Index: head/contrib/llvm/tools/lld/ELF/Config.h
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Config.h (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Config.h (revision 350467)
@@ -1,298 +1,298 @@
//===- Config.h -------------------------------------------------*- C++ -*-===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#ifndef LLD_ELF_CONFIG_H
#define LLD_ELF_CONFIG_H
#include "lld/Common/ErrorHandler.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/Support/CachePruning.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/Endian.h"
#include <atomic>
#include <vector>
namespace lld {
namespace elf {
class InputFile;
class InputSectionBase;
enum ELFKind {
ELFNoneKind,
ELF32LEKind,
ELF32BEKind,
ELF64LEKind,
ELF64BEKind
};
// For --build-id.
enum class BuildIdKind { None, Fast, Md5, Sha1, Hexstring, Uuid };
// For --discard-{all,locals,none}.
enum class DiscardPolicy { Default, All, Locals, None };
// For --icf={none,safe,all}.
enum class ICFLevel { None, Safe, All };
// For --strip-{all,debug}.
enum class StripPolicy { None, All, Debug };
// For --unresolved-symbols.
enum class UnresolvedPolicy { ReportError, Warn, Ignore };
// For --orphan-handling.
enum class OrphanHandlingPolicy { Place, Warn, Error };
// For --sort-section and linkerscript sorting rules.
enum class SortSectionPolicy { Default, None, Alignment, Name, Priority };
// For --target2
enum class Target2Policy { Abs, Rel, GotRel };
// For tracking ARM Float Argument PCS
enum class ARMVFPArgKind { Default, Base, VFP, ToolChain };
struct SymbolVersion {
llvm::StringRef Name;
bool IsExternCpp;
bool HasWildcard;
};
// This struct contains symbols version definition that
// can be found in version script if it is used for link.
struct VersionDefinition {
llvm::StringRef Name;
uint16_t Id = 0;
std::vector<SymbolVersion> Globals;
size_t NameOff = 0; // Offset in the string table
};
// This struct contains the global configuration for the linker.
// Most fields are direct mapping from the command line options
// and such fields have the same name as the corresponding options.
// Most fields are initialized by the driver.
struct Configuration {
std::atomic<bool> HasStaticTlsModel{false};
uint8_t OSABI = 0;
llvm::CachePruningPolicy ThinLTOCachePolicy;
llvm::StringMap<uint64_t> SectionStartMap;
llvm::StringRef Chroot;
llvm::StringRef DynamicLinker;
llvm::StringRef DwoDir;
llvm::StringRef Entry;
llvm::StringRef Emulation;
llvm::StringRef Fini;
llvm::StringRef Init;
llvm::StringRef LTOAAPipeline;
llvm::StringRef LTONewPmPasses;
llvm::StringRef LTOObjPath;
llvm::StringRef LTOSampleProfile;
llvm::StringRef MapFile;
llvm::StringRef OutputFile;
llvm::StringRef OptRemarksFilename;
llvm::StringRef ProgName;
llvm::StringRef SoName;
llvm::StringRef Sysroot;
llvm::StringRef ThinLTOCacheDir;
llvm::StringRef ThinLTOIndexOnlyArg;
std::pair<llvm::StringRef, llvm::StringRef> ThinLTOObjectSuffixReplace;
std::pair<llvm::StringRef, llvm::StringRef> ThinLTOPrefixReplace;
std::string Rpath;
std::vector<VersionDefinition> VersionDefinitions;
std::vector<llvm::StringRef> AuxiliaryList;
std::vector<llvm::StringRef> FilterList;
std::vector<llvm::StringRef> SearchPaths;
std::vector<llvm::StringRef> SymbolOrderingFile;
std::vector<llvm::StringRef> Undefined;
std::vector<SymbolVersion> DynamicList;
std::vector<SymbolVersion> VersionScriptGlobals;
std::vector<SymbolVersion> VersionScriptLocals;
std::vector<uint8_t> BuildIdVector;
llvm::MapVector<std::pair<const InputSectionBase *, const InputSectionBase *>,
uint64_t>
CallGraphProfile;
bool AllowMultipleDefinition;
bool AllowShlibUndefined;
bool AndroidPackDynRelocs;
bool ARMHasBlx = false;
bool ARMHasMovtMovw = false;
bool ARMJ1J2BranchEncoding = false;
bool AsNeeded = false;
bool Bsymbolic;
bool BsymbolicFunctions;
bool CallGraphProfileSort;
bool CheckSections;
bool CompressDebugSections;
bool Cref;
bool DefineCommon;
bool Demangle = true;
bool DisableVerify;
bool EhFrameHdr;
bool EmitLLVM;
bool EmitRelocs;
bool EnableNewDtags;
bool ExecuteOnly;
bool ExportDynamic;
bool FixCortexA53Errata843419;
bool FormatBinary = false;
bool GcSections;
bool GdbIndex;
bool GnuHash = false;
bool GnuUnique;
bool HasDynamicList = false;
bool HasDynSymTab;
bool IgnoreDataAddressEquality;
bool IgnoreFunctionAddressEquality;
bool LTODebugPassManager;
bool LTONewPassManager;
bool MergeArmExidx;
bool MipsN32Abi = false;
bool NoinhibitExec;
bool Nostdlib;
bool OFormatBinary;
bool Omagic;
bool OptRemarksWithHotness;
bool PicThunk;
bool Pie;
bool PrintGcSections;
bool PrintIcfSections;
bool Relocatable;
bool RelrPackDynRelocs;
bool SaveTemps;
bool SingleRoRx;
bool Shared;
bool Static = false;
bool SysvHash = false;
bool Target1Rel;
bool Trace;
bool ThinLTOEmitImportsFiles;
bool ThinLTOIndexOnly;
bool TocOptimize;
bool UndefinedVersion;
bool UseAndroidRelrTags = false;
bool WarnBackrefs;
bool WarnCommon;
bool WarnIfuncTextrel;
bool WarnMissingEntry;
bool WarnSymbolOrdering;
bool WriteAddends;
bool ZCombreloc;
bool ZCopyreloc;
bool ZExecstack;
bool ZGlobal;
bool ZHazardplt;
- bool ZIfuncnoplt;
+ bool ZIfuncNoplt;
bool ZInitfirst;
bool ZInterpose;
bool ZKeepTextSectionPrefix;
bool ZNodefaultlib;
bool ZNodelete;
bool ZNodlopen;
bool ZNow;
bool ZOrigin;
bool ZRelro;
bool ZRodynamic;
bool ZText;
bool ZRetpolineplt;
bool ZWxneeded;
DiscardPolicy Discard;
ICFLevel ICF;
OrphanHandlingPolicy OrphanHandling;
SortSectionPolicy SortSection;
StripPolicy Strip;
UnresolvedPolicy UnresolvedSymbols;
Target2Policy Target2;
ARMVFPArgKind ARMVFPArgs = ARMVFPArgKind::Default;
BuildIdKind BuildId = BuildIdKind::None;
ELFKind EKind = ELFNoneKind;
uint16_t DefaultSymbolVersion = llvm::ELF::VER_NDX_GLOBAL;
uint16_t EMachine = llvm::ELF::EM_NONE;
llvm::Optional<uint64_t> ImageBase;
uint64_t MaxPageSize;
uint64_t MipsGotSize;
uint64_t ZStackSize;
unsigned LTOPartitions;
unsigned LTOO;
unsigned Optimize;
unsigned ThinLTOJobs;
int32_t SplitStackAdjustSize;
// The following config options do not directly correspond to any
// particualr command line options.
// True if we need to pass through relocations in input files to the
// output file. Usually false because we consume relocations.
bool CopyRelocs;
// True if the target is ELF64. False if ELF32.
bool Is64;
// True if the target is little-endian. False if big-endian.
bool IsLE;
// endianness::little if IsLE is true. endianness::big otherwise.
llvm::support::endianness Endianness;
// True if the target is the little-endian MIPS64.
//
// The reason why we have this variable only for the MIPS is because
// we use this often. Some ELF headers for MIPS64EL are in a
// mixed-endian (which is horrible and I'd say that's a serious spec
// bug), and we need to know whether we are reading MIPS ELF files or
// not in various places.
//
// (Note that MIPS64EL is not a typo for MIPS64LE. This is the official
// name whatever that means. A fun hypothesis is that "EL" is short for
// little-endian written in the little-endian order, but I don't know
// if that's true.)
bool IsMips64EL;
// Holds set of ELF header flags for the target.
uint32_t EFlags = 0;
// The ELF spec defines two types of relocation table entries, RELA and
// REL. RELA is a triplet of (offset, info, addend) while REL is a
// tuple of (offset, info). Addends for REL are implicit and read from
// the location where the relocations are applied. So, REL is more
// compact than RELA but requires a bit of more work to process.
//
// (From the linker writer's view, this distinction is not necessary.
// If the ELF had chosen whichever and sticked with it, it would have
// been easier to write code to process relocations, but it's too late
// to change the spec.)
//
// Each ABI defines its relocation type. IsRela is true if target
// uses RELA. As far as we know, all 64-bit ABIs are using RELA. A
// few 32-bit ABIs are using RELA too.
bool IsRela;
// True if we are creating position-independent code.
bool Pic;
// 4 for ELF32, 8 for ELF64.
int Wordsize;
};
// The only instance of Configuration struct.
extern Configuration *Config;
static inline void errorOrWarn(const Twine &Msg) {
if (!Config->NoinhibitExec)
error(Msg);
else
warn(Msg);
}
} // namespace elf
} // namespace lld
#endif
Index: head/contrib/llvm/tools/lld/ELF/Driver.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Driver.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Driver.cpp (revision 350467)
@@ -1,1654 +1,1656 @@
//===- 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
// 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"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/TarWriter.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/raw_ostream.h"
#include <cstdlib>
#include <utility>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::sys;
using namespace llvm::support;
using namespace lld;
using namespace lld::elf;
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::getFilenameWithoutExe(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();
BinaryFiles.clear();
BitcodeFiles.clear();
ObjectFiles.clear();
SharedFiles.clear();
Config = make<Configuration>();
Driver = make<LinkerDriver>();
Script = make<LinkerScript>();
Symtab = make<SymbolTable>();
Tar = nullptr;
memset(&In, 0, sizeof(In));
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("elf32lriscv", {ELF32LEKind, EM_RISCV})
.Cases("elf32ppc", "elf32ppclinux", {ELF32BEKind, EM_PPC})
.Case("elf64btsmip", {ELF64BEKind, EM_MIPS})
.Case("elf64ltsmip", {ELF64LEKind, EM_MIPS})
.Case("elf64lriscv", {ELF64LEKind, EM_RISCV})
.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 (Config->FormatBinary) {
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->Static || 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() {
// 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->TocOptimize && Config->EMachine != EM_PPC64)
error("--toc-optimize is only supported on the PowerPC64 target");
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->ZText && Config->ZIfuncNoplt)
+ error("-z text and -z ifunc-noplt may not be used together");
+
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->GdbIndex)
error("-r and --gdb-index may not be used together");
if (Config->ICF != ICFLevel::None)
error("-r and --icf may not be used together");
if (Config->Pie)
error("-r and -pie may not be used together");
}
if (Config->ExecuteOnly) {
if (Config->EMachine != EM_AARCH64)
error("-execute-only is only supported on AArch64 targets");
if (Config->SingleRoRx && !Script->HasSectionsCommand)
error("-execute-only and -no-rosegment cannot 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 isKnownZFlag(StringRef S) {
return S == "combreloc" || S == "copyreloc" || S == "defs" ||
S == "execstack" || S == "global" || S == "hazardplt" ||
- S == "ifunc-noplt" ||
- S == "initfirst" || S == "interpose" ||
+ S == "ifunc-noplt" || S == "initfirst" || S == "interpose" ||
S == "keep-text-section-prefix" || S == "lazy" || S == "muldefs" ||
S == "nocombreloc" || S == "nocopyreloc" || S == "nodefaultlib" ||
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 (!isKnownZFlag(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)");
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 = std::move(*ErrOrWriter);
Tar->append("response.txt", createResponseFile(Args));
Tar->append("version.txt", getLLDVersion() + "\n");
} else {
error("--reproduce: " + toString(ErrOrWriter.takeError()));
}
}
readConfigs(Args);
checkZOptions(Args);
// 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;
initLLVM();
createFiles(Args);
if (errorCount())
return;
inferMachineType();
setConfigs(Args);
checkOptions();
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) {
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) {
StringRef S = Args.getLastArgValue(OPT_oformat, "elf");
if (S == "binary")
return true;
if (!S.startswith("elf"))
error("unknown --oformat value: " + S);
return false;
}
static DiscardPolicy getDiscard(opt::InputArgList &Args) {
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;
if (Arg->getOption().getID() == OPT_discard_all)
return DiscardPolicy::All;
if (Arg->getOption().getID() == OPT_discard_locals)
return DiscardPolicy::Locals;
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 ICFLevel getICF(opt::InputArgList &Args) {
auto *Arg = Args.getLastArg(OPT_icf_none, OPT_icf_safe, OPT_icf_all);
if (!Arg || Arg->getOption().getID() == OPT_icf_none)
return ICFLevel::None;
if (Arg->getOption().getID() == OPT_icf_safe)
return ICFLevel::Safe;
return ICFLevel::All;
}
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 std::pair<bool, bool> getPackDynRelocs(opt::InputArgList &Args) {
StringRef S = Args.getLastArgValue(OPT_pack_dyn_relocs, "none");
if (S == "android")
return {true, false};
if (S == "relr")
return {false, true};
if (S == "android+relr")
return {true, true};
if (S != "none")
error("unknown -pack-dyn-relocs format: " + S);
return {false, false};
}
static void readCallGraph(MemoryBufferRef MB) {
// Build a map from symbol name to section
DenseMap<StringRef, Symbol *> Map;
for (InputFile *File : ObjectFiles)
for (Symbol *Sym : File->getSymbols())
Map[Sym->getName()] = Sym;
auto FindSection = [&](StringRef Name) -> InputSectionBase * {
Symbol *Sym = Map.lookup(Name);
if (!Sym) {
if (Config->WarnSymbolOrdering)
warn(MB.getBufferIdentifier() + ": no such symbol: " + Name);
return nullptr;
}
maybeWarnUnorderableSymbol(Sym);
if (Defined *DR = dyn_cast_or_null<Defined>(Sym))
return dyn_cast_or_null<InputSectionBase>(DR->Section);
return nullptr;
};
for (StringRef Line : args::getLines(MB)) {
SmallVector<StringRef, 3> Fields;
Line.split(Fields, ' ');
uint64_t Count;
if (Fields.size() != 3 || !to_integer(Fields[2], Count)) {
error(MB.getBufferIdentifier() + ": parse error");
return;
}
if (InputSectionBase *From = FindSection(Fields[0]))
if (InputSectionBase *To = FindSection(Fields[1]))
Config->CallGraphProfile[std::make_pair(From, To)] += Count;
}
}
template <class ELFT> static void readCallGraphsFromObjectFiles() {
for (auto File : ObjectFiles) {
auto *Obj = cast<ObjFile<ELFT>>(File);
for (const Elf_CGProfile_Impl<ELFT> &CGPE : Obj->CGProfile) {
auto *FromSym = dyn_cast<Defined>(&Obj->getSymbol(CGPE.cgp_from));
auto *ToSym = dyn_cast<Defined>(&Obj->getSymbol(CGPE.cgp_to));
if (!FromSym || !ToSym)
continue;
auto *From = dyn_cast_or_null<InputSectionBase>(FromSym->Section);
auto *To = dyn_cast_or_null<InputSectionBase>(ToSym->Section);
if (From && To)
Config->CallGraphProfile[{From, To}] += CGPE.cgp_weight;
}
}
}
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->AllowShlibUndefined =
Args.hasFlag(OPT_allow_shlib_undefined, OPT_no_allow_shlib_undefined,
Args.hasArg(OPT_shared));
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->DwoDir = Args.getLastArgValue(OPT_plugin_opt_dwo_dir_eq);
Config->DynamicLinker = getDynamicLinker(Args);
Config->EhFrameHdr =
Args.hasFlag(OPT_eh_frame_hdr, OPT_no_eh_frame_hdr, false);
Config->EmitLLVM = Args.hasArg(OPT_plugin_opt_emit_llvm, false);
Config->EmitRelocs = Args.hasArg(OPT_emit_relocs);
Config->CallGraphProfileSort = Args.hasFlag(
OPT_call_graph_profile_sort, OPT_no_call_graph_profile_sort, true);
Config->EnableNewDtags =
Args.hasFlag(OPT_enable_new_dtags, OPT_disable_new_dtags, true);
Config->Entry = Args.getLastArgValue(OPT_entry);
Config->ExecuteOnly =
Args.hasFlag(OPT_execute_only, OPT_no_execute_only, false);
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 = getICF(Args);
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);
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);
Config->Nostdlib = Args.hasArg(OPT_nostdlib);
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);
Config->SectionStartMap = getSectionStartMap(Args);
Config->Shared = Args.hasArg(OPT_shared);
Config->SingleRoRx = Args.hasArg(OPT_no_rosegment);
Config->SoName = Args.getLastArgValue(OPT_soname);
Config->SortSection = getSortSection(Args);
Config->SplitStackAdjustSize = args::getInteger(Args, OPT_split_stack_adjust_size, 16384);
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);
Config->UseAndroidRelrTags = Args.hasFlag(
OPT_use_android_relr_tags, OPT_no_use_android_relr_tags, false);
Config->UnresolvedSymbols = getUnresolvedSymbolPolicy(Args);
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->WarnIfuncTextrel =
Args.hasFlag(OPT_warn_ifunc_textrel, OPT_no_warn_ifunc_textrel, 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->ZGlobal = hasZOption(Args, "global");
Config->ZHazardplt = hasZOption(Args, "hazardplt");
- Config->ZIfuncnoplt = hasZOption(Args, "ifunc-noplt");
+ Config->ZIfuncNoplt = hasZOption(Args, "ifunc-noplt");
Config->ZInitfirst = hasZOption(Args, "initfirst");
Config->ZInterpose = hasZOption(Args, "interpose");
Config->ZKeepTextSectionPrefix = getZFlag(
Args, "keep-text-section-prefix", "nokeep-text-section-prefix", false);
Config->ZNodefaultlib = hasZOption(Args, "nodefaultlib");
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);
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());
if (Config->LTOO > 3)
error("invalid optimization level for LTO: " + Twine(Config->LTOO));
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");
if (Config->SplitStackAdjustSize < 0)
error("--split-stack-adjust-size: size must be >= 0");
// Parse ELF{32,64}{LE,BE} and CPU type.
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;
}
// 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);
std::tie(Config->AndroidPackDynRelocs, Config->RelrPackDynRelocs) =
getPackDynRelocs(Args);
if (auto *Arg = Args.getLastArg(OPT_symbol_ordering_file))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
Config->SymbolOrderingFile = getSymbolOrderingFile(*Buffer);
// 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<std::string> Path = searchScript(Arg->getValue())) {
if (Optional<MemoryBufferRef> Buffer = readFile(*Path))
readVersionScript(*Buffer);
} else {
error(Twine("cannot find version script ") + Arg->getValue());
}
}
// 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 K = Config->EKind;
uint16_t M = Config->EMachine;
Config->CopyRelocs = (Config->Relocatable || Config->EmitRelocs);
Config->Is64 = (K == ELF64LEKind || K == ELF64BEKind);
Config->IsLE = (K == ELF32LEKind || K == ELF64LEKind);
Config->Endianness = Config->IsLE ? endianness::little : endianness::big;
Config->IsMips64EL = (K == ELF64LEKind && M == EM_MIPS);
Config->Pic = Config->Pie || Config->Shared;
Config->PicThunk = Args.hasArg(OPT_pic_veneer, Config->Pic);
Config->Wordsize = Config->Is64 ? 8 : 4;
// 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 = M == EM_AARCH64 || M == EM_AMDGPU || M == EM_HEXAGON ||
M == EM_PPC || M == EM_PPC64 || M == EM_RISCV ||
M == EM_X86_64;
// 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;
Config->TocOptimize =
Args.hasFlag(OPT_toc_optimize, OPT_no_toc_optimize, M == EM_PPC64);
}
// Returns a value of "-format" option.
static bool isFormatBinary(StringRef S) {
if (S == "binary")
return true;
if (S == "elf" || S == "default")
return false;
error("unknown -format value: " + S +
" (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('=');
if (From.empty() || To.empty())
error("-defsym: syntax error: " + StringRef(Arg->getValue()));
else
readDefsym(From, MemoryBufferRef(To, "-defsym"));
break;
}
case OPT_script:
if (Optional<std::string> Path = searchScript(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;
case OPT_format:
Config->FormatBinary = isFormatBinary(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;
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;
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");
auto Visit = [&](InputFile *File) {
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;
};
for (InputFile *File : ObjectFiles)
Visit(File);
for (BitcodeFile *File : BitcodeFiles)
Visit(File);
}
// 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 void handleLibcall(StringRef Name) {
Symbol *Sym = Symtab->find(Name);
if (!Sym || !Sym->isLazy())
return;
MemoryBufferRef MB;
if (auto *LO = dyn_cast<LazyObject>(Sym))
MB = LO->File->MB;
else
MB = cast<LazyArchive>(Sym)->getMemberBuffer();
if (isBitcode(MB))
Symtab->fetchLazy<ELFT>(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.
template <class ELFT> static void demoteSharedSymbols() {
for (Symbol *Sym : Symtab->getSymbols()) {
if (auto *S = dyn_cast<SharedSymbol>(Sym)) {
if (!S->getFile<ELFT>().IsNeeded) {
bool Used = S->Used;
replaceSymbol<Undefined>(S, nullptr, S->getName(), STB_WEAK, S->StOther,
S->Type);
S->Used = Used;
}
}
}
}
// The section referred to by S is considered address-significant. Set the
// KeepUnique flag on the section if appropriate.
static void markAddrsig(Symbol *S) {
if (auto *D = dyn_cast_or_null<Defined>(S))
if (D->Section)
// We don't need to keep text sections unique under --icf=all even if they
// are address-significant.
if (Config->ICF == ICFLevel::Safe || !(D->Section->Flags & SHF_EXECINSTR))
D->Section->KeepUnique = true;
}
// Record sections that define symbols mentioned in --keep-unique <symbol>
// and symbols referred to by address-significance tables. These sections are
// ineligible for ICF.
template <class ELFT>
static void findKeepUniqueSections(opt::InputArgList &Args) {
for (auto *Arg : Args.filtered(OPT_keep_unique)) {
StringRef Name = Arg->getValue();
auto *D = dyn_cast_or_null<Defined>(Symtab->find(Name));
if (!D || !D->Section) {
warn("could not find symbol " + Name + " to keep unique");
continue;
}
D->Section->KeepUnique = true;
}
// --icf=all --ignore-data-address-equality means that we can ignore
// the dynsym and address-significance tables entirely.
if (Config->ICF == ICFLevel::All && Config->IgnoreDataAddressEquality)
return;
// Symbols in the dynsym could be address-significant in other executables
// or DSOs, so we conservatively mark them as address-significant.
for (Symbol *S : Symtab->getSymbols())
if (S->includeInDynsym())
markAddrsig(S);
// Visit the address-significance table in each object file and mark each
// referenced symbol as address-significant.
for (InputFile *F : ObjectFiles) {
auto *Obj = cast<ObjFile<ELFT>>(F);
ArrayRef<Symbol *> Syms = Obj->getSymbols();
if (Obj->AddrsigSec) {
ArrayRef<uint8_t> Contents =
check(Obj->getObj().getSectionContents(Obj->AddrsigSec));
const uint8_t *Cur = Contents.begin();
while (Cur != Contents.end()) {
unsigned Size;
const char *Err;
uint64_t SymIndex = decodeULEB128(Cur, &Size, Contents.end(), &Err);
if (Err)
fatal(toString(F) + ": could not decode addrsig section: " + Err);
markAddrsig(Syms[SymIndex]);
Cur += Size;
}
} else {
// If an object file does not have an address-significance table,
// conservatively mark all of its symbols as address-significant.
for (Symbol *S : Syms)
markAddrsig(S);
}
}
}
template <class ELFT> static Symbol *addUndefined(StringRef Name) {
return Symtab->addUndefined<ELFT>(Name, STB_GLOBAL, STV_DEFAULT, 0, false,
nullptr);
}
// The --wrap option is a feature to rename symbols so that you can write
// wrappers for existing functions. If you pass `-wrap=foo`, all
// occurrences of symbol `foo` are resolved to `wrap_foo` (so, you are
// expected to write `wrap_foo` function as a wrapper). The original
// symbol becomes accessible as `real_foo`, so you can call that from your
// wrapper.
//
// This data structure is instantiated for each -wrap option.
struct WrappedSymbol {
Symbol *Sym;
Symbol *Real;
Symbol *Wrap;
};
// Handles -wrap option.
//
// This function instantiates wrapper symbols. At this point, they seem
// like they are not being used at all, so we explicitly set some flags so
// that LTO won't eliminate them.
template <class ELFT>
static std::vector<WrappedSymbol> addWrappedSymbols(opt::InputArgList &Args) {
std::vector<WrappedSymbol> V;
DenseSet<StringRef> Seen;
for (auto *Arg : Args.filtered(OPT_wrap)) {
StringRef Name = Arg->getValue();
if (!Seen.insert(Name).second)
continue;
Symbol *Sym = Symtab->find(Name);
if (!Sym)
continue;
Symbol *Real = addUndefined<ELFT>(Saver.save("__real_" + Name));
Symbol *Wrap = addUndefined<ELFT>(Saver.save("__wrap_" + Name));
V.push_back({Sym, Real, Wrap});
// We want to tell LTO not to inline symbols to be overwritten
// because LTO doesn't know the final symbol contents after renaming.
Real->CanInline = false;
Sym->CanInline = false;
// Tell LTO not to eliminate these symbols.
Sym->IsUsedInRegularObj = true;
Wrap->IsUsedInRegularObj = true;
}
return V;
}
// Do renaming for -wrap by updating pointers to symbols.
//
// When this function is executed, only InputFiles and symbol table
// contain pointers to symbol objects. We visit them to replace pointers,
// so that wrapped symbols are swapped as instructed by the command line.
template <class ELFT> static void wrapSymbols(ArrayRef<WrappedSymbol> Wrapped) {
DenseMap<Symbol *, Symbol *> Map;
for (const WrappedSymbol &W : Wrapped) {
Map[W.Sym] = W.Wrap;
Map[W.Real] = W.Sym;
}
// Update pointers in input files.
parallelForEach(ObjectFiles, [&](InputFile *File) {
std::vector<Symbol *> &Syms = File->getMutableSymbols();
for (size_t I = 0, E = Syms.size(); I != E; ++I)
if (Symbol *S = Map.lookup(Syms[I]))
Syms[I] = S;
});
// Update pointers in the symbol table.
for (const WrappedSymbol &W : Wrapped)
Symtab->wrap(W.Sym, W.Real, W.Wrap);
}
static const char *LibcallRoutineNames[] = {
#define HANDLE_LIBCALL(code, name) name,
#include "llvm/IR/RuntimeLibcalls.def"
#undef HANDLE_LIBCALL
};
// 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();
InX<ELFT>::VerSym = nullptr;
InX<ELFT>::VerNeed = nullptr;
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 Name : Script->ReferencedSymbols)
addUndefined<ELFT>(Name);
// 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.
handleUndefined<ELFT>(Config->Entry);
// If any of our inputs are bitcode files, the LTO code generator may create
// references to certain library functions that might not be explicit in the
// bitcode file's symbol table. If any of those library functions are defined
// in a bitcode file in an archive member, we need to arrange to use LTO to
// compile those archive members by adding them to the link beforehand.
//
// However, adding all libcall symbols to the link can have undesired
// consequences. For example, the libgcc implementation of
// __sync_val_compare_and_swap_8 on 32-bit ARM pulls in an .init_array entry
// that aborts the program if the Linux kernel does not support 64-bit
// atomics, which would prevent the program from running even if it does not
// use 64-bit atomics.
//
// Therefore, we only add libcall symbols to the link before LTO if we have
// to, i.e. if the symbol's definition is in bitcode. Any other required
// libcall symbols will be added to the link after LTO when we add the LTO
// object file to the link.
if (!BitcodeFiles.empty())
for (const char *S : LibcallRoutineNames)
handleLibcall<ELFT>(S);
// 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);
// Create wrapped symbols for -wrap option.
std::vector<WrappedSymbol> Wrapped = addWrappedSymbols<ELFT>(Args);
// 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();
// Do link-time optimization if given files are LLVM bitcode files.
// This compiles bitcode files into real object files.
//
// With this the symbol table should be complete. After this, no new names
// except a few linker-synthesized ones will be added to the symbol table.
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;
// Likewise, --plugin-opt=emit-llvm is an option to make LTO create
// an output file in bitcode and exit, so that you can just get a
// combined bitcode file.
if (Config->EmitLLVM)
return;
// Apply symbol renames for -wrap.
if (!Wrapped.empty())
wrapSymbols<ELFT>(Wrapped);
// 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");
}
// This adds a .comment section containing a version string. We have to add it
// before mergeSections 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.
splitSections<ELFT>();
markLive<ELFT>();
demoteSharedSymbols<ELFT>();
mergeSections();
if (Config->ICF != ICFLevel::None) {
findKeepUniqueSections<ELFT>(Args);
doIcf<ELFT>();
}
// Read the callgraph now that we know what was gced or icfed
if (Config->CallGraphProfileSort) {
if (auto *Arg = Args.getLastArg(OPT_call_graph_ordering_file))
if (Optional<MemoryBufferRef> Buffer = readFile(Arg->getValue()))
readCallGraph(*Buffer);
readCallGraphsFromObjectFiles<ELFT>();
}
// Write the result to the file.
writeResult<ELFT>();
}
Index: head/contrib/llvm/tools/lld/ELF/InputSection.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/InputSection.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/InputSection.cpp (revision 350467)
@@ -1,1281 +1,1275 @@
//===- InputSection.cpp ---------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "InputSection.h"
#include "Config.h"
#include "EhFrame.h"
#include "InputFiles.h"
#include "LinkerScript.h"
#include "OutputSections.h"
#include "Relocations.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "Thunks.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/Threading.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
#include <mutex>
#include <set>
#include <vector>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::support;
using namespace llvm::support::endian;
using namespace llvm::sys;
using namespace lld;
using namespace lld::elf;
std::vector<InputSectionBase *> elf::InputSections;
// Returns a string to construct an error message.
std::string lld::toString(const InputSectionBase *Sec) {
return (toString(Sec->File) + ":(" + Sec->Name + ")").str();
}
template <class ELFT>
static ArrayRef<uint8_t> getSectionContents(ObjFile<ELFT> &File,
const typename ELFT::Shdr &Hdr) {
if (Hdr.sh_type == SHT_NOBITS)
return makeArrayRef<uint8_t>(nullptr, Hdr.sh_size);
return check(File.getObj().getSectionContents(&Hdr));
}
InputSectionBase::InputSectionBase(InputFile *File, uint64_t Flags,
uint32_t Type, uint64_t Entsize,
uint32_t Link, uint32_t Info,
uint32_t Alignment, ArrayRef<uint8_t> Data,
StringRef Name, Kind SectionKind)
: SectionBase(SectionKind, Name, Flags, Entsize, Alignment, Type, Info,
Link),
File(File), RawData(Data) {
// In order to reduce memory allocation, we assume that mergeable
// sections are smaller than 4 GiB, which is not an unreasonable
// assumption as of 2017.
if (SectionKind == SectionBase::Merge && RawData.size() > UINT32_MAX)
error(toString(this) + ": section too large");
NumRelocations = 0;
AreRelocsRela = false;
// The ELF spec states that a value of 0 means the section has
// no alignment constraits.
uint32_t V = std::max<uint64_t>(Alignment, 1);
if (!isPowerOf2_64(V))
fatal(toString(File) + ": section sh_addralign is not a power of 2");
this->Alignment = V;
// In ELF, each section can be compressed by zlib, and if compressed,
// section name may be mangled by appending "z" (e.g. ".zdebug_info").
// If that's the case, demangle section name so that we can handle a
// section as if it weren't compressed.
if ((Flags & SHF_COMPRESSED) || Name.startswith(".zdebug")) {
if (!zlib::isAvailable())
error(toString(File) + ": contains a compressed section, " +
"but zlib is not available");
parseCompressedHeader();
}
}
// Drop SHF_GROUP bit unless we are producing a re-linkable object file.
// SHF_GROUP is a marker that a section belongs to some comdat group.
// That flag doesn't make sense in an executable.
static uint64_t getFlags(uint64_t Flags) {
Flags &= ~(uint64_t)SHF_INFO_LINK;
if (!Config->Relocatable)
Flags &= ~(uint64_t)SHF_GROUP;
return Flags;
}
// GNU assembler 2.24 and LLVM 4.0.0's MC (the newest release as of
// March 2017) fail to infer section types for sections starting with
// ".init_array." or ".fini_array.". They set SHT_PROGBITS instead of
// SHF_INIT_ARRAY. As a result, the following assembler directive
// creates ".init_array.100" with SHT_PROGBITS, for example.
//
// .section .init_array.100, "aw"
//
// This function forces SHT_{INIT,FINI}_ARRAY so that we can handle
// incorrect inputs as if they were correct from the beginning.
static uint64_t getType(uint64_t Type, StringRef Name) {
if (Type == SHT_PROGBITS && Name.startswith(".init_array."))
return SHT_INIT_ARRAY;
if (Type == SHT_PROGBITS && Name.startswith(".fini_array."))
return SHT_FINI_ARRAY;
return Type;
}
template <class ELFT>
InputSectionBase::InputSectionBase(ObjFile<ELFT> &File,
const typename ELFT::Shdr &Hdr,
StringRef Name, Kind SectionKind)
: InputSectionBase(&File, getFlags(Hdr.sh_flags),
getType(Hdr.sh_type, Name), Hdr.sh_entsize, Hdr.sh_link,
Hdr.sh_info, Hdr.sh_addralign,
getSectionContents(File, Hdr), Name, SectionKind) {
// We reject object files having insanely large alignments even though
// they are allowed by the spec. I think 4GB is a reasonable limitation.
// We might want to relax this in the future.
if (Hdr.sh_addralign > UINT32_MAX)
fatal(toString(&File) + ": section sh_addralign is too large");
}
size_t InputSectionBase::getSize() const {
if (auto *S = dyn_cast<SyntheticSection>(this))
return S->getSize();
if (UncompressedSize >= 0)
return UncompressedSize;
return RawData.size();
}
void InputSectionBase::uncompress() const {
size_t Size = UncompressedSize;
UncompressedBuf.reset(new char[Size]);
if (Error E =
zlib::uncompress(toStringRef(RawData), UncompressedBuf.get(), Size))
fatal(toString(this) +
": uncompress failed: " + llvm::toString(std::move(E)));
RawData = makeArrayRef((uint8_t *)UncompressedBuf.get(), Size);
}
uint64_t InputSectionBase::getOffsetInFile() const {
const uint8_t *FileStart = (const uint8_t *)File->MB.getBufferStart();
const uint8_t *SecStart = data().begin();
return SecStart - FileStart;
}
uint64_t SectionBase::getOffset(uint64_t Offset) const {
switch (kind()) {
case Output: {
auto *OS = cast<OutputSection>(this);
// For output sections we treat offset -1 as the end of the section.
return Offset == uint64_t(-1) ? OS->Size : Offset;
}
case Regular:
case Synthetic:
return cast<InputSection>(this)->getOffset(Offset);
case EHFrame:
// The file crtbeginT.o has relocations pointing to the start of an empty
// .eh_frame that is known to be the first in the link. It does that to
// identify the start of the output .eh_frame.
return Offset;
case Merge:
const MergeInputSection *MS = cast<MergeInputSection>(this);
if (InputSection *IS = MS->getParent())
return IS->getOffset(MS->getParentOffset(Offset));
return MS->getParentOffset(Offset);
}
llvm_unreachable("invalid section kind");
}
uint64_t SectionBase::getVA(uint64_t Offset) const {
const OutputSection *Out = getOutputSection();
return (Out ? Out->Addr : 0) + getOffset(Offset);
}
OutputSection *SectionBase::getOutputSection() {
InputSection *Sec;
if (auto *IS = dyn_cast<InputSection>(this))
Sec = IS;
else if (auto *MS = dyn_cast<MergeInputSection>(this))
Sec = MS->getParent();
else if (auto *EH = dyn_cast<EhInputSection>(this))
Sec = EH->getParent();
else
return cast<OutputSection>(this);
return Sec ? Sec->getParent() : nullptr;
}
// When a section is compressed, `RawData` consists with a header followed
// by zlib-compressed data. This function parses a header to initialize
// `UncompressedSize` member and remove the header from `RawData`.
void InputSectionBase::parseCompressedHeader() {
typedef typename ELF64LE::Chdr Chdr64;
typedef typename ELF32LE::Chdr Chdr32;
// Old-style header
if (Name.startswith(".zdebug")) {
if (!toStringRef(RawData).startswith("ZLIB")) {
error(toString(this) + ": corrupted compressed section header");
return;
}
RawData = RawData.slice(4);
if (RawData.size() < 8) {
error(toString(this) + ": corrupted compressed section header");
return;
}
UncompressedSize = read64be(RawData.data());
RawData = RawData.slice(8);
// Restore the original section name.
// (e.g. ".zdebug_info" -> ".debug_info")
Name = Saver.save("." + Name.substr(2));
return;
}
assert(Flags & SHF_COMPRESSED);
Flags &= ~(uint64_t)SHF_COMPRESSED;
// New-style 64-bit header
if (Config->Is64) {
if (RawData.size() < sizeof(Chdr64)) {
error(toString(this) + ": corrupted compressed section");
return;
}
auto *Hdr = reinterpret_cast<const Chdr64 *>(RawData.data());
if (Hdr->ch_type != ELFCOMPRESS_ZLIB) {
error(toString(this) + ": unsupported compression type");
return;
}
UncompressedSize = Hdr->ch_size;
Alignment = std::max<uint64_t>(Hdr->ch_addralign, 1);
RawData = RawData.slice(sizeof(*Hdr));
return;
}
// New-style 32-bit header
if (RawData.size() < sizeof(Chdr32)) {
error(toString(this) + ": corrupted compressed section");
return;
}
auto *Hdr = reinterpret_cast<const Chdr32 *>(RawData.data());
if (Hdr->ch_type != ELFCOMPRESS_ZLIB) {
error(toString(this) + ": unsupported compression type");
return;
}
UncompressedSize = Hdr->ch_size;
Alignment = std::max<uint64_t>(Hdr->ch_addralign, 1);
RawData = RawData.slice(sizeof(*Hdr));
}
InputSection *InputSectionBase::getLinkOrderDep() const {
assert(Link);
assert(Flags & SHF_LINK_ORDER);
return cast<InputSection>(File->getSections()[Link]);
}
// Find a function symbol that encloses a given location.
template <class ELFT>
Defined *InputSectionBase::getEnclosingFunction(uint64_t Offset) {
for (Symbol *B : File->getSymbols())
if (Defined *D = dyn_cast<Defined>(B))
if (D->Section == this && D->Type == STT_FUNC && D->Value <= Offset &&
Offset < D->Value + D->Size)
return D;
return nullptr;
}
// Returns a source location string. Used to construct an error message.
template <class ELFT>
std::string InputSectionBase::getLocation(uint64_t Offset) {
std::string SecAndOffset = (Name + "+0x" + utohexstr(Offset)).str();
// We don't have file for synthetic sections.
if (getFile<ELFT>() == nullptr)
return (Config->OutputFile + ":(" + SecAndOffset + ")")
.str();
// First check if we can get desired values from debugging information.
if (Optional<DILineInfo> Info = getFile<ELFT>()->getDILineInfo(this, Offset))
return Info->FileName + ":" + std::to_string(Info->Line) + ":(" +
SecAndOffset + ")";
// File->SourceFile contains STT_FILE symbol that contains a
// source file name. If it's missing, we use an object file name.
std::string SrcFile = getFile<ELFT>()->SourceFile;
if (SrcFile.empty())
SrcFile = toString(File);
if (Defined *D = getEnclosingFunction<ELFT>(Offset))
return SrcFile + ":(function " + toString(*D) + ": " + SecAndOffset + ")";
// If there's no symbol, print out the offset in the section.
return (SrcFile + ":(" + SecAndOffset + ")");
}
// This function is intended to be used for constructing an error message.
// The returned message looks like this:
//
// foo.c:42 (/home/alice/possibly/very/long/path/foo.c:42)
//
// Returns an empty string if there's no way to get line info.
std::string InputSectionBase::getSrcMsg(const Symbol &Sym, uint64_t Offset) {
return File->getSrcMsg(Sym, *this, Offset);
}
// Returns a filename string along with an optional section name. This
// function is intended to be used for constructing an error
// message. The returned message looks like this:
//
// path/to/foo.o:(function bar)
//
// or
//
// path/to/foo.o:(function bar) in archive path/to/bar.a
std::string InputSectionBase::getObjMsg(uint64_t Off) {
std::string Filename = File->getName();
std::string Archive;
if (!File->ArchiveName.empty())
Archive = " in archive " + File->ArchiveName;
// Find a symbol that encloses a given location.
for (Symbol *B : File->getSymbols())
if (auto *D = dyn_cast<Defined>(B))
if (D->Section == this && D->Value <= Off && Off < D->Value + D->Size)
return Filename + ":(" + toString(*D) + ")" + Archive;
// If there's no symbol, print out the offset in the section.
return (Filename + ":(" + Name + "+0x" + utohexstr(Off) + ")" + Archive)
.str();
}
InputSection InputSection::Discarded(nullptr, 0, 0, 0, ArrayRef<uint8_t>(), "");
InputSection::InputSection(InputFile *F, uint64_t Flags, uint32_t Type,
uint32_t Alignment, ArrayRef<uint8_t> Data,
StringRef Name, Kind K)
: InputSectionBase(F, Flags, Type,
/*Entsize*/ 0, /*Link*/ 0, /*Info*/ 0, Alignment, Data,
Name, K) {}
template <class ELFT>
InputSection::InputSection(ObjFile<ELFT> &F, const typename ELFT::Shdr &Header,
StringRef Name)
: InputSectionBase(F, Header, Name, InputSectionBase::Regular) {}
bool InputSection::classof(const SectionBase *S) {
return S->kind() == SectionBase::Regular ||
S->kind() == SectionBase::Synthetic;
}
OutputSection *InputSection::getParent() const {
return cast_or_null<OutputSection>(Parent);
}
// Copy SHT_GROUP section contents. Used only for the -r option.
template <class ELFT> void InputSection::copyShtGroup(uint8_t *Buf) {
// ELFT::Word is the 32-bit integral type in the target endianness.
typedef typename ELFT::Word u32;
ArrayRef<u32> From = getDataAs<u32>();
auto *To = reinterpret_cast<u32 *>(Buf);
// The first entry is not a section number but a flag.
