Check in LLVM r95781.
diff --git a/lib/AsmParser/CMakeLists.txt b/lib/AsmParser/CMakeLists.txt
new file mode 100644
index 0000000..985ebe2
--- /dev/null
+++ b/lib/AsmParser/CMakeLists.txt
@@ -0,0 +1,6 @@
+# AsmParser
+add_llvm_library(LLVMAsmParser
+ LLLexer.cpp
+ LLParser.cpp
+ Parser.cpp
+ )
diff --git a/lib/AsmParser/LLLexer.cpp b/lib/AsmParser/LLLexer.cpp
new file mode 100644
index 0000000..8ad658d
--- /dev/null
+++ b/lib/AsmParser/LLLexer.cpp
@@ -0,0 +1,864 @@
+//===- LLLexer.cpp - Lexer for .ll Files ----------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Implement the Lexer for .ll files.
+//
+//===----------------------------------------------------------------------===//
+
+#include "LLLexer.h"
+#include "llvm/DerivedTypes.h"
+#include "llvm/Instruction.h"
+#include "llvm/LLVMContext.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/SourceMgr.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Assembly/Parser.h"
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+using namespace llvm;
+
+bool LLLexer::Error(LocTy ErrorLoc, const std::string &Msg) const {
+ ErrorInfo = SM.GetMessage(ErrorLoc, Msg, "error");
+ return true;
+}
+
+//===----------------------------------------------------------------------===//
+// Helper functions.
+//===----------------------------------------------------------------------===//
+
+// atoull - Convert an ascii string of decimal digits into the unsigned long
+// long representation... this does not have to do input error checking,
+// because we know that the input will be matched by a suitable regex...
+//
+uint64_t LLLexer::atoull(const char *Buffer, const char *End) {
+ uint64_t Result = 0;
+ for (; Buffer != End; Buffer++) {
+ uint64_t OldRes = Result;
+ Result *= 10;
+ Result += *Buffer-'0';
+ if (Result < OldRes) { // Uh, oh, overflow detected!!!
+ Error("constant bigger than 64 bits detected!");
+ return 0;
+ }
+ }
+ return Result;
+}
+
+uint64_t LLLexer::HexIntToVal(const char *Buffer, const char *End) {
+ uint64_t Result = 0;
+ for (; Buffer != End; ++Buffer) {
+ uint64_t OldRes = Result;
+ Result *= 16;
+ char C = *Buffer;
+ if (C >= '0' && C <= '9')
+ Result += C-'0';
+ else if (C >= 'A' && C <= 'F')
+ Result += C-'A'+10;
+ else if (C >= 'a' && C <= 'f')
+ Result += C-'a'+10;
+
+ if (Result < OldRes) { // Uh, oh, overflow detected!!!
+ Error("constant bigger than 64 bits detected!");
+ return 0;
+ }
+ }
+ return Result;
+}
+
+void LLLexer::HexToIntPair(const char *Buffer, const char *End,
+ uint64_t Pair[2]) {
+ Pair[0] = 0;
+ for (int i=0; i<16; i++, Buffer++) {
+ assert(Buffer != End);
+ Pair[0] *= 16;
+ char C = *Buffer;
+ if (C >= '0' && C <= '9')
+ Pair[0] += C-'0';
+ else if (C >= 'A' && C <= 'F')
+ Pair[0] += C-'A'+10;
+ else if (C >= 'a' && C <= 'f')
+ Pair[0] += C-'a'+10;
+ }
+ Pair[1] = 0;
+ for (int i=0; i<16 && Buffer != End; i++, Buffer++) {
+ Pair[1] *= 16;
+ char C = *Buffer;
+ if (C >= '0' && C <= '9')
+ Pair[1] += C-'0';
+ else if (C >= 'A' && C <= 'F')
+ Pair[1] += C-'A'+10;
+ else if (C >= 'a' && C <= 'f')
+ Pair[1] += C-'a'+10;
+ }
+ if (Buffer != End)
+ Error("constant bigger than 128 bits detected!");
+}
+
+/// FP80HexToIntPair - translate an 80 bit FP80 number (20 hexits) into
+/// { low64, high16 } as usual for an APInt.
+void LLLexer::FP80HexToIntPair(const char *Buffer, const char *End,
+ uint64_t Pair[2]) {
+ Pair[1] = 0;
+ for (int i=0; i<4 && Buffer != End; i++, Buffer++) {
+ assert(Buffer != End);
+ Pair[1] *= 16;
+ char C = *Buffer;
+ if (C >= '0' && C <= '9')
+ Pair[1] += C-'0';
+ else if (C >= 'A' && C <= 'F')
+ Pair[1] += C-'A'+10;
+ else if (C >= 'a' && C <= 'f')
+ Pair[1] += C-'a'+10;
+ }
+ Pair[0] = 0;
+ for (int i=0; i<16; i++, Buffer++) {
+ Pair[0] *= 16;
+ char C = *Buffer;
+ if (C >= '0' && C <= '9')
+ Pair[0] += C-'0';
+ else if (C >= 'A' && C <= 'F')
+ Pair[0] += C-'A'+10;
+ else if (C >= 'a' && C <= 'f')
+ Pair[0] += C-'a'+10;
+ }
+ if (Buffer != End)
+ Error("constant bigger than 128 bits detected!");
+}
+
+// UnEscapeLexed - Run through the specified buffer and change \xx codes to the
+// appropriate character.
+static void UnEscapeLexed(std::string &Str) {
+ if (Str.empty()) return;
+
+ char *Buffer = &Str[0], *EndBuffer = Buffer+Str.size();
+ char *BOut = Buffer;
+ for (char *BIn = Buffer; BIn != EndBuffer; ) {
+ if (BIn[0] == '\\') {
+ if (BIn < EndBuffer-1 && BIn[1] == '\\') {
+ *BOut++ = '\\'; // Two \ becomes one
+ BIn += 2;
+ } else if (BIn < EndBuffer-2 && isxdigit(BIn[1]) && isxdigit(BIn[2])) {
+ char Tmp = BIn[3]; BIn[3] = 0; // Terminate string
+ *BOut = (char)strtol(BIn+1, 0, 16); // Convert to number
+ BIn[3] = Tmp; // Restore character
+ BIn += 3; // Skip over handled chars
+ ++BOut;
+ } else {
+ *BOut++ = *BIn++;
+ }
+ } else {
+ *BOut++ = *BIn++;
+ }
+ }
+ Str.resize(BOut-Buffer);
+}
+
+/// isLabelChar - Return true for [-a-zA-Z$._0-9].
+static bool isLabelChar(char C) {
+ return isalnum(C) || C == '-' || C == '$' || C == '.' || C == '_';
+}
+
+
+/// isLabelTail - Return true if this pointer points to a valid end of a label.
+static const char *isLabelTail(const char *CurPtr) {
+ while (1) {
+ if (CurPtr[0] == ':') return CurPtr+1;
+ if (!isLabelChar(CurPtr[0])) return 0;
+ ++CurPtr;
+ }
+}
+
+
+
+//===----------------------------------------------------------------------===//
+// Lexer definition.
+//===----------------------------------------------------------------------===//
+
+LLLexer::LLLexer(MemoryBuffer *StartBuf, SourceMgr &sm, SMDiagnostic &Err,
+ LLVMContext &C)
+ : CurBuf(StartBuf), ErrorInfo(Err), SM(sm), Context(C), APFloatVal(0.0) {
+ CurPtr = CurBuf->getBufferStart();
+}
+
+std::string LLLexer::getFilename() const {
+ return CurBuf->getBufferIdentifier();
+}
+
+int LLLexer::getNextChar() {
+ char CurChar = *CurPtr++;
+ switch (CurChar) {
+ default: return (unsigned char)CurChar;
+ case 0:
+ // A nul character in the stream is either the end of the current buffer or
+ // a random nul in the file. Disambiguate that here.
+ if (CurPtr-1 != CurBuf->getBufferEnd())
+ return 0; // Just whitespace.
+
+ // Otherwise, return end of file.
+ --CurPtr; // Another call to lex will return EOF again.
+ return EOF;
+ }
+}
+
+
+lltok::Kind LLLexer::LexToken() {
+ TokStart = CurPtr;
+
+ int CurChar = getNextChar();
+ switch (CurChar) {
+ default:
+ // Handle letters: [a-zA-Z_]
+ if (isalpha(CurChar) || CurChar == '_')
+ return LexIdentifier();
+
+ return lltok::Error;
+ case EOF: return lltok::Eof;
+ case 0:
+ case ' ':
+ case '\t':
+ case '\n':
+ case '\r':
+ // Ignore whitespace.
+ return LexToken();
+ case '+': return LexPositive();
+ case '@': return LexAt();
+ case '%': return LexPercent();
+ case '"': return LexQuote();
+ case '.':
+ if (const char *Ptr = isLabelTail(CurPtr)) {
+ CurPtr = Ptr;
+ StrVal.assign(TokStart, CurPtr-1);
+ return lltok::LabelStr;
+ }
+ if (CurPtr[0] == '.' && CurPtr[1] == '.') {
+ CurPtr += 2;
+ return lltok::dotdotdot;
+ }
+ return lltok::Error;
+ case '$':
+ if (const char *Ptr = isLabelTail(CurPtr)) {
+ CurPtr = Ptr;
+ StrVal.assign(TokStart, CurPtr-1);
+ return lltok::LabelStr;
+ }
+ return lltok::Error;
+ case ';':
+ SkipLineComment();
+ return LexToken();
+ case '!': return LexExclaim();
+ case '0': case '1': case '2': case '3': case '4':
+ case '5': case '6': case '7': case '8': case '9':
+ case '-':
+ return LexDigitOrNegative();
+ case '=': return lltok::equal;
+ case '[': return lltok::lsquare;
+ case ']': return lltok::rsquare;
+ case '{': return lltok::lbrace;
+ case '}': return lltok::rbrace;
+ case '<': return lltok::less;
+ case '>': return lltok::greater;
+ case '(': return lltok::lparen;
+ case ')': return lltok::rparen;
+ case ',': return lltok::comma;
+ case '*': return lltok::star;
+ case '\\': return lltok::backslash;
+ }
+}
+
+void LLLexer::SkipLineComment() {
+ while (1) {
+ if (CurPtr[0] == '\n' || CurPtr[0] == '\r' || getNextChar() == EOF)
+ return;
+ }
+}
+
+/// LexAt - Lex all tokens that start with an @ character:
+/// GlobalVar @\"[^\"]*\"
+/// GlobalVar @[-a-zA-Z$._][-a-zA-Z$._0-9]*
+/// GlobalVarID @[0-9]+
+lltok::Kind LLLexer::LexAt() {
+ // Handle AtStringConstant: @\"[^\"]*\"
+ if (CurPtr[0] == '"') {
+ ++CurPtr;
+
+ while (1) {
+ int CurChar = getNextChar();
+
+ if (CurChar == EOF) {
+ Error("end of file in global variable name");
+ return lltok::Error;
+ }
+ if (CurChar == '"') {
+ StrVal.assign(TokStart+2, CurPtr-1);
+ UnEscapeLexed(StrVal);
+ return lltok::GlobalVar;
+ }
+ }
+ }
+
+ // Handle GlobalVarName: @[-a-zA-Z$._][-a-zA-Z$._0-9]*
+ if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ CurPtr[0] == '.' || CurPtr[0] == '_') {
+ ++CurPtr;
+ while (isalnum(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ CurPtr[0] == '.' || CurPtr[0] == '_')
+ ++CurPtr;
+
+ StrVal.assign(TokStart+1, CurPtr); // Skip @
+ return lltok::GlobalVar;
+ }
+
+ // Handle GlobalVarID: @[0-9]+
+ if (isdigit(CurPtr[0])) {
+ for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ /*empty*/;
+
+ uint64_t Val = atoull(TokStart+1, CurPtr);
+ if ((unsigned)Val != Val)
+ Error("invalid value number (too large)!");
+ UIntVal = unsigned(Val);
+ return lltok::GlobalID;
+ }
+
+ return lltok::Error;
+}
+
+
+/// LexPercent - Lex all tokens that start with a % character:
+/// LocalVar ::= %\"[^\"]*\"
+/// LocalVar ::= %[-a-zA-Z$._][-a-zA-Z$._0-9]*
+/// LocalVarID ::= %[0-9]+
+lltok::Kind LLLexer::LexPercent() {
+ // Handle LocalVarName: %\"[^\"]*\"
+ if (CurPtr[0] == '"') {
+ ++CurPtr;
+
+ while (1) {
+ int CurChar = getNextChar();
+
+ if (CurChar == EOF) {
+ Error("end of file in string constant");
+ return lltok::Error;
+ }
+ if (CurChar == '"') {
+ StrVal.assign(TokStart+2, CurPtr-1);
+ UnEscapeLexed(StrVal);
+ return lltok::LocalVar;
+ }
+ }
+ }
+
+ // Handle LocalVarName: %[-a-zA-Z$._][-a-zA-Z$._0-9]*
+ if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ CurPtr[0] == '.' || CurPtr[0] == '_') {
+ ++CurPtr;
+ while (isalnum(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ CurPtr[0] == '.' || CurPtr[0] == '_')
+ ++CurPtr;
+
+ StrVal.assign(TokStart+1, CurPtr); // Skip %
+ return lltok::LocalVar;
+ }
+
+ // Handle LocalVarID: %[0-9]+
+ if (isdigit(CurPtr[0])) {
+ for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ /*empty*/;
+
+ uint64_t Val = atoull(TokStart+1, CurPtr);
+ if ((unsigned)Val != Val)
+ Error("invalid value number (too large)!");
+ UIntVal = unsigned(Val);
+ return lltok::LocalVarID;
+ }
+
+ return lltok::Error;
+}
+
+/// LexQuote - Lex all tokens that start with a " character:
+/// QuoteLabel "[^"]+":
+/// StringConstant "[^"]*"
+lltok::Kind LLLexer::LexQuote() {
+ while (1) {
+ int CurChar = getNextChar();
+
+ if (CurChar == EOF) {
+ Error("end of file in quoted string");
+ return lltok::Error;
+ }
+
+ if (CurChar != '"') continue;
+
+ if (CurPtr[0] != ':') {
+ StrVal.assign(TokStart+1, CurPtr-1);
+ UnEscapeLexed(StrVal);
+ return lltok::StringConstant;
+ }
+
+ ++CurPtr;
+ StrVal.assign(TokStart+1, CurPtr-2);
+ UnEscapeLexed(StrVal);
+ return lltok::LabelStr;
+ }
+}
+
+static bool JustWhitespaceNewLine(const char *&Ptr) {
+ const char *ThisPtr = Ptr;
+ while (*ThisPtr == ' ' || *ThisPtr == '\t')
+ ++ThisPtr;
+ if (*ThisPtr == '\n' || *ThisPtr == '\r') {
+ Ptr = ThisPtr;
+ return true;
+ }
+ return false;
+}
+
+/// LexExclaim:
+/// !foo
+/// !
+lltok::Kind LLLexer::LexExclaim() {
+ // Lex a metadata name as a MetadataVar.
+ if (isalpha(CurPtr[0])) {
+ ++CurPtr;
+ while (isalnum(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ CurPtr[0] == '.' || CurPtr[0] == '_')
+ ++CurPtr;
+
+ StrVal.assign(TokStart+1, CurPtr); // Skip !
+ return lltok::MetadataVar;
+ }
+ return lltok::exclaim;
+}
+
+/// LexIdentifier: Handle several related productions:
+/// Label [-a-zA-Z$._0-9]+:
+/// IntegerType i[0-9]+
+/// Keyword sdiv, float, ...
+/// HexIntConstant [us]0x[0-9A-Fa-f]+
+lltok::Kind LLLexer::LexIdentifier() {
+ const char *StartChar = CurPtr;
+ const char *IntEnd = CurPtr[-1] == 'i' ? 0 : StartChar;
+ const char *KeywordEnd = 0;
+
+ for (; isLabelChar(*CurPtr); ++CurPtr) {
+ // If we decide this is an integer, remember the end of the sequence.
+ if (!IntEnd && !isdigit(*CurPtr)) IntEnd = CurPtr;
+ if (!KeywordEnd && !isalnum(*CurPtr) && *CurPtr != '_') KeywordEnd = CurPtr;
+ }
+
+ // If we stopped due to a colon, this really is a label.
+ if (*CurPtr == ':') {
+ StrVal.assign(StartChar-1, CurPtr++);
+ return lltok::LabelStr;
+ }
+
+ // Otherwise, this wasn't a label. If this was valid as an integer type,
+ // return it.
+ if (IntEnd == 0) IntEnd = CurPtr;
+ if (IntEnd != StartChar) {
+ CurPtr = IntEnd;
+ uint64_t NumBits = atoull(StartChar, CurPtr);
+ if (NumBits < IntegerType::MIN_INT_BITS ||
+ NumBits > IntegerType::MAX_INT_BITS) {
+ Error("bitwidth for integer type out of range!");
+ return lltok::Error;
+ }
+ TyVal = IntegerType::get(Context, NumBits);
+ return lltok::Type;
+ }
+
+ // Otherwise, this was a letter sequence. See which keyword this is.
+ if (KeywordEnd == 0) KeywordEnd = CurPtr;
+ CurPtr = KeywordEnd;
+ --StartChar;
+ unsigned Len = CurPtr-StartChar;
+#define KEYWORD(STR) \
+ if (Len == strlen(#STR) && !memcmp(StartChar, #STR, strlen(#STR))) \
+ return lltok::kw_##STR;
+
+ KEYWORD(begin); KEYWORD(end);
+ KEYWORD(true); KEYWORD(false);
+ KEYWORD(declare); KEYWORD(define);
+ KEYWORD(global); KEYWORD(constant);
+
+ KEYWORD(private);
+ KEYWORD(linker_private);
+ KEYWORD(internal);
+ KEYWORD(available_externally);
+ KEYWORD(linkonce);
+ KEYWORD(linkonce_odr);
+ KEYWORD(weak);
+ KEYWORD(weak_odr);
+ KEYWORD(appending);
+ KEYWORD(dllimport);
+ KEYWORD(dllexport);
+ KEYWORD(common);
+ KEYWORD(default);
+ KEYWORD(hidden);
+ KEYWORD(protected);
+ KEYWORD(extern_weak);
+ KEYWORD(external);
+ KEYWORD(thread_local);
+ KEYWORD(zeroinitializer);
+ KEYWORD(undef);
+ KEYWORD(null);
+ KEYWORD(to);
+ KEYWORD(tail);
+ KEYWORD(target);
+ KEYWORD(triple);
+ KEYWORD(deplibs);
+ KEYWORD(datalayout);
+ KEYWORD(volatile);
+ KEYWORD(nuw);
+ KEYWORD(nsw);
+ KEYWORD(exact);
+ KEYWORD(inbounds);
+ KEYWORD(align);
+ KEYWORD(addrspace);
+ KEYWORD(section);
+ KEYWORD(alias);
+ KEYWORD(module);
+ KEYWORD(asm);
+ KEYWORD(sideeffect);
+ KEYWORD(alignstack);
+ KEYWORD(gc);
+
+ KEYWORD(ccc);
+ KEYWORD(fastcc);
+ KEYWORD(coldcc);
+ KEYWORD(x86_stdcallcc);
+ KEYWORD(x86_fastcallcc);
+ KEYWORD(arm_apcscc);
+ KEYWORD(arm_aapcscc);
+ KEYWORD(arm_aapcs_vfpcc);
+ KEYWORD(msp430_intrcc);
+
+ KEYWORD(cc);
+ KEYWORD(c);
+
+ KEYWORD(signext);
+ KEYWORD(zeroext);
+ KEYWORD(inreg);
+ KEYWORD(sret);
+ KEYWORD(nounwind);
+ KEYWORD(noreturn);
+ KEYWORD(noalias);
+ KEYWORD(nocapture);
+ KEYWORD(byval);
+ KEYWORD(nest);
+ KEYWORD(readnone);
+ KEYWORD(readonly);
+
+ KEYWORD(inlinehint);
+ KEYWORD(noinline);
+ KEYWORD(alwaysinline);
+ KEYWORD(optsize);
+ KEYWORD(ssp);
+ KEYWORD(sspreq);
+ KEYWORD(noredzone);
+ KEYWORD(noimplicitfloat);
+ KEYWORD(naked);
+
+ KEYWORD(type);
+ KEYWORD(opaque);
+
+ KEYWORD(eq); KEYWORD(ne); KEYWORD(slt); KEYWORD(sgt); KEYWORD(sle);
+ KEYWORD(sge); KEYWORD(ult); KEYWORD(ugt); KEYWORD(ule); KEYWORD(uge);
+ KEYWORD(oeq); KEYWORD(one); KEYWORD(olt); KEYWORD(ogt); KEYWORD(ole);
+ KEYWORD(oge); KEYWORD(ord); KEYWORD(uno); KEYWORD(ueq); KEYWORD(une);
+
+ KEYWORD(x);
+ KEYWORD(blockaddress);
+#undef KEYWORD
+
+ // Keywords for types.
+#define TYPEKEYWORD(STR, LLVMTY) \
+ if (Len == strlen(STR) && !memcmp(StartChar, STR, strlen(STR))) { \
+ TyVal = LLVMTY; return lltok::Type; }
+ TYPEKEYWORD("void", Type::getVoidTy(Context));
+ TYPEKEYWORD("float", Type::getFloatTy(Context));
+ TYPEKEYWORD("double", Type::getDoubleTy(Context));
+ TYPEKEYWORD("x86_fp80", Type::getX86_FP80Ty(Context));
+ TYPEKEYWORD("fp128", Type::getFP128Ty(Context));
+ TYPEKEYWORD("ppc_fp128", Type::getPPC_FP128Ty(Context));
+ TYPEKEYWORD("label", Type::getLabelTy(Context));
+ TYPEKEYWORD("metadata", Type::getMetadataTy(Context));
+#undef TYPEKEYWORD
+
+ // Handle special forms for autoupgrading. Drop these in LLVM 3.0. This is
+ // to avoid conflicting with the sext/zext instructions, below.
+ if (Len == 4 && !memcmp(StartChar, "sext", 4)) {
+ // Scan CurPtr ahead, seeing if there is just whitespace before the newline.
+ if (JustWhitespaceNewLine(CurPtr))
+ return lltok::kw_signext;
+ } else if (Len == 4 && !memcmp(StartChar, "zext", 4)) {
+ // Scan CurPtr ahead, seeing if there is just whitespace before the newline.
+ if (JustWhitespaceNewLine(CurPtr))
+ return lltok::kw_zeroext;
+ } else if (Len == 6 && !memcmp(StartChar, "malloc", 6)) {
+ // FIXME: Remove in LLVM 3.0.
+ // Autoupgrade malloc instruction.
+ return lltok::kw_malloc;
+ } else if (Len == 4 && !memcmp(StartChar, "free", 4)) {
+ // FIXME: Remove in LLVM 3.0.
+ // Autoupgrade malloc instruction.
+ return lltok::kw_free;
+ }
+
+ // Keywords for instructions.
+#define INSTKEYWORD(STR, Enum) \
+ if (Len == strlen(#STR) && !memcmp(StartChar, #STR, strlen(#STR))) { \
+ UIntVal = Instruction::Enum; return lltok::kw_##STR; }
+
+ INSTKEYWORD(add, Add); INSTKEYWORD(fadd, FAdd);
+ INSTKEYWORD(sub, Sub); INSTKEYWORD(fsub, FSub);
+ INSTKEYWORD(mul, Mul); INSTKEYWORD(fmul, FMul);
+ INSTKEYWORD(udiv, UDiv); INSTKEYWORD(sdiv, SDiv); INSTKEYWORD(fdiv, FDiv);
+ INSTKEYWORD(urem, URem); INSTKEYWORD(srem, SRem); INSTKEYWORD(frem, FRem);
+ INSTKEYWORD(shl, Shl); INSTKEYWORD(lshr, LShr); INSTKEYWORD(ashr, AShr);
+ INSTKEYWORD(and, And); INSTKEYWORD(or, Or); INSTKEYWORD(xor, Xor);
+ INSTKEYWORD(icmp, ICmp); INSTKEYWORD(fcmp, FCmp);
+
+ INSTKEYWORD(phi, PHI);
+ INSTKEYWORD(call, Call);
+ INSTKEYWORD(trunc, Trunc);
+ INSTKEYWORD(zext, ZExt);
+ INSTKEYWORD(sext, SExt);
+ INSTKEYWORD(fptrunc, FPTrunc);
+ INSTKEYWORD(fpext, FPExt);
+ INSTKEYWORD(uitofp, UIToFP);
+ INSTKEYWORD(sitofp, SIToFP);
+ INSTKEYWORD(fptoui, FPToUI);
+ INSTKEYWORD(fptosi, FPToSI);
+ INSTKEYWORD(inttoptr, IntToPtr);
+ INSTKEYWORD(ptrtoint, PtrToInt);
+ INSTKEYWORD(bitcast, BitCast);
+ INSTKEYWORD(select, Select);
+ INSTKEYWORD(va_arg, VAArg);
+ INSTKEYWORD(ret, Ret);
+ INSTKEYWORD(br, Br);
+ INSTKEYWORD(switch, Switch);
+ INSTKEYWORD(indirectbr, IndirectBr);
+ INSTKEYWORD(invoke, Invoke);
+ INSTKEYWORD(unwind, Unwind);
+ INSTKEYWORD(unreachable, Unreachable);
+
+ INSTKEYWORD(alloca, Alloca);
+ INSTKEYWORD(load, Load);
+ INSTKEYWORD(store, Store);
+ INSTKEYWORD(getelementptr, GetElementPtr);
+
+ INSTKEYWORD(extractelement, ExtractElement);
+ INSTKEYWORD(insertelement, InsertElement);
+ INSTKEYWORD(shufflevector, ShuffleVector);
+ INSTKEYWORD(getresult, ExtractValue);
+ INSTKEYWORD(extractvalue, ExtractValue);
+ INSTKEYWORD(insertvalue, InsertValue);
+#undef INSTKEYWORD
+
+ // Check for [us]0x[0-9A-Fa-f]+ which are Hexadecimal constant generated by
+ // the CFE to avoid forcing it to deal with 64-bit numbers.
