llvm-project/lld/ELF/Driver.cpp

1406 lines
51 KiB
C++
Raw Normal View History

//===- Driver.cpp ---------------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The driver drives the entire linking process. It is responsible for
// parsing command line options and doing whatever it is instructed to do.
//
// One notable thing in the LLD's driver when compared to other linkers is
// that the LLD's driver is agnostic on the host operating system.
// Other linkers usually have implicit default values (such as a dynamic
// linker path or library paths) for each host OS.
//
// I don't think implicit default values are useful because they are
// usually explicitly specified by the compiler driver. They can even
// be harmful when you are doing cross-linking. Therefore, in LLD, we
2017-03-24 08:15:57 +08:00
// simply trust the compiler driver to pass all required options and
// don't try to make effort on our side.
//
//===----------------------------------------------------------------------===//
#include "Driver.h"
#include "Config.h"
#include "Filesystem.h"
#include "ICF.h"
#include "InputFiles.h"
#include "InputSection.h"
#include "LinkerScript.h"
#include "MarkLive.h"
#include "OutputSections.h"
#include "ScriptParser.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "Writer.h"
#include "lld/Common/Args.h"
#include "lld/Common/Driver.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "lld/Common/TargetOptionsCommandFlags.h"
#include "lld/Common/Threads.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/SetVector.h"
2015-09-12 05:18:56 +08:00
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/TarWriter.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/raw_ostream.h"
#include <cstdlib>
2015-10-11 10:22:31 +08:00
#include <utility>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::sys;
using namespace lld;
2016-02-28 08:25:54 +08:00
using namespace lld::elf;
2016-02-28 08:25:54 +08:00
Configuration *elf::Config;
LinkerDriver *elf::Driver;
static void setConfigs(opt::InputArgList &Args);
bool elf::link(ArrayRef<const char *> Args, bool CanExitEarly,
raw_ostream &Error) {
errorHandler().LogName = Args[0];
errorHandler().ErrorLimitExceededMsg =
"too many errors emitted, stopping now (use "
"-error-limit=0 to see all errors)";
errorHandler().ErrorOS = &Error;
errorHandler().ExitEarly = CanExitEarly;
errorHandler().ColorDiagnostics = Error.has_colors();
InputSections.clear();
OutputSections.clear();
Tar = nullptr;
BinaryFiles.clear();
BitcodeFiles.clear();
ObjectFiles.clear();
SharedFiles.clear();
Config = make<Configuration>();
Driver = make<LinkerDriver>();
Script = make<LinkerScript>();
Symtab = make<SymbolTable>();
Config->ProgName = Args[0];
Driver->main(Args);
// Exit immediately if we don't need to return to the caller.
// This saves time because the overhead of calling destructors
// for all globally-allocated objects is not negligible.
if (CanExitEarly)
exitLld(errorCount() ? 1 : 0);
freeArena();
return !errorCount();
}
// Parses a linker -m option.
static std::tuple<ELFKind, uint16_t, uint8_t> parseEmulation(StringRef Emul) {
uint8_t OSABI = 0;
StringRef S = Emul;
if (S.endswith("_fbsd")) {
S = S.drop_back(5);
OSABI = ELFOSABI_FREEBSD;
}
std::pair<ELFKind, uint16_t> Ret =
StringSwitch<std::pair<ELFKind, uint16_t>>(S)
.Cases("aarch64elf", "aarch64linux", "aarch64_elf64_le_vec",
{ELF64LEKind, EM_AARCH64})
.Cases("armelf", "armelf_linux_eabi", {ELF32LEKind, EM_ARM})
.Case("elf32_x86_64", {ELF32LEKind, EM_X86_64})
.Cases("elf32btsmip", "elf32btsmipn32", {ELF32BEKind, EM_MIPS})
.Cases("elf32ltsmip", "elf32ltsmipn32", {ELF32LEKind, EM_MIPS})
.Case("elf32ppc", {ELF32BEKind, EM_PPC})
.Case("elf64btsmip", {ELF64BEKind, EM_MIPS})
.Case("elf64ltsmip", {ELF64LEKind, EM_MIPS})
.Case("elf64ppc", {ELF64BEKind, EM_PPC64})
.Case("elf64lppc", {ELF64LEKind, EM_PPC64})
.Cases("elf_amd64", "elf_x86_64", {ELF64LEKind, EM_X86_64})
.Case("elf_i386", {ELF32LEKind, EM_386})
.Case("elf_iamcu", {ELF32LEKind, EM_IAMCU})
.Default({ELFNoneKind, EM_NONE});
if (Ret.first == ELFNoneKind)
error("unknown emulation: " + Emul);
return std::make_tuple(Ret.first, Ret.second, OSABI);
}
// Returns slices of MB by parsing MB as an archive file.
// Each slice consists of a member file in the archive.
std::vector<std::pair<MemoryBufferRef, uint64_t>> static getArchiveMembers(
MemoryBufferRef MB) {
std::unique_ptr<Archive> File =
CHECK(Archive::create(MB),
MB.getBufferIdentifier() + ": failed to parse archive");
std::vector<std::pair<MemoryBufferRef, uint64_t>> V;
Error Err = Error::success();
bool AddToTar = File->isThin() && Tar;
for (const ErrorOr<Archive::Child> &COrErr : File->children(Err)) {
Archive::Child C =
CHECK(COrErr, MB.getBufferIdentifier() +
": could not get the child of the archive");
MemoryBufferRef MBRef =
CHECK(C.getMemoryBufferRef(),
MB.getBufferIdentifier() +
": could not get the buffer for a child of the archive");
if (AddToTar)
Tar->append(relativeToRoot(check(C.getFullName())), MBRef.getBuffer());
V.push_back(std::make_pair(MBRef, C.getChildOffset()));
}
if (Err)
fatal(MB.getBufferIdentifier() + ": Archive::children failed: " +
toString(std::move(Err)));
// Take ownership of memory buffers created for members of thin archives.
for (std::unique_ptr<MemoryBuffer> &MB : File->takeThinBuffers())
make<std::unique_ptr<MemoryBuffer>>(std::move(MB));
return V;
}
// Opens a file and create a file object. Path has to be resolved already.
void LinkerDriver::addFile(StringRef Path, bool WithLOption) {
using namespace sys::fs;
Optional<MemoryBufferRef> Buffer = readFile(Path);
if (!Buffer.hasValue())
return;
MemoryBufferRef MBRef = *Buffer;
if (InBinary) {
Files.push_back(make<BinaryFile>(MBRef));
return;
}
switch (identify_magic(MBRef.getBuffer())) {
case file_magic::unknown:
readLinkerScript(MBRef);
return;
case file_magic::archive: {
// Handle -whole-archive.
if (InWholeArchive) {
for (const auto &P : getArchiveMembers(MBRef))
Files.push_back(createObjectFile(P.first, Path, P.second));
return;
}
std::unique_ptr<Archive> File =
CHECK(Archive::create(MBRef), Path + ": failed to parse archive");
// If an archive file has no symbol table, it is likely that a user
// is attempting LTO and using a default ar command that doesn't
// understand the LLVM bitcode file. It is a pretty common error, so
// we'll handle it as if it had a symbol table.
if (!File->isEmpty() && !File->hasSymbolTable()) {
for (const auto &P : getArchiveMembers(MBRef))
Files.push_back(make<LazyObjFile>(P.first, Path, P.second));
return;
}
// Handle the regular case.
Files.push_back(make<ArchiveFile>(std::move(File)));
return;
}
case file_magic::elf_shared_object:
if (Config->Relocatable) {
error("attempted static link of dynamic object " + Path);
return;
}
// DSOs usually have DT_SONAME tags in their ELF headers, and the
// sonames are used to identify DSOs. But if they are missing,
// they are identified by filenames. We don't know whether the new
// file has a DT_SONAME or not because we haven't parsed it yet.
// Here, we set the default soname for the file because we might
// need it later.
//
// If a file was specified by -lfoo, the directory part is not
// significant, as a user did not specify it. This behavior is
// compatible with GNU.
Files.push_back(
createSharedFile(MBRef, WithLOption ? path::filename(Path) : Path));
return;
case file_magic::bitcode:
case file_magic::elf_relocatable:
if (InLib)
Files.push_back(make<LazyObjFile>(MBRef, "", 0));
else
Files.push_back(createObjectFile(MBRef));
break;
default:
error(Path + ": unknown file type");
}
}
// Add a given library by searching it from input search paths.
void LinkerDriver::addLibrary(StringRef Name) {
if (Optional<std::string> Path = searchLibrary(Name))
addFile(*Path, /*WithLOption=*/true);
else
error("unable to find library -l" + Name);
}
// This function is called on startup. We need this for LTO since
// LTO calls LLVM functions to compile bitcode files to native code.
