1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00

[ms] [llvm-ml] Add placeholder for llvm-ml, based on llvm-mc

As discussed on the mailing list, I plan to introduce an ml-compatible MASM assembler as part of providing more of the Windows build tools. This will be similar to llvm-mc, but with different command-line parameters.

This placeholder is purely a stripped-down version of llvm-mc; we'll eventually add support for the Microsoft-style command-line flags, and back it with a MASM parser.

Relanding this revision after fixing ARM-compatibility issues.

Reviewers: rnk, thakis, RKSimon

Reviewed By: thakis, RKSimon

Differential Revision: https://reviews.llvm.org/D72679
This commit is contained in:
Eric Astor 2020-01-20 09:18:25 -05:00
parent 1952f10ca7
commit f5ab9140ce
9 changed files with 661 additions and 0 deletions

View File

@ -80,6 +80,7 @@ set(LLVM_TEST_DEPENDS
llvm-lto2
llvm-mc
llvm-mca
llvm-ml
llvm-modextract
llvm-mt
llvm-nm

View File

@ -0,0 +1,4 @@
# REQUIRES: x86-registered-target
# RUN: not llvm-ml %t.blah -o /dev/null 2>&1 | FileCheck --check-prefix=ENOENT %s
# ENOENT: {{.*}}.blah: {{[Nn]}}o such file or directory

View File

@ -0,0 +1,3 @@
# RUN: llvm-ml --help | FileCheck %s
# CHECK: USAGE: llvm-ml

View File

@ -0,0 +1,15 @@
set(LLVM_LINK_COMPONENTS
AllTargetsAsmPrinters
AllTargetsAsmParsers
AllTargetsDescs
AllTargetsDisassemblers
AllTargetsInfos
MC
MCParser
Support
)
add_llvm_tool(llvm-ml
llvm-ml.cpp
Disassembler.cpp
)

