); @@ -376,6 +409,94 @@ private: Function *F, DenseMap<Function *, uint64_t>::iterator DeferredFunctionInfoIterator); }; + +/// Class to manage reading and parsing function summary index bitcode +/// files/sections. +class FunctionIndexBitcodeReader { + DiagnosticHandlerFunction DiagnosticHandler; + + /// Eventually points to the function index built during parsing. + FunctionInfoIndex *TheIndex = nullptr; + + std::unique_ptr<MemoryBuffer> Buffer; + std::unique_ptr<BitstreamReader> StreamFile; + BitstreamCursor Stream; + + /// \brief Used to indicate whether we are doing lazy parsing of summary data. + /// + /// If false, the summary section is fully parsed into the index during + /// the initial parse. Otherwise, if true, the caller is expected to + /// invoke \a readFunctionSummary for each summary needed, and the summary + /// section is thus parsed lazily. + bool IsLazy = false; + + /// Used to indicate whether caller only wants to check for the presence + /// of the function summary bitcode section. All blocks are skipped, + /// but the SeenFuncSummary boolean is set. + bool CheckFuncSummaryPresenceOnly = false; + + /// Indicates whether we have encountered a function summary section + /// yet during parsing, used when checking if file contains function + /// summary section. + bool SeenFuncSummary = false; + + /// \brief Map populated during function summary section parsing, and + /// consumed during ValueSymbolTable parsing. + /// + /// Used to correlate summary records with VST entries. For the per-module + /// index this maps the ValueID to the parsed function summary, and + /// for the combined index this maps the summary record's bitcode + /// offset to the function summary (since in the combined index the + /// VST records do not hold value IDs but rather hold the function + /// summary record offset). + DenseMap<uint64_t, std::unique_ptr<FunctionSummary>> SummaryMap; + + /// Map populated during module path string table parsing, from the + /// module ID to a string reference owned by the index's module + /// path string table, used to correlate with combined index function + /// summary records. + DenseMap<uint64_t, StringRef> ModuleIdMap; + +public: + std::error_code error(BitcodeError E, const Twine &Message); + std::error_code error(BitcodeError E); + std::error_code error(const Twine &Message); + + FunctionIndexBitcodeReader(MemoryBuffer *Buffer, + DiagnosticHandlerFunction DiagnosticHandler, + bool IsLazy = false, + bool CheckFuncSummaryPresenceOnly = false); + FunctionIndexBitcodeReader(DiagnosticHandlerFunction DiagnosticHandler, + bool IsLazy = false, + bool CheckFuncSummaryPresenceOnly = false); + ~FunctionIndexBitcodeReader() { freeState(); } + + void freeState(); + + void releaseBuffer(); + + /// Check if the parser has encountered a function summary section. + bool foundFuncSummary() { return SeenFuncSummary; } + + /// \brief Main interface to parsing a bitcode buffer. + /// \returns true if an error occurred. + std::error_code parseSummaryIndexInto(std::unique_ptr<DataStreamer> Streamer, + FunctionInfoIndex *I); + + /// \brief Interface for parsing a function summary lazily. + std::error_code parseFunctionSummary(std::unique_ptr<DataStreamer> Streamer, + FunctionInfoIndex *I, + size_t FunctionSummaryOffset); + +private: + std::error_code parseModule(); + std::error_code parseValueSymbolTable(); + std::error_code parseEntireSummary(); + std::error_code parseModuleStringTable(); + std::error_code initStream(std::unique_ptr<DataStreamer> Streamer); + std::error_code initStreamFromBuffer(); + std::error_code initLazyStream(std::unique_ptr<DataStreamer> Streamer); +}; } // namespace BitcodeDiagnosticInfo::BitcodeDiagnosticInfo(std::error_code EC, @@ -397,43 +518,51 @@ static std::error_code error(DiagnosticHandlerFunction DiagnosticHandler, return error(DiagnosticHandler, EC, EC.message()); } -static std::error_code error(DiagnosticHandlerFunction DiagnosticHandler, +static std::error_code error(LLVMContext &Context, std::error_code EC, const Twine &Message) { - return error(DiagnosticHandler, - make_error_code(BitcodeError::CorruptedBitcode), Message); + return error([&](const DiagnosticInfo &DI) { Context.diagnose(DI); }, EC, + Message); +} + +static std::error_code error(LLVMContext &Context, std::error_code EC) { + return error(Context, EC, EC.message()); +} + +static std::error_code error(LLVMContext &Context, const Twine &Message) { + return error(Context, make_error_code(BitcodeError::CorruptedBitcode), + Message); } std::error_code BitcodeReader::error(BitcodeError E, const Twine &Message) { - return ::error(DiagnosticHandler, make_error_code(E), Message); + if (!ProducerIdentification.empty()) { + return ::error(Context, make_error_code(E), + Message + " (Producer: '" + ProducerIdentification + + "' Reader: 'LLVM " + LLVM_VERSION_STRING "')"); + } + return ::error(Context, make_error_code(E), Message); } std::error_code BitcodeReader::error(const Twine &Message) { - return ::error(DiagnosticHandler, - make_error_code(BitcodeError::CorruptedBitcode), Message); + if (!ProducerIdentification.empty()) { + return ::error(Context, make_error_code(BitcodeError::CorruptedBitcode), + Message + " (Producer: '" + ProducerIdentification + + "' Reader: 'LLVM " + LLVM_VERSION_STRING "')"); + } + return ::error(Context, make_error_code(BitcodeError::CorruptedBitcode), + Message); } std::error_code BitcodeReader::error(BitcodeError E) { - return ::error(DiagnosticHandler, make_error_code(E)); + return ::error(Context, make_error_code(E)); } -static DiagnosticHandlerFunction getDiagHandler(DiagnosticHandlerFunction F, - LLVMContext &C) { - if (F) - return F; - return [&C](const DiagnosticInfo &DI) { C.diagnose(DI); }; -} - -BitcodeReader::BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler) - : Context(Context), - DiagnosticHandler(getDiagHandler(DiagnosticHandler, Context)), - Buffer(Buffer), ValueList(Context), MDValueList(Context) {} +BitcodeReader::BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context) + : Context(Context), Buffer(Buffer), ValueList(Context), + MetadataList(Context) {} -BitcodeReader::BitcodeReader(LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler) - : Context(Context), - DiagnosticHandler(getDiagHandler(DiagnosticHandler, Context)), - Buffer(nullptr), ValueList(Context), MDValueList(Context) {} +BitcodeReader::BitcodeReader(LLVMContext &Context) + : Context(Context), Buffer(nullptr), ValueList(Context), + MetadataList(Context) {} std::error_code BitcodeReader::materializeForwardReferencedFunctions() { if (WillMaterializeAllForwardRefs) @@ -472,7 +601,7 @@ void BitcodeReader::freeState() { Buffer = nullptr; std::vector<Type*>().swap(TypeList); ValueList.clear(); - MDValueList.clear(); + MetadataList.clear(); std::vector<Comdat *>().swap(ComdatList); std::vector<AttributeSet>().swap(MAttributes); @@ -779,6 +908,8 @@ void BitcodeReaderValueList::assignValue(Value *V, unsigned Idx) { OldV->replaceAllUsesWith(V); delete PrevVal; } + + return; } @@ -904,7 +1035,7 @@ void BitcodeReaderValueList::resolveConstantForwardRefs() { } } -void BitcodeReaderMDValueList::assignValue(Metadata *MD, unsigned Idx) { +void BitcodeReaderMetadataList::assignValue(Metadata *MD, unsigned Idx) { if (Idx == size()) { push_back(MD); return; @@ -913,7 +1044,7 @@ void BitcodeReaderMDValueList::assignValue(Metadata *MD, unsigned Idx) { if (Idx >= size()) resize(Idx+1); - TrackingMDRef &OldMD = MDValuePtrs[Idx]; + TrackingMDRef &OldMD = MetadataPtrs[Idx]; if (!OldMD) { OldMD.reset(MD); return; @@ -925,11 +1056,11 @@ void BitcodeReaderMDValueList::assignValue(Metadata *MD, unsigned Idx) { --NumFwdRefs; } -Metadata *BitcodeReaderMDValueList::getValueFwdRef(unsigned Idx) { +Metadata *BitcodeReaderMetadataList::getValueFwdRef(unsigned Idx) { if (Idx >= size()) resize(Idx + 1); - if (Metadata *MD = MDValuePtrs[Idx]) + if (Metadata *MD = MetadataPtrs[Idx]) return MD; // Track forward refs to be resolved later. @@ -944,11 +1075,11 @@ Metadata *BitcodeReaderMDValueList::getValueFwdRef(unsigned Idx) { // Create and return a placeholder, which will later be RAUW'd. Metadata *MD = MDNode::getTemporary(Context, None).release(); - MDValuePtrs[Idx].reset(MD); + MetadataPtrs[Idx].reset(MD); return MD; } -void BitcodeReaderMDValueList::tryToResolveCycles() { +void BitcodeReaderMetadataList::tryToResolveCycles() { if (!AnyFwdRefs) // Nothing to do. return; @@ -959,7 +1090,7 @@ void BitcodeReaderMDValueList::tryToResolveCycles() { // Resolve any cycles. for (unsigned I = MinFwdRef, E = MaxFwdRef + 1; I != E; ++I) { - auto &MD = MDValuePtrs[I]; + auto &MD = MetadataPtrs[I]; auto *N = dyn_cast_or_null<MDNode>(MD); if (!N) continue; @@ -1102,6 +1233,10 @@ static Attribute::AttrKind getAttrFromCode(uint64_t Code) { return Attribute::Cold; case bitc::ATTR_KIND_CONVERGENT: return Attribute::Convergent; + case bitc::ATTR_KIND_INACCESSIBLEMEM_ONLY: + return Attribute::InaccessibleMemOnly; + case bitc::ATTR_KIND_INACCESSIBLEMEM_OR_ARGMEMONLY: + return Attribute::InaccessibleMemOrArgMemOnly; case bitc::ATTR_KIND_INLINE_HINT: return Attribute::InlineHint; case bitc::ATTR_KIND_IN_REG: @@ -1126,6 +1261,8 @@ static Attribute::AttrKind getAttrFromCode(uint64_t Code) { return Attribute::NoImplicitFloat; case bitc::ATTR_KIND_NO_INLINE: return Attribute::NoInline; + case bitc::ATTR_KIND_NO_RECURSE: + return Attribute::NoRecurse; case bitc::ATTR_KIND_NON_LAZY_BIND: return Attribute::NonLazyBind; case bitc::ATTR_KIND_NON_NULL: @@ -1360,6 +1497,9 @@ std::error_code BitcodeReader::parseTypeTableBody() { case bitc::TYPE_CODE_X86_MMX: // X86_MMX ResultTy = Type::getX86_MMXTy(Context); break; + case bitc::TYPE_CODE_TOKEN: // TOKEN + ResultTy = Type::getTokenTy(Context); + break; case bitc::TYPE_CODE_INTEGER: { // INTEGER: [width] if (Record.size() < 1) return error("Invalid record"); @@ -1524,7 +1664,107 @@ std::error_code BitcodeReader::parseTypeTableBody() { } } -std::error_code BitcodeReader::parseValueSymbolTable() { +std::error_code BitcodeReader::parseOperandBundleTags() { + if (Stream.EnterSubBlock(bitc::OPERAND_BUNDLE_TAGS_BLOCK_ID)) + return error("Invalid record"); + + if (!BundleTags.empty()) + return error("Invalid multiple blocks"); + + SmallVector<uint64_t, 64> Record; + + while (1) { + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + case BitstreamEntry::SubBlock: // Handled for us already. + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } + + // Tags are implicitly mapped to integers by their order. + + if (Stream.readRecord(Entry.ID, Record) != bitc::OPERAND_BUNDLE_TAG) + return error("Invalid record"); + + // OPERAND_BUNDLE_TAG: [strchr x N] + BundleTags.emplace_back(); + if (convertToString(Record, 0, BundleTags.back())) + return error("Invalid record"); + Record.clear(); + } +} + +/// Associate a value with its name from the given index in the provided record. +ErrorOr<Value *> BitcodeReader::recordValue(SmallVectorImpl<uint64_t> &Record, + unsigned NameIndex, Triple &TT) { + SmallString<128> ValueName; + if (convertToString(Record, NameIndex, ValueName)) + return error("Invalid record"); + unsigned ValueID = Record[0]; + if (ValueID >= ValueList.size() || !ValueList[ValueID]) + return