summaryrefslogtreecommitdiffstats
path: root/lib/MC
diff options
context:
space:
mode:
Diffstat (limited to 'lib/MC')
-rw-r--r--lib/MC/CMakeLists.txt3
-rw-r--r--lib/MC/MCAsmInfo.cpp17
-rw-r--r--lib/MC/MCAsmInfoCOFF.cpp7
-rw-r--r--lib/MC/MCAsmInfoDarwin.cpp17
-rw-r--r--lib/MC/MCAsmParser.cpp18
-rw-r--r--lib/MC/MCAsmStreamer.cpp352
-rw-r--r--lib/MC/MCAssembler.cpp2
-rw-r--r--lib/MC/MCExpr.cpp29
-rw-r--r--lib/MC/MCInst.cpp4
-rw-r--r--lib/MC/MCMachOStreamer.cpp71
-rw-r--r--lib/MC/MCNullStreamer.cpp12
-rw-r--r--lib/MC/MCParser/AsmLexer.cpp320
-rw-r--r--lib/MC/MCParser/AsmParser.cpp1781
-rw-r--r--lib/MC/MCParser/CMakeLists.txt7
-rw-r--r--lib/MC/MCParser/MCAsmLexer.cpp (renamed from lib/MC/MCAsmLexer.cpp)2
-rw-r--r--lib/MC/MCParser/MCAsmParser.cpp35
-rw-r--r--lib/MC/MCParser/Makefile16
-rw-r--r--lib/MC/MCParser/TargetAsmParser.cpp (renamed from lib/MC/TargetAsmParser.cpp)0
-rw-r--r--lib/MC/MCSectionELF.cpp12
-rw-r--r--lib/MC/MCStreamer.cpp25
-rw-r--r--lib/MC/MCSymbol.cpp77
-rw-r--r--lib/MC/MCValue.cpp8
-rw-r--r--lib/MC/Makefile2
23 files changed, 2557 insertions, 260 deletions
diff --git a/lib/MC/CMakeLists.txt b/lib/MC/CMakeLists.txt
index 8a1a058..9ead33b 100644
--- a/lib/MC/CMakeLists.txt
+++ b/lib/MC/CMakeLists.txt
@@ -2,8 +2,6 @@ add_llvm_library(LLVMMC
MCAsmInfo.cpp
MCAsmInfoCOFF.cpp
MCAsmInfoDarwin.cpp
- MCAsmLexer.cpp
- MCAsmParser.cpp
MCAsmStreamer.cpp
MCAssembler.cpp
MCCodeEmitter.cpp
@@ -20,5 +18,4 @@ add_llvm_library(LLVMMC
MCStreamer.cpp
MCSymbol.cpp
MCValue.cpp
- TargetAsmParser.cpp
)
diff --git a/lib/MC/MCAsmInfo.cpp b/lib/MC/MCAsmInfo.cpp
index 3e5c97d..547f904 100644
--- a/lib/MC/MCAsmInfo.cpp
+++ b/lib/MC/MCAsmInfo.cpp
@@ -19,8 +19,9 @@
using namespace llvm;
MCAsmInfo::MCAsmInfo() {
- ZeroFillDirective = 0;
- NonexecutableStackDirective = 0;
+ HasSubsectionsViaSymbols = false;
+ HasMachoZeroFillDirective = false;
+ HasStaticCtorDtorReferenceInStaticMode = false;
NeedsSet = false;
MaxInstLength = 4;
PCSymbol = "$";
@@ -36,7 +37,6 @@ MCAsmInfo::MCAsmInfo() {
AllowQuotesInName = false;
AllowNameToStartWithDigit = false;
ZeroDirective = "\t.zero\t";
- ZeroDirectiveSuffix = 0;
AsciiDirective = "\t.ascii\t";
AscizDirective = "\t.asciz\t";
Data8bitsDirective = "\t.byte\t";
@@ -52,17 +52,16 @@ MCAsmInfo::MCAsmInfo() {
PICJumpTableDirective = 0;
GlobalDirective = "\t.globl\t";
SetDirective = 0;
- LCOMMDirective = 0;
- COMMDirective = "\t.comm\t";
+ HasLCOMMDirective = false;
COMMDirectiveTakesAlignment = true;
HasDotTypeDotSizeDirective = true;
HasSingleParameterDotFile = true;
- UsedDirective = 0;
+ HasNoDeadStrip = false;
WeakRefDirective = 0;
WeakDefDirective = 0;
- // FIXME: These are ELFish - move to ELFMAI.
- HiddenDirective = "\t.hidden\t";
- ProtectedDirective = "\t.protected\t";
+ LinkOnceDirective = 0;
+ HiddenVisibilityAttr = MCSA_Hidden;
+ ProtectedVisibilityAttr = MCSA_Protected;
AbsoluteDebugSectionOffsets = false;
AbsoluteEHSectionOffsets = false;
HasLEB128 = false;
diff --git a/lib/MC/MCAsmInfoCOFF.cpp b/lib/MC/MCAsmInfoCOFF.cpp
index 23b0dd7..e395acd 100644
--- a/lib/MC/MCAsmInfoCOFF.cpp
+++ b/lib/MC/MCAsmInfoCOFF.cpp
@@ -18,14 +18,17 @@ using namespace llvm;
MCAsmInfoCOFF::MCAsmInfoCOFF() {
GlobalPrefix = "_";
- LCOMMDirective = "\t.lcomm\t";
+ HasLCOMMDirective = true;
COMMDirectiveTakesAlignment = false;
HasDotTypeDotSizeDirective = false;
HasSingleParameterDotFile = false;
- HiddenDirective = NULL;
PrivateGlobalPrefix = "L"; // Prefix for private global symbols
WeakRefDirective = "\t.weak\t";
+ LinkOnceDirective = "\t.linkonce same_size\n";
SetDirective = "\t.set\t";
+
+ // Doesn't support visibility:
+ HiddenVisibilityAttr = ProtectedVisibilityAttr = MCSA_Invalid;
// Set up DWARF directives
HasLEB128 = true; // Target asm supports leb128 directives (little-endian)
diff --git a/lib/MC/MCAsmInfoDarwin.cpp b/lib/MC/MCAsmInfoDarwin.cpp
index d99120d..9902f50 100644
--- a/lib/MC/MCAsmInfoDarwin.cpp
+++ b/lib/MC/MCAsmInfoDarwin.cpp
@@ -24,6 +24,7 @@ MCAsmInfoDarwin::MCAsmInfoDarwin() {
NeedsSet = true;
AllowQuotesInName = true;
HasSingleParameterDotFile = false;
+ HasSubsectionsViaSymbols = true;
AlignmentIsInBytes = false;
InlineAsmStart = " InlineAsm Start";
@@ -32,14 +33,20 @@ MCAsmInfoDarwin::MCAsmInfoDarwin() {
// Directives:
WeakDefDirective = "\t.weak_definition ";
WeakRefDirective = "\t.weak_reference ";
- HiddenDirective = "\t.private_extern ";
- LCOMMDirective = "\t.lcomm\t";
ZeroDirective = "\t.space\t"; // ".space N" emits N zeros.
- ZeroFillDirective = "\t.zerofill\t"; // Uses .zerofill
+ HasMachoZeroFillDirective = true; // Uses .zerofill
+ HasStaticCtorDtorReferenceInStaticMode = true;
SetDirective = "\t.set";
- ProtectedDirective = "\t.globl\t";
+
+ HiddenVisibilityAttr = MCSA_PrivateExtern;
+ // Doesn't support protected visibility.
+ ProtectedVisibilityAttr = MCSA_Global;
+
+
HasDotTypeDotSizeDirective = false;
- UsedDirective = "\t.no_dead_strip\t";
+ HasNoDeadStrip = true;
+ // Note: Even though darwin has the .lcomm directive, it is just a synonym for
+ // zerofill, so we prefer to use .zerofill.
// _foo.eh symbols are currently always exported so that the linker knows
// about them. This is not necessary on 10.6 and later, but it
diff --git a/lib/MC/MCAsmParser.cpp b/lib/MC/MCAsmParser.cpp
deleted file mode 100644
index 2287e89..0000000
--- a/lib/MC/MCAsmParser.cpp
+++ /dev/null
@@ -1,18 +0,0 @@
-//===-- MCAsmParser.cpp - Abstract Asm Parser Interface -------------------===//
-//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#include "llvm/MC/MCAsmParser.h"
-
-using namespace llvm;
-
-MCAsmParser::MCAsmParser() {
-}
-
-MCAsmParser::~MCAsmParser() {
-}
diff --git a/lib/MC/MCAsmStreamer.cpp b/lib/MC/MCAsmStreamer.cpp
index b6ebb1a..bf39239 100644
--- a/lib/MC/MCAsmStreamer.cpp
+++ b/lib/MC/MCAsmStreamer.cpp
@@ -8,7 +8,6 @@
//===----------------------------------------------------------------------===//
#include "llvm/MC/MCStreamer.h"
-#include "llvm/ADT/SmallString.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCContext.h"
@@ -17,26 +16,68 @@
#include "llvm/MC/MCInstPrinter.h"
#include "llvm/MC/MCSectionMachO.h"
#include "llvm/MC/MCSymbol.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/Twine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/Format.h"
-#include "llvm/Support/raw_ostream.h"
+#include "llvm/Support/FormattedStream.h"
using namespace llvm;
namespace {
class MCAsmStreamer : public MCStreamer {
- raw_ostream &OS;
+ formatted_raw_ostream &OS;
const MCAsmInfo &MAI;
+ bool IsLittleEndian, IsVerboseAsm;
MCInstPrinter *InstPrinter;
MCCodeEmitter *Emitter;
+
+ SmallString<128> CommentToEmit;
+ raw_svector_ostream CommentStream;
public:
- MCAsmStreamer(MCContext &Context, raw_ostream &_OS, const MCAsmInfo &tai,
- MCInstPrinter *_Printer, MCCodeEmitter *_Emitter)
- : MCStreamer(Context), OS(_OS), MAI(tai), InstPrinter(_Printer),
- Emitter(_Emitter) {}
+ MCAsmStreamer(MCContext &Context, formatted_raw_ostream &os,
+ const MCAsmInfo &mai,
+ bool isLittleEndian, bool isVerboseAsm, MCInstPrinter *printer,
+ MCCodeEmitter *emitter)
+ : MCStreamer(Context), OS(os), MAI(mai), IsLittleEndian(isLittleEndian),
+ IsVerboseAsm(isVerboseAsm), InstPrinter(printer), Emitter(emitter),
+ CommentStream(CommentToEmit) {}
~MCAsmStreamer() {}
+ bool isLittleEndian() const { return IsLittleEndian; }
+
+
+ inline void EmitEOL() {
+ // If we don't have any comments, just emit a \n.
+ if (!IsVerboseAsm) {
+ OS << '\n';
+ return;
+ }
+ EmitCommentsAndEOL();
+ }
+ void EmitCommentsAndEOL();
+
+ /// AddComment - Add a comment that can be emitted to the generated .s
+ /// file if applicable as a QoI issue to make the output of the compiler
+ /// more readable. This only affects the MCAsmStreamer, and only when
+ /// verbose assembly output is enabled.
+ virtual void AddComment(const Twine &T);
+
+ /// GetCommentOS - Return a raw_ostream that comments can be written to.
+ /// Unlike AddComment, you are required to terminate comments with \n if you
+ /// use this method.
+ virtual raw_ostream &GetCommentOS() {
+ if (!IsVerboseAsm)
+ return nulls(); // Discard comments unless in verbose asm mode.
+ return CommentStream;
+ }
+
+ /// AddBlankLine - Emit a blank line to a .s file to pretty it up.
+ virtual void AddBlankLine() {
+ EmitEOL();
+ }
+
/// @name MCStreamer Interface
/// @{
@@ -44,23 +85,33 @@ public:
virtual void EmitLabel(MCSymbol *Symbol);
- virtual void EmitAssemblerFlag(AssemblerFlag Flag);
+ virtual void EmitAssemblerFlag(MCAssemblerFlag Flag);
virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value);
- virtual void EmitSymbolAttribute(MCSymbol *Symbol, SymbolAttr Attribute);
+ virtual void EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute);
virtual void EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue);
- virtual void EmitCommonSymbol(MCSymbol *Symbol, unsigned Size,
+ virtual void EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
unsigned ByteAlignment);
+ /// EmitLocalCommonSymbol - Emit a local common (.lcomm) symbol.
+ ///
+ /// @param Symbol - The common symbol to emit.
+ /// @param Size - The size of the common symbol.
