//
//===----------------------------------------------------------------------===//
+#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringSwitch.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/MCSectionMachO.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSymbol.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"
/// 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);
/// }
private:
+ void CheckForValidSection();
+
bool ParseStatement();
bool HandleMacroEntry(StringRef Name, SMLoc NameLoc, const Macro *M);
void HandleMacroExit();
void PrintMacroInstantiations();
- void PrintMessage(SMLoc Loc, const std::string &Msg, const char *Type) const;
-
+ 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);
/// ParseIdentifier - Parse an identifier or string (as a quoted identifier)
/// and set \arg Res to the identifier contents.
bool ParseIdentifier(StringRef &Res);
-
+
// Directive Parsing.
- bool ParseDirectiveAscii(bool ZeroTerminated); // ".ascii", ".asciiz"
+
+ // ".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 ParseDirectiveSet(); // ".set"
+ bool ParseDirectiveZero(); // ".zero"
+ bool ParseDirectiveSet(StringRef IDVal); // ".set" or ".equ"
bool ParseDirectiveOrg(); // ".org"
// ".align{,32}", ".p2align{,w,l}"
bool ParseDirectiveAlign(bool IsPow2, unsigned ValueSize);
/// 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
AddDirectiveHandler<&GenericAsmParser::ParseDirectiveFile>(".file");
AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLine>(".line");
AddDirectiveHandler<&GenericAsmParser::ParseDirectiveLoc>(".loc");
+ AddDirectiveHandler<&GenericAsmParser::ParseDirectiveStabs>(".stabs");
// Macro directives.
AddDirectiveHandler<&GenericAsmParser::ParseDirectiveMacrosOnOff>(
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);
};
}
extern MCAsmParserExtension *createDarwinAsmParser();
extern MCAsmParserExtension *createELFAsmParser();
+extern MCAsmParserExtension *createCOFFAsmParser();
}
//
// FIXME: This is a hack, we need to (majorly) cleanup how these objects are
// created.
- if (_MAI.hasSubsectionsViaSymbols()) {
+ if (_MAI.hasMicrosoftFastStdCallMangling()) {
+ PlatformParser = createCOFFAsmParser();
+ PlatformParser->Initialize(*this);
+ } else if (_MAI.hasSubsectionsViaSymbols()) {
PlatformParser = createDarwinAsmParser();
PlatformParser->Initialize(*this);
} else {
}
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");
+ PrintMessage(L, Msg, "warning");
PrintMacroInstantiations();
}
bool AsmParser::Error(SMLoc L, const Twine &Msg) {
- PrintMessage(L, Msg.str(), "error");
+ 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;
}
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.
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.
- //
- // 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();
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('@');
+ std::pair<StringRef, StringRef> Split = Identifier.split('@');
MCSymbol *Sym = getContext().GetOrCreateSymbol(Split.first);
// Mark the symbol as used in an expression.
// 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.
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
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();
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)) {
if (const Macro *M = MacroMap.lookup(IDVal))
return HandleMacroEntry(IDVal, IDLoc, M);
- // Otherwise, we have a normal instruction or directive.
+ // Otherwise, we have a normal instruction or directive.
if (IDVal[0] == '.') {
// 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_Protected);
if (IDVal == ".reference")
return ParseDirectiveSymbolAttribute(MCSA_Reference);
- if (IDVal == ".type")
- return ParseDirectiveELFType();
if (IDVal == ".weak")
return ParseDirectiveSymbolAttribute(MCSA_Weak);
if (IDVal == ".weak_definition")
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(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,
// list.
if (ParenLevel == 0 && Lexer.is(AsmToken::Comma)) {
MacroArguments.push_back(std::vector<AsmToken>());
- } else if (Lexer.is(AsmToken::LParen)) {
- ++ParenLevel;
- } else if (Lexer.is(AsmToken::RParen)) {
- if (ParenLevel)
- --ParenLevel;
} 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();
const MCExpr *Value;
if (ParseExpression(Value))
return true;
-
+
if (Lexer.isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in assignment");
/// ::= 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");
-
+ return TokError("expected identifier after '" + Twine(IDVal) + "'");
+
if (getLexer().isNot(AsmToken::Comma))
- return TokError("unexpected token in '.set'");
+ return TokError("unexpected token in '" + Twine(IDVal) + "'");
Lex();
return ParseAssignment(Name);
}
/// ParseDirectiveAscii:
-/// ::= ( .ascii | .asciz ) [ "string" ( , "string" )* ]
-bool AsmParser::ParseDirectiveAscii(bool ZeroTerminated) {
+/// ::= ( .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 '.ascii' or '.asciz' directive");
+ return TokError("expected string in '" + Twine(IDVal) + "' directive");
std::string Data;
if (ParseEscapedString(Data))
break;
if (getLexer().isNot(AsmToken::Comma))
- return TokError("unexpected token in '.ascii' or '.asciz' directive");
+ return TokError("unexpected token in '" + Twine(IDVal) + "' directive");
Lex();
}
}
/// ::= (.byte | .short | ... ) [ expression (, expression)* ]
bool AsmParser::ParseDirectiveValue(unsigned Size) {
if (getLexer().isNot(AsmToken::EndOfStatement)) {
+ CheckForValidSection();
+
for (;;) {
const MCExpr *Value;
- SMLoc ATTRIBUTE_UNUSED StartLoc = getLexer().getLoc();
if (ParseExpression(Value))
return true;
if (getLexer().is(AsmToken::EndOfStatement))
break;
-
+
// FIXME: Improve diagnostic.
