1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 02:52:53 +02:00
llvm-mirror/tools/llvm-ml/Disassembler.cpp
Philipp Krones df7a8b162e [MC] Refactor MCObjectFileInfo initialization and allow targets to create MCObjectFileInfo
This makes it possible for targets to define their own MCObjectFileInfo.
This MCObjectFileInfo is then used to determine things like section alignment.

This is a follow up to D101462 and prepares for the RISCV backend defining the
text section alignment depending on the enabled extensions.

Reviewed By: MaskRay

Differential Revision: https://reviews.llvm.org/D101921
2021-05-23 14:15:23 -07:00

204 lines
6.2 KiB
C++

//===- 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 &TripleName,
MCSubtargetInfo &STI, MCStreamer &Streamer,
MemoryBuffer &Buffer, SourceMgr &SM,
raw_ostream &Out) {
std::unique_ptr<const MCRegisterInfo> MRI(T.createMCRegInfo(TripleName));
if (!MRI) {
errs() << "error: no register info for target " << TripleName << "\n";
return -1;
}
MCTargetOptions MCOptions;
std::unique_ptr<const MCAsmInfo> MAI(
T.createMCAsmInfo(*MRI, TripleName, MCOptions));
if (!MAI) {
errs() << "error: no assembly info for target " << TripleName << "\n";
return -1;
}
// Set up the MCContext for creating symbols and MCExpr's.
MCContext Ctx(Triple(TripleName), MAI.get(), MRI.get(), &STI);
std::unique_ptr<const MCDisassembler> DisAsm(
T.createMCDisassembler(STI, Ctx));
if (!DisAsm) {
errs() << "error: no disassembler for target " << TripleName << "\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;
}