// Technically this can be delayed until we read bitcode files, but
// we don't bother to do lazily because the initialization is fast.
static void initLLVM() {
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
InitializeAllAsmParsers();
}
// Some command line options or some combinations of them are not allowed.
// This function checks for such errors.
static void checkOptions(opt::InputArgList &Args) {
// The MIPS ABI as of 2016 does not support the GNU-style symbol lookup
// table which is a relatively new feature.
if (Config->EMachine == EM_MIPS && Config->GnuHash)
error("the .gnu.hash section is not compatible with the MIPS target.");
if (Config->FixCortexA53Errata843419 && Config->EMachine != EM_AARCH64)
error("--fix-cortex-a53-843419 is only supported on AArch64 targets.");
if (Config->Pie && Config->Shared)
error("-shared and -pie may not be used together");
if (!Config->Shared && !Config->FilterList.empty())
error("-F may not be used without -shared");
if (!Config->Shared && !Config->AuxiliaryList.empty())
error("-f may not be used without -shared");
if (!Config->Relocatable && !Config->DefineCommon)
error("-no-define-common not supported in non relocatable output");
if (Config->Relocatable) {
if (Config->Shared)
error("-r and -shared may not be used together");
if (Config->GcSections)
error("-r and --gc-sections may not be used together");
if (Config->ICF)
error("-r and --icf may not be used together");
if (Config->Pie)
error("-r and -pie may not be used together");
}
}
static const char *getReproduceOption(opt::InputArgList &Args) {
if (auto *Arg = Args.getLastArg(OPT_reproduce))
return Arg->getValue();
return getenv("LLD_REPRODUCE");
}
static bool hasZOption(opt::InputArgList &Args, StringRef Key) {
for (auto *Arg : Args.filtered(OPT_z))
if (Key == Arg->getValue())
return true;
return false;
}
static bool getZFlag(opt::InputArgList &Args, StringRef K1, StringRef K2,
bool Default) {
for (auto *Arg : Args.filtered_reverse(OPT_z)) {
if (K1 == Arg->getValue())
return true;
if (K2 == Arg->getValue())
return false;
}
return Default;
}
static bool isKnown(StringRef S) {
return S == "combreloc" || S == "copyreloc" || S == "defs" ||
S == "execstack" || S == "hazardplt" || S == "initfirst" ||
S == "keep-text-section-prefix" || S == "lazy" || S == "muldefs" ||
S == "nocombreloc" || S == "nocopyreloc" || S == "nodelete" ||
S == "nodlopen" || S == "noexecstack" ||
S == "nokeep-text-section-prefix" || S == "norelro" || S == "notext" ||
S == "now" || S == "origin" || S == "relro" || S == "retpolineplt" ||
S == "rodynamic" || S == "text" || S == "wxneeded" ||
S.startswith("max-page-size=") || S.startswith("stack-size=");
}
// Report an error for an unknown -z option.
static void checkZOptions(opt::InputArgList &Args) {
for (auto *Arg : Args.filtered(OPT_z))
if (!isKnown(Arg->getValue()))
error("unknown -z value: " + StringRef(Arg->getValue()));
}
void LinkerDriver::main(ArrayRef<const char *> ArgsArr) {
ELFOptTable Parser;
opt::InputArgList Args = Parser.parse(ArgsArr.slice(1));
// Interpret this flag early because error() depends on them.
errorHandler().ErrorLimit = args::getInteger(Args, OPT_error_limit, 20);
// Handle -help
if (Args.hasArg(OPT_help)) {
printHelp();
return;
}
// Handle -v or -version.
//
// A note about "compatible with GNU linkers" message: this is a hack for
// scripts generated by GNU Libtool 2.4.6 (released in February 2014 and
// still the newest version in March 2017) or earlier to recognize LLD as
// a GNU compatible linker. As long as an output for the -v option
// contains "GNU" or "with BFD", they recognize us as GNU-compatible.
//
// This is somewhat ugly hack, but in reality, we had no choice other
// than doing this. Considering the very long release cycle of Libtool,
// it is not easy to improve it to recognize LLD as a GNU compatible
// linker in a timely manner. Even if we can make it, there are still a
// lot of "configure" scripts out there that are generated by old version
// of Libtool. We cannot convince every software developer to migrate to
// the latest version and re-generate scripts. So we have this hack.
if (Args.hasArg(OPT_v) || Args.hasArg(OPT_version))
message(getLLDVersion() + " (compatible with GNU linkers)");
// The behavior of -v or --version is a bit strange, but this is
// needed for compatibility with GNU linkers.
if (Args.hasArg(OPT_v) && !Args.hasArg(OPT_INPUT))
return;
if (Args.hasArg(OPT_version))
return;
if (const char *Path = getReproduceOption(Args)) {
// Note that --reproduce is a debug option so you can ignore it
// if you are trying to understand the whole picture of the code.
Expected<std::unique_ptr<TarWriter>> ErrOrWriter =
TarWriter::create(Path, path::stem(Path));
if (ErrOrWriter) {
Tar = ErrOrWriter->get();
Tar->append("response.txt", createResponseFile(Args));
Tar->append("version.txt", getLLDVersion() + "\n");
make<std::unique_ptr<TarWriter>>(std::move(*ErrOrWriter));
} else {
error(Twine("--reproduce: failed to open ") + Path + ": " +
toString(ErrOrWriter.takeError()));
}
}
readConfigs(Args);
checkZOptions(Args);
initLLVM();
createFiles(Args);
if (errorCount())
return;
inferMachineType();
setConfigs(Args);
checkOptions(Args);
if (errorCount())
return;
switch (Config->EKind) {
case ELF32LEKind:
link<ELF32LE>(Args);
return;
case ELF32BEKind:
link<ELF32BE>(Args);
return;
case ELF64LEKind:
link<ELF64LE>(Args);
return;
case ELF64BEKind:
link<ELF64BE>(Args);
return;
default:
llvm_unreachable("unknown Config->EKind");
}
}
static std::string getRpath(opt::InputArgList &Args) {
std::vector<StringRef> V = args::getStrings(Args, OPT_rpath);
return llvm::join(V.begin(), V.end(), ":");
}
// Determines what we should do if there are remaining unresolved
// symbols after the name resolution.
static UnresolvedPolicy getUnresolvedSymbolPolicy(opt::InputArgList &Args) {
2017-02-25 09:51:25 +08:00
if (Args.hasArg(OPT_relocatable))
return UnresolvedPolicy::IgnoreAll;
UnresolvedPolicy ErrorOrWarn = Args.hasFlag(OPT_error_unresolved_symbols,
OPT_warn_unresolved_symbols, true)
? UnresolvedPolicy::ReportError
: UnresolvedPolicy::Warn;
// Process the last of -unresolved-symbols, -no-undefined or -z defs.
for (auto *Arg : llvm::reverse(Args)) {
switch (Arg->getOption().getID()) {
case OPT_unresolved_symbols: {
StringRef S = Arg->getValue();
if (S == "ignore-all" || S == "ignore-in-object-files")
return UnresolvedPolicy::Ignore;
if (S == "ignore-in-shared-libs" || S == "report-all")
return ErrorOrWarn;
error("unknown --unresolved-symbols value: " + S);
continue;
}
case OPT_no_undefined:
return ErrorOrWarn;
case OPT_z:
if (StringRef(Arg->getValue()) == "defs")
return ErrorOrWarn;
continue;
}
}
// -shared implies -unresolved-symbols=ignore-all because missing
// symbols are likely to be resolved at runtime using other DSOs.
