//===----------------------------------------------------------------------===//
#include "Disassembler.h"
-
-#include "llvm/ADT/OwningPtr.h"
#include "llvm/ADT/Triple.h"
#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDisassembler.h"
#include "llvm/MC/MCInst.h"
-#include "llvm/MC/MCInstPrinter.h"
-#include "llvm/Target/TargetRegistry.h"
+#include "llvm/MC/MCRegisterInfo.h"
+#include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/Support/MemoryBuffer.h"
-#include "llvm/Support/MemoryObject.h"
-#include "llvm/Support/raw_ostream.h"
#include "llvm/Support/SourceMgr.h"
-
-#include "llvm-c/EnhancedDisassembly.h"
+#include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/raw_ostream.h"
using namespace llvm;
-typedef std::vector<std::pair<unsigned char, const char*> > ByteArrayTy;
-
-namespace {
-class VectorMemoryObject : public MemoryObject {
-private:
- const ByteArrayTy &Bytes;
-public:
- VectorMemoryObject(const ByteArrayTy &bytes) : Bytes(bytes) {}
-
- uint64_t getBase() const { return 0; }
- uint64_t getExtent() const { return Bytes.size(); }
-
- int readByte(uint64_t Addr, uint8_t *Byte) const {
- if (Addr > getExtent())
- return -1;
- *Byte = Bytes[Addr].first;
- return 0;
- }
-};
-}
+typedef std::pair<std::vector<unsigned char>, std::vector<const char *>>
+ ByteArrayTy;
static bool PrintInsts(const MCDisassembler &DisAsm,
- MCInstPrinter &Printer, const ByteArrayTy &Bytes,
- SourceMgr &SM) {
- // Wrap the vector in a MemoryObject.
- VectorMemoryObject memoryObject(Bytes);
-
+ 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.size(); Index += Size) {
+
+ for (Index = 0; Index < Bytes.first.size(); Index += Size) {
MCInst Inst;
-
- if (DisAsm.getInstruction(Inst, Size, memoryObject, Index,
- /*REMOVE*/ nulls())) {
- Printer.printInst(&Inst, outs());
- outs() << "\n";
- } else {
- SM.PrintMessage(SMLoc::getFromPointer(Bytes[Index].second),
- "invalid instruction encoding", "warning");
+
+ MCDisassembler::DecodeStatus S;
+ S = DisAsm.getInstruction(Inst, Size, Data.slice(Index), Index,
+ /*REMOVE*/ nulls(), 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");
+ // Fall through
+
+ case MCDisassembler::Success:
+ Streamer.EmitInstruction(Inst, STI);
+ break;
}
}
-
+
return false;
}
-static bool ByteArrayFromString(ByteArrayTy &ByteArray,
- StringRef &Str,
- SourceMgr &SM) {
- while (!Str.empty()) {
- // Strip horizontal whitespace.
- if (size_t Pos = Str.find_first_not_of(" \t\r")) {
+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 end of a line or start of a comment, remove the rest of
- // the line.
- if (Str[0] == '\n' || Str[0] == '#') {
- // Strip to the end of line if we already processed any bytes on this
- // line. This strips the comment and/or the \n.
- if (Str[0] == '\n') {
- Str = Str.substr(1);
- } else {
+
+ // 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'));
- if (!Str.empty())
- Str = Str.substr(1);
- }
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#");
+ 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()),
- "invalid input token", "error");
+ SM.PrintMessage(SMLoc::getFromPointer(Value.data()), SourceMgr::DK_Error,
+ "invalid input token");
Str = Str.substr(Str.find('\n'));
- ByteArray.clear();
+ ByteArray.first.clear();
+ ByteArray.second.clear();
continue;
}
-
- ByteArray.push_back(std::make_pair((unsigned char)ByteVal, Value.data()));
+
+ 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,
- MemoryBuffer &Buffer) {
- // Set up disassembler.
- OwningPtr<const MCAsmInfo> AsmInfo(T.createAsmInfo(Triple));
-
- if (!AsmInfo) {
+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;
+ }
+
+ std::unique_ptr<const MCAsmInfo> MAI(T.createMCAsmInfo(*MRI, Triple));
+ if (!MAI) {
errs() << "error: no assembly info for target " << Triple << "\n";
return -1;
}
-
- OwningPtr<const MCDisassembler> DisAsm(T.createMCDisassembler());
+
+ // 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;
}
-
- OwningPtr<MCInstPrinter> IP(T.createMCInstPrinter(0, *AsmInfo));
- if (!IP) {
- errs() << "error: no instruction printer for target " << Triple << '\n';
- return -1;
- }
-
+
+ // Set up initial section manually here
+ Streamer.InitSections(false);
+
bool ErrorOccurred = false;
-
- SourceMgr SM;
- SM.AddNewSourceBuffer(&Buffer, SMLoc());
-
+
// Convert the input to a vector for disassembly.
