2010-06-09 00:52:24 +08:00
|
|
|
//===-- Disassembler.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/Disassembler.h"
|
|
|
|
|
|
|
|
// C Includes
|
|
|
|
// C++ Includes
|
|
|
|
// Other libraries and framework includes
|
|
|
|
// Project includes
|
|
|
|
#include "lldb/lldb-private.h"
|
|
|
|
#include "lldb/Core/Error.h"
|
|
|
|
#include "lldb/Core/DataBufferHeap.h"
|
|
|
|
#include "lldb/Core/DataExtractor.h"
|
|
|
|
#include "lldb/Core/Debugger.h"
|
2011-04-06 02:46:00 +08:00
|
|
|
#include "lldb/Core/EmulateInstruction.h"
|
2010-06-09 00:52:24 +08:00
|
|
|
#include "lldb/Core/Module.h"
|
|
|
|
#include "lldb/Core/PluginManager.h"
|
|
|
|
#include "lldb/Core/Timer.h"
|
|
|
|
#include "lldb/Symbol/ObjectFile.h"
|
|
|
|
#include "lldb/Target/ExecutionContext.h"
|
|
|
|
#include "lldb/Target/Process.h"
|
|
|
|
#include "lldb/Target/StackFrame.h"
|
|
|
|
#include "lldb/Target/Target.h"
|
|
|
|
|
|
|
|
#define DEFAULT_DISASM_BYTE_SIZE 32
|
|
|
|
|
|
|
|
using namespace lldb;
|
|
|
|
using namespace lldb_private;
|
|
|
|
|
|
|
|
|
|
|
|
Disassembler*
|
2011-03-26 02:03:16 +08:00
|
|
|
Disassembler::FindPlugin (const ArchSpec &arch, const char *plugin_name)
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
Timer scoped_timer (__PRETTY_FUNCTION__,
|
2011-03-26 02:03:16 +08:00
|
|
|
"Disassembler::FindPlugin (arch = %s, plugin_name = %s)",
|
|
|
|
arch.GetArchitectureName(),
|
|
|
|
plugin_name);
|
2010-06-09 00:52:24 +08:00
|
|
|
|
|
|
|
std::auto_ptr<Disassembler> disassembler_ap;
|
2011-03-26 02:03:16 +08:00
|
|
|
DisassemblerCreateInstance create_callback = NULL;
|
|
|
|
|
|
|
|
if (plugin_name)
|
|
|
|
{
|
|
|
|
create_callback = PluginManager::GetDisassemblerCreateCallbackForPluginName (plugin_name);
|
|
|
|
if (create_callback)
|
|
|
|
{
|
|
|
|
disassembler_ap.reset (create_callback(arch));
|
|
|
|
|
|
|
|
if (disassembler_ap.get())
|
|
|
|
return disassembler_ap.release();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2011-03-26 02:03:16 +08:00
|
|
|
for (uint32_t idx = 0; (create_callback = PluginManager::GetDisassemblerCreateCallbackAtIndex(idx)) != NULL; ++idx)
|
|
|
|
{
|
|
|
|
disassembler_ap.reset (create_callback(arch));
|
2010-06-09 00:52:24 +08:00
|
|
|
|
2011-03-26 02:03:16 +08:00
|
|
|
if (disassembler_ap.get())
|
|
|
|
return disassembler_ap.release();
|
|
|
|
}
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2010-07-01 07:03:03 +08:00
|
|
|
|
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
|
|
|
static void
|
|
|
|
ResolveAddress (const ExecutionContext &exe_ctx,
|
|
|
|
const Address &addr,
|
|
|
|
Address &resolved_addr)
|
|
|
|
{
|
|
|
|
if (!addr.IsSectionOffset())
|
|
|
|
{
|
|
|
|
// If we weren't passed in a section offset address range,
|
|
|
|
// try and resolve it to something
|
|
|
|
if (exe_ctx.target)
|
|
|
|
{
|
|
|
|
if (exe_ctx.target->GetSectionLoadList().IsEmpty())
|
|
|
|
{
|
|
|
|
exe_ctx.target->GetImages().ResolveFileAddress (addr.GetOffset(), resolved_addr);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
exe_ctx.target->GetSectionLoadList().ResolveLoadAddress (addr.GetOffset(), resolved_addr);
|
|
|
|
}
|
|
|
|
// We weren't able to resolve the address, just treat it as a
|
|
|
|
// raw address
|
|
|
|
if (resolved_addr.IsValid())
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
resolved_addr = addr;
|
|
|
|
}
|
2010-07-01 07:03:03 +08:00
|
|
|
|
|
|
|
size_t
|
2010-06-09 00:52:24 +08:00
|
|
|
Disassembler::Disassemble
|
|
|
|
(
|
2010-06-23 09:19:29 +08:00
|
|
|
Debugger &debugger,
|
2010-06-09 00:52:24 +08:00
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2010-06-09 00:52:24 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
2010-07-01 07:03:03 +08:00
|
|
|
SymbolContextList &sc_list,
|
2011-03-22 09:48:42 +08:00
|
|
|
uint32_t num_instructions,
|
2010-07-01 07:03:03 +08:00
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
2011-03-11 07:35:12 +08:00
|
|
|
bool raw,
|
2010-06-09 00:52:24 +08:00
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
2010-07-01 07:03:03 +08:00
|
|
|
size_t success_count = 0;
|
|
|
|
const size_t count = sc_list.GetSize();
|
|
|
|
SymbolContext sc;
|
|
|
|
AddressRange range;
|
2011-03-22 09:48:42 +08:00
|
|
|
|
2010-07-01 07:03:03 +08:00
|
|
|
for (size_t i=0; i<count; ++i)
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2010-07-01 07:03:03 +08:00
|
|
|
if (sc_list.GetContextAtIndex(i, sc) == false)
|
|
|
|
break;
|
|
|
|
if (sc.GetAddressRange(eSymbolContextFunction | eSymbolContextSymbol, range))
