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

1087 lines
37 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
#include <cstdio>
#include <cstring>
// Other libraries and framework includes
// Project includes
#include "lldb/Core/DataBufferHeap.h"
#include "lldb/Core/DataExtractor.h"
#include "lldb/Core/Debugger.h"
#include "lldb/Core/EmulateInstruction.h"
#include "lldb/Core/Error.h"
#include "lldb/Core/Module.h"
#include "lldb/Core/PluginManager.h"
#include "lldb/Core/RegularExpression.h"
#include "lldb/Core/Timer.h"
#include "lldb/Host/FileSystem.h"
#include "lldb/Interpreter/OptionValue.h"
#include "lldb/Interpreter/OptionValueArray.h"
#include "lldb/Interpreter/OptionValueDictionary.h"
#include "lldb/Interpreter/OptionValueString.h"
#include "lldb/Interpreter/OptionValueUInt64.h"
<rdar://problem/11757916> Make breakpoint setting by file and line much more efficient by only looking for inlined breakpoint locations if we are setting a breakpoint in anything but a source implementation file. Implementing this complex for a many reasons. Turns out that parsing compile units lazily had some issues with respect to how we need to do things with DWARF in .o files. So the fixes in the checkin for this makes these changes: - Add a new setting called "target.inline-breakpoint-strategy" which can be set to "never", "always", or "headers". "never" will never try and set any inlined breakpoints (fastest). "always" always looks for inlined breakpoint locations (slowest, but most accurate). "headers", which is the default setting, will only look for inlined breakpoint locations if the breakpoint is set in what are consudered to be header files, which is realy defined as "not in an implementation source file". - modify the breakpoint setting by file and line to check the current "target.inline-breakpoint-strategy" setting and act accordingly - Modify compile units to be able to get their language and other info lazily. This allows us to create compile units from the debug map and not have to fill all of the details in, and then lazily discover this information as we go on debuggging. This is needed to avoid parsing all .o files when setting breakpoints in implementation only files (no inlines). Otherwise we would need to parse the .o file, the object file (mach-o in our case) and the symbol file (DWARF in the object file) just to see what the compile unit was. - modify the "SymbolFileDWARFDebugMap" to subclass lldb_private::Module so that the virtual "GetObjectFile()" and "GetSymbolVendor()" functions can be intercepted when the .o file contenst are later lazilly needed. Prior to this fix, when we first instantiated the "SymbolFileDWARFDebugMap" class, we would also make modules, object files and symbol files for every .o file in the debug map because we needed to fix up the sections in the .o files with information that is in the executable debug map. Now we lazily do this in the DebugMapModule::GetObjectFile() Cleaned up header includes a bit as well. llvm-svn: 162860
2012-08-30 05:13:06 +08:00
#include "lldb/Symbol/Function.h"
#include "lldb/Symbol/ObjectFile.h"
#include "lldb/Target/ExecutionContext.h"
#include "lldb/Target/Process.h"
#include "lldb/Target/SectionLoadList.h"
#include "lldb/Target/StackFrame.h"
#include "lldb/Target/Target.h"
#include "lldb/lldb-private.h"
#define DEFAULT_DISASM_BYTE_SIZE 32
using namespace lldb;
using namespace lldb_private;
DisassemblerSP Disassembler::FindPlugin(const ArchSpec &arch,
const char *flavor,
const char *plugin_name) {
Timer scoped_timer(LLVM_PRETTY_FUNCTION,
"Disassembler::FindPlugin (arch = %s, plugin_name = %s)",
arch.GetArchitectureName(), plugin_name);
DisassemblerCreateInstance create_callback = nullptr;
if (plugin_name) {
ConstString const_plugin_name(plugin_name);
create_callback = PluginManager::GetDisassemblerCreateCallbackForPluginName(
const_plugin_name);
if (create_callback) {
DisassemblerSP disassembler_sp(create_callback(arch, flavor));
if (disassembler_sp)
return disassembler_sp;
}
} else {
for (uint32_t idx = 0;
(create_callback = PluginManager::GetDisassemblerCreateCallbackAtIndex(