*To++ = From[0];
// Adjust section numbers because section numbers in an input object
// files are different in the output.
ArrayRef<InputSectionBase *> Sections = File->getSections();
for (uint32_t Idx : From.slice(1))
*To++ = Sections[Idx]->getOutputSection()->SectionIndex;
}
InputSectionBase *InputSection::getRelocatedSection() const {
if (!File || (Type != SHT_RELA && Type != SHT_REL))
return nullptr;
ArrayRef<InputSectionBase *> Sections = File->getSections();
return Sections[Info];
}
// This is used for -r and --emit-relocs. We can't use memcpy to copy
// relocations because we need to update symbol table offset and section index
// for each relocation. So we copy relocations one by one.
template <class ELFT, class RelTy>
void InputSection::copyRelocations(uint8_t *Buf, ArrayRef<RelTy> Rels) {
InputSectionBase *Sec = getRelocatedSection();
for (const RelTy &Rel : Rels) {
RelType Type = Rel.getType(Config->IsMips64EL);
Symbol &Sym = getFile<ELFT>()->getRelocTargetSym(Rel);
auto *P = reinterpret_cast<typename ELFT::Rela *>(Buf);
Buf += sizeof(RelTy);
if (RelTy::IsRela)
P->r_addend = getAddend<ELFT>(Rel);
// Output section VA is zero for -r, so r_offset is an offset within the
// section, but for --emit-relocs it is an virtual address.
P->r_offset = Sec->getVA(Rel.r_offset);
P->setSymbolAndType(In.SymTab->getSymbolIndex(&Sym), Type,
Config->IsMips64EL);
if (Sym.Type == STT_SECTION) {
// We combine multiple section symbols into only one per
// section. This means we have to update the addend. That is
// trivial for Elf_Rela, but for Elf_Rel we have to write to the
// section data. We do that by adding to the Relocation vector.
// .eh_frame is horribly special and can reference discarded sections. To
// avoid having to parse and recreate .eh_frame, we just replace any
// relocation in it pointing to discarded sections with R_*_NONE, which
// hopefully creates a frame that is ignored at runtime.
auto *D = dyn_cast<Defined>(&Sym);
if (!D) {
error("STT_SECTION symbol should be defined");
continue;
}
SectionBase *Section = D->Section->Repl;
if (!Section->Live) {
P->setSymbolAndType(0, 0, false);
continue;
}
int64_t Addend = getAddend<ELFT>(Rel);
const uint8_t *BufLoc = Sec->data().begin() + Rel.r_offset;
if (!RelTy::IsRela)
Addend = Target->getImplicitAddend(BufLoc, Type);
if (Config->EMachine == EM_MIPS && Config->Relocatable &&
Target->getRelExpr(Type, Sym, BufLoc) == R_MIPS_GOTREL) {
// Some MIPS relocations depend on "gp" value. By default,
// this value has 0x7ff0 offset from a .got section. But
// relocatable files produced by a complier or a linker
// might redefine this default value and we must use it
// for a calculation of the relocation result. When we
// generate EXE or DSO it's trivial. Generating a relocatable
// output is more difficult case because the linker does
// not calculate relocations in this mode and loses
// individual "gp" values used by each input object file.
// As a workaround we add the "gp" value to the relocation
// addend and save it back to the file.
Addend += Sec->getFile<ELFT>()->MipsGp0;
}
if (RelTy::IsRela)
P->r_addend = Sym.getVA(Addend) - Section->getOutputSection()->Addr;
else if (Config->Relocatable)
Sec->Relocations.push_back({R_ABS, Type, Rel.r_offset, Addend, &Sym});
}
}
}
// The ARM and AArch64 ABI handle pc-relative relocations to undefined weak
// references specially. The general rule is that the value of the symbol in
// this context is the address of the place P. A further special case is that
// branch relocations to an undefined weak reference resolve to the next
// instruction.
static uint32_t getARMUndefinedRelativeWeakVA(RelType Type, uint32_t A,
uint32_t P) {
switch (Type) {
// Unresolved branch relocations to weak references resolve to next
// instruction, this will be either 2 or 4 bytes on from P.
case R_ARM_THM_JUMP11:
return P + 2 + A;
case R_ARM_CALL:
case R_ARM_JUMP24:
case R_ARM_PC24:
case R_ARM_PLT32:
case R_ARM_PREL31:
case R_ARM_THM_JUMP19:
case R_ARM_THM_JUMP24:
return P + 4 + A;
case R_ARM_THM_CALL:
// We don't want an interworking BLX to ARM
return P + 5 + A;
// Unresolved non branch pc-relative relocations
// R_ARM_TARGET2 which can be resolved relatively is not present as it never
// targets a weak-reference.
case R_ARM_MOVW_PREL_NC:
case R_ARM_MOVT_PREL:
case R_ARM_REL32:
case R_ARM_THM_MOVW_PREL_NC:
case R_ARM_THM_MOVT_PREL:
return P + A;
}
llvm_unreachable("ARM pc-relative relocation expected\n");
}
// The comment above getARMUndefinedRelativeWeakVA applies to this function.
static uint64_t getAArch64UndefinedRelativeWeakVA(uint64_t Type, uint64_t A,
uint64_t P) {
switch (Type) {
// Unresolved branch relocations to weak references resolve to next
// instruction, this is 4 bytes on from P.
case R_AARCH64_CALL26:
case R_AARCH64_CONDBR19:
case R_AARCH64_JUMP26:
case R_AARCH64_TSTBR14:
return P + 4 + A;
// Unresolved non branch pc-relative relocations
case R_AARCH64_PREL16:
case R_AARCH64_PREL32:
case R_AARCH64_PREL64:
case R_AARCH64_ADR_PREL_LO21:
case R_AARCH64_LD_PREL_LO19:
return P + A;
}
llvm_unreachable("AArch64 pc-relative relocation expected\n");
}
// ARM SBREL relocations are of the form S + A - B where B is the static base
// The ARM ABI defines base to be "addressing origin of the output segment
// defining the symbol S". We defined the "addressing origin"/static base to be
// the base of the PT_LOAD segment containing the Sym.
// The procedure call standard only defines a Read Write Position Independent
// RWPI variant so in practice we should expect the static base to be the base
// of the RW segment.
static uint64_t getARMStaticBase(const Symbol &Sym) {
OutputSection *OS = Sym.getOutputSection();
if (!OS || !OS->PtLoad || !OS->PtLoad->FirstSec)
fatal("SBREL relocation to " + Sym.getName() + " without static base");
return OS->PtLoad->FirstSec->Addr;
}
// For R_RISCV_PC_INDIRECT (R_RISCV_PCREL_LO12_{I,S}), the symbol actually
// points the corresponding R_RISCV_PCREL_HI20 relocation, and the target VA
// is calculated using PCREL_HI20's symbol.
//
// This function returns the R_RISCV_PCREL_HI20 relocation from
// R_RISCV_PCREL_LO12's symbol and addend.
static Relocation *getRISCVPCRelHi20(const Symbol *Sym, uint64_t Addend) {
const Defined *D = cast<Defined>(Sym);
InputSection *IS = cast<InputSection>(D->Section);
if (Addend != 0)
warn("Non-zero addend in R_RISCV_PCREL_LO12 relocation to " +
IS->getObjMsg(D->Value) + " is ignored");
// Relocations are sorted by offset, so we can use std::equal_range to do
// binary search.
auto Range = std::equal_range(IS->Relocations.begin(), IS->Relocations.end(),
D->Value, RelocationOffsetComparator{});
for (auto It = std::get<0>(Range); It != std::get<1>(Range); ++It)
if (isRelExprOneOf<R_PC>(It->Expr))
return &*It;
error("R_RISCV_PCREL_LO12 relocation points to " + IS->getObjMsg(D->Value) +
" without an associated R_RISCV_PCREL_HI20 relocation");
return nullptr;
}
// A TLS symbol's virtual address is relative to the TLS segment. Add a
// target-specific adjustment to produce a thread-pointer-relative offset.
static int64_t getTlsTpOffset() {
switch (Config->EMachine) {
case EM_ARM:
case EM_AARCH64:
// Variant 1. The thread pointer points to a TCB with a fixed 2-word size,
// followed by a variable amount of alignment padding, followed by the TLS
// segment.
return alignTo(Config->Wordsize * 2, Out::TlsPhdr->p_align);
case EM_386:
case EM_X86_64:
// Variant 2. The TLS segment is located just before the thread pointer.
return -Out::TlsPhdr->p_memsz;
case EM_PPC64:
// The thread pointer points to a fixed offset from the start of the
// executable's TLS segment. An offset of 0x7000 allows a signed 16-bit
// offset to reach 0x1000 of TCB/thread-library data and 0xf000 of the
// program's TLS segment.
return -0x7000;
default:
llvm_unreachable("unhandled Config->EMachine");
}
}
static uint64_t getRelocTargetVA(const InputFile *File, RelType Type, int64_t A,
uint64_t P, const Symbol &Sym, RelExpr Expr) {
switch (Expr) {
case R_INVALID:
return 0;
case R_ABS:
case R_RELAX_TLS_LD_TO_LE_ABS:
case R_RELAX_GOT_PC_NOPIC:
return Sym.getVA(A);
case R_ADDEND:
return A;
case R_ARM_SBREL:
return Sym.getVA(A) - getARMStaticBase(Sym);
case R_GOT:
- case R_GOT_PLT:
case R_RELAX_TLS_GD_TO_IE_ABS:
return Sym.getGotVA() + A;
case R_GOTONLY_PC:
return In.Got->getVA() + A - P;
case R_GOTONLY_PC_FROM_END:
return In.Got->getVA() + A - P + In.Got->getSize();
case R_GOTREL:
return Sym.getVA(A) - In.Got->getVA();
case R_GOTREL_FROM_END:
return Sym.getVA(A) - In.Got->getVA() - In.Got->getSize();
case R_GOT_FROM_END:
case R_RELAX_TLS_GD_TO_IE_END:
return Sym.getGotOffset() + A - In.Got->getSize();
case R_TLSLD_GOT_OFF:
case R_GOT_OFF:
case R_RELAX_TLS_GD_TO_IE_GOT_OFF:
return Sym.getGotOffset() + A;
case R_AARCH64_GOT_PAGE_PC:
- case R_AARCH64_GOT_PAGE_PC_PLT:
case R_AARCH64_RELAX_TLS_GD_TO_IE_PAGE_PC:
return getAArch64Page(Sym.getGotVA() + A) - getAArch64Page(P);
case R_GOT_PC:
case R_RELAX_TLS_GD_TO_IE:
return Sym.getGotVA() + A - P;
case R_HEXAGON_GOT:
return Sym.getGotVA() - In.GotPlt->getVA();
case R_MIPS_GOTREL:
return Sym.getVA(A) - In.MipsGot->getGp(File);
case R_MIPS_GOT_GP:
return In.MipsGot->getGp(File) + A;
case R_MIPS_GOT_GP_PC: {
// R_MIPS_LO16 expression has R_MIPS_GOT_GP_PC type iif the target
// is _gp_disp symbol. In that case we should use the following
// formula for calculation "AHL + GP - P + 4". For details see p. 4-19 at
// ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
// microMIPS variants of these relocations use slightly different
// expressions: AHL + GP - P + 3 for %lo() and AHL + GP - P - 1 for %hi()
// to correctly handle less-sugnificant bit of the microMIPS symbol.
uint64_t V = In.MipsGot->getGp(File) + A - P;
if (Type == R_MIPS_LO16 || Type == R_MICROMIPS_LO16)
V += 4;
if (Type == R_MICROMIPS_LO16 || Type == R_MICROMIPS_HI16)
V -= 1;
return V;
}
case R_MIPS_GOT_LOCAL_PAGE:
// If relocation against MIPS local symbol requires GOT entry, this entry
// should be initialized by 'page address'. This address is high 16-bits
// of sum the symbol's value and the addend.
return In.MipsGot->getVA() + In.MipsGot->getPageEntryOffset(File, Sym, A) -
In.MipsGot->getGp(File);
case R_MIPS_GOT_OFF:
case R_MIPS_GOT_OFF32:
// In case of MIPS if a GOT relocation has non-zero addend this addend
// should be applied to the GOT entry content not to the GOT entry offset.
// That is why we use separate expression type.
return In.MipsGot->getVA() + In.MipsGot->getSymEntryOffset(File, Sym, A) -
In.MipsGot->getGp(File);
case R_MIPS_TLSGD:
return In.MipsGot->getVA() + In.MipsGot->getGlobalDynOffset(File, Sym) -
In.MipsGot->getGp(File);
case R_MIPS_TLSLD:
return In.MipsGot->getVA() + In.MipsGot->getTlsIndexOffset(File) -
In.MipsGot->getGp(File);
case R_AARCH64_PAGE_PC: {
uint64_t Val = Sym.isUndefWeak() ? P + A : Sym.getVA(A);
- return getAArch64Page(Val) - getAArch64Page(P);
- }
- case R_AARCH64_PLT_PAGE_PC: {
- uint64_t Val = Sym.isUndefWeak() ? P + A : Sym.getPltVA() + A;
return getAArch64Page(Val) - getAArch64Page(P);
}
case R_RISCV_PC_INDIRECT: {
if (const Relocation *HiRel = getRISCVPCRelHi20(&Sym, A))
return getRelocTargetVA(File, HiRel->Type, HiRel->Addend, Sym.getVA(),
*HiRel->Sym, HiRel->Expr);
return 0;
}
case R_PC: {
uint64_t Dest;
if (Sym.isUndefWeak()) {
// On ARM and AArch64 a branch to an undefined weak resolves to the
// next instruction, otherwise the place.
if (Config->EMachine == EM_ARM)
Dest = getARMUndefinedRelativeWeakVA(Type, A, P);
else if (Config->EMachine == EM_AARCH64)
Dest = getAArch64UndefinedRelativeWeakVA(Type, A, P);
else
Dest = Sym.getVA(A);
} else {
Dest = Sym.getVA(A);
}
return Dest - P;
}
case R_PLT:
return Sym.getPltVA() + A;
case R_PLT_PC:
case R_PPC_CALL_PLT:
return Sym.getPltVA() + A - P;
case R_PPC_CALL: {
uint64_t SymVA = Sym.getVA(A);
// If we have an undefined weak symbol, we might get here with a symbol
// address of zero. That could overflow, but the code must be unreachable,
// so don't bother doing anything at all.
if (!SymVA)
return 0;
// PPC64 V2 ABI describes two entry points to a function. The global entry
// point is used for calls where the caller and callee (may) have different
// TOC base pointers and r2 needs to be modified to hold the TOC base for
// the callee. For local calls the caller and callee share the same
// TOC base and so the TOC pointer initialization code should be skipped by
// branching to the local entry point.
return SymVA - P + getPPC64GlobalEntryToLocalEntryOffset(Sym.StOther);
}
case R_PPC_TOC:
return getPPC64TocBase() + A;
case R_RELAX_GOT_PC:
return Sym.getVA(A) - P;
case R_RELAX_TLS_GD_TO_LE:
case R_RELAX_TLS_IE_TO_LE:
case R_RELAX_TLS_LD_TO_LE:
case R_TLS:
// A weak undefined TLS symbol resolves to the base of the TLS
// block, i.e. gets a value of zero. If we pass --gc-sections to
// lld and .tbss is not referenced, it gets reclaimed and we don't
// create a TLS program header. Therefore, we resolve this
// statically to zero.
if (Sym.isTls() && Sym.isUndefWeak())
return 0;
return Sym.getVA(A) + getTlsTpOffset();
case R_RELAX_TLS_GD_TO_LE_NEG:
case R_NEG_TLS:
return Out::TlsPhdr->p_memsz - Sym.getVA(A);
case R_SIZE:
return Sym.getSize() + A;
case R_TLSDESC:
return In.Got->getGlobalDynAddr(Sym) + A;
case R_AARCH64_TLSDESC_PAGE:
return getAArch64Page(In.Got->getGlobalDynAddr(Sym) + A) -
getAArch64Page(P);
case R_TLSGD_GOT:
return In.Got->getGlobalDynOffset(Sym) + A;
case R_TLSGD_GOT_FROM_END:
return In.Got->getGlobalDynOffset(Sym) + A - In.Got->getSize();
case R_TLSGD_PC:
return In.Got->getGlobalDynAddr(Sym) + A - P;
case R_TLSLD_GOT_FROM_END:
return In.Got->getTlsIndexOff() + A - In.Got->getSize();
case R_TLSLD_GOT:
return In.Got->getTlsIndexOff() + A;
case R_TLSLD_PC:
return In.Got->getTlsIndexVA() + A - P;
default:
llvm_unreachable("invalid expression");
}
}
// This function applies relocations to sections without SHF_ALLOC bit.
// Such sections are never mapped to memory at runtime. Debug sections are
// an example. Relocations in non-alloc sections are much easier to
// handle than in allocated sections because it will never need complex
// treatement such as GOT or PLT (because at runtime no one refers them).
// So, we handle relocations for non-alloc sections directly in this
// function as a performance optimization.
template <class ELFT, class RelTy>
void InputSection::relocateNonAlloc(uint8_t *Buf, ArrayRef<RelTy> Rels) {
const unsigned Bits = sizeof(typename ELFT::uint) * 8;
for (const RelTy &Rel : Rels) {
RelType Type = Rel.getType(Config->IsMips64EL);
// GCC 8.0 or earlier have a bug that they emit R_386_GOTPC relocations
// against _GLOBAL_OFFSET_TABLE_ for .debug_info. The bug has been fixed
// in 2017 (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82630), but we
// need to keep this bug-compatible code for a while.
if (Config->EMachine == EM_386 && Type == R_386_GOTPC)
continue;
uint64_t Offset = getOffset(Rel.r_offset);
uint8_t *BufLoc = Buf + Offset;
int64_t Addend = getAddend<ELFT>(Rel);
if (!RelTy::IsRela)
Addend += Target->getImplicitAddend(BufLoc, Type);
Symbol &Sym = getFile<ELFT>()->getRelocTargetSym(Rel);
RelExpr Expr = Target->getRelExpr(Type, Sym, BufLoc);
if (Expr == R_NONE)
continue;
if (Expr != R_ABS) {
std::string Msg = getLocation<ELFT>(Offset) +
": has non-ABS relocation " + toString(Type) +
" against symbol '" + toString(Sym) + "'";
if (Expr != R_PC) {
error(Msg);
return;
}
// If the control reaches here, we found a PC-relative relocation in a
// non-ALLOC section. Since non-ALLOC section is not loaded into memory
// at runtime, the notion of PC-relative doesn't make sense here. So,
// this is a usage error. However, GNU linkers historically accept such
// relocations without any errors and relocate them as if they were at
// address 0. For bug-compatibilty, we accept them with warnings. We
// know Steel Bank Common Lisp as of 2018 have this bug.
warn(Msg);
Target->relocateOne(BufLoc, Type,
SignExtend64<Bits>(Sym.getVA(Addend - Offset)));
continue;
}
if (Sym.isTls() && !Out::TlsPhdr)
Target->relocateOne(BufLoc, Type, 0);
else
Target->relocateOne(BufLoc, Type, SignExtend64<Bits>(Sym.getVA(Addend)));
}
}
// This is used when '-r' is given.
// For REL targets, InputSection::copyRelocations() may store artificial
// relocations aimed to update addends. They are handled in relocateAlloc()
// for allocatable sections, and this function does the same for
// non-allocatable sections, such as sections with debug information.
static void relocateNonAllocForRelocatable(InputSection *Sec, uint8_t *Buf) {
const unsigned Bits = Config->Is64 ? 64 : 32;
for (const Relocation &Rel : Sec->Relocations) {
// InputSection::copyRelocations() adds only R_ABS relocations.
assert(Rel.Expr == R_ABS);
uint8_t *BufLoc = Buf + Rel.Offset + Sec->OutSecOff;
uint64_t TargetVA = SignExtend64(Rel.Sym->getVA(Rel.Addend), Bits);
Target->relocateOne(BufLoc, Rel.Type, TargetVA);
}
}
template <class ELFT>
void InputSectionBase::relocate(uint8_t *Buf, uint8_t *BufEnd) {
if (Flags & SHF_EXECINSTR)
adjustSplitStackFunctionPrologues<ELFT>(Buf, BufEnd);
if (Flags & SHF_ALLOC) {
relocateAlloc(Buf, BufEnd);
return;
}
auto *Sec = cast<InputSection>(this);
if (Config->Relocatable)
relocateNonAllocForRelocatable(Sec, Buf);
else if (Sec->AreRelocsRela)
Sec->relocateNonAlloc<ELFT>(Buf, Sec->template relas<ELFT>());
else
Sec->relocateNonAlloc<ELFT>(Buf, Sec->template rels<ELFT>());
}
void InputSectionBase::relocateAlloc(uint8_t *Buf, uint8_t *BufEnd) {
assert(Flags & SHF_ALLOC);
const unsigned Bits = Config->Wordsize * 8;
for (const Relocation &Rel : Relocations) {
uint64_t Offset = Rel.Offset;
if (auto *Sec = dyn_cast<InputSection>(this))
Offset += Sec->OutSecOff;
uint8_t *BufLoc = Buf + Offset;
RelType Type = Rel.Type;
uint64_t AddrLoc = getOutputSection()->Addr + Offset;
RelExpr Expr = Rel.Expr;
uint64_t TargetVA = SignExtend64(
getRelocTargetVA(File, Type, Rel.Addend, AddrLoc, *Rel.Sym, Expr),
Bits);
switch (Expr) {
case R_RELAX_GOT_PC:
case R_RELAX_GOT_PC_NOPIC:
Target->relaxGot(BufLoc, TargetVA);
break;
case R_RELAX_TLS_IE_TO_LE:
Target->relaxTlsIeToLe(BufLoc, Type, TargetVA);
break;
case R_RELAX_TLS_LD_TO_LE:
case R_RELAX_TLS_LD_TO_LE_ABS:
Target->relaxTlsLdToLe(BufLoc, Type, TargetVA);
break;
case R_RELAX_TLS_GD_TO_LE:
case R_RELAX_TLS_GD_TO_LE_NEG:
Target->relaxTlsGdToLe(BufLoc, Type, TargetVA);
break;
case R_AARCH64_RELAX_TLS_GD_TO_IE_PAGE_PC:
case R_RELAX_TLS_GD_TO_IE:
case R_RELAX_TLS_GD_TO_IE_ABS:
case R_RELAX_TLS_GD_TO_IE_GOT_OFF:
case R_RELAX_TLS_GD_TO_IE_END:
Target->relaxTlsGdToIe(BufLoc, Type, TargetVA);
break;
case R_PPC_CALL:
// If this is a call to __tls_get_addr, it may be part of a TLS
// sequence that has been relaxed and turned into a nop. In this
// case, we don't want to handle it as a call.
if (read32(BufLoc) == 0x60000000) // nop
break;
// Patch a nop (0x60000000) to a ld.
if (Rel.Sym->NeedsTocRestore) {
if (BufLoc + 8 > BufEnd || read32(BufLoc + 4) != 0x60000000) {
error(getErrorLocation(BufLoc) + "call lacks nop, can't restore toc");
break;
}
write32(BufLoc + 4, 0xe8410018); // ld %r2, 24(%r1)
}
Target->relocateOne(BufLoc, Type, TargetVA);
break;
default:
Target->relocateOne(BufLoc, Type, TargetVA);
break;
}
}
}
// For each function-defining prologue, find any calls to __morestack,
// and replace them with calls to __morestack_non_split.
static void switchMorestackCallsToMorestackNonSplit(
DenseSet<Defined *> &Prologues, std::vector<Relocation *> &MorestackCalls) {
// If the target adjusted a function's prologue, all calls to
// __morestack inside that function should be switched to
// __morestack_non_split.
Symbol *MoreStackNonSplit = Symtab->find("__morestack_non_split");
if (!MoreStackNonSplit) {
error("Mixing split-stack objects requires a definition of "
"__morestack_non_split");
return;
}
// Sort both collections to compare addresses efficiently.
llvm::sort(MorestackCalls, [](const Relocation *L, const Relocation *R) {
return L->Offset < R->Offset;
});
std::vector<Defined *> Functions(Prologues.begin(), Prologues.end());
llvm::sort(Functions, [](const Defined *L, const Defined *R) {
return L->Value < R->Value;
});
auto It = MorestackCalls.begin();
for (Defined *F : Functions) {
// Find the first call to __morestack within the function.
while (It != MorestackCalls.end() && (*It)->Offset < F->Value)
++It;
// Adjust all calls inside the function.
while (It != MorestackCalls.end() && (*It)->Offset < F->Value + F->Size) {
(*It)->Sym = MoreStackNonSplit;
++It;
}
}
}
static bool enclosingPrologueAttempted(uint64_t Offset,
const DenseSet<Defined *> &Prologues) {
for (Defined *F : Prologues)
if (F->Value <= Offset && Offset < F->Value + F->Size)
return true;
return false;
}
// If a function compiled for split stack calls a function not
// compiled for split stack, then the caller needs its prologue
// adjusted to ensure that the called function will have enough stack
// available. Find those functions, and adjust their prologues.
template <class ELFT>
void InputSectionBase::adjustSplitStackFunctionPrologues(uint8_t *Buf,
uint8_t *End) {
if (!getFile<ELFT>()->SplitStack)
return;
DenseSet<Defined *> Prologues;
std::vector<Relocation *> MorestackCalls;
for (Relocation &Rel : Relocations) {
// Local symbols can't possibly be cross-calls, and should have been
// resolved long before this line.
if (Rel.Sym->isLocal())
continue;
// Ignore calls into the split-stack api.
if (Rel.Sym->getName().startswith("__morestack")) {
if (Rel.Sym->getName().equals("__morestack"))
MorestackCalls.push_back(&Rel);
continue;
}
// A relocation to non-function isn't relevant. Sometimes
// __morestack is not marked as a function, so this check comes
// after the name check.
if (Rel.Sym->Type != STT_FUNC)
continue;
// If the callee's-file was compiled with split stack, nothing to do. In
// this context, a "Defined" symbol is one "defined by the binary currently
// being produced". So an "undefined" symbol might be provided by a shared
// library. It is not possible to tell how such symbols were compiled, so be
// conservative.
if (Defined *D = dyn_cast<Defined>(Rel.Sym))
if (InputSection *IS = cast_or_null<InputSection>(D->Section))
if (!IS || !IS->getFile<ELFT>() || IS->getFile<ELFT>()->SplitStack)
continue;
if (enclosingPrologueAttempted(Rel.Offset, Prologues))
continue;
if (Defined *F = getEnclosingFunction<ELFT>(Rel.Offset)) {
Prologues.insert(F);
if (Target->adjustPrologueForCrossSplitStack(Buf + getOffset(F->Value),
End, F->StOther))
continue;
if (!getFile<ELFT>()->SomeNoSplitStack)
error(lld::toString(this) + ": " + F->getName() +
" (with -fsplit-stack) calls " + Rel.Sym->getName() +
" (without -fsplit-stack), but couldn't adjust its prologue");
}
}
if (Target->NeedsMoreStackNonSplit)
switchMorestackCallsToMorestackNonSplit(Prologues, MorestackCalls);
}
template <class ELFT> void InputSection::writeTo(uint8_t *Buf) {
if (Type == SHT_NOBITS)
return;
if (auto *S = dyn_cast<SyntheticSection>(this)) {
S->writeTo(Buf + OutSecOff);
return;
}
// If -r or --emit-relocs is given, then an InputSection
// may be a relocation section.
if (Type == SHT_RELA) {
copyRelocations<ELFT>(Buf + OutSecOff, getDataAs<typename ELFT::Rela>());
return;
}
if (Type == SHT_REL) {
copyRelocations<ELFT>(Buf + OutSecOff, getDataAs<typename ELFT::Rel>());
return;
}
// If -r is given, we may have a SHT_GROUP section.
if (Type == SHT_GROUP) {
copyShtGroup<ELFT>(Buf + OutSecOff);
return;
}
// If this is a compressed section, uncompress section contents directly
// to the buffer.
if (UncompressedSize >= 0 && !UncompressedBuf) {
size_t Size = UncompressedSize;
if (Error E = zlib::uncompress(toStringRef(RawData),
(char *)(Buf + OutSecOff), Size))
fatal(toString(this) +
": uncompress failed: " + llvm::toString(std::move(E)));
uint8_t *BufEnd = Buf + OutSecOff + Size;
relocate<ELFT>(Buf, BufEnd);
return;
}
// Copy section contents from source object file to output file
// and then apply relocations.
memcpy(Buf + OutSecOff, data().data(), data().size());
uint8_t *BufEnd = Buf + OutSecOff + data().size();
relocate<ELFT>(Buf, BufEnd);
}
void InputSection::replace(InputSection *Other) {
Alignment = std::max(Alignment, Other->Alignment);
Other->Repl = Repl;
Other->Live = false;
}
template <class ELFT>
EhInputSection::EhInputSection(ObjFile<ELFT> &F,
const typename ELFT::Shdr &Header,
StringRef Name)
: InputSectionBase(F, Header, Name, InputSectionBase::EHFrame) {}
SyntheticSection *EhInputSection::getParent() const {
return cast_or_null<SyntheticSection>(Parent);
}
// Returns the index of the first relocation that points to a region between
// Begin and Begin+Size.
template <class IntTy, class RelTy>
static unsigned getReloc(IntTy Begin, IntTy Size, const ArrayRef<RelTy> &Rels,
unsigned &RelocI) {
// Start search from RelocI for fast access. That works because the
// relocations are sorted in .eh_frame.
for (unsigned N = Rels.size(); RelocI < N; ++RelocI) {
const RelTy &Rel = Rels[RelocI];
if (Rel.r_offset < Begin)
continue;
if (Rel.r_offset < Begin + Size)
return RelocI;
return -1;
}
return -1;
}
// .eh_frame is a sequence of CIE or FDE records.
// This function splits an input section into records and returns them.
template <class ELFT> void EhInputSection::split() {
if (AreRelocsRela)
split<ELFT>(relas<ELFT>());
else
split<ELFT>(rels<ELFT>());
}
template <class ELFT, class RelTy>
void EhInputSection::split(ArrayRef<RelTy> Rels) {
unsigned RelI = 0;
for (size_t Off = 0, End = data().size(); Off != End;) {
size_t Size = readEhRecordSize(this, Off);
Pieces.emplace_back(Off, this, Size, getReloc(Off, Size, Rels, RelI));
// The empty record is the end marker.
if (Size == 4)
break;
Off += Size;
}
}
static size_t findNull(StringRef S, size_t EntSize) {
// Optimize the common case.
if (EntSize == 1)
return S.find(0);
for (unsigned I = 0, N = S.size(); I != N; I += EntSize) {
const char *B = S.begin() + I;
if (std::all_of(B, B + EntSize, [](char C) { return C == 0; }))
return I;
}
return StringRef::npos;
}
SyntheticSection *MergeInputSection::getParent() const {
return cast_or_null<SyntheticSection>(Parent);
}
// Split SHF_STRINGS section. Such section is a sequence of
// null-terminated strings.
void MergeInputSection::splitStrings(ArrayRef<uint8_t> Data, size_t EntSize) {
size_t Off = 0;
bool IsAlloc = Flags & SHF_ALLOC;
StringRef S = toStringRef(Data);
while (!S.empty()) {
size_t End = findNull(S, EntSize);
if (End == StringRef::npos)
fatal(toString(this) + ": string is not null terminated");
size_t Size = End + EntSize;
Pieces.emplace_back(Off, xxHash64(S.substr(0, Size)), !IsAlloc);
S = S.substr(Size);
Off += Size;
}
}
// Split non-SHF_STRINGS section. Such section is a sequence of
// fixed size records.
void MergeInputSection::splitNonStrings(ArrayRef<uint8_t> Data,
size_t EntSize) {
size_t Size = Data.size();
assert((Size % EntSize) == 0);
bool IsAlloc = Flags & SHF_ALLOC;
for (size_t I = 0; I != Size; I += EntSize)
Pieces.emplace_back(I, xxHash64(Data.slice(I, EntSize)), !IsAlloc);
}
template <class ELFT>
MergeInputSection::MergeInputSection(ObjFile<ELFT> &F,
const typename ELFT::Shdr &Header,
StringRef Name)
: InputSectionBase(F, Header, Name, InputSectionBase::Merge) {}
MergeInputSection::MergeInputSection(uint64_t Flags, uint32_t Type,
uint64_t Entsize, ArrayRef<uint8_t> Data,
StringRef Name)
: InputSectionBase(nullptr, Flags, Type, Entsize, /*Link*/ 0, /*Info*/ 0,
/*Alignment*/ Entsize, Data, Name, SectionBase::Merge) {}
// This function is called after we obtain a complete list of input sections
// that need to be linked. This is responsible to split section contents
// into small chunks for further processing.
//
// Note that this function is called from parallelForEach. This must be
// thread-safe (i.e. no memory allocation from the pools).
void MergeInputSection::splitIntoPieces() {
assert(Pieces.empty());
if (Flags & SHF_STRINGS)
splitStrings(data(), Entsize);
else
splitNonStrings(data(), Entsize);
}
SectionPiece *MergeInputSection::getSectionPiece(uint64_t Offset) {
if (this->data().size() <= Offset)
fatal(toString(this) + ": offset is outside the section");
// If Offset is not at beginning of a section piece, it is not in the map.
// In that case we need to do a binary search of the original section piece vector.
auto It2 =
llvm::upper_bound(Pieces, Offset, [](uint64_t Offset, SectionPiece P) {
return Offset < P.InputOff;
});
return &It2[-1];
}
// Returns the offset in an output section for a given input offset.
// Because contents of a mergeable section is not contiguous in output,
// it is not just an addition to a base output offset.
uint64_t MergeInputSection::getParentOffset(uint64_t Offset) const {
// If Offset is not at beginning of a section piece, it is not in the map.
// In that case we need to search from the original section piece vector.
const SectionPiece &Piece =
*(const_cast<MergeInputSection *>(this)->getSectionPiece (Offset));
uint64_t Addend = Offset - Piece.InputOff;
return Piece.OutputOff + Addend;
}
template InputSection::InputSection(ObjFile<ELF32LE> &, const ELF32LE::Shdr &,
StringRef);
template InputSection::InputSection(ObjFile<ELF32BE> &, const ELF32BE::Shdr &,
StringRef);
template InputSection::InputSection(ObjFile<ELF64LE> &, const ELF64LE::Shdr &,
StringRef);
template InputSection::InputSection(ObjFile<ELF64BE> &, const ELF64BE::Shdr &,
StringRef);
template std::string InputSectionBase::getLocation<ELF32LE>(uint64_t);
template std::string InputSectionBase::getLocation<ELF32BE>(uint64_t);
template std::string InputSectionBase::getLocation<ELF64LE>(uint64_t);
template std::string InputSectionBase::getLocation<ELF64BE>(uint64_t);
template void InputSection::writeTo<ELF32LE>(uint8_t *);
template void InputSection::writeTo<ELF32BE>(uint8_t *);
template void InputSection::writeTo<ELF64LE>(uint8_t *);
template void InputSection::writeTo<ELF64BE>(uint8_t *);
template MergeInputSection::MergeInputSection(ObjFile<ELF32LE> &,
const ELF32LE::Shdr &, StringRef);
template MergeInputSection::MergeInputSection(ObjFile<ELF32BE> &,
const ELF32BE::Shdr &, StringRef);
template MergeInputSection::MergeInputSection(ObjFile<ELF64LE> &,
const ELF64LE::Shdr &, StringRef);
template MergeInputSection::MergeInputSection(ObjFile<ELF64BE> &,
const ELF64BE::Shdr &, StringRef);
template EhInputSection::EhInputSection(ObjFile<ELF32LE> &,
const ELF32LE::Shdr &, StringRef);
template EhInputSection::EhInputSection(ObjFile<ELF32BE> &,
const ELF32BE::Shdr &, StringRef);
template EhInputSection::EhInputSection(ObjFile<ELF64LE> &,
const ELF64LE::Shdr &, StringRef);
template EhInputSection::EhInputSection(ObjFile<ELF64BE> &,
const ELF64BE::Shdr &, StringRef);
template void EhInputSection::split<ELF32LE>();
template void EhInputSection::split<ELF32BE>();
template void EhInputSection::split<ELF64LE>();
template void EhInputSection::split<ELF64BE>();
Index: head/contrib/llvm/tools/lld/ELF/Relocations.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Relocations.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Relocations.cpp (revision 350467)
@@ -1,1520 +1,1634 @@
//===- Relocations.cpp ----------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains platform-independent functions to process relocations.
// I'll describe the overview of this file here.
//
// Simple relocations are easy to handle for the linker. For example,
// for R_X86_64_PC64 relocs, the linker just has to fix up locations
// with the relative offsets to the target symbols. It would just be
// reading records from relocation sections and applying them to output.
//
// But not all relocations are that easy to handle. For example, for
// R_386_GOTOFF relocs, the linker has to create new GOT entries for
// symbols if they don't exist, and fix up locations with GOT entry
// offsets from the beginning of GOT section. So there is more than
// fixing addresses in relocation processing.
//
// ELF defines a large number of complex relocations.
//
// The functions in this file analyze relocations and do whatever needs
// to be done. It includes, but not limited to, the following.
//
// - create GOT/PLT entries
// - create new relocations in .dynsym to let the dynamic linker resolve
// them at runtime (since ELF supports dynamic linking, not all
// relocations can be resolved at link-time)
// - create COPY relocs and reserve space in .bss
// - replace expensive relocs (in terms of runtime cost) with cheap ones
// - error out infeasible combinations such as PIC and non-relative relocs
//
// Note that the functions in this file don't actually apply relocations
// because it doesn't know about the output file nor the output file buffer.
// It instead stores Relocation objects to InputSection's Relocations
// vector to let it apply later in InputSection::writeTo.
//
//===----------------------------------------------------------------------===//
#include "Relocations.h"
#include "Config.h"
#include "LinkerScript.h"
#include "OutputSections.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "Thunks.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::support::endian;
using namespace lld;
using namespace lld::elf;
static Optional<std::string> getLinkerScriptLocation(const Symbol &Sym) {
for (BaseCommand *Base : Script->SectionCommands)
if (auto *Cmd = dyn_cast<SymbolAssignment>(Base))
if (Cmd->Sym == &Sym)
return Cmd->Location;
return None;
}
// Construct a message in the following format.
//
// >>> defined in /home/alice/src/foo.o
// >>> referenced by bar.c:12 (/home/alice/src/bar.c:12)
// >>> /home/alice/src/bar.o:(.text+0x1)
static std::string getLocation(InputSectionBase &S, const Symbol &Sym,
uint64_t Off) {
std::string Msg = "\n>>> defined in ";
if (Sym.File)
Msg += toString(Sym.File);
else if (Optional<std::string> Loc = getLinkerScriptLocation(Sym))
Msg += *Loc;
Msg += "\n>>> referenced by ";
std::string Src = S.getSrcMsg(Sym, Off);
if (!Src.empty())
Msg += Src + "\n>>> ";
return Msg + S.getObjMsg(Off);
}
// This function is similar to the `handleTlsRelocation`. MIPS does not
// support any relaxations for TLS relocations so by factoring out MIPS
// handling in to the separate function we can simplify the code and do not
// pollute other `handleTlsRelocation` by MIPS `ifs` statements.
// Mips has a custom MipsGotSection that handles the writing of GOT entries
// without dynamic relocations.
static unsigned handleMipsTlsRelocation(RelType Type, Symbol &Sym,
InputSectionBase &C, uint64_t Offset,
int64_t Addend, RelExpr Expr) {
if (Expr == R_MIPS_TLSLD) {
In.MipsGot->addTlsIndex(*C.File);
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
if (Expr == R_MIPS_TLSGD) {
In.MipsGot->addDynTlsEntry(*C.File, Sym);
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
return 0;
}
// This function is similar to the `handleMipsTlsRelocation`. ARM also does not
// support any relaxations for TLS relocations. ARM is logically similar to Mips
// in how it handles TLS, but Mips uses its own custom GOT which handles some
// of the cases that ARM uses GOT relocations for.
//
// We look for TLS global dynamic and local dynamic relocations, these may
// require the generation of a pair of GOT entries that have associated
// dynamic relocations. When the results of the dynamic relocations can be
// resolved at static link time we do so. This is necessary for static linking
// as there will be no dynamic loader to resolve them at load-time.
//
// The pair of GOT entries created are of the form
// GOT[e0] Module Index (Used to find pointer to TLS block at run-time)
// GOT[e1] Offset of symbol in TLS block
template <class ELFT>
static unsigned handleARMTlsRelocation(RelType Type, Symbol &Sym,
InputSectionBase &C, uint64_t Offset,
int64_t Addend, RelExpr Expr) {
// The Dynamic TLS Module Index Relocation for a symbol defined in an
// executable is always 1. If the target Symbol is not preemptible then
// we know the offset into the TLS block at static link time.
bool NeedDynId = Sym.IsPreemptible || Config->Shared;
bool NeedDynOff = Sym.IsPreemptible;
auto AddTlsReloc = [&](uint64_t Off, RelType Type, Symbol *Dest, bool Dyn) {
if (Dyn)
In.RelaDyn->addReloc(Type, In.Got, Off, Dest);
else
In.Got->Relocations.push_back({R_ABS, Type, Off, 0, Dest});
};
// Local Dynamic is for access to module local TLS variables, while still
// being suitable for being dynamically loaded via dlopen.
