#define LLVM_ASMPARSER_LLPARSER_H
#include "LLLexer.h"
+#include "llvm/Instructions.h"
+#include "llvm/Module.h"
#include "llvm/Type.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/Support/ValueHandle.h"
#include <map>
namespace llvm {
class Instruction;
class Constant;
class GlobalValue;
- struct ValID;
-
+ class MDString;
+ class MDNode;
+ class StructType;
+
+ /// ValID - Represents a reference of a definition of some sort with no type.
+ /// There are several cases where we have to parse the value but where the
+ /// type can depend on later context. This may either be a numeric reference
+ /// or a symbolic (%var) reference. This is just a discriminated union.
+ struct ValID {
+ enum {
+ t_LocalID, t_GlobalID, // ID in UIntVal.
+ t_LocalName, t_GlobalName, // Name in StrVal.
+ t_APSInt, t_APFloat, // Value in APSIntVal/APFloatVal.
+ t_Null, t_Undef, t_Zero, // No value.
+ t_EmptyArray, // No value: []
+ t_Constant, // Value in ConstantVal.
+ t_InlineAsm, // Value in StrVal/StrVal2/UIntVal.
+ t_MDNode, // Value in MDNodeVal.
+ t_MDString, // Value in MDStringVal.
+ t_ConstantStruct, // Value in ConstantStructElts.
+ t_PackedConstantStruct // Value in ConstantStructElts.
+ } Kind;
+
+ LLLexer::LocTy Loc;
+ unsigned UIntVal;
+ std::string StrVal, StrVal2;
+ APSInt APSIntVal;
+ APFloat APFloatVal;
+ Constant *ConstantVal;
+ MDNode *MDNodeVal;
+ MDString *MDStringVal;
+ Constant **ConstantStructElts;
+
+ ValID() : Kind(t_LocalID), APFloatVal(0.0) {}
+ ~ValID() {
+ if (Kind == t_ConstantStruct || Kind == t_PackedConstantStruct)
+ delete [] ConstantStructElts;
+ }
+
+ bool operator<(const ValID &RHS) const {
+ if (Kind == t_LocalID || Kind == t_GlobalID)
+ return UIntVal < RHS.UIntVal;
+ assert((Kind == t_LocalName || Kind == t_GlobalName ||
+ Kind == t_ConstantStruct || Kind == t_PackedConstantStruct) &&
+ "Ordering not defined for this ValID kind yet");
+ return StrVal < RHS.StrVal;
+ }
+ };
+
class LLParser {
public:
typedef LLLexer::LocTy LocTy;
private:
-
+ LLVMContext &Context;
LLLexer Lex;
Module *M;
-
- // Type resolution handling data structures.
- std::map<std::string, std::pair<PATypeHolder, LocTy> > ForwardRefTypes;
- std::map<unsigned, std::pair<PATypeHolder, LocTy> > ForwardRefTypeIDs;
- std::vector<PATypeHolder> NumberedTypes;
-
- struct UpRefRecord {
- /// Loc - This is the location of the upref.
- LocTy Loc;
-
- /// NestingLevel - The number of nesting levels that need to be popped
- /// before this type is resolved.
- unsigned NestingLevel;
-
- /// LastContainedTy - This is the type at the current binding level for
- /// the type. Every time we reduce the nesting level, this gets updated.
- const Type *LastContainedTy;
-
- /// UpRefTy - This is the actual opaque type that the upreference is
- /// represented with.
- OpaqueType *UpRefTy;
-
- UpRefRecord(LocTy L, unsigned NL, OpaqueType *URTy)
- : Loc(L), NestingLevel(NL), LastContainedTy((Type*)URTy),
- UpRefTy(URTy) {}
+
+ // Instruction metadata resolution. Each instruction can have a list of
+ // MDRef info associated with them.
+ //
+ // The simpler approach of just creating temporary MDNodes and then calling
+ // RAUW on them when the definition is processed doesn't work because some
+ // instruction metadata kinds, such as dbg, get stored in the IR in an
+ // "optimized" format which doesn't participate in the normal value use
+ // lists. This means that RAUW doesn't work, even on temporary MDNodes
+ // which otherwise support RAUW. Instead, we defer resolving MDNode
+ // references until the definitions have been processed.
+ struct MDRef {
+ SMLoc Loc;
+ unsigned MDKind, MDSlot;
};
- std::vector<UpRefRecord> UpRefs;
+ DenseMap<Instruction*, std::vector<MDRef> > ForwardRefInstMetadata;
+
+ // Type resolution handling data structures. The location is set when we
+ // have processed a use of the type but not a definition yet.