if (Config->Shared)
return UnresolvedPolicy::Ignore;
return ErrorOrWarn;
}
static Target2Policy getTarget2(opt::InputArgList &Args) {
StringRef S = Args.getLastArgValue(OPT_target2, "got-rel");
if (S == "rel")
return Target2Policy::Rel;
if (S == "abs")
return Target2Policy::Abs;
if (S == "got-rel")
return Target2Policy::GotRel;
error("unknown --target2 option: " + S);
return Target2Policy::GotRel;
}
static bool isOutputFormatBinary(opt::InputArgList &Args) {
if (auto *Arg = Args.getLastArg(OPT_oformat)) {
StringRef S = Arg->getValue();
if (S == "binary")
return true;
error("unknown --oformat value: " + S);
}
return false;
}
static DiscardPolicy getDiscard(opt::InputArgList &Args) {
2017-02-25 09:51:25 +08:00
if (Args.hasArg(OPT_relocatable))
return DiscardPolicy::None;
auto *Arg =
Args.getLastArg(OPT_discard_all, OPT_discard_locals, OPT_discard_none);
if (!Arg)
return DiscardPolicy::Default;
2016-09-03 03:49:27 +08:00
if (Arg->getOption().getID() == OPT_discard_all)
return DiscardPolicy::All;
2016-09-03 03:49:27 +08:00
if (Arg->getOption().getID() == OPT_discard_locals)
return DiscardPolicy::Locals;
2016-09-03 03:49:27 +08:00
return DiscardPolicy::None;
}
static StringRef getDynamicLinker(opt::InputArgList &Args) {
auto *Arg = Args.getLastArg(OPT_dynamic_linker, OPT_no_dynamic_linker);
if (!Arg || Arg->getOption().getID() == OPT_no_dynamic_linker)
return "";
return Arg->getValue();
}
static StripPolicy getStrip(opt::InputArgList &Args) {
if (Args.hasArg(OPT_relocatable))
return StripPolicy::None;
auto *Arg = Args.getLastArg(OPT_strip_all, OPT_strip_debug);
if (!Arg)
return StripPolicy::None;
if (Arg->getOption().getID() == OPT_strip_all)
return StripPolicy::All;
return StripPolicy::Debug;
}
static uint64_t parseSectionAddress(StringRef S, const opt::Arg &Arg) {
uint64_t VA = 0;
if (S.startswith("0x"))
S = S.drop_front(2);
if (!to_integer(S, VA, 16))
error("invalid argument: " + toString(Arg));
return VA;
}
static StringMap<uint64_t> getSectionStartMap(opt::InputArgList &Args) {
StringMap<uint64_t> Ret;
for (auto *Arg : Args.filtered(OPT_section_start)) {
StringRef Name;
StringRef Addr;
std::tie(Name, Addr) = StringRef(Arg->getValue()).split('=');
Ret[Name] = parseSectionAddress(Addr, *Arg);
}
if (auto *Arg = Args.getLastArg(OPT_Ttext))
Ret[".text"] = parseSectionAddress(Arg->getValue(), *Arg);
if (auto *Arg = Args.getLastArg(OPT_Tdata))
Ret[".data"] = parseSectionAddress(Arg->getValue(), *Arg);
if (auto *Arg = Args.getLastArg(OPT_Tbss))
Ret[".bss"] = parseSectionAddress(Arg->getValue(), *Arg);
return Ret;
}
static SortSectionPolicy getSortSection(opt::InputArgList &Args) {
StringRef S = Args.getLastArgValue(OPT_sort_section);
if (S == "alignment")
return SortSectionPolicy::Alignment;
if (S == "name")
return SortSectionPolicy::Name;
if (!S.empty())
error("unknown --sort-section rule: " + S);
return SortSectionPolicy::Default;
}
static OrphanHandlingPolicy getOrphanHandling(opt::InputArgList &Args) {
StringRef S = Args.getLastArgValue(OPT_orphan_handling, "place");
if (S == "warn")
return OrphanHandlingPolicy::Warn;
if (S == "error")
return OrphanHandlingPolicy::Error;
if (S != "place")
error("unknown --orphan-handling mode: " + S);
return OrphanHandlingPolicy::Place;
}
// Parse --build-id or --build-id=<style>. We handle "tree" as a
// synonym for "sha1" because all our hash functions including
// -build-id=sha1 are actually tree hashes for performance reasons.
static std::pair<BuildIdKind, std::vector<uint8_t>>
getBuildId(opt::InputArgList &Args) {
auto *Arg = Args.getLastArg(OPT_build_id, OPT_build_id_eq);
if (!Arg)
return {BuildIdKind::None, {}};
if (Arg->getOption().getID() == OPT_build_id)
return {BuildIdKind::Fast, {}};
StringRef S = Arg->getValue();
if (S == "fast")
return {BuildIdKind::Fast, {}};
if (S == "md5")
return {BuildIdKind::Md5, {}};
if (S == "sha1" || S == "tree")
return {BuildIdKind::Sha1, {}};
if (S == "uuid")
return {BuildIdKind::Uuid, {}};
if (S.startswith("0x"))
return {BuildIdKind::Hexstring, parseHex(S.substr(2))};
if (S != "none")
error("unknown --build-id style: " + S);
return {BuildIdKind::None, {}};
}
static void readCallGraph(MemoryBufferRef MB) {
// Build a map from symbol name to section
DenseMap<StringRef, const Symbol *> SymbolNameToSymbol;
for (InputFile *File : ObjectFiles)
for (Symbol *Sym : File->getSymbols())
SymbolNameToSymbol[Sym->getName()] = Sym;
for (StringRef L : args::getLines(MB)) {
SmallVector<StringRef, 3> Fields;
L.split(Fields, ' ');
if (Fields.size() != 3)
fatal("parse error");
uint64_t Count;
if (!to_integer(Fields[2], Count))
fatal("parse error");
const Symbol *FromSym = SymbolNameToSymbol.lookup(Fields[0]);
const Symbol *ToSym = SymbolNameToSymbol.lookup(Fields[1]);
if (Config->WarnSymbolOrdering) {
if (!FromSym)
warn("call graph file: no such symbol: " + Fields[0]);
if (!ToSym)
warn("call graph file: no such symbol: " + Fields[1]);
}
if (!FromSym || !ToSym || Count == 0)
continue;
warnUnorderableSymbol(FromSym);
warnUnorderableSymbol(ToSym);
const Defined *FromSymD = dyn_cast<Defined>(FromSym);
const Defined *ToSymD = dyn_cast<Defined>(ToSym);
if (!FromSymD || !ToSymD)
continue;
const auto *FromSB = dyn_cast_or_null<InputSectionBase>(FromSymD->Section);
const auto *ToSB = dyn_cast_or_null<InputSectionBase>(ToSymD->Section);
if (!FromSB || !ToSB)
continue;
Config->CallGraphProfile[std::make_pair(FromSB, ToSB)] += Count;
}
}
static bool getCompressDebugSections(opt::InputArgList &Args) {
StringRef S = Args.getLastArgValue(OPT_compress_debug_sections, "none");
if (S == "none")
return false;
if (S != "zlib")
error("unknown --compress-debug-sections value: " + S);
if (!zlib::isAvailable())
error("--compress-debug-sections: zlib is not available");
return true;
}
static std::pair<StringRef, StringRef> getOldNewOptions(opt::InputArgList &Args,
unsigned Id) {
auto *Arg = Args.getLastArg(Id);
if (!Arg)
return {"", ""};
StringRef S = Arg->getValue();
std::pair<StringRef, StringRef> Ret = S.split(';');
if (Ret.second.empty())
error(Arg->getSpelling() + " expects 'old;new' format, but got " + S);
return Ret;
}
// Parse the symbol ordering file and warn for any duplicate entries.
static std::vector<StringRef> getSymbolOrderingFile(MemoryBufferRef MB) {
SetVector<StringRef> Names;
for (StringRef S : args::getLines(MB))
if (!Names.insert(S) && Config->WarnSymbolOrdering)
warn(MB.getBufferIdentifier() + ": duplicate ordered symbol: " + S);
return Names.takeVector();
}
static void parseClangOption(StringRef Opt, const Twine &Msg) {
std::string Err;
raw_string_ostream OS(Err);
const char *Argv[] = {Config->ProgName.data(), Opt.data()};
if (cl::ParseCommandLineOptions(2, Argv, "", &OS))
return;
OS.flush();
error(Msg + ": " + StringRef(Err).trim());
}
// Initializes Config members by the command line options.
