diff options
Diffstat (limited to 'contrib/llvm/lib/MC/MCParser')
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/AsmLexer.cpp | 469 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/AsmParser.cpp | 3411 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/COFFAsmParser.cpp | 498 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/DarwinAsmParser.cpp | 747 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/ELFAsmParser.cpp | 611 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/MCAsmLexer.cpp | 31 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/MCAsmParser.cpp | 48 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/MCAsmParserExtension.cpp | 22 | ||||
-rw-r--r-- | contrib/llvm/lib/MC/MCParser/MCTargetAsmParser.cpp | 19 |
9 files changed, 5856 insertions, 0 deletions
diff --git a/contrib/llvm/lib/MC/MCParser/AsmLexer.cpp b/contrib/llvm/lib/MC/MCParser/AsmLexer.cpp new file mode 100644 index 0000000..c76052d --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/AsmLexer.cpp @@ -0,0 +1,469 @@ +//===- AsmLexer.cpp - Lexer for Assembly Files ----------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This class implements the lexer for assembly files. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/AsmLexer.h" +#include "llvm/Support/SMLoc.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/MC/MCAsmInfo.h" +#include <cctype> +#include <cerrno> +#include <cstdio> +#include <cstdlib> +using namespace llvm; + +AsmLexer::AsmLexer(const MCAsmInfo &_MAI) : MAI(_MAI) { + CurBuf = NULL; + CurPtr = NULL; + isAtStartOfLine = true; +} + +AsmLexer::~AsmLexer() { +} + +void AsmLexer::setBuffer(const MemoryBuffer *buf, const char *ptr) { + CurBuf = buf; + + if (ptr) + CurPtr = ptr; + else + CurPtr = CurBuf->getBufferStart(); + + TokStart = 0; +} + +/// ReturnError - Set the error to the specified string at the specified +/// location. This is defined to always return AsmToken::Error. +AsmToken AsmLexer::ReturnError(const char *Loc, const std::string &Msg) { + SetError(SMLoc::getFromPointer(Loc), Msg); + + return AsmToken(AsmToken::Error, StringRef(Loc, 0)); +} + +int AsmLexer::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; + } +} + +/// LexFloatLiteral: [0-9]*[.][0-9]*([eE][+-]?[0-9]*)? +/// +/// The leading integral digit sequence and dot should have already been +/// consumed, some or all of the fractional digit sequence *can* have been +/// consumed. +AsmToken AsmLexer::LexFloatLiteral() { + // Skip the fractional digit sequence. + while (isdigit(*CurPtr)) + ++CurPtr; + + // Check for exponent; we intentionally accept a slighlty wider set of + // literals here and rely on the upstream client to reject invalid ones (e.g., + // "1e+"). + if (*CurPtr == 'e' || *CurPtr == 'E') { + ++CurPtr; + if (*CurPtr == '-' || *CurPtr == '+') + ++CurPtr; + while (isdigit(*CurPtr)) + ++CurPtr; + } + + return AsmToken(AsmToken::Real, + StringRef(TokStart, CurPtr - TokStart)); +} + +/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]* +static bool IsIdentifierChar(char c) { + return isalnum(c) || c == '_' || c == '$' || c == '.' || c == '@'; +} +AsmToken AsmLexer::LexIdentifier() { + // Check for floating point literals. + if (CurPtr[-1] == '.' && isdigit(*CurPtr)) { + // Disambiguate a .1243foo identifier from a floating literal. + while (isdigit(*CurPtr)) + ++CurPtr; + if (*CurPtr == 'e' || *CurPtr == 'E' || !IsIdentifierChar(*CurPtr)) + return LexFloatLiteral(); + } + + while (IsIdentifierChar(*CurPtr)) + ++CurPtr; + + // Handle . as a special case. + if (CurPtr == TokStart+1 && TokStart[0] == '.') + return AsmToken(AsmToken::Dot, StringRef(TokStart, 1)); + + return AsmToken(AsmToken::Identifier, StringRef(TokStart, CurPtr - TokStart)); +} + +/// LexSlash: Slash: / +/// C-Style Comment: /* ... */ +AsmToken AsmLexer::LexSlash() { + switch (*CurPtr) { + case '*': break; // C style comment. + case '/': return ++CurPtr, LexLineComment(); + default: return AsmToken(AsmToken::Slash, StringRef(CurPtr-1, 1)); + } + + // C Style comment. + ++CurPtr; // skip the star. + while (1) { + int CurChar = getNextChar(); + switch (CurChar) { + case EOF: + return ReturnError(TokStart, "unterminated comment"); + case '*': + // End of the comment? + if (CurPtr[0] != '/') break; + + ++CurPtr; // End the */. + return LexToken(); + } + } +} + +/// LexLineComment: Comment: #[^\n]* +/// : //[^\n]* +AsmToken AsmLexer::LexLineComment() { + // FIXME: This is broken if we happen to a comment at the end of a file, which + // was .included, and which doesn't end with a newline. + int CurChar = getNextChar(); + while (CurChar != '\n' && CurChar != '\r' && CurChar != EOF) + CurChar = getNextChar(); + + if (CurChar == EOF) + return AsmToken(AsmToken::Eof, StringRef(CurPtr, 0)); + return AsmToken(AsmToken::EndOfStatement, StringRef(CurPtr, 0)); +} + +static void SkipIgnoredIntegerSuffix(const char *&CurPtr) { + if (CurPtr[0] == 'L' && CurPtr[1] == 'L') + CurPtr += 2; + if (CurPtr[0] == 'U' && CurPtr[1] == 'L' && CurPtr[2] == 'L') + CurPtr += 3; +} + +/// LexDigit: First character is [0-9]. +/// Local Label: [0-9][:] +/// Forward/Backward Label: [0-9][fb] +/// Binary integer: 0b[01]+ +/// Octal integer: 0[0-7]+ +/// Hex integer: 0x[0-9a-fA-F]+ +/// Decimal integer: [1-9][0-9]* +AsmToken AsmLexer::LexDigit() { + // Decimal integer: [1-9][0-9]* + if (CurPtr[-1] != '0' || CurPtr[0] == '.') { + while (isdigit(*CurPtr)) + ++CurPtr; + + // Check for floating point literals. + if (*CurPtr == '.' || *CurPtr == 'e') { + ++CurPtr; + return LexFloatLiteral(); + } + + StringRef Result(TokStart, CurPtr - TokStart); + + long long Value; + if (Result.getAsInteger(10, Value)) { + // Allow positive values that are too large to fit into a signed 64-bit + // integer, but that do fit in an unsigned one, we just convert them over. + unsigned long long UValue; + if (Result.getAsInteger(10, UValue)) + return ReturnError(TokStart, "invalid decimal number"); + Value = (long long)UValue; + } + + // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL + // suffixes on integer literals. + SkipIgnoredIntegerSuffix(CurPtr); + + return AsmToken(AsmToken::Integer, Result, Value); + } + + if (*CurPtr == 'b') { + ++CurPtr; + // See if we actually have "0b" as part of something like "jmp 0b\n" + if (!isdigit(CurPtr[0])) { + --CurPtr; + StringRef Result(TokStart, CurPtr - TokStart); + return AsmToken(AsmToken::Integer, Result, 0); + } + const char *NumStart = CurPtr; + while (CurPtr[0] == '0' || CurPtr[0] == '1') + ++CurPtr; + + // Requires at least one binary digit. + if (CurPtr == NumStart) + return ReturnError(TokStart, "invalid binary number"); + + StringRef Result(TokStart, CurPtr - TokStart); + + long long Value; + if (Result.substr(2).getAsInteger(2, Value)) + return ReturnError(TokStart, "invalid binary number"); + + // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL + // suffixes on integer literals. + SkipIgnoredIntegerSuffix(CurPtr); + + return AsmToken(AsmToken::Integer, Result, Value); + } + + if (*CurPtr == 'x') { + ++CurPtr; + const char *NumStart = CurPtr; + while (isxdigit(CurPtr[0])) + ++CurPtr; + + // Requires at least one hex digit. + if (CurPtr == NumStart) + return ReturnError(CurPtr-2, "invalid hexadecimal number"); + + unsigned long long Result; + if (StringRef(TokStart, CurPtr - TokStart).getAsInteger(0, Result)) + return ReturnError(TokStart, "invalid hexadecimal number"); + + // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL + // suffixes on integer literals. + SkipIgnoredIntegerSuffix(CurPtr); + + return AsmToken(AsmToken::Integer, StringRef(TokStart, CurPtr - TokStart), + (int64_t)Result); + } + + // Must be an octal number, it starts with 0. + while (*CurPtr >= '0' && *CurPtr <= '9') + ++CurPtr; + + StringRef Result(TokStart, CurPtr - TokStart); + long long Value; + if (Result.getAsInteger(8, Value)) + return ReturnError(TokStart, "invalid octal number"); + + // The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL + // suffixes on integer literals. + SkipIgnoredIntegerSuffix(CurPtr); + + return AsmToken(AsmToken::Integer, Result, Value); +} + +/// LexSingleQuote: Integer: 'b' +AsmToken AsmLexer::LexSingleQuote() { + int CurChar = getNextChar(); + + if (CurChar == '\\') + CurChar = getNextChar(); + + if (CurChar == EOF) + return ReturnError(TokStart, "unterminated single quote"); + + CurChar = getNextChar(); + + if (CurChar != '\'') + return ReturnError(TokStart, "single quote way too long"); + + // The idea here being that 'c' is basically just an integral + // constant. + StringRef Res = StringRef(TokStart,CurPtr - TokStart); + long long Value; + + if (Res.startswith("\'\\")) { + char theChar = Res[2]; + switch (theChar) { + default: Value = theChar; break; + case '\'': Value = '\''; break; + case 't': Value = '\t'; break; + case 'n': Value = '\n'; break; + case 'b': Value = '\b'; break; + } + } else + Value = TokStart[1]; + + return AsmToken(AsmToken::Integer, Res, Value); +} + + +/// LexQuote: String: "..." +AsmToken AsmLexer::LexQuote() { + int CurChar = getNextChar(); + // TODO: does gas allow multiline string constants? + while (CurChar != '"') { + if (CurChar == '\\') { + // Allow \", etc. + CurChar = getNextChar(); + } + + if (CurChar == EOF) + return ReturnError(TokStart, "unterminated string constant"); + + CurChar = getNextChar(); + } + + return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart)); +} + +StringRef AsmLexer::LexUntilEndOfStatement() { + TokStart = CurPtr; + + while (!isAtStartOfComment(*CurPtr) && // Start of line comment. + !isAtStatementSeparator(CurPtr) && // End of statement marker. + *CurPtr != '\n' && + *CurPtr != '\r' && + (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) { + ++CurPtr; + } + return StringRef(TokStart, CurPtr-TokStart); +} + +StringRef AsmLexer::LexUntilEndOfLine() { + TokStart = CurPtr; + + while (*CurPtr != '\n' && + *CurPtr != '\r' && + (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) { + ++CurPtr; + } + return StringRef(TokStart, CurPtr-TokStart); +} + +bool AsmLexer::isAtStartOfComment(char Char) { + // FIXME: This won't work for multi-character comment indicators like "//". + return Char == *MAI.getCommentString(); +} + +bool AsmLexer::isAtStatementSeparator(const char *Ptr) { + return strncmp(Ptr, MAI.getSeparatorString(), + strlen(MAI.getSeparatorString())) == 0; +} + +AsmToken AsmLexer::LexToken() { + TokStart = CurPtr; + // This always consumes at least one character. + int CurChar = getNextChar(); + + if (isAtStartOfComment(CurChar)) { + // If this comment starts with a '#', then return the Hash token and let + // the assembler parser see if it can be parsed as a cpp line filename + // comment. We do this only if we are at the start of a line. + if (CurChar == '#' && isAtStartOfLine) + return AsmToken(AsmToken::Hash, StringRef(TokStart, 1)); + isAtStartOfLine = true; + return LexLineComment(); + } + if (isAtStatementSeparator(TokStart)) { + CurPtr += strlen(MAI.getSeparatorString()) - 1; + return AsmToken(AsmToken::EndOfStatement, + StringRef(TokStart, strlen(MAI.getSeparatorString()))); + } + + // If we're missing a newline at EOF, make sure we still get an + // EndOfStatement token before the Eof token. + if (CurChar == EOF && !isAtStartOfLine) { + isAtStartOfLine = true; + return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1)); + } + + isAtStartOfLine = false; + switch (CurChar) { + default: + // Handle identifier: [a-zA-Z_.][a-zA-Z0-9_$.@]* + if (isalpha(CurChar) || CurChar == '_' || CurChar == '.') + return LexIdentifier(); + + // Unknown character, emit an error. + return ReturnError(TokStart, "invalid character in input"); + case EOF: return AsmToken(AsmToken::Eof, StringRef(TokStart, 0)); + case 0: + case ' ': + case '\t': + // Ignore whitespace. + return LexToken(); + case '\n': // FALL THROUGH. + case '\r': + isAtStartOfLine = true; + return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1)); + case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1)); + case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1)); + case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1)); + case '~': return AsmToken(AsmToken::Tilde, StringRef(TokStart, 1)); + case '(': return AsmToken(AsmToken::LParen, StringRef(TokStart, 1)); + case ')': return AsmToken(AsmToken::RParen, StringRef(TokStart, 1)); + case '[': return AsmToken(AsmToken::LBrac, StringRef(TokStart, 1)); + case ']': return AsmToken(AsmToken::RBrac, StringRef(TokStart, 1)); + case '{': return AsmToken(AsmToken::LCurly, StringRef(TokStart, 1)); + case '}': return AsmToken(AsmToken::RCurly, StringRef(TokStart, 1)); + case '*': return AsmToken(AsmToken::Star, StringRef(TokStart, 1)); + case ',': return AsmToken(AsmToken::Comma, StringRef(TokStart, 1)); + case '$': return AsmToken(AsmToken::Dollar, StringRef(TokStart, 1)); + case '@': return AsmToken(AsmToken::At, StringRef(TokStart, 1)); + case '\\': return AsmToken(AsmToken::BackSlash, StringRef(TokStart, 1)); + case '=': + if (*CurPtr == '=') + return ++CurPtr, AsmToken(AsmToken::EqualEqual, StringRef(TokStart, 2)); + return AsmToken(AsmToken::Equal, StringRef(TokStart, 1)); + case '|': + if (*CurPtr == '|') + return ++CurPtr, AsmToken(AsmToken::PipePipe, StringRef(TokStart, 2)); + return AsmToken(AsmToken::Pipe, StringRef(TokStart, 1)); + case '^': return AsmToken(AsmToken::Caret, StringRef(TokStart, 1)); + case '&': + if (*CurPtr == '&') + return ++CurPtr, AsmToken(AsmToken::AmpAmp, StringRef(TokStart, 2)); + return AsmToken(AsmToken::Amp, StringRef(TokStart, 1)); + case '!': + if (*CurPtr == '=') + return ++CurPtr, AsmToken(AsmToken::ExclaimEqual, StringRef(TokStart, 2)); + return AsmToken(AsmToken::Exclaim, StringRef(TokStart, 1)); + case '%': return AsmToken(AsmToken::Percent, StringRef(TokStart, 1)); + case '/': return LexSlash(); + case '#': return AsmToken(AsmToken::Hash, StringRef(TokStart, 1)); + case '\'': return LexSingleQuote(); + case '"': return LexQuote(); + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + return LexDigit(); + case '<': + switch (*CurPtr) { + case '<': return ++CurPtr, AsmToken(AsmToken::LessLess, + StringRef(TokStart, 2)); + case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual, + StringRef(TokStart, 2)); + case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater, + StringRef(TokStart, 2)); + default: return AsmToken(AsmToken::Less, StringRef(TokStart, 1)); + } + case '>': + switch (*CurPtr) { + case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater, + StringRef(TokStart, 2)); + case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual, + StringRef(TokStart, 2)); + default: return AsmToken(AsmToken::Greater, StringRef(TokStart, 1)); + } + + // TODO: Quoted identifiers (objc methods etc) + // local labels: [0-9][:] + // Forward/backward labels: [0-9][fb] + // Integers, fp constants, character constants. + } +} diff --git a/contrib/llvm/lib/MC/MCParser/AsmParser.cpp b/contrib/llvm/lib/MC/MCParser/AsmParser.cpp new file mode 100644 index 0000000..b67c769 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/AsmParser.cpp @@ -0,0 +1,3411 @@ +//===- AsmParser.cpp - Parser for Assembly Files --------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This class implements the parser for assembly files. +// +//===----------------------------------------------------------------------===// + +#include "llvm/ADT/APFloat.h" +#include "llvm/ADT/SmallString.h" +#include "llvm/ADT/StringMap.h" +#include "llvm/ADT/Twine.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCDwarf.h" +#include "llvm/MC/MCExpr.h" +#include "llvm/MC/MCParser/AsmCond.h" +#include "llvm/MC/MCParser/AsmLexer.h" +#include "llvm/MC/MCParser/MCAsmParser.h" +#include "llvm/MC/MCParser/MCParsedAsmOperand.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCSectionMachO.h" +#include "llvm/MC/MCStreamer.h" +#include "llvm/MC/MCSymbol.h" +#include "llvm/MC/MCTargetAsmParser.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/MathExtras.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/SourceMgr.h" +#include "llvm/Support/raw_ostream.h" +#include <cctype> +#include <vector> +using namespace llvm; + +static cl::opt<bool> +FatalAssemblerWarnings("fatal-assembler-warnings", + cl::desc("Consider warnings as error")); + +namespace { + +/// \brief Helper class for tracking macro definitions. +typedef std::vector<AsmToken> MacroArgument; +typedef std::vector<MacroArgument> MacroArguments; +typedef StringRef MacroParameter; +typedef std::vector<MacroParameter> MacroParameters; + +struct Macro { + StringRef Name; + StringRef Body; + MacroParameters Parameters; + +public: + Macro(StringRef N, StringRef B, const MacroParameters &P) : + Name(N), Body(B), Parameters(P) {} +}; + +/// \brief Helper class for storing information about an active macro +/// instantiation. +struct MacroInstantiation { + /// The macro being instantiated. + const Macro *TheMacro; + + /// The macro instantiation with substitutions. + MemoryBuffer *Instantiation; + + /// The location of the instantiation. + SMLoc InstantiationLoc; + + /// The location where parsing should resume upon instantiation completion. + SMLoc ExitLoc; + +public: + MacroInstantiation(const Macro *M, SMLoc IL, SMLoc EL, + MemoryBuffer *I); +}; + +/// \brief The concrete assembly parser instance. +class AsmParser : public MCAsmParser { + friend class GenericAsmParser; + + AsmParser(const AsmParser &); // DO NOT IMPLEMENT + void operator=(const AsmParser &); // DO NOT IMPLEMENT +private: + AsmLexer Lexer; + MCContext &Ctx; + MCStreamer &Out; + const MCAsmInfo &MAI; + SourceMgr &SrcMgr; + SourceMgr::DiagHandlerTy SavedDiagHandler; + void *SavedDiagContext; + MCAsmParserExtension *GenericParser; + MCAsmParserExtension *PlatformParser; + + /// This is the current buffer index we're lexing from as managed by the + /// SourceMgr object. + int CurBuffer; + + AsmCond TheCondState; + std::vector<AsmCond> TheCondStack; + + /// DirectiveMap - This is a table handlers for directives. Each handler is + /// invoked after the directive identifier is read and is responsible for + /// parsing and validating the rest of the directive. The handler is passed + /// in the directive name and the location of the directive keyword. + StringMap<std::pair<MCAsmParserExtension*, DirectiveHandler> > DirectiveMap; + + /// MacroMap - Map of currently defined macros. + StringMap<Macro*> MacroMap; + + /// ActiveMacros - Stack of active macro instantiations. + std::vector<MacroInstantiation*> ActiveMacros; + + /// Boolean tracking whether macro substitution is enabled. + unsigned MacrosEnabled : 1; + + /// Flag tracking whether any errors have been encountered. + unsigned HadError : 1; + + /// The values from the last parsed cpp hash file line comment if any. + StringRef CppHashFilename; + int64_t CppHashLineNumber; + SMLoc CppHashLoc; + + /// AssemblerDialect. ~OU means unset value and use value provided by MAI. + unsigned AssemblerDialect; + +public: + AsmParser(SourceMgr &SM, MCContext &Ctx, MCStreamer &Out, + const MCAsmInfo &MAI); + ~AsmParser(); + + virtual bool Run(bool NoInitialTextSection, bool NoFinalize = false); + + void AddDirectiveHandler(MCAsmParserExtension *Object, + StringRef Directive, + DirectiveHandler Handler) { + DirectiveMap[Directive] = std::make_pair(Object, Handler); + } + +public: + /// @name MCAsmParser Interface + /// { + + virtual SourceMgr &getSourceManager() { return SrcMgr; } + virtual MCAsmLexer &getLexer() { return Lexer; } + virtual MCContext &getContext() { return Ctx; } + virtual MCStreamer &getStreamer() { return Out; } + virtual unsigned getAssemblerDialect() { + if (AssemblerDialect == ~0U) + return MAI.getAssemblerDialect(); + else + return AssemblerDialect; + } + virtual void setAssemblerDialect(unsigned i) { + AssemblerDialect = i; + } + + virtual bool Warning(SMLoc L, const Twine &Msg, + ArrayRef<SMRange> Ranges = ArrayRef<SMRange>()); + virtual bool Error(SMLoc L, const Twine &Msg, + ArrayRef<SMRange> Ranges = ArrayRef<SMRange>()); + + const AsmToken &Lex(); + + bool ParseExpression(const MCExpr *&Res); + virtual bool ParseExpression(const MCExpr *&Res, SMLoc &EndLoc); + virtual bool ParseParenExpression(const MCExpr *&Res, SMLoc &EndLoc); + virtual bool ParseAbsoluteExpression(int64_t &Res); + + /// } + +private: + void CheckForValidSection(); + + bool ParseStatement(); + void EatToEndOfLine(); + bool ParseCppHashLineFilenameComment(const SMLoc &L); + + bool HandleMacroEntry(StringRef Name, SMLoc NameLoc, const Macro *M); + bool expandMacro(raw_svector_ostream &OS, StringRef Body, + const MacroParameters &Parameters, + const MacroArguments &A, + const SMLoc &L); + void HandleMacroExit(); + + void PrintMacroInstantiations(); + void PrintMessage(SMLoc Loc, SourceMgr::DiagKind Kind, const Twine &Msg, + ArrayRef<SMRange> Ranges = ArrayRef<SMRange>()) const { + SrcMgr.PrintMessage(Loc, Kind, Msg, Ranges); + } + static void DiagHandler(const SMDiagnostic &Diag, void *Context); + + /// EnterIncludeFile - Enter the specified file. This returns true on failure. + bool EnterIncludeFile(const std::string &Filename); + /// ProcessIncbinFile - Process the specified file for the .incbin directive. + /// This returns true on failure. + bool ProcessIncbinFile(const std::string &Filename); + + /// \brief Reset the current lexer position to that given by \arg Loc. The + /// current token is not set; clients should ensure Lex() is called + /// subsequently. + void JumpToLoc(SMLoc Loc); + + void EatToEndOfStatement(); + + bool ParseMacroArgument(MacroArgument &MA); + bool ParseMacroArguments(const Macro *M, MacroArguments &A); + + /// \brief Parse up to the end of statement and a return the contents from the + /// current token until the end