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2011-03-26 02:03:16 +08:00
|
|
|
if (Disassemble (debugger,
|
|
|
|
arch,
|
|
|
|
plugin_name,
|
|
|
|
exe_ctx,
|
|
|
|
range,
|
|
|
|
num_instructions,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
show_bytes,
|
|
|
|
raw,
|
|
|
|
strm))
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2010-07-01 07:03:03 +08:00
|
|
|
++success_count;
|
|
|
|
strm.EOL();
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
2010-07-01 07:03:03 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return success_count;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool
|
|
|
|
Disassembler::Disassemble
|
|
|
|
(
|
|
|
|
Debugger &debugger,
|
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2010-07-01 07:03:03 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
|
|
|
const ConstString &name,
|
|
|
|
Module *module,
|
2011-03-22 09:48:42 +08:00
|
|
|
uint32_t num_instructions,
|
2010-07-01 07:03:03 +08:00
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
2011-03-11 07:35:12 +08:00
|
|
|
bool raw,
|
2010-07-01 07:03:03 +08:00
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
|
|
|
SymbolContextList sc_list;
|
2011-01-27 14:44:37 +08:00
|
|
|
if (name)
|
2010-07-01 07:03:03 +08:00
|
|
|
{
|
2011-01-27 14:44:37 +08:00
|
|
|
const bool include_symbols = true;
|
|
|
|
if (module)
|
|
|
|
{
|
|
|
|
module->FindFunctions (name,
|
|
|
|
eFunctionNameTypeBase |
|
|
|
|
eFunctionNameTypeFull |
|
|
|
|
eFunctionNameTypeMethod |
|
|
|
|
eFunctionNameTypeSelector,
|
|
|
|
include_symbols,
|
|
|
|
true,
|
|
|
|
sc_list);
|
|
|
|
}
|
|
|
|
else if (exe_ctx.target)
|
|
|
|
{
|
|
|
|
exe_ctx.target->GetImages().FindFunctions (name,
|
2010-09-15 13:51:24 +08:00
|
|
|
eFunctionNameTypeBase |
|
|
|
|
eFunctionNameTypeFull |
|
|
|
|
eFunctionNameTypeMethod |
|
|
|
|
eFunctionNameTypeSelector,
|
2011-01-27 14:44:37 +08:00
|
|
|
include_symbols,
|
2010-07-27 08:55:47 +08:00
|
|
|
false,
|
2011-01-27 14:44:37 +08:00
|
|
|
sc_list);
|
2010-07-01 07:03:03 +08:00
|
|
|
}
|
|
|
|
}
|
2011-01-27 14:44:37 +08:00
|
|
|
|
|
|
|
if (sc_list.GetSize ())
|
|
|
|
{
|
|
|
|
return Disassemble (debugger,
|
|
|
|
arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
plugin_name,
|
2011-01-27 14:44:37 +08:00
|
|
|
exe_ctx,
|
2011-03-22 09:48:42 +08:00
|
|
|
sc_list,
|
|
|
|
num_instructions,
|
2011-01-27 14:44:37 +08:00
|
|
|
num_mixed_context_lines,
|
2011-03-11 07:35:12 +08:00
|
|
|
show_bytes,
|
|
|
|
raw,
|
2011-01-27 14:44:37 +08:00
|
|
|
strm);
|
|
|
|
}
|
2010-07-01 07:03:03 +08:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
|
|
|
|
lldb::DisassemblerSP
|
|
|
|
Disassembler::DisassembleRange
|
|
|
|
(
|
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2010-10-06 11:09:58 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
|
|
|
const AddressRange &range
|
|
|
|
)
|
|
|
|
{
|
|
|
|
lldb::DisassemblerSP disasm_sp;
|
|
|
|
if (range.GetByteSize() > 0 && range.GetBaseAddress().IsValid())
|
|
|
|
{
|
2011-03-26 02:03:16 +08:00
|
|
|
disasm_sp.reset (Disassembler::FindPlugin(arch, plugin_name));
|
2010-10-06 11:09:58 +08:00
|
|
|
|
|
|
|
if (disasm_sp)
|
|
|
|
{
|
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
|
|
|
size_t bytes_disassembled = disasm_sp->ParseInstructions (&exe_ctx, range);
|
2010-10-06 11:09:58 +08:00
|
|
|
if (bytes_disassembled == 0)
|
|
|
|
disasm_sp.reset();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return disasm_sp;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2010-07-01 07:03:03 +08:00
|
|
|
bool
|
|
|
|
Disassembler::Disassemble
|
|
|
|
(
|
|
|
|
Debugger &debugger,
|
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2010-07-01 07:03:03 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
|
|
|
const AddressRange &disasm_range,
|
2011-03-22 09:48:42 +08:00
|
|
|
uint32_t num_instructions,
|
2010-07-01 07:03:03 +08:00
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
2011-03-11 07:35:12 +08:00
|
|
|
bool raw,
|
2010-07-01 07:03:03 +08:00
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
|
|
|
if (disasm_range.GetByteSize())
|
|
|
|
{
|
2011-03-26 02:03:16 +08:00
|
|
|
std::auto_ptr<Disassembler> disasm_ap (Disassembler::FindPlugin(arch, plugin_name));
|
2010-07-01 07:03:03 +08:00
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
if (disasm_ap.get())
|
2010-07-01 07:03:03 +08:00
|
|
|
{
|
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
|
|
|
AddressRange range;
|
|
|
|