// GOT[e0] is the module index, with a special value of 0 for the current
// module. GOT[e1] is unused. There only needs to be one module index entry.
if (Expr == R_TLSLD_PC && In.Got->addTlsIndex()) {
AddTlsReloc(In.Got->getTlsIndexOff(), Target->TlsModuleIndexRel,
NeedDynId ? nullptr : &Sym, NeedDynId);
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
// Global Dynamic is the most general purpose access model. When we know
// the module index and offset of symbol in TLS block we can fill these in
// using static GOT relocations.
if (Expr == R_TLSGD_PC) {
if (In.Got->addDynTlsEntry(Sym)) {
uint64_t Off = In.Got->getGlobalDynOffset(Sym);
AddTlsReloc(Off, Target->TlsModuleIndexRel, &Sym, NeedDynId);
AddTlsReloc(Off + Config->Wordsize, Target->TlsOffsetRel, &Sym,
NeedDynOff);
}
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
return 0;
}
// Returns the number of relocations processed.
template <class ELFT>
static unsigned
handleTlsRelocation(RelType Type, Symbol &Sym, InputSectionBase &C,
typename ELFT::uint Offset, int64_t Addend, RelExpr Expr) {
if (!Sym.isTls())
return 0;
if (Config->EMachine == EM_ARM)
return handleARMTlsRelocation<ELFT>(Type, Sym, C, Offset, Addend, Expr);
if (Config->EMachine == EM_MIPS)
return handleMipsTlsRelocation(Type, Sym, C, Offset, Addend, Expr);
if (isRelExprOneOf<R_TLSDESC, R_AARCH64_TLSDESC_PAGE, R_TLSDESC_CALL>(Expr) &&
Config->Shared) {
if (In.Got->addDynTlsEntry(Sym)) {
uint64_t Off = In.Got->getGlobalDynOffset(Sym);
In.RelaDyn->addReloc(
{Target->TlsDescRel, In.Got, Off, !Sym.IsPreemptible, &Sym, 0});
}
if (Expr != R_TLSDESC_CALL)
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
if (isRelExprOneOf<R_TLSLD_GOT, R_TLSLD_GOT_FROM_END, R_TLSLD_PC,
R_TLSLD_HINT>(Expr)) {
// Local-Dynamic relocs can be relaxed to Local-Exec.
if (!Config->Shared) {
C.Relocations.push_back(
{Target->adjustRelaxExpr(Type, nullptr, R_RELAX_TLS_LD_TO_LE), Type,
Offset, Addend, &Sym});
return Target->TlsGdRelaxSkip;
}
if (Expr == R_TLSLD_HINT)
return 1;
if (In.Got->addTlsIndex())
In.RelaDyn->addReloc(Target->TlsModuleIndexRel, In.Got,
In.Got->getTlsIndexOff(), nullptr);
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
// Local-Dynamic relocs can be relaxed to Local-Exec.
if (Expr == R_ABS && !Config->Shared) {
C.Relocations.push_back(
{Target->adjustRelaxExpr(Type, nullptr, R_RELAX_TLS_LD_TO_LE), Type,
Offset, Addend, &Sym});
return 1;
}
// Local-Dynamic sequence where offset of tls variable relative to dynamic
// thread pointer is stored in the got.
if (Expr == R_TLSLD_GOT_OFF) {
// Local-Dynamic relocs can be relaxed to local-exec
if (!Config->Shared) {
C.Relocations.push_back({R_RELAX_TLS_LD_TO_LE, Type, Offset, Addend, &Sym});
return 1;
}
if (!Sym.isInGot()) {
In.Got->addEntry(Sym);
uint64_t Off = Sym.getGotOffset();
In.Got->Relocations.push_back(
{R_ABS, Target->TlsOffsetRel, Off, 0, &Sym});
}
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
if (isRelExprOneOf<R_TLSDESC, R_AARCH64_TLSDESC_PAGE, R_TLSDESC_CALL,
R_TLSGD_GOT, R_TLSGD_GOT_FROM_END, R_TLSGD_PC>(Expr)) {
if (Config->Shared) {
if (In.Got->addDynTlsEntry(Sym)) {
uint64_t Off = In.Got->getGlobalDynOffset(Sym);
In.RelaDyn->addReloc(Target->TlsModuleIndexRel, In.Got, Off, &Sym);
// If the symbol is preemptible we need the dynamic linker to write
// the offset too.
uint64_t OffsetOff = Off + Config->Wordsize;
if (Sym.IsPreemptible)
In.RelaDyn->addReloc(Target->TlsOffsetRel, In.Got, OffsetOff, &Sym);
else
In.Got->Relocations.push_back(
{R_ABS, Target->TlsOffsetRel, OffsetOff, 0, &Sym});
}
C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return 1;
}
// Global-Dynamic relocs can be relaxed to Initial-Exec or Local-Exec
// depending on the symbol being locally defined or not.
if (Sym.IsPreemptible) {
C.Relocations.push_back(
{Target->adjustRelaxExpr(Type, nullptr, R_RELAX_TLS_GD_TO_IE), Type,
Offset, Addend, &Sym});
if (!Sym.isInGot()) {
In.Got->addEntry(Sym);
In.RelaDyn->addReloc(Target->TlsGotRel, In.Got, Sym.getGotOffset(),
&Sym);
}
} else {
C.Relocations.push_back(
{Target->adjustRelaxExpr(Type, nullptr, R_RELAX_TLS_GD_TO_LE), Type,
Offset, Addend, &Sym});
}
return Target->TlsGdRelaxSkip;
}
// Initial-Exec relocs can be relaxed to Local-Exec if the symbol is locally
// defined.
if (isRelExprOneOf<R_GOT, R_GOT_FROM_END, R_GOT_PC, R_AARCH64_GOT_PAGE_PC,
R_GOT_OFF, R_TLSIE_HINT>(Expr) &&
!Config->Shared && !Sym.IsPreemptible) {
C.Relocations.push_back({R_RELAX_TLS_IE_TO_LE, Type, Offset, Addend, &Sym});
return 1;
}
if (Expr == R_TLSIE_HINT)
return 1;
return 0;
}
static RelType getMipsPairType(RelType Type, bool IsLocal) {
switch (Type) {
case R_MIPS_HI16:
return R_MIPS_LO16;
case R_MIPS_GOT16:
// In case of global symbol, the R_MIPS_GOT16 relocation does not
// have a pair. Each global symbol has a unique entry in the GOT
// and a corresponding instruction with help of the R_MIPS_GOT16
// relocation loads an address of the symbol. In case of local
// symbol, the R_MIPS_GOT16 relocation creates a GOT entry to hold
// the high 16 bits of the symbol's value. A paired R_MIPS_LO16
// relocations handle low 16 bits of the address. That allows
// to allocate only one GOT entry for every 64 KBytes of local data.
return IsLocal ? R_MIPS_LO16 : R_MIPS_NONE;
case R_MICROMIPS_GOT16:
return IsLocal ? R_MICROMIPS_LO16 : R_MIPS_NONE;
case R_MIPS_PCHI16:
return R_MIPS_PCLO16;
case R_MICROMIPS_HI16:
return R_MICROMIPS_LO16;
default:
return R_MIPS_NONE;
}
}
// True if non-preemptable symbol always has the same value regardless of where
// the DSO is loaded.
static bool isAbsolute(const Symbol &Sym) {
if (Sym.isUndefWeak())
return true;
if (const auto *DR = dyn_cast<Defined>(&Sym))
return DR->Section == nullptr; // Absolute symbol.
return false;
}
static bool isAbsoluteValue(const Symbol &Sym) {
return isAbsolute(Sym) || Sym.isTls();
}
// Returns true if Expr refers a PLT entry.
static bool needsPlt(RelExpr Expr) {
- return isRelExprOneOf<R_PLT_PC, R_PPC_CALL_PLT, R_PLT, R_AARCH64_PLT_PAGE_PC,
- R_GOT_PLT, R_AARCH64_GOT_PAGE_PC_PLT>(Expr);
+ return isRelExprOneOf<R_PLT_PC, R_PPC_CALL_PLT, R_PLT>(Expr);
}
// Returns true if Expr refers a GOT entry. Note that this function
// returns false for TLS variables even though they need GOT, because
// TLS variables uses GOT differently than the regular variables.
static bool needsGot(RelExpr Expr) {
return isRelExprOneOf<R_GOT, R_GOT_OFF, R_HEXAGON_GOT, R_MIPS_GOT_LOCAL_PAGE,
R_MIPS_GOT_OFF, R_MIPS_GOT_OFF32, R_AARCH64_GOT_PAGE_PC,
- R_AARCH64_GOT_PAGE_PC_PLT, R_GOT_PC, R_GOT_FROM_END,
- R_GOT_PLT>(Expr);
+ R_GOT_PC, R_GOT_FROM_END>(Expr);
}
// True if this expression is of the form Sym - X, where X is a position in the
// file (PC, or GOT for example).
static bool isRelExpr(RelExpr Expr) {
return isRelExprOneOf<R_PC, R_GOTREL, R_GOTREL_FROM_END, R_MIPS_GOTREL,
R_PPC_CALL, R_PPC_CALL_PLT, R_AARCH64_PAGE_PC,
- R_AARCH64_PLT_PAGE_PC, R_RELAX_GOT_PC>(Expr);
+ R_RELAX_GOT_PC>(Expr);
}
// Returns true if a given relocation can be computed at link-time.
//
// For instance, we know the offset from a relocation to its target at
// link-time if the relocation is PC-relative and refers a
// non-interposable function in the same executable. This function
// will return true for such relocation.
//
// If this function returns false, that means we need to emit a
// dynamic relocation so that the relocation will be fixed at load-time.
static bool isStaticLinkTimeConstant(RelExpr E, RelType Type, const Symbol &Sym,
InputSectionBase &S, uint64_t RelOff) {
// These expressions always compute a constant
if (isRelExprOneOf<R_GOT_FROM_END, R_GOT_OFF, R_HEXAGON_GOT, R_TLSLD_GOT_OFF,
R_MIPS_GOT_LOCAL_PAGE, R_MIPS_GOTREL, R_MIPS_GOT_OFF,
R_MIPS_GOT_OFF32, R_MIPS_GOT_GP_PC, R_MIPS_TLSGD,
- R_AARCH64_GOT_PAGE_PC, R_AARCH64_GOT_PAGE_PC_PLT, R_GOT_PC,
- R_GOTONLY_PC, R_GOTONLY_PC_FROM_END, R_PLT_PC, R_TLSGD_GOT,
+ R_AARCH64_GOT_PAGE_PC, R_GOT_PC, R_GOTONLY_PC,
+ R_GOTONLY_PC_FROM_END, R_PLT_PC, R_TLSGD_GOT,
R_TLSGD_GOT_FROM_END, R_TLSGD_PC, R_PPC_CALL_PLT,
R_TLSDESC_CALL, R_AARCH64_TLSDESC_PAGE, R_HINT,
R_TLSLD_HINT, R_TLSIE_HINT>(E))
return true;
- // The computation involves output from the ifunc resolver.
- if (Sym.isGnuIFunc() && Config->ZIfuncnoplt)
- return false;
-
// These never do, except if the entire file is position dependent or if
// only the low bits are used.
- if (E == R_GOT || E == R_GOT_PLT || E == R_PLT || E == R_TLSDESC)
+ if (E == R_GOT || E == R_PLT || E == R_TLSDESC)
return Target->usesOnlyLowPageBits(Type) || !Config->Pic;
if (Sym.IsPreemptible)
return false;
if (!Config->Pic)
return true;
// The size of a non preemptible symbol is a constant.
if (E == R_SIZE)
return true;
// For the target and the relocation, we want to know if they are
// absolute or relative.
bool AbsVal = isAbsoluteValue(Sym);
bool RelE = isRelExpr(E);
if (AbsVal && !RelE)
return true;
if (!AbsVal && RelE)
return true;
if (!AbsVal && !RelE)
return Target->usesOnlyLowPageBits(Type);
// Relative relocation to an absolute value. This is normally unrepresentable,
// but if the relocation refers to a weak undefined symbol, we allow it to
// resolve to the image base. This is a little strange, but it allows us to
// link function calls to such symbols. Normally such a call will be guarded
// with a comparison, which will load a zero from the GOT.
// Another special case is MIPS _gp_disp symbol which represents offset
// between start of a function and '_gp' value and defined as absolute just
// to simplify the code.
assert(AbsVal && RelE);
if (Sym.isUndefWeak())
return true;
error("relocation " + toString(Type) + " cannot refer to absolute symbol: " +
toString(Sym) + getLocation(S, Sym, RelOff));
return true;
}
static RelExpr toPlt(RelExpr Expr) {
switch (Expr) {
case R_PPC_CALL:
return R_PPC_CALL_PLT;
case R_PC:
return R_PLT_PC;
- case R_AARCH64_PAGE_PC:
- return R_AARCH64_PLT_PAGE_PC;
- case R_AARCH64_GOT_PAGE_PC:
- return R_AARCH64_GOT_PAGE_PC_PLT;
case R_ABS:
return R_PLT;
- case R_GOT:
- return R_GOT_PLT;
default:
return Expr;
}
}
static RelExpr fromPlt(RelExpr Expr) {
// We decided not to use a plt. Optimize a reference to the plt to a
// reference to the symbol itself.
switch (Expr) {
case R_PLT_PC:
return R_PC;
case R_PPC_CALL_PLT:
return R_PPC_CALL;
case R_PLT:
return R_ABS;
default:
return Expr;
}
}
// Returns true if a given shared symbol is in a read-only segment in a DSO.
template <class ELFT> static bool isReadOnly(SharedSymbol &SS) {
typedef typename ELFT::Phdr Elf_Phdr;
// Determine if the symbol is read-only by scanning the DSO's program headers.
const SharedFile<ELFT> &File = SS.getFile<ELFT>();
for (const Elf_Phdr &Phdr : check(File.getObj().program_headers()))
if ((Phdr.p_type == ELF::PT_LOAD || Phdr.p_type == ELF::PT_GNU_RELRO) &&
!(Phdr.p_flags & ELF::PF_W) && SS.Value >= Phdr.p_vaddr &&
SS.Value < Phdr.p_vaddr + Phdr.p_memsz)
return true;
return false;
}
// Returns symbols at the same offset as a given symbol, including SS itself.
//
// If two or more symbols are at the same offset, and at least one of
// them are copied by a copy relocation, all of them need to be copied.
// Otherwise, they would refer to different places at runtime.
template <class ELFT>
static SmallSet<SharedSymbol *, 4> getSymbolsAt(SharedSymbol &SS) {
typedef typename ELFT::Sym Elf_Sym;
SharedFile<ELFT> &File = SS.getFile<ELFT>();
SmallSet<SharedSymbol *, 4> Ret;
for (const Elf_Sym &S : File.getGlobalELFSyms()) {
if (S.st_shndx == SHN_UNDEF || S.st_shndx == SHN_ABS ||
S.getType() == STT_TLS || S.st_value != SS.Value)
continue;
StringRef Name = check(S.getName(File.getStringTable()));
Symbol *Sym = Symtab->find(Name);
if (auto *Alias = dyn_cast_or_null<SharedSymbol>(Sym))
Ret.insert(Alias);
}
return Ret;
}
// When a symbol is copy relocated or we create a canonical plt entry, it is
// effectively a defined symbol. In the case of copy relocation the symbol is
// in .bss and in the case of a canonical plt entry it is in .plt. This function
// replaces the existing symbol with a Defined pointing to the appropriate
// location.
static void replaceWithDefined(Symbol &Sym, SectionBase *Sec, uint64_t Value,
uint64_t Size) {
Symbol Old = Sym;
replaceSymbol<Defined>(&Sym, Sym.File, Sym.getName(), Sym.Binding,
Sym.StOther, Sym.Type, Value, Size, Sec);
Sym.PltIndex = Old.PltIndex;
Sym.GotIndex = Old.GotIndex;
Sym.VerdefIndex = Old.VerdefIndex;
Sym.PPC64BranchltIndex = Old.PPC64BranchltIndex;
Sym.IsPreemptible = true;
Sym.ExportDynamic = true;
Sym.IsUsedInRegularObj = true;
Sym.Used = true;
}
// Reserve space in .bss or .bss.rel.ro for copy relocation.
//
// The copy relocation is pretty much a hack. If you use a copy relocation
// in your program, not only the symbol name but the symbol's size, RW/RO
// bit and alignment become part of the ABI. In addition to that, if the
// symbol has aliases, the aliases become part of the ABI. That's subtle,
// but if you violate that implicit ABI, that can cause very counter-
// intuitive consequences.
//
// So, what is the copy relocation? It's for linking non-position
// independent code to DSOs. In an ideal world, all references to data
// exported by DSOs should go indirectly through GOT. But if object files
// are compiled as non-PIC, all data references are direct. There is no
// way for the linker to transform the code to use GOT, as machine
// instructions are already set in stone in object files. This is where
// the copy relocation takes a role.
//
// A copy relocation instructs the dynamic linker to copy data from a DSO
// to a specified address (which is usually in .bss) at load-time. If the
// static linker (that's us) finds a direct data reference to a DSO
// symbol, it creates a copy relocation, so that the symbol can be
// resolved as if it were in .bss rather than in a DSO.
//
// As you can see in this function, we create a copy relocation for the
// dynamic linker, and the relocation contains not only symbol name but
// various other informtion about the symbol. So, such attributes become a
// part of the ABI.
//
// Note for application developers: I can give you a piece of advice if
// you are writing a shared library. You probably should export only
// functions from your library. You shouldn't export variables.
//
// As an example what can happen when you export variables without knowing
// the semantics of copy relocations, assume that you have an exported
// variable of type T. It is an ABI-breaking change to add new members at
// end of T even though doing that doesn't change the layout of the
// existing members. That's because the space for the new members are not
// reserved in .bss unless you recompile the main program. That means they
// are likely to overlap with other data that happens to be laid out next
// to the variable in .bss. This kind of issue is sometimes very hard to
// debug. What's a solution? Instead of exporting a varaible V from a DSO,
// define an accessor getV().
template <class ELFT> static void addCopyRelSymbol(SharedSymbol &SS) {
// Copy relocation against zero-sized symbol doesn't make sense.
uint64_t SymSize = SS.getSize();
if (SymSize == 0 || SS.Alignment == 0)
fatal("cannot create a copy relocation for symbol " + toString(SS));
// See if this symbol is in a read-only segment. If so, preserve the symbol's
// memory protection by reserving space in the .bss.rel.ro section.
bool IsReadOnly = isReadOnly<ELFT>(SS);
BssSection *Sec = make<BssSection>(IsReadOnly ? ".bss.rel.ro" : ".bss",
SymSize, SS.Alignment);
if (IsReadOnly)
In.BssRelRo->getParent()->addSection(Sec);
else
In.Bss->getParent()->addSection(Sec);
// Look through the DSO's dynamic symbol table for aliases and create a
// dynamic symbol for each one. This causes the copy relocation to correctly
// interpose any aliases.
for (SharedSymbol *Sym : getSymbolsAt<ELFT>(SS))
replaceWithDefined(*Sym, Sec, 0, Sym->Size);
In.RelaDyn->addReloc(Target->CopyRel, Sec, 0, &SS);
}
// MIPS has an odd notion of "paired" relocations to calculate addends.
// For example, if a relocation is of R_MIPS_HI16, there must be a
// R_MIPS_LO16 relocation after that, and an addend is calculated using
// the two relocations.
template <class ELFT, class RelTy>
static int64_t computeMipsAddend(const RelTy &Rel, const RelTy *End,
InputSectionBase &Sec, RelExpr Expr,
bool IsLocal) {
if (Expr == R_MIPS_GOTREL && IsLocal)
return Sec.getFile<ELFT>()->MipsGp0;
// The ABI says that the paired relocation is used only for REL.
// See p. 4-17 at ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
if (RelTy::IsRela)
return 0;
RelType Type = Rel.getType(Config->IsMips64EL);
uint32_t PairTy = getMipsPairType(Type, IsLocal);
if (PairTy == R_MIPS_NONE)
return 0;
const uint8_t *Buf = Sec.data().data();
uint32_t SymIndex = Rel.getSymbol(Config->IsMips64EL);
// To make things worse, paired relocations might not be contiguous in
// the relocation table, so we need to do linear search. *sigh*
for (const RelTy *RI = &Rel; RI != End; ++RI)
if (RI->getType(Config->IsMips64EL) == PairTy &&
RI->getSymbol(Config->IsMips64EL) == SymIndex)
return Target->getImplicitAddend(Buf + RI->r_offset, PairTy);
warn("can't find matching " + toString(PairTy) + " relocation for " +
toString(Type));
return 0;
}
// Returns an addend of a given relocation. If it is RELA, an addend
// is in a relocation itself. If it is REL, we need to read it from an
// input section.
template <class ELFT, class RelTy>
static int64_t computeAddend(const RelTy &Rel, const RelTy *End,
InputSectionBase &Sec, RelExpr Expr,
bool IsLocal) {
int64_t Addend;
RelType Type = Rel.getType(Config->IsMips64EL);
if (RelTy::IsRela) {
Addend = getAddend<ELFT>(Rel);
} else {
const uint8_t *Buf = Sec.data().data();
Addend = Target->getImplicitAddend(Buf + Rel.r_offset, Type);
}
if (Config->EMachine == EM_PPC64 && Config->Pic && Type == R_PPC64_TOC)
Addend += getPPC64TocBase();
if (Config->EMachine == EM_MIPS)
Addend += computeMipsAddend<ELFT>(Rel, End, Sec, Expr, IsLocal);
return Addend;
}
// Report an undefined symbol if necessary.
// Returns true if this function printed out an error message.
static bool maybeReportUndefined(Symbol &Sym, InputSectionBase &Sec,
uint64_t Offset) {
if (Sym.isLocal() || !Sym.isUndefined() || Sym.isWeak())
return false;
bool CanBeExternal =
Sym.computeBinding() != STB_LOCAL && Sym.Visibility == STV_DEFAULT;
if (Config->UnresolvedSymbols == UnresolvedPolicy::Ignore && CanBeExternal)
return false;
std::string Msg =
"undefined symbol: " + toString(Sym) + "\n>>> referenced by ";
std::string Src = Sec.getSrcMsg(Sym, Offset);
if (!Src.empty())
Msg += Src + "\n>>> ";
Msg += Sec.getObjMsg(Offset);
if (Sym.getName().startswith("_ZTV"))
Msg += "\nthe vtable symbol may be undefined because the class is missing "
"its key function (see https://lld.llvm.org/missingkeyfunction)";
if ((Config->UnresolvedSymbols == UnresolvedPolicy::Warn && CanBeExternal) ||
Config->NoinhibitExec) {
warn(Msg);
return false;
}
error(Msg);
return true;
}
// MIPS N32 ABI treats series of successive relocations with the same offset
// as a single relocation. The similar approach used by N64 ABI, but this ABI
// packs all relocations into the single relocation record. Here we emulate
// this for the N32 ABI. Iterate over relocation with the same offset and put
// theirs types into the single bit-set.
template <class RelTy> static RelType getMipsN32RelType(RelTy *&Rel, RelTy *End) {
RelType Type = 0;
uint64_t Offset = Rel->r_offset;
int N = 0;
while (Rel != End && Rel->r_offset == Offset)
Type |= (Rel++)->getType(Config->IsMips64EL) << (8 * N++);
return Type;
}
// .eh_frame sections are mergeable input sections, so their input
// offsets are not linearly mapped to output section. For each input
// offset, we need to find a section piece containing the offset and
// add the piece's base address to the input offset to compute the
// output offset. That isn't cheap.
//
// This class is to speed up the offset computation. When we process
// relocations, we access offsets in the monotonically increasing
// order. So we can optimize for that access pattern.
//
// For sections other than .eh_frame, this class doesn't do anything.
namespace {
class OffsetGetter {
public:
explicit OffsetGetter(InputSectionBase &Sec) {
if (auto *Eh = dyn_cast<EhInputSection>(&Sec))
Pieces = Eh->Pieces;
}
// Translates offsets in input sections to offsets in output sections.
// Given offset must increase monotonically. We assume that Piece is
// sorted by InputOff.
uint64_t get(uint64_t Off) {
if (Pieces.empty())
return Off;
while (I != Pieces.size() && Pieces[I].InputOff + Pieces[I].Size <= Off)
++I;
if (I == Pieces.size())
fatal(".eh_frame: relocation is not in any piece");
// Pieces must be contiguous, so there must be no holes in between.
assert(Pieces[I].InputOff <= Off && "Relocation not in any piece");
// Offset -1 means that the piece is dead (i.e. garbage collected).
if (Pieces[I].OutputOff == -1)
return -1;
return Pieces[I].OutputOff + Off - Pieces[I].InputOff;
}
private:
ArrayRef<EhSectionPiece> Pieces;
size_t I = 0;
};
} // namespace
static void addRelativeReloc(InputSectionBase *IS, uint64_t OffsetInSec,
Symbol *Sym, int64_t Addend, RelExpr Expr,
RelType Type) {
// Add a relative relocation. If RelrDyn section is enabled, and the
// relocation offset is guaranteed to be even, add the relocation to
// the RelrDyn section, otherwise add it to the RelaDyn section.
// RelrDyn sections don't support odd offsets. Also, RelrDyn sections
// don't store the addend values, so we must write it to the relocated
// address.
if (In.RelrDyn && IS->Alignment >= 2 && OffsetInSec % 2 == 0) {
IS->Relocations.push_back({Expr, Type, OffsetInSec, Addend, Sym});
In.RelrDyn->Relocs.push_back({IS, OffsetInSec});
return;
}
In.RelaDyn->addReloc(Target->RelativeRel, IS, OffsetInSec, Sym, Addend, Expr,
Type);
}
template <class ELFT, class GotPltSection>
static void addPltEntry(PltSection *Plt, GotPltSection *GotPlt,
RelocationBaseSection *Rel, RelType Type, Symbol &Sym) {
Plt->addEntry<ELFT>(Sym);
GotPlt->addEntry(Sym);
Rel->addReloc(
{Type, GotPlt, Sym.getGotPltOffset(), !Sym.IsPreemptible, &Sym, 0});
}
template <class ELFT> static void addGotEntry(Symbol &Sym) {
In.Got->addEntry(Sym);
- RelExpr Expr;
- if (Sym.isTls())
- Expr = R_TLS;
- else if (Sym.isGnuIFunc())
- Expr = R_PLT;
- else
- Expr = R_ABS;
-
+ RelExpr Expr = Sym.isTls() ? R_TLS : R_ABS;
uint64_t Off = Sym.getGotOffset();
// If a GOT slot value can be calculated at link-time, which is now,
// we can just fill that out.
//
// (We don't actually write a value to a GOT slot right now, but we
// add a static relocation to a Relocations vector so that
// InputSection::relocate will do the work for us. We may be able
// to just write a value now, but it is a TODO.)
bool IsLinkTimeConstant =
!Sym.IsPreemptible && (!Config->Pic || isAbsolute(Sym));
if (IsLinkTimeConstant) {
In.Got->Relocations.push_back({Expr, Target->GotRel, Off, 0, &Sym});
return;
}
// Otherwise, we emit a dynamic relocation to .rel[a].dyn so that
// the GOT slot will be fixed at load-time.
if (!Sym.isTls() && !Sym.IsPreemptible && Config->Pic && !isAbsolute(Sym)) {
addRelativeReloc(In.Got, Off, &Sym, 0, R_ABS, Target->GotRel);
return;
}
In.RelaDyn->addReloc(Sym.isTls() ? Target->TlsGotRel : Target->GotRel, In.Got,
Off, &Sym, 0, Sym.IsPreemptible ? R_ADDEND : R_ABS,
Target->GotRel);
}
// Return true if we can define a symbol in the executable that
// contains the value/function of a symbol defined in a shared
// library.
static bool canDefineSymbolInExecutable(Symbol &Sym) {
// If the symbol has default visibility the symbol defined in the
// executable will preempt it.
// Note that we want the visibility of the shared symbol itself, not
// the visibility of the symbol in the output file we are producing. That is
// why we use Sym.StOther.
if ((Sym.StOther & 0x3) == STV_DEFAULT)
return true;
// If we are allowed to break address equality of functions, defining
// a plt entry will allow the program to call the function in the
// .so, but the .so and the executable will no agree on the address
// of the function. Similar logic for objects.
return ((Sym.isFunc() && Config->IgnoreFunctionAddressEquality) ||
(Sym.isObject() && Config->IgnoreDataAddressEquality));
}
// The reason we have to do this early scan is as follows
// * To mmap the output file, we need to know the size
// * For that, we need to know how many dynamic relocs we will have.
// It might be possible to avoid this by outputting the file with write:
// * Write the allocated output sections, computing addresses.
// * Apply relocations, recording which ones require a dynamic reloc.
// * Write the dynamic relocations.
// * Write the rest of the file.
// This would have some drawbacks. For example, we would only know if .rela.dyn
// is needed after applying relocations. If it is, it will go after rw and rx
// sections. Given that it is ro, we will need an extra PT_LOAD. This
// complicates things for the dynamic linker and means we would have to reserve
// space for the extra PT_LOAD even if we end up not using it.
template <class ELFT, class RelTy>
static void processRelocAux(InputSectionBase &Sec, RelExpr Expr, RelType Type,
uint64_t Offset, Symbol &Sym, const RelTy &Rel,
int64_t Addend) {
if (isStaticLinkTimeConstant(Expr, Type, Sym, Sec, Offset)) {
Sec.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return;
}
- if (Sym.isGnuIFunc() && Config->ZIfuncnoplt) {
- In.RelaDyn->addReloc(Type, &Sec, Offset, &Sym, Addend, R_ADDEND, Type);
- return;
- }
bool CanWrite = (Sec.Flags & SHF_WRITE) || !Config->ZText;
if (CanWrite) {
// R_GOT refers to a position in the got, even if the symbol is preemptible.
bool IsPreemptibleValue = Sym.IsPreemptible && Expr != R_GOT;
if (!IsPreemptibleValue) {
addRelativeReloc(&Sec, Offset, &Sym, Addend, Expr, Type);
return;
} else if (RelType Rel = Target->getDynRel(Type)) {
In.RelaDyn->addReloc(Rel, &Sec, Offset, &Sym, Addend, R_ADDEND, Type);
// MIPS ABI turns using of GOT and dynamic relocations inside out.
// While regular ABI uses dynamic relocations to fill up GOT entries
// MIPS ABI requires dynamic linker to fills up GOT entries using
// specially sorted dynamic symbol table. This affects even dynamic
// relocations against symbols which do not require GOT entries
// creation explicitly, i.e. do not have any GOT-relocations. So if
// a preemptible symbol has a dynamic relocation we anyway have
// to create a GOT entry for it.
// If a non-preemptible symbol has a dynamic relocation against it,
// dynamic linker takes it st_value, adds offset and writes down
// result of the dynamic relocation. In case of preemptible symbol
// dynamic linker performs symbol resolution, writes the symbol value
// to the GOT entry and reads the GOT entry when it needs to perform
// a dynamic relocation.
// ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf p.4-19
if (Config->EMachine == EM_MIPS)
In.MipsGot->addEntry(*Sec.File, Sym, Addend, Expr);
return;
}
}
// If the relocation is to a weak undef, and we are producing
// executable, give up on it and produce a non preemptible 0.
if (!Config->Shared && Sym.isUndefWeak()) {
Sec.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return;
}
if (!CanWrite && (Config->Pic && !isRelExpr(Expr))) {
error(
"can't create dynamic relocation " + toString(Type) + " against " +
(Sym.getName().empty() ? "local symbol" : "symbol: " + toString(Sym)) +
" in readonly segment; recompile object files with -fPIC "
"or pass '-Wl,-z,notext' to allow text relocations in the output" +
getLocation(Sec, Sym, Offset));
return;
}
// Copy relocations are only possible if we are creating an executable.
if (Config->Shared) {
errorOrWarn("relocation " + toString(Type) +
" cannot be used against symbol " + toString(Sym) +
"; recompile with -fPIC" + getLocation(Sec, Sym, Offset));
return;
}
// If the symbol is undefined we already reported any relevant errors.
if (Sym.isUndefined())
return;
if (!canDefineSymbolInExecutable(Sym)) {
error("cannot preempt symbol: " + toString(Sym) +
getLocation(Sec, Sym, Offset));
return;
}
if (Sym.isObject()) {
// Produce a copy relocation.
if (auto *SS = dyn_cast<SharedSymbol>(&Sym)) {
if (!Config->ZCopyreloc)
error("unresolvable relocation " + toString(Type) +
" against symbol '" + toString(*SS) +
"'; recompile with -fPIC or remove '-z nocopyreloc'" +
getLocation(Sec, Sym, Offset));
addCopyRelSymbol<ELFT>(*SS);
}
Sec.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return;
}
if (Sym.isFunc()) {
// This handles a non PIC program call to function in a shared library. In
// an ideal world, we could just report an error saying the relocation can
// overflow at runtime. In the real world with glibc, crt1.o has a
// R_X86_64_PC32 pointing to libc.so.
//
// The general idea on how to handle such cases is to create a PLT entry and
// use that as the function value.
//
// For the static linking part, we just return a plt expr and everything
// else will use the PLT entry as the address.
//
// The remaining problem is making sure pointer equality still works. We
// need the help of the dynamic linker for that. We let it know that we have
// a direct reference to a so symbol by creating an undefined symbol with a
// non zero st_value. Seeing that, the dynamic linker resolves the symbol to
// the value of the symbol we created. This is true even for got entries, so
// pointer equality is maintained. To avoid an infinite loop, the only entry
// that points to the real function is a dedicated got entry used by the
// plt. That is identified by special relocation types (R_X86_64_JUMP_SLOT,
// R_386_JMP_SLOT, etc).
// For position independent executable on i386, the plt entry requires ebx
// to be set. This causes two problems:
// * If some code has a direct reference to a function, it was probably
// compiled without -fPIE/-fPIC and doesn't maintain ebx.
// * If a library definition gets preempted to the executable, it will have
// the wrong ebx value.
if (Config->Pie && Config->EMachine == EM_386)
errorOrWarn("symbol '" + toString(Sym) +
"' cannot be preempted; recompile with -fPIE" +
getLocation(Sec, Sym, Offset));
if (!Sym.isInPlt())
addPltEntry<ELFT>(In.Plt, In.GotPlt, In.RelaPlt, Target->PltRel, Sym);
if (!Sym.isDefined())
replaceWithDefined(Sym, In.Plt, getPltEntryOffset(Sym.PltIndex), 0);
Sym.NeedsPltAddr = true;
Sec.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
return;
}
errorOrWarn("symbol '" + toString(Sym) + "' has no type" +
getLocation(Sec, Sym, Offset));
}
+struct IRelativeReloc {
+ RelType Type;
+ InputSectionBase *Sec;
+ uint64_t Offset;
+ Symbol *Sym;
+};
+
+static std::vector<IRelativeReloc> IRelativeRelocs;
+
template <class ELFT, class RelTy>
static void scanReloc(InputSectionBase &Sec, OffsetGetter &GetOffset, RelTy *&I,
RelTy *End) {
const RelTy &Rel = *I;
Symbol &Sym = Sec.getFile<ELFT>()->getRelocTargetSym(Rel);
RelType Type;
// Deal with MIPS oddity.
if (Config->MipsN32Abi) {
Type = getMipsN32RelType(I, End);
} else {
Type = Rel.getType(Config->IsMips64EL);
++I;
}
// Get an offset in an output section this relocation is applied to.
uint64_t Offset = GetOffset.get(Rel.r_offset);
if (Offset == uint64_t(-1))
return;
// Skip if the target symbol is an erroneous undefined symbol.
if (maybeReportUndefined(Sym, Sec, Rel.r_offset))
return;
const uint8_t *RelocatedAddr = Sec.data().begin() + Rel.r_offset;
RelExpr Expr = Target->getRelExpr(Type, Sym, RelocatedAddr);
// Ignore "hint" relocations because they are only markers for relaxation.
if (isRelExprOneOf<R_HINT, R_NONE>(Expr))
return;
- // Strenghten or relax relocations.
+ if (Sym.isGnuIFunc() && !Config->ZText && Config->WarnIfuncTextrel) {
+ warn("using ifunc symbols when text relocations are allowed may produce "
+ "a binary that will segfault, if the object file is linked with "
+ "old version of glibc (glibc 2.28 and earlier). If this applies to "
+ "you, consider recompiling the object files without -fPIC and "
+ "without -Wl,-z,notext option. Use -no-warn-ifunc-textrel to "
+ "turn off this warning." +
+ getLocation(Sec, Sym, Offset));
+ }
+
+ // Relax relocations.
//
- // GNU ifunc symbols must be accessed via PLT because their addresses
- // are determined by runtime.
- //
- // On the other hand, if we know that a PLT entry will be resolved within
- // the same ELF module, we can skip PLT access and directly jump to the
- // destination function. For example, if we are linking a main exectuable,
- // all dynamic symbols that can be resolved within the executable will
- // actually be resolved that way at runtime, because the main exectuable
- // is always at the beginning of a search list. We can leverage that fact.
- if (Sym.isGnuIFunc() && !Config->ZIfuncnoplt) {
- if (!Config->ZText && Config->WarnIfuncTextrel) {
- warn("using ifunc symbols when text relocations are allowed may produce "
- "a binary that will segfault, if the object file is linked with "
- "old version of glibc (glibc 2.28 and earlier). If this applies to "
- "you, consider recompiling the object files without -fPIC and "
- "without -Wl,-z,notext option. Use -no-warn-ifunc-textrel to "
- "turn off this warning." +
- getLocation(Sec, Sym, Offset));
- }
- Expr = toPlt(Expr);
- } else if (!Sym.IsPreemptible && Expr == R_GOT_PC && !isAbsoluteValue(Sym)) {
- Expr = Target->adjustRelaxExpr(Type, RelocatedAddr, Expr);
- } else if (!Sym.IsPreemptible) {
- Expr = fromPlt(Expr);
+ // If we know that a PLT entry will be resolved within the same ELF module, we
+ // can skip PLT access and directly jump to the destination function. For
+ // example, if we are linking a main exectuable, all dynamic symbols that can
+ // be resolved within the executable will actually be resolved that way at
+ // runtime, because the main exectuable is always at the beginning of a search
+ // list. We can leverage that fact.
+ if (!Sym.IsPreemptible && (!Sym.isGnuIFunc() || Config->ZIfuncNoplt)) {
+ if (Expr == R_GOT_PC && !isAbsoluteValue(Sym))
+ Expr = Target->adjustRelaxExpr(Type, RelocatedAddr, Expr);
+ else
+ Expr = fromPlt(Expr);
}
// This relocation does not require got entry, but it is relative to got and
// needs it to be created. Here we request for that.
if (isRelExprOneOf<R_GOTONLY_PC, R_GOTONLY_PC_FROM_END, R_GOTREL,
R_GOTREL_FROM_END, R_PPC_TOC>(Expr))
In.Got->HasGotOffRel = true;
// Read an addend.
int64_t Addend = computeAddend<ELFT>(Rel, End, Sec, Expr, Sym.isLocal());
// Process some TLS relocations, including relaxing TLS relocations.
// Note that this function does not handle all TLS relocations.
if (unsigned Processed =
handleTlsRelocation<ELFT>(Type, Sym, Sec, Offset, Addend, Expr)) {
I += (Processed - 1);
return;
}
- // If a relocation needs PLT, we create PLT and GOTPLT slots for the symbol.
- if (needsPlt(Expr) && !Sym.isInPlt()) {
- if (Sym.isGnuIFunc() && !Sym.IsPreemptible)
- addPltEntry<ELFT>(In.Iplt, In.IgotPlt, In.RelaIplt, Target->IRelativeRel,
- Sym);
- else
- addPltEntry<ELFT>(In.Plt, In.GotPlt, In.RelaPlt, Target->PltRel, Sym);
+ // We were asked not to generate PLT entries for ifuncs. Instead, pass the
+ // direct relocation on through.
+ if (Sym.isGnuIFunc() && Config->ZIfuncNoplt) {
+ Sym.ExportDynamic = true;
+ In.RelaDyn->addReloc(Type, &Sec, Offset, &Sym, Addend, R_ADDEND, Type);
+ return;
}
- // Create a GOT slot if a relocation needs GOT.
- if (needsGot(Expr)) {
- if (Config->EMachine == EM_MIPS) {
- // MIPS ABI has special rules to process GOT entries and doesn't
- // require relocation entries for them. A special case is TLS
- // relocations. In that case dynamic loader applies dynamic
- // relocations to initialize TLS GOT entries.
- // See "Global Offset Table" in Chapter 5 in the following document
- // for detailed description:
- // ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
- In.MipsGot->addEntry(*Sec.File, Sym, Addend, Expr);
- } else if (!Sym.isInGot()) {
- addGotEntry<ELFT>(Sym);
+ // Non-preemptible ifuncs require special handling. First, handle the usual
+ // case where the symbol isn't one of these.
+ if (!Sym.isGnuIFunc() || Sym.IsPreemptible) {
+ // If a relocation needs PLT, we create PLT and GOTPLT slots for the symbol.
+ if (needsPlt(Expr) && !Sym.isInPlt())
+ addPltEntry<ELFT>(In.Plt, In.GotPlt, In.RelaPlt, Target->PltRel, Sym);
+
+ // Create a GOT slot if a relocation needs GOT.
+ if (needsGot(Expr)) {
+ if (Config->EMachine == EM_MIPS) {
+ // MIPS ABI has special rules to process GOT entries and doesn't
+ // require relocation entries for them. A special case is TLS
+ // relocations. In that case dynamic loader applies dynamic
+ // relocations to initialize TLS GOT entries.
+ // See "Global Offset Table" in Chapter 5 in the following document
+ // for detailed description:
+ // ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
+ In.MipsGot->addEntry(*Sec.File, Sym, Addend, Expr);
+ } else if (!Sym.isInGot()) {
+ addGotEntry<ELFT>(Sym);
+ }
}
+ } else {
+ // Handle a reference to a non-preemptible ifunc. These are special in a
+ // few ways:
+ //
+ // - Unlike most non-preemptible symbols, non-preemptible ifuncs do not have
+ // a fixed value. But assuming that all references to the ifunc are
+ // GOT-generating or PLT-generating, the handling of an ifunc is
+ // relatively straightforward. We create a PLT entry in Iplt, which is
+ // usually at the end of .plt, which makes an indirect call using a
+ // matching GOT entry in IgotPlt, which is usually at the end of .got.plt.
+ // The GOT entry is relocated using an IRELATIVE relocation in RelaIplt,
+ // which is usually at the end of .rela.plt. Unlike most relocations in
+ // .rela.plt, which may be evaluated lazily without -z now, dynamic
+ // loaders evaluate IRELATIVE relocs eagerly, which means that for
+ // IRELATIVE relocs only, GOT-generating relocations can point directly to
+ // .got.plt without requiring a separate GOT entry.
+ //
+ // - Despite the fact that an ifunc does not have a fixed value, compilers
+ // that are not passed -fPIC will assume that they do, and will emit
+ // direct (non-GOT-generating, non-PLT-generating) relocations to the
+ // symbol. This means that if a direct relocation to the symbol is
+ // seen, the linker must set a value for the symbol, and this value must
+ // be consistent no matter what type of reference is made to the symbol.
+ // This can be done by creating a PLT entry for the symbol in the way
+ // described above and making it canonical, that is, making all references
+ // point to the PLT entry instead of the resolver. In lld we also store
+ // the address of the PLT entry in the dynamic symbol table, which means
+ // that the symbol will also have the same value in other modules.
