+/// Indicates which operator an operand allows (for the few operands that may
+/// only reference a certain operator).
+enum OperatorConstraint {
+ OC_None = 0, // No constraint
+ OC_CatchPad, // Must be CatchPadInst
+ OC_CleanupPad // Must be CleanupPadInst
+};
+
+class BitcodeReaderValueList {
+ std::vector<WeakVH> ValuePtrs;
+
+ /// As we resolve forward-referenced constants, we add information about them
+ /// to this vector. This allows us to resolve them in bulk instead of
+ /// resolving each reference at a time. See the code in
+ /// ResolveConstantForwardRefs for more information about this.
+ ///
+ /// The key of this vector is the placeholder constant, the value is the slot
+ /// number that holds the resolved value.
+ typedef std::vector<std::pair<Constant*, unsigned> > ResolveConstantsTy;
+ ResolveConstantsTy ResolveConstants;
+ LLVMContext &Context;
+public:
+ BitcodeReaderValueList(LLVMContext &C) : Context(C) {}
+ ~BitcodeReaderValueList() {
+ assert(ResolveConstants.empty() && "Constants not resolved?");
+ }
+
+ // vector compatibility methods
+ unsigned size() const { return ValuePtrs.size(); }
+ void resize(unsigned N) { ValuePtrs.resize(N); }
+ void push_back(Value *V) { ValuePtrs.emplace_back(V); }
+
+ void clear() {
+ assert(ResolveConstants.empty() && "Constants not resolved?");
+ ValuePtrs.clear();
+ }
+
+ Value *operator[](unsigned i) const {
+ assert(i < ValuePtrs.size());
+ return ValuePtrs[i];
+ }
+
+ Value *back() const { return ValuePtrs.back(); }
+ void pop_back() { ValuePtrs.pop_back(); }
+ bool empty() const { return ValuePtrs.empty(); }
+ void shrinkTo(unsigned N) {
+ assert(N <= size() && "Invalid shrinkTo request!");
+ ValuePtrs.resize(N);
+ }
+
+ Constant *getConstantFwdRef(unsigned Idx, Type *Ty);
+ Value *getValueFwdRef(unsigned Idx, Type *Ty,
+ OperatorConstraint OC = OC_None);
+
+ bool assignValue(Value *V, unsigned Idx);
+
+ /// Once all constants are read, this method bulk resolves any forward
+ /// references.
+ void resolveConstantForwardRefs();
+};
+
+class BitcodeReaderMDValueList {
+ unsigned NumFwdRefs;
+ bool AnyFwdRefs;
+ unsigned MinFwdRef;
+ unsigned MaxFwdRef;
+ std::vector<TrackingMDRef> MDValuePtrs;
+
+ LLVMContext &Context;
+public:
+ BitcodeReaderMDValueList(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(); }
+
+ Metadata *operator[](unsigned i) const {
+ assert(i < MDValuePtrs.size());
+ return MDValuePtrs[i];
+ }
+
+ void shrinkTo(unsigned N) {
+ assert(N <= size() && "Invalid shrinkTo request!");
+ MDValuePtrs.resize(N);
+ }
+
+ Metadata *getValueFwdRef(unsigned Idx);
+ void assignValue(Metadata *MD, unsigned Idx);
+ void tryToResolveCycles();
+};
+
+class BitcodeReader : public GVMaterializer {
+ LLVMContext &Context;
+ DiagnosticHandlerFunction DiagnosticHandler;
+ Module *TheModule = nullptr;
+ std::unique_ptr<MemoryBuffer> Buffer;
+ std::unique_ptr<BitstreamReader> StreamFile;
+ BitstreamCursor Stream;
+ uint64_t NextUnreadBit = 0;
+ bool SeenValueSymbolTable = false;
+ unsigned VSTOffset = 0;
+
+ std::vector<Type*> TypeList;
+ BitcodeReaderValueList ValueList;
+ BitcodeReaderMDValueList MDValueList;
+ std::vector<Comdat *> ComdatList;
+ SmallVector<Instruction *, 64> InstructionList;
+
+ std::vector<std::pair<GlobalVariable*, unsigned> > GlobalInits;
+ std::vector<std::pair<GlobalAlias*, unsigned> > AliasInits;
+ std::vector<std::pair<Function*, unsigned> > FunctionPrefixes;
+ std::vector<std::pair<Function*, unsigned> > FunctionPrologues;
+ std::vector<std::pair<Function*, unsigned> > FunctionPersonalityFns;
+
+ SmallVector<Instruction*, 64> InstsWithTBAATag;
+
+ /// The set of attributes by index. Index zero in the file is for null, and
+ /// is thus not represented here. As such all indices are off by one.
