//
//===----------------------------------------------------------------------===//
+#include "llvm/MC/MCParser/AsmLexer.h"
+#include "llvm/MC/MCParser/MCAsmLexer.h"
#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCCodeEmitter.h"
+#include "llvm/MC/MCInstPrinter.h"
+#include "llvm/MC/MCSectionMachO.h"
#include "llvm/MC/MCStreamer.h"
+#include "llvm/Target/TargetAsmBackend.h"
+#include "llvm/Target/TargetAsmParser.h"
+#include "llvm/Target/TargetData.h"
+#include "llvm/Target/TargetRegistry.h"
+#include "llvm/Target/SubtargetFeature.h" // FIXME.
+#include "llvm/Target/TargetMachine.h" // FIXME.
+#include "llvm/Target/TargetSelect.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/FileUtilities.h"
+#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/PrettyStackTrace.h"
#include "llvm/Support/SourceMgr.h"
-#include "llvm/Support/raw_ostream.h"
-#include "llvm/System/Signals.h"
-#include "AsmParser.h"
+#include "llvm/Support/ToolOutputFile.h"
+#include "llvm/Support/Host.h"
+#include "llvm/Support/Signals.h"
+#include "llvm/Support/system_error.h"
+#include "Disassembler.h"
using namespace llvm;
static cl::opt<std::string>
OutputFilename("o", cl::desc("Output filename"),
cl::value_desc("filename"));
+static cl::opt<bool>
+ShowEncoding("show-encoding", cl::desc("Show instruction encodings"));
+
+static cl::opt<bool>
+ShowInst("show-inst", cl::desc("Show internal instruction representation"));
+
+static cl::opt<bool>
+ShowInstOperands("show-inst-operands",
+ cl::desc("Show instructions operands as parsed"));
+
+static cl::opt<unsigned>
+OutputAsmVariant("output-asm-variant",
+ cl::desc("Syntax variant to use for output printing"));
+
+static cl::opt<bool>
+RelaxAll("mc-relax-all", cl::desc("Relax all fixups"));
+
+static cl::opt<bool>
+EnableLogging("enable-api-logging", cl::desc("Enable MC API logging"));
+
+enum OutputFileType {
+ OFT_Null,
+ OFT_AssemblyFile,
+ OFT_ObjectFile
+};
+static cl::opt<OutputFileType>
+FileType("filetype", cl::init(OFT_AssemblyFile),
+ cl::desc("Choose an output file type:"),
+ cl::values(
+ clEnumValN(OFT_AssemblyFile, "asm",
+ "Emit an assembly ('.s') file"),
+ clEnumValN(OFT_Null, "null",
+ "Don't emit anything (for timing purposes)"),
+ clEnumValN(OFT_ObjectFile, "obj",
+ "Emit a native object ('.o') file"),
+ clEnumValEnd));
+
static cl::list<std::string>
IncludeDirs("I", cl::desc("Directory of include files"),
cl::value_desc("directory"), cl::Prefix);
+static cl::opt<std::string>
+ArchName("arch", cl::desc("Target arch to assemble for, "
+ "see -version for available targets"));
+
+static cl::opt<std::string>
+TripleName("triple", cl::desc("Target triple to assemble for, "
+ "see -version for available targets"));
+
+static cl::opt<std::string>
+MCPU("mcpu",
+ cl::desc("Target a specific cpu type (-mcpu=help for details)"),
+ cl::value_desc("cpu-name"),
+ cl::init(""));
+
+static cl::opt<bool>
+NoInitialTextSection("n", cl::desc(
+ "Don't assume assembly file starts in the text section"));
+
enum ActionType {
AC_AsLex,
- AC_Assemble
+ AC_Assemble,
+ AC_Disassemble,
+ AC_EDisassemble
};
static cl::opt<ActionType>
"Lex tokens from a .s file"),
clEnumValN(AC_Assemble, "assemble",
"Assemble a .s file (default)"),
+ clEnumValN(AC_Disassemble, "disassemble",
+ "Disassemble strings of hex bytes"),
+ clEnumValN(AC_EDisassemble, "edis",
+ "Enhanced disassembly of strings of hex bytes"),
clEnumValEnd));
+static const Target *GetTarget(const char *ProgName) {
+ // Figure out the target triple.
+ if (TripleName.empty())
+ TripleName = sys::getHostTriple();
+ if (!ArchName.empty()) {
+ llvm::Triple TT(TripleName);
+ TT.setArchName(ArchName);
+ TripleName = TT.str();
+ }
+
+ // Get the target specific parser.