error("Invalid record"); + Value *V = ValueList[ValueID]; + + StringRef NameStr(ValueName.data(), ValueName.size()); + if (NameStr.find_first_of(0) != StringRef::npos) + return error("Invalid value name"); + V->setName(NameStr); + auto *GO = dyn_cast<GlobalObject>(V); + if (GO) { + if (GO->getComdat() == reinterpret_cast<Comdat *>(1)) { + if (TT.isOSBinFormatMachO()) + GO->setComdat(nullptr); + else + GO->setComdat(TheModule->getOrInsertComdat(V->getName())); + } + } + return V; +} + +/// Parse the value symbol table at either the current parsing location or +/// at the given bit offset if provided. +std::error_code BitcodeReader::parseValueSymbolTable(uint64_t Offset) { + uint64_t CurrentBit; + // Pass in the Offset to distinguish between calling for the module-level + // VST (where we want to jump to the VST offset) and the function-level + // VST (where we don't). + if (Offset > 0) { + // Save the current parsing location so we can jump back at the end + // of the VST read. + CurrentBit = Stream.GetCurrentBitNo(); + Stream.JumpToBit(Offset * 32); +#ifndef NDEBUG + // Do some checking if we are in debug mode. + BitstreamEntry Entry = Stream.advance(); + assert(Entry.Kind == BitstreamEntry::SubBlock); + assert(Entry.ID == bitc::VALUE_SYMTAB_BLOCK_ID); +#else + // In NDEBUG mode ignore the output so we don't get an unused variable + // warning. + Stream.advance(); +#endif + } + + // Compute the delta between the bitcode indices in the VST (the word offset + // to the word-aligned ENTER_SUBBLOCK for the function block, and that + // expected by the lazy reader. The reader's EnterSubBlock expects to have + // already read the ENTER_SUBBLOCK code (size getAbbrevIDWidth) and BlockID + // (size BlockIDWidth). Note that we access the stream's AbbrevID width here + // just before entering the VST subblock because: 1) the EnterSubBlock + // changes the AbbrevID width; 2) the VST block is nested within the same + // outer MODULE_BLOCK as the FUNCTION_BLOCKs and therefore have the same + // AbbrevID width before calling EnterSubBlock; and 3) when we want to + // jump to the FUNCTION_BLOCK using this offset later, we don't want + // to rely on the stream's AbbrevID width being that of the MODULE_BLOCK. + unsigned FuncBitcodeOffsetDelta = + Stream.getAbbrevIDWidth() + bitc::BlockIDWidth; + if (Stream.EnterSubBlock(bitc::VALUE_SYMTAB_BLOCK_ID)) return error("Invalid record"); @@ -1542,6 +1782,8 @@ std::error_code BitcodeReader::parseValueSymbolTable() { case BitstreamEntry::Error: return error("Malformed block"); case BitstreamEntry::EndBlock: + if (Offset > 0) + Stream.JumpToBit(CurrentBit); return std::error_code(); case BitstreamEntry::Record: // The interesting case. @@ -1554,23 +1796,39 @@ std::error_code BitcodeReader::parseValueSymbolTable() { default: // Default behavior: unknown type. break; case bitc::VST_CODE_ENTRY: { // VST_ENTRY: [valueid, namechar x N] - if (convertToString(Record, 1, ValueName)) - return error("Invalid record"); - unsigned ValueID = Record[0]; - if (ValueID >= ValueList.size() || !ValueList[ValueID]) - return error("Invalid record"); - Value *V = ValueList[ValueID]; - - V->setName(StringRef(ValueName.data(), ValueName.size())); - if (auto *GO = dyn_cast<GlobalObject>(V)) { - if (GO->getComdat() == reinterpret_cast<Comdat *>(1)) { - if (TT.isOSBinFormatMachO()) - GO->setComdat(nullptr); - else - GO->setComdat(TheModule->getOrInsertComdat(V->getName())); - } + ErrorOr<Value *> ValOrErr = recordValue(Record, 1, TT); + if (std::error_code EC = ValOrErr.getError()) + return EC; + ValOrErr.get(); + break; + } + case bitc::VST_CODE_FNENTRY: { + // VST_FNENTRY: [valueid, offset, namechar x N] + ErrorOr<Value *> ValOrErr = recordValue(Record, 2, TT); + if (std::error_code EC = ValOrErr.getError()) + return EC; + Value *V = ValOrErr.get(); + + auto *GO = dyn_cast<GlobalObject>(V); + if (!GO) { + // If this is an alias, need to get the actual Function object + // it aliases, in order to set up the DeferredFunctionInfo entry below. + auto *GA = dyn_cast<GlobalAlias>(V); + if (GA) + GO = GA->getBaseObject(); + assert(GO); } - ValueName.clear(); + + uint64_t FuncWordOffset = Record[1]; + Function *F = dyn_cast<Function>(GO); + assert(F); + uint64_t FuncBitOffset = FuncWordOffset * 32; + DeferredFunctionInfo[F] = FuncBitOffset + FuncBitcodeOffsetDelta; + // Set the LastFunctionBlockBit to point to the last function block. + // Later when parsing is resumed after function materialization, + // we can simply skip that last function block. + if (FuncBitOffset > LastFunctionBlockBit) + LastFunctionBlockBit = FuncBitOffset; break; } case bitc::VST_CODE_BBENTRY: { @@ -1588,19 +1846,51 @@ std::error_code BitcodeReader::parseValueSymbolTable() { } } +/// Parse a single METADATA_KIND record, inserting result in MDKindMap. +std::error_code +BitcodeReader::parseMetadataKindRecord(SmallVectorImpl<uint64_t> &Record) { + if (Record.size() < 2) + return error("Invalid record"); + + unsigned Kind = Record[0]; + SmallString<8> Name(Record.begin() + 1, Record.end()); + + unsigned NewKind = TheModule->getMDKindID(Name.str()); + if (!MDKindMap.insert(std::make_pair(Kind, NewKind)).second) + return error("Conflicting METADATA_KIND records"); + return std::error_code(); +} + static int64_t unrotateSign(uint64_t U) { return U & 1 ? ~(U >> 1) : U >> 1; } -std::error_code BitcodeReader::parseMetadata() { +/// Parse a METADATA_BLOCK. If ModuleLevel is true then we are parsing +/// module level metadata. +std::error_code BitcodeReader::parseMetadata(bool ModuleLevel) { IsMetadataMaterialized = true; - unsigned NextMDValueNo = MDValueList.size(); + unsigned NextMetadataNo = MetadataList.size(); + if (ModuleLevel && SeenModuleValuesRecord) { + // Now that we are parsing the module level metadata, we want to restart + // the numbering of the MD values, and replace temp MD created earlier + // with their real values. If we saw a METADATA_VALUE record then we + // would have set the MetadataList size to the number specified in that + // record, to support parsing function-level metadata first, and we need + // to reset back to 0 to fill the MetadataList in with the parsed module + // The function-level metadata parsing should have reset the MetadataList + // size back to the value reported by the METADATA_VALUE record, saved in + // NumModuleMDs. + assert(NumModuleMDs == MetadataList.size() && + "Expected MetadataList to only contain module level values"); + NextMetadataNo = 0; + } if (Stream.EnterSubBlock(bitc::METADATA_BLOCK_ID)) return error("Invalid record"); SmallVector<uint64_t, 64> Record; - auto getMD = - [&](unsigned ID) -> Metadata *{ return MDValueList.getValueFwdRef(ID); }; + auto getMD = [&](unsigned ID) -> Metadata * { + return MetadataList.getValueFwdRef(ID); + }; auto getMDOrNull = [&](unsigned ID) -> Metadata *{ if (ID) return getMD(ID - 1); @@ -1624,7 +1914,10 @@ std::error_code BitcodeReader::parseMetadata() { case BitstreamEntry::Error: return error("Malformed block"); case BitstreamEntry::EndBlock: - MDValueList.tryToResolveCycles(); + MetadataList.tryToResolveCycles(); + assert((!(ModuleLevel && SeenModuleValuesRecord) || + NumModuleMDs == MetadataList.size()) && + "Inconsistent bitcode: METADATA_VALUES mismatch"); return std::error_code(); case BitstreamEntry::Record: // The interesting case. @@ -1652,7 +1945,8 @@ std::error_code BitcodeReader::parseMetadata() { unsigned Size = Record.size(); NamedMDNode *NMD = TheModule->getOrInsertNamedMetadata(Name); for (unsigned i = 0; i != Size; ++i) { - MDNode *MD = dyn_cast_or_null<MDNode>(MDValueList.getValueFwdRef(Record[i])); + MDNode *MD = + dyn_cast_or_null<MDNode>(MetadataList.getValueFwdRef(Record[i])); if (!MD) return error("Invalid record"); NMD->addOperand(MD); @@ -1669,7 +1963,7 @@ std::error_code BitcodeReader::parseMetadata() { // If this isn't a LocalAsMetadata record, we're dropping it. This used // to be legal, but there's no upgrade path. auto dropRecord = [&] { - MDValueList.assignValue(MDNode::get(Context, None), NextMDValueNo++); + MetadataList.assignValue(MDNode::get(Context, None), NextMetadataNo++); }; if (Record.size() != 2) { dropRecord(); @@ -1682,9 +1976,9 @@ std::error_code BitcodeReader::parseMetadata() { break; } - MDValueList.assignValue( + MetadataList.assignValue( LocalAsMetadata::get(ValueList.getValueFwdRef(Record[1], Ty)), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_OLD_NODE: { @@ -1699,7 +1993,7 @@ std::error_code BitcodeReader::parseMetadata() { if (!Ty) return error("Invalid record"); if (Ty->isMetadataTy()) - Elts.push_back(MDValueList.getValueFwdRef(Record[i+1])); + Elts.push_back(MetadataList.getValueFwdRef(Record[i + 1])); else if (!Ty->isVoidTy()) { auto *MD = ValueAsMetadata::get(ValueList.getValueFwdRef(Record[i + 1], Ty)); @@ -1709,7 +2003,7 @@ std::error_code BitcodeReader::parseMetadata() { } else Elts.push_back(nullptr); } - MDValueList.assignValue(MDNode::get(Context, Elts), NextMDValueNo++); + MetadataList.assignValue(MDNode::get(Context, Elts), NextMetadataNo++); break; } case bitc::METADATA_VALUE: { @@ -1720,9 +2014,9 @@ std::error_code BitcodeReader::parseMetadata() { if (Ty->isMetadataTy() || Ty->isVoidTy()) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( ValueAsMetadata::get(ValueList.getValueFwdRef(Record[1], Ty)), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_DISTINCT_NODE: @@ -1732,10 +2026,10 @@ std::error_code BitcodeReader::parseMetadata() { SmallVector<Metadata *, 8> Elts; Elts.reserve(Record.size()); for (unsigned ID : Record) - Elts.push_back(ID ? MDValueList.getValueFwdRef(ID - 1) : nullptr); - MDValueList.assignValue(IsDistinct ? MDNode::getDistinct(Context, Elts) - : MDNode::get(Context, Elts), - NextMDValueNo++); + Elts.push_back(ID ? MetadataList.getValueFwdRef(ID - 1) : nullptr); + MetadataList.assignValue(IsDistinct ? MDNode::getDistinct(Context, Elts) + : MDNode::get(Context, Elts), + NextMetadataNo++); break; } case bitc::METADATA_LOCATION: { @@ -1744,13 +2038,13 @@ std::error_code BitcodeReader::parseMetadata() { unsigned Line = Record[1]; unsigned Column = Record[2]; - MDNode *Scope = cast<MDNode>(MDValueList.getValueFwdRef(Record[3])); + MDNode *Scope = cast<MDNode>(MetadataList.getValueFwdRef(Record[3])); Metadata *InlinedAt = - Record[4] ? MDValueList.getValueFwdRef(Record[4] - 1) : nullptr; - MDValueList.assignValue( + Record[4] ? MetadataList.getValueFwdRef(Record[4] - 1) : nullptr; + MetadataList.assignValue( GET_OR_DISTINCT(DILocation, Record[0], (Context, Line, Column, Scope, InlinedAt)), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_GENERIC_DEBUG: { @@ -1766,63 +2060,65 @@ std::error_code BitcodeReader::parseMetadata() { auto *Header = getMDString(Record[3]); SmallVector<Metadata *, 8> DwarfOps; for (unsigned I = 4, E = Record.size(); I != E; ++I) - DwarfOps.push_back(Record[I] ? MDValueList.getValueFwdRef(Record[I] - 1) - : nullptr); - MDValueList.assignValue(GET_OR_DISTINCT(GenericDINode, Record[0], - (Context, Tag, Header, DwarfOps)), - NextMDValueNo++); + DwarfOps.push_back( + Record[I] ? MetadataList.getValueFwdRef(Record[I] - 1) : nullptr); + MetadataList.assignValue( + GET_OR_DISTINCT(GenericDINode, Record[0], + (Context, Tag, Header, DwarfOps)), + NextMetadataNo++); break; } case