+ virtual void EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size);
+
virtual void EmitZerofill(const MCSection *Section, MCSymbol *Symbol = 0,
unsigned Size = 0, unsigned ByteAlignment = 0);
- virtual void EmitBytes(StringRef Data);
+ virtual void EmitBytes(StringRef Data, unsigned AddrSpace);
- virtual void EmitValue(const MCExpr *Value, unsigned Size);
+ virtual void EmitValue(const MCExpr *Value, unsigned Size,unsigned AddrSpace);
+ virtual void EmitIntValue(uint64_t Value, unsigned Size, unsigned AddrSpace);
+
+ virtual void EmitFill(uint64_t NumBytes, uint8_t FillValue,
+ unsigned AddrSpace);
virtual void EmitValueToAlignment(unsigned ByteAlignment, int64_t Value = 0,
unsigned ValueSize = 1,
@@ -78,6 +129,50 @@ public:
} // end anonymous namespace.
+/// AddComment - Add a comment that can be emitted to the generated .s
+/// file if applicable as a QoI issue to make the output of the compiler
+/// more readable. This only affects the MCAsmStreamer, and only when
+/// verbose assembly output is enabled.
+void MCAsmStreamer::AddComment(const Twine &T) {
+ if (!IsVerboseAsm) return;
+
+ // Make sure that CommentStream is flushed.
+ CommentStream.flush();
+
+ T.toVector(CommentToEmit);
+ // Each comment goes on its own line.
+ CommentToEmit.push_back('\n');
+
+ // Tell the comment stream that the vector changed underneath it.
+ CommentStream.resync();
+}
+
+void MCAsmStreamer::EmitCommentsAndEOL() {
+ if (CommentToEmit.empty() && CommentStream.GetNumBytesInBuffer() == 0) {
+ OS << '\n';
+ return;
+ }
+
+ CommentStream.flush();
+ StringRef Comments = CommentToEmit.str();
+
+ assert(Comments.back() == '\n' &&
+ "Comment array not newline terminated");
+ do {
+ // Emit a line of comments.
+ OS.PadToColumn(MAI.getCommentColumn());
+ size_t Position = Comments.find('\n');
+ OS << MAI.getCommentString() << ' ' << Comments.substr(0, Position) << '\n';
+
+ Comments = Comments.substr(Position+1);
+ } while (!Comments.empty());
+
+ CommentToEmit.clear();
+ // Tell the comment stream that the vector changed underneath it.
+ CommentStream.resync();
+}
+
+
static inline int64_t truncateToSize(int64_t Value, unsigned Bytes) {
assert(Bytes && "Invalid size!");
return Value & ((uint64_t) (int64_t) -1 >> (64 - Bytes * 8));
@@ -101,17 +196,17 @@ void MCAsmStreamer::EmitLabel(MCSymbol *Symbol) {
assert(Symbol->isUndefined() && "Cannot define a symbol twice!");
assert(CurSection && "Cannot emit before setting section!");
- Symbol->print(OS, &MAI);
- OS << ":\n";
+ OS << *Symbol << ":";
+ EmitEOL();
Symbol->setSection(*CurSection);
}
-void MCAsmStreamer::EmitAssemblerFlag(AssemblerFlag Flag) {
+void MCAsmStreamer::EmitAssemblerFlag(MCAssemblerFlag Flag) {
switch (Flag) {
default: assert(0 && "Invalid flag!");
- case SubsectionsViaSymbols: OS << ".subsections_via_symbols"; break;
+ case MCAF_SubsectionsViaSymbols: OS << ".subsections_via_symbols"; break;
}
- OS << '\n';
+ EmitEOL();
}
void MCAsmStreamer::EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
@@ -119,10 +214,8 @@ void MCAsmStreamer::EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
assert((Symbol->isUndefined() || Symbol->isAbsolute()) &&
"Cannot define a symbol twice!");
- Symbol->print(OS, &MAI);
- OS << " = ";
- Value->print(OS, &MAI);
- OS << '\n';
+ OS << *Symbol << " = " << *Value;
+ EmitEOL();
// FIXME: Lift context changes into super class.
// FIXME: Set associated section.
@@ -130,41 +223,54 @@ void MCAsmStreamer::EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
}
void MCAsmStreamer::EmitSymbolAttribute(MCSymbol *Symbol,
- SymbolAttr Attribute) {
+ MCSymbolAttr Attribute) {
switch (Attribute) {
- case Global: OS << ".globl"; break;
- case Hidden: OS << ".hidden"; break;
- case IndirectSymbol: OS << ".indirect_symbol"; break;
- case Internal: OS << ".internal"; break;
- case LazyReference: OS << ".lazy_reference"; break;
- case NoDeadStrip: OS << ".no_dead_strip"; break;
- case PrivateExtern: OS << ".private_extern"; break;
- case Protected: OS << ".protected"; break;
- case Reference: OS << ".reference"; break;
- case Weak: OS << ".weak"; break;
- case WeakDefinition: OS << ".weak_definition"; break;
- case WeakReference: OS << ".weak_reference"; break;
+ case MCSA_Invalid: assert(0 && "Invalid symbol attribute");
+ case MCSA_Global: OS << MAI.getGlobalDirective(); break; // .globl
+ case MCSA_Hidden: OS << ".hidden "; break;
+ case MCSA_IndirectSymbol: OS << ".indirect_symbol "; break;
+ case MCSA_Internal: OS << ".internal "; break;
+ case MCSA_LazyReference: OS << ".lazy_reference "; break;
+ case MCSA_Local: OS << ".local "; break;
+ case MCSA_NoDeadStrip: OS << ".no_dead_strip "; break;
+ case MCSA_PrivateExtern: OS << ".private_extern "; break;
+ case MCSA_Protected: OS << ".protected "; break;
+ case MCSA_Reference: OS << ".reference "; break;
+ case MCSA_Weak: OS << ".weak "; break;
+ case MCSA_WeakDefinition: OS << ".weak_definition "; break;
+ // .weak_reference
+ case MCSA_WeakReference: OS << MAI.getWeakRefDirective(); break;
}
- OS << ' ';
- Symbol->print(OS, &MAI);
- OS << '\n';
+ OS << *Symbol;
+ EmitEOL();
}
void MCAsmStreamer::EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {
- OS << ".desc" << ' ';
- Symbol->print(OS, &MAI);
- OS << ',' << DescValue << '\n';
+ OS << ".desc" << ' ' << *Symbol << ',' << DescValue;
+ EmitEOL();
}
-void MCAsmStreamer::EmitCommonSymbol(MCSymbol *Symbol, unsigned Size,
+void MCAsmStreamer::EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
unsigned ByteAlignment) {
- OS << ".comm ";
- Symbol->print(OS, &MAI);
- OS << ',' << Size;
- if (ByteAlignment != 0)
- OS << ',' << Log2_32(ByteAlignment);
- OS << '\n';
+ OS << "\t.comm\t" << *Symbol << ',' << Size;
+ if (ByteAlignment != 0 && MAI.getCOMMDirectiveTakesAlignment()) {
+ if (MAI.getAlignmentIsInBytes())
+ OS << ',' << ByteAlignment;
+ else
+ OS << ',' << Log2_32(ByteAlignment);
+ }
+ EmitEOL();
+}
+
+/// EmitLocalCommonSymbol - Emit a local common (.lcomm) symbol.
+///
+/// @param Symbol - The common symbol to emit.
+/// @param Size - The size of the common symbol.
+void MCAsmStreamer::EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size) {
+ assert(MAI.hasLCOMMDirective() && "Doesn't have .lcomm, can't emit it!");
+ OS << "\t.lcomm\t" << *Symbol << ',' << Size;
+ EmitEOL();
}
void MCAsmStreamer::EmitZerofill(const MCSection *Section, MCSymbol *Symbol,
@@ -177,36 +283,130 @@ void MCAsmStreamer::EmitZerofill(const MCSection *Section, MCSymbol *Symbol,
OS << MOSection->getSegmentName() << "," << MOSection->getSectionName();
if (Symbol != NULL) {
- OS << ',';
- Symbol->print(OS, &MAI);
- OS << ',' << Size;
+ OS << ',' << *Symbol << ',' << Size;
if (ByteAlignment != 0)
OS << ',' << Log2_32(ByteAlignment);
}
- OS << '\n';
+ EmitEOL();
+}
+
+static inline char toOctal(int X) { return (X&7)+'0'; }
+
+void MCAsmStreamer::EmitBytes(StringRef Data, unsigned AddrSpace) {
+ assert(CurSection && "Cannot emit contents before setting section!");
+ if (Data.empty()) return;
+
+ if (Data.size() == 1) {
+ OS << MAI.getData8bitsDirective(AddrSpace);
+ OS << (unsigned)(unsigned char)Data[0];
+ EmitEOL();
+ return;
+ }
+
+ // If the data ends with 0 and the target supports .asciz, use it, otherwise
+ // use .ascii
+ if (MAI.getAscizDirective() && Data.back() == 0) {
+ OS << MAI.getAscizDirective();
+ Data = Data.substr(0, Data.size()-1);
+ } else {
+ OS << MAI.getAsciiDirective();
+ }
+
+ OS << " \"";
+ for (unsigned i = 0, e = Data.size(); i != e; ++i) {
+ unsigned char C = Data[i];
+ if (C == '"' || C == '\\') {
+ OS << '\\' << (char)C;
+ continue;
+ }
+
+ if (isprint((unsigned char)C)) {
+ OS << (char)C;
+ continue;
+ }
+
+ switch (C) {
+ case '\b': OS << "\\b"; break;
+ case '\f': OS << "\\f"; break;
+ case '\n': OS << "\\n"; break;
+ case '\r': OS << "\\r"; break;
+ case '\t': OS << "\\t"; break;
+ default:
+ OS << '\\';
+ OS << toOctal(C >> 6);
+ OS << toOctal(C >> 3);
+ OS << toOctal(C >> 0);
+ break;
+ }
+ }
+ OS << '"';
+ EmitEOL();
}
-void MCAsmStreamer::EmitBytes(StringRef Data) {
+/// EmitIntValue - Special case of EmitValue that avoids the client having
+/// to pass in a MCExpr for constant integers.
+void MCAsmStreamer::EmitIntValue(uint64_t Value, unsigned Size,
+ unsigned AddrSpace) {
assert(CurSection && "Cannot emit contents before setting section!");
- for (unsigned i = 0, e = Data.size(); i != e; ++i)
- OS << ".byte " << (unsigned) (unsigned char) Data[i] << '\n';
+ const char *Directive = 0;
+ switch (Size) {
+ default: break;
+ case 1: Directive = MAI.getData8bitsDirective(AddrSpace); break;
+ case 2: Directive = MAI.getData16bitsDirective(AddrSpace); break;
+ case 4: Directive = MAI.getData32bitsDirective(AddrSpace); break;
+ case 8:
+ Directive = MAI.getData64bitsDirective(AddrSpace);
+ // If the target doesn't support 64-bit data, emit as two 32-bit halves.
+ if (Directive) break;
+ if (isLittleEndian()) {
+ EmitIntValue((uint32_t)(Value >> 0 ), 4, AddrSpace);
+ EmitIntValue((uint32_t)(Value >> 32), 4, AddrSpace);
+ } else {
+ EmitIntValue((uint32_t)(Value >> 32), 4, AddrSpace);
+ EmitIntValue((uint32_t)(Value >> 0 ), 4, AddrSpace);
+ }
+ return;
+ }
+
+ assert(Directive && "Invalid size for machine code value!");
+ OS << Directive << truncateToSize(Value, Size);
+ EmitEOL();
}
-void MCAsmStreamer::EmitValue(const MCExpr *Value, unsigned Size) {
+void MCAsmStreamer::EmitValue(const MCExpr *Value, unsigned Size,
+ unsigned AddrSpace) {
assert(CurSection && "Cannot emit contents before setting section!");
- // Need target hooks to know how to print this.
+ const char *Directive = 0;
switch (Size) {
- default:
- llvm_unreachable("Invalid size for machine code value!");
- case 1: OS << ".byte"; break;
- case 2: OS << ".short"; break;
- case 4: OS << ".long"; break;
- case 8: OS << ".quad"; break;
+ default: break;
+ case 1: Directive = MAI.getData8bitsDirective(AddrSpace); break;
+ case 2: Directive = MAI.getData16bitsDirective(AddrSpace); break;
+ case 4: Directive = MAI.getData32bitsDirective(AddrSpace); break;
+ case 8: Directive = MAI.getData64bitsDirective(AddrSpace); break;
}
+
+ assert(Directive && "Invalid size for machine code value!");
+ OS << Directive << *truncateToSize(Value, Size);
+ EmitEOL();
+}
+
+/// EmitFill - Emit NumBytes bytes worth of the value specified by
+/// FillValue. This implements directives such as '.space'.
+void MCAsmStreamer::EmitFill(uint64_t NumBytes, uint8_t FillValue,
+ unsigned AddrSpace) {
+ if (NumBytes == 0) return;
+
+ if (AddrSpace == 0)
+ if (const char *ZeroDirective = MAI.getZeroDirective()) {
+ OS << ZeroDirective << NumBytes;
+ if (FillValue != 0)
+ OS << ',' << (int)FillValue;
+ EmitEOL();
+ return;
+ }
- OS << ' ';
- truncateToSize(Value, Size)->print(OS, &MAI);
- OS << '\n';
+ // Emit a byte at a time.
