//
//===----------------------------------------------------------------------===//
-#include "llvm/MC/MCParser/AsmParser.h"
+#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/StringMap.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/MCInst.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/MCSectionMachO.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSymbol.h"
-#include "llvm/MC/MCParser/MCParsedAsmOperand.h"
-#include "llvm/Support/Compiler.h"
+#include "llvm/MC/MCDwarf.h"
+#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetAsmParser.h"
+#include <vector>
using namespace llvm;
+namespace {
+
+/// \brief Helper class for tracking macro definitions.
+struct Macro {
+ StringRef Name;
+ StringRef Body;
+
+public:
+ Macro(StringRef N, StringRef B) : Name(N), Body(B) {}
+};
+
+/// \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,
+ const std::vector<std::vector<AsmToken> > &A);
+};
+
+/// \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;
+ SourceMgr &SrcMgr;
+ 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;
+
+public:
+ AsmParser(const Target &T, 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 void Warning(SMLoc L, const Twine &Meg);
+ virtual bool Error(SMLoc L, const Twine &Msg);
+
+ 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();
+
+ bool HandleMacroEntry(StringRef Name, SMLoc NameLoc, const Macro *M);
+ void HandleMacroExit();
+
+ void PrintMacroInstantiations();
+ void PrintMessage(SMLoc Loc, const Twine &Msg, const char *Type) const {
+ SrcMgr.PrintMessage(Loc, Msg, Type);
+ }
+
+ /// EnterIncludeFile - Enter the specified file. This returns true on failure.
+ bool EnterIncludeFile(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();
+
+ /// \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();
+
+ bool ParseAssignment(StringRef Name);
+
+ bool ParsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc);
+ bool ParseBinOpRHS(unsigned Precedence, const MCExpr *&Res, SMLoc &EndLoc);
+ bool ParseParenExpr(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); // ".set" or ".equ"
+ 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 ParseDirectiveELFType(); // ELF specific ".type"
+
+ bool ParseDirectiveComm(bool IsLocal); // ".comm" and ".lcomm"
+
+ bool ParseDirectiveAbort(); // ".abort"
+ bool ParseDirectiveInclude(); // ".include"
+
+ bool ParseDirectiveIf(SMLoc DirectiveLoc); // ".if"
+ 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);
+};
+
+/// \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");
+
+ // 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::ParseDirectiveLEB128>(".sleb128");
+ AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLEB128>(".uleb128");
+ }
+
+ bool ParseDirectiveFile(StringRef, SMLoc DirectiveLoc);
+ bool ParseDirectiveLine(StringRef, SMLoc DirectiveLoc);
+ bool ParseDirectiveLoc(StringRef, SMLoc DirectiveLoc);
+ bool ParseDirectiveStabs(StringRef, SMLoc DirectiveLoc);
+
+ bool ParseDirectiveMacrosOnOff(StringRef, SMLoc DirectiveLoc);
+ bool ParseDirectiveMacro(StringRef, SMLoc DirectiveLoc);
+ bool ParseDirectiveEndMacro(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), SrcMgr(_SM), TargetParser(0),
- CurBuffer(0) {
+AsmParser::AsmParser(const Target &T, SourceMgr &_SM, MCContext &_Ctx,
+ MCStreamer &_Out, const MCAsmInfo &_MAI)
+ : Lexer(_MAI), Ctx(_Ctx), Out(_Out), SrcMgr(_SM),
+ GenericParser(new GenericAsmParser), PlatformParser(0),
+ CurBuffer(0), MacrosEnabled(true) {
Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer));
-
- // Debugging directives.
- AddDirectiveHandler(".file", &AsmParser::ParseDirectiveFile);
- AddDirectiveHandler(".line", &AsmParser::ParseDirectiveLine);
- AddDirectiveHandler(".loc", &AsmParser::ParseDirectiveLoc);
-}
+ // 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::Warning(SMLoc L, const Twine &Msg) {
- PrintMessage(L, Msg.str(), "warning");
+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, "while in macro instantiation",
+ "note");
}
-bool AsmParser::Error(SMLoc L, const Twine &Msg) {
- PrintMessage(L, Msg.str(), "error");
- return true;
+void AsmParser::Warning(SMLoc L, const Twine &Msg) {
+ PrintMessage(L, Msg, "warning");
+ PrintMacroInstantiations();
}
-bool AsmParser::TokError(const char *Msg) {
- PrintMessage(Lexer.getLoc(), Msg, "error");
+bool AsmParser::Error(SMLoc L, const Twine &Msg) {
+ HadError = true;
+ PrintMessage(L, Msg, "error");
+ PrintMacroInstantiations();
return true;
}
-void AsmParser::PrintMessage(SMLoc Loc, const std::string &Msg,
- const char *Type) const {
- SrcMgr.PrintMessage(Loc, Msg, Type);
-}
-
bool AsmParser::EnterIncludeFile(const std::string &Filename) {
int NewBuf = SrcMgr.AddIncludeFile(Filename, Lexer.getLoc());
if (NewBuf == -1)
return true;
-
+
CurBuffer = NewBuf;
-
+
Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer));
-
+
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()) {
- CurBuffer = SrcMgr.FindBufferContainingLoc(ParentIncludeLoc);
- Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer),
- ParentIncludeLoc.getPointer());
+ JumpToLoc(ParentIncludeLoc);
tok = &Lexer.Lex();
}
}
-
+
if (tok->is(AsmToken::Error))
- PrintMessage(Lexer.getErrLoc(), Lexer.getErr(), "error");
-
+ Error(Lexer.getErrLoc(), Lexer.getErr());
+
return *tok;
}
bool AsmParser::Run(bool NoInitialTextSection, bool NoFinalize) {
// Create the initial section, if requested.
- //
- // FIXME: Target hook & command line option for initial section.
if (!NoInitialTextSection)
- Out.SwitchSection(Ctx.getMachOSection("__TEXT", "__text",
- MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS,
- 0, SectionKind::getText()));
+ Out.InitSections();
// Prime the lexer.
Lex();
-
- bool HadError = false;
-
+
+ HadError = false;
AsmCond StartingCondState = TheCondState;
// While we have input, parse each statement.
while (Lexer.isNot(AsmToken::Eof)) {
if (!ParseStatement()) continue;
-
- // We had an error, remember it and recover by skipping to the next line.
- HadError = true;
+
+ // 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");
+ }
+
// Finalize the output stream if there are no errors and if the client wants
// us to.
- if (!HadError && !NoFinalize)
+ 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);
+}
/// ParseParenExpr - Parse a paren expression and return it.