idx)) != nullptr;
++idx) {
DisassemblerSP disassembler_sp(create_callback(arch, flavor));
if (disassembler_sp)
return disassembler_sp;
}
}
return DisassemblerSP();
}
DisassemblerSP Disassembler::FindPluginForTarget(const TargetSP target_sp,
const ArchSpec &arch,
const char *flavor,
const char *plugin_name) {
if (target_sp && flavor == nullptr) {
// FIXME - we don't have the mechanism in place to do per-architecture
// settings. But since we know that for now
// we only support flavors on x86 & x86_64,
if (arch.GetTriple().getArch() == llvm::Triple::x86 ||
arch.GetTriple().getArch() == llvm::Triple::x86_64)
flavor = target_sp->GetDisassemblyFlavor();
}
return FindPlugin(arch, flavor, 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
Target *target = exe_ctx.GetTargetPtr();
if (target) {
if (target->GetSectionLoadList().IsEmpty()) {
target->GetImages().ResolveFileAddress(addr.GetOffset(), resolved_addr);
} else {
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 char *flavor,
const ExecutionContext &exe_ctx,
SymbolContextList &sc_list,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
uint32_t options, Stream &strm) {
size_t success_count = 0;
const size_t count = sc_list.GetSize();
SymbolContext sc;
AddressRange range;
const uint32_t scope =
eSymbolContextBlock | eSymbolContextFunction | eSymbolContextSymbol;
const bool use_inline_block_range = true;
for (size_t i = 0; i < count; ++i) {
if (!sc_list.GetContextAtIndex(i, sc))
break;
for (uint32_t range_idx = 0;
sc.GetAddressRange(scope, range_idx, use_inline_block_range, range);
++range_idx) {
if (Disassemble(debugger, arch, plugin_name, flavor, exe_ctx, range,
num_instructions, num_mixed_context_lines, options,
strm)) {
++success_count;
strm.EOL();
}
}
}
return success_count;
}
bool Disassembler::Disassemble(Debugger &debugger, const ArchSpec &arch,
const char *plugin_name, const char *flavor,
const ExecutionContext &exe_ctx,
const ConstString &name, Module *module,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
uint32_t options, Stream &strm) {
SymbolContextList sc_list;
if (name) {
const bool include_symbols = true;
const bool include_inlines = true;
if (module) {
module->FindFunctions(name, nullptr, eFunctionNameTypeAuto,
include_symbols, include_inlines, true, sc_list);
} else if (exe_ctx.GetTargetPtr()) {
exe_ctx.GetTargetPtr()->GetImages().FindFunctions(
name, eFunctionNameTypeAuto, include_symbols, include_inlines, false,
sc_list);
}
}
if (sc_list.GetSize()) {
return Disassemble(debugger, arch, plugin_name, flavor, exe_ctx, sc_list,
num_instructions, num_mixed_context_lines, options,
strm);
}
return false;
}
lldb::DisassemblerSP Disassembler::DisassembleRange(
const ArchSpec &arch, const char *plugin_name, const char *flavor,
const ExecutionContext &exe_ctx, const AddressRange &range,
bool prefer_file_cache) {
lldb::DisassemblerSP disasm_sp;
if (range.GetByteSize() > 0 && range.GetBaseAddress().IsValid()) {
disasm_sp = Disassembler::FindPluginForTarget(exe_ctx.GetTargetSP(), arch,
flavor, plugin_name);
if (disasm_sp) {
size_t bytes_disassembled = disasm_sp->ParseInstructions(
&exe_ctx, range, nullptr, prefer_file_cache);
if (bytes_disassembled == 0)
disasm_sp.reset();
}
}
return disasm_sp;
}
lldb::DisassemblerSP
Disassembler::DisassembleBytes(const ArchSpec &arch, const char *plugin_name,
const char *flavor, const Address &start,
const void *src, size_t src_len,
uint32_t num_instructions, bool data_from_file) {
lldb::DisassemblerSP disasm_sp;
if (src) {
disasm_sp = Disassembler::FindPlugin(arch, flavor, plugin_name);
if (disasm_sp) {
DataExtractor data(src, src_len, arch.GetByteOrder(),
arch.GetAddressByteSize());
(void)disasm_sp->DecodeInstructions(start, data, 0, num_instructions,
false, data_from_file);
}
}
return disasm_sp;
}
bool Disassembler::Disassemble(Debugger &debugger, const ArchSpec &arch,
const char *plugin_name, const char *flavor,
const ExecutionContext &exe_ctx,
const AddressRange &disasm_range,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
uint32_t options, Stream &strm) {
if (disasm_range.GetByteSize()) {
