llvm-project/lld/MachO/InputFiles.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

171 lines
5.0 KiB
C
Raw Normal View History

//===- InputFiles.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 LLD_MACHO_INPUT_FILES_H
#define LLD_MACHO_INPUT_FILES_H
#include "MachOStructs.h"
#include "lld/Common/LLVM.h"
#include "lld/Common/Memory.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/BinaryFormat/MachO.h"
[lld-macho] Emit STABS symbols for debugging, and drop debug sections Debug sections contain a large amount of data. In order not to bloat the size of the final binary, we remove them and instead emit STABS symbols for `dsymutil` and the debugger to locate their contents in the object files. With this diff, `dsymutil` is able to locate the debug info. However, we need a few more features before `lldb` is able to work well with our binaries -- e.g. having `LC_DYSYMTAB` accurately reflect the number of local symbols, emitting `LC_UUID`, and more. Those will be handled in follow-up diffs. Note also that the STABS we emit differ slightly from what ld64 does. First, we emit the path to the source file as one `N_SO` symbol instead of two. (`ld64` emits one `N_SO` for the dirname and one of the basename.) Second, we do not emit `N_BNSYM` and `N_ENSYM` STABS to mark the start and end of functions, because the `N_FUN` STABS already serve that purpose. @clayborg recommended these changes based on his knowledge of what the debugging tools look for. Additionally, this current implementation doesn't accurately reflect the size of function symbols. It uses the size of their containing sectioins as a proxy, but that is only accurate if `.subsections_with_symbols` is set, and if there isn't an `N_ALT_ENTRY` in that particular subsection. I think we have two options to solve this: 1. We can split up subsections by symbol even if `.subsections_with_symbols` is not set, but include constraints to ensure those subsections retain their order in the final output. This is `ld64`'s approach. 2. We could just add a `size` field to our `Symbol` class. This seems simpler, and I'm more inclined toward it, but I'm not sure if there are use cases that it doesn't handle well. As such I'm punting on the decision for now. Reviewed By: clayborg Differential Revision: https://reviews.llvm.org/D89257
2020-12-02 06:45:01 +08:00
#include "llvm/DebugInfo/DWARF/DWARFUnit.h"
#include "llvm/Object/Archive.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/TextAPI/MachO/InterfaceFile.h"
#include "llvm/TextAPI/MachO/TextAPIReader.h"
#include <map>
#include <vector>
namespace llvm {
namespace lto {
class InputFile;
} // namespace lto
class TarWriter;
} // namespace llvm
namespace lld {
namespace macho {
class InputSection;
class Symbol;
struct Reloc;
// If --reproduce option is given, all input files are written
// to this tar archive.
extern std::unique_ptr<llvm::TarWriter> tar;
// If .subsections_via_symbols is set, each InputSection will be split along
// symbol boundaries. The keys of a SubsectionMap represent the offsets of
// each subsection from the start of the original pre-split InputSection.
using SubsectionMap = std::map<uint32_t, InputSection *>;
class InputFile {
public:
enum Kind {
ObjKind,
OpaqueKind,
DylibKind,
ArchiveKind,
BitcodeKind,
};
virtual ~InputFile() = default;
Kind kind() const { return fileKind; }
StringRef getName() const { return name; }
MemoryBufferRef mb;
std::vector<Symbol *> symbols;
ArrayRef<llvm::MachO::section_64> sectionHeaders;
std::vector<SubsectionMap> subsections;
protected:
InputFile(Kind kind, MemoryBufferRef mb)
: mb(mb), fileKind(kind), name(mb.getBufferIdentifier()) {}
InputFile(Kind kind, const llvm::MachO::InterfaceFile &interface)
: fileKind(kind), name(saver.save(interface.getPath())) {}
void parseSections(ArrayRef<llvm::MachO::section_64>);
void parseSymbols(ArrayRef<lld::structs::nlist_64> nList, const char *strtab,
bool subsectionsViaSymbols);
Symbol *parseNonSectionSymbol(const structs::nlist_64 &sym, StringRef name);
void parseRelocations(const llvm::MachO::section_64 &, SubsectionMap &);
private:
const Kind fileKind;
const StringRef name;
};
// .o file
class ObjFile : public InputFile {
public:
explicit ObjFile(MemoryBufferRef mb, uint32_t modTime);
static bool classof(const InputFile *f) { return f->kind() == ObjKind; }
[lld-macho] Emit STABS symbols for debugging, and drop debug sections Debug sections contain a large amount of data. In order not to bloat the size of the final binary, we remove them and instead emit STABS symbols for `dsymutil` and the debugger to locate their contents in the object files. With this diff, `dsymutil` is able to locate the debug info. However, we need a few more features before `lldb` is able to work well with our binaries -- e.g. having `LC_DYSYMTAB` accurately reflect the number of local symbols, emitting `LC_UUID`, and more. Those will be handled in follow-up diffs. Note also that the STABS we emit differ slightly from what ld64 does. First, we emit the path to the source file as one `N_SO` symbol instead of two. (`ld64` emits one `N_SO` for the dirname and one of the basename.) Second, we do not emit `N_BNSYM` and `N_ENSYM` STABS to mark the start and end of functions, because the `N_FUN` STABS already serve that purpose. @clayborg recommended these changes based on his knowledge of what the debugging tools look for. Additionally, this current implementation doesn't accurately reflect the size of function symbols. It uses the size of their containing sectioins as a proxy, but that is only accurate if `.subsections_with_symbols` is set, and if there isn't an `N_ALT_ENTRY` in that particular subsection. I think we have two options to solve this: 1. We can split up subsections by symbol even if `.subsections_with_symbols` is not set, but include constraints to ensure those subsections retain their order in the final output. This is `ld64`'s approach. 