+ std::vector<AttributeSet> MAttributes;
+
+ /// 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
+ /// function.
+ std::vector<BasicBlock*> FunctionBBs;
+
+ // When reading the module header, this list is populated with functions that
+ // have bodies later in the file.
+ std::vector<Function*> FunctionsWithBodies;
+
+ // When intrinsic functions are encountered which require upgrading they are
+ // stored here with their replacement function.
+ typedef DenseMap<Function*, Function*> UpgradedIntrinsicMap;
+ UpgradedIntrinsicMap UpgradedIntrinsics;
+
+ // Map the bitcode's custom MDKind ID to the Module's MDKind ID.
+ DenseMap<unsigned, unsigned> MDKindMap;
+
+ // Several operations happen after the module header has been read, but
+ // before function bodies are processed. This keeps track of whether
+ // we've done this yet.
+ bool SeenFirstFunctionBody = false;
+
+ /// When function bodies are initially scanned, this map contains info about
+ /// where to find deferred function body in the stream.
+ DenseMap<Function*, uint64_t> DeferredFunctionInfo;
+
+ /// When Metadata block is initially scanned when parsing the module, we may
+ /// choose to defer parsing of the metadata. This vector contains info about
+ /// which Metadata blocks are deferred.
+ std::vector<uint64_t> DeferredMetadataInfo;
+
+ /// These are basic blocks forward-referenced by block addresses. They are
+ /// inserted lazily into functions when they're loaded. The basic block ID is
+ /// its index into the vector.
+ DenseMap<Function *, std::vector<BasicBlock *>> BasicBlockFwdRefs;
+ std::deque<Function *> BasicBlockFwdRefQueue;
+
+ /// Indicates that we are using a new encoding for instruction operands where
+ /// most operands in the current FUNCTION_BLOCK are encoded relative to the
+ /// instruction number, for a more compact encoding. Some instruction
+ /// operands are not relative to the instruction ID: basic block numbers, and
+ /// types. Once the old style function blocks have been phased out, we would
+ /// not need this flag.
+ bool UseRelativeIDs = false;
+
+ /// True if all functions will be materialized, negating the need to process
+ /// (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;
+
+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() override { freeState(); }
+
+ std::error_code materializeForwardReferencedFunctions();
+
+ void freeState();
+
+ void releaseBuffer();
+
+ bool isDematerializable(const GlobalValue *GV) const override;
+ std::error_code materialize(GlobalValue *GV) override;
+ std::error_code materializeModule(Module *M) 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.
+ std::error_code parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer,
+ Module *M,
+ bool ShouldLazyLoadMetadata = false);
+
+ /// \brief Cheap mechanism to just extract module triple
+ /// \returns true if an error occurred.
+ ErrorOr<std::string> parseTriple();
+
+ static uint64_t decodeSignRotatedValue(uint64_t V);
+
+ /// Materialize any deferred Metadata block.
+ std::error_code materializeMetadata() override;
+
+ void setStripDebugInfo() override;
+
+private:
+ std::vector<StructType *> IdentifiedStructTypes;
+ StructType *createIdentifiedStructType(LLVMContext &Context, StringRef Name);
+ StructType *createIdentifiedStructType(LLVMContext &Context);
+
+ Type *getTypeByID(unsigned ID);
+ Value *getFnValueByID(unsigned ID, Type *Ty,
+ OperatorConstraint OC = OC_None) {
+ if (Ty && Ty->isMetadataTy())
+ return MetadataAsValue::get(Ty->getContext(), getFnMetadataByID(ID));
+ return ValueList.getValueFwdRef(ID, Ty, OC);
+ }
+ Metadata *getFnMetadataByID(unsigned ID) {
+ return MDValueList.getValueFwdRef(ID);
+ }
+ BasicBlock *getBasicBlock(unsigned ID) const {
+ if (ID >= FunctionBBs.size()) return nullptr; // Invalid ID
+ return FunctionBBs[ID];
+ }
+ AttributeSet getAttributes(unsigned i) const {
+ if (i-1 < MAttributes.size())
+ return MAttributes[i-1];
+ return AttributeSet();
+ }
+
+ /// Read a value/type pair out of the specified record from slot 'Slot'.