lldb::DisassemblerSP disasm_sp(Disassembler::FindPluginForTarget(
exe_ctx.GetTargetSP(), arch, flavor, plugin_name));
if (disasm_sp) {
AddressRange range;
ResolveAddress(exe_ctx, disasm_range.GetBaseAddress(),
range.GetBaseAddress());
range.SetByteSize(disasm_range.GetByteSize());
const bool prefer_file_cache = false;
size_t bytes_disassembled = disasm_sp->ParseInstructions(
&exe_ctx, range, &strm, prefer_file_cache);
if (bytes_disassembled == 0)
return false;
return PrintInstructions(disasm_sp.get(), debugger, arch, exe_ctx,
num_instructions, num_mixed_context_lines,
options, strm);
}
}
return false;
}
bool Disassembler::Disassemble(Debugger &debugger, const ArchSpec &arch,
const char *plugin_name, const char *flavor,
const ExecutionContext &exe_ctx,
const Address &start_address,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
uint32_t options, Stream &strm) {
if (num_instructions > 0) {
lldb::DisassemblerSP disasm_sp(Disassembler::FindPluginForTarget(
exe_ctx.GetTargetSP(), arch, flavor, plugin_name));
if (disasm_sp) {
Address addr;
ResolveAddress(exe_ctx, start_address, addr);
const bool prefer_file_cache = false;
size_t bytes_disassembled = disasm_sp->ParseInstructions(
&exe_ctx, addr, num_instructions, prefer_file_cache);
if (bytes_disassembled == 0)
return false;
return PrintInstructions(disasm_sp.get(), debugger, arch, exe_ctx,
num_instructions, num_mixed_context_lines,
options, 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,
uint32_t options, 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;
const uint32_t max_opcode_byte_size =
disasm_ptr->GetInstructionList().GetMaxOpcocdeByteSize();
uint32_t offset = 0;
SymbolContext sc;
SymbolContext prev_sc;
AddressRange sc_range;
const Address *pc_addr_ptr = nullptr;
StackFrame *frame = exe_ctx.GetFramePtr();
TargetSP target_sp(exe_ctx.GetTargetSP());
SourceManager &source_manager =
target_sp ? target_sp->GetSourceManager() : debugger.GetSourceManager();
if (frame) {
pc_addr_ptr = &frame->GetFrameCodeAddress();
}
const uint32_t scope =
eSymbolContextLineEntry | eSymbolContextFunction | eSymbolContextSymbol;
const bool use_inline_block_range = false;
const FormatEntity::Entry *disassembly_format = nullptr;
FormatEntity::Entry format;
if (exe_ctx.HasTargetScope()) {
disassembly_format =
exe_ctx.GetTargetRef().GetDebugger().GetDisassemblyFormat();
} else {
FormatEntity::Parse("${addr}: ", format);
disassembly_format = &format;
}
// First pass: step through the list of instructions,
// find how long the initial addresses strings are, insert padding
// in the second pass so the opcodes all line up nicely.
size_t address_text_size = 0;
for (size_t i = 0; i < num_instructions_found; ++i) {
Instruction *inst =
disasm_ptr->GetInstructionList().GetInstructionAtIndex(i).get();
if (inst) {
const Address &addr = inst->GetAddress();
ModuleSP module_sp(addr.GetModule());
if (module_sp) {
const uint32_t resolve_mask =
eSymbolContextFunction | eSymbolContextSymbol;
uint32_t resolved_mask =
module_sp->ResolveSymbolContextForAddress(addr, resolve_mask, sc);
if (resolved_mask) {
StreamString strmstr;
Debugger::FormatDisassemblerAddress(disassembly_format, &sc, nullptr,
&exe_ctx, &addr, strmstr);
size_t cur_line = strmstr.GetSizeOfLastLine();
if (cur_line > address_text_size)
address_text_size = cur_line;
}
sc.Clear(false);
}
}
}
for (size_t i = 0; i < num_instructions_found; ++i) {
Instruction *inst =
disasm_ptr->GetInstructionList().GetInstructionAtIndex(i).get();
if (inst) {
const Address &addr = inst->GetAddress();
const bool inst_is_at_pc = pc_addr_ptr && addr == *pc_addr_ptr;
prev_sc = sc;
ModuleSP module_sp(addr.GetModule());
if (module_sp) {
uint32_t resolved_mask = module_sp->ResolveSymbolContextForAddress(
addr, eSymbolContextEverything, sc);
if (resolved_mask) {
if (num_mixed_context_lines) {
if (!sc_range.ContainsFileAddress(addr)) {
sc.GetAddressRange(scope, 0, use_inline_block_range, sc_range);
if (sc != prev_sc) {
if (offset != 0)
strm.EOL();
sc.DumpStopContext(&strm, exe_ctx.GetProcessPtr(), addr, false,
true, false, false, true);
strm.EOL();
if (sc.comp_unit && sc.line_entry.IsValid()) {
source_manager.DisplaySourceLinesWithLineNumbers(