/// NOTE: This assumes the leading '(' has already been consumed.
return false;
}
-MCSymbol *AsmParser::CreateSymbol(StringRef Name) {
- // FIXME: Inline into callers.
- return Ctx.GetOrCreateSymbol(Name);
-}
-
/// ParsePrimaryExpr - Parse a primary expression and return it.
/// primaryexpr ::= (parenexpr
/// primaryexpr ::= symbol
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 false;
+
// This is a symbol reference.
- std::pair<StringRef, StringRef> Split = getTok().getIdentifier().split('@');
- MCSymbol *Sym = CreateSymbol(Split.first);
+ std::pair<StringRef, StringRef> Split = Identifier.split('@');
+ MCSymbol *Sym = getContext().GetOrCreateSymbol(Split.first);
+
+ // Mark the symbol as used in an expression.
+ Sym->setUsedInExpr(true);
// Lookup the symbol variant if used.
MCSymbolRefExpr::VariantKind Variant = MCSymbolRefExpr::VK_None;
- if (Split.first.size() != getTok().getIdentifier().size())
+ if (Split.first.size() != Identifier.size()) {
Variant = MCSymbolRefExpr::getVariantKindForName(Split.second);
-
- EndLoc = Lexer.getLoc();
- Lex(); // Eat identifier.
+ if (Variant == MCSymbolRefExpr::VK_Invalid) {
+ Variant = MCSymbolRefExpr::VK_None;
+ TokError("invalid variant '" + Split.second + "'");
+ }
+ }
// If this is an absolute variable reference, substitute it now to preserve
// semantics in the face of reassignment.
Res = MCSymbolRefExpr::Create(Sym, Variant, getContext());
return false;
}
- case AsmToken::Integer:
- Res = MCConstantExpr::Create(getTok().getIntVal(), getContext());
+ 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::Dot: {
// This is a '.' reference, which references the current PC. Emit a
// temporary label to the streamer and refer to it.
Lex(); // Eat identifier.
return false;
}
-
+
case AsmToken::LParen:
Lex(); // Eat the '('.
return ParseParenExpr(Res, 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());
+ }
+ }
+
+ assert(0 && "Invalid expression kind!");
+ return 0;
+}
+
/// ParseExpression - Parse an expression and return it.
-///
+///
/// expr ::= expr +,- expr -> lowest.
/// expr ::= expr |,^,&,! expr -> middle.
/// expr ::= expr *,/,%,<<,>> expr -> highest.
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)");
+ return true;
+ }
+
+ Res = ModifiedRes;
+ Lex();
+ }
+
// Try to constant fold it up front, if possible.
int64_t Value;
if (Res->EvaluateAsAbsolute(Value))
bool AsmParser::ParseAbsoluteExpression(int64_t &Res) {
const MCExpr *Expr;
-
+
SMLoc StartLoc = Lexer.getLoc();
if (ParseExpression(Expr))
return true;
return false;
}
-static unsigned getBinOpPrecedence(AsmToken::TokenKind K,
+static unsigned getBinOpPrecedence(AsmToken::TokenKind K,
MCBinaryExpr::Opcode &Kind) {
switch (K) {
default:
return 0; // not a binop.
- // Lowest Precedence: &&, ||
+ // Lowest Precedence: &&, ||, @
case AsmToken::AmpAmp:
Kind = MCBinaryExpr::LAnd;
return 1;
Kind = MCBinaryExpr::LOr;
return 1;
- // Low Precedence: +, -, ==, !=, <>, <, <=, >, >=
- case AsmToken::Plus:
- Kind = MCBinaryExpr::Add;
+
+ // Low Precedence: |, &, ^
+ //
+ // FIXME: gas seems to support '!' as an infix operator?
+ case AsmToken::Pipe:
+ Kind = MCBinaryExpr::Or;
return 2;
- case AsmToken::Minus:
- Kind = MCBinaryExpr::Sub;
+ 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 2;
+ return 3;
case AsmToken::ExclaimEqual:
case AsmToken::LessGreater:
Kind = MCBinaryExpr::NE;
- return 2;
+ return 3;
case AsmToken::Less:
Kind = MCBinaryExpr::LT;
- return 2;
+ return 3;
case AsmToken::LessEqual:
Kind = MCBinaryExpr::LTE;
- return 2;
+ return 3;
case AsmToken::Greater:
Kind = MCBinaryExpr::GT;
- return 2;
+ return 3;
case AsmToken::GreaterEqual:
Kind = MCBinaryExpr::GTE;
- return 2;
-
- // Intermediate Precedence: |, &, ^
- //
- // FIXME: gas seems to support '!' as an infix operator?
- case AsmToken::Pipe:
- Kind = MCBinaryExpr::Or;
- return 3;
- case AsmToken::Caret:
- Kind = MCBinaryExpr::Xor;
- return 3;
- case AsmToken::Amp:
- Kind = MCBinaryExpr::And;
return 3;
+ // High Intermediate Precedence: +, -
+ case AsmToken::Plus:
+ Kind = MCBinaryExpr::Add;
+ return 4;
+ case AsmToken::Minus:
+ Kind = MCBinaryExpr::Sub;
+ return 4;
+
// Highest Precedence: *, /, %, <<, >>
case AsmToken::Star:
Kind = MCBinaryExpr::Mul;
- return 4;
+ return 5;
case AsmToken::Slash:
Kind = MCBinaryExpr::Div;
- return 4;
+ return 5;
case AsmToken::Percent:
Kind = MCBinaryExpr::Mod;
- return 4;
+ return 5;
case AsmToken::LessLess:
Kind = MCBinaryExpr::Shl;
- return 4;
+ return 5;
case AsmToken::GreaterGreater:
Kind = MCBinaryExpr::Shr;
- return 4;
+ return 5;
}
}
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;
}
}
-
-
-
+
+
+
/// ParseStatement:
/// ::= EndOfStatement
/// ::= Label* Directive ...Operands... EndOfStatement
/// ::= Label* Identifier OperandList* EndOfStatement
bool AsmParser::ParseStatement() {
if (Lexer.is(AsmToken::EndOfStatement)) {
+ Out.AddBlankLine();
Lex();
return false;
}
AsmToken ID = getTok();
SMLoc IDLoc = ID.getLoc();
StringRef IDVal;
- if (ParseIdentifier(IDVal)) {
+ int64_t LocalLabelVal = -1;
+ // GUESS 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 (ParseIdentifier(IDVal)) {
if (!TheCondState.Ignore)
return TokError("unexpected token at start of statement");
IDVal = "";
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();
// 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 = CreateSymbol(IDVal);
+ 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);
-
+
+ // 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();
}
default: // Normal instruction or directive.
break;
}
-
- // Otherwise, we have a normal instruction or directive.