ResolveAddress (exe_ctx, disasm_range.GetBaseAddress(), range.GetBaseAddress());
|
|
|
|
range.SetByteSize (disasm_range.GetByteSize());
|
2010-07-01 07:03:03 +08:00
|
|
|
|
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
|
|
|
size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, range);
|
2010-06-09 00:52:24 +08:00
|
|
|
if (bytes_disassembled == 0)
|
|
|
|
return false;
|
2011-03-26 02:03:16 +08:00
|
|
|
|
|
|
|
return PrintInstructions (disasm_ap.get(),
|
|
|
|
debugger,
|
|
|
|
arch,
|
|
|
|
exe_ctx,
|
|
|
|
num_instructions,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
show_bytes,
|
|
|
|
raw,
|
|
|
|
strm);
|
2011-03-22 09:48:42 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool
|
|
|
|
Disassembler::Disassemble
|
|
|
|
(
|
|
|
|
Debugger &debugger,
|
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2011-03-22 09:48:42 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
|
|
|
const Address &start_address,
|
|
|
|
uint32_t num_instructions,
|
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
|
|
|
bool raw,
|
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
|
|
|
if (num_instructions > 0)
|
|
|
|
{
|
2011-03-26 02:03:16 +08:00
|
|
|
std::auto_ptr<Disassembler> disasm_ap (Disassembler::FindPlugin(arch, plugin_name));
|
2011-03-22 09:48:42 +08:00
|
|
|
if (disasm_ap.get())
|
|
|
|
{
|
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
|
|
|
Address addr;
|
|
|
|
ResolveAddress (exe_ctx, start_address, addr);
|
2010-07-01 07:03:03 +08:00
|
|
|
|
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
|
|
|
size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, addr, num_instructions);
|
2011-03-22 09:48:42 +08:00
|
|
|
if (bytes_disassembled == 0)
|
|
|
|
return false;
|
2011-03-26 02:03:16 +08:00
|
|
|
return PrintInstructions (disasm_ap.get(),
|
|
|
|
debugger,
|
|
|
|
arch,
|
|
|
|
exe_ctx,
|
|
|
|
num_instructions,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
show_bytes,
|
|
|
|
raw,
|
|
|
|
strm);
|
2011-03-22 09:48:42 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool
|
|
|
|
Disassembler::PrintInstructions
|
|
|
|
(
|
|
|
|
Disassembler *disasm_ptr,
|
|
|
|
Debugger &debugger,
|
|
|
|
const ArchSpec &arch,
|
|
|
|
const ExecutionContext &exe_ctx,
|
|
|
|
uint32_t num_instructions,
|
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
|
|
|
bool raw,
|
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
|
|
|
// We got some things disassembled...
|
|
|
|
size_t num_instructions_found = disasm_ptr->GetInstructionList().GetSize();
|
2010-07-01 07:03:03 +08:00
|
|
|
|
2011-03-22 09:48:42 +08:00
|
|
|
if (num_instructions > 0 && num_instructions < num_instructions_found)
|
|
|
|
num_instructions_found = num_instructions;
|
|
|
|
|
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
|
|
|
const uint32_t max_opcode_byte_size = disasm_ptr->GetInstructionList().GetMaxOpcocdeByteSize ();
|
2011-03-22 09:48:42 +08:00
|
|
|
uint32_t offset = 0;
|
|
|
|
SymbolContext sc;
|
|
|
|
SymbolContext prev_sc;
|
|
|
|
AddressRange sc_range;
|
Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make
sense by default so that subclasses can check:
int
PlatformSubclass::Foo ()
{
if (IsHost())
return Platform::Foo (); // Let the platform base class do the host specific stuff
// Platform subclass specific code...
int result = ...
return result;
}
Added new functions to the platform:
virtual const char *Platform::GetUserName (uint32_t uid);
virtual const char *Platform::GetGroupName (uint32_t gid);
The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.
Added the parent process ID to the ProcessInfo class.
Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value,
euid == value, egid == value, arch == value, parent == value.
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class
implements the process lookup routines, you can now lists processes on
your local machine:
machine1.foo.com % lldb
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode
92742 92710 username usergroup username usergroup i386-apple-darwin debugserver
This of course also works remotely with the lldb-platform:
machine1.foo.com % lldb-platform --listen 1234
machine2.foo.com % lldb
(lldb) platform create remote-macosx
Platform: remote-macosx
Connected: no
(lldb) platform connect connect://localhost:1444
Platform: remote-macosx
Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
Hostname: machine1.foo.com
Connected: yes
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation
99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.
Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:
% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out
Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.
Modified the disassembly to show the current PC value. Example output:
(lldb) disassemble --frame
a.out`main:
0x1eb7: pushl %ebp
0x1eb8: movl %esp, %ebp
0x1eba: pushl %ebx
0x1ebb: subl $20, %esp
0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18
0x1ec3: popl %ebx
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
0x1edb: leal 213(%ebx), %eax
0x1ee1: movl %eax, (%esp)
0x1ee4: calll 0x1f1e ; puts
0x1ee9: calll 0x1f0c ; getchar
0x1eee: movl $20, (%esp)
0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6
0x1efa: movl $12, %eax
0x1eff: addl $20, %esp
0x1f02: popl %ebx
0x1f03: leave
0x1f04: ret
This can be handy when dealing with the new --line options that was recently
added:
(lldb) disassemble --line
a.out`main + 13 at test.c:19
18 {
-> 19 printf("Process: %i\n\n", getpid());
20 puts("Press any key to continue..."); getchar();
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.
Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two
following functions to retrieve both paths:
const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;
llvm-svn: 128563
2011-03-31 02:16:51 +08:00
|
|
|
Address *pc_addr_ptr = NULL;
|
|
|
|
if (exe_ctx.frame)
|
|
|
|
pc_addr_ptr = &exe_ctx.frame->GetFrameCodeAddress();
|
2010-07-01 07:03:03 +08:00
|
|
|
|
2011-03-22 09:48:42 +08:00
|
|
|
for (size_t i=0; i<num_instructions_found; ++i)
|
|
|
|
{
|
|
|
|
Instruction *inst = disasm_ptr->GetInstructionList().GetInstructionAtIndex (i).get();
|
|
|
|
if (inst)
|
|
|
|
{
|
Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make
sense by default so that subclasses can check:
int
PlatformSubclass::Foo ()
{
if (IsHost())
return Platform::Foo (); // Let the platform base class do the host specific stuff
// Platform subclass specific code...
int result = ...
return result;
}
Added new functions to the platform:
virtual const char *Platform::GetUserName (uint32_t uid);
virtual const char *Platform::GetGroupName (uint32_t gid);
The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.
Added the parent process ID to the ProcessInfo class.
Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value,
euid == value, egid == value, arch == value, parent == value.
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class
implements the process lookup routines, you can now lists processes on
your local machine:
machine1.foo.com % lldb
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode
92742 92710 username usergroup username usergroup i386-apple-darwin debugserver
This of course also works remotely with the lldb-platform:
machine1.foo.com % lldb-platform --listen 1234
machine2.foo.com % lldb
(lldb) platform create remote-macosx
Platform: remote-macosx
Connected: no
(lldb) platform connect connect://localhost:1444
Platform: remote-macosx
Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
Hostname: machine1.foo.com
Connected: yes
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation
99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.
Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:
% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out
Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.
Modified the disassembly to show the current PC value. Example output:
(lldb) disassemble --frame
a.out`main:
0x1eb7: pushl %ebp
0x1eb8: movl %esp, %ebp
0x1eba: pushl %ebx
0x1ebb: subl $20, %esp
0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18
0x1ec3: popl %ebx
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
0x1edb: leal 213(%ebx), %eax
0x1ee1: movl %eax, (%esp)
0x1ee4: calll 0x1f1e ; puts
0x1ee9: calll 0x1f0c ; getchar
0x1eee: movl $20, (%esp)
0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6
0x1efa: movl $12, %eax
0x1eff: addl $20, %esp
0x1f02: popl %ebx
0x1f03: leave
0x1f04: ret
This can be handy when dealing with the new --line options that was recently
added:
(lldb) disassemble --line
a.out`main + 13 at test.c:19
18 {
-> 19 printf("Process: %i\n\n", getpid());
20 puts("Press any key to continue..."); getchar();
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.
Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two
following functions to retrieve both paths:
const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;
llvm-svn: 128563
2011-03-31 02:16:51 +08:00
|
|
|
const Address &addr = inst->GetAddress();
|
|
|
|
const bool inst_is_at_pc = pc_addr_ptr && addr == *pc_addr_ptr;
|
2011-03-22 09:48:42 +08:00
|
|
|
|
|
|
|
prev_sc = sc;
|
|
|
|
|
Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make
sense by default so that subclasses can check:
int
PlatformSubclass::Foo ()
{
if (IsHost())
return Platform::Foo (); // Let the platform base class do the host specific stuff
// Platform subclass specific code...
int result = ...
return result;
}
Added new functions to the platform:
virtual const char *Platform::GetUserName (uint32_t uid);
virtual const char *Platform::GetGroupName (uint32_t gid);
The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.
Added the parent process ID to the ProcessInfo class.
Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value,
euid == value, egid == value, arch == value, parent == value.
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class
implements the process lookup routines, you can now lists processes on
your local machine:
machine1.foo.com % lldb
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode
92742 92710 username usergroup username usergroup i386-apple-darwin debugserver
This of course also works remotely with the lldb-platform:
machine1.foo.com % lldb-platform --listen 1234
machine2.foo.com % lldb
(lldb) platform create remote-macosx
Platform: remote-macosx
Connected: no
(lldb) platform connect connect://localhost:1444
Platform: remote-macosx
Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
Hostname: machine1.foo.com
Connected: yes
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation
99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.
Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:
% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out
Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.
Modified the disassembly to show the current PC value. Example output:
(lldb) disassemble --frame
a.out`main:
0x1eb7: pushl %ebp
0x1eb8: movl %esp, %ebp
0x1eba: pushl %ebx
0x1ebb: subl $20, %esp
0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18
0x1ec3: popl %ebx
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
0x1edb: leal 213(%ebx), %eax
0x1ee1: movl %eax, (%esp)
0x1ee4: calll 0x1f1e ; puts
0x1ee9: calll 0x1f0c ; getchar
0x1eee: movl $20, (%esp)
0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6
0x1efa: movl $12, %eax
0x1eff: addl $20, %esp
0x1f02: popl %ebx
0x1f03: leave
0x1f04: ret
This can be handy when dealing with the new --line options that was recently
added:
(lldb) disassemble --line
a.out`main + 13 at test.c:19
18 {
-> 19 printf("Process: %i\n\n", getpid());
20 puts("Press any key to continue..."); getchar();
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.
Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two
following functions to retrieve both paths:
const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;
llvm-svn: 128563
2011-03-31 02:16:51 +08:00
|
|
|
Module *module = addr.GetModule();
|
|
|
|
if (module)
|
2011-03-22 09:48:42 +08:00
|
|
|
{
|
|
|
|
uint32_t resolved_mask = module->ResolveSymbolContextForAddress(addr, eSymbolContextEverything, sc);
|
|
|
|
if (resolved_mask)
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make
sense by default so that subclasses can check:
int
PlatformSubclass::Foo ()
{
if (IsHost())
return Platform::Foo (); // Let the platform base class do the host specific stuff
// Platform subclass specific code...
int result = ...
return result;
}
Added new functions to the platform:
virtual const char *Platform::GetUserName (uint32_t uid);
virtual const char *Platform::GetGroupName (uint32_t gid);
The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.
Added the parent process ID to the ProcessInfo class.
Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value,
euid == value, egid == value, arch == value, parent == value.
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class
implements the process lookup routines, you can now lists processes on
your local machine:
machine1.foo.com % lldb
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode
92742 92710 username usergroup username usergroup i386-apple-darwin debugserver
This of course also works remotely with the lldb-platform:
machine1.foo.com % lldb-platform --listen 1234
machine2.foo.com % lldb
(lldb) platform create remote-macosx
Platform: remote-macosx
Connected: no
(lldb) platform connect connect://localhost:1444
Platform: remote-macosx
Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
Hostname: machine1.foo.com
Connected: yes
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation
99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.
Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:
% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out
Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.
Modified the disassembly to show the current PC value. Example output:
(lldb) disassemble --frame
a.out`main:
0x1eb7: pushl %ebp
0x1eb8: movl %esp, %ebp
0x1eba: pushl %ebx
0x1ebb: subl $20, %esp
0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18
0x1ec3: popl %ebx
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
0x1edb: leal 213(%ebx), %eax
0x1ee1: movl %eax, (%esp)
0x1ee4: calll 0x1f1e ; puts
0x1ee9: calll 0x1f0c ; getchar
0x1eee: movl $20, (%esp)
0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6
0x1efa: movl $12, %eax
0x1eff: addl $20, %esp
0x1f02: popl %ebx
0x1f03: leave
0x1f04: ret
This can be handy when dealing with the new --line options that was recently
added:
(lldb) disassemble --line
a.out`main + 13 at test.c:19
18 {
-> 19 printf("Process: %i\n\n", getpid());
20 puts("Press any key to continue..."); getchar();
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.
Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two
following functions to retrieve both paths:
const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;
llvm-svn: 128563
2011-03-31 02:16:51 +08:00
|
|
|
if (num_mixed_context_lines)
|
|
|
|
{
|
|
|
|
if (!sc_range.ContainsFileAddress (addr))
|
|
|
|
{
|
|
|
|
sc.GetAddressRange (eSymbolContextEverything, sc_range);
|
|
|
|
|
|
|
|
if (sc != prev_sc)
|
|
|
|
{
|
|
|
|
if (offset != 0)
|
|
|
|
strm.EOL();
|
|
|
|
|
|
|
|
sc.DumpStopContext(&strm, exe_ctx.process, addr, false, true, false);
|
|
|
|
strm.EOL();
|
|
|
|
|
|
|
|
if (sc.comp_unit && sc.line_entry.IsValid())
|
|
|
|
{
|
|
|
|
debugger.GetSourceManager().DisplaySourceLinesWithLineNumbers (sc.line_entry.file,
|
|
|
|
sc.line_entry.line,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
num_mixed_context_lines ? "->" : "",
|
|
|
|
&strm);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else if (!(prev_sc.function == sc.function || prev_sc.symbol == sc.symbol))
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2011-03-22 09:48:42 +08:00
|
|
|
if (prev_sc.function || prev_sc.symbol)
|
|
|
|
strm.EOL();
|
2010-07-01 07:03:03 +08:00
|
|
|
|
2011-03-22 09:48:42 +08:00
|
|
|
strm << sc.module_sp->GetFileSpec().GetFilename();
|
|
|
|
|
|
|
|
if (sc.function)
|
|
|
|
strm << '`' << sc.function->GetMangled().GetName();
|
|
|
|
else if (sc.symbol)
|
|
|
|
strm << '`' << sc.symbol->GetMangled().GetName();
|
|
|
|
strm << ":\n";
|
|
|
|
}
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
2011-03-22 09:48:42 +08:00
|
|
|
else
|
|
|
|
{
|
|
|
|
sc.Clear();
|
|
|
|
}
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
2011-03-22 09:48:42 +08:00
|
|
|
|
Many improvements to the Platform base class and subclasses. The base Platform
class now implements the Host functionality for a lot of things that make
sense by default so that subclasses can check:
int
PlatformSubclass::Foo ()
{
if (IsHost())
return Platform::Foo (); // Let the platform base class do the host specific stuff
// Platform subclass specific code...