ByteArrayTy ByteArray;
StringRef Str = Buffer.getBuffer();
-
- ErrorOccurred |= ByteArrayFromString(ByteArray, Str, SM);
-
- if (!ByteArray.empty())
- ErrorOccurred |= PrintInsts(*DisAsm, *IP, ByteArray, SM);
-
- return ErrorOccurred;
-}
+ bool InAtomicBlock = false;
-static int byteArrayReader(uint8_t *B, uint64_t A, void *Arg) {
- ByteArrayTy &ByteArray = *((ByteArrayTy*)Arg);
-
- if (A >= ByteArray.size())
- return -1;
-
- *B = ByteArray[A].first;
-
- return 0;
-}
-
-static int verboseEvaluator(uint64_t *V, unsigned R, void *Arg) {
- EDDisassemblerRef &disassembler = *((EDDisassemblerRef*)Arg);
-
- const char *regName;
-
- if (!EDGetRegisterName(®Name,
- disassembler,
- R))
- outs() << "[" << regName << "/" << R << "]";
- if (EDRegisterIsStackPointer(disassembler, R))
- outs() << "(sp)";
- if (EDRegisterIsProgramCounter(disassembler, R))
- outs() << "(pc)";
-
- *V = 0;
-
- return 0;
-}
+ while (SkipToToken(Str)) {
+ ByteArray.first.clear();
+ ByteArray.second.clear();
-int Disassembler::disassembleEnhanced(const std::string &TS,
- MemoryBuffer &Buffer) {
- ByteArrayTy ByteArray;
- StringRef Str = Buffer.getBuffer();
- SourceMgr SM;
-
- SM.AddNewSourceBuffer(&Buffer, SMLoc());
-
- if (ByteArrayFromString(ByteArray, Str, SM)) {
- return -1;
- }
-
- EDDisassemblerRef disassembler;
-
- Triple T(TS);
- EDAssemblySyntax_t AS;
-
- switch (T.getArch()) {
- default:
- errs() << "error: no default assembly syntax for " << TS.c_str() << "\n";
- return -1;
- case Triple::arm:
- case Triple::thumb:
- AS = kEDAssemblySyntaxARMUAL;
- break;
- case Triple::x86:
- case Triple::x86_64:
- AS = kEDAssemblySyntaxX86ATT;
- break;
- }
-
- if (EDGetDisassembler(&disassembler,
- TS.c_str(),
- AS)) {
- errs() << "error: couldn't get disassembler for " << TS.c_str() << "\n";
- return -1;
- }
-
- EDInstRef inst;
-
- if (EDCreateInsts(&inst, 1, disassembler, byteArrayReader, 0,&ByteArray)
- != 1) {
- errs() << "error: Didn't get an instruction\n";
- return -1;
- }
-
- int numTokens = EDNumTokens(inst);
-
- if (numTokens < 0) {
- errs() << "error: Couldn't count the instruction's tokens\n";
- return -1;
- }
-
- int tokenIndex;
-
- for (tokenIndex = 0; tokenIndex < numTokens; ++tokenIndex) {
- EDTokenRef token;
-
- if (EDGetToken(&token, inst, tokenIndex)) {
- errs() << "error: Couldn't get token\n";
- return -1;
- }
-
- const char *buf;
-
- if (EDGetTokenString(&buf, token)) {
- errs() << "error: Couldn't get string for token\n";
- return -1;
- }
-
- outs() << "[";
-
- int operandIndex = EDOperandIndexForToken(token);
-
- if (operandIndex >= 0)
- outs() << operandIndex << "-";
-
- if (EDTokenIsWhitespace(token)) {
- outs() << "w";
- } else if (EDTokenIsPunctuation(token)) {
- outs() << "p";
- } else if (EDTokenIsOpcode(token)) {
- outs() << "o";
- } else if (EDTokenIsLiteral(token)) {
- outs() << "l";
- } else if (EDTokenIsRegister(token)) {
- outs() << "r";
- } else {
- outs() << "?";
- }
-
- outs() << ":" << buf;
-
- if (EDTokenIsLiteral(token)) {
- outs() << "=";
- if (EDTokenIsNegativeLiteral(token))
- outs() << "-";
- uint64_t absoluteValue;
- if (EDLiteralTokenAbsoluteValue(&absoluteValue, token)) {
- errs() << "error: Couldn't get the value of a literal token\n";
- return -1;
+ if (Str[0] == '[') {
+ if (InAtomicBlock) {
+ SM.PrintMessage(SMLoc::getFromPointer(Str.data()), SourceMgr::DK_Error,
+ "nested atomic blocks make no sense");
+ ErrorOccurred = true;
}
- outs() << absoluteValue;
- } else if (EDTokenIsRegister(token)) {
- outs() << "=";
- unsigned regID;
- if (EDRegisterTokenValue(®ID, token)) {
- errs() << "error: Couldn't get the ID of a register token\n";
- return -1;
+ 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;
}
- outs() << "r" << regID;
+ InAtomicBlock = false;
+ Str = Str.drop_front();
+ continue;
}
-
- outs() << "]";
- }
-
- outs() << " ";
-
- int numOperands = EDNumOperands(inst);
-
- if (numOperands < 0) {
- errs() << "error: Couldn't count operands\n";
- return -1;
+
+ // 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);
}
-
- int operandIndex;
-
- for (operandIndex = 0; operandIndex < numOperands; ++operandIndex) {
- outs() << operandIndex << ":";
-
- EDOperandRef operand;
-
- if (EDGetOperand(&operand,
- inst,
- operandIndex)) {
- errs() << "error: Couldn't get operand\n";
- return -1;
- }
-
- uint64_t evaluatedResult;
-
- EDEvaluateOperand(&evaluatedResult,
- operand,
- verboseEvaluator,
- &disassembler);
-
- outs() << " ";
+
+ if (InAtomicBlock) {
+ SM.PrintMessage(SMLoc::getFromPointer(Str.data()), SourceMgr::DK_Error,
+ "unclosed atomic block");
+ ErrorOccurred = true;
}
-
- outs() << "\n";
-
- return 0;
-}
+ return ErrorOccurred;
+}
projects / oota-llvm.git / blobdiff