+
+ // 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] == '.') {
- // FIXME: This should be driven based on a hash lookup and callback.
- if (IDVal == ".section")
- return ParseDirectiveDarwinSection();
- if (IDVal == ".text")
- // FIXME: This changes behavior based on the -static flag to the
- // assembler.
- return ParseDirectiveSectionSwitch("__TEXT", "__text",
- MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS);
- if (IDVal == ".const")
- return ParseDirectiveSectionSwitch("__TEXT", "__const");
- if (IDVal == ".static_const")
- return ParseDirectiveSectionSwitch("__TEXT", "__static_const");
- if (IDVal == ".cstring")
- return ParseDirectiveSectionSwitch("__TEXT","__cstring",
- MCSectionMachO::S_CSTRING_LITERALS);
- if (IDVal == ".literal4")
- return ParseDirectiveSectionSwitch("__TEXT", "__literal4",
- MCSectionMachO::S_4BYTE_LITERALS,
- 4);
- if (IDVal == ".literal8")
- return ParseDirectiveSectionSwitch("__TEXT", "__literal8",
- MCSectionMachO::S_8BYTE_LITERALS,
- 8);
- if (IDVal == ".literal16")
- return ParseDirectiveSectionSwitch("__TEXT","__literal16",
- MCSectionMachO::S_16BYTE_LITERALS,
- 16);
- if (IDVal == ".constructor")
- return ParseDirectiveSectionSwitch("__TEXT","__constructor");
- if (IDVal == ".destructor")
- return ParseDirectiveSectionSwitch("__TEXT","__destructor");
- if (IDVal == ".fvmlib_init0")
- return ParseDirectiveSectionSwitch("__TEXT","__fvmlib_init0");
- if (IDVal == ".fvmlib_init1")
- return ParseDirectiveSectionSwitch("__TEXT","__fvmlib_init1");
-
- // FIXME: The assembler manual claims that this has the self modify code
- // flag, at least on x86-32, but that does not appear to be correct.
- if (IDVal == ".symbol_stub")
- return ParseDirectiveSectionSwitch("__TEXT","__symbol_stub",
- MCSectionMachO::S_SYMBOL_STUBS |
- MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS,
- // FIXME: Different on PPC and ARM.
- 0, 16);
- // FIXME: PowerPC only?
- if (IDVal == ".picsymbol_stub")
- return ParseDirectiveSectionSwitch("__TEXT","__picsymbol_stub",
- MCSectionMachO::S_SYMBOL_STUBS |
- MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS,
- 0, 26);
- if (IDVal == ".data")
- return ParseDirectiveSectionSwitch("__DATA", "__data");
- if (IDVal == ".static_data")
- return ParseDirectiveSectionSwitch("__DATA", "__static_data");
-
- // FIXME: The section names of these two are misspelled in the assembler
- // manual.
- if (IDVal == ".non_lazy_symbol_pointer")
- return ParseDirectiveSectionSwitch("__DATA", "__nl_symbol_ptr",
- MCSectionMachO::S_NON_LAZY_SYMBOL_POINTERS,
- 4);
- if (IDVal == ".lazy_symbol_pointer")
- return ParseDirectiveSectionSwitch("__DATA", "__la_symbol_ptr",
- MCSectionMachO::S_LAZY_SYMBOL_POINTERS,
- 4);
-
- if (IDVal == ".dyld")
- return ParseDirectiveSectionSwitch("__DATA", "__dyld");
- if (IDVal == ".mod_init_func")
- return ParseDirectiveSectionSwitch("__DATA", "__mod_init_func",
- MCSectionMachO::S_MOD_INIT_FUNC_POINTERS,
- 4);
- if (IDVal == ".mod_term_func")
- return ParseDirectiveSectionSwitch("__DATA", "__mod_term_func",
- MCSectionMachO::S_MOD_TERM_FUNC_POINTERS,
- 4);
- if (IDVal == ".const_data")
- return ParseDirectiveSectionSwitch("__DATA", "__const");
-
-
- if (IDVal == ".objc_class")
- return ParseDirectiveSectionSwitch("__OBJC", "__class",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_meta_class")
- return ParseDirectiveSectionSwitch("__OBJC", "__meta_class",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_cat_cls_meth")
- return ParseDirectiveSectionSwitch("__OBJC", "__cat_cls_meth",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_cat_inst_meth")
- return ParseDirectiveSectionSwitch("__OBJC", "__cat_inst_meth",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_protocol")
- return ParseDirectiveSectionSwitch("__OBJC", "__protocol",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_string_object")
- return ParseDirectiveSectionSwitch("__OBJC", "__string_object",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_cls_meth")
- return ParseDirectiveSectionSwitch("__OBJC", "__cls_meth",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_inst_meth")
- return ParseDirectiveSectionSwitch("__OBJC", "__inst_meth",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_cls_refs")
- return ParseDirectiveSectionSwitch("__OBJC", "__cls_refs",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP |
- MCSectionMachO::S_LITERAL_POINTERS,
- 4);
- if (IDVal == ".objc_message_refs")
- return ParseDirectiveSectionSwitch("__OBJC", "__message_refs",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP |
- MCSectionMachO::S_LITERAL_POINTERS,
- 4);
- if (IDVal == ".objc_symbols")
- return ParseDirectiveSectionSwitch("__OBJC", "__symbols",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_category")
- return ParseDirectiveSectionSwitch("__OBJC", "__category",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_class_vars")
- return ParseDirectiveSectionSwitch("__OBJC", "__class_vars",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_instance_vars")
- return ParseDirectiveSectionSwitch("__OBJC", "__instance_vars",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_module_info")
- return ParseDirectiveSectionSwitch("__OBJC", "__module_info",
- MCSectionMachO::S_ATTR_NO_DEAD_STRIP);
- if (IDVal == ".objc_class_names")
- return ParseDirectiveSectionSwitch("__TEXT", "__cstring",
- MCSectionMachO::S_CSTRING_LITERALS);
- if (IDVal == ".objc_meth_var_types")
- return ParseDirectiveSectionSwitch("__TEXT", "__cstring",
- MCSectionMachO::S_CSTRING_LITERALS);
- if (IDVal == ".objc_meth_var_names")
- return ParseDirectiveSectionSwitch("__TEXT", "__cstring",
- MCSectionMachO::S_CSTRING_LITERALS);
- if (IDVal == ".objc_selector_strs")
- return ParseDirectiveSectionSwitch("__OBJC", "__selector_strs",
- MCSectionMachO::S_CSTRING_LITERALS);
-
// Assembler features
- if (IDVal == ".set")
- return ParseDirectiveSet();
+ if (IDVal == ".set" || IDVal == ".equ")
+ return ParseDirectiveSet(IDVal);
// Data directives
if (IDVal == ".ascii")
- return ParseDirectiveAscii(false);
- if (IDVal == ".asciz")
- return ParseDirectiveAscii(true);
+ 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 == ".long")
return ParseDirectiveValue(4);
if (IDVal == ".quad")
return ParseDirectiveValue(8);
-
- // FIXME: Target hooks for IsPow2.