int result = ...
return result;
}
Added new functions to the platform:
virtual const char *Platform::GetUserName (uint32_t uid);
virtual const char *Platform::GetGroupName (uint32_t gid);
The user and group names are cached locally so that remote platforms can avoid
sending packets multiple times to resolve this information.
Added the parent process ID to the ProcessInfo class.
Added a new ProcessInfoMatch class which helps us to match processes up
and changed the Host layer over to using this new class. The new class allows
us to search for processs:
1 - by name (equal to, starts with, ends with, contains, and regex)
2 - by pid
3 - And further check for parent pid == value, uid == value, gid == value,
euid == value, egid == value, arch == value, parent == value.
This is all hookup up to the "platform process list" command which required
adding dumping routines to dump process information. If the Host class
implements the process lookup routines, you can now lists processes on
your local machine:
machine1.foo.com % lldb
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode
92742 92710 username usergroup username usergroup i386-apple-darwin debugserver
This of course also works remotely with the lldb-platform:
machine1.foo.com % lldb-platform --listen 1234
machine2.foo.com % lldb
(lldb) platform create remote-macosx
Platform: remote-macosx
Connected: no
(lldb) platform connect connect://localhost:1444
Platform: remote-macosx
Triple: x86_64-apple-darwin
OS Version: 10.6.7 (10J869)
Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386
Hostname: machine1.foo.com
Connected: yes
(lldb) platform process list
PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME
====== ====== ========== ========== ========== ========== ======================== ============================
99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation
99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb
99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge
94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker
94852 244 username usergroup username usergroup x86_64-apple-darwin Safari
The lldb-platform implements everything with the Host:: layer, so this should
"just work" for linux. I will probably be adding more stuff to the Host layer
for launching processes and attaching to processes so that this support should
eventually just work as well.
Modified the target to be able to be created with an architecture that differs
from the main executable. This is needed for iOS debugging since we can have
an "armv6" binary which can run on an "armv7" machine, so we want to be able
to do:
% lldb
(lldb) platform create remote-ios
(lldb) file --arch armv7 a.out
Where "a.out" is an armv6 executable. The platform then can correctly decide
to open all "armv7" images for all dependent shared libraries.
Modified the disassembly to show the current PC value. Example output:
(lldb) disassemble --frame
a.out`main:
0x1eb7: pushl %ebp
0x1eb8: movl %esp, %ebp
0x1eba: pushl %ebx
0x1ebb: subl $20, %esp
0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18
0x1ec3: popl %ebx
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
0x1edb: leal 213(%ebx), %eax
0x1ee1: movl %eax, (%esp)
0x1ee4: calll 0x1f1e ; puts
0x1ee9: calll 0x1f0c ; getchar
0x1eee: movl $20, (%esp)
0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6
0x1efa: movl $12, %eax
0x1eff: addl $20, %esp
0x1f02: popl %ebx
0x1f03: leave
0x1f04: ret
This can be handy when dealing with the new --line options that was recently
added:
(lldb) disassemble --line
a.out`main + 13 at test.c:19
18 {
-> 19 printf("Process: %i\n\n", getpid());
20 puts("Press any key to continue..."); getchar();
-> 0x1ec4: calll 0x1f12 ; getpid
0x1ec9: movl %eax, 4(%esp)
0x1ecd: leal 199(%ebx), %eax
0x1ed3: movl %eax, (%esp)
0x1ed6: calll 0x1f18 ; printf
Modified the ModuleList to have a lookup based solely on a UUID. Since the
UUID is typically the MD5 checksum of a binary image, there is no need
to give the path and architecture when searching for a pre-existing
image in an image list.