void LinkerDriver::readConfigs(opt::InputArgList &Args) {
errorHandler().Verbose = Args.hasArg(OPT_verbose);
errorHandler().FatalWarnings =
Args.hasFlag(OPT_fatal_warnings, OPT_no_fatal_warnings, false);
ThreadsEnabled = Args.hasFlag(OPT_threads, OPT_no_threads, true);
Config->AllowMultipleDefinition =
Args.hasFlag(OPT_allow_multiple_definition,
OPT_no_allow_multiple_definition, false) ||
hasZOption(Args, "muldefs");
Config->AuxiliaryList = args::getStrings(Args, OPT_auxiliary);
Config->Bsymbolic = Args.hasArg(OPT_Bsymbolic);
Config->BsymbolicFunctions = Args.hasArg(OPT_Bsymbolic_functions);
Config->CheckSections =
Args.hasFlag(OPT_check_sections, OPT_no_check_sections, true);
Config->Chroot = Args.getLastArgValue(OPT_chroot);
Config->CompressDebugSections = getCompressDebugSections(Args);
Config->Cref = Args.hasFlag(OPT_cref, OPT_no_cref, false);
Config->DefineCommon = Args.hasFlag(OPT_define_common, OPT_no_define_common,
!Args.hasArg(OPT_relocatable));
Config->Demangle = Args.hasFlag(OPT_demangle, OPT_no_demangle, true);
Config->DisableVerify = Args.hasArg(OPT_disable_verify);
Config->Discard = getDiscard(Args);
Config->DynamicLinker = getDynamicLinker(Args);
Config->EhFrameHdr =
Args.hasFlag(OPT_eh_frame_hdr, OPT_no_eh_frame_hdr, false);
2017-02-25 09:51:25 +08:00
Config->EmitRelocs = Args.hasArg(OPT_emit_relocs);
Config->EnableNewDtags =
Args.hasFlag(OPT_enable_new_dtags, OPT_disable_new_dtags, true);
Config->Entry = Args.getLastArgValue(OPT_entry);
Config->ExportDynamic =
Args.hasFlag(OPT_export_dynamic, OPT_no_export_dynamic, false);
Config->FilterList = args::getStrings(Args, OPT_filter);
Config->Fini = Args.getLastArgValue(OPT_fini, "_fini");
Config->FixCortexA53Errata843419 = Args.hasArg(OPT_fix_cortex_a53_843419);
Config->GcSections = Args.hasFlag(OPT_gc_sections, OPT_no_gc_sections, false);
Config->GnuUnique = Args.hasFlag(OPT_gnu_unique, OPT_no_gnu_unique, true);
Config->GdbIndex = Args.hasFlag(OPT_gdb_index, OPT_no_gdb_index, false);
Config->ICF = Args.hasFlag(OPT_icf_all, OPT_icf_none, false);
Config->IgnoreDataAddressEquality =
Args.hasArg(OPT_ignore_data_address_equality);
Config->IgnoreFunctionAddressEquality =
Args.hasArg(OPT_ignore_function_address_equality);
Config->Init = Args.getLastArgValue(OPT_init, "_init");
Config->LTOAAPipeline = Args.getLastArgValue(OPT_lto_aa_pipeline);
Config->LTODebugPassManager = Args.hasArg(OPT_lto_debug_pass_manager);
Config->LTONewPassManager = Args.hasArg(OPT_lto_new_pass_manager);
Config->LTONewPmPasses = Args.getLastArgValue(OPT_lto_newpm_passes);
Config->LTOO = args::getInteger(Args, OPT_lto_O, 2);
Config->LTOObjPath = Args.getLastArgValue(OPT_plugin_opt_obj_path_eq);
Config->LTOPartitions = args::getInteger(Args, OPT_lto_partitions, 1);
Config->LTOSampleProfile = Args.getLastArgValue(OPT_lto_sample_profile);
Config->MapFile = Args.getLastArgValue(OPT_Map);
[ELF][MIPS] Multi-GOT implementation Almost all entries inside MIPS GOT are referenced by signed 16-bit index. Zero entry lies approximately in the middle of the GOT. So the total number of GOT entries cannot exceed ~16384 for 32-bit architecture and ~8192 for 64-bit architecture. This limitation makes impossible to link rather large application like for example LLVM+Clang. There are two workaround for this problem. The first one is using the -mxgot compiler's flag. It enables using a 32-bit index to access GOT entries. But each access requires two assembly instructions two load GOT entry index to a register. Another workaround is multi-GOT. This patch implements it. Here is a brief description of multi-GOT for detailed one see the following link https://dmz-portal.mips.com/wiki/MIPS_Multi_GOT. If the sum of local, global and tls entries is less than 64K only single got is enough. Otherwise, multi-got is created. Series of primary and multiple secondary GOTs have the following layout: ``` - Primary GOT Header Local entries Global entries Relocation only entries TLS entries - Secondary GOT Local entries Global entries TLS entries ... ``` All GOT entries required by relocations from a single input file entirely belong to either primary or one of secondary GOTs. To reference GOT entries each GOT has its own _gp value points to the "middle" of the GOT. In the code this value loaded to the register which is used for GOT access. MIPS 32 function's prologue: ``` lui v0,0x0 0: R_MIPS_HI16 _gp_disp addiu v0,v0,0 4: R_MIPS_LO16 _gp_disp ``` MIPS 64 function's prologue: ``` lui at,0x0 14: R_MIPS_GPREL16 main ``` Dynamic linker does not know anything about secondary GOTs and cannot use a regular MIPS mechanism for GOT entries initialization. So we have to use an approach accepted by other architectures and create dynamic relocations R_MIPS_REL32 to initialize global entries (and local in case of PIC code) in secondary GOTs. But ironically MIPS dynamic linker requires GOT entries and correspondingly ordered dynamic symbol table entries to deal with dynamic relocations. To handle this problem relocation-only section in the primary GOT contains entries for all symbols referenced in global parts of secondary GOTs. Although the sum of local and normal global entries of the primary got should be less than 64K, the size of the primary got (including relocation-only entries can be greater than 64K, because parts of the primary got that overflow the 64K limit are used only by the dynamic linker at dynamic link-time and not by 16-bit gp-relative addressing at run-time. The patch affects common LLD code in the following places: - Added new hidden -mips-got-size flag. This flag required to set low maximum size of a single GOT to be able to test the implementation using small test cases. - Added InputFile argument to the getRelocTargetVA function. The same symbol referenced by GOT relocation from different input file might be allocated in different GOT. So result of relocation depends on the file. - Added new ctor to the DynamicReloc class. This constructor records settings of dynamic relocation which used to adjust address of 64kb page lies inside a specific output section. With the patch LLD is able to link all LLVM+Clang+LLD applications and libraries for MIPS 32/64 targets. Differential revision: https://reviews.llvm.org/D31528 llvm-svn: 334390
2018-06-11 15:24:31 +08:00
Config->MipsGotSize = args::getInteger(Args, OPT_mips_got_size, 0xfff0);
Config->MergeArmExidx =
Args.hasFlag(OPT_merge_exidx_entries, OPT_no_merge_exidx_entries, true);
Config->NoinhibitExec = Args.hasArg(OPT_noinhibit_exec);
2016-09-03 03:20:33 +08:00
Config->Nostdlib = Args.hasArg(OPT_nostdlib);
2017-02-25 09:51:25 +08:00
Config->OFormatBinary = isOutputFormatBinary(Args);
Config->Omagic = Args.hasFlag(OPT_omagic, OPT_no_omagic, false);
Config->OptRemarksFilename = Args.getLastArgValue(OPT_opt_remarks_filename);
Config->OptRemarksWithHotness = Args.hasArg(OPT_opt_remarks_with_hotness);
Config->Optimize = args::getInteger(Args, OPT_O, 1);
Config->OrphanHandling = getOrphanHandling(Args);
Config->OutputFile = Args.getLastArgValue(OPT_o);
Config->Pie = Args.hasFlag(OPT_pie, OPT_no_pie, false);
Config->PrintIcfSections =
Args.hasFlag(OPT_print_icf_sections, OPT_no_print_icf_sections, false);
Config->PrintGcSections =
Args.hasFlag(OPT_print_gc_sections, OPT_no_print_gc_sections, false);
Config->Rpath = getRpath(Args);
Config->Relocatable = Args.hasArg(OPT_relocatable);
Config->SaveTemps = Args.hasArg(OPT_save_temps);
Config->SearchPaths = args::getStrings(Args, OPT_library_path);
2017-02-25 09:51:25 +08:00
Config->SectionStartMap = getSectionStartMap(Args);
Config->Shared = Args.hasArg(OPT_shared);
2017-02-25 09:51:25 +08:00
Config->SingleRoRx = Args.hasArg(OPT_no_rosegment);
Config->SoName = Args.getLastArgValue(OPT_soname);
Config->SortSection = getSortSection(Args);
Config->Strip = getStrip(Args);
Config->Sysroot = Args.getLastArgValue(OPT_sysroot);
Config->Target1Rel = Args.hasFlag(OPT_target1_rel, OPT_target1_abs, false);
Config->Target2 = getTarget2(Args);
Config->ThinLTOCacheDir = Args.getLastArgValue(OPT_thinlto_cache_dir);
Config->ThinLTOCachePolicy = CHECK(
parseCachePruningPolicy(Args.getLastArgValue(OPT_thinlto_cache_policy)),
"--thinlto-cache-policy: invalid cache policy");
Config->ThinLTOEmitImportsFiles =
Args.hasArg(OPT_plugin_opt_thinlto_emit_imports_files);
Config->ThinLTOIndexOnly = Args.hasArg(OPT_plugin_opt_thinlto_index_only) ||
Args.hasArg(OPT_plugin_opt_thinlto_index_only_eq);
Config->ThinLTOIndexOnlyArg =
Args.getLastArgValue(OPT_plugin_opt_thinlto_index_only_eq);
Config->ThinLTOJobs = args::getInteger(Args, OPT_thinlto_jobs, -1u);
Config->ThinLTOObjectSuffixReplace =
getOldNewOptions(Args, OPT_plugin_opt_thinlto_object_suffix_replace_eq);
Config->ThinLTOPrefixReplace =
getOldNewOptions(Args, OPT_plugin_opt_thinlto_prefix_replace_eq);
Config->Trace = Args.hasArg(OPT_trace);
Config->Undefined = args::getStrings(Args, OPT_undefined);
Config->UndefinedVersion =
Args.hasFlag(OPT_undefined_version, OPT_no_undefined_version, true);
2017-02-25 09:51:25 +08:00
Config->UnresolvedSymbols = getUnresolvedSymbolPolicy(Args);
