llvm-project/lldb/source/Core/Opcode.cpp

166 lines
4.6 KiB
C++
Raw Normal View History

//===-- Opcode.cpp ----------------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "lldb/Core/Opcode.h"
// C Includes
// C++ Includes
// Other libraries and framework includes
#include "llvm/ADT/Triple.h"
// Project includes
#include "lldb/Core/ArchSpec.h"
#include "lldb/Core/DataBufferHeap.h"
#include "lldb/Core/DataExtractor.h"
#include "lldb/Core/Stream.h"
#include "lldb/Host/Endian.h"
using namespace lldb;
using namespace lldb_private;
int
Opcode::Dump (Stream *s, uint32_t min_byte_width)
{
int bytes_written = 0;
switch (m_type)
{
case Opcode::eTypeInvalid:
bytes_written = s->PutCString ("<invalid>");
break;
case Opcode::eType8:
bytes_written = s->Printf ("0x%2.2x", m_data.inst8);
break;
case Opcode::eType16:
bytes_written = s->Printf ("0x%4.4x", m_data.inst16);
break;
case Opcode::eType16_2:
case Opcode::eType32:
bytes_written = s->Printf ("0x%8.8x", m_data.inst32);
break;
case Opcode::eType64:
bytes_written = s->Printf ("0x%16.16" PRIx64, m_data.inst64);
break;
case Opcode::eTypeBytes:
{
for (uint32_t i=0; i<m_data.inst.length; ++i)
{
if (i > 0)
Added the ability to get the min and max instruction byte size for an architecture into ArchSpec: uint32_t ArchSpec::GetMinimumOpcodeByteSize() const; uint32_t ArchSpec::GetMaximumOpcodeByteSize() const; Added an AddressClass to the Instruction class in Disassembler.h. This allows decoded instructions to know know if they are code, code with alternate ISA (thumb), or even data which can be mixed into code. The instruction does have an address, but it is a good idea to cache this value so we don't have to look it up more than once. Fixed an issue in Opcode::SetOpcodeBytes() where the length wasn't getting set. Changed: bool SymbolContextList::AppendIfUnique (const SymbolContext& sc); To: bool SymbolContextList::AppendIfUnique (const SymbolContext& sc, bool merge_symbol_into_function); This function was typically being used when looking up functions and symbols. Now if you lookup a function, then find the symbol, they can be merged into the same symbol context and not cause multiple symbol contexts to appear in a symbol context list that describes the same function. Fixed the SymbolContext not equal operator which was causing mixed mode disassembly to not work ("disassembler --mixed --name main"). Modified the disassembler classes to know about the fact we know, for a given architecture, what the min and max opcode byte sizes are. The InstructionList class was modified to return the max opcode byte size for all of the instructions in its list. These two fixes means when disassemble a list of instructions and dump them and show the opcode bytes, we can format the output more intelligently when showing opcode bytes. This affects any architectures that have varying opcode byte sizes (x86_64 and i386). Knowing the max opcode byte size also helps us to be able to disassemble N instructions without having to re-read data if we didn't read enough bytes. Added the ability to set the architecture for the disassemble command. This means you can easily cross disassemble data for any supported architecture. I also added the ability to specify "thumb" as an architecture so that we can force disassembly into thumb mode when needed. In GDB this was done using a hack of specifying an odd address when disassembling. I don't want to repeat this hack in LLDB, so the auto detection between ARM and thumb is failing, just specify thumb when disassembling: (lldb) disassemble --arch thumb --name main You can also have data in say an x86_64 file executable and disassemble data as any other supported architecture: % lldb a.out Current executable set to 'a.out' (x86_64). (lldb) b main (lldb) run (lldb) disassemble --arch thumb --count 2 --start-address 0x0000000100001080 --bytes 0x100001080: 0xb580 push {r7, lr} 0x100001082: 0xaf00 add r7, sp, #0 Fixed Target::ReadMemory(...) to be able to deal with Address argument object that isn't section offset. When an address object was supplied that was out on the heap or stack, target read memory would fail. Disassembly uses Target::ReadMemory(...), and the example above where we disassembler thumb opcodes in an x86 binary was failing do to this bug. llvm-svn: 128347
2011-03-27 03:14:58 +08:00
bytes_written += s->PutChar (' ');
bytes_written += s->Printf ("%2.2x", m_data.inst.bytes[i]);
}
}
break;
}
// Add spaces to make sure bytes dispay comes out even in case opcodes
// aren't all the same size
if (static_cast<uint32_t>(bytes_written) < min_byte_width)
bytes_written = s->Printf ("%*s", min_byte_width - bytes_written, "");
return bytes_written;
}
lldb::ByteOrder
Opcode::GetDataByteOrder () const
{
if (m_byte_order != eByteOrderInvalid)
{
return m_byte_order;
}
switch (m_type)
{
case Opcode::eTypeInvalid: break;
case Opcode::eType8:
case Opcode::eType16:
case Opcode::eType16_2:
case Opcode::eType32:
case Opcode::eType64: return lldb::endian::InlHostByteOrder();
case Opcode::eTypeBytes:
break;
}
return eByteOrderInvalid;
}
uint32_t
Opcode::GetData (DataExtractor &data) const
{
uint32_t byte_size = GetByteSize ();
uint8_t swap_buf[8];
const void *buf = NULL;
if (byte_size > 0)
{
if (!GetEndianSwap())
{
if (m_type == Opcode::eType16_2)
{
// 32 bit thumb instruction, we need to sizzle this a bit
swap_buf[0] = m_data.inst.bytes[2];
swap_buf[1] = m_data.inst.bytes[3];
swap_buf[2] = m_data.inst.bytes[0];
swap_buf[3] = m_data.inst.bytes[1];
buf = swap_buf;
}
else
{
buf = GetOpcodeDataBytes();
}
}
else
{
switch (m_type)
{
case Opcode::eTypeInvalid:
break;
case Opcode::eType8:
buf = GetOpcodeDataBytes();
break;
case Opcode::eType16:
*(uint16_t *)swap_buf = llvm::ByteSwap_16(m_data.inst16);
buf = swap_buf;
break;
case Opcode::eType16_2:
swap_buf[0] = m_data.inst.bytes[1];
swap_buf[1] = m_data.inst.bytes[0];
swap_buf[2] = m_data.inst.bytes[3];
swap_buf[3] = m_data.inst.bytes[2];
buf = swap_buf;
break;
case Opcode::eType32:
*(uint32_t *)swap_buf = llvm::ByteSwap_32(m_data.inst32);
buf = swap_buf;
break;
case Opcode::eType64:
*(uint32_t *)swap_buf = llvm::ByteSwap_64(m_data.inst64);
buf = swap_buf;
break;
case Opcode::eTypeBytes:
buf = GetOpcodeDataBytes();
break;
}
}
}
if (buf)
{
DataBufferSP buffer_sp;
buffer_sp.reset (new DataBufferHeap (buf, byte_size));
data.SetByteOrder(GetDataByteOrder());
data.SetData (buffer_sp);
return byte_size;
}
data.Clear();
return 0;
}