+ // Because the value loaded from the GOT needs to be consistent with
+ // the value computed using a direct relocation, a non-preemptible ifunc
+ // may end up with two GOT entries, one in .got.plt that points to the
+ // address returned by the resolver and is used only by the PLT entry,
+ // and another in .got that points to the PLT entry and is used by
+ // GOT-generating relocations.
+ //
+ // - The fact that these symbols do not have a fixed value makes them an
+ // exception to the general rule that a statically linked executable does
+ // not require any form of dynamic relocation. To handle these relocations
+ // correctly, the IRELATIVE relocations are stored in an array which a
+ // statically linked executable's startup code must enumerate using the
+ // linker-defined symbols __rela?_iplt_{start,end}.
+ //
+ // - An absolute relocation to a non-preemptible ifunc (such as a global
+ // variable containing a pointer to the ifunc) needs to be relocated in
+ // the exact same way as a GOT entry, so we can avoid needing to make the
+ // PLT entry canonical by translating such relocations into IRELATIVE
+ // relocations in the RelaIplt.
+ if (!Sym.isInPlt()) {
+ // Create PLT and GOTPLT slots for the symbol.
+ Sym.IsInIplt = true;
+
+ // Create a copy of the symbol to use as the target of the IRELATIVE
+ // relocation in the IgotPlt. This is in case we make the PLT canonical
+ // later, which would overwrite the original symbol.
+ //
+ // FIXME: Creating a copy of the symbol here is a bit of a hack. All
+ // that's really needed to create the IRELATIVE is the section and value,
+ // so ideally we should just need to copy those.
+ auto *DirectSym = make<Defined>(cast<Defined>(Sym));
+ addPltEntry<ELFT>(In.Iplt, In.IgotPlt, In.RelaIplt, Target->IRelativeRel,
+ *DirectSym);
+ Sym.PltIndex = DirectSym->PltIndex;
+ }
+ if (Expr == R_ABS && Addend == 0 && (Sec.Flags & SHF_WRITE)) {
+ // We might be able to represent this as an IRELATIVE. But we don't know
+ // yet whether some later relocation will make the symbol point to a
+ // canonical PLT, which would make this either a dynamic RELATIVE (PIC) or
+ // static (non-PIC) relocation. So we keep a record of the information
+ // required to process the relocation, and after scanRelocs() has been
+ // called on all relocations, the relocation is resolved by
+ // addIRelativeRelocs().
+ IRelativeRelocs.push_back({Type, &Sec, Offset, &Sym});
+ return;
+ }
+ if (needsGot(Expr)) {
+ // Redirect GOT accesses to point to the Igot.
+ //
+ // This field is also used to keep track of whether we ever needed a GOT
+ // entry. If we did and we make the PLT canonical later, we'll need to
+ // create a GOT entry pointing to the PLT entry for Sym.
+ Sym.GotInIgot = true;
+ } else if (!needsPlt(Expr)) {
+ // Make the ifunc's PLT entry canonical by changing the value of its
+ // symbol to redirect all references to point to it.
+ unsigned EntryOffset = Sym.PltIndex * Target->PltEntrySize;
+ if (Config->ZRetpolineplt)
+ EntryOffset += Target->PltHeaderSize;
+
+ auto &D = cast<Defined>(Sym);
+ D.Section = In.Iplt;
+ D.Value = EntryOffset;
+ D.Size = 0;
+ // It's important to set the symbol type here so that dynamic loaders
+ // don't try to call the PLT as if it were an ifunc resolver.
+ D.Type = STT_FUNC;
+
+ if (Sym.GotInIgot) {
+ // We previously encountered a GOT generating reference that we
+ // redirected to the Igot. Now that the PLT entry is canonical we must
+ // clear the redirection to the Igot and add a GOT entry. As we've
+ // changed the symbol type to STT_FUNC future GOT generating references
+ // will naturally use this GOT entry.
+ //
+ // We don't need to worry about creating a MIPS GOT here because ifuncs
+ // aren't a thing on MIPS.
+ Sym.GotInIgot = false;
+ addGotEntry<ELFT>(Sym);
+ }
+ }
}
processRelocAux<ELFT>(Sec, Expr, Type, Offset, Sym, Rel, Addend);
}
template <class ELFT, class RelTy>
static void scanRelocs(InputSectionBase &Sec, ArrayRef<RelTy> Rels) {
OffsetGetter GetOffset(Sec);
// Not all relocations end up in Sec.Relocations, but a lot do.
Sec.Relocations.reserve(Rels.size());
for (auto I = Rels.begin(), End = Rels.end(); I != End;)
scanReloc<ELFT>(Sec, GetOffset, I, End);
// Sort relocations by offset to binary search for R_RISCV_PCREL_HI20
if (Config->EMachine == EM_RISCV)
std::stable_sort(Sec.Relocations.begin(), Sec.Relocations.end(),
RelocationOffsetComparator{});
}
template <class ELFT> void elf::scanRelocations(InputSectionBase &S) {
if (S.AreRelocsRela)
scanRelocs<ELFT>(S, S.relas<ELFT>());
else
scanRelocs<ELFT>(S, S.rels<ELFT>());
+}
+
+// Figure out which representation to use for any absolute relocs to
+// non-preemptible ifuncs that we visited during scanRelocs().
+void elf::addIRelativeRelocs() {
+ for (IRelativeReloc &R : IRelativeRelocs) {
+ if (R.Sym->Type == STT_GNU_IFUNC)
+ In.RelaIplt->addReloc(
+ {Target->IRelativeRel, R.Sec, R.Offset, true, R.Sym, 0});
+ else if (Config->Pic)
+ addRelativeReloc(R.Sec, R.Offset, R.Sym, 0, R_ABS, R.Type);
+ else
+ R.Sec->Relocations.push_back({R_ABS, R.Type, R.Offset, 0, R.Sym});
+ }
+ IRelativeRelocs.clear();
}
static bool mergeCmp(const InputSection *A, const InputSection *B) {
// std::merge requires a strict weak ordering.
if (A->OutSecOff < B->OutSecOff)
return true;
if (A->OutSecOff == B->OutSecOff) {
auto *TA = dyn_cast<ThunkSection>(A);
auto *TB = dyn_cast<ThunkSection>(B);
// Check if Thunk is immediately before any specific Target
// InputSection for example Mips LA25 Thunks.
if (TA && TA->getTargetInputSection() == B)
return true;
// Place Thunk Sections without specific targets before
// non-Thunk Sections.
if (TA && !TB && !TA->getTargetInputSection())
return true;
}
return false;
}
// Call Fn on every executable InputSection accessed via the linker script
// InputSectionDescription::Sections.
static void forEachInputSectionDescription(
ArrayRef<OutputSection *> OutputSections,
llvm::function_ref<void(OutputSection *, InputSectionDescription *)> Fn) {
for (OutputSection *OS : OutputSections) {
if (!(OS->Flags & SHF_ALLOC) || !(OS->Flags & SHF_EXECINSTR))
continue;
for (BaseCommand *BC : OS->SectionCommands)
if (auto *ISD = dyn_cast<InputSectionDescription>(BC))
Fn(OS, ISD);
}
}
// Thunk Implementation
//
// Thunks (sometimes called stubs, veneers or branch islands) are small pieces
// of code that the linker inserts inbetween a caller and a callee. The thunks
// are added at link time rather than compile time as the decision on whether
// a thunk is needed, such as the caller and callee being out of range, can only
// be made at link time.
//
// It is straightforward to tell given the current state of the program when a
// thunk is needed for a particular call. The more difficult part is that
// the thunk needs to be placed in the program such that the caller can reach
// the thunk and the thunk can reach the callee; furthermore, adding thunks to
// the program alters addresses, which can mean more thunks etc.
//
// In lld we have a synthetic ThunkSection that can hold many Thunks.
// The decision to have a ThunkSection act as a container means that we can
// more easily handle the most common case of a single block of contiguous
// Thunks by inserting just a single ThunkSection.
//
// The implementation of Thunks in lld is split across these areas
// Relocations.cpp : Framework for creating and placing thunks
// Thunks.cpp : The code generated for each supported thunk
// Target.cpp : Target specific hooks that the framework uses to decide when
// a thunk is used
// Synthetic.cpp : Implementation of ThunkSection
// Writer.cpp : Iteratively call framework until no more Thunks added
//
// Thunk placement requirements:
// Mips LA25 thunks. These must be placed immediately before the callee section
// We can assume that the caller is in range of the Thunk. These are modelled
// by Thunks that return the section they must precede with
// getTargetInputSection().
//
// ARM interworking and range extension thunks. These thunks must be placed
// within range of the caller. All implemented ARM thunks can always reach the
// callee as they use an indirect jump via a register that has no range
// restrictions.
//
// Thunk placement algorithm:
// For Mips LA25 ThunkSections; the placement is explicit, it has to be before
// getTargetInputSection().
//
// For thunks that must be placed within range of the caller there are many
// possible choices given that the maximum range from the caller is usually
// much larger than the average InputSection size. Desirable properties include:
// - Maximize reuse of thunks by multiple callers
// - Minimize number of ThunkSections to simplify insertion
// - Handle impact of already added Thunks on addresses
// - Simple to understand and implement
//
// In lld for the first pass, we pre-create one or more ThunkSections per
// InputSectionDescription at Target specific intervals. A ThunkSection is
// placed so that the estimated end of the ThunkSection is within range of the
// start of the InputSectionDescription or the previous ThunkSection. For
// example:
// InputSectionDescription
// Section 0
// ...
// Section N
// ThunkSection 0
// Section N + 1
// ...
// Section N + K
// Thunk Section 1
//
// The intention is that we can add a Thunk to a ThunkSection that is well
// spaced enough to service a number of callers without having to do a lot
// of work. An important principle is that it is not an error if a Thunk cannot
// be placed in a pre-created ThunkSection; when this happens we create a new
// ThunkSection placed next to the caller. This allows us to handle the vast
// majority of thunks simply, but also handle rare cases where the branch range
// is smaller than the target specific spacing.
//
// The algorithm is expected to create all the thunks that are needed in a
// single pass, with a small number of programs needing a second pass due to
// the insertion of thunks in the first pass increasing the offset between
// callers and callees that were only just in range.
//
// A consequence of allowing new ThunkSections to be created outside of the
// pre-created ThunkSections is that in rare cases calls to Thunks that were in
// range in pass K, are out of range in some pass > K due to the insertion of
// more Thunks in between the caller and callee. When this happens we retarget
// the relocation back to the original target and create another Thunk.
// Remove ThunkSections that are empty, this should only be the initial set
// precreated on pass 0.
// Insert the Thunks for OutputSection OS into their designated place
// in the Sections vector, and recalculate the InputSection output section
// offsets.
// This may invalidate any output section offsets stored outside of InputSection
void ThunkCreator::mergeThunks(ArrayRef<OutputSection *> OutputSections) {
forEachInputSectionDescription(
OutputSections, [&](OutputSection *OS, InputSectionDescription *ISD) {
if (ISD->ThunkSections.empty())
return;
// Remove any zero sized precreated Thunks.
llvm::erase_if(ISD->ThunkSections,
[](const std::pair<ThunkSection *, uint32_t> &TS) {
return TS.first->getSize() == 0;
});
// ISD->ThunkSections contains all created ThunkSections, including
// those inserted in previous passes. Extract the Thunks created this
// pass and order them in ascending OutSecOff.
std::vector<ThunkSection *> NewThunks;
for (const std::pair<ThunkSection *, uint32_t> TS : ISD->ThunkSections)
if (TS.second == Pass)
NewThunks.push_back(TS.first);
std::stable_sort(NewThunks.begin(), NewThunks.end(),
[](const ThunkSection *A, const ThunkSection *B) {
return A->OutSecOff < B->OutSecOff;
});
// Merge sorted vectors of Thunks and InputSections by OutSecOff
std::vector<InputSection *> Tmp;
Tmp.reserve(ISD->Sections.size() + NewThunks.size());
std::merge(ISD->Sections.begin(), ISD->Sections.end(),
NewThunks.begin(), NewThunks.end(), std::back_inserter(Tmp),
mergeCmp);
ISD->Sections = std::move(Tmp);
});
}
// Find or create a ThunkSection within the InputSectionDescription (ISD) that
// is in range of Src. An ISD maps to a range of InputSections described by a
// linker script section pattern such as { .text .text.* }.
ThunkSection *ThunkCreator::getISDThunkSec(OutputSection *OS, InputSection *IS,
InputSectionDescription *ISD,
uint32_t Type, uint64_t Src) {
for (std::pair<ThunkSection *, uint32_t> TP : ISD->ThunkSections) {
ThunkSection *TS = TP.first;
uint64_t TSBase = OS->Addr + TS->OutSecOff;
uint64_t TSLimit = TSBase + TS->getSize();
if (Target->inBranchRange(Type, Src, (Src > TSLimit) ? TSBase : TSLimit))
return TS;
}
// No suitable ThunkSection exists. This can happen when there is a branch
// with lower range than the ThunkSection spacing or when there are too
// many Thunks. Create a new ThunkSection as close to the InputSection as
// possible. Error if InputSection is so large we cannot place ThunkSection
// anywhere in Range.
uint64_t ThunkSecOff = IS->OutSecOff;
if (!Target->inBranchRange(Type, Src, OS->Addr + ThunkSecOff)) {
ThunkSecOff = IS->OutSecOff + IS->getSize();
if (!Target->inBranchRange(Type, Src, OS->Addr + ThunkSecOff))
fatal("InputSection too large for range extension thunk " +
IS->getObjMsg(Src - (OS->Addr + IS->OutSecOff)));
}
return addThunkSection(OS, ISD, ThunkSecOff);
}
// Add a Thunk that needs to be placed in a ThunkSection that immediately
// precedes its Target.
ThunkSection *ThunkCreator::getISThunkSec(InputSection *IS) {
ThunkSection *TS = ThunkedSections.lookup(IS);
if (TS)
return TS;
// Find InputSectionRange within Target Output Section (TOS) that the
// InputSection (IS) that we need to precede is in.
OutputSection *TOS = IS->getParent();
for (BaseCommand *BC : TOS->SectionCommands) {
auto *ISD = dyn_cast<InputSectionDescription>(BC);
if (!ISD || ISD->Sections.empty())
continue;
InputSection *First = ISD->Sections.front();
InputSection *Last = ISD->Sections.back();
if (IS->OutSecOff < First->OutSecOff || Last->OutSecOff < IS->OutSecOff)
continue;
TS = addThunkSection(TOS, ISD, IS->OutSecOff);
ThunkedSections[IS] = TS;
return TS;
}
return nullptr;
}
// Create one or more ThunkSections per OS that can be used to place Thunks.
// We attempt to place the ThunkSections using the following desirable
// properties:
// - Within range of the maximum number of callers
// - Minimise the number of ThunkSections
//
// We follow a simple but conservative heuristic to place ThunkSections at
// offsets that are multiples of a Target specific branch range.
// For an InputSectionDescription that is smaller than the range, a single
// ThunkSection at the end of the range will do.
//
// For an InputSectionDescription that is more than twice the size of the range,
// we place the last ThunkSection at range bytes from the end of the
// InputSectionDescription in order to increase the likelihood that the
// distance from a thunk to its target will be sufficiently small to
// allow for the creation of a short thunk.
void ThunkCreator::createInitialThunkSections(
ArrayRef<OutputSection *> OutputSections) {
uint32_t ThunkSectionSpacing = Target->getThunkSectionSpacing();
forEachInputSectionDescription(
OutputSections, [&](OutputSection *OS, InputSectionDescription *ISD) {
if (ISD->Sections.empty())
return;
uint32_t ISDBegin = ISD->Sections.front()->OutSecOff;
uint32_t ISDEnd =
ISD->Sections.back()->OutSecOff + ISD->Sections.back()->getSize();
uint32_t LastThunkLowerBound = -1;
if (ISDEnd - ISDBegin > ThunkSectionSpacing * 2)
LastThunkLowerBound = ISDEnd - ThunkSectionSpacing;
uint32_t ISLimit;
uint32_t PrevISLimit = ISDBegin;
uint32_t ThunkUpperBound = ISDBegin + ThunkSectionSpacing;
for (const InputSection *IS : ISD->Sections) {
ISLimit = IS->OutSecOff + IS->getSize();
if (ISLimit > ThunkUpperBound) {
addThunkSection(OS, ISD, PrevISLimit);
ThunkUpperBound = PrevISLimit + ThunkSectionSpacing;
}
if (ISLimit > LastThunkLowerBound)
break;
PrevISLimit = ISLimit;
}
addThunkSection(OS, ISD, ISLimit);
});
}
ThunkSection *ThunkCreator::addThunkSection(OutputSection *OS,
InputSectionDescription *ISD,
uint64_t Off) {
auto *TS = make<ThunkSection>(OS, Off);
ISD->ThunkSections.push_back({TS, Pass});
return TS;
}
std::pair<Thunk *, bool> ThunkCreator::getThunk(Symbol &Sym, RelType Type,
uint64_t Src) {
std::vector<Thunk *> *ThunkVec = nullptr;
// We use (section, offset) pair to find the thunk position if possible so
// that we create only one thunk for aliased symbols or ICFed sections.
if (auto *D = dyn_cast<Defined>(&Sym))
if (!D->isInPlt() && D->Section)
ThunkVec = &ThunkedSymbolsBySection[{D->Section->Repl, D->Value}];
if (!ThunkVec)
ThunkVec = &ThunkedSymbols[&Sym];
// Check existing Thunks for Sym to see if they can be reused
for (Thunk *T : *ThunkVec)
if (T->isCompatibleWith(Type) &&
Target->inBranchRange(Type, Src, T->getThunkTargetSym()->getVA()))
return std::make_pair(T, false);
// No existing compatible Thunk in range, create a new one
Thunk *T = addThunk(Type, Sym);
ThunkVec->push_back(T);
return std::make_pair(T, true);
}
// Return true if the relocation target is an in range Thunk.
// Return false if the relocation is not to a Thunk. If the relocation target
// was originally to a Thunk, but is no longer in range we revert the
// relocation back to its original non-Thunk target.
bool ThunkCreator::normalizeExistingThunk(Relocation &Rel, uint64_t Src) {
if (Thunk *T = Thunks.lookup(Rel.Sym)) {
if (Target->inBranchRange(Rel.Type, Src, Rel.Sym->getVA()))
return true;
Rel.Sym = &T->Destination;
if (Rel.Sym->isInPlt())
Rel.Expr = toPlt(Rel.Expr);
}
return false;
}
// Process all relocations from the InputSections that have been assigned
// to InputSectionDescriptions and redirect through Thunks if needed. The
// function should be called iteratively until it returns false.
//
// PreConditions:
// All InputSections that may need a Thunk are reachable from
// OutputSectionCommands.
//
// All OutputSections have an address and all InputSections have an offset
// within the OutputSection.
//
// The offsets between caller (relocation place) and callee
// (relocation target) will not be modified outside of createThunks().
//
// PostConditions:
// If return value is true then ThunkSections have been inserted into
// OutputSections. All relocations that needed a Thunk based on the information
// available to createThunks() on entry have been redirected to a Thunk. Note
// that adding Thunks changes offsets between caller and callee so more Thunks
// may be required.
//
// If return value is false then no more Thunks are needed, and createThunks has
// made no changes. If the target requires range extension thunks, currently
// ARM, then any future change in offset between caller and callee risks a
// relocation out of range error.
bool ThunkCreator::createThunks(ArrayRef<OutputSection *> OutputSections) {
bool AddressesChanged = false;
if (Pass == 0 && Target->getThunkSectionSpacing())
createInitialThunkSections(OutputSections);
// With Thunk Size much smaller than branch range we expect to
// converge quickly; if we get to 10 something has gone wrong.
if (Pass == 10)
fatal("thunk creation not converged");
// Create all the Thunks and insert them into synthetic ThunkSections. The
// ThunkSections are later inserted back into InputSectionDescriptions.
// We separate the creation of ThunkSections from the insertion of the
// ThunkSections as ThunkSections are not always inserted into the same
// InputSectionDescription as the caller.
forEachInputSectionDescription(
OutputSections, [&](OutputSection *OS, InputSectionDescription *ISD) {
for (InputSection *IS : ISD->Sections)
for (Relocation &Rel : IS->Relocations) {
uint64_t Src = IS->getVA(Rel.Offset);
// If we are a relocation to an existing Thunk, check if it is
// still in range. If not then Rel will be altered to point to its
// original target so another Thunk can be generated.
if (Pass > 0 && normalizeExistingThunk(Rel, Src))
continue;
if (!Target->needsThunk(Rel.Expr, Rel.Type, IS->File, Src,
*Rel.Sym))
continue;
Thunk *T;
bool IsNew;
std::tie(T, IsNew) = getThunk(*Rel.Sym, Rel.Type, Src);
if (IsNew) {
// Find or create a ThunkSection for the new Thunk
ThunkSection *TS;
if (auto *TIS = T->getTargetInputSection())
TS = getISThunkSec(TIS);
else
TS = getISDThunkSec(OS, IS, ISD, Rel.Type, Src);
TS->addThunk(T);
Thunks[T->getThunkTargetSym()] = T;
}
// Redirect relocation to Thunk, we never go via the PLT to a Thunk
Rel.Sym = T->getThunkTargetSym();
Rel.Expr = fromPlt(Rel.Expr);
}
for (auto &P : ISD->ThunkSections)
AddressesChanged |= P.first->assignOffsets();
});
for (auto &P : ThunkedSections)
AddressesChanged |= P.second->assignOffsets();
// Merge all created synthetic ThunkSections back into OutputSection
mergeThunks(OutputSections);
++Pass;
return AddressesChanged;
}
template void elf::scanRelocations<ELF32LE>(InputSectionBase &);
template void elf::scanRelocations<ELF32BE>(InputSectionBase &);
template void elf::scanRelocations<ELF64LE>(InputSectionBase &);
template void elf::scanRelocations<ELF64BE>(InputSectionBase &);
Index: head/contrib/llvm/tools/lld/ELF/Relocations.h
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Relocations.h (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Relocations.h (revision 350467)
@@ -1,219 +1,213 @@
//===- Relocations.h -------------------------------------------*- C++ -*-===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#ifndef LLD_ELF_RELOCATIONS_H
#define LLD_ELF_RELOCATIONS_H
#include "lld/Common/LLVM.h"
#include "llvm/ADT/DenseMap.h"
#include <map>
#include <vector>
namespace lld {
namespace elf {
class Symbol;
class InputSection;
class InputSectionBase;
class OutputSection;
class SectionBase;
// Represents a relocation type, such as R_X86_64_PC32 or R_ARM_THM_CALL.
typedef uint32_t RelType;
// List of target-independent relocation types. Relocations read
// from files are converted to these types so that the main code
// doesn't have to know about architecture-specific details.
enum RelExpr {
R_INVALID,
R_ABS,
R_ADDEND,
R_AARCH64_GOT_PAGE_PC,
- // The expression is used for IFUNC support. Describes PC-relative
- // address of the memory page of GOT entry. This entry is used for
- // a redirection to IPLT.
- R_AARCH64_GOT_PAGE_PC_PLT,
R_AARCH64_RELAX_TLS_GD_TO_IE_PAGE_PC,
R_AARCH64_PAGE_PC,
- R_AARCH64_PLT_PAGE_PC,
R_AARCH64_TLSDESC_PAGE,
R_ARM_SBREL,
R_GOT,
- // The expression is used for IFUNC support. Evaluates to GOT entry,
- // containing redirection to the IPLT.
- R_GOT_PLT,
R_GOTONLY_PC,
R_GOTONLY_PC_FROM_END,
R_GOTREL,
R_GOTREL_FROM_END,
R_GOT_FROM_END,
R_GOT_OFF,
R_GOT_PC,
R_HEXAGON_GOT,
R_HINT,
R_MIPS_GOTREL,
R_MIPS_GOT_GP,
R_MIPS_GOT_GP_PC,
R_MIPS_GOT_LOCAL_PAGE,
R_MIPS_GOT_OFF,
R_MIPS_GOT_OFF32,
R_MIPS_TLSGD,
R_MIPS_TLSLD,
R_NEG_TLS,
R_NONE,
R_PC,
R_PLT,
R_PLT_PC,
R_PPC_CALL,
R_PPC_CALL_PLT,
R_PPC_TOC,
R_RELAX_GOT_PC,
R_RELAX_GOT_PC_NOPIC,
R_RELAX_TLS_GD_TO_IE,
R_RELAX_TLS_GD_TO_IE_ABS,
R_RELAX_TLS_GD_TO_IE_END,
R_RELAX_TLS_GD_TO_IE_GOT_OFF,
R_RELAX_TLS_GD_TO_LE,
R_RELAX_TLS_GD_TO_LE_NEG,
R_RELAX_TLS_IE_TO_LE,
R_RELAX_TLS_LD_TO_LE,
R_RELAX_TLS_LD_TO_LE_ABS,
R_RISCV_PC_INDIRECT,
R_SIZE,
R_TLS,
R_TLSDESC,
R_TLSDESC_CALL,
R_TLSGD_GOT,
R_TLSGD_GOT_FROM_END,
R_TLSGD_PC,
R_TLSIE_HINT,
R_TLSLD_GOT,
R_TLSLD_GOT_FROM_END,
R_TLSLD_GOT_OFF,
R_TLSLD_HINT,
R_TLSLD_PC,
};
// Build a bitmask with one bit set for each RelExpr.
//
// Constexpr function arguments can't be used in static asserts, so we
// use template arguments to build the mask.
// But function template partial specializations don't exist (needed
// for base case of the recursion), so we need a dummy struct.
template <RelExpr... Exprs> struct RelExprMaskBuilder {
static inline uint64_t build() { return 0; }
};
// Specialization for recursive case.
template <RelExpr Head, RelExpr... Tail>
struct RelExprMaskBuilder<Head, Tail...> {
static inline uint64_t build() {
static_assert(0 <= Head && Head < 64,
"RelExpr is too large for 64-bit mask!");
return (uint64_t(1) << Head) | RelExprMaskBuilder<Tail...>::build();
}
};
// Return true if `Expr` is one of `Exprs`.
// There are fewer than 64 RelExpr's, so we can represent any set of
// RelExpr's as a constant bit mask and test for membership with a
// couple cheap bitwise operations.
template <RelExpr... Exprs> bool isRelExprOneOf(RelExpr Expr) {
assert(0 <= Expr && (int)Expr < 64 &&
"RelExpr is too large for 64-bit mask!");
return (uint64_t(1) << Expr) & RelExprMaskBuilder<Exprs...>::build();
}
// Architecture-neutral representation of relocation.
struct Relocation {
RelExpr Expr;
RelType Type;
uint64_t Offset;
int64_t Addend;
Symbol *Sym;
};
struct RelocationOffsetComparator {
bool operator()(const Relocation &Lhs, const Relocation &Rhs) {
return Lhs.Offset < Rhs.Offset;
}
// For std::lower_bound, std::upper_bound, std::equal_range.
bool operator()(const Relocation &Rel, uint64_t Val) {
return Rel.Offset < Val;
}
bool operator()(uint64_t Val, const Relocation &Rel) {
return Val < Rel.Offset;
}
};
template <class ELFT> void scanRelocations(InputSectionBase &);
+
+void addIRelativeRelocs();
class ThunkSection;
class Thunk;
struct InputSectionDescription;
class ThunkCreator {
public:
// Return true if Thunks have been added to OutputSections
bool createThunks(ArrayRef<OutputSection *> OutputSections);
// The number of completed passes of createThunks this permits us
// to do one time initialization on Pass 0 and put a limit on the
// number of times it can be called to prevent infinite loops.
uint32_t Pass = 0;
private:
void mergeThunks(ArrayRef<OutputSection *> OutputSections);
ThunkSection *getISDThunkSec(OutputSection *OS, InputSection *IS,
InputSectionDescription *ISD, uint32_t Type,
uint64_t Src);
ThunkSection *getISThunkSec(InputSection *IS);
void createInitialThunkSections(ArrayRef<OutputSection *> OutputSections);
std::pair<Thunk *, bool> getThunk(Symbol &Sym, RelType Type, uint64_t Src);
ThunkSection *addThunkSection(OutputSection *OS, InputSectionDescription *,
uint64_t Off);
bool normalizeExistingThunk(Relocation &Rel, uint64_t Src);
// Record all the available Thunks for a Symbol
llvm::DenseMap<std::pair<SectionBase *, uint64_t>, std::vector<Thunk *>>
ThunkedSymbolsBySection;
llvm::DenseMap<Symbol *, std::vector<Thunk *>> ThunkedSymbols;
// Find a Thunk from the Thunks symbol definition, we can use this to find
// the Thunk from a relocation to the Thunks symbol definition.
llvm::DenseMap<Symbol *, Thunk *> Thunks;
// Track InputSections that have an inline ThunkSection placed in front
// an inline ThunkSection may have control fall through to the section below
// so we need to make sure that there is only one of them.
// The Mips LA25 Thunk is an example of an inline ThunkSection.
llvm::DenseMap<InputSection *, ThunkSection *> ThunkedSections;
};
// Return a int64_t to make sure we get the sign extension out of the way as
// early as possible.
template <class ELFT>
static inline int64_t getAddend(const typename ELFT::Rel &Rel) {
return 0;
}
template <class ELFT>
static inline int64_t getAddend(const typename ELFT::Rela &Rel) {
return Rel.r_addend;
}
} // namespace elf
} // namespace lld
#endif
Index: head/contrib/llvm/tools/lld/ELF/Symbols.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Symbols.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Symbols.cpp (revision 350467)
@@ -1,305 +1,309 @@
//===- Symbols.cpp --------------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "Symbols.h"
#include "InputFiles.h"
#include "InputSection.h"
#include "OutputSections.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "Writer.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Strings.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Support/Path.h"
#include <cstring>
using namespace llvm;
using namespace llvm::object;
using namespace llvm::ELF;
using namespace lld;
using namespace lld::elf;
Defined *ElfSym::Bss;
Defined *ElfSym::Etext1;
Defined *ElfSym::Etext2;
Defined *ElfSym::Edata1;
Defined *ElfSym::Edata2;
Defined *ElfSym::End1;
Defined *ElfSym::End2;
Defined *ElfSym::GlobalOffsetTable;
Defined *ElfSym::MipsGp;
Defined *ElfSym::MipsGpDisp;
Defined *ElfSym::MipsLocalGp;
Defined *ElfSym::RelaIpltStart;
Defined *ElfSym::RelaIpltEnd;
static uint64_t getSymVA(const Symbol &Sym, int64_t &Addend) {
switch (Sym.kind()) {
case Symbol::DefinedKind: {
auto &D = cast<Defined>(Sym);
SectionBase *IS = D.Section;
// According to the ELF spec reference to a local symbol from outside
// the group are not allowed. Unfortunately .eh_frame breaks that rule
// and must be treated specially. For now we just replace the symbol with
// 0.
if (IS == &InputSection::Discarded)
return 0;
// This is an absolute symbol.
if (!IS)
return D.Value;
IS = IS->Repl;
uint64_t Offset = D.Value;
// An object in an SHF_MERGE section might be referenced via a
// section symbol (as a hack for reducing the number of local
// symbols).
// Depending on the addend, the reference via a section symbol
// refers to a different object in the merge section.
// Since the objects in the merge section are not necessarily
// contiguous in the output, the addend can thus affect the final
// VA in a non-linear way.
// To make this work, we incorporate the addend into the section
// offset (and zero out the addend for later processing) so that
// we find the right object in the section.
if (D.isSection()) {
Offset += Addend;
Addend = 0;
}
// In the typical case, this is actually very simple and boils
// down to adding together 3 numbers:
// 1. The address of the output section.
// 2. The offset of the input section within the output section.
// 3. The offset within the input section (this addition happens
// inside InputSection::getOffset).
//
// If you understand the data structures involved with this next
// line (and how they get built), then you have a pretty good
// understanding of the linker.
uint64_t VA = IS->getVA(Offset);
if (D.isTls() && !Config->Relocatable) {
// Use the address of the TLS segment's first section rather than the
// segment's address, because segment addresses aren't initialized until
// after sections are finalized. (e.g. Measuring the size of .rela.dyn
// for Android relocation packing requires knowing TLS symbol addresses
// during section finalization.)
if (!Out::TlsPhdr || !Out::TlsPhdr->FirstSec)
fatal(toString(D.File) +
" has an STT_TLS symbol but doesn't have an SHF_TLS section");
return VA - Out::TlsPhdr->FirstSec->Addr;
}
return VA;
}
case Symbol::SharedKind:
case Symbol::UndefinedKind:
return 0;
case Symbol::LazyArchiveKind:
case Symbol::LazyObjectKind:
assert(Sym.IsUsedInRegularObj && "lazy symbol reached writer");
return 0;
case Symbol::PlaceholderKind:
llvm_unreachable("placeholder symbol reached writer");
}
llvm_unreachable("invalid symbol kind");
}
uint64_t Symbol::getVA(int64_t Addend) const {
uint64_t OutVA = getSymVA(*this, Addend);
return OutVA + Addend;
}
-uint64_t Symbol::getGotVA() const { return In.Got->getVA() + getGotOffset(); }
+uint64_t Symbol::getGotVA() const {
+ if (GotInIgot)
+ return In.IgotPlt->getVA() + getGotPltOffset();
+ return In.Got->getVA() + getGotOffset();
+}
uint64_t Symbol::getGotOffset() const {
return GotIndex * Target->GotEntrySize;
}
uint64_t Symbol::getGotPltVA() const {
- if (this->IsInIgot)
+ if (IsInIplt)
return In.IgotPlt->getVA() + getGotPltOffset();
return In.GotPlt->getVA() + getGotPltOffset();
}
uint64_t Symbol::getGotPltOffset() const {
- if (IsInIgot)
+ if (IsInIplt)
return PltIndex * Target->GotPltEntrySize;
return (PltIndex + Target->GotPltHeaderEntriesNum) * Target->GotPltEntrySize;
}
uint64_t Symbol::getPPC64LongBranchOffset() const {
assert(PPC64BranchltIndex != 0xffff);
return PPC64BranchltIndex * Target->GotPltEntrySize;
}
uint64_t Symbol::getPltVA() const {
PltSection *Plt = IsInIplt ? In.Iplt : In.Plt;
return Plt->getVA() + Plt->HeaderSize + PltIndex * Target->PltEntrySize;
}
uint64_t Symbol::getPPC64LongBranchTableVA() const {
assert(PPC64BranchltIndex != 0xffff);
return In.PPC64LongBranchTarget->getVA() +
PPC64BranchltIndex * Target->GotPltEntrySize;
}
uint64_t Symbol::getSize() const {
if (const auto *DR = dyn_cast<Defined>(this))
return DR->Size;
return cast<SharedSymbol>(this)->Size;
}
OutputSection *Symbol::getOutputSection() const {
if (auto *S = dyn_cast<Defined>(this)) {
if (auto *Sec = S->Section)
return Sec->Repl->getOutputSection();
return nullptr;
}
return nullptr;
}
// If a symbol name contains '@', the characters after that is
// a symbol version name. This function parses that.
void Symbol::parseSymbolVersion() {
StringRef S = getName();
size_t Pos = S.find('@');
if (Pos == 0 || Pos == StringRef::npos)
return;
StringRef Verstr = S.substr(Pos + 1);
if (Verstr.empty())
return;
// Truncate the symbol name so that it doesn't include the version string.
NameSize = Pos;
// If this is not in this DSO, it is not a definition.
if (!isDefined())
return;
// '@@' in a symbol name means the default version.
// It is usually the most recent one.
bool IsDefault = (Verstr[0] == '@');
if (IsDefault)
Verstr = Verstr.substr(1);
for (VersionDefinition &Ver : Config->VersionDefinitions) {
if (Ver.Name != Verstr)
continue;
if (IsDefault)
VersionId = Ver.Id;
else
VersionId = Ver.Id | VERSYM_HIDDEN;
return;
}
// It is an error if the specified version is not defined.
// Usually version script is not provided when linking executable,
// but we may still want to override a versioned symbol from DSO,
// so we do not report error in this case. We also do not error
// if the symbol has a local version as it won't be in the dynamic
// symbol table.
if (Config->Shared && VersionId != VER_NDX_LOCAL)
error(toString(File) + ": symbol " + S + " has undefined version " +
Verstr);
}
InputFile *LazyArchive::fetch() { return cast<ArchiveFile>(File)->fetch(Sym); }
MemoryBufferRef LazyArchive::getMemberBuffer() {
Archive::Child C = CHECK(
Sym.getMember(), "could not get the member for symbol " + Sym.getName());
return CHECK(C.getMemoryBufferRef(),
"could not get the buffer for the member defining symbol " +
Sym.getName());
}
uint8_t Symbol::computeBinding() const {
if (Config->Relocatable)
return Binding;
if (Visibility != STV_DEFAULT && Visibility != STV_PROTECTED)
return STB_LOCAL;
if (VersionId == VER_NDX_LOCAL && isDefined() && !IsPreemptible)
return STB_LOCAL;
if (!Config->GnuUnique && Binding == STB_GNU_UNIQUE)
return STB_GLOBAL;
return Binding;
}
bool Symbol::includeInDynsym() const {
if (!Config->HasDynSymTab)
return false;
if (computeBinding() == STB_LOCAL)
return false;
if (!isDefined())
return true;
return ExportDynamic;
}
// Print out a log message for --trace-symbol.
void elf::printTraceSymbol(Symbol *Sym) {
std::string S;
if (Sym->isUndefined())
S = ": reference to ";
else if (Sym->isLazy())
S = ": lazy definition of ";
else if (Sym->isShared())
S = ": shared definition of ";
else if (dyn_cast_or_null<BssSection>(cast<Defined>(Sym)->Section))
S = ": common definition of ";
else
S = ": definition of ";
message(toString(Sym->File) + S + Sym->getName());
}
void elf::maybeWarnUnorderableSymbol(const Symbol *Sym) {
if (!Config->WarnSymbolOrdering)
return;
// If UnresolvedPolicy::Ignore is used, no "undefined symbol" error/warning
// is emitted. It makes sense to not warn on undefined symbols.
//
// Note, ld.bfd --symbol-ordering-file= does not warn on undefined symbols,
// but we don't have to be compatible here.
if (Sym->isUndefined() &&
Config->UnresolvedSymbols == UnresolvedPolicy::Ignore)
return;
const InputFile *File = Sym->File;
auto *D = dyn_cast<Defined>(Sym);
auto Warn = [&](StringRef S) { warn(toString(File) + S + Sym->getName()); };
if (Sym->isUndefined())
Warn(": unable to order undefined symbol: ");
else if (Sym->isShared())
Warn(": unable to order shared symbol: ");
else if (D && !D->Section)
Warn(": unable to order absolute symbol: ");
else if (D && isa<OutputSection>(D->Section))
Warn(": unable to order synthetic symbol: ");
else if (D && !D->Section->Repl->Live)
Warn(": unable to order discarded symbol: ");
}
// Returns a symbol for an error message.
std::string lld::toString(const Symbol &B) {
if (Config->Demangle)
if (Optional<std::string> S = demangleItanium(B.getName()))
return *S;
return B.getName();
}
Index: head/contrib/llvm/tools/lld/ELF/Symbols.h
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Symbols.h (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Symbols.h (revision 350467)
@@ -1,419 +1,421 @@
//===- Symbols.h ------------------------------------------------*- C++ -*-===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines various types of Symbols.
//
//===----------------------------------------------------------------------===//
#ifndef LLD_ELF_SYMBOLS_H
#define LLD_ELF_SYMBOLS_H
#include "InputSection.h"
#include "lld/Common/LLVM.h"
#include "lld/Common/Strings.h"
#include "llvm/Object/Archive.h"
#include "llvm/Object/ELF.h"
namespace lld {
namespace elf {
class Symbol;
class InputFile;
} // namespace elf
std::string toString(const elf::Symbol &);
std::string toString(const elf::InputFile *);
namespace elf {
class ArchiveFile;
class BitcodeFile;
class BssSection;
class InputFile;
class LazyObjFile;
template <class ELFT> class ObjFile;
class OutputSection;
template <class ELFT> class SharedFile;
// This is a StringRef-like container that doesn't run strlen().
//
// ELF string tables contain a lot of null-terminated strings. Most of them
// are not necessary for the linker because they are names of local symbols,
// and the linker doesn't use local symbol names for name resolution. So, we
// use this class to represents strings read from string tables.
struct StringRefZ {
StringRefZ(const char *S) : Data(S), Size(-1) {}
StringRefZ(StringRef S) : Data(S.data()), Size(S.size()) {}
const char *Data;
const uint32_t Size;
};
// The base class for real symbol classes.
class Symbol {
public:
enum Kind {
PlaceholderKind,
DefinedKind,
SharedKind,
UndefinedKind,
LazyArchiveKind,
LazyObjectKind,
};
Kind kind() const { return static_cast<Kind>(SymbolKind); }
// The file from which this symbol was created.
InputFile *File;
protected:
const char *NameData;
mutable uint32_t NameSize;
public:
uint32_t DynsymIndex = 0;
uint32_t GotIndex = -1;
uint32_t PltIndex = -1;
uint32_t GlobalDynIndex = -1;
// This field is a index to the symbol's version definition.
uint32_t VerdefIndex = -1;
// Version definition index.
uint16_t VersionId;
// An index into the .branch_lt section on PPC64.
uint16_t PPC64BranchltIndex = -1;
// Symbol binding. This is not overwritten by replaceSymbol to track
// changes during resolution. In particular:
// - An undefined weak is still weak when it resolves to a shared library.
