diff options
author | Greg Clayton <gclayton@apple.com> | 2011-03-26 19:14:58 +0000 |
---|---|---|
committer | Greg Clayton <gclayton@apple.com> | 2011-03-26 19:14:58 +0000 |
commit | 357132eb9a7e47b58a097548ad484f7e4b1025a3 (patch) | |
tree | dedcb77d2866c4615dfc0e2b6df1a7c638b4b56d /lldb/source/Core/Disassembler.cpp | |
parent | bbbeea11a8fa600dc77d2e88a9dfe4c914ab0d1d (diff) | |
download | bcm5719-llvm-357132eb9a7e47b58a097548ad484f7e4b1025a3.tar.gz bcm5719-llvm-357132eb9a7e47b58a097548ad484f7e4b1025a3.zip |
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
Diffstat (limited to 'lldb/source/Core/Disassembler.cpp')
-rw-r--r-- | lldb/source/Core/Disassembler.cpp | 200 |
1 files changed, 101 insertions, 99 deletions
diff --git a/lldb/source/Core/Disassembler.cpp b/lldb/source/Core/Disassembler.cpp index 9f3897752fe..e37f4818c9c 100644 --- a/lldb/source/Core/Disassembler.cpp +++ b/lldb/source/Core/Disassembler.cpp @@ -69,6 +69,33 @@ Disassembler::FindPlugin (const ArchSpec &arch, const char *plugin_name) } +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 @@ -192,8 +219,7 @@ Disassembler::DisassembleRange if (disasm_sp) { - DataExtractor data; - size_t bytes_disassembled = disasm_sp->ParseInstructions (&exe_ctx, range, data); + size_t bytes_disassembled = disasm_sp->ParseInstructions (&exe_ctx, range); if (bytes_disassembled == 0) disasm_sp.reset(); } @@ -223,27 +249,11 @@ Disassembler::Disassemble if (disasm_ap.get()) { - AddressRange range(disasm_range); + AddressRange range; + ResolveAddress (exe_ctx, disasm_range.GetBaseAddress(), range.GetBaseAddress()); + range.SetByteSize (disasm_range.GetByteSize()); - // If we weren't passed in a section offset address range, - // try and resolve it to something - if (range.GetBaseAddress().IsSectionOffset() == false) - { - if (exe_ctx.target) - { - if (exe_ctx.target->GetSectionLoadList().IsEmpty()) - { - exe_ctx.target->GetImages().ResolveFileAddress (range.GetBaseAddress().GetOffset(), range.GetBaseAddress()); - } - else - { - exe_ctx.target->GetSectionLoadList().ResolveLoadAddress (range.GetBaseAddress().GetOffset(), range.GetBaseAddress()); - } - } - } - - DataExtractor data; - size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, range, data); + size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, range); if (bytes_disassembled == 0) return false; @@ -280,29 +290,12 @@ Disassembler::Disassemble if (num_instructions > 0) { std::auto_ptr<Disassembler> disasm_ap (Disassembler::FindPlugin(arch, plugin_name)); - Address addr = start_address; - if (disasm_ap.get()) { - // If we weren't passed in a section offset address range, - // try and resolve it to something - if (addr.IsSectionOffset() == false) - { - if (exe_ctx.target) - { - if (exe_ctx.target->GetSectionLoadList().IsEmpty()) - { - exe_ctx.target->GetImages().ResolveFileAddress (addr.GetOffset(), addr); - } - else - { - exe_ctx.target->GetSectionLoadList().ResolveLoadAddress (addr.GetOffset(), addr); - } - } - } + Address addr; + ResolveAddress (exe_ctx, start_address, addr); - DataExtractor data; - size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, addr, num_instructions, data); + size_t bytes_disassembled = disasm_ap->ParseInstructions (&exe_ctx, addr, num_instructions); if (bytes_disassembled == 0) return false; return PrintInstructions (disasm_ap.get(), @@ -341,11 +334,12 @@ Disassembler::PrintInstructions if (num_instructions > 0 && num_instructions < num_instructions_found) num_instructions_found = num_instructions; + const uint32_t max_opcode_byte_size = disasm_ptr->GetInstructionList().GetMaxOpcocdeByteSize (); uint32_t offset = 0; SymbolContext sc; SymbolContext prev_sc; AddressRange sc_range; - Address addr = start_addr; + Address addr (start_addr); if (num_mixed_context_lines) strm.IndentMore (); @@ -425,7 +419,7 @@ Disassembler::PrintInstructions if (num_mixed_context_lines) strm.IndentMore (); strm.Indent(); - inst->Dump(&strm, true, show_bytes, &exe_ctx, raw); + inst->Dump(&strm, max_opcode_byte_size, true, show_bytes, &exe_ctx, raw); strm.EOL(); addr.Slide(inst->GetOpcode().GetByteSize()); @@ -492,8 +486,9 @@ Disassembler::Disassemble strm); } -Instruction::Instruction(const Address &address) : +Instruction::Instruction(const Address &address, AddressClass addr_class) : m_address (address), + m_address_class (addr_class), m_opcode() { } @@ -502,6 +497,13 @@ Instruction::~Instruction() { } +AddressClass +Instruction::GetAddressClass () +{ + if (m_address_class == eAddressClassInvalid) + m_address_class = m_address.GetAddressClass(); + return m_address_class; +} InstructionList::InstructionList() : m_instructions() @@ -518,6 +520,23 @@ InstructionList::GetSize() const return m_instructions.size(); } +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 @@ -546,8 +565,7 @@ size_t Disassembler::ParseInstructions ( const ExecutionContext *exe_ctx, - const AddressRange &range, - DataExtractor& data + const AddressRange &range ) { Target *target = exe_ctx->target; @@ -559,17 +577,20 @@ Disassembler::ParseInstructions DataBufferSP data_sp(heap_buffer); Error error; - bool prefer_file_cache = true; - const size_t bytes_read = target->ReadMemory (range.GetBaseAddress(), prefer_file_cache, heap_buffer->GetBytes(), heap_buffer->GetByteSize(), error); + 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); - - data.SetData(data_sp); - data.SetByteOrder(target->GetArchitecture().GetByteOrder()); - data.SetAddressByteSize(target->GetArchitecture().GetAddressByteSize()); + DataExtractor data (data_sp, + m_arch.GetByteOrder(), + m_arch.GetAddressByteSize()); return DecodeInstructions (range.GetBaseAddress(), data, 0, UINT32_MAX, false); } @@ -581,64 +602,45 @@ Disassembler::ParseInstructions ( const ExecutionContext *exe_ctx, const Address &start, - uint32_t num_instructions, - DataExtractor& data + uint32_t num_instructions ) { - Address addr = start; - - if (num_instructions == 0) + m_instruction_list.Clear(); + + if (num_instructions == 0 || !start.IsValid()) return 0; Target *target = exe_ctx->target; - // We'll guess at a size for the buffer, if we don't get all the instructions we want we can just re-fill & reuse it. - const addr_t byte_size = num_instructions * 2; - addr_t data_offset = 0; - addr_t next_instruction_offset = 0; - size_t buffer_size = byte_size; + // Calculate the max buffer size we will need in order to disassemble + const addr_t byte_size = num_instructions * m_arch.GetMaximumOpcodeByteSize(); - uint32_t num_instructions_found = 0; - - if (target == NULL || byte_size == 0 || !start.IsValid()) + if (target == NULL || byte_size == 0) return 0; DataBufferHeap *heap_buffer = new DataBufferHeap (byte_size, '\0'); - DataBufferSP data_sp(heap_buffer); - - data.SetData(data_sp); - data.SetByteOrder(target->GetArchitecture().GetByteOrder()); - data.SetAddressByteSize(target->GetArchitecture().GetAddressByteSize()); + DataBufferSP data_sp (heap_buffer); Error error; bool prefer_file_cache = true; - - m_instruction_list.Clear(); - - while (num_instructions_found < num_instructions) - { - if (buffer_size < data_offset + byte_size) - { - buffer_size = data_offset + byte_size; - heap_buffer->SetByteSize (buffer_size); - data.SetData(data_sp); // Resizing might have changed the backing store location, so we have to reset - // the DataBufferSP in the extractor so it changes to pointing at the right thing. - } - const size_t bytes_read = target->ReadMemory (addr, prefer_file_cache, heap_buffer->GetBytes() + data_offset, byte_size, error); - size_t num_bytes_read = 0; - if (bytes_read == 0) - break; - - num_bytes_read = DecodeInstructions (start, data, next_instruction_offset, num_instructions - num_instructions_found, true); - if (num_bytes_read == 0) - break; - num_instructions_found = m_instruction_list.GetSize(); - - // Prepare for the next round. - data_offset += bytes_read; - addr.Slide (bytes_read); - next_instruction_offset += num_bytes_read; - } - + 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(); } |