+ if ((TokStart[0] == 'u' || TokStart[0] == 's') &&
+ TokStart[1] == '0' && TokStart[2] == 'x' && isxdigit(TokStart[3])) {
+ int len = CurPtr-TokStart-3;
+ uint32_t bits = len * 4;
+ APInt Tmp(bits, StringRef(TokStart+3, len), 16);
+ uint32_t activeBits = Tmp.getActiveBits();
+ if (activeBits > 0 && activeBits < bits)
+ Tmp.trunc(activeBits);
+ APSIntVal = APSInt(Tmp, TokStart[0] == 'u');
+ return lltok::APSInt;
+ }
+
+ // If this is "cc1234", return this as just "cc".
+ if (TokStart[0] == 'c' && TokStart[1] == 'c') {
+ CurPtr = TokStart+2;
+ return lltok::kw_cc;
+ }
+
+ // If this starts with "call", return it as CALL. This is to support old
+ // broken .ll files. FIXME: remove this with LLVM 3.0.
+ if (CurPtr-TokStart > 4 && !memcmp(TokStart, "call", 4)) {
+ CurPtr = TokStart+4;
+ UIntVal = Instruction::Call;
+ return lltok::kw_call;
+ }
+
+ // Finally, if this isn't known, return an error.
+ CurPtr = TokStart+1;
+ return lltok::Error;
+}
+
+
+/// Lex0x: Handle productions that start with 0x, knowing that it matches and
+/// that this is not a label:
+/// HexFPConstant 0x[0-9A-Fa-f]+
+/// HexFP80Constant 0xK[0-9A-Fa-f]+
+/// HexFP128Constant 0xL[0-9A-Fa-f]+
+/// HexPPC128Constant 0xM[0-9A-Fa-f]+
+lltok::Kind LLLexer::Lex0x() {
+ CurPtr = TokStart + 2;
+
+ char Kind;
+ if (CurPtr[0] >= 'K' && CurPtr[0] <= 'M') {
+ Kind = *CurPtr++;
+ } else {
+ Kind = 'J';
+ }
+
+ if (!isxdigit(CurPtr[0])) {
+ // Bad token, return it as an error.
+ CurPtr = TokStart+1;
+ return lltok::Error;
+ }
+
+ while (isxdigit(CurPtr[0]))
+ ++CurPtr;
+
+ if (Kind == 'J') {
+ // HexFPConstant - Floating point constant represented in IEEE format as a
+ // hexadecimal number for when exponential notation is not precise enough.
+ // Float and double only.
+ APFloatVal = APFloat(BitsToDouble(HexIntToVal(TokStart+2, CurPtr)));
+ return lltok::APFloat;
+ }
+
+ uint64_t Pair[2];
+ switch (Kind) {
+ default: llvm_unreachable("Unknown kind!");
+ case 'K':
+ // F80HexFPConstant - x87 long double in hexadecimal format (10 bytes)
+ FP80HexToIntPair(TokStart+3, CurPtr, Pair);
+ APFloatVal = APFloat(APInt(80, 2, Pair));
+ return lltok::APFloat;
+ case 'L':
+ // F128HexFPConstant - IEEE 128-bit in hexadecimal format (16 bytes)
+ HexToIntPair(TokStart+3, CurPtr, Pair);
+ APFloatVal = APFloat(APInt(128, 2, Pair), true);
+ return lltok::APFloat;
+ case 'M':
+ // PPC128HexFPConstant - PowerPC 128-bit in hexadecimal format (16 bytes)
+ HexToIntPair(TokStart+3, CurPtr, Pair);
+ APFloatVal = APFloat(APInt(128, 2, Pair));
+ return lltok::APFloat;
+ }
+}
+
+/// LexIdentifier: Handle several related productions:
+/// Label [-a-zA-Z$._0-9]+:
+/// NInteger -[0-9]+
+/// FPConstant [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
+/// PInteger [0-9]+
+/// HexFPConstant 0x[0-9A-Fa-f]+
+/// HexFP80Constant 0xK[0-9A-Fa-f]+
+/// HexFP128Constant 0xL[0-9A-Fa-f]+
+/// HexPPC128Constant 0xM[0-9A-Fa-f]+
+lltok::Kind LLLexer::LexDigitOrNegative() {
+ // If the letter after the negative is a number, this is probably a label.
+ if (!isdigit(TokStart[0]) && !isdigit(CurPtr[0])) {
+ // Okay, this is not a number after the -, it's probably a label.
+ if (const char *End = isLabelTail(CurPtr)) {
+ StrVal.assign(TokStart, End-1);
+ CurPtr = End;
+ return lltok::LabelStr;
+ }
+
+ return lltok::Error;
+ }
+
+ // At this point, it is either a label, int or fp constant.
+
+ // Skip digits, we have at least one.
+ for (; isdigit(CurPtr[0]); ++CurPtr)
+ /*empty*/;
+
+ // Check to see if this really is a label afterall, e.g. "-1:".
+ if (isLabelChar(CurPtr[0]) || CurPtr[0] == ':') {
+ if (const char *End = isLabelTail(CurPtr)) {
+ StrVal.assign(TokStart, End-1);
+ CurPtr = End;
+ return lltok::LabelStr;
+ }
+ }
+
+ // If the next character is a '.', then it is a fp value, otherwise its
+ // integer.
+ if (CurPtr[0] != '.') {
+ if (TokStart[0] == '0' && TokStart[1] == 'x')
+ return Lex0x();
+ unsigned Len = CurPtr-TokStart;
+ uint32_t numBits = ((Len * 64) / 19) + 2;
+ APInt Tmp(numBits, StringRef(TokStart, Len), 10);
+ if (TokStart[0] == '-') {
+ uint32_t minBits = Tmp.getMinSignedBits();
+ if (minBits > 0 && minBits < numBits)
+ Tmp.trunc(minBits);
+ APSIntVal = APSInt(Tmp, false);
+ } else {
+ uint32_t activeBits = Tmp.getActiveBits();
+ if (activeBits > 0 && activeBits < numBits)
+ Tmp.trunc(activeBits);
+ APSIntVal = APSInt(Tmp, true);
+ }
+ return lltok::APSInt;
+ }
+
+ ++CurPtr;
+
+ // Skip over [0-9]*([eE][-+]?[0-9]+)?
+ while (isdigit(CurPtr[0])) ++CurPtr;
+
+ if (CurPtr[0] == 'e' || CurPtr[0] == 'E') {
+ if (isdigit(CurPtr[1]) ||
+ ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+ CurPtr += 2;
+ while (isdigit(CurPtr[0])) ++CurPtr;
+ }
+ }
+
+ APFloatVal = APFloat(atof(TokStart));
+ return lltok::APFloat;
+}
+
+/// FPConstant [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
+lltok::Kind LLLexer::LexPositive() {
+ // If the letter after the negative is a number, this is probably not a
+ // label.
+ if (!isdigit(CurPtr[0]))
+ return lltok::Error;
+
+ // Skip digits.
+ for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ /*empty*/;
+
+ // At this point, we need a '.'.
+ if (CurPtr[0] != '.') {
+ CurPtr = TokStart+1;
+ return lltok::Error;
+ }
+
+ ++CurPtr;
+
+ // Skip over [0-9]*([eE][-+]?[0-9]+)?
+ while (isdigit(CurPtr[0])) ++CurPtr;
+
+ if (CurPtr[0] == 'e' || CurPtr[0] == 'E') {
+ if (isdigit(CurPtr[1]) ||
+ ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+ CurPtr += 2;
+ while (isdigit(CurPtr[0])) ++CurPtr;
+ }
+ }
+
+ APFloatVal = APFloat(atof(TokStart));
+ return lltok::APFloat;
+}
diff --git a/lib/AsmParser/LLLexer.h b/lib/AsmParser/LLLexer.h
new file mode 100644
index 0000000..3057992
--- /dev/null
+++ b/lib/AsmParser/LLLexer.h
@@ -0,0 +1,90 @@
+//===- LLLexer.h - Lexer for LLVM Assembly Files ----------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This class represents the Lexer for .ll files.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LIB_ASMPARSER_LLLEXER_H
+#define LIB_ASMPARSER_LLLEXER_H
+
+#include "LLToken.h"
+#include "llvm/ADT/APSInt.h"
+#include "llvm/ADT/APFloat.h"
+#include "llvm/Support/SourceMgr.h"
+#include <string>
+
+namespace llvm {
+ class MemoryBuffer;
+ class Type;
+ class SMDiagnostic;
+ class LLVMContext;
+
+ class LLLexer {
+ const char *CurPtr;
+ MemoryBuffer *CurBuf;
+ SMDiagnostic &ErrorInfo;
+ SourceMgr &SM;
+ LLVMContext &Context;
+
+ // Information about the current token.
+ const char *TokStart;
+ lltok::Kind CurKind;
+ std::string StrVal;
+ unsigned UIntVal;
+ const Type *TyVal;
+ APFloat APFloatVal;
+ APSInt APSIntVal;
+
+ std::string TheError;
+ public:
+ explicit LLLexer(MemoryBuffer *StartBuf, SourceMgr &SM, SMDiagnostic &,
+ LLVMContext &C);
+ ~LLLexer() {}
+
+ lltok::Kind Lex() {
+ return CurKind = LexToken();
+ }
+
+ typedef SMLoc LocTy;
+ LocTy getLoc() const { return SMLoc::getFromPointer(TokStart); }
+ lltok::Kind getKind() const { return CurKind; }
+ const std::string getStrVal() const { return StrVal; }
+ const Type *getTyVal() const { return TyVal; }
+ unsigned getUIntVal() const { return UIntVal; }
+ const APSInt &getAPSIntVal() const { return APSIntVal; }
+ const APFloat &getAPFloatVal() const { return APFloatVal; }
+
+
+ bool Error(LocTy L, const std::string &Msg) const;
+ bool Error(const std::string &Msg) const { return Error(getLoc(), Msg); }
+ std::string getFilename() const;
+
+ private:
+ lltok::Kind LexToken();
+
+ int getNextChar();
+ void SkipLineComment();
+ lltok::Kind LexIdentifier();
+ lltok::Kind LexDigitOrNegative();
+ lltok::Kind LexPositive();
+ lltok::Kind LexAt();
+ lltok::Kind LexExclaim();
+ lltok::Kind LexPercent();
+ lltok::Kind LexQuote();
+ lltok::Kind Lex0x();
+
+ uint64_t atoull(const char *Buffer, const char *End);
+ uint64_t HexIntToVal(const char *Buffer, const char *End);
+ void HexToIntPair(const char *Buffer, const char *End, uint64_t Pair[2]);
+ void FP80HexToIntPair(const char *Buff, const char *End, uint64_t Pair[2]);
+ };
+} // end namespace llvm
+
+#endif
diff --git a/lib/AsmParser/LLParser.cpp b/lib/AsmParser/LLParser.cpp
new file mode 100644
index 0000000..5dd6569
--- /dev/null
+++ b/lib/AsmParser/LLParser.cpp
@@ -0,0 +1,3846 @@
+//===-- LLParser.cpp - Parser Class ---------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the parser class for .ll files.
+//
+//===----------------------------------------------------------------------===//
+
+#include "LLParser.h"
+#include "llvm/AutoUpgrade.h"
+#include "llvm/CallingConv.h"
+#include "llvm/Constants.h"
+#include "llvm/DerivedTypes.h"
+#include "llvm/InlineAsm.h"
+#include "llvm/Instructions.h"
+#include "llvm/Module.h"
+#include "llvm/Operator.h"
+#include "llvm/ValueSymbolTable.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/raw_ostream.h"
+using namespace llvm;
+
+/// Run: module ::= toplevelentity*
+bool LLParser::Run() {
+ // Prime the lexer.
+ Lex.Lex();
+
+ return ParseTopLevelEntities() ||
+ ValidateEndOfModule();
+}
+
+/// ValidateEndOfModule - Do final validity and sanity checks at the end of the
+/// module.
+bool LLParser::ValidateEndOfModule() {
+ // Update auto-upgraded malloc calls to "malloc".
+ // FIXME: Remove in LLVM 3.0.
+ if (MallocF) {
+ MallocF->setName("malloc");
+ // If setName() does not set the name to "malloc", then there is already a
+ // declaration of "malloc". In that case, iterate over all calls to MallocF
+ // and get them to call the declared "malloc" instead.
+ if (MallocF->getName() != "malloc") {
+ Constant *RealMallocF = M->getFunction("malloc");
+ if (RealMallocF->getType() != MallocF->getType())
+ RealMallocF = ConstantExpr::getBitCast(RealMallocF, MallocF->getType());
+ MallocF->replaceAllUsesWith(RealMallocF);
+ MallocF->eraseFromParent();
+ MallocF = NULL;
+ }
+ }
+
+
+ // If there are entries in ForwardRefBlockAddresses at this point, they are
+ // references after the function was defined. Resolve those now.
+ while (!ForwardRefBlockAddresses.empty()) {
+ // Okay, we are referencing an already-parsed function, resolve them now.
+ Function *TheFn = 0;
+ const ValID &Fn = ForwardRefBlockAddresses.begin()->first;
+ if (Fn.Kind == ValID::t_GlobalName)
+ TheFn = M->getFunction(Fn.StrVal);
+ else if (Fn.UIntVal < NumberedVals.size())
+ TheFn = dyn_cast<Function>(NumberedVals[Fn.UIntVal]);
+
+ if (TheFn == 0)
+ return Error(Fn.Loc, "unknown function referenced by blockaddress");
+
+ // Resolve all these references.
+ if (ResolveForwardRefBlockAddresses(TheFn,
+ ForwardRefBlockAddresses.begin()->second,
+ 0))
+ return true;
+
+ ForwardRefBlockAddresses.erase(ForwardRefBlockAddresses.begin());
+ }
+
+
+ if (!ForwardRefTypes.empty())
+ return Error(ForwardRefTypes.begin()->second.second,
+ "use of undefined type named '" +
+ ForwardRefTypes.begin()->first + "'");
+ if (!ForwardRefTypeIDs.empty())
+ return Error(ForwardRefTypeIDs.begin()->second.second,
+ "use of undefined type '%" +
+ utostr(ForwardRefTypeIDs.begin()->first) + "'");
+
+ if (!ForwardRefVals.empty())
+ return Error(ForwardRefVals.begin()->second.second,
+ "use of undefined value '@" + ForwardRefVals.begin()->first +
+ "'");
+
+ if (!ForwardRefValIDs.empty())
+ return Error(ForwardRefValIDs.begin()->second.second,
+ "use of undefined value '@" +
+ utostr(ForwardRefValIDs.begin()->first) + "'");
+
+ if (!ForwardRefMDNodes.empty())
+ return Error(ForwardRefMDNodes.begin()->second.second,
+ "use of undefined metadata '!" +
+ utostr(ForwardRefMDNodes.begin()->first) + "'");
+
+
+ // Look for intrinsic functions and CallInst that need to be upgraded
+ for (Module::iterator FI = M->begin(), FE = M->end(); FI != FE; )
+ UpgradeCallsToIntrinsic(FI++); // must be post-increment, as we remove
+
+ // Check debug info intrinsics.
+ CheckDebugInfoIntrinsics(M);
+ return false;
+}
+
+bool LLParser::ResolveForwardRefBlockAddresses(Function *TheFn,
+ std::vector<std::pair<ValID, GlobalValue*> > &Refs,
+ PerFunctionState *PFS) {
+ // Loop over all the references, resolving them.
+ for (unsigned i = 0, e = Refs.size(); i != e; ++i) {
+ BasicBlock *Res;
+ if (PFS) {
+ if (Refs[i].first.Kind == ValID::t_LocalName)
+ Res = PFS->GetBB(Refs[i].first.StrVal, Refs[i].first.Loc);
+ else
+ Res = PFS->GetBB(Refs[i].first.UIntVal, Refs[i].first.Loc);
+ } else if (Refs[i].first.Kind == ValID::t_LocalID) {
+ return Error(Refs[i].first.Loc,
+ "cannot take address of numeric label after the function is defined");
+ } else {
+ Res = dyn_cast_or_null<BasicBlock>(
+ TheFn->getValueSymbolTable().lookup(Refs[i].first.StrVal));
+ }
+
+ if (Res == 0)
+ return Error(Refs[i].first.Loc,
+ "referenced value is not a basic block");
+
+ // Get the BlockAddress for this and update references to use it.
+ BlockAddress *BA = BlockAddress::get(TheFn, Res);
+ Refs[i].second->replaceAllUsesWith(BA);
+ Refs[i].second->eraseFromParent();
+ }
+ return false;
+}
+
+
+//===----------------------------------------------------------------------===//
+// Top-Level Entities
+//===----------------------------------------------------------------------===//
+
+bool LLParser::ParseTopLevelEntities() {
+ while (1) {
+ switch (Lex.getKind()) {
+ default: return TokError("expected top-level entity");
+ case lltok::Eof: return false;
+ //case lltok::kw_define:
+ case lltok::kw_declare: if (ParseDeclare()) return true; break;
+ case lltok::kw_define: if (ParseDefine()) return true; break;
+ case lltok::kw_module: if (ParseModuleAsm()) return true; break;
+ case lltok::kw_target: if (ParseTargetDefinition()) return true; break;
+ case lltok::kw_deplibs: if (ParseDepLibs()) return true; break;
+ case lltok::kw_type: if (ParseUnnamedType()) return true; break;
+ case lltok::LocalVarID: if (ParseUnnamedType()) return true; break;
+ case lltok::StringConstant: // FIXME: REMOVE IN LLVM 3.0
+ case lltok::LocalVar: if (ParseNamedType()) return true; break;
+ case lltok::GlobalID: if (ParseUnnamedGlobal()) return true; break;
+ case lltok::GlobalVar: if (ParseNamedGlobal()) return true; break;
+ case lltok::exclaim: if (ParseStandaloneMetadata()) return true; break;
+ case lltok::MetadataVar: if (ParseNamedMetadata()) return true; break;
+
+ // The Global variable production with no name can have many different
+ // optional leading prefixes, the production is:
+ // GlobalVar ::= OptionalLinkage OptionalVisibility OptionalThreadLocal
+ // OptionalAddrSpace ('constant'|'global') ...
+ case lltok::kw_private : // OptionalLinkage
+ case lltok::kw_linker_private: // OptionalLinkage
+ case lltok::kw_internal: // OptionalLinkage
+ case lltok::kw_weak: // OptionalLinkage
+ case lltok::kw_weak_odr: // OptionalLinkage
+ case lltok::kw_linkonce: // OptionalLinkage
+ case lltok::kw_linkonce_odr: // OptionalLinkage
+ case lltok::kw_appending: // OptionalLinkage
+ case lltok::kw_dllexport: // OptionalLinkage
+ case lltok::kw_common: // OptionalLinkage
+ case lltok::kw_dllimport: // OptionalLinkage
+ case lltok::kw_extern_weak: // OptionalLinkage
+ case lltok::kw_external: { // OptionalLinkage
+ unsigned Linkage, Visibility;
+ if (ParseOptionalLinkage(Linkage) ||
+ ParseOptionalVisibility(Visibility) ||
+ ParseGlobal("", SMLoc(), Linkage, true, Visibility))
+ return true;
+ break;
+ }
+ case lltok::kw_default: // OptionalVisibility
+ case lltok::kw_hidden: // OptionalVisibility
+ case lltok::kw_protected: { // OptionalVisibility
+ unsigned Visibility;
+ if (ParseOptionalVisibility(Visibility) ||
+ ParseGlobal("", SMLoc(), 0, false, Visibility))
+ return true;
+ break;
+ }
+
+ case lltok::kw_thread_local: // OptionalThreadLocal
+ case lltok::kw_addrspace: // OptionalAddrSpace
+ case lltok::kw_constant: // GlobalType
+ case lltok::kw_global: // GlobalType
+ if (ParseGlobal("", SMLoc(), 0, false, 0)) return true;
+ break;
+ }
+ }
+}
+
+
+/// toplevelentity
+/// ::= 'module' 'asm' STRINGCONSTANT
+bool LLParser::ParseModuleAsm() {
+ assert(Lex.getKind() == lltok::kw_module);
+ Lex.Lex();
+
+ std::string AsmStr;
+ if (ParseToken(lltok::kw_asm, "expected 'module asm'") ||
+ ParseStringConstant(AsmStr)) return true;
+
+ const std::string &AsmSoFar = M->getModuleInlineAsm();
+ if (AsmSoFar.empty())
+ M->setModuleInlineAsm(AsmStr);
+ else
+ M->setModuleInlineAsm(AsmSoFar+"\n"+AsmStr);
+ return false;
+}
+
+/// toplevelentity
+/// ::= 'target' 'triple' '=' STRINGCONSTANT
+/// ::= 'target' 'datalayout' '=' STRINGCONSTANT
+bool LLParser::ParseTargetDefinition() {
+ assert(Lex.getKind() == lltok::kw_target);
+ std::string Str;
+ switch (Lex.Lex()) {
+ default: return TokError("unknown target property");
+ case lltok::kw_triple:
+ Lex.Lex();
+ if (ParseToken(lltok::equal, "expected '=' after target triple") ||
+ ParseStringConstant(Str))
+ return true;
+ M->setTargetTriple(Str);
+ return false;
+ case lltok::kw_datalayout:
+ Lex.Lex();
+ if (ParseToken(lltok::equal, "expected '=' after target datalayout") ||
+ ParseStringConstant(Str))
+ return true;
+ M->setDataLayout(Str);
+ return false;
+ }
+}
+
+/// toplevelentity
+/// ::= 'deplibs' '=' '[' ']'
+/// ::= 'deplibs' '=' '[' STRINGCONSTANT (',' STRINGCONSTANT)* ']'
+bool LLParser::ParseDepLibs() {
+ assert(Lex.getKind() == lltok::kw_deplibs);
+ Lex.Lex();
+ if (ParseToken(lltok::equal, "expected '=' after deplibs") ||
+ ParseToken(lltok::lsquare, "expected '=' after deplibs"))
+ return true;
+
+ if (EatIfPresent(lltok::rsquare))
+ return false;
+
+ std::string Str;
+ if (ParseStringConstant(Str)) return true;
+ M->addLibrary(Str);
+
+ while (EatIfPresent(lltok::comma)) {
+ if (ParseStringConstant(Str)) return true;
+ M->addLibrary(Str);
+ }
+
+ return ParseToken(lltok::rsquare, "expected ']' at end of list");
+}
+
+/// ParseUnnamedType:
+/// ::= 'type' type
+/// ::= LocalVarID '=' 'type' type
+bool LLParser::ParseUnnamedType() {
+ unsigned TypeID = NumberedTypes.size();
+
+ // Handle the LocalVarID form.
+ if (Lex.getKind() == lltok::LocalVarID) {
+ if (Lex.getUIntVal() != TypeID)
+ return Error(Lex.getLoc(), "type expected to be numbered '%" +
+ utostr(TypeID) + "'");
+ Lex.Lex(); // eat LocalVarID;
+
+ if (ParseToken(lltok::equal, "expected '=' after name"))
+ return true;
+ }
+
+ assert(Lex.getKind() == lltok::kw_type);
+ LocTy TypeLoc = Lex.getLoc();
+ Lex.Lex(); // eat kw_type
+
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ if (ParseType(Ty)) return true;
+
+ // See if this type was previously referenced.
+ std::map<unsigned, std::pair<PATypeHolder, LocTy> >::iterator
+ FI = ForwardRefTypeIDs.find(TypeID);
+ if (FI != ForwardRefTypeIDs.end()) {
+ if (FI->second.first.get() == Ty)
+ return Error(TypeLoc, "self referential type is invalid");
+
+ cast<DerivedType>(FI->second.first.get())->refineAbstractTypeTo(Ty);
+ Ty = FI->second.first.get();
+ ForwardRefTypeIDs.erase(FI);
+ }
+
+ NumberedTypes.push_back(Ty);
+
+ return false;
+}
+
+/// toplevelentity
+/// ::= LocalVar '=' 'type' type
+bool LLParser::ParseNamedType() {
+ std::string Name = Lex.getStrVal();
+ LocTy NameLoc = Lex.getLoc();
+ Lex.Lex(); // eat LocalVar.
+
+ PATypeHolder Ty(Type::getVoidTy(Context));
+
+ if (ParseToken(lltok::equal, "expected '=' after name") ||
+ ParseToken(lltok::kw_type, "expected 'type' after name") ||
+ ParseType(Ty))
+ return true;
+
+ // Set the type name, checking for conflicts as we do so.
+ bool AlreadyExists = M->addTypeName(Name, Ty);
+ if (!AlreadyExists) return false;
+
+ // See if this type is a forward reference. We need to eagerly resolve
+ // types to allow recursive type redefinitions below.
+ std::map<std::string, std::pair<PATypeHolder, LocTy> >::iterator
+ FI = ForwardRefTypes.find(Name);
+ if (FI != ForwardRefTypes.end()) {
+ if (FI->second.first.get() == Ty)
+ return Error(NameLoc, "self referential type is invalid");
+
+ cast<DerivedType>(FI->second.first.get())->refineAbstractTypeTo(Ty);
+ Ty = FI->second.first.get();
+ ForwardRefTypes.erase(FI);
+ }
+
+ // Inserting a name that is already defined, get the existing name.
+ const Type *Existing = M->getTypeByName(Name);
+ assert(Existing && "Conflict but no matching type?!");
+
+ // Otherwise, this is an attempt to redefine a type. That's okay if
+ // the redefinition is identical to the original.
+ // FIXME: REMOVE REDEFINITIONS IN LLVM 3.0
+ if (Existing == Ty) return false;
+
+ // Any other kind of (non-equivalent) redefinition is an error.
+ return Error(NameLoc, "redefinition of type named '" + Name + "' of type '" +
+ Ty->getDescription() + "'");
+}
+
+
+/// toplevelentity
+/// ::= 'declare' FunctionHeader
+bool LLParser::ParseDeclare() {
+ assert(Lex.getKind() == lltok::kw_declare);
+ Lex.Lex();
+
+ Function *F;
+ return ParseFunctionHeader(F, false);
+}
+
+/// toplevelentity
+/// ::= 'define' FunctionHeader '{' ...