of the statement; the current token on exit + /// will be either the EndOfStatement or EOF. + StringRef ParseStringToEndOfStatement(); + + /// \brief Parse until the end of a statement or a comma is encountered, + /// return the contents from the current token up to the end or comma. + StringRef ParseStringToComma(); + + bool ParseAssignment(StringRef Name, bool allow_redef); + + bool ParsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc); + bool ParseBinOpRHS(unsigned Precedence, const MCExpr *&Res, SMLoc &EndLoc); + bool ParseParenExpr(const MCExpr *&Res, SMLoc &EndLoc); + bool ParseBracketExpr(const MCExpr *&Res, SMLoc &EndLoc); + + /// ParseIdentifier - Parse an identifier or string (as a quoted identifier) + /// and set \arg Res to the identifier contents. + bool ParseIdentifier(StringRef &Res); + + // Directive Parsing. + + // ".ascii", ".asciiz", ".string" + bool ParseDirectiveAscii(StringRef IDVal, bool ZeroTerminated); + bool ParseDirectiveValue(unsigned Size); // ".byte", ".long", ... + bool ParseDirectiveRealValue(const fltSemantics &); // ".single", ... + bool ParseDirectiveFill(); // ".fill" + bool ParseDirectiveSpace(); // ".space" + bool ParseDirectiveZero(); // ".zero" + bool ParseDirectiveSet(StringRef IDVal, bool allow_redef); // ".set", ".equ", ".equiv" + bool ParseDirectiveOrg(); // ".org" + // ".align{,32}", ".p2align{,w,l}" + bool ParseDirectiveAlign(bool IsPow2, unsigned ValueSize); + + /// ParseDirectiveSymbolAttribute - Parse a directive like ".globl" which + /// accepts a single symbol (which should be a label or an external). + bool ParseDirectiveSymbolAttribute(MCSymbolAttr Attr); + + bool ParseDirectiveComm(bool IsLocal); // ".comm" and ".lcomm" + + bool ParseDirectiveAbort(); // ".abort" + bool ParseDirectiveInclude(); // ".include" + bool ParseDirectiveIncbin(); // ".incbin" + + bool ParseDirectiveIf(SMLoc DirectiveLoc); // ".if" + // ".ifb" or ".ifnb", depending on ExpectBlank. + bool ParseDirectiveIfb(SMLoc DirectiveLoc, bool ExpectBlank); + // ".ifc" or ".ifnc", depending on ExpectEqual. + bool ParseDirectiveIfc(SMLoc DirectiveLoc, bool ExpectEqual); + // ".ifdef" or ".ifndef", depending on expect_defined + bool ParseDirectiveIfdef(SMLoc DirectiveLoc, bool expect_defined); + bool ParseDirectiveElseIf(SMLoc DirectiveLoc); // ".elseif" + bool ParseDirectiveElse(SMLoc DirectiveLoc); // ".else" + bool ParseDirectiveEndIf(SMLoc DirectiveLoc); // .endif + + /// ParseEscapedString - Parse the current token as a string which may include + /// escaped characters and return the string contents. + bool ParseEscapedString(std::string &Data); + + const MCExpr *ApplyModifierToExpr(const MCExpr *E, + MCSymbolRefExpr::VariantKind Variant); + + // Macro-like directives + Macro *ParseMacroLikeBody(SMLoc DirectiveLoc); + void InstantiateMacroLikeBody(Macro *M, SMLoc DirectiveLoc, + raw_svector_ostream &OS); + bool ParseDirectiveRept(SMLoc DirectiveLoc); // ".rept" + bool ParseDirectiveIrp(SMLoc DirectiveLoc); // ".irp" + bool ParseDirectiveIrpc(SMLoc DirectiveLoc); // ".irpc" + bool ParseDirectiveEndr(SMLoc DirectiveLoc); // ".endr" +}; + +/// \brief Generic implementations of directive handling, etc. which is shared +/// (or the default, at least) for all assembler parser. +class GenericAsmParser : public MCAsmParserExtension { + template<bool (GenericAsmParser::*Handler)(StringRef, SMLoc)> + void AddDirectiveHandler(StringRef Directive) { + getParser().AddDirectiveHandler(this, Directive, + HandleDirective<GenericAsmParser, Handler>); + } +public: + GenericAsmParser() {} + + AsmParser &getParser() { + return (AsmParser&) this->MCAsmParserExtension::getParser(); + } + + virtual void Initialize(MCAsmParser &Parser) { + // Call the base implementation. + this->MCAsmParserExtension::Initialize(Parser); + + // Debugging directives. + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveFile>(".file"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLine>(".line"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLoc>(".loc"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveStabs>(".stabs"); + + // CFI directives. + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFISections>( + ".cfi_sections"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIStartProc>( + ".cfi_startproc"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIEndProc>( + ".cfi_endproc"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIDefCfa>( + ".cfi_def_cfa"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIDefCfaOffset>( + ".cfi_def_cfa_offset"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIAdjustCfaOffset>( + ".cfi_adjust_cfa_offset"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIDefCfaRegister>( + ".cfi_def_cfa_register"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIOffset>( + ".cfi_offset"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveCFIRelOffset>( + ".cfi_rel_offset"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIPersonalityOrLsda>(".cfi_personality"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIPersonalityOrLsda>(".cfi_lsda"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIRememberState>(".cfi_remember_state"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIRestoreState>(".cfi_restore_state"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFISameValue>(".cfi_same_value"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIRestore>(".cfi_restore"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFIEscape>(".cfi_escape"); + AddDirectiveHandler< + &GenericAsmParser::ParseDirectiveCFISignalFrame>(".cfi_signal_frame"); + + // Macro directives. + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveMacrosOnOff>( + ".macros_on"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveMacrosOnOff>( + ".macros_off"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveMacro>(".macro"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveEndMacro>(".endm"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveEndMacro>(".endmacro"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectivePurgeMacro>(".purgem"); + + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLEB128>(".sleb128"); + AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLEB128>(".uleb128"); + } + + bool ParseRegisterOrRegisterNumber(int64_t &Register, SMLoc DirectiveLoc); + + bool ParseDirectiveFile(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveLine(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveLoc(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveStabs(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFISections(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIStartProc(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIEndProc(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIDefCfa(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIDefCfaOffset(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIAdjustCfaOffset(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIDefCfaRegister(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIOffset(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIRelOffset(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIPersonalityOrLsda(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIRememberState(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIRestoreState(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFISameValue(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIRestore(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFIEscape(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveCFISignalFrame(StringRef, SMLoc DirectiveLoc); + + bool ParseDirectiveMacrosOnOff(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveMacro(StringRef, SMLoc DirectiveLoc); + bool ParseDirectiveEndMacro(StringRef, SMLoc DirectiveLoc); + bool ParseDirectivePurgeMacro(StringRef, SMLoc DirectiveLoc); + + bool ParseDirectiveLEB128(StringRef, SMLoc); +}; + +} + +namespace llvm { + +extern MCAsmParserExtension *createDarwinAsmParser(); +extern MCAsmParserExtension *createELFAsmParser(); +extern MCAsmParserExtension *createCOFFAsmParser(); + +} + +enum { DEFAULT_ADDRSPACE = 0 }; + +AsmParser::AsmParser(SourceMgr &_SM, MCContext &_Ctx, + MCStreamer &_Out, const MCAsmInfo &_MAI) + : Lexer(_MAI), Ctx(_Ctx), Out(_Out), MAI(_MAI), SrcMgr(_SM), + GenericParser(new GenericAsmParser), PlatformParser(0), + CurBuffer(0), MacrosEnabled(true), CppHashLineNumber(0), + AssemblerDialect(~0U) { + // Save the old handler. + SavedDiagHandler = SrcMgr.getDiagHandler(); + SavedDiagContext = SrcMgr.getDiagContext(); + // Set our own handler which calls the saved handler. + SrcMgr.setDiagHandler(DiagHandler, this); + Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer)); + + // Initialize the generic parser. + GenericParser->Initialize(*this); + + // Initialize the platform / file format parser. + // + // FIXME: This is a hack, we need to (majorly) cleanup how these objects are + // created. + if (_MAI.hasMicrosoftFastStdCallMangling()) { + PlatformParser = createCOFFAsmParser(); + PlatformParser->Initialize(*this); + } else if (_MAI.hasSubsectionsViaSymbols()) { + PlatformParser = createDarwinAsmParser(); + PlatformParser->Initialize(*this); + } else { + PlatformParser = createELFAsmParser(); + PlatformParser->Initialize(*this); + } +} + +AsmParser::~AsmParser() { + assert(ActiveMacros.empty() && "Unexpected active macro instantiation!"); + + // Destroy any macros. + for (StringMap<Macro*>::iterator it = MacroMap.begin(), + ie = MacroMap.end(); it != ie; ++it) + delete it->getValue(); + + delete PlatformParser; + delete GenericParser; +} + +void AsmParser::PrintMacroInstantiations() { + // Print the active macro instantiation stack. + for (std::vector<MacroInstantiation*>::const_reverse_iterator + it = ActiveMacros.rbegin(), ie = ActiveMacros.rend(); it != ie; ++it) + PrintMessage((*it)->InstantiationLoc, SourceMgr::DK_Note, + "while in macro instantiation"); +} + +bool AsmParser::Warning(SMLoc L, const Twine &Msg, ArrayRef<SMRange> Ranges) { + if (FatalAssemblerWarnings) + return Error(L, Msg, Ranges); + PrintMessage(L, SourceMgr::DK_Warning, Msg, Ranges); + PrintMacroInstantiations(); + return false; +} + +bool AsmParser::Error(SMLoc L, const Twine &Msg, ArrayRef<SMRange> Ranges) { + HadError = true; + PrintMessage(L, SourceMgr::DK_Error, Msg, Ranges); + PrintMacroInstantiations(); + return true; +} + +bool AsmParser::EnterIncludeFile(const std::string &Filename) { + std::string IncludedFile; + int NewBuf = SrcMgr.AddIncludeFile(Filename, Lexer.getLoc(), IncludedFile); + if (NewBuf == -1) + return true; + + CurBuffer = NewBuf; + + Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer)); + + return false; +} + +/// Process the specified .incbin file by seaching for it in the include paths +/// then just emitting the byte contents of the file to the streamer. This +/// returns true on failure. +bool AsmParser::ProcessIncbinFile(const std::string &Filename) { + std::string IncludedFile; + int NewBuf = SrcMgr.AddIncludeFile(Filename, Lexer.getLoc(), IncludedFile); + if (NewBuf == -1) + return true; + + // Pick up the bytes from the file and emit them. + getStreamer().EmitBytes(SrcMgr.getMemoryBuffer(NewBuf)->getBuffer(), + DEFAULT_ADDRSPACE); + return false; +} + +void AsmParser::JumpToLoc(SMLoc Loc) { + CurBuffer = SrcMgr.FindBufferContainingLoc(Loc); + Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer), Loc.getPointer()); +} + +const AsmToken &AsmParser::Lex() { + const AsmToken *tok = &Lexer.Lex(); + + if (tok->is(AsmToken::Eof)) { + // If this is the end of an included file, pop the parent file off the + // include stack. + SMLoc ParentIncludeLoc = SrcMgr.getParentIncludeLoc(CurBuffer); + if (ParentIncludeLoc != SMLoc()) { + JumpToLoc(ParentIncludeLoc); + tok = &Lexer.Lex(); + } + } + + if (tok->is(AsmToken::Error)) + Error(Lexer.getErrLoc(), Lexer.getErr()); + + return *tok; +} + +bool AsmParser::Run(bool NoInitialTextSection, bool NoFinalize) { + // Create the initial section, if requested. + if (!NoInitialTextSection) + Out.InitSections(); + + // Prime the lexer. + Lex(); + + HadError = false; + AsmCond StartingCondState = TheCondState; + + // If we are generating dwarf for assembly source files save the initial text + // section and generate a .file directive. + if (getContext().getGenDwarfForAssembly()) { + getContext().setGenDwarfSection(getStreamer().getCurrentSection()); + MCSymbol *SectionStartSym = getContext().CreateTempSymbol(); + getStreamer().EmitLabel(SectionStartSym); + getContext().setGenDwarfSectionStartSym(SectionStartSym); + getStreamer().EmitDwarfFileDirective(getContext().nextGenDwarfFileNumber(), + StringRef(), SrcMgr.getMemoryBuffer(CurBuffer)->getBufferIdentifier()); + } + + // While we have input, parse each statement. + while (Lexer.isNot(AsmToken::Eof)) { + if (!ParseStatement()) continue; + + // We had an error, validate that one was emitted and recover by skipping to + // the next line. + assert(HadError && "Parse statement returned an error, but none emitted!"); + EatToEndOfStatement(); + } + + if (TheCondState.TheCond != StartingCondState.TheCond || + TheCondState.Ignore != StartingCondState.Ignore) + return TokError("unmatched .ifs or .elses"); + + // Check to see there are no empty DwarfFile slots. + const std::vector<MCDwarfFile *> &MCDwarfFiles = + getContext().getMCDwarfFiles(); + for (unsigned i = 1; i < MCDwarfFiles.size(); i++) { + if (!MCDwarfFiles[i]) + TokError("unassigned file number: " + Twine(i) + " for .file directives"); + } + + // Check to see that all assembler local symbols were actually defined. + // Targets that don't do subsections via symbols may not want this, though, + // so conservatively exclude them. Only do this if we're finalizing, though, + // as otherwise we won't necessarilly have seen everything yet. + if (!NoFinalize && MAI.hasSubsectionsViaSymbols()) { + const MCContext::SymbolTable &Symbols = getContext().getSymbols(); + for (MCContext::SymbolTable::const_iterator i = Symbols.begin(), + e = Symbols.end(); + i != e; ++i) { + MCSymbol *Sym = i->getValue(); + // Variable symbols may not be marked as defined, so check those + // explicitly. If we know it's a variable, we have a definition for + // the purposes of this check. + if (Sym->isTemporary() && !Sym->isVariable() && !Sym->isDefined()) + // FIXME: We would really like to refer back to where the symbol was + // first referenced for a source location. We need to add something + // to track that. Currently, we just point to the end of the file. + PrintMessage(getLexer().getLoc(), SourceMgr::DK_Error, + "assembler local symbol '" + Sym->getName() + + "' not defined"); + } + } + + + // Finalize the output stream if there are no errors and if the client wants + // us to. + if (!HadError && !NoFinalize) + Out.Finish(); + + return HadError; +} + +void AsmParser::CheckForValidSection() { + if (!getStreamer().getCurrentSection()) { + TokError("expected section directive before assembly directive"); + Out.SwitchSection(Ctx.getMachOSection( + "__TEXT", "__text", + MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS, + 0, SectionKind::getText())); + } +} + +/// EatToEndOfStatement - Throw away the rest of the line for testing purposes. +void AsmParser::EatToEndOfStatement() { + while (Lexer.isNot(AsmToken::EndOfStatement) && + Lexer.isNot(AsmToken::Eof)) + Lex(); + + // Eat EOL. + if (Lexer.is(AsmToken::EndOfStatement)) + Lex(); +} + +StringRef AsmParser::ParseStringToEndOfStatement() { + const char *Start = getTok().getLoc().getPointer(); + + while (Lexer.isNot(AsmToken::EndOfStatement) && + Lexer.isNot(AsmToken::Eof)) + Lex(); + + const char *End = getTok().getLoc().getPointer(); + return StringRef(Start, End - Start); +} + +StringRef AsmParser::ParseStringToComma() { + const char *Start = getTok().getLoc().getPointer(); + + while (Lexer.isNot(AsmToken::EndOfStatement) && + Lexer.isNot(AsmToken::Comma) && + Lexer.isNot(AsmToken::Eof)) + Lex(); + + const char *End = getTok().getLoc().getPointer(); + return StringRef(Start, End - Start); +} + +/// ParseParenExpr - Parse a paren expression and return it. +/// NOTE: This assumes the leading '(' has already been consumed. +/// +/// parenexpr ::= expr) +/// +bool AsmParser::ParseParenExpr(const MCExpr *&Res, SMLoc &EndLoc) { + if (ParseExpression(Res)) return true; + if (Lexer.isNot(AsmToken::RParen)) + return TokError("expected ')' in parentheses expression"); + EndLoc = Lexer.getLoc(); + Lex(); + return false; +} + +/// ParseBracketExpr - Parse a bracket expression and return it. +/// NOTE: This assumes the leading '[' has already been consumed. +/// +/// bracketexpr ::= expr] +/// +bool AsmParser::ParseBracketExpr(const MCExpr *&Res, SMLoc &EndLoc) { + if (ParseExpression(Res)) return true; + if (Lexer.isNot(AsmToken::RBrac)) + return TokError("expected ']' in brackets expression"); + EndLoc = Lexer.getLoc(); + Lex(); + return false; +} + +/// ParsePrimaryExpr - Parse a primary expression and return it. +/// primaryexpr ::= (parenexpr +/// primaryexpr ::= symbol +/// primaryexpr ::= number +/// primaryexpr ::= '.' +/// primaryexpr ::= ~,+,- primaryexpr +bool AsmParser::ParsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) { + switch (Lexer.getKind()) { + default: + return TokError("unknown token in expression"); + // If we have an error assume that we've already handled it. + case AsmToken::Error: + return true; + case AsmToken::Exclaim: + Lex(); // Eat the operator. + if (ParsePrimaryExpr(Res, EndLoc)) + return true; + Res = MCUnaryExpr::CreateLNot(Res, getContext()); + return false; + case AsmToken::Dollar: + case AsmToken::String: + case AsmToken::Identifier: { + EndLoc = Lexer.getLoc(); + + StringRef Identifier; + if (ParseIdentifier(Identifier)) + return true; + + // This is a symbol reference. + std::pair<StringRef, StringRef> Split = Identifier.split('@'); + MCSymbol *Sym = getContext().GetOrCreateSymbol(Split.first); + + // Lookup the symbol variant if used. + MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None; + if (Split.first.size() != Identifier.size()) { + Variant = MCSymbolRefExpr::getVariantKindForName(Split.second); + if (Variant == MCSymbolRefExpr::VK_Invalid) { + Variant = MCSymbolRefExpr::VK_None; + return TokError("invalid variant '" + Split.second + "'"); + } + } + + // If this is an absolute variable reference, substitute it now to preserve + // semantics in the face of reassignment. + if (Sym->isVariable() && isa<MCConstantExpr>(Sym->getVariableValue())) { + if (Variant) + return Error(EndLoc, "unexpected modifier on variable reference"); + + Res = Sym->getVariableValue(); + return false; + } + + // Otherwise create a symbol ref. + Res = MCSymbolRefExpr::Create(Sym, Variant, getContext()); + return false; + } + case AsmToken::Integer: { + SMLoc Loc = getTok().getLoc(); + int64_t IntVal = getTok().getIntVal(); + Res = MCConstantExpr::Create(IntVal, getContext()); + EndLoc = Lexer.getLoc(); + Lex(); // Eat token. + // Look for 'b' or 'f' following an Integer as a directional label + if (Lexer.getKind() == AsmToken::Identifier) { + StringRef IDVal = getTok().getString(); + if (IDVal == "f" || IDVal == "b"){ + MCSymbol *Sym = Ctx.GetDirectionalLocalSymbol(IntVal, + IDVal == "f" ? 1 : 0); + Res = MCSymbolRefExpr::Create(Sym, MCSymbolRefExpr::VK_None, + getContext()); + if (IDVal == "b" && Sym->isUndefined()) + return Error(Loc, "invalid reference to undefined symbol"); + EndLoc = Lexer.getLoc(); + Lex(); // Eat identifier. + } + } + return false; + } + case AsmToken::Real: { + APFloat RealVal(APFloat::IEEEdouble, getTok().getString()); + uint64_t IntVal = RealVal.bitcastToAPInt().getZExtValue(); + Res = MCConstantExpr::Create(IntVal, getContext()); + Lex(); // Eat token. + return false; + } + case AsmToken::Dot: { + // This is a '.' reference, which references the current PC. Emit a + // temporary label to the streamer and refer to it. + MCSymbol *Sym = Ctx.CreateTempSymbol(); + Out.EmitLabel(Sym); + Res = MCSymbolRefExpr::Create(Sym, MCSymbolRefExpr::VK_None, getContext()); + EndLoc = Lexer.getLoc(); + Lex(); // Eat identifier. + return false; + } + case AsmToken::LParen: + Lex(); // Eat the '('. + return ParseParenExpr(Res, EndLoc); + case AsmToken::LBrac: + if (!PlatformParser->HasBracketExpressions()) + return TokError("brackets expression not supported on this target"); + Lex(); // Eat the '['. + return ParseBracketExpr(Res, EndLoc); + case AsmToken::Minus: + Lex(); // Eat the operator. + if (ParsePrimaryExpr(Res, EndLoc)) + return true; + Res = MCUnaryExpr::CreateMinus(Res, getContext()); + return false; + case AsmToken::Plus: + Lex(); // Eat the operator. + if (ParsePrimaryExpr(Res, EndLoc)) + return true; + Res = MCUnaryExpr::CreatePlus(Res, getContext()); + return false; + case AsmToken::Tilde: + Lex(); // Eat the operator. + if (ParsePrimaryExpr(Res, EndLoc)) + return true; + Res = MCUnaryExpr::CreateNot(Res, getContext()); + return false; + } +} + +bool AsmParser::ParseExpression(const MCExpr *&Res) { + SMLoc EndLoc; + return ParseExpression(Res, EndLoc); +} + +const MCExpr * +AsmParser::ApplyModifierToExpr(const MCExpr *E, + MCSymbolRefExpr::VariantKind Variant) { + // Recurse over the given expression, rebuilding it to apply the given variant + // if there is exactly one symbol. + switch (E->getKind()) { + case MCExpr::Target: + case MCExpr::Constant: + return 0; + + case MCExpr::SymbolRef: { + const MCSymbolRefExpr *SRE = cast<MCSymbolRefExpr>(E); + + if (SRE->getKind() != MCSymbolRefExpr::VK_None) { + TokError("invalid variant on expression '" + + getTok().getIdentifier() + "' (already modified)"); + return E; + } + + return MCSymbolRefExpr::Create(&SRE->getSymbol(), Variant, getContext()); + } + + case MCExpr::Unary: { + const MCUnaryExpr *UE = cast<MCUnaryExpr>(E); + const MCExpr *Sub = ApplyModifierToExpr(UE->getSubExpr(), Variant); + if (!Sub) + return 0; + return MCUnaryExpr::Create(UE->getOpcode(), Sub, getContext()); + } + + case MCExpr::Binary: { + const MCBinaryExpr *BE = cast<MCBinaryExpr>(E); + const MCExpr *LHS = ApplyModifierToExpr(BE->getLHS(), Variant); + const MCExpr *RHS = ApplyModifierToExpr(BE->getRHS(), Variant); + + if (!LHS && !RHS) + return 0; + + if (!LHS) LHS = BE->getLHS(); + if (!RHS) RHS = BE->getRHS(); + + return MCBinaryExpr::Create(BE->getOpcode(), LHS, RHS, getContext()); + } + } + + llvm_unreachable("Invalid expression kind!"); +} + +/// ParseExpression - Parse an expression and return it. +/// +/// expr ::= expr &&,|| expr -> lowest. +/// expr ::= expr |,^,&,! expr +/// expr ::= expr ==,!