+ MCStreamer::EmitFill(NumBytes, FillValue, AddrSpace);
}
void MCAsmStreamer::EmitValueToAlignment(unsigned ByteAlignment, int64_t Value,
@@ -236,7 +436,7 @@ void MCAsmStreamer::EmitValueToAlignment(unsigned ByteAlignment, int64_t Value,
if (MaxBytesToEmit)
OS << ", " << MaxBytesToEmit;
}
- OS << '\n';
+ EmitEOL();
return;
}
@@ -254,15 +454,14 @@ void MCAsmStreamer::EmitValueToAlignment(unsigned ByteAlignment, int64_t Value,
OS << ", " << truncateToSize(Value, ValueSize);
if (MaxBytesToEmit)
OS << ", " << MaxBytesToEmit;
- OS << '\n';
+ EmitEOL();
}
void MCAsmStreamer::EmitValueToOffset(const MCExpr *Offset,
unsigned char Value) {
// FIXME: Verify that Offset is associated with the current section.
- OS << ".org ";
- Offset->print(OS, &MAI);
- OS << ", " << (unsigned) Value << '\n';
+ OS << ".org " << *Offset << ", " << (unsigned) Value;
+ EmitEOL();
}
void MCAsmStreamer::EmitInstruction(const MCInst &Inst) {
@@ -271,7 +470,7 @@ void MCAsmStreamer::EmitInstruction(const MCInst &Inst) {
// If we have an AsmPrinter, use that to print.
if (InstPrinter) {
InstPrinter->printInst(&Inst);
- OS << '\n';
+ EmitEOL();
// Show the encoding if we have a code emitter.
if (Emitter) {
@@ -296,15 +495,18 @@ void MCAsmStreamer::EmitInstruction(const MCInst &Inst) {
// Otherwise fall back to a structural printing for now. Eventually we should
// always have access to the target specific printer.
Inst.print(OS, &MAI);
- OS << '\n';
+ EmitEOL();
}
void MCAsmStreamer::Finish() {
OS.flush();
}
-MCStreamer *llvm::createAsmStreamer(MCContext &Context, raw_ostream &OS,
- const MCAsmInfo &MAI, MCInstPrinter *IP,
+MCStreamer *llvm::createAsmStreamer(MCContext &Context,
+ formatted_raw_ostream &OS,
+ const MCAsmInfo &MAI, bool isLittleEndian,
+ bool isVerboseAsm, MCInstPrinter *IP,
MCCodeEmitter *CE) {
- return new MCAsmStreamer(Context, OS, MAI, IP, CE);
+ return new MCAsmStreamer(Context, OS, MAI, isLittleEndian, isVerboseAsm,
+ IP, CE);
}
diff --git a/lib/MC/MCAssembler.cpp b/lib/MC/MCAssembler.cpp
index 1f5b6f1..f0f5a47 100644
--- a/lib/MC/MCAssembler.cpp
+++ b/lib/MC/MCAssembler.cpp
@@ -679,8 +679,6 @@ public:
UndefinedSymbolData[i].SymbolData->setIndex(Index++);
// The string table is padded to a multiple of 4.
- //
- // FIXME: Check to see if this varies per arch.
while (StringTable.size() % 4)
StringTable += '\x00';
}
diff --git a/lib/MC/MCExpr.cpp b/lib/MC/MCExpr.cpp
index a19ec19..1ee1b1b 100644
--- a/lib/MC/MCExpr.cpp
+++ b/lib/MC/MCExpr.cpp
@@ -15,7 +15,7 @@
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
-void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
+void MCExpr::print(raw_ostream &OS) const {
switch (getKind()) {
case MCExpr::Constant:
OS << cast<MCConstantExpr>(*this).getValue();
@@ -26,13 +26,10 @@ void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
// Parenthesize names that start with $ so that they don't look like
// absolute names.
- if (Sym.getName()[0] == '$') {
- OS << '(';
- Sym.print(OS, MAI);
- OS << ')';
- } else {
- Sym.print(OS, MAI);
- }
+ if (Sym.getName()[0] == '$')
+ OS << '(' << Sym << ')';
+ else
+ OS << Sym;
return;
}
@@ -45,7 +42,7 @@ void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
case MCUnaryExpr::Not: OS << '~'; break;
case MCUnaryExpr::Plus: OS << '+'; break;
}
- UE.getSubExpr()->print(OS, MAI);
+ OS << *UE.getSubExpr();
return;
}
@@ -54,11 +51,9 @@ void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
// Only print parens around the LHS if it is non-trivial.
if (isa<MCConstantExpr>(BE.getLHS()) || isa<MCSymbolRefExpr>(BE.getLHS())) {
- BE.getLHS()->print(OS, MAI);
+ OS << *BE.getLHS();
} else {
- OS << '(';
- BE.getLHS()->print(OS, MAI);
- OS << ')';
+ OS << '(' << *BE.getLHS() << ')';
}
switch (BE.getOpcode()) {
@@ -95,11 +90,9 @@ void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
// Only print parens around the LHS if it is non-trivial.
if (isa<MCConstantExpr>(BE.getRHS()) || isa<MCSymbolRefExpr>(BE.getRHS())) {
- BE.getRHS()->print(OS, MAI);
+ OS << *BE.getRHS();
} else {
- OS << '(';
- BE.getRHS()->print(OS, MAI);
- OS << ')';
+ OS << '(' << *BE.getRHS() << ')';
}
return;
}
@@ -109,7 +102,7 @@ void MCExpr::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
}
void MCExpr::dump() const {
- print(dbgs(), 0);
+ print(dbgs());
dbgs() << '\n';
}
diff --git a/lib/MC/MCInst.cpp b/lib/MC/MCInst.cpp
index 7c7a644..0634c9f 100644
--- a/lib/MC/MCInst.cpp
+++ b/lib/MC/MCInst.cpp
@@ -23,9 +23,7 @@ void MCOperand::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
else if (isImm())
OS << "Imm:" << getImm();
else if (isExpr()) {
- OS << "Expr:(";
- getExpr()->print(OS, MAI);
- OS << ")";
+ OS << "Expr:(" << *getExpr() << ")";
} else
OS << "UNDEFINED";
OS << ">";
diff --git a/lib/MC/MCMachOStreamer.cpp b/lib/MC/MCMachOStreamer.cpp
index 828b92a..e559c65 100644
--- a/lib/MC/MCMachOStreamer.cpp
+++ b/lib/MC/MCMachOStreamer.cpp
@@ -117,36 +117,26 @@ public:
/// @{
virtual void SwitchSection(const MCSection *Section);
-
virtual void EmitLabel(MCSymbol *Symbol);
-
- virtual void EmitAssemblerFlag(AssemblerFlag Flag);
-
+ virtual void EmitAssemblerFlag(MCAssemblerFlag Flag);
virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value);
-
- virtual void EmitSymbolAttribute(MCSymbol *Symbol, SymbolAttr Attribute);
-
+ virtual void EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute);
virtual void EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue);
-
- virtual void EmitCommonSymbol(MCSymbol *Symbol, unsigned Size,
+ virtual void EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
unsigned ByteAlignment);
-
+ virtual void EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size) {
+ assert(0 && "macho doesn't support this directive");
+ }
virtual void EmitZerofill(const MCSection *Section, MCSymbol *Symbol = 0,
unsigned Size = 0, unsigned ByteAlignment = 0);
-
- virtual void EmitBytes(StringRef Data);
-
- virtual void EmitValue(const MCExpr *Value, unsigned Size);
-
+ virtual void EmitBytes(StringRef Data, unsigned AddrSpace);
+ virtual void EmitValue(const MCExpr *Value, unsigned Size,unsigned AddrSpace);
virtual void EmitValueToAlignment(unsigned ByteAlignment, int64_t Value = 0,
unsigned ValueSize = 1,
unsigned MaxBytesToEmit = 0);
-
virtual void EmitValueToOffset(const MCExpr *Offset,
unsigned char Value = 0);
-
virtual void EmitInstruction(const MCInst &Inst);
-
virtual void Finish();
/// @}
@@ -183,9 +173,9 @@ void MCMachOStreamer::EmitLabel(MCSymbol *Symbol) {
Symbol->setSection(*CurSection);
}
-void MCMachOStreamer::EmitAssemblerFlag(AssemblerFlag Flag) {
+void MCMachOStreamer::EmitAssemblerFlag(MCAssemblerFlag Flag) {
switch (Flag) {
- case SubsectionsViaSymbols:
+ case MCAF_SubsectionsViaSymbols:
Assembler.setSubsectionsViaSymbols(true);
return;
}
@@ -204,10 +194,10 @@ void MCMachOStreamer::EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {
}
void MCMachOStreamer::EmitSymbolAttribute(MCSymbol *Symbol,
- SymbolAttr Attribute) {
+ MCSymbolAttr Attribute) {
// Indirect symbols are handled differently, to match how 'as' handles
// them. This makes writing matching .o files easier.
- if (Attribute == MCStreamer::IndirectSymbol) {
+ if (Attribute == MCSA_IndirectSymbol) {
// Note that we intentionally cannot use the symbol data here; this is
// important for matching the string table that 'as' generates.
IndirectSymbolData ISD;
@@ -229,19 +219,21 @@ void MCMachOStreamer::EmitSymbolAttribute(MCSymbol *Symbol,
// In the future it might be worth trying to make these operations more well
// defined.
switch (Attribute) {
- case MCStreamer::IndirectSymbol:
- case MCStreamer::Hidden:
- case MCStreamer::Internal:
- case MCStreamer::Protected:
- case MCStreamer::Weak:
+ case MCSA_Invalid:
+ case MCSA_IndirectSymbol:
+ case MCSA_Hidden:
+ case MCSA_Internal:
+ case MCSA_Protected:
+ case MCSA_Weak:
+ case MCSA_Local:
assert(0 && "Invalid symbol attribute for Mach-O!");
break;
- case MCStreamer::Global:
+ case MCSA_Global:
SD.setExternal(true);
break;
- case MCStreamer::LazyReference:
+ case MCSA_LazyReference:
// FIXME: This requires -dynamic.
SD.setFlags(SD.getFlags() | SF_NoDeadStrip);
if (Symbol->isUndefined())
@@ -250,23 +242,23 @@ void MCMachOStreamer::EmitSymbolAttribute(MCSymbol *Symbol,
// Since .reference sets the no dead strip bit, it is equivalent to
// .no_dead_strip in practice.
- case MCStreamer::Reference:
- case MCStreamer::NoDeadStrip:
+ case MCSA_Reference:
+ case MCSA_NoDeadStrip:
SD.setFlags(SD.getFlags() | SF_NoDeadStrip);
break;
- case MCStreamer::PrivateExtern:
+ case MCSA_PrivateExtern:
SD.setExternal(true);
SD.setPrivateExtern(true);
break;
- case MCStreamer::WeakReference:
+ case MCSA_WeakReference:
// FIXME: This requires -dynamic.
if (Symbol->isUndefined())
SD.setFlags(SD.getFlags() | SF_WeakReference);
break;
- case MCStreamer::WeakDefinition:
+ case MCSA_WeakDefinition:
// FIXME: 'as' enforces that this is defined and global. The manual claims
// it has to be in a coalesced section, but this isn't enforced.
SD.setFlags(SD.getFlags() | SF_WeakDefinition);
@@ -281,7 +273,7 @@ void MCMachOStreamer::EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {
getSymbolData(*Symbol).setFlags(DescValue & SF_DescFlagsMask);
}
-void MCMachOStreamer::EmitCommonSymbol(MCSymbol *Symbol, unsigned Size,
+void MCMachOStreamer::EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
unsigned ByteAlignment) {
// FIXME: Darwin 'as' does appear to allow redef of a .comm by itself.
assert(Symbol->isUndefined() && "Cannot define a symbol twice!");
@@ -315,14 +307,15 @@ void MCMachOStreamer::EmitZerofill(const MCSection *Section, MCSymbol *Symbol,
SectData.setAlignment(ByteAlignment);
}
-void MCMachOStreamer::EmitBytes(StringRef Data) {
+void MCMachOStreamer::EmitBytes(StringRef Data, unsigned AddrSpace) {
MCDataFragment *DF = dyn_cast_or_null<MCDataFragment>(getCurrentFragment());
if (!DF)
DF = new MCDataFragment(CurSectionData);
DF->getContents().append(Data.begin(), Data.end());
}
-void MCMachOStreamer::EmitValue(const MCExpr *Value, unsigned Size) {
+void MCMachOStreamer::EmitValue(const MCExpr *Value, unsigned Size,
+ unsigned AddrSpace) {
new MCFillFragment(*AddValueSymbols(Value), Size, 1, CurSectionData);
}
@@ -353,11 +346,13 @@ void MCMachOStreamer::EmitInstruction(const MCInst &Inst) {
if (!Emitter)
llvm_unreachable("no code emitter available!");
+ // FIXME: Emitting an instruction should cause S_ATTR_SOME_INSTRUCTIONS to
+ // be set for the current section.