Add --warn-backrefs to maintain compatibility with other linkers I'm proposing a new command line flag, --warn-backrefs in this patch. The flag and the feature proposed below don't exist in GNU linkers nor the current lld. --warn-backrefs is an option to detect reverse or cyclic dependencies between static archives, and it can be used to keep your program compatible with GNU linkers after you switch to lld. I'll explain the feature and why you may find it useful below. lld's symbol resolution semantics is more relaxed than traditional Unix linkers. Therefore, ld.lld foo.a bar.o succeeds even if bar.o contains an undefined symbol that have to be resolved by some object file in foo.a. Traditional Unix linkers don't allow this kind of backward reference, as they visit each file only once from left to right in the command line while resolving all undefined symbol at the moment of visiting. In the above case, since there's no undefined symbol when a linker visits foo.a, no files are pulled out from foo.a, and because the linker forgets about foo.a after visiting, it can't resolve undefined symbols that could have been resolved otherwise. That lld accepts more relaxed form means (besides it makes more sense) that you can accidentally write a command line or a build file that works only with lld, even if you have a plan to distribute it to wider users who may be using GNU linkers. With --check-library-dependency, you can detect a library order that doesn't work with other Unix linkers. The option is also useful to detect cyclic dependencies between static archives. Again, lld accepts ld.lld foo.a bar.a even if foo.a and bar.a depend on each other. With --warn-backrefs it is handled as an error. Here is how the option works. We assign a group ID to each file. A file with a smaller group ID can pull out object files from an archive file with an equal or greater group ID. Otherwise, it is a reverse dependency and an error. A file outside --{start,end}-group gets a fresh ID when instantiated. All files within the same --{start,end}-group get the same group ID. E.g. ld.lld A B --start-group C D --end-group E A and B form group 0, C, D and their member object files form group 1, and E forms group 2. I think that you can see how this group assignment rule simulates the traditional linker's semantics. Differential Revision: https://reviews.llvm.org/D45195 llvm-svn: 329636
2018-04-10 07:05:48 +08:00
Config->WarnBackrefs =
Args.hasFlag(OPT_warn_backrefs, OPT_no_warn_backrefs, false);
Config->WarnCommon = Args.hasFlag(OPT_warn_common, OPT_no_warn_common, false);
Config->WarnSymbolOrdering =
Args.hasFlag(OPT_warn_symbol_ordering, OPT_no_warn_symbol_ordering, true);
Config->ZCombreloc = getZFlag(Args, "combreloc", "nocombreloc", true);
Config->ZCopyreloc = getZFlag(Args, "copyreloc", "nocopyreloc", true);
Config->ZExecstack = getZFlag(Args, "execstack", "noexecstack", false);
Config->ZHazardplt = hasZOption(Args, "hazardplt");
Config->ZInitfirst = hasZOption(Args, "initfirst");
Config->ZKeepTextSectionPrefix = getZFlag(
Args, "keep-text-section-prefix", "nokeep-text-section-prefix", false);
Config->ZNodelete = hasZOption(Args, "nodelete");
Config->ZNodlopen = hasZOption(Args, "nodlopen");
Config->ZNow = getZFlag(Args, "now", "lazy", false);
Config->ZOrigin = hasZOption(Args, "origin");
Config->ZRelro = getZFlag(Args, "relro", "norelro", true);
Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre.. Summary: First, we need to explain the core of the vulnerability. Note that this is a very incomplete description, please see the Project Zero blog post for details: https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html The basis for branch target injection is to direct speculative execution of the processor to some "gadget" of executable code by poisoning the prediction of indirect branches with the address of that gadget. The gadget in turn contains an operation that provides a side channel for reading data. Most commonly, this will look like a load of secret data followed by a branch on the loaded value and then a load of some predictable cache line. The attacker then uses timing of the processors cache to determine which direction the branch took *in the speculative execution*, and in turn what one bit of the loaded value was. Due to the nature of these timing side channels and the branch predictor on Intel processors, this allows an attacker to leak data only accessible to a privileged domain (like the kernel) back into an unprivileged domain. The goal is simple: avoid generating code which contains an indirect branch that could have its prediction poisoned by an attacker. In many cases, the compiler can simply use directed conditional branches and a small search tree. LLVM already has support for lowering switches in this way and the first step of this patch is to disable jump-table lowering of switches and introduce a pass to rewrite explicit indirectbr sequences into a switch over integers. However, there is no fully general alternative to indirect calls. We introduce a new construct we call a "retpoline" to implement indirect calls in a non-speculatable way. It can be thought of loosely as a trampoline for indirect calls which uses the RET instruction on x86. Further, we arrange for a specific call->ret sequence which ensures the processor predicts the return to go to a controlled, known location. The retpoline then "smashes" the return address pushed onto the stack by the call with the desired target of the original indirect call. The result is a predicted return to the next instruction after a call (which can be used to trap speculative execution within an infinite loop) and an actual indirect branch to an arbitrary address. On 64-bit x86 ABIs, this is especially easily done in the compiler by using a guaranteed scratch register to pass the target into this device. For 32-bit ABIs there isn't a guaranteed scratch register and so several different retpoline variants are introduced to use a scratch register if one is available in the calling convention and to otherwise use direct stack push/pop sequences to pass the target address. This "retpoline" mitigation is fully described in the following blog post: https://support.google.com/faqs/answer/7625886 We also support a target feature that disables emission of the retpoline thunk by the compiler to allow for custom thunks if users want them. These are particularly useful in environments like kernels that routinely do hot-patching on boot and want to hot-patch their thunk to different code sequences. They can write this custom thunk and use `-mretpoline-external-thunk` *in addition* to `-mretpoline`. In this case, on x86-64 thu thunk names must be: ``` __llvm_external_retpoline_r11 ``` or on 32-bit: ``` __llvm_external_retpoline_eax __llvm_external_retpoline_ecx __llvm_external_retpoline_edx __llvm_external_retpoline_push ``` And the target of the retpoline is passed in the named register, or in the case of the `push` suffix on the top of the stack via a `pushl` instruction. There is one other important source of indirect branches in x86 ELF binaries: the PLT. These patches also include support for LLD to generate PLT entries that perform a retpoline-style indirection. The only other indirect branches remaining that we are aware of are from precompiled runtimes (such as crt0.o and similar). The ones we have found are not really attackable, and so we have not focused on them here, but eventually these runtimes should also be replicated for retpoline-ed configurations for completeness. For kernels or other freestanding or fully static executables, the compiler switch `-mretpoline` is sufficient to fully mitigate this particular attack. For dynamic executables, you must compile *all* libraries with `-mretpoline` and additionally link the dynamic executable and all shared libraries with LLD and pass `-z retpolineplt` (or use similar functionality from some other linker). We strongly recommend also using `-z now` as non-lazy binding allows the retpoline-mitigated PLT to be substantially smaller. When manually apply similar transformations to `-mretpoline` to the Linux kernel we observed very small performance hits to applications running typical workloads, and relatively minor hits (approximately 2%) even for extremely syscall-heavy applications. This is largely due to the small number of indirect branches that occur in performance sensitive paths of the kernel. When using these patches on statically linked applications, especially C++ applications, you should expect to see a much more dramatic performance hit. For microbenchmarks that are switch, indirect-, or virtual-call heavy we have seen overheads ranging from 10% to 50%. However, real-world workloads exhibit substantially lower performance impact. Notably, techniques such as PGO and ThinLTO dramatically reduce the impact of hot indirect calls (by speculatively promoting them to direct calls) and allow optimized search trees to be used to lower switches. If you need to deploy these techniques in C++ applications, we *strongly* recommend that you ensure all hot call targets are statically linked (avoiding PLT indirection) and use both PGO and ThinLTO. Well tuned servers using all of these techniques saw 5% - 10% overhead from the use of retpoline. We will add detailed documentation covering these components in subsequent patches, but wanted to make the core functionality available as soon as possible. Happy for more code review, but we'd really like to get these patches landed and backported ASAP for obvious reasons. We're planning to backport this to both 6.0 and 5.0 release streams and get a 5.0 release with just this cherry picked ASAP for distros and vendors. This patch is the work of a number of people over the past month: Eric, Reid, Rui, and myself. I'm mailing it out as a single commit due to the time sensitive nature of landing this and the need to backport it. Huge thanks to everyone who helped out here, and everyone at Intel who helped out in discussions about how to craft this. Also, credit goes to Paul Turner (at Google, but not an LLVM contributor) for much of the underlying retpoline design. Reviewers: echristo, rnk, ruiu, craig.topper, DavidKreitzer Subscribers: sanjoy, emaste, mcrosier, mgorny, mehdi_amini, hiraditya, llvm-commits Differential Revision: https://reviews.llvm.org/D41723 llvm-svn: 323155
2018-01-23 06:05:25 +08:00
Config->ZRetpolineplt = hasZOption(Args, "retpolineplt");
Config->ZRodynamic = hasZOption(Args, "rodynamic");
Config->ZStackSize = args::getZOptionValue(Args, OPT_z, "stack-size", 0);
Config->ZText = getZFlag(Args, "text", "notext", true);
Config->ZWxneeded = hasZOption(Args, "wxneeded");
// Parse LTO options.