View File

@ -0,0 +1,203 @@
//===- Disassembler.cpp - Disassembler for hex strings --------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This class implements the disassembler of strings of bytes written in
// hexadecimal, from standard input or from a file.
//
//===----------------------------------------------------------------------===//
#include "Disassembler.h"
#include "llvm/ADT/Triple.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDisassembler/MCDisassembler.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
typedef std::pair<std::vector<unsigned char>, std::vector<const char *>>
ByteArrayTy;
static bool PrintInsts(const MCDisassembler &DisAsm, const ByteArrayTy &Bytes,
SourceMgr &SM, raw_ostream &Out, MCStreamer &Streamer,
bool InAtomicBlock, const MCSubtargetInfo &STI) {
ArrayRef<uint8_t> Data(Bytes.first.data(), Bytes.first.size());
// Disassemble it to strings.
uint64_t Size;
uint64_t Index;
for (Index = 0; Index < Bytes.first.size(); Index += Size) {
MCInst Inst;
MCDisassembler::DecodeStatus S;
S = DisAsm.getInstruction(Inst, Size, Data.slice(Index), Index, nulls());
switch (S) {
case MCDisassembler::Fail:
SM.PrintMessage(SMLoc::getFromPointer(Bytes.second[Index]),
SourceMgr::DK_Warning, "invalid instruction encoding");
// Don't try to resynchronise the stream in a block
if (InAtomicBlock)
return true;
if (Size == 0)
Size = 1; // skip illegible bytes
break;
case MCDisassembler::SoftFail:
SM.PrintMessage(SMLoc::getFromPointer(Bytes.second[Index]),
SourceMgr::DK_Warning,
"potentially undefined instruction encoding");
LLVM_FALLTHROUGH;
case MCDisassembler::Success:
Streamer.EmitInstruction(Inst, STI);
break;
}
}
return false;
}
static bool SkipToToken(StringRef &Str) {
for (;;) {
if (Str.empty())
return false;
// Strip horizontal whitespace and commas.
if (size_t Pos = Str.find_first_not_of(" \t\r\n,")) {
Str = Str.substr(Pos);
continue;
}
// If this is the start of a comment, remove the rest of the line.
if (Str[0] == '#') {
Str = Str.substr(Str.find_first_of('\n'));
continue;
}
return true;
}
}
static bool ByteArrayFromString(ByteArrayTy &ByteArray, StringRef &Str,
SourceMgr &SM) {
while (SkipToToken(Str)) {
// Handled by higher level
if (Str[0] == '[' || Str[0] == ']')
return false;
// Get the current token.
size_t Next = Str.find_first_of(" \t\n\r,#[]");
StringRef Value = Str.substr(0, Next);
// Convert to a byte and add to the byte vector.
unsigned ByteVal;
if (Value.getAsInteger(0, ByteVal) || ByteVal > 255) {
// If we have an error, print it and skip to the end of line.
SM.PrintMessage(SMLoc::getFromPointer(Value.data()), SourceMgr::DK_Error,
"invalid input token");
Str = Str.substr(Str.find('\n'));
ByteArray.first.clear();
ByteArray.second.clear();
continue;
}
ByteArray.first.push_back(ByteVal);
ByteArray.second.push_back(Value.data());
Str = Str.substr(Next);
}
return false;
}
int Disassembler::disassemble(const Target &T, const std::string &Triple,
MCSubtargetInfo &STI, MCStreamer &Streamer,
MemoryBuffer &Buffer, SourceMgr &SM,
raw_ostream &Out) {
std::unique_ptr<const MCRegisterInfo> MRI(T.createMCRegInfo(Triple));
if (!MRI) {
errs() << "error: no register info for target " << Triple << "\n";
return -1;
}
MCTargetOptions MCOptions;
std::unique_ptr<const MCAsmInfo> MAI(
T.createMCAsmInfo(*MRI, Triple, MCOptions));
if (!MAI) {
errs() << "error: no assembly info for target " << Triple << "\n";
return -1;
}
// Set up the MCContext for creating symbols and MCExpr's.
MCContext Ctx(MAI.get(), MRI.get(), nullptr);
std::unique_ptr<const MCDisassembler> DisAsm(
T.createMCDisassembler(STI, Ctx));
if (!DisAsm) {
errs() << "error: no disassembler for target " << Triple << "\n";
return -1;
}
// Set up initial section manually here
Streamer.InitSections(false);
bool ErrorOccurred = false;
// Convert the input to a vector for disassembly.
ByteArrayTy ByteArray;
StringRef Str = Buffer.getBuffer();
bool InAtomicBlock = false;
while (SkipToToken(Str)) {
ByteArray.first.clear();
ByteArray.second.clear();
if (Str[0] == '[') {
if (InAtomicBlock) {
SM.PrintMessage(SMLoc::getFromPointer(Str.data()), SourceMgr::DK_Error,
"nested atomic blocks make no sense");
ErrorOccurred = true;
}
InAtomicBlock = true;
Str = Str.drop_front();
continue;
} else if (Str[0] == ']') {
if (!InAtomicBlock) {
SM.PrintMessage(SMLoc::getFromPointer(Str.data()), SourceMgr::DK_Error,
"attempt to close atomic block without opening");
ErrorOccurred = true;
}
InAtomicBlock = false;
Str = Str.drop_front();
continue;
}
// It's a real token, get the bytes and emit them
ErrorOccurred |= ByteArrayFromString(ByteArray, Str, SM);
if (!ByteArray.first.empty())
ErrorOccurred |=
PrintInsts(*DisAsm, ByteArray, SM, Out, Streamer, InAtomicBlock, STI);
}
if (InAtomicBlock) {
SM.PrintMessage(SMLoc::getFromPointer(Str.data()), SourceMgr::DK_Error,
"unclosed atomic block");
ErrorOccurred = true;
}
return ErrorOccurred;
}

View File

@ -0,0 +1,37 @@
//===- Disassembler.h - Text File Disassembler ----------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This class implements the disassembler of strings of bytes written in
// hexadecimal, from standard input or from a file.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_TOOLS_LLVM_MC_DISASSEMBLER_H
#define LLVM_TOOLS_LLVM_MC_DISASSEMBLER_H
#include <string>
namespace llvm {
class MemoryBuffer;
class Target;
class raw_ostream;
class SourceMgr;
class MCSubtargetInfo;
class MCStreamer;
class Disassembler {
public:
static int disassemble(const Target &T, const std::string &Triple,
MCSubtargetInfo &STI, MCStreamer &Streamer,
MemoryBuffer &Buffer, SourceMgr &SM, raw_ostream &Out);
};
} // namespace llvm
#endif