// - An undefined weak will not fetch archive members, but we have to
// remember it is weak.
uint8_t Binding;
// The following fields have the same meaning as the ELF symbol attributes.
uint8_t Type; // symbol type
uint8_t StOther; // st_other field value
uint8_t SymbolKind;
// Symbol visibility. This is the computed minimum visibility of all
// observed non-DSO symbols.
unsigned Visibility : 2;
// True if the symbol was used for linking and thus need to be added to the
// output file's symbol table. This is true for all symbols except for
// unreferenced DSO symbols and bitcode symbols that are unreferenced except
// by other bitcode objects.
unsigned IsUsedInRegularObj : 1;
// If this flag is true and the symbol has protected or default visibility, it
// will appear in .dynsym. This flag is set by interposable DSO symbols in
// executables, by most symbols in DSOs and executables built with
// --export-dynamic, and by dynamic lists.
unsigned ExportDynamic : 1;
// False if LTO shouldn't inline whatever this symbol points to. If a symbol
// is overwritten after LTO, LTO shouldn't inline the symbol because it
// doesn't know the final contents of the symbol.
unsigned CanInline : 1;
// True if this symbol is specified by --trace-symbol option.
unsigned Traced : 1;
bool includeInDynsym() const;
uint8_t computeBinding() const;
bool isWeak() const { return Binding == llvm::ELF::STB_WEAK; }
bool isUndefined() const { return SymbolKind == UndefinedKind; }
bool isDefined() const { return SymbolKind == DefinedKind; }
bool isShared() const { return SymbolKind == SharedKind; }
bool isLocal() const { return Binding == llvm::ELF::STB_LOCAL; }
bool isLazy() const {
return SymbolKind == LazyArchiveKind || SymbolKind == LazyObjectKind;
}
// True if this is an undefined weak symbol. This only works once
// all input files have been added.
bool isUndefWeak() const {
// See comment on lazy symbols for details.
return isWeak() && (isUndefined() || isLazy());
}
StringRef getName() const {
if (NameSize == (uint32_t)-1)
NameSize = strlen(NameData);
return {NameData, NameSize};
}
void setName(StringRef S) {
NameData = S.data();
NameSize = S.size();
}
void parseSymbolVersion();
bool isInGot() const { return GotIndex != -1U; }
bool isInPlt() const { return PltIndex != -1U; }
bool isInPPC64Branchlt() const { return PPC64BranchltIndex != 0xffff; }
uint64_t getVA(int64_t Addend = 0) const;
uint64_t getGotOffset() const;
uint64_t getGotVA() const;
uint64_t getGotPltOffset() const;
uint64_t getGotPltVA() const;
uint64_t getPltVA() const;
uint64_t getPPC64LongBranchTableVA() const;
uint64_t getPPC64LongBranchOffset() const;
uint64_t getSize() const;
OutputSection *getOutputSection() const;
protected:
Symbol(Kind K, InputFile *File, StringRefZ Name, uint8_t Binding,
uint8_t StOther, uint8_t Type)
: File(File), NameData(Name.Data), NameSize(Name.Size), Binding(Binding),
Type(Type), StOther(StOther), SymbolKind(K), NeedsPltAddr(false),
- IsInIplt(false), IsInIgot(false), IsPreemptible(false),
+ IsInIplt(false), GotInIgot(false), IsPreemptible(false),
Used(!Config->GcSections), NeedsTocRestore(false),
ScriptDefined(false) {}
public:
// True the symbol should point to its PLT entry.
// For SharedSymbol only.
unsigned NeedsPltAddr : 1;
- // True if this symbol is in the Iplt sub-section of the Plt.
+ // True if this symbol is in the Iplt sub-section of the Plt and the Igot
+ // sub-section of the .got.plt or .got.
unsigned IsInIplt : 1;
- // True if this symbol is in the Igot sub-section of the .got.plt or .got.
- unsigned IsInIgot : 1;
+ // True if this symbol needs a GOT entry and its GOT entry is actually in
+ // Igot. This will be true only for certain non-preemptible ifuncs.
+ unsigned GotInIgot : 1;
// True if this symbol is preemptible at load time.
unsigned IsPreemptible : 1;
// True if an undefined or shared symbol is used from a live section.
unsigned Used : 1;
// True if a call to this symbol needs to be followed by a restore of the
// PPC64 toc pointer.
unsigned NeedsTocRestore : 1;
// True if this symbol is defined by a linker script.
unsigned ScriptDefined : 1;
bool isSection() const { return Type == llvm::ELF::STT_SECTION; }
bool isTls() const { return Type == llvm::ELF::STT_TLS; }
bool isFunc() const { return Type == llvm::ELF::STT_FUNC; }
bool isGnuIFunc() const { return Type == llvm::ELF::STT_GNU_IFUNC; }
bool isObject() const { return Type == llvm::ELF::STT_OBJECT; }
bool isFile() const { return Type == llvm::ELF::STT_FILE; }
};
// Represents a symbol that is defined in the current output file.
class Defined : public Symbol {
public:
Defined(InputFile *File, StringRefZ Name, uint8_t Binding, uint8_t StOther,
uint8_t Type, uint64_t Value, uint64_t Size, SectionBase *Section)
: Symbol(DefinedKind, File, Name, Binding, StOther, Type), Value(Value),
Size(Size), Section(Section) {}
static bool classof(const Symbol *S) { return S->isDefined(); }
uint64_t Value;
uint64_t Size;
SectionBase *Section;
};
class Undefined : public Symbol {
public:
Undefined(InputFile *File, StringRefZ Name, uint8_t Binding, uint8_t StOther,
uint8_t Type)
: Symbol(UndefinedKind, File, Name, Binding, StOther, Type) {}
static bool classof(const Symbol *S) { return S->kind() == UndefinedKind; }
};
class SharedSymbol : public Symbol {
public:
static bool classof(const Symbol *S) { return S->kind() == SharedKind; }
SharedSymbol(InputFile &File, StringRef Name, uint8_t Binding,
uint8_t StOther, uint8_t Type, uint64_t Value, uint64_t Size,
uint32_t Alignment, uint32_t VerdefIndex)
: Symbol(SharedKind, &File, Name, Binding, StOther, Type),
Alignment(Alignment), Value(Value), Size(Size) {
this->VerdefIndex = VerdefIndex;
// GNU ifunc is a mechanism to allow user-supplied functions to
// resolve PLT slot values at load-time. This is contrary to the
// regular symbol resolution scheme in which symbols are resolved just
// by name. Using this hook, you can program how symbols are solved
// for you program. For example, you can make "memcpy" to be resolved
// to a SSE-enabled version of memcpy only when a machine running the
// program supports the SSE instruction set.
//
// Naturally, such symbols should always be called through their PLT
// slots. What GNU ifunc symbols point to are resolver functions, and
// calling them directly doesn't make sense (unless you are writing a
// loader).
//
// For DSO symbols, we always call them through PLT slots anyway.
// So there's no difference between GNU ifunc and regular function
// symbols if they are in DSOs. So we can handle GNU_IFUNC as FUNC.
if (this->Type == llvm::ELF::STT_GNU_IFUNC)
this->Type = llvm::ELF::STT_FUNC;
}
template <class ELFT> SharedFile<ELFT> &getFile() const {
return *cast<SharedFile<ELFT>>(File);
}
uint32_t Alignment;
uint64_t Value; // st_value
uint64_t Size; // st_size
};
// LazyArchive and LazyObject represent a symbols that is not yet in the link,
// but we know where to find it if needed. If the resolver finds both Undefined
// and Lazy for the same name, it will ask the Lazy to load a file.
//
// A special complication is the handling of weak undefined symbols. They should
// not load a file, but we have to remember we have seen both the weak undefined
// and the lazy. We represent that with a lazy symbol with a weak binding. This
// means that code looking for undefined symbols normally also has to take lazy
// symbols into consideration.
// This class represents a symbol defined in an archive file. It is
// created from an archive file header, and it knows how to load an
// object file from an archive to replace itself with a defined
// symbol.
class LazyArchive : public Symbol {
public:
LazyArchive(InputFile &File, uint8_t Type,
const llvm::object::Archive::Symbol S)
: Symbol(LazyArchiveKind, &File, S.getName(), llvm::ELF::STB_GLOBAL,
llvm::ELF::STV_DEFAULT, Type),
Sym(S) {}
static bool classof(const Symbol *S) { return S->kind() == LazyArchiveKind; }
InputFile *fetch();
MemoryBufferRef getMemberBuffer();
private:
const llvm::object::Archive::Symbol Sym;
};
// LazyObject symbols represents symbols in object files between
// --start-lib and --end-lib options.
class LazyObject : public Symbol {
public:
LazyObject(InputFile &File, uint8_t Type, StringRef Name)
: Symbol(LazyObjectKind, &File, Name, llvm::ELF::STB_GLOBAL,
llvm::ELF::STV_DEFAULT, Type) {}
static bool classof(const Symbol *S) { return S->kind() == LazyObjectKind; }
};
// Some linker-generated symbols need to be created as
// Defined symbols.
struct ElfSym {
// __bss_start
static Defined *Bss;
// etext and _etext
static Defined *Etext1;
static Defined *Etext2;
// edata and _edata
static Defined *Edata1;
static Defined *Edata2;
// end and _end
static Defined *End1;
static Defined *End2;
// The _GLOBAL_OFFSET_TABLE_ symbol is defined by target convention to
// be at some offset from the base of the .got section, usually 0 or
// the end of the .got.
static Defined *GlobalOffsetTable;
// _gp, _gp_disp and __gnu_local_gp symbols. Only for MIPS.
static Defined *MipsGp;
static Defined *MipsGpDisp;
static Defined *MipsLocalGp;
// __rel{,a}_iplt_{start,end} symbols.
static Defined *RelaIpltStart;
static Defined *RelaIpltEnd;
};
// A buffer class that is large enough to hold any Symbol-derived
// object. We allocate memory using this class and instantiate a symbol
// using the placement new.
union SymbolUnion {
alignas(Defined) char A[sizeof(Defined)];
alignas(Undefined) char C[sizeof(Undefined)];
alignas(SharedSymbol) char D[sizeof(SharedSymbol)];
alignas(LazyArchive) char E[sizeof(LazyArchive)];
alignas(LazyObject) char F[sizeof(LazyObject)];
};
void printTraceSymbol(Symbol *Sym);
template <typename T, typename... ArgT>
void replaceSymbol(Symbol *S, ArgT &&... Arg) {
using llvm::ELF::STT_TLS;
static_assert(std::is_trivially_destructible<T>(),
"Symbol types must be trivially destructible");
static_assert(sizeof(T) <= sizeof(SymbolUnion), "SymbolUnion too small");
static_assert(alignof(T) <= alignof(SymbolUnion),
"SymbolUnion not aligned enough");
assert(static_cast<Symbol *>(static_cast<T *>(nullptr)) == nullptr &&
"Not a Symbol");
Symbol Sym = *S;
new (S) T(std::forward<ArgT>(Arg)...);
S->VersionId = Sym.VersionId;
S->Visibility = Sym.Visibility;
S->IsUsedInRegularObj = Sym.IsUsedInRegularObj;
S->ExportDynamic = Sym.ExportDynamic;
S->CanInline = Sym.CanInline;
S->Traced = Sym.Traced;
S->ScriptDefined = Sym.ScriptDefined;
// Symbols representing thread-local variables must be referenced by
// TLS-aware relocations, and non-TLS symbols must be reference by
// non-TLS relocations, so there's a clear distinction between TLS
// and non-TLS symbols. It is an error if the same symbol is defined
// as a TLS symbol in one file and as a non-TLS symbol in other file.
bool TlsMismatch = (Sym.Type == STT_TLS && S->Type != STT_TLS) ||
(Sym.Type != STT_TLS && S->Type == STT_TLS);
if (Sym.SymbolKind != Symbol::PlaceholderKind && TlsMismatch && !Sym.isLazy())
error("TLS attribute mismatch: " + toString(Sym) + "\n>>> defined in " +
toString(Sym.File) + "\n>>> defined in " + toString(S->File));
// Print out a log message if --trace-symbol was specified.
// This is for debugging.
if (S->Traced)
printTraceSymbol(S);
}
void maybeWarnUnorderableSymbol(const Symbol *Sym);
} // namespace elf
} // namespace lld
#endif
Index: head/contrib/llvm/tools/lld/ELF/SyntheticSections.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/SyntheticSections.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/SyntheticSections.cpp (revision 350467)
@@ -1,3233 +1,3230 @@
//===- SyntheticSections.cpp ----------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains linker-synthesized sections. Currently,
// synthetic sections are created either output sections or input sections,
// but we are rewriting code so that all synthetic sections are created as
// input sections.
//
//===----------------------------------------------------------------------===//
#include "SyntheticSections.h"
#include "Bits.h"
#include "Config.h"
#include "InputFiles.h"
#include "LinkerScript.h"
#include "OutputSections.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "Target.h"
#include "Writer.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "lld/Common/Threads.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/SetOperations.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/BinaryFormat/Dwarf.h"
#include "llvm/DebugInfo/DWARF/DWARFDebugPubTable.h"
#include "llvm/Object/ELFObjectFile.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MD5.h"
#include "llvm/Support/RandomNumberGenerator.h"
#include "llvm/Support/SHA1.h"
#include "llvm/Support/xxhash.h"
#include <cstdlib>
#include <thread>
using namespace llvm;
using namespace llvm::dwarf;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::support;
using namespace lld;
using namespace lld::elf;
using llvm::support::endian::read32le;
using llvm::support::endian::write32le;
using llvm::support::endian::write64le;
constexpr size_t MergeNoTailSection::NumShards;
// Returns an LLD version string.
static ArrayRef<uint8_t> getVersion() {
// Check LLD_VERSION first for ease of testing.
// You can get consistent output by using the environment variable.
// This is only for testing.
StringRef S = getenv("LLD_VERSION");
if (S.empty())
S = Saver.save(Twine("Linker: ") + getLLDVersion());
// +1 to include the terminating '\0'.
return {(const uint8_t *)S.data(), S.size() + 1};
}
// Creates a .comment section containing LLD version info.
// With this feature, you can identify LLD-generated binaries easily
// by "readelf --string-dump .comment <file>".
// The returned object is a mergeable string section.
MergeInputSection *elf::createCommentSection() {
return make<MergeInputSection>(SHF_MERGE | SHF_STRINGS, SHT_PROGBITS, 1,
getVersion(), ".comment");
}
// .MIPS.abiflags section.
template <class ELFT>
MipsAbiFlagsSection<ELFT>::MipsAbiFlagsSection(Elf_Mips_ABIFlags Flags)
: SyntheticSection(SHF_ALLOC, SHT_MIPS_ABIFLAGS, 8, ".MIPS.abiflags"),
Flags(Flags) {
this->Entsize = sizeof(Elf_Mips_ABIFlags);
}
template <class ELFT> void MipsAbiFlagsSection<ELFT>::writeTo(uint8_t *Buf) {
memcpy(Buf, &Flags, sizeof(Flags));
}
template <class ELFT>
MipsAbiFlagsSection<ELFT> *MipsAbiFlagsSection<ELFT>::create() {
Elf_Mips_ABIFlags Flags = {};
bool Create = false;
for (InputSectionBase *Sec : InputSections) {
if (Sec->Type != SHT_MIPS_ABIFLAGS)
continue;
Sec->Live = false;
Create = true;
std::string Filename = toString(Sec->File);
const size_t Size = Sec->data().size();
// Older version of BFD (such as the default FreeBSD linker) concatenate
// .MIPS.abiflags instead of merging. To allow for this case (or potential
// zero padding) we ignore everything after the first Elf_Mips_ABIFlags
if (Size < sizeof(Elf_Mips_ABIFlags)) {
error(Filename + ": invalid size of .MIPS.abiflags section: got " +
Twine(Size) + " instead of " + Twine(sizeof(Elf_Mips_ABIFlags)));
return nullptr;
}
auto *S = reinterpret_cast<const Elf_Mips_ABIFlags *>(Sec->data().data());
if (S->version != 0) {
error(Filename + ": unexpected .MIPS.abiflags version " +
Twine(S->version));
return nullptr;
}
// LLD checks ISA compatibility in calcMipsEFlags(). Here we just
// select the highest number of ISA/Rev/Ext.
Flags.isa_level = std::max(Flags.isa_level, S->isa_level);
Flags.isa_rev = std::max(Flags.isa_rev, S->isa_rev);
Flags.isa_ext = std::max(Flags.isa_ext, S->isa_ext);
Flags.gpr_size = std::max(Flags.gpr_size, S->gpr_size);
Flags.cpr1_size = std::max(Flags.cpr1_size, S->cpr1_size);
Flags.cpr2_size = std::max(Flags.cpr2_size, S->cpr2_size);
Flags.ases |= S->ases;
Flags.flags1 |= S->flags1;
Flags.flags2 |= S->flags2;
Flags.fp_abi = elf::getMipsFpAbiFlag(Flags.fp_abi, S->fp_abi, Filename);
};
if (Create)
return make<MipsAbiFlagsSection<ELFT>>(Flags);
return nullptr;
}
// .MIPS.options section.
template <class ELFT>
MipsOptionsSection<ELFT>::MipsOptionsSection(Elf_Mips_RegInfo Reginfo)
: SyntheticSection(SHF_ALLOC, SHT_MIPS_OPTIONS, 8, ".MIPS.options"),
Reginfo(Reginfo) {
this->Entsize = sizeof(Elf_Mips_Options) + sizeof(Elf_Mips_RegInfo);
}
template <class ELFT> void MipsOptionsSection<ELFT>::writeTo(uint8_t *Buf) {
auto *Options = reinterpret_cast<Elf_Mips_Options *>(Buf);
Options->kind = ODK_REGINFO;
Options->size = getSize();
if (!Config->Relocatable)
Reginfo.ri_gp_value = In.MipsGot->getGp();
memcpy(Buf + sizeof(Elf_Mips_Options), &Reginfo, sizeof(Reginfo));
}
template <class ELFT>
MipsOptionsSection<ELFT> *MipsOptionsSection<ELFT>::create() {
// N64 ABI only.
if (!ELFT::Is64Bits)
return nullptr;
std::vector<InputSectionBase *> Sections;
for (InputSectionBase *Sec : InputSections)
if (Sec->Type == SHT_MIPS_OPTIONS)
Sections.push_back(Sec);
if (Sections.empty())
return nullptr;
Elf_Mips_RegInfo Reginfo = {};
for (InputSectionBase *Sec : Sections) {
Sec->Live = false;
std::string Filename = toString(Sec->File);
ArrayRef<uint8_t> D = Sec->data();
while (!D.empty()) {
if (D.size() < sizeof(Elf_Mips_Options)) {
error(Filename + ": invalid size of .MIPS.options section");
break;
}
auto *Opt = reinterpret_cast<const Elf_Mips_Options *>(D.data());
if (Opt->kind == ODK_REGINFO) {
Reginfo.ri_gprmask |= Opt->getRegInfo().ri_gprmask;
Sec->getFile<ELFT>()->MipsGp0 = Opt->getRegInfo().ri_gp_value;
break;
}
if (!Opt->size)
fatal(Filename + ": zero option descriptor size");
D = D.slice(Opt->size);
}
};
return make<MipsOptionsSection<ELFT>>(Reginfo);
}
// MIPS .reginfo section.
template <class ELFT>
MipsReginfoSection<ELFT>::MipsReginfoSection(Elf_Mips_RegInfo Reginfo)
: SyntheticSection(SHF_ALLOC, SHT_MIPS_REGINFO, 4, ".reginfo"),
Reginfo(Reginfo) {
this->Entsize = sizeof(Elf_Mips_RegInfo);
}
template <class ELFT> void MipsReginfoSection<ELFT>::writeTo(uint8_t *Buf) {
if (!Config->Relocatable)
Reginfo.ri_gp_value = In.MipsGot->getGp();
memcpy(Buf, &Reginfo, sizeof(Reginfo));
}
template <class ELFT>
MipsReginfoSection<ELFT> *MipsReginfoSection<ELFT>::create() {
// Section should be alive for O32 and N32 ABIs only.
if (ELFT::Is64Bits)
return nullptr;
std::vector<InputSectionBase *> Sections;
for (InputSectionBase *Sec : InputSections)
if (Sec->Type == SHT_MIPS_REGINFO)
Sections.push_back(Sec);
if (Sections.empty())
return nullptr;
Elf_Mips_RegInfo Reginfo = {};
for (InputSectionBase *Sec : Sections) {
Sec->Live = false;
if (Sec->data().size() != sizeof(Elf_Mips_RegInfo)) {
error(toString(Sec->File) + ": invalid size of .reginfo section");
return nullptr;
}
auto *R = reinterpret_cast<const Elf_Mips_RegInfo *>(Sec->data().data());
Reginfo.ri_gprmask |= R->ri_gprmask;
Sec->getFile<ELFT>()->MipsGp0 = R->ri_gp_value;
};
return make<MipsReginfoSection<ELFT>>(Reginfo);
}
InputSection *elf::createInterpSection() {
// StringSaver guarantees that the returned string ends with '\0'.
StringRef S = Saver.save(Config->DynamicLinker);
ArrayRef<uint8_t> Contents = {(const uint8_t *)S.data(), S.size() + 1};
auto *Sec = make<InputSection>(nullptr, SHF_ALLOC, SHT_PROGBITS, 1, Contents,
".interp");
Sec->Live = true;
return Sec;
}
Defined *elf::addSyntheticLocal(StringRef Name, uint8_t Type, uint64_t Value,
uint64_t Size, InputSectionBase &Section) {
auto *S = make<Defined>(Section.File, Name, STB_LOCAL, STV_DEFAULT, Type,
Value, Size, &Section);
if (In.SymTab)
In.SymTab->addSymbol(S);
return S;
}
static size_t getHashSize() {
switch (Config->BuildId) {
case BuildIdKind::Fast:
return 8;
case BuildIdKind::Md5:
case BuildIdKind::Uuid:
return 16;
case BuildIdKind::Sha1:
return 20;
case BuildIdKind::Hexstring:
return Config->BuildIdVector.size();
default:
llvm_unreachable("unknown BuildIdKind");
}
}
BuildIdSection::BuildIdSection()
: SyntheticSection(SHF_ALLOC, SHT_NOTE, 4, ".note.gnu.build-id"),
HashSize(getHashSize()) {}
void BuildIdSection::writeTo(uint8_t *Buf) {
write32(Buf, 4); // Name size
write32(Buf + 4, HashSize); // Content size
write32(Buf + 8, NT_GNU_BUILD_ID); // Type
memcpy(Buf + 12, "GNU", 4); // Name string
HashBuf = Buf + 16;
}
// Split one uint8 array into small pieces of uint8 arrays.
static std::vector<ArrayRef<uint8_t>> split(ArrayRef<uint8_t> Arr,
size_t ChunkSize) {
std::vector<ArrayRef<uint8_t>> Ret;
while (Arr.size() > ChunkSize) {
Ret.push_back(Arr.take_front(ChunkSize));
Arr = Arr.drop_front(ChunkSize);
}
if (!Arr.empty())
Ret.push_back(Arr);
return Ret;
}
// Computes a hash value of Data using a given hash function.
// In order to utilize multiple cores, we first split data into 1MB
// chunks, compute a hash for each chunk, and then compute a hash value
// of the hash values.
void BuildIdSection::computeHash(
llvm::ArrayRef<uint8_t> Data,
std::function<void(uint8_t *Dest, ArrayRef<uint8_t> Arr)> HashFn) {
std::vector<ArrayRef<uint8_t>> Chunks = split(Data, 1024 * 1024);
std::vector<uint8_t> Hashes(Chunks.size() * HashSize);
// Compute hash values.
parallelForEachN(0, Chunks.size(), [&](size_t I) {
HashFn(Hashes.data() + I * HashSize, Chunks[I]);
});
// Write to the final output buffer.
HashFn(HashBuf, Hashes);
}
BssSection::BssSection(StringRef Name, uint64_t Size, uint32_t Alignment)
: SyntheticSection(SHF_ALLOC | SHF_WRITE, SHT_NOBITS, Alignment, Name) {
this->Bss = true;
this->Size = Size;
}
void BuildIdSection::writeBuildId(ArrayRef<uint8_t> Buf) {
switch (Config->BuildId) {
case BuildIdKind::Fast:
computeHash(Buf, [](uint8_t *Dest, ArrayRef<uint8_t> Arr) {
write64le(Dest, xxHash64(Arr));
});
break;
case BuildIdKind::Md5:
computeHash(Buf, [](uint8_t *Dest, ArrayRef<uint8_t> Arr) {
memcpy(Dest, MD5::hash(Arr).data(), 16);
});
break;
case BuildIdKind::Sha1:
computeHash(Buf, [](uint8_t *Dest, ArrayRef<uint8_t> Arr) {
memcpy(Dest, SHA1::hash(Arr).data(), 20);
});
break;
case BuildIdKind::Uuid:
if (auto EC = getRandomBytes(HashBuf, HashSize))
error("entropy source failure: " + EC.message());
break;
case BuildIdKind::Hexstring:
memcpy(HashBuf, Config->BuildIdVector.data(), Config->BuildIdVector.size());
break;
default:
llvm_unreachable("unknown BuildIdKind");
}
}
EhFrameSection::EhFrameSection()
: SyntheticSection(SHF_ALLOC, SHT_PROGBITS, 1, ".eh_frame") {}
// Search for an existing CIE record or create a new one.
// CIE records from input object files are uniquified by their contents
// and where their relocations point to.
template <class ELFT, class RelTy>
CieRecord *EhFrameSection::addCie(EhSectionPiece &Cie, ArrayRef<RelTy> Rels) {
Symbol *Personality = nullptr;
unsigned FirstRelI = Cie.FirstRelocation;
if (FirstRelI != (unsigned)-1)
Personality =
&Cie.Sec->template getFile<ELFT>()->getRelocTargetSym(Rels[FirstRelI]);
// Search for an existing CIE by CIE contents/relocation target pair.
CieRecord *&Rec = CieMap[{Cie.data(), Personality}];
// If not found, create a new one.
if (!Rec) {
Rec = make<CieRecord>();
Rec->Cie = &Cie;
CieRecords.push_back(Rec);
}
return Rec;
}
// There is one FDE per function. Returns true if a given FDE
// points to a live function.
template <class ELFT, class RelTy>
bool EhFrameSection::isFdeLive(EhSectionPiece &Fde, ArrayRef<RelTy> Rels) {
auto *Sec = cast<EhInputSection>(Fde.Sec);
unsigned FirstRelI = Fde.FirstRelocation;
// An FDE should point to some function because FDEs are to describe
// functions. That's however not always the case due to an issue of
// ld.gold with -r. ld.gold may discard only functions and leave their
// corresponding FDEs, which results in creating bad .eh_frame sections.
// To deal with that, we ignore such FDEs.
if (FirstRelI == (unsigned)-1)
return false;
const RelTy &Rel = Rels[FirstRelI];
Symbol &B = Sec->template getFile<ELFT>()->getRelocTargetSym(Rel);
// FDEs for garbage-collected or merged-by-ICF sections are dead.
if (auto *D = dyn_cast<Defined>(&B))
if (SectionBase *Sec = D->Section)
return Sec->Live;
return false;
}
// .eh_frame is a sequence of CIE or FDE records. In general, there
// is one CIE record per input object file which is followed by
// a list of FDEs. This function searches an existing CIE or create a new
// one and associates FDEs to the CIE.
template <class ELFT, class RelTy>
void EhFrameSection::addSectionAux(EhInputSection *Sec, ArrayRef<RelTy> Rels) {
OffsetToCie.clear();
for (EhSectionPiece &Piece : Sec->Pieces) {
// The empty record is the end marker.
if (Piece.Size == 4)
return;
size_t Offset = Piece.InputOff;
uint32_t ID = read32(Piece.data().data() + 4);
if (ID == 0) {
OffsetToCie[Offset] = addCie<ELFT>(Piece, Rels);
continue;
}
uint32_t CieOffset = Offset + 4 - ID;
CieRecord *Rec = OffsetToCie[CieOffset];
if (!Rec)
fatal(toString(Sec) + ": invalid CIE reference");
if (!isFdeLive<ELFT>(Piece, Rels))
continue;
Rec->Fdes.push_back(&Piece);
NumFdes++;
}
}
template <class ELFT> void EhFrameSection::addSection(InputSectionBase *C) {
auto *Sec = cast<EhInputSection>(C);
Sec->Parent = this;
Alignment = std::max(Alignment, Sec->Alignment);
Sections.push_back(Sec);
for (auto *DS : Sec->DependentSections)
DependentSections.push_back(DS);
if (Sec->Pieces.empty())
return;
if (Sec->AreRelocsRela)
addSectionAux<ELFT>(Sec, Sec->template relas<ELFT>());
else
addSectionAux<ELFT>(Sec, Sec->template rels<ELFT>());
}
static void writeCieFde(uint8_t *Buf, ArrayRef<uint8_t> D) {
memcpy(Buf, D.data(), D.size());
size_t Aligned = alignTo(D.size(), Config->Wordsize);
// Zero-clear trailing padding if it exists.
memset(Buf + D.size(), 0, Aligned - D.size());
// Fix the size field. -4 since size does not include the size field itself.
write32(Buf, Aligned - 4);
}
void EhFrameSection::finalizeContents() {
assert(!this->Size); // Not finalized.
size_t Off = 0;
for (CieRecord *Rec : CieRecords) {
Rec->Cie->OutputOff = Off;
Off += alignTo(Rec->Cie->Size, Config->Wordsize);
for (EhSectionPiece *Fde : Rec->Fdes) {
Fde->OutputOff = Off;
Off += alignTo(Fde->Size, Config->Wordsize);
}
}
// The LSB standard does not allow a .eh_frame section with zero
// Call Frame Information records. glibc unwind-dw2-fde.c
// classify_object_over_fdes expects there is a CIE record length 0 as a
// terminator. Thus we add one unconditionally.
Off += 4;
this->Size = Off;
}
// Returns data for .eh_frame_hdr. .eh_frame_hdr is a binary search table
// to get an FDE from an address to which FDE is applied. This function
// returns a list of such pairs.
std::vector<EhFrameSection::FdeData> EhFrameSection::getFdeData() const {
uint8_t *Buf = getParent()->Loc + OutSecOff;
std::vector<FdeData> Ret;
uint64_t VA = In.EhFrameHdr->getVA();
for (CieRecord *Rec : CieRecords) {
uint8_t Enc = getFdeEncoding(Rec->Cie);
for (EhSectionPiece *Fde : Rec->Fdes) {
uint64_t Pc = getFdePc(Buf, Fde->OutputOff, Enc);
uint64_t FdeVA = getParent()->Addr + Fde->OutputOff;
if (!isInt<32>(Pc - VA))
fatal(toString(Fde->Sec) + ": PC offset is too large: 0x" +
Twine::utohexstr(Pc - VA));
Ret.push_back({uint32_t(Pc - VA), uint32_t(FdeVA - VA)});
}
}
// Sort the FDE list by their PC and uniqueify. Usually there is only
// one FDE for a PC (i.e. function), but if ICF merges two functions
// into one, there can be more than one FDEs pointing to the address.
auto Less = [](const FdeData &A, const FdeData &B) {
return A.PcRel < B.PcRel;
};
std::stable_sort(Ret.begin(), Ret.end(), Less);
auto Eq = [](const FdeData &A, const FdeData &B) {
return A.PcRel == B.PcRel;
};
Ret.erase(std::unique(Ret.begin(), Ret.end(), Eq), Ret.end());
return Ret;
}
static uint64_t readFdeAddr(uint8_t *Buf, int Size) {
switch (Size) {
case DW_EH_PE_udata2:
return read16(Buf);
case DW_EH_PE_sdata2:
return (int16_t)read16(Buf);
case DW_EH_PE_udata4:
return read32(Buf);
case DW_EH_PE_sdata4:
return (int32_t)read32(Buf);
case DW_EH_PE_udata8:
case DW_EH_PE_sdata8:
return read64(Buf);
case DW_EH_PE_absptr:
return readUint(Buf);
}
fatal("unknown FDE size encoding");
}
// Returns the VA to which a given FDE (on a mmap'ed buffer) is applied to.
// We need it to create .eh_frame_hdr section.
uint64_t EhFrameSection::getFdePc(uint8_t *Buf, size_t FdeOff,
uint8_t Enc) const {
// The starting address to which this FDE applies is
// stored at FDE + 8 byte.
size_t Off = FdeOff + 8;
uint64_t Addr = readFdeAddr(Buf + Off, Enc & 0xf);
if ((Enc & 0x70) == DW_EH_PE_absptr)
return Addr;
if ((Enc & 0x70) == DW_EH_PE_pcrel)
return Addr + getParent()->Addr + Off;
fatal("unknown FDE size relative encoding");
}
void EhFrameSection::writeTo(uint8_t *Buf) {
// Write CIE and FDE records.
for (CieRecord *Rec : CieRecords) {
size_t CieOffset = Rec->Cie->OutputOff;
writeCieFde(Buf + CieOffset, Rec->Cie->data());
for (EhSectionPiece *Fde : Rec->Fdes) {
size_t Off = Fde->OutputOff;
writeCieFde(Buf + Off, Fde->data());
// FDE's second word should have the offset to an associated CIE.
// Write it.
write32(Buf + Off + 4, Off + 4 - CieOffset);
}
}
// Apply relocations. .eh_frame section contents are not contiguous
// in the output buffer, but relocateAlloc() still works because
// getOffset() takes care of discontiguous section pieces.
for (EhInputSection *S : Sections)
S->relocateAlloc(Buf, nullptr);
}
GotSection::GotSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE, SHT_PROGBITS,
Target->GotEntrySize, ".got") {
// PPC64 saves the ElfSym::GlobalOffsetTable .TOC. as the first entry in the
// .got. If there are no references to .TOC. in the symbol table,
// ElfSym::GlobalOffsetTable will not be defined and we won't need to save
// .TOC. in the .got. When it is defined, we increase NumEntries by the number
// of entries used to emit ElfSym::GlobalOffsetTable.
if (ElfSym::GlobalOffsetTable && !Target->GotBaseSymInGotPlt)
NumEntries += Target->GotHeaderEntriesNum;
}
void GotSection::addEntry(Symbol &Sym) {
Sym.GotIndex = NumEntries;
++NumEntries;
}
bool GotSection::addDynTlsEntry(Symbol &Sym) {
if (Sym.GlobalDynIndex != -1U)
return false;
Sym.GlobalDynIndex = NumEntries;
// Global Dynamic TLS entries take two GOT slots.
NumEntries += 2;
return true;
}
// Reserves TLS entries for a TLS module ID and a TLS block offset.
// In total it takes two GOT slots.
bool GotSection::addTlsIndex() {
if (TlsIndexOff != uint32_t(-1))
return false;
TlsIndexOff = NumEntries * Config->Wordsize;
NumEntries += 2;
return true;
}
uint64_t GotSection::getGlobalDynAddr(const Symbol &B) const {
return this->getVA() + B.GlobalDynIndex * Config->Wordsize;
}
uint64_t GotSection::getGlobalDynOffset(const Symbol &B) const {
return B.GlobalDynIndex * Config->Wordsize;
}
void GotSection::finalizeContents() {
Size = NumEntries * Config->Wordsize;
}
bool GotSection::empty() const {
// We need to emit a GOT even if it's empty if there's a relocation that is
// relative to GOT(such as GOTOFFREL) or there's a symbol that points to a GOT
// (i.e. _GLOBAL_OFFSET_TABLE_) that the target defines relative to the .got.
return NumEntries == 0 && !HasGotOffRel &&
!(ElfSym::GlobalOffsetTable && !Target->GotBaseSymInGotPlt);
}
void GotSection::writeTo(uint8_t *Buf) {
// Buf points to the start of this section's buffer,
// whereas InputSectionBase::relocateAlloc() expects its argument
// to point to the start of the output section.
Target->writeGotHeader(Buf);
relocateAlloc(Buf - OutSecOff, Buf - OutSecOff + Size);
}
static uint64_t getMipsPageAddr(uint64_t Addr) {
return (Addr + 0x8000) & ~0xffff;
}
static uint64_t getMipsPageCount(uint64_t Size) {
return (Size + 0xfffe) / 0xffff + 1;
}
MipsGotSection::MipsGotSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE | SHF_MIPS_GPREL, SHT_PROGBITS, 16,
".got") {}
void MipsGotSection::addEntry(InputFile &File, Symbol &Sym, int64_t Addend,
RelExpr Expr) {
FileGot &G = getGot(File);
if (Expr == R_MIPS_GOT_LOCAL_PAGE) {
if (const OutputSection *OS = Sym.getOutputSection())
G.PagesMap.insert({OS, {}});
else
G.Local16.insert({{nullptr, getMipsPageAddr(Sym.getVA(Addend))}, 0});
} else if (Sym.isTls())
G.Tls.insert({&Sym, 0});
else if (Sym.IsPreemptible && Expr == R_ABS)
G.Relocs.insert({&Sym, 0});
else if (Sym.IsPreemptible)
G.Global.insert({&Sym, 0});
else if (Expr == R_MIPS_GOT_OFF32)
G.Local32.insert({{&Sym, Addend}, 0});
else
G.Local16.insert({{&Sym, Addend}, 0});
}
void MipsGotSection::addDynTlsEntry(InputFile &File, Symbol &Sym) {
getGot(File).DynTlsSymbols.insert({&Sym, 0});
}
void MipsGotSection::addTlsIndex(InputFile &File) {
getGot(File).DynTlsSymbols.insert({nullptr, 0});
}
size_t MipsGotSection::FileGot::getEntriesNum() const {
return getPageEntriesNum() + Local16.size() + Global.size() + Relocs.size() +
Tls.size() + DynTlsSymbols.size() * 2;
}
size_t MipsGotSection::FileGot::getPageEntriesNum() const {
size_t Num = 0;
for (const std::pair<const OutputSection *, FileGot::PageBlock> &P : PagesMap)
Num += P.second.Count;
return Num;
}
size_t MipsGotSection::FileGot::getIndexedEntriesNum() const {
size_t Count = getPageEntriesNum() + Local16.size() + Global.size();
// If there are relocation-only entries in the GOT, TLS entries
// are allocated after them. TLS entries should be addressable
// by 16-bit index so count both reloc-only and TLS entries.
if (!Tls.empty() || !DynTlsSymbols.empty())
Count += Relocs.size() + Tls.size() + DynTlsSymbols.size() * 2;
return Count;
}
MipsGotSection::FileGot &MipsGotSection::getGot(InputFile &F) {
if (!F.MipsGotIndex.hasValue()) {
Gots.emplace_back();
Gots.back().File = &F;
F.MipsGotIndex = Gots.size() - 1;
}
return Gots[*F.MipsGotIndex];
}
uint64_t MipsGotSection::getPageEntryOffset(const InputFile *F,
const Symbol &Sym,
int64_t Addend) const {
const FileGot &G = Gots[*F->MipsGotIndex];
uint64_t Index = 0;
if (const OutputSection *OutSec = Sym.getOutputSection()) {
uint64_t SecAddr = getMipsPageAddr(OutSec->Addr);
uint64_t SymAddr = getMipsPageAddr(Sym.getVA(Addend));
Index = G.PagesMap.lookup(OutSec).FirstIndex + (SymAddr - SecAddr) / 0xffff;
} else {
Index = G.Local16.lookup({nullptr, getMipsPageAddr(Sym.getVA(Addend))});
}
return Index * Config->Wordsize;
}
uint64_t MipsGotSection::getSymEntryOffset(const InputFile *F, const Symbol &S,
int64_t Addend) const {
const FileGot &G = Gots[*F->MipsGotIndex];
Symbol *Sym = const_cast<Symbol *>(&S);
if (Sym->isTls())
return G.Tls.lookup(Sym) * Config->Wordsize;
if (Sym->IsPreemptible)
return G.Global.lookup(Sym) * Config->Wordsize;
return G.Local16.lookup({Sym, Addend}) * Config->Wordsize;
}
uint64_t MipsGotSection::getTlsIndexOffset(const InputFile *F) const {
const FileGot &G = Gots[*F->MipsGotIndex];
return G.DynTlsSymbols.lookup(nullptr) * Config->Wordsize;
}
uint64_t MipsGotSection::getGlobalDynOffset(const InputFile *F,
const Symbol &S) const {
const FileGot &G = Gots[*F->MipsGotIndex];
Symbol *Sym = const_cast<Symbol *>(&S);
return G.DynTlsSymbols.lookup(Sym) * Config->Wordsize;
}
const Symbol *MipsGotSection::getFirstGlobalEntry() const {
if (Gots.empty())
return nullptr;
const FileGot &PrimGot = Gots.front();
if (!PrimGot.Global.empty())
return PrimGot.Global.front().first;
if (!PrimGot.Relocs.empty())
return PrimGot.Relocs.front().first;
return nullptr;
}
unsigned MipsGotSection::getLocalEntriesNum() const {
if (Gots.empty())
return HeaderEntriesNum;
return HeaderEntriesNum + Gots.front().getPageEntriesNum() +
Gots.front().Local16.size();
}
bool MipsGotSection::tryMergeGots(FileGot &Dst, FileGot &Src, bool IsPrimary) {
FileGot Tmp = Dst;
set_union(Tmp.PagesMap, Src.PagesMap);
set_union(Tmp.Local16, Src.Local16);
set_union(Tmp.Global, Src.Global);
set_union(Tmp.Relocs, Src.Relocs);
set_union(Tmp.Tls, Src.Tls);
set_union(Tmp.DynTlsSymbols, Src.DynTlsSymbols);
size_t Count = IsPrimary ? HeaderEntriesNum : 0;
Count += Tmp.getIndexedEntriesNum();
if (Count * Config->Wordsize > Config->MipsGotSize)
return false;
std::swap(Tmp, Dst);
return true;
}
void MipsGotSection::finalizeContents() { updateAllocSize(); }
bool MipsGotSection::updateAllocSize() {
Size = HeaderEntriesNum * Config->Wordsize;
for (const FileGot &G : Gots)
Size += G.getEntriesNum() * Config->Wordsize;
return false;
}
template <class ELFT> void MipsGotSection::build() {
if (Gots.empty())
return;
std::vector<FileGot> MergedGots(1);
// For each GOT move non-preemptible symbols from the `Global`
// to `Local16` list. Preemptible symbol might become non-preemptible
// one if, for example, it gets a related copy relocation.
for (FileGot &Got : Gots) {
for (auto &P: Got.Global)
if (!P.first->IsPreemptible)
Got.Local16.insert({{P.first, 0}, 0});
Got.Global.remove_if([&](const std::pair<Symbol *, size_t> &P) {
return !P.first->IsPreemptible;
});
}
// For each GOT remove "reloc-only" entry if there is "global"
// entry for the same symbol. And add local entries which indexed
// using 32-bit value at the end of 16-bit entries.
for (FileGot &Got : Gots) {
Got.Relocs.remove_if([&](const std::pair<Symbol *, size_t> &P) {
return Got.Global.count(P.first);
});
set_union(Got.Local16, Got.Local32);
Got.Local32.clear();
}
// Evaluate number of "reloc-only" entries in the resulting GOT.
// To do that put all unique "reloc-only" and "global" entries
// from all GOTs to the future primary GOT.