+bool LLParser::ParseDefine() {
+ assert(Lex.getKind() == lltok::kw_define);
+ Lex.Lex();
+
+ Function *F;
+ return ParseFunctionHeader(F, true) ||
+ ParseFunctionBody(*F);
+}
+
+/// ParseGlobalType
+/// ::= 'constant'
+/// ::= 'global'
+bool LLParser::ParseGlobalType(bool &IsConstant) {
+ if (Lex.getKind() == lltok::kw_constant)
+ IsConstant = true;
+ else if (Lex.getKind() == lltok::kw_global)
+ IsConstant = false;
+ else {
+ IsConstant = false;
+ return TokError("expected 'global' or 'constant'");
+ }
+ Lex.Lex();
+ return false;
+}
+
+/// ParseUnnamedGlobal:
+/// OptionalVisibility ALIAS ...
+/// OptionalLinkage OptionalVisibility ... -> global variable
+/// GlobalID '=' OptionalVisibility ALIAS ...
+/// GlobalID '=' OptionalLinkage OptionalVisibility ... -> global variable
+bool LLParser::ParseUnnamedGlobal() {
+ unsigned VarID = NumberedVals.size();
+ std::string Name;
+ LocTy NameLoc = Lex.getLoc();
+
+ // Handle the GlobalID form.
+ if (Lex.getKind() == lltok::GlobalID) {
+ if (Lex.getUIntVal() != VarID)
+ return Error(Lex.getLoc(), "variable expected to be numbered '%" +
+ utostr(VarID) + "'");
+ Lex.Lex(); // eat GlobalID;
+
+ if (ParseToken(lltok::equal, "expected '=' after name"))
+ return true;
+ }
+
+ bool HasLinkage;
+ unsigned Linkage, Visibility;
+ if (ParseOptionalLinkage(Linkage, HasLinkage) ||
+ ParseOptionalVisibility(Visibility))
+ return true;
+
+ if (HasLinkage || Lex.getKind() != lltok::kw_alias)
+ return ParseGlobal(Name, NameLoc, Linkage, HasLinkage, Visibility);
+ return ParseAlias(Name, NameLoc, Visibility);
+}
+
+/// ParseNamedGlobal:
+/// GlobalVar '=' OptionalVisibility ALIAS ...
+/// GlobalVar '=' OptionalLinkage OptionalVisibility ... -> global variable
+bool LLParser::ParseNamedGlobal() {
+ assert(Lex.getKind() == lltok::GlobalVar);
+ LocTy NameLoc = Lex.getLoc();
+ std::string Name = Lex.getStrVal();
+ Lex.Lex();
+
+ bool HasLinkage;
+ unsigned Linkage, Visibility;
+ if (ParseToken(lltok::equal, "expected '=' in global variable") ||
+ ParseOptionalLinkage(Linkage, HasLinkage) ||
+ ParseOptionalVisibility(Visibility))
+ return true;
+
+ if (HasLinkage || Lex.getKind() != lltok::kw_alias)
+ return ParseGlobal(Name, NameLoc, Linkage, HasLinkage, Visibility);
+ return ParseAlias(Name, NameLoc, Visibility);
+}
+
+// MDString:
+// ::= '!' STRINGCONSTANT
+bool LLParser::ParseMDString(MDString *&Result) {
+ std::string Str;
+ if (ParseStringConstant(Str)) return true;
+ Result = MDString::get(Context, Str);
+ return false;
+}
+
+// MDNode:
+// ::= '!' MDNodeNumber
+bool LLParser::ParseMDNodeID(MDNode *&Result) {
+ // !{ ..., !42, ... }
+ unsigned MID = 0;
+ if (ParseUInt32(MID)) return true;
+
+ // Check existing MDNode.
+ if (MID < NumberedMetadata.size() && NumberedMetadata[MID] != 0) {
+ Result = NumberedMetadata[MID];
+ return false;
+ }
+
+ // Create MDNode forward reference.
+
+ // FIXME: This is not unique enough!
+ std::string FwdRefName = "llvm.mdnode.fwdref." + utostr(MID);
+ Value *V = MDString::get(Context, FwdRefName);
+ MDNode *FwdNode = MDNode::get(Context, &V, 1);
+ ForwardRefMDNodes[MID] = std::make_pair(FwdNode, Lex.getLoc());
+
+ if (NumberedMetadata.size() <= MID)
+ NumberedMetadata.resize(MID+1);
+ NumberedMetadata[MID] = FwdNode;
+ Result = FwdNode;
+ return false;
+}
+
+/// ParseNamedMetadata:
+/// !foo = !{ !1, !2 }
+bool LLParser::ParseNamedMetadata() {
+ assert(Lex.getKind() == lltok::MetadataVar);
+ std::string Name = Lex.getStrVal();
+ Lex.Lex();
+
+ if (ParseToken(lltok::equal, "expected '=' here") ||
+ ParseToken(lltok::exclaim, "Expected '!' here") ||
+ ParseToken(lltok::lbrace, "Expected '{' here"))
+ return true;
+
+ SmallVector<MDNode *, 8> Elts;
+ do {
+ // Null is a special case since it is typeless.
+ if (EatIfPresent(lltok::kw_null)) {
+ Elts.push_back(0);
+ continue;
+ }
+
+ if (ParseToken(lltok::exclaim, "Expected '!' here"))
+ return true;
+
+ MDNode *N = 0;
+ if (ParseMDNodeID(N)) return true;
+ Elts.push_back(N);
+ } while (EatIfPresent(lltok::comma));
+
+ if (ParseToken(lltok::rbrace, "expected end of metadata node"))
+ return true;
+
+ NamedMDNode::Create(Context, Name, Elts.data(), Elts.size(), M);
+ return false;
+}
+
+/// ParseStandaloneMetadata:
+/// !42 = !{...}
+bool LLParser::ParseStandaloneMetadata() {
+ assert(Lex.getKind() == lltok::exclaim);
+ Lex.Lex();
+ unsigned MetadataID = 0;
+
+ LocTy TyLoc;
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ SmallVector<Value *, 16> Elts;
+ if (ParseUInt32(MetadataID) ||
+ ParseToken(lltok::equal, "expected '=' here") ||
+ ParseType(Ty, TyLoc) ||
+ ParseToken(lltok::exclaim, "Expected '!' here") ||
+ ParseToken(lltok::lbrace, "Expected '{' here") ||
+ ParseMDNodeVector(Elts, NULL) ||
+ ParseToken(lltok::rbrace, "expected end of metadata node"))
+ return true;
+
+ MDNode *Init = MDNode::get(Context, Elts.data(), Elts.size());
+
+ // See if this was forward referenced, if so, handle it.
+ std::map<unsigned, std::pair<TrackingVH<MDNode>, LocTy> >::iterator
+ FI = ForwardRefMDNodes.find(MetadataID);
+ if (FI != ForwardRefMDNodes.end()) {
+ FI->second.first->replaceAllUsesWith(Init);
+ ForwardRefMDNodes.erase(FI);
+
+ assert(NumberedMetadata[MetadataID] == Init && "Tracking VH didn't work");
+ } else {
+ if (MetadataID >= NumberedMetadata.size())
+ NumberedMetadata.resize(MetadataID+1);
+
+ if (NumberedMetadata[MetadataID] != 0)
+ return TokError("Metadata id is already used");
+ NumberedMetadata[MetadataID] = Init;
+ }
+
+ return false;
+}
+
+/// ParseAlias:
+/// ::= GlobalVar '=' OptionalVisibility 'alias' OptionalLinkage Aliasee
+/// Aliasee
+/// ::= TypeAndValue
+/// ::= 'bitcast' '(' TypeAndValue 'to' Type ')'
+/// ::= 'getelementptr' 'inbounds'? '(' ... ')'
+///
+/// Everything through visibility has already been parsed.
+///
+bool LLParser::ParseAlias(const std::string &Name, LocTy NameLoc,
+ unsigned Visibility) {
+ assert(Lex.getKind() == lltok::kw_alias);
+ Lex.Lex();
+ unsigned Linkage;
+ LocTy LinkageLoc = Lex.getLoc();
+ if (ParseOptionalLinkage(Linkage))
+ return true;
+
+ if (Linkage != GlobalValue::ExternalLinkage &&
+ Linkage != GlobalValue::WeakAnyLinkage &&
+ Linkage != GlobalValue::WeakODRLinkage &&
+ Linkage != GlobalValue::InternalLinkage &&
+ Linkage != GlobalValue::PrivateLinkage &&
+ Linkage != GlobalValue::LinkerPrivateLinkage)
+ return Error(LinkageLoc, "invalid linkage type for alias");
+
+ Constant *Aliasee;
+ LocTy AliaseeLoc = Lex.getLoc();
+ if (Lex.getKind() != lltok::kw_bitcast &&
+ Lex.getKind() != lltok::kw_getelementptr) {
+ if (ParseGlobalTypeAndValue(Aliasee)) return true;
+ } else {
+ // The bitcast dest type is not present, it is implied by the dest type.
+ ValID ID;
+ if (ParseValID(ID)) return true;
+ if (ID.Kind != ValID::t_Constant)
+ return Error(AliaseeLoc, "invalid aliasee");
+ Aliasee = ID.ConstantVal;
+ }
+
+ if (!isa<PointerType>(Aliasee->getType()))
+ return Error(AliaseeLoc, "alias must have pointer type");
+
+ // Okay, create the alias but do not insert it into the module yet.
+ GlobalAlias* GA = new GlobalAlias(Aliasee->getType(),
+ (GlobalValue::LinkageTypes)Linkage, Name,
+ Aliasee);
+ GA->setVisibility((GlobalValue::VisibilityTypes)Visibility);
+
+ // See if this value already exists in the symbol table. If so, it is either
+ // a redefinition or a definition of a forward reference.
+ if (GlobalValue *Val = M->getNamedValue(Name)) {
+ // See if this was a redefinition. If so, there is no entry in
+ // ForwardRefVals.
+ std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator
+ I = ForwardRefVals.find(Name);
+ if (I == ForwardRefVals.end())
+ return Error(NameLoc, "redefinition of global named '@" + Name + "'");
+
+ // Otherwise, this was a definition of forward ref. Verify that types
+ // agree.
+ if (Val->getType() != GA->getType())
+ return Error(NameLoc,
+ "forward reference and definition of alias have different types");
+
+ // If they agree, just RAUW the old value with the alias and remove the
+ // forward ref info.
+ Val->replaceAllUsesWith(GA);
+ Val->eraseFromParent();
+ ForwardRefVals.erase(I);
+ }
+
+ // Insert into the module, we know its name won't collide now.
+ M->getAliasList().push_back(GA);
+ assert(GA->getNameStr() == Name && "Should not be a name conflict!");
+
+ return false;
+}
+
+/// ParseGlobal
+/// ::= GlobalVar '=' OptionalLinkage OptionalVisibility OptionalThreadLocal
+/// OptionalAddrSpace GlobalType Type Const
+/// ::= OptionalLinkage OptionalVisibility OptionalThreadLocal
+/// OptionalAddrSpace GlobalType Type Const
+///
+/// Everything through visibility has been parsed already.
+///
+bool LLParser::ParseGlobal(const std::string &Name, LocTy NameLoc,
+ unsigned Linkage, bool HasLinkage,
+ unsigned Visibility) {
+ unsigned AddrSpace;
+ bool ThreadLocal, IsConstant;
+ LocTy TyLoc;
+
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ if (ParseOptionalToken(lltok::kw_thread_local, ThreadLocal) ||
+ ParseOptionalAddrSpace(AddrSpace) ||
+ ParseGlobalType(IsConstant) ||
+ ParseType(Ty, TyLoc))
+ return true;
+
+ // If the linkage is specified and is external, then no initializer is
+ // present.
+ Constant *Init = 0;
+ if (!HasLinkage || (Linkage != GlobalValue::DLLImportLinkage &&
+ Linkage != GlobalValue::ExternalWeakLinkage &&
+ Linkage != GlobalValue::ExternalLinkage)) {
+ if (ParseGlobalValue(Ty, Init))
+ return true;
+ }
+
+ if (isa<FunctionType>(Ty) || Ty->isLabelTy())
+ return Error(TyLoc, "invalid type for global variable");
+
+ GlobalVariable *GV = 0;
+
+ // See if the global was forward referenced, if so, use the global.
+ if (!Name.empty()) {
+ if (GlobalValue *GVal = M->getNamedValue(Name)) {
+ if (!ForwardRefVals.erase(Name) || !isa<GlobalValue>(GVal))
+ return Error(NameLoc, "redefinition of global '@" + Name + "'");
+ GV = cast<GlobalVariable>(GVal);
+ }
+ } else {
+ std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator
+ I = ForwardRefValIDs.find(NumberedVals.size());
+ if (I != ForwardRefValIDs.end()) {
+ GV = cast<GlobalVariable>(I->second.first);
+ ForwardRefValIDs.erase(I);
+ }
+ }
+
+ if (GV == 0) {
+ GV = new GlobalVariable(*M, Ty, false, GlobalValue::ExternalLinkage, 0,
+ Name, 0, false, AddrSpace);
+ } else {
+ if (GV->getType()->getElementType() != Ty)
+ return Error(TyLoc,
+ "forward reference and definition of global have different types");
+
+ // Move the forward-reference to the correct spot in the module.
+ M->getGlobalList().splice(M->global_end(), M->getGlobalList(), GV);
+ }
+
+ if (Name.empty())
+ NumberedVals.push_back(GV);
+
+ // Set the parsed properties on the global.
+ if (Init)
+ GV->setInitializer(Init);
+ GV->setConstant(IsConstant);
+ GV->setLinkage((GlobalValue::LinkageTypes)Linkage);
+ GV->setVisibility((GlobalValue::VisibilityTypes)Visibility);
+ GV->setThreadLocal(ThreadLocal);
+
+ // Parse attributes on the global.
+ while (Lex.getKind() == lltok::comma) {
+ Lex.Lex();
+
+ if (Lex.getKind() == lltok::kw_section) {
+ Lex.Lex();
+ GV->setSection(Lex.getStrVal());
+ if (ParseToken(lltok::StringConstant, "expected global section string"))
+ return true;
+ } else if (Lex.getKind() == lltok::kw_align) {
+ unsigned Alignment;
+ if (ParseOptionalAlignment(Alignment)) return true;
+ GV->setAlignment(Alignment);
+ } else {
+ TokError("unknown global variable property!");
+ }
+ }
+
+ return false;
+}
+
+
+//===----------------------------------------------------------------------===//
+// GlobalValue Reference/Resolution Routines.
+//===----------------------------------------------------------------------===//
+
+/// 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 *LLParser::GetGlobalVal(const std::string &Name, const Type *Ty,
+ LocTy Loc) {
+ const PointerType *PTy = dyn_cast<PointerType>(Ty);
+ if (PTy == 0) {
+ Error(Loc, "global variable reference must have pointer type");
+ return 0;
+ }
+
+ // Look this name up in the normal function symbol table.
+ GlobalValue *Val =
+ cast_or_null<GlobalValue>(M->getValueSymbolTable().lookup(Name));
+
+ // If this is a forward reference for the value, see if we already created a
+ // forward ref record.
+ if (Val == 0) {
+ std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator
+ I = ForwardRefVals.find(Name);
+ if (I != ForwardRefVals.end())
+ Val = I->second.first;
+ }
+
+ // If we have the value in the symbol table or fwd-ref table, return it.
+ if (Val) {
+ if (Val->getType() == Ty) return Val;
+ Error(Loc, "'@" + Name + "' defined with type '" +
+ Val->getType()->getDescription() + "'");
+ return 0;
+ }
+
+ // Otherwise, create a new forward reference for this value and remember it.
+ GlobalValue *FwdVal;
+ if (const FunctionType *FT = dyn_cast<FunctionType>(PTy->getElementType())) {
+ // Function types can return opaque but functions can't.
+ if (isa<OpaqueType>(FT->getReturnType())) {
+ Error(Loc, "function may not return opaque type");
+ return 0;
+ }
+
+ FwdVal = Function::Create(FT, GlobalValue::ExternalWeakLinkage, Name, M);
+ } else {
+ FwdVal = new GlobalVariable(*M, PTy->getElementType(), false,
+ GlobalValue::ExternalWeakLinkage, 0, Name);
+ }
+
+ ForwardRefVals[Name] = std::make_pair(FwdVal, Loc);
+ return FwdVal;
+}
+
+GlobalValue *LLParser::GetGlobalVal(unsigned ID, const Type *Ty, LocTy Loc) {
+ const PointerType *PTy = dyn_cast<PointerType>(Ty);
+ if (PTy == 0) {
+ Error(Loc, "global variable reference must have pointer type");
+ return 0;
+ }
+
+ GlobalValue *Val = ID < NumberedVals.size() ? NumberedVals[ID] : 0;
+
+ // If this is a forward reference for the value, see if we already created a
+ // forward ref record.
+ if (Val == 0) {
+ std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator
+ I = ForwardRefValIDs.find(ID);
+ if (I != ForwardRefValIDs.end())
+ Val = I->second.first;
+ }
+
+ // If we have the value in the symbol table or fwd-ref table, return it.
+ if (Val) {
+ if (Val->getType() == Ty) return Val;
+ Error(Loc, "'@" + utostr(ID) + "' defined with type '" +
+ Val->getType()->getDescription() + "'");
+ return 0;
+ }
+
+ // Otherwise, create a new forward reference for this value and remember it.
+ GlobalValue *FwdVal;
+ if (const FunctionType *FT = dyn_cast<FunctionType>(PTy->getElementType())) {
+ // Function types can return opaque but functions can't.
+ if (isa<OpaqueType>(FT->getReturnType())) {
+ Error(Loc, "function may not return opaque type");
+ return 0;
+ }
+ FwdVal = Function::Create(FT, GlobalValue::ExternalWeakLinkage, "", M);
+ } else {
+ FwdVal = new GlobalVariable(*M, PTy->getElementType(), false,
+ GlobalValue::ExternalWeakLinkage, 0, "");
+ }
+
+ ForwardRefValIDs[ID] = std::make_pair(FwdVal, Loc);
+ return FwdVal;
+}
+
+
+//===----------------------------------------------------------------------===//
+// Helper Routines.
+//===----------------------------------------------------------------------===//
+
+/// ParseToken - If the current token has the specified kind, eat it and return
+/// success. Otherwise, emit the specified error and return failure.
+bool LLParser::ParseToken(lltok::Kind T, const char *ErrMsg) {
+ if (Lex.getKind() != T)
+ return TokError(ErrMsg);
+ Lex.Lex();
+ return false;
+}
+
+/// ParseStringConstant
+/// ::= StringConstant
+bool LLParser::ParseStringConstant(std::string &Result) {
+ if (Lex.getKind() != lltok::StringConstant)
+ return TokError("expected string constant");
+ Result = Lex.getStrVal();
+ Lex.Lex();
+ return false;
+}
+
+/// ParseUInt32
+/// ::= uint32
+bool LLParser::ParseUInt32(unsigned &Val) {
+ if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned())
+ return TokError("expected integer");
+ uint64_t Val64 = Lex.getAPSIntVal().getLimitedValue(0xFFFFFFFFULL+1);
+ if (Val64 != unsigned(Val64))
+ return TokError("expected 32-bit integer (too large)");
+ Val = Val64;
+ Lex.Lex();
+ return false;
+}
+
+
+/// ParseOptionalAddrSpace
+/// := /*empty*/
+/// := 'addrspace' '(' uint32 ')'
+bool LLParser::ParseOptionalAddrSpace(unsigned &AddrSpace) {
+ AddrSpace = 0;
+ if (!EatIfPresent(lltok::kw_addrspace))
+ return false;
+ return ParseToken(lltok::lparen, "expected '(' in address space") ||
+ ParseUInt32(AddrSpace) ||
+ ParseToken(lltok::rparen, "expected ')' in address space");
+}
+
+/// ParseOptionalAttrs - Parse a potentially empty attribute list. AttrKind
+/// indicates what kind of attribute list this is: 0: function arg, 1: result,
+/// 2: function attr.
+/// 3: function arg after value: FIXME: REMOVE IN LLVM 3.0
+bool LLParser::ParseOptionalAttrs(unsigned &Attrs, unsigned AttrKind) {
+ Attrs = Attribute::None;
+ LocTy AttrLoc = Lex.getLoc();
+
+ while (1) {
+ switch (Lex.getKind()) {
+ case lltok::kw_sext:
+ case lltok::kw_zext:
+ // Treat these as signext/zeroext if they occur in the argument list after
+ // the value, as in "call i8 @foo(i8 10 sext)". If they occur before the
+ // value, as in "call i8 @foo(i8 sext (" then it is part of a constant
+ // expr.
+ // FIXME: REMOVE THIS IN LLVM 3.0
+ if (AttrKind == 3) {
+ if (Lex.getKind() == lltok::kw_sext)
+ Attrs |= Attribute::SExt;
+ else
+ Attrs |= Attribute::ZExt;
+ break;
+ }
+ // FALL THROUGH.
+ default: // End of attributes.
+ if (AttrKind != 2 && (Attrs & Attribute::FunctionOnly))
+ return Error(AttrLoc, "invalid use of function-only attribute");
+
+ if (AttrKind != 0 && AttrKind != 3 && (Attrs & Attribute::ParameterOnly))
+ return Error(AttrLoc, "invalid use of parameter-only attribute");
+
+ return false;
+ case lltok::kw_zeroext: Attrs |= Attribute::ZExt; break;
+ case lltok::kw_signext: Attrs |= Attribute::SExt; break;
+ case lltok::kw_inreg: Attrs |= Attribute::InReg; break;
+ case lltok::kw_sret: Attrs |= Attribute::StructRet; break;
+ case lltok::kw_noalias: Attrs |= Attribute::NoAlias; break;
+ case lltok::kw_nocapture: Attrs |= Attribute::NoCapture; break;
+ case lltok::kw_byval: Attrs |= Attribute::ByVal; break;
+ case lltok::kw_nest: Attrs |= Attribute::Nest; break;
+
+ case lltok::kw_noreturn: Attrs |= Attribute::NoReturn; break;
+ case lltok::kw_nounwind: Attrs |= Attribute::NoUnwind; break;
+ case lltok::kw_noinline: Attrs |= Attribute::NoInline; break;
+ case lltok::kw_readnone: Attrs |= Attribute::ReadNone; break;
+ case lltok::kw_readonly: Attrs |= Attribute::ReadOnly; break;
+ case lltok::kw_inlinehint: Attrs |= Attribute::InlineHint; break;
+ case lltok::kw_alwaysinline: Attrs |= Attribute::AlwaysInline; break;
+ case lltok::kw_optsize: Attrs |= Attribute::OptimizeForSize; break;
+ case lltok::kw_ssp: Attrs |= Attribute::StackProtect; break;
+ case lltok::kw_sspreq: Attrs |= Attribute::StackProtectReq; break;
+ case lltok::kw_noredzone: Attrs |= Attribute::NoRedZone; break;
+ case lltok::kw_noimplicitfloat: Attrs |= Attribute::NoImplicitFloat; break;
+ case lltok::kw_naked: Attrs |= Attribute::Naked; break;
+
+ case lltok::kw_align: {
+ unsigned Alignment;
+ if (ParseOptionalAlignment(Alignment))
+ return true;
+ Attrs |= Attribute::constructAlignmentFromInt(Alignment);
+ continue;
+ }
+ }
+ Lex.Lex();
+ }
+}
+
+/// ParseOptionalLinkage
+/// ::= /*empty*/
+/// ::= 'private'
+/// ::= 'linker_private'
+/// ::= 'internal'
+/// ::= 'weak'
+/// ::= 'weak_odr'
+/// ::= 'linkonce'
+/// ::= 'linkonce_odr'
+/// ::= 'appending'
+/// ::= 'dllexport'
+/// ::= 'common'
+/// ::= 'dllimport'
+/// ::= 'extern_weak'
+/// ::= 'external'
+bool LLParser::ParseOptionalLinkage(unsigned &Res, bool &HasLinkage) {
+ HasLinkage = false;
+ switch (Lex.getKind()) {
+ default: Res=GlobalValue::ExternalLinkage; return false;
+ case lltok::kw_private: Res = GlobalValue::PrivateLinkage; break;
+ case lltok::kw_linker_private: Res = GlobalValue::LinkerPrivateLinkage; break;
+ case lltok::kw_internal: Res = GlobalValue::InternalLinkage; break;
+ case lltok::kw_weak: Res = GlobalValue::WeakAnyLinkage; break;
+ case lltok::kw_weak_odr: Res = GlobalValue::WeakODRLinkage; break;
+ case lltok::kw_linkonce: Res = GlobalValue::LinkOnceAnyLinkage; break;
+ case lltok::kw_linkonce_odr: Res = GlobalValue::LinkOnceODRLinkage; break;
+ case lltok::kw_available_externally:
+ Res = GlobalValue::AvailableExternallyLinkage;
+ break;
+ case lltok::kw_appending: Res = GlobalValue::AppendingLinkage; break;
+ case lltok::kw_dllexport: Res = GlobalValue::DLLExportLinkage; break;
+ case lltok::kw_common: Res = GlobalValue::CommonLinkage; break;
+ case lltok::kw_dllimport: Res = GlobalValue::DLLImportLinkage; break;
+ case lltok::kw_extern_weak: Res = GlobalValue::ExternalWeakLinkage; break;
+ case lltok::kw_external: Res = GlobalValue::ExternalLinkage; break;
+ }
+ Lex.Lex();
+ HasLinkage = true;
+ return false;
+}
+
+/// ParseOptionalVisibility
+/// ::= /*empty*/
+/// ::= 'default'
+/// ::= 'hidden'
+/// ::= 'protected'
+///
+bool LLParser::ParseOptionalVisibility(unsigned &Res) {
+ switch (Lex.getKind()) {
+ default: Res = GlobalValue::DefaultVisibility; return false;
+ case lltok::kw_default: Res = GlobalValue::DefaultVisibility; break;
+ case lltok::kw_hidden: Res = GlobalValue::HiddenVisibility; break;
+ case lltok::kw_protected: Res = GlobalValue::ProtectedVisibility; break;
+ }
+ Lex.Lex();
+ return false;
+}
+
+/// ParseOptionalCallingConv
+/// ::= /*empty*/
+/// ::= 'ccc'
+/// ::= 'fastcc'
+/// ::= 'coldcc'
+/// ::= 'x86_stdcallcc'
+/// ::= 'x86_fastcallcc'
+/// ::= 'arm_apcscc'
+/// ::= 'arm_aapcscc'
+/// ::= 'arm_aapcs_vfpcc'
+/// ::= 'msp430_intrcc'
+/// ::= 'cc' UINT
+///
+bool LLParser::ParseOptionalCallingConv(CallingConv::ID &CC) {
+ switch (Lex.getKind()) {
+ default: CC = CallingConv::C; return false;
+ case lltok::kw_ccc: CC = CallingConv::C; break;
+ case lltok::kw_fastcc: CC = CallingConv::Fast; break;
+ case lltok::kw_coldcc: CC = CallingConv::Cold; break;
+ case lltok::kw_x86_stdcallcc: CC = CallingConv::X86_StdCall; break;
+ case lltok::kw_x86_fastcallcc: CC = CallingConv::X86_FastCall; break;
+ case lltok::kw_arm_apcscc: CC = CallingConv::ARM_APCS; break;
+ case lltok::kw_arm_aapcscc: CC = CallingConv::ARM_AAPCS; break;
+ case lltok::kw_arm_aapcs_vfpcc:CC = CallingConv::ARM_AAPCS_VFP; break;
+ case lltok::kw_msp430_intrcc: CC = CallingConv::MSP430_INTR; break;
+ case lltok::kw_cc: {
+ unsigned ArbitraryCC;
+ Lex.Lex();
+ if (ParseUInt32(ArbitraryCC)) {
+ return true;
+ } else
+ CC = static_cast<CallingConv::ID>(ArbitraryCC);
+ return false;
+ }
+ break;
+ }
+
+ Lex.Lex();
+ return false;
+}
+
+/// ParseInstructionMetadata
+/// ::= !dbg !42 (',' !dbg !57)*
+bool LLParser::
+ParseInstructionMetadata(SmallVectorImpl<std::pair<unsigned,
+ MDNode *> > &Result){
+ do {
+ if (Lex.getKind() != lltok::MetadataVar)
+ return TokError("expected metadata after comma");
+
+ std::string Name = Lex.getStrVal();
+ Lex.Lex();
+
+ MDNode *Node;
+ if (ParseToken(lltok::exclaim, "expected '!' here") ||
+ ParseMDNodeID(Node))
+ return true;
+
+ unsigned MDK = M->getMDKindID(Name.c_str());
+ Result.push_back(std::make_pair(MDK, Node));
+
+ // If this is the end of the list, we're done.