bitc::METADATA_SUBRANGE: { if (Record.size() != 3) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DISubrange, Record[0], (Context, Record[1], unrotateSign(Record[2]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_ENUMERATOR: { if (Record.size() != 3) return error("Invalid record"); - MDValueList.assignValue(GET_OR_DISTINCT(DIEnumerator, Record[0], - (Context, unrotateSign(Record[1]), - getMDString(Record[2]))), - NextMDValueNo++); + MetadataList.assignValue( + GET_OR_DISTINCT( + DIEnumerator, Record[0], + (Context, unrotateSign(Record[1]), getMDString(Record[2]))), + NextMetadataNo++); break; } case bitc::METADATA_BASIC_TYPE: { if (Record.size() != 6) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIBasicType, Record[0], (Context, Record[1], getMDString(Record[2]), Record[3], Record[4], Record[5])), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_DERIVED_TYPE: { if (Record.size() != 12) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIDerivedType, Record[0], (Context, Record[1], getMDString(Record[2]), getMDOrNull(Record[3]), Record[4], getMDOrNull(Record[5]), getMDOrNull(Record[6]), Record[7], Record[8], Record[9], Record[10], getMDOrNull(Record[11]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_COMPOSITE_TYPE: { if (Record.size() != 16) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DICompositeType, Record[0], (Context, Record[1], getMDString(Record[2]), getMDOrNull(Record[3]), Record[4], @@ -1831,17 +2127,17 @@ std::error_code BitcodeReader::parseMetadata() { getMDOrNull(Record[11]), Record[12], getMDOrNull(Record[13]), getMDOrNull(Record[14]), getMDString(Record[15]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_SUBROUTINE_TYPE: { if (Record.size() != 3) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DISubroutineType, Record[0], (Context, Record[1], getMDOrNull(Record[2]))), - NextMDValueNo++); + NextMetadataNo++); break; } @@ -1849,12 +2145,12 @@ std::error_code BitcodeReader::parseMetadata() { if (Record.size() != 6) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIModule, Record[0], (Context, getMDOrNull(Record[1]), - getMDString(Record[2]), getMDString(Record[3]), - getMDString(Record[4]), getMDString(Record[5]))), - NextMDValueNo++); + getMDString(Record[2]), getMDString(Record[3]), + getMDString(Record[4]), getMDString(Record[5]))), + NextMetadataNo++); break; } @@ -1862,185 +2158,260 @@ std::error_code BitcodeReader::parseMetadata() { if (Record.size() != 3) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIFile, Record[0], (Context, getMDString(Record[1]), getMDString(Record[2]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_COMPILE_UNIT: { - if (Record.size() < 14 || Record.size() > 15) + if (Record.size() < 14 || Record.size() > 16) return error("Invalid record"); - MDValueList.assignValue( - GET_OR_DISTINCT( - DICompileUnit, Record[0], - (Context, Record[1], getMDOrNull(Record[2]), - getMDString(Record[3]), Record[4], getMDString(Record[5]), - Record[6], getMDString(Record[7]), Record[8], - getMDOrNull(Record[9]), getMDOrNull(Record[10]), - getMDOrNull(Record[11]), getMDOrNull(Record[12]), - getMDOrNull(Record[13]), Record.size() == 14 ? 0 : Record[14])), - NextMDValueNo++); + // Ignore Record[0], which indicates whether this compile unit is + // distinct. It's always distinct. + MetadataList.assignValue( + DICompileUnit::getDistinct( + Context, Record[1], getMDOrNull(Record[2]), + getMDString(Record[3]), Record[4], getMDString(Record[5]), + Record[6], getMDString(Record[7]), Record[8], + getMDOrNull(Record[9]), getMDOrNull(Record[10]), + getMDOrNull(Record[11]), getMDOrNull(Record[12]), + getMDOrNull(Record[13]), + Record.size() <= 15 ? 0 : getMDOrNull(Record[15]), + Record.size() <= 14 ? 0 : Record[14]), + NextMetadataNo++); break; } case bitc::METADATA_SUBPROGRAM: { - if (Record.size() != 19) - return error("Invalid record"); - - MDValueList.assignValue( - GET_OR_DISTINCT( - DISubprogram, Record[0], - (Context, getMDOrNull(Record[1]), getMDString(Record[2]), - getMDString(Record[3]), getMDOrNull(Record[4]), Record[5], - getMDOrNull(Record[6]), Record[7], Record[8], Record[9], - getMDOrNull(Record[10]), Record[11], Record[12], Record[13], - Record[14], getMDOrNull(Record[15]), getMDOrNull(Record[16]), - getMDOrNull(Record[17]), getMDOrNull(Record[18]))), - NextMDValueNo++); + if (Record.size() != 18 && Record.size() != 19) + return error("Invalid record"); + + bool HasFn = Record.size() == 19; + DISubprogram *SP = GET_OR_DISTINCT( + DISubprogram, + Record[0] || Record[8], // All definitions should be distinct. + (Context, getMDOrNull(Record[1]), getMDString(Record[2]), + getMDString(Record[3]), getMDOrNull(Record[4]), Record[5], + getMDOrNull(Record[6]), Record[7], Record[8], Record[9], + getMDOrNull(Record[10]), Record[11], Record[12], Record[13], + Record[14], getMDOrNull(Record[15 + HasFn]), + getMDOrNull(Record[16 + HasFn]), getMDOrNull(Record[17 + HasFn]))); + MetadataList.assignValue(SP, NextMetadataNo++); + + // Upgrade sp->function mapping to function->sp mapping. + if (HasFn && Record[15]) { + if (auto *CMD = dyn_cast<ConstantAsMetadata>(getMDOrNull(Record[15]))) + if (auto *F = dyn_cast<Function>(CMD->getValue())) { + if (F->isMaterializable()) + // Defer until materialized; unmaterialized functions may not have + // metadata. + FunctionsWithSPs[F] = SP; + else if (!F->empty()) + F->setSubprogram(SP); + } + } break; } case bitc::METADATA_LEXICAL_BLOCK: { if (Record.size() != 5) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DILexicalBlock, Record[0], (Context, getMDOrNull(Record[1]), getMDOrNull(Record[2]), Record[3], Record[4])), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_LEXICAL_BLOCK_FILE: { if (Record.size() != 4) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DILexicalBlockFile, Record[0], (Context, getMDOrNull(Record[1]), getMDOrNull(Record[2]), Record[3])), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_NAMESPACE: { if (Record.size() != 5) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DINamespace, Record[0], (Context, getMDOrNull(Record[1]), getMDOrNull(Record[2]), getMDString(Record[3]), Record[4])), - NextMDValueNo++); + NextMetadataNo++); + break; + } + case bitc::METADATA_MACRO: { + if (Record.size() != 5) + return error("Invalid record"); + + MetadataList.assignValue( + GET_OR_DISTINCT(DIMacro, Record[0], + (Context, Record[1], Record[2], + getMDString(Record[3]), getMDString(Record[4]))), + NextMetadataNo++); + break; + } + case bitc::METADATA_MACRO_FILE: { + if (Record.size() != 5) + return error("Invalid record"); + + MetadataList.assignValue( + GET_OR_DISTINCT(DIMacroFile, Record[0], + (Context, Record[1], Record[2], + getMDOrNull(Record[3]), getMDOrNull(Record[4]))), + NextMetadataNo++); break; } case bitc::METADATA_TEMPLATE_TYPE: { if (Record.size() != 3) return error("Invalid record"); - MDValueList.assignValue(GET_OR_DISTINCT(DITemplateTypeParameter, - Record[0], - (Context, getMDString(Record[1]), - getMDOrNull(Record[2]))), - NextMDValueNo++); + MetadataList.assignValue(GET_OR_DISTINCT(DITemplateTypeParameter, + Record[0], + (Context, getMDString(Record[1]), + getMDOrNull(Record[2]))), + NextMetadataNo++); break; } case bitc::METADATA_TEMPLATE_VALUE: { if (Record.size() != 5) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DITemplateValueParameter, Record[0], (Context, Record[1], getMDString(Record[2]), getMDOrNull(Record[3]), getMDOrNull(Record[4]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_GLOBAL_VAR: { if (Record.size() != 11) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIGlobalVariable, Record[0], (Context, getMDOrNull(Record[1]), getMDString(Record[2]), getMDString(Record[3]), getMDOrNull(Record[4]), Record[5], getMDOrNull(Record[6]), Record[7], Record[8], getMDOrNull(Record[9]), getMDOrNull(Record[10]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_LOCAL_VAR: { // 10th field is for the obseleted 'inlinedAt:' field. - if (Record.size() != 9 && Record.size() != 10) + if (Record.size() < 8 || Record.size() > 10) return error("Invalid record"); - MDValueList.assignValue( + // 2nd field used to be an artificial tag, either DW_TAG_auto_variable or + // DW_TAG_arg_variable. + bool HasTag = Record.size() > 8; + MetadataList.assignValue( GET_OR_DISTINCT(DILocalVariable, Record[0], - (Context, Record[1], getMDOrNull(Record[2]), - getMDString(Record[3]), getMDOrNull(Record[4]), - Record[5], getMDOrNull(Record[6]), Record[7], - Record[8])), - NextMDValueNo++); + (Context, getMDOrNull(Record[1 + HasTag]), + getMDString(Record[2 + HasTag]), + getMDOrNull(Record[3 + HasTag]), Record[4 + HasTag], + getMDOrNull(Record[5 + HasTag]), Record[6 + HasTag], + Record[7 + HasTag])), + NextMetadataNo++); break; } case bitc::METADATA_EXPRESSION: { if (Record.size() < 1) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIExpression, Record[0], (Context, makeArrayRef(Record).slice(1))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_OBJC_PROPERTY: { if (Record.size() != 8) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIObjCProperty, Record[0], (Context, getMDString(Record[1]), getMDOrNull(Record[2]), Record[3], getMDString(Record[4]), getMDString(Record[5]), Record[6], getMDOrNull(Record[7]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_IMPORTED_ENTITY: { if (Record.size() != 6) return error("Invalid record"); - MDValueList.assignValue( + MetadataList.assignValue( GET_OR_DISTINCT(DIImportedEntity, Record[0], (Context, Record[1], getMDOrNull(Record[2]), getMDOrNull(Record[3]), Record[4], getMDString(Record[5]))), - NextMDValueNo++); + NextMetadataNo++); break; } case bitc::METADATA_STRING: { std::string String(Record.begin(), Record.end()); llvm::UpgradeMDStringConstant(String); Metadata *MD = MDString::get(Context, String); - MDValueList.assignValue(MD, NextMDValueNo++); + MetadataList.assignValue(MD, NextMetadataNo++); break; } case bitc::METADATA_KIND: { - if (Record.size() < 2) - return error("Invalid record"); + // Support older bitcode files that had METADATA_KIND records in a + // block with METADATA_BLOCK_ID. + if (std::error_code EC = parseMetadataKindRecord(Record)) + return EC; + break; + } + } + } +#undef GET_OR_DISTINCT +} - unsigned Kind = Record[0]; - SmallString<8> Name(Record.begin()+1, Record.end()); +/// Parse the metadata kinds out of the METADATA_KIND_BLOCK. +std::error_code BitcodeReader::parseMetadataKinds() { + if (Stream.EnterSubBlock(bitc::METADATA_KIND_BLOCK_ID)) + return error("Invalid record"); + + SmallVector<uint64_t, 64> Record; + + // Read all the records. + while (1) { + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + case BitstreamEntry::SubBlock: // Handled for us already. + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } - unsigned NewKind = TheModule->getMDKindID(Name.str()); - if (!MDKindMap.insert(std::make_pair(Kind, NewKind)).second) - return error("Conflicting METADATA_KIND records"); + // Read a record. + Record.clear(); + unsigned Code = Stream.readRecord(Entry.ID, Record); + switch (Code) { + default: // Default behavior: ignore. + break; + case bitc::METADATA_KIND: { + if (std::error_code EC = parseMetadataKindRecord(Record)) + return