FileGot *PrimGot = &MergedGots.front();
for (FileGot &Got : Gots) {
set_union(PrimGot->Relocs, Got.Global);
set_union(PrimGot->Relocs, Got.Relocs);
Got.Relocs.clear();
}
// Evaluate number of "page" entries in each GOT.
for (FileGot &Got : Gots) {
for (std::pair<const OutputSection *, FileGot::PageBlock> &P :
Got.PagesMap) {
const OutputSection *OS = P.first;
uint64_t SecSize = 0;
for (BaseCommand *Cmd : OS->SectionCommands) {
if (auto *ISD = dyn_cast<InputSectionDescription>(Cmd))
for (InputSection *IS : ISD->Sections) {
uint64_t Off = alignTo(SecSize, IS->Alignment);
SecSize = Off + IS->getSize();
}
}
P.second.Count = getMipsPageCount(SecSize);
}
}
// Merge GOTs. Try to join as much as possible GOTs but do not exceed
// maximum GOT size. At first, try to fill the primary GOT because
// the primary GOT can be accessed in the most effective way. If it
// is not possible, try to fill the last GOT in the list, and finally
// create a new GOT if both attempts failed.
for (FileGot &SrcGot : Gots) {
InputFile *File = SrcGot.File;
if (tryMergeGots(MergedGots.front(), SrcGot, true)) {
File->MipsGotIndex = 0;
} else {
// If this is the first time we failed to merge with the primary GOT,
// MergedGots.back() will also be the primary GOT. We must make sure not
// to try to merge again with IsPrimary=false, as otherwise, if the
// inputs are just right, we could allow the primary GOT to become 1 or 2
// words too big due to ignoring the header size.
if (MergedGots.size() == 1 ||
!tryMergeGots(MergedGots.back(), SrcGot, false)) {
MergedGots.emplace_back();
std::swap(MergedGots.back(), SrcGot);
}
File->MipsGotIndex = MergedGots.size() - 1;
}
}
std::swap(Gots, MergedGots);
// Reduce number of "reloc-only" entries in the primary GOT
// by substracting "global" entries exist in the primary GOT.
PrimGot = &Gots.front();
PrimGot->Relocs.remove_if([&](const std::pair<Symbol *, size_t> &P) {
return PrimGot->Global.count(P.first);
});
// Calculate indexes for each GOT entry.
size_t Index = HeaderEntriesNum;
for (FileGot &Got : Gots) {
Got.StartIndex = &Got == PrimGot ? 0 : Index;
for (std::pair<const OutputSection *, FileGot::PageBlock> &P :
Got.PagesMap) {
// For each output section referenced by GOT page relocations calculate
// and save into PagesMap an upper bound of MIPS GOT entries required
// to store page addresses of local symbols. We assume the worst case -
// each 64kb page of the output section has at least one GOT relocation
// against it. And take in account the case when the section intersects
// page boundaries.
P.second.FirstIndex = Index;
Index += P.second.Count;
}
for (auto &P: Got.Local16)
P.second = Index++;
for (auto &P: Got.Global)
P.second = Index++;
for (auto &P: Got.Relocs)
P.second = Index++;
for (auto &P: Got.Tls)
P.second = Index++;
for (auto &P: Got.DynTlsSymbols) {
P.second = Index;
Index += 2;
}
}
// Update Symbol::GotIndex field to use this
// value later in the `sortMipsSymbols` function.
for (auto &P : PrimGot->Global)
P.first->GotIndex = P.second;
for (auto &P : PrimGot->Relocs)
P.first->GotIndex = P.second;
// Create dynamic relocations.
for (FileGot &Got : Gots) {
// Create dynamic relocations for TLS entries.
for (std::pair<Symbol *, size_t> &P : Got.Tls) {
Symbol *S = P.first;
uint64_t Offset = P.second * Config->Wordsize;
if (S->IsPreemptible)
In.RelaDyn->addReloc(Target->TlsGotRel, this, Offset, S);
}
for (std::pair<Symbol *, size_t> &P : Got.DynTlsSymbols) {
Symbol *S = P.first;
uint64_t Offset = P.second * Config->Wordsize;
if (S == nullptr) {
if (!Config->Pic)
continue;
In.RelaDyn->addReloc(Target->TlsModuleIndexRel, this, Offset, S);
} else {
// When building a shared library we still need a dynamic relocation
// for the module index. Therefore only checking for
// S->IsPreemptible is not sufficient (this happens e.g. for
// thread-locals that have been marked as local through a linker script)
if (!S->IsPreemptible && !Config->Pic)
continue;
In.RelaDyn->addReloc(Target->TlsModuleIndexRel, this, Offset, S);
// However, we can skip writing the TLS offset reloc for non-preemptible
// symbols since it is known even in shared libraries
if (!S->IsPreemptible)
continue;
Offset += Config->Wordsize;
In.RelaDyn->addReloc(Target->TlsOffsetRel, this, Offset, S);
}
}
// Do not create dynamic relocations for non-TLS
// entries in the primary GOT.
if (&Got == PrimGot)
continue;
// Dynamic relocations for "global" entries.
for (const std::pair<Symbol *, size_t> &P : Got.Global) {
uint64_t Offset = P.second * Config->Wordsize;
In.RelaDyn->addReloc(Target->RelativeRel, this, Offset, P.first);
}
if (!Config->Pic)
continue;
// Dynamic relocations for "local" entries in case of PIC.
for (const std::pair<const OutputSection *, FileGot::PageBlock> &L :
Got.PagesMap) {
size_t PageCount = L.second.Count;
for (size_t PI = 0; PI < PageCount; ++PI) {
uint64_t Offset = (L.second.FirstIndex + PI) * Config->Wordsize;
In.RelaDyn->addReloc({Target->RelativeRel, this, Offset, L.first,
int64_t(PI * 0x10000)});
}
}
for (const std::pair<GotEntry, size_t> &P : Got.Local16) {
uint64_t Offset = P.second * Config->Wordsize;
In.RelaDyn->addReloc({Target->RelativeRel, this, Offset, true,
P.first.first, P.first.second});
}
}
}
bool MipsGotSection::empty() const {
// We add the .got section to the result for dynamic MIPS target because
// its address and properties are mentioned in the .dynamic section.
return Config->Relocatable;
}
uint64_t MipsGotSection::getGp(const InputFile *F) const {
// For files without related GOT or files refer a primary GOT
// returns "common" _gp value. For secondary GOTs calculate
// individual _gp values.
if (!F || !F->MipsGotIndex.hasValue() || *F->MipsGotIndex == 0)
return ElfSym::MipsGp->getVA(0);
return getVA() + Gots[*F->MipsGotIndex].StartIndex * Config->Wordsize +
0x7ff0;
}
void MipsGotSection::writeTo(uint8_t *Buf) {
// Set the MSB of the second GOT slot. This is not required by any
// MIPS ABI documentation, though.
//
// There is a comment in glibc saying that "The MSB of got[1] of a
// gnu object is set to identify gnu objects," and in GNU gold it
// says "the second entry will be used by some runtime loaders".
// But how this field is being used is unclear.
//
// We are not really willing to mimic other linkers behaviors
// without understanding why they do that, but because all files
// generated by GNU tools have this special GOT value, and because
// we've been doing this for years, it is probably a safe bet to
// keep doing this for now. We really need to revisit this to see
// if we had to do this.
writeUint(Buf + Config->Wordsize, (uint64_t)1 << (Config->Wordsize * 8 - 1));
for (const FileGot &G : Gots) {
auto Write = [&](size_t I, const Symbol *S, int64_t A) {
uint64_t VA = A;
if (S) {
VA = S->getVA(A);
if (S->StOther & STO_MIPS_MICROMIPS)
VA |= 1;
}
writeUint(Buf + I * Config->Wordsize, VA);
};
// Write 'page address' entries to the local part of the GOT.
for (const std::pair<const OutputSection *, FileGot::PageBlock> &L :
G.PagesMap) {
size_t PageCount = L.second.Count;
uint64_t FirstPageAddr = getMipsPageAddr(L.first->Addr);
for (size_t PI = 0; PI < PageCount; ++PI)
Write(L.second.FirstIndex + PI, nullptr, FirstPageAddr + PI * 0x10000);
}
// Local, global, TLS, reloc-only entries.
// If TLS entry has a corresponding dynamic relocations, leave it
// initialized by zero. Write down adjusted TLS symbol's values otherwise.
// To calculate the adjustments use offsets for thread-local storage.
// https://www.linux-mips.org/wiki/NPTL
for (const std::pair<GotEntry, size_t> &P : G.Local16)
Write(P.second, P.first.first, P.first.second);
// Write VA to the primary GOT only. For secondary GOTs that
// will be done by REL32 dynamic relocations.
if (&G == &Gots.front())
for (const std::pair<const Symbol *, size_t> &P : G.Global)
Write(P.second, P.first, 0);
for (const std::pair<Symbol *, size_t> &P : G.Relocs)
Write(P.second, P.first, 0);
for (const std::pair<Symbol *, size_t> &P : G.Tls)
Write(P.second, P.first, P.first->IsPreemptible ? 0 : -0x7000);
for (const std::pair<Symbol *, size_t> &P : G.DynTlsSymbols) {
if (P.first == nullptr && !Config->Pic)
Write(P.second, nullptr, 1);
else if (P.first && !P.first->IsPreemptible) {
// If we are emitting PIC code with relocations we mustn't write
// anything to the GOT here. When using Elf_Rel relocations the value
// one will be treated as an addend and will cause crashes at runtime
if (!Config->Pic)
Write(P.second, nullptr, 1);
Write(P.second + 1, P.first, -0x8000);
}
}
}
}
// On PowerPC the .plt section is used to hold the table of function addresses
// instead of the .got.plt, and the type is SHT_NOBITS similar to a .bss
// section. I don't know why we have a BSS style type for the section but it is
// consitent across both 64-bit PowerPC ABIs as well as the 32-bit PowerPC ABI.
GotPltSection::GotPltSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE,
Config->EMachine == EM_PPC64 ? SHT_NOBITS : SHT_PROGBITS,
Target->GotPltEntrySize,
Config->EMachine == EM_PPC64 ? ".plt" : ".got.plt") {}
void GotPltSection::addEntry(Symbol &Sym) {
assert(Sym.PltIndex == Entries.size());
Entries.push_back(&Sym);
}
size_t GotPltSection::getSize() const {
return (Target->GotPltHeaderEntriesNum + Entries.size()) *
Target->GotPltEntrySize;
}
void GotPltSection::writeTo(uint8_t *Buf) {
Target->writeGotPltHeader(Buf);
Buf += Target->GotPltHeaderEntriesNum * Target->GotPltEntrySize;
for (const Symbol *B : Entries) {
Target->writeGotPlt(Buf, *B);
Buf += Config->Wordsize;
}
}
bool GotPltSection::empty() const {
// We need to emit a GOT.PLT even if it's empty if there's a symbol that
// references the _GLOBAL_OFFSET_TABLE_ and the Target defines the symbol
// relative to the .got.plt section.
return Entries.empty() &&
!(ElfSym::GlobalOffsetTable && Target->GotBaseSymInGotPlt);
}
static StringRef getIgotPltName() {
// On ARM the IgotPltSection is part of the GotSection.
if (Config->EMachine == EM_ARM)
return ".got";
// On PowerPC64 the GotPltSection is renamed to '.plt' so the IgotPltSection
// needs to be named the same.
if (Config->EMachine == EM_PPC64)
return ".plt";
return ".got.plt";
}
// On PowerPC64 the GotPltSection type is SHT_NOBITS so we have to follow suit
// with the IgotPltSection.
IgotPltSection::IgotPltSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE,
Config->EMachine == EM_PPC64 ? SHT_NOBITS : SHT_PROGBITS,
Target->GotPltEntrySize, getIgotPltName()) {}
void IgotPltSection::addEntry(Symbol &Sym) {
- Sym.IsInIgot = true;
assert(Sym.PltIndex == Entries.size());
Entries.push_back(&Sym);
}
size_t IgotPltSection::getSize() const {
return Entries.size() * Target->GotPltEntrySize;
}
void IgotPltSection::writeTo(uint8_t *Buf) {
for (const Symbol *B : Entries) {
Target->writeIgotPlt(Buf, *B);
Buf += Config->Wordsize;
}
}
StringTableSection::StringTableSection(StringRef Name, bool Dynamic)
: SyntheticSection(Dynamic ? (uint64_t)SHF_ALLOC : 0, SHT_STRTAB, 1, Name),
Dynamic(Dynamic) {
// ELF string tables start with a NUL byte.
addString("");
}
// Adds a string to the string table. If HashIt is true we hash and check for
// duplicates. It is optional because the name of global symbols are already
// uniqued and hashing them again has a big cost for a small value: uniquing
// them with some other string that happens to be the same.
unsigned StringTableSection::addString(StringRef S, bool HashIt) {
if (HashIt) {
auto R = StringMap.insert(std::make_pair(S, this->Size));
if (!R.second)
return R.first->second;
}
unsigned Ret = this->Size;
this->Size = this->Size + S.size() + 1;
Strings.push_back(S);
return Ret;
}
void StringTableSection::writeTo(uint8_t *Buf) {
for (StringRef S : Strings) {
memcpy(Buf, S.data(), S.size());
Buf[S.size()] = '\0';
Buf += S.size() + 1;
}
}
// Returns the number of version definition entries. Because the first entry
// is for the version definition itself, it is the number of versioned symbols
// plus one. Note that we don't support multiple versions yet.
static unsigned getVerDefNum() { return Config->VersionDefinitions.size() + 1; }
template <class ELFT>
DynamicSection<ELFT>::DynamicSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE, SHT_DYNAMIC, Config->Wordsize,
".dynamic") {
this->Entsize = ELFT::Is64Bits ? 16 : 8;
// .dynamic section is not writable on MIPS and on Fuchsia OS
// which passes -z rodynamic.
// See "Special Section" in Chapter 4 in the following document:
// ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
if (Config->EMachine == EM_MIPS || Config->ZRodynamic)
this->Flags = SHF_ALLOC;
// Add strings to .dynstr early so that .dynstr's size will be
// fixed early.
for (StringRef S : Config->FilterList)
addInt(DT_FILTER, In.DynStrTab->addString(S));
for (StringRef S : Config->AuxiliaryList)
addInt(DT_AUXILIARY, In.DynStrTab->addString(S));
if (!Config->Rpath.empty())
addInt(Config->EnableNewDtags ? DT_RUNPATH : DT_RPATH,
In.DynStrTab->addString(Config->Rpath));
for (InputFile *File : SharedFiles) {
SharedFile<ELFT> *F = cast<SharedFile<ELFT>>(File);
if (F->IsNeeded)
addInt(DT_NEEDED, In.DynStrTab->addString(F->SoName));
}
if (!Config->SoName.empty())
addInt(DT_SONAME, In.DynStrTab->addString(Config->SoName));
}
template <class ELFT>
void DynamicSection<ELFT>::add(int32_t Tag, std::function<uint64_t()> Fn) {
Entries.push_back({Tag, Fn});
}
template <class ELFT>
void DynamicSection<ELFT>::addInt(int32_t Tag, uint64_t Val) {
Entries.push_back({Tag, [=] { return Val; }});
}
template <class ELFT>
void DynamicSection<ELFT>::addInSec(int32_t Tag, InputSection *Sec) {
Entries.push_back({Tag, [=] { return Sec->getVA(0); }});
}
template <class ELFT>
void DynamicSection<ELFT>::addInSecRelative(int32_t Tag, InputSection *Sec) {
size_t TagOffset = Entries.size() * Entsize;
Entries.push_back(
{Tag, [=] { return Sec->getVA(0) - (getVA() + TagOffset); }});
}
template <class ELFT>
void DynamicSection<ELFT>::addOutSec(int32_t Tag, OutputSection *Sec) {
Entries.push_back({Tag, [=] { return Sec->Addr; }});
}
template <class ELFT>
void DynamicSection<ELFT>::addSize(int32_t Tag, OutputSection *Sec) {
Entries.push_back({Tag, [=] { return Sec->Size; }});
}
template <class ELFT>
void DynamicSection<ELFT>::addSym(int32_t Tag, Symbol *Sym) {
Entries.push_back({Tag, [=] { return Sym->getVA(); }});
}
// A Linker script may assign the RELA relocation sections to the same
// output section. When this occurs we cannot just use the OutputSection
// Size. Moreover the [DT_JMPREL, DT_JMPREL + DT_PLTRELSZ) is permitted to
// overlap with the [DT_RELA, DT_RELA + DT_RELASZ).
static uint64_t addPltRelSz() {
size_t Size = In.RelaPlt->getSize();
if (In.RelaIplt->getParent() == In.RelaPlt->getParent() &&
In.RelaIplt->Name == In.RelaPlt->Name)
Size += In.RelaIplt->getSize();
return Size;
}
// Add remaining entries to complete .dynamic contents.
template <class ELFT> void DynamicSection<ELFT>::finalizeContents() {
// Set DT_FLAGS and DT_FLAGS_1.
uint32_t DtFlags = 0;
uint32_t DtFlags1 = 0;
if (Config->Bsymbolic)
DtFlags |= DF_SYMBOLIC;
if (Config->ZGlobal)
DtFlags1 |= DF_1_GLOBAL;
if (Config->ZInitfirst)
DtFlags1 |= DF_1_INITFIRST;
if (Config->ZInterpose)
DtFlags1 |= DF_1_INTERPOSE;
if (Config->ZNodefaultlib)
DtFlags1 |= DF_1_NODEFLIB;
if (Config->ZNodelete)
DtFlags1 |= DF_1_NODELETE;
if (Config->ZNodlopen)
DtFlags1 |= DF_1_NOOPEN;
if (Config->ZNow) {
DtFlags |= DF_BIND_NOW;
DtFlags1 |= DF_1_NOW;
}
if (Config->ZOrigin) {
DtFlags |= DF_ORIGIN;
DtFlags1 |= DF_1_ORIGIN;
}
if (!Config->ZText)
DtFlags |= DF_TEXTREL;
if (Config->HasStaticTlsModel)
DtFlags |= DF_STATIC_TLS;
if (DtFlags)
addInt(DT_FLAGS, DtFlags);
if (DtFlags1)
addInt(DT_FLAGS_1, DtFlags1);
// DT_DEBUG is a pointer to debug informaion used by debuggers at runtime. We
// need it for each process, so we don't write it for DSOs. The loader writes
// the pointer into this entry.
//
// DT_DEBUG is the only .dynamic entry that needs to be written to. Some
// systems (currently only Fuchsia OS) provide other means to give the
// debugger this information. Such systems may choose make .dynamic read-only.
// If the target is such a system (used -z rodynamic) don't write DT_DEBUG.
if (!Config->Shared && !Config->Relocatable && !Config->ZRodynamic)
addInt(DT_DEBUG, 0);
if (OutputSection *Sec = In.DynStrTab->getParent())
this->Link = Sec->SectionIndex;
if (!In.RelaDyn->empty()) {
addInSec(In.RelaDyn->DynamicTag, In.RelaDyn);
addSize(In.RelaDyn->SizeDynamicTag, In.RelaDyn->getParent());
bool IsRela = Config->IsRela;
addInt(IsRela ? DT_RELAENT : DT_RELENT,
IsRela ? sizeof(Elf_Rela) : sizeof(Elf_Rel));
// MIPS dynamic loader does not support RELCOUNT tag.
// The problem is in the tight relation between dynamic
// relocations and GOT. So do not emit this tag on MIPS.
if (Config->EMachine != EM_MIPS) {
size_t NumRelativeRels = In.RelaDyn->getRelativeRelocCount();
if (Config->ZCombreloc && NumRelativeRels)
addInt(IsRela ? DT_RELACOUNT : DT_RELCOUNT, NumRelativeRels);
}
}
if (In.RelrDyn && !In.RelrDyn->Relocs.empty()) {
addInSec(Config->UseAndroidRelrTags ? DT_ANDROID_RELR : DT_RELR,
In.RelrDyn);
addSize(Config->UseAndroidRelrTags ? DT_ANDROID_RELRSZ : DT_RELRSZ,
In.RelrDyn->getParent());
addInt(Config->UseAndroidRelrTags ? DT_ANDROID_RELRENT : DT_RELRENT,
sizeof(Elf_Relr));
}
// .rel[a].plt section usually consists of two parts, containing plt and
// iplt relocations. It is possible to have only iplt relocations in the
// output. In that case RelaPlt is empty and have zero offset, the same offset
// as RelaIplt have. And we still want to emit proper dynamic tags for that
// case, so here we always use RelaPlt as marker for the begining of
// .rel[a].plt section.
if (In.RelaPlt->getParent()->Live) {
addInSec(DT_JMPREL, In.RelaPlt);
Entries.push_back({DT_PLTRELSZ, addPltRelSz});
switch (Config->EMachine) {
case EM_MIPS:
addInSec(DT_MIPS_PLTGOT, In.GotPlt);
break;
case EM_SPARCV9:
addInSec(DT_PLTGOT, In.Plt);
break;
default:
addInSec(DT_PLTGOT, In.GotPlt);
break;
}
addInt(DT_PLTREL, Config->IsRela ? DT_RELA : DT_REL);
}
addInSec(DT_SYMTAB, In.DynSymTab);
addInt(DT_SYMENT, sizeof(Elf_Sym));
addInSec(DT_STRTAB, In.DynStrTab);
addInt(DT_STRSZ, In.DynStrTab->getSize());
if (!Config->ZText)
addInt(DT_TEXTREL, 0);
if (In.GnuHashTab)
addInSec(DT_GNU_HASH, In.GnuHashTab);
if (In.HashTab)
addInSec(DT_HASH, In.HashTab);
if (Out::PreinitArray) {
addOutSec(DT_PREINIT_ARRAY, Out::PreinitArray);
addSize(DT_PREINIT_ARRAYSZ, Out::PreinitArray);
}
if (Out::InitArray) {
addOutSec(DT_INIT_ARRAY, Out::InitArray);
addSize(DT_INIT_ARRAYSZ, Out::InitArray);
}
if (Out::FiniArray) {
addOutSec(DT_FINI_ARRAY, Out::FiniArray);
addSize(DT_FINI_ARRAYSZ, Out::FiniArray);
}
if (Symbol *B = Symtab->find(Config->Init))
if (B->isDefined())
addSym(DT_INIT, B);
if (Symbol *B = Symtab->find(Config->Fini))
if (B->isDefined())
addSym(DT_FINI, B);
bool HasVerNeed = InX<ELFT>::VerNeed->getNeedNum() != 0;
if (HasVerNeed || In.VerDef)
addInSec(DT_VERSYM, InX<ELFT>::VerSym);
if (In.VerDef) {
addInSec(DT_VERDEF, In.VerDef);
addInt(DT_VERDEFNUM, getVerDefNum());
}
if (HasVerNeed) {
addInSec(DT_VERNEED, InX<ELFT>::VerNeed);
addInt(DT_VERNEEDNUM, InX<ELFT>::VerNeed->getNeedNum());
}
if (Config->EMachine == EM_MIPS) {
addInt(DT_MIPS_RLD_VERSION, 1);
addInt(DT_MIPS_FLAGS, RHF_NOTPOT);
addInt(DT_MIPS_BASE_ADDRESS, Target->getImageBase());
addInt(DT_MIPS_SYMTABNO, In.DynSymTab->getNumSymbols());
add(DT_MIPS_LOCAL_GOTNO, [] { return In.MipsGot->getLocalEntriesNum(); });
if (const Symbol *B = In.MipsGot->getFirstGlobalEntry())
addInt(DT_MIPS_GOTSYM, B->DynsymIndex);
else
addInt(DT_MIPS_GOTSYM, In.DynSymTab->getNumSymbols());
addInSec(DT_PLTGOT, In.MipsGot);
if (In.MipsRldMap) {
if (!Config->Pie)
addInSec(DT_MIPS_RLD_MAP, In.MipsRldMap);
// Store the offset to the .rld_map section
// relative to the address of the tag.
addInSecRelative(DT_MIPS_RLD_MAP_REL, In.MipsRldMap);
}
}
// Glink dynamic tag is required by the V2 abi if the plt section isn't empty.
if (Config->EMachine == EM_PPC64 && !In.Plt->empty()) {
// The Glink tag points to 32 bytes before the first lazy symbol resolution
// stub, which starts directly after the header.
Entries.push_back({DT_PPC64_GLINK, [=] {
unsigned Offset = Target->PltHeaderSize - 32;
return In.Plt->getVA(0) + Offset;
}});
}
addInt(DT_NULL, 0);
getParent()->Link = this->Link;
this->Size = Entries.size() * this->Entsize;
}
template <class ELFT> void DynamicSection<ELFT>::writeTo(uint8_t *Buf) {
auto *P = reinterpret_cast<Elf_Dyn *>(Buf);
for (std::pair<int32_t, std::function<uint64_t()>> &KV : Entries) {
P->d_tag = KV.first;
P->d_un.d_val = KV.second();
++P;
}
}
uint64_t DynamicReloc::getOffset() const {
return InputSec->getVA(OffsetInSec);
}
int64_t DynamicReloc::computeAddend() const {
if (UseSymVA)
return Sym->getVA(Addend);
if (!OutputSec)
return Addend;
// See the comment in the DynamicReloc ctor.
return getMipsPageAddr(OutputSec->Addr) + Addend;
}
uint32_t DynamicReloc::getSymIndex() const {
if (Sym && !UseSymVA)
return Sym->DynsymIndex;
return 0;
}
RelocationBaseSection::RelocationBaseSection(StringRef Name, uint32_t Type,
int32_t DynamicTag,
int32_t SizeDynamicTag)
: SyntheticSection(SHF_ALLOC, Type, Config->Wordsize, Name),
DynamicTag(DynamicTag), SizeDynamicTag(SizeDynamicTag) {}
void RelocationBaseSection::addReloc(RelType DynType, InputSectionBase *IS,
uint64_t OffsetInSec, Symbol *Sym) {
addReloc({DynType, IS, OffsetInSec, false, Sym, 0});
}
void RelocationBaseSection::addReloc(RelType DynType,
InputSectionBase *InputSec,
uint64_t OffsetInSec, Symbol *Sym,
int64_t Addend, RelExpr Expr,
RelType Type) {
// Write the addends to the relocated address if required. We skip
// it if the written value would be zero.
if (Config->WriteAddends && (Expr != R_ADDEND || Addend != 0))
InputSec->Relocations.push_back({Expr, Type, OffsetInSec, Addend, Sym});
addReloc({DynType, InputSec, OffsetInSec, Expr != R_ADDEND, Sym, Addend});
}
void RelocationBaseSection::addReloc(const DynamicReloc &Reloc) {
if (Reloc.Type == Target->RelativeRel)
++NumRelativeRelocs;
Relocs.push_back(Reloc);
}
void RelocationBaseSection::finalizeContents() {
// When linking glibc statically, .rel{,a}.plt contains R_*_IRELATIVE
// relocations due to IFUNC (e.g. strcpy). sh_link will be set to 0 in that
// case.
InputSection *SymTab = Config->Relocatable ? In.SymTab : In.DynSymTab;
if (SymTab && SymTab->getParent())
getParent()->Link = SymTab->getParent()->SectionIndex;
else
getParent()->Link = 0;
if (In.RelaPlt == this)
getParent()->Info = In.GotPlt->getParent()->SectionIndex;
if (In.RelaIplt == this)
getParent()->Info = In.IgotPlt->getParent()->SectionIndex;
}
RelrBaseSection::RelrBaseSection()
: SyntheticSection(SHF_ALLOC,
Config->UseAndroidRelrTags ? SHT_ANDROID_RELR : SHT_RELR,
Config->Wordsize, ".relr.dyn") {}
template <class ELFT>
static void encodeDynamicReloc(typename ELFT::Rela *P,
const DynamicReloc &Rel) {
if (Config->IsRela)
P->r_addend = Rel.computeAddend();
P->r_offset = Rel.getOffset();
P->setSymbolAndType(Rel.getSymIndex(), Rel.Type, Config->IsMips64EL);
}
template <class ELFT>
RelocationSection<ELFT>::RelocationSection(StringRef Name, bool Sort)
: RelocationBaseSection(Name, Config->IsRela ? SHT_RELA : SHT_REL,
Config->IsRela ? DT_RELA : DT_REL,
Config->IsRela ? DT_RELASZ : DT_RELSZ),
Sort(Sort) {
this->Entsize = Config->IsRela ? sizeof(Elf_Rela) : sizeof(Elf_Rel);
}
static bool compRelocations(const DynamicReloc &A, const DynamicReloc &B) {
bool AIsRel = A.Type == Target->RelativeRel;
bool BIsRel = B.Type == Target->RelativeRel;
if (AIsRel != BIsRel)
return AIsRel;
return A.getSymIndex() < B.getSymIndex();
}
template <class ELFT> void RelocationSection<ELFT>::writeTo(uint8_t *Buf) {
if (Sort)
std::stable_sort(Relocs.begin(), Relocs.end(), compRelocations);
for (const DynamicReloc &Rel : Relocs) {
encodeDynamicReloc<ELFT>(reinterpret_cast<Elf_Rela *>(Buf), Rel);
Buf += Config->IsRela ? sizeof(Elf_Rela) : sizeof(Elf_Rel);
}
}
template <class ELFT> unsigned RelocationSection<ELFT>::getRelocOffset() {
return this->Entsize * Relocs.size();
}
template <class ELFT>
AndroidPackedRelocationSection<ELFT>::AndroidPackedRelocationSection(
StringRef Name)
: RelocationBaseSection(
Name, Config->IsRela ? SHT_ANDROID_RELA : SHT_ANDROID_REL,
Config->IsRela ? DT_ANDROID_RELA : DT_ANDROID_REL,
Config->IsRela ? DT_ANDROID_RELASZ : DT_ANDROID_RELSZ) {
this->Entsize = 1;
}
template <class ELFT>
bool AndroidPackedRelocationSection<ELFT>::updateAllocSize() {
// This function computes the contents of an Android-format packed relocation
// section.
//
// This format compresses relocations by using relocation groups to factor out
// fields that are common between relocations and storing deltas from previous
// relocations in SLEB128 format (which has a short representation for small
// numbers). A good example of a relocation type with common fields is
// R_*_RELATIVE, which is normally used to represent function pointers in
// vtables. In the REL format, each relative relocation has the same r_info
// field, and is only different from other relative relocations in terms of
// the r_offset field. By sorting relocations by offset, grouping them by
// r_info and representing each relocation with only the delta from the
// previous offset, each 8-byte relocation can be compressed to as little as 1
// byte (or less with run-length encoding). This relocation packer was able to
// reduce the size of the relocation section in an Android Chromium DSO from
// 2,911,184 bytes to 174,693 bytes, or 6% of the original size.
//
// A relocation section consists of a header containing the literal bytes
// 'APS2' followed by a sequence of SLEB128-encoded integers. The first two
// elements are the total number of relocations in the section and an initial
// r_offset value. The remaining elements define a sequence of relocation
// groups. Each relocation group starts with a header consisting of the
// following elements:
//
// - the number of relocations in the relocation group
// - flags for the relocation group
// - (if RELOCATION_GROUPED_BY_OFFSET_DELTA_FLAG is set) the r_offset delta
// for each relocation in the group.
// - (if RELOCATION_GROUPED_BY_INFO_FLAG is set) the value of the r_info
// field for each relocation in the group.
// - (if RELOCATION_GROUP_HAS_ADDEND_FLAG and
// RELOCATION_GROUPED_BY_ADDEND_FLAG are set) the r_addend delta for
// each relocation in the group.
//
// Following the relocation group header are descriptions of each of the
// relocations in the group. They consist of the following elements:
//
// - (if RELOCATION_GROUPED_BY_OFFSET_DELTA_FLAG is not set) the r_offset
// delta for this relocation.
// - (if RELOCATION_GROUPED_BY_INFO_FLAG is not set) the value of the r_info
// field for this relocation.
// - (if RELOCATION_GROUP_HAS_ADDEND_FLAG is set and
// RELOCATION_GROUPED_BY_ADDEND_FLAG is not set) the r_addend delta for
// this relocation.
size_t OldSize = RelocData.size();
RelocData = {'A', 'P', 'S', '2'};
raw_svector_ostream OS(RelocData);
auto Add = [&](int64_t V) { encodeSLEB128(V, OS); };
// The format header includes the number of relocations and the initial
// offset (we set this to zero because the first relocation group will
// perform the initial adjustment).
Add(Relocs.size());
Add(0);
std::vector<Elf_Rela> Relatives, NonRelatives;
for (const DynamicReloc &Rel : Relocs) {
Elf_Rela R;
encodeDynamicReloc<ELFT>(&R, Rel);
if (R.getType(Config->IsMips64EL) == Target->RelativeRel)
Relatives.push_back(R);
else
NonRelatives.push_back(R);
}
llvm::sort(Relatives, [](const Elf_Rel &A, const Elf_Rel &B) {
return A.r_offset < B.r_offset;
});
// Try to find groups of relative relocations which are spaced one word
// apart from one another. These generally correspond to vtable entries. The
// format allows these groups to be encoded using a sort of run-length
// encoding, but each group will cost 7 bytes in addition to the offset from
// the previous group, so it is only profitable to do this for groups of
// size 8 or larger.
std::vector<Elf_Rela> UngroupedRelatives;
std::vector<std::vector<Elf_Rela>> RelativeGroups;
for (auto I = Relatives.begin(), E = Relatives.end(); I != E;) {
std::vector<Elf_Rela> Group;
do {
Group.push_back(*I++);
} while (I != E && (I - 1)->r_offset + Config->Wordsize == I->r_offset);
if (Group.size() < 8)
UngroupedRelatives.insert(UngroupedRelatives.end(), Group.begin(),
Group.end());
else
RelativeGroups.emplace_back(std::move(Group));
}
unsigned HasAddendIfRela =
Config->IsRela ? RELOCATION_GROUP_HAS_ADDEND_FLAG : 0;
uint64_t Offset = 0;
uint64_t Addend = 0;
// Emit the run-length encoding for the groups of adjacent relative
// relocations. Each group is represented using two groups in the packed
// format. The first is used to set the current offset to the start of the
// group (and also encodes the first relocation), and the second encodes the
// remaining relocations.
for (std::vector<Elf_Rela> &G : RelativeGroups) {
// The first relocation in the group.
Add(1);
Add(RELOCATION_GROUPED_BY_OFFSET_DELTA_FLAG |
RELOCATION_GROUPED_BY_INFO_FLAG | HasAddendIfRela);
Add(G[0].r_offset - Offset);
Add(Target->RelativeRel);
if (Config->IsRela) {
Add(G[0].r_addend - Addend);
Addend = G[0].r_addend;
}
// The remaining relocations.
Add(G.size() - 1);
Add(RELOCATION_GROUPED_BY_OFFSET_DELTA_FLAG |
RELOCATION_GROUPED_BY_INFO_FLAG | HasAddendIfRela);
Add(Config->Wordsize);
Add(Target->RelativeRel);
if (Config->IsRela) {
for (auto I = G.begin() + 1, E = G.end(); I != E; ++I) {
Add(I->r_addend - Addend);
Addend = I->r_addend;
}
}
Offset = G.back().r_offset;
}
// Now the ungrouped relatives.
if (!UngroupedRelatives.empty()) {
Add(UngroupedRelatives.size());
Add(RELOCATION_GROUPED_BY_INFO_FLAG | HasAddendIfRela);
Add(Target->RelativeRel);
for (Elf_Rela &R : UngroupedRelatives) {
Add(R.r_offset - Offset);
Offset = R.r_offset;
if (Config->IsRela) {
Add(R.r_addend - Addend);
Addend = R.r_addend;
}
}
}
// Finally the non-relative relocations.
llvm::sort(NonRelatives, [](const Elf_Rela &A, const Elf_Rela &B) {
return A.r_offset < B.r_offset;
});
if (!NonRelatives.empty()) {
Add(NonRelatives.size());
Add(HasAddendIfRela);
for (Elf_Rela &R : NonRelatives) {
Add(R.r_offset - Offset);
Offset = R.r_offset;
Add(R.r_info);
if (Config->IsRela) {
Add(R.r_addend - Addend);
Addend = R.r_addend;
}
}
}
// Don't allow the section to shrink; otherwise the size of the section can
// oscillate infinitely.
if (RelocData.size() < OldSize)
RelocData.append(OldSize - RelocData.size(), 0);
// Returns whether the section size changed. We need to keep recomputing both
// section layout and the contents of this section until the size converges
// because changing this section's size can affect section layout, which in
// turn can affect the sizes of the LEB-encoded integers stored in this
// section.
return RelocData.size() != OldSize;
}
template <class ELFT> RelrSection<ELFT>::RelrSection() {
this->Entsize = Config->Wordsize;
}
template <class ELFT> bool RelrSection<ELFT>::updateAllocSize() {
// This function computes the contents of an SHT_RELR packed relocation
// section.
//
// Proposal for adding SHT_RELR sections to generic-abi is here:
// https://groups.google.com/forum/#!topic/generic-abi/bX460iggiKg
//
// The encoded sequence of Elf64_Relr entries in a SHT_RELR section looks
// like [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ]
//
// i.e. start with an address, followed by any number of bitmaps. The address
// entry encodes 1 relocation. The subsequent bitmap entries encode up to 63
// relocations each, at subsequent offsets following the last address entry.
//
// The bitmap entries must have 1 in the least significant bit. The assumption
// here is that an address cannot have 1 in lsb. Odd addresses are not
// supported.
//
// Excluding the least significant bit in the bitmap, each non-zero bit in
// the bitmap represents a relocation to be applied to a corresponding machine
// word that follows the base address word. The second least significant bit
// represents the machine word immediately following the initial address, and
// each bit that follows represents the next word, in linear order. As such,
// a single bitmap can encode up to 31 relocations in a 32-bit object, and
// 63 relocations in a 64-bit object.
//
// This encoding has a couple of interesting properties:
// 1. Looking at any entry, it is clear whether it's an address or a bitmap:
// even means address, odd means bitmap.
// 2. Just a simple list of addresses is a valid encoding.
size_t OldSize = RelrRelocs.size();
RelrRelocs.clear();
// Same as Config->Wordsize but faster because this is a compile-time
// constant.
const size_t Wordsize = sizeof(typename ELFT::uint);
// Number of bits to use for the relocation offsets bitmap.
// Must be either 63 or 31.
const size_t NBits = Wordsize * 8 - 1;
// Get offsets for all relative relocations and sort them.
std::vector<uint64_t> Offsets;
for (const RelativeReloc &Rel : Relocs)
Offsets.push_back(Rel.getOffset());
llvm::sort(Offsets.begin(), Offsets.end());
// For each leading relocation, find following ones that can be folded
// as a bitmap and fold them.
for (size_t I = 0, E = Offsets.size(); I < E;) {
// Add a leading relocation.
RelrRelocs.push_back(Elf_Relr(Offsets[I]));
uint64_t Base = Offsets[I] + Wordsize;
++I;
// Find foldable relocations to construct bitmaps.
while (I < E) {
uint64_t Bitmap = 0;
while (I < E) {
uint64_t Delta = Offsets[I] - Base;
// If it is too far, it cannot be folded.
if (Delta >= NBits * Wordsize)
break;
// If it is not a multiple of wordsize away, it cannot be folded.
if (Delta % Wordsize)
break;
// Fold it.
Bitmap |= 1ULL << (Delta / Wordsize);
++I;
}
if (!Bitmap)
break;
RelrRelocs.push_back(Elf_Relr((Bitmap << 1) | 1));
Base += NBits * Wordsize;
}
}
return RelrRelocs.size() != OldSize;
}
SymbolTableBaseSection::SymbolTableBaseSection(StringTableSection &StrTabSec)
: SyntheticSection(StrTabSec.isDynamic() ? (uint64_t)SHF_ALLOC : 0,
StrTabSec.isDynamic() ? SHT_DYNSYM : SHT_SYMTAB,
Config->Wordsize,
StrTabSec.isDynamic() ? ".dynsym" : ".symtab"),
StrTabSec(StrTabSec) {}
// Orders symbols according to their positions in the GOT,
// in compliance with MIPS ABI rules.
// See "Global Offset Table" in Chapter 5 in the following document
// for detailed description:
// ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
static bool sortMipsSymbols(const SymbolTableEntry &L,
const SymbolTableEntry &R) {
// Sort entries related to non-local preemptible symbols by GOT indexes.
// All other entries go to the beginning of a dynsym in arbitrary order.
if (L.Sym->isInGot() && R.Sym->isInGot())
return L.Sym->GotIndex < R.Sym->GotIndex;
if (!L.Sym->isInGot() && !R.Sym->isInGot())
return false;
return !L.Sym->isInGot();
}
void SymbolTableBaseSection::finalizeContents() {
if (OutputSection *Sec = StrTabSec.getParent())
getParent()->Link = Sec->SectionIndex;
if (this->Type != SHT_DYNSYM) {
sortSymTabSymbols();
return;
}
// If it is a .dynsym, there should be no local symbols, but we need
// to do a few things for the dynamic linker.
// Section's Info field has the index of the first non-local symbol.
// Because the first symbol entry is a null entry, 1 is the first.
getParent()->Info = 1;
if (In.GnuHashTab) {
// NB: It also sorts Symbols to meet the GNU hash table requirements.
In.GnuHashTab->addSymbols(Symbols);
} else if (Config->EMachine == EM_MIPS) {
std::stable_sort(Symbols.begin(), Symbols.end(), sortMipsSymbols);
}
size_t I = 0;
for (const SymbolTableEntry &S : Symbols)
S.Sym->DynsymIndex = ++I;
}
// The ELF spec requires that all local symbols precede global symbols, so we
// sort symbol entries in this function. (For .dynsym, we don't do that because
// symbols for dynamic linking are inherently all globals.)
//
// Aside from above, we put local symbols in groups starting with the STT_FILE
// symbol. That is convenient for purpose of identifying where are local symbols
// coming from.
void SymbolTableBaseSection::sortSymTabSymbols() {
// Move all local symbols before global symbols.
auto E = std::stable_partition(
Symbols.begin(), Symbols.end(), [](const SymbolTableEntry &S) {
return S.Sym->isLocal() || S.Sym->computeBinding() == STB_LOCAL;
});
size_t NumLocals = E - Symbols.begin();
getParent()->Info = NumLocals + 1;
// We want to group the local symbols by file. For that we rebuild the local
// part of the symbols vector. We do not need to care about the STT_FILE
// symbols, they are already naturally placed first in each group. That
// happens because STT_FILE is always the first symbol in the object and hence
// precede all other local symbols we add for a file.