+ } while (EatIfPresent(lltok::comma));
+ return false;
+}
+
+/// ParseOptionalAlignment
+/// ::= /* empty */
+/// ::= 'align' 4
+bool LLParser::ParseOptionalAlignment(unsigned &Alignment) {
+ Alignment = 0;
+ if (!EatIfPresent(lltok::kw_align))
+ return false;
+ LocTy AlignLoc = Lex.getLoc();
+ if (ParseUInt32(Alignment)) return true;
+ if (!isPowerOf2_32(Alignment))
+ return Error(AlignLoc, "alignment is not a power of two");
+ return false;
+}
+
+/// ParseOptionalCommaAlign
+/// ::=
+/// ::= ',' align 4
+///
+/// This returns with AteExtraComma set to true if it ate an excess comma at the
+/// end.
+bool LLParser::ParseOptionalCommaAlign(unsigned &Alignment,
+ bool &AteExtraComma) {
+ AteExtraComma = false;
+ while (EatIfPresent(lltok::comma)) {
+ // Metadata at the end is an early exit.
+ if (Lex.getKind() == lltok::MetadataVar) {
+ AteExtraComma = true;
+ return false;
+ }
+
+ if (Lex.getKind() == lltok::kw_align) {
+ if (ParseOptionalAlignment(Alignment)) return true;
+ } else
+ return true;
+ }
+
+ return false;
+}
+
+
+/// ParseIndexList - This parses the index list for an insert/extractvalue
+/// instruction. This sets AteExtraComma in the case where we eat an extra
+/// comma at the end of the line and find that it is followed by metadata.
+/// Clients that don't allow metadata can call the version of this function that
+/// only takes one argument.
+///
+/// ParseIndexList
+/// ::= (',' uint32)+
+///
+bool LLParser::ParseIndexList(SmallVectorImpl<unsigned> &Indices,
+ bool &AteExtraComma) {
+ AteExtraComma = false;
+
+ if (Lex.getKind() != lltok::comma)
+ return TokError("expected ',' as start of index list");
+
+ while (EatIfPresent(lltok::comma)) {
+ if (Lex.getKind() == lltok::MetadataVar) {
+ AteExtraComma = true;
+ return false;
+ }
+ unsigned Idx;
+ if (ParseUInt32(Idx)) return true;
+ Indices.push_back(Idx);
+ }
+
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Type Parsing.
+//===----------------------------------------------------------------------===//
+
+/// ParseType - Parse and resolve a full type.
+bool LLParser::ParseType(PATypeHolder &Result, bool AllowVoid) {
+ LocTy TypeLoc = Lex.getLoc();
+ if (ParseTypeRec(Result)) return true;
+
+ // Verify no unresolved uprefs.
+ if (!UpRefs.empty())
+ return Error(UpRefs.back().Loc, "invalid unresolved type up reference");
+
+ if (!AllowVoid && Result.get()->isVoidTy())
+ return Error(TypeLoc, "void type only allowed for function results");
+
+ return false;
+}
+
+/// HandleUpRefs - Every time we finish a new layer of types, this function is
+/// called. It loops through the UpRefs vector, which is a list of the
+/// currently active types. For each type, if the up-reference is contained in
+/// the newly completed type, we decrement the level count. When the level
+/// count reaches zero, the up-referenced type is the type that is passed in:
+/// thus we can complete the cycle.
+///
+PATypeHolder LLParser::HandleUpRefs(const Type *ty) {
+ // If Ty isn't abstract, or if there are no up-references in it, then there is
+ // nothing to resolve here.
+ if (!ty->isAbstract() || UpRefs.empty()) return ty;
+
+ PATypeHolder Ty(ty);
+#if 0
+ dbgs() << "Type '" << Ty->getDescription()
+ << "' newly formed. Resolving upreferences.\n"
+ << UpRefs.size() << " upreferences active!\n";
+#endif
+
+ // If we find any resolvable upreferences (i.e., those whose NestingLevel goes
+ // to zero), we resolve them all together before we resolve them to Ty. At
+ // the end of the loop, if there is anything to resolve to Ty, it will be in
+ // this variable.
+ OpaqueType *TypeToResolve = 0;
+
+ for (unsigned i = 0; i != UpRefs.size(); ++i) {
+ // Determine if 'Ty' directly contains this up-references 'LastContainedTy'.
+ bool ContainsType =
+ std::find(Ty->subtype_begin(), Ty->subtype_end(),
+ UpRefs[i].LastContainedTy) != Ty->subtype_end();
+
+#if 0
+ dbgs() << " UR#" << i << " - TypeContains(" << Ty->getDescription() << ", "
+ << UpRefs[i].LastContainedTy->getDescription() << ") = "
+ << (ContainsType ? "true" : "false")
+ << " level=" << UpRefs[i].NestingLevel << "\n";
+#endif
+ if (!ContainsType)
+ continue;
+
+ // Decrement level of upreference
+ unsigned Level = --UpRefs[i].NestingLevel;
+ UpRefs[i].LastContainedTy = Ty;
+
+ // If the Up-reference has a non-zero level, it shouldn't be resolved yet.
+ if (Level != 0)
+ continue;
+
+#if 0
+ dbgs() << " * Resolving upreference for " << UpRefs[i].UpRefTy << "\n";
+#endif
+ if (!TypeToResolve)
+ TypeToResolve = UpRefs[i].UpRefTy;
+ else
+ UpRefs[i].UpRefTy->refineAbstractTypeTo(TypeToResolve);
+ UpRefs.erase(UpRefs.begin()+i); // Remove from upreference list.
+ --i; // Do not skip the next element.
+ }
+
+ if (TypeToResolve)
+ TypeToResolve->refineAbstractTypeTo(Ty);
+
+ return Ty;
+}
+
+
+/// ParseTypeRec - The recursive function used to process the internal
+/// implementation details of types.
+bool LLParser::ParseTypeRec(PATypeHolder &Result) {
+ switch (Lex.getKind()) {
+ default:
+ return TokError("expected type");
+ case lltok::Type:
+ // TypeRec ::= 'float' | 'void' (etc)
+ Result = Lex.getTyVal();
+ Lex.Lex();
+ break;
+ case lltok::kw_opaque:
+ // TypeRec ::= 'opaque'
+ Result = OpaqueType::get(Context);
+ Lex.Lex();
+ break;
+ case lltok::lbrace:
+ // TypeRec ::= '{' ... '}'
+ if (ParseStructType(Result, false))
+ return true;
+ break;
+ case lltok::lsquare:
+ // TypeRec ::= '[' ... ']'
+ Lex.Lex(); // eat the lsquare.
+ if (ParseArrayVectorType(Result, false))
+ return true;
+ break;
+ case lltok::less: // Either vector or packed struct.
+ // TypeRec ::= '<' ... '>'
+ Lex.Lex();
+ if (Lex.getKind() == lltok::lbrace) {
+ if (ParseStructType(Result, true) ||
+ ParseToken(lltok::greater, "expected '>' at end of packed struct"))
+ return true;
+ } else if (ParseArrayVectorType(Result, true))
+ return true;
+ break;
+ case lltok::LocalVar:
+ case lltok::StringConstant: // FIXME: REMOVE IN LLVM 3.0
+ // TypeRec ::= %foo
+ if (const Type *T = M->getTypeByName(Lex.getStrVal())) {
+ Result = T;
+ } else {
+ Result = OpaqueType::get(Context);
+ ForwardRefTypes.insert(std::make_pair(Lex.getStrVal(),
+ std::make_pair(Result,
+ Lex.getLoc())));
+ M->addTypeName(Lex.getStrVal(), Result.get());
+ }
+ Lex.Lex();
+ break;
+
+ case lltok::LocalVarID:
+ // TypeRec ::= %4
+ if (Lex.getUIntVal() < NumberedTypes.size())
+ Result = NumberedTypes[Lex.getUIntVal()];
+ else {
+ std::map<unsigned, std::pair<PATypeHolder, LocTy> >::iterator
+ I = ForwardRefTypeIDs.find(Lex.getUIntVal());
+ if (I != ForwardRefTypeIDs.end())
+ Result = I->second.first;
+ else {
+ Result = OpaqueType::get(Context);
+ ForwardRefTypeIDs.insert(std::make_pair(Lex.getUIntVal(),
+ std::make_pair(Result,
+ Lex.getLoc())));
+ }
+ }
+ Lex.Lex();
+ break;
+ case lltok::backslash: {
+ // TypeRec ::= '\' 4
+ Lex.Lex();
+ unsigned Val;
+ if (ParseUInt32(Val)) return true;
+ OpaqueType *OT = OpaqueType::get(Context); //Use temporary placeholder.
+ UpRefs.push_back(UpRefRecord(Lex.getLoc(), Val, OT));
+ Result = OT;
+ break;
+ }
+ }
+
+ // Parse the type suffixes.
+ while (1) {
+ switch (Lex.getKind()) {
+ // End of type.
+ default: return false;
+
+ // TypeRec ::= TypeRec '*'
+ case lltok::star:
+ if (Result.get()->isLabelTy())
+ return TokError("basic block pointers are invalid");
+ if (Result.get()->isVoidTy())
+ return TokError("pointers to void are invalid; use i8* instead");
+ if (!PointerType::isValidElementType(Result.get()))
+ return TokError("pointer to this type is invalid");
+ Result = HandleUpRefs(PointerType::getUnqual(Result.get()));
+ Lex.Lex();
+ break;
+
+ // TypeRec ::= TypeRec 'addrspace' '(' uint32 ')' '*'
+ case lltok::kw_addrspace: {
+ if (Result.get()->isLabelTy())
+ return TokError("basic block pointers are invalid");
+ if (Result.get()->isVoidTy())
+ return TokError("pointers to void are invalid; use i8* instead");
+ if (!PointerType::isValidElementType(Result.get()))
+ return TokError("pointer to this type is invalid");
+ unsigned AddrSpace;
+ if (ParseOptionalAddrSpace(AddrSpace) ||
+ ParseToken(lltok::star, "expected '*' in address space"))
+ return true;
+
+ Result = HandleUpRefs(PointerType::get(Result.get(), AddrSpace));
+ break;
+ }
+
+ /// Types '(' ArgTypeListI ')' OptFuncAttrs
+ case lltok::lparen:
+ if (ParseFunctionType(Result))
+ return true;
+ break;
+ }
+ }
+}
+
+/// ParseParameterList
+/// ::= '(' ')'
+/// ::= '(' Arg (',' Arg)* ')'
+/// Arg
+/// ::= Type OptionalAttributes Value OptionalAttributes
+bool LLParser::ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
+ PerFunctionState &PFS) {
+ if (ParseToken(lltok::lparen, "expected '(' in call"))
+ return true;
+
+ while (Lex.getKind() != lltok::rparen) {
+ // If this isn't the first argument, we need a comma.
+ if (!ArgList.empty() &&
+ ParseToken(lltok::comma, "expected ',' in argument list"))
+ return true;
+
+ // Parse the argument.
+ LocTy ArgLoc;
+ PATypeHolder ArgTy(Type::getVoidTy(Context));
+ unsigned ArgAttrs1 = Attribute::None;
+ unsigned ArgAttrs2 = Attribute::None;
+ Value *V;
+ if (ParseType(ArgTy, ArgLoc))
+ return true;
+
+ // Otherwise, handle normal operands.
+ if (ParseOptionalAttrs(ArgAttrs1, 0) ||
+ ParseValue(ArgTy, V, PFS) ||
+ // FIXME: Should not allow attributes after the argument, remove this
+ // in LLVM 3.0.
+ ParseOptionalAttrs(ArgAttrs2, 3))
+ return true;
+ ArgList.push_back(ParamInfo(ArgLoc, V, ArgAttrs1|ArgAttrs2));
+ }
+
+ Lex.Lex(); // Lex the ')'.
+ return false;
+}
+
+
+
+/// ParseArgumentList - Parse the argument list for a function type or function
+/// prototype. If 'inType' is true then we are parsing a FunctionType.
+/// ::= '(' ArgTypeListI ')'
+/// ArgTypeListI
+/// ::= /*empty*/
+/// ::= '...'
+/// ::= ArgTypeList ',' '...'
+/// ::= ArgType (',' ArgType)*
+///
+bool LLParser::ParseArgumentList(std::vector<ArgInfo> &ArgList,
+ bool &isVarArg, bool inType) {
+ isVarArg = false;
+ assert(Lex.getKind() == lltok::lparen);
+ Lex.Lex(); // eat the (.
+
+ if (Lex.getKind() == lltok::rparen) {
+ // empty
+ } else if (Lex.getKind() == lltok::dotdotdot) {
+ isVarArg = true;
+ Lex.Lex();
+ } else {
+ LocTy TypeLoc = Lex.getLoc();
+ PATypeHolder ArgTy(Type::getVoidTy(Context));
+ unsigned Attrs;
+ std::string Name;
+
+ // If we're parsing a type, use ParseTypeRec, because we allow recursive
+ // types (such as a function returning a pointer to itself). If parsing a
+ // function prototype, we require fully resolved types.
+ if ((inType ? ParseTypeRec(ArgTy) : ParseType(ArgTy)) ||
+ ParseOptionalAttrs(Attrs, 0)) return true;
+
+ if (ArgTy->isVoidTy())
+ return Error(TypeLoc, "argument can not have void type");
+
+ if (Lex.getKind() == lltok::LocalVar ||
+ Lex.getKind() == lltok::StringConstant) { // FIXME: REMOVE IN LLVM 3.0
+ Name = Lex.getStrVal();
+ Lex.Lex();
+ }
+
+ if (!FunctionType::isValidArgumentType(ArgTy))
+ return Error(TypeLoc, "invalid type for function argument");
+
+ ArgList.push_back(ArgInfo(TypeLoc, ArgTy, Attrs, Name));
+
+ while (EatIfPresent(lltok::comma)) {
+ // Handle ... at end of arg list.
+ if (EatIfPresent(lltok::dotdotdot)) {
+ isVarArg = true;
+ break;
+ }
+
+ // Otherwise must be an argument type.
+ TypeLoc = Lex.getLoc();
+ if ((inType ? ParseTypeRec(ArgTy) : ParseType(ArgTy)) ||
+ ParseOptionalAttrs(Attrs, 0)) return true;
+
+ if (ArgTy->isVoidTy())
+ return Error(TypeLoc, "argument can not have void type");
+
+ if (Lex.getKind() == lltok::LocalVar ||
+ Lex.getKind() == lltok::StringConstant) { // FIXME: REMOVE IN LLVM 3.0
+ Name = Lex.getStrVal();
+ Lex.Lex();
+ } else {
+ Name = "";
+ }
+
+ if (!ArgTy->isFirstClassType() && !isa<OpaqueType>(ArgTy))
+ return Error(TypeLoc, "invalid type for function argument");
+
+ ArgList.push_back(ArgInfo(TypeLoc, ArgTy, Attrs, Name));
+ }
+ }
+
+ return ParseToken(lltok::rparen, "expected ')' at end of argument list");
+}
+
+/// ParseFunctionType
+/// ::= Type ArgumentList OptionalAttrs
+bool LLParser::ParseFunctionType(PATypeHolder &Result) {
+ assert(Lex.getKind() == lltok::lparen);
+
+ if (!FunctionType::isValidReturnType(Result))
+ return TokError("invalid function return type");
+
+ std::vector<ArgInfo> ArgList;
+ bool isVarArg;
+ unsigned Attrs;
+ if (ParseArgumentList(ArgList, isVarArg, true) ||
+ // FIXME: Allow, but ignore attributes on function types!
+ // FIXME: Remove in LLVM 3.0
+ ParseOptionalAttrs(Attrs, 2))
+ return true;
+
+ // Reject names on the arguments lists.
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
+ if (!ArgList[i].Name.empty())
+ return Error(ArgList[i].Loc, "argument name invalid in function type");
+ if (!ArgList[i].Attrs != 0) {
+ // Allow but ignore attributes on function types; this permits
+ // auto-upgrade.
+ // FIXME: REJECT ATTRIBUTES ON FUNCTION TYPES in LLVM 3.0
+ }
+ }
+
+ std::vector<const Type*> ArgListTy;
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
+ ArgListTy.push_back(ArgList[i].Type);
+
+ Result = HandleUpRefs(FunctionType::get(Result.get(),
+ ArgListTy, isVarArg));
+ return false;
+}
+
+/// ParseStructType: Handles packed and unpacked types. </> parsed elsewhere.
+/// TypeRec
+/// ::= '{' '}'
+/// ::= '{' TypeRec (',' TypeRec)* '}'
+/// ::= '<' '{' '}' '>'
+/// ::= '<' '{' TypeRec (',' TypeRec)* '}' '>'
+bool LLParser::ParseStructType(PATypeHolder &Result, bool Packed) {
+ assert(Lex.getKind() == lltok::lbrace);
+ Lex.Lex(); // Consume the '{'
+
+ if (EatIfPresent(lltok::rbrace)) {
+ Result = StructType::get(Context, Packed);
+ return false;
+ }
+
+ std::vector<PATypeHolder> ParamsList;
+ LocTy EltTyLoc = Lex.getLoc();
+ if (ParseTypeRec(Result)) return true;
+ ParamsList.push_back(Result);
+
+ if (Result->isVoidTy())
+ return Error(EltTyLoc, "struct element can not have void type");
+ if (!StructType::isValidElementType(Result))
+ return Error(EltTyLoc, "invalid element type for struct");
+
+ while (EatIfPresent(lltok::comma)) {
+ EltTyLoc = Lex.getLoc();
+ if (ParseTypeRec(Result)) return true;
+
+ if (Result->isVoidTy())
+ return Error(EltTyLoc, "struct element can not have void type");
+ if (!StructType::isValidElementType(Result))
+ return Error(EltTyLoc, "invalid element type for struct");
+
+ ParamsList.push_back(Result);
+ }
+
+ if (ParseToken(lltok::rbrace, "expected '}' at end of struct"))
+ return true;
+
+ std::vector<const Type*> ParamsListTy;
+ for (unsigned i = 0, e = ParamsList.size(); i != e; ++i)
+ ParamsListTy.push_back(ParamsList[i].get());
+ Result = HandleUpRefs(StructType::get(Context, ParamsListTy, Packed));
+ return false;
+}
+
+/// ParseArrayVectorType - Parse an array or vector type, assuming the first
+/// token has already been consumed.
+/// TypeRec
+/// ::= '[' APSINTVAL 'x' Types ']'
+/// ::= '<' APSINTVAL 'x' Types '>'
+bool LLParser::ParseArrayVectorType(PATypeHolder &Result, bool isVector) {
+ if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned() ||
+ Lex.getAPSIntVal().getBitWidth() > 64)
+ return TokError("expected number in address space");
+
+ LocTy SizeLoc = Lex.getLoc();
+ uint64_t Size = Lex.getAPSIntVal().getZExtValue();
+ Lex.Lex();
+
+ if (ParseToken(lltok::kw_x, "expected 'x' after element count"))
+ return true;
+
+ LocTy TypeLoc = Lex.getLoc();
+ PATypeHolder EltTy(Type::getVoidTy(Context));
+ if (ParseTypeRec(EltTy)) return true;
+
+ if (EltTy->isVoidTy())
+ return Error(TypeLoc, "array and vector element type cannot be void");
+
+ if (ParseToken(isVector ? lltok::greater : lltok::rsquare,
+ "expected end of sequential type"))
+ return true;
+
+ if (isVector) {
+ if (Size == 0)
+ return Error(SizeLoc, "zero element vector is illegal");
+ if ((unsigned)Size != Size)
+ return Error(SizeLoc, "size too large for vector");
+ if (!VectorType::isValidElementType(EltTy))
+ return Error(TypeLoc, "vector element type must be fp or integer");
+ Result = VectorType::get(EltTy, unsigned(Size));
+ } else {
+ if (!ArrayType::isValidElementType(EltTy))
+ return Error(TypeLoc, "invalid array element type");
+ Result = HandleUpRefs(ArrayType::get(EltTy, Size));
+ }
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Function Semantic Analysis.
+//===----------------------------------------------------------------------===//
+
+LLParser::PerFunctionState::PerFunctionState(LLParser &p, Function &f,
+ int functionNumber)
+ : P(p), F(f), FunctionNumber(functionNumber) {
+
+ // Insert unnamed arguments into the NumberedVals list.
+ for (Function::arg_iterator AI = F.arg_begin(), E = F.arg_end();
+ AI != E; ++AI)
+ if (!AI->hasName())
+ NumberedVals.push_back(AI);
+}
+
+LLParser::PerFunctionState::~PerFunctionState() {
+ // If there were any forward referenced non-basicblock values, delete them.
+ for (std::map<std::string, std::pair<Value*, LocTy> >::iterator
+ I = ForwardRefVals.begin(), E = ForwardRefVals.end(); I != E; ++I)
+ if (!isa<BasicBlock>(I->second.first)) {
+ I->second.first->replaceAllUsesWith(
+ UndefValue::get(I->second.first->getType()));
+ delete I->second.first;
+ I->second.first = 0;
+ }
+
+ for (std::map<unsigned, std::pair<Value*, LocTy> >::iterator
+ I = ForwardRefValIDs.begin(), E = ForwardRefValIDs.end(); I != E; ++I)
+ if (!isa<BasicBlock>(I->second.first)) {
+ I->second.first->replaceAllUsesWith(
+ UndefValue::get(I->second.first->getType()));
+ delete I->second.first;
+ I->second.first = 0;
+ }
+}
+
+bool LLParser::PerFunctionState::FinishFunction() {
+ // Check to see if someone took the address of labels in this block.
+ if (!P.ForwardRefBlockAddresses.empty()) {
+ ValID FunctionID;
+ if (!F.getName().empty()) {
+ FunctionID.Kind = ValID::t_GlobalName;
+ FunctionID.StrVal = F.getName();
+ } else {
+ FunctionID.Kind = ValID::t_GlobalID;
+ FunctionID.UIntVal = FunctionNumber;
+ }
+
+ std::map<ValID, std::vector<std::pair<ValID, GlobalValue*> > >::iterator
+ FRBAI = P.ForwardRefBlockAddresses.find(FunctionID);
+ if (FRBAI != P.ForwardRefBlockAddresses.end()) {
+ // Resolve all these references.
+ if (P.ResolveForwardRefBlockAddresses(&F, FRBAI->second, this))
+ return true;
+
+ P.ForwardRefBlockAddresses.erase(FRBAI);
+ }
+ }
+
+ if (!ForwardRefVals.empty())
+ return P.Error(ForwardRefVals.begin()->second.second,
+ "use of undefined value '%" + ForwardRefVals.begin()->first +
+ "'");
+ if (!ForwardRefValIDs.empty())
+ return P.Error(ForwardRefValIDs.begin()->second.second,
+ "use of undefined value '%" +
+ utostr(ForwardRefValIDs.begin()->first) + "'");
+ return false;
+}
+
+
+/// 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 *LLParser::PerFunctionState::GetVal(const std::string &Name,
+ const Type *Ty, LocTy Loc) {
+ // Look this name up in the normal function symbol table.
+ Value *Val = F.getValueSymbolTable().lookup(Name);
+
+ // If this is a forward reference for the value, see if we already created a
+ // forward ref record.
+ if (Val == 0) {
+ std::map<std::string, std::pair<Value*, LocTy> >::iterator
+ I = ForwardRefVals.find(Name);
+ if (I != ForwardRefVals.end())
+ Val = I->second.first;
+ }
+
+ // If we have the value in the symbol table or fwd-ref table, return it.
+ if (Val) {
+ if (Val->getType() == Ty) return Val;
+ if (Ty->isLabelTy())
+ P.Error(Loc, "'%" + Name + "' is not a basic block");
+ else
+ P.Error(Loc, "'%" + Name + "' defined with type '" +
+ Val->getType()->getDescription() + "'");
+ return 0;
+ }
+
+ // Don't make placeholders with invalid type.
+ if (!Ty->isFirstClassType() && !isa<OpaqueType>(Ty) && !Ty->isLabelTy()) {
+ P.Error(Loc, "invalid use of a non-first-class type");
+ return 0;
+ }
+
+ // Otherwise, create a new forward reference for this value and remember it.