Now that we support remote debugging a bit better, our lldb_private::Module
needs to be able to track what the original path for file was as the platform
knows it, as well as where the file is locally. The module has the two
following functions to retrieve both paths:
const FileSpec &Module::GetFileSpec () const;
const FileSpec &Module::GetPlatformFileSpec () const;
llvm-svn: 128563
2011-03-31 02:16:51 +08:00
|
|
|
if (pc_addr_ptr)
|
|
|
|
{
|
|
|
|
if (inst_is_at_pc)
|
|
|
|
strm.PutCString("-> ");
|
|
|
|
else
|
|
|
|
strm.PutCString(" ");
|
|
|
|
}
|
|
|
|
inst->Dump(&strm, max_opcode_byte_size, true, show_bytes, &exe_ctx, raw);
|
|
|
|
strm.EOL();
|
2011-03-22 09:48:42 +08:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
break;
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
|
|
|
}
|
2011-03-22 09:48:42 +08:00
|
|
|
|
|
|
|
return true;
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
|
|
|
|
2010-07-01 07:03:03 +08:00
|
|
|
|
|
|
|
bool
|
|
|
|
Disassembler::Disassemble
|
|
|
|
(
|
|
|
|
Debugger &debugger,
|
|
|
|
const ArchSpec &arch,
|
2011-03-26 02:03:16 +08:00
|
|
|
const char *plugin_name,
|
2010-07-01 07:03:03 +08:00
|
|
|
const ExecutionContext &exe_ctx,
|
2011-03-22 09:48:42 +08:00
|
|
|
uint32_t num_instructions,
|
2010-07-01 07:03:03 +08:00
|
|
|
uint32_t num_mixed_context_lines,
|
|
|
|
bool show_bytes,
|
2011-03-11 07:35:12 +08:00
|
|
|
bool raw,
|
2010-07-01 07:03:03 +08:00
|
|
|
Stream &strm
|
|
|
|
)
|
|
|
|
{
|
|
|
|
AddressRange range;
|
|
|
|
if (exe_ctx.frame)
|
|
|
|
{
|
|
|
|
SymbolContext sc(exe_ctx.frame->GetSymbolContext(eSymbolContextFunction | eSymbolContextSymbol));
|
|
|
|
if (sc.function)
|
|
|
|
{
|
|
|
|
range = sc.function->GetAddressRange();
|
|
|
|
}
|
|
|
|
else if (sc.symbol && sc.symbol->GetAddressRangePtr())
|
|
|
|
{
|
|
|
|
range = *sc.symbol->GetAddressRangePtr();
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2010-08-25 05:05:24 +08:00
|
|
|
range.GetBaseAddress() = exe_ctx.frame->GetFrameCodeAddress();
|
2010-07-01 07:03:03 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (range.GetBaseAddress().IsValid() && range.GetByteSize() == 0)
|
|
|
|
range.SetByteSize (DEFAULT_DISASM_BYTE_SIZE);
|
|
|
|
}
|
|
|
|
|
2011-03-26 02:03:16 +08:00
|
|
|
return Disassemble (debugger,
|
|
|
|
arch,
|
|
|
|
plugin_name,
|
|
|
|
exe_ctx,
|
|
|
|
range,
|
|
|
|
num_instructions,
|
|
|
|
num_mixed_context_lines,
|
|
|
|
show_bytes,
|
|
|
|
raw,
|
|
|
|
strm);
|
2010-07-01 07:03:03 +08:00
|
|
|
}
|
|
|
|
|
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
|
|
|
Instruction::Instruction(const Address &address, AddressClass addr_class) :
|
2011-03-26 02:03:16 +08:00
|
|
|
m_address (address),
|
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
|
|
|
m_address_class (addr_class),
|
2011-03-26 02:03:16 +08:00
|
|
|
m_opcode()
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
Instruction::~Instruction()
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
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
|
|
|
AddressClass
|
|
|
|
Instruction::GetAddressClass ()
|
|
|
|
{
|
|
|
|
if (m_address_class == eAddressClassInvalid)
|
|
|
|
m_address_class = m_address.GetAddressClass();
|
|
|
|
return m_address_class;
|
|
|
|
}
|
2010-06-09 00:52:24 +08:00
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList::InstructionList() :
|
2010-06-09 00:52:24 +08:00
|
|
|
m_instructions()
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList::~InstructionList()
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
size_t
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList::GetSize() const
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
return m_instructions.size();
|
|
|
|
}
|
|
|
|
|
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
|
|
|
uint32_t
|
|
|
|
InstructionList::GetMaxOpcocdeByteSize () const
|
|
|
|
{
|
|
|
|
uint32_t max_inst_size = 0;
|
|
|
|
collection::const_iterator pos, end;
|
|
|
|
for (pos = m_instructions.begin(), end = m_instructions.end();
|
|
|
|
pos != end;
|
|
|
|
++pos)
|
|
|
|
{
|
|
|
|
uint32_t inst_size = (*pos)->GetOpcode().GetByteSize();
|
|
|
|
if (max_inst_size < inst_size)
|
|
|
|
max_inst_size = inst_size;
|
|
|
|
}
|
|
|
|
return max_inst_size;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2010-06-09 00:52:24 +08:00
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionSP
|
|
|
|
InstructionList::GetInstructionAtIndex (uint32_t idx) const
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionSP inst_sp;
|
2010-06-09 00:52:24 +08:00
|
|
|
if (idx < m_instructions.size())
|
2010-10-06 11:09:58 +08:00
|
|
|
inst_sp = m_instructions[idx];
|
|
|
|
return inst_sp;
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList::Clear()
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