if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in directive");
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();
+ }
+ }
+
+ Lex();
+ return false;
+}
+
/// ParseDirectiveSpace
/// ::= .space expression [ , expression ]
bool AsmParser::ParseDirectiveSpace() {
+ CheckForValidSection();
+
int64_t NumBytes;
if (ParseAbsoluteExpression(NumBytes))
return true;
if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.space' directive");
Lex();
-
+
if (ParseAbsoluteExpression(FillExpr))
return true;
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)
/// ParseDirectiveOrg
/// ::= .org expression [ , expression ]
bool AsmParser::ParseDirectiveOrg() {
+ CheckForValidSection();
+
const MCExpr *Offset;
if (ParseExpression(Offset))
return true;
if (getLexer().isNot(AsmToken::Comma))
return TokError("unexpected token in '.org' directive");
Lex();
-
+
if (ParseAbsoluteExpression(FillExpr))
return true;
/// ParseDirectiveAlign
/// ::= {.align, ...} expression [ , expression [ , expression ]]
bool AsmParser::ParseDirectiveAlign(bool IsPow2, unsigned ValueSize) {
+ CheckForValidSection();
+
SMLoc AlignmentLoc = getLexer().getLoc();
int64_t Alignment;
if (ParseAbsoluteExpression(Alignment))
MaxBytesLoc = getLexer().getLoc();
if (ParseAbsoluteExpression(MaxBytesToFill))
return true;
-
+
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in directive");
}
// Check whether we should use optimal code alignment for this .align
// directive.
- //
- // FIXME: This should be using a target hook.
- bool UseCodeAlign = false;
- if (const MCSectionMachO *S = dyn_cast<MCSectionMachO>(
- getStreamer().getCurrentSection()))
- UseCodeAlign = S->hasAttribute(MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS);
+ bool UseCodeAlign = getStreamer().getCurrentSection()->UseCodeAlign();
if ((!HasFillExpr || Lexer.getMAI().getTextAlignFillValue() == FillExpr) &&
ValueSize == 1 && UseCodeAlign) {
getStreamer().EmitCodeAlignment(Alignment, MaxBytesToFill);
if (ParseIdentifier(Name))
return TokError("expected identifier in directive");
-
+
MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
getStreamer().EmitSymbolAttribute(Sym, Attr);
}
Lex();
- return false;
-}
-
-/// ParseDirectiveELFType
-/// ::= .type identifier , @attribute
-bool AsmParser::ParseDirectiveELFType() {
- 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 '.type' directive");
- Lex();
-
- if (getLexer().isNot(AsmToken::At))
- return TokError("expected '@' before type");
- Lex();
-
- StringRef Type;
- SMLoc TypeLoc;
-
- TypeLoc = getLexer().getLoc();
- if (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)
- .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;
}
/// 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);
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 (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
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)) {
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.if' directive");
-
+
Lex();
TheCondState.CondMet = ExprValue;
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.elseif' directive");
-
+
Lex();
TheCondState.CondMet = ExprValue;
TheCondState.Ignore = !TheCondState.CondMet;
bool AsmParser::ParseDirectiveElse(SMLoc DirectiveLoc) {
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.else' directive");
-
+
Lex();
if (TheCondState.TheCond != AsmCond::IfCond &&
bool AsmParser::ParseDirectiveEndIf(SMLoc DirectiveLoc) {
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.endif' directive");
-
+
Lex();
if ((TheCondState.TheCond == AsmCond::NoCond) ||
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)
getStreamer().EmitFileDirective(Filename);
- else
+ else {
+ if (getContext().GetDwarfFile(Filename, FileNumber) == 0)
+ Error(FileNumberLoc, "file number already allocated");
getStreamer().EmitDwarfFileDirective(FileNumber, Filename);
+ }
return false;
}
/// ParseDirectiveLoc
-/// ::= .loc number [number [number]]
+/// ::= .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 (getLexer().isNot(AsmToken::EndOfStatement)) {
- if (getLexer().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();
+ }
- if (getLexer().isNot(AsmToken::EndOfStatement)) {
- if (getLexer().isNot(AsmToken::Integer))
+ 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;
+ 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 (getLexer().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
"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,
projects / oota-llvm.git / blobdiff