if (auto *Arg = Args.getLastArg(OPT_plugin_opt_mcpu_eq))
parseClangOption(Saver.save("-mcpu=" + StringRef(Arg->getValue())),
Arg->getSpelling());
for (auto *Arg : Args.filtered(OPT_plugin_opt))
parseClangOption(Arg->getValue(), Arg->getSpelling());
// Parse -mllvm options.
for (auto *Arg : Args.filtered(OPT_mllvm))
parseClangOption(Arg->getValue(), Arg->getSpelling());
2017-02-25 09:51:25 +08:00
if (Config->LTOO > 3)
error("invalid optimization level for LTO: " + Twine(Config->LTOO));
2017-02-25 09:51:25 +08:00
if (Config->LTOPartitions == 0)
error("--lto-partitions: number of threads must be > 0");
if (Config->ThinLTOJobs == 0)
error("--thinlto-jobs: number of threads must be > 0");
// Parse ELF{32,64}{LE,BE} and CPU type.
2017-02-25 09:51:25 +08:00
if (auto *Arg = Args.getLastArg(OPT_m)) {
StringRef S = Arg->getValue();
std::tie(Config->EKind, Config->EMachine, Config->OSABI) =
parseEmulation(S);
Config->MipsN32Abi = (S == "elf32btsmipn32" || S == "elf32ltsmipn32");
Config->Emulation = S;
}
2016-10-20 13:23:23 +08:00
// Parse -hash-style={sysv,gnu,both}.
if (auto *Arg = Args.getLastArg(OPT_hash_style)) {
StringRef S = Arg->getValue();
if (S == "sysv")
Config->SysvHash = true;
else if (S == "gnu")
Config->GnuHash = true;
else if (S == "both")
Config->SysvHash = Config->GnuHash = true;
else
error("unknown -hash-style: " + S);
}
if (Args.hasArg(OPT_print_map))
Config->MapFile = "-";
// --omagic is an option to create old-fashioned executables in which
// .text segments are writable. Today, the option is still in use to
// create special-purpose programs such as boot loaders. It doesn't
// make sense to create PT_GNU_RELRO for such executables.
if (Config->Omagic)
Config->ZRelro = false;
std::tie(Config->BuildId, Config->BuildIdVector) = getBuildId(Args);
if (auto *Arg = Args.getLastArg(OPT_pack_dyn_relocs)) {
StringRef S = Arg->getValue();
if (S == "android")
Config->AndroidPackDynRelocs = true;
else if (S != "none")
error("unknown -pack-dyn-relocs format: " + S);
}
if (auto *Arg = Args.getLastArg(OPT_symbol_ordering_file))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
Config->SymbolOrderingFile = getSymbolOrderingFile(*Buffer);
2017-01-26 05:49:23 +08:00
// If --retain-symbol-file is used, we'll keep only the symbols listed in
// the file and discard all others.
if (auto *Arg = Args.getLastArg(OPT_retain_symbols_file)) {
Config->DefaultSymbolVersion = VER_NDX_LOCAL;
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
for (StringRef S : args::getLines(*Buffer))
Config->VersionScriptGlobals.push_back(
{S, /*IsExternCpp*/ false, /*HasWildcard*/ false});
}
bool HasExportDynamic =
Args.hasFlag(OPT_export_dynamic, OPT_no_export_dynamic, false);
// Parses -dynamic-list and -export-dynamic-symbol. They make some
// symbols private. Note that -export-dynamic takes precedence over them
// as it says all symbols should be exported.
if (!HasExportDynamic) {
for (auto *Arg : Args.filtered(OPT_dynamic_list))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
readDynamicList(*Buffer);
for (auto *Arg : Args.filtered(OPT_export_dynamic_symbol))
Config->DynamicList.push_back(
{Arg->getValue(), /*IsExternCpp*/ false, /*HasWildcard*/ false});
}
// If --export-dynamic-symbol=foo is given and symbol foo is defined in
// an object file in an archive file, that object file should be pulled
// out and linked. (It doesn't have to behave like that from technical
// point of view, but this is needed for compatibility with GNU.)
for (auto *Arg : Args.filtered(OPT_export_dynamic_symbol))
Config->Undefined.push_back(Arg->getValue());
for (auto *Arg : Args.filtered(OPT_version_script))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
readVersionScript(*Buffer);
}
// Some Config members do not directly correspond to any particular
// command line options, but computed based on other Config values.
// This function initialize such members. See Config.h for the details
// of these values.
static void setConfigs(opt::InputArgList &Args) {
ELFKind Kind = Config->EKind;
uint16_t Machine = Config->EMachine;
Config->CopyRelocs = (Config->Relocatable || Config->EmitRelocs);
Config->Is64 = (Kind == ELF64LEKind || Kind == ELF64BEKind);
Config->IsLE = (Kind == ELF32LEKind || Kind == ELF64LEKind);
Config->Endianness =
Config->IsLE ? support::endianness::little : support::endianness::big;
Config->IsMips64EL = (Kind == ELF64LEKind && Machine == EM_MIPS);
Config->Pic = Config->Pie || Config->Shared;
Config->Wordsize = Config->Is64 ? 8 : 4;
2018-06-08 08:18:32 +08:00
// There is an ILP32 ABI for x86-64, although it's not very popular.
// It is called the x32 ABI.
bool IsX32 = (Kind == ELF32LEKind && Machine == EM_X86_64);
// ELF defines two different ways to store relocation addends as shown below:
//
// Rel: Addends are stored to the location where relocations are applied.
// Rela: Addends are stored as part of relocation entry.
//
// In other words, Rela makes it easy to read addends at the price of extra
// 4 or 8 byte for each relocation entry. We don't know why ELF defined two
// different mechanisms in the first place, but this is how the spec is
// defined.
//
// You cannot choose which one, Rel or Rela, you want to use. Instead each
// ABI defines which one you need to use. The following expression expresses
// that.
Config->IsRela =
(Config->Is64 || IsX32 || Machine == EM_PPC) && Machine != EM_MIPS;
// If the output uses REL relocations we must store the dynamic relocation
// addends to the output sections. We also store addends for RELA relocations
// if --apply-dynamic-relocs is used.
// We default to not writing the addends when using RELA relocations since
// any standard conforming tool can find it in r_addend.
Config->WriteAddends = Args.hasFlag(OPT_apply_dynamic_relocs,
OPT_no_apply_dynamic_relocs, false) ||
!Config->IsRela;
}
2016-10-20 12:36:36 +08:00
// Returns a value of "-format" option.
static bool getBinaryOption(StringRef S) {
2016-10-20 12:36:36 +08:00
if (S == "binary")
return true;
if (S == "elf" || S == "default")
return false;
error("unknown -format value: " + S +
2016-10-20 12:36:36 +08:00
" (supported formats: elf, default, binary)");
return false;
}
void LinkerDriver::createFiles(opt::InputArgList &Args) {
// For --{push,pop}-state.
std::vector<std::tuple<bool, bool, bool>> Stack;
// Iterate over argv to process input files and positional arguments.
