In a PR last month I changed the ObjectFile CreateInstance etc methods to accept an optional DataExtractorSP instead of a DataBufferSP, and retain the extractor in a shared pointer internally in all of the ObjectFile subclasses. This is laying the groundwork for using a VirtualDataExtractor for some Mach-O binaries on macOS, where the segments of the binary are out-of-order in actual memory, and we add a lookup table to make it appear that the TEXT segment is at offset 0 in the Extractor, etc. Working on the actual implementation, I realized we were still using DataBufferSP's in ModuleSpec and Module, as well as in ObjectFile::GetModuleSpecifications. I originally was making a much larger NFC change where I had all ObjectFile subclasses operating on DataExtractors throughout their implementation, as well as in the DWARF parser. It was a very large patchset. Many subclasses start with their DataExtractor, then create smaller DataExtractors for parts of the binary image - the string table, the symbol table, etc., for processing. After consideration and discussion with Jonas, we agreed that a segment/section of a binary will never require a lookup table to access the bytes within it, so I changed VirtualDataExtractor::GetSubsetExtractorSP to (1) require that the Subset be contained within a single lookup table entry, and (2) return a simple DataExtractor bounded on that byte range. By doing this, I was able to remove all of my very-invasive changes to the ObjectFile subclass internals; it's only when they are operating on the entire binary image that care is needed. One pattern that subclasses like ObjectFileBreakpad use is to take an ArrayRef of the DataBuffer for a binary, then create a StringRef of that, then look for strings in it. With a VirtualDataExtractor and out-of-order binary segments, with gaps between them, this allows us to search the entire buffer looking for a string, and segfault when it gets to an unmapped region of the buffer. I added a VirtualDataExtractor::GetSubsetExtractorSP(0) which gets the largest contiguous memory region starting at offset 0 for this use case, and I added a comment about what was being done there because I know it is not obvious, and people not working on macOS wouldn't be familiar with the requirement. (when we have a ModuleSpec with a DataExtractor, any of the ObjectFile subclasses get a shot at Creating, so they all have to be able to iterate on these) rdar://148939795
95 lines
3.7 KiB
C++
95 lines
3.7 KiB
C++
//===-- ObjectContainerMachOFileset.h ---------------------------*- C++ -*-===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLDB_SOURCE_PLUGINS_OBJECTCONTAINER_MACH_O_FILESET_OBJECTCONTAINERMADCHOFILESET_H
|
|
#define LLDB_SOURCE_PLUGINS_OBJECTCONTAINER_MACH_O_FILESET_OBJECTCONTAINERMADCHOFILESET_H
|
|
|
|
#include "lldb/Host/SafeMachO.h"
|
|
#include "lldb/Symbol/ObjectContainer.h"
|
|
#include "lldb/Utility/FileSpec.h"
|
|
|
|
namespace lldb_private {
|
|
|
|
class ObjectContainerMachOFileset : public lldb_private::ObjectContainer {
|
|
public:
|
|
ObjectContainerMachOFileset(const lldb::ModuleSP &module_sp,
|
|
lldb::DataBufferSP &data_sp,
|
|
lldb::offset_t data_offset,
|
|
const lldb_private::FileSpec *file,
|
|
lldb::offset_t offset, lldb::offset_t length);
|
|
|
|
ObjectContainerMachOFileset(const lldb::ModuleSP &module_sp,
|
|
lldb::WritableDataBufferSP data_sp,
|
|
const lldb::ProcessSP &process_sp,
|
|
lldb::addr_t header_addr);
|
|
|
|
~ObjectContainerMachOFileset() override;
|
|
|
|
static void Initialize();
|
|
static void Terminate();
|
|
|
|
static llvm::StringRef GetPluginNameStatic() { return "mach-o-fileset"; }
|
|
|
|
static llvm::StringRef GetPluginDescriptionStatic() {
|
|
return "Mach-O Fileset container reader.";
|
|
}
|
|
|
|
static lldb_private::ObjectContainer *
|
|
CreateInstance(const lldb::ModuleSP &module_sp, lldb::DataBufferSP &data_sp,
|
|
lldb::offset_t data_offset, const lldb_private::FileSpec *file,
|
|
lldb::offset_t offset, lldb::offset_t length);
|
|
|
|
static lldb_private::ObjectContainer *CreateMemoryInstance(
|
|
const lldb::ModuleSP &module_sp, lldb::WritableDataBufferSP data_sp,
|
|
const lldb::ProcessSP &process_sp, lldb::addr_t header_addr);
|
|
|
|
static size_t GetModuleSpecifications(const lldb_private::FileSpec &file,
|
|
lldb::DataExtractorSP &extractor_sp,
|
|
lldb::offset_t data_offset,
|
|
lldb::offset_t file_offset,
|
|
lldb::offset_t length,
|
|
lldb_private::ModuleSpecList &specs);
|
|
|
|
static bool MagicBytesMatch(const lldb_private::DataExtractor &data);
|
|
static bool MagicBytesMatch(lldb::DataBufferSP data_sp,
|
|
lldb::addr_t data_offset,
|
|
lldb::addr_t data_length);
|
|
|
|
bool ParseHeader() override;
|
|
|
|
size_t GetNumObjects() const override { return m_entries.size(); }
|
|
|
|
lldb::ObjectFileSP GetObjectFile(const lldb_private::FileSpec *file) override;
|
|
|
|
llvm::StringRef GetPluginName() override { return GetPluginNameStatic(); }
|
|
|
|
struct Entry {
|
|
Entry(uint64_t vmaddr, uint64_t fileoff, std::string id)
|
|
: vmaddr(vmaddr), fileoff(fileoff), id(id) {}
|
|
uint64_t vmaddr;
|
|
uint64_t fileoff;
|
|
std::string id;
|
|
};
|
|
|
|
Entry *FindEntry(llvm::StringRef id);
|
|
|
|
private:
|
|
static bool ParseHeader(lldb_private::DataExtractor &data,
|
|
const lldb_private::FileSpec &file,
|
|
lldb::offset_t file_offset,
|
|
std::vector<Entry> &entries);
|
|
|
|
std::vector<Entry> m_entries;
|
|
lldb::ProcessWP m_process_wp;
|
|
const lldb::addr_t m_memory_addr;
|
|
};
|
|
|
|
} // namespace lldb_private
|
|
|
|
#endif // LLDB_SOURCE_PLUGINS_OBJECTCONTAINER_MACH_O_FILESET_OBJECTCONTAINERMADCHOFILESET_H
|