// FIXME: Relocations!
SmallString<256> Code;
raw_svector_ostream VecOS(Code);
Emitter->EncodeInstruction(Inst, VecOS);
- EmitBytes(VecOS.str());
+ EmitBytes(VecOS.str(), 0);
}
void MCMachOStreamer::Finish() {
diff --git a/lib/MC/MCNullStreamer.cpp b/lib/MC/MCNullStreamer.cpp
index ddc4e69..7c219b3 100644
--- a/lib/MC/MCNullStreamer.cpp
+++ b/lib/MC/MCNullStreamer.cpp
@@ -31,23 +31,25 @@ namespace {
virtual void EmitLabel(MCSymbol *Symbol) {}
- virtual void EmitAssemblerFlag(AssemblerFlag Flag) {}
+ virtual void EmitAssemblerFlag(MCAssemblerFlag Flag) {}
virtual void EmitAssignment(MCSymbol *Symbol, const MCExpr *Value) {}
- virtual void EmitSymbolAttribute(MCSymbol *Symbol, SymbolAttr Attribute) {}
+ virtual void EmitSymbolAttribute(MCSymbol *Symbol, MCSymbolAttr Attribute){}
virtual void EmitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {}
- virtual void EmitCommonSymbol(MCSymbol *Symbol, unsigned Size,
+ virtual void EmitCommonSymbol(MCSymbol *Symbol, uint64_t Size,
unsigned ByteAlignment) {}
+ virtual void EmitLocalCommonSymbol(MCSymbol *Symbol, uint64_t Size) {}
virtual void EmitZerofill(const MCSection *Section, MCSymbol *Symbol = 0,
unsigned Size = 0, unsigned ByteAlignment = 0) {}
- virtual void EmitBytes(StringRef Data) {}
+ virtual void EmitBytes(StringRef Data, unsigned AddrSpace) {}
- virtual void EmitValue(const MCExpr *Value, unsigned Size) {}
+ virtual void EmitValue(const MCExpr *Value, unsigned Size,
+ unsigned AddrSpace) {}
virtual void EmitValueToAlignment(unsigned ByteAlignment, int64_t Value = 0,
unsigned ValueSize = 1,
diff --git a/lib/MC/MCParser/AsmLexer.cpp b/lib/MC/MCParser/AsmLexer.cpp
new file mode 100644
index 0000000..482eefd
--- /dev/null
+++ b/lib/MC/MCParser/AsmLexer.cpp
@@ -0,0 +1,320 @@
+//===- AsmLexer.cpp - Lexer for Assembly Files ----------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This class implements the lexer for assembly files.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCParser/AsmLexer.h"
+#include "llvm/Support/SMLoc.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/MC/MCAsmInfo.h"
+#include <cerrno>
+#include <cstdio>
+#include <cstdlib>
+using namespace llvm;
+
+AsmLexer::AsmLexer(const MCAsmInfo &_MAI) : MAI(_MAI) {
+ CurBuf = NULL;
+ CurPtr = NULL;
+ TokStart = 0;
+}
+
+AsmLexer::~AsmLexer() {
+}
+
+void AsmLexer::setBuffer(const MemoryBuffer *buf, const char *ptr) {
+ CurBuf = buf;
+
+ if (ptr)
+ CurPtr = ptr;
+ else
+ CurPtr = CurBuf->getBufferStart();
+
+ TokStart = 0;
+}
+
+SMLoc AsmLexer::getLoc() const {
+ return SMLoc::getFromPointer(TokStart);
+}
+
+/// ReturnError - Set the error to the specified string at the specified
+/// location. This is defined to always return AsmToken::Error.
+AsmToken AsmLexer::ReturnError(const char *Loc, const std::string &Msg) {
+ SetError(SMLoc::getFromPointer(Loc), Msg);
+
+ return AsmToken(AsmToken::Error, StringRef(Loc, 0));
+}
+
+int AsmLexer::getNextChar() {
+ char CurChar = *CurPtr++;
+ switch (CurChar) {
+ default:
+ return (unsigned char)CurChar;
+ case 0:
+ // A nul character in the stream is either the end of the current buffer or
+ // a random nul in the file. Disambiguate that here.
+ if (CurPtr-1 != CurBuf->getBufferEnd())
+ return 0; // Just whitespace.
+
+ // Otherwise, return end of file.
+ --CurPtr; // Another call to lex will return EOF again.
+ return EOF;
+ }
+}
+
+/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
+AsmToken AsmLexer::LexIdentifier() {
+ while (isalnum(*CurPtr) || *CurPtr == '_' || *CurPtr == '$' ||
+ *CurPtr == '.' || *CurPtr == '@')
+ ++CurPtr;
+ return AsmToken(AsmToken::Identifier, StringRef(TokStart, CurPtr - TokStart));
+}
+
+/// LexSlash: Slash: /
+/// C-Style Comment: /* ... */
+AsmToken AsmLexer::LexSlash() {
+ switch (*CurPtr) {
+ case '*': break; // C style comment.
+ case '/': return ++CurPtr, LexLineComment();
+ default: return AsmToken(AsmToken::Slash, StringRef(CurPtr, 1));
+ }
+
+ // C Style comment.
+ ++CurPtr; // skip the star.
+ while (1) {
+ int CurChar = getNextChar();
+ switch (CurChar) {
+ case EOF:
+ return ReturnError(TokStart, "unterminated comment");
+ case '*':
+ // End of the comment?
+ if (CurPtr[0] != '/') break;
+
+ ++CurPtr; // End the */.
+ return LexToken();
+ }
+ }
+}
+
+/// LexLineComment: Comment: #[^\n]*
+/// : //[^\n]*
+AsmToken AsmLexer::LexLineComment() {
+ // FIXME: This is broken if we happen to a comment at the end of a file, which
+ // was .included, and which doesn't end with a newline.
+ int CurChar = getNextChar();
+ while (CurChar != '\n' && CurChar != '\n' && CurChar != EOF)
+ CurChar = getNextChar();
+
+ if (CurChar == EOF)
+ return AsmToken(AsmToken::Eof, StringRef(CurPtr, 0));
+ return AsmToken(AsmToken::EndOfStatement, StringRef(CurPtr, 0));
+}
+
+
+/// LexDigit: First character is [0-9].
+/// Local Label: [0-9][:]
+/// Forward/Backward Label: [0-9][fb]
+/// Binary integer: 0b[01]+
+/// Octal integer: 0[0-7]+
+/// Hex integer: 0x[0-9a-fA-F]+
+/// Decimal integer: [1-9][0-9]*
+/// TODO: FP literal.
+AsmToken AsmLexer::LexDigit() {
+ if (*CurPtr == ':')
+ return ReturnError(TokStart, "FIXME: local label not implemented");
+ if (*CurPtr == 'f' || *CurPtr == 'b')
+ return ReturnError(TokStart, "FIXME: directional label not implemented");
+
+ // Decimal integer: [1-9][0-9]*
+ if (CurPtr[-1] != '0') {
+ while (isdigit(*CurPtr))
+ ++CurPtr;
+
+ StringRef Result(TokStart, CurPtr - TokStart);
+
+ long long Value;
+ if (Result.getAsInteger(10, Value))
+ return ReturnError(TokStart, "Invalid decimal number");
+ return AsmToken(AsmToken::Integer, Result, Value);
+ }
+
+ if (*CurPtr == 'b') {
+ ++CurPtr;
+ const char *NumStart = CurPtr;
+ while (CurPtr[0] == '0' || CurPtr[0] == '1')
+ ++CurPtr;
+
+ // Requires at least one binary digit.
+ if (CurPtr == NumStart)
+ return ReturnError(TokStart, "Invalid binary number");
+
+ StringRef Result(TokStart, CurPtr - TokStart);
+
+ long long Value;
+ if (Result.getAsInteger(2, Value))
+ return ReturnError(TokStart, "Invalid binary number");
+
+ return AsmToken(AsmToken::Integer, Result, Value);
+ }
+
+ if (*CurPtr == 'x') {
+ ++CurPtr;
+ const char *NumStart = CurPtr;
+ while (isxdigit(CurPtr[0]))
+ ++CurPtr;
+
+ // Requires at least one hex digit.
+ if (CurPtr == NumStart)
+ return ReturnError(CurPtr-2, "Invalid hexadecimal number");
+
+ unsigned long long Result;
+ if (StringRef(TokStart, CurPtr - TokStart).getAsInteger(0, Result))
+ return ReturnError(TokStart, "Invalid hexadecimal number");
+
+ return AsmToken(AsmToken::Integer, StringRef(TokStart, CurPtr - TokStart),
+ (int64_t)Result);
+ }
+
+ // Must be an octal number, it starts with 0.
+ while (*CurPtr >= '0' && *CurPtr <= '7')
+ ++CurPtr;
+
+ StringRef Result(TokStart, CurPtr - TokStart);
+ long long Value;
+ if (Result.getAsInteger(8, Value))
+ return ReturnError(TokStart, "Invalid octal number");
+
+ return AsmToken(AsmToken::Integer, Result, Value);
+}
+
+/// LexQuote: String: "..."
+AsmToken AsmLexer::LexQuote() {
+ int CurChar = getNextChar();
+ // TODO: does gas allow multiline string constants?
+ while (CurChar != '"') {
+ if (CurChar == '\\') {
+ // Allow \", etc.
+ CurChar = getNextChar();
+ }
+
+ if (CurChar == EOF)
+ return ReturnError(TokStart, "unterminated string constant");
+
+ CurChar = getNextChar();
+ }
+
+ return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart));
+}
+
+StringRef AsmLexer::LexUntilEndOfStatement() {
+ TokStart = CurPtr;
+
+ while (!isAtStartOfComment(*CurPtr) && // Start of line comment.
+ *CurPtr != ';' && // End of statement marker.
+ *CurPtr != '\n' &&
+ *CurPtr != '\r' &&
+ (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) {
+ ++CurPtr;
+ }
+ return StringRef(TokStart, CurPtr-TokStart);
+}
+
+bool AsmLexer::isAtStartOfComment(char Char) {
+ // FIXME: This won't work for multi-character comment indicators like "//".
+ return Char == *MAI.getCommentString();
+}
+
+AsmToken AsmLexer::LexToken() {
+ TokStart = CurPtr;
+ // This always consumes at least one character.
+ int CurChar = getNextChar();
+
+ if (isAtStartOfComment(CurChar))
+ return LexLineComment();
+
+ switch (CurChar) {
+ default:
+ // Handle identifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
+ if (isalpha(CurChar) || CurChar == '_' || CurChar == '.')
+ return LexIdentifier();
+
+ // Unknown character, emit an error.
+ return ReturnError(TokStart, "invalid character in input");
+ case EOF: return AsmToken(AsmToken::Eof, StringRef(TokStart, 0));
+ case 0:
+ case ' ':
+ case '\t':
+ // Ignore whitespace.
+ return LexToken();
+ case '\n': // FALL THROUGH.
+ case '\r': // FALL THROUGH.