EC; break; } } } -#undef GET_OR_DISTINCT } /// Decode a signed value stored with the sign bit in the LSB for dense VBR @@ -2410,11 +2781,12 @@ std::error_code BitcodeReader::parseConstants() { Type *SelectorTy = Type::getInt1Ty(Context); - // If CurTy is a vector of length n, then Record[0] must be a <n x i1> - // vector. Otherwise, it must be a single bit. + // The selector might be an i1 or an <n x i1> + // Get the type from the ValueList before getting a forward ref. if (VectorType *VTy = dyn_cast<VectorType>(CurTy)) - SelectorTy = VectorType::get(Type::getInt1Ty(Context), - VTy->getNumElements()); + if (Value *V = ValueList[Record[0]]) + if (SelectorTy != V->getType()) + SelectorTy = VectorType::get(SelectorTy, VTy->getNumElements()); V = ConstantExpr::getSelect(ValueList.getConstantFwdRef(Record[0], SelectorTy), @@ -2567,9 +2939,6 @@ std::error_code BitcodeReader::parseConstants() { if (!Fn) return error("Invalid record"); - // Don't let Fn get dematerialized. - BlockAddressesTaken.insert(Fn); - // If the function is already parsed we can insert the block address right // away. BasicBlock *BB; @@ -2584,7 +2953,7 @@ std::error_code BitcodeReader::parseConstants() { return error("Invalid ID"); ++BBI; } - BB = BBI; + BB = &*BBI; } else { // Otherwise insert a placeholder and remember it so it can be inserted // when the function is parsed. @@ -2652,7 +3021,7 @@ std::error_code BitcodeReader::parseUseLists() { V = ValueList[ID]; unsigned NumUses = 0; SmallDenseMap<const Use *, unsigned, 16> Order; - for (const Use &U : V->uses()) { + for (const Use &U : V->materialized_uses()) { if (++NumUses > Record.size()) break; Order[&U] = Record[NumUses - 1]; @@ -2688,7 +3057,7 @@ std::error_code BitcodeReader::materializeMetadata() { for (uint64_t BitPos : DeferredMetadataInfo) { // Move the bit stream to the saved position. Stream.JumpToBit(BitPos); - if (std::error_code EC = parseMetadata()) + if (std::error_code EC = parseMetadata(true)) return EC; } DeferredMetadataInfo.clear(); @@ -2697,6 +3066,25 @@ std::error_code BitcodeReader::materializeMetadata() { void BitcodeReader::setStripDebugInfo() { StripDebugInfo = true; } +void BitcodeReader::saveMetadataList( + DenseMap<const Metadata *, unsigned> &MetadataToIDs, bool OnlyTempMD) { + for (unsigned ID = 0; ID < MetadataList.size(); ++ID) { + Metadata *MD = MetadataList[ID]; + auto *N = dyn_cast_or_null<MDNode>(MD); + // Save all values if !OnlyTempMD, otherwise just the temporary metadata. + if (!OnlyTempMD || (N && N->isTemporary())) { + // Will call this after materializing each function, in order to + // handle remapping of the function's instructions/metadata. + // See if we already have an entry in that case. + if (OnlyTempMD && MetadataToIDs.count(MD)) { + assert(MetadataToIDs[MD] == ID && "Inconsistent metadata value id"); + continue; + } + MetadataToIDs[MD] = ID; + } + } +} + /// When we see the block for a function body, remember where it is and then /// skip it. This lets us lazily deserialize the functions. std::error_code BitcodeReader::rememberAndSkipFunctionBody() { @@ -2709,6 +3097,9 @@ std::error_code BitcodeReader::rememberAndSkipFunctionBody() { // Save the current stream state. uint64_t CurBit = Stream.GetCurrentBitNo(); + assert( + (DeferredFunctionInfo[Fn] == 0 || DeferredFunctionInfo[Fn] == CurBit) && + "Mismatch between VST and scanned function offsets"); DeferredFunctionInfo[Fn] = CurBit; // Skip over the function block for now. @@ -2741,10 +3132,91 @@ std::error_code BitcodeReader::globalCleanup() { return std::error_code(); } -std::error_code BitcodeReader::parseModule(bool Resume, +/// Support for lazy parsing of function bodies. This is required if we +/// either have an old bitcode file without a VST forward declaration record, +/// or if we have an anonymous function being materialized, since anonymous +/// functions do not have a name and are therefore not in the VST. +std::error_code BitcodeReader::rememberAndSkipFunctionBodies() { + Stream.JumpToBit(NextUnreadBit); + + if (Stream.AtEndOfStream()) + return error("Could not find function in stream"); + + if (!SeenFirstFunctionBody) + return error("Trying to materialize functions before seeing function blocks"); + + // An old bitcode file with the symbol table at the end would have + // finished the parse greedily. + assert(SeenValueSymbolTable); + + SmallVector<uint64_t, 64> Record; + + while (1) { + BitstreamEntry Entry = Stream.advance(); + switch (Entry.Kind) { + default: + return error("Expect SubBlock"); + case BitstreamEntry::SubBlock: + switch (Entry.ID) { + default: + return error("Expect function block"); + case bitc::FUNCTION_BLOCK_ID: + if (std::error_code EC = rememberAndSkipFunctionBody()) + return EC; + NextUnreadBit = Stream.GetCurrentBitNo(); + return std::error_code(); + } + } + } +} + +std::error_code BitcodeReader::parseBitcodeVersion() { + if (Stream.EnterSubBlock(bitc::IDENTIFICATION_BLOCK_ID)) + return error("Invalid record"); + + // Read all the records. + SmallVector<uint64_t, 64> Record; + while (1) { + BitstreamEntry Entry = Stream.advance(); + + switch (Entry.Kind) { + default: + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } + + // Read a record. + Record.clear(); + unsigned BitCode = Stream.readRecord(Entry.ID, Record); + switch (BitCode) { + default: // Default behavior: reject + return error("Invalid value"); + case bitc::IDENTIFICATION_CODE_STRING: { // IDENTIFICATION: [strchr x + // N] + convertToString(Record, 0, ProducerIdentification); + break; + } + case bitc::IDENTIFICATION_CODE_EPOCH: { // EPOCH: [epoch#] + unsigned epoch = (unsigned)Record[0]; + if (epoch != bitc::BITCODE_CURRENT_EPOCH) { + return error( + Twine("Incompatible epoch: Bitcode '") + Twine(epoch) + + "' vs current: '" + Twine(bitc::BITCODE_CURRENT_EPOCH) + "'"); + } + } + } + } +} + +std::error_code BitcodeReader::parseModule(uint64_t ResumeBit, bool ShouldLazyLoadMetadata) { - if (Resume) - Stream.JumpToBit(NextUnreadBit); + if (ResumeBit) + Stream.JumpToBit(ResumeBit); else if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID)) return error("Invalid record"); @@ -2785,9 +3257,23 @@ std::error_code BitcodeReader::parseModule(bool Resume, return EC; break; case bitc::VALUE_SYMTAB_BLOCK_ID: - if (std::error_code EC = parseValueSymbolTable()) - return EC; - SeenValueSymbolTable = true; + if (!SeenValueSymbolTable) { + // Either this is an old form VST without function index and an + // associated VST forward declaration record (which would have caused + // the VST to be jumped to and parsed before it was encountered + // normally in the stream), or there were no function blocks to + // trigger an earlier parsing of the VST. + assert(VSTOffset == 0 || FunctionsWithBodies.empty()); + if (std::error_code EC = parseValueSymbolTable()) + return EC; + SeenValueSymbolTable = true; + } else { + // We must have had a VST forward declaration record, which caused + // the parser to jump to and parse the VST earlier. + assert(VSTOffset > 0); + if (Stream.SkipBlock()) + return error("Invalid record"); + } break; case bitc::CONSTANTS_BLOCK_ID: if (std::error_code EC = parseConstants()) @@ -2802,7 +3288,11 @@ std::error_code BitcodeReader::parseModule(bool Resume, break; } assert(DeferredMetadataInfo.empty() && "Unexpected deferred metadata"); - if (std::error_code EC = parseMetadata()) + if (std::error_code EC = parseMetadata(true)) + return EC; + break; + case bitc::METADATA_KIND_BLOCK_ID: + if (std::error_code EC = parseMetadataKinds()) return EC; break; case bitc::FUNCTION_BLOCK_ID: @@ -2815,8 +3305,39 @@ std::error_code BitcodeReader::parseModule(bool Resume, SeenFirstFunctionBody = true; } + if (VSTOffset > 0) { + // If we have a VST forward declaration record, make sure we + // parse the VST now if we haven't already. It is needed to + // set up the DeferredFunctionInfo vector for lazy reading. + if (!SeenValueSymbolTable) { + if (std::error_code EC = + BitcodeReader::parseValueSymbolTable(VSTOffset)) + return EC; + SeenValueSymbolTable = true; + // Fall through so that we record the NextUnreadBit below. + // This is necessary in case we have an anonymous function that + // is later materialized. Since it will not have a VST entry we + // need to fall back to the lazy parse to find its offset. + } else { + // If we have a VST forward declaration record, but have already + // parsed the VST (just above, when the first function body was + // encountered here), then we are resuming the parse after + // materializing functions. The ResumeBit points to the + // start of the last function block recorded in the + // DeferredFunctionInfo map. Skip it. + if (Stream.SkipBlock()) + return error("Invalid record"); + continue; + } + } + + // Support older bitcode files that did not have the function + // index in the VST, nor a VST forward declaration record, as + // well as anonymous functions that do not have VST entries. + // Build the DeferredFunctionInfo vector on the fly. if (std::error_code EC = rememberAndSkipFunctionBody()) return EC; + // Suspend parsing when we reach the function bodies. Subsequent // materialization calls will resume it when necessary. If the bitcode // file is old, the symbol table will be at the end instead and will not @@ -2830,6 +3351,10 @@ std::error_code BitcodeReader::parseModule(bool Resume, if (std::error_code EC = parseUseLists()) return EC; break; + case bitc::OPERAND_BUNDLE_TAGS_BLOCK_ID: + if (std::error_code EC = parseOperandBundleTags()) + return EC; + break; } continue; @@ -2840,7 +3365,8 @@ std::error_code BitcodeReader::parseModule(bool Resume, // Read a record. - switch (Stream.readRecord(Entry.ID, Record)) { + auto BitCode = Stream.readRecord(Entry.ID, Record); + switch (BitCode) { default: break; // Default behavior, ignore unknown content. case bitc::MODULE_CODE_VERSION: { // VERSION: [version#] if (Record.size() < 1) @@ -3012,11 +3538,14 @@ std::error_code BitcodeReader::parseModule(bool Resume, auto *FTy = dyn_cast<FunctionType>(Ty); if (!FTy) return error("Invalid type for value"); + auto CC = static_cast<CallingConv::ID>(Record[1]); + if (CC & ~CallingConv::MaxID) + return error("Invalid calling convention ID"); Function *Func = Function::Create(FTy, GlobalValue::ExternalLinkage, "", TheModule); - Func->setCallingConv(static_cast<CallingConv::ID>(Record[1])); + Func->setCallingConv(CC); bool isProto = Record[2]; uint64_t RawLinkage = Record[3]; Func->setLinkage(getDecodedLinkage(RawLinkage)); @@ -3079,35 +3608,51 @@ std::error_code BitcodeReader::parseModule(bool Resume, } break; } - // ALIAS: [alias type, aliasee val#, linkage] - // ALIAS: [alias type, aliasee val#, linkage, visibility, dllstorageclass] - case bitc::MODULE_CODE_ALIAS: { - if (Record.size() < 3) + // ALIAS: [alias type, addrspace, aliasee val#, linkage] + // ALIAS: [alias type, addrspace, aliasee val#, linkage, visibility, dllstorageclass] + case bitc::MODULE_CODE_ALIAS: + case bitc::MODULE_CODE_ALIAS_OLD: { + bool NewRecord = BitCode == bitc::MODULE_CODE_ALIAS; + if (Record.size() < (3 + (unsigned)NewRecord)) return error("Invalid record"); - Type *Ty = getTypeByID(Record[0]); + unsigned OpNum = 0; + Type *Ty = getTypeByID(Record[OpNum++]); if (!Ty) return error("Invalid