sc.line_entry.file, sc.line_entry.line,
num_mixed_context_lines, num_mixed_context_lines,
((inst_is_at_pc && (options & eOptionMarkPCSourceLine))
? "->"
: ""),
&strm);
}
}
}
}
} else {
sc.Clear(true);
}
}
const bool show_bytes = (options & eOptionShowBytes) != 0;
inst->Dump(&strm, max_opcode_byte_size, true, show_bytes, &exe_ctx, &sc,
&prev_sc, nullptr, address_text_size);
strm.EOL();
} else {
break;
}
}
return true;
}
bool Disassembler::Disassemble(Debugger &debugger, const ArchSpec &arch,
const char *plugin_name, const char *flavor,
const ExecutionContext &exe_ctx,
uint32_t num_instructions,
uint32_t num_mixed_context_lines,
uint32_t options, Stream &strm) {
AddressRange range;
StackFrame *frame = exe_ctx.GetFramePtr();
if (frame) {
SymbolContext sc(
frame->GetSymbolContext(eSymbolContextFunction | eSymbolContextSymbol));
if (sc.function) {
range = sc.function->GetAddressRange();
} else if (sc.symbol && sc.symbol->ValueIsAddress()) {
range.GetBaseAddress() = sc.symbol->GetAddressRef();
range.SetByteSize(sc.symbol->GetByteSize());
} else {
range.GetBaseAddress() = frame->GetFrameCodeAddress();
}
if (range.GetBaseAddress().IsValid() && range.GetByteSize() == 0)
range.SetByteSize(DEFAULT_DISASM_BYTE_SIZE);
}
return Disassemble(debugger, arch, plugin_name, flavor, exe_ctx, range,
num_instructions, num_mixed_context_lines, options, strm);
}
Instruction::Instruction(const Address &address, AddressClass addr_class)
: m_address(address), m_address_class(addr_class), m_opcode(),
m_calculated_strings(false) {}
Instruction::~Instruction() = default;
AddressClass Instruction::GetAddressClass() {
if (m_address_class == eAddressClassInvalid)
m_address_class = m_address.GetAddressClass();
return m_address_class;
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
}
void Instruction::Dump(lldb_private::Stream *s, uint32_t max_opcode_byte_size,
bool show_address, bool show_bytes,
const ExecutionContext *exe_ctx,
const SymbolContext *sym_ctx,
const SymbolContext *prev_sym_ctx,
const FormatEntity::Entry *disassembly_addr_format,
size_t max_address_text_size) {
size_t opcode_column_width = 7;
const size_t operand_column_width = 25;
CalculateMnemonicOperandsAndCommentIfNeeded(exe_ctx);
StreamString ss;
if (show_address) {
Debugger::FormatDisassemblerAddress(disassembly_addr_format, sym_ctx,
prev_sym_ctx, exe_ctx, &m_address, ss);
ss.FillLastLineToColumn(max_address_text_size, ' ');
}
if (show_bytes) {
if (m_opcode.GetType() == Opcode::eTypeBytes) {
// x86_64 and i386 are the only ones that use bytes right now so
// pad out the byte dump to be able to always show 15 bytes (3 chars each)
// plus a space
if (max_opcode_byte_size > 0)
m_opcode.Dump(&ss, max_opcode_byte_size * 3 + 1);
else
m_opcode.Dump(&ss, 15 * 3 + 1);
} else {
// Else, we have ARM or MIPS which can show up to a uint32_t
// 0x00000000 (10 spaces) plus two for padding...
if (max_opcode_byte_size > 0)
m_opcode.Dump(&ss, max_opcode_byte_size * 3 + 1);
else
m_opcode.Dump(&ss, 12);
}
}
const size_t opcode_pos = ss.GetSizeOfLastLine();
// The default opcode size of 7 characters is plenty for most architectures
// but some like arm can pull out the occasional vqrshrun.s16. We won't get
// consistent column spacing in these cases, unfortunately.
if (m_opcode_name.length() >= opcode_column_width) {
opcode_column_width = m_opcode_name.length() + 1;
}
ss.PutCString(m_opcode_name.c_str());
ss.FillLastLineToColumn(opcode_pos + opcode_column_width, ' ');
ss.PutCString(m_mnemonics.c_str());
if (!m_comment.empty()) {
ss.FillLastLineToColumn(
opcode_pos + opcode_column_width + operand_column_width, ' ');
ss.PutCString(" ; ");
ss.PutCString(m_comment.c_str());
}
s->Write(ss.GetData(), ss.GetSize());
}
bool Instruction::DumpEmulation(const ArchSpec &arch) {
std::unique_ptr<EmulateInstruction> insn_emulator_ap(
EmulateInstruction::FindPlugin(arch, eInstructionTypeAny, nullptr));
if (insn_emulator_ap) {
insn_emulator_ap->SetInstruction(GetOpcode(), GetAddress(), nullptr);
return insn_emulator_ap->EvaluateInstruction(0);
}
return false;
}
bool Instruction::HasDelaySlot() {
// Default is false.