=,<>,<,<=,>,>= expr +/// expr ::= expr <<,>> expr +/// expr ::= expr +,- expr +/// expr ::= expr *,/,% expr -> highest. +/// expr ::= primaryexpr +/// +bool AsmParser::ParseExpression(const MCExpr *&Res, SMLoc &EndLoc) { + // Parse the expression. + Res = 0; + if (ParsePrimaryExpr(Res, EndLoc) || ParseBinOpRHS(1, Res, EndLoc)) + return true; + + // As a special case, we support 'a op b @ modifier' by rewriting the + // expression to include the modifier. This is inefficient, but in general we + // expect users to use 'a@modifier op b'. + if (Lexer.getKind() == AsmToken::At) { + Lex(); + + if (Lexer.isNot(AsmToken::Identifier)) + return TokError("unexpected symbol modifier following '@'"); + + MCSymbolRefExpr::VariantKind Variant = + MCSymbolRefExpr::getVariantKindForName(getTok().getIdentifier()); + if (Variant == MCSymbolRefExpr::VK_Invalid) + return TokError("invalid variant '" + getTok().getIdentifier() + "'"); + + const MCExpr *ModifiedRes = ApplyModifierToExpr(Res, Variant); + if (!ModifiedRes) { + return TokError("invalid modifier '" + getTok().getIdentifier() + + "' (no symbols present)"); + } + + Res = ModifiedRes; + Lex(); + } + + // Try to constant fold it up front, if possible. + int64_t Value; + if (Res->EvaluateAsAbsolute(Value)) + Res = MCConstantExpr::Create(Value, getContext()); + + return false; +} + +bool AsmParser::ParseParenExpression(const MCExpr *&Res, SMLoc &EndLoc) { + Res = 0; + return ParseParenExpr(Res, EndLoc) || + ParseBinOpRHS(1, Res, EndLoc); +} + +bool AsmParser::ParseAbsoluteExpression(int64_t &Res) { + const MCExpr *Expr; + + SMLoc StartLoc = Lexer.getLoc(); + if (ParseExpression(Expr)) + return true; + + if (!Expr->EvaluateAsAbsolute(Res)) + return Error(StartLoc, "expected absolute expression"); + + return false; +} + +static unsigned getBinOpPrecedence(AsmToken::TokenKind K, + MCBinaryExpr::Opcode &Kind) { + switch (K) { + default: + return 0; // not a binop. + + // Lowest Precedence: &&, || + case AsmToken::AmpAmp: + Kind = MCBinaryExpr::LAnd; + return 1; + case AsmToken::PipePipe: + Kind = MCBinaryExpr::LOr; + return 1; + + + // Low Precedence: |, &, ^ + // + // FIXME: gas seems to support '!' as an infix operator? + case AsmToken::Pipe: + Kind = MCBinaryExpr::Or; + return 2; + case AsmToken::Caret: + Kind = MCBinaryExpr::Xor; + return 2; + case AsmToken::Amp: + Kind = MCBinaryExpr::And; + return 2; + + // Low Intermediate Precedence: ==, !=, <>, <, <=, >, >= + case AsmToken::EqualEqual: + Kind = MCBinaryExpr::EQ; + return 3; + case AsmToken::ExclaimEqual: + case AsmToken::LessGreater: + Kind = MCBinaryExpr::NE; + return 3; + case AsmToken::Less: + Kind = MCBinaryExpr::LT; + return 3; + case AsmToken::LessEqual: + Kind = MCBinaryExpr::LTE; + return 3; + case AsmToken::Greater: + Kind = MCBinaryExpr::GT; + return 3; + case AsmToken::GreaterEqual: + Kind = MCBinaryExpr::GTE; + return 3; + + // Intermediate Precedence: <<, >> + case AsmToken::LessLess: + Kind = MCBinaryExpr::Shl; + return 4; + case AsmToken::GreaterGreater: + Kind = MCBinaryExpr::Shr; + return 4; + + // High Intermediate Precedence: +, - + case AsmToken::Plus: + Kind = MCBinaryExpr::Add; + return 5; + case AsmToken::Minus: + Kind = MCBinaryExpr::Sub; + return 5; + + // Highest Precedence: *, /, % + case AsmToken::Star: + Kind = MCBinaryExpr::Mul; + return 6; + case AsmToken::Slash: + Kind = MCBinaryExpr::Div; + return 6; + case AsmToken::Percent: + Kind = MCBinaryExpr::Mod; + return 6; + } +} + + +/// ParseBinOpRHS - Parse all binary operators with precedence >= 'Precedence'. +/// Res contains the LHS of the expression on input. +bool AsmParser::ParseBinOpRHS(unsigned Precedence, const MCExpr *&Res, + SMLoc &EndLoc) { + while (1) { + MCBinaryExpr::Opcode Kind = MCBinaryExpr::Add; + unsigned TokPrec = getBinOpPrecedence(Lexer.getKind(), Kind); + + // If the next token is lower precedence than we are allowed to eat, return + // successfully with what we ate already. + if (TokPrec < Precedence) + return false; + + Lex(); + + // Eat the next primary expression. + const MCExpr *RHS; + if (ParsePrimaryExpr(RHS, EndLoc)) return true; + + // If BinOp binds less tightly with RHS than the operator after RHS, let + // the pending operator take RHS as its LHS. + MCBinaryExpr::Opcode Dummy; + unsigned NextTokPrec = getBinOpPrecedence(Lexer.getKind(), Dummy); + if (TokPrec < NextTokPrec) { + if (ParseBinOpRHS(Precedence+1, RHS, EndLoc)) return true; + } + + // Merge LHS and RHS according to operator. + Res = MCBinaryExpr::Create(Kind, Res, RHS, getContext()); + } +} + + + + +/// ParseStatement: +/// ::= EndOfStatement +/// ::= Label* Directive ...Operands... EndOfStatement +/// ::= Label* Identifier OperandList* EndOfStatement +bool AsmParser::ParseStatement() { + if (Lexer.is(AsmToken::EndOfStatement)) { + Out.AddBlankLine(); + Lex(); + return false; + } + + // Statements always start with an identifier or are a full line comment. + AsmToken ID = getTok(); + SMLoc IDLoc = ID.getLoc(); + StringRef IDVal; + int64_t LocalLabelVal = -1; + // A full line comment is a '#' as the first token. + if (Lexer.is(AsmToken::Hash)) + return ParseCppHashLineFilenameComment(IDLoc); + + // Allow an integer followed by a ':' as a directional local label. + if (Lexer.is(AsmToken::Integer)) { + LocalLabelVal = getTok().getIntVal(); + if (LocalLabelVal < 0) { + if (!TheCondState.Ignore) + return TokError("unexpected token at start of statement"); + IDVal = ""; + } + else { + IDVal = getTok().getString(); + Lex(); // Consume the integer token to be used as an identifier token. + if (Lexer.getKind() != AsmToken::Colon) { + if (!TheCondState.Ignore) + return TokError("unexpected token at start of statement"); + } + } + + } else if (Lexer.is(AsmToken::Dot)) { + // Treat '.' as a valid identifier in this context. + Lex(); + IDVal = "."; + + } else if (ParseIdentifier(IDVal)) { + if (!TheCondState.Ignore) + return TokError("unexpected token at start of statement"); + IDVal = ""; + } + + + // Handle conditional assembly here before checking for skipping. We + // have to do this so that .endif isn't skipped in a ".if 0" block for + // example. + if (IDVal == ".if") + return ParseDirectiveIf(IDLoc); + if (IDVal == ".ifb") + return ParseDirectiveIfb(IDLoc, true); + if (IDVal == ".ifnb") + return ParseDirectiveIfb(IDLoc, false); + if (IDVal == ".ifc") + return ParseDirectiveIfc(IDLoc, true); + if (IDVal == ".ifnc") + return ParseDirectiveIfc(IDLoc, false); + if (IDVal == ".ifdef") + return ParseDirectiveIfdef(IDLoc, true); + if (IDVal == ".ifndef" || IDVal == ".ifnotdef") + return ParseDirectiveIfdef(IDLoc, false); + if (IDVal == ".elseif") + return ParseDirectiveElseIf(IDLoc); + if (IDVal == ".else") + return ParseDirectiveElse(IDLoc); + if (IDVal == ".endif") + return ParseDirectiveEndIf(IDLoc); + + // If we are in a ".if 0" block, ignore this statement. + if (TheCondState.Ignore) { + EatToEndOfStatement(); + return false; + } + + // FIXME: Recurse on local labels? + + // See what kind of statement we have. + switch (Lexer.getKind()) { + case AsmToken::Colon: { + CheckForValidSection(); + + // identifier ':' -> Label. + Lex(); + + // Diagnose attempt to use '.' as a label. + if (IDVal == ".") + return Error(IDLoc, "invalid use of pseudo-symbol '.' as a label"); + + // Diagnose attempt to use a variable as a label. + // + // FIXME: Diagnostics. Note the location of the definition as a label. + // FIXME: This doesn't diagnose assignment to a symbol which has been + // implicitly marked as external. + MCSymbol *Sym; + if (LocalLabelVal == -1) + Sym = getContext().GetOrCreateSymbol(IDVal); + else + Sym = Ctx.CreateDirectionalLocalSymbol(LocalLabelVal); + if (!Sym->isUndefined() || Sym->isVariable()) + return Error(IDLoc, "invalid symbol redefinition"); + + // Emit the label. + Out.EmitLabel(Sym); + + // If we are generating dwarf for assembly source files then gather the + // info to make a dwarf label entry for this label if needed. + if (getContext().getGenDwarfForAssembly()) + MCGenDwarfLabelEntry::Make(Sym, &getStreamer(), getSourceManager(), + IDLoc); + + // Consume any end of statement token, if present, to avoid spurious + // AddBlankLine calls(). + if (Lexer.is(AsmToken::EndOfStatement)) { + Lex(); + if (Lexer.is(AsmToken::Eof)) + return false; + } + + return ParseStatement(); + } + + case AsmToken::Equal: + // identifier '=' ... -> assignment statement + Lex(); + + return ParseAssignment(IDVal, true); + + default: // Normal instruction or directive. + break; + } + + // If macros are enabled, check to see if this is a macro instantiation. + if (MacrosEnabled) + if (const Macro *M = MacroMap.lookup(IDVal)) + return HandleMacroEntry(IDVal, IDLoc, M); + + // Otherwise, we have a normal instruction or directive. + if (IDVal[0] == '.' && IDVal != ".") { + + // Target hook for parsing target specific directives. + if (!getTargetParser().ParseDirective(ID)) + return false; + + // Assembler features + if (IDVal == ".set" || IDVal == ".equ") + return ParseDirectiveSet(IDVal, true); + if (IDVal == ".equiv") + return ParseDirectiveSet(IDVal, false); + + // Data directives + + if (IDVal == ".ascii") + return ParseDirectiveAscii(IDVal, false); + if (IDVal == ".asciz" || IDVal == ".string") + return ParseDirectiveAscii(IDVal, true); + + if (IDVal == ".byte") + return ParseDirectiveValue(1); + if (IDVal == ".short") + return ParseDirectiveValue(2); + if (IDVal == ".value") + return ParseDirectiveValue(2); + if (IDVal == ".2byte") + return ParseDirectiveValue(2); + if (IDVal == ".long") + return ParseDirectiveValue(4); + if (IDVal == ".int") + return ParseDirectiveValue(4); + if (IDVal == ".4byte") + return ParseDirectiveValue(4); + if (IDVal == ".quad") + return ParseDirectiveValue(8); + if (IDVal == ".8byte") + return ParseDirectiveValue(8); + if (IDVal == ".single" || IDVal == ".float") + return ParseDirectiveRealValue(APFloat::IEEEsingle); + if (IDVal == ".double") + return ParseDirectiveRealValue(APFloat::IEEEdouble); + + if (IDVal == ".align") { + bool IsPow2 = !getContext().getAsmInfo().getAlignmentIsInBytes(); + return ParseDirectiveAlign(IsPow2, /*ExprSize=*/1); + } + if (IDVal == ".align32") { + bool IsPow2 = !getContext().getAsmInfo().getAlignmentIsInBytes(); + return ParseDirectiveAlign(IsPow2, /*ExprSize=*/4); + } + if (IDVal == ".balign") + return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/1); + if (IDVal == ".balignw") + return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/2); + if (IDVal == ".balignl") + return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/4); + if (IDVal == ".p2align") + return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/1); + if (IDVal == ".p2alignw") + return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/2); + if (IDVal == ".p2alignl") + return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/4); + + if (IDVal == ".org") + return ParseDirectiveOrg(); + + if (IDVal == ".fill") + return ParseDirectiveFill(); + if (IDVal == ".space" || IDVal == ".skip") + return ParseDirectiveSpace(); + if (IDVal == ".zero") + return ParseDirectiveZero(); + + // Symbol attribute directives + + if (IDVal == ".extern") { + EatToEndOfStatement(); // .extern is the default, ignore it. + return false; + } + if (IDVal == ".globl" || IDVal == ".global") + return ParseDirectiveSymbolAttribute(MCSA_Global); + if (IDVal == ".indirect_symbol") + return ParseDirectiveSymbolAttribute(MCSA_IndirectSymbol); + if (IDVal == ".lazy_reference") + return ParseDirectiveSymbolAttribute(MCSA_LazyReference); + if (IDVal == ".no_dead_strip") + return ParseDirectiveSymbolAttribute(MCSA_NoDeadStrip); + if (IDVal == ".symbol_resolver") + return ParseDirectiveSymbolAttribute(MCSA_SymbolResolver); + if (IDVal == ".private_extern") + return ParseDirectiveSymbolAttribute(MCSA_PrivateExtern); + if (IDVal == ".reference") + return ParseDirectiveSymbolAttribute(MCSA_Reference); + if (IDVal == ".weak_definition") + return ParseDirectiveSymbolAttribute(MCSA_WeakDefinition); + if (IDVal == ".weak_reference") + return ParseDirectiveSymbolAttribute(MCSA_WeakReference); + if (IDVal == ".weak_def_can_be_hidden") + return ParseDirectiveSymbolAttribute(MCSA_WeakDefAutoPrivate); + + if (IDVal == ".comm" || IDVal == ".common") + return ParseDirectiveComm(/*IsLocal=*/false); + if (IDVal == ".lcomm") + return ParseDirectiveComm(/*IsLocal=*/true); + + if (IDVal == ".abort") + return ParseDirectiveAbort(); + if (IDVal == ".include") + return ParseDirectiveInclude(); + if (IDVal == ".incbin") + return ParseDirectiveIncbin(); + + if (IDVal == ".code16" || IDVal == ".code16gcc") + return TokError(Twine(IDVal) + " not supported yet"); + + // Macro-like directives + if (IDVal == ".rept") + return ParseDirectiveRept(IDLoc); + if (IDVal == ".irp") + return ParseDirectiveIrp(IDLoc); + if (IDVal == ".irpc") + return ParseDirectiveIrpc(IDLoc); + if (IDVal == ".endr") + return ParseDirectiveEndr(IDLoc); + + // Look up the handler in the handler table. + std::pair<MCAsmParserExtension*, DirectiveHandler> Handler = + DirectiveMap.lookup(IDVal); + if (Handler.first) + return (*Handler.second)(Handler.first, IDVal, IDLoc); + + + return Error(IDLoc, "unknown directive"); + } + + CheckForValidSection(); + + // Canonicalize the opcode to lower case. + SmallString<128> Opcode; + for (unsigned i = 0, e = IDVal.size(); i != e; ++i) + Opcode.push_back(tolower(IDVal[i])); + + SmallVector<MCParsedAsmOperand*, 8> ParsedOperands; + bool HadError = getTargetParser().ParseInstruction(Opcode.str(), IDLoc, + ParsedOperands); + + // Dump the parsed representation, if requested. + if (getShowParsedOperands()) { + SmallString<256> Str; + raw_svector_ostream OS(Str); + OS << "parsed instruction: ["; + for (unsigned i = 0; i != ParsedOperands.size(); ++i) { + if (i != 0) + OS << ", "; + ParsedOperands[i]->print(OS); + } + OS << "]"; + + PrintMessage(IDLoc, SourceMgr::DK_Note, OS.str()); + } + + // If we are generating dwarf for assembly source files and the current + // section is the initial text section then generate a .loc directive for + // the instruction. + if (!HadError && getContext().getGenDwarfForAssembly() && + getContext().getGenDwarfSection() == getStreamer().getCurrentSection() ) { + getStreamer().EmitDwarfLocDirective(getContext().getGenDwarfFileNumber(), + SrcMgr.FindLineNumber(IDLoc, CurBuffer), + 0, DWARF2_LINE_DEFAULT_IS_STMT ? + DWARF2_FLAG_IS_STMT : 0, 0, 0, + StringRef()); + } + + // If parsing succeeded, match the instruction. + if (!HadError) + HadError = getTargetParser().MatchAndEmitInstruction(IDLoc, ParsedOperands, + Out); + + // Free any parsed operands. + for (unsigned i = 0, e = ParsedOperands.size(); i != e; ++i) + delete ParsedOperands[i]; + + // Don't skip the rest of the line, the instruction parser is responsible for + // that. + return false; +} + +/// EatToEndOfLine uses the Lexer to eat the characters to the end of the line +/// since they may not be able to be tokenized to get to the end of line token. +void AsmParser::EatToEndOfLine() { + if (!Lexer.is(AsmToken::EndOfStatement)) + Lexer.LexUntilEndOfLine(); + // Eat EOL. + Lex(); +} + +/// ParseCppHashLineFilenameComment as this: +/// ::= # number "filename" +/// or just as a full line comment if it doesn't have a number and a string. +bool AsmParser::ParseCppHashLineFilenameComment(const SMLoc &L) { + Lex(); // Eat the hash token. + + if (getLexer().isNot(AsmToken::Integer)) { + // Consume the line since in cases it is not a well-formed line directive, + // as if were simply a full line comment. + EatToEndOfLine(); + return false; + } + + int64_t LineNumber = getTok().getIntVal(); + Lex(); + + if (getLexer().isNot(AsmToken::String)) { + EatToEndOfLine(); + return false; + } + + StringRef Filename = getTok().getString(); + // Get rid of the enclosing quotes. + Filename = Filename.substr(1, Filename.size()-2); + + // Save the SMLoc, Filename and LineNumber for later use by diagnostics. + CppHashLoc = L; + CppHashFilename = Filename; + CppHashLineNumber = LineNumber; + + // Ignore any trailing characters, they're just comment. + EatToEndOfLine(); + return false; +} + +/// DiagHandler - will use the last parsed cpp hash line filename comment +/// for the Filename and LineNo if any in the diagnostic. +void AsmParser::DiagHandler(const SMDiagnostic &Diag, void *Context) { + const AsmParser *Parser = static_cast<const AsmParser*>(Context); + raw_ostream &OS = errs(); + + const SourceMgr &DiagSrcMgr = *Diag.getSourceMgr(); + const SMLoc &DiagLoc = Diag.getLoc(); + int DiagBuf = DiagSrcMgr.FindBufferContainingLoc(DiagLoc); + int CppHashBuf = Parser->SrcMgr.FindBufferContainingLoc(Parser->CppHashLoc); + + // Like SourceMgr::PrintMessage() we need to print the include stack if any + // before printing the message. + int DiagCurBuffer = DiagSrcMgr.FindBufferContainingLoc(DiagLoc); + if (!Parser->SavedDiagHandler && DiagCurBuffer > 0) { + SMLoc ParentIncludeLoc = DiagSrcMgr.getParentIncludeLoc(DiagCurBuffer); + DiagSrcMgr.PrintIncludeStack(ParentIncludeLoc, OS); + } + + // If we have not parsed a cpp hash line filename comment or the source + // manager changed or buffer changed (like in a nested include) then just + // print the normal diagnostic using its Filename and LineNo. + if (!Parser->CppHashLineNumber || + &DiagSrcMgr != &Parser->SrcMgr || + DiagBuf != CppHashBuf) { + if (Parser->SavedDiagHandler) + Parser->SavedDiagHandler(Diag, Parser->SavedDiagContext); + else + Diag.print(0, OS); + return; + } + + // Use the CppHashFilename and calculate a line number based on the + // CppHashLoc and CppHashLineNumber relative to this Diag's SMLoc for + // the diagnostic. + const std::string Filename = Parser->CppHashFilename; + + int DiagLocLineNo = DiagSrcMgr.FindLineNumber(DiagLoc, DiagBuf); + int CppHashLocLineNo = + Parser->SrcMgr.FindLineNumber(Parser->CppHashLoc, CppHashBuf); + int LineNo = Parser->CppHashLineNumber - 1 + + (DiagLocLineNo - CppHashLocLineNo); + + SMDiagnostic NewDiag(*Diag.getSourceMgr(), Diag.getLoc(), + Filename, LineNo, Diag.getColumnNo(), + Diag.getKind(), Diag.getMessage(), + Diag.getLineContents(), Diag.getRanges()); + + if (Parser->SavedDiagHandler) + Parser->SavedDiagHandler(NewDiag, Parser->SavedDiagContext); + else + NewDiag.print(0, OS); +} + +bool AsmParser::expandMacro(raw_svector_ostream &OS, StringRef Body, + const MacroParameters &Parameters, + const MacroArguments &A, + const SMLoc &L) { + unsigned NParameters = Parameters.size(); + if (NParameters != 0 && NParameters != A.size()) + return Error(L, "Wrong number of arguments"); + + while (!Body.empty()) { + // Scan for the next substitution. + std::size_t End = Body.size(), Pos = 0; + for (; Pos != End; ++Pos) { + // Check for a substitution or escape. + if (!NParameters) { + // This macro has no parameters, look for $0, $1, etc. + if (Body[Pos] != '$' || Pos + 1 == End) + continue; + + char Next = Body[Pos + 1]; + if (Next == '$' || Next == 'n' || isdigit(Next)) + break; + } else { + // This macro has parameters, look for \foo, \bar, etc. + if (Body[Pos] == '\\' && Pos + 1 != End) + break; + } + } + + // Add the prefix. + OS << Body.slice(0, Pos); + + // Check if we reached the end. + if (Pos == End) + break; + + if (!NParameters) { + switch (Body[Pos+1]) { + // $$ => $ + case '$': + OS << '$'; + break; + + // $n => number of arguments + case 'n': + OS << A.size(); + break; + + // $[0-9] => argument + default: { + // Missing arguments are ignored. + unsigned Index = Body[Pos+1] - '0'; + if (Index >= A.size()) + break; + + // Otherwise substitute with the token values, with spaces eliminated. + for (MacroArgument::const_iterator it = A[Index].begin(), + ie = A[Index].end(); it != ie; ++it) + OS << it->getString(); + break; + } + } + Pos += 2; + } else { + unsigned I = Pos + 1; + while (isalnum(Body[I]) && I + 1 != End) + ++I; + + const char *Begin = Body.data() + Pos +1; + StringRef Argument(Begin, I - (Pos +1)); + unsigned Index = 0; + for (; Index < NParameters; ++Index) + if (Parameters[Index] == Argument) + break; + + // FIXME: We should error at the macro definition. + if (Index == NParameters) + return Error(L, "Parameter not found"); + + for (MacroArgument::const_iterator it = A[Index].begin(), + ie = A[Index].end(); it != ie; ++it) + OS << it->getString(); + + Pos += 1 + Argument.size(); + } + // Update the scan point. + Body = Body.substr(Pos); + } + + return false; +} + +MacroInstantiation::MacroInstantiation(const Macro *M, SMLoc IL, SMLoc EL, + MemoryBuffer *I) + : TheMacro(M), Instantiation(I), InstantiationLoc(IL), ExitLoc(EL) +{ +} + +/// ParseMacroArgument - Extract AsmTokens for a macro argument. +/// This is used for both default macro parameter values and the +/// arguments in macro invocations +bool AsmParser::ParseMacroArgument(MacroArgument &MA) { + unsigned ParenLevel = 0; + + for (;;) { + SMLoc LastTokenLoc; + + if (Lexer.is(AsmToken::Eof) || Lexer.is(AsmToken::Equal)) + return TokError("unexpected token in macro instantiation"); + + // HandleMacroEntry relies on not advancing the lexer here + // to be able to fill in the remaining default parameter values + if (Lexer.is(AsmToken::EndOfStatement)) + break; + if (ParenLevel == 0 && Lexer.is(AsmToken::Comma)) + break; + + // Adjust the current parentheses level. + if (Lexer.is(AsmToken::LParen)) + ++ParenLevel; + else if (Lexer.is(AsmToken::RParen) && ParenLevel) + --ParenLevel; + + // Append the token to the current argument list. + MA.push_back(getTok()); + Lex(); + } + if (ParenLevel != 0) + return TokError("unbalanced parenthesises in macro argument"); + return false; +} + +// Parse the macro instantiation arguments. +bool AsmParser::ParseMacroArguments(const Macro *M, MacroArguments &A) { + const unsigned NParameters = M ? M->Parameters.size() : 0; + + // Parse two kinds of macro invocations: + // - macros defined without any parameters accept an arbitrary number of them + // - macros defined with parameters accept at most that many of them + for (unsigned Parameter = 0; !NParameters || Parameter < NParameters; + ++Parameter) { + MacroArgument MA; + + if (ParseMacroArgument(MA)) + return true; + + A.push_back(MA); + + if (Lexer.is(AsmToken::EndOfStatement)) + return false; + + if (Lexer.is(AsmToken::Comma)) + Lex(); + } + return TokError("Too many arguments"); +} + +bool AsmParser::HandleMacroEntry(StringRef Name, SMLoc NameLoc, + const Macro *M) { + // Arbitrarily limit macro nesting depth, to match 'as'. We can eliminate + // this, although we should protect against infinite loops. + if (ActiveMacros.size() == 20) + return TokError("macros cannot be nested more than 20 levels deep"); + + MacroArguments A; + if (ParseMacroArguments(M, A)) + return true; + + // Remove any trailing empty arguments. Do this after-the-fact as we have + // to keep empty arguments in the middle of the list or positionality + // gets off. e.g., "foo 1, , 2" vs. "foo 1, 2," + while (!A.empty() && A.back().empty()) + A.pop_back(); + + // Macro instantiation is lexical, unfortunately. We construct a new buffer + // to hold the macro body with substitutions. + SmallString<256> Buf; + StringRef Body = M->Body; + raw_svector_ostream OS(Buf); + + if (expandMacro(OS, Body, M->Parameters, A, getTok().getLoc())) + return true; + + // We include the .endmacro in the buffer as our queue to exit the macro + // instantiation. + OS << ".endmacro\n"; + + MemoryBuffer *Instantiation = + MemoryBuffer::getMemBufferCopy(OS.str(), "<instantiation>"); + + // Create the macro instantiation object and add to the current macro + // instantiation stack. + MacroInstantiation *MI = new MacroInstantiation(M, NameLoc, + getTok().getLoc(), + Instantiation); + ActiveMacros.push_back(MI); + + // Jump to the macro instantiation and prime the lexer. + CurBuffer = SrcMgr.AddNewSourceBuffer(MI->Instantiation, SMLoc()); + Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer)); + Lex(); + + return false; +} + +void AsmParser::HandleMacroExit() { + // Jump to the EndOfStatement we should return to, and consume it. + JumpToLoc(ActiveMacros.back()->ExitLoc); + Lex(); + + // Pop the instantiation entry. + delete ActiveMacros.back(); + ActiveMacros.pop_back(); +} + +static bool IsUsedIn(const MCSymbol *Sym, const MCExpr *Value) { + switch (Value->getKind()) { + case MCExpr::Binary: { + const MCBinaryExpr *BE = static_cast<const MCBinaryExpr*>(Value); + return IsUsedIn(Sym, BE->getLHS()) || IsUsedIn(Sym, BE->getRHS()); + break; + } + case MCExpr::Target: + case MCExpr::Constant: + return false; + case MCExpr::SymbolRef: { + const MCSymbol &S = static_cast<const MCSymbolRefExpr*>(Value)->getSymbol(); + if (S.isVariable()) + return IsUsedIn(Sym, S.getVariableValue()); + return &S == Sym; + } + case MCExpr::Unary: + return IsUsedIn(Sym, static_cast<const MCUnaryExpr*>(Value)->getSubExpr()); + } + + llvm_unreachable("Unknown expr kind!"); +} + +bool AsmParser::ParseAssignment(StringRef Name, bool allow_redef) { + // FIXME: Use better location, we should use proper tokens. + SMLoc EqualLoc = Lexer.getLoc(); + + const MCExpr *Value; + if (ParseExpression(Value)) + return true; + + // Note: we don't count b as used in "a = b". This is to allow + // a = b + // b = c + + if (Lexer.isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in assignment"); + + // Error on assignment to '.'. + if (Name == ".") { + return Error(EqualLoc, ("assignment to pseudo-symbol '.' is unsupported " + "(use '.space' or '.org').)")); + } + + // Eat the end of statement marker. + Lex(); + + // Validate that the LHS is allowed to be a variable (either it has not been + // used as a symbol, or it is an absolute symbol). + MCSymbol *Sym = getContext().LookupSymbol(Name); + if (Sym) { + // Diagnose assignment to a label. + // + // FIXME: Diagnostics. Note the location of the definition as a label. + // FIXME: Diagnose assignment to protected identifier (e.g., register name). + if (IsUsedIn(Sym, Value)) + return Error(EqualLoc, "Recursive use of '" + Name + "'"); + else if (Sym->isUndefined() && !Sym->isUsed() && !Sym->isVariable()) + ; // Allow redefinitions of undefined symbols only used in directives. + else if (Sym->isVariable() && !Sym->isUsed() && allow_redef) + ; // Allow redefinitions of variables that haven't yet been used. + else if (!Sym->isUndefined() && (!Sym->isVariable() || !allow_redef)) + return Error(EqualLoc, "redefinition of '" + Name + "'"); + else if (!Sym->isVariable()) + return Error(EqualLoc, "invalid assignment to '" + Name + "'"); + else if (!isa<MCConstantExpr>(Sym->getVariableValue())) + return Error(EqualLoc, "invalid reassignment of non-absolute variable '" + + Name + "'"); + + // Don't count these checks as uses. + Sym->setUsed(false); + } else + Sym = getContext().GetOrCreateSymbol(Name); + + // FIXME: Handle '.'. + + // Do the assignment. + Out.EmitAssignment(Sym, Value); + + return false; +} + +/// ParseIdentifier: +/// ::= identifier +/// ::= string +bool AsmParser::ParseIdentifier(StringRef &Res) { + // The assembler has relaxed rules for accepting identifiers, in particular we + // allow things like '.globl $foo', which would normally be separate + // tokens. At this level, we have already lexed so we cannot (currently) + // handle this as a context dependent token, instead we detect adjacent tokens + // and return the combined identifier. + if (Lexer.is(AsmToken::Dollar)) { + SMLoc DollarLoc = getLexer().getLoc(); + + // Consume the dollar sign, and check for a following identifier. + Lex(); + if (Lexer.isNot(AsmToken::Identifier)) + return true; + + // We have a '$' followed by an identifier, make sure they are adjacent. + if (DollarLoc.getPointer() + 1 != getTok().getLoc().getPointer()) + return true; + + // Construct the joined identifier and consume the token. + Res = StringRef(DollarLoc.getPointer(), + getTok().getIdentifier().size() + 1); + Lex(); + return false; + } + + if (Lexer.isNot(AsmToken::Identifier) && + Lexer.isNot(AsmToken::String)) + return true; + + Res = getTok().getIdentifier(); + + Lex(); // Consume the identifier token. + + return false; +} + +/// ParseDirectiveSet: +/// ::= .equ identifier ',' expression +/// ::= .equiv identifier ',' expression +/// ::= .set identifier ',' expression +bool AsmParser::ParseDirectiveSet(StringRef IDVal, bool allow_redef) { + StringRef Name; + + if (ParseIdentifier(Name)) + return TokError("expected identifier after '" + Twine(IDVal) + "'"); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '" + Twine(IDVal) + "'"); + Lex(); + + return ParseAssignment(Name, allow_redef); +} + +bool AsmParser::ParseEscapedString(std::string &Data) { + assert(getLexer().is(AsmToken::String) && "Unexpected current token!"); + + Data = ""; + StringRef Str = getTok().getStringContents(); + for (unsigned i = 0, e = Str.size(); i != e; ++i) { + if (Str[i] != '\\') { + Data += Str[i]; + continue; + } + + // Recognize escaped characters. Note that this escape semantics currently + // loosely follows Darwin 'as'. Notably, it doesn't support hex escapes. + ++i; + if (i == e) + return TokError("unexpected backslash at end of string"); + + // Recognize octal sequences. + if ((unsigned) (Str[i] - '0') <= 7) { + // Consume up to three octal characters. + unsigned Value = Str[i] - '0'; + + if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) { + ++i; + Value = Value * 8 + (Str[i] - '0'); + + if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) { + ++i; + Value = Value * 8 + (Str[i] - '0'); + } + } + + if (Value > 255) + return TokError("invalid octal escape sequence (out of range)"); + + Data += (unsigned char) Value; + continue; + } + + // Otherwise recognize individual escapes. + switch (Str[i]) { + default: + // Just reject invalid escape sequences for now. + return TokError("invalid escape sequence (unrecognized character)"); + + case 'b': Data += '\b'; break; + case 'f': Data += '\f'; break; + case 'n': Data += '\n'; break; + case 'r': Data += '\r'; break; + case 't': Data += '\t'; break; + case '"': Data += '"'; break; + case '\\': Data += '\\'; break; + } + } + + return false; +} + +/// ParseDirectiveAscii: +/// ::= ( .ascii | .asciz | .string ) [ "string" ( , "string" )* ] +bool AsmParser::ParseDirectiveAscii(StringRef IDVal, bool ZeroTerminated) { + if (getLexer().isNot(AsmToken::EndOfStatement)) { + CheckForValidSection(); + + for (;;) { + if (getLexer().isNot(AsmToken::String)) + return TokError("expected string in '" + Twine(IDVal) + "' directive"); + + std::string Data; + if (ParseEscapedString(Data)) + return true; + + getStreamer().EmitBytes(Data, DEFAULT_ADDRSPACE); + if (ZeroTerminated) + getStreamer().EmitBytes(StringRef("\0", 1), DEFAULT_ADDRSPACE); + + Lex(); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '" + Twine(IDVal) + "' directive"); + Lex(); + } + } + + Lex(); + return false; +} + +/// ParseDirectiveValue +/// ::= (.byte | .short | ... ) [ expression (, expression)* ] +bool AsmParser::ParseDirectiveValue(unsigned Size) { + if (getLexer().isNot(AsmToken::EndOfStatement)) { + CheckForValidSection(); + + for (;;) { + const MCExpr *Value; + SMLoc ExprLoc = getLexer().getLoc(); + if (ParseExpression(Value)) + return true; + + // Special case constant expressions to match code generator. + if (const MCConstantExpr *MCE = dyn_cast<MCConstantExpr>(Value)) { + assert(Size <= 8 && "Invalid size"); + uint64_t IntValue = MCE->getValue(); + if (!isUIntN(8 * Size, IntValue) && !isIntN(8 * Size, IntValue)) + return Error(ExprLoc, "literal value out of range for directive"); + getStreamer().EmitIntValue(IntValue, Size, DEFAULT_ADDRSPACE); + } else + getStreamer().EmitValue(Value, Size, DEFAULT_ADDRSPACE); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + // FIXME: Improve diagnostic. + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + } + } + + Lex(); + return false; +} + +/// ParseDirectiveRealValue +/// ::= (.single | .double) [ expression (, expression)* ] +bool AsmParser::ParseDirectiveRealValue(const fltSemantics &Semantics) { + if (getLexer().isNot(AsmToken::EndOfStatement)) { + CheckForValidSection(); + + for (;;) { + // We don't truly support arithmetic on floating point expressions, so we + // have to manually parse unary prefixes. + bool IsNeg = false; + if (getLexer().is(AsmToken::Minus)) { + Lex(); + IsNeg = true; + } else if (getLexer().is(AsmToken::Plus)) + Lex(); + + if (getLexer().isNot(AsmToken::Integer) && + getLexer().isNot(AsmToken::Real) && + getLexer().isNot(AsmToken::Identifier)) + return TokError("unexpected token in directive"); + + // Convert to an APFloat. + APFloat Value(Semantics); + StringRef IDVal = getTok().getString(); + if (getLexer().is(AsmToken::Identifier)) { + if (!IDVal.compare_lower("infinity") || !IDVal.compare_lower("inf")) + Value = APFloat::getInf(Semantics); + else if (!IDVal.compare_lower("nan")) + Value = APFloat::getNaN(Semantics, false, ~0); + else + return TokError("invalid floating point literal"); + } else if (Value.convertFromString(IDVal, APFloat::rmNearestTiesToEven) == + APFloat::opInvalidOp) + return TokError("invalid floating point literal"); + if (IsNeg) + Value.changeSign(); + + // Consume the numeric token. + Lex(); + + // Emit the value as an integer. + APInt AsInt = Value.bitcastToAPInt(); + getStreamer().EmitIntValue(AsInt.getLimitedValue(), + AsInt.getBitWidth() / 8, DEFAULT_ADDRSPACE); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + } + } + + Lex(); + return false; +} + +/// ParseDirectiveSpace +/// ::= .space expression [ , expression ] +bool AsmParser::ParseDirectiveSpace() { + CheckForValidSection(); + + int64_t NumBytes; + if (ParseAbsoluteExpression(NumBytes)) + return true; + + int64_t FillExpr = 0; + if (getLexer().isNot(AsmToken::EndOfStatement)) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.space' directive"); + Lex(); + + if (ParseAbsoluteExpression(FillExpr)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.space' directive"); + } + + Lex(); + + if (NumBytes <= 0) + return TokError("invalid number of bytes in '.space' directive"); + + // FIXME: Sometimes the fill expr is 'nop' if it isn't supplied, instead of 0. + getStreamer().EmitFill(NumBytes, FillExpr, DEFAULT_ADDRSPACE); + + return false; +} + +/// ParseDirectiveZero +/// ::= .zero expression +bool AsmParser::ParseDirectiveZero() { + CheckForValidSection(); + + int64_t NumBytes; + if (ParseAbsoluteExpression(NumBytes)) + return true; + + int64_t Val = 0; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + if (ParseAbsoluteExpression(Val)) + return true; + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.zero' directive"); + + Lex(); + + getStreamer().EmitFill(NumBytes, Val, DEFAULT_ADDRSPACE); + + return false; +} + +/// ParseDirectiveFill +/// ::= .fill expression , expression , expression +bool AsmParser::ParseDirectiveFill() { + CheckForValidSection(); + + int64_t NumValues; + if (ParseAbsoluteExpression(NumValues)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.fill' directive"); + Lex(); + + int64_t FillSize; + if (ParseAbsoluteExpression(FillSize)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.fill' directive"); + Lex(); + + int64_t FillExpr; + if (ParseAbsoluteExpression(FillExpr)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.fill' directive"); + + Lex(); + + if (FillSize != 1 && FillSize != 2 && FillSize != 4 && FillSize != 8) + return TokError("invalid '.fill' size, expected 1, 2, 4, or 8"); + + for (uint64_t i = 0, e = NumValues; i != e; ++i) + getStreamer().EmitIntValue(FillExpr, FillSize, DEFAULT_ADDRSPACE); + + return false; +} + +/// ParseDirectiveOrg +/// ::= .org expression [ , expression ] +bool AsmParser::ParseDirectiveOrg() { + CheckForValidSection(); + + const MCExpr *Offset; + SMLoc Loc = getTok().getLoc(); + if (ParseExpression(Offset)) + return true; + + // Parse optional fill expression. + int64_t FillExpr = 0; + if (getLexer().isNot(AsmToken::EndOfStatement)) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.org' directive"); + Lex(); + + if (ParseAbsoluteExpression(FillExpr)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.org' directive"); + } + + Lex(); + + // Only limited forms of relocatable expressions are accepted here, it + // has to be relative to the current section. The streamer will return + // 'true' if the expression wasn't evaluatable. + if (getStreamer().EmitValueToOffset(Offset, FillExpr)) + return Error(Loc, "expected assembly-time absolute expression"); + + return false; +} + +/// ParseDirectiveAlign +/// ::= {.align, ...} expression [ , expression [ , expression ]] +bool AsmParser::ParseDirectiveAlign(bool IsPow2, unsigned ValueSize) { + CheckForValidSection(); + + SMLoc AlignmentLoc = getLexer().getLoc(); + int64_t Alignment; + if (ParseAbsoluteExpression(Alignment)) + return true; + + SMLoc MaxBytesLoc; + bool HasFillExpr = false; + int64_t FillExpr = 0; + int64_t MaxBytesToFill = 0; + if (getLexer().isNot(AsmToken::EndOfStatement)) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + // The fill expression can be omitted while specifying a maximum number of + // alignment bytes, e.g: + // .align 3,,4 + if (getLexer().isNot(AsmToken::Comma)) { + HasFillExpr = true; + if (ParseAbsoluteExpression(FillExpr)) + return true; + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + MaxBytesLoc = getLexer().getLoc(); + if (ParseAbsoluteExpression(MaxBytesToFill)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + } + } + + Lex(); + + if (!HasFillExpr) + FillExpr = 0; + + // Compute alignment in bytes. + if (IsPow2) { + // FIXME: Diagnose overflow. + if (Alignment >= 32) { + Error(AlignmentLoc, "invalid alignment value"); + Alignment = 31; + } + + Alignment = 1ULL << Alignment; + } + + // Diagnose non-sensical max bytes to align. + if (MaxBytesLoc.isValid()) { + if (MaxBytesToFill < 1) { + Error(MaxBytesLoc, "alignment directive can never be satisfied in this " + "many bytes, ignoring maximum bytes expression"); + MaxBytesToFill = 0; + } + + if (MaxBytesToFill >= Alignment) { + Warning(MaxBytesLoc, "maximum bytes expression exceeds alignment and " + "has no effect"); + MaxBytesToFill = 0; + } + } + + // Check whether we should use optimal code alignment for this .align + // directive. + bool UseCodeAlign = getStreamer().getCurrentSection()->UseCodeAlign(); + if ((!HasFillExpr || Lexer.getMAI().getTextAlignFillValue() == FillExpr) && + ValueSize == 1 && UseCodeAlign) { + getStreamer().EmitCodeAlignment(Alignment, MaxBytesToFill); + } else { + // FIXME: Target specific behavior about how the "extra" bytes are filled. + getStreamer().EmitValueToAlignment(Alignment, FillExpr, ValueSize, + MaxBytesToFill); + } + + return false; +} + +/// ParseDirectiveSymbolAttribute +/// ::= { ".globl", ".weak", ... } [ identifier ( , identifier )* ] +bool AsmParser::ParseDirectiveSymbolAttribute(MCSymbolAttr Attr) { + if (getLexer().isNot(AsmToken::EndOfStatement)) { + for (;;) { + StringRef Name; + SMLoc Loc = getTok().getLoc(); + + if (ParseIdentifier(Name)) + return Error(Loc, "expected identifier in directive"); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + // Assembler local symbols don't make any sense here. Complain loudly. + if (Sym->isTemporary()) + return Error(Loc, "non-local symbol required in directive"); + + getStreamer().EmitSymbolAttribute(Sym, Attr); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + } + } + + Lex(); + return false; +} + +/// ParseDirectiveComm +/// ::= ( .comm | .lcomm ) identifier , size_expression [ , align_expression ] +bool AsmParser::ParseDirectiveComm(bool IsLocal) { + CheckForValidSection(); + + SMLoc IDLoc = getLexer().getLoc(); + StringRef Name; + if (ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + // Handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + int64_t Size; + SMLoc SizeLoc = getLexer().getLoc(); + if (ParseAbsoluteExpression(Size)) + return true; + + int64_t Pow2Alignment = 0; + SMLoc Pow2AlignmentLoc; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + Pow2AlignmentLoc = getLexer().getLoc(); + if (ParseAbsoluteExpression(Pow2Alignment)) + return true; + + // If this target takes alignments in bytes (not log) validate and convert. + if (Lexer.getMAI().getAlignmentIsInBytes()) { + if (!isPowerOf2_64(Pow2Alignment)) + return Error(Pow2AlignmentLoc, "alignment must be a power of 2"); + Pow2Alignment = Log2_64(Pow2Alignment); + } + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.comm' or '.lcomm' directive"); + + Lex(); + + // NOTE: a size of zero for a .comm should create a undefined symbol + // but a size of .lcomm creates a bss symbol of size zero. + if (Size < 0) + return Error(SizeLoc, "invalid '.comm' or '.lcomm' directive size, can't " + "be less than zero"); + + // NOTE: The alignment in the directive is a power of 2 value, the assembler + // may internally end up wanting an alignment in bytes. + // FIXME: Diagnose overflow. + if (Pow2Alignment < 0) + return Error(Pow2AlignmentLoc, "invalid '.comm' or '.lcomm' directive " + "alignment, can't be less than zero"); + + if (!Sym->isUndefined()) + return Error(IDLoc, "invalid symbol redefinition"); + + // '.lcomm' is equivalent to '.zerofill'. + // Create the Symbol as a common or local common with Size and Pow2Alignment + if (IsLocal) { + getStreamer().EmitZerofill(Ctx.getMachOSection( + "__DATA", "__bss", MCSectionMachO::S_ZEROFILL, + 0, SectionKind::getBSS()), + Sym, Size, 1 << Pow2Alignment); + return false; + } + + getStreamer().EmitCommonSymbol(Sym, Size, 1 << Pow2Alignment); + return false; +} + +/// ParseDirectiveAbort +/// ::= .abort [... message ...] +bool AsmParser::ParseDirectiveAbort() { + // FIXME: Use loc from directive. + SMLoc Loc = getLexer().getLoc(); + + StringRef Str = ParseStringToEndOfStatement(); + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.abort' directive"); + + Lex(); + + if (Str.empty()) + Error(Loc, ".abort detected. Assembly stopping."); + else + Error(Loc, ".abort '" + Str + "' detected. Assembly stopping."); + // FIXME: Actually abort assembly here. + + return false; +} + +/// ParseDirectiveInclude +/// ::= .include "filename" +bool AsmParser::ParseDirectiveInclude() { + if (getLexer().isNot(AsmToken::String)) + return TokError("expected string in '.include' directive"); + + std::string Filename = getTok().getString(); + SMLoc IncludeLoc = getLexer().getLoc(); + Lex(); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.include' directive"); + + // Strip the quotes. + Filename = Filename.substr(1, Filename.size()-2); + + // Attempt to switch the lexer to the included file before consuming the end + // of statement to avoid losing it when we switch. + if (EnterIncludeFile(Filename)) { + Error(IncludeLoc, "Could