+ case ';': return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
+ case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1));
+ case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1));
+ case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1));
+ case '~': return AsmToken(AsmToken::Tilde, StringRef(TokStart, 1));
+ case '(': return AsmToken(AsmToken::LParen, StringRef(TokStart, 1));
+ case ')': return AsmToken(AsmToken::RParen, StringRef(TokStart, 1));
+ case '[': return AsmToken(AsmToken::LBrac, StringRef(TokStart, 1));
+ case ']': return AsmToken(AsmToken::RBrac, StringRef(TokStart, 1));
+ case '{': return AsmToken(AsmToken::LCurly, StringRef(TokStart, 1));
+ case '}': return AsmToken(AsmToken::RCurly, StringRef(TokStart, 1));
+ case '*': return AsmToken(AsmToken::Star, StringRef(TokStart, 1));
+ case ',': return AsmToken(AsmToken::Comma, StringRef(TokStart, 1));
+ case '$': return AsmToken(AsmToken::Dollar, StringRef(TokStart, 1));
+ case '=':
+ if (*CurPtr == '=')
+ return ++CurPtr, AsmToken(AsmToken::EqualEqual, StringRef(TokStart, 2));
+ return AsmToken(AsmToken::Equal, StringRef(TokStart, 1));
+ case '|':
+ if (*CurPtr == '|')
+ return ++CurPtr, AsmToken(AsmToken::PipePipe, StringRef(TokStart, 2));
+ return AsmToken(AsmToken::Pipe, StringRef(TokStart, 1));
+ case '^': return AsmToken(AsmToken::Caret, StringRef(TokStart, 1));
+ case '&':
+ if (*CurPtr == '&')
+ return ++CurPtr, AsmToken(AsmToken::AmpAmp, StringRef(TokStart, 2));
+ return AsmToken(AsmToken::Amp, StringRef(TokStart, 1));
+ case '!':
+ if (*CurPtr == '=')
+ return ++CurPtr, AsmToken(AsmToken::ExclaimEqual, StringRef(TokStart, 2));
+ return AsmToken(AsmToken::Exclaim, StringRef(TokStart, 1));
+ case '%': return AsmToken(AsmToken::Percent, StringRef(TokStart, 1));
+ case '/': return LexSlash();
+ case '#': return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
+ case '"': return LexQuote();
+ case '0': case '1': case '2': case '3': case '4':
+ case '5': case '6': case '7': case '8': case '9':
+ return LexDigit();
+ case '<':
+ switch (*CurPtr) {
+ case '<': return ++CurPtr, AsmToken(AsmToken::LessLess,
+ StringRef(TokStart, 2));
+ case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual,
+ StringRef(TokStart, 2));
+ case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater,
+ StringRef(TokStart, 2));
+ default: return AsmToken(AsmToken::Less, StringRef(TokStart, 1));
+ }
+ case '>':
+ switch (*CurPtr) {
+ case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater,
+ StringRef(TokStart, 2));
+ case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual,
+ StringRef(TokStart, 2));
+ default: return AsmToken(AsmToken::Greater, StringRef(TokStart, 1));
+ }
+
+ // TODO: Quoted identifiers (objc methods etc)
+ // local labels: [0-9][:]
+ // Forward/backward labels: [0-9][fb]
+ // Integers, fp constants, character constants.
+ }
+}
diff --git a/lib/MC/MCParser/AsmParser.cpp b/lib/MC/MCParser/AsmParser.cpp
new file mode 100644
index 0000000..dd438b7
--- /dev/null
+++ b/lib/MC/MCParser/AsmParser.cpp
@@ -0,0 +1,1781 @@
+//===- AsmParser.cpp - Parser for Assembly Files --------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This class implements the parser for assembly files.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCParser/AsmParser.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/Twine.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCSectionMachO.h"
+#include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSymbol.h"
+#include "llvm/MC/MCValue.h"
+#include "llvm/MC/MCParser/MCParsedAsmOperand.h"
+#include "llvm/Support/Compiler.h"
+#include "llvm/Support/SourceMgr.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Target/TargetAsmParser.h"
+using namespace llvm;
+
+
+enum { DEFAULT_ADDRSPACE = 0 };
+
+// Mach-O section uniquing.
+//
+// FIXME: Figure out where this should live, it should be shared by
+// TargetLoweringObjectFile.
+typedef StringMap<const MCSectionMachO*> MachOUniqueMapTy;
+
+AsmParser::AsmParser(SourceMgr &_SM, MCContext &_Ctx, MCStreamer &_Out,
+ const MCAsmInfo &_MAI)
+ : Lexer(_MAI), Ctx(_Ctx), Out(_Out), SrcMgr(_SM), TargetParser(0),
+ CurBuffer(0), SectionUniquingMap(0) {
+ Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer));
+
+ // Debugging directives.
+ AddDirectiveHandler(".file", &AsmParser::ParseDirectiveFile);
+ AddDirectiveHandler(".line", &AsmParser::ParseDirectiveLine);
+ AddDirectiveHandler(".loc", &AsmParser::ParseDirectiveLoc);
+}
+
+
+
+AsmParser::~AsmParser() {
+ // If we have the MachO uniquing map, free it.
+ delete (MachOUniqueMapTy*)SectionUniquingMap;
+}
+
+const MCSection *AsmParser::getMachOSection(const StringRef &Segment,
+ const StringRef &Section,
+ unsigned TypeAndAttributes,
+ unsigned Reserved2,
+ SectionKind Kind) const {
+ // We unique sections by their segment/section pair. The returned section
+ // may not have the same flags as the requested section, if so this should be
+ // diagnosed by the client as an error.
+
+ // Create the map if it doesn't already exist.
+ if (SectionUniquingMap == 0)
+ SectionUniquingMap = new MachOUniqueMapTy();
+ MachOUniqueMapTy &Map = *(MachOUniqueMapTy*)SectionUniquingMap;
+
+ // Form the name to look up.
+ SmallString<64> Name;
+ Name += Segment;
+ Name.push_back(',');
+ Name += Section;
+
+ // Do the lookup, if we have a hit, return it.
+ const MCSectionMachO *&Entry = Map[Name.str()];
+
+ // FIXME: This should validate the type and attributes.
+ if (Entry) return Entry;
+
+ // Otherwise, return a new section.
+ return Entry = MCSectionMachO::Create(Segment, Section, TypeAndAttributes,
+ Reserved2, Kind, Ctx);
+}
+
+void AsmParser::Warning(SMLoc L, const Twine &Msg) {
+ PrintMessage(L, Msg.str(), "warning");
+}
+
+bool AsmParser::Error(SMLoc L, const Twine &Msg) {
+ PrintMessage(L, Msg.str(), "error");
+ return true;
+}
+
+bool AsmParser::TokError(const char *Msg) {
+ PrintMessage(Lexer.getLoc(), Msg, "error");
+ 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.
+ SMLoc ParentIncludeLoc = SrcMgr.getParentIncludeLoc(CurBuffer);
+ if (ParentIncludeLoc != SMLoc()) {
+ CurBuffer = SrcMgr.FindBufferContainingLoc(ParentIncludeLoc);
+ Lexer.setBuffer(SrcMgr.getMemoryBuffer(CurBuffer),
+ ParentIncludeLoc.getPointer());
+ tok = &Lexer.Lex();
+ }
+ }
+
+ if (tok->is(AsmToken::Error))
+ PrintMessage(Lexer.getErrLoc(), Lexer.getErr(), "error");
+
+ return *tok;
+}
+
+bool AsmParser::Run() {
+ // Create the initial section.
+ //
+ // FIXME: Support -n.
+ // FIXME: Target hook & command line option for initial section.
+ Out.SwitchSection(getMachOSection("__TEXT", "__text",
+ MCSectionMachO::S_ATTR_PURE_INSTRUCTIONS,
+ 0, SectionKind()));
+
+
+ // Prime the lexer.
+ Lex();
+
+ bool HadError = false;
+
+ AsmCond StartingCondState = TheCondState;
+
+ // While we have input, parse each statement.
+ while (Lexer.isNot(AsmToken::Eof)) {
+ // Handle conditional assembly here before calling ParseStatement()
+ if (Lexer.getKind() == AsmToken::Identifier) {
+ // If we have an identifier, handle it as the key symbol.
+ AsmToken ID = getTok();
+ SMLoc IDLoc = ID.getLoc();
+ StringRef IDVal = ID.getString();
+
+ if (IDVal == ".if" ||
+ IDVal == ".elseif" ||
+ IDVal == ".else" ||
+ IDVal == ".endif") {
+ if (!ParseConditionalAssemblyDirectives(IDVal, IDLoc))
+ continue;
+ HadError = true;
+ EatToEndOfStatement();
+ continue;
+ }
+ }
+ if (TheCondState.Ignore) {
+ EatToEndOfStatement();
+ continue;
+ }
+
+ if (!ParseStatement()) continue;
+
+ // We had an error, remember it and recover by skipping to the next line.
+ HadError = true;
+ EatToEndOfStatement();
+ }
+
+ if (TheCondState.TheCond != StartingCondState.TheCond ||
+ TheCondState.Ignore != StartingCondState.Ignore)
+ return TokError("unmatched .ifs or .elses");
+
+ if (!HadError)
+ Out.Finish();
+
+ return HadError;
+}
+
+/// ParseConditionalAssemblyDirectives - parse the conditional assembly
+/// directives
+bool AsmParser::ParseConditionalAssemblyDirectives(StringRef Directive,
+ SMLoc DirectiveLoc) {
+ if (Directive == ".if")
+ return ParseDirectiveIf(DirectiveLoc);
+ if (Directive == ".elseif")
+ return ParseDirectiveElseIf(DirectiveLoc);
+ if (Directive == ".else")
+ return ParseDirectiveElse(DirectiveLoc);
+ if (Directive == ".endif")
+ return ParseDirectiveEndIf(DirectiveLoc);
+ return true;
+}
+
+/// 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();
+}
+
+
+/// ParseParenExpr - Parse a paren expression and return it.
+/// NOTE: This assumes the leading '(' has already been consumed.
+///
+/// parenexpr ::= expr)
+///
+bool AsmParser::ParseParenExpr(const MCExpr *&Res, SMLoc &EndLoc) {
+ if (ParseExpression(Res)) return true;
+ if (Lexer.isNot(AsmToken::RParen))
+ return TokError("expected ')' in parentheses expression");
+ EndLoc = Lexer.getLoc();
+ Lex();
+ return false;
+}
+
+MCSymbol *AsmParser::CreateSymbol(StringRef Name) {
+ if (MCSymbol *S = Ctx.LookupSymbol(Name))
+ return S;
+
+ // If the label starts with L it is an assembler temporary label.
+ if (Name.startswith("L"))
+ return Ctx.CreateTemporarySymbol(Name);
+
+ return Ctx.CreateSymbol(Name);
+}
+
+/// ParsePrimaryExpr - Parse a primary expression and return it.
+/// primaryexpr ::= (parenexpr
+/// primaryexpr ::= symbol
+/// primaryexpr ::= number
+/// primaryexpr ::= ~,+,- primaryexpr
+bool AsmParser::ParsePrimaryExpr(const MCExpr *&Res, SMLoc &EndLoc) {
+ switch (Lexer.getKind()) {
+ default:
+ return TokError("unknown token in expression");
+ case AsmToken::Exclaim:
+ Lex(); // Eat the operator.
+ if (ParsePrimaryExpr(Res, EndLoc))
+ return true;
+ Res = MCUnaryExpr::CreateLNot(Res, getContext());
+ return false;
+ case AsmToken::String:
+ case AsmToken::Identifier: {
+ // This is a symbol reference.
+ MCSymbol *Sym = CreateSymbol(getTok().getIdentifier());
+ EndLoc = Lexer.getLoc();
+ Lex(); // Eat identifier.
+
+ // If this is an absolute variable reference, substitute it now to preserve
+ // semantics in the face of reassignment.
+ if (Sym->getValue() && isa<MCConstantExpr>(Sym->getValue())) {
+ Res = Sym->getValue();
+ return false;
+ }
+
+ // Otherwise create a symbol ref.
+ Res = MCSymbolRefExpr::Create(Sym, getContext());
+ return false;
+ }
+ case AsmToken::Integer:
+ Res = MCConstantExpr::Create(getTok().getIntVal(), getContext());
+ EndLoc = Lexer.getLoc();
+ Lex(); // Eat token.
+ return false;
+ case AsmToken::LParen:
+ Lex(); // Eat the '('.
+ return ParseParenExpr(Res, EndLoc);
+ case AsmToken::Minus:
+ Lex(); // Eat the operator.
+ if (ParsePrimaryExpr(Res, EndLoc))
+ return true;
+ Res = MCUnaryExpr::CreateMinus(Res, getContext());
+ return false;
+ case AsmToken::Plus:
+ Lex(); // Eat the operator.
+ if (ParsePrimaryExpr(Res, EndLoc))
+ return true;
+ Res = MCUnaryExpr::CreatePlus(Res, getContext());
+ return false;
+ case AsmToken::Tilde:
+ Lex(); // Eat the operator.
+ if (ParsePrimaryExpr(Res, EndLoc))
+ return true;
+ Res = MCUnaryExpr::CreateNot(Res, getContext());
+ return false;
+ }
+}
+
+bool AsmParser::ParseExpression(const MCExpr *&Res) {
+ SMLoc EndLoc;
+ return ParseExpression(Res, EndLoc);
+}
+
+/// ParseExpression - Parse an expression and return it.
+///
+/// expr ::= expr +,- expr -> lowest.
+/// expr ::= expr |,^,&,! expr -> middle.
+/// expr ::= expr *,/,%,<<,>> expr -> highest.
+/// expr ::= primaryexpr
+///
+bool AsmParser::ParseExpression(const MCExpr *&Res, SMLoc &EndLoc) {
+ Res = 0;
+ return ParsePrimaryExpr(Res, EndLoc) ||
+ ParseBinOpRHS(1, Res, EndLoc);
+}
+
+bool AsmParser::ParseParenExpression(const MCExpr *&Res, SMLoc &EndLoc) {
+ if (ParseParenExpr(Res, EndLoc))
+ return true;
+
+ return false;
+}
+
+bool AsmParser::ParseAbsoluteExpression(int64_t &Res) {
+ const MCExpr *Expr;
+
+ SMLoc StartLoc = Lexer.getLoc();
+ if (ParseExpression(Expr))
+ return true;
+
+ if (!Expr->EvaluateAsAbsolute(Res))
+ return Error(StartLoc, "expected absolute expression");
+
+ return false;
+}
+
+static unsigned getBinOpPrecedence(AsmToken::TokenKind K,
+ MCBinaryExpr::Opcode &Kind) {
+ switch (K) {
+ default:
+ return 0; // not a binop.