+ /// Increment Slot past the number of slots used in the record. Return true on
+ /// failure.
+ bool getValueTypePair(SmallVectorImpl<uint64_t> &Record, unsigned &Slot,
+ unsigned InstNum, Value *&ResVal) {
+ if (Slot == Record.size()) return true;
+ unsigned ValNo = (unsigned)Record[Slot++];
+ // Adjust the ValNo, if it was encoded relative to the InstNum.
+ if (UseRelativeIDs)
+ ValNo = InstNum - ValNo;
+ if (ValNo < InstNum) {
+ // If this is not a forward reference, just return the value we already
+ // have.
+ ResVal = getFnValueByID(ValNo, nullptr);
+ return ResVal == nullptr;
+ }
+ if (Slot == Record.size())
+ return true;
+
+ unsigned TypeNo = (unsigned)Record[Slot++];
+ ResVal = getFnValueByID(ValNo, getTypeByID(TypeNo));
+ return ResVal == nullptr;
+ }
+
+ /// Read a value out of the specified record from slot 'Slot'. Increment Slot
+ /// past the number of slots used by the value in the record. Return true if
+ /// there is an error.
+ bool popValue(SmallVectorImpl<uint64_t> &Record, unsigned &Slot,
+ unsigned InstNum, Type *Ty, Value *&ResVal,
+ OperatorConstraint OC = OC_None) {
+ if (getValue(Record, Slot, InstNum, Ty, ResVal, OC))
+ return true;
+ // All values currently take a single record slot.
+ ++Slot;
+ return false;
+ }
+
+ /// Like popValue, but does not increment the Slot number.
+ bool getValue(SmallVectorImpl<uint64_t> &Record, unsigned Slot,
+ unsigned InstNum, Type *Ty, Value *&ResVal,
+ OperatorConstraint OC = OC_None) {
+ ResVal = getValue(Record, Slot, InstNum, Ty, OC);
+ return ResVal == nullptr;
+ }
+
+ /// Version of getValue that returns ResVal directly, or 0 if there is an
+ /// error.
+ Value *getValue(SmallVectorImpl<uint64_t> &Record, unsigned Slot,
+ unsigned InstNum, Type *Ty, OperatorConstraint OC = OC_None) {
+ if (Slot == Record.size()) return nullptr;
+ unsigned ValNo = (unsigned)Record[Slot];
+ // Adjust the ValNo, if it was encoded relative to the InstNum.
+ if (UseRelativeIDs)
+ ValNo = InstNum - ValNo;
+ return getFnValueByID(ValNo, Ty, OC);
+ }
+
+ /// Like getValue, but decodes signed VBRs.
+ Value *getValueSigned(SmallVectorImpl<uint64_t> &Record, unsigned Slot,
+ unsigned InstNum, Type *Ty,
+ OperatorConstraint OC = OC_None) {
+ if (Slot == Record.size()) return nullptr;
+ unsigned ValNo = (unsigned)decodeSignRotatedValue(Record[Slot]);
+ // Adjust the ValNo, if it was encoded relative to the InstNum.
+ if (UseRelativeIDs)
+ ValNo = InstNum - ValNo;
+ return getFnValueByID(ValNo, Ty, OC);
+ }
+
+ /// Converts alignment exponent (i.e. power of two (or zero)) to the
+ /// corresponding alignment to use. If alignment is too large, returns
+ /// 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 parseAttributeBlock();
+ std::error_code parseAttributeGroupBlock();
+ std::error_code parseTypeTable();
+ std::error_code parseTypeTableBody();
+
+ ErrorOr<Value *> recordValue(SmallVectorImpl<uint64_t> &Record,
+ unsigned NameIndex, Triple &TT);
+ std::error_code parseValueSymbolTable(unsigned Offset = 0);
+ std::error_code parseConstants();
+ 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 parseMetadataAttachment(Function &F);
+ ErrorOr<std::string> parseModuleTriple();
+ std::error_code parseUseLists();
+ std::error_code initStream(std::unique_ptr<DataStreamer> Streamer);
+ std::error_code initStreamFromBuffer();
+ std::error_code initLazyStream(std::unique_ptr<DataStreamer> Streamer);
+ std::error_code findFunctionInStream(
+ Function *F,
+ DenseMap<Function *, uint64_t>::iterator DeferredFunctionInfoIterator);
+};
+} // namespace
+