- if (IDVal == ".align")
- return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/1);
- if (IDVal == ".align32")
- return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/4);
+ if (IDVal == ".single")
+ 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 ParseDirectiveFill();
if (IDVal == ".space")
return ParseDirectiveSpace();
+ if (IDVal == ".zero")
+ return ParseDirectiveZero();
// Symbol attribute directives
if (IDVal == ".globl" || IDVal == ".global")
return ParseDirectiveSymbolAttribute(MCSA_Global);
+ // ELF only? Should it be here?
+ if (IDVal == ".local")
+ return ParseDirectiveSymbolAttribute(MCSA_Local);
if (IDVal == ".hidden")
return ParseDirectiveSymbolAttribute(MCSA_Hidden);
if (IDVal == ".indirect_symbol")
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")
return ParseDirectiveComm(/*IsLocal=*/false);
if (IDVal == ".lcomm")
return ParseDirectiveComm(/*IsLocal=*/true);
- if (IDVal == ".zerofill")
- return ParseDirectiveDarwinZerofill();
- if (IDVal == ".desc")
- return ParseDirectiveDarwinSymbolDesc();
- if (IDVal == ".lsym")
- return ParseDirectiveDarwinLsym();
-
- if (IDVal == ".subsections_via_symbols")
- return ParseDirectiveDarwinSubsectionsViaSymbols();
+
if (IDVal == ".abort")
return ParseDirectiveAbort();
if (IDVal == ".include")
return ParseDirectiveInclude();
- if (IDVal == ".dump")
- return ParseDirectiveDarwinDumpOrLoad(IDLoc, /*IsDump=*/true);
- if (IDVal == ".load")
- return ParseDirectiveDarwinDumpOrLoad(IDLoc, /*IsLoad=*/false);
-
- // Look up the handler in the handler table,
- bool(AsmParser::*Handler)(StringRef, SMLoc) = DirectiveMap[IDVal];
- if (Handler)
- return (this->*Handler)(IDVal, 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);
+
// Target hook for parsing target specific directives.
if (!getTargetParser().ParseDirective(ID))
return false;
return false;
}
+ 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(IDVal, IDLoc,
+ bool HadError = getTargetParser().ParseInstruction(Opcode.str(), IDLoc,
ParsedOperands);
- if (!HadError && Lexer.isNot(AsmToken::EndOfStatement))
- HadError = TokError("unexpected token in argument list");
- // If parsing succeeded, match the instruction.
- if (!HadError) {
- MCInst Inst;
- if (!getTargetParser().MatchInstruction(ParsedOperands, Inst)) {
- // Emit the instruction on success.
- Out.EmitInstruction(Inst);
- } else {
- // Otherwise emit a diagnostic about the match failure and set the error
- // flag.
- //
- // FIXME: We should give nicer diagnostics about the exact failure.
- Error(IDLoc, "unrecognized instruction");
- HadError = true;
+ // 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]->dump(OS);
}
+ OS << "]";
+
+ PrintMessage(IDLoc, OS.str(), "note");
}
- // If there was no error, consume the end-of-statement token. Otherwise this
- // will be done by our caller.
+ // If parsing succeeded, match the instruction.
if (!HadError)
- Lex();
+ HadError = getTargetParser().MatchAndEmitInstruction(IDLoc, ParsedOperands,
+ Out);
// Free any parsed operands.
for (unsigned i = 0, e = ParsedOperands.size(); i != e; ++i)
delete ParsedOperands[i];
- return HadError;
+ // Don't skip the rest of the line, the instruction parser is responsible for
+ // that.
+ return false;
+}
+
+MacroInstantiation::MacroInstantiation(const Macro *M, SMLoc IL, SMLoc EL,
+ const std::vector<std::vector<AsmToken> > &A)
+ : TheMacro(M), InstantiationLoc(IL), ExitLoc(EL)
+{
+ // 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 Body = M->Body;
+ 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 (Body[Pos] != '$' || Pos + 1 == End)
+ continue;
+
+ char Next = Body[Pos + 1];
+ if (Next == '$' || Next == 'n' || isdigit(Next))
+ break;
+ }
+
+ // Add the prefix.
+ OS << Body.slice(0, Pos);
+
+ // Check if we reached the end.
+ if (Pos == End)
+ break;
+
+ 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 (std::vector<AsmToken>::const_iterator it = A[Index].begin(),
+ ie = A[Index].end(); it != ie; ++it)
+ OS << it->getString();
+ break;
+ }
+ }
+
+ // Update the scan point.
+ Body = Body.substr(Pos + 2);
+ }
+
+ // We include the .endmacro in the buffer as our queue to exit the macro
+ // instantiation.
+ OS << ".endmacro\n";
+
+ Instantiation = MemoryBuffer::getMemBufferCopy(OS.str(), "<instantiation>");
+}
+
+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");
+
+ // Parse the macro instantiation arguments.
+ std::vector<std::vector<AsmToken> > MacroArguments;
+ MacroArguments.push_back(std::vector<AsmToken>());
+ unsigned ParenLevel = 0;
+ for (;;) {
+ if (Lexer.is(AsmToken::Eof))
+ return TokError("unexpected token in macro instantiation");
+ if (Lexer.is(AsmToken::EndOfStatement))
+ break;
+
+ // If we aren't inside parentheses and this is a comma, start a new token
+ // list.
+ if (ParenLevel == 0 && Lexer.is(AsmToken::Comma)) {
+ MacroArguments.push_back(std::vector<AsmToken>());
+ } else {
+ // 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.
+ MacroArguments.back().push_back(getTok());
+ }
+ Lex();
+ }
+
+ // Create the macro instantiation object and add to the current macro
+ // instantiation stack.