+ StringMap<std::pair<Type*, LocTy> > NamedTypes;
+ std::vector<std::pair<Type*, LocTy> > NumberedTypes;
+
+ std::vector<TrackingVH<MDNode> > NumberedMetadata;
+ std::map<unsigned, std::pair<TrackingVH<MDNode>, LocTy> > ForwardRefMDNodes;
// Global Value reference information.
std::map<std::string, std::pair<GlobalValue*, LocTy> > ForwardRefVals;
std::map<unsigned, std::pair<GlobalValue*, LocTy> > ForwardRefValIDs;
std::vector<GlobalValue*> NumberedVals;
+
+ // References to blockaddress. The key is the function ValID, the value is
+ // a list of references to blocks in that function.
+ std::map<ValID, std::vector<std::pair<ValID, GlobalValue*> > >
+ ForwardRefBlockAddresses;
+
public:
- LLParser(MemoryBuffer *F, ParseError &Err, Module *m) : Lex(F, Err), M(m) {}
+ LLParser(MemoryBuffer *F, SourceMgr &SM, SMDiagnostic &Err, Module *m) :
+ Context(m->getContext()), Lex(F, SM, Err, m->getContext()),
+ M(m) {}
bool Run();
+ LLVMContext &getContext() { return Context; }
+
private:
- bool Error(LocTy L, const std::string &Msg) const {
+ bool Error(LocTy L, const Twine &Msg) const {
return Lex.Error(L, Msg);
}
- bool TokError(const std::string &Msg) const {
+ bool TokError(const Twine &Msg) const {
return Error(Lex.getLoc(), Msg);
}
/// GetGlobalVal - Get a value with the specified name or ID, creating a
/// forward reference record if needed. This can return null if the value
/// exists but does not have the right type.
- GlobalValue *GetGlobalVal(const std::string &N, const Type *Ty, LocTy Loc);
- GlobalValue *GetGlobalVal(unsigned ID, const Type *Ty, LocTy Loc);
+ GlobalValue *GetGlobalVal(const std::string &N, Type *Ty, LocTy Loc);
+ GlobalValue *GetGlobalVal(unsigned ID, Type *Ty, LocTy Loc);
// Helper Routines.
bool ParseToken(lltok::Kind T, const char *ErrMsg);
Lex.Lex();
return true;
}
- bool ParseOptionalToken(lltok::Kind T, bool &Present) {
+ bool ParseOptionalToken(lltok::Kind T, bool &Present, LocTy *Loc = 0) {
if (Lex.getKind() != T) {
Present = false;
} else {
+ if (Loc)
+ *Loc = Lex.getLoc();
Lex.Lex();
Present = true;
}
bool HasLinkage; return ParseOptionalLinkage(Linkage, HasLinkage);
}
bool ParseOptionalVisibility(unsigned &Visibility);
- bool ParseOptionalCallingConv(unsigned &CC);
+ bool ParseOptionalCallingConv(CallingConv::ID &CC);
bool ParseOptionalAlignment(unsigned &Alignment);
- bool ParseOptionalCommaAlignment(unsigned &Alignment);
- bool ParseIndexList(SmallVectorImpl<unsigned> &Indices);
+ bool ParseScopeAndOrdering(bool isAtomic, SynchronizationScope &Scope,
+ AtomicOrdering &Ordering);
+ bool ParseOptionalStackAlignment(unsigned &Alignment);
+ bool ParseOptionalCommaAlign(unsigned &Alignment, bool &AteExtraComma);
+ bool ParseIndexList(SmallVectorImpl<unsigned> &Indices,bool &AteExtraComma);
+ bool ParseIndexList(SmallVectorImpl<unsigned> &Indices) {
+ bool AteExtraComma;
+ if (ParseIndexList(Indices, AteExtraComma)) return true;
+ if (AteExtraComma)
+ return TokError("expected index");
+ return false;
+ }
// Top-Level Entities
bool ParseTopLevelEntities();
bool ParseDefine();
bool ParseGlobalType(bool &IsConstant);
+ bool ParseUnnamedGlobal();
bool ParseNamedGlobal();
bool ParseGlobal(const std::string &Name, LocTy Loc, unsigned Linkage,
bool HasLinkage, unsigned Visibility);
bool ParseAlias(const std::string &Name, LocTy Loc, unsigned Visibility);
+ bool ParseStandaloneMetadata();
+ bool ParseNamedMetadata();
+ bool ParseMDString(MDString *&Result);
+ bool ParseMDNodeID(MDNode *&Result);
+ bool ParseMDNodeID(MDNode *&Result, unsigned &SlotNo);
// Type Parsing.