not find include file '" + Filename + "'"); + return true; + } + + return false; +} + +/// ParseDirectiveIncbin +/// ::= .incbin "filename" +bool AsmParser::ParseDirectiveIncbin() { + if (getLexer().isNot(AsmToken::String)) + return TokError("expected string in '.incbin' directive"); + + std::string Filename = getTok().getString(); + SMLoc IncbinLoc = getLexer().getLoc(); + Lex(); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.incbin' directive"); + + // Strip the quotes. + Filename = Filename.substr(1, Filename.size()-2); + + // Attempt to process the included file. + if (ProcessIncbinFile(Filename)) { + Error(IncbinLoc, "Could not find incbin file '" + Filename + "'"); + return true; + } + + return false; +} + +/// ParseDirectiveIf +/// ::= .if expression +bool AsmParser::ParseDirectiveIf(SMLoc DirectiveLoc) { + TheCondStack.push_back(TheCondState); + TheCondState.TheCond = AsmCond::IfCond; + if (TheCondState.Ignore) { + EatToEndOfStatement(); + } else { + int64_t ExprValue; + if (ParseAbsoluteExpression(ExprValue)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.if' directive"); + + Lex(); + + TheCondState.CondMet = ExprValue; + TheCondState.Ignore = !TheCondState.CondMet; + } + + return false; +} + +/// ParseDirectiveIfb +/// ::= .ifb string +bool AsmParser::ParseDirectiveIfb(SMLoc DirectiveLoc, bool ExpectBlank) { + TheCondStack.push_back(TheCondState); + TheCondState.TheCond = AsmCond::IfCond; + + if (TheCondState.Ignore) { + EatToEndOfStatement(); + } else { + StringRef Str = ParseStringToEndOfStatement(); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.ifb' directive"); + + Lex(); + + TheCondState.CondMet = ExpectBlank == Str.empty(); + TheCondState.Ignore = !TheCondState.CondMet; + } + + return false; +} + +/// ParseDirectiveIfc +/// ::= .ifc string1, string2 +bool AsmParser::ParseDirectiveIfc(SMLoc DirectiveLoc, bool ExpectEqual) { + TheCondStack.push_back(TheCondState); + TheCondState.TheCond = AsmCond::IfCond; + + if (TheCondState.Ignore) { + EatToEndOfStatement(); + } else { + StringRef Str1 = ParseStringToComma(); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.ifc' directive"); + + Lex(); + + StringRef Str2 = ParseStringToEndOfStatement(); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.ifc' directive"); + + Lex(); + + TheCondState.CondMet = ExpectEqual == (Str1 == Str2); + TheCondState.Ignore = !TheCondState.CondMet; + } + + return false; +} + +/// ParseDirectiveIfdef +/// ::= .ifdef symbol +bool AsmParser::ParseDirectiveIfdef(SMLoc DirectiveLoc, bool expect_defined) { + StringRef Name; + TheCondStack.push_back(TheCondState); + TheCondState.TheCond = AsmCond::IfCond; + + if (TheCondState.Ignore) { + EatToEndOfStatement(); + } else { + if (ParseIdentifier(Name)) + return TokError("expected identifier after '.ifdef'"); + + Lex(); + + MCSymbol *Sym = getContext().LookupSymbol(Name); + + if (expect_defined) + TheCondState.CondMet = (Sym != NULL && !Sym->isUndefined()); + else + TheCondState.CondMet = (Sym == NULL || Sym->isUndefined()); + TheCondState.Ignore = !TheCondState.CondMet; + } + + return false; +} + +/// ParseDirectiveElseIf +/// ::= .elseif expression +bool AsmParser::ParseDirectiveElseIf(SMLoc DirectiveLoc) { + if (TheCondState.TheCond != AsmCond::IfCond && + TheCondState.TheCond != AsmCond::ElseIfCond) + Error(DirectiveLoc, "Encountered a .elseif that doesn't follow a .if or " + " an .elseif"); + TheCondState.TheCond = AsmCond::ElseIfCond; + + bool LastIgnoreState = false; + if (!TheCondStack.empty()) + LastIgnoreState = TheCondStack.back().Ignore; + if (LastIgnoreState || TheCondState.CondMet) { + TheCondState.Ignore = true; + EatToEndOfStatement(); + } + else { + int64_t ExprValue; + if (ParseAbsoluteExpression(ExprValue)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.elseif' directive"); + + Lex(); + TheCondState.CondMet = ExprValue; + TheCondState.Ignore = !TheCondState.CondMet; + } + + return false; +} + +/// ParseDirectiveElse +/// ::= .else +bool AsmParser::ParseDirectiveElse(SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.else' directive"); + + Lex(); + + if (TheCondState.TheCond != AsmCond::IfCond && + TheCondState.TheCond != AsmCond::ElseIfCond) + Error(DirectiveLoc, "Encountered a .else that doesn't follow a .if or an " + ".elseif"); + TheCondState.TheCond = AsmCond::ElseCond; + bool LastIgnoreState = false; + if (!TheCondStack.empty()) + LastIgnoreState = TheCondStack.back().Ignore; + if (LastIgnoreState || TheCondState.CondMet) + TheCondState.Ignore = true; + else + TheCondState.Ignore = false; + + return false; +} + +/// ParseDirectiveEndIf +/// ::= .endif +bool AsmParser::ParseDirectiveEndIf(SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.endif' directive"); + + Lex(); + + if ((TheCondState.TheCond == AsmCond::NoCond) || + TheCondStack.empty()) + Error(DirectiveLoc, "Encountered a .endif that doesn't follow a .if or " + ".else"); + if (!TheCondStack.empty()) { + TheCondState = TheCondStack.back(); + TheCondStack.pop_back(); + } + + return false; +} + +/// ParseDirectiveFile +/// ::= .file [number] filename +/// ::= .file number directory filename +bool GenericAsmParser::ParseDirectiveFile(StringRef, SMLoc DirectiveLoc) { + // FIXME: I'm not sure what this is. + int64_t FileNumber = -1; + SMLoc FileNumberLoc = getLexer().getLoc(); + if (getLexer().is(AsmToken::Integer)) { + FileNumber = getTok().getIntVal(); + Lex(); + + if (FileNumber < 1) + return TokError("file number less than one"); + } + + if (getLexer().isNot(AsmToken::String)) + return TokError("unexpected token in '.file' directive"); + + // Usually the directory and filename together, otherwise just the directory. + StringRef Path = getTok().getString(); + Path = Path.substr(1, Path.size()-2); + Lex(); + + StringRef Directory; + StringRef Filename; + if (getLexer().is(AsmToken::String)) { + if (FileNumber == -1) + return TokError("explicit path specified, but no file number"); + Filename = getTok().getString(); + Filename = Filename.substr(1, Filename.size()-2); + Directory = Path; + Lex(); + } else { + Filename = Path; + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.file' directive"); + + if (FileNumber == -1) + getStreamer().EmitFileDirective(Filename); + else { + if (getContext().getGenDwarfForAssembly() == true) + Error(DirectiveLoc, "input can't have .file dwarf directives when -g is " + "used to generate dwarf debug info for assembly code"); + + if (getStreamer().EmitDwarfFileDirective(FileNumber, Directory, Filename)) + Error(FileNumberLoc, "file number already allocated"); + } + + return false; +} + +/// ParseDirectiveLine +/// ::= .line [number] +bool GenericAsmParser::ParseDirectiveLine(StringRef, SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) { + if (getLexer().isNot(AsmToken::Integer)) + return TokError("unexpected token in '.line' directive"); + + int64_t LineNumber = getTok().getIntVal(); + (void) LineNumber; + Lex(); + + // FIXME: Do something with the .line. + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.line' directive"); + + return false; +} + + +/// ParseDirectiveLoc +/// ::= .loc FileNumber [LineNumber] [ColumnPos] [basic_block] [prologue_end] +/// [epilogue_begin] [is_stmt VALUE] [isa VALUE] +/// The first number is a file number, must have been previously assigned with +/// a .file directive, the second number is the line number and optionally the +/// third number is a column position (zero if not specified). The remaining +/// optional items are .loc sub-directives. +bool GenericAsmParser::ParseDirectiveLoc(StringRef, SMLoc DirectiveLoc) { + + if (getLexer().isNot(AsmToken::Integer)) + return TokError("unexpected token in '.loc' directive"); + int64_t FileNumber = getTok().getIntVal(); + if (FileNumber < 1) + return TokError("file number less than one in '.loc' directive"); + if (!getContext().isValidDwarfFileNumber(FileNumber)) + return TokError("unassigned file number in '.loc' directive"); + Lex(); + + int64_t LineNumber = 0; + if (getLexer().is(AsmToken::Integer)) { + LineNumber = getTok().getIntVal(); + if (LineNumber < 1) + return TokError("line number less than one in '.loc' directive"); + Lex(); + } + + int64_t ColumnPos = 0; + if (getLexer().is(AsmToken::Integer)) { + ColumnPos = getTok().getIntVal(); + if (ColumnPos < 0) + return TokError("column position less than zero in '.loc' directive"); + Lex(); + } + + unsigned Flags = DWARF2_LINE_DEFAULT_IS_STMT ? DWARF2_FLAG_IS_STMT : 0; + unsigned Isa = 0; + int64_t Discriminator = 0; + if (getLexer().isNot(AsmToken::EndOfStatement)) { + for (;;) { + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + StringRef Name; + SMLoc Loc = getTok().getLoc(); + if (getParser().ParseIdentifier(Name)) + return TokError("unexpected token in '.loc' directive"); + + if (Name == "basic_block") + Flags |= DWARF2_FLAG_BASIC_BLOCK; + else if (Name == "prologue_end") + Flags |= DWARF2_FLAG_PROLOGUE_END; + else if (Name == "epilogue_begin") + Flags |= DWARF2_FLAG_EPILOGUE_BEGIN; + else if (Name == "is_stmt") { + SMLoc Loc = getTok().getLoc(); + const MCExpr *Value; + if (getParser().ParseExpression(Value)) + return true; + // The expression must be the constant 0 or 1. + if (const MCConstantExpr *MCE = dyn_cast<MCConstantExpr>(Value)) { + int Value = MCE->getValue(); + if (Value == 0) + Flags &= ~DWARF2_FLAG_IS_STMT; + else if (Value == 1) + Flags |= DWARF2_FLAG_IS_STMT; + else + return Error(Loc, "is_stmt value not 0 or 1"); + } + else { + return Error(Loc, "is_stmt value not the constant value of 0 or 1"); + } + } + else if (Name == "isa") { + SMLoc Loc = getTok().getLoc(); + const MCExpr *Value; + if (getParser().ParseExpression(Value)) + return true; + // The expression must be a constant greater or equal to 0. + if (const MCConstantExpr *MCE = dyn_cast<MCConstantExpr>(Value)) { + int Value = MCE->getValue(); + if (Value < 0) + return Error(Loc, "isa number less than zero"); + Isa = Value; + } + else { + return Error(Loc, "isa number not a constant value"); + } + } + else if (Name == "discriminator") { + if (getParser().ParseAbsoluteExpression(Discriminator)) + return true; + } + else { + return Error(Loc, "unknown sub-directive in '.loc' directive"); + } + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + } + } + + getStreamer().EmitDwarfLocDirective(FileNumber, LineNumber, ColumnPos, Flags, + Isa, Discriminator, StringRef()); + + return false; +} + +/// ParseDirectiveStabs +/// ::= .stabs string, number, number, number +bool GenericAsmParser::ParseDirectiveStabs(StringRef Directive, + SMLoc DirectiveLoc) { + return TokError("unsupported directive '" + Directive + "'"); +} + +/// ParseDirectiveCFISections +/// ::= .cfi_sections section [, section] +bool GenericAsmParser::ParseDirectiveCFISections(StringRef, + SMLoc DirectiveLoc) { + StringRef Name; + bool EH = false; + bool Debug = false; + + if (getParser().ParseIdentifier(Name)) + return TokError("Expected an identifier"); + + if (Name == ".eh_frame") + EH = true; + else if (Name == ".debug_frame") + Debug = true; + + if (getLexer().is(AsmToken::Comma)) { + Lex(); + + if (getParser().ParseIdentifier(Name)) + return TokError("Expected an identifier"); + + if (Name == ".eh_frame") + EH = true; + else if (Name == ".debug_frame") + Debug = true; + } + + getStreamer().EmitCFISections(EH, Debug); + + return false; +} + +/// ParseDirectiveCFIStartProc +/// ::= .cfi_startproc +bool GenericAsmParser::ParseDirectiveCFIStartProc(StringRef, + SMLoc DirectiveLoc) { + getStreamer().EmitCFIStartProc(); + return false; +} + +/// ParseDirectiveCFIEndProc +/// ::= .cfi_endproc +bool GenericAsmParser::ParseDirectiveCFIEndProc(StringRef, SMLoc DirectiveLoc) { + getStreamer().EmitCFIEndProc(); + return false; +} + +/// ParseRegisterOrRegisterNumber - parse register name or number. +bool GenericAsmParser::ParseRegisterOrRegisterNumber(int64_t &Register, + SMLoc DirectiveLoc) { + unsigned RegNo; + + if (getLexer().isNot(AsmToken::Integer)) { + if (getParser().getTargetParser().ParseRegister(RegNo, DirectiveLoc, + DirectiveLoc)) + return true; + Register = getContext().getRegisterInfo().getDwarfRegNum(RegNo, true); + } else + return getParser().ParseAbsoluteExpression(Register); + + return false; +} + +/// ParseDirectiveCFIDefCfa +/// ::= .cfi_def_cfa register, offset +bool GenericAsmParser::ParseDirectiveCFIDefCfa(StringRef, + SMLoc DirectiveLoc) { + int64_t Register = 0; + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + int64_t Offset = 0; + if (getParser().ParseAbsoluteExpression(Offset)) + return true; + + getStreamer().EmitCFIDefCfa(Register, Offset); + return false; +} + +/// ParseDirectiveCFIDefCfaOffset +/// ::= .cfi_def_cfa_offset offset +bool GenericAsmParser::ParseDirectiveCFIDefCfaOffset(StringRef, + SMLoc DirectiveLoc) { + int64_t Offset = 0; + if (getParser().ParseAbsoluteExpression(Offset)) + return true; + + getStreamer().EmitCFIDefCfaOffset(Offset); + return false; +} + +/// ParseDirectiveCFIAdjustCfaOffset +/// ::= .cfi_adjust_cfa_offset adjustment +bool GenericAsmParser::ParseDirectiveCFIAdjustCfaOffset(StringRef, + SMLoc DirectiveLoc) { + int64_t Adjustment = 0; + if (getParser().ParseAbsoluteExpression(Adjustment)) + return true; + + getStreamer().EmitCFIAdjustCfaOffset(Adjustment); + return false; +} + +/// ParseDirectiveCFIDefCfaRegister +/// ::= .cfi_def_cfa_register register +bool GenericAsmParser::ParseDirectiveCFIDefCfaRegister(StringRef, + SMLoc DirectiveLoc) { + int64_t Register = 0; + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + getStreamer().EmitCFIDefCfaRegister(Register); + return false; +} + +/// ParseDirectiveCFIOffset +/// ::= .cfi_offset register, offset +bool GenericAsmParser::ParseDirectiveCFIOffset(StringRef, SMLoc DirectiveLoc) { + int64_t Register = 0; + int64_t Offset = 0; + + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + if (getParser().ParseAbsoluteExpression(Offset)) + return true; + + getStreamer().EmitCFIOffset(Register, Offset); + return false; +} + +/// ParseDirectiveCFIRelOffset +/// ::= .cfi_rel_offset register, offset +bool GenericAsmParser::ParseDirectiveCFIRelOffset(StringRef, + SMLoc DirectiveLoc) { + int64_t Register = 0; + + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + int64_t Offset = 0; + if (getParser().ParseAbsoluteExpression(Offset)) + return true; + + getStreamer().EmitCFIRelOffset(Register, Offset); + return false; +} + +static bool isValidEncoding(int64_t Encoding) { + if (Encoding & ~0xff) + return false; + + if (Encoding == dwarf::DW_EH_PE_omit) + return true; + + const unsigned Format = Encoding & 0xf; + if (Format != dwarf::DW_EH_PE_absptr && Format != dwarf::DW_EH_PE_udata2 && + Format != dwarf::DW_EH_PE_udata4 && Format != dwarf::DW_EH_PE_udata8 && + Format != dwarf::DW_EH_PE_sdata2 && Format != dwarf::DW_EH_PE_sdata4 && + Format != dwarf::DW_EH_PE_sdata8 && Format != dwarf::DW_EH_PE_signed) + return false; + + const unsigned Application = Encoding & 0x70; + if (Application != dwarf::DW_EH_PE_absptr && + Application != dwarf::DW_EH_PE_pcrel) + return false; + + return true; +} + +/// ParseDirectiveCFIPersonalityOrLsda +/// ::= .cfi_personality encoding, [symbol_name] +/// ::= .cfi_lsda encoding, [symbol_name] +bool GenericAsmParser::ParseDirectiveCFIPersonalityOrLsda(StringRef IDVal, + SMLoc DirectiveLoc) { + int64_t Encoding = 0; + if (getParser().ParseAbsoluteExpression(Encoding)) + return true; + if (Encoding == dwarf::DW_EH_PE_omit) + return false; + + if (!isValidEncoding(Encoding)) + return TokError("unsupported encoding."); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (IDVal == ".cfi_personality") + getStreamer().EmitCFIPersonality(Sym, Encoding); + else { + assert(IDVal == ".cfi_lsda"); + getStreamer().EmitCFILsda(Sym, Encoding); + } + return false; +} + +/// ParseDirectiveCFIRememberState +/// ::= .cfi_remember_state +bool GenericAsmParser::ParseDirectiveCFIRememberState(StringRef IDVal, + SMLoc DirectiveLoc) { + getStreamer().EmitCFIRememberState(); + return false; +} + +/// ParseDirectiveCFIRestoreState +/// ::= .cfi_remember_state +bool GenericAsmParser::ParseDirectiveCFIRestoreState(StringRef IDVal, + SMLoc DirectiveLoc) { + getStreamer().EmitCFIRestoreState(); + return false; +} + +/// ParseDirectiveCFISameValue +/// ::= .cfi_same_value register +bool GenericAsmParser::ParseDirectiveCFISameValue(StringRef IDVal, + SMLoc DirectiveLoc) { + int64_t Register = 0; + + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + getStreamer().EmitCFISameValue(Register); + + return false; +} + +/// ParseDirectiveCFIRestore +/// ::= .cfi_restore register +bool GenericAsmParser::ParseDirectiveCFIRestore(StringRef IDVal, + SMLoc DirectiveLoc) { + int64_t Register = 0; + if (ParseRegisterOrRegisterNumber(Register, DirectiveLoc)) + return true; + + getStreamer().EmitCFIRestore(Register); + + return false; +} + +/// ParseDirectiveCFIEscape +/// ::= .cfi_escape expression[,...] +bool GenericAsmParser::ParseDirectiveCFIEscape(StringRef IDVal, + SMLoc DirectiveLoc) { + std::string Values; + int64_t CurrValue; + if (getParser().ParseAbsoluteExpression(CurrValue)) + return true; + + Values.push_back((uint8_t)CurrValue); + + while (getLexer().is(AsmToken::Comma)) { + Lex(); + + if (getParser().ParseAbsoluteExpression(CurrValue)) + return true; + + Values.push_back((uint8_t)CurrValue); + } + + getStreamer().EmitCFIEscape(Values); + return false; +} + +/// ParseDirectiveCFISignalFrame +/// ::= .cfi_signal_frame +bool GenericAsmParser::ParseDirectiveCFISignalFrame(StringRef Directive, + SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return Error(getLexer().getLoc(), + "unexpected token in '" + Directive + "' directive"); + + getStreamer().EmitCFISignalFrame(); + + return false; +} + +/// ParseDirectiveMacrosOnOff +/// ::= .macros_on +/// ::= .macros_off +bool GenericAsmParser::ParseDirectiveMacrosOnOff(StringRef Directive, + SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return Error(getLexer().getLoc(), + "unexpected token in '" + Directive + "' directive"); + + getParser().MacrosEnabled = Directive == ".macros_on"; + + return false; +} + +/// ParseDirectiveMacro +/// ::= .macro name [parameters] +bool GenericAsmParser::ParseDirectiveMacro(StringRef Directive, + SMLoc DirectiveLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + MacroParameters Parameters; + if (getLexer().isNot(AsmToken::EndOfStatement)) { + for(;;) { + StringRef Parameter; + if (getParser().ParseIdentifier(Parameter)) + return TokError("expected identifier in directive"); + Parameters.push_back(Parameter); + + if (getLexer().isNot(AsmToken::Comma)) + break; + Lex(); + } + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.macro' directive"); + + // Eat the end of statement. + Lex(); + + AsmToken EndToken, StartToken = getTok(); + + // Lex the macro definition. + for (;;) { + // Check whether we have reached the end of the file. + if (getLexer().is(AsmToken::Eof)) + return Error(DirectiveLoc, "no matching '.endmacro' in definition"); + + // Otherwise, check whether we have reach the .endmacro. + if (getLexer().is(AsmToken::Identifier) && + (getTok().getIdentifier() == ".endm" || + getTok().getIdentifier() == ".endmacro")) { + EndToken = getTok(); + Lex(); + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '" + EndToken.getIdentifier() + + "' directive"); + break; + } + + // Otherwise, scan til the end of the statement. + getParser().EatToEndOfStatement(); + } + + if (getParser().MacroMap.lookup(Name)) { + return Error(DirectiveLoc, "macro '" + Name + "' is already defined"); + } + + const char *BodyStart = StartToken.getLoc().getPointer(); + const char *BodyEnd = EndToken.getLoc().getPointer(); + StringRef Body = StringRef(BodyStart, BodyEnd - BodyStart); + getParser().MacroMap[Name] = new Macro(Name, Body, Parameters); + return false; +} + +/// ParseDirectiveEndMacro +/// ::= .endm +/// ::= .endmacro +bool GenericAsmParser::ParseDirectiveEndMacro(StringRef Directive, + SMLoc DirectiveLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '" + Directive + "' directive"); + + // If we are inside a macro instantiation, terminate the current + // instantiation. + if (!getParser().ActiveMacros.empty()) { + getParser().HandleMacroExit(); + return false; + } + + // Otherwise, this .endmacro is a stray entry in the file; well formed + // .endmacro directives are handled during the macro definition parsing. + return TokError("unexpected '" + Directive + "' in file, " + "no current macro definition"); +} + +/// ParseDirectivePurgeMacro +/// ::= .purgem +bool GenericAsmParser::ParseDirectivePurgeMacro(StringRef Directive, + SMLoc DirectiveLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in '.purgem' directive"); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.purgem' directive"); + + StringMap<Macro*>::iterator I = getParser().MacroMap.find(Name); + if (I == getParser().MacroMap.end()) + return Error(DirectiveLoc, "macro '" + Name + "' is not defined"); + + // Undefine the macro. + delete I->getValue(); + getParser().MacroMap.erase(I); + return false; +} + +bool GenericAsmParser::ParseDirectiveLEB128(StringRef DirName, SMLoc) { + getParser().CheckForValidSection(); + + const MCExpr *Value; + + if (getParser().ParseExpression(Value)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + if (DirName[1] == 's') + getStreamer().EmitSLEB128Value(Value); + else + getStreamer().EmitULEB128Value(Value); + + return false; +} + +Macro *AsmParser::ParseMacroLikeBody(SMLoc DirectiveLoc) { + AsmToken EndToken, StartToken = getTok(); + + unsigned NestLevel = 0; + for (;;) { + // Check whether we have reached the end of the file. + if (getLexer().is(AsmToken::Eof)) { + Error(DirectiveLoc, "no matching '.endr' in definition"); + return 0; + } + + if (Lexer.is(AsmToken::Identifier) && + (getTok().getIdentifier() == ".rept")) { + ++NestLevel; + } + + // Otherwise, check whether we have reached the .endr. + if (Lexer.is(AsmToken::Identifier) && + getTok().getIdentifier() == ".endr") { + if (NestLevel == 0) { + EndToken = getTok(); + Lex(); + if (Lexer.isNot(AsmToken::EndOfStatement)) { + TokError("unexpected token in '.endr' directive"); + return 0; + } + break; + } + --NestLevel; + } + + // Otherwise, scan till the end of the statement. + EatToEndOfStatement(); + } + + const char *BodyStart = StartToken.getLoc().getPointer(); + const char *BodyEnd = EndToken.getLoc().getPointer(); + StringRef Body = StringRef(BodyStart, BodyEnd - BodyStart); + + // We Are Anonymous. + StringRef Name; + MacroParameters Parameters; + return new Macro(Name, Body, Parameters); +} + +void AsmParser::InstantiateMacroLikeBody(Macro *M, SMLoc DirectiveLoc, + raw_svector_ostream &OS) { + OS << ".endr\n"; + + MemoryBuffer *Instantiation = + MemoryBuffer::getMemBufferCopy(OS.str(), "<instantiation>"); + + // Create the macro instantiation object and add to the current macro + // instantiation stack. + MacroInstantiation *MI = new MacroInstantiation(M, DirectiveLoc, + getTok().getLoc(), + Instantiation); + ActiveMacros.push_back(MI); + + // Jump to the macro instantiation and prime the lexer. + CurBuffer = SrcMgr.AddNewSourceBuffer(MI->Instantiation, SMLoc()); + Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer)); + Lex(); +} + +bool AsmParser::ParseDirectiveRept(SMLoc DirectiveLoc) { + int64_t Count; + if (ParseAbsoluteExpression(Count)) + return TokError("unexpected token in '.rept' directive"); + + if (Count < 0) + return TokError("Count is negative"); + + if (Lexer.isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.rept' directive"); + + // Eat the end of statement. + Lex(); + + // Lex the rept definition. + Macro *M = ParseMacroLikeBody(DirectiveLoc); + if (!M) + return true; + + // Macro instantiation is lexical, unfortunately. We construct a new buffer + // to hold the macro body with substitutions. + SmallString<256> Buf; + MacroParameters Parameters; + MacroArguments A; + raw_svector_ostream OS(Buf); + while (Count--) { + if (expandMacro(OS, M->Body, Parameters, A, getTok().getLoc())) + return true; + } + InstantiateMacroLikeBody(M, DirectiveLoc, OS); + + return false; +} + +/// ParseDirectiveIrp +/// ::= .irp symbol,values +bool AsmParser::ParseDirectiveIrp(SMLoc DirectiveLoc) { + MacroParameters Parameters; + MacroParameter Parameter; + + if (ParseIdentifier(Parameter)) + return TokError("expected identifier in '.irp' directive"); + + Parameters.push_back(Parameter); + + if (Lexer.isNot(AsmToken::Comma)) + return TokError("expected comma in '.irp' directive"); + + Lex(); + + MacroArguments A; + if (ParseMacroArguments(0, A)) + return true; + + // Eat the end of statement. + Lex(); + + // Lex the irp definition. + Macro *M = ParseMacroLikeBody(DirectiveLoc); + if (!M) + return true; + + // Macro instantiation is lexical, unfortunately. We construct a new buffer + // to hold the macro body with substitutions. + SmallString<256> Buf; + raw_svector_ostream OS(Buf); + + for (std::vector<MacroArgument>::iterator i = A.begin(), e = A.end(); i != e; + ++i) { + std::vector<MacroArgument> Args; + Args.push_back(*i); + + if (expandMacro(OS, M->Body, Parameters, Args, getTok().getLoc())) + return true; + } + + InstantiateMacroLikeBody(M, DirectiveLoc, OS); + + return false; +} + +/// ParseDirectiveIrpc +/// ::= .irpc symbol,values +bool AsmParser::ParseDirectiveIrpc(SMLoc DirectiveLoc) { + MacroParameters Parameters; + MacroParameter Parameter; + + if (ParseIdentifier(Parameter)) + return TokError("expected identifier in '.irpc' directive"); + + Parameters.push_back(Parameter); + + if (Lexer.isNot(AsmToken::Comma)) + return TokError("expected comma in '.irpc' directive"); + + Lex(); + + MacroArguments A; + if (ParseMacroArguments(0, A)) + return true; + + if (A.size() != 1 || A.front().size() != 1) + return TokError("unexpected token in '.irpc' directive"); + + // Eat the end of statement. + Lex(); + + // Lex the irpc definition. + Macro *M = ParseMacroLikeBody(DirectiveLoc); + if (!M) + return true; + + // Macro instantiation is lexical, unfortunately. We construct a new buffer + // to hold the macro body with substitutions. + SmallString<256> Buf; + raw_svector_ostream OS(Buf); + + StringRef Values = A.front().front().getString(); + std::size_t I, End = Values.size(); + for (I = 0; I < End; ++I) { + MacroArgument Arg; + Arg.push_back(AsmToken(AsmToken::Identifier, Values.slice(I, I+1))); + + MacroArguments Args; + Args.push_back(Arg); + + if (expandMacro(OS, M->Body, Parameters, Args, getTok().getLoc())) + return true; + } + + InstantiateMacroLikeBody(M, DirectiveLoc, OS); + + return false; +} + +bool AsmParser::ParseDirectiveEndr(SMLoc DirectiveLoc) { + if (ActiveMacros.empty()) + return TokError("unexpected '.endr' directive, no current .rept"); + + // The only .repl that should get here are the ones created by + // InstantiateMacroLikeBody. + assert(getLexer().is(AsmToken::EndOfStatement)); + + HandleMacroExit(); + return false; +} + +/// \brief Create an MCAsmParser instance. +MCAsmParser *llvm::createMCAsmParser(SourceMgr &SM, + MCContext &C, MCStreamer &Out, + const MCAsmInfo &MAI) { + return new AsmParser(SM, C, Out, MAI); +} diff --git a/contrib/llvm/lib/MC/MCParser/COFFAsmParser.cpp b/contrib/llvm/lib/MC/MCParser/COFFAsmParser.cpp new file mode 100644 index 0000000..c4cdc3c --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/COFFAsmParser.cpp @@ -0,0 +1,498 @@ +//===- COFFAsmParser.cpp - COFF Assembly Parser ---------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmParserExtension.h" +#include "llvm/ADT/StringSwitch.h" +#include "llvm/ADT/Twine.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCParser/MCAsmLexer.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCSectionCOFF.h" +#include "llvm/MC/MCStreamer.h" +#include "llvm/MC/MCExpr.h" +#include "llvm/MC/MCTargetAsmParser.h" +#include "llvm/Support/COFF.h" +using namespace llvm; + +namespace { + +class COFFAsmParser : public MCAsmParserExtension { + template<bool (COFFAsmParser::*Handler)(StringRef, SMLoc)> + void AddDirectiveHandler(StringRef Directive) { + getParser().AddDirectiveHandler(this, Directive, + HandleDirective<COFFAsmParser, Handler>); + } + + bool ParseSectionSwitch(StringRef Section, + unsigned Characteristics, + SectionKind Kind); + + virtual void Initialize(MCAsmParser &Parser) { + // Call the base implementation. + MCAsmParserExtension::Initialize(Parser); + + AddDirectiveHandler<&COFFAsmParser::ParseSectionDirectiveText>(".text"); + AddDirectiveHandler<&COFFAsmParser::ParseSectionDirectiveData>(".data"); + AddDirectiveHandler<&COFFAsmParser::ParseSectionDirectiveBSS>(".bss"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveDef>(".def"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveScl>(".scl"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveType>(".type"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveEndef>(".endef"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveSecRel32>(".secrel32"); + + // Win64 EH directives. + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveStartProc>( + ".seh_proc"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveEndProc>( + ".seh_endproc"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveStartChained>( + ".seh_startchained"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveEndChained>( + ".seh_endchained"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveHandler>( + ".seh_handler"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveHandlerData>( + ".seh_handlerdata"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectivePushReg>( + ".seh_pushreg"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveSetFrame>( + ".seh_setframe"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveAllocStack>( + ".seh_stackalloc"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveSaveReg>( + ".seh_savereg"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveSaveXMM>( + ".seh_savexmm"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectivePushFrame>( + ".seh_pushframe"); + AddDirectiveHandler<&COFFAsmParser::ParseSEHDirectiveEndProlog>( + ".seh_endprologue"); + AddDirectiveHandler<&COFFAsmParser::ParseDirectiveSymbolAttribute>(".weak"); + } + + bool ParseSectionDirectiveText(StringRef, SMLoc) { + return ParseSectionSwitch(".text", + COFF::IMAGE_SCN_CNT_CODE + | COFF::IMAGE_SCN_MEM_EXECUTE + | COFF::IMAGE_SCN_MEM_READ, + SectionKind::getText()); + } + bool ParseSectionDirectiveData(StringRef, SMLoc) { + return ParseSectionSwitch(".data", + COFF::IMAGE_SCN_CNT_INITIALIZED_DATA + | COFF::IMAGE_SCN_MEM_READ + | COFF::IMAGE_SCN_MEM_WRITE, + SectionKind::getDataRel()); + } + bool ParseSectionDirectiveBSS(StringRef, SMLoc) { + return ParseSectionSwitch(".bss", + COFF::IMAGE_SCN_CNT_UNINITIALIZED_DATA + | COFF::IMAGE_SCN_MEM_READ + | COFF::IMAGE_SCN_MEM_WRITE, + SectionKind::getBSS()); + } + + bool ParseDirectiveDef(StringRef, SMLoc); + bool ParseDirectiveScl(StringRef, SMLoc); + bool ParseDirectiveType(StringRef, SMLoc); + bool ParseDirectiveEndef(StringRef, SMLoc); + bool ParseDirectiveSecRel32(StringRef, SMLoc); + + // Win64 EH directives. + bool ParseSEHDirectiveStartProc(StringRef, SMLoc); + bool ParseSEHDirectiveEndProc(StringRef, SMLoc); + bool ParseSEHDirectiveStartChained(StringRef, SMLoc); + bool ParseSEHDirectiveEndChained(StringRef, SMLoc); + bool ParseSEHDirectiveHandler(StringRef, SMLoc); + bool ParseSEHDirectiveHandlerData(StringRef, SMLoc); + bool ParseSEHDirectivePushReg(StringRef, SMLoc); + bool ParseSEHDirectiveSetFrame(StringRef, SMLoc); + bool ParseSEHDirectiveAllocStack(StringRef, SMLoc); + bool ParseSEHDirectiveSaveReg(StringRef, SMLoc); + bool ParseSEHDirectiveSaveXMM(StringRef, SMLoc); + bool ParseSEHDirectivePushFrame(StringRef, SMLoc); + bool ParseSEHDirectiveEndProlog(StringRef, SMLoc); + + bool ParseAtUnwindOrAtExcept(bool &unwind, bool &except); + bool ParseSEHRegisterNumber(unsigned &RegNo); + bool ParseDirectiveSymbolAttribute(StringRef Directive, SMLoc); +public: + COFFAsmParser() {} +}; + +} // end annonomous namespace. + +/// ParseDirectiveSymbolAttribute +/// ::= { ".weak", ... } [ identifier ( , identifier )* ] +bool COFFAsmParser::ParseDirectiveSymbolAttribute(StringRef Directive, SMLoc) { + MCSymbolAttr Attr = StringSwitch<MCSymbolAttr>(Directive) + .Case(".weak", MCSA_Weak) + .Default(MCSA_Invalid); + assert(Attr != MCSA_Invalid && "unexpected symbol attribute directive!"); + if (getLexer().isNot(AsmToken::EndOfStatement)) { + for (;;) { + StringRef Name; + + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + getStreamer().EmitSymbolAttribute(Sym, Attr); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + } + } + + Lex(); + return false; +} + +bool COFFAsmParser::ParseSectionSwitch(StringRef Section, + unsigned Characteristics, + SectionKind Kind) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in section switching directive"); + Lex(); + + getStreamer().SwitchSection(getContext().getCOFFSection( + Section, Characteristics, Kind)); + + return false; +} + +bool COFFAsmParser::ParseDirectiveDef(StringRef, SMLoc) { + StringRef SymbolName; + + if (getParser().ParseIdentifier(SymbolName)) + return TokError("expected identifier in directive"); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(SymbolName); + + getStreamer().BeginCOFFSymbolDef(Sym); + + Lex(); + return false; +} + +bool COFFAsmParser::ParseDirectiveScl(StringRef, SMLoc) { + int64_t SymbolStorageClass; + if (getParser().ParseAbsoluteExpression(SymbolStorageClass)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitCOFFSymbolStorageClass(SymbolStorageClass); + return false; +} + +bool COFFAsmParser::ParseDirectiveType(StringRef, SMLoc) { + int64_t Type; + if (getParser().ParseAbsoluteExpression(Type)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitCOFFSymbolType(Type); + return false; +} + +bool COFFAsmParser::ParseDirectiveEndef(StringRef, SMLoc) { + Lex(); + getStreamer().EndCOFFSymbolDef(); + return false; +} + +bool COFFAsmParser::ParseDirectiveSecRel32(StringRef, SMLoc) { + StringRef SymbolID; + if (getParser().ParseIdentifier(SymbolID)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + MCSymbol *Symbol = getContext().GetOrCreateSymbol(SymbolID); + + Lex(); + getStreamer().EmitCOFFSecRel32(Symbol); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveStartProc(StringRef, SMLoc) { + StringRef SymbolID; + if (getParser().ParseIdentifier(SymbolID)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + MCSymbol *Symbol = getContext().GetOrCreateSymbol(SymbolID); + + Lex(); + getStreamer().EmitWin64EHStartProc(Symbol); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveEndProc(StringRef, SMLoc) { + Lex(); + getStreamer().EmitWin64EHEndProc(); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveStartChained(StringRef, SMLoc) { + Lex(); + getStreamer().EmitWin64EHStartChained(); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveEndChained(StringRef, SMLoc) { + Lex(); + getStreamer().EmitWin64EHEndChained(); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveHandler(StringRef, SMLoc) { + StringRef SymbolID; + if (getParser().ParseIdentifier(SymbolID)) + return true; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("you must specify one or both of @unwind or @except"); + Lex(); + bool unwind = false, except = false; + if (ParseAtUnwindOrAtExcept(unwind, except)) + return true; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + if (ParseAtUnwindOrAtExcept(unwind, except)) + return true; + } + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + MCSymbol *handler = getContext().GetOrCreateSymbol(SymbolID); + + Lex(); + getStreamer().EmitWin64EHHandler(handler, unwind, except); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveHandlerData(StringRef, SMLoc) { + Lex(); + getStreamer().EmitWin64EHHandlerData(); + return false; +} + +bool COFFAsmParser::ParseSEHDirectivePushReg(StringRef, SMLoc L) { + unsigned Reg; + if (ParseSEHRegisterNumber(Reg)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitWin64EHPushReg(Reg); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveSetFrame(StringRef, SMLoc L) { + unsigned Reg; + int64_t Off; + if (ParseSEHRegisterNumber(Reg)) + return true; + if (getLexer().isNot(AsmToken::Comma)) + return TokError("you must specify a stack pointer offset"); + + Lex(); + SMLoc startLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Off)) + return true; + + if (Off & 0x0F) + return Error(startLoc, "offset is not a multiple of 16"); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitWin64EHSetFrame(Reg, Off); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveAllocStack(StringRef, SMLoc) { + int64_t Size; + SMLoc startLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Size)) + return true; + + if (Size & 7) + return Error(startLoc, "size is not a multiple of 8"); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitWin64EHAllocStack(Size); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveSaveReg(StringRef, SMLoc L) { + unsigned Reg; + int64_t Off; + if (ParseSEHRegisterNumber(Reg)) + return true; + if (getLexer().isNot(AsmToken::Comma)) + return TokError("you must specify an offset on the stack"); + + Lex(); + SMLoc startLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Off)) + return true; + + if (Off & 7) + return Error(startLoc, "size is not a multiple of 8"); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + // FIXME: Err on %xmm* registers + getStreamer().EmitWin64EHSaveReg(Reg, Off); + return false; +} + +// FIXME: This method is inherently x86-specific. It should really be in the +// x86 backend. +bool COFFAsmParser::ParseSEHDirectiveSaveXMM(StringRef, SMLoc L) { + unsigned Reg; + int64_t Off; + if (ParseSEHRegisterNumber(Reg)) + return true; + if (getLexer().isNot(AsmToken::Comma)) + return TokError("you must specify an offset on the stack"); + + Lex(); + SMLoc startLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Off)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + if (Off & 0x0F) + return Error(startLoc, "offset is not a multiple of 16"); + + Lex(); + // FIXME: Err on non-%xmm* registers + getStreamer().EmitWin64EHSaveXMM(Reg, Off); + return false; +} + +bool COFFAsmParser::ParseSEHDirectivePushFrame(StringRef, SMLoc) { + bool Code = false; + StringRef CodeID; + if (getLexer().is(AsmToken::At)) { + SMLoc startLoc = getLexer().getLoc(); + Lex(); + if (!getParser().ParseIdentifier(CodeID)) { + if (CodeID != "code") + return Error(startLoc, "expected @code"); + Code = true; + } + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + Lex(); + getStreamer().EmitWin64EHPushFrame(Code); + return false; +} + +bool COFFAsmParser::ParseSEHDirectiveEndProlog(StringRef, SMLoc) { + Lex(); + getStreamer().EmitWin64EHEndProlog(); + return false; +} + +bool COFFAsmParser::ParseAtUnwindOrAtExcept(bool &unwind, bool &except) { + StringRef identifier; + if (getLexer().isNot(AsmToken::At)) + return TokError("a handler attribute must begin with '@'"); + SMLoc startLoc = getLexer().getLoc(); + Lex(); + if (getParser().ParseIdentifier(identifier)) + return Error(startLoc, "expected @unwind or @except"); + if (identifier == "unwind") + unwind = true; + else if (identifier == "except") + except = true; + else + return Error(startLoc, "expected @unwind or @except"); + return false; +} + +bool COFFAsmParser::ParseSEHRegisterNumber(unsigned &RegNo) { + SMLoc startLoc = getLexer().getLoc(); + if (getLexer().is(AsmToken::Percent)) { + const MCRegisterInfo &MRI = getContext().getRegisterInfo(); + SMLoc endLoc; + unsigned LLVMRegNo; + if (getParser().getTargetParser().ParseRegister(LLVMRegNo,startLoc,endLoc)) + return true; + +#if 0 + // FIXME: TargetAsmInfo::getCalleeSavedRegs() commits a serious layering + // violation so this validation code is disabled. + + // Check that this is a non-volatile register. + const unsigned *NVRegs = TAI.getCalleeSavedRegs(); + unsigned i; + for (i = 0; NVRegs[i] != 0; ++i) + if (NVRegs[i] == LLVMRegNo) + break; + if (NVRegs[i] == 0) + return Error(startLoc, "expected non-volatile register"); +#endif + + int SEHRegNo = MRI.getSEHRegNum(LLVMRegNo); + if (SEHRegNo < 0) + return Error(startLoc,"register can't be represented in SEH unwind info"); + RegNo = SEHRegNo; + } + else { + int64_t n; + if (getParser().ParseAbsoluteExpression(n)) + return true; + if (n > 15) + return Error(startLoc, "register number is too high"); + RegNo = n; + } + + return false; +} + +namespace llvm { + +MCAsmParserExtension *createCOFFAsmParser() { + return new COFFAsmParser; +} + +} diff --git a/contrib/llvm/lib/MC/MCParser/DarwinAsmParser.cpp b/contrib/llvm/lib/MC/MCParser/DarwinAsmParser.cpp new file mode 100644 index 0000000..18033d0 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/DarwinAsmParser.cpp @@ -0,0 +1,747 @@ +//===- DarwinAsmParser.cpp - Darwin (Mach-O) Assembly Parser --------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmParserExtension.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCSectionMachO.h" +#include "llvm/MC/MCStreamer.h" +#include "llvm/MC/MCSymbol.h" +#include "llvm/MC/MCParser/MCAsmLexer.h" +#include "llvm/MC/MCParser/MCAsmParser.h" +#include "llvm/ADT/StringSwitch.h" +#include "llvm/ADT/StringRef.h" +#include "llvm/ADT/Twine.