+
+ // Lowest Precedence: &&, ||
+ case AsmToken::AmpAmp:
+ Kind = MCBinaryExpr::LAnd;
+ return 1;
+ case AsmToken::PipePipe:
+ Kind = MCBinaryExpr::LOr;
+ return 1;
+
+ // Low Precedence: +, -, ==, !=, <>, <, <=, >, >=
+ case AsmToken::Plus:
+ Kind = MCBinaryExpr::Add;
+ return 2;
+ case AsmToken::Minus:
+ Kind = MCBinaryExpr::Sub;
+ return 2;
+ case AsmToken::EqualEqual:
+ Kind = MCBinaryExpr::EQ;
+ return 2;
+ case AsmToken::ExclaimEqual:
+ case AsmToken::LessGreater:
+ Kind = MCBinaryExpr::NE;
+ return 2;
+ case AsmToken::Less:
+ Kind = MCBinaryExpr::LT;
+ return 2;
+ case AsmToken::LessEqual:
+ Kind = MCBinaryExpr::LTE;
+ return 2;
+ case AsmToken::Greater:
+ Kind = MCBinaryExpr::GT;
+ return 2;
+ 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;
+
+ // Highest Precedence: *, /, %, <<, >>
+ case AsmToken::Star:
+ Kind = MCBinaryExpr::Mul;
+ return 4;
+ case AsmToken::Slash:
+ Kind = MCBinaryExpr::Div;
+ return 4;
+ case AsmToken::Percent:
+ Kind = MCBinaryExpr::Mod;
+ return 4;
+ case AsmToken::LessLess:
+ Kind = MCBinaryExpr::Shl;
+ return 4;
+ case AsmToken::GreaterGreater:
+ Kind = MCBinaryExpr::Shr;
+ return 4;
+ }
+}
+
+
+/// ParseBinOpRHS - Parse all binary operators with precedence >= 'Precedence'.
+/// Res contains the LHS of the expression on input.
+bool AsmParser::ParseBinOpRHS(unsigned Precedence, const MCExpr *&Res,
+ SMLoc &EndLoc) {
+ while (1) {
+ MCBinaryExpr::Opcode Kind = MCBinaryExpr::Add;
+ unsigned TokPrec = getBinOpPrecedence(Lexer.getKind(), Kind);
+
+ // If the next token is lower precedence than we are allowed to eat, return
+ // successfully with what we ate already.
+ if (TokPrec < Precedence)
+ return false;
+
+ Lex();
+
+ // Eat the next primary expression.
+ const MCExpr *RHS;
+ if (ParsePrimaryExpr(RHS, EndLoc)) return true;
+
+ // If BinOp binds less tightly with RHS than the operator after RHS, let
+ // the pending operator take RHS as its LHS.
+ MCBinaryExpr::Opcode Dummy;
+ unsigned NextTokPrec = getBinOpPrecedence(Lexer.getKind(), Dummy);
+ if (TokPrec < NextTokPrec) {
+ if (ParseBinOpRHS(Precedence+1, RHS, EndLoc)) return true;
+ }
+
+ // Merge LHS and RHS according to operator.
+ Res = MCBinaryExpr::Create(Kind, Res, RHS, getContext());
+ }
+}
+
+
+
+
+/// ParseStatement:
+/// ::= EndOfStatement
+/// ::= Label* Directive ...Operands... EndOfStatement
+/// ::= Label* Identifier OperandList* EndOfStatement
+bool AsmParser::ParseStatement() {
+ if (Lexer.is(AsmToken::EndOfStatement)) {
+ Lex();
+ return false;
+ }
+
+ // Statements always start with an identifier.
+ AsmToken ID = getTok();
+ SMLoc IDLoc = ID.getLoc();
+ StringRef IDVal;
+ if (ParseIdentifier(IDVal))
+ return TokError("unexpected token at start of statement");
+
+ // FIXME: Recurse on local labels?
+
+ // See what kind of statement we have.
+ switch (Lexer.getKind()) {
+ case AsmToken::Colon: {
+ // identifier ':' -> Label.
+ Lex();
+
+ // Diagnose attempt to use a variable as a label.
+ //
+ // FIXME: Diagnostics. Note the location of the definition as a label.
+ // FIXME: This doesn't diagnose assignment to a symbol which has been
+ // implicitly marked as external.
+ MCSymbol *Sym = CreateSymbol(IDVal);
+ if (!Sym->isUndefined())
+ return Error(IDLoc, "invalid symbol redefinition");
+
+ // Emit the label.
+ Out.EmitLabel(Sym);
+
+ return ParseStatement();
+ }
+
+ case AsmToken::Equal:
+ // identifier '=' ... -> assignment statement
+ Lex();
+
+ return ParseAssignment(IDVal);
+
+ default: // Normal instruction or directive.
+ break;
+ }
+
+ // 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();
+
+ // Data directives
+
+ if (IDVal == ".ascii")
+ return ParseDirectiveAscii(false);
+ if (IDVal == ".asciz")
+ return ParseDirectiveAscii(true);
+
+ if (IDVal == ".byte")
+ return ParseDirectiveValue(1);
+ if (IDVal == ".short")
+ 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 == ".balign")
+ return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/1);
+ if (IDVal == ".balignw")
+ return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/2);
+ if (IDVal == ".balignl")
+ return ParseDirectiveAlign(/*IsPow2=*/false, /*ExprSize=*/4);
+ if (IDVal == ".p2align")
+ return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/1);
+ if (IDVal == ".p2alignw")
+ return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/2);
+ if (IDVal == ".p2alignl")
+ return ParseDirectiveAlign(/*IsPow2=*/true, /*ExprSize=*/4);
+
+ if (IDVal == ".org")
+ return ParseDirectiveOrg();
+
+ if (IDVal == ".fill")
+ return ParseDirectiveFill();
+ if (IDVal == ".space")
+ return ParseDirectiveSpace();
+
+ // Symbol attribute directives
+
+ if (IDVal == ".globl" || IDVal == ".global")
+ return ParseDirectiveSymbolAttribute(MCSA_Global);
+ if (IDVal == ".hidden")
+ return ParseDirectiveSymbolAttribute(MCSA_Hidden);
+ if (IDVal == ".indirect_symbol")
+ return ParseDirectiveSymbolAttribute(MCSA_IndirectSymbol);
+ if (IDVal == ".internal")
+ return ParseDirectiveSymbolAttribute(MCSA_Internal);
+ if (IDVal == ".lazy_reference")
+ return ParseDirectiveSymbolAttribute(MCSA_LazyReference);
+ if (IDVal == ".no_dead_strip")
+ return ParseDirectiveSymbolAttribute(MCSA_NoDeadStrip);
+ if (IDVal == ".private_extern")
+ return ParseDirectiveSymbolAttribute(MCSA_PrivateExtern);
+ if (IDVal == ".protected")
+ return ParseDirectiveSymbolAttribute(MCSA_Protected);
+ if (IDVal == ".reference")
+ return ParseDirectiveSymbolAttribute(MCSA_Reference);
+ if (IDVal == ".weak")
+ return ParseDirectiveSymbolAttribute(MCSA_Weak);
+ if (IDVal == ".weak_definition")
+ return ParseDirectiveSymbolAttribute(MCSA_WeakDefinition);
+ if (IDVal == ".weak_reference")
+ return ParseDirectiveSymbolAttribute(MCSA_WeakReference);
+
+ 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);
+
+ // Target hook for parsing target specific directives.
+ if (!getTargetParser().ParseDirective(ID))
+ return false;
+
+ Warning(IDLoc, "ignoring directive for now");
+ EatToEndOfStatement();
+ return false;
+ }
+
+
+ SmallVector<MCParsedAsmOperand*, 8> ParsedOperands;
+ if (getTargetParser().ParseInstruction(IDVal, IDLoc, ParsedOperands))
+ // FIXME: Leaking ParsedOperands on failure.
+ return true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ // FIXME: Leaking ParsedOperands on failure.
+ return TokError("unexpected token in argument list");
+
+ // Eat the end of statement marker.
+ Lex();
+
+
+ MCInst Inst;
+
+ bool MatchFail = getTargetParser().MatchInstruction(ParsedOperands, Inst);
+
+ // Free any parsed operands.
+ for (unsigned i = 0, e = ParsedOperands.size(); i != e; ++i)
+ delete ParsedOperands[i];
+
+ if (MatchFail) {
+ // FIXME: We should give nicer diagnostics about the exact failure.
+ Error(IDLoc, "unrecognized instruction");
+ return true;
+ }
+
+ // Instruction is good, process it.
+ Out.EmitInstruction(Inst);
+
+ // Skip to end of line for now.
+ return false;
+}
+
+bool AsmParser::ParseAssignment(const 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");
+
+ // Eat the end of statement marker.
+ Lex();
+
+ // Validate that the LHS is allowed to be a variable (either it has not been
+ // used as a symbol, or it is an absolute symbol).
+ MCSymbol *Sym = getContext().LookupSymbol(Name);
+ if (Sym) {
+ // Diagnose assignment to a label.
+ //
+ // FIXME: Diagnostics. Note the location of the definition as a label.
+ // FIXME: Diagnose assignment to protected identifier (e.g., register name).
+ if (!Sym->isUndefined() && !Sym->isAbsolute())
+ return Error(EqualLoc, "redefinition of '" + Name + "'");
+ else if (!Sym->isVariable())
+ return Error(EqualLoc, "invalid assignment to '" + Name + "'");
+ else if (!isa<MCConstantExpr>(Sym->getValue()))
+ return Error(EqualLoc, "invalid reassignment of non-absolute variable '" +
+ Name + "'");
+ } else
+ Sym = CreateSymbol(Name);
+
+ // FIXME: Handle '.'.
+
+ // Do the assignment.
+ Out.EmitAssignment(Sym, Value);
+
+ return false;
+}
+
+/// ParseIdentifier:
+/// ::= identifier
+/// ::= string
+bool AsmParser::ParseIdentifier(StringRef &Res) {
+ if (Lexer.isNot(AsmToken::Identifier) &&
+ Lexer.isNot(AsmToken::String))
+ return true;
+
+ Res = getTok().getIdentifier();
+
+ Lex(); // Consume the identifier token.
+
+ return false;
+}
+
+/// ParseDirectiveSet:
+/// ::= .set identifier ',' expression
+bool AsmParser::ParseDirectiveSet() {
+ StringRef Name;
+
+ if (ParseIdentifier(Name))
+ return TokError("expected identifier after '.set' directive");
+
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in '.set'");
+ 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");
+
+ // Verify there is a following comma.
+ if (!Lexer.is(AsmToken::Comma))
+ return TokError("unexpected token in '.section' directive");
+
+ std::string SectionSpec = SectionName;
+ SectionSpec += ",";
+
+ // Add all the tokens until the end of the line, ParseSectionSpecifier will
+ // handle this.
+ StringRef EOL = 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.
+ Out.SwitchSection(getMachOSection(Segment, Section, TAA, StubSize,
+ SectionKind()));
+ 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.
+ Out.SwitchSection(getMachOSection(Segment, Section, TAA, StubSize,
+ SectionKind()));
+
+ // 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 octal sequences.
+ if ((unsigned) (Str[i] - '0') <= 7) {
+ // Consume up to three octal characters.
+ unsigned Value = Str[i] - '0';
+
+ if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) {
+ ++i;
+ Value = Value * 8 + (Str[i] - '0');
+
+ if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) {
+ ++i;
+ Value = Value * 8 + (Str[i] - '0');
+ }
+ }
+
+ if (Value > 255)
+ return TokError("invalid octal escape sequence (out of range)");
+
+ Data += (unsigned char) Value;
+ continue;
+ }
+
+ // Otherwise recognize individual escapes.
+ switch (Str[i]) {
+ default:
+ // Just reject invalid escape sequences for now.