MapVector<InputFile *, std::vector<SymbolTableEntry>> Arr;
for (const SymbolTableEntry &S : llvm::make_range(Symbols.begin(), E))
Arr[S.Sym->File].push_back(S);
auto I = Symbols.begin();
for (std::pair<InputFile *, std::vector<SymbolTableEntry>> &P : Arr)
for (SymbolTableEntry &Entry : P.second)
*I++ = Entry;
}
void SymbolTableBaseSection::addSymbol(Symbol *B) {
// Adding a local symbol to a .dynsym is a bug.
assert(this->Type != SHT_DYNSYM || !B->isLocal());
bool HashIt = B->isLocal();
Symbols.push_back({B, StrTabSec.addString(B->getName(), HashIt)});
}
size_t SymbolTableBaseSection::getSymbolIndex(Symbol *Sym) {
// Initializes symbol lookup tables lazily. This is used only
// for -r or -emit-relocs.
llvm::call_once(OnceFlag, [&] {
SymbolIndexMap.reserve(Symbols.size());
size_t I = 0;
for (const SymbolTableEntry &E : Symbols) {
if (E.Sym->Type == STT_SECTION)
SectionIndexMap[E.Sym->getOutputSection()] = ++I;
else
SymbolIndexMap[E.Sym] = ++I;
}
});
// Section symbols are mapped based on their output sections
// to maintain their semantics.
if (Sym->Type == STT_SECTION)
return SectionIndexMap.lookup(Sym->getOutputSection());
return SymbolIndexMap.lookup(Sym);
}
template <class ELFT>
SymbolTableSection<ELFT>::SymbolTableSection(StringTableSection &StrTabSec)
: SymbolTableBaseSection(StrTabSec) {
this->Entsize = sizeof(Elf_Sym);
}
static BssSection *getCommonSec(Symbol *Sym) {
if (!Config->DefineCommon)
if (auto *D = dyn_cast<Defined>(Sym))
return dyn_cast_or_null<BssSection>(D->Section);
return nullptr;
}
static uint32_t getSymSectionIndex(Symbol *Sym) {
if (getCommonSec(Sym))
return SHN_COMMON;
if (!isa<Defined>(Sym) || Sym->NeedsPltAddr)
return SHN_UNDEF;
if (const OutputSection *OS = Sym->getOutputSection())
return OS->SectionIndex >= SHN_LORESERVE ? (uint32_t)SHN_XINDEX
: OS->SectionIndex;
return SHN_ABS;
}
// Write the internal symbol table contents to the output symbol table.
template <class ELFT> void SymbolTableSection<ELFT>::writeTo(uint8_t *Buf) {
// The first entry is a null entry as per the ELF spec.
memset(Buf, 0, sizeof(Elf_Sym));
Buf += sizeof(Elf_Sym);
auto *ESym = reinterpret_cast<Elf_Sym *>(Buf);
for (SymbolTableEntry &Ent : Symbols) {
Symbol *Sym = Ent.Sym;
// Set st_info and st_other.
ESym->st_other = 0;
if (Sym->isLocal()) {
ESym->setBindingAndType(STB_LOCAL, Sym->Type);
} else {
ESym->setBindingAndType(Sym->computeBinding(), Sym->Type);
ESym->setVisibility(Sym->Visibility);
}
// The 3 most significant bits of st_other are used by OpenPOWER ABI.
// See getPPC64GlobalEntryToLocalEntryOffset() for more details.
if (Config->EMachine == EM_PPC64)
ESym->st_other |= Sym->StOther & 0xe0;
ESym->st_name = Ent.StrTabOffset;
ESym->st_shndx = getSymSectionIndex(Ent.Sym);
// Copy symbol size if it is a defined symbol. st_size is not significant
// for undefined symbols, so whether copying it or not is up to us if that's
// the case. We'll leave it as zero because by not setting a value, we can
// get the exact same outputs for two sets of input files that differ only
// in undefined symbol size in DSOs.
if (ESym->st_shndx == SHN_UNDEF)
ESym->st_size = 0;
else
ESym->st_size = Sym->getSize();
// st_value is usually an address of a symbol, but that has a
// special meaining for uninstantiated common symbols (this can
// occur if -r is given).
if (BssSection *CommonSec = getCommonSec(Ent.Sym))
ESym->st_value = CommonSec->Alignment;
else
ESym->st_value = Sym->getVA();
++ESym;
}
// On MIPS we need to mark symbol which has a PLT entry and requires
// pointer equality by STO_MIPS_PLT flag. That is necessary to help
// dynamic linker distinguish such symbols and MIPS lazy-binding stubs.
// https://sourceware.org/ml/binutils/2008-07/txt00000.txt
if (Config->EMachine == EM_MIPS) {
auto *ESym = reinterpret_cast<Elf_Sym *>(Buf);
for (SymbolTableEntry &Ent : Symbols) {
Symbol *Sym = Ent.Sym;
if (Sym->isInPlt() && Sym->NeedsPltAddr)
ESym->st_other |= STO_MIPS_PLT;
if (isMicroMips()) {
// Set STO_MIPS_MICROMIPS flag and less-significant bit for
// a defined microMIPS symbol and symbol should point to its
// PLT entry (in case of microMIPS, PLT entries always contain
// microMIPS code).
if (Sym->isDefined() &&
((Sym->StOther & STO_MIPS_MICROMIPS) || Sym->NeedsPltAddr)) {
if (StrTabSec.isDynamic())
ESym->st_value |= 1;
ESym->st_other |= STO_MIPS_MICROMIPS;
}
}
if (Config->Relocatable)
if (auto *D = dyn_cast<Defined>(Sym))
if (isMipsPIC<ELFT>(D))
ESym->st_other |= STO_MIPS_PIC;
++ESym;
}
}
}
SymtabShndxSection::SymtabShndxSection()
: SyntheticSection(0, SHT_SYMTAB_SHNDX, 4, ".symtab_shndxr") {
this->Entsize = 4;
}
void SymtabShndxSection::writeTo(uint8_t *Buf) {
// We write an array of 32 bit values, where each value has 1:1 association
// with an entry in .symtab. If the corresponding entry contains SHN_XINDEX,
// we need to write actual index, otherwise, we must write SHN_UNDEF(0).
Buf += 4; // Ignore .symtab[0] entry.
for (const SymbolTableEntry &Entry : In.SymTab->getSymbols()) {
if (getSymSectionIndex(Entry.Sym) == SHN_XINDEX)
write32(Buf, Entry.Sym->getOutputSection()->SectionIndex);
Buf += 4;
}
}
bool SymtabShndxSection::empty() const {
// SHT_SYMTAB can hold symbols with section indices values up to
// SHN_LORESERVE. If we need more, we want to use extension SHT_SYMTAB_SHNDX
// section. Problem is that we reveal the final section indices a bit too
// late, and we do not know them here. For simplicity, we just always create
// a .symtab_shndxr section when the amount of output sections is huge.
size_t Size = 0;
for (BaseCommand *Base : Script->SectionCommands)
if (isa<OutputSection>(Base))
++Size;
return Size < SHN_LORESERVE;
}
void SymtabShndxSection::finalizeContents() {
getParent()->Link = In.SymTab->getParent()->SectionIndex;
}
size_t SymtabShndxSection::getSize() const {
return In.SymTab->getNumSymbols() * 4;
}
// .hash and .gnu.hash sections contain on-disk hash tables that map
// symbol names to their dynamic symbol table indices. Their purpose
// is to help the dynamic linker resolve symbols quickly. If ELF files
// don't have them, the dynamic linker has to do linear search on all
// dynamic symbols, which makes programs slower. Therefore, a .hash
// section is added to a DSO by default. A .gnu.hash is added if you
// give the -hash-style=gnu or -hash-style=both option.
//
// The Unix semantics of resolving dynamic symbols is somewhat expensive.
// Each ELF file has a list of DSOs that the ELF file depends on and a
// list of dynamic symbols that need to be resolved from any of the
// DSOs. That means resolving all dynamic symbols takes O(m)*O(n)
// where m is the number of DSOs and n is the number of dynamic
// symbols. For modern large programs, both m and n are large. So
// making each step faster by using hash tables substiantially
// improves time to load programs.
//
// (Note that this is not the only way to design the shared library.
// For instance, the Windows DLL takes a different approach. On
// Windows, each dynamic symbol has a name of DLL from which the symbol
// has to be resolved. That makes the cost of symbol resolution O(n).
// This disables some hacky techniques you can use on Unix such as
// LD_PRELOAD, but this is arguably better semantics than the Unix ones.)
//
// Due to historical reasons, we have two different hash tables, .hash
// and .gnu.hash. They are for the same purpose, and .gnu.hash is a new
// and better version of .hash. .hash is just an on-disk hash table, but
// .gnu.hash has a bloom filter in addition to a hash table to skip
// DSOs very quickly. If you are sure that your dynamic linker knows
// about .gnu.hash, you want to specify -hash-style=gnu. Otherwise, a
// safe bet is to specify -hash-style=both for backward compatibilty.
GnuHashTableSection::GnuHashTableSection()
: SyntheticSection(SHF_ALLOC, SHT_GNU_HASH, Config->Wordsize, ".gnu.hash") {
}
void GnuHashTableSection::finalizeContents() {
if (OutputSection *Sec = In.DynSymTab->getParent())
getParent()->Link = Sec->SectionIndex;
// Computes bloom filter size in word size. We want to allocate 12
// bits for each symbol. It must be a power of two.
if (Symbols.empty()) {
MaskWords = 1;
} else {
uint64_t NumBits = Symbols.size() * 12;
MaskWords = NextPowerOf2(NumBits / (Config->Wordsize * 8));
}
Size = 16; // Header
Size += Config->Wordsize * MaskWords; // Bloom filter
Size += NBuckets * 4; // Hash buckets
Size += Symbols.size() * 4; // Hash values
}
void GnuHashTableSection::writeTo(uint8_t *Buf) {
// The output buffer is not guaranteed to be zero-cleared because we pre-
// fill executable sections with trap instructions. This is a precaution
// for that case, which happens only when -no-rosegment is given.
memset(Buf, 0, Size);
// Write a header.
write32(Buf, NBuckets);
write32(Buf + 4, In.DynSymTab->getNumSymbols() - Symbols.size());
write32(Buf + 8, MaskWords);
write32(Buf + 12, Shift2);
Buf += 16;
// Write a bloom filter and a hash table.
writeBloomFilter(Buf);
Buf += Config->Wordsize * MaskWords;
writeHashTable(Buf);
}
// This function writes a 2-bit bloom filter. This bloom filter alone
// usually filters out 80% or more of all symbol lookups [1].
// The dynamic linker uses the hash table only when a symbol is not
// filtered out by a bloom filter.
//
// [1] Ulrich Drepper (2011), "How To Write Shared Libraries" (Ver. 4.1.2),
// p.9, https://www.akkadia.org/drepper/dsohowto.pdf
void GnuHashTableSection::writeBloomFilter(uint8_t *Buf) {
unsigned C = Config->Is64 ? 64 : 32;
for (const Entry &Sym : Symbols) {
// When C = 64, we choose a word with bits [6:...] and set 1 to two bits in
// the word using bits [0:5] and [26:31].
size_t I = (Sym.Hash / C) & (MaskWords - 1);
uint64_t Val = readUint(Buf + I * Config->Wordsize);
Val |= uint64_t(1) << (Sym.Hash % C);
Val |= uint64_t(1) << ((Sym.Hash >> Shift2) % C);
writeUint(Buf + I * Config->Wordsize, Val);
}
}
void GnuHashTableSection::writeHashTable(uint8_t *Buf) {
uint32_t *Buckets = reinterpret_cast<uint32_t *>(Buf);
uint32_t OldBucket = -1;
uint32_t *Values = Buckets + NBuckets;
for (auto I = Symbols.begin(), E = Symbols.end(); I != E; ++I) {
// Write a hash value. It represents a sequence of chains that share the
// same hash modulo value. The last element of each chain is terminated by
// LSB 1.
uint32_t Hash = I->Hash;
bool IsLastInChain = (I + 1) == E || I->BucketIdx != (I + 1)->BucketIdx;
Hash = IsLastInChain ? Hash | 1 : Hash & ~1;
write32(Values++, Hash);
if (I->BucketIdx == OldBucket)
continue;
// Write a hash bucket. Hash buckets contain indices in the following hash
// value table.
write32(Buckets + I->BucketIdx, I->Sym->DynsymIndex);
OldBucket = I->BucketIdx;
}
}
static uint32_t hashGnu(StringRef Name) {
uint32_t H = 5381;
for (uint8_t C : Name)
H = (H << 5) + H + C;
return H;
}
// Add symbols to this symbol hash table. Note that this function
// destructively sort a given vector -- which is needed because
// GNU-style hash table places some sorting requirements.
void GnuHashTableSection::addSymbols(std::vector<SymbolTableEntry> &V) {
// We cannot use 'auto' for Mid because GCC 6.1 cannot deduce
// its type correctly.
std::vector<SymbolTableEntry>::iterator Mid =
std::stable_partition(V.begin(), V.end(), [](const SymbolTableEntry &S) {
return !S.Sym->isDefined();
});
// We chose load factor 4 for the on-disk hash table. For each hash
// collision, the dynamic linker will compare a uint32_t hash value.
// Since the integer comparison is quite fast, we believe we can
// make the load factor even larger. 4 is just a conservative choice.
//
// Note that we don't want to create a zero-sized hash table because
// Android loader as of 2018 doesn't like a .gnu.hash containing such
// table. If that's the case, we create a hash table with one unused
// dummy slot.
NBuckets = std::max<size_t>((V.end() - Mid) / 4, 1);
if (Mid == V.end())
return;
for (SymbolTableEntry &Ent : llvm::make_range(Mid, V.end())) {
Symbol *B = Ent.Sym;
uint32_t Hash = hashGnu(B->getName());
uint32_t BucketIdx = Hash % NBuckets;
Symbols.push_back({B, Ent.StrTabOffset, Hash, BucketIdx});
}
std::stable_sort(
Symbols.begin(), Symbols.end(),
[](const Entry &L, const Entry &R) { return L.BucketIdx < R.BucketIdx; });
V.erase(Mid, V.end());
for (const Entry &Ent : Symbols)
V.push_back({Ent.Sym, Ent.StrTabOffset});
}
HashTableSection::HashTableSection()
: SyntheticSection(SHF_ALLOC, SHT_HASH, 4, ".hash") {
this->Entsize = 4;
}
void HashTableSection::finalizeContents() {
if (OutputSection *Sec = In.DynSymTab->getParent())
getParent()->Link = Sec->SectionIndex;
unsigned NumEntries = 2; // nbucket and nchain.
NumEntries += In.DynSymTab->getNumSymbols(); // The chain entries.
// Create as many buckets as there are symbols.
NumEntries += In.DynSymTab->getNumSymbols();
this->Size = NumEntries * 4;
}
void HashTableSection::writeTo(uint8_t *Buf) {
// See comment in GnuHashTableSection::writeTo.
memset(Buf, 0, Size);
unsigned NumSymbols = In.DynSymTab->getNumSymbols();
uint32_t *P = reinterpret_cast<uint32_t *>(Buf);
write32(P++, NumSymbols); // nbucket
write32(P++, NumSymbols); // nchain
uint32_t *Buckets = P;
uint32_t *Chains = P + NumSymbols;
for (const SymbolTableEntry &S : In.DynSymTab->getSymbols()) {
Symbol *Sym = S.Sym;
StringRef Name = Sym->getName();
unsigned I = Sym->DynsymIndex;
uint32_t Hash = hashSysV(Name) % NumSymbols;
Chains[I] = Buckets[Hash];
write32(Buckets + Hash, I);
}
}
// On PowerPC64 the lazy symbol resolvers go into the `global linkage table`
// in the .glink section, rather then the typical .plt section.
PltSection::PltSection(bool IsIplt)
: SyntheticSection(SHF_ALLOC | SHF_EXECINSTR, SHT_PROGBITS, 16,
Config->EMachine == EM_PPC64 ? ".glink" : ".plt"),
HeaderSize(!IsIplt || Config->ZRetpolineplt ? Target->PltHeaderSize : 0),
IsIplt(IsIplt) {
// The PLT needs to be writable on SPARC as the dynamic linker will
// modify the instructions in the PLT entries.
if (Config->EMachine == EM_SPARCV9)
this->Flags |= SHF_WRITE;
}
void PltSection::writeTo(uint8_t *Buf) {
// At beginning of PLT or retpoline IPLT, we have code to call the dynamic
// linker to resolve dynsyms at runtime. Write such code.
if (HeaderSize > 0)
Target->writePltHeader(Buf);
size_t Off = HeaderSize;
// The IPlt is immediately after the Plt, account for this in RelOff
unsigned PltOff = getPltRelocOff();
for (auto &I : Entries) {
const Symbol *B = I.first;
unsigned RelOff = I.second + PltOff;
uint64_t Got = B->getGotPltVA();
uint64_t Plt = this->getVA() + Off;
Target->writePlt(Buf + Off, Got, Plt, B->PltIndex, RelOff);
Off += Target->PltEntrySize;
}
}
template <class ELFT> void PltSection::addEntry(Symbol &Sym) {
Sym.PltIndex = Entries.size();
RelocationBaseSection *PltRelocSection = In.RelaPlt;
- if (IsIplt) {
+ if (IsIplt)
PltRelocSection = In.RelaIplt;
- Sym.IsInIplt = true;
- }
unsigned RelOff =
static_cast<RelocationSection<ELFT> *>(PltRelocSection)->getRelocOffset();
Entries.push_back(std::make_pair(&Sym, RelOff));
}
size_t PltSection::getSize() const {
return HeaderSize + Entries.size() * Target->PltEntrySize;
}
// Some architectures such as additional symbols in the PLT section. For
// example ARM uses mapping symbols to aid disassembly
void PltSection::addSymbols() {
// The PLT may have symbols defined for the Header, the IPLT has no header
if (!IsIplt)
Target->addPltHeaderSymbols(*this);
size_t Off = HeaderSize;
for (size_t I = 0; I < Entries.size(); ++I) {
Target->addPltSymbols(*this, Off);
Off += Target->PltEntrySize;
}
}
unsigned PltSection::getPltRelocOff() const {
return IsIplt ? In.Plt->getSize() : 0;
}
// The string hash function for .gdb_index.
static uint32_t computeGdbHash(StringRef S) {
uint32_t H = 0;
for (uint8_t C : S)
H = H * 67 + toLower(C) - 113;
return H;
}
GdbIndexSection::GdbIndexSection()
: SyntheticSection(0, SHT_PROGBITS, 1, ".gdb_index") {}
// Returns the desired size of an on-disk hash table for a .gdb_index section.
// There's a tradeoff between size and collision rate. We aim 75% utilization.
size_t GdbIndexSection::computeSymtabSize() const {
return std::max<size_t>(NextPowerOf2(Symbols.size() * 4 / 3), 1024);
}
// Compute the output section size.
void GdbIndexSection::initOutputSize() {
Size = sizeof(GdbIndexHeader) + computeSymtabSize() * 8;
for (GdbChunk &Chunk : Chunks)
Size += Chunk.CompilationUnits.size() * 16 + Chunk.AddressAreas.size() * 20;
// Add the constant pool size if exists.
if (!Symbols.empty()) {
GdbSymbol &Sym = Symbols.back();
Size += Sym.NameOff + Sym.Name.size() + 1;
}
}
static std::vector<InputSection *> getDebugInfoSections() {
std::vector<InputSection *> Ret;
for (InputSectionBase *S : InputSections)
if (InputSection *IS = dyn_cast<InputSection>(S))
if (IS->Name == ".debug_info")
Ret.push_back(IS);
return Ret;
}
static std::vector<GdbIndexSection::CuEntry> readCuList(DWARFContext &Dwarf) {
std::vector<GdbIndexSection::CuEntry> Ret;
for (std::unique_ptr<DWARFUnit> &Cu : Dwarf.compile_units())
Ret.push_back({Cu->getOffset(), Cu->getLength() + 4});
return Ret;
}
static std::vector<GdbIndexSection::AddressEntry>
readAddressAreas(DWARFContext &Dwarf, InputSection *Sec) {
std::vector<GdbIndexSection::AddressEntry> Ret;
uint32_t CuIdx = 0;
for (std::unique_ptr<DWARFUnit> &Cu : Dwarf.compile_units()) {
Expected<DWARFAddressRangesVector> Ranges = Cu->collectAddressRanges();
if (!Ranges) {
error(toString(Sec) + ": " + toString(Ranges.takeError()));
return {};
}
ArrayRef<InputSectionBase *> Sections = Sec->File->getSections();
for (DWARFAddressRange &R : *Ranges) {
InputSectionBase *S = Sections[R.SectionIndex];
if (!S || S == &InputSection::Discarded || !S->Live)
continue;
// Range list with zero size has no effect.
if (R.LowPC == R.HighPC)
continue;
auto *IS = cast<InputSection>(S);
uint64_t Offset = IS->getOffsetInFile();
Ret.push_back({IS, R.LowPC - Offset, R.HighPC - Offset, CuIdx});
}
++CuIdx;
}
return Ret;
}
template <class ELFT>
static std::vector<GdbIndexSection::NameAttrEntry>
readPubNamesAndTypes(const LLDDwarfObj<ELFT> &Obj,
const std::vector<GdbIndexSection::CuEntry> &CUs) {
const DWARFSection &PubNames = Obj.getGnuPubNamesSection();
const DWARFSection &PubTypes = Obj.getGnuPubTypesSection();
std::vector<GdbIndexSection::NameAttrEntry> Ret;
for (const DWARFSection *Pub : {&PubNames, &PubTypes}) {
DWARFDebugPubTable Table(Obj, *Pub, Config->IsLE, true);
for (const DWARFDebugPubTable::Set &Set : Table.getData()) {
// The value written into the constant pool is Kind << 24 | CuIndex. As we
// don't know how many compilation units precede this object to compute
// CuIndex, we compute (Kind << 24 | CuIndexInThisObject) instead, and add
// the number of preceding compilation units later.
uint32_t I =
lower_bound(CUs, Set.Offset,
[](GdbIndexSection::CuEntry CU, uint32_t Offset) {
return CU.CuOffset < Offset;
}) -
CUs.begin();
for (const DWARFDebugPubTable::Entry &Ent : Set.Entries)
Ret.push_back({{Ent.Name, computeGdbHash(Ent.Name)},
(Ent.Descriptor.toBits() << 24) | I});
}
}
return Ret;
}
// Create a list of symbols from a given list of symbol names and types
// by uniquifying them by name.
static std::vector<GdbIndexSection::GdbSymbol>
createSymbols(ArrayRef<std::vector<GdbIndexSection::NameAttrEntry>> NameAttrs,
const std::vector<GdbIndexSection::GdbChunk> &Chunks) {
typedef GdbIndexSection::GdbSymbol GdbSymbol;
typedef GdbIndexSection::NameAttrEntry NameAttrEntry;
// For each chunk, compute the number of compilation units preceding it.
uint32_t CuIdx = 0;
std::vector<uint32_t> CuIdxs(Chunks.size());
for (uint32_t I = 0, E = Chunks.size(); I != E; ++I) {
CuIdxs[I] = CuIdx;
CuIdx += Chunks[I].CompilationUnits.size();
}
// The number of symbols we will handle in this function is of the order
// of millions for very large executables, so we use multi-threading to
// speed it up.
size_t NumShards = 32;
size_t Concurrency = 1;
if (ThreadsEnabled)
Concurrency =
std::min<size_t>(PowerOf2Floor(hardware_concurrency()), NumShards);
// A sharded map to uniquify symbols by name.
std::vector<DenseMap<CachedHashStringRef, size_t>> Map(NumShards);
size_t Shift = 32 - countTrailingZeros(NumShards);
// Instantiate GdbSymbols while uniqufying them by name.
std::vector<std::vector<GdbSymbol>> Symbols(NumShards);
parallelForEachN(0, Concurrency, [&](size_t ThreadId) {
uint32_t I = 0;
for (ArrayRef<NameAttrEntry> Entries : NameAttrs) {
for (const NameAttrEntry &Ent : Entries) {
size_t ShardId = Ent.Name.hash() >> Shift;
if ((ShardId & (Concurrency - 1)) != ThreadId)
continue;
uint32_t V = Ent.CuIndexAndAttrs + CuIdxs[I];
size_t &Idx = Map[ShardId][Ent.Name];
if (Idx) {
Symbols[ShardId][Idx - 1].CuVector.push_back(V);
continue;
}
Idx = Symbols[ShardId].size() + 1;
Symbols[ShardId].push_back({Ent.Name, {V}, 0, 0});
}
++I;
}
});
size_t NumSymbols = 0;
for (ArrayRef<GdbSymbol> V : Symbols)
NumSymbols += V.size();
// The return type is a flattened vector, so we'll copy each vector
// contents to Ret.
std::vector<GdbSymbol> Ret;
Ret.reserve(NumSymbols);
for (std::vector<GdbSymbol> &Vec : Symbols)
for (GdbSymbol &Sym : Vec)
Ret.push_back(std::move(Sym));
// CU vectors and symbol names are adjacent in the output file.
// We can compute their offsets in the output file now.
size_t Off = 0;
for (GdbSymbol &Sym : Ret) {
Sym.CuVectorOff = Off;
Off += (Sym.CuVector.size() + 1) * 4;
}
for (GdbSymbol &Sym : Ret) {
Sym.NameOff = Off;
Off += Sym.Name.size() + 1;
}
return Ret;
}
// Returns a newly-created .gdb_index section.
template <class ELFT> GdbIndexSection *GdbIndexSection::create() {
std::vector<InputSection *> Sections = getDebugInfoSections();
// .debug_gnu_pub{names,types} are useless in executables.
// They are present in input object files solely for creating
// a .gdb_index. So we can remove them from the output.
for (InputSectionBase *S : InputSections)
if (S->Name == ".debug_gnu_pubnames" || S->Name == ".debug_gnu_pubtypes")
S->Live = false;
std::vector<GdbChunk> Chunks(Sections.size());
std::vector<std::vector<NameAttrEntry>> NameAttrs(Sections.size());
parallelForEachN(0, Sections.size(), [&](size_t I) {
ObjFile<ELFT> *File = Sections[I]->getFile<ELFT>();
DWARFContext Dwarf(make_unique<LLDDwarfObj<ELFT>>(File));
Chunks[I].Sec = Sections[I];
Chunks[I].CompilationUnits = readCuList(Dwarf);
Chunks[I].AddressAreas = readAddressAreas(Dwarf, Sections[I]);
NameAttrs[I] = readPubNamesAndTypes<ELFT>(
static_cast<const LLDDwarfObj<ELFT> &>(Dwarf.getDWARFObj()),
Chunks[I].CompilationUnits);
});
auto *Ret = make<GdbIndexSection>();
Ret->Chunks = std::move(Chunks);
Ret->Symbols = createSymbols(NameAttrs, Ret->Chunks);
Ret->initOutputSize();
return Ret;
}
void GdbIndexSection::writeTo(uint8_t *Buf) {
// Write the header.
auto *Hdr = reinterpret_cast<GdbIndexHeader *>(Buf);
uint8_t *Start = Buf;
Hdr->Version = 7;
Buf += sizeof(*Hdr);
// Write the CU list.
Hdr->CuListOff = Buf - Start;
for (GdbChunk &Chunk : Chunks) {
for (CuEntry &Cu : Chunk.CompilationUnits) {
write64le(Buf, Chunk.Sec->OutSecOff + Cu.CuOffset);
write64le(Buf + 8, Cu.CuLength);
Buf += 16;
}
}
// Write the address area.
Hdr->CuTypesOff = Buf - Start;
Hdr->AddressAreaOff = Buf - Start;
uint32_t CuOff = 0;
for (GdbChunk &Chunk : Chunks) {
for (AddressEntry &E : Chunk.AddressAreas) {
uint64_t BaseAddr = E.Section->getVA(0);
write64le(Buf, BaseAddr + E.LowAddress);
write64le(Buf + 8, BaseAddr + E.HighAddress);
write32le(Buf + 16, E.CuIndex + CuOff);
Buf += 20;
}
CuOff += Chunk.CompilationUnits.size();
}
// Write the on-disk open-addressing hash table containing symbols.
Hdr->SymtabOff = Buf - Start;
size_t SymtabSize = computeSymtabSize();
uint32_t Mask = SymtabSize - 1;
for (GdbSymbol &Sym : Symbols) {
uint32_t H = Sym.Name.hash();
uint32_t I = H & Mask;
uint32_t Step = ((H * 17) & Mask) | 1;
while (read32le(Buf + I * 8))
I = (I + Step) & Mask;
write32le(Buf + I * 8, Sym.NameOff);
write32le(Buf + I * 8 + 4, Sym.CuVectorOff);
}
Buf += SymtabSize * 8;
// Write the string pool.
Hdr->ConstantPoolOff = Buf - Start;
parallelForEach(Symbols, [&](GdbSymbol &Sym) {
memcpy(Buf + Sym.NameOff, Sym.Name.data(), Sym.Name.size());
});
// Write the CU vectors.
for (GdbSymbol &Sym : Symbols) {
write32le(Buf, Sym.CuVector.size());
Buf += 4;
for (uint32_t Val : Sym.CuVector) {
write32le(Buf, Val);
Buf += 4;
}
}
}
bool GdbIndexSection::empty() const { return Chunks.empty(); }
EhFrameHeader::EhFrameHeader()
: SyntheticSection(SHF_ALLOC, SHT_PROGBITS, 4, ".eh_frame_hdr") {}
// .eh_frame_hdr contains a binary search table of pointers to FDEs.
// Each entry of the search table consists of two values,
// the starting PC from where FDEs covers, and the FDE's address.
// It is sorted by PC.
void EhFrameHeader::writeTo(uint8_t *Buf) {
typedef EhFrameSection::FdeData FdeData;
std::vector<FdeData> Fdes = In.EhFrame->getFdeData();
Buf[0] = 1;
Buf[1] = DW_EH_PE_pcrel | DW_EH_PE_sdata4;
Buf[2] = DW_EH_PE_udata4;
Buf[3] = DW_EH_PE_datarel | DW_EH_PE_sdata4;
write32(Buf + 4, In.EhFrame->getParent()->Addr - this->getVA() - 4);
write32(Buf + 8, Fdes.size());
Buf += 12;
for (FdeData &Fde : Fdes) {
write32(Buf, Fde.PcRel);
write32(Buf + 4, Fde.FdeVARel);
Buf += 8;
}
}
size_t EhFrameHeader::getSize() const {
// .eh_frame_hdr has a 12 bytes header followed by an array of FDEs.
return 12 + In.EhFrame->NumFdes * 8;
}
bool EhFrameHeader::empty() const { return In.EhFrame->empty(); }
VersionDefinitionSection::VersionDefinitionSection()
: SyntheticSection(SHF_ALLOC, SHT_GNU_verdef, sizeof(uint32_t),
".gnu.version_d") {}
static StringRef getFileDefName() {
if (!Config->SoName.empty())
return Config->SoName;
return Config->OutputFile;
}
void VersionDefinitionSection::finalizeContents() {
FileDefNameOff = In.DynStrTab->addString(getFileDefName());
for (VersionDefinition &V : Config->VersionDefinitions)
V.NameOff = In.DynStrTab->addString(V.Name);
if (OutputSection *Sec = In.DynStrTab->getParent())
getParent()->Link = Sec->SectionIndex;
// sh_info should be set to the number of definitions. This fact is missed in
// documentation, but confirmed by binutils community:
// https://sourceware.org/ml/binutils/2014-11/msg00355.html
getParent()->Info = getVerDefNum();
}
void VersionDefinitionSection::writeOne(uint8_t *Buf, uint32_t Index,
StringRef Name, size_t NameOff) {
uint16_t Flags = Index == 1 ? VER_FLG_BASE : 0;
// Write a verdef.
write16(Buf, 1); // vd_version
write16(Buf + 2, Flags); // vd_flags
write16(Buf + 4, Index); // vd_ndx
write16(Buf + 6, 1); // vd_cnt
write32(Buf + 8, hashSysV(Name)); // vd_hash
write32(Buf + 12, 20); // vd_aux
write32(Buf + 16, 28); // vd_next
// Write a veraux.
write32(Buf + 20, NameOff); // vda_name
write32(Buf + 24, 0); // vda_next
}
void VersionDefinitionSection::writeTo(uint8_t *Buf) {
writeOne(Buf, 1, getFileDefName(), FileDefNameOff);
for (VersionDefinition &V : Config->VersionDefinitions) {
Buf += EntrySize;
writeOne(Buf, V.Id, V.Name, V.NameOff);
}
// Need to terminate the last version definition.
write32(Buf + 16, 0); // vd_next
}
size_t VersionDefinitionSection::getSize() const {
return EntrySize * getVerDefNum();
}
// .gnu.version is a table where each entry is 2 byte long.
template <class ELFT>
VersionTableSection<ELFT>::VersionTableSection()
: SyntheticSection(SHF_ALLOC, SHT_GNU_versym, sizeof(uint16_t),
".gnu.version") {
this->Entsize = 2;
}
template <class ELFT> void VersionTableSection<ELFT>::finalizeContents() {
// At the moment of june 2016 GNU docs does not mention that sh_link field
// should be set, but Sun docs do. Also readelf relies on this field.
getParent()->Link = In.DynSymTab->getParent()->SectionIndex;
}
template <class ELFT> size_t VersionTableSection<ELFT>::getSize() const {
return (In.DynSymTab->getSymbols().size() + 1) * 2;
}
template <class ELFT> void VersionTableSection<ELFT>::writeTo(uint8_t *Buf) {
Buf += 2;
for (const SymbolTableEntry &S : In.DynSymTab->getSymbols()) {
write16(Buf, S.Sym->VersionId);
Buf += 2;
}
}
template <class ELFT> bool VersionTableSection<ELFT>::empty() const {
return !In.VerDef && InX<ELFT>::VerNeed->empty();
}
template <class ELFT>
VersionNeedSection<ELFT>::VersionNeedSection()
: SyntheticSection(SHF_ALLOC, SHT_GNU_verneed, sizeof(uint32_t),
".gnu.version_r") {
// Identifiers in verneed section start at 2 because 0 and 1 are reserved
// for VER_NDX_LOCAL and VER_NDX_GLOBAL.
// First identifiers are reserved by verdef section if it exist.
NextIndex = getVerDefNum() + 1;
}
template <class ELFT> void VersionNeedSection<ELFT>::addSymbol(Symbol *SS) {
auto &File = cast<SharedFile<ELFT>>(*SS->File);
if (SS->VerdefIndex == VER_NDX_GLOBAL) {
SS->VersionId = VER_NDX_GLOBAL;
return;
}
// If we don't already know that we need an Elf_Verneed for this DSO, prepare
// to create one by adding it to our needed list and creating a dynstr entry
// for the soname.
if (File.VerdefMap.empty())
Needed.push_back({&File, In.DynStrTab->addString(File.SoName)});
const typename ELFT::Verdef *Ver = File.Verdefs[SS->VerdefIndex];
typename SharedFile<ELFT>::NeededVer &NV = File.VerdefMap[Ver];
// If we don't already know that we need an Elf_Vernaux for this Elf_Verdef,
// prepare to create one by allocating a version identifier and creating a
// dynstr entry for the version name.
if (NV.Index == 0) {
NV.StrTab = In.DynStrTab->addString(File.getStringTable().data() +
Ver->getAux()->vda_name);
NV.Index = NextIndex++;
}
SS->VersionId = NV.Index;
}
template <class ELFT> void VersionNeedSection<ELFT>::writeTo(uint8_t *Buf) {
// The Elf_Verneeds need to appear first, followed by the Elf_Vernauxs.
auto *Verneed = reinterpret_cast<Elf_Verneed *>(Buf);
auto *Vernaux = reinterpret_cast<Elf_Vernaux *>(Verneed + Needed.size());
for (std::pair<SharedFile<ELFT> *, size_t> &P : Needed) {
// Create an Elf_Verneed for this DSO.
Verneed->vn_version = 1;
Verneed->vn_cnt = P.first->VerdefMap.size();
Verneed->vn_file = P.second;
Verneed->vn_aux =
reinterpret_cast<char *>(Vernaux) - reinterpret_cast<char *>(Verneed);
Verneed->vn_next = sizeof(Elf_Verneed);
++Verneed;
// Create the Elf_Vernauxs for this Elf_Verneed. The loop iterates over
// VerdefMap, which will only contain references to needed version
// definitions. Each Elf_Vernaux is based on the information contained in
// the Elf_Verdef in the source DSO. This loop iterates over a std::map of
// pointers, but is deterministic because the pointers refer to Elf_Verdef
// data structures within a single input file.
for (auto &NV : P.first->VerdefMap) {
Vernaux->vna_hash = NV.first->vd_hash;
Vernaux->vna_flags = 0;
Vernaux->vna_other = NV.second.Index;
Vernaux->vna_name = NV.second.StrTab;
Vernaux->vna_next = sizeof(Elf_Vernaux);
++Vernaux;
}
Vernaux[-1].vna_next = 0;
}
Verneed[-1].vn_next = 0;
}
template <class ELFT> void VersionNeedSection<ELFT>::finalizeContents() {
if (OutputSection *Sec = In.DynStrTab->getParent())
getParent()->Link = Sec->SectionIndex;
getParent()->Info = Needed.size();
}
template <class ELFT> size_t VersionNeedSection<ELFT>::getSize() const {
unsigned Size = Needed.size() * sizeof(Elf_Verneed);
for (const std::pair<SharedFile<ELFT> *, size_t> &P : Needed)
Size += P.first->VerdefMap.size() * sizeof(Elf_Vernaux);
return Size;
}
template <class ELFT> bool VersionNeedSection<ELFT>::empty() const {
return getNeedNum() == 0;
}
void MergeSyntheticSection::addSection(MergeInputSection *MS) {
MS->Parent = this;
Sections.push_back(MS);
}
MergeTailSection::MergeTailSection(StringRef Name, uint32_t Type,
uint64_t Flags, uint32_t Alignment)
: MergeSyntheticSection(Name, Type, Flags, Alignment),
Builder(StringTableBuilder::RAW, Alignment) {}
size_t MergeTailSection::getSize() const { return Builder.getSize(); }
void MergeTailSection::writeTo(uint8_t *Buf) { Builder.write(Buf); }
void MergeTailSection::finalizeContents() {
// Add all string pieces to the string table builder to create section
// contents.
for (MergeInputSection *Sec : Sections)
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I)
if (Sec->Pieces[I].Live)
Builder.add(Sec->getData(I));
// Fix the string table content. After this, the contents will never change.
Builder.finalize();
// finalize() fixed tail-optimized strings, so we can now get
// offsets of strings. Get an offset for each string and save it
// to a corresponding StringPiece for easy access.
for (MergeInputSection *Sec : Sections)
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I)
if (Sec->Pieces[I].Live)
Sec->Pieces[I].OutputOff = Builder.getOffset(Sec->getData(I));
}
void MergeNoTailSection::writeTo(uint8_t *Buf) {
for (size_t I = 0; I < NumShards; ++I)
Shards[I].write(Buf + ShardOffsets[I]);
}
// This function is very hot (i.e. it can take several seconds to finish)
// because sometimes the number of inputs is in an order of magnitude of
// millions. So, we use multi-threading.
//
// For any strings S and T, we know S is not mergeable with T if S's hash
// value is different from T's. If that's the case, we can safely put S and
// T into different string builders without worrying about merge misses.
// We do it in parallel.
void MergeNoTailSection::finalizeContents() {
// Initializes string table builders.
for (size_t I = 0; I < NumShards; ++I)
Shards.emplace_back(StringTableBuilder::RAW, Alignment);
// Concurrency level. Must be a power of 2 to avoid expensive modulo
// operations in the following tight loop.
size_t Concurrency = 1;
if (ThreadsEnabled)
Concurrency =
std::min<size_t>(PowerOf2Floor(hardware_concurrency()), NumShards);
// Add section pieces to the builders.
parallelForEachN(0, Concurrency, [&](size_t ThreadId) {
for (MergeInputSection *Sec : Sections) {
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I) {
size_t ShardId = getShardId(Sec->Pieces[I].Hash);
if ((ShardId & (Concurrency - 1)) == ThreadId && Sec->Pieces[I].Live)
Sec->Pieces[I].OutputOff = Shards[ShardId].add(Sec->getData(I));
}
}
});
// Compute an in-section offset for each shard.
size_t Off = 0;
for (size_t I = 0; I < NumShards; ++I) {
Shards[I].finalizeInOrder();
if (Shards[I].getSize() > 0)
Off = alignTo(Off, Alignment);
ShardOffsets[I] = Off;
Off += Shards[I].getSize();
}
Size = Off;
// So far, section pieces have offsets from beginning of shards, but
// we want offsets from beginning of the whole section. Fix them.
parallelForEach(Sections, [&](MergeInputSection *Sec) {
for (size_t I = 0, E = Sec->Pieces.size(); I != E; ++I)
if (Sec->Pieces[I].Live)
Sec->Pieces[I].OutputOff +=
ShardOffsets[getShardId(Sec->Pieces[I].Hash)];
});
}
static MergeSyntheticSection *createMergeSynthetic(StringRef Name,
uint32_t Type,
uint64_t Flags,
uint32_t Alignment) {
bool ShouldTailMerge = (Flags & SHF_STRINGS) && Config->Optimize >= 2;
if (ShouldTailMerge)
return make<MergeTailSection>(Name, Type, Flags, Alignment);
return make<MergeNoTailSection>(Name, Type, Flags, Alignment);
}
template <class ELFT> void elf::splitSections() {
// splitIntoPieces needs to be called on each MergeInputSection
// before calling finalizeContents().
parallelForEach(InputSections, [](InputSectionBase *Sec) {
if (auto *S = dyn_cast<MergeInputSection>(Sec))
S->splitIntoPieces();
else if (auto *Eh = dyn_cast<EhInputSection>(Sec))
Eh->split<ELFT>();
});
}
// This function scans over the inputsections to create mergeable
// synthetic sections.
//
// It removes MergeInputSections from the input section array and adds
// new synthetic sections at the location of the first input section
// that it replaces. It then finalizes each synthetic section in order
// to compute an output offset for each piece of each input section.
void elf::mergeSections() {
std::vector<MergeSyntheticSection *> MergeSections;
for (InputSectionBase *&S : InputSections) {
MergeInputSection *MS = dyn_cast<MergeInputSection>(S);
if (!MS)
continue;
// We do not want to handle sections that are not alive, so just remove
// them instead of trying to merge.
if (!MS->Live) {
S = nullptr;
continue;
}
StringRef OutsecName = getOutputSectionName(MS);
uint32_t Alignment = std::max<uint32_t>(MS->Alignment, MS->Entsize);
auto I = llvm::find_if(MergeSections, [=](MergeSyntheticSection *Sec) {
// While we could create a single synthetic section for two different
// values of Entsize, it is better to take Entsize into consideration.
//
// With a single synthetic section no two pieces with different Entsize
// could be equal, so we may as well have two sections.