return false;
}
OptionValueSP Instruction::ReadArray(FILE *in_file, Stream *out_stream,
OptionValue::Type data_type) {
bool done = false;
char buffer[1024];
OptionValueSP option_value_sp(new OptionValueArray(1u << data_type));
int idx = 0;
while (!done) {
if (!fgets(buffer, 1023, in_file)) {
out_stream->Printf(
"Instruction::ReadArray: Error reading file (fgets).\n");
option_value_sp.reset();
return option_value_sp;
}
std::string line(buffer);
size_t len = line.size();
if (line[len - 1] == '\n') {
line[len - 1] = '\0';
line.resize(len - 1);
}
if ((line.size() == 1) && line[0] == ']') {
done = true;
line.clear();
}
if (!line.empty()) {
std::string value;
static RegularExpression g_reg_exp("^[ \t]*([^ \t]+)[ \t]*$");
RegularExpression::Match regex_match(1);
bool reg_exp_success = g_reg_exp.Execute(line.c_str(), &regex_match);
if (reg_exp_success)
regex_match.GetMatchAtIndex(line.c_str(), 1, value);
else
value = line;
OptionValueSP data_value_sp;
switch (data_type) {
case OptionValue::eTypeUInt64:
data_value_sp.reset(new OptionValueUInt64(0, 0));
data_value_sp->SetValueFromString(value);
break;
// Other types can be added later as needed.
default:
data_value_sp.reset(new OptionValueString(value.c_str(), ""));
break;
}
option_value_sp->GetAsArray()->InsertValue(idx, data_value_sp);
++idx;
}
}
return option_value_sp;
}
OptionValueSP Instruction::ReadDictionary(FILE *in_file, Stream *out_stream) {
bool done = false;
char buffer[1024];
OptionValueSP option_value_sp(new OptionValueDictionary());
static ConstString encoding_key("data_encoding");
OptionValue::Type data_type = OptionValue::eTypeInvalid;
while (!done) {
// Read the next line in the file
if (!fgets(buffer, 1023, in_file)) {
out_stream->Printf(
"Instruction::ReadDictionary: Error reading file (fgets).\n");
option_value_sp.reset();
return option_value_sp;
}
// Check to see if the line contains the end-of-dictionary marker ("}")
std::string line(buffer);
size_t len = line.size();
if (line[len - 1] == '\n') {
line[len - 1] = '\0';
line.resize(len - 1);
}
if ((line.size() == 1) && (line[0] == '}')) {
done = true;
line.clear();
}
// Try to find a key-value pair in the current line and add it to the
// dictionary.
if (!line.empty()) {
static RegularExpression g_reg_exp(
"^[ \t]*([a-zA-Z_][a-zA-Z0-9_]*)[ \t]*=[ \t]*(.*)[ \t]*$");
RegularExpression::Match regex_match(2);
bool reg_exp_success = g_reg_exp.Execute(line.c_str(), &regex_match);
std::string key;
std::string value;
if (reg_exp_success) {
regex_match.GetMatchAtIndex(line.c_str(), 1, key);
regex_match.GetMatchAtIndex(line.c_str(), 2, value);
} else {
out_stream->Printf("Instruction::ReadDictionary: Failure executing "
"regular expression.\n");
option_value_sp.reset();
return option_value_sp;
}
ConstString const_key(key.c_str());
// Check value to see if it's the start of an array or dictionary.
lldb::OptionValueSP value_sp;
assert(value.empty() == false);
assert(key.empty() == false);
if (value[0] == '{') {
assert(value.size() == 1);
// value is a dictionary
value_sp = ReadDictionary(in_file, out_stream);
if (!value_sp) {
option_value_sp.reset();
return option_value_sp;
}
} else if (value[0] == '[') {
assert(value.size() == 1);
// value is an array
value_sp = ReadArray(in_file, out_stream, data_type);
if (!value_sp) {
option_value_sp.reset();
return option_value_sp;
}
// We've used the data_type to read an array; re-set the type to Invalid
data_type = OptionValue::eTypeInvalid;
} else if ((value[0] == '0') && (value[1] == 'x')) {
value_sp.reset(new OptionValueUInt64(0, 0));
value_sp->SetValueFromString(value);
} else {
size_t len = value.size();
if ((value[0] == '"') && (value[len - 1] == '"'))
value = value.substr(1, len - 2);
value_sp.reset(new OptionValueString(value.c_str(), ""));
}
if (const_key == encoding_key) {
// A 'data_encoding=..." is NOT a normal key-value pair; it is meta-data
// indicating the
// data type of an upcoming array (usually the next bit of data to be
// read in).