for (auto *Arg : Args) {
switch (Arg->getOption().getUnaliasedOption().getID()) {
case OPT_library:
addLibrary(Arg->getValue());
break;
case OPT_INPUT:
addFile(Arg->getValue(), /*WithLOption=*/false);
break;
case OPT_defsym: {
StringRef From;
StringRef To;
std::tie(From, To) = StringRef(Arg->getValue()).split('=');
readDefsym(From, MemoryBufferRef(To, "-defsym"));
break;
}
case OPT_script:
if (Optional<std::string> Path = searchLinkerScript(Arg->getValue())) {
if (Optional<MemoryBufferRef> MB = readFile(*Path))
readLinkerScript(*MB);
break;
}
error(Twine("cannot find linker script ") + Arg->getValue());
break;
case OPT_as_needed:
Config->AsNeeded = true;
break;
2016-10-20 12:36:36 +08:00
case OPT_format:
InBinary = getBinaryOption(Arg->getValue());
break;
case OPT_no_as_needed:
Config->AsNeeded = false;
break;
case OPT_Bstatic:
Config->Static = true;
break;
case OPT_Bdynamic:
Config->Static = false;
break;
case OPT_whole_archive:
InWholeArchive = true;
break;
case OPT_no_whole_archive:
InWholeArchive = false;
break;
case OPT_just_symbols:
if (Optional<MemoryBufferRef> MB = readFile(Arg->getValue())) {
Files.push_back(createObjectFile(*MB));
Files.back()->JustSymbols = true;
}
break;
Add --warn-backrefs to maintain compatibility with other linkers I'm proposing a new command line flag, --warn-backrefs in this patch. The flag and the feature proposed below don't exist in GNU linkers nor the current lld. --warn-backrefs is an option to detect reverse or cyclic dependencies between static archives, and it can be used to keep your program compatible with GNU linkers after you switch to lld. I'll explain the feature and why you may find it useful below. lld's symbol resolution semantics is more relaxed than traditional Unix linkers. Therefore, ld.lld foo.a bar.o succeeds even if bar.o contains an undefined symbol that have to be resolved by some object file in foo.a. Traditional Unix linkers don't allow this kind of backward reference, as they visit each file only once from left to right in the command line while resolving all undefined symbol at the moment of visiting. In the above case, since there's no undefined symbol when a linker visits foo.a, no files are pulled out from foo.a, and because the linker forgets about foo.a after visiting, it can't resolve undefined symbols that could have been resolved otherwise. That lld accepts more relaxed form means (besides it makes more sense) that you can accidentally write a command line or a build file that works only with lld, even if you have a plan to distribute it to wider users who may be using GNU linkers. With --check-library-dependency, you can detect a library order that doesn't work with other Unix linkers. The option is also useful to detect cyclic dependencies between static archives. Again, lld accepts ld.lld foo.a bar.a even if foo.a and bar.a depend on each other. With --warn-backrefs it is handled as an error. Here is how the option works. We assign a group ID to each file. A file with a smaller group ID can pull out object files from an archive file with an equal or greater group ID. Otherwise, it is a reverse dependency and an error. A file outside --{start,end}-group gets a fresh ID when instantiated. All files within the same --{start,end}-group get the same group ID. E.g. ld.lld A B --start-group C D --end-group E A and B form group 0, C, D and their member object files form group 1, and E forms group 2. I think that you can see how this group assignment rule simulates the traditional linker's semantics. Differential Revision: https://reviews.llvm.org/D45195 llvm-svn: 329636
2018-04-10 07:05:48 +08:00
case OPT_start_group:
if (InputFile::IsInGroup)
error("nested --start-group");
InputFile::IsInGroup = true;
break;
case OPT_end_group:
if (!InputFile::IsInGroup)
error("stray --end-group");
InputFile::IsInGroup = false;
++InputFile::NextGroupId;
Add --warn-backrefs to maintain compatibility with other linkers I'm proposing a new command line flag, --warn-backrefs in this patch. The flag and the feature proposed below don't exist in GNU linkers nor the current lld. --warn-backrefs is an option to detect reverse or cyclic dependencies between static archives, and it can be used to keep your program compatible with GNU linkers after you switch to lld. I'll explain the feature and why you may find it useful below. lld's symbol resolution semantics is more relaxed than traditional Unix linkers. Therefore, ld.lld foo.a bar.o succeeds even if bar.o contains an undefined symbol that have to be resolved by some object file in foo.a. Traditional Unix linkers don't allow this kind of backward reference, as they visit each file only once from left to right in the command line while resolving all undefined symbol at the moment of visiting. In the above case, since there's no undefined symbol when a linker visits foo.a, no files are pulled out from foo.a, and because the linker forgets about foo.a after visiting, it can't resolve undefined symbols that could have been resolved otherwise. That lld accepts more relaxed form means (besides it makes more sense) that you can accidentally write a command line or a build file that works only with lld, even if you have a plan to distribute it to wider users who may be using GNU linkers. With --check-library-dependency, you can detect a library order that doesn't work with other Unix linkers. The option is also useful to detect cyclic dependencies between static archives. Again, lld accepts ld.lld foo.a bar.a even if foo.a and bar.a depend on each other. With --warn-backrefs it is handled as an error. Here is how the option works. We assign a group ID to each file. A file with a smaller group ID can pull out object files from an archive file with an equal or greater group ID. Otherwise, it is a reverse dependency and an error. A file outside --{start,end}-group gets a fresh ID when instantiated. All files within the same --{start,end}-group get the same group ID. E.g. ld.lld A B --start-group C D --end-group E A and B form group 0, C, D and their member object files form group 1, and E forms group 2. I think that you can see how this group assignment rule simulates the traditional linker's semantics. Differential Revision: https://reviews.llvm.org/D45195 llvm-svn: 329636
2018-04-10 07:05:48 +08:00
break;
case OPT_start_lib:
if (InLib)
error("nested --start-lib");
if (InputFile::IsInGroup)
error("may not nest --start-lib in --start-group");
InLib = true;
InputFile::IsInGroup = true;
break;
case OPT_end_lib:
if (!InLib)
error("stray --end-lib");
InLib = false;
InputFile::IsInGroup = false;
++InputFile::NextGroupId;
break;
case OPT_push_state:
Stack.emplace_back(Config->AsNeeded, Config->Static, InWholeArchive);
break;
case OPT_pop_state:
if (Stack.empty()) {
error("unbalanced --push-state/--pop-state");
break;
}
std::tie(Config->AsNeeded, Config->Static, InWholeArchive) = Stack.back();
Stack.pop_back();
break;
}
}
if (Files.empty() && errorCount() == 0)
error("no input files");
}
// If -m <machine_type> was not given, infer it from object files.
void LinkerDriver::inferMachineType() {
if (Config->EKind != ELFNoneKind)
return;
for (InputFile *F : Files) {
if (F->EKind == ELFNoneKind)
continue;
Config->EKind = F->EKind;
Config->EMachine = F->EMachine;
Config->OSABI = F->OSABI;
Config->MipsN32Abi = Config->EMachine == EM_MIPS && isMipsN32Abi(F);
return;
}
error("target emulation unknown: -m or at least one .o file required");
}
// Parse -z max-page-size=<value>. The default value is defined by
// each target.
static uint64_t getMaxPageSize(opt::InputArgList &Args) {
uint64_t Val = args::getZOptionValue(Args, OPT_z, "max-page-size",
Target->DefaultMaxPageSize);
if (!isPowerOf2_64(Val))
error("max-page-size: value isn't a power of 2");
return Val;
}
// Parses -image-base option.
static Optional<uint64_t> getImageBase(opt::InputArgList &Args) {
// Because we are using "Config->MaxPageSize" here, this function has to be
// called after the variable is initialized.
auto *Arg = Args.getLastArg(OPT_image_base);
if (!Arg)
return None;
StringRef S = Arg->getValue();
uint64_t V;
if (!to_integer(S, V)) {
error("-image-base: number expected, but got " + S);
return 0;
}
if ((V % Config->MaxPageSize) != 0)
warn("-image-base: address isn't multiple of page size: " + S);
return V;
}
// Parses `--exclude-libs=lib,lib,...`.
// The library names may be delimited by commas or colons.
static DenseSet<StringRef> getExcludeLibs(opt::InputArgList &Args) {
DenseSet<StringRef> Ret;
for (auto *Arg : Args.filtered(OPT_exclude_libs)) {
StringRef S = Arg->getValue();
for (;;) {
size_t Pos = S.find_first_of(",:");
if (Pos == StringRef::npos)
break;
Ret.insert(S.substr(0, Pos));
S = S.substr(Pos + 1);
}
Ret.insert(S);
}
return Ret;
}
// Handles the -exclude-libs option. If a static library file is specified
// by the -exclude-libs option, all public symbols from the archive become
// private unless otherwise specified by version scripts or something.
// A special library name "ALL" means all archive files.
//
// This is not a popular option, but some programs such as bionic libc use it.
template <class ELFT>
static void excludeLibs(opt::InputArgList &Args) {
DenseSet<StringRef> Libs = getExcludeLibs(Args);
bool All = Libs.count("ALL");
for (InputFile *File : ObjectFiles)
if (!File->ArchiveName.empty())
if (All || Libs.count(path::filename(File->ArchiveName)))
for (Symbol *Sym : File->getSymbols())
if (!Sym->isLocal() && Sym->File == File)
Sym->VersionId = VER_NDX_LOCAL;
}
// Force Sym to be entered in the output. Used for -u or equivalent.
template <class ELFT> static void handleUndefined(StringRef Name) {
Symbol *Sym = Symtab->find(Name);
if (!Sym)
return;
// Since symbol S may not be used inside the program, LTO may
// eliminate it. Mark the symbol as "used" to prevent it.