- bool ParseType(PATypeHolder &Result);
- bool ParseType(PATypeHolder &Result, LocTy &Loc) {
+ bool ParseType(Type *&Result, bool AllowVoid = false);
+ bool ParseType(Type *&Result, LocTy &Loc, bool AllowVoid = false) {
Loc = Lex.getLoc();
- return ParseType(Result);
+ return ParseType(Result, AllowVoid);
}
- bool ParseTypeRec(PATypeHolder &H);
- bool ParseStructType(PATypeHolder &H, bool Packed);
- bool ParseArrayVectorType(PATypeHolder &H, bool isVector);
- bool ParseFunctionType(PATypeHolder &Result);
- PATypeHolder HandleUpRefs(const Type *Ty);
-
- // Constants.
- bool ParseValID(ValID &ID);
- bool ConvertGlobalValIDToValue(const Type *Ty, ValID &ID, Constant *&V);
- bool ParseGlobalValue(const Type *Ty, Constant *&V);
- bool ParseGlobalTypeAndValue(Constant *&V);
- bool ParseGlobalValueVector(SmallVectorImpl<Constant*> &Elts);
+ bool ParseAnonStructType(Type *&Result, bool Packed);
+ bool ParseStructBody(SmallVectorImpl<Type*> &Body);
+ bool ParseStructDefinition(SMLoc TypeLoc, StringRef Name,
+ std::pair<Type*, LocTy> &Entry,
+ Type *&ResultTy);
+ bool ParseArrayVectorType(Type *&Result, bool isVector);
+ bool ParseFunctionType(Type *&Result);
// Function Semantic Analysis.
class PerFunctionState {
std::map<std::string, std::pair<Value*, LocTy> > ForwardRefVals;
std::map<unsigned, std::pair<Value*, LocTy> > ForwardRefValIDs;
std::vector<Value*> NumberedVals;
+
+ /// FunctionNumber - If this is an unnamed function, this is the slot
+ /// number of it, otherwise it is -1.
+ int FunctionNumber;
public:
- PerFunctionState(LLParser &p, Function &f);
+ PerFunctionState(LLParser &p, Function &f, int FunctionNumber);
~PerFunctionState();
Function &getFunction() const { return F; }
- bool VerifyFunctionComplete();
+ bool FinishFunction();
/// GetVal - Get a value with the specified name or ID, creating a
/// forward reference record if needed. This can return null if the value
/// exists but does not have the right type.
- Value *GetVal(const std::string &Name, const Type *Ty, LocTy Loc);
- Value *GetVal(unsigned ID, const Type *Ty, LocTy Loc);
+ Value *GetVal(const std::string &Name, Type *Ty, LocTy Loc);
+ Value *GetVal(unsigned ID, Type *Ty, LocTy Loc);
/// SetInstName - After an instruction is parsed and inserted into its
/// basic block, this installs its name.
BasicBlock *DefineBB(const std::string &Name, LocTy Loc);
};
- bool ConvertValIDToValue(const Type *Ty, ValID &ID, Value *&V,
- PerFunctionState &PFS);
+ bool ConvertValIDToValue(Type *Ty, ValID &ID, Value *&V,
+ PerFunctionState *PFS);
- bool ParseValue(const Type *Ty, Value *&V, PerFunctionState &PFS);
- bool ParseValue(const Type *Ty, Value *&V, LocTy &Loc,
+ bool ParseValue(Type *Ty, Value *&V, PerFunctionState *PFS);
+ bool ParseValue(Type *Ty, Value *&V, PerFunctionState &PFS) {
+ return ParseValue(Ty, V, &PFS);
+ }
+ bool ParseValue(Type *Ty, Value *&V, LocTy &Loc,
PerFunctionState &PFS) {
Loc = Lex.getLoc();
- return ParseValue(Ty, V, PFS);
+ return ParseValue(Ty, V, &PFS);
}
- bool ParseTypeAndValue(Value *&V, PerFunctionState &PFS);
+ bool ParseTypeAndValue(Value *&V, PerFunctionState *PFS);
+ bool ParseTypeAndValue(Value *&V, PerFunctionState &PFS) {
+ return ParseTypeAndValue(V, &PFS);
+ }
bool ParseTypeAndValue(Value *&V, LocTy &Loc, PerFunctionState &PFS) {
Loc = Lex.getLoc();
return ParseTypeAndValue(V, PFS);
}
+ bool ParseTypeAndBasicBlock(BasicBlock *&BB, LocTy &Loc,
+ PerFunctionState &PFS);
+ bool ParseTypeAndBasicBlock(BasicBlock *&BB, PerFunctionState &PFS) {
+ LocTy Loc;
+ return ParseTypeAndBasicBlock(BB, Loc, PFS);
+ }
+
struct ParamInfo {
LocTy Loc;
bool ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
PerFunctionState &PFS);
+ // Constant Parsing.