+ return TokError("invalid escape sequence (unrecognized character)");
+
+ case 'b': Data += '\b'; break;
+ case 'f': Data += '\f'; break;
+ case 'n': Data += '\n'; break;
+ case 'r': Data += '\r'; break;
+ case 't': Data += '\t'; break;
+ case '"': Data += '"'; break;
+ case '\\': Data += '\\'; break;
+ }
+ }
+
+ return false;
+}
+
+/// ParseDirectiveAscii:
+/// ::= ( .ascii | .asciz ) [ "string" ( , "string" )* ]
+bool AsmParser::ParseDirectiveAscii(bool ZeroTerminated) {
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ for (;;) {
+ if (Lexer.isNot(AsmToken::String))
+ return TokError("expected string in '.ascii' or '.asciz' directive");
+
+ std::string Data;
+ if (ParseEscapedString(Data))
+ return true;
+
+ Out.EmitBytes(Data, DEFAULT_ADDRSPACE);
+ if (ZeroTerminated)
+ Out.EmitBytes(StringRef("\0", 1), DEFAULT_ADDRSPACE);
+
+ Lex();
+
+ if (Lexer.is(AsmToken::EndOfStatement))
+ break;
+
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in '.ascii' or '.asciz' directive");
+ Lex();
+ }
+ }
+
+ Lex();
+ return false;
+}
+
+/// ParseDirectiveValue
+/// ::= (.byte | .short | ... ) [ expression (, expression)* ]
+bool AsmParser::ParseDirectiveValue(unsigned Size) {
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ for (;;) {
+ const MCExpr *Value;
+ SMLoc ATTRIBUTE_UNUSED StartLoc = Lexer.getLoc();
+ if (ParseExpression(Value))
+ return true;
+
+ Out.EmitValue(Value, Size, DEFAULT_ADDRSPACE);
+
+ if (Lexer.is(AsmToken::EndOfStatement))
+ break;
+
+ // FIXME: Improve diagnostic.
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in directive");
+ Lex();
+ }
+ }
+
+ Lex();
+ return false;
+}
+
+/// ParseDirectiveSpace
+/// ::= .space expression [ , expression ]
+bool AsmParser::ParseDirectiveSpace() {
+ 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))
+ return TokError("unexpected token in '.space' directive");
+ Lex();
+
+ if (ParseAbsoluteExpression(FillExpr))
+ return true;
+
+ HasFillExpr = true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.space' directive");
+ }
+
+ Lex();
+
+ if (NumBytes <= 0)
+ return TokError("invalid number of bytes in '.space' directive");
+
+ // FIXME: Sometimes the fill expr is 'nop' if it isn't supplied, instead of 0.
+ Out.EmitFill(NumBytes, FillExpr, DEFAULT_ADDRSPACE);
+
+ return false;
+}
+
+/// ParseDirectiveFill
+/// ::= .fill expression , expression , expression
+bool AsmParser::ParseDirectiveFill() {
+ int64_t NumValues;
+ if (ParseAbsoluteExpression(NumValues))
+ return true;
+
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in '.fill' directive");
+ Lex();
+
+ int64_t FillSize;
+ if (ParseAbsoluteExpression(FillSize))
+ return true;
+
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in '.fill' directive");
+ Lex();
+
+ int64_t FillExpr;
+ if (ParseAbsoluteExpression(FillExpr))
+ return true;
+
+ if (Lexer.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);
+
+ return false;
+}
+
+/// ParseDirectiveOrg
+/// ::= .org expression [ , expression ]
+bool AsmParser::ParseDirectiveOrg() {
+ 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))
+ return TokError("unexpected token in '.org' directive");
+ Lex();
+
+ if (ParseAbsoluteExpression(FillExpr))
+ return true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.org' directive");
+ }
+
+ Lex();
+
+ // FIXME: Only limited forms of relocatable expressions are accepted here, it
+ // has to be relative to the current section.
+ Out.EmitValueToOffset(Offset, FillExpr);
+
+ return false;
+}
+
+/// ParseDirectiveAlign
+/// ::= {.align, ...} expression [ , expression [ , expression ]]
+bool AsmParser::ParseDirectiveAlign(bool IsPow2, unsigned ValueSize) {
+ SMLoc AlignmentLoc = Lexer.getLoc();
+ int64_t Alignment;
+ if (ParseAbsoluteExpression(Alignment))
+ return true;
+
+ SMLoc MaxBytesLoc;
+ bool HasFillExpr = false;
+ int64_t FillExpr = 0;
+ int64_t MaxBytesToFill = 0;
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (Lexer.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)) {
+ HasFillExpr = true;
+ if (ParseAbsoluteExpression(FillExpr))
+ return true;
+ }
+
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (Lexer.isNot(AsmToken::Comma))
+ return TokError("unexpected token in directive");
+ Lex();
+
+ MaxBytesLoc = Lexer.getLoc();
+ if (ParseAbsoluteExpression(MaxBytesToFill))
+ return true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in directive");
+ }
+ }
+
+ Lex();
+
+ if (!HasFillExpr) {
+ // FIXME: Sometimes fill with nop.
+ FillExpr = 0;
+ }
+
+ // Compute alignment in bytes.
+ if (IsPow2) {
+ // FIXME: Diagnose overflow.
+ if (Alignment >= 32) {
+ Error(AlignmentLoc, "invalid alignment value");
+ Alignment = 31;
+ }
+
+ Alignment = 1ULL << Alignment;
+ }
+
+ // Diagnose non-sensical max bytes to align.
+ if (MaxBytesLoc.isValid()) {
+ if (MaxBytesToFill < 1) {
+ Error(MaxBytesLoc, "alignment directive can never be satisfied in this "
+ "many bytes, ignoring maximum bytes expression");
+ MaxBytesToFill = 0;
+ }
+
+ if (MaxBytesToFill >= Alignment) {
+ Warning(MaxBytesLoc, "maximum bytes expression exceeds alignment and "
+ "has no effect");
+ MaxBytesToFill = 0;
+ }
+ }
+
+ // FIXME: Target specific behavior about how the "extra" bytes are filled.
+ Out.EmitValueToAlignment(Alignment, FillExpr, ValueSize, MaxBytesToFill);
+
+ return false;
+}
+
+/// ParseDirectiveSymbolAttribute
+/// ::= { ".globl", ".weak", ... } [ identifier ( , identifier )* ]
+bool AsmParser::ParseDirectiveSymbolAttribute(MCSymbolAttr Attr) {
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ for (;;) {
+ StringRef Name;
+
+ if (ParseIdentifier(Name))
+ return TokError("expected identifier in directive");
+
+ MCSymbol *Sym = CreateSymbol(Name);
+
+ Out.EmitSymbolAttribute(Sym, Attr);
+
+ if (Lexer.is(AsmToken::EndOfStatement))
+ break;
+
+ if (Lexer.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();
+ 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 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 this target takes alignments in bytes (not log) validate and convert.
+ if (Lexer.getMAI().getAlignmentIsInBytes()) {
+ if (!isPowerOf2_64(Pow2Alignment))
+ return Error(Pow2AlignmentLoc, "alignment must be a power of 2");
+ Pow2Alignment = Log2_64(Pow2Alignment);
+ }
+ }
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.comm' or '.lcomm' directive");
+
+ Lex();
+
+ // NOTE: a size of zero for a .comm should create a undefined symbol
+ // but a size of .lcomm creates a bss symbol of size zero.
+ if (Size < 0)
+ return Error(SizeLoc, "invalid '.comm' or '.lcomm' directive size, can't "
+ "be less than zero");
+
+ // NOTE: The alignment in the directive is a power of 2 value, the assember
+ // may internally end up wanting an alignment in bytes.
+ // FIXME: Diagnose overflow.
+ if (Pow2Alignment < 0)
+ return Error(Pow2AlignmentLoc, "invalid '.comm' or '.lcomm' directive "
+ "alignment, can't be less than zero");
+
+ if (!Sym->isUndefined())
+ return Error(IDLoc, "invalid symbol redefinition");
+
+ // '.lcomm' is equivalent to '.zerofill'.
+ // Create the Symbol as a common or local common with Size and Pow2Alignment
+ if (IsLocal) {
+ Out.EmitZerofill(getMachOSection("__DATA", "__bss",
+ MCSectionMachO::S_ZEROFILL, 0,
+ SectionKind()),
+ 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(getMachOSection(Segment, Section,
+ MCSectionMachO::S_ZEROFILL, 0,
+ SectionKind()));
+ 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(getMachOSection(Segment, Section,
+ MCSectionMachO::S_ZEROFILL, 0,
+ SectionKind()),
+ 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);
+
+ return false;
+}
+
+/// ParseDirectiveAbort
+/// ::= .abort [ "abort_string" ]
+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();
+ }
+
+ if (Lexer.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.");
+
+ 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))
+ return TokError("expected string in '.include' directive");
+
+ std::string Filename = getTok().getString();
+ SMLoc IncludeLoc = Lexer.getLoc();
+ Lex();
+
+ if (Lexer.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");
+ 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) {
+ // Consume the identifier that was the .if directive
+ Lex();
+
+ TheCondStack.push_back(TheCondState);
+ TheCondState.TheCond = AsmCond::IfCond;
+ if(TheCondState.Ignore) {
+ EatToEndOfStatement();
+ }
+ else {
+ int64_t ExprValue;
+ if (ParseAbsoluteExpression(ExprValue))
+ return true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.if' directive");
+
+ Lex();
+
+ TheCondState.CondMet = ExprValue;
+ TheCondState.Ignore = !TheCondState.CondMet;
+ }
+
+ return false;
+}
+
+/// ParseDirectiveElseIf
+/// ::= .elseif expression
+bool AsmParser::ParseDirectiveElseIf(SMLoc DirectiveLoc) {
+ if (TheCondState.TheCond != AsmCond::IfCond &&
+ TheCondState.TheCond != AsmCond::ElseIfCond)
+ Error(DirectiveLoc, "Encountered a .elseif that doesn't follow a .if or "
+ " an .elseif");
+ TheCondState.TheCond = AsmCond::ElseIfCond;
+
+ // Consume the identifier that was the .elseif directive
+ Lex();
+
+ bool LastIgnoreState = false;
+ if (!TheCondStack.empty())
+ LastIgnoreState = TheCondStack.back().Ignore;
+ if (LastIgnoreState || TheCondState.CondMet) {
+ TheCondState.Ignore = true;
+ EatToEndOfStatement();
+ }
+ else {
+ int64_t ExprValue;
+ if (ParseAbsoluteExpression(ExprValue))
+ return true;
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.elseif' directive");
+
+ Lex();
+ TheCondState.CondMet = ExprValue;
+ TheCondState.Ignore = !TheCondState.CondMet;
+ }
+
+ return false;
+}
+
+/// ParseDirectiveElse
+/// ::= .else
+bool AsmParser::ParseDirectiveElse(SMLoc DirectiveLoc) {
+ // Consume the identifier that was the .else directive
+ Lex();
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.else' directive");
+
+ Lex();
+
+ if (TheCondState.TheCond != AsmCond::IfCond &&
+ TheCondState.TheCond != AsmCond::ElseIfCond)
+ Error(DirectiveLoc, "Encountered a .else that doesn't follow a .if or an "
+ ".elseif");
+ TheCondState.TheCond = AsmCond::ElseCond;
+ bool LastIgnoreState = false;
+ if (!TheCondStack.empty())
+ LastIgnoreState = TheCondStack.back().Ignore;
+ if (LastIgnoreState || TheCondState.CondMet)
+ TheCondState.Ignore = true;
+ else
+ TheCondState.Ignore = false;
+
+ return false;
+}
+
+/// ParseDirectiveEndIf
+/// ::= .endif
+bool AsmParser::ParseDirectiveEndIf(SMLoc DirectiveLoc) {
+ // Consume the identifier that was the .endif directive
+ Lex();
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.endif' directive");
+
+ Lex();
+
+ if ((TheCondState.TheCond == AsmCond::NoCond) ||
+ TheCondStack.empty())
+ Error(DirectiveLoc, "Encountered a .endif that doesn't follow a .if or "
+ ".else");
+ if (!TheCondStack.empty()) {
+ TheCondState = TheCondStack.back();
+ TheCondStack.pop_back();
+ }
+
+ return false;
+}
+
+/// ParseDirectiveFile
+/// ::= .file [number] string
+bool AsmParser::ParseDirectiveFile(StringRef, SMLoc DirectiveLoc) {
+ // FIXME: I'm not sure what this is.
+ int64_t FileNumber = -1;
+ if (Lexer.is(AsmToken::Integer)) {
+ FileNumber = getTok().getIntVal();
+ Lex();
+
+ if (FileNumber < 1)
+ return TokError("file number less than one");
+ }
+
+ if (Lexer.isNot(AsmToken::String))
+ return TokError("unexpected token in '.file' directive");
+
+ StringRef ATTRIBUTE_UNUSED FileName = getTok().getString();
+ Lex();
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.file' directive");
+
+ // FIXME: Do something with the .file.
+
+ return false;
+}
+
+/// ParseDirectiveLine
+/// ::= .line [number]
+bool AsmParser::ParseDirectiveLine(StringRef, SMLoc DirectiveLoc) {
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (Lexer.isNot(AsmToken::Integer))
+ return TokError("unexpected token in '.line' directive");
+
+ int64_t LineNumber = getTok().getIntVal();
+ (void) LineNumber;
+ Lex();
+
+ // FIXME: Do something with the .line.