if (strcmp(value.c_str(), "uint32_t") == 0)
data_type = OptionValue::eTypeUInt64;
} else
option_value_sp->GetAsDictionary()->SetValueForKey(const_key, value_sp,
false);
}
}
return option_value_sp;
}
bool Instruction::TestEmulation(Stream *out_stream, const char *file_name) {
if (!out_stream)
return false;
if (!file_name) {
out_stream->Printf("Instruction::TestEmulation: Missing file_name.");
return false;
}
FILE *test_file = FileSystem::Fopen(file_name, "r");
if (!test_file) {
out_stream->Printf(
"Instruction::TestEmulation: Attempt to open test file failed.");
return false;
}
char buffer[256];
if (!fgets(buffer, 255, test_file)) {
out_stream->Printf(
"Instruction::TestEmulation: Error reading first line of test file.\n");
fclose(test_file);
return false;
}
if (strncmp(buffer, "InstructionEmulationState={", 27) != 0) {
out_stream->Printf("Instructin::TestEmulation: Test file does not contain "
"emulation state dictionary\n");
fclose(test_file);
return false;
}
// Read all the test information from the test file into an
// OptionValueDictionary.
OptionValueSP data_dictionary_sp(ReadDictionary(test_file, out_stream));
if (!data_dictionary_sp) {
out_stream->Printf(
"Instruction::TestEmulation: Error reading Dictionary Object.\n");
fclose(test_file);
return false;
}
fclose(test_file);
OptionValueDictionary *data_dictionary =
data_dictionary_sp->GetAsDictionary();
static ConstString description_key("assembly_string");
static ConstString triple_key("triple");
OptionValueSP value_sp = data_dictionary->GetValueForKey(description_key);
if (!value_sp) {
out_stream->Printf("Instruction::TestEmulation: Test file does not "
"contain description string.\n");
return false;
}
SetDescription(value_sp->GetStringValue());
value_sp = data_dictionary->GetValueForKey(triple_key);
if (!value_sp) {
out_stream->Printf(
"Instruction::TestEmulation: Test file does not contain triple.\n");
return false;
}
ArchSpec arch;
arch.SetTriple(llvm::Triple(value_sp->GetStringValue()));
bool success = false;
std::unique_ptr<EmulateInstruction> insn_emulator_ap(
EmulateInstruction::FindPlugin(arch, eInstructionTypeAny, nullptr));
if (insn_emulator_ap)
success =
insn_emulator_ap->TestEmulation(out_stream, arch, data_dictionary);
if (success)
out_stream->Printf("Emulation test succeeded.");
else
out_stream->Printf("Emulation test failed.");
return success;
}
bool Instruction::Emulate(
const ArchSpec &arch, uint32_t evaluate_options, void *baton,
EmulateInstruction::ReadMemoryCallback read_mem_callback,
EmulateInstruction::WriteMemoryCallback write_mem_callback,
EmulateInstruction::ReadRegisterCallback read_reg_callback,
EmulateInstruction::WriteRegisterCallback write_reg_callback) {
std::unique_ptr<EmulateInstruction> insn_emulator_ap(
EmulateInstruction::FindPlugin(arch, eInstructionTypeAny, nullptr));
if (insn_emulator_ap) {
insn_emulator_ap->SetBaton(baton);
insn_emulator_ap->SetCallbacks(read_mem_callback, write_mem_callback,
read_reg_callback, write_reg_callback);
insn_emulator_ap->SetInstruction(GetOpcode(), GetAddress(), nullptr);
return insn_emulator_ap->EvaluateInstruction(evaluate_options);
}
return false;
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 Instruction::GetData(DataExtractor &data) {
return m_opcode.GetData(data);
}
InstructionList::InstructionList() : m_instructions() {}
Get rid of Debugger::FormatPrompt() and replace it with the new FormatEntity class. Why? Debugger::FormatPrompt() would run through the format prompt every time and parse it and emit it piece by piece. It also did formatting differently depending on which key/value pair it was parsing. The new code improves on this with the following features: 1 - Allow format strings to be parsed into a FormatEntity::Entry which can contain multiple child FormatEntity::Entry objects. This FormatEntity::Entry is a parsed version of what was previously always done in Debugger::FormatPrompt() so it is more efficient to emit formatted strings using the new parsed FormatEntity::Entry. 2 - Allows errors in format strings to be shown immediately when setting the settings (frame-format, thread-format, disassembly-format 3 - Allows auto completion by implementing a new OptionValueFormatEntity and switching frame-format, thread-format, and disassembly-format settings over to using it. 4 - The FormatEntity::Entry for each of the frame-format, thread-format, disassembly-format settings only replaces the old one if the format parses correctly 5 - Combines all consecutive string values together for efficient output. This means all "${ansi.