Test harness for the LLVM disassembler. When invoked

with -disassemble, llvm-mc now accepts lines of the
form
0x00 0x00
and passes the resulting bytes to the disassembler for
the chosen (or default) target, printing the result.

llvm-svn: 91579

tools/llvm-mc/HexDisassembler.cpp

@@ -0,0 +1,158 @@
+//===- HexDisassembler.cpp - Disassembler for hex strings -----------------===//
+//
+//                     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 disassembler of strings of bytes written in
+// hexadecimal, from standard input or from a file.
+//
+//===----------------------------------------------------------------------===//
+
+#include "HexDisassembler.h"
+
+#include "llvm/ADT/OwningPtr.h"
+#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCDisassembler.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCInstPrinter.h"
+#include "llvm/Target/TargetRegistry.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/MemoryObject.h"
+#include "llvm/Support/raw_ostream.h"
+
+#include <vector>
+
+using namespace llvm;
+
+class VectorMemoryObject : public MemoryObject {
+private:
+  const std::vector<unsigned char> &Bytes;
+public:
+  VectorMemoryObject(const std::vector<unsigned char> &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;
+    else
+      *byte = Bytes[addr];
+    
+    return 0;
+  }
+};
+
+void printInst(const llvm::MCDisassembler &disassembler,
+               llvm::MCInstPrinter &instPrinter,
+               const std::vector<unsigned char> &bytes) {
+  // Wrap the vector in a MemoryObject.
+  
+  VectorMemoryObject memoryObject(bytes);
+  
+  // Disassemble it.
+  
+  MCInst inst;
+  uint64_t size;
+  
+  std::string verboseOStr;
+  llvm::raw_string_ostream verboseOS(verboseOStr); 
+  
+  if (disassembler.getInstruction(inst, 
+                                  size, 
+                                  memoryObject, 
+                                  0, 
+                                  verboseOS)) {
+    instPrinter.printInst(&inst);
+    outs() << "\n";
+  }
+  else {
+    errs() << "error: invalid instruction" << "\n";
+    errs() << "Diagnostic log:" << "\n";
+    errs() << verboseOStr.c_str() << "\n";
+  }
+}
+
+int HexDisassembler::disassemble(const Target &target,
+                                 const std::string &tripleString,
+                                 MemoryBuffer &buffer) {
+  // Set up disassembler
+  
+  llvm::OwningPtr<const llvm::MCAsmInfo> asmInfo
+    (target.createAsmInfo(tripleString));
+  
+  if (!asmInfo) {
+    errs() << "error: no assembly info for target " << tripleString << "\n";
+    return -1;
+  }
+  
+  llvm::OwningPtr<const llvm::MCDisassembler> disassembler
+    (target.createMCDisassembler());
+  
+  if (!disassembler) {
+    errs() << "error: no disassembler for target " << tripleString << "\n";
+    return -1;
+  }
+  
+  llvm::MCInstPrinter *instPrinter = target.createMCInstPrinter(0,
+                                                                *asmInfo,
+                                                                outs());
+  
+  if (!instPrinter) {
+    errs() << "error: no instruction printer for target " << tripleString
+      << "\n";
+    return -1;
+  }
+  
+  // Convert the input to a vector for disassembly.
+  
+  std::vector<unsigned char> bytes;
+  
+  StringRef str = buffer.getBuffer();
+  
+  while (!str.empty()) {
+    if(str.find_first_of("\n") < str.find_first_not_of(" \t\n\r")) {
+      printInst(*disassembler, *instPrinter, bytes);
+      
+      bytes.clear();
+    }
+    
+    // Skip leading space.
+    str = str.substr(str.find_first_not_of(" \t\n\r"));
+    
+    // Get the current token.
+    size_t next = str.find_first_of(" \t\n\r");
+    
+    if(next == (size_t)StringRef::npos)
+      break;
+    
+    StringRef value = str.slice(0, next);
+    
+    // Convert to a byte and add to the byte vector.
+    unsigned byte;
+    if (value.getAsInteger(0, byte) || byte > 255) {
+      errs() << "warning: invalid input token '" << value << "' of length " 
+        << next << "\n";
+    }
+    else {
+      bytes.push_back((unsigned char)byte);
+    }
+    str = str.substr(next);
+  }
+  
+  if (!bytes.empty())
+    printInst(*disassembler, *instPrinter, bytes);
+    
+  return 0;
+}