+ std::string Error;
+ const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error);
+ if (TheTarget)
+ return TheTarget;
+
+ errs() << ProgName << ": error: unable to get target for '" << TripleName
+ << "', see --version and --triple.\n";
+ return 0;
+}
+
+static tool_output_file *GetOutputStream() {
+ if (OutputFilename == "")
+ OutputFilename = "-";
+
+ std::string Err;
+ tool_output_file *Out = new tool_output_file(OutputFilename.c_str(), Err,
+ raw_fd_ostream::F_Binary);
+ if (!Err.empty()) {
+ errs() << Err << '\n';
+ delete Out;
+ return 0;
+ }
+
+ return Out;
+}
+
static int AsLexInput(const char *ProgName) {
- std::string ErrorMessage;
- MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename,
- &ErrorMessage);
+ error_code ec;
+ MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename, ec);
if (Buffer == 0) {
- errs() << ProgName << ": ";
- if (ErrorMessage.size())
- errs() << ErrorMessage << "\n";
- else
- errs() << "input file didn't read correctly.\n";
+ errs() << ProgName << ": " << ec.message() << '\n';
return 1;
}
// it later.
SrcMgr.setIncludeDirs(IncludeDirs);
- AsmLexer Lexer(SrcMgr);
-
+ const Target *TheTarget = GetTarget(ProgName);
+ if (!TheTarget)
+ return 1;
+
+ llvm::OwningPtr<MCAsmInfo> MAI(TheTarget->createAsmInfo(TripleName));
+ assert(MAI && "Unable to create target asm info!");
+
+ AsmLexer Lexer(*MAI);
+ Lexer.setBuffer(SrcMgr.getMemoryBuffer(0));
+
+ OwningPtr<tool_output_file> Out(GetOutputStream());
+ if (!Out)
+ return 1;
+
bool Error = false;
-
- asmtok::TokKind Tok = Lexer.Lex();
- while (Tok != asmtok::Eof) {
- switch (Tok) {
+ while (Lexer.Lex().isNot(AsmToken::Eof)) {
+ AsmToken Tok = Lexer.getTok();
+
+ switch (Tok.getKind()) {
default:
- Lexer.PrintMessage(Lexer.getLoc(), "driver: unknown token");
+ SrcMgr.PrintMessage(Lexer.getLoc(), "unknown token", "warning");
Error = true;
break;
- case asmtok::Error:
+ case AsmToken::Error:
Error = true; // error already printed.
break;
- case asmtok::Identifier:
- outs() << "identifier: " << Lexer.getCurStrVal() << '\n';
+ case AsmToken::Identifier:
+ Out->os() << "identifier: " << Lexer.getTok().getString();
break;
- case asmtok::Register:
- outs() << "register: " << Lexer.getCurStrVal() << '\n';
+ case AsmToken::Integer:
+ Out->os() << "int: " << Lexer.getTok().getString();
break;
- case asmtok::String:
- outs() << "string: " << Lexer.getCurStrVal() << '\n';
+ case AsmToken::Real:
+ Out->os() << "real: " << Lexer.getTok().getString();
break;
- case asmtok::IntVal:
- outs() << "int: " << Lexer.getCurIntVal() << '\n';
+ case AsmToken::Register:
+ Out->os() << "register: " << Lexer.getTok().getRegVal();
break;
- case asmtok::EndOfStatement: outs() << "EndOfStatement\n"; break;
- case asmtok::Colon: outs() << "Colon\n"; break;
- case asmtok::Plus: outs() << "Plus\n"; break;
- case asmtok::Minus: outs() << "Minus\n"; break;
- case asmtok::Tilde: outs() << "Tilde\n"; break;
- case asmtok::Slash: outs() << "Slash\n"; break;
- case asmtok::LParen: outs() << "LParen\n"; break;
- case asmtok::RParen: outs() << "RParen\n"; break;
- case asmtok::Star: outs() << "Star\n"; break;
- case asmtok::Comma: outs() << "Comma\n"; break;
- case asmtok::Dollar: outs() << "Dollar\n"; break;
+ case AsmToken::String:
+ Out->os() << "string: " << Lexer.getTok().getString();
+ break;
+
+ case AsmToken::Amp: Out->os() << "Amp"; break;
+ case AsmToken::AmpAmp: Out->os() << "AmpAmp"; break;
+ case AsmToken::At: Out->os() << "At"; break;
+ case AsmToken::Caret: Out->os() << "Caret"; break;
+ case AsmToken::Colon: Out->os() << "Colon"; break;