+ bool ParseValID(ValID &ID, PerFunctionState *PFS = NULL);
+ bool ParseGlobalValue(Type *Ty, Constant *&V);
+ bool ParseGlobalTypeAndValue(Constant *&V);
+ bool ParseGlobalValueVector(SmallVectorImpl<Constant*> &Elts);
+ bool ParseMetadataListValue(ValID &ID, PerFunctionState *PFS);
+ bool ParseMetadataValue(ValID &ID, PerFunctionState *PFS);
+ bool ParseMDNodeVector(SmallVectorImpl<Value*> &, PerFunctionState *PFS);
+ bool ParseInstructionMetadata(Instruction *Inst, PerFunctionState *PFS);
+
// Function Parsing.
struct ArgInfo {
LocTy Loc;
- PATypeHolder Type;
+ Type *Ty;
unsigned Attrs;
std::string Name;
- ArgInfo(LocTy L, PATypeHolder Ty, unsigned Attr, const std::string &N)
- : Loc(L), Type(Ty), Attrs(Attr), Name(N) {}
+ ArgInfo(LocTy L, Type *ty, unsigned Attr, const std::string &N)
+ : Loc(L), Ty(ty), Attrs(Attr), Name(N) {}
};
- bool ParseArgumentList(std::vector<ArgInfo> &ArgList,
- bool &isVarArg);
+ bool ParseArgumentList(SmallVectorImpl<ArgInfo> &ArgList, bool &isVarArg);
bool ParseFunctionHeader(Function *&Fn, bool isDefine);
bool ParseFunctionBody(Function &Fn);
bool ParseBasicBlock(PerFunctionState &PFS);
- // Instruction Parsing.
- bool ParseInstruction(Instruction *&Inst, BasicBlock *BB,
- PerFunctionState &PFS);
+ // Instruction Parsing. Each instruction parsing routine can return with a
+ // normal result, an error result, or return having eaten an extra comma.
+ enum InstResult { InstNormal = 0, InstError = 1, InstExtraComma = 2 };
+ int ParseInstruction(Instruction *&Inst, BasicBlock *BB,
+ PerFunctionState &PFS);
bool ParseCmpPredicate(unsigned &Pred, unsigned Opc);
bool ParseRet(Instruction *&Inst, BasicBlock *BB, PerFunctionState &PFS);
bool ParseBr(Instruction *&Inst, PerFunctionState &PFS);
bool ParseSwitch(Instruction *&Inst, PerFunctionState &PFS);
+ bool ParseIndirectBr(Instruction *&Inst, PerFunctionState &PFS);
bool ParseInvoke(Instruction *&Inst, PerFunctionState &PFS);
+ bool ParseResume(Instruction *&Inst, PerFunctionState &PFS);
- bool ParseArithmetic(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
+ bool ParseArithmetic(Instruction *&I, PerFunctionState &PFS, unsigned Opc,
+ unsigned OperandType);
bool ParseLogical(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseCompare(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseCast(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
bool ParseExtractElement(Instruction *&I, PerFunctionState &PFS);
bool ParseInsertElement(Instruction *&I, PerFunctionState &PFS);
bool ParseShuffleVector(Instruction *&I, PerFunctionState &PFS);
- bool ParsePHI(Instruction *&I, PerFunctionState &PFS);
+ int ParsePHI(Instruction *&I, PerFunctionState &PFS);
+ bool ParseLandingPad(Instruction *&I, PerFunctionState &PFS);
bool ParseCall(Instruction *&I, PerFunctionState &PFS, bool isTail);
- bool ParseAlloc(Instruction *&I, PerFunctionState &PFS, unsigned Opc);
- bool ParseFree(Instruction *&I, PerFunctionState &PFS);
- bool ParseLoad(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
- bool ParseStore(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
- bool ParseGetResult(Instruction *&I, PerFunctionState &PFS);
- bool ParseGetElementPtr(Instruction *&I, PerFunctionState &PFS);
- bool ParseExtractValue(Instruction *&I, PerFunctionState &PFS);
- bool ParseInsertValue(Instruction *&I, PerFunctionState &PFS);
+ int ParseAlloc(Instruction *&I, PerFunctionState &PFS);
+ int ParseLoad(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
+ int ParseStore(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
+ int ParseCmpXchg(Instruction *&I, PerFunctionState &PFS);
+ int ParseAtomicRMW(Instruction *&I, PerFunctionState &PFS);
+ int ParseFence(Instruction *&I, PerFunctionState &PFS);
+ int ParseGetElementPtr(Instruction *&I, PerFunctionState &PFS);
+ int ParseExtractValue(Instruction *&I, PerFunctionState &PFS);
+ int ParseInsertValue(Instruction *&I, PerFunctionState &PFS);
+
+ bool ResolveForwardRefBlockAddresses(Function *TheFn,
+ std::vector<std::pair<ValID, GlobalValue*> > &Refs,
+ PerFunctionState *PFS);
};
} // End llvm namespace