2. We could just add a `size` field to our `Symbol` class. This seems simpler, and I'm more inclined toward it, but I'm not sure if there are use cases that it doesn't handle well. As such I'm punting on the decision for now. Reviewed By: clayborg Differential Revision: https://reviews.llvm.org/D89257
2020-12-02 06:45:01 +08:00
llvm::DWARFUnit *compileUnit = nullptr;
StringRef archiveName = "";
const uint32_t modTime;
[lld-macho] Emit STABS symbols for debugging, and drop debug sections Debug sections contain a large amount of data. In order not to bloat the size of the final binary, we remove them and instead emit STABS symbols for `dsymutil` and the debugger to locate their contents in the object files. With this diff, `dsymutil` is able to locate the debug info. However, we need a few more features before `lldb` is able to work well with our binaries -- e.g. having `LC_DYSYMTAB` accurately reflect the number of local symbols, emitting `LC_UUID`, and more. Those will be handled in follow-up diffs. Note also that the STABS we emit differ slightly from what ld64 does. First, we emit the path to the source file as one `N_SO` symbol instead of two. (`ld64` emits one `N_SO` for the dirname and one of the basename.) Second, we do not emit `N_BNSYM` and `N_ENSYM` STABS to mark the start and end of functions, because the `N_FUN` STABS already serve that purpose. @clayborg recommended these changes based on his knowledge of what the debugging tools look for. Additionally, this current implementation doesn't accurately reflect the size of function symbols. It uses the size of their containing sectioins as a proxy, but that is only accurate if `.subsections_with_symbols` is set, and if there isn't an `N_ALT_ENTRY` in that particular subsection. I think we have two options to solve this: 1. We can split up subsections by symbol even if `.subsections_with_symbols` is not set, but include constraints to ensure those subsections retain their order in the final output. This is `ld64`'s approach. 2. We could just add a `size` field to our `Symbol` class. This seems simpler, and I'm more inclined toward it, but I'm not sure if there are use cases that it doesn't handle well. As such I'm punting on the decision for now. Reviewed By: clayborg Differential Revision: https://reviews.llvm.org/D89257
2020-12-02 06:45:01 +08:00
private:
void parseDebugInfo();
};
// command-line -sectcreate file
class OpaqueFile : public InputFile {
public:
explicit OpaqueFile(MemoryBufferRef mb, StringRef segName,
StringRef sectName);
static bool classof(const InputFile *f) { return f->kind() == OpaqueKind; }
};
// .dylib file
class DylibFile : public InputFile {
public:
// Mach-O dylibs can re-export other dylibs as sub-libraries, meaning that the
// symbols in those sub-libraries will be available under the umbrella
// library's namespace. Those sub-libraries can also have their own
// re-exports. When loading a re-exported dylib, `umbrella` should be set to
// the root dylib to ensure symbols in the child library are correctly bound
// to the root. On the other hand, if a dylib is being directly loaded
// (through an -lfoo flag), then `umbrella` should be a nullptr.
explicit DylibFile(MemoryBufferRef mb, DylibFile *umbrella = nullptr);
explicit DylibFile(const llvm::MachO::InterfaceFile &interface,
DylibFile *umbrella = nullptr);
static bool classof(const InputFile *f) { return f->kind() == DylibKind; }
StringRef dylibName;
uint64_t ordinal = 0; // Ordinal numbering starts from 1, so 0 is a sentinel
bool reexport = false;
bool forceWeakImport = false;
std::vector<DylibFile *> reexported;
};
// .a file
class ArchiveFile : public InputFile {
public:
explicit ArchiveFile(std::unique_ptr<llvm::object::Archive> &&file);
static bool classof(const InputFile *f) { return f->kind() == ArchiveKind; }
void fetch(const llvm::object::Archive::Symbol &sym);
private:
std::unique_ptr<llvm::object::Archive> file;
// Keep track of children fetched from the archive by tracking
// which address offsets have been fetched already.
llvm::DenseSet<uint64_t> seen;
};
class BitcodeFile : public InputFile {
public:
explicit BitcodeFile(MemoryBufferRef mb);
static bool classof(const InputFile *f) { return f->kind() == BitcodeKind; }
std::unique_ptr<llvm::lto::InputFile> obj;
};
extern std::vector<InputFile *> inputFiles;
llvm::Optional<MemoryBufferRef> readFile(StringRef path);
const llvm::MachO::load_command *
findCommand(const llvm::MachO::mach_header_64 *, uint32_t type);
} // namespace macho
std::string toString(const macho::InputFile *file);
} // namespace lld
#endif