record"); - auto *PTy = dyn_cast<PointerType>(Ty); - if (!PTy) - return error("Invalid type for value"); - auto *NewGA = - GlobalAlias::create(PTy, getDecodedLinkage(Record[2]), "", TheModule); + unsigned AddrSpace; + if (!NewRecord) { + auto *PTy = dyn_cast<PointerType>(Ty); + if (!PTy) + return error("Invalid type for value"); + Ty = PTy->getElementType(); + AddrSpace = PTy->getAddressSpace(); + } else { + AddrSpace = Record[OpNum++]; + } + + auto Val = Record[OpNum++]; + auto Linkage = Record[OpNum++]; + auto *NewGA = GlobalAlias::create( + Ty, AddrSpace, getDecodedLinkage(Linkage), "", TheModule); // Old bitcode files didn't have visibility field. // Local linkage must have default visibility. - if (Record.size() > 3 && !NewGA->hasLocalLinkage()) - // FIXME: Change to an error if non-default in 4.0. - NewGA->setVisibility(getDecodedVisibility(Record[3])); - if (Record.size() > 4) - NewGA->setDLLStorageClass(getDecodedDLLStorageClass(Record[4])); + if (OpNum != Record.size()) { + auto VisInd = OpNum++; + if (!NewGA->hasLocalLinkage()) + // FIXME: Change to an error if non-default in 4.0. + NewGA->setVisibility(getDecodedVisibility(Record[VisInd])); + } + if (OpNum != Record.size()) + NewGA->setDLLStorageClass(getDecodedDLLStorageClass(Record[OpNum++])); else - upgradeDLLImportExportLinkage(NewGA, Record[2]); - if (Record.size() > 5) - NewGA->setThreadLocalMode(getDecodedThreadLocalMode(Record[5])); - if (Record.size() > 6) - NewGA->setUnnamedAddr(Record[6]); + upgradeDLLImportExportLinkage(NewGA, Linkage); + if (OpNum != Record.size()) + NewGA->setThreadLocalMode(getDecodedThreadLocalMode(Record[OpNum++])); + if (OpNum != Record.size()) + NewGA->setUnnamedAddr(Record[OpNum++]); ValueList.push_back(NewGA); - AliasInits.push_back(std::make_pair(NewGA, Record[1])); + AliasInits.push_back(std::make_pair(NewGA, Val)); break; } /// MODULE_CODE_PURGEVALS: [numvals] @@ -3117,11 +3662,52 @@ std::error_code BitcodeReader::parseModule(bool Resume, return error("Invalid record"); ValueList.shrinkTo(Record[0]); break; + /// MODULE_CODE_VSTOFFSET: [offset] + case bitc::MODULE_CODE_VSTOFFSET: + if (Record.size() < 1) + return error("Invalid record"); + VSTOffset = Record[0]; + break; + /// MODULE_CODE_METADATA_VALUES: [numvals] + case bitc::MODULE_CODE_METADATA_VALUES: + if (Record.size() < 1) + return error("Invalid record"); + assert(!IsMetadataMaterialized); + // This record contains the number of metadata values in the module-level + // METADATA_BLOCK. It is used to support lazy parsing of metadata as + // a postpass, where we will parse function-level metadata first. + // This is needed because the ids of metadata are assigned implicitly + // based on their ordering in the bitcode, with the function-level + // metadata ids starting after the module-level metadata ids. Otherwise, + // we would have to parse the module-level metadata block to prime the + // MetadataList when we are lazy loading metadata during function + // importing. Initialize the MetadataList size here based on the + // record value, regardless of whether we are doing lazy metadata + // loading, so that we have consistent handling and assertion + // checking in parseMetadata for module-level metadata. + NumModuleMDs = Record[0]; + SeenModuleValuesRecord = true; + assert(MetadataList.size() == 0); + MetadataList.resize(NumModuleMDs); + break; } Record.clear(); } } +/// Helper to read the header common to all bitcode files. +static bool hasValidBitcodeHeader(BitstreamCursor &Stream) { + // Sniff for the signature. + if (Stream.Read(8) != 'B' || + Stream.Read(8) != 'C' || + Stream.Read(4) != 0x0 || + Stream.Read(4) != 0xC || + Stream.Read(4) != 0xE || + Stream.Read(4) != 0xD) + return false; + return true; +} + std::error_code BitcodeReader::parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer, Module *M, bool ShouldLazyLoadMetadata) { @@ -3131,12 +3717,7 @@ BitcodeReader::parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer, return EC; // Sniff for the signature. - if (Stream.Read(8) != 'B' || - Stream.Read(8) != 'C' || - Stream.Read(4) != 0x0 || - Stream.Read(4) != 0xC || - Stream.Read(4) != 0xE || - Stream.Read(4) != 0xD) + if (!hasValidBitcodeHeader(Stream)) return error("Invalid bitcode signature"); // We expect a number of well-defined blocks, though we don't necessarily @@ -3153,8 +3734,13 @@ BitcodeReader::parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer, if (Entry.Kind != BitstreamEntry::SubBlock) return error("Malformed block"); + if (Entry.ID == bitc::IDENTIFICATION_BLOCK_ID) { + parseBitcodeVersion(); + continue; + } + if (Entry.ID == bitc::MODULE_BLOCK_ID) - return parseModule(false, ShouldLazyLoadMetadata); + return parseModule(0, ShouldLazyLoadMetadata); if (Stream.SkipBlock()) return error("Invalid record"); @@ -3204,12 +3790,7 @@ ErrorOr<std::string> BitcodeReader::parseTriple() { return EC; // Sniff for the signature. - if (Stream.Read(8) != 'B' || - Stream.Read(8) != 'C' || - Stream.Read(4) != 0x0 || - Stream.Read(4) != 0xC || - Stream.Read(4) != 0xE || - Stream.Read(4) != 0xD) + if (!hasValidBitcodeHeader(Stream)) return error("Invalid bitcode signature"); // We expect a number of well-defined blocks, though we don't necessarily @@ -3239,6 +3820,41 @@ ErrorOr<std::string> BitcodeReader::parseTriple() { } } +ErrorOr<std::string> BitcodeReader::parseIdentificationBlock() { + if (std::error_code EC = initStream(nullptr)) + return EC; + + // Sniff for the signature. + if (!hasValidBitcodeHeader(Stream)) + return error("Invalid bitcode signature"); + + // We expect a number of well-defined blocks, though we don't necessarily + // need to understand them all. + while (1) { + BitstreamEntry Entry = Stream.advance(); + switch (Entry.Kind) { + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + + case BitstreamEntry::SubBlock: + if (Entry.ID == bitc::IDENTIFICATION_BLOCK_ID) { + if (std::error_code EC = parseBitcodeVersion()) + return EC; + return ProducerIdentification; + } + // Ignore other sub-blocks. + if (Stream.SkipBlock()) + return error("Malformed block"); + continue; + case BitstreamEntry::Record: + Stream.skipRecord(Entry.ID); + continue; + } + } +} + /// Parse metadata attachments. std::error_code BitcodeReader::parseMetadataAttachment(Function &F) { if (Stream.EnterSubBlock(bitc::METADATA_ATTACHMENT_ID)) @@ -3274,7 +3890,7 @@ std::error_code BitcodeReader::parseMetadataAttachment(Function &F) { auto K = MDKindMap.find(Record[I]); if (K == MDKindMap.end()) return error("Invalid ID"); - Metadata *MD = MDValueList.getValueFwdRef(Record[I + 1]); + Metadata *MD = MetadataList.getValueFwdRef(Record[I + 1]); F.setMetadata(K->second, cast<MDNode>(MD)); } continue; @@ -3288,7 +3904,7 @@ std::error_code BitcodeReader::parseMetadataAttachment(Function &F) { MDKindMap.find(Kind); if (I == MDKindMap.end()) return error("Invalid ID"); - Metadata *Node = MDValueList.getValueFwdRef(Record[i + 1]); + Metadata *Node = MetadataList.getValueFwdRef(Record[i + 1]); if (isa<LocalAsMetadata>(Node)) // Drop the attachment. This used to be legal, but there's no // upgrade path. @@ -3303,17 +3919,17 @@ std::error_code BitcodeReader::parseMetadataAttachment(Function &F) { } } -static std::error_code typeCheckLoadStoreInst(DiagnosticHandlerFunction DH, - Type *ValType, Type *PtrType) { +static std::error_code typeCheckLoadStoreInst(Type *ValType, Type *PtrType) { + LLVMContext &Context = PtrType->getContext(); if (!isa<PointerType>(PtrType)) - return error(DH, "Load/Store operand is not a pointer type"); + return error(Context, "Load/Store operand is not a pointer type"); Type *ElemType = cast<PointerType>(PtrType)->getElementType(); if (ValType && ValType != ElemType) - return error(DH, "Explicit load/store type does not match pointee type of " - "pointer operand"); + return error(Context, "Explicit load/store type does not match pointee " + "type of pointer operand"); if (!PointerType::isLoadableOrStorableType(ElemType)) - return error(DH, "Cannot load/store from pointer"); + return error(Context, "Cannot load/store from pointer"); return std::error_code(); } @@ -3324,11 +3940,11 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { InstructionList.clear(); unsigned ModuleValueListSize = ValueList.size(); - unsigned ModuleMDValueListSize = MDValueList.size(); + unsigned ModuleMetadataListSize = MetadataList.size(); // Add all the function arguments to the value table. - for(Function::arg_iterator I = F->arg_begin(), E = F->arg_end(); I != E; ++I) - ValueList.push_back(I); + for (Argument &I : F->args()) + ValueList.push_back(&I); unsigned NextValueNo = ValueList.size(); BasicBlock *CurBB = nullptr; @@ -3344,6 +3960,8 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { return nullptr; }; + std::vector<OperandBundleDef> OperandBundles; + // Read all the records. SmallVector<uint64_t, 64> Record; while (1) { @@ -3452,8 +4070,10 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { unsigned ScopeID = Record[2], IAID = Record[3]; MDNode *Scope = nullptr, *IA = nullptr; - if (ScopeID) Scope = cast<MDNode>(MDValueList.getValueFwdRef(ScopeID-1)); - if (IAID) IA = cast<MDNode>(MDValueList.getValueFwdRef(IAID-1)); + if (ScopeID) + Scope = cast<MDNode>(MetadataList.getValueFwdRef(ScopeID - 1)); + if (IAID) + IA = cast<MDNode>(MetadataList.getValueFwdRef(IAID - 1)); LastLoc = DebugLoc::get(Line, Col, Scope, IA); I->setDebugLoc(LastLoc); I = nullptr; @@ -3515,7 +4135,10 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { CurBB->getInstList().push_back(Temp); } } else { - I = CastInst::Create((Instruction::CastOps)Opc, Op, ResTy); + auto CastOp = (Instruction::CastOps)Opc; + if (!CastInst::castIsValid(CastOp, Op, ResTy)) + return error("Invalid cast"); + I = CastInst::Create(CastOp, Op, ResTy); } InstructionList.push_back(I); break; @@ -3811,6 +4434,110 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { } break; } + case bitc::FUNC_CODE_INST_CLEANUPRET: { // CLEANUPRET: [val] or [val,bb#] + if (Record.size() != 1 && Record.size() != 2) + return error("Invalid record"); + unsigned Idx = 0; + Value *CleanupPad = + getValue(Record, Idx++, NextValueNo, Type::getTokenTy(Context)); + if (!CleanupPad) + return error("Invalid record"); + BasicBlock *UnwindDest = nullptr; + if (Record.size() == 2) { + UnwindDest = getBasicBlock(Record[Idx++]); + if (!UnwindDest) + return error("Invalid record"); + } + + I = CleanupReturnInst::Create(CleanupPad, UnwindDest); + InstructionList.push_back(I); + break; + } + case bitc::FUNC_CODE_INST_CATCHRET: { // CATCHRET: [val,bb#] + if (Record.size() != 2) + return error("Invalid record"); + unsigned Idx = 0; + Value *CatchPad = + getValue(Record, Idx++, NextValueNo, Type::getTokenTy(Context)); + if (!CatchPad) + return error("Invalid record"); + BasicBlock *BB = getBasicBlock(Record[Idx++]); + if (!BB) + return error("Invalid record"); + + I = CatchReturnInst::Create(CatchPad, BB); + InstructionList.push_back(I); + break; + } + case bitc::FUNC_CODE_INST_CATCHSWITCH: { // CATCHSWITCH: [tok,num,(bb)*,bb?] + // We must have, at minimum, the outer scope and the number of arguments. + if (Record.size() < 2) + return error("Invalid record"); + + unsigned Idx = 0; + + Value *ParentPad = + getValue(Record, Idx++, NextValueNo, Type::getTokenTy(Context)); + + unsigned NumHandlers = Record[Idx++]; + + SmallVector<BasicBlock *, 2> Handlers; + for (unsigned Op = 0; Op != NumHandlers; ++Op) { + BasicBlock *BB = getBasicBlock(Record[Idx++]); + if (!BB) + return error("Invalid record"); + Handlers.push_back(BB); + } + + BasicBlock *UnwindDest = nullptr; + if (Idx + 1 == Record.size()) { + UnwindDest = getBasicBlock(Record[Idx++]); + if (!UnwindDest) + return error("Invalid record"); + } + + if (Record.size() != Idx) + return error("Invalid record"); + + auto *CatchSwitch = + CatchSwitchInst::Create(ParentPad, UnwindDest, NumHandlers); + for (BasicBlock *Handler : Handlers) + CatchSwitch->addHandler(Handler); + I = CatchSwitch; + InstructionList.push_back(I); + break; + } + case bitc::FUNC_CODE_INST_CATCHPAD: + case bitc::FUNC_CODE_INST_CLEANUPPAD: { // [tok,num,(ty,val)*] + // We must have, at minimum, the outer scope and the number of arguments. + if (Record.size() < 2) + return error("Invalid record"); + + unsigned Idx = 0; + + Value *ParentPad = + getValue(Record, Idx++, NextValueNo, Type::getTokenTy(Context)); + + unsigned NumArgOperands = Record[Idx++]; + + SmallVector<Value *, 2> Args; + for (unsigned Op = 0; Op != NumArgOperands; ++Op) { + Value *Val; + if (getValueTypePair(Record, Idx, NextValueNo, Val)) + return error("Invalid record"); + Args.push_back(Val); + } + + if (Record.size() != Idx) + return error("Invalid record"); + + if (BitCode == bitc::FUNC_CODE_INST_CLEANUPPAD) + I = CleanupPadInst::Create(ParentPad, Args); + else + I = CatchPadInst::Create(ParentPad, Args); + InstructionList.push_back(I); + break; + } case bitc::FUNC_CODE_INST_SWITCH: { // SWITCH: [opty, op0, op1, ...] // Check magic if ((Record[0] >> 16) == SWITCH_INST_MAGIC) { @@ -3973,10 +4700,11 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { } } - I = InvokeInst::Create(Callee, NormalBB, UnwindBB, Ops); + I = InvokeInst::Create(Callee, NormalBB, UnwindBB, Ops, OperandBundles); + OperandBundles.clear(); InstructionList.push_back(I); - cast<InvokeInst>(I) - ->setCallingConv(static_cast<CallingConv::ID>(~(1U << 13) & CCInfo)); + cast<InvokeInst>(I)->setCallingConv( + static_cast<CallingConv::ID>(CallingConv::MaxID & CCInfo)); cast<InvokeInst>(I)->setAttributes(PAL); break; } @@ -4081,6 +4809,8 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { uint64_t AlignRecord = Record[3]; const uint64_t InAllocaMask = uint64_t(1) << 5; const uint64_t ExplicitTypeMask = uint64_t(1) << 6; + // Reserve bit 7 for SwiftError flag. + // const uint64_t SwiftErrorMask = uint64_t(1) << 7; const uint64_t FlagMask = InAllocaMask | ExplicitTypeMask; bool InAlloca = AlignRecord & InAllocaMask; Type *Ty = getTypeByID(Record[0]); @@ -4115,8 +4845,7 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { Type *Ty = nullptr; if (OpNum + 3 == Record.size()) Ty = getTypeByID(Record[OpNum++]); - if (std::error_code EC = - typeCheckLoadStoreInst(DiagnosticHandler, Ty, Op->getType())) + if (std::error_code EC = typeCheckLoadStoreInst(Ty, Op->getType())) return EC; if (!Ty) Ty = cast<PointerType>(Op->getType())->getElementType(); @@ -4140,8 +4869,7 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { Type *Ty = nullptr; if (OpNum + 5 == Record.size()) Ty = getTypeByID(Record[OpNum++]); - if (std::error_code EC = - typeCheckLoadStoreInst(DiagnosticHandler, Ty, Op->getType())) + if (std::error_code EC = typeCheckLoadStoreInst(Ty, Op->getType())) return EC; if (!Ty) Ty = cast<PointerType>(Op->getType())->getElementType(); @@ -4175,8 +4903,8 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { OpNum + 2 != Record.size()) return error("Invalid record"); - if (std::error_code EC = typeCheckLoadStoreInst( - DiagnosticHandler, Val->getType(), Ptr->getType())) + if (std::error_code EC = + typeCheckLoadStoreInst(Val->getType(), Ptr->getType())) return EC; unsigned Align; if (std::error_code EC = parseAlignmentValue(Record[OpNum], Align)) @@ -4199,8 +4927,8 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { OpNum + 4 != Record.size()) return error("Invalid record"); - if (std::error_code EC = typeCheckLoadStoreInst( - DiagnosticHandler, Val->getType(), Ptr->getType())) + if (std::error_code EC = + typeCheckLoadStoreInst(Val->getType(), Ptr->getType())) return EC; AtomicOrdering Ordering = getDecodedOrdering(Record[OpNum + 2]); if (Ordering == NotAtomic || Ordering == Acquire || @@ -4237,8 +4965,8 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { return error("Invalid record"); SynchronizationScope SynchScope = getDecodedSynchScope(Record[OpNum + 2]); - if (std::error_code EC = typeCheckLoadStoreInst( - DiagnosticHandler, Cmp->getType(), Ptr->getType())) + if (std::error_code EC = + typeCheckLoadStoreInst(Cmp->getType(), Ptr->getType())) return EC; AtomicOrdering FailureOrdering; if (Record.size() < 7) @@ -4299,7 +5027,7 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { break; } case bitc::FUNC_CODE_INST_CALL: { - // CALL: [paramattrs, cc, fnty, fnid, arg0, arg1...] + // CALL: [paramattrs, cc, fmf, fnty, fnid, arg0, arg1...] if (Record.size() < 3) return error("Invalid record"); @@ -4307,8 +5035,15 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { AttributeSet PAL = getAttributes(Record[OpNum++]); unsigned CCInfo = Record[OpNum++]; + FastMathFlags FMF; + if ((CCInfo >> bitc::CALL_FMF) & 1) { + FMF = getDecodedFastMathFlags(Record[OpNum++]); + if (!FMF.any()) + return error("Fast math flags indicator set for call with no FMF"); + } + FunctionType *FTy = nullptr; - if (CCInfo >> 15 & 1 && + if (CCInfo >> bitc::CALL_EXPLICIT_TYPE & 1 && !(FTy = dyn_cast<FunctionType>(getTypeByID(Record[OpNum++])))) return error("Explicit call type is not a function type"); @@ -4354,17 +5089,26 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { } } - I = CallInst::Create(FTy, Callee, Args); + I = CallInst::Create(FTy, Callee, Args, OperandBundles); + OperandBundles.clear(); InstructionList.push_back(I); cast<CallInst>(I)->setCallingConv( - static_cast<CallingConv::ID>((~(1U << 14) & CCInfo) >> 1)); + static_cast<CallingConv::ID>((0x7ff & CCInfo) >> bitc::CALL_CCONV)); CallInst::TailCallKind TCK = CallInst::TCK_None; - if (CCInfo & 1) + if (CCInfo & 1 << bitc::CALL_TAIL) TCK = CallInst::TCK_Tail; - if (CCInfo & (1 << 14)) + if (CCInfo & (1 << bitc::CALL_MUSTTAIL)) TCK = CallInst::TCK_MustTail; + if (CCInfo & (1 << bitc::CALL_NOTAIL)) + TCK = CallInst::TCK_NoTail; cast<CallInst>(I)->setTailCallKind(TCK); cast<CallInst>(I)->setAttributes(PAL); + if (FMF.any()) { + if (!isa<FPMathOperator>(I)) + return error("Fast-math-flags specified for call without " + "floating-point scalar or vector return type"); + I->setFastMathFlags(FMF); + } break; } case bitc::FUNC_CODE_INST_VAARG: { // VAARG: [valistty, valist, instty] @@ -4379,6 +5123,28 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { InstructionList.push_back(I); break; } + + case bitc::FUNC_CODE_OPERAND_BUNDLE: { + // A call or an invoke can be optionally prefixed with some variable + // number of operand bundle blocks. These blocks are read into + // OperandBundles and consumed at the next call or invoke instruction. + + if (Record.size() < 1 || Record[0] >= BundleTags.size()) + return error("Invalid record"); + + std::vector<Value *> Inputs; + + unsigned OpNum = 1; + while (OpNum != Record.size()) { + Value *Op; + if (getValueTypePair(Record, OpNum, NextValueNo, Op)) + return error("Invalid record"); + Inputs.push_back(Op); + } + + OperandBundles.emplace_back(BundleTags[Record[0]], std::move(Inputs)); + continue; + } } // Add instruction to end of current BB. If there is no current BB, reject @@ -4387,6 +5153,10 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { delete I; return error("Invalid instruction with no BB"); } + if (!OperandBundles.empty()) { + delete I; + return error("Operand bundles found with no consumer"); + } CurBB->getInstList().push_back(I); // If this was a terminator instruction, move to the next block. @@ -4402,6 +5172,9 @@ std::error_code BitcodeReader::parseFunctionBody(Function *F) { OutOfRecordLoop: + if (!OperandBundles.empty()) + return error("Operand bundles found with no consumer"); + // Check the function list for unresolved values. if (Argument *A = dyn_cast<Argument>(ValueList.back())) { if (!A->getParent()) { @@ -4421,7 +5194,7 @@ OutOfRecordLoop: // Trim the value list down to the size it was before we parsed this function. ValueList.shrinkTo(ModuleValueListSize); - MDValueList.shrinkTo(ModuleMDValueListSize); + MetadataList.shrinkTo(ModuleMetadataListSize); std::vector<BasicBlock*>().swap(FunctionBBs); return std::error_code(); } @@ -4431,11 +5204,14 @@ std::error_code BitcodeReader::findFunctionInStream( Function *F, DenseMap<Function *, uint64_t>::iterator DeferredFunctionInfoIterator) { while (DeferredFunctionInfoIterator->second == 0) { - if (Stream.AtEndOfStream()) - return error("Could not find function in stream"); - // ParseModule will parse the next body in the stream and set its - // position in the DeferredFunctionInfo map. - if (std::error_code EC = parseModule(true)) + // This is the fallback handling for the old format bitcode that + // didn't contain the function index in the VST, or when we have + // an anonymous function which would not have a VST entry. + // Assert that we have one of those two cases. + assert(VSTOffset == 0 || !F->hasName()); + // Parse the next body in the stream and set its position in the + // DeferredFunctionInfo map. + if (std::error_code EC = rememberAndSkipFunctionBodies()) return EC; } return std::error_code(); @@ -4448,8 +5224,12 @@ std::error_code BitcodeReader::findFunctionInStream( void BitcodeReader::releaseBuffer() { Buffer.release(); } std::error_code BitcodeReader::materialize(GlobalValue *GV) { - if (std::error_code EC = materializeMetadata()) - return EC; + // In older bitcode we must materialize the metadata before parsing + // any functions, in order to set up the MetadataList properly. + if (!SeenModuleValuesRecord) { + if (std::error_code EC = materializeMetadata()) + return EC; + } Function *F = dyn_cast<Function>(GV); // If it's not a function or is already material, ignore the request. @@ -4476,7 +5256,8 @@ std::error_code BitcodeReader::materialize(GlobalValue *GV) { // Upgrade any old intrinsic calls in the function. for (auto &I : UpgradedIntrinsics) { - for (auto UI = I.first->user_begin(), UE = I.first->user_end(); UI != UE;) { + for (auto UI = I.first->materialized_user_begin(), UE = I.first->user_end(); + UI != UE;) { User *U = *UI; ++UI; if (CallInst *CI = dyn_cast<CallInst>(U)) @@ -4484,41 +5265,16 @@ std::error_code BitcodeReader::materialize(GlobalValue *GV) { } } + // Finish fn->subprogram upgrade for materialized functions. + if (DISubprogram *SP = FunctionsWithSPs.lookup(F)) + F->setSubprogram(SP); + // Bring in any functions that this function forward-referenced via // blockaddresses. return materializeForwardReferencedFunctions(); } -bool BitcodeReader::isDematerializable(const GlobalValue *GV) const { - const Function *F = dyn_cast<Function>(GV); - if (!F || F->isDeclaration()) - return false; - - // Dematerializing F would leave dangling references that wouldn't be - // reconnected on