+ Value *FwdVal;
+ if (Ty->isLabelTy())
+ FwdVal = BasicBlock::Create(F.getContext(), Name, &F);
+ else
+ FwdVal = new Argument(Ty, Name);
+
+ ForwardRefVals[Name] = std::make_pair(FwdVal, Loc);
+ return FwdVal;
+}
+
+Value *LLParser::PerFunctionState::GetVal(unsigned ID, const Type *Ty,
+ LocTy Loc) {
+ // Look this name up in the normal function symbol table.
+ Value *Val = ID < NumberedVals.size() ? NumberedVals[ID] : 0;
+
+ // If this is a forward reference for the value, see if we already created a
+ // forward ref record.
+ if (Val == 0) {
+ std::map<unsigned, std::pair<Value*, LocTy> >::iterator
+ I = ForwardRefValIDs.find(ID);
+ if (I != ForwardRefValIDs.end())
+ Val = I->second.first;
+ }
+
+ // If we have the value in the symbol table or fwd-ref table, return it.
+ if (Val) {
+ if (Val->getType() == Ty) return Val;
+ if (Ty->isLabelTy())
+ P.Error(Loc, "'%" + utostr(ID) + "' is not a basic block");
+ else
+ P.Error(Loc, "'%" + utostr(ID) + "' defined with type '" +
+ Val->getType()->getDescription() + "'");
+ return 0;
+ }
+
+ if (!Ty->isFirstClassType() && !isa<OpaqueType>(Ty) && !Ty->isLabelTy()) {
+ P.Error(Loc, "invalid use of a non-first-class type");
+ return 0;
+ }
+
+ // Otherwise, create a new forward reference for this value and remember it.
+ Value *FwdVal;
+ if (Ty->isLabelTy())
+ FwdVal = BasicBlock::Create(F.getContext(), "", &F);
+ else
+ FwdVal = new Argument(Ty);
+
+ ForwardRefValIDs[ID] = std::make_pair(FwdVal, Loc);
+ return FwdVal;
+}
+
+/// SetInstName - After an instruction is parsed and inserted into its
+/// basic block, this installs its name.
+bool LLParser::PerFunctionState::SetInstName(int NameID,
+ const std::string &NameStr,
+ LocTy NameLoc, Instruction *Inst) {
+ // If this instruction has void type, it cannot have a name or ID specified.
+ if (Inst->getType()->isVoidTy()) {
+ if (NameID != -1 || !NameStr.empty())
+ return P.Error(NameLoc, "instructions returning void cannot have a name");
+ return false;
+ }
+
+ // If this was a numbered instruction, verify that the instruction is the
+ // expected value and resolve any forward references.
+ if (NameStr.empty()) {
+ // If neither a name nor an ID was specified, just use the next ID.
+ if (NameID == -1)
+ NameID = NumberedVals.size();
+
+ if (unsigned(NameID) != NumberedVals.size())
+ return P.Error(NameLoc, "instruction expected to be numbered '%" +
+ utostr(NumberedVals.size()) + "'");
+
+ std::map<unsigned, std::pair<Value*, LocTy> >::iterator FI =
+ ForwardRefValIDs.find(NameID);
+ if (FI != ForwardRefValIDs.end()) {
+ if (FI->second.first->getType() != Inst->getType())
+ return P.Error(NameLoc, "instruction forward referenced with type '" +
+ FI->second.first->getType()->getDescription() + "'");
+ FI->second.first->replaceAllUsesWith(Inst);
+ delete FI->second.first;
+ ForwardRefValIDs.erase(FI);
+ }
+
+ NumberedVals.push_back(Inst);
+ return false;
+ }
+
+ // Otherwise, the instruction had a name. Resolve forward refs and set it.
+ std::map<std::string, std::pair<Value*, LocTy> >::iterator
+ FI = ForwardRefVals.find(NameStr);
+ if (FI != ForwardRefVals.end()) {
+ if (FI->second.first->getType() != Inst->getType())
+ return P.Error(NameLoc, "instruction forward referenced with type '" +
+ FI->second.first->getType()->getDescription() + "'");
+ FI->second.first->replaceAllUsesWith(Inst);
+ delete FI->second.first;
+ ForwardRefVals.erase(FI);
+ }
+
+ // Set the name on the instruction.
+ Inst->setName(NameStr);
+
+ if (Inst->getNameStr() != NameStr)
+ return P.Error(NameLoc, "multiple definition of local value named '" +
+ NameStr + "'");
+ return false;
+}
+
+/// GetBB - Get a basic block with the specified name or ID, creating a
+/// forward reference record if needed.
+BasicBlock *LLParser::PerFunctionState::GetBB(const std::string &Name,
+ LocTy Loc) {
+ return cast_or_null<BasicBlock>(GetVal(Name,
+ Type::getLabelTy(F.getContext()), Loc));
+}
+
+BasicBlock *LLParser::PerFunctionState::GetBB(unsigned ID, LocTy Loc) {
+ return cast_or_null<BasicBlock>(GetVal(ID,
+ Type::getLabelTy(F.getContext()), Loc));
+}
+
+/// DefineBB - Define the specified basic block, which is either named or
+/// unnamed. If there is an error, this returns null otherwise it returns
+/// the block being defined.
+BasicBlock *LLParser::PerFunctionState::DefineBB(const std::string &Name,
+ LocTy Loc) {
+ BasicBlock *BB;
+ if (Name.empty())
+ BB = GetBB(NumberedVals.size(), Loc);
+ else
+ BB = GetBB(Name, Loc);
+ if (BB == 0) return 0; // Already diagnosed error.
+
+ // Move the block to the end of the function. Forward ref'd blocks are
+ // inserted wherever they happen to be referenced.
+ F.getBasicBlockList().splice(F.end(), F.getBasicBlockList(), BB);
+
+ // Remove the block from forward ref sets.
+ if (Name.empty()) {
+ ForwardRefValIDs.erase(NumberedVals.size());
+ NumberedVals.push_back(BB);
+ } else {
+ // BB forward references are already in the function symbol table.
+ ForwardRefVals.erase(Name);
+ }
+
+ return BB;
+}
+
+//===----------------------------------------------------------------------===//
+// Constants.
+//===----------------------------------------------------------------------===//
+
+/// ParseValID - Parse an abstract value that doesn't necessarily have a
+/// type implied. For example, if we parse "4" we don't know what integer type
+/// it has. The value will later be combined with its type and checked for
+/// sanity. PFS is used to convert function-local operands of metadata (since
+/// metadata operands are not just parsed here but also converted to values).
+/// PFS can be null when we are not parsing metadata values inside a function.
+bool LLParser::ParseValID(ValID &ID, PerFunctionState *PFS) {
+ ID.Loc = Lex.getLoc();
+ switch (Lex.getKind()) {
+ default: return TokError("expected value token");
+ case lltok::GlobalID: // @42
+ ID.UIntVal = Lex.getUIntVal();
+ ID.Kind = ValID::t_GlobalID;
+ break;
+ case lltok::GlobalVar: // @foo
+ ID.StrVal = Lex.getStrVal();
+ ID.Kind = ValID::t_GlobalName;
+ break;
+ case lltok::LocalVarID: // %42
+ ID.UIntVal = Lex.getUIntVal();
+ ID.Kind = ValID::t_LocalID;
+ break;
+ case lltok::LocalVar: // %foo
+ case lltok::StringConstant: // "foo" - FIXME: REMOVE IN LLVM 3.0
+ ID.StrVal = Lex.getStrVal();
+ ID.Kind = ValID::t_LocalName;
+ break;
+ case lltok::exclaim: // !{...} MDNode, !"foo" MDString
+ Lex.Lex();
+
+ if (EatIfPresent(lltok::lbrace)) {
+ SmallVector<Value*, 16> Elts;
+ if (ParseMDNodeVector(Elts, PFS) ||
+ ParseToken(lltok::rbrace, "expected end of metadata node"))
+ return true;
+
+ ID.MDNodeVal = MDNode::get(Context, Elts.data(), Elts.size());
+ ID.Kind = ValID::t_MDNode;
+ return false;
+ }
+
+ // Standalone metadata reference
+ // !{ ..., !42, ... }
+ if (Lex.getKind() == lltok::APSInt) {
+ if (ParseMDNodeID(ID.MDNodeVal)) return true;
+ ID.Kind = ValID::t_MDNode;
+ return false;
+ }
+
+ // MDString:
+ // ::= '!' STRINGCONSTANT
+ if (ParseMDString(ID.MDStringVal)) return true;
+ ID.Kind = ValID::t_MDString;
+ return false;
+ case lltok::APSInt:
+ ID.APSIntVal = Lex.getAPSIntVal();
+ ID.Kind = ValID::t_APSInt;
+ break;
+ case lltok::APFloat:
+ ID.APFloatVal = Lex.getAPFloatVal();
+ ID.Kind = ValID::t_APFloat;
+ break;
+ case lltok::kw_true:
+ ID.ConstantVal = ConstantInt::getTrue(Context);
+ ID.Kind = ValID::t_Constant;
+ break;
+ case lltok::kw_false:
+ ID.ConstantVal = ConstantInt::getFalse(Context);
+ ID.Kind = ValID::t_Constant;
+ break;
+ case lltok::kw_null: ID.Kind = ValID::t_Null; break;
+ case lltok::kw_undef: ID.Kind = ValID::t_Undef; break;
+ case lltok::kw_zeroinitializer: ID.Kind = ValID::t_Zero; break;
+
+ case lltok::lbrace: {
+ // ValID ::= '{' ConstVector '}'
+ Lex.Lex();
+ SmallVector<Constant*, 16> Elts;
+ if (ParseGlobalValueVector(Elts) ||
+ ParseToken(lltok::rbrace, "expected end of struct constant"))
+ return true;
+
+ ID.ConstantVal = ConstantStruct::get(Context, Elts.data(),
+ Elts.size(), false);
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::less: {
+ // ValID ::= '<' ConstVector '>' --> Vector.
+ // ValID ::= '<' '{' ConstVector '}' '>' --> Packed Struct.
+ Lex.Lex();
+ bool isPackedStruct = EatIfPresent(lltok::lbrace);
+
+ SmallVector<Constant*, 16> Elts;
+ LocTy FirstEltLoc = Lex.getLoc();
+ if (ParseGlobalValueVector(Elts) ||
+ (isPackedStruct &&
+ ParseToken(lltok::rbrace, "expected end of packed struct")) ||
+ ParseToken(lltok::greater, "expected end of constant"))
+ return true;
+
+ if (isPackedStruct) {
+ ID.ConstantVal =
+ ConstantStruct::get(Context, Elts.data(), Elts.size(), true);
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+
+ if (Elts.empty())
+ return Error(ID.Loc, "constant vector must not be empty");
+
+ if (!Elts[0]->getType()->isInteger() &&
+ !Elts[0]->getType()->isFloatingPoint())
+ return Error(FirstEltLoc,
+ "vector elements must have integer or floating point type");
+
+ // Verify that all the vector elements have the same type.
+ for (unsigned i = 1, e = Elts.size(); i != e; ++i)
+ if (Elts[i]->getType() != Elts[0]->getType())
+ return Error(FirstEltLoc,
+ "vector element #" + utostr(i) +
+ " is not of type '" + Elts[0]->getType()->getDescription());
+
+ ID.ConstantVal = ConstantVector::get(Elts.data(), Elts.size());
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::lsquare: { // Array Constant
+ Lex.Lex();
+ SmallVector<Constant*, 16> Elts;
+ LocTy FirstEltLoc = Lex.getLoc();
+ if (ParseGlobalValueVector(Elts) ||
+ ParseToken(lltok::rsquare, "expected end of array constant"))
+ return true;
+
+ // Handle empty element.
+ if (Elts.empty()) {
+ // Use undef instead of an array because it's inconvenient to determine
+ // the element type at this point, there being no elements to examine.
+ ID.Kind = ValID::t_EmptyArray;
+ return false;
+ }
+
+ if (!Elts[0]->getType()->isFirstClassType())
+ return Error(FirstEltLoc, "invalid array element type: " +
+ Elts[0]->getType()->getDescription());
+
+ ArrayType *ATy = ArrayType::get(Elts[0]->getType(), Elts.size());
+
+ // Verify all elements are correct type!
+ for (unsigned i = 0, e = Elts.size(); i != e; ++i) {
+ if (Elts[i]->getType() != Elts[0]->getType())
+ return Error(FirstEltLoc,
+ "array element #" + utostr(i) +
+ " is not of type '" +Elts[0]->getType()->getDescription());
+ }
+
+ ID.ConstantVal = ConstantArray::get(ATy, Elts.data(), Elts.size());
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::kw_c: // c "foo"
+ Lex.Lex();
+ ID.ConstantVal = ConstantArray::get(Context, Lex.getStrVal(), false);
+ if (ParseToken(lltok::StringConstant, "expected string")) return true;
+ ID.Kind = ValID::t_Constant;
+ return false;
+
+ case lltok::kw_asm: {
+ // ValID ::= 'asm' SideEffect? AlignStack? STRINGCONSTANT ',' STRINGCONSTANT
+ bool HasSideEffect, AlignStack;
+ Lex.Lex();
+ if (ParseOptionalToken(lltok::kw_sideeffect, HasSideEffect) ||
+ ParseOptionalToken(lltok::kw_alignstack, AlignStack) ||
+ ParseStringConstant(ID.StrVal) ||
+ ParseToken(lltok::comma, "expected comma in inline asm expression") ||
+ ParseToken(lltok::StringConstant, "expected constraint string"))
+ return true;
+ ID.StrVal2 = Lex.getStrVal();
+ ID.UIntVal = unsigned(HasSideEffect) | (unsigned(AlignStack)<<1);
+ ID.Kind = ValID::t_InlineAsm;
+ return false;
+ }
+
+ case lltok::kw_blockaddress: {
+ // ValID ::= 'blockaddress' '(' @foo ',' %bar ')'
+ Lex.Lex();
+
+ ValID Fn, Label;
+ LocTy FnLoc, LabelLoc;
+
+ if (ParseToken(lltok::lparen, "expected '(' in block address expression") ||
+ ParseValID(Fn) ||
+ ParseToken(lltok::comma, "expected comma in block address expression")||
+ ParseValID(Label) ||
+ ParseToken(lltok::rparen, "expected ')' in block address expression"))
+ return true;
+
+ if (Fn.Kind != ValID::t_GlobalID && Fn.Kind != ValID::t_GlobalName)
+ return Error(Fn.Loc, "expected function name in blockaddress");
+ if (Label.Kind != ValID::t_LocalID && Label.Kind != ValID::t_LocalName)
+ return Error(Label.Loc, "expected basic block name in blockaddress");
+
+ // Make a global variable as a placeholder for this reference.
+ GlobalVariable *FwdRef = new GlobalVariable(*M, Type::getInt8Ty(Context),
+ false, GlobalValue::InternalLinkage,
+ 0, "");
+ ForwardRefBlockAddresses[Fn].push_back(std::make_pair(Label, FwdRef));
+ ID.ConstantVal = FwdRef;
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+
+ case lltok::kw_trunc:
+ case lltok::kw_zext:
+ case lltok::kw_sext:
+ case lltok::kw_fptrunc:
+ case lltok::kw_fpext:
+ case lltok::kw_bitcast:
+ case lltok::kw_uitofp:
+ case lltok::kw_sitofp:
+ case lltok::kw_fptoui:
+ case lltok::kw_fptosi:
+ case lltok::kw_inttoptr:
+ case lltok::kw_ptrtoint: {
+ unsigned Opc = Lex.getUIntVal();
+ PATypeHolder DestTy(Type::getVoidTy(Context));
+ Constant *SrcVal;
+ Lex.Lex();
+ if (ParseToken(lltok::lparen, "expected '(' after constantexpr cast") ||
+ ParseGlobalTypeAndValue(SrcVal) ||
+ ParseToken(lltok::kw_to, "expected 'to' in constantexpr cast") ||
+ ParseType(DestTy) ||
+ ParseToken(lltok::rparen, "expected ')' at end of constantexpr cast"))
+ return true;
+ if (!CastInst::castIsValid((Instruction::CastOps)Opc, SrcVal, DestTy))
+ return Error(ID.Loc, "invalid cast opcode for cast from '" +
+ SrcVal->getType()->getDescription() + "' to '" +
+ DestTy->getDescription() + "'");
+ ID.ConstantVal = ConstantExpr::getCast((Instruction::CastOps)Opc,
+ SrcVal, DestTy);
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::kw_extractvalue: {
+ Lex.Lex();
+ Constant *Val;
+ SmallVector<unsigned, 4> Indices;
+ if (ParseToken(lltok::lparen, "expected '(' in extractvalue constantexpr")||
+ ParseGlobalTypeAndValue(Val) ||
+ ParseIndexList(Indices) ||
+ ParseToken(lltok::rparen, "expected ')' in extractvalue constantexpr"))
+ return true;
+
+ if (!isa<StructType>(Val->getType()) && !isa<ArrayType>(Val->getType()))
+ return Error(ID.Loc, "extractvalue operand must be array or struct");
+ if (!ExtractValueInst::getIndexedType(Val->getType(), Indices.begin(),
+ Indices.end()))
+ return Error(ID.Loc, "invalid indices for extractvalue");
+ ID.ConstantVal =
+ ConstantExpr::getExtractValue(Val, Indices.data(), Indices.size());
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::kw_insertvalue: {
+ Lex.Lex();
+ Constant *Val0, *Val1;
+ SmallVector<unsigned, 4> Indices;
+ if (ParseToken(lltok::lparen, "expected '(' in insertvalue constantexpr")||
+ ParseGlobalTypeAndValue(Val0) ||
+ ParseToken(lltok::comma, "expected comma in insertvalue constantexpr")||
+ ParseGlobalTypeAndValue(Val1) ||
+ ParseIndexList(Indices) ||
+ ParseToken(lltok::rparen, "expected ')' in insertvalue constantexpr"))
+ return true;
+ if (!isa<StructType>(Val0->getType()) && !isa<ArrayType>(Val0->getType()))
+ return Error(ID.Loc, "extractvalue operand must be array or struct");
+ if (!ExtractValueInst::getIndexedType(Val0->getType(), Indices.begin(),
+ Indices.end()))
+ return Error(ID.Loc, "invalid indices for insertvalue");
+ ID.ConstantVal = ConstantExpr::getInsertValue(Val0, Val1,
+ Indices.data(), Indices.size());
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ case lltok::kw_icmp:
+ case lltok::kw_fcmp: {
+ unsigned PredVal, Opc = Lex.getUIntVal();
+ Constant *Val0, *Val1;
+ Lex.Lex();
+ if (ParseCmpPredicate(PredVal, Opc) ||
+ ParseToken(lltok::lparen, "expected '(' in compare constantexpr") ||
+ ParseGlobalTypeAndValue(Val0) ||
+ ParseToken(lltok::comma, "expected comma in compare constantexpr") ||
+ ParseGlobalTypeAndValue(Val1) ||
+ ParseToken(lltok::rparen, "expected ')' in compare constantexpr"))
+ return true;
+
+ if (Val0->getType() != Val1->getType())
+ return Error(ID.Loc, "compare operands must have the same type");
+
+ CmpInst::Predicate Pred = (CmpInst::Predicate)PredVal;
+
+ if (Opc == Instruction::FCmp) {
+ if (!Val0->getType()->isFPOrFPVector())
+ return Error(ID.Loc, "fcmp requires floating point operands");
+ ID.ConstantVal = ConstantExpr::getFCmp(Pred, Val0, Val1);
+ } else {
+ assert(Opc == Instruction::ICmp && "Unexpected opcode for CmpInst!");
+ if (!Val0->getType()->isIntOrIntVector() &&
+ !isa<PointerType>(Val0->getType()))
+ return Error(ID.Loc, "icmp requires pointer or integer operands");
+ ID.ConstantVal = ConstantExpr::getICmp(Pred, Val0, Val1);
+ }
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+
+ // Binary Operators.
+ case lltok::kw_add:
+ case lltok::kw_fadd:
+ case lltok::kw_sub:
+ case lltok::kw_fsub:
+ case lltok::kw_mul:
+ case lltok::kw_fmul:
+ case lltok::kw_udiv:
+ case lltok::kw_sdiv:
+ case lltok::kw_fdiv:
+ case lltok::kw_urem:
+ case lltok::kw_srem:
+ case lltok::kw_frem: {
+ bool NUW = false;
+ bool NSW = false;
+ bool Exact = false;
+ unsigned Opc = Lex.getUIntVal();
+ Constant *Val0, *Val1;
+ Lex.Lex();
+ LocTy ModifierLoc = Lex.getLoc();
+ if (Opc == Instruction::Add ||
+ Opc == Instruction::Sub ||
+ Opc == Instruction::Mul) {
+ if (EatIfPresent(lltok::kw_nuw))
+ NUW = true;
+ if (EatIfPresent(lltok::kw_nsw)) {
+ NSW = true;
+ if (EatIfPresent(lltok::kw_nuw))
+ NUW = true;
+ }
+ } else if (Opc == Instruction::SDiv) {
+ if (EatIfPresent(lltok::kw_exact))
+ Exact = true;
+ }
+ if (ParseToken(lltok::lparen, "expected '(' in binary constantexpr") ||
+ ParseGlobalTypeAndValue(Val0) ||
+ ParseToken(lltok::comma, "expected comma in binary constantexpr") ||
+ ParseGlobalTypeAndValue(Val1) ||
+ ParseToken(lltok::rparen, "expected ')' in binary constantexpr"))
+ return true;
+ if (Val0->getType() != Val1->getType())
+ return Error(ID.Loc, "operands of constexpr must have same type");
+ if (!Val0->getType()->isIntOrIntVector()) {
+ if (NUW)
+ return Error(ModifierLoc, "nuw only applies to integer operations");
+ if (NSW)
+ return Error(ModifierLoc, "nsw only applies to integer operations");
+ }
+ // API compatibility: Accept either integer or floating-point types with
+ // add, sub, and mul.
+ if (!Val0->getType()->isIntOrIntVector() &&
+ !Val0->getType()->isFPOrFPVector())
+ return Error(ID.Loc,"constexpr requires integer, fp, or vector operands");
+ unsigned Flags = 0;
+ if (NUW) Flags |= OverflowingBinaryOperator::NoUnsignedWrap;
+ if (NSW) Flags |= OverflowingBinaryOperator::NoSignedWrap;
+ if (Exact) Flags |= SDivOperator::IsExact;
+ Constant *C = ConstantExpr::get(Opc, Val0, Val1, Flags);
+ ID.ConstantVal = C;
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+
+ // Logical Operations
+ case lltok::kw_shl:
+ case lltok::kw_lshr:
+ case lltok::kw_ashr:
+ case lltok::kw_and:
+ case lltok::kw_or:
+ case lltok::kw_xor: {
+ unsigned Opc = Lex.getUIntVal();
+ Constant *Val0, *Val1;
+ Lex.Lex();
+ if (ParseToken(lltok::lparen, "expected '(' in logical constantexpr") ||
+ ParseGlobalTypeAndValue(Val0) ||
+ ParseToken(lltok::comma, "expected comma in logical constantexpr") ||
+ ParseGlobalTypeAndValue(Val1) ||
+ ParseToken(lltok::rparen, "expected ')' in logical constantexpr"))
+ return true;
+ if (Val0->getType() != Val1->getType())
+ return Error(ID.Loc, "operands of constexpr must have same type");
+ if (!Val0->getType()->isIntOrIntVector())
+ return Error(ID.Loc,
+ "constexpr requires integer or integer vector operands");
+ ID.ConstantVal = ConstantExpr::get(Opc, Val0, Val1);
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+
+ case lltok::kw_getelementptr:
+ case lltok::kw_shufflevector:
+ case lltok::kw_insertelement:
+ case lltok::kw_extractelement:
+ case lltok::kw_select: {
+ unsigned Opc = Lex.getUIntVal();
+ SmallVector<Constant*, 16> Elts;
+ bool InBounds = false;
+ Lex.Lex();
+ if (Opc == Instruction::GetElementPtr)
+ InBounds = EatIfPresent(lltok::kw_inbounds);
+ if (ParseToken(lltok::lparen, "expected '(' in constantexpr") ||
+ ParseGlobalValueVector(Elts) ||
+ ParseToken(lltok::rparen, "expected ')' in constantexpr"))
+ return true;
+
+ if (Opc == Instruction::GetElementPtr) {
+ if (Elts.size() == 0 || !isa<PointerType>(Elts[0]->getType()))
+ return Error(ID.Loc, "getelementptr requires pointer operand");
+
+ if (!GetElementPtrInst::getIndexedType(Elts[0]->getType(),
+ (Value**)(Elts.data() + 1),
+ Elts.size() - 1))
+ return Error(ID.Loc, "invalid indices for getelementptr");
+ ID.ConstantVal = InBounds ?
+ ConstantExpr::getInBoundsGetElementPtr(Elts[0],
+ Elts.data() + 1,
+ Elts.size() - 1) :
+ ConstantExpr::getGetElementPtr(Elts[0],
+ Elts.data() + 1, Elts.size() - 1);
+ } else if (Opc == Instruction::Select) {
+ if (Elts.size() != 3)
+ return Error(ID.Loc, "expected three operands to select");
+ if (const char *Reason = SelectInst::areInvalidOperands(Elts[0], Elts[1],
+ Elts[2]))
+ return Error(ID.Loc, Reason);
+ ID.ConstantVal = ConstantExpr::getSelect(Elts[0], Elts[1], Elts[2]);
+ } else if (Opc == Instruction::ShuffleVector) {
+ if (Elts.size() != 3)
+ return Error(ID.Loc, "expected three operands to shufflevector");
+ if (!ShuffleVectorInst::isValidOperands(Elts[0], Elts[1], Elts[2]))
+ return Error(ID.Loc, "invalid operands to shufflevector");
+ ID.ConstantVal =
+ ConstantExpr::getShuffleVector(Elts[0], Elts[1],Elts[2]);
+ } else if (Opc == Instruction::ExtractElement) {
+ if (Elts.size() != 2)
+ return Error(ID.Loc, "expected two operands to extractelement");
+ if (!ExtractElementInst::isValidOperands(Elts[0], Elts[1]))
+ return Error(ID.Loc, "invalid extractelement operands");
+ ID.ConstantVal = ConstantExpr::getExtractElement(Elts[0], Elts[1]);
+ } else {
+ assert(Opc == Instruction::InsertElement && "Unknown opcode");
+ if (Elts.size() != 3)
+ return Error(ID.Loc, "expected three operands to insertelement");
+ if (!InsertElementInst::isValidOperands(Elts[0], Elts[1], Elts[2]))
+ return Error(ID.Loc, "invalid insertelement operands");
+ ID.ConstantVal =
+ ConstantExpr::getInsertElement(Elts[0], Elts[1],Elts[2]);
+ }
+
+ ID.Kind = ValID::t_Constant;
+ return false;
+ }
+ }
+
+ Lex.Lex();
+ return false;
+}
+
+/// ParseGlobalValue - Parse a global value with the specified type.