tools/llvm-mc/HexDisassembler.h

@@ -0,0 +1,34 @@
+//===- HexDisassembler.h - Disassembler for hex strings -------------------===//
+//
+//                     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 disassembler of strings of bytes written in
+// hexadecimal, from standard input or from a file.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef HEXDISASSEMBLER_H
+#define HEXDISASSEMBLER_H
+
+#include <string>
+
+namespace llvm {
+
+class Target;
+class MemoryBuffer;
+
+class HexDisassembler {
+public:
+  static int disassemble(const Target &target, 
+                         const std::string &tripleString,
+                         MemoryBuffer &buffer);
+};
+  
+} // namespace llvm
+
+#endif

tools/llvm-mc/llvm-mc.cpp

@@ -32,6 +32,7 @@
 #include "llvm/Target/TargetMachine.h"  // FIXME.
 #include "llvm/Target/TargetSelect.h"
 #include "AsmParser.h"
+#include "HexDisassembler.h"
 using namespace llvm;
 
 static cl::opt<std::string>
@@ -76,7 +77,8 @@ TripleName("triple", cl::desc("Target triple to assemble for, "
 
 enum ActionType {
   AC_AsLex,
-  AC_Assemble
+  AC_Assemble,
+  AC_Disassemble
 };
 
 static cl::opt<ActionType>
@@ -86,6 +88,8 @@ Action(cl::desc("Action to perform:"),
                              "Lex tokens from a .s file"),
                   clEnumValN(AC_Assemble, "assemble",
                              "Assemble a .s file (default)"),
+                  clEnumValN(AC_Disassemble, "disassemble",
+                             "Disassemble strings of hex bytes"),
                   clEnumValEnd));
 
 static const Target *GetTarget(const char *ProgName) {
@@ -281,7 +285,33 @@ static int AssembleInput(const char *ProgName) {
     delete Out;
 
   return Res;
-}  
+}
+
+static int DisassembleInput(const char *ProgName) {
+  std::string Error;
+  const Target *TheTarget = TargetRegistry::lookupTarget(TripleName, Error);
+  if (TheTarget == 0) {
+    errs() << ProgName << ": error: unable to get target for '" << TripleName
+    << "', see --version and --triple.\n";
+    return 0;
+  }
+  
+  std::string ErrorMessage;
+  
+  MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename,
+                                                      &ErrorMessage);
+
+  if (Buffer == 0) {
+    errs() << ProgName << ": ";
+    if (ErrorMessage.size())
+      errs() << ErrorMessage << "\n";
+    else
+      errs() << "input file didn't read correctly.\n";
+    return 1;
+  }
+  
+  return HexDisassembler::disassemble(*TheTarget, TripleName, *Buffer);
+}
 
 
 int main(int argc, char **argv) {
@@ -296,6 +326,7 @@ int main(int argc, char **argv) {
   llvm::InitializeAllTargets();
   llvm::InitializeAllAsmPrinters();
   llvm::InitializeAllAsmParsers();
+  llvm::InitializeAllDisassemblers();
   
   cl::ParseCommandLineOptions(argc, argv, "llvm machine code playground\n");
 
@@ -305,6 +336,8 @@ int main(int argc, char **argv) {
     return AsLexInput(argv[0]);
   case AC_Assemble:
     return AssembleInput(argv[0]);
+  case AC_Disassemble:
+    return DisassembleInput(argv[0]);
   }
   
   return 0;