Jonas Devlieghere cf3524a574
[lldb] Introduce new SymbolFileJSON and ObjectFileJSON
Introduce a new object and symbol file format with the goal of mapping
addresses to symbol names. I'd like to think of is as an extremely
simple textual symtab. The file format consists of a triple, a UUID and
a list of symbols. JSON is used for the encoding, but that's mostly an
implementation detail. The goal of the format was to be simple and human
readable.

The new file format is motivated by two use cases:

 - Stripped binaries: when a binary is stripped, you lose the ability to
   do thing like setting symbolic breakpoints. You can keep the
   unstripped binary around, but if all you need is the stripped
   symbols then that's a lot of overhead. Instead, we could save the
   stripped symbols to a file and load them in the debugger when
   needed. I want to extend llvm-strip to have a mode where it emits
   this new file format.

 - Interactive crashlogs: with interactive crashlogs, if we don't have
   the binary or the dSYM for a particular module, we currently show an
   unnamed symbol for those frames. This is a regression compared to the
   textual format, that has these frames pre-symbolicated. Given that
   this information is available in the JSON crashlog, we need a way to
   tell LLDB about it. With the new symbol file format, we can easily
   synthesize a symbol file for each of those modules and load them to
   symbolicate those frames.

Here's an example of the file format:

 {
     "triple": "arm64-apple-macosx13.0.0",
     "uuid": "36D0CCE7-8ED2-3CA3-96B0-48C1764DA908",
     "symbols": [
         {
             "name": "main",
             "type": "code",
             "size": 32,
             "address": 4294983568
         },
         {
             "name": "foo",
             "type": "code",
             "size": 8,
             "address": 4294983560
         }
     ]
 }

Differential revision: https://reviews.llvm.org/D145180
2023-03-08 20:56:11 -08:00

177 lines
5.4 KiB
C++

//===-- ObjectFileJSON.cpp ------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "Plugins/ObjectFile/JSON/ObjectFileJSON.h"
#include "lldb/Core/Module.h"
#include "lldb/Core/ModuleSpec.h"
#include "lldb/Core/PluginManager.h"
#include "lldb/Core/Section.h"
#include "lldb/Symbol/Symbol.h"
#include "lldb/Utility/LLDBLog.h"
#include "lldb/Utility/Log.h"
#include "llvm/ADT/DenseSet.h"
#include <optional>
using namespace llvm;
using namespace lldb;
using namespace lldb_private;
LLDB_PLUGIN_DEFINE(ObjectFileJSON)
char ObjectFileJSON::ID;
void ObjectFileJSON::Initialize() {
PluginManager::RegisterPlugin(GetPluginNameStatic(),
GetPluginDescriptionStatic(), CreateInstance,
CreateMemoryInstance, GetModuleSpecifications);
}
void ObjectFileJSON::Terminate() {
PluginManager::UnregisterPlugin(CreateInstance);
}
ObjectFile *
ObjectFileJSON::CreateInstance(const ModuleSP &module_sp, DataBufferSP data_sp,
offset_t data_offset, const FileSpec *file,
offset_t file_offset, offset_t length) {
if (!data_sp) {
data_sp = MapFileData(*file, length, file_offset);
if (!data_sp)
return nullptr;
data_offset = 0;
}
if (!MagicBytesMatch(data_sp, 0, data_sp->GetByteSize()))
return nullptr;
if (data_sp->GetByteSize() < length) {
data_sp = MapFileData(*file, length, file_offset);
if (!data_sp)
return nullptr;
data_offset = 0;
}
auto text =
llvm::StringRef(reinterpret_cast<const char *>(data_sp->GetBytes()));
Expected<json::Value> json = json::parse(text);
if (!json) {
llvm::consumeError(json.takeError());
return nullptr;
}
json::Path::Root root;
Header header;
if (!fromJSON(*json, header, root))
return nullptr;
ArchSpec arch(header.triple);
UUID uuid;
uuid.SetFromStringRef(header.uuid);
Body body;
fromJSON(*json, body, root);
return new ObjectFileJSON(module_sp, data_sp, data_offset, file, file_offset,
length, std::move(arch), std::move(uuid),
std::move(body.symbols));
}
ObjectFile *ObjectFileJSON::CreateMemoryInstance(const ModuleSP &module_sp,
WritableDataBufferSP data_sp,
const ProcessSP &process_sp,
addr_t header_addr) {
return nullptr;
}
size_t ObjectFileJSON::GetModuleSpecifications(
const FileSpec &file, DataBufferSP &data_sp, offset_t data_offset,
offset_t file_offset, offset_t length, ModuleSpecList &specs) {
if (!MagicBytesMatch(data_sp, data_offset, data_sp->GetByteSize()))
return 0;
auto text =
llvm::StringRef(reinterpret_cast<const char *>(data_sp->GetBytes()));
Expected<json::Value> json = json::parse(text);
if (!json) {
llvm::consumeError(json.takeError());
return 0;
}
json::Path::Root root;
Header header;
if (!fromJSON(*json, header, root))
return 0;
ArchSpec arch(header.triple);
UUID uuid;
uuid.SetFromStringRef(header.uuid);
ModuleSpec spec(file, std::move(arch));
spec.GetUUID() = std::move(uuid);
specs.Append(spec);
return 1;
}
ObjectFileJSON::ObjectFileJSON(const ModuleSP &module_sp, DataBufferSP &data_sp,
offset_t data_offset, const FileSpec *file,
offset_t offset, offset_t length, ArchSpec arch,
UUID uuid, std::vector<JSONSymbol> symbols)
: ObjectFile(module_sp, file, offset, length, data_sp, data_offset),
m_arch(std::move(arch)), m_uuid(std::move(uuid)),
m_symbols(std::move(symbols)) {}
bool ObjectFileJSON::ParseHeader() {
// We already parsed the header during initialization.
return true;
}
void ObjectFileJSON::ParseSymtab(Symtab &symtab) {
Log *log = GetLog(LLDBLog::Symbols);
SectionList *section_list = GetModule()->GetSectionList();
for (JSONSymbol json_symbol : m_symbols) {
llvm::Expected<Symbol> symbol = Symbol::FromJSON(json_symbol, section_list);
if (!symbol) {
LLDB_LOG_ERROR(log, symbol.takeError(), "invalid symbol");
continue;
}
symtab.AddSymbol(*symbol);
}
symtab.Finalize();
}
void ObjectFileJSON::CreateSections(SectionList &unified_section_list) {}
bool ObjectFileJSON::MagicBytesMatch(DataBufferSP data_sp,
lldb::addr_t data_offset,
lldb::addr_t data_length) {
DataExtractor data;
data.SetData(data_sp, data_offset, data_length);
lldb::offset_t offset = 0;
uint32_t magic = data.GetU8(&offset);
return magic == '{';
}
namespace lldb_private {
bool fromJSON(const json::Value &value, ObjectFileJSON::Header &header,
json::Path path) {
json::ObjectMapper o(value, path);
return o && o.map("triple", header.triple) && o.map("uuid", header.uuid);
}
bool fromJSON(const json::Value &value, ObjectFileJSON::Body &body,
json::Path path) {
json::ObjectMapper o(value, path);
return o && o.map("symbols", body.symbols);
}
} // namespace lldb_private