+ MacroInstantiation *MI = new MacroInstantiation(M, NameLoc,
+ getTok().getLoc(),
+ MacroArguments);
+ 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();
}
-bool AsmParser::ParseAssignment(const StringRef &Name) {
+bool AsmParser::ParseAssignment(StringRef Name) {
// FIXME: Use better location, we should use proper tokens.
SMLoc EqualLoc = Lexer.getLoc();
const MCExpr *Value;
- SMLoc StartLoc = Lexer.getLoc();
if (ParseExpression(Value))
return true;
-
+
if (Lexer.isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in assignment");
//
// FIXME: Diagnostics. Note the location of the definition as a label.
// FIXME: Diagnose assignment to protected identifier (e.g., register name).
- if (!Sym->isUndefined() && !Sym->isAbsolute())
+ if (Sym->isUndefined() && !Sym->isUsedInExpr())
+ ; // Allow redefinitions of undefined symbols only used in directives.
+ else if (!Sym->isUndefined() && !Sym->isAbsolute())
return Error(EqualLoc, "redefinition of '" + Name + "'");
else if (!Sym->isVariable())
return Error(EqualLoc, "invalid assignment to '" + Name + "'");
return Error(EqualLoc, "invalid reassignment of non-absolute variable '" +
Name + "'");
} else
- Sym = CreateSymbol(Name);
+ Sym = getContext().GetOrCreateSymbol(Name);
// FIXME: Handle '.'.
+ Sym->setUsedInExpr(true);
+
// Do the assignment.
Out.EmitAssignment(Sym, Value);
/// ::= 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;
/// ParseDirectiveSet:
/// ::= .set identifier ',' expression
-bool AsmParser::ParseDirectiveSet() {
+bool AsmParser::ParseDirectiveSet(StringRef IDVal) {
StringRef Name;
if (ParseIdentifier(Name))
- return TokError("expected identifier after '.set' directive");
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in '.set'");
+ return TokError("expected identifier after '" + Twine(IDVal) + "'");
+
+ if (getLexer().isNot(AsmToken::Comma))
+ return TokError("unexpected token in '" + Twine(IDVal) + "'");
Lex();
return ParseAssignment(Name);
}
-/// ParseDirectiveSection:
-/// ::= .section identifier (',' identifier)*
-/// FIXME: This should actually parse out the segment, section, attributes and
-/// sizeof_stub fields.
-bool AsmParser::ParseDirectiveDarwinSection() {
- SMLoc Loc = Lexer.getLoc();
-
- StringRef SectionName;
- if (ParseIdentifier(SectionName))
- return Error(Loc, "expected identifier after '.section' directive");
+bool AsmParser::ParseEscapedString(std::string &Data) {
+ assert(getLexer().is(AsmToken::String) && "Unexpected current token!");
- // Verify there is a following comma.
- if (!Lexer.is(AsmToken::Comma))
- return TokError("unexpected token in '.section' directive");
+ Data = "";
+ StringRef Str = getTok().getStringContents();
+ for (unsigned i = 0, e = Str.size(); i != e; ++i) {
+ if (Str[i] != '\\') {
+ Data += Str[i];
+ continue;
+ }
- std::string SectionSpec = SectionName;
- SectionSpec += ",";
-
- // Add all the tokens until the end of the line, ParseSectionSpecifier will
- // handle this.
- StringRef EOL = Lexer.LexUntilEndOfStatement();
- SectionSpec.append(EOL.begin(), EOL.end());
-
- Lex();
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in '.section' directive");
- Lex();
-
-
- StringRef Segment, Section;
- unsigned TAA, StubSize;
- std::string ErrorStr =
- MCSectionMachO::ParseSectionSpecifier(SectionSpec, Segment, Section,
- TAA, StubSize);
-
- if (!ErrorStr.empty())
- return Error(Loc, ErrorStr.c_str());
-
- // FIXME: Arch specific.
- bool isText = Segment == "__TEXT"; // FIXME: Hack.
- Out.SwitchSection(Ctx.getMachOSection(Segment, Section, TAA, StubSize,
- isText ? SectionKind::getText()
- : SectionKind::getDataRel()));
- return false;
-}
-
-/// ParseDirectiveSectionSwitch -
-bool AsmParser::ParseDirectiveSectionSwitch(const char *Segment,
- const char *Section,
- unsigned TAA, unsigned Align,
- unsigned StubSize) {
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in section switching directive");
- Lex();
-
- // FIXME: Arch specific.
- bool isText = StringRef(Segment) == "__TEXT"; // FIXME: Hack.
- Out.SwitchSection(Ctx.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 issueing 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)
- Out.EmitValueToAlignment(Align, 0, 1, 0);
-
- return false;
-}
-
-bool AsmParser::ParseEscapedString(std::string &Data) {
- assert(Lexer.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 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) {
}
/// ParseDirectiveAscii:
-/// ::= ( .ascii | .asciz ) [ "string" ( , "string" )* ]
-bool AsmParser::ParseDirectiveAscii(bool ZeroTerminated) {
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
+/// ::= ( .ascii | .asciz | .string ) [ "string" ( , "string" )* ]
+bool AsmParser::ParseDirectiveAscii(StringRef IDVal, bool ZeroTerminated) {
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ CheckForValidSection();
+
for (;;) {
- if (Lexer.isNot(AsmToken::String))
- return TokError("expected string in '.ascii' or '.asciz' directive");
-
+ if (getLexer().isNot(AsmToken::String))
+ return TokError("expected string in '" + Twine(IDVal) + "' directive");
+
std::string Data;
if (ParseEscapedString(Data))
return true;
-
- Out.EmitBytes(Data, DEFAULT_ADDRSPACE);
+
+ getStreamer().EmitBytes(Data, DEFAULT_ADDRSPACE);
if (ZeroTerminated)
- Out.EmitBytes(StringRef("\0", 1), DEFAULT_ADDRSPACE);
-
+ getStreamer().EmitBytes(StringRef("\0", 1), DEFAULT_ADDRSPACE);
+
Lex();
-
- if (Lexer.is(AsmToken::EndOfStatement))
+
+ if (getLexer().is(AsmToken::EndOfStatement))
break;
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in '.ascii' or '.asciz' directive");
+ if (getLexer().isNot(AsmToken::Comma))
+ return TokError("unexpected token in '" + Twine(IDVal) + "' directive");
Lex();
}
}
/// ParseDirectiveValue
/// ::= (.byte | .short | ... ) [ expression (, expression)* ]
bool AsmParser::ParseDirectiveValue(unsigned Size) {
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ CheckForValidSection();
+
for (;;) {
const MCExpr *Value;
- SMLoc ATTRIBUTE_UNUSED StartLoc = Lexer.getLoc();
if (ParseExpression(Value))
return true;
- Out.EmitValue(Value, Size, DEFAULT_ADDRSPACE);
+ // Special case constant expressions to match code generator.