+bool LLParser::ParseGlobalValue(const Type *Ty, Constant *&C) {
+ C = 0;
+ ValID ID;
+ Value *V = NULL;
+ bool Parsed = ParseValID(ID) ||
+ ConvertValIDToValue(Ty, ID, V, NULL);
+ if (V && !(C = dyn_cast<Constant>(V)))
+ return Error(ID.Loc, "global values must be constants");
+ return Parsed;
+}
+
+bool LLParser::ParseGlobalTypeAndValue(Constant *&V) {
+ PATypeHolder Type(Type::getVoidTy(Context));
+ return ParseType(Type) ||
+ ParseGlobalValue(Type, V);
+}
+
+/// ParseGlobalValueVector
+/// ::= /*empty*/
+/// ::= TypeAndValue (',' TypeAndValue)*
+bool LLParser::ParseGlobalValueVector(SmallVectorImpl<Constant*> &Elts) {
+ // Empty list.
+ if (Lex.getKind() == lltok::rbrace ||
+ Lex.getKind() == lltok::rsquare ||
+ Lex.getKind() == lltok::greater ||
+ Lex.getKind() == lltok::rparen)
+ return false;
+
+ Constant *C;
+ if (ParseGlobalTypeAndValue(C)) return true;
+ Elts.push_back(C);
+
+ while (EatIfPresent(lltok::comma)) {
+ if (ParseGlobalTypeAndValue(C)) return true;
+ Elts.push_back(C);
+ }
+
+ return false;
+}
+
+
+//===----------------------------------------------------------------------===//
+// Function Parsing.
+//===----------------------------------------------------------------------===//
+
+bool LLParser::ConvertValIDToValue(const Type *Ty, ValID &ID, Value *&V,
+ PerFunctionState *PFS) {
+ if (isa<FunctionType>(Ty))
+ return Error(ID.Loc, "functions are not values, refer to them as pointers");
+
+ switch (ID.Kind) {
+ default: llvm_unreachable("Unknown ValID!");
+ case ValID::t_LocalID:
+ if (!PFS) return Error(ID.Loc, "invalid use of function-local name");
+ V = PFS->GetVal(ID.UIntVal, Ty, ID.Loc);
+ return (V == 0);
+ case ValID::t_LocalName:
+ if (!PFS) return Error(ID.Loc, "invalid use of function-local name");
+ V = PFS->GetVal(ID.StrVal, Ty, ID.Loc);
+ return (V == 0);
+ case ValID::t_InlineAsm: {
+ const PointerType *PTy = dyn_cast<PointerType>(Ty);
+ const FunctionType *FTy =
+ PTy ? dyn_cast<FunctionType>(PTy->getElementType()) : 0;
+ if (!FTy || !InlineAsm::Verify(FTy, ID.StrVal2))
+ return Error(ID.Loc, "invalid type for inline asm constraint string");
+ V = InlineAsm::get(FTy, ID.StrVal, ID.StrVal2, ID.UIntVal&1, ID.UIntVal>>1);
+ return false;
+ }
+ case ValID::t_MDNode:
+ if (!Ty->isMetadataTy())
+ return Error(ID.Loc, "metadata value must have metadata type");
+ V = ID.MDNodeVal;
+ return false;
+ case ValID::t_MDString:
+ if (!Ty->isMetadataTy())
+ return Error(ID.Loc, "metadata value must have metadata type");
+ V = ID.MDStringVal;
+ return false;
+ case ValID::t_GlobalName:
+ V = GetGlobalVal(ID.StrVal, Ty, ID.Loc);
+ return V == 0;
+ case ValID::t_GlobalID:
+ V = GetGlobalVal(ID.UIntVal, Ty, ID.Loc);
+ return V == 0;
+ case ValID::t_APSInt:
+ if (!isa<IntegerType>(Ty))
+ return Error(ID.Loc, "integer constant must have integer type");
+ ID.APSIntVal.extOrTrunc(Ty->getPrimitiveSizeInBits());
+ V = ConstantInt::get(Context, ID.APSIntVal);
+ return false;
+ case ValID::t_APFloat:
+ if (!Ty->isFloatingPoint() ||
+ !ConstantFP::isValueValidForType(Ty, ID.APFloatVal))
+ return Error(ID.Loc, "floating point constant invalid for type");
+
+ // The lexer has no type info, so builds all float and double FP constants
+ // as double. Fix this here. Long double does not need this.
+ if (&ID.APFloatVal.getSemantics() == &APFloat::IEEEdouble &&
+ Ty->isFloatTy()) {
+ bool Ignored;
+ ID.APFloatVal.convert(APFloat::IEEEsingle, APFloat::rmNearestTiesToEven,
+ &Ignored);
+ }
+ V = ConstantFP::get(Context, ID.APFloatVal);
+
+ if (V->getType() != Ty)
+ return Error(ID.Loc, "floating point constant does not have type '" +
+ Ty->getDescription() + "'");
+
+ return false;
+ case ValID::t_Null:
+ if (!isa<PointerType>(Ty))
+ return Error(ID.Loc, "null must be a pointer type");
+ V = ConstantPointerNull::get(cast<PointerType>(Ty));
+ return false;
+ case ValID::t_Undef:
+ // FIXME: LabelTy should not be a first-class type.
+ if ((!Ty->isFirstClassType() || Ty->isLabelTy()) &&
+ !isa<OpaqueType>(Ty))
+ return Error(ID.Loc, "invalid type for undef constant");
+ V = UndefValue::get(Ty);
+ return false;
+ case ValID::t_EmptyArray:
+ if (!isa<ArrayType>(Ty) || cast<ArrayType>(Ty)->getNumElements() != 0)
+ return Error(ID.Loc, "invalid empty array initializer");
+ V = UndefValue::get(Ty);
+ return false;
+ case ValID::t_Zero:
+ // FIXME: LabelTy should not be a first-class type.
+ if (!Ty->isFirstClassType() || Ty->isLabelTy())
+ return Error(ID.Loc, "invalid type for null constant");
+ V = Constant::getNullValue(Ty);
+ return false;
+ case ValID::t_Constant:
+ if (ID.ConstantVal->getType() != Ty)
+ return Error(ID.Loc, "constant expression type mismatch");
+ V = ID.ConstantVal;
+ return false;
+ }
+}
+
+bool LLParser::ParseValue(const Type *Ty, Value *&V, PerFunctionState &PFS) {
+ V = 0;
+ ValID ID;
+ return ParseValID(ID, &PFS) ||
+ ConvertValIDToValue(Ty, ID, V, &PFS);
+}
+
+bool LLParser::ParseTypeAndValue(Value *&V, PerFunctionState &PFS) {
+ PATypeHolder T(Type::getVoidTy(Context));
+ return ParseType(T) ||
+ ParseValue(T, V, PFS);
+}
+
+bool LLParser::ParseTypeAndBasicBlock(BasicBlock *&BB, LocTy &Loc,
+ PerFunctionState &PFS) {
+ Value *V;
+ Loc = Lex.getLoc();
+ if (ParseTypeAndValue(V, PFS)) return true;
+ if (!isa<BasicBlock>(V))
+ return Error(Loc, "expected a basic block");
+ BB = cast<BasicBlock>(V);
+ return false;
+}
+
+
+/// FunctionHeader
+/// ::= OptionalLinkage OptionalVisibility OptionalCallingConv OptRetAttrs
+/// Type GlobalName '(' ArgList ')' OptFuncAttrs OptSection
+/// OptionalAlign OptGC
+bool LLParser::ParseFunctionHeader(Function *&Fn, bool isDefine) {
+ // Parse the linkage.
+ LocTy LinkageLoc = Lex.getLoc();
+ unsigned Linkage;
+
+ unsigned Visibility, RetAttrs;
+ CallingConv::ID CC;
+ PATypeHolder RetType(Type::getVoidTy(Context));
+ LocTy RetTypeLoc = Lex.getLoc();
+ if (ParseOptionalLinkage(Linkage) ||
+ ParseOptionalVisibility(Visibility) ||
+ ParseOptionalCallingConv(CC) ||
+ ParseOptionalAttrs(RetAttrs, 1) ||
+ ParseType(RetType, RetTypeLoc, true /*void allowed*/))
+ return true;
+
+ // Verify that the linkage is ok.
+ switch ((GlobalValue::LinkageTypes)Linkage) {
+ case GlobalValue::ExternalLinkage:
+ break; // always ok.
+ case GlobalValue::DLLImportLinkage:
+ case GlobalValue::ExternalWeakLinkage:
+ if (isDefine)
+ return Error(LinkageLoc, "invalid linkage for function definition");
+ break;
+ case GlobalValue::PrivateLinkage:
+ case GlobalValue::LinkerPrivateLinkage:
+ case GlobalValue::InternalLinkage:
+ case GlobalValue::AvailableExternallyLinkage:
+ case GlobalValue::LinkOnceAnyLinkage:
+ case GlobalValue::LinkOnceODRLinkage:
+ case GlobalValue::WeakAnyLinkage:
+ case GlobalValue::WeakODRLinkage:
+ case GlobalValue::DLLExportLinkage:
+ if (!isDefine)
+ return Error(LinkageLoc, "invalid linkage for function declaration");
+ break;
+ case GlobalValue::AppendingLinkage:
+ case GlobalValue::CommonLinkage:
+ return Error(LinkageLoc, "invalid function linkage type");
+ }
+
+ if (!FunctionType::isValidReturnType(RetType) ||
+ isa<OpaqueType>(RetType))
+ return Error(RetTypeLoc, "invalid function return type");
+
+ LocTy NameLoc = Lex.getLoc();
+
+ std::string FunctionName;
+ if (Lex.getKind() == lltok::GlobalVar) {
+ FunctionName = Lex.getStrVal();
+ } else if (Lex.getKind() == lltok::GlobalID) { // @42 is ok.
+ unsigned NameID = Lex.getUIntVal();
+
+ if (NameID != NumberedVals.size())
+ return TokError("function expected to be numbered '%" +
+ utostr(NumberedVals.size()) + "'");
+ } else {
+ return TokError("expected function name");
+ }
+
+ Lex.Lex();
+
+ if (Lex.getKind() != lltok::lparen)
+ return TokError("expected '(' in function argument list");
+
+ std::vector<ArgInfo> ArgList;
+ bool isVarArg;
+ unsigned FuncAttrs;
+ std::string Section;
+ unsigned Alignment;
+ std::string GC;
+
+ if (ParseArgumentList(ArgList, isVarArg, false) ||
+ ParseOptionalAttrs(FuncAttrs, 2) ||
+ (EatIfPresent(lltok::kw_section) &&
+ ParseStringConstant(Section)) ||
+ ParseOptionalAlignment(Alignment) ||
+ (EatIfPresent(lltok::kw_gc) &&
+ ParseStringConstant(GC)))
+ return true;
+
+ // If the alignment was parsed as an attribute, move to the alignment field.
+ if (FuncAttrs & Attribute::Alignment) {
+ Alignment = Attribute::getAlignmentFromAttrs(FuncAttrs);
+ FuncAttrs &= ~Attribute::Alignment;
+ }
+
+ // Okay, if we got here, the function is syntactically valid. Convert types
+ // and do semantic checks.
+ std::vector<const Type*> ParamTypeList;
+ SmallVector<AttributeWithIndex, 8> Attrs;
+ // FIXME : In 3.0, stop accepting zext, sext and inreg as optional function
+ // attributes.
+ unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
+ if (FuncAttrs & ObsoleteFuncAttrs) {
+ RetAttrs |= FuncAttrs & ObsoleteFuncAttrs;
+ FuncAttrs &= ~ObsoleteFuncAttrs;
+ }
+
+ if (RetAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
+
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
+ ParamTypeList.push_back(ArgList[i].Type);
+ if (ArgList[i].Attrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
+ }
+
+ if (FuncAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(~0, FuncAttrs));
+
+ AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
+
+ if (PAL.paramHasAttr(1, Attribute::StructRet) && !RetType->isVoidTy())
+ return Error(RetTypeLoc, "functions with 'sret' argument must return void");
+
+ const FunctionType *FT =
+ FunctionType::get(RetType, ParamTypeList, isVarArg);
+ const PointerType *PFT = PointerType::getUnqual(FT);
+
+ Fn = 0;
+ if (!FunctionName.empty()) {
+ // If this was a definition of a forward reference, remove the definition
+ // from the forward reference table and fill in the forward ref.
+ std::map<std::string, std::pair<GlobalValue*, LocTy> >::iterator FRVI =
+ ForwardRefVals.find(FunctionName);
+ if (FRVI != ForwardRefVals.end()) {
+ Fn = M->getFunction(FunctionName);
+ ForwardRefVals.erase(FRVI);
+ } else if ((Fn = M->getFunction(FunctionName))) {
+ // If this function already exists in the symbol table, then it is
+ // multiply defined. We accept a few cases for old backwards compat.
+ // FIXME: Remove this stuff for LLVM 3.0.
+ if (Fn->getType() != PFT || Fn->getAttributes() != PAL ||
+ (!Fn->isDeclaration() && isDefine)) {
+ // If the redefinition has different type or different attributes,
+ // reject it. If both have bodies, reject it.
+ return Error(NameLoc, "invalid redefinition of function '" +
+ FunctionName + "'");
+ } else if (Fn->isDeclaration()) {
+ // Make sure to strip off any argument names so we can't get conflicts.
+ for (Function::arg_iterator AI = Fn->arg_begin(), AE = Fn->arg_end();
+ AI != AE; ++AI)
+ AI->setName("");
+ }
+ } else if (M->getNamedValue(FunctionName)) {
+ return Error(NameLoc, "redefinition of function '@" + FunctionName + "'");
+ }
+
+ } else {
+ // If this is a definition of a forward referenced function, make sure the
+ // types agree.
+ std::map<unsigned, std::pair<GlobalValue*, LocTy> >::iterator I
+ = ForwardRefValIDs.find(NumberedVals.size());
+ if (I != ForwardRefValIDs.end()) {
+ Fn = cast<Function>(I->second.first);
+ if (Fn->getType() != PFT)
+ return Error(NameLoc, "type of definition and forward reference of '@" +
+ utostr(NumberedVals.size()) +"' disagree");
+ ForwardRefValIDs.erase(I);
+ }
+ }
+
+ if (Fn == 0)
+ Fn = Function::Create(FT, GlobalValue::ExternalLinkage, FunctionName, M);
+ else // Move the forward-reference to the correct spot in the module.
+ M->getFunctionList().splice(M->end(), M->getFunctionList(), Fn);
+
+ if (FunctionName.empty())
+ NumberedVals.push_back(Fn);
+
+ Fn->setLinkage((GlobalValue::LinkageTypes)Linkage);
+ Fn->setVisibility((GlobalValue::VisibilityTypes)Visibility);
+ Fn->setCallingConv(CC);
+ Fn->setAttributes(PAL);
+ Fn->setAlignment(Alignment);
+ Fn->setSection(Section);
+ if (!GC.empty()) Fn->setGC(GC.c_str());
+
+ // Add all of the arguments we parsed to the function.
+ Function::arg_iterator ArgIt = Fn->arg_begin();
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i, ++ArgIt) {
+ // If we run out of arguments in the Function prototype, exit early.
+ // FIXME: REMOVE THIS IN LLVM 3.0, this is just for the mismatch case above.
+ if (ArgIt == Fn->arg_end()) break;
+
+ // If the argument has a name, insert it into the argument symbol table.
+ if (ArgList[i].Name.empty()) continue;
+
+ // Set the name, if it conflicted, it will be auto-renamed.
+ ArgIt->setName(ArgList[i].Name);
+
+ if (ArgIt->getNameStr() != ArgList[i].Name)
+ return Error(ArgList[i].Loc, "redefinition of argument '%" +
+ ArgList[i].Name + "'");
+ }
+
+ return false;
+}
+
+
+/// ParseFunctionBody
+/// ::= '{' BasicBlock+ '}'
+/// ::= 'begin' BasicBlock+ 'end' // FIXME: remove in LLVM 3.0
+///
+bool LLParser::ParseFunctionBody(Function &Fn) {
+ if (Lex.getKind() != lltok::lbrace && Lex.getKind() != lltok::kw_begin)
+ return TokError("expected '{' in function body");
+ Lex.Lex(); // eat the {.
+
+ int FunctionNumber = -1;
+ if (!Fn.hasName()) FunctionNumber = NumberedVals.size()-1;
+
+ PerFunctionState PFS(*this, Fn, FunctionNumber);
+
+ // We need at least one basic block.
+ if (Lex.getKind() == lltok::rbrace || Lex.getKind() == lltok::kw_end)
+ return TokError("function body requires at least one basic block");
+
+ while (Lex.getKind() != lltok::rbrace && Lex.getKind() != lltok::kw_end)
+ if (ParseBasicBlock(PFS)) return true;
+
+ // Eat the }.
+ Lex.Lex();
+
+ // Verify function is ok.
+ return PFS.FinishFunction();
+}
+
+/// ParseBasicBlock
+/// ::= LabelStr? Instruction*
+bool LLParser::ParseBasicBlock(PerFunctionState &PFS) {
+ // If this basic block starts out with a name, remember it.
+ std::string Name;
+ LocTy NameLoc = Lex.getLoc();
+ if (Lex.getKind() == lltok::LabelStr) {
+ Name = Lex.getStrVal();
+ Lex.Lex();
+ }
+
+ BasicBlock *BB = PFS.DefineBB(Name, NameLoc);
+ if (BB == 0) return true;
+
+ std::string NameStr;
+
+ // Parse the instructions in this block until we get a terminator.
+ Instruction *Inst;
+ SmallVector<std::pair<unsigned, MDNode *>, 4> MetadataOnInst;
+ do {
+ // This instruction may have three possibilities for a name: a) none
+ // specified, b) name specified "%foo =", c) number specified: "%4 =".
+ LocTy NameLoc = Lex.getLoc();
+ int NameID = -1;
+ NameStr = "";
+
+ if (Lex.getKind() == lltok::LocalVarID) {
+ NameID = Lex.getUIntVal();
+ Lex.Lex();
+ if (ParseToken(lltok::equal, "expected '=' after instruction id"))
+ return true;
+ } else if (Lex.getKind() == lltok::LocalVar ||
+ // FIXME: REMOVE IN LLVM 3.0
+ Lex.getKind() == lltok::StringConstant) {
+ NameStr = Lex.getStrVal();
+ Lex.Lex();
+ if (ParseToken(lltok::equal, "expected '=' after instruction name"))
+ return true;
+ }
+
+ switch (ParseInstruction(Inst, BB, PFS)) {
+ default: assert(0 && "Unknown ParseInstruction result!");
+ case InstError: return true;
+ case InstNormal:
+ // With a normal result, we check to see if the instruction is followed by
+ // a comma and metadata.
+ if (EatIfPresent(lltok::comma))
+ if (ParseInstructionMetadata(MetadataOnInst))
+ return true;
+ break;
+ case InstExtraComma:
+ // If the instruction parser ate an extra comma at the end of it, it
+ // *must* be followed by metadata.
+ if (ParseInstructionMetadata(MetadataOnInst))
+ return true;
+ break;
+ }
+
+ // Set metadata attached with this instruction.
+ for (unsigned i = 0, e = MetadataOnInst.size(); i != e; ++i)
+ Inst->setMetadata(MetadataOnInst[i].first, MetadataOnInst[i].second);
+ MetadataOnInst.clear();
+
+ BB->getInstList().push_back(Inst);
+
+ // Set the name on the instruction.
+ if (PFS.SetInstName(NameID, NameStr, NameLoc, Inst)) return true;
+ } while (!isa<TerminatorInst>(Inst));
+
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Instruction Parsing.
+//===----------------------------------------------------------------------===//
+
+/// ParseInstruction - Parse one of the many different instructions.
+///
+int LLParser::ParseInstruction(Instruction *&Inst, BasicBlock *BB,
+ PerFunctionState &PFS) {
+ lltok::Kind Token = Lex.getKind();
+ if (Token == lltok::Eof)
+ return TokError("found end of file when expecting more instructions");
+ LocTy Loc = Lex.getLoc();
+ unsigned KeywordVal = Lex.getUIntVal();
+ Lex.Lex(); // Eat the keyword.
+
+ switch (Token) {
+ default: return Error(Loc, "expected instruction opcode");
+ // Terminator Instructions.
+ case lltok::kw_unwind: Inst = new UnwindInst(Context); return false;
+ case lltok::kw_unreachable: Inst = new UnreachableInst(Context); return false;
+ case lltok::kw_ret: return ParseRet(Inst, BB, PFS);
+ case lltok::kw_br: return ParseBr(Inst, PFS);
+ case lltok::kw_switch: return ParseSwitch(Inst, PFS);
+ case lltok::kw_indirectbr: return ParseIndirectBr(Inst, PFS);
+ case lltok::kw_invoke: return ParseInvoke(Inst, PFS);
+ // Binary Operators.
+ case lltok::kw_add:
+ case lltok::kw_sub:
+ case lltok::kw_mul: {
+ bool NUW = false;
+ bool NSW = false;
+ LocTy ModifierLoc = Lex.getLoc();
+ if (EatIfPresent(lltok::kw_nuw))
+ NUW = true;
+ if (EatIfPresent(lltok::kw_nsw)) {
+ NSW = true;
+ if (EatIfPresent(lltok::kw_nuw))
+ NUW = true;
+ }
+ // API compatibility: Accept either integer or floating-point types.
+ bool Result = ParseArithmetic(Inst, PFS, KeywordVal, 0);
+ if (!Result) {
+ if (!Inst->getType()->isIntOrIntVector()) {
+ if (NUW)
+ return Error(ModifierLoc, "nuw only applies to integer operations");
+ if (NSW)
+ return Error(ModifierLoc, "nsw only applies to integer operations");
+ }
+ if (NUW)
+ cast<BinaryOperator>(Inst)->setHasNoUnsignedWrap(true);
+ if (NSW)
+ cast<BinaryOperator>(Inst)->setHasNoSignedWrap(true);
+ }
+ return Result;
+ }
+ case lltok::kw_fadd:
+ case lltok::kw_fsub:
+ case lltok::kw_fmul: return ParseArithmetic(Inst, PFS, KeywordVal, 2);
+
+ case lltok::kw_sdiv: {
+ bool Exact = false;
+ if (EatIfPresent(lltok::kw_exact))
+ Exact = true;
+ bool Result = ParseArithmetic(Inst, PFS, KeywordVal, 1);
+ if (!Result)
+ if (Exact)
+ cast<BinaryOperator>(Inst)->setIsExact(true);
+ return Result;
+ }
+
+ case lltok::kw_udiv:
+ case lltok::kw_urem:
+ case lltok::kw_srem: return ParseArithmetic(Inst, PFS, KeywordVal, 1);
+ case lltok::kw_fdiv:
+ case lltok::kw_frem: return ParseArithmetic(Inst, PFS, KeywordVal, 2);
+ case lltok::kw_shl:
+ case lltok::kw_lshr:
+ case lltok::kw_ashr:
+ case lltok::kw_and:
+ case lltok::kw_or:
+ case lltok::kw_xor: return ParseLogical(Inst, PFS, KeywordVal);
+ case lltok::kw_icmp:
+ case lltok::kw_fcmp: return ParseCompare(Inst, PFS, KeywordVal);
+ // Casts.
+ case lltok::kw_trunc:
+ case lltok::kw_zext:
+ case lltok::kw_sext:
+ case lltok::kw_fptrunc:
+ case lltok::kw_fpext:
+ case lltok::kw_bitcast:
+ case lltok::kw_uitofp:
+ case lltok::kw_sitofp:
+ case lltok::kw_fptoui:
+ case lltok::kw_fptosi:
+ case lltok::kw_inttoptr:
+ case lltok::kw_ptrtoint: return ParseCast(Inst, PFS, KeywordVal);
+ // Other.
+ case lltok::kw_select: return ParseSelect(Inst, PFS);
+ case lltok::kw_va_arg: return ParseVA_Arg(Inst, PFS);
+ case lltok::kw_extractelement: return ParseExtractElement(Inst, PFS);
+ case lltok::kw_insertelement: return ParseInsertElement(Inst, PFS);
+ case lltok::kw_shufflevector: return ParseShuffleVector(Inst, PFS);
+ case lltok::kw_phi: return ParsePHI(Inst, PFS);
+ case lltok::kw_call: return ParseCall(Inst, PFS, false);
+ case lltok::kw_tail: return ParseCall(Inst, PFS, true);
+ // Memory.
+ case lltok::kw_alloca: return ParseAlloc(Inst, PFS);
+ case lltok::kw_malloc: return ParseAlloc(Inst, PFS, BB, false);
+ case lltok::kw_free: return ParseFree(Inst, PFS, BB);
+ case lltok::kw_load: return ParseLoad(Inst, PFS, false);
+ case lltok::kw_store: return ParseStore(Inst, PFS, false);
+ case lltok::kw_volatile:
+ if (EatIfPresent(lltok::kw_load))
+ return ParseLoad(Inst, PFS, true);
+ else if (EatIfPresent(lltok::kw_store))
+ return ParseStore(Inst, PFS, true);
+ else
+ return TokError("expected 'load' or 'store'");
+ case lltok::kw_getresult: return ParseGetResult(Inst, PFS);
+ case lltok::kw_getelementptr: return ParseGetElementPtr(Inst, PFS);
+ case lltok::kw_extractvalue: return ParseExtractValue(Inst, PFS);
+ case lltok::kw_insertvalue: return ParseInsertValue(Inst, PFS);
+ }
+}
+
+/// ParseCmpPredicate - Parse an integer or fp predicate, based on Kind.