m_instructions.clear();
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList::Append (lldb::InstructionSP &inst_sp)
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
|
|
|
if (inst_sp)
|
|
|
|
m_instructions.push_back(inst_sp);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
size_t
|
|
|
|
Disassembler::ParseInstructions
|
|
|
|
(
|
|
|
|
const ExecutionContext *exe_ctx,
|
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
|
|
|
const AddressRange &range
|
2010-06-09 00:52:24 +08:00
|
|
|
)
|
|
|
|
{
|
2010-07-01 07:03:03 +08:00
|
|
|
Target *target = exe_ctx->target;
|
|
|
|
const addr_t byte_size = range.GetByteSize();
|
|
|
|
if (target == NULL || byte_size == 0 || !range.GetBaseAddress().IsValid())
|
2010-06-09 00:52:24 +08:00
|
|
|
return 0;
|
|
|
|
|
2010-07-01 07:03:03 +08:00
|
|
|
DataBufferHeap *heap_buffer = new DataBufferHeap (byte_size, '\0');
|
|
|
|
DataBufferSP data_sp(heap_buffer);
|
2010-06-09 00:52:24 +08:00
|
|
|
|
|
|
|
Error error;
|
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
|
|
|
const bool prefer_file_cache = true;
|
|
|
|
const size_t bytes_read = target->ReadMemory (range.GetBaseAddress(),
|
|
|
|
prefer_file_cache,
|
|
|
|
heap_buffer->GetBytes(),
|
|
|
|
heap_buffer->GetByteSize(),
|
|
|
|
error);
|
2010-07-01 07:03:03 +08:00
|
|
|
|
|
|
|
if (bytes_read > 0)
|
2010-06-09 00:52:24 +08:00
|
|
|
{
|
2010-07-01 07:03:03 +08:00
|
|
|
if (bytes_read != heap_buffer->GetByteSize())
|
|
|
|
heap_buffer->SetByteSize (bytes_read);
|
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
|
|
|
DataExtractor data (data_sp,
|
|
|
|
m_arch.GetByteOrder(),
|
|
|
|
m_arch.GetAddressByteSize());
|
2011-03-22 09:48:42 +08:00
|
|
|
return DecodeInstructions (range.GetBaseAddress(), data, 0, UINT32_MAX, false);
|
2010-06-09 00:52:24 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-03-22 09:48:42 +08:00
|
|
|
size_t
|
|
|
|
Disassembler::ParseInstructions
|
|
|
|
(
|
|
|
|
const ExecutionContext *exe_ctx,
|
|
|
|
const Address &start,
|
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
|
|
|
uint32_t num_instructions
|
2011-03-22 09:48:42 +08:00
|
|
|
)
|
|
|
|
{
|
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
|
|
|
m_instruction_list.Clear();
|
|
|
|
|
|
|
|
if (num_instructions == 0 || !start.IsValid())
|
2011-03-22 09:48:42 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
Target *target = exe_ctx->target;
|
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
|
|
|
// Calculate the max buffer size we will need in order to disassemble
|
|
|
|
const addr_t byte_size = num_instructions * m_arch.GetMaximumOpcodeByteSize();
|
2011-03-22 09:48:42 +08:00
|
|
|
|
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
|
|
|
if (target == NULL || byte_size == 0)
|
2011-03-22 09:48:42 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
DataBufferHeap *heap_buffer = new DataBufferHeap (byte_size, '\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
|
|
|
DataBufferSP data_sp (heap_buffer);
|
2011-03-22 09:48:42 +08:00
|
|
|
|
|
|
|
Error error;
|
|
|
|
bool prefer_file_cache = true;
|
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
|
|
|
const size_t bytes_read = target->ReadMemory (start,
|
|
|
|
prefer_file_cache,
|
|
|
|
heap_buffer->GetBytes(),
|
|
|
|
byte_size,
|
|
|
|
error);
|
|
|
|
|
|
|
|
if (bytes_read == 0)
|
|
|
|
return 0;
|
|
|
|
DataExtractor data (data_sp,
|
|
|
|
m_arch.GetByteOrder(),
|
|
|
|
m_arch.GetAddressByteSize());
|
|
|
|
|
|
|
|
const bool append_instructions = true;
|
|
|
|
DecodeInstructions (start,
|
|
|
|
data,
|
|
|
|
0,
|
|
|
|
num_instructions,
|
|
|
|
append_instructions);
|
|
|
|
|
2011-03-22 09:48:42 +08:00
|
|
|
return m_instruction_list.GetSize();
|
|
|
|
}
|
|
|
|
|
2010-06-09 00:52:24 +08:00
|
|
|
//----------------------------------------------------------------------
|
|
|
|
// Disassembler copy constructor
|
|
|
|
//----------------------------------------------------------------------
|
|
|
|
Disassembler::Disassembler(const ArchSpec& arch) :
|
|
|
|
m_arch (arch),
|
|
|
|
m_instruction_list(),
|
|
|
|
m_base_addr(LLDB_INVALID_ADDRESS)
|
|
|
|
{
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
//----------------------------------------------------------------------
|
|
|
|
// Destructor
|
|
|
|
//----------------------------------------------------------------------
|
|
|
|
Disassembler::~Disassembler()
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
InstructionList &
|
2010-06-09 00:52:24 +08:00
|
|
|
Disassembler::GetInstructionList ()
|
|
|
|
{
|
|
|
|
return m_instruction_list;
|
|
|
|
}
|
|
|
|
|
2010-10-06 11:09:58 +08:00
|
|
|
const InstructionList &
|
2010-06-09 00:52:24 +08:00
|
|
|
Disassembler::GetInstructionList () const
|
|
|
|
{
|
|
|
|
return m_instruction_list;
|
|
|
|
}
|