381
tools/llvm-ml/llvm-ml.cpp Normal file
View File

@ -0,0 +1,381 @@
//===-- llvm-ml.cpp - masm-compatible assembler -----------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// A simple driver around MasmParser; based on llvm-mc.
//
//===----------------------------------------------------------------------===//
#include "Disassembler.h"
#include "llvm/MC/MCAsmBackend.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCInstPrinter.h"
#include "llvm/MC/MCInstrInfo.h"
#include "llvm/MC/MCObjectFileInfo.h"
#include "llvm/MC/MCObjectWriter.h"
#include "llvm/MC/MCParser/AsmLexer.h"
#include "llvm/MC/MCParser/MCTargetAsmParser.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/MC/MCTargetOptionsCommandFlags.inc"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/FileUtilities.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/InitLLVM.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/ToolOutputFile.h"
#include "llvm/Support/WithColor.h"
using namespace llvm;
static cl::opt<std::string>
InputFilename(cl::Positional, cl::desc("<input file>"), cl::init("-"));
static cl::opt<std::string>
OutputFilename("o", cl::desc("Output filename"), cl::value_desc("filename"),
cl::init("-"));
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<bool>
OutputATTAsm("output-att-asm", cl::desc("Use ATT syntax for output printing"));
static cl::opt<bool>
PrintImmHex("print-imm-hex", cl::init(false),
cl::desc("Prefer hex format for immediate values"));
static cl::opt<bool>
PreserveComments("preserve-comments",
cl::desc("Preserve Comments in outputted assembly"));
enum OutputFileType {
OFT_Null,
OFT_AssemblyFile,
OFT_ObjectFile
};
static cl::opt<OutputFileType>
FileType("filetype", cl::init(OFT_ObjectFile),
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")));
static cl::list<std::string>
IncludeDirs("I", cl::desc("Directory of include files"),
cl::value_desc("directory"), cl::Prefix);
enum BitnessType {
m32,
m64,
};
cl::opt<BitnessType> Bitness(cl::desc("Choose bitness:"), cl::init(m64),
cl::values(clEnumVal(m32, "32-bit"),
clEnumVal(m64, "64-bit (default)")));
static cl::opt<std::string>
TripleName("triple", cl::desc("Target triple to assemble for, "
"see -version for available targets"));
static cl::opt<std::string>
DebugCompilationDir("fdebug-compilation-dir",
cl::desc("Specifies the debug info's compilation dir"));
static cl::list<std::string>
DebugPrefixMap("fdebug-prefix-map",
cl::desc("Map file source paths in debug info"),
cl::value_desc("= separated key-value pairs"));
static cl::opt<std::string>
MainFileName("main-file-name",
cl::desc("Specifies the name we should consider the input file"));
static cl::opt<bool> SaveTempLabels("save-temp-labels",
cl::desc("Don't discard temporary labels"));
enum ActionType {
AC_AsLex,
AC_Assemble,
AC_Disassemble,
AC_MDisassemble,
};
static cl::opt<ActionType>
Action(cl::desc("Action to perform:"),
cl::init(AC_Assemble),
cl::values(clEnumValN(AC_AsLex, "as-lex",
"Lex tokens from a .asm file"),
clEnumValN(AC_Assemble, "assemble",
"Assemble a .asm file (default)"),
clEnumValN(AC_Disassemble, "disassemble",
"Disassemble strings of hex bytes"),
clEnumValN(AC_MDisassemble, "mdis",
"Marked up disassembly of strings of hex bytes")));
static const Target *GetTarget(const char *ProgName) {
// Figure out the target triple.
if (TripleName.empty()) {
if (Bitness == m32)
TripleName = "i386-pc-windows";
else if (Bitness == m64)
TripleName = "x86_64-pc-windows";
}
Triple TheTriple(Triple::normalize(TripleName));
// Get the target specific parser.
std::string Error;
const Target *TheTarget = TargetRegistry::lookupTarget("", TheTriple, Error);
if (!TheTarget) {