+ }
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.file' directive");
+
+ return false;
+}
+
+
+/// ParseDirectiveLoc
+/// ::= .loc number [number [number]]
+bool AsmParser::ParseDirectiveLoc(StringRef, SMLoc DirectiveLoc) {
+ if (Lexer.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.
+
+ 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;
+ Lex();
+
+ if (Lexer.isNot(AsmToken::EndOfStatement)) {
+ if (Lexer.isNot(AsmToken::Integer))
+ return TokError("unexpected token in '.loc' directive");
+
+ int64_t Param3 = getTok().getIntVal();
+ (void) Param3;
+ Lex();
+
+ // FIXME: Do something with the .loc.
+ }
+ }
+
+ if (Lexer.isNot(AsmToken::EndOfStatement))
+ return TokError("unexpected token in '.file' directive");
+
+ return false;
+}
+
diff --git a/lib/MC/MCParser/CMakeLists.txt b/lib/MC/MCParser/CMakeLists.txt
new file mode 100644
index 0000000..a5c0818
--- /dev/null
+++ b/lib/MC/MCParser/CMakeLists.txt
@@ -0,0 +1,7 @@
+add_llvm_library(LLVMMCParser
+ AsmLexer.cpp
+ AsmParser.cpp
+ MCAsmLexer.cpp
+ MCAsmParser.cpp
+ TargetAsmParser.cpp
+ )
diff --git a/lib/MC/MCAsmLexer.cpp b/lib/MC/MCParser/MCAsmLexer.cpp
index 1e34ed6..e5b2955 100644
--- a/lib/MC/MCAsmLexer.cpp
+++ b/lib/MC/MCParser/MCAsmLexer.cpp
@@ -7,7 +7,7 @@
//
//===----------------------------------------------------------------------===//
-#include "llvm/MC/MCAsmLexer.h"
+#include "llvm/MC/MCParser/MCAsmLexer.h"
#include "llvm/Support/SourceMgr.h"
using namespace llvm;
diff --git a/lib/MC/MCParser/MCAsmParser.cpp b/lib/MC/MCParser/MCAsmParser.cpp
new file mode 100644
index 0000000..b8c2054
--- /dev/null
+++ b/lib/MC/MCParser/MCAsmParser.cpp
@@ -0,0 +1,35 @@
+//===-- MCAsmParser.cpp - Abstract Asm Parser Interface -------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCParser/MCAsmParser.h"
+#include "llvm/MC/MCParser/MCAsmLexer.h"
+#include "llvm/MC/MCParser/MCParsedAsmOperand.h"
+#include "llvm/Support/SourceMgr.h"
+using namespace llvm;
+
+MCAsmParser::MCAsmParser() {
+}
+
+MCAsmParser::~MCAsmParser() {
+}
+
+const AsmToken &MCAsmParser::getTok() {
+ return getLexer().getTok();
+}
+
+bool MCAsmParser::ParseExpression(const MCExpr *&Res) {
+ SMLoc L;
+ return ParseExpression(Res, L);
+}
+
+/// getStartLoc - Get the location of the first token of this operand.
+SMLoc MCParsedAsmOperand::getStartLoc() const { return SMLoc(); }
+SMLoc MCParsedAsmOperand::getEndLoc() const { return SMLoc(); }
+
+
diff --git a/lib/MC/MCParser/Makefile b/lib/MC/MCParser/Makefile
new file mode 100644
index 0000000..e4eb483
--- /dev/null
+++ b/lib/MC/MCParser/Makefile
@@ -0,0 +1,16 @@
+##===- lib/MC/MCParser/Makefile ----------------------------*- Makefile -*-===##
+#
+# The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+#
+##===----------------------------------------------------------------------===##
+
+LEVEL = ../../..
+LIBRARYNAME = LLVMMCParser
+BUILD_ARCHIVE := 1
+CXXFLAGS = -fno-rtti
+
+include $(LEVEL)/Makefile.common
+
diff --git a/lib/MC/TargetAsmParser.cpp b/lib/MC/MCParser/TargetAsmParser.cpp
index 05760c9..05760c9 100644
--- a/lib/MC/TargetAsmParser.cpp
+++ b/lib/MC/MCParser/TargetAsmParser.cpp
diff --git a/lib/MC/MCSectionELF.cpp b/lib/MC/MCSectionELF.cpp
index 4d520ec..ebfe269 100644
--- a/lib/MC/MCSectionELF.cpp
+++ b/lib/MC/MCSectionELF.cpp
@@ -22,14 +22,12 @@ Create(StringRef Section, unsigned Type, unsigned Flags,
// ShouldOmitSectionDirective - Decides whether a '.section' directive
// should be printed before the section name
-bool MCSectionELF::ShouldOmitSectionDirective(const char *Name,
+bool MCSectionELF::ShouldOmitSectionDirective(StringRef Name,
const MCAsmInfo &MAI) const {
// FIXME: Does .section .bss/.data/.text work everywhere??
- if (strcmp(Name, ".text") == 0 ||
- strcmp(Name, ".data") == 0 ||
- (strcmp(Name, ".bss") == 0 &&
- !MAI.usesELFSectionDirectiveForBSS()))
+ if (Name == ".text" || Name == ".data" ||
+ (Name == ".bss" && !MAI.usesELFSectionDirectiveForBSS()))
return true;
return false;
@@ -46,7 +44,7 @@ bool MCSectionELF::ShouldPrintSectionType(unsigned Ty) const {
void MCSectionELF::PrintSwitchToSection(const MCAsmInfo &MAI,
raw_ostream &OS) const {
- if (ShouldOmitSectionDirective(SectionName.c_str(), MAI)) {
+ if (ShouldOmitSectionDirective(SectionName, MAI)) {
OS << '\t' << getSectionName() << '\n';
return;
}
@@ -128,7 +126,7 @@ void MCSectionELF::PrintSwitchToSection(const MCAsmInfo &MAI,
// header index.
bool MCSectionELF::HasCommonSymbols() const {
- if (strncmp(SectionName.c_str(), ".gnu.linkonce.", 14) == 0)
+ if (StringRef(SectionName).startswith(".gnu.linkonce."))
return true;
return false;
diff --git a/lib/MC/MCStreamer.cpp b/lib/MC/MCStreamer.cpp
index 8a6dcda..15b3079 100644
--- a/lib/MC/MCStreamer.cpp
+++ b/lib/MC/MCStreamer.cpp
@@ -8,7 +8,8 @@
//===----------------------------------------------------------------------===//
#include "llvm/MC/MCStreamer.h"
-
+#include "llvm/MC/MCExpr.h"
+#include "llvm/Support/raw_ostream.h"
using namespace llvm;
MCStreamer::MCStreamer(MCContext &_Context) : Context(_Context), CurSection(0) {
@@ -16,3 +17,25 @@ MCStreamer::MCStreamer(MCContext &_Context) : Context(_Context), CurSection(0) {
MCStreamer::~MCStreamer() {
}
+
+raw_ostream &MCStreamer::GetCommentOS() {
+ // By default, discard comments.
+ return nulls();
+}
+
+
+/// EmitIntValue - Special case of EmitValue that avoids the client having to
+/// pass in a MCExpr for constant integers.
+void MCStreamer::EmitIntValue(uint64_t Value, unsigned Size,
+ unsigned AddrSpace) {
+ EmitValue(MCConstantExpr::Create(Value, getContext()), Size, AddrSpace);
+}
+
+/// EmitFill - Emit NumBytes bytes worth of the value specified by
+/// FillValue. This implements directives such as '.space'.
+void MCStreamer::EmitFill(uint64_t NumBytes, uint8_t FillValue,
+ unsigned AddrSpace) {
+ const MCExpr *E = MCConstantExpr::Create(FillValue, getContext());
+ for (uint64_t i = 0, e = NumBytes; i != e; ++i)
+ EmitValue(E, 1, AddrSpace);
+}
diff --git a/lib/MC/MCSymbol.cpp b/lib/MC/MCSymbol.cpp
index 265d06c..3fb1233 100644
--- a/lib/MC/MCSymbol.cpp
+++ b/lib/MC/MCSymbol.cpp
@@ -8,7 +8,6 @@
//===----------------------------------------------------------------------===//
#include "llvm/MC/MCSymbol.h"
-#include "llvm/MC/MCAsmInfo.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
@@ -26,24 +25,11 @@ static bool isAcceptableChar(char C) {
return true;
}
-static char HexDigit(int V) {
- return V < 10 ? V+'0' : V+'A'-10;
-}
-
-static void MangleLetter(raw_ostream &OS, unsigned char C) {
- OS << '_' << HexDigit(C >> 4) << HexDigit(C & 15) << '_';
-}
-
-/// NameNeedsEscaping - Return true if the identifier \arg Str needs quotes
-/// for this assembler.
-static bool NameNeedsEscaping(StringRef Str, const MCAsmInfo &MAI) {
+/// NameNeedsQuoting - Return true if the identifier \arg Str needs quotes to be
+/// syntactically correct.
+static bool NameNeedsQuoting(StringRef Str) {
assert(!Str.empty() && "Cannot create an empty MCSymbol");
- // If the first character is a number and the target does not allow this, we
- // need quotes.
- if (!MAI.doesAllowNameToStartWithDigit() && Str[0] >= '0' && Str[0] <= '9')
- return true;
-
// If any of the characters in the string is an unacceptable character, force
// quotes.
for (unsigned i = 0, e = Str.size(); i != e; ++i)
@@ -52,63 +38,18 @@ static bool NameNeedsEscaping(StringRef Str, const MCAsmInfo &MAI) {
return false;
}
-/// printMangledName - Print the specified string in mangled form if it uses
-/// any unusual characters.
-void MCSymbol::printMangledName(StringRef Str, raw_ostream &OS,
- const MCAsmInfo *MAI) {
- // The first character is not allowed to be a number unless the target
- // explicitly allows it.
- if ((MAI == 0 || !MAI->doesAllowNameToStartWithDigit()) &&
- Str[0] >= '0' && Str[0] <= '9') {
- MangleLetter(OS, Str[0]);
- Str = Str.substr(1);
- }
-
- for (unsigned i = 0, e = Str.size(); i != e; ++i) {
- if (!isAcceptableChar(Str[i]))
- MangleLetter(OS, Str[i]);
- else
- OS << Str[i];
- }
-}
-
-/// PrintMangledQuotedName - On systems that support quoted symbols, we still
-/// have to escape some (obscure) characters like " and \n which would break the
-/// assembler's lexing.
-static void PrintMangledQuotedName(raw_ostream &OS, StringRef Str) {
- OS << '"';
-
- for (unsigned i = 0, e = Str.size(); i != e; ++i) {
- if (Str[i] == '"')
- OS << "_QQ_";
- else if (Str[i] == '\n')
- OS << "_NL_";
- else
- OS << Str[i];
- }
- OS << '"';
-}
-
-
-void MCSymbol::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
- if (MAI == 0 || !NameNeedsEscaping(getName(), *MAI)) {
+void MCSymbol::print(raw_ostream &OS) const {
+ // The name for this MCSymbol is required to be a valid target name. However,
+ // some targets support quoting names with funny characters. If the name
+ // contains a funny character, then print it quoted.
+ if (!NameNeedsQuoting(getName())) {
OS << getName();
return;
}
-
- // On systems that do not allow quoted names, print with mangling.
- if (!MAI->doesAllowQuotesInName())
- return printMangledName(getName(), OS, MAI);
-
- // If the string contains a double quote or newline, we still have to mangle
- // it.
- if (getName().find('"') != std::string::npos ||
- getName().find('\n') != std::string::npos)
- return PrintMangledQuotedName(OS, getName());
OS << '"' << getName() << '"';
}
void MCSymbol::dump() const {
- print(dbgs(), 0);
+ print(dbgs());
}
diff --git a/lib/MC/MCValue.cpp b/lib/MC/MCValue.cpp
index c1222ec..043a49d 100644
--- a/lib/MC/MCValue.cpp
+++ b/lib/MC/MCValue.cpp
@@ -19,12 +19,10 @@ void MCValue::print(raw_ostream &OS, const MCAsmInfo *MAI) const {
return;
}
- getSymA()->print(OS, MAI);
+ OS << *getSymA();
- if (getSymB()) {
- OS << " - ";
- getSymB()->print(OS, MAI);
- }
+ if (getSymB())
+ OS << " - " << *getSymB();
if (getConstant())
OS << " + " << getConstant();
diff --git a/lib/MC/Makefile b/lib/MC/Makefile
index 314a5b1..371776f 100644
--- a/lib/MC/Makefile
+++ b/lib/MC/Makefile
@@ -10,6 +10,8 @@
LEVEL = ../..
LIBRARYNAME = LLVMMC
BUILD_ARCHIVE := 1
+PARALLEL_DIRS := MCParser
+CXXFLAGS = -fno-rtti
include $(LEVEL)/Makefile.common
OpenPOWER on IntegriCloud