+bool LLParser::ParseCmpPredicate(unsigned &P, unsigned Opc) {
+ if (Opc == Instruction::FCmp) {
+ switch (Lex.getKind()) {
+ default: TokError("expected fcmp predicate (e.g. 'oeq')");
+ case lltok::kw_oeq: P = CmpInst::FCMP_OEQ; break;
+ case lltok::kw_one: P = CmpInst::FCMP_ONE; break;
+ case lltok::kw_olt: P = CmpInst::FCMP_OLT; break;
+ case lltok::kw_ogt: P = CmpInst::FCMP_OGT; break;
+ case lltok::kw_ole: P = CmpInst::FCMP_OLE; break;
+ case lltok::kw_oge: P = CmpInst::FCMP_OGE; break;
+ case lltok::kw_ord: P = CmpInst::FCMP_ORD; break;
+ case lltok::kw_uno: P = CmpInst::FCMP_UNO; break;
+ case lltok::kw_ueq: P = CmpInst::FCMP_UEQ; break;
+ case lltok::kw_une: P = CmpInst::FCMP_UNE; break;
+ case lltok::kw_ult: P = CmpInst::FCMP_ULT; break;
+ case lltok::kw_ugt: P = CmpInst::FCMP_UGT; break;
+ case lltok::kw_ule: P = CmpInst::FCMP_ULE; break;
+ case lltok::kw_uge: P = CmpInst::FCMP_UGE; break;
+ case lltok::kw_true: P = CmpInst::FCMP_TRUE; break;
+ case lltok::kw_false: P = CmpInst::FCMP_FALSE; break;
+ }
+ } else {
+ switch (Lex.getKind()) {
+ default: TokError("expected icmp predicate (e.g. 'eq')");
+ case lltok::kw_eq: P = CmpInst::ICMP_EQ; break;
+ case lltok::kw_ne: P = CmpInst::ICMP_NE; break;
+ case lltok::kw_slt: P = CmpInst::ICMP_SLT; break;
+ case lltok::kw_sgt: P = CmpInst::ICMP_SGT; break;
+ case lltok::kw_sle: P = CmpInst::ICMP_SLE; break;
+ case lltok::kw_sge: P = CmpInst::ICMP_SGE; break;
+ case lltok::kw_ult: P = CmpInst::ICMP_ULT; break;
+ case lltok::kw_ugt: P = CmpInst::ICMP_UGT; break;
+ case lltok::kw_ule: P = CmpInst::ICMP_ULE; break;
+ case lltok::kw_uge: P = CmpInst::ICMP_UGE; break;
+ }
+ }
+ Lex.Lex();
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Terminator Instructions.
+//===----------------------------------------------------------------------===//
+
+/// ParseRet - Parse a return instruction.
+/// ::= 'ret' void (',' !dbg, !1)*
+/// ::= 'ret' TypeAndValue (',' !dbg, !1)*
+/// ::= 'ret' TypeAndValue (',' TypeAndValue)+ (',' !dbg, !1)*
+/// [[obsolete: LLVM 3.0]]
+int LLParser::ParseRet(Instruction *&Inst, BasicBlock *BB,
+ PerFunctionState &PFS) {
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ if (ParseType(Ty, true /*void allowed*/)) return true;
+
+ if (Ty->isVoidTy()) {
+ Inst = ReturnInst::Create(Context);
+ return false;
+ }
+
+ Value *RV;
+ if (ParseValue(Ty, RV, PFS)) return true;
+
+ bool ExtraComma = false;
+ if (EatIfPresent(lltok::comma)) {
+ // Parse optional custom metadata, e.g. !dbg
+ if (Lex.getKind() == lltok::MetadataVar) {
+ ExtraComma = true;
+ } else {
+ // The normal case is one return value.
+ // FIXME: LLVM 3.0 remove MRV support for 'ret i32 1, i32 2', requiring
+ // use of 'ret {i32,i32} {i32 1, i32 2}'
+ SmallVector<Value*, 8> RVs;
+ RVs.push_back(RV);
+
+ do {
+ // If optional custom metadata, e.g. !dbg is seen then this is the
+ // end of MRV.
+ if (Lex.getKind() == lltok::MetadataVar)
+ break;
+ if (ParseTypeAndValue(RV, PFS)) return true;
+ RVs.push_back(RV);
+ } while (EatIfPresent(lltok::comma));
+
+ RV = UndefValue::get(PFS.getFunction().getReturnType());
+ for (unsigned i = 0, e = RVs.size(); i != e; ++i) {
+ Instruction *I = InsertValueInst::Create(RV, RVs[i], i, "mrv");
+ BB->getInstList().push_back(I);
+ RV = I;
+ }
+ }
+ }
+
+ Inst = ReturnInst::Create(Context, RV);
+ return ExtraComma ? InstExtraComma : InstNormal;
+}
+
+
+/// ParseBr
+/// ::= 'br' TypeAndValue
+/// ::= 'br' TypeAndValue ',' TypeAndValue ',' TypeAndValue
+bool LLParser::ParseBr(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy Loc, Loc2;
+ Value *Op0;
+ BasicBlock *Op1, *Op2;
+ if (ParseTypeAndValue(Op0, Loc, PFS)) return true;
+
+ if (BasicBlock *BB = dyn_cast<BasicBlock>(Op0)) {
+ Inst = BranchInst::Create(BB);
+ return false;
+ }
+
+ if (Op0->getType() != Type::getInt1Ty(Context))
+ return Error(Loc, "branch condition must have 'i1' type");
+
+ if (ParseToken(lltok::comma, "expected ',' after branch condition") ||
+ ParseTypeAndBasicBlock(Op1, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after true destination") ||
+ ParseTypeAndBasicBlock(Op2, Loc2, PFS))
+ return true;
+
+ Inst = BranchInst::Create(Op1, Op2, Op0);
+ return false;
+}
+
+/// ParseSwitch
+/// Instruction
+/// ::= 'switch' TypeAndValue ',' TypeAndValue '[' JumpTable ']'
+/// JumpTable
+/// ::= (TypeAndValue ',' TypeAndValue)*
+bool LLParser::ParseSwitch(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy CondLoc, BBLoc;
+ Value *Cond;
+ BasicBlock *DefaultBB;
+ if (ParseTypeAndValue(Cond, CondLoc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after switch condition") ||
+ ParseTypeAndBasicBlock(DefaultBB, BBLoc, PFS) ||
+ ParseToken(lltok::lsquare, "expected '[' with switch table"))
+ return true;
+
+ if (!isa<IntegerType>(Cond->getType()))
+ return Error(CondLoc, "switch condition must have integer type");
+
+ // Parse the jump table pairs.
+ SmallPtrSet<Value*, 32> SeenCases;
+ SmallVector<std::pair<ConstantInt*, BasicBlock*>, 32> Table;
+ while (Lex.getKind() != lltok::rsquare) {
+ Value *Constant;
+ BasicBlock *DestBB;
+
+ if (ParseTypeAndValue(Constant, CondLoc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after case value") ||
+ ParseTypeAndBasicBlock(DestBB, PFS))
+ return true;
+
+ if (!SeenCases.insert(Constant))
+ return Error(CondLoc, "duplicate case value in switch");
+ if (!isa<ConstantInt>(Constant))
+ return Error(CondLoc, "case value is not a constant integer");
+
+ Table.push_back(std::make_pair(cast<ConstantInt>(Constant), DestBB));
+ }
+
+ Lex.Lex(); // Eat the ']'.
+
+ SwitchInst *SI = SwitchInst::Create(Cond, DefaultBB, Table.size());
+ for (unsigned i = 0, e = Table.size(); i != e; ++i)
+ SI->addCase(Table[i].first, Table[i].second);
+ Inst = SI;
+ return false;
+}
+
+/// ParseIndirectBr
+/// Instruction
+/// ::= 'indirectbr' TypeAndValue ',' '[' LabelList ']'
+bool LLParser::ParseIndirectBr(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy AddrLoc;
+ Value *Address;
+ if (ParseTypeAndValue(Address, AddrLoc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after indirectbr address") ||
+ ParseToken(lltok::lsquare, "expected '[' with indirectbr"))
+ return true;
+
+ if (!isa<PointerType>(Address->getType()))
+ return Error(AddrLoc, "indirectbr address must have pointer type");
+
+ // Parse the destination list.
+ SmallVector<BasicBlock*, 16> DestList;
+
+ if (Lex.getKind() != lltok::rsquare) {
+ BasicBlock *DestBB;
+ if (ParseTypeAndBasicBlock(DestBB, PFS))
+ return true;
+ DestList.push_back(DestBB);
+
+ while (EatIfPresent(lltok::comma)) {
+ if (ParseTypeAndBasicBlock(DestBB, PFS))
+ return true;
+ DestList.push_back(DestBB);
+ }
+ }
+
+ if (ParseToken(lltok::rsquare, "expected ']' at end of block list"))
+ return true;
+
+ IndirectBrInst *IBI = IndirectBrInst::Create(Address, DestList.size());
+ for (unsigned i = 0, e = DestList.size(); i != e; ++i)
+ IBI->addDestination(DestList[i]);
+ Inst = IBI;
+ return false;
+}
+
+
+/// ParseInvoke
+/// ::= 'invoke' OptionalCallingConv OptionalAttrs Type Value ParamList
+/// OptionalAttrs 'to' TypeAndValue 'unwind' TypeAndValue
+bool LLParser::ParseInvoke(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy CallLoc = Lex.getLoc();
+ unsigned RetAttrs, FnAttrs;
+ CallingConv::ID CC;
+ PATypeHolder RetType(Type::getVoidTy(Context));
+ LocTy RetTypeLoc;
+ ValID CalleeID;
+ SmallVector<ParamInfo, 16> ArgList;
+
+ BasicBlock *NormalBB, *UnwindBB;
+ if (ParseOptionalCallingConv(CC) ||
+ ParseOptionalAttrs(RetAttrs, 1) ||
+ ParseType(RetType, RetTypeLoc, true /*void allowed*/) ||
+ ParseValID(CalleeID) ||
+ ParseParameterList(ArgList, PFS) ||
+ ParseOptionalAttrs(FnAttrs, 2) ||
+ ParseToken(lltok::kw_to, "expected 'to' in invoke") ||
+ ParseTypeAndBasicBlock(NormalBB, PFS) ||
+ ParseToken(lltok::kw_unwind, "expected 'unwind' in invoke") ||
+ ParseTypeAndBasicBlock(UnwindBB, PFS))
+ return true;
+
+ // If RetType is a non-function pointer type, then this is the short syntax
+ // for the call, which means that RetType is just the return type. Infer the
+ // rest of the function argument types from the arguments that are present.
+ const PointerType *PFTy = 0;
+ const FunctionType *Ty = 0;
+ if (!(PFTy = dyn_cast<PointerType>(RetType)) ||
+ !(Ty = dyn_cast<FunctionType>(PFTy->getElementType()))) {
+ // Pull out the types of all of the arguments...
+ std::vector<const Type*> ParamTypes;
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
+ ParamTypes.push_back(ArgList[i].V->getType());
+
+ if (!FunctionType::isValidReturnType(RetType))
+ return Error(RetTypeLoc, "Invalid result type for LLVM function");
+
+ Ty = FunctionType::get(RetType, ParamTypes, false);
+ PFTy = PointerType::getUnqual(Ty);
+ }
+
+ // Look up the callee.
+ Value *Callee;
+ if (ConvertValIDToValue(PFTy, CalleeID, Callee, &PFS)) return true;
+
+ // FIXME: In LLVM 3.0, stop accepting zext, sext and inreg as optional
+ // function attributes.
+ unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
+ if (FnAttrs & ObsoleteFuncAttrs) {
+ RetAttrs |= FnAttrs & ObsoleteFuncAttrs;
+ FnAttrs &= ~ObsoleteFuncAttrs;
+ }
+
+ // Set up the Attributes for the function.
+ SmallVector<AttributeWithIndex, 8> Attrs;
+ if (RetAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
+
+ SmallVector<Value*, 8> Args;
+
+ // Loop through FunctionType's arguments and ensure they are specified
+ // correctly. Also, gather any parameter attributes.
+ FunctionType::param_iterator I = Ty->param_begin();
+ FunctionType::param_iterator E = Ty->param_end();
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
+ const Type *ExpectedTy = 0;
+ if (I != E) {
+ ExpectedTy = *I++;
+ } else if (!Ty->isVarArg()) {
+ return Error(ArgList[i].Loc, "too many arguments specified");
+ }
+
+ if (ExpectedTy && ExpectedTy != ArgList[i].V->getType())
+ return Error(ArgList[i].Loc, "argument is not of expected type '" +
+ ExpectedTy->getDescription() + "'");
+ Args.push_back(ArgList[i].V);
+ if (ArgList[i].Attrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
+ }
+
+ if (I != E)
+ return Error(CallLoc, "not enough parameters specified for call");
+
+ if (FnAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(~0, FnAttrs));
+
+ // Finish off the Attributes and check them
+ AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
+
+ InvokeInst *II = InvokeInst::Create(Callee, NormalBB, UnwindBB,
+ Args.begin(), Args.end());
+ II->setCallingConv(CC);
+ II->setAttributes(PAL);
+ Inst = II;
+ return false;
+}
+
+
+
+//===----------------------------------------------------------------------===//
+// Binary Operators.
+//===----------------------------------------------------------------------===//
+
+/// ParseArithmetic
+/// ::= ArithmeticOps TypeAndValue ',' Value
+///
+/// If OperandType is 0, then any FP or integer operand is allowed. If it is 1,
+/// then any integer operand is allowed, if it is 2, any fp operand is allowed.
+bool LLParser::ParseArithmetic(Instruction *&Inst, PerFunctionState &PFS,
+ unsigned Opc, unsigned OperandType) {
+ LocTy Loc; Value *LHS, *RHS;
+ if (ParseTypeAndValue(LHS, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' in arithmetic operation") ||
+ ParseValue(LHS->getType(), RHS, PFS))
+ return true;
+
+ bool Valid;
+ switch (OperandType) {
+ default: llvm_unreachable("Unknown operand type!");
+ case 0: // int or FP.
+ Valid = LHS->getType()->isIntOrIntVector() ||
+ LHS->getType()->isFPOrFPVector();
+ break;
+ case 1: Valid = LHS->getType()->isIntOrIntVector(); break;
+ case 2: Valid = LHS->getType()->isFPOrFPVector(); break;
+ }
+
+ if (!Valid)
+ return Error(Loc, "invalid operand type for instruction");
+
+ Inst = BinaryOperator::Create((Instruction::BinaryOps)Opc, LHS, RHS);
+ return false;
+}
+
+/// ParseLogical
+/// ::= ArithmeticOps TypeAndValue ',' Value {
+bool LLParser::ParseLogical(Instruction *&Inst, PerFunctionState &PFS,
+ unsigned Opc) {
+ LocTy Loc; Value *LHS, *RHS;
+ if (ParseTypeAndValue(LHS, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' in logical operation") ||
+ ParseValue(LHS->getType(), RHS, PFS))
+ return true;
+
+ if (!LHS->getType()->isIntOrIntVector())
+ return Error(Loc,"instruction requires integer or integer vector operands");
+
+ Inst = BinaryOperator::Create((Instruction::BinaryOps)Opc, LHS, RHS);
+ return false;
+}
+
+
+/// ParseCompare
+/// ::= 'icmp' IPredicates TypeAndValue ',' Value
+/// ::= 'fcmp' FPredicates TypeAndValue ',' Value
+bool LLParser::ParseCompare(Instruction *&Inst, PerFunctionState &PFS,
+ unsigned Opc) {
+ // Parse the integer/fp comparison predicate.
+ LocTy Loc;
+ unsigned Pred;
+ Value *LHS, *RHS;
+ if (ParseCmpPredicate(Pred, Opc) ||
+ ParseTypeAndValue(LHS, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after compare value") ||
+ ParseValue(LHS->getType(), RHS, PFS))
+ return true;
+
+ if (Opc == Instruction::FCmp) {
+ if (!LHS->getType()->isFPOrFPVector())
+ return Error(Loc, "fcmp requires floating point operands");
+ Inst = new FCmpInst(CmpInst::Predicate(Pred), LHS, RHS);
+ } else {
+ assert(Opc == Instruction::ICmp && "Unknown opcode for CmpInst!");
+ if (!LHS->getType()->isIntOrIntVector() &&
+ !isa<PointerType>(LHS->getType()))
+ return Error(Loc, "icmp requires integer operands");
+ Inst = new ICmpInst(CmpInst::Predicate(Pred), LHS, RHS);
+ }
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Other Instructions.
+//===----------------------------------------------------------------------===//
+
+
+/// ParseCast
+/// ::= CastOpc TypeAndValue 'to' Type
+bool LLParser::ParseCast(Instruction *&Inst, PerFunctionState &PFS,
+ unsigned Opc) {
+ LocTy Loc; Value *Op;
+ PATypeHolder DestTy(Type::getVoidTy(Context));
+ if (ParseTypeAndValue(Op, Loc, PFS) ||
+ ParseToken(lltok::kw_to, "expected 'to' after cast value") ||
+ ParseType(DestTy))
+ return true;
+
+ if (!CastInst::castIsValid((Instruction::CastOps)Opc, Op, DestTy)) {
+ CastInst::castIsValid((Instruction::CastOps)Opc, Op, DestTy);
+ return Error(Loc, "invalid cast opcode for cast from '" +
+ Op->getType()->getDescription() + "' to '" +
+ DestTy->getDescription() + "'");
+ }
+ Inst = CastInst::Create((Instruction::CastOps)Opc, Op, DestTy);
+ return false;
+}
+
+/// ParseSelect
+/// ::= 'select' TypeAndValue ',' TypeAndValue ',' TypeAndValue
+bool LLParser::ParseSelect(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy Loc;
+ Value *Op0, *Op1, *Op2;
+ if (ParseTypeAndValue(Op0, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after select condition") ||
+ ParseTypeAndValue(Op1, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after select value") ||
+ ParseTypeAndValue(Op2, PFS))
+ return true;
+
+ if (const char *Reason = SelectInst::areInvalidOperands(Op0, Op1, Op2))
+ return Error(Loc, Reason);
+
+ Inst = SelectInst::Create(Op0, Op1, Op2);
+ return false;
+}
+
+/// ParseVA_Arg
+/// ::= 'va_arg' TypeAndValue ',' Type
+bool LLParser::ParseVA_Arg(Instruction *&Inst, PerFunctionState &PFS) {
+ Value *Op;
+ PATypeHolder EltTy(Type::getVoidTy(Context));
+ LocTy TypeLoc;
+ if (ParseTypeAndValue(Op, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after vaarg operand") ||
+ ParseType(EltTy, TypeLoc))
+ return true;
+
+ if (!EltTy->isFirstClassType())
+ return Error(TypeLoc, "va_arg requires operand with first class type");
+
+ Inst = new VAArgInst(Op, EltTy);
+ return false;
+}
+
+/// ParseExtractElement
+/// ::= 'extractelement' TypeAndValue ',' TypeAndValue
+bool LLParser::ParseExtractElement(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy Loc;
+ Value *Op0, *Op1;
+ if (ParseTypeAndValue(Op0, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after extract value") ||
+ ParseTypeAndValue(Op1, PFS))
+ return true;
+
+ if (!ExtractElementInst::isValidOperands(Op0, Op1))
+ return Error(Loc, "invalid extractelement operands");
+
+ Inst = ExtractElementInst::Create(Op0, Op1);
+ return false;
+}
+
+/// ParseInsertElement
+/// ::= 'insertelement' TypeAndValue ',' TypeAndValue ',' TypeAndValue
+bool LLParser::ParseInsertElement(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy Loc;
+ Value *Op0, *Op1, *Op2;
+ if (ParseTypeAndValue(Op0, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after insertelement value") ||
+ ParseTypeAndValue(Op1, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after insertelement value") ||
+ ParseTypeAndValue(Op2, PFS))
+ return true;
+
+ if (!InsertElementInst::isValidOperands(Op0, Op1, Op2))
+ return Error(Loc, "invalid insertelement operands");
+
+ Inst = InsertElementInst::Create(Op0, Op1, Op2);
+ return false;
+}
+
+/// ParseShuffleVector
+/// ::= 'shufflevector' TypeAndValue ',' TypeAndValue ',' TypeAndValue
+bool LLParser::ParseShuffleVector(Instruction *&Inst, PerFunctionState &PFS) {
+ LocTy Loc;
+ Value *Op0, *Op1, *Op2;
+ if (ParseTypeAndValue(Op0, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after shuffle mask") ||
+ ParseTypeAndValue(Op1, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after shuffle value") ||
+ ParseTypeAndValue(Op2, PFS))
+ return true;
+
+ if (!ShuffleVectorInst::isValidOperands(Op0, Op1, Op2))
+ return Error(Loc, "invalid extractelement operands");
+
+ Inst = new ShuffleVectorInst(Op0, Op1, Op2);
+ return false;
+}
+
+/// ParsePHI
+/// ::= 'phi' Type '[' Value ',' Value ']' (',' '[' Value ',' Value ']')*
+int LLParser::ParsePHI(Instruction *&Inst, PerFunctionState &PFS) {
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ Value *Op0, *Op1;
+ LocTy TypeLoc = Lex.getLoc();
+
+ if (ParseType(Ty) ||
+ ParseToken(lltok::lsquare, "expected '[' in phi value list") ||
+ ParseValue(Ty, Op0, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after insertelement value") ||
+ ParseValue(Type::getLabelTy(Context), Op1, PFS) ||
+ ParseToken(lltok::rsquare, "expected ']' in phi value list"))
+ return true;
+
+ bool AteExtraComma = false;
+ SmallVector<std::pair<Value*, BasicBlock*>, 16> PHIVals;
+ while (1) {
+ PHIVals.push_back(std::make_pair(Op0, cast<BasicBlock>(Op1)));
+
+ if (!EatIfPresent(lltok::comma))
+ break;
+
+ if (Lex.getKind() == lltok::MetadataVar) {
+ AteExtraComma = true;
+ break;
+ }
+
+ if (ParseToken(lltok::lsquare, "expected '[' in phi value list") ||
+ ParseValue(Ty, Op0, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after insertelement value") ||
+ ParseValue(Type::getLabelTy(Context), Op1, PFS) ||
+ ParseToken(lltok::rsquare, "expected ']' in phi value list"))
+ return true;
+ }
+
+ if (!Ty->isFirstClassType())
+ return Error(TypeLoc, "phi node must have first class type");
+
+ PHINode *PN = PHINode::Create(Ty);
+ PN->reserveOperandSpace(PHIVals.size());
+ for (unsigned i = 0, e = PHIVals.size(); i != e; ++i)
+ PN->addIncoming(PHIVals[i].first, PHIVals[i].second);
+ Inst = PN;
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseCall
+/// ::= 'tail'? 'call' OptionalCallingConv OptionalAttrs Type Value
+/// ParameterList OptionalAttrs
+bool LLParser::ParseCall(Instruction *&Inst, PerFunctionState &PFS,
+ bool isTail) {
+ unsigned RetAttrs, FnAttrs;
+ CallingConv::ID CC;
+ PATypeHolder RetType(Type::getVoidTy(Context));
+ LocTy RetTypeLoc;
+ ValID CalleeID;
+ SmallVector<ParamInfo, 16> ArgList;
+ LocTy CallLoc = Lex.getLoc();
+
+ if ((isTail && ParseToken(lltok::kw_call, "expected 'tail call'")) ||
+ ParseOptionalCallingConv(CC) ||
+ ParseOptionalAttrs(RetAttrs, 1) ||
+ ParseType(RetType, RetTypeLoc, true /*void allowed*/) ||
+ ParseValID(CalleeID) ||
+ ParseParameterList(ArgList, PFS) ||
+ ParseOptionalAttrs(FnAttrs, 2))
+ return true;
+
+ // If RetType is a non-function pointer type, then this is the short syntax
+ // for the call, which means that RetType is just the return type. Infer the
+ // rest of the function argument types from the arguments that are present.
+ const PointerType *PFTy = 0;
+ const FunctionType *Ty = 0;
+ if (!(PFTy = dyn_cast<PointerType>(RetType)) ||
+ !(Ty = dyn_cast<FunctionType>(PFTy->getElementType()))) {
+ // Pull out the types of all of the arguments...
+ std::vector<const Type*> ParamTypes;
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i)
+ ParamTypes.push_back(ArgList[i].V->getType());
+
+ if (!FunctionType::isValidReturnType(RetType))
+ return Error(RetTypeLoc, "Invalid result type for LLVM function");
+
+ Ty = FunctionType::get(RetType, ParamTypes, false);
+ PFTy = PointerType::getUnqual(Ty);
+ }
+
+ // Look up the callee.
+ Value *Callee;
+ if (ConvertValIDToValue(PFTy, CalleeID, Callee, &PFS)) return true;
+
+ // FIXME: In LLVM 3.0, stop accepting zext, sext and inreg as optional
+ // function attributes.
+ unsigned ObsoleteFuncAttrs = Attribute::ZExt|Attribute::SExt|Attribute::InReg;
+ if (FnAttrs & ObsoleteFuncAttrs) {
+ RetAttrs |= FnAttrs & ObsoleteFuncAttrs;
+ FnAttrs &= ~ObsoleteFuncAttrs;
+ }
+
+ // Set up the Attributes for the function.
+ SmallVector<AttributeWithIndex, 8> Attrs;
+ if (RetAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(0, RetAttrs));
+
+ SmallVector<Value*, 8> Args;
+
+ // Loop through FunctionType's arguments and ensure they are specified
+ // correctly. Also, gather any parameter attributes.
+ FunctionType::param_iterator I = Ty->param_begin();
+ FunctionType::param_iterator E = Ty->param_end();
+ for (unsigned i = 0, e = ArgList.size(); i != e; ++i) {
+ const Type *ExpectedTy = 0;
+ if (I != E) {
+ ExpectedTy = *I++;
+ } else if (!Ty->isVarArg()) {
+ return Error(ArgList[i].Loc, "too many arguments specified");
+ }
+
+ if (ExpectedTy && ExpectedTy != ArgList[i].V->getType())
+ return Error(ArgList[i].Loc, "argument is not of expected type '" +
+ ExpectedTy->getDescription() + "'");
+ Args.push_back(ArgList[i].V);
+ if (ArgList[i].Attrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(i+1, ArgList[i].Attrs));
+ }
+
+ if (I != E)
+ return Error(CallLoc, "not enough parameters specified for call");
+
+ if (FnAttrs != Attribute::None)
+ Attrs.push_back(AttributeWithIndex::get(~0, FnAttrs));
+
+ // Finish off the Attributes and check them
+ AttrListPtr PAL = AttrListPtr::get(Attrs.begin(), Attrs.end());
+
+ CallInst *CI = CallInst::Create(Callee, Args.begin(), Args.end());
+ CI->setTailCall(isTail);
+ CI->setCallingConv(CC);
+ CI->setAttributes(PAL);
+ Inst = CI;
+ return false;
+}
+
+//===----------------------------------------------------------------------===//
+// Memory Instructions.