WithColor::error(errs(), ProgName) << Error;
return nullptr;
}
// Update the triple name and return the found target.
TripleName = TheTriple.getTriple();
return TheTarget;
}
static std::unique_ptr<ToolOutputFile> GetOutputStream(StringRef Path) {
std::error_code EC;
auto Out = std::make_unique<ToolOutputFile>(Path, EC, sys::fs::F_None);
if (EC) {
WithColor::error() << EC.message() << '\n';
return nullptr;
}
return Out;
}
static int AsLexInput(SourceMgr &SrcMgr, MCAsmInfo &MAI, raw_ostream &OS) {
AsmLexer Lexer(MAI);
Lexer.setBuffer(SrcMgr.getMemoryBuffer(SrcMgr.getMainFileID())->getBuffer());
bool Error = false;
while (Lexer.Lex().isNot(AsmToken::Eof)) {
Lexer.getTok().dump(OS);
OS << "\n";
if (Lexer.getTok().getKind() == AsmToken::Error)
Error = true;
}
return Error;
}
static int AssembleInput(const char *ProgName, const Target *TheTarget,
SourceMgr &SrcMgr, MCContext &Ctx, MCStreamer &Str,
MCAsmInfo &MAI, MCSubtargetInfo &STI,
MCInstrInfo &MCII, MCTargetOptions &MCOptions) {
std::unique_ptr<MCAsmParser> Parser(createMCAsmParser(SrcMgr, Ctx, Str, MAI));
std::unique_ptr<MCTargetAsmParser> TAP(
TheTarget->createMCAsmParser(STI, *Parser, MCII, MCOptions));
if (!TAP) {
WithColor::error(errs(), ProgName)
<< "this target does not support assembly parsing.\n";
return 1;
}
Parser->setShowParsedOperands(ShowInstOperands);
Parser->setTargetParser(*TAP);
Parser->getLexer().setLexMasmIntegers(true);
int Res = Parser->Run(/*NoInitialTextSection=*/true);
return Res;
}
int main(int argc, char **argv) {
InitLLVM X(argc, argv);
// Initialize targets and assembly printers/parsers.
llvm::InitializeAllTargetInfos();
llvm::InitializeAllTargetMCs();
llvm::InitializeAllAsmParsers();
llvm::InitializeAllDisassemblers();
// Register the target printer for --version.
cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
cl::ParseCommandLineOptions(argc, argv, "llvm machine code playground\n");
MCTargetOptions MCOptions = InitMCTargetOptionsFromFlags();
const char *ProgName = argv[0];
const Target *TheTarget = GetTarget(ProgName);
if (!TheTarget)
return 1;
// Now that GetTarget() has (potentially) replaced TripleName, it's safe to
// construct the Triple object.
Triple TheTriple(TripleName);
ErrorOr<std::unique_ptr<MemoryBuffer>> BufferPtr =
MemoryBuffer::getFileOrSTDIN(InputFilename);
if (std::error_code EC = BufferPtr.getError()) {
WithColor::error(errs(), ProgName)
<< InputFilename << ": " << EC.message() << '\n';
return 1;
}
MemoryBuffer *Buffer = BufferPtr->get();
SourceMgr SrcMgr;
// Tell SrcMgr about this buffer, which is what the parser will pick up.
SrcMgr.AddNewSourceBuffer(std::move(*BufferPtr), SMLoc());
// Record the location of the include directories so that the lexer can find
// it later.
SrcMgr.setIncludeDirs(IncludeDirs);
std::unique_ptr<MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
assert(MRI && "Unable to create target register info!");
std::unique_ptr<MCAsmInfo> MAI(
TheTarget->createMCAsmInfo(*MRI, TripleName, MCOptions));
assert(MAI && "Unable to create target asm info!");
MAI->setPreserveAsmComments(PreserveComments);
// FIXME: This is not pretty. MCContext has a ptr to MCObjectFileInfo and
// MCObjectFileInfo needs a MCContext reference in order to initialize itself.
MCObjectFileInfo MOFI;
MCContext Ctx(MAI.get(), MRI.get(), &MOFI, &SrcMgr);
MOFI.InitMCObjectFileInfo(TheTriple, /*PIC=*/false, Ctx,
/*LargeCodeModel=*/true);
if (SaveTempLabels)
Ctx.setAllowTemporaryLabels(false);
if (!DebugCompilationDir.empty()) {
Ctx.setCompilationDir(DebugCompilationDir);
} else {
// If no compilation dir is set, try to use the current directory.
SmallString<128> CWD;