+ if (const MCConstantExpr *MCE = dyn_cast<MCConstantExpr>(Value))
+ getStreamer().EmitIntValue(MCE->getValue(), Size, DEFAULT_ADDRSPACE);
+ else
+ getStreamer().EmitValue(Value, Size, DEFAULT_ADDRSPACE);
- if (Lexer.is(AsmToken::EndOfStatement))
+ if (getLexer().is(AsmToken::EndOfStatement))
break;
-
+
// FIXME: Improve diagnostic.
- if (Lexer.isNot(AsmToken::Comma))
+ 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))
+ return TokError("unexpected token in directive");
+
+ // Convert to an APFloat.
+ APFloat Value(Semantics);
+ if (Value.convertFromString(getTok().getString(),
+ 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();
}
/// ParseDirectiveSpace
/// ::= .space expression [ , expression ]
bool AsmParser::ParseDirectiveSpace() {
+ CheckForValidSection();
+
int64_t NumBytes;
if (ParseAbsoluteExpression(NumBytes))
return true;
int64_t FillExpr = 0;
- bool HasFillExpr = false;
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.space' directive");
Lex();
-
+
if (ParseAbsoluteExpression(FillExpr))
return true;
- HasFillExpr = true;
-
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.space' directive");
}
return TokError("invalid number of bytes in '.space' directive");
// FIXME: Sometimes the fill expr is 'nop' if it isn't supplied, instead of 0.
- Out.EmitFill(NumBytes, FillExpr, DEFAULT_ADDRSPACE);
+ 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 (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.fill' directive");
Lex();
-
+
int64_t FillSize;
if (ParseAbsoluteExpression(FillSize))
return true;
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.fill' directive");
Lex();
-
+
int64_t FillExpr;
if (ParseAbsoluteExpression(FillExpr))
return true;
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ 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)
- Out.EmitValue(MCConstantExpr::Create(FillExpr, getContext()), FillSize,
- DEFAULT_ADDRSPACE);
+ getStreamer().EmitIntValue(FillExpr, FillSize, DEFAULT_ADDRSPACE);
return false;
}
/// ParseDirectiveOrg
/// ::= .org expression [ , expression ]
bool AsmParser::ParseDirectiveOrg() {
+ CheckForValidSection();
+
const MCExpr *Offset;
- SMLoc StartLoc = Lexer.getLoc();
if (ParseExpression(Offset))
return true;
// Parse optional fill expression.
int64_t FillExpr = 0;
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.org' directive");
Lex();
-
+
if (ParseAbsoluteExpression(FillExpr))
return true;
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.org' directive");
}
// FIXME: Only limited forms of relocatable expressions are accepted here, it
// has to be relative to the current section.
- Out.EmitValueToOffset(Offset, FillExpr);
+ getStreamer().EmitValueToOffset(Offset, FillExpr);
return false;
}
/// ParseDirectiveAlign
/// ::= {.align, ...} expression [ , expression [ , expression ]]
bool AsmParser::ParseDirectiveAlign(bool IsPow2, unsigned ValueSize) {
- SMLoc AlignmentLoc = Lexer.getLoc();
+ CheckForValidSection();
+
+ SMLoc AlignmentLoc = getLexer().getLoc();
int64_t Alignment;
if (ParseAbsoluteExpression(Alignment))
return true;
bool HasFillExpr = false;
int64_t FillExpr = 0;
int64_t MaxBytesToFill = 0;
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Comma))
+ 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 (Lexer.isNot(AsmToken::Comma)) {
+ if (getLexer().isNot(AsmToken::Comma)) {
HasFillExpr = true;
if (ParseAbsoluteExpression(FillExpr))
return true;
}
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in directive");
Lex();
- MaxBytesLoc = Lexer.getLoc();
+ MaxBytesLoc = getLexer().getLoc();
if (ParseAbsoluteExpression(MaxBytesToFill))
return true;
-
- if (Lexer.isNot(AsmToken::EndOfStatement))
+
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in directive");
}
}
Lex();
- if (!HasFillExpr) {
- // FIXME: Sometimes fill with nop.
+ if (!HasFillExpr)
FillExpr = 0;
- }
// Compute alignment in bytes.
if (IsPow2) {
}
}
- // FIXME: hard code the parser to use EmitCodeAlignment for text when using
- // the TextAlignFillValue.
- if(Out.getCurrentSection()->getKind().isText() &&
- Lexer.getMAI().getTextAlignFillValue() == FillExpr)
- Out.EmitCodeAlignment(Alignment, MaxBytesToFill);
- else
+ // 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.
- Out.EmitValueToAlignment(Alignment, FillExpr, ValueSize, MaxBytesToFill);
+ getStreamer().EmitValueToAlignment(Alignment, FillExpr, ValueSize,
+ MaxBytesToFill);
+ }
return false;
}
/// ParseDirectiveSymbolAttribute
/// ::= { ".globl", ".weak", ... } [ identifier ( , identifier )* ]
bool AsmParser::ParseDirectiveSymbolAttribute(MCSymbolAttr Attr) {
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (getLexer().isNot(AsmToken::EndOfStatement)) {
for (;;) {
StringRef Name;
if (ParseIdentifier(Name))
return TokError("expected identifier in directive");
-
- MCSymbol *Sym = CreateSymbol(Name);
- Out.EmitSymbolAttribute(Sym, Attr);
+ MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
+
+ getStreamer().EmitSymbolAttribute(Sym, Attr);
- if (Lexer.is(AsmToken::EndOfStatement))
+ if (getLexer().is(AsmToken::EndOfStatement))
break;
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in directive");
Lex();
}
}
Lex();
- return false;
-}
-
-/// ParseDirectiveDarwinSymbolDesc
-/// ::= .desc identifier , expression
-bool AsmParser::ParseDirectiveDarwinSymbolDesc() {
- StringRef Name;
- if (ParseIdentifier(Name))
- return TokError("expected identifier in directive");
-
- // Handle the identifier as the key symbol.