+//===----------------------------------------------------------------------===//
+
+/// ParseAlloc
+/// ::= 'malloc' Type (',' TypeAndValue)? (',' OptionalInfo)?
+/// ::= 'alloca' Type (',' TypeAndValue)? (',' OptionalInfo)?
+int LLParser::ParseAlloc(Instruction *&Inst, PerFunctionState &PFS,
+ BasicBlock* BB, bool isAlloca) {
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ Value *Size = 0;
+ LocTy SizeLoc;
+ unsigned Alignment = 0;
+ if (ParseType(Ty)) return true;
+
+ bool AteExtraComma = false;
+ if (EatIfPresent(lltok::comma)) {
+ if (Lex.getKind() == lltok::kw_align) {
+ if (ParseOptionalAlignment(Alignment)) return true;
+ } else if (Lex.getKind() == lltok::MetadataVar) {
+ AteExtraComma = true;
+ } else {
+ if (ParseTypeAndValue(Size, SizeLoc, PFS) ||
+ ParseOptionalCommaAlign(Alignment, AteExtraComma))
+ return true;
+ }
+ }
+
+ if (Size && !Size->getType()->isInteger(32))
+ return Error(SizeLoc, "element count must be i32");
+
+ if (isAlloca) {
+ Inst = new AllocaInst(Ty, Size, Alignment);
+ return AteExtraComma ? InstExtraComma : InstNormal;
+ }
+
+ // Autoupgrade old malloc instruction to malloc call.
+ // FIXME: Remove in LLVM 3.0.
+ const Type *IntPtrTy = Type::getInt32Ty(Context);
+ Constant *AllocSize = ConstantExpr::getSizeOf(Ty);
+ AllocSize = ConstantExpr::getTruncOrBitCast(AllocSize, IntPtrTy);
+ if (!MallocF)
+ // Prototype malloc as "void *(int32)".
+ // This function is renamed as "malloc" in ValidateEndOfModule().
+ MallocF = cast<Function>(
+ M->getOrInsertFunction("", Type::getInt8PtrTy(Context), IntPtrTy, NULL));
+ Inst = CallInst::CreateMalloc(BB, IntPtrTy, Ty, AllocSize, Size, MallocF);
+return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseFree
+/// ::= 'free' TypeAndValue
+bool LLParser::ParseFree(Instruction *&Inst, PerFunctionState &PFS,
+ BasicBlock* BB) {
+ Value *Val; LocTy Loc;
+ if (ParseTypeAndValue(Val, Loc, PFS)) return true;
+ if (!isa<PointerType>(Val->getType()))
+ return Error(Loc, "operand to free must be a pointer");
+ Inst = CallInst::CreateFree(Val, BB);
+ return false;
+}
+
+/// ParseLoad
+/// ::= 'volatile'? 'load' TypeAndValue (',' OptionalInfo)?
+int LLParser::ParseLoad(Instruction *&Inst, PerFunctionState &PFS,
+ bool isVolatile) {
+ Value *Val; LocTy Loc;
+ unsigned Alignment = 0;
+ bool AteExtraComma = false;
+ if (ParseTypeAndValue(Val, Loc, PFS) ||
+ ParseOptionalCommaAlign(Alignment, AteExtraComma))
+ return true;
+
+ if (!isa<PointerType>(Val->getType()) ||
+ !cast<PointerType>(Val->getType())->getElementType()->isFirstClassType())
+ return Error(Loc, "load operand must be a pointer to a first class type");
+
+ Inst = new LoadInst(Val, "", isVolatile, Alignment);
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseStore
+/// ::= 'volatile'? 'store' TypeAndValue ',' TypeAndValue (',' 'align' i32)?
+int LLParser::ParseStore(Instruction *&Inst, PerFunctionState &PFS,
+ bool isVolatile) {
+ Value *Val, *Ptr; LocTy Loc, PtrLoc;
+ unsigned Alignment = 0;
+ bool AteExtraComma = false;
+ if (ParseTypeAndValue(Val, Loc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after store operand") ||
+ ParseTypeAndValue(Ptr, PtrLoc, PFS) ||
+ ParseOptionalCommaAlign(Alignment, AteExtraComma))
+ return true;
+
+ if (!isa<PointerType>(Ptr->getType()))
+ return Error(PtrLoc, "store operand must be a pointer");
+ if (!Val->getType()->isFirstClassType())
+ return Error(Loc, "store operand must be a first class value");
+ if (cast<PointerType>(Ptr->getType())->getElementType() != Val->getType())
+ return Error(Loc, "stored value and pointer type do not match");
+
+ Inst = new StoreInst(Val, Ptr, isVolatile, Alignment);
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseGetResult
+/// ::= 'getresult' TypeAndValue ',' i32
+/// FIXME: Remove support for getresult in LLVM 3.0
+bool LLParser::ParseGetResult(Instruction *&Inst, PerFunctionState &PFS) {
+ Value *Val; LocTy ValLoc, EltLoc;
+ unsigned Element;
+ if (ParseTypeAndValue(Val, ValLoc, PFS) ||
+ ParseToken(lltok::comma, "expected ',' after getresult operand") ||
+ ParseUInt32(Element, EltLoc))
+ return true;
+
+ if (!isa<StructType>(Val->getType()) && !isa<ArrayType>(Val->getType()))
+ return Error(ValLoc, "getresult inst requires an aggregate operand");
+ if (!ExtractValueInst::getIndexedType(Val->getType(), Element))
+ return Error(EltLoc, "invalid getresult index for value");
+ Inst = ExtractValueInst::Create(Val, Element);
+ return false;
+}
+
+/// ParseGetElementPtr
+/// ::= 'getelementptr' 'inbounds'? TypeAndValue (',' TypeAndValue)*
+int LLParser::ParseGetElementPtr(Instruction *&Inst, PerFunctionState &PFS) {
+ Value *Ptr, *Val; LocTy Loc, EltLoc;
+
+ bool InBounds = EatIfPresent(lltok::kw_inbounds);
+
+ if (ParseTypeAndValue(Ptr, Loc, PFS)) return true;
+
+ if (!isa<PointerType>(Ptr->getType()))
+ return Error(Loc, "base of getelementptr must be a pointer");
+
+ SmallVector<Value*, 16> Indices;
+ bool AteExtraComma = false;
+ while (EatIfPresent(lltok::comma)) {
+ if (Lex.getKind() == lltok::MetadataVar) {
+ AteExtraComma = true;
+ break;
+ }
+ if (ParseTypeAndValue(Val, EltLoc, PFS)) return true;
+ if (!isa<IntegerType>(Val->getType()))
+ return Error(EltLoc, "getelementptr index must be an integer");
+ Indices.push_back(Val);
+ }
+
+ if (!GetElementPtrInst::getIndexedType(Ptr->getType(),
+ Indices.begin(), Indices.end()))
+ return Error(Loc, "invalid getelementptr indices");
+ Inst = GetElementPtrInst::Create(Ptr, Indices.begin(), Indices.end());
+ if (InBounds)
+ cast<GetElementPtrInst>(Inst)->setIsInBounds(true);
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseExtractValue
+/// ::= 'extractvalue' TypeAndValue (',' uint32)+
+int LLParser::ParseExtractValue(Instruction *&Inst, PerFunctionState &PFS) {
+ Value *Val; LocTy Loc;
+ SmallVector<unsigned, 4> Indices;
+ bool AteExtraComma;
+ if (ParseTypeAndValue(Val, Loc, PFS) ||
+ ParseIndexList(Indices, AteExtraComma))
+ return true;
+
+ if (!isa<StructType>(Val->getType()) && !isa<ArrayType>(Val->getType()))
+ return Error(Loc, "extractvalue operand must be array or struct");
+
+ if (!ExtractValueInst::getIndexedType(Val->getType(), Indices.begin(),
+ Indices.end()))
+ return Error(Loc, "invalid indices for extractvalue");
+ Inst = ExtractValueInst::Create(Val, Indices.begin(), Indices.end());
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+/// ParseInsertValue
+/// ::= 'insertvalue' TypeAndValue ',' TypeAndValue (',' uint32)+
+int LLParser::ParseInsertValue(Instruction *&Inst, PerFunctionState &PFS) {
+ Value *Val0, *Val1; LocTy Loc0, Loc1;
+ SmallVector<unsigned, 4> Indices;
+ bool AteExtraComma;
+ if (ParseTypeAndValue(Val0, Loc0, PFS) ||
+ ParseToken(lltok::comma, "expected comma after insertvalue operand") ||
+ ParseTypeAndValue(Val1, Loc1, PFS) ||
+ ParseIndexList(Indices, AteExtraComma))
+ return true;
+
+ if (!isa<StructType>(Val0->getType()) && !isa<ArrayType>(Val0->getType()))
+ return Error(Loc0, "extractvalue operand must be array or struct");
+
+ if (!ExtractValueInst::getIndexedType(Val0->getType(), Indices.begin(),
+ Indices.end()))
+ return Error(Loc0, "invalid indices for insertvalue");
+ Inst = InsertValueInst::Create(Val0, Val1, Indices.begin(), Indices.end());
+ return AteExtraComma ? InstExtraComma : InstNormal;
+}
+
+//===----------------------------------------------------------------------===//
+// Embedded metadata.
+//===----------------------------------------------------------------------===//
+
+/// ParseMDNodeVector
+/// ::= Element (',' Element)*
+/// Element
+/// ::= 'null' | TypeAndValue
+bool LLParser::ParseMDNodeVector(SmallVectorImpl<Value*> &Elts,
+ PerFunctionState *PFS) {
+ do {
+ // Null is a special case since it is typeless.
+ if (EatIfPresent(lltok::kw_null)) {
+ Elts.push_back(0);
+ continue;
+ }
+
+ Value *V = 0;
+ PATypeHolder Ty(Type::getVoidTy(Context));
+ ValID ID;
+ if (ParseType(Ty) || ParseValID(ID, PFS) ||
+ ConvertValIDToValue(Ty, ID, V, PFS))
+ return true;
+
+ Elts.push_back(V);
+ } while (EatIfPresent(lltok::comma));
+
+ return false;
+}
diff --git a/lib/AsmParser/LLParser.h b/lib/AsmParser/LLParser.h
new file mode 100644
index 0000000..85c07ff
--- /dev/null
+++ b/lib/AsmParser/LLParser.h
@@ -0,0 +1,355 @@
+//===-- LLParser.h - Parser Class -------------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the parser class for .ll files.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ASMPARSER_LLPARSER_H
+#define LLVM_ASMPARSER_LLPARSER_H
+
+#include "LLLexer.h"
+#include "llvm/Module.h"
+#include "llvm/Type.h"
+#include "llvm/Support/ValueHandle.h"
+#include <map>
+
+namespace llvm {
+ class Module;
+ class OpaqueType;
+ class Function;
+ class Value;
+ class BasicBlock;
+ class Instruction;
+ class Constant;
+ class GlobalValue;
+ class MDString;
+ class MDNode;
+
+ /// 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.
+ } Kind;
+
+ LLLexer::LocTy Loc;
+ unsigned UIntVal;
+ std::string StrVal, StrVal2;
+ APSInt APSIntVal;
+ APFloat APFloatVal;
+ Constant *ConstantVal;
+ MDNode *MDNodeVal;
+ MDString *MDStringVal;
+ ValID() : APFloatVal(0.0) {}
+
+ bool operator<(const ValID &RHS) const {
+ if (Kind == t_LocalID || Kind == t_GlobalID)
+ return UIntVal < RHS.UIntVal;
+ assert((Kind == t_LocalName || Kind == t_GlobalName) &&
+ "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;
+ std::vector<TrackingVH<MDNode> > NumberedMetadata;
+ std::map<unsigned, std::pair<TrackingVH<MDNode>, LocTy> > ForwardRefMDNodes;
+ 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) {}
+ };
+ std::vector<UpRefRecord> UpRefs;
+
+ // 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;
+
+ Function *MallocF;
+ public:
+ LLParser(MemoryBuffer *F, SourceMgr &SM, SMDiagnostic &Err, Module *m) :
+ Context(m->getContext()), Lex(F, SM, Err, m->getContext()),
+ M(m), MallocF(NULL) {}
+ bool Run();
+
+ LLVMContext& getContext() { return Context; }
+
+ private:
+
+ bool Error(LocTy L, const std::string &Msg) const {
+ return Lex.Error(L, Msg);
+ }
+ bool TokError(const std::string &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);
+
+ // Helper Routines.
+ bool ParseToken(lltok::Kind T, const char *ErrMsg);
+ bool EatIfPresent(lltok::Kind T) {
+ if (Lex.getKind() != T) return false;
+ Lex.Lex();
+ return true;
+ }
+ bool ParseOptionalToken(lltok::Kind T, bool &Present) {
+ if (Lex.getKind() != T) {
+ Present = false;
+ } else {
+ Lex.Lex();
+ Present = true;
+ }
+ return false;
+ }
+ bool ParseStringConstant(std::string &Result);
+ bool ParseUInt32(unsigned &Val);
+ bool ParseUInt32(unsigned &Val, LocTy &Loc) {
+ Loc = Lex.getLoc();
+ return ParseUInt32(Val);
+ }
+ bool ParseOptionalAddrSpace(unsigned &AddrSpace);
+ bool ParseOptionalAttrs(unsigned &Attrs, unsigned AttrKind);
+ bool ParseOptionalLinkage(unsigned &Linkage, bool &HasLinkage);
+ bool ParseOptionalLinkage(unsigned &Linkage) {
+ bool HasLinkage; return ParseOptionalLinkage(Linkage, HasLinkage);
+ }
+ bool ParseOptionalVisibility(unsigned &Visibility);
+ bool ParseOptionalCallingConv(CallingConv::ID &CC);
+ bool ParseOptionalAlignment(unsigned &Alignment);
+ bool ParseInstructionMetadata(SmallVectorImpl<std::pair<unsigned,
+ MDNode *> > &);
+ 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 ValidateEndOfModule();
+ bool ParseTargetDefinition();
+ bool ParseDepLibs();
+ bool ParseModuleAsm();
+ bool ParseUnnamedType();
+ bool ParseNamedType();
+ bool ParseDeclare();
+ 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);
+
+ // Type Parsing.
+ bool ParseType(PATypeHolder &Result, bool AllowVoid = false);
+ bool ParseType(PATypeHolder &Result, LocTy &Loc, bool AllowVoid = false) {
+ Loc = Lex.getLoc();
+ 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);
+
+ // Function Semantic Analysis.
+ class PerFunctionState {
+ LLParser &P;
+ Function &F;
+ 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, int FunctionNumber);
+ ~PerFunctionState();
+
+ Function &getFunction() const { return F; }
+
+ 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);
+
+ /// SetInstName - After an instruction is parsed and inserted into its
+ /// basic block, this installs its name.
+ bool SetInstName(int NameID, const std::string &NameStr, LocTy NameLoc,
+ Instruction *Inst);
+
+ /// GetBB - Get a basic block with the specified name or ID, creating a
+ /// forward reference record if needed. This can return null if the value
+ /// is not a BasicBlock.
+ BasicBlock *GetBB(const std::string &Name, LocTy Loc);
+ BasicBlock *GetBB(unsigned ID, LocTy Loc);
+
+ /// DefineBB - Define the specified basic block, which is either named or
+ /// unnamed. If there is an error, this returns null otherwise it returns
+ /// the block being defined.
+ BasicBlock *DefineBB(const std::string &Name, LocTy Loc);
+ };
+
+ bool ConvertValIDToValue(const 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,
+ PerFunctionState &PFS) {
+ Loc = Lex.getLoc();
+ return ParseValue(Ty, V, PFS);
+ }
+
+ bool ParseTypeAndValue(Value *&V, PerFunctionState &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;
+ Value *V;
+ unsigned Attrs;
+ ParamInfo(LocTy loc, Value *v, unsigned attrs)
+ : Loc(loc), V(v), Attrs(attrs) {}
+ };
+ bool ParseParameterList(SmallVectorImpl<ParamInfo> &ArgList,
+ PerFunctionState &PFS);
+
+ // Constant Parsing.
+ bool ParseValID(ValID &ID, PerFunctionState *PFS = NULL);
+ bool ParseGlobalValue(const Type *Ty, Constant *&V);
+ bool ParseGlobalTypeAndValue(Constant *&V);
+ bool ParseGlobalValueVector(SmallVectorImpl<Constant*> &Elts);
+ bool ParseMDNodeVector(SmallVectorImpl<Value*> &, PerFunctionState *PFS);
+
+ // Function Parsing.
+ struct ArgInfo {
+ LocTy Loc;
+ PATypeHolder Type;
+ unsigned Attrs;
+ std::string Name;
+ ArgInfo(LocTy L, PATypeHolder Ty, unsigned Attr, const std::string &N)
+ : Loc(L), Type(Ty), Attrs(Attr), Name(N) {}
+ };
+ bool ParseArgumentList(std::vector<ArgInfo> &ArgList,
+ bool &isVarArg, bool inType);
+ bool ParseFunctionHeader(Function *&Fn, bool isDefine);
+ bool ParseFunctionBody(Function &Fn);
+ bool ParseBasicBlock(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);
+
+ int 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 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 ParseSelect(Instruction *&I, PerFunctionState &PFS);
+ bool ParseVA_Arg(Instruction *&I, PerFunctionState &PFS);
+ bool ParseExtractElement(Instruction *&I, PerFunctionState &PFS);
+ bool ParseInsertElement(Instruction *&I, PerFunctionState &PFS);
+ bool ParseShuffleVector(Instruction *&I, PerFunctionState &PFS);
+ int ParsePHI(Instruction *&I, PerFunctionState &PFS);
+ bool ParseCall(Instruction *&I, PerFunctionState &PFS, bool isTail);
+ int ParseAlloc(Instruction *&I, PerFunctionState &PFS,
+ BasicBlock *BB = 0, bool isAlloca = true);
+ bool ParseFree(Instruction *&I, PerFunctionState &PFS, BasicBlock *BB);
+ int ParseLoad(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
+ int ParseStore(Instruction *&I, PerFunctionState &PFS, bool isVolatile);
+ bool ParseGetResult(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
+
+#endif
diff --git a/lib/AsmParser/LLToken.h b/lib/AsmParser/LLToken.h
new file mode 100644
index 0000000..7f1807c
--- /dev/null
+++ b/lib/AsmParser/LLToken.h
@@ -0,0 +1,144 @@
+//===- LLToken.h - Token Codes for LLVM Assembly Files ----------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the enums for the .ll lexer.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LIBS_ASMPARSER_LLTOKEN_H
+#define LIBS_ASMPARSER_LLTOKEN_H
+
+namespace llvm {
+namespace lltok {
+ enum Kind {
+ // Markers
+ Eof, Error,
+
+ // Tokens with no info.
+ dotdotdot, // ...
+ equal, comma, // = ,
+ star, // *
+ lsquare, rsquare, // [ ]
+ lbrace, rbrace, // { }
+ less, greater, // < >
+ lparen, rparen, // ( )
+ backslash, // \ (not /)
+ exclaim, // !
+
+ kw_x,
+ kw_begin, kw_end,
+ kw_true, kw_false,
+ kw_declare, kw_define,
+ kw_global, kw_constant,
+
+ kw_private, kw_linker_private, kw_internal, kw_linkonce, kw_linkonce_odr,
+ kw_weak, kw_weak_odr, kw_appending, kw_dllimport, kw_dllexport, kw_common,
+ kw_available_externally,
+ kw_default, kw_hidden, kw_protected,
+ kw_extern_weak,
+ kw_external, kw_thread_local,
+ kw_zeroinitializer,
+ kw_undef, kw_null,
+ kw_to,
+ kw_tail,
+ kw_target,
+ kw_triple,
+ kw_deplibs,
+ kw_datalayout,
+ kw_volatile,
+ kw_nuw,
+ kw_nsw,
+ kw_exact,
+ kw_inbounds,
+ kw_align,
+ kw_addrspace,
+ kw_section,
+ kw_alias,
+ kw_module,
+ kw_asm,
+ kw_sideeffect,
+ kw_alignstack,
+ kw_gc,
+ kw_c,
+
+ kw_cc, kw_ccc, kw_fastcc, kw_coldcc,
+ kw_x86_stdcallcc, kw_x86_fastcallcc,
+ kw_arm_apcscc, kw_arm_aapcscc, kw_arm_aapcs_vfpcc,
+ kw_msp430_intrcc,
+
+ kw_signext,
+ kw_zeroext,
+ kw_inreg,
+ kw_sret,
+ kw_nounwind,
+ kw_noreturn,
+ kw_noalias,
+ kw_nocapture,
+ kw_byval,
+ kw_nest,
+ kw_readnone,
+ kw_readonly,
+
+ kw_inlinehint,
+ kw_noinline,
+ kw_alwaysinline,
+ kw_optsize,
+ kw_ssp,
+ kw_sspreq,
+ kw_noredzone,
+ kw_noimplicitfloat,
+ kw_naked,
+
+ kw_type,
+ kw_opaque,
+
+ kw_eq, kw_ne, kw_slt, kw_sgt, kw_sle, kw_sge, kw_ult, kw_ugt, kw_ule,
+ kw_uge, kw_oeq, kw_one, kw_olt, kw_ogt, kw_ole, kw_oge, kw_ord, kw_uno,
+ kw_ueq, kw_une,
+
+ // Instruction Opcodes (Opcode in UIntVal).
+ kw_add, kw_fadd, kw_sub, kw_fsub, kw_mul, kw_fmul,
+ kw_udiv, kw_sdiv, kw_fdiv,
+ kw_urem, kw_srem, kw_frem, kw_shl, kw_lshr, kw_ashr,
+ kw_and, kw_or, kw_xor, kw_icmp, kw_fcmp,
+
+ kw_phi, kw_call,
+ kw_trunc, kw_zext, kw_sext, kw_fptrunc, kw_fpext, kw_uitofp, kw_sitofp,
+ kw_fptoui, kw_fptosi, kw_inttoptr, kw_ptrtoint, kw_bitcast,
+ kw_select, kw_va_arg,
+
+ kw_ret, kw_br, kw_switch, kw_indirectbr, kw_invoke, kw_unwind,
+ kw_unreachable,
+
+ kw_malloc, kw_alloca, kw_free, kw_load, kw_store, kw_getelementptr,
+
+ kw_extractelement, kw_insertelement, kw_shufflevector, kw_getresult,
+ kw_extractvalue, kw_insertvalue, kw_blockaddress,
+
+ // Unsigned Valued tokens (UIntVal).
+ GlobalID, // @42
+ LocalVarID, // %42
+
+ // String valued tokens (StrVal).
+ LabelStr, // foo:
+ GlobalVar, // @foo @"foo"
+ LocalVar, // %foo %"foo"
+ MetadataVar, // !foo
+ StringConstant, // "foo"
+
+ // Type valued tokens (TyVal).
+ Type,
+
+ APFloat, // APFloatVal
+ APSInt // APSInt
+ };
+} // end namespace lltok
+} // end namespace llvm
+
+#endif
diff --git a/lib/AsmParser/Makefile b/lib/AsmParser/Makefile
new file mode 100644
index 0000000..995bb0e
--- /dev/null
+++ b/lib/AsmParser/Makefile
@@ -0,0 +1,14 @@
+##===- lib/AsmParser/Makefile ------------------------------*- Makefile -*-===##
+#
+# The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+#
+##===----------------------------------------------------------------------===##
+
+LEVEL = ../..
+LIBRARYNAME := LLVMAsmParser
+BUILD_ARCHIVE = 1
+
+include $(LEVEL)/Makefile.common
diff --git a/lib/AsmParser/Parser.cpp b/lib/AsmParser/Parser.cpp
new file mode 100644
index 0000000..aac4027
--- /dev/null
+++ b/lib/AsmParser/Parser.cpp
@@ -0,0 +1,63 @@
+//===- Parser.cpp - Main dispatch module for the Parser library -----------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This library implements the functionality defined in llvm/Assembly/Parser.h
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Assembly/Parser.h"
+#include "LLParser.h"
+#include "llvm/Module.h"
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/Support/SourceMgr.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/raw_ostream.h"
+#include <cstring>
+using namespace llvm;
+
+Module *llvm::ParseAssembly(MemoryBuffer *F,
+ Module *M,
+ SMDiagnostic &Err,
+ LLVMContext &Context) {
+ SourceMgr SM;
+ SM.AddNewSourceBuffer(F, SMLoc());
+
+ // If we are parsing into an existing module, do it.
+ if (M)
+ return LLParser(F, SM, Err, M).Run() ? 0 : M;
+
+ // Otherwise create a new module.
+ OwningPtr<Module> M2(new Module(F->getBufferIdentifier(), Context));
+ if (LLParser(F, SM, Err, M2.get()).Run())
+ return 0;
+ return M2.take();
+}
+
+Module *llvm::ParseAssemblyFile(const std::string &Filename, SMDiagnostic &Err,
+ LLVMContext &Context) {
+ std::string ErrorStr;
+ MemoryBuffer *F = MemoryBuffer::getFileOrSTDIN(Filename.c_str(), &ErrorStr);
+ if (F == 0) {
+ Err = SMDiagnostic("", -1, -1,
+ "Could not open input file '" + Filename + "': " +
+ ErrorStr, "");
+ return 0;
+ }
+
+ return ParseAssembly(F, 0, Err, Context);
+}
+
+Module *llvm::ParseAssemblyString(const char *AsmString, Module *M,
+ SMDiagnostic &Err, LLVMContext &Context) {
+ MemoryBuffer *F =
+ MemoryBuffer::getMemBuffer(AsmString, AsmString+strlen(AsmString),
+ "<string>");
+
+ return ParseAssembly(F, M, Err, Context);
+}