if (!sys::fs::current_path(CWD))
Ctx.setCompilationDir(CWD);
}
for (const auto &Arg : DebugPrefixMap) {
const auto &KV = StringRef(Arg).split('=');
Ctx.addDebugPrefixMapEntry(KV.first, KV.second);
}
if (!MainFileName.empty())
Ctx.setMainFileName(MainFileName);
std::unique_ptr<ToolOutputFile> Out = GetOutputStream(OutputFilename);
if (!Out)
return 1;
std::unique_ptr<buffer_ostream> BOS;
raw_pwrite_stream *OS = &Out->os();
std::unique_ptr<MCStreamer> Str;
std::unique_ptr<MCInstrInfo> MCII(TheTarget->createMCInstrInfo());
std::unique_ptr<MCSubtargetInfo> STI(TheTarget->createMCSubtargetInfo(
TripleName, /*CPU=*/"", /*Features=*/""));
MCInstPrinter *IP = nullptr;
if (FileType == OFT_AssemblyFile) {
const unsigned OutputAsmVariant = OutputATTAsm ? 0U // ATT dialect
: 1U; // Intel dialect
IP = TheTarget->createMCInstPrinter(Triple(TripleName), OutputAsmVariant,
*MAI, *MCII, *MRI);
if (!IP) {
WithColor::error()
<< "unable to create instruction printer for target triple '"
<< TheTriple.normalize() << "' with "
<< (OutputATTAsm ? "ATT" : "Intel") << " assembly variant.\n";
return 1;
}
// Set the display preference for hex vs. decimal immediates.
IP->setPrintImmHex(PrintImmHex);
// Set up the AsmStreamer.
std::unique_ptr<MCCodeEmitter> CE;
if (ShowEncoding)
CE.reset(TheTarget->createMCCodeEmitter(*MCII, *MRI, Ctx));
std::unique_ptr<MCAsmBackend> MAB(
TheTarget->createMCAsmBackend(*STI, *MRI, MCOptions));
auto FOut = std::make_unique<formatted_raw_ostream>(*OS);
Str.reset(
TheTarget->createAsmStreamer(Ctx, std::move(FOut), /*asmverbose*/ true,
/*useDwarfDirectory*/ true, IP,
std::move(CE), std::move(MAB), ShowInst));
} else if (FileType == OFT_Null) {
Str.reset(TheTarget->createNullStreamer(Ctx));
} else {
assert(FileType == OFT_ObjectFile && "Invalid file type!");
// Don't waste memory on names of temp labels.
Ctx.setUseNamesOnTempLabels(false);
if (!Out->os().supportsSeeking()) {
BOS = std::make_unique<buffer_ostream>(Out->os());
OS = BOS.get();
}
MCCodeEmitter *CE = TheTarget->createMCCodeEmitter(*MCII, *MRI, Ctx);
MCAsmBackend *MAB = TheTarget->createMCAsmBackend(*STI, *MRI, MCOptions);
Str.reset(TheTarget->createMCObjectStreamer(
TheTriple, Ctx, std::unique_ptr<MCAsmBackend>(MAB),
MAB->createObjectWriter(*OS), std::unique_ptr<MCCodeEmitter>(CE), *STI,
MCOptions.MCRelaxAll, MCOptions.MCIncrementalLinkerCompatible,
/*DWARFMustBeAtTheEnd*/ false));
}
// Use Assembler information for parsing.
Str->setUseAssemblerInfoForParsing(true);
int Res = 1;
bool disassemble = false;
switch (Action) {
case AC_AsLex:
Res = AsLexInput(SrcMgr, *MAI, Out->os());
break;
case AC_Assemble:
Res = AssembleInput(ProgName, TheTarget, SrcMgr, Ctx, *Str, *MAI, *STI,
*MCII, MCOptions);
break;
case AC_MDisassemble:
assert(IP && "Expected assembly output");
IP->setUseMarkup(1);
disassemble = true;
break;
case AC_Disassemble:
disassemble = true;
break;
}
if (disassemble)
Res = Disassembler::disassemble(*TheTarget, TripleName, *STI, *Str, *Buffer,
SrcMgr, Out->os());
// Keep output if no errors.
if (Res == 0)
Out->keep();
return Res;
}

View File

@ -225,6 +225,7 @@ group("test") {
"//llvm/tools/llvm-lto2",
"//llvm/tools/llvm-mc",
"//llvm/tools/llvm-mca",
"//llvm/tools/llvm-ml",
"//llvm/tools/llvm-modextract",
"//llvm/tools/llvm-mt",
"//llvm/tools/llvm-nm",

View File

@ -0,0 +1,16 @@
executable("llvm-ml") {
deps = [
"//llvm/lib/MC",
"//llvm/lib/MC/MCParser",
"//llvm/lib/Support",
"//llvm/lib/Target:AllTargetsAsmParsers",
"//llvm/lib/Target:AllTargetsAsmPrinters",
"//llvm/lib/Target:AllTargetsDescs",
"//llvm/lib/Target:AllTargetsDisassemblers",
"//llvm/lib/Target:AllTargetsInfos",
]
sources = [
"Disassembler.cpp",
"llvm-ml.cpp",
]
}