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

660 lines
19 KiB
C++
Raw Normal View History

//===-- 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"
#include "lldb/Core/EmulateInstruction.h"
#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*
Disassembler::FindPlugin (const ArchSpec &arch, const char *plugin_name)
{
Timer scoped_timer (__PRETTY_FUNCTION__,
"Disassembler::FindPlugin (arch = %s, plugin_name = %s)",
arch.GetArchitectureName(),
plugin_name);
std::auto_ptr<Disassembler> disassembler_ap;
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
{
for (uint32_t idx = 0; (create_callback = PluginManager::GetDisassemblerCreateCallbackAtIndex(idx)) != NULL; ++idx)
{
disassembler_ap.reset (create_callback(arch));
if (disassembler_ap.get())
return disassembler_ap.release();
}
}
return NULL;
}
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;
}
size_t
Disassembler::Disassemble
(
Debugger &debugger,
const ArchSpec &arch,
const char *plugin_name,
const ExecutionContext &exe_ctx,
SymbolContextList &sc_list,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
bool show_bytes,
bool raw,
Stream &strm
)
{
size_t success_count = 0;
const size_t count = sc_list.GetSize();
SymbolContext sc;
AddressRange range;
for (size_t i=0; i<count; ++i)
{
if (sc_list.GetContextAtIndex(i, sc) == false)
break;
if (sc.GetAddressRange(eSymbolContextFunction | eSymbolContextSymbol, range))
{
if (Disassemble (debugger,
arch,
plugin_name,
exe_ctx,
range,
num_instructions,
num_mixed_context_lines,
show_bytes,
raw,
strm))
{
++success_count;
strm.EOL();
}
}
}
return success_count;
}
bool
Disassembler::Disassemble
(
Debugger &debugger,
const ArchSpec &arch,
const char *plugin_name,
const ExecutionContext &exe_ctx,
const ConstString &name,
Module *module,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
bool show_bytes,
bool raw,
Stream &strm
)
{
SymbolContextList sc_list;
if (name)
{
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,
eFunctionNameTypeBase |
eFunctionNameTypeFull |
eFunctionNameTypeMethod |
eFunctionNameTypeSelector,
include_symbols,
false,
sc_list);
}
}
if (sc_list.GetSize ())
{
return Disassemble (debugger,
arch,
plugin_name,
exe_ctx,
sc_list,
num_instructions,
num_mixed_context_lines,
show_bytes,
raw,
strm);
}
return false;
}
lldb::DisassemblerSP
Disassembler::DisassembleRange
(
const ArchSpec &arch,
const char *plugin_name,
const ExecutionContext &exe_ctx,
const AddressRange &range
)
{
lldb::DisassemblerSP disasm_sp;
if (range.GetByteSize() > 0 && range.GetBaseAddress().IsValid())
{
disasm_sp.reset (Disassembler::FindPlugin(arch, plugin_name));
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);
if (bytes_disassembled == 0)
disasm_sp.reset();
}
}
return disasm_sp;
}
bool
Disassembler::Disassemble
(
Debugger &debugger,
const ArchSpec &arch,
const char *plugin_name,
const ExecutionContext &exe_ctx,
const AddressRange &disasm_range,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
bool show_bytes,
bool raw,
Stream &strm
)
{
if (disasm_range.GetByteSize())
{
std::auto_ptr<Disassembler> disasm_ap (Disassembler::FindPlugin(arch, plugin_name));
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
AddressRange range;
ResolveAddress (exe_ctx, disasm_range.GetBaseAddress(), range.GetBaseAddress());
range.SetByteSize (disasm_range.GetByteSize());
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);
if (bytes_disassembled == 0)
return false;
return PrintInstructions (disasm_ap.get(),
debugger,
arch,
exe_ctx,
num_instructions,
num_mixed_context_lines,
show_bytes,
raw,
strm);
}
}
return false;
}
bool
Disassembler::Disassemble
(
Debugger &debugger,
const ArchSpec &arch,
const char *plugin_name,
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)
{
std::auto_ptr<Disassembler> disasm_ap (Disassembler::FindPlugin(arch, plugin_name));
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);
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);
if (bytes_disassembled == 0)
return false;
return PrintInstructions (disasm_ap.get(),
debugger,
arch,
exe_ctx,
num_instructions,
num_mixed_context_lines,
show_bytes,
raw,
strm);
}
}
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();
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 ();
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();
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;
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)
{
uint32_t resolved_mask = module->ResolveSymbolContextForAddress(addr, eSymbolContextEverything, sc);
if (resolved_mask)
{
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))
{
if (prev_sc.function || prev_sc.symbol)
strm.EOL();
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";
}
}
else
{
sc.Clear();
}
}
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();
}
else
{
break;
}
}
return true;
}
bool
Disassembler::Disassemble
(
Debugger &debugger,
const ArchSpec &arch,
const char *plugin_name,
const ExecutionContext &exe_ctx,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
bool show_bytes,
bool raw,
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
{
range.GetBaseAddress() = exe_ctx.frame->GetFrameCodeAddress();
}
if (range.GetBaseAddress().IsValid() && range.GetByteSize() == 0)
range.SetByteSize (DEFAULT_DISASM_BYTE_SIZE);
}
return Disassemble (debugger,
arch,
plugin_name,
exe_ctx,
range,
num_instructions,
num_mixed_context_lines,
show_bytes,
raw,
strm);
}
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) :
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),
m_opcode()
{
}
Instruction::~Instruction()
{
}
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;
}
InstructionList::InstructionList() :
m_instructions()
{
}
InstructionList::~InstructionList()
{
}
size_t
InstructionList::GetSize() const
{
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;
}
InstructionSP
InstructionList::GetInstructionAtIndex (uint32_t idx) const
{
InstructionSP inst_sp;
if (idx < m_instructions.size())
inst_sp = m_instructions[idx];
return inst_sp;
}
void
InstructionList::Clear()
{
m_instructions.clear();
}
void
InstructionList::Append (lldb::InstructionSP &inst_sp)
{
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
)
{
Target *target = exe_ctx->target;
const addr_t byte_size = range.GetByteSize();
if (target == NULL || byte_size == 0 || !range.GetBaseAddress().IsValid())
return 0;
DataBufferHeap *heap_buffer = new DataBufferHeap (byte_size, '\0');
DataBufferSP data_sp(heap_buffer);
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);
if (bytes_read > 0)
{
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());
return DecodeInstructions (range.GetBaseAddress(), data, 0, UINT32_MAX, false);
}
return 0;
}
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
)
{
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())
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();
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)
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);
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);
return m_instruction_list.GetSize();
}
//----------------------------------------------------------------------
// Disassembler copy constructor
//----------------------------------------------------------------------
Disassembler::Disassembler(const ArchSpec& arch) :
m_arch (arch),
m_instruction_list(),
m_base_addr(LLDB_INVALID_ADDRESS)
{
}
//----------------------------------------------------------------------
// Destructor
//----------------------------------------------------------------------
Disassembler::~Disassembler()
{
}
InstructionList &
Disassembler::GetInstructionList ()
{
return m_instruction_list;
}
const InstructionList &
Disassembler::GetInstructionList () const
{
return m_instruction_list;
}