- MCSymbol *Sym = CreateSymbol(Name);
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in '.desc' directive");
- Lex();
-
- SMLoc DescLoc = Lexer.getLoc();
- int64_t DescValue;
- if (ParseAbsoluteExpression(DescValue))
- return true;
-
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in '.desc' directive");
-
- Lex();
-
- // Set the n_desc field of this Symbol to this DescValue
- Out.EmitSymbolDesc(Sym, DescValue);
-
return false;
}
/// ParseDirectiveComm
/// ::= ( .comm | .lcomm ) identifier , size_expression [ , align_expression ]
bool AsmParser::ParseDirectiveComm(bool IsLocal) {
- SMLoc IDLoc = Lexer.getLoc();
+ 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 = CreateSymbol(Name);
+ MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
- if (Lexer.isNot(AsmToken::Comma))
+ if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in directive");
Lex();
int64_t Size;
- SMLoc SizeLoc = Lexer.getLoc();
+ SMLoc SizeLoc = getLexer().getLoc();
if (ParseAbsoluteExpression(Size))
return true;
int64_t Pow2Alignment = 0;
SMLoc Pow2AlignmentLoc;
- if (Lexer.is(AsmToken::Comma)) {
+ if (getLexer().is(AsmToken::Comma)) {
Lex();
- Pow2AlignmentLoc = Lexer.getLoc();
+ 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))
Pow2Alignment = Log2_64(Pow2Alignment);
}
}
-
- if (Lexer.isNot(AsmToken::EndOfStatement))
+
+ 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
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 assember
+ // 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)
// '.lcomm' is equivalent to '.zerofill'.
// Create the Symbol as a common or local common with Size and Pow2Alignment
if (IsLocal) {
- Out.EmitZerofill(Ctx.getMachOSection("__DATA", "__bss",
- MCSectionMachO::S_ZEROFILL, 0,
- SectionKind::getBSS()),
- Sym, Size, 1 << Pow2Alignment);
+ getStreamer().EmitZerofill(Ctx.getMachOSection(
+ "__DATA", "__bss", MCSectionMachO::S_ZEROFILL,
+ 0, SectionKind::getBSS()),
+ Sym, Size, 1 << Pow2Alignment);
return false;
}
- Out.EmitCommonSymbol(Sym, Size, 1 << Pow2Alignment);
- return false;
-}
-
-/// ParseDirectiveDarwinZerofill
-/// ::= .zerofill segname , sectname [, identifier , size_expression [
-/// , align_expression ]]
-bool AsmParser::ParseDirectiveDarwinZerofill() {
- // FIXME: Handle quoted names here.
-
- if (Lexer.isNot(AsmToken::Identifier))
- return TokError("expected segment name after '.zerofill' directive");
- StringRef Segment = getTok().getString();
- Lex();
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in directive");
- Lex();
-
- if (Lexer.isNot(AsmToken::Identifier))
- return TokError("expected section name after comma in '.zerofill' "
- "directive");
- StringRef Section = getTok().getString();
- Lex();
-
- // If this is the end of the line all that was wanted was to create the
- // the section but with no symbol.
- if (Lexer.is(AsmToken::EndOfStatement)) {
- // Create the zerofill section but no symbol
- Out.EmitZerofill(Ctx.getMachOSection(Segment, Section,
- MCSectionMachO::S_ZEROFILL, 0,
- SectionKind::getBSS()));
- return false;
- }
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in directive");
- Lex();
-
- if (Lexer.isNot(AsmToken::Identifier))
- return TokError("expected identifier in directive");
-
- // handle the identifier as the key symbol.
- SMLoc IDLoc = Lexer.getLoc();
- MCSymbol *Sym = CreateSymbol(getTok().getString());
- Lex();
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in directive");
- Lex();
-
- int64_t Size;
- SMLoc SizeLoc = Lexer.getLoc();
- if (ParseAbsoluteExpression(Size))
- return true;
-
- int64_t Pow2Alignment = 0;
- SMLoc Pow2AlignmentLoc;
- if (Lexer.is(AsmToken::Comma)) {
- Lex();
- Pow2AlignmentLoc = Lexer.getLoc();
- if (ParseAbsoluteExpression(Pow2Alignment))
- return true;
- }
-
- if (Lexer.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 assember
- // 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.
- Out.EmitZerofill(Ctx.getMachOSection(Segment, Section,
- MCSectionMachO::S_ZEROFILL, 0,
- SectionKind::getBSS()),
- Sym, Size, 1 << Pow2Alignment);
-
- return false;
-}
-
-/// ParseDirectiveDarwinSubsectionsViaSymbols
-/// ::= .subsections_via_symbols
-bool AsmParser::ParseDirectiveDarwinSubsectionsViaSymbols() {
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in '.subsections_via_symbols' directive");
-
- Lex();
-
- Out.EmitAssemblerFlag(MCAF_SubsectionsViaSymbols);
-
+ getStreamer().EmitCommonSymbol(Sym, Size, 1 << Pow2Alignment);
return false;
}
/// ParseDirectiveAbort
-/// ::= .abort [ "abort_string" ]
+/// ::= .abort [... message ...]
bool AsmParser::ParseDirectiveAbort() {
// FIXME: Use loc from directive.
- SMLoc Loc = Lexer.getLoc();
-
- StringRef Str = "";
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::String))
- return TokError("expected string in '.abort' directive");
-
- Str = getTok().getString();
-
- Lex();
- }
+ SMLoc Loc = getLexer().getLoc();
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ StringRef Str = ParseStringToEndOfStatement();
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.abort' directive");
-
+
Lex();
- // FIXME: Handle here.
if (Str.empty())
Error(Loc, ".abort detected. Assembly stopping.");
else
Error(Loc, ".abort '" + Str + "' detected. Assembly stopping.");
+ // FIXME: Actually abort assembly here.
return false;
}
-/// ParseDirectiveLsym
-/// ::= .lsym identifier , expression
-bool AsmParser::ParseDirectiveDarwinLsym() {
- StringRef Name;
- if (ParseIdentifier(Name))
- return TokError("expected identifier in directive");
-
- // Handle the identifier as the key symbol.