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/SourceMgr.h" +using namespace llvm; + +namespace { + +/// \brief Implementation of directive handling which is shared across all +/// Darwin targets. +class DarwinAsmParser : public MCAsmParserExtension { + template<bool (DarwinAsmParser::*Handler)(StringRef, SMLoc)> + void AddDirectiveHandler(StringRef Directive) { + getParser().AddDirectiveHandler(this, Directive, + HandleDirective<DarwinAsmParser, Handler>); + } + + bool ParseSectionSwitch(const char *Segment, const char *Section, + unsigned TAA = 0, unsigned ImplicitAlign = 0, + unsigned StubSize = 0); + +public: + DarwinAsmParser() {} + + virtual void Initialize(MCAsmParser &Parser) { + // Call the base implementation. + this->MCAsmParserExtension::Initialize(Parser); + + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDesc>(".desc"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveLsym>(".lsym"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveSubsectionsViaSymbols>( + ".subsections_via_symbols"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDumpOrLoad>(".dump"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDumpOrLoad>(".load"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveSection>(".section"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectivePushSection>(".pushsection"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectivePopSection>(".popsection"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectivePrevious>(".previous"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveSecureLogUnique>( + ".secure_log_unique"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveSecureLogReset>( + ".secure_log_reset"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveTBSS>(".tbss"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveZerofill>(".zerofill"); + + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDataRegion>(".data_region"); + AddDirectiveHandler<&DarwinAsmParser::ParseDirectiveDataRegionEnd>(".end_data_region"); + + // Special section directives. + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveConst>(".const"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveConstData>(".const_data"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveConstructor>(".constructor"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveCString>(".cstring"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveData>(".data"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveDestructor>(".destructor"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveDyld>(".dyld"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveFVMLibInit0>(".fvmlib_init0"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveFVMLibInit1>(".fvmlib_init1"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveLazySymbolPointers>(".lazy_symbol_pointer"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveLiteral16>(".literal16"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveLiteral4>(".literal4"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveLiteral8>(".literal8"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveModInitFunc>(".mod_init_func"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveModTermFunc>(".mod_term_func"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveNonLazySymbolPointers>(".non_lazy_symbol_pointer"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCCatClsMeth>(".objc_cat_cls_meth"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCCatInstMeth>(".objc_cat_inst_meth"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCCategory>(".objc_category"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCClass>(".objc_class"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCClassNames>(".objc_class_names"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCClassVars>(".objc_class_vars"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCClsMeth>(".objc_cls_meth"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCClsRefs>(".objc_cls_refs"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCInstMeth>(".objc_inst_meth"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCInstanceVars>(".objc_instance_vars"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCMessageRefs>(".objc_message_refs"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCMetaClass>(".objc_meta_class"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCMethVarNames>(".objc_meth_var_names"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCMethVarTypes>(".objc_meth_var_types"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCModuleInfo>(".objc_module_info"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCProtocol>(".objc_protocol"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCSelectorStrs>(".objc_selector_strs"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCStringObject>(".objc_string_object"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveObjCSymbols>(".objc_symbols"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectivePICSymbolStub>(".picsymbol_stub"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveStaticConst>(".static_const"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveStaticData>(".static_data"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveSymbolStub>(".symbol_stub"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveTData>(".tdata"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveText>(".text"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveThreadInitFunc>(".thread_init_func"); + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveTLV>(".tlv"); + + AddDirectiveHandler<&DarwinAsmParser::ParseSectionDirectiveIdent>(".ident"); + } + + bool ParseDirectiveDesc(StringRef, SMLoc); + bool ParseDirectiveDumpOrLoad(StringRef, SMLoc); + bool ParseDirectiveLsym(StringRef, SMLoc); + bool ParseDirectiveSection(StringRef, SMLoc); + bool ParseDirectivePushSection(StringRef, SMLoc); + bool ParseDirectivePopSection(StringRef, SMLoc); + bool ParseDirectivePrevious(StringRef, SMLoc); + bool ParseDirectiveSecureLogReset(StringRef, SMLoc); + bool ParseDirectiveSecureLogUnique(StringRef, SMLoc); + bool ParseDirectiveSubsectionsViaSymbols(StringRef, SMLoc); + bool ParseDirectiveTBSS(StringRef, SMLoc); + bool ParseDirectiveZerofill(StringRef, SMLoc); + bool ParseDirectiveDataRegion(StringRef, SMLoc); + bool ParseDirectiveDataRegionEnd(StringRef, SMLoc); + + // Named Section Directive + bool ParseSectionDirectiveConst(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__const"); + } + bool ParseSectionDirectiveStaticConst(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__static_const"); + } + bool ParseSectionDirectiveCString(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__cstring", + MCSectionMachO::S_CSTRING_LITERALS); + } + bool ParseSectionDirectiveLiteral4(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__literal4", + MCSectionMachO::S_4BYTE_LITERALS, 4); + } + bool ParseSectionDirectiveLiteral8(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__literal8", + MCSectionMachO::S_8BYTE_LITERALS, 8); + } + bool ParseSectionDirectiveLiteral16(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__literal16", + MCSectionMachO::S_16BYTE_LITERALS, 16); + } + bool ParseSectionDirectiveConstructor(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__constructor"); + } + bool ParseSectionDirectiveDestructor(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__destructor"); + } + bool ParseSectionDirectiveFVMLibInit0(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__fvmlib_init0"); + } + bool ParseSectionDirectiveFVMLibInit1(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__fvmlib_init1"); + } + bool ParseSectionDirectiveSymbolStub(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__symbol_stub", + MCSectionMachO::S_SYMBOL_STUBS | + MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS, + // FIXME: Different on PPC and ARM. + 0, 16); + } + bool ParseSectionDirectivePICSymbolStub(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT","__picsymbol_stub", + MCSectionMachO::S_SYMBOL_STUBS | + MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS, 0, 26); + } + bool ParseSectionDirectiveData(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__data"); + } + bool ParseSectionDirectiveStaticData(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__static_data"); + } + bool ParseSectionDirectiveNonLazySymbolPointers(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__nl_symbol_ptr", + MCSectionMachO::S_NON_LAZY_SYMBOL_POINTERS, 4); + } + bool ParseSectionDirectiveLazySymbolPointers(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__la_symbol_ptr", + MCSectionMachO::S_LAZY_SYMBOL_POINTERS, 4); + } + bool ParseSectionDirectiveDyld(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__dyld"); + } + bool ParseSectionDirectiveModInitFunc(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__mod_init_func", + MCSectionMachO::S_MOD_INIT_FUNC_POINTERS, 4); + } + bool ParseSectionDirectiveModTermFunc(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__mod_term_func", + MCSectionMachO::S_MOD_TERM_FUNC_POINTERS, 4); + } + bool ParseSectionDirectiveConstData(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__const"); + } + bool ParseSectionDirectiveObjCClass(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__class", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCMetaClass(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__meta_class", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCCatClsMeth(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__cat_cls_meth", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCCatInstMeth(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__cat_inst_meth", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCProtocol(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__protocol", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCStringObject(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__string_object", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCClsMeth(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__cls_meth", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCInstMeth(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__inst_meth", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCClsRefs(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__cls_refs", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP | + MCSectionMachO::S_LITERAL_POINTERS, 4); + } + bool ParseSectionDirectiveObjCMessageRefs(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__message_refs", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP | + MCSectionMachO::S_LITERAL_POINTERS, 4); + } + bool ParseSectionDirectiveObjCSymbols(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__symbols", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCCategory(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__category", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCClassVars(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__class_vars", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCInstanceVars(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__instance_vars", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCModuleInfo(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__module_info", + MCSectionMachO::S_ATTR_NO_DEAD_STRIP); + } + bool ParseSectionDirectiveObjCClassNames(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__cstring", + MCSectionMachO::S_CSTRING_LITERALS); + } + bool ParseSectionDirectiveObjCMethVarTypes(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__cstring", + MCSectionMachO::S_CSTRING_LITERALS); + } + bool ParseSectionDirectiveObjCMethVarNames(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__cstring", + MCSectionMachO::S_CSTRING_LITERALS); + } + bool ParseSectionDirectiveObjCSelectorStrs(StringRef, SMLoc) { + return ParseSectionSwitch("__OBJC", "__selector_strs", + MCSectionMachO::S_CSTRING_LITERALS); + } + bool ParseSectionDirectiveTData(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__thread_data", + MCSectionMachO::S_THREAD_LOCAL_REGULAR); + } + bool ParseSectionDirectiveText(StringRef, SMLoc) { + return ParseSectionSwitch("__TEXT", "__text", + MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS); + } + bool ParseSectionDirectiveTLV(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__thread_vars", + MCSectionMachO::S_THREAD_LOCAL_VARIABLES); + } + bool ParseSectionDirectiveIdent(StringRef, SMLoc) { + // Darwin silently ignores the .ident directive. + getParser().EatToEndOfStatement(); + return false; + } + bool ParseSectionDirectiveThreadInitFunc(StringRef, SMLoc) { + return ParseSectionSwitch("__DATA", "__thread_init", + MCSectionMachO::S_THREAD_LOCAL_INIT_FUNCTION_POINTERS); + } + +}; + +} // end anonymous namespace + +bool DarwinAsmParser::ParseSectionSwitch(const char *Segment, + const char *Section, + unsigned TAA, unsigned Align, + unsigned StubSize) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in section switching directive"); + Lex(); + + // FIXME: Arch specific. + bool isText = StringRef(Segment) == "__TEXT"; // FIXME: Hack. + getStreamer().SwitchSection(getContext().getMachOSection( + Segment, Section, TAA, StubSize, + isText ? SectionKind::getText() + : SectionKind::getDataRel())); + + // Set the implicit alignment, if any. + // + // FIXME: This isn't really what 'as' does; I think it just uses the implicit + // alignment on the section (e.g., if one manually inserts bytes into the + // section, then just issuing the section switch directive will not realign + // the section. However, this is arguably more reasonable behavior, and there + // is no good reason for someone to intentionally emit incorrectly sized + // values into the implicitly aligned sections. + if (Align) + getStreamer().EmitValueToAlignment(Align, 0, 1, 0); + + return false; +} + +/// ParseDirectiveDesc +/// ::= .desc identifier , expression +bool DarwinAsmParser::ParseDirectiveDesc(StringRef, SMLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + // Handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.desc' directive"); + Lex(); + + int64_t DescValue; + if (getParser().ParseAbsoluteExpression(DescValue)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.desc' directive"); + + Lex(); + + // Set the n_desc field of this Symbol to this DescValue + getStreamer().EmitSymbolDesc(Sym, DescValue); + + return false; +} + +/// ParseDirectiveDumpOrLoad +/// ::= ( .dump | .load ) "filename" +bool DarwinAsmParser::ParseDirectiveDumpOrLoad(StringRef Directive, + SMLoc IDLoc) { + bool IsDump = Directive == ".dump"; + if (getLexer().isNot(AsmToken::String)) + return TokError("expected string in '.dump' or '.load' directive"); + + Lex(); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.dump' or '.load' directive"); + + Lex(); + + // FIXME: If/when .dump and .load are implemented they will be done in the + // the assembly parser and not have any need for an MCStreamer API. + if (IsDump) + return Warning(IDLoc, "ignoring directive .dump for now"); + else + return Warning(IDLoc, "ignoring directive .load for now"); +} + +/// ParseDirectiveLsym +/// ::= .lsym identifier , expression +bool DarwinAsmParser::ParseDirectiveLsym(StringRef, SMLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + // Handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.lsym' directive"); + Lex(); + + const MCExpr *Value; + if (getParser().ParseExpression(Value)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.lsym' directive"); + + Lex(); + + // We don't currently support this directive. + // + // FIXME: Diagnostic location! + (void) Sym; + return TokError("directive '.lsym' is unsupported"); +} + +/// ParseDirectiveSection: +/// ::= .section identifier (',' identifier)* +bool DarwinAsmParser::ParseDirectiveSection(StringRef, SMLoc) { + SMLoc Loc = getLexer().getLoc(); + + StringRef SectionName; + if (getParser().ParseIdentifier(SectionName)) + return Error(Loc, "expected identifier after '.section' directive"); + + // Verify there is a following comma. + if (!getLexer().is(AsmToken::Comma)) + return TokError("unexpected token in '.section' directive"); + + std::string SectionSpec = SectionName; + SectionSpec += ","; + + // Add all the tokens until the end of the line, ParseSectionSpecifier will + // handle this. + StringRef EOL = getLexer().LexUntilEndOfStatement(); + SectionSpec.append(EOL.begin(), EOL.end()); + + Lex(); + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.section' directive"); + Lex(); + + + StringRef Segment, Section; + unsigned StubSize; + unsigned TAA; + bool TAAParsed; + std::string ErrorStr = + MCSectionMachO::ParseSectionSpecifier(SectionSpec, Segment, Section, + TAA, TAAParsed, StubSize); + + if (!ErrorStr.empty()) + return Error(Loc, ErrorStr.c_str()); + + // FIXME: Arch specific. + bool isText = Segment == "__TEXT"; // FIXME: Hack. + getStreamer().SwitchSection(getContext().getMachOSection( + Segment, Section, TAA, StubSize, + isText ? SectionKind::getText() + : SectionKind::getDataRel())); + return false; +} + +/// ParseDirectivePushSection: +/// ::= .pushsection identifier (',' identifier)* +bool DarwinAsmParser::ParseDirectivePushSection(StringRef S, SMLoc Loc) { + getStreamer().PushSection(); + + if (ParseDirectiveSection(S, Loc)) { + getStreamer().PopSection(); + return true; + } + + return false; +} + +/// ParseDirectivePopSection: +/// ::= .popsection +bool DarwinAsmParser::ParseDirectivePopSection(StringRef, SMLoc) { + if (!getStreamer().PopSection()) + return TokError(".popsection without corresponding .pushsection"); + return false; +} + +/// ParseDirectivePrevious: +/// ::= .previous +bool DarwinAsmParser::ParseDirectivePrevious(StringRef DirName, SMLoc) { + const MCSection *PreviousSection = getStreamer().getPreviousSection(); + if (PreviousSection == NULL) + return TokError(".previous without corresponding .section"); + getStreamer().SwitchSection(PreviousSection); + return false; +} + +/// ParseDirectiveSecureLogUnique +/// ::= .secure_log_unique ... message ... +bool DarwinAsmParser::ParseDirectiveSecureLogUnique(StringRef, SMLoc IDLoc) { + StringRef LogMessage = getParser().ParseStringToEndOfStatement(); + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.secure_log_unique' directive"); + + if (getContext().getSecureLogUsed() != false) + return Error(IDLoc, ".secure_log_unique specified multiple times"); + + // Get the secure log path. + const char *SecureLogFile = getContext().getSecureLogFile(); + if (SecureLogFile == NULL) + return Error(IDLoc, ".secure_log_unique used but AS_SECURE_LOG_FILE " + "environment variable unset."); + + // Open the secure log file if we haven't already. + raw_ostream *OS = getContext().getSecureLog(); + if (OS == NULL) { + std::string Err; + OS = new raw_fd_ostream(SecureLogFile, Err, raw_fd_ostream::F_Append); + if (!Err.empty()) { + delete OS; + return Error(IDLoc, Twine("can't open secure log file: ") + + SecureLogFile + " (" + Err + ")"); + } + getContext().setSecureLog(OS); + } + + // Write the message. + int CurBuf = getSourceManager().FindBufferContainingLoc(IDLoc); + *OS << getSourceManager().getBufferInfo(CurBuf).Buffer->getBufferIdentifier() + << ":" << getSourceManager().FindLineNumber(IDLoc, CurBuf) << ":" + << LogMessage + "\n"; + + getContext().setSecureLogUsed(true); + + return false; +} + +/// ParseDirectiveSecureLogReset +/// ::= .secure_log_reset +bool DarwinAsmParser::ParseDirectiveSecureLogReset(StringRef, SMLoc IDLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.secure_log_reset' directive"); + + Lex(); + + getContext().setSecureLogUsed(false); + + return false; +} + +/// ParseDirectiveSubsectionsViaSymbols +/// ::= .subsections_via_symbols +bool DarwinAsmParser::ParseDirectiveSubsectionsViaSymbols(StringRef, SMLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.subsections_via_symbols' directive"); + + Lex(); + + getStreamer().EmitAssemblerFlag(MCAF_SubsectionsViaSymbols); + + return false; +} + +/// ParseDirectiveTBSS +/// ::= .tbss identifier, size, align +bool DarwinAsmParser::ParseDirectiveTBSS(StringRef, SMLoc) { + SMLoc IDLoc = getLexer().getLoc(); + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + // Handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + int64_t Size; + SMLoc SizeLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Size)) + return true; + + int64_t Pow2Alignment = 0; + SMLoc Pow2AlignmentLoc; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + Pow2AlignmentLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Pow2Alignment)) + return true; + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.tbss' directive"); + + Lex(); + + if (Size < 0) + return Error(SizeLoc, "invalid '.tbss' directive size, can't be less than" + "zero"); + + // FIXME: Diagnose overflow. + if (Pow2Alignment < 0) + return Error(Pow2AlignmentLoc, "invalid '.tbss' alignment, can't be less" + "than zero"); + + if (!Sym->isUndefined()) + return Error(IDLoc, "invalid symbol redefinition"); + + getStreamer().EmitTBSSSymbol(getContext().getMachOSection( + "__DATA", "__thread_bss", + MCSectionMachO::S_THREAD_LOCAL_ZEROFILL, + 0, SectionKind::getThreadBSS()), + Sym, Size, 1 << Pow2Alignment); + + return false; +} + +/// ParseDirectiveZerofill +/// ::= .zerofill segname , sectname [, identifier , size_expression [ +/// , align_expression ]] +bool DarwinAsmParser::ParseDirectiveZerofill(StringRef, SMLoc) { + StringRef Segment; + if (getParser().ParseIdentifier(Segment)) + return TokError("expected segment name after '.zerofill' directive"); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + StringRef Section; + if (getParser().ParseIdentifier(Section)) + return TokError("expected section name after comma in '.zerofill' " + "directive"); + + // If this is the end of the line all that was wanted was to create the + // the section but with no symbol. + if (getLexer().is(AsmToken::EndOfStatement)) { + // Create the zerofill section but no symbol + getStreamer().EmitZerofill(getContext().getMachOSection( + Segment, Section, MCSectionMachO::S_ZEROFILL, + 0, SectionKind::getBSS())); + return false; + } + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + SMLoc IDLoc = getLexer().getLoc(); + StringRef IDStr; + if (getParser().ParseIdentifier(IDStr)) + return TokError("expected identifier in directive"); + + // handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(IDStr); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + int64_t Size; + SMLoc SizeLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Size)) + return true; + + int64_t Pow2Alignment = 0; + SMLoc Pow2AlignmentLoc; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + Pow2AlignmentLoc = getLexer().getLoc(); + if (getParser().ParseAbsoluteExpression(Pow2Alignment)) + return true; + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.zerofill' directive"); + + Lex(); + + if (Size < 0) + return Error(SizeLoc, "invalid '.zerofill' directive size, can't be less " + "than zero"); + + // NOTE: The alignment in the directive is a power of 2 value, the assembler + // may internally end up wanting an alignment in bytes. + // FIXME: Diagnose overflow. + if (Pow2Alignment < 0) + return Error(Pow2AlignmentLoc, "invalid '.zerofill' directive alignment, " + "can't be less than zero"); + + if (!Sym->isUndefined()) + return Error(IDLoc, "invalid symbol redefinition"); + + // Create the zerofill Symbol with Size and Pow2Alignment + // + // FIXME: Arch specific. + getStreamer().EmitZerofill(getContext().getMachOSection( + Segment, Section, MCSectionMachO::S_ZEROFILL, + 0, SectionKind::getBSS()), + Sym, Size, 1 << Pow2Alignment); + + return false; +} + +/// ParseDirectiveDataRegion +/// ::= .data_region [ ( jt8 | jt16 | jt32 ) ] +bool DarwinAsmParser::ParseDirectiveDataRegion(StringRef, SMLoc) { + if (getLexer().is(AsmToken::EndOfStatement)) { + Lex(); + getStreamer().EmitDataRegion(MCDR_DataRegion); + return false; + } + StringRef RegionType; + SMLoc Loc = getParser().getTok().getLoc(); + if (getParser().ParseIdentifier(RegionType)) + return TokError("expected region type after '.data_region' directive"); + int Kind = StringSwitch<int>(RegionType) + .Case("jt8", MCDR_DataRegionJT8) + .Case("jt16", MCDR_DataRegionJT16) + .Case("jt32", MCDR_DataRegionJT32) + .Default(-1); + if (Kind == -1) + return Error(Loc, "unknown region type in '.data_region' directive"); + Lex(); + + getStreamer().EmitDataRegion((MCDataRegionType)Kind); + return false; +} + +/// ParseDirectiveDataRegionEnd +/// ::= .end_data_region +bool DarwinAsmParser::ParseDirectiveDataRegionEnd(StringRef, SMLoc) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.end_data_region' directive"); + + Lex(); + getStreamer().EmitDataRegion(MCDR_DataRegionEnd); + return false; +} + +namespace llvm { + +MCAsmParserExtension *createDarwinAsmParser() { + return new DarwinAsmParser; +} + +} // end llvm namespace diff --git a/contrib/llvm/lib/MC/MCParser/ELFAsmParser.cpp b/contrib/llvm/lib/MC/MCParser/ELFAsmParser.cpp new file mode 100644 index 0000000..9316bb1 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/ELFAsmParser.cpp @@ -0,0 +1,611 @@ +//===- ELFAsmParser.cpp - ELF Assembly Parser -----------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmParserExtension.h" +#include "llvm/ADT/StringSwitch.h" +#include "llvm/ADT/Twine.