re-materialization. - if (BlockAddressesTaken.count(F)) - return false; - - return DeferredFunctionInfo.count(const_cast<Function*>(F)); -} - -void BitcodeReader::dematerialize(GlobalValue *GV) { - Function *F = dyn_cast<Function>(GV); - // If this function isn't dematerializable, this is a noop. - if (!F || !isDematerializable(F)) - return; - - assert(DeferredFunctionInfo.count(F) && "No info to read function later?"); - - // Just forget the function body, we can remat it later. - F->dropAllReferences(); - F->setIsMaterializable(true); -} - -std::error_code BitcodeReader::materializeModule(Module *M) { - assert(M == TheModule && - "Can only Materialize the Module this BitcodeReader is attached to."); - +std::error_code BitcodeReader::materializeModule() { if (std::error_code EC = materializeMetadata()) return EC; @@ -4527,16 +5283,16 @@ std::error_code BitcodeReader::materializeModule(Module *M) { // Iterate over the module, deserializing any functions that are still on // disk. - for (Module::iterator F = TheModule->begin(), E = TheModule->end(); - F != E; ++F) { - if (std::error_code EC = materialize(F)) + for (Function &F : *TheModule) { + if (std::error_code EC = materialize(&F)) return EC; } - // At this point, if there are any function bodies, the current bit is - // pointing to the END_BLOCK record after them. Now make sure the rest - // of the bits in the module have been read. - if (NextUnreadBit) - parseModule(true); + // At this point, if there are any function bodies, parse the rest of + // the bits in the module past the last function block we have recorded + // through either lazy scanning or the VST. + if (LastFunctionBlockBit || NextUnreadBit) + parseModule(LastFunctionBlockBit > NextUnreadBit ? LastFunctionBlockBit + : NextUnreadBit); // Check that all block address forward references got resolved (as we // promised above). @@ -4561,7 +5317,7 @@ std::error_code BitcodeReader::materializeModule(Module *M) { for (unsigned I = 0, E = InstsWithTBAATag.size(); I < E; I++) UpgradeInstWithTBAATag(InstsWithTBAATag[I]); - UpgradeDebugInfo(*M); + UpgradeDebugInfo(*TheModule); return std::error_code(); } @@ -4622,6 +5378,416 @@ BitcodeReader::initLazyStream(std::unique_ptr<DataStreamer> Streamer) { return std::error_code(); } +std::error_code FunctionIndexBitcodeReader::error(BitcodeError E, + const Twine &Message) { + return ::error(DiagnosticHandler, make_error_code(E), Message); +} + +std::error_code FunctionIndexBitcodeReader::error(const Twine &Message) { + return ::error(DiagnosticHandler, + make_error_code(BitcodeError::CorruptedBitcode), Message); +} + +std::error_code FunctionIndexBitcodeReader::error(BitcodeError E) { + return ::error(DiagnosticHandler, make_error_code(E)); +} + +FunctionIndexBitcodeReader::FunctionIndexBitcodeReader( + MemoryBuffer *Buffer, DiagnosticHandlerFunction DiagnosticHandler, + bool IsLazy, bool CheckFuncSummaryPresenceOnly) + : DiagnosticHandler(DiagnosticHandler), Buffer(Buffer), IsLazy(IsLazy), + CheckFuncSummaryPresenceOnly(CheckFuncSummaryPresenceOnly) {} + +FunctionIndexBitcodeReader::FunctionIndexBitcodeReader( + DiagnosticHandlerFunction DiagnosticHandler, bool IsLazy, + bool CheckFuncSummaryPresenceOnly) + : DiagnosticHandler(DiagnosticHandler), Buffer(nullptr), IsLazy(IsLazy), + CheckFuncSummaryPresenceOnly(CheckFuncSummaryPresenceOnly) {} + +void FunctionIndexBitcodeReader::freeState() { Buffer = nullptr; } + +void FunctionIndexBitcodeReader::releaseBuffer() { Buffer.release(); } + +// Specialized value symbol table parser used when reading function index +// blocks where we don't actually create global values. +// At the end of this routine the function index is populated with a map +// from function name to FunctionInfo. The function info contains +// the function block's bitcode offset as well as the offset into the +// function summary section. +std::error_code FunctionIndexBitcodeReader::parseValueSymbolTable() { + if (Stream.EnterSubBlock(bitc::VALUE_SYMTAB_BLOCK_ID)) + return error("Invalid record"); + + SmallVector<uint64_t, 64> Record; + + // Read all the records for this value table. + SmallString<128> ValueName; + while (1) { + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + case BitstreamEntry::SubBlock: // Handled for us already. + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } + + // Read a record. + Record.clear(); + switch (Stream.readRecord(Entry.ID, Record)) { + default: // Default behavior: ignore (e.g. VST_CODE_BBENTRY records). + break; + case bitc::VST_CODE_FNENTRY: { + // VST_FNENTRY: [valueid, offset, namechar x N] + if (convertToString(Record, 2, ValueName)) + return error("Invalid record"); + unsigned ValueID = Record[0]; + uint64_t FuncOffset = Record[1]; + std::unique_ptr<FunctionInfo> FuncInfo = + llvm::make_unique<FunctionInfo>(FuncOffset); + if (foundFuncSummary() && !IsLazy) { + DenseMap<uint64_t, std::unique_ptr<FunctionSummary>>::iterator SMI = + SummaryMap.find(ValueID); + assert(SMI != SummaryMap.end() && "Summary info not found"); + FuncInfo->setFunctionSummary(std::move(SMI->second)); + } + TheIndex->addFunctionInfo(ValueName, std::move(FuncInfo)); + + ValueName.clear(); + break; + } + case bitc::VST_CODE_COMBINED_FNENTRY: { + // VST_FNENTRY: [offset, namechar x N] + if (convertToString(Record, 1, ValueName)) + return error("Invalid record"); + uint64_t FuncSummaryOffset = Record[0]; + std::unique_ptr<FunctionInfo> FuncInfo = + llvm::make_unique<FunctionInfo>(FuncSummaryOffset); + if (foundFuncSummary() && !IsLazy) { + DenseMap<uint64_t, std::unique_ptr<FunctionSummary>>::iterator SMI = + SummaryMap.find(FuncSummaryOffset); + assert(SMI != SummaryMap.end() && "Summary info not found"); + FuncInfo->setFunctionSummary(std::move(SMI->second)); + } + TheIndex->addFunctionInfo(ValueName, std::move(FuncInfo)); + + ValueName.clear(); + break; + } + } + } +} + +// Parse just the blocks needed for function index building out of the module. +// At the end of this routine the function Index is populated with a map +// from function name to FunctionInfo. The function info contains +// either the parsed function summary information (when parsing summaries +// eagerly), or just to the function summary record's offset +// if parsing lazily (IsLazy). +std::error_code FunctionIndexBitcodeReader::parseModule() { + if (Stream.EnterSubBlock(bitc::MODULE_BLOCK_ID)) + return error("Invalid record"); + + // Read the function index for this module. + while (1) { + BitstreamEntry Entry = Stream.advance(); + + switch (Entry.Kind) { + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + + case BitstreamEntry::SubBlock: + if (CheckFuncSummaryPresenceOnly) { + if (Entry.ID == bitc::FUNCTION_SUMMARY_BLOCK_ID) { + SeenFuncSummary = true; + // No need to parse the rest since we found the summary. + return std::error_code(); + } + if (Stream.SkipBlock()) + return error("Invalid record"); + continue; + } + switch (Entry.ID) { + default: // Skip unknown content. + if (Stream.SkipBlock()) + return error("Invalid record"); + break; + case bitc::BLOCKINFO_BLOCK_ID: + // Need to parse these to get abbrev ids (e.g. for VST) + if (Stream.ReadBlockInfoBlock()) + return error("Malformed block"); + break; + case bitc::VALUE_SYMTAB_BLOCK_ID: + if (std::error_code EC = parseValueSymbolTable()) + return EC; + break; + case bitc::FUNCTION_SUMMARY_BLOCK_ID: + SeenFuncSummary = true; + if (IsLazy) { + // Lazy parsing of summary info, skip it. + if (Stream.SkipBlock()) + return error("Invalid record"); + } else if (std::error_code EC = parseEntireSummary()) + return EC; + break; + case bitc::MODULE_STRTAB_BLOCK_ID: + if (std::error_code EC = parseModuleStringTable()) + return EC; + break; + } + continue; + + case BitstreamEntry::Record: + Stream.skipRecord(Entry.ID); + continue; + } + } +} + +// Eagerly parse the entire function summary block (i.e. for all functions +// in the index). This populates the FunctionSummary objects in +// the index. +std::error_code FunctionIndexBitcodeReader::parseEntireSummary() { + if (Stream.EnterSubBlock(bitc::FUNCTION_SUMMARY_BLOCK_ID)) + return error("Invalid record"); + + SmallVector<uint64_t, 64> Record; + + while (1) { + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + case BitstreamEntry::SubBlock: // Handled for us already. + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } + + // Read a record. The record format depends on whether this + // is a per-module index or a combined index file. In the per-module + // case the records contain the associated value's ID for correlation + // with VST entries. In the combined index the correlation is done + // via the bitcode offset of the summary records (which were saved + // in the combined index VST entries). The records also contain + // information used for ThinLTO renaming and importing. + Record.clear(); + uint64_t CurRecordBit = Stream.GetCurrentBitNo(); + switch (Stream.readRecord(Entry.ID, Record)) { + default: // Default behavior: ignore. + break; + // FS_PERMODULE_ENTRY: [valueid, islocal, instcount] + case bitc::FS_CODE_PERMODULE_ENTRY: { + unsigned ValueID = Record[0]; + bool IsLocal = Record[1]; + unsigned InstCount = Record[2]; + std::unique_ptr<FunctionSummary> FS = + llvm::make_unique<FunctionSummary>(InstCount); + FS->setLocalFunction(IsLocal); + // The module path string ref set in the summary must be owned by the + // index's module string table. Since we don't have a module path + // string table section in the per-module index, we create a single + // module path string table entry with an empty (0) ID to take + // ownership. + FS->setModulePath( + TheIndex->addModulePath(Buffer->getBufferIdentifier(), 0)); + SummaryMap[ValueID] = std::move(FS); + } + // FS_COMBINED_ENTRY: [modid, instcount] + case bitc::FS_CODE_COMBINED_ENTRY: { + uint64_t ModuleId = Record[0]; + unsigned InstCount = Record[1]; + std::unique_ptr<FunctionSummary> FS = + llvm::make_unique<FunctionSummary>(InstCount); + FS->setModulePath(ModuleIdMap[ModuleId]); + SummaryMap[CurRecordBit] = std::move(FS); + } + } + } + llvm_unreachable("Exit infinite loop"); +} + +// Parse the module string table block into the Index. +// This populates the ModulePathStringTable map in the index. +std::error_code FunctionIndexBitcodeReader::parseModuleStringTable() { + if (Stream.EnterSubBlock(bitc::MODULE_STRTAB_BLOCK_ID)) + return error("Invalid record"); + + SmallVector<uint64_t, 64> Record; + + SmallString<128> ModulePath; + while (1) { + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + case BitstreamEntry::SubBlock: // Handled for us already. + case BitstreamEntry::Error: + return error("Malformed block"); + case BitstreamEntry::EndBlock: + return std::error_code(); + case BitstreamEntry::Record: + // The interesting case. + break; + } + + Record.clear(); + switch (Stream.readRecord(Entry.ID, Record)) { + default: // Default behavior: ignore. + break; + case bitc::MST_CODE_ENTRY: { + // MST_ENTRY: [modid, namechar x N] + if (convertToString(Record, 1, ModulePath)) + return error("Invalid record"); + uint64_t ModuleId = Record[0]; + StringRef ModulePathInMap = TheIndex->addModulePath(ModulePath, ModuleId); + ModuleIdMap[ModuleId] = ModulePathInMap; + ModulePath.clear(); + break; + } + } + } + llvm_unreachable("Exit