+ case AsmToken::Comma: Out->os() << "Comma"; break;
+ case AsmToken::Dollar: Out->os() << "Dollar"; break;
+ case AsmToken::Dot: Out->os() << "Dot"; break;
+ case AsmToken::EndOfStatement: Out->os() << "EndOfStatement"; break;
+ case AsmToken::Eof: Out->os() << "Eof"; break;
+ case AsmToken::Equal: Out->os() << "Equal"; break;
+ case AsmToken::EqualEqual: Out->os() << "EqualEqual"; break;
+ case AsmToken::Exclaim: Out->os() << "Exclaim"; break;
+ case AsmToken::ExclaimEqual: Out->os() << "ExclaimEqual"; break;
+ case AsmToken::Greater: Out->os() << "Greater"; break;
+ case AsmToken::GreaterEqual: Out->os() << "GreaterEqual"; break;
+ case AsmToken::GreaterGreater: Out->os() << "GreaterGreater"; break;
+ case AsmToken::Hash: Out->os() << "Hash"; break;
+ case AsmToken::LBrac: Out->os() << "LBrac"; break;
+ case AsmToken::LCurly: Out->os() << "LCurly"; break;
+ case AsmToken::LParen: Out->os() << "LParen"; break;
+ case AsmToken::Less: Out->os() << "Less"; break;
+ case AsmToken::LessEqual: Out->os() << "LessEqual"; break;
+ case AsmToken::LessGreater: Out->os() << "LessGreater"; break;
+ case AsmToken::LessLess: Out->os() << "LessLess"; break;
+ case AsmToken::Minus: Out->os() << "Minus"; break;
+ case AsmToken::Percent: Out->os() << "Percent"; break;
+ case AsmToken::Pipe: Out->os() << "Pipe"; break;
+ case AsmToken::PipePipe: Out->os() << "PipePipe"; break;
+ case AsmToken::Plus: Out->os() << "Plus"; break;
+ case AsmToken::RBrac: Out->os() << "RBrac"; break;
+ case AsmToken::RCurly: Out->os() << "RCurly"; break;
+ case AsmToken::RParen: Out->os() << "RParen"; break;
+ case AsmToken::Slash: Out->os() << "Slash"; break;
+ case AsmToken::Star: Out->os() << "Star"; break;
+ case AsmToken::Tilde: Out->os() << "Tilde"; break;
}
-
- Tok = Lexer.Lex();
+
+ // Print the token string.
+ Out->os() << " (\"";
+ Out->os().write_escaped(Tok.getString());
+ Out->os() << "\")\n";
}
-
+
+ // Keep output if no errors.
+ if (Error == 0) Out->keep();
+
return Error;
}
static int AssembleInput(const char *ProgName) {
- std::string ErrorMessage;
- MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename,
- &ErrorMessage);
+ const Target *TheTarget = GetTarget(ProgName);
+ if (!TheTarget)
+ return 1;
+
+ error_code ec;
+ MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename, ec);
if (Buffer == 0) {
- errs() << ProgName << ": ";
- if (ErrorMessage.size())
- errs() << ErrorMessage << "\n";
- else
- errs() << "input file didn't read correctly.\n";
+ errs() << ProgName << ": " << ec.message() << '\n';
return 1;
}
SourceMgr SrcMgr;
- // Tell SrcMgr about this buffer, which is what TGParser will pick up.
+ // Tell SrcMgr about this buffer, which is what the parser will pick up.
SrcMgr.AddNewSourceBuffer(Buffer, SMLoc());
// Record the location of the include directories so that the lexer can find
// it later.
SrcMgr.setIncludeDirs(IncludeDirs);
- MCContext Ctx;
- OwningPtr<MCStreamer> Str(createAsmStreamer(Ctx, outs()));
+
+ llvm::OwningPtr<MCAsmInfo> MAI(TheTarget->createAsmInfo(TripleName));
+ assert(MAI && "Unable to create target asm info!");
+
+ MCContext Ctx(*MAI);
+
+ // Package up features to be passed to target/subtarget
+ std::string FeaturesStr;
+ if (MCPU.size()) {
+ SubtargetFeatures Features;
+ Features.setCPU(MCPU);
+ FeaturesStr = Features.getString();
+ }
+
+ // FIXME: We shouldn't need to do this (and link in codegen).
+ // When we split this out, we should do it in a way that makes
+ // it straightforward to switch subtargets on the fly (.e.g,
+ // the .cpu and .code16 directives).