*}" keys and all desensitized characters like "\n" "\t" "\0721" "\x23" will get combined with their previous strings 6 - ${*.script:} (like "${var.script:mymodule.my_var_function}") have all been switched over to use ${script.*:} "${script.var:mymodule.my_var_function}") to make the format easier to parse as I don't believe anyone was using these format string power user features. 7 - All key values pairs are defined in simple C arrays of entries so it is much easier to add new entries. These changes pave the way for subsequent modifications where we can modify formats to do more (like control the width of value strings can do more and add more functionality more easily like string formatting to control the width, printf formats and more). llvm-svn: 228207
2015-02-05 06:00:53 +08:00
InstructionList::~InstructionList() = default;
size_t 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(size_t idx) const {
InstructionSP inst_sp;
if (idx < m_instructions.size())
inst_sp = m_instructions[idx];
return inst_sp;
}
void InstructionList::Dump(Stream *s, bool show_address, bool show_bytes,
const ExecutionContext *exe_ctx) {
const uint32_t max_opcode_byte_size = GetMaxOpcocdeByteSize();
collection::const_iterator pos, begin, end;
const FormatEntity::Entry *disassembly_format = nullptr;
FormatEntity::Entry format;
if (exe_ctx && exe_ctx->HasTargetScope()) {
disassembly_format =
exe_ctx->GetTargetRef().GetDebugger().GetDisassemblyFormat();
} else {
FormatEntity::Parse("${addr}: ", format);
disassembly_format = &format;
}
for (begin = m_instructions.begin(), end = m_instructions.end(), pos = begin;
pos != end; ++pos) {
if (pos != begin)
s->EOL();
(*pos)->Dump(s, max_opcode_byte_size, show_address, show_bytes, exe_ctx,
nullptr, nullptr, disassembly_format, 0);
}
}
void InstructionList::Clear() { m_instructions.clear(); }
void InstructionList::Append(lldb::InstructionSP &inst_sp) {
if (inst_sp)
m_instructions.push_back(inst_sp);
}
uint32_t
InstructionList::GetIndexOfNextBranchInstruction(uint32_t start,
Target &target) const {
size_t num_instructions = m_instructions.size();
uint32_t next_branch = UINT32_MAX;
size_t i;
for (i = start; i < num_instructions; i++) {
if (m_instructions[i]->DoesBranch()) {
next_branch = i;
break;
}
}
// Hexagon needs the first instruction of the packet with the branch.
// Go backwards until we find an instruction marked end-of-packet, or
// until we hit start.
if (target.GetArchitecture().GetTriple().getArch() == llvm::Triple::hexagon) {
// If we didn't find a branch, find the last packet start.
if (next_branch == UINT32_MAX) {
i = num_instructions - 1;
}
while (i > start) {
--i;
Error error;
uint32_t inst_bytes;
bool prefer_file_cache = false; // Read from process if process is running
lldb::addr_t load_addr = LLDB_INVALID_ADDRESS;
target.ReadMemory(m_instructions[i]->GetAddress(), prefer_file_cache,
&inst_bytes, sizeof(inst_bytes), error, &load_addr);
// If we have an error reading memory, return start
if (!error.Success())
return start;
// check if this is the last instruction in a packet
// bits 15:14 will be 11b or 00b for a duplex
if (((inst_bytes & 0xC000) == 0xC000) ||
((inst_bytes & 0xC000) == 0x0000)) {
// instruction after this should be the start of next packet
next_branch = i + 1;
break;
}
}
if (next_branch == UINT32_MAX) {
// We couldn't find the previous packet, so return start
next_branch = start;
}
}
return next_branch;
}
uint32_t
InstructionList::GetIndexOfInstructionAtAddress(const Address &address) {
size_t num_instructions = m_instructions.size();
uint32_t index = UINT32_MAX;
for (size_t i = 0; i < num_instructions; i++) {
if (m_instructions[i]->GetAddress() == address) {
index = i;
break;
}
}
return index;
}
uint32_t
InstructionList::GetIndexOfInstructionAtLoadAddress(lldb::addr_t load_addr,
Target &target) {
Address address;
address.SetLoadAddress(load_addr, &target);
return GetIndexOfInstructionAtAddress(address);
}
size_t Disassembler::ParseInstructions(const ExecutionContext *exe_ctx,
const AddressRange &range,
Stream *error_strm_ptr,
bool prefer_file_cache) {
if (exe_ctx) {
Target *target = exe_ctx->GetTargetPtr();
const addr_t byte_size = range.GetByteSize();
if (target == nullptr || byte_size == 0 ||
!range.GetBaseAddress().IsValid())
return 0;
DataBufferHeap *heap_buffer = new DataBufferHeap(byte_size, '\0');