- MCSymbol *Sym = CreateSymbol(Name);
-
- if (Lexer.isNot(AsmToken::Comma))
- return TokError("unexpected token in '.lsym' directive");
- Lex();
-
- const MCExpr *Value;
- SMLoc StartLoc = Lexer.getLoc();
- if (ParseExpression(Value))
- return true;
-
- if (Lexer.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");
-}
-
/// ParseDirectiveInclude
/// ::= .include "filename"
bool AsmParser::ParseDirectiveInclude() {
- if (Lexer.isNot(AsmToken::String))
+ if (getLexer().isNot(AsmToken::String))
return TokError("expected string in '.include' directive");
-
+
std::string Filename = getTok().getString();
- SMLoc IncludeLoc = Lexer.getLoc();
+ SMLoc IncludeLoc = getLexer().getLoc();
Lex();
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ 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)) {
- PrintMessage(IncludeLoc,
- "Could not find include file '" + Filename + "'",
- "error");
+ Error(IncludeLoc, "Could not find include file '" + Filename + "'");
return true;
}
return false;
}
-/// ParseDirectiveDarwinDumpOrLoad
-/// ::= ( .dump | .load ) "filename"
-bool AsmParser::ParseDirectiveDarwinDumpOrLoad(SMLoc IDLoc, bool IsDump) {
- if (Lexer.isNot(AsmToken::String))
- return TokError("expected string in '.dump' or '.load' directive");
-
- Lex();
-
- if (Lexer.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)
- Warning(IDLoc, "ignoring directive .dump for now");
- else
- Warning(IDLoc, "ignoring directive .load for now");
-
- return false;
-}
-
/// ParseDirectiveIf
/// ::= .if expression
bool AsmParser::ParseDirectiveIf(SMLoc DirectiveLoc) {
if (ParseAbsoluteExpression(ExprValue))
return true;
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.if' directive");
-
+
Lex();
TheCondState.CondMet = ExprValue;
if (ParseAbsoluteExpression(ExprValue))
return true;
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.elseif' directive");
-
+
Lex();
TheCondState.CondMet = ExprValue;
TheCondState.Ignore = !TheCondState.CondMet;
/// ParseDirectiveElse
/// ::= .else
bool AsmParser::ParseDirectiveElse(SMLoc DirectiveLoc) {
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.else' directive");
-
+
Lex();
if (TheCondState.TheCond != AsmCond::IfCond &&
/// ParseDirectiveEndIf
/// ::= .endif
bool AsmParser::ParseDirectiveEndIf(SMLoc DirectiveLoc) {
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.endif' directive");
-
+
Lex();
if ((TheCondState.TheCond == AsmCond::NoCond) ||
/// ParseDirectiveFile
/// ::= .file [number] string
-bool AsmParser::ParseDirectiveFile(StringRef, SMLoc DirectiveLoc) {
+bool GenericAsmParser::ParseDirectiveFile(StringRef, SMLoc DirectiveLoc) {
// FIXME: I'm not sure what this is.
int64_t FileNumber = -1;
- if (Lexer.is(AsmToken::Integer)) {
+ SMLoc FileNumberLoc = getLexer().getLoc();
+ if (getLexer().is(AsmToken::Integer)) {
FileNumber = getTok().getIntVal();
Lex();
-
+
if (FileNumber < 1)
return TokError("file number less than one");
}
- if (Lexer.isNot(AsmToken::String))
+ if (getLexer().isNot(AsmToken::String))
return TokError("unexpected token in '.file' directive");
-
+
StringRef Filename = getTok().getString();
Filename = Filename.substr(1, Filename.size()-2);
Lex();
- if (Lexer.isNot(AsmToken::EndOfStatement))
+ if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.file' directive");
if (FileNumber == -1)
- Out.EmitFileDirective(Filename);
- else
- Out.EmitDwarfFileDirective(FileNumber, Filename);
-
+ getStreamer().EmitFileDirective(Filename);
+ else {
+ if (getContext().GetDwarfFile(Filename, FileNumber) == 0)
+ Error(FileNumberLoc, "file number already allocated");
+ getStreamer().EmitDwarfFileDirective(FileNumber, Filename);
+ }
+
return false;
}
/// ParseDirectiveLine
/// ::= .line [number]
-bool AsmParser::ParseDirectiveLine(StringRef, SMLoc DirectiveLoc) {
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Integer))
+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();
// FIXME: Do something with the .line.
}
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in '.file' directive");
+ if (getLexer().isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.line' directive");
return false;
}
/// ParseDirectiveLoc
-/// ::= .loc number [number [number]]
-bool AsmParser::ParseDirectiveLoc(StringRef, SMLoc DirectiveLoc) {
- if (Lexer.isNot(AsmToken::Integer))
+/// ::= .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");
-
- // FIXME: What are these fields?
int64_t FileNumber = getTok().getIntVal();
- (void) FileNumber;
- // FIXME: Validate file.
-
+ 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();
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Integer))
- return TokError("unexpected token in '.loc' directive");
- int64_t Param2 = getTok().getIntVal();
- (void) Param2;
+ 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();
+ }
- if (Lexer.isNot(AsmToken::EndOfStatement)) {
- if (Lexer.isNot(AsmToken::Integer))
+ unsigned Flags = DWARF2_LINE_DEFAULT_IS_STMT ? DWARF2_FLAG_IS_STMT : 0;
+ unsigned Isa = 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");
- int64_t Param3 = getTok().getIntVal();
- (void) Param3;
- Lex();
+ 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 {
+ return Error(Loc, "unknown sub-directive in '.loc' directive");
+ }
- // FIXME: Do something with the .loc.
+ if (getLexer().is(AsmToken::EndOfStatement))
+ break;
}
}
- if (Lexer.isNot(AsmToken::EndOfStatement))
- return TokError("unexpected token in '.file' directive");
+ getContext().setCurrentDwarfLoc(FileNumber, LineNumber, ColumnPos, Flags,Isa);
return false;
}
+/// ParseDirectiveStabs
+/// ::= .stabs string, number, number, number
+bool GenericAsmParser::ParseDirectiveStabs(StringRef Directive,
+ SMLoc DirectiveLoc) {
+ return TokError("unsupported directive '" + Directive + "'");
+}
+
+/// 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
+bool GenericAsmParser::ParseDirectiveMacro(StringRef Directive,
+ SMLoc DirectiveLoc) {
+ StringRef Name;
+ if (getParser().ParseIdentifier(Name))
+ return TokError("expected identifier in directive");
+
+ 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);
+ 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");
+}
+
+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;
+}
+
+
+/// \brief Create an MCAsmParser instance.
+MCAsmParser *llvm::createMCAsmParser(const Target &T, SourceMgr &SM,
+ MCContext &C, MCStreamer &Out,
+ const MCAsmInfo &MAI) {
+ return new AsmParser(T, SM, C, Out, MAI);
+}
projects / oota-llvm.git / blobdiff