+ OwningPtr<TargetMachine> TM(TheTarget->createTargetMachine(TripleName,
+ FeaturesStr));
+
+ if (!TM) {
+ errs() << ProgName << ": error: could not create target for triple '"
+ << TripleName << "'.\n";
+ return 1;
+ }
+
+ OwningPtr<tool_output_file> Out(GetOutputStream());
+ if (!Out)
+ return 1;
+
+ formatted_raw_ostream FOS(Out->os());
+ OwningPtr<MCStreamer> Str;
+
+ if (FileType == OFT_AssemblyFile) {
+ MCInstPrinter *IP =
+ TheTarget->createMCInstPrinter(OutputAsmVariant, *MAI);
+ MCCodeEmitter *CE = 0;
+ if (ShowEncoding)
+ CE = TheTarget->createCodeEmitter(*TM, Ctx);
+ Str.reset(TheTarget->createAsmStreamer(Ctx, FOS,
+ TM->getTargetData()->isLittleEndian(),
+ /*asmverbose*/true, IP, CE, ShowInst));
+ } else if (FileType == OFT_Null) {
+ Str.reset(createNullStreamer(Ctx));
+ } else {
+ assert(FileType == OFT_ObjectFile && "Invalid file type!");
+ MCCodeEmitter *CE = TheTarget->createCodeEmitter(*TM, Ctx);
+ TargetAsmBackend *TAB = TheTarget->createAsmBackend(TripleName);
+ Str.reset(TheTarget->createObjectStreamer(TripleName, Ctx, *TAB,
+ FOS, CE, RelaxAll));
+ }
+
+ if (EnableLogging) {
+ Str.reset(createLoggingStreamer(Str.take(), errs()));
+ }
+
+ OwningPtr<MCAsmParser> Parser(createMCAsmParser(*TheTarget, SrcMgr, Ctx,
+ *Str.get(), *MAI));
+ OwningPtr<TargetAsmParser> TAP(TheTarget->createAsmParser(*Parser, *TM));
+ if (!TAP) {
+ errs() << ProgName
+ << ": error: this target does not support assembly parsing.\n";
+ return 1;
+ }
+
+ Parser->setShowParsedOperands(ShowInstOperands);
+ Parser->setTargetParser(*TAP.get());
+
+ int Res = Parser->Run(NoInitialTextSection);
+
+ // Keep output if no errors.
+ if (Res == 0) Out->keep();
+
+ return Res;
+}
+
+static int DisassembleInput(const char *ProgName, bool Enhanced) {
+ const Target *TheTarget = GetTarget(ProgName);
+ if (!TheTarget)
+ return 0;
+
+ error_code ec;
+ MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename, ec);
+ if (Buffer == 0) {
+ errs() << ProgName << ": " << ec.message() << '\n';
+ return 1;
+ }
+
+ OwningPtr<tool_output_file> Out(GetOutputStream());
+ if (!Out)
+ return 1;
- // FIXME: Target hook & command line option for initial section.
- Str.get()->SwitchSection(Ctx.GetSection("__TEXT,__text,regular,pure_instructions"));
+ int Res;
+ if (Enhanced)
+ Res = Disassembler::disassembleEnhanced(TripleName, *Buffer, Out->os());
+ else
+ Res = Disassembler::disassemble(*TheTarget, TripleName, *Buffer, Out->os());
- AsmParser Parser(SrcMgr, Ctx, *Str.get());
- return Parser.Run();
-}
+ // Keep output if no errors.
+ if (Res == 0) Out->keep();
+
+ return Res;
+}
int main(int argc, char **argv) {
sys::PrintStackTraceOnErrorSignal();
PrettyStackTraceProgram X(argc, argv);
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
+
+ // Initialize targets and assembly printers/parsers.
+ llvm::InitializeAllTargetInfos();
+ // FIXME: We shouldn't need to initialize the Target(Machine)s.
+ llvm::InitializeAllTargets();
+ llvm::InitializeAllAsmPrinters();
+ llvm::InitializeAllAsmParsers();
+ llvm::InitializeAllDisassemblers();
+
cl::ParseCommandLineOptions(argc, argv, "llvm machine code playground\n");
+ TripleName = Triple::normalize(TripleName);
switch (Action) {
default:
return AsLexInput(argv[0]);
case AC_Assemble:
return AssembleInput(argv[0]);
+ case AC_Disassemble:
+ return DisassembleInput(argv[0], false);
+ case AC_EDisassemble:
+ return DisassembleInput(argv[0], true);
}
return 0;
projects / oota-llvm.git / blobdiff