infinite loop"); +} + +// Parse the function info index from the bitcode streamer into the given index. +std::error_code FunctionIndexBitcodeReader::parseSummaryIndexInto( + std::unique_ptr<DataStreamer> Streamer, FunctionInfoIndex *I) { + TheIndex = I; + + if (std::error_code EC = initStream(std::move(Streamer))) + return EC; + + // Sniff for the signature. + if (!hasValidBitcodeHeader(Stream)) + return error("Invalid bitcode signature"); + + // We expect a number of well-defined blocks, though we don't necessarily + // need to understand them all. + while (1) { + if (Stream.AtEndOfStream()) { + // We didn't really read a proper Module block. + return error("Malformed block"); + } + + BitstreamEntry Entry = + Stream.advance(BitstreamCursor::AF_DontAutoprocessAbbrevs); + + if (Entry.Kind != BitstreamEntry::SubBlock) + return error("Malformed block"); + + // If we see a MODULE_BLOCK, parse it to find the blocks needed for + // building the function summary index. + if (Entry.ID == bitc::MODULE_BLOCK_ID) + return parseModule(); + + if (Stream.SkipBlock()) + return error("Invalid record"); + } +} + +// Parse the function information at the given offset in the buffer into +// the index. Used to support lazy parsing of function summaries from the +// combined index during importing. +// TODO: This function is not yet complete as it won't have a consumer +// until ThinLTO function importing is added. +std::error_code FunctionIndexBitcodeReader::parseFunctionSummary( + std::unique_ptr<DataStreamer> Streamer, FunctionInfoIndex *I, + size_t FunctionSummaryOffset) { + TheIndex = I; + + if (std::error_code EC = initStream(std::move(Streamer))) + return EC; + + // Sniff for the signature. + if (!hasValidBitcodeHeader(Stream)) + return error("Invalid bitcode signature"); + + Stream.JumpToBit(FunctionSummaryOffset); + + BitstreamEntry Entry = Stream.advanceSkippingSubblocks(); + + switch (Entry.Kind) { + default: + return error("Malformed block"); + case BitstreamEntry::Record: + // The expected case. + break; + } + + // TODO: Read a record. This interface will be completed when ThinLTO + // importing is added so that it can be tested. + SmallVector<uint64_t, 64> Record; + switch (Stream.readRecord(Entry.ID, Record)) { + case bitc::FS_CODE_COMBINED_ENTRY: + default: + return error("Invalid record"); + } + + return std::error_code(); +} + +std::error_code +FunctionIndexBitcodeReader::initStream(std::unique_ptr<DataStreamer> Streamer) { + if (Streamer) + return initLazyStream(std::move(Streamer)); + return initStreamFromBuffer(); +} + +std::error_code FunctionIndexBitcodeReader::initStreamFromBuffer() { + const unsigned char *BufPtr = (const unsigned char *)Buffer->getBufferStart(); + const unsigned char *BufEnd = BufPtr + Buffer->getBufferSize(); + + if (Buffer->getBufferSize() & 3) + return error("Invalid bitcode signature"); + + // If we have a wrapper header, parse it and ignore the non-bc file contents. + // The magic number is 0x0B17C0DE stored in little endian. + if (isBitcodeWrapper(BufPtr, BufEnd)) + if (SkipBitcodeWrapperHeader(BufPtr, BufEnd, true)) + return error("Invalid bitcode wrapper header"); + + StreamFile.reset(new BitstreamReader(BufPtr, BufEnd)); + Stream.init(&*StreamFile); + + return std::error_code(); +} + +std::error_code FunctionIndexBitcodeReader::initLazyStream( + std::unique_ptr<DataStreamer> Streamer) { + // Check and strip off the bitcode wrapper; BitstreamReader expects never to + // see it. + auto OwnedBytes = + llvm::make_unique<StreamingMemoryObject>(std::move(Streamer)); + StreamingMemoryObject &Bytes = *OwnedBytes; + StreamFile = llvm::make_unique<BitstreamReader>(std::move(OwnedBytes)); + Stream.init(&*StreamFile); + + unsigned char buf[16]; + if (Bytes.readBytes(buf, 16, 0) != 16) + return error("Invalid bitcode signature"); + + if (!isBitcode(buf, buf + 16)) + return error("Invalid bitcode signature"); + + if (isBitcodeWrapper(buf, buf + 4)) { + const unsigned char *bitcodeStart = buf; + const unsigned char *bitcodeEnd = buf + 16; + SkipBitcodeWrapperHeader(bitcodeStart, bitcodeEnd, false); + Bytes.dropLeadingBytes(bitcodeStart - buf); + Bytes.setKnownObjectSize(bitcodeEnd - bitcodeStart); + } + return std::error_code(); +} + namespace { class BitcodeErrorCategoryType : public std::error_category { const char *name() const LLVM_NOEXCEPT override { @@ -4669,7 +5835,7 @@ getBitcodeModuleImpl(std::unique_ptr<DataStreamer> Streamer, StringRef Name, if (MaterializeAll) { // Read in the entire module, and destroy the BitcodeReader. - if (std::error_code EC = M->materializeAllPermanently()) + if (std::error_code EC = M->materializeAll()) return cleanupOnError(EC); } else { // Resolve forward references from blockaddresses. @@ -4690,10 +5856,8 @@ getBitcodeModuleImpl(std::unique_ptr<DataStreamer> Streamer, StringRef Name, static ErrorOr<std::unique_ptr<Module>> getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer, LLVMContext &Context, bool MaterializeAll, - DiagnosticHandlerFunction DiagnosticHandler, bool ShouldLazyLoadMetadata = false) { - BitcodeReader *R = - new BitcodeReader(Buffer.get(), Context, DiagnosticHandler); + BitcodeReader *R = new BitcodeReader(Buffer.get(), Context); ErrorOr<std::unique_ptr<Module>> Ret = getBitcodeModuleImpl(nullptr, Buffer->getBufferIdentifier(), R, Context, @@ -4705,41 +5869,124 @@ getLazyBitcodeModuleImpl(std::unique_ptr<MemoryBuffer> &&Buffer, return Ret; } -ErrorOr<std::unique_ptr<Module>> llvm::getLazyBitcodeModule( - std::unique_ptr<MemoryBuffer> &&Buffer, LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler, bool ShouldLazyLoadMetadata) { +ErrorOr<std::unique_ptr<Module>> +llvm::getLazyBitcodeModule(std::unique_ptr<MemoryBuffer> &&Buffer, + LLVMContext &Context, bool ShouldLazyLoadMetadata) { return getLazyBitcodeModuleImpl(std::move(Buffer), Context, false, - DiagnosticHandler, ShouldLazyLoadMetadata); + ShouldLazyLoadMetadata); } -ErrorOr<std::unique_ptr<Module>> llvm::getStreamedBitcodeModule( - StringRef Name, std::unique_ptr<DataStreamer> Streamer, - LLVMContext &Context, DiagnosticHandlerFunction DiagnosticHandler) { +ErrorOr<std::unique_ptr<Module>> +llvm::getStreamedBitcodeModule(StringRef Name, + std::unique_ptr<DataStreamer> Streamer, + LLVMContext &Context) { std::unique_ptr<Module> M = make_unique<Module>(Name, Context); - BitcodeReader *R = new BitcodeReader(Context, DiagnosticHandler); + BitcodeReader *R = new BitcodeReader(Context); return getBitcodeModuleImpl(std::move(Streamer), Name, R, Context, false, false); } -ErrorOr<std::unique_ptr<Module>> -llvm::parseBitcodeFile(MemoryBufferRef Buffer, LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler) { +ErrorOr<std::unique_ptr<Module>> llvm::parseBitcodeFile(MemoryBufferRef Buffer, + LLVMContext &Context) { std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); - return getLazyBitcodeModuleImpl(std::move(Buf), Context, true, - DiagnosticHandler); + return getLazyBitcodeModuleImpl(std::move(Buf), Context, true); // TODO: Restore the use-lists to the in-memory state when the bitcode was // written. We must defer until the Module has been fully materialized. } -std::string -llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer, LLVMContext &Context, - DiagnosticHandlerFunction DiagnosticHandler) { +std::string llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer, + LLVMContext &Context) { std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); - auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context, - DiagnosticHandler); + auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context); ErrorOr<std::string> Triple = R->parseTriple(); if (Triple.getError()) return ""; return Triple.get(); } + +std::string llvm::getBitcodeProducerString(MemoryBufferRef Buffer, + LLVMContext &Context) { + std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); + BitcodeReader R(Buf.release(), Context); + ErrorOr<std::string> ProducerString = R.parseIdentificationBlock(); + if (ProducerString.getError()) + return ""; + return ProducerString.get(); +} + +// Parse the specified bitcode buffer, returning the function info index. +// If IsLazy is false, parse the entire function summary into +// the index. Otherwise skip the function summary section, and only create +// an index object with a map from function name to function summary offset. +// The index is used to perform lazy function summary reading later. +ErrorOr<std::unique_ptr<FunctionInfoIndex>> +llvm::getFunctionInfoIndex(MemoryBufferRef Buffer, + DiagnosticHandlerFunction DiagnosticHandler, + bool IsLazy) { + std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); + FunctionIndexBitcodeReader R(Buf.get(), DiagnosticHandler, IsLazy); + + auto Index = llvm::make_unique<FunctionInfoIndex>(); + + auto cleanupOnError = [&](std::error_code EC) { + R.releaseBuffer(); // Never take ownership on error. + return EC; + }; + + if (std::error_code EC = R.parseSummaryIndexInto(nullptr, Index.get())) + return cleanupOnError(EC); + + Buf.release(); // The FunctionIndexBitcodeReader owns it now. + return std::move(Index); +} + +// Check if the given bitcode buffer contains a function summary block. +bool llvm::hasFunctionSummary(MemoryBufferRef Buffer, + DiagnosticHandlerFunction DiagnosticHandler) { + std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); + FunctionIndexBitcodeReader R(Buf.get(), DiagnosticHandler, false, true); + + auto cleanupOnError = [&](std::error_code EC) { + R.releaseBuffer(); // Never take ownership on error. + return false; + }; + + if (std::error_code EC = R.parseSummaryIndexInto(nullptr, nullptr)) + return cleanupOnError(EC); + + Buf.release(); // The FunctionIndexBitcodeReader owns it now. + return R.foundFuncSummary(); +} + +// This method supports lazy reading of function summary data from the combined +// index during ThinLTO function importing. When reading the combined index +// file, getFunctionInfoIndex is first invoked with IsLazy=true. +// Then this method is called for each function considered for importing, +// to parse the summary information for the given function name into +// the index. +std::error_code llvm::readFunctionSummary( + MemoryBufferRef Buffer, DiagnosticHandlerFunction DiagnosticHandler, + StringRef FunctionName, std::unique_ptr<FunctionInfoIndex> Index) { + std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false); + FunctionIndexBitcodeReader R(Buf.get(), DiagnosticHandler); + + auto cleanupOnError = [&](std::error_code EC) { + R.releaseBuffer(); // Never take ownership on error. + return EC; + }; + + // Lookup the given function name in the FunctionMap, which may + // contain a list of function infos in the case of a COMDAT. Walk through + // and parse each function summary info at the function summary offset + // recorded when parsing the value symbol table. + for (const auto &FI : Index->getFunctionInfoList(FunctionName)) { + size_t FunctionSummaryOffset = FI->bitcodeIndex(); + if (std::error_code EC = + R.parseFunctionSummary(nullptr, Index.get(), FunctionSummaryOffset)) + return cleanupOnError(EC); + } + + Buf.release(); // The FunctionIndexBitcodeReader owns it now. + return std::error_code(); +} |