Sym->IsUsedInRegularObj = true;
if (Sym->isLazy())
Symtab->fetchLazy<ELFT>(Sym);
}
template <class ELFT> static bool shouldDemote(Symbol &Sym) {
// If all references to a DSO happen to be weak, the DSO is not added to
// DT_NEEDED. If that happens, we need to eliminate shared symbols created
// from the DSO. Otherwise, they become dangling references that point to a
// non-existent DSO.
if (auto *S = dyn_cast<SharedSymbol>(&Sym))
return !S->getFile<ELFT>().IsNeeded;
// We are done processing archives, so lazy symbols that were used but not
// found can be converted to undefined. We could also just delete the other
// lazy symbols, but that seems to be more work than it is worth.
return Sym.isLazy() && Sym.IsUsedInRegularObj;
}
2018-06-08 08:18:32 +08:00
// Some files, such as .so or files between -{start,end}-lib may be removed
// after their symbols are added to the symbol table. If that happens, we
// need to remove symbols that refer files that no longer exist, so that
// they won't appear in the symbol table of the output file.
//
// We remove symbols by demoting them to undefined symbol.
template <class ELFT> static void demoteSymbols() {
for (Symbol *Sym : Symtab->getSymbols()) {
if (shouldDemote<ELFT>(*Sym)) {
bool Used = Sym->Used;
replaceSymbol<Undefined>(Sym, nullptr, Sym->getName(), Sym->Binding,
Sym->StOther, Sym->Type);
Sym->Used = Used;
}
}
}
// Record sections that define symbols mentioned in --keep-unique <symbol>
// these sections are inelligible for ICF.
static void findKeepUniqueSections(opt::InputArgList &Args) {
for (auto *Arg : Args.filtered(OPT_keep_unique)) {
StringRef Name = Arg->getValue();
if (auto *Sym = dyn_cast_or_null<Defined>(Symtab->find(Name)))
Sym->Section->KeepUnique = true;
else
warn("could not find symbol " + Name + " to keep unique");
}
}
// Do actual linking. Note that when this function is called,
// all linker scripts have already been parsed.
template <class ELFT> void LinkerDriver::link(opt::InputArgList &Args) {
Target = getTarget();
Config->MaxPageSize = getMaxPageSize(Args);
Config->ImageBase = getImageBase(Args);
// If a -hash-style option was not given, set to a default value,
// which varies depending on the target.
if (!Args.hasArg(OPT_hash_style)) {
if (Config->EMachine == EM_MIPS)
Config->SysvHash = true;
else
Config->SysvHash = Config->GnuHash = true;
}
// Default output filename is "a.out" by the Unix tradition.
if (Config->OutputFile.empty())
Config->OutputFile = "a.out";
// Fail early if the output file or map file is not writable. If a user has a
// long link, e.g. due to a large LTO link, they do not wish to run it and
// find that it failed because there was a mistake in their command-line.
if (auto E = tryCreateFile(Config->OutputFile))
error("cannot open output file " + Config->OutputFile + ": " + E.message());
if (auto E = tryCreateFile(Config->MapFile))
error("cannot open map file " + Config->MapFile + ": " + E.message());
if (errorCount())
return;
// Use default entry point name if no name was given via the command
// line nor linker scripts. For some reason, MIPS entry point name is
// different from others.
Config->WarnMissingEntry =
(!Config->Entry.empty() || (!Config->Shared && !Config->Relocatable));
if (Config->Entry.empty() && !Config->Relocatable)
Config->Entry = (Config->EMachine == EM_MIPS) ? "__start" : "_start";
// Handle --trace-symbol.
for (auto *Arg : Args.filtered(OPT_trace_symbol))
Symtab->trace(Arg->getValue());
// Add all files to the symbol table. This will add almost all
// symbols that we need to the symbol table.
for (InputFile *F : Files)
Symtab->addFile<ELFT>(F);
// Now that we have every file, we can decide if we will need a
// dynamic symbol table.
// We need one if we were asked to export dynamic symbols or if we are
// producing a shared library.
// We also need one if any shared libraries are used and for pie executables
// (probably because the dynamic linker needs it).
Config->HasDynSymTab =
!SharedFiles.empty() || Config->Pic || Config->ExportDynamic;
// Some symbols (such as __ehdr_start) are defined lazily only when there
// are undefined symbols for them, so we add these to trigger that logic.
for (StringRef Sym : Script->ReferencedSymbols)
Symtab->addUndefined<ELFT>(Sym);
// Handle the `--undefined <sym>` options.
for (StringRef S : Config->Undefined)
handleUndefined<ELFT>(S);
// If an entry symbol is in a static archive, pull out that file now
// to complete the symbol table. After this, no new names except a
// few linker-synthesized ones will be added to the symbol table.
handleUndefined<ELFT>(Config->Entry);
// Return if there were name resolution errors.
if (errorCount())
return;
// Now when we read all script files, we want to finalize order of linker
// script commands, which can be not yet final because of INSERT commands.
Script->processInsertCommands();
// We want to declare linker script's symbols early,
// so that we can version them.
// They also might be exported if referenced by DSOs.
Script->declareSymbols();
// Handle the -exclude-libs option.
if (Args.hasArg(OPT_exclude_libs))
excludeLibs<ELFT>(Args);
// Create ElfHeader early. We need a dummy section in
// addReservedSymbols to mark the created symbols as not absolute.
Out::ElfHeader = make<OutputSection>("", 0, SHF_ALLOC);
Out::ElfHeader->Size = sizeof(typename ELFT::Ehdr);
// We need to create some reserved symbols such as _end. Create them.
if (!Config->Relocatable)
addReservedSymbols();
// Apply version scripts.
//
// For a relocatable output, version scripts don't make sense, and
// parsing a symbol version string (e.g. dropping "@ver1" from a symbol
// name "foo@ver1") rather do harm, so we don't call this if -r is given.
if (!Config->Relocatable)
Symtab->scanVersionScript();
// Create wrapped symbols for -wrap option.
for (auto *Arg : Args.filtered(OPT_wrap))
Symtab->addSymbolWrap<ELFT>(Arg->getValue());
// Do link-time optimization if given files are LLVM bitcode files.
// This compiles bitcode files into real object files.
Symtab->addCombinedLTOObject<ELFT>();
if (errorCount())
return;
// If -thinlto-index-only is given, we should create only "index
// files" and not object files. Index file creation is already done
// in addCombinedLTOObject, so we are done if that's the case.
if (Config->ThinLTOIndexOnly)
return;
// Apply symbol renames for -wrap.
Symtab->applySymbolWrap();
// Now that we have a complete list of input files.
// Beyond this point, no new files are added.
// Aggregate all input sections into one place.
for (InputFile *F : ObjectFiles)
for (InputSectionBase *S : F->getSections())
if (S && S != &InputSection::Discarded)
InputSections.push_back(S);
for (BinaryFile *F : BinaryFiles)
for (InputSectionBase *S : F->getSections())
InputSections.push_back(cast<InputSection>(S));
// We do not want to emit debug sections if --strip-all
// or -strip-debug are given.
if (Config->Strip != StripPolicy::None)
llvm::erase_if(InputSections, [](InputSectionBase *S) {
return S->Name.startswith(".debug") || S->Name.startswith(".zdebug");
});
Config->EFlags = Target->calcEFlags();
if (Config->EMachine == EM_ARM) {
// FIXME: These warnings can be removed when lld only uses these features
// when the input objects have been compiled with an architecture that
// supports them.
if (Config->ARMHasBlx == false)
warn("lld uses blx instruction, no object with architecture supporting "
"feature detected.");
if (Config->ARMJ1J2BranchEncoding == false)
warn("lld uses extended branch encoding, no object with architecture "
"supporting feature detected.");
if (Config->ARMHasMovtMovw == false)
warn("lld may use movt/movw, no object with architecture supporting "
"feature detected.");
}
// This adds a .comment section containing a version string. We have to add it
// before decompressAndMergeSections because the .comment section is a
// mergeable section.
if (!Config->Relocatable)
InputSections.push_back(createCommentSection());
// Do size optimizations: garbage collection, merging of SHF_MERGE sections
// and identical code folding.
decompressSections();
splitSections<ELFT>();
markLive<ELFT>();
demoteSymbols<ELFT>();
mergeSections();
if (Config->ICF) {
findKeepUniqueSections(Args);
doIcf<ELFT>();
}
// Read the callgraph now that we know what was gced or icfed
if (auto *Arg = Args.getLastArg(OPT_call_graph_ordering_file))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
readCallGraph(*Buffer);
2016-09-14 03:56:25 +08:00
// Write the result to the file.
writeResult<ELFT>();
}