DataBufferSP data_sp(heap_buffer);
Error error;
lldb::addr_t load_addr = LLDB_INVALID_ADDRESS;
const size_t bytes_read = target->ReadMemory(
range.GetBaseAddress(), prefer_file_cache, heap_buffer->GetBytes(),
heap_buffer->GetByteSize(), error, &load_addr);
if (bytes_read > 0) {
if (bytes_read != heap_buffer->GetByteSize())
heap_buffer->SetByteSize(bytes_read);
DataExtractor data(data_sp, m_arch.GetByteOrder(),
m_arch.GetAddressByteSize());
const bool data_from_file = load_addr == LLDB_INVALID_ADDRESS;
return DecodeInstructions(range.GetBaseAddress(), data, 0, UINT32_MAX,
false, data_from_file);
} else if (error_strm_ptr) {
const char *error_cstr = error.AsCString();
if (error_cstr) {
error_strm_ptr->Printf("error: %s\n", error_cstr);
}
}
} else if (error_strm_ptr) {
error_strm_ptr->PutCString("error: invalid execution context\n");
}
return 0;
}
size_t Disassembler::ParseInstructions(const ExecutionContext *exe_ctx,
const Address &start,
uint32_t num_instructions,
bool prefer_file_cache) {
m_instruction_list.Clear();
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 (exe_ctx == nullptr || num_instructions == 0 || !start.IsValid())
return 0;
Target *target = exe_ctx->GetTargetPtr();
// Calculate the max buffer size we will need in order to disassemble
const addr_t byte_size = num_instructions * m_arch.GetMaximumOpcodeByteSize();
if (target == nullptr || byte_size == 0)
return 0;
DataBufferHeap *heap_buffer = new DataBufferHeap(byte_size, '\0');
DataBufferSP data_sp(heap_buffer);
Error error;
lldb::addr_t load_addr = LLDB_INVALID_ADDRESS;
const size_t bytes_read =
target->ReadMemory(start, prefer_file_cache, heap_buffer->GetBytes(),
byte_size, error, &load_addr);
const bool data_from_file = load_addr == LLDB_INVALID_ADDRESS;
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,
data_from_file);
return m_instruction_list.GetSize();
}
//----------------------------------------------------------------------
// Disassembler copy constructor
//----------------------------------------------------------------------
Disassembler::Disassembler(const ArchSpec &arch, const char *flavor)
: m_arch(arch), m_instruction_list(), m_base_addr(LLDB_INVALID_ADDRESS),
m_flavor() {
if (flavor == nullptr)
m_flavor.assign("default");
else
m_flavor.assign(flavor);
// If this is an arm variant that can only include thumb (T16, T32)
// instructions, force the arch triple to be "thumbv.." instead of
// "armv..."
if (arch.IsAlwaysThumbInstructions()) {
std::string thumb_arch_name(arch.GetTriple().getArchName().str());
// Replace "arm" with "thumb" so we get all thumb variants correct
if (thumb_arch_name.size() > 3) {
thumb_arch_name.erase(0, 3);
thumb_arch_name.insert(0, "thumb");
}
m_arch.SetTriple(thumb_arch_name.c_str());
}
}
Disassembler::~Disassembler() = default;
InstructionList &Disassembler::GetInstructionList() {
return m_instruction_list;
}
const InstructionList &Disassembler::GetInstructionList() const {
return m_instruction_list;
}
//----------------------------------------------------------------------
// Class PseudoInstruction
//----------------------------------------------------------------------
PseudoInstruction::PseudoInstruction()
: Instruction(Address(), eAddressClassUnknown), m_description() {}
PseudoInstruction::~PseudoInstruction() = default;
bool PseudoInstruction::DoesBranch() {
// This is NOT a valid question for a pseudo instruction.
return false;
}
bool PseudoInstruction::HasDelaySlot() {
// This is NOT a valid question for a pseudo instruction.
return false;
}
size_t PseudoInstruction::Decode(const lldb_private::Disassembler &disassembler,
const lldb_private::DataExtractor &data,
lldb::offset_t data_offset) {
return m_opcode.GetByteSize();
}
void PseudoInstruction::SetOpcode(size_t opcode_size, void *opcode_data) {
if (!opcode_data)
return;
switch (opcode_size) {
case 8: {
uint8_t value8 = *((uint8_t *)opcode_data);
m_opcode.SetOpcode8(value8, eByteOrderInvalid);
break;
}
case 16: {
uint16_t value16 = *((uint16_t *)opcode_data);
m_opcode.SetOpcode16(value16, eByteOrderInvalid);
break;
}
case 32: {
uint32_t value32 = *((uint32_t *)opcode_data);
m_opcode.SetOpcode32(value32, eByteOrderInvalid);
break;
}
case 64: {
uint64_t value64 = *((uint64_t *)opcode_data);
m_opcode.SetOpcode64(value64, eByteOrderInvalid);
break;
}
default:
break;
}
}
void PseudoInstruction::SetDescription(const char *description) {
if (description && strlen(description) > 0)
m_description = description;
}