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCExpr.h" +#include "llvm/MC/MCParser/MCAsmLexer.h" +#include "llvm/MC/MCSectionELF.h" +#include "llvm/MC/MCStreamer.h" +#include "llvm/Support/ELF.h" +using namespace llvm; + +namespace { + +class ELFAsmParser : public MCAsmParserExtension { + template<bool (ELFAsmParser::*Handler)(StringRef, SMLoc)> + void AddDirectiveHandler(StringRef Directive) { + getParser().AddDirectiveHandler(this, Directive, + HandleDirective<ELFAsmParser, Handler>); + } + + bool ParseSectionSwitch(StringRef Section, unsigned Type, + unsigned Flags, SectionKind Kind); + bool SeenIdent; + +public: + ELFAsmParser() : SeenIdent(false) { + BracketExpressionsSupported = true; + } + + virtual void Initialize(MCAsmParser &Parser) { + // Call the base implementation. + this->MCAsmParserExtension::Initialize(Parser); + + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveData>(".data"); + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveText>(".text"); + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveBSS>(".bss"); + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveRoData>(".rodata"); + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveTData>(".tdata"); + AddDirectiveHandler<&ELFAsmParser::ParseSectionDirectiveTBSS>(".tbss"); + AddDirectiveHandler< + &ELFAsmParser::ParseSectionDirectiveDataRel>(".data.rel"); + AddDirectiveHandler< + &ELFAsmParser::ParseSectionDirectiveDataRelRo>(".data.rel.ro"); + AddDirectiveHandler< + &ELFAsmParser::ParseSectionDirectiveDataRelRoLocal>(".data.rel.ro.local"); + AddDirectiveHandler< + &ELFAsmParser::ParseSectionDirectiveEhFrame>(".eh_frame"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveSection>(".section"); + AddDirectiveHandler< + &ELFAsmParser::ParseDirectivePushSection>(".pushsection"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectivePopSection>(".popsection"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveSize>(".size"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectivePrevious>(".previous"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveType>(".type"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveIdent>(".ident"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveSymver>(".symver"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveVersion>(".version"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveWeakref>(".weakref"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveSymbolAttribute>(".weak"); + AddDirectiveHandler<&ELFAsmParser::ParseDirectiveSymbolAttribute>(".local"); + AddDirectiveHandler< + &ELFAsmParser::ParseDirectiveSymbolAttribute>(".protected"); + AddDirectiveHandler< + &ELFAsmParser::ParseDirectiveSymbolAttribute>(".internal"); + AddDirectiveHandler< + &ELFAsmParser::ParseDirectiveSymbolAttribute>(".hidden"); + } + + // FIXME: Part of this logic is duplicated in the MCELFStreamer. What is + // the best way for us to get access to it? + bool ParseSectionDirectiveData(StringRef, SMLoc) { + return ParseSectionSwitch(".data", ELF::SHT_PROGBITS, + ELF::SHF_WRITE |ELF::SHF_ALLOC, + SectionKind::getDataRel()); + } + bool ParseSectionDirectiveText(StringRef, SMLoc) { + return ParseSectionSwitch(".text", ELF::SHT_PROGBITS, + ELF::SHF_EXECINSTR | + ELF::SHF_ALLOC, SectionKind::getText()); + } + bool ParseSectionDirectiveBSS(StringRef, SMLoc) { + return ParseSectionSwitch(".bss", ELF::SHT_NOBITS, + ELF::SHF_WRITE | + ELF::SHF_ALLOC, SectionKind::getBSS()); + } + bool ParseSectionDirectiveRoData(StringRef, SMLoc) { + return ParseSectionSwitch(".rodata", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC, + SectionKind::getReadOnly()); + } + bool ParseSectionDirectiveTData(StringRef, SMLoc) { + return ParseSectionSwitch(".tdata", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC | + ELF::SHF_TLS | ELF::SHF_WRITE, + SectionKind::getThreadData()); + } + bool ParseSectionDirectiveTBSS(StringRef, SMLoc) { + return ParseSectionSwitch(".tbss", ELF::SHT_NOBITS, + ELF::SHF_ALLOC | + ELF::SHF_TLS | ELF::SHF_WRITE, + SectionKind::getThreadBSS()); + } + bool ParseSectionDirectiveDataRel(StringRef, SMLoc) { + return ParseSectionSwitch(".data.rel", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC | + ELF::SHF_WRITE, + SectionKind::getDataRel()); + } + bool ParseSectionDirectiveDataRelRo(StringRef, SMLoc) { + return ParseSectionSwitch(".data.rel.ro", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC | + ELF::SHF_WRITE, + SectionKind::getReadOnlyWithRel()); + } + bool ParseSectionDirectiveDataRelRoLocal(StringRef, SMLoc) { + return ParseSectionSwitch(".data.rel.ro.local", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC | + ELF::SHF_WRITE, + SectionKind::getReadOnlyWithRelLocal()); + } + bool ParseSectionDirectiveEhFrame(StringRef, SMLoc) { + return ParseSectionSwitch(".eh_frame", ELF::SHT_PROGBITS, + ELF::SHF_ALLOC | + ELF::SHF_WRITE, + SectionKind::getDataRel()); + } + bool ParseDirectivePushSection(StringRef, SMLoc); + bool ParseDirectivePopSection(StringRef, SMLoc); + bool ParseDirectiveSection(StringRef, SMLoc); + bool ParseDirectiveSize(StringRef, SMLoc); + bool ParseDirectivePrevious(StringRef, SMLoc); + bool ParseDirectiveType(StringRef, SMLoc); + bool ParseDirectiveIdent(StringRef, SMLoc); + bool ParseDirectiveSymver(StringRef, SMLoc); + bool ParseDirectiveVersion(StringRef, SMLoc); + bool ParseDirectiveWeakref(StringRef, SMLoc); + bool ParseDirectiveSymbolAttribute(StringRef, SMLoc); + +private: + bool ParseSectionName(StringRef &SectionName); +}; + +} + +/// ParseDirectiveSymbolAttribute +/// ::= { ".local", ".weak", ... } [ identifier ( , identifier )* ] +bool ELFAsmParser::ParseDirectiveSymbolAttribute(StringRef Directive, SMLoc) { + MCSymbolAttr Attr = StringSwitch<MCSymbolAttr>(Directive) + .Case(".weak", MCSA_Weak) + .Case(".local", MCSA_Local) + .Case(".hidden", MCSA_Hidden) + .Case(".internal", MCSA_Internal) + .Case(".protected", MCSA_Protected) + .Default(MCSA_Invalid); + assert(Attr != MCSA_Invalid && "unexpected symbol attribute directive!"); + if (getLexer().isNot(AsmToken::EndOfStatement)) { + for (;;) { + StringRef Name; + + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + getStreamer().EmitSymbolAttribute(Sym, Attr); + + if (getLexer().is(AsmToken::EndOfStatement)) + break; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + } + } + + Lex(); + return false; +} + +bool ELFAsmParser::ParseSectionSwitch(StringRef Section, unsigned Type, + unsigned Flags, SectionKind Kind) { + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in section switching directive"); + Lex(); + + getStreamer().SwitchSection(getContext().getELFSection( + Section, Type, Flags, Kind)); + + return false; +} + +bool ELFAsmParser::ParseDirectiveSize(StringRef, SMLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);; + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in directive"); + Lex(); + + const MCExpr *Expr; + if (getParser().ParseExpression(Expr)) + return true; + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + getStreamer().EmitELFSize(Sym, Expr); + return false; +} + +bool ELFAsmParser::ParseSectionName(StringRef &SectionName) { + // A section name can contain -, so we cannot just use + // ParseIdentifier. + SMLoc FirstLoc = getLexer().getLoc(); + unsigned Size = 0; + + if (getLexer().is(AsmToken::String)) { + SectionName = getTok().getIdentifier(); + Lex(); + return false; + } + + for (;;) { + StringRef Tmp; + unsigned CurSize; + + SMLoc PrevLoc = getLexer().getLoc(); + if (getLexer().is(AsmToken::Minus)) { + CurSize = 1; + Lex(); // Consume the "-". + } else if (getLexer().is(AsmToken::String)) { + CurSize = getTok().getIdentifier().size() + 2; + Lex(); + } else if (getLexer().is(AsmToken::Identifier)) { + CurSize = getTok().getIdentifier().size(); + Lex(); + } else { + break; + } + + Size += CurSize; + SectionName = StringRef(FirstLoc.getPointer(), Size); + + // Make sure the following token is adjacent. + if (PrevLoc.getPointer() + CurSize != getTok().getLoc().getPointer()) + break; + } + if (Size == 0) + return true; + + return false; +} + +static SectionKind computeSectionKind(unsigned Flags) { + if (Flags & ELF::SHF_EXECINSTR) + return SectionKind::getText(); + if (Flags & ELF::SHF_TLS) + return SectionKind::getThreadData(); + return SectionKind::getDataRel(); +} + +static int parseSectionFlags(StringRef flagsStr) { + int flags = 0; + + for (unsigned i = 0; i < flagsStr.size(); i++) { + switch (flagsStr[i]) { + case 'a': + flags |= ELF::SHF_ALLOC; + break; + case 'x': + flags |= ELF::SHF_EXECINSTR; + break; + case 'w': + flags |= ELF::SHF_WRITE; + break; + case 'M': + flags |= ELF::SHF_MERGE; + break; + case 'S': + flags |= ELF::SHF_STRINGS; + break; + case 'T': + flags |= ELF::SHF_TLS; + break; + case 'c': + flags |= ELF::XCORE_SHF_CP_SECTION; + break; + case 'd': + flags |= ELF::XCORE_SHF_DP_SECTION; + break; + case 'G': + flags |= ELF::SHF_GROUP; + break; + default: + return -1; + } + } + + return flags; +} + +bool ELFAsmParser::ParseDirectivePushSection(StringRef s, SMLoc loc) { + getStreamer().PushSection(); + + if (ParseDirectiveSection(s, loc)) { + getStreamer().PopSection(); + return true; + } + + return false; +} + +bool ELFAsmParser::ParseDirectivePopSection(StringRef, SMLoc) { + if (!getStreamer().PopSection()) + return TokError(".popsection without corresponding .pushsection"); + return false; +} + +// FIXME: This is a work in progress. +bool ELFAsmParser::ParseDirectiveSection(StringRef, SMLoc) { + StringRef SectionName; + + if (ParseSectionName(SectionName)) + return TokError("expected identifier in directive"); + + StringRef TypeName; + int64_t Size = 0; + StringRef GroupName; + unsigned Flags = 0; + + // Set the defaults first. + if (SectionName == ".fini" || SectionName == ".init" || + SectionName == ".rodata") + Flags |= ELF::SHF_ALLOC; + if (SectionName == ".fini" || SectionName == ".init") + Flags |= ELF::SHF_EXECINSTR; + + if (getLexer().is(AsmToken::Comma)) { + Lex(); + + if (getLexer().isNot(AsmToken::String)) + return TokError("expected string in directive"); + + StringRef FlagsStr = getTok().getStringContents(); + Lex(); + + int extraFlags = parseSectionFlags(FlagsStr); + if (extraFlags < 0) + return TokError("unknown flag"); + Flags |= extraFlags; + + bool Mergeable = Flags & ELF::SHF_MERGE; + bool Group = Flags & ELF::SHF_GROUP; + + if (getLexer().isNot(AsmToken::Comma)) { + if (Mergeable) + return TokError("Mergeable section must specify the type"); + if (Group) + return TokError("Group section must specify the type"); + } else { + Lex(); + if (getLexer().isNot(AsmToken::Percent) && getLexer().isNot(AsmToken::At)) + return TokError("expected '@' or '%' before type"); + + Lex(); + if (getParser().ParseIdentifier(TypeName)) + return TokError("expected identifier in directive"); + + if (Mergeable) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("expected the entry size"); + Lex(); + if (getParser().ParseAbsoluteExpression(Size)) + return true; + if (Size <= 0) + return TokError("entry size must be positive"); + } + + if (Group) { + if (getLexer().isNot(AsmToken::Comma)) + return TokError("expected group name"); + Lex(); + if (getParser().ParseIdentifier(GroupName)) + return true; + if (getLexer().is(AsmToken::Comma)) { + Lex(); + StringRef Linkage; + if (getParser().ParseIdentifier(Linkage)) + return true; + if (Linkage != "comdat") + return TokError("Linkage must be 'comdat'"); + } + } + } + } + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in directive"); + + unsigned Type = ELF::SHT_PROGBITS; + + if (!TypeName.empty()) { + if (TypeName == "init_array") + Type = ELF::SHT_INIT_ARRAY; + else if (TypeName == "fini_array") + Type = ELF::SHT_FINI_ARRAY; + else if (TypeName == "preinit_array") + Type = ELF::SHT_PREINIT_ARRAY; + else if (TypeName == "nobits") + Type = ELF::SHT_NOBITS; + else if (TypeName == "progbits") + Type = ELF::SHT_PROGBITS; + else if (TypeName == "note") + Type = ELF::SHT_NOTE; + else if (TypeName == "unwind") + Type = ELF::SHT_X86_64_UNWIND; + else + return TokError("unknown section type"); + } + + SectionKind Kind = computeSectionKind(Flags); + getStreamer().SwitchSection(getContext().getELFSection(SectionName, Type, + Flags, Kind, Size, + GroupName)); + return false; +} + +bool ELFAsmParser::ParseDirectivePrevious(StringRef DirName, SMLoc) { + const MCSection *PreviousSection = getStreamer().getPreviousSection(); + if (PreviousSection == NULL) + return TokError(".previous without corresponding .section"); + getStreamer().SwitchSection(PreviousSection); + + return false; +} + +/// ParseDirectiveELFType +/// ::= .type identifier , @attribute +bool ELFAsmParser::ParseDirectiveType(StringRef, SMLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + // Handle the identifier as the key symbol. + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("unexpected token in '.type' directive"); + Lex(); + + if (getLexer().isNot(AsmToken::Percent) && getLexer().isNot(AsmToken::At)) + return TokError("expected '@' or '%' before type"); + Lex(); + + StringRef Type; + SMLoc TypeLoc; + + TypeLoc = getLexer().getLoc(); + if (getParser().ParseIdentifier(Type)) + return TokError("expected symbol type in directive"); + + MCSymbolAttr Attr = StringSwitch<MCSymbolAttr>(Type) + .Case("function", MCSA_ELF_TypeFunction) + .Case("object", MCSA_ELF_TypeObject) + .Case("tls_object", MCSA_ELF_TypeTLS) + .Case("common", MCSA_ELF_TypeCommon) + .Case("notype", MCSA_ELF_TypeNoType) + .Case("gnu_unique_object", MCSA_ELF_TypeGnuUniqueObject) + .Case("gnu_indirect_function", MCSA_ELF_TypeIndFunction) + .Default(MCSA_Invalid); + + if (Attr == MCSA_Invalid) + return Error(TypeLoc, "unsupported attribute in '.type' directive"); + + if (getLexer().isNot(AsmToken::EndOfStatement)) + return TokError("unexpected token in '.type' directive"); + + Lex(); + + getStreamer().EmitSymbolAttribute(Sym, Attr); + + return false; +} + +/// ParseDirectiveIdent +/// ::= .ident string +bool ELFAsmParser::ParseDirectiveIdent(StringRef, SMLoc) { + if (getLexer().isNot(AsmToken::String)) + return TokError("unexpected token in '.ident' directive"); + + StringRef Data = getTok().getIdentifier(); + + Lex(); + + const MCSection *Comment = + getContext().getELFSection(".comment", ELF::SHT_PROGBITS, + ELF::SHF_MERGE | + ELF::SHF_STRINGS, + SectionKind::getReadOnly(), + 1, ""); + + getStreamer().PushSection(); + getStreamer().SwitchSection(Comment); + if (!SeenIdent) { + getStreamer().EmitIntValue(0, 1); + SeenIdent = true; + } + getStreamer().EmitBytes(Data, 0); + getStreamer().EmitIntValue(0, 1); + getStreamer().PopSection(); + return false; +} + +/// ParseDirectiveSymver +/// ::= .symver foo, bar2@zed +bool ELFAsmParser::ParseDirectiveSymver(StringRef, SMLoc) { + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("expected a comma"); + + Lex(); + + StringRef AliasName; + if (getParser().ParseIdentifier(AliasName)) + return TokError("expected identifier in directive"); + + if (AliasName.find('@') == StringRef::npos) + return TokError("expected a '@' in the name"); + + MCSymbol *Alias = getContext().GetOrCreateSymbol(AliasName); + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + const MCExpr *Value = MCSymbolRefExpr::Create(Sym, getContext()); + + getStreamer().EmitAssignment(Alias, Value); + return false; +} + +/// ParseDirectiveVersion +/// ::= .version string +bool ELFAsmParser::ParseDirectiveVersion(StringRef, SMLoc) { + if (getLexer().isNot(AsmToken::String)) + return TokError("unexpected token in '.version' directive"); + + StringRef Data = getTok().getIdentifier(); + + Lex(); + + const MCSection *Note = + getContext().getELFSection(".note", ELF::SHT_NOTE, 0, + SectionKind::getReadOnly()); + + getStreamer().PushSection(); + getStreamer().SwitchSection(Note); + getStreamer().EmitIntValue(Data.size()+1, 4); // namesz. + getStreamer().EmitIntValue(0, 4); // descsz = 0 (no description). + getStreamer().EmitIntValue(1, 4); // type = NT_VERSION. + getStreamer().EmitBytes(Data, 0); // name. + getStreamer().EmitIntValue(0, 1); // terminate the string. + getStreamer().EmitValueToAlignment(4); // ensure 4 byte alignment. + getStreamer().PopSection(); + return false; +} + +/// ParseDirectiveWeakref +/// ::= .weakref foo, bar +bool ELFAsmParser::ParseDirectiveWeakref(StringRef, SMLoc) { + // FIXME: Share code with the other alias building directives. + + StringRef AliasName; + if (getParser().ParseIdentifier(AliasName)) + return TokError("expected identifier in directive"); + + if (getLexer().isNot(AsmToken::Comma)) + return TokError("expected a comma"); + + Lex(); + + StringRef Name; + if (getParser().ParseIdentifier(Name)) + return TokError("expected identifier in directive"); + + MCSymbol *Alias = getContext().GetOrCreateSymbol(AliasName); + + MCSymbol *Sym = getContext().GetOrCreateSymbol(Name); + + getStreamer().EmitWeakReference(Alias, Sym); + return false; +} + +namespace llvm { + +MCAsmParserExtension *createELFAsmParser() { + return new ELFAsmParser; +} + +} diff --git a/contrib/llvm/lib/MC/MCParser/MCAsmLexer.cpp b/contrib/llvm/lib/MC/MCParser/MCAsmLexer.cpp new file mode 100644 index 0000000..3a3ff14 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/MCAsmLexer.cpp @@ -0,0 +1,31 @@ +//===-- MCAsmLexer.cpp - Abstract Asm Lexer Interface ---------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmLexer.h" +#include "llvm/Support/SourceMgr.h" + +using namespace llvm; + +MCAsmLexer::MCAsmLexer() : CurTok(AsmToken::Error, StringRef()), TokStart(0) { +} + +MCAsmLexer::~MCAsmLexer() { +} + +SMLoc MCAsmLexer::getLoc() const { + return SMLoc::getFromPointer(TokStart); +} + +SMLoc AsmToken::getLoc() const { + return SMLoc::getFromPointer(Str.data()); +} + +SMLoc AsmToken::getEndLoc() const { + return SMLoc::getFromPointer(Str.data() + Str.size() - 1); +} diff --git a/contrib/llvm/lib/MC/MCParser/MCAsmParser.cpp b/contrib/llvm/lib/MC/MCParser/MCAsmParser.cpp new file mode 100644 index 0000000..3a825f0 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/MCAsmParser.cpp @@ -0,0 +1,48 @@ +//===-- MCAsmParser.cpp - Abstract Asm Parser Interface -------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmParser.h" +#include "llvm/MC/MCParser/MCAsmLexer.h" +#include "llvm/MC/MCParser/MCParsedAsmOperand.h" +#include "llvm/MC/MCTargetAsmParser.h" +#include "llvm/Support/SourceMgr.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/Debug.h" +#include "llvm/ADT/Twine.h" +using namespace llvm; + +MCAsmParser::MCAsmParser() : TargetParser(0), ShowParsedOperands(0) { +} + +MCAsmParser::~MCAsmParser() { +} + +void MCAsmParser::setTargetParser(MCTargetAsmParser &P) { + assert(!TargetParser && "Target parser is already initialized!"); + TargetParser = &P; + TargetParser->Initialize(*this); +} + +const AsmToken &MCAsmParser::getTok() { + return getLexer().getTok(); +} + +bool MCAsmParser::TokError(const Twine &Msg, ArrayRef<SMRange> Ranges) { + Error(getLexer().getLoc(), Msg, Ranges); + return true; +} + +bool MCAsmParser::ParseExpression(const MCExpr *&Res) { + SMLoc L; + return ParseExpression(Res, L); +} + +void MCParsedAsmOperand::dump() const { + dbgs() << " " << *this; +} diff --git a/contrib/llvm/lib/MC/MCParser/MCAsmParserExtension.cpp b/contrib/llvm/lib/MC/MCParser/MCAsmParserExtension.cpp new file mode 100644 index 0000000..3f25a14 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/MCAsmParserExtension.cpp @@ -0,0 +1,22 @@ +//===-- MCAsmParserExtension.cpp - Asm Parser Hooks -----------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCParser/MCAsmParserExtension.h" +using namespace llvm; + +MCAsmParserExtension::MCAsmParserExtension() : + BracketExpressionsSupported(false) { +} + +MCAsmParserExtension::~MCAsmParserExtension() { +} + +void MCAsmParserExtension::Initialize(MCAsmParser &Parser) { + this->Parser = &Parser; +} diff --git a/contrib/llvm/lib/MC/MCParser/MCTargetAsmParser.cpp b/contrib/llvm/lib/MC/MCParser/MCTargetAsmParser.cpp new file mode 100644 index 0000000..6fb1ba4 --- /dev/null +++ b/contrib/llvm/lib/MC/MCParser/MCTargetAsmParser.cpp @@ -0,0 +1,19 @@ +//===-- MCTargetAsmParser.cpp - Target Assembly Parser ---------------------==// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm/MC/MCTargetAsmParser.h" +using namespace llvm; + +MCTargetAsmParser::MCTargetAsmParser() + : AvailableFeatures(0) +{ +} + +MCTargetAsmParser::~MCTargetAsmParser() { +} |