//
// Using Entsize in here also allows us to propagate it to the synthetic
// section.
return Sec->Name == OutsecName && Sec->Flags == MS->Flags &&
Sec->Entsize == MS->Entsize && Sec->Alignment == Alignment;
});
if (I == MergeSections.end()) {
MergeSyntheticSection *Syn =
createMergeSynthetic(OutsecName, MS->Type, MS->Flags, Alignment);
MergeSections.push_back(Syn);
I = std::prev(MergeSections.end());
S = Syn;
Syn->Entsize = MS->Entsize;
} else {
S = nullptr;
}
(*I)->addSection(MS);
}
for (auto *MS : MergeSections)
MS->finalizeContents();
std::vector<InputSectionBase *> &V = InputSections;
V.erase(std::remove(V.begin(), V.end(), nullptr), V.end());
}
MipsRldMapSection::MipsRldMapSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE, SHT_PROGBITS, Config->Wordsize,
".rld_map") {}
ARMExidxSentinelSection::ARMExidxSentinelSection()
: SyntheticSection(SHF_ALLOC | SHF_LINK_ORDER, SHT_ARM_EXIDX,
Config->Wordsize, ".ARM.exidx") {}
// Write a terminating sentinel entry to the end of the .ARM.exidx table.
// This section will have been sorted last in the .ARM.exidx table.
// This table entry will have the form:
// | PREL31 upper bound of code that has exception tables | EXIDX_CANTUNWIND |
// The sentinel must have the PREL31 value of an address higher than any
// address described by any other table entry.
void ARMExidxSentinelSection::writeTo(uint8_t *Buf) {
assert(Highest);
uint64_t S = Highest->getVA(Highest->getSize());
uint64_t P = getVA();
Target->relocateOne(Buf, R_ARM_PREL31, S - P);
write32le(Buf + 4, 1);
}
// The sentinel has to be removed if there are no other .ARM.exidx entries.
bool ARMExidxSentinelSection::empty() const {
for (InputSection *IS : getInputSections(getParent()))
if (!isa<ARMExidxSentinelSection>(IS))
return false;
return true;
}
bool ARMExidxSentinelSection::classof(const SectionBase *D) {
return D->kind() == InputSectionBase::Synthetic && D->Type == SHT_ARM_EXIDX;
}
ThunkSection::ThunkSection(OutputSection *OS, uint64_t Off)
: SyntheticSection(SHF_ALLOC | SHF_EXECINSTR, SHT_PROGBITS,
Config->Wordsize, ".text.thunk") {
this->Parent = OS;
this->OutSecOff = Off;
}
void ThunkSection::addThunk(Thunk *T) {
Thunks.push_back(T);
T->addSymbols(*this);
}
void ThunkSection::writeTo(uint8_t *Buf) {
for (Thunk *T : Thunks)
T->writeTo(Buf + T->Offset);
}
InputSection *ThunkSection::getTargetInputSection() const {
if (Thunks.empty())
return nullptr;
const Thunk *T = Thunks.front();
return T->getTargetInputSection();
}
bool ThunkSection::assignOffsets() {
uint64_t Off = 0;
for (Thunk *T : Thunks) {
Off = alignTo(Off, T->Alignment);
T->setOffset(Off);
uint32_t Size = T->size();
T->getThunkTargetSym()->Size = Size;
Off += Size;
}
bool Changed = Off != Size;
Size = Off;
return Changed;
}
// If linking position-dependent code then the table will store the addresses
// directly in the binary so the section has type SHT_PROGBITS. If linking
// position-independent code the section has type SHT_NOBITS since it will be
// allocated and filled in by the dynamic linker.
PPC64LongBranchTargetSection::PPC64LongBranchTargetSection()
: SyntheticSection(SHF_ALLOC | SHF_WRITE,
Config->Pic ? SHT_NOBITS : SHT_PROGBITS, 8,
".branch_lt") {}
void PPC64LongBranchTargetSection::addEntry(Symbol &Sym) {
assert(Sym.PPC64BranchltIndex == 0xffff);
Sym.PPC64BranchltIndex = Entries.size();
Entries.push_back(&Sym);
}
size_t PPC64LongBranchTargetSection::getSize() const {
return Entries.size() * 8;
}
void PPC64LongBranchTargetSection::writeTo(uint8_t *Buf) {
assert(Target->GotPltEntrySize == 8);
// If linking non-pic we have the final addresses of the targets and they get
// written to the table directly. For pic the dynamic linker will allocate
// the section and fill it it.
if (Config->Pic)
return;
for (const Symbol *Sym : Entries) {
assert(Sym->getVA());
// Need calls to branch to the local entry-point since a long-branch
// must be a local-call.
write64(Buf,
Sym->getVA() + getPPC64GlobalEntryToLocalEntryOffset(Sym->StOther));
Buf += Target->GotPltEntrySize;
}
}
bool PPC64LongBranchTargetSection::empty() const {
// `removeUnusedSyntheticSections()` is called before thunk allocation which
// is too early to determine if this section will be empty or not. We need
// Finalized to keep the section alive until after thunk creation. Finalized
// only gets set to true once `finalizeSections()` is called after thunk
// creation. Becuase of this, if we don't create any long-branch thunks we end
// up with an empty .branch_lt section in the binary.
return Finalized && Entries.empty();
}
InStruct elf::In;
template GdbIndexSection *GdbIndexSection::create<ELF32LE>();
template GdbIndexSection *GdbIndexSection::create<ELF32BE>();
template GdbIndexSection *GdbIndexSection::create<ELF64LE>();
template GdbIndexSection *GdbIndexSection::create<ELF64BE>();
template void elf::splitSections<ELF32LE>();
template void elf::splitSections<ELF32BE>();
template void elf::splitSections<ELF64LE>();
template void elf::splitSections<ELF64BE>();
template void EhFrameSection::addSection<ELF32LE>(InputSectionBase *);
template void EhFrameSection::addSection<ELF32BE>(InputSectionBase *);
template void EhFrameSection::addSection<ELF64LE>(InputSectionBase *);
template void EhFrameSection::addSection<ELF64BE>(InputSectionBase *);
template void PltSection::addEntry<ELF32LE>(Symbol &Sym);
template void PltSection::addEntry<ELF32BE>(Symbol &Sym);
template void PltSection::addEntry<ELF64LE>(Symbol &Sym);
template void PltSection::addEntry<ELF64BE>(Symbol &Sym);
template void MipsGotSection::build<ELF32LE>();
template void MipsGotSection::build<ELF32BE>();
template void MipsGotSection::build<ELF64LE>();
template void MipsGotSection::build<ELF64BE>();
template class elf::MipsAbiFlagsSection<ELF32LE>;
template class elf::MipsAbiFlagsSection<ELF32BE>;
template class elf::MipsAbiFlagsSection<ELF64LE>;
template class elf::MipsAbiFlagsSection<ELF64BE>;
template class elf::MipsOptionsSection<ELF32LE>;
template class elf::MipsOptionsSection<ELF32BE>;
template class elf::MipsOptionsSection<ELF64LE>;
template class elf::MipsOptionsSection<ELF64BE>;
template class elf::MipsReginfoSection<ELF32LE>;
template class elf::MipsReginfoSection<ELF32BE>;
template class elf::MipsReginfoSection<ELF64LE>;
template class elf::MipsReginfoSection<ELF64BE>;
template class elf::DynamicSection<ELF32LE>;
template class elf::DynamicSection<ELF32BE>;
template class elf::DynamicSection<ELF64LE>;
template class elf::DynamicSection<ELF64BE>;
template class elf::RelocationSection<ELF32LE>;
template class elf::RelocationSection<ELF32BE>;
template class elf::RelocationSection<ELF64LE>;
template class elf::RelocationSection<ELF64BE>;
template class elf::AndroidPackedRelocationSection<ELF32LE>;
template class elf::AndroidPackedRelocationSection<ELF32BE>;
template class elf::AndroidPackedRelocationSection<ELF64LE>;
template class elf::AndroidPackedRelocationSection<ELF64BE>;
template class elf::RelrSection<ELF32LE>;
template class elf::RelrSection<ELF32BE>;
template class elf::RelrSection<ELF64LE>;
template class elf::RelrSection<ELF64BE>;
template class elf::SymbolTableSection<ELF32LE>;
template class elf::SymbolTableSection<ELF32BE>;
template class elf::SymbolTableSection<ELF64LE>;
template class elf::SymbolTableSection<ELF64BE>;
template class elf::VersionTableSection<ELF32LE>;
template class elf::VersionTableSection<ELF32BE>;
template class elf::VersionTableSection<ELF64LE>;
template class elf::VersionTableSection<ELF64BE>;
template class elf::VersionNeedSection<ELF32LE>;
template class elf::VersionNeedSection<ELF32BE>;
template class elf::VersionNeedSection<ELF64LE>;
template class elf::VersionNeedSection<ELF64BE>;
Index: head/contrib/llvm/tools/lld/ELF/Writer.cpp
===================================================================
--- head/contrib/llvm/tools/lld/ELF/Writer.cpp (revision 350466)
+++ head/contrib/llvm/tools/lld/ELF/Writer.cpp (revision 350467)
@@ -1,2545 +1,2543 @@
//===- Writer.cpp ---------------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "Writer.h"
#include "AArch64ErrataFix.h"
#include "CallGraphSort.h"
#include "Config.h"
#include "Filesystem.h"
#include "LinkerScript.h"
#include "MapFile.h"
#include "OutputSections.h"
#include "Relocations.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "lld/Common/Threads.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringSwitch.h"
#include <climits>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
using namespace llvm::support;
using namespace llvm::support::endian;
using namespace lld;
using namespace lld::elf;
namespace {
// The writer writes a SymbolTable result to a file.
template <class ELFT> class Writer {
public:
Writer() : Buffer(errorHandler().OutputBuffer) {}
typedef typename ELFT::Shdr Elf_Shdr;
typedef typename ELFT::Ehdr Elf_Ehdr;
typedef typename ELFT::Phdr Elf_Phdr;
void run();
private:
void copyLocalSymbols();
void addSectionSymbols();
void forEachRelSec(llvm::function_ref<void(InputSectionBase &)> Fn);
void sortSections();
void resolveShfLinkOrder();
void maybeAddThunks();
void sortInputSections();
void finalizeSections();
void checkExecuteOnly();
void setReservedSymbolSections();
std::vector<PhdrEntry *> createPhdrs();
void removeEmptyPTLoad();
void addPtArmExid(std::vector<PhdrEntry *> &Phdrs);
void assignFileOffsets();
void assignFileOffsetsBinary();
void setPhdrs();
void checkSections();
void fixSectionAlignments();
void openFile();
void writeTrapInstr();
void writeHeader();
void writeSections();
void writeSectionsBinary();
void writeBuildId();
std::unique_ptr<FileOutputBuffer> &Buffer;
void addRelIpltSymbols();
void addStartEndSymbols();
void addStartStopSymbols(OutputSection *Sec);
std::vector<PhdrEntry *> Phdrs;
uint64_t FileSize;
uint64_t SectionHeaderOff;
};
} // anonymous namespace
static bool isSectionPrefix(StringRef Prefix, StringRef Name) {
return Name.startswith(Prefix) || Name == Prefix.drop_back();
}
StringRef elf::getOutputSectionName(const InputSectionBase *S) {
if (Config->Relocatable)
return S->Name;
// This is for --emit-relocs. If .text.foo is emitted as .text.bar, we want
// to emit .rela.text.foo as .rela.text.bar for consistency (this is not
// technically required, but not doing it is odd). This code guarantees that.
if (auto *IS = dyn_cast<InputSection>(S)) {
if (InputSectionBase *Rel = IS->getRelocatedSection()) {
OutputSection *Out = Rel->getOutputSection();
if (S->Type == SHT_RELA)
return Saver.save(".rela" + Out->Name);
return Saver.save(".rel" + Out->Name);
}
}
// This check is for -z keep-text-section-prefix. This option separates text
// sections with prefix ".text.hot", ".text.unlikely", ".text.startup" or
// ".text.exit".
// When enabled, this allows identifying the hot code region (.text.hot) in
// the final binary which can be selectively mapped to huge pages or mlocked,
// for instance.
if (Config->ZKeepTextSectionPrefix)
for (StringRef V :
{".text.hot.", ".text.unlikely.", ".text.startup.", ".text.exit."})
if (isSectionPrefix(V, S->Name))
return V.drop_back();
for (StringRef V :
{".text.", ".rodata.", ".data.rel.ro.", ".data.", ".bss.rel.ro.",
".bss.", ".init_array.", ".fini_array.", ".ctors.", ".dtors.", ".tbss.",
".gcc_except_table.", ".tdata.", ".ARM.exidx.", ".ARM.extab."})
if (isSectionPrefix(V, S->Name))
return V.drop_back();
// CommonSection is identified as "COMMON" in linker scripts.
// By default, it should go to .bss section.
if (S->Name == "COMMON")
return ".bss";
return S->Name;
}
static bool needsInterpSection() {
return !SharedFiles.empty() && !Config->DynamicLinker.empty() &&
Script->needsInterpSection();
}
template <class ELFT> void elf::writeResult() { Writer<ELFT>().run(); }
template <class ELFT> void Writer<ELFT>::removeEmptyPTLoad() {
llvm::erase_if(Phdrs, [&](const PhdrEntry *P) {
if (P->p_type != PT_LOAD)
return false;
if (!P->FirstSec)
return true;
uint64_t Size = P->LastSec->Addr + P->LastSec->Size - P->FirstSec->Addr;
return Size == 0;
});
}
template <class ELFT> static void combineEhFrameSections() {
for (InputSectionBase *&S : InputSections) {
EhInputSection *ES = dyn_cast<EhInputSection>(S);
if (!ES || !ES->Live)
continue;
In.EhFrame->addSection<ELFT>(ES);
S = nullptr;
}
std::vector<InputSectionBase *> &V = InputSections;
V.erase(std::remove(V.begin(), V.end(), nullptr), V.end());
}
static Defined *addOptionalRegular(StringRef Name, SectionBase *Sec,
uint64_t Val, uint8_t StOther = STV_HIDDEN,
uint8_t Binding = STB_GLOBAL) {
Symbol *S = Symtab->find(Name);
if (!S || S->isDefined())
return nullptr;
return Symtab->addDefined(Name, StOther, STT_NOTYPE, Val,
/*Size=*/0, Binding, Sec,
/*File=*/nullptr);
}
static Defined *addAbsolute(StringRef Name) {
return Symtab->addDefined(Name, STV_HIDDEN, STT_NOTYPE, 0, 0, STB_GLOBAL,
nullptr, nullptr);
}
// The linker is expected to define some symbols depending on
// the linking result. This function defines such symbols.
void elf::addReservedSymbols() {
if (Config->EMachine == EM_MIPS) {
// Define _gp for MIPS. st_value of _gp symbol will be updated by Writer
// so that it points to an absolute address which by default is relative
// to GOT. Default offset is 0x7ff0.
// See "Global Data Symbols" in Chapter 6 in the following document:
// ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
ElfSym::MipsGp = addAbsolute("_gp");
// On MIPS O32 ABI, _gp_disp is a magic symbol designates offset between
// start of function and 'gp' pointer into GOT.
if (Symtab->find("_gp_disp"))
ElfSym::MipsGpDisp = addAbsolute("_gp_disp");
// The __gnu_local_gp is a magic symbol equal to the current value of 'gp'
// pointer. This symbol is used in the code generated by .cpload pseudo-op
// in case of using -mno-shared option.
// https://sourceware.org/ml/binutils/2004-12/msg00094.html
if (Symtab->find("__gnu_local_gp"))
ElfSym::MipsLocalGp = addAbsolute("__gnu_local_gp");
}
// The Power Architecture 64-bit v2 ABI defines a TableOfContents (TOC) which
// combines the typical ELF GOT with the small data sections. It commonly
// includes .got .toc .sdata .sbss. The .TOC. symbol replaces both
// _GLOBAL_OFFSET_TABLE_ and _SDA_BASE_ from the 32-bit ABI. It is used to
// represent the TOC base which is offset by 0x8000 bytes from the start of
// the .got section.
// We do not allow _GLOBAL_OFFSET_TABLE_ to be defined by input objects as the
// correctness of some relocations depends on its value.
StringRef GotTableSymName =
(Config->EMachine == EM_PPC64) ? ".TOC." : "_GLOBAL_OFFSET_TABLE_";
if (Symbol *S = Symtab->find(GotTableSymName)) {
if (S->isDefined())
error(toString(S->File) + " cannot redefine linker defined symbol '" +
GotTableSymName + "'");
else
ElfSym::GlobalOffsetTable = Symtab->addDefined(
GotTableSymName, STV_HIDDEN, STT_NOTYPE, Target->GotBaseSymOff,
/*Size=*/0, STB_GLOBAL, Out::ElfHeader,
/*File=*/nullptr);
}
// __ehdr_start is the location of ELF file headers. Note that we define
// this symbol unconditionally even when using a linker script, which
// differs from the behavior implemented by GNU linker which only define
// this symbol if ELF headers are in the memory mapped segment.
addOptionalRegular("__ehdr_start", Out::ElfHeader, 0, STV_HIDDEN);
// __executable_start is not documented, but the expectation of at
// least the Android libc is that it points to the ELF header.
addOptionalRegular("__executable_start", Out::ElfHeader, 0, STV_HIDDEN);
// __dso_handle symbol is passed to cxa_finalize as a marker to identify
// each DSO. The address of the symbol doesn't matter as long as they are
// different in different DSOs, so we chose the start address of the DSO.
addOptionalRegular("__dso_handle", Out::ElfHeader, 0, STV_HIDDEN);
// If linker script do layout we do not need to create any standart symbols.
if (Script->HasSectionsCommand)
return;
auto Add = [](StringRef S, int64_t Pos) {
return addOptionalRegular(S, Out::ElfHeader, Pos, STV_DEFAULT);
};
ElfSym::Bss = Add("__bss_start", 0);
ElfSym::End1 = Add("end", -1);
ElfSym::End2 = Add("_end", -1);
ElfSym::Etext1 = Add("etext", -1);
ElfSym::Etext2 = Add("_etext", -1);
ElfSym::Edata1 = Add("edata", -1);
ElfSym::Edata2 = Add("_edata", -1);
}
static OutputSection *findSection(StringRef Name) {
for (BaseCommand *Base : Script->SectionCommands)
if (auto *Sec = dyn_cast<OutputSection>(Base))
if (Sec->Name == Name)
return Sec;
return nullptr;
}
// Initialize Out members.
template <class ELFT> static void createSyntheticSections() {
// Initialize all pointers with NULL. This is needed because
// you can call lld::elf::main more than once as a library.
memset(&Out::First, 0, sizeof(Out));
auto Add = [](InputSectionBase *Sec) { InputSections.push_back(Sec); };
In.DynStrTab = make<StringTableSection>(".dynstr", true);
In.Dynamic = make<DynamicSection<ELFT>>();
if (Config->AndroidPackDynRelocs) {
In.RelaDyn = make<AndroidPackedRelocationSection<ELFT>>(
Config->IsRela ? ".rela.dyn" : ".rel.dyn");
} else {
In.RelaDyn = make<RelocationSection<ELFT>>(
Config->IsRela ? ".rela.dyn" : ".rel.dyn", Config->ZCombreloc);
}
In.ShStrTab = make<StringTableSection>(".shstrtab", false);
Out::ProgramHeaders = make<OutputSection>("", 0, SHF_ALLOC);
Out::ProgramHeaders->Alignment = Config->Wordsize;
if (needsInterpSection()) {
In.Interp = createInterpSection();
Add(In.Interp);
}
if (Config->Strip != StripPolicy::All) {
In.StrTab = make<StringTableSection>(".strtab", false);
In.SymTab = make<SymbolTableSection<ELFT>>(*In.StrTab);
In.SymTabShndx = make<SymtabShndxSection>();
}
if (Config->BuildId != BuildIdKind::None) {
In.BuildId = make<BuildIdSection>();
Add(In.BuildId);
}
In.Bss = make<BssSection>(".bss", 0, 1);
Add(In.Bss);
// If there is a SECTIONS command and a .data.rel.ro section name use name
// .data.rel.ro.bss so that we match in the .data.rel.ro output section.
// This makes sure our relro is contiguous.
bool HasDataRelRo = Script->HasSectionsCommand && findSection(".data.rel.ro");
In.BssRelRo =
make<BssSection>(HasDataRelRo ? ".data.rel.ro.bss" : ".bss.rel.ro", 0, 1);
Add(In.BssRelRo);
// Add MIPS-specific sections.
if (Config->EMachine == EM_MIPS) {
if (!Config->Shared && Config->HasDynSymTab) {
In.MipsRldMap = make<MipsRldMapSection>();
Add(In.MipsRldMap);
}
if (auto *Sec = MipsAbiFlagsSection<ELFT>::create())
Add(Sec);
if (auto *Sec = MipsOptionsSection<ELFT>::create())
Add(Sec);
if (auto *Sec = MipsReginfoSection<ELFT>::create())
Add(Sec);
}
if (Config->HasDynSymTab) {
In.DynSymTab = make<SymbolTableSection<ELFT>>(*In.DynStrTab);
Add(In.DynSymTab);
InX<ELFT>::VerSym = make<VersionTableSection<ELFT>>();
Add(InX<ELFT>::VerSym);
if (!Config->VersionDefinitions.empty()) {
In.VerDef = make<VersionDefinitionSection>();
Add(In.VerDef);
}
InX<ELFT>::VerNeed = make<VersionNeedSection<ELFT>>();
Add(InX<ELFT>::VerNeed);
if (Config->GnuHash) {
In.GnuHashTab = make<GnuHashTableSection>();
Add(In.GnuHashTab);
}
if (Config->SysvHash) {
In.HashTab = make<HashTableSection>();
Add(In.HashTab);
}
Add(In.Dynamic);
Add(In.DynStrTab);
Add(In.RelaDyn);
}
if (Config->RelrPackDynRelocs) {
In.RelrDyn = make<RelrSection<ELFT>>();
Add(In.RelrDyn);
}
// Add .got. MIPS' .got is so different from the other archs,
// it has its own class.
if (Config->EMachine == EM_MIPS) {
In.MipsGot = make<MipsGotSection>();
Add(In.MipsGot);
} else {
In.Got = make<GotSection>();
Add(In.Got);
}
if (Config->EMachine == EM_PPC64) {
In.PPC64LongBranchTarget = make<PPC64LongBranchTargetSection>();
Add(In.PPC64LongBranchTarget);
}
In.GotPlt = make<GotPltSection>();
Add(In.GotPlt);
In.IgotPlt = make<IgotPltSection>();
Add(In.IgotPlt);
if (Config->GdbIndex) {
In.GdbIndex = GdbIndexSection::create<ELFT>();
Add(In.GdbIndex);
}
// We always need to add rel[a].plt to output if it has entries.
// Even for static linking it can contain R_[*]_IRELATIVE relocations.
In.RelaPlt = make<RelocationSection<ELFT>>(
Config->IsRela ? ".rela.plt" : ".rel.plt", false /*Sort*/);
Add(In.RelaPlt);
// The RelaIplt immediately follows .rel.plt (.rel.dyn for ARM) to ensure
// that the IRelative relocations are processed last by the dynamic loader.
// We cannot place the iplt section in .rel.dyn when Android relocation
// packing is enabled because that would cause a section type mismatch.
// However, because the Android dynamic loader reads .rel.plt after .rel.dyn,
// we can get the desired behaviour by placing the iplt section in .rel.plt.
In.RelaIplt = make<RelocationSection<ELFT>>(
(Config->EMachine == EM_ARM && !Config->AndroidPackDynRelocs)
? ".rel.dyn"
: In.RelaPlt->Name,
false /*Sort*/);
Add(In.RelaIplt);
In.Plt = make<PltSection>(false);
Add(In.Plt);
In.Iplt = make<PltSection>(true);
Add(In.Iplt);
// .note.GNU-stack is always added when we are creating a re-linkable
// object file. Other linkers are using the presence of this marker
// section to control the executable-ness of the stack area, but that
// is irrelevant these days. Stack area should always be non-executable
// by default. So we emit this section unconditionally.
if (Config->Relocatable)
Add(make<GnuStackSection>());
if (!Config->Relocatable) {
if (Config->EhFrameHdr) {
In.EhFrameHdr = make<EhFrameHeader>();
Add(In.EhFrameHdr);
}
In.EhFrame = make<EhFrameSection>();
Add(In.EhFrame);
}
if (In.SymTab)
Add(In.SymTab);
if (In.SymTabShndx)
Add(In.SymTabShndx);
Add(In.ShStrTab);
if (In.StrTab)
Add(In.StrTab);
if (Config->EMachine == EM_ARM && !Config->Relocatable)
// Add a sentinel to terminate .ARM.exidx. It helps an unwinder
// to find the exact address range of the last entry.
Add(make<ARMExidxSentinelSection>());
}
// The main function of the writer.
template <class ELFT> void Writer<ELFT>::run() {
// Create linker-synthesized sections such as .got or .plt.
// Such sections are of type input section.
createSyntheticSections<ELFT>();
if (!Config->Relocatable)
combineEhFrameSections<ELFT>();
// We want to process linker script commands. When SECTIONS command
// is given we let it create sections.
Script->processSectionCommands();
// Linker scripts controls how input sections are assigned to output sections.
// Input sections that were not handled by scripts are called "orphans", and
// they are assigned to output sections by the default rule. Process that.
Script->addOrphanSections();
if (Config->Discard != DiscardPolicy::All)
copyLocalSymbols();
if (Config->CopyRelocs)
addSectionSymbols();
// Now that we have a complete set of output sections. This function
// completes section contents. For example, we need to add strings
// to the string table, and add entries to .got and .plt.
// finalizeSections does that.
finalizeSections();
checkExecuteOnly();
if (errorCount())
return;
Script->assignAddresses();
// If -compressed-debug-sections is specified, we need to compress
// .debug_* sections. Do it right now because it changes the size of
// output sections.
for (OutputSection *Sec : OutputSections)
Sec->maybeCompress<ELFT>();
Script->allocateHeaders(Phdrs);
// Remove empty PT_LOAD to avoid causing the dynamic linker to try to mmap a
// 0 sized region. This has to be done late since only after assignAddresses
// we know the size of the sections.
removeEmptyPTLoad();
if (!Config->OFormatBinary)
assignFileOffsets();
else
assignFileOffsetsBinary();
setPhdrs();
if (Config->Relocatable)
for (OutputSection *Sec : OutputSections)
Sec->Addr = 0;
if (Config->CheckSections)
checkSections();
// It does not make sense try to open the file if we have error already.
if (errorCount())
return;
// Write the result down to a file.
openFile();
if (errorCount())
return;
if (!Config->OFormatBinary) {
writeTrapInstr();
writeHeader();
writeSections();
} else {
writeSectionsBinary();
}
// Backfill .note.gnu.build-id section content. This is done at last
// because the content is usually a hash value of the entire output file.
writeBuildId();
if (errorCount())
return;
// Handle -Map and -cref options.
writeMapFile();
writeCrossReferenceTable();
if (errorCount())
return;
if (auto E = Buffer->commit())
error("failed to write to the output file: " + toString(std::move(E)));
}
static bool shouldKeepInSymtab(SectionBase *Sec, StringRef SymName,
const Symbol &B) {
if (B.isSection())
return false;
if (Config->Discard == DiscardPolicy::None)
return true;
// If -emit-reloc is given, all symbols including local ones need to be
// copied because they may be referenced by relocations.
if (Config->EmitRelocs)
return true;
// In ELF assembly .L symbols are normally discarded by the assembler.
// If the assembler fails to do so, the linker discards them if
// * --discard-locals is used.
// * The symbol is in a SHF_MERGE section, which is normally the reason for
// the assembler keeping the .L symbol.
if (!SymName.startswith(".L") && !SymName.empty())
return true;
if (Config->Discard == DiscardPolicy::Locals)
return false;
return !Sec || !(Sec->Flags & SHF_MERGE);
}
static bool includeInSymtab(const Symbol &B) {
if (!B.isLocal() && !B.IsUsedInRegularObj)
return false;
if (auto *D = dyn_cast<Defined>(&B)) {
// Always include absolute symbols.
SectionBase *Sec = D->Section;
if (!Sec)
return true;
Sec = Sec->Repl;
// Exclude symbols pointing to garbage-collected sections.
if (isa<InputSectionBase>(Sec) && !Sec->Live)
return false;
if (auto *S = dyn_cast<MergeInputSection>(Sec))
if (!S->getSectionPiece(D->Value)->Live)
return false;
return true;
}
return B.Used;
}
// Local symbols are not in the linker's symbol table. This function scans
// each object file's symbol table to copy local symbols to the output.
template <class ELFT> void Writer<ELFT>::copyLocalSymbols() {
if (!In.SymTab)
return;
for (InputFile *File : ObjectFiles) {
ObjFile<ELFT> *F = cast<ObjFile<ELFT>>(File);
for (Symbol *B : F->getLocalSymbols()) {
if (!B->isLocal())
fatal(toString(F) +
": broken object: getLocalSymbols returns a non-local symbol");
auto *DR = dyn_cast<Defined>(B);
// No reason to keep local undefined symbol in symtab.
if (!DR)
continue;
if (!includeInSymtab(*B))
continue;
SectionBase *Sec = DR->Section;
if (!shouldKeepInSymtab(Sec, B->getName(), *B))
continue;
In.SymTab->addSymbol(B);
}
}
}
// Create a section symbol for each output section so that we can represent
// relocations that point to the section. If we know that no relocation is
// referring to a section (that happens if the section is a synthetic one), we
// don't create a section symbol for that section.
template <class ELFT> void Writer<ELFT>::addSectionSymbols() {
for (BaseCommand *Base : Script->SectionCommands) {
auto *Sec = dyn_cast<OutputSection>(Base);
if (!Sec)
continue;
auto I = llvm::find_if(Sec->SectionCommands, [](BaseCommand *Base) {
if (auto *ISD = dyn_cast<InputSectionDescription>(Base))
return !ISD->Sections.empty();
return false;
});
if (I == Sec->SectionCommands.end())
continue;
InputSection *IS = cast<InputSectionDescription>(*I)->Sections[0];
// Relocations are not using REL[A] section symbols.
if (IS->Type == SHT_REL || IS->Type == SHT_RELA)
continue;
// Unlike other synthetic sections, mergeable output sections contain data
// copied from input sections, and there may be a relocation pointing to its
// contents if -r or -emit-reloc are given.
if (isa<SyntheticSection>(IS) && !(IS->Flags & SHF_MERGE))
continue;
auto *Sym =
make<Defined>(IS->File, "", STB_LOCAL, /*StOther=*/0, STT_SECTION,
/*Value=*/0, /*Size=*/0, IS);
In.SymTab->addSymbol(Sym);
}
}
// Today's loaders have a feature to make segments read-only after
// processing dynamic relocations to enhance security. PT_GNU_RELRO
// is defined for that.
//
// This function returns true if a section needs to be put into a
// PT_GNU_RELRO segment.
static bool isRelroSection(const OutputSection *Sec) {
if (!Config->ZRelro)
return false;
uint64_t Flags = Sec->Flags;
// Non-allocatable or non-writable sections don't need RELRO because
// they are not writable or not even mapped to memory in the first place.
// RELRO is for sections that are essentially read-only but need to
// be writable only at process startup to allow dynamic linker to
// apply relocations.
if (!(Flags & SHF_ALLOC) || !(Flags & SHF_WRITE))
return false;
// Once initialized, TLS data segments are used as data templates
// for a thread-local storage. For each new thread, runtime
// allocates memory for a TLS and copy templates there. No thread
// are supposed to use templates directly. Thus, it can be in RELRO.
if (Flags & SHF_TLS)
return true;
// .init_array, .preinit_array and .fini_array contain pointers to
// functions that are executed on process startup or exit. These
// pointers are set by the static linker, and they are not expected
// to change at runtime. But if you are an attacker, you could do
// interesting things by manipulating pointers in .fini_array, for
// example. So they are put into RELRO.
uint32_t Type = Sec->Type;
if (Type == SHT_INIT_ARRAY || Type == SHT_FINI_ARRAY ||
Type == SHT_PREINIT_ARRAY)
return true;
// .got contains pointers to external symbols. They are resolved by
// the dynamic linker when a module is loaded into memory, and after
// that they are not expected to change. So, it can be in RELRO.
if (In.Got && Sec == In.Got->getParent())
return true;
// .toc is a GOT-ish section for PowerPC64. Their contents are accessed
// through r2 register, which is reserved for that purpose. Since r2 is used
// for accessing .got as well, .got and .toc need to be close enough in the
// virtual address space. Usually, .toc comes just after .got. Since we place
// .got into RELRO, .toc needs to be placed into RELRO too.
if (Sec->Name.equals(".toc"))
return true;
// .got.plt contains pointers to external function symbols. They are
// by default resolved lazily, so we usually cannot put it into RELRO.
// However, if "-z now" is given, the lazy symbol resolution is
// disabled, which enables us to put it into RELRO.
if (Sec == In.GotPlt->getParent())
return Config->ZNow;
// .dynamic section contains data for the dynamic linker, and
// there's no need to write to it at runtime, so it's better to put
// it into RELRO.
if (Sec == In.Dynamic->getParent())
return true;
// Sections with some special names are put into RELRO. This is a
// bit unfortunate because section names shouldn't be significant in
// ELF in spirit. But in reality many linker features depend on
// magic section names.
StringRef S = Sec->Name;
return S == ".data.rel.ro" || S == ".bss.rel.ro" || S == ".ctors" ||
S == ".dtors" || S == ".jcr" || S == ".eh_frame" ||
S == ".openbsd.randomdata";
}
// We compute a rank for each section. The rank indicates where the
// section should be placed in the file. Instead of using simple
// numbers (0,1,2...), we use a series of flags. One for each decision
// point when placing the section.
// Using flags has two key properties:
// * It is easy to check if a give branch was taken.
// * It is easy two see how similar two ranks are (see getRankProximity).
enum RankFlags {
RF_NOT_ADDR_SET = 1 << 18,
RF_NOT_ALLOC = 1 << 17,
RF_NOT_INTERP = 1 << 16,
RF_NOT_NOTE = 1 << 15,
RF_WRITE = 1 << 14,
RF_EXEC_WRITE = 1 << 13,
RF_EXEC = 1 << 12,
RF_RODATA = 1 << 11,
RF_NON_TLS_BSS = 1 << 10,
RF_NON_TLS_BSS_RO = 1 << 9,
RF_NOT_TLS = 1 << 8,
RF_BSS = 1 << 7,
RF_PPC_NOT_TOCBSS = 1 << 6,
RF_PPC_TOCL = 1 << 5,
RF_PPC_TOC = 1 << 4,
RF_PPC_GOT = 1 << 3,
RF_PPC_BRANCH_LT = 1 << 2,
RF_MIPS_GPREL = 1 << 1,
RF_MIPS_NOT_GOT = 1 << 0
};
static unsigned getSectionRank(const OutputSection *Sec) {
unsigned Rank = 0;
// We want to put section specified by -T option first, so we
// can start assigning VA starting from them later.
if (Config->SectionStartMap.count(Sec->Name))
return Rank;
Rank |= RF_NOT_ADDR_SET;
// Allocatable sections go first to reduce the total PT_LOAD size and
// so debug info doesn't change addresses in actual code.
if (!(Sec->Flags & SHF_ALLOC))
return Rank | RF_NOT_ALLOC;
// Put .interp first because some loaders want to see that section
// on the first page of the executable file when loaded into memory.
if (Sec->Name == ".interp")
return Rank;
Rank |= RF_NOT_INTERP;
// Put .note sections (which make up one PT_NOTE) at the beginning so that
// they are likely to be included in a core file even if core file size is
// limited. In particular, we want a .note.gnu.build-id and a .note.tag to be
// included in a core to match core files with executables.
if (Sec->Type == SHT_NOTE)
return Rank;
Rank |= RF_NOT_NOTE;
// Sort sections based on their access permission in the following
// order: R, RX, RWX, RW. This order is based on the following
// considerations:
// * Read-only sections come first such that they go in the
// PT_LOAD covering the program headers at the start of the file.
// * Read-only, executable sections come next.
// * Writable, executable sections follow such that .plt on
// architectures where it needs to be writable will be placed
// between .text and .data.
// * Writable sections come last, such that .bss lands at the very
// end of the last PT_LOAD.
bool IsExec = Sec->Flags & SHF_EXECINSTR;
bool IsWrite = Sec->Flags & SHF_WRITE;
if (IsExec) {
if (IsWrite)
Rank |= RF_EXEC_WRITE;
else
Rank |= RF_EXEC;
} else if (IsWrite) {
Rank |= RF_WRITE;
} else if (Sec->Type == SHT_PROGBITS) {
// Make non-executable and non-writable PROGBITS sections (e.g .rodata
// .eh_frame) closer to .text. They likely contain PC or GOT relative
// relocations and there could be relocation overflow if other huge sections
// (.dynstr .dynsym) were placed in between.
Rank |= RF_RODATA;
}
// If we got here we know that both A and B are in the same PT_LOAD.
bool IsTls = Sec->Flags & SHF_TLS;
bool IsNoBits = Sec->Type == SHT_NOBITS;
// The first requirement we have is to put (non-TLS) nobits sections last. The
// reason is that the only thing the dynamic linker will see about them is a
// p_memsz that is larger than p_filesz. Seeing that it zeros the end of the
// PT_LOAD, so that has to correspond to the nobits sections.
bool IsNonTlsNoBits = IsNoBits && !IsTls;
if (IsNonTlsNoBits)
Rank |= RF_NON_TLS_BSS;
// We place nobits RelRo sections before plain r/w ones, and non-nobits RelRo
// sections after r/w ones, so that the RelRo sections are contiguous.
bool IsRelRo = isRelroSection(Sec);
if (IsNonTlsNoBits && !IsRelRo)
Rank |= RF_NON_TLS_BSS_RO;
if (!IsNonTlsNoBits && IsRelRo)
Rank |= RF_NON_TLS_BSS_RO;
// The TLS initialization block needs to be a single contiguous block in a R/W
// PT_LOAD, so stick TLS sections directly before the other RelRo R/W
// sections. The TLS NOBITS sections are placed here as they don't take up
// virtual address space in the PT_LOAD.
if (!IsTls)
Rank |= RF_NOT_TLS;
// Within the TLS initialization block, the non-nobits sections need to appear
// first.
if (IsNoBits)
Rank |= RF_BSS;
// Some architectures have additional ordering restrictions for sections
// within the same PT_LOAD.
if (Config->EMachine == EM_PPC64) {
// PPC64 has a number of special SHT_PROGBITS+SHF_ALLOC+SHF_WRITE sections
// that we would like to make sure appear is a specific order to maximize
// their coverage by a single signed 16-bit offset from the TOC base
// pointer. Conversely, the special .tocbss section should be first among
// all SHT_NOBITS sections. This will put it next to the loaded special
// PPC64 sections (and, thus, within reach of the TOC base pointer).
StringRef Name = Sec->Name;
if (Name != ".tocbss")
Rank |= RF_PPC_NOT_TOCBSS;
if (Name == ".toc1")
Rank |= RF_PPC_TOCL;
if (Name == ".toc")
Rank |= RF_PPC_TOC;
if (Name == ".got")
Rank |= RF_PPC_GOT;
if (Name == ".branch_lt")
Rank |= RF_PPC_BRANCH_LT;
}
if (Config->EMachine == EM_MIPS) {
// All sections with SHF_MIPS_GPREL flag should be grouped together
// because data in these sections is addressable with a gp relative address.
if (Sec->Flags & SHF_MIPS_GPREL)
Rank |= RF_MIPS_GPREL;
if (Sec->Name != ".got")
Rank |= RF_MIPS_NOT_GOT;
}
return Rank;
}
static bool compareSections(const BaseCommand *ACmd, const BaseCommand *BCmd) {
const OutputSection *A = cast<OutputSection>(ACmd);
const OutputSection *B = cast<OutputSection>(BCmd);
if (A->SortRank != B->SortRank)
return A->SortRank < B->SortRank;
if (!(A->SortRank & RF_NOT_ADDR_SET))
return Config->SectionStartMap.lookup(A->Name) <
Config->SectionStartMap.lookup(B->Name);
return false;
}
void PhdrEntry::add(OutputSection *Sec) {
LastSec = Sec;
if (!FirstSec)
FirstSec = Sec;
p_align = std::max(p_align, Sec->Alignment);
if (p_type == PT_LOAD)
Sec->PtLoad = this;
}
// The beginning and the ending of .rel[a].plt section are marked
// with __rel[a]_iplt_{start,end} symbols if it is a statically linked
// executable. The runtime needs these symbols in order to resolve
// all IRELATIVE relocs on startup. For dynamic executables, we don't
// need these symbols, since IRELATIVE relocs are resolved through GOT
// and PLT. For details, see http://www.airs.com/blog/archives/403.
template <class ELFT> void Writer<ELFT>::addRelIpltSymbols() {
if (Config->Relocatable || needsInterpSection())
return;
// By default, __rela_iplt_{start,end} belong to a dummy section 0
// because .rela.plt might be empty and thus removed from output.
// We'll override Out::ElfHeader with In.RelaIplt later when we are
// sure that .rela.plt exists in output.
ElfSym::RelaIpltStart = addOptionalRegular(
Config->IsRela ? "__rela_iplt_start" : "__rel_iplt_start",
Out::ElfHeader, 0, STV_HIDDEN, STB_WEAK);
ElfSym::RelaIpltEnd = addOptionalRegular(
Config->IsRela ? "__rela_iplt_end" : "__rel_iplt_end",
Out::ElfHeader, 0, STV_HIDDEN, STB_WEAK);
}
template <class ELFT>
void Writer<ELFT>::forEachRelSec(
llvm::function_ref<void(InputSectionBase &)> Fn) {
// Scan all relocations. Each relocation goes through a series
// of tests to determine if it needs special treatment, such as
// creating GOT, PLT, copy relocations, etc.
// Note that relocations for non-alloc sections are directly
// processed by InputSection::relocateNonAlloc.
for (InputSectionBase *IS : InputSections)
if (IS->Live && isa<InputSection>(IS) && (IS->Flags & SHF_ALLOC))
Fn(*IS);
for (EhInputSection *ES : In.EhFrame->Sections)
Fn(*ES);
}
// This function generates assignments for predefined symbols (e.g. _end or
// _etext) and inserts them into the commands sequence to be processed at the
// appropriate time. This ensures that the value is going to be correct by the
// time any references to these symbols are processed and is equivalent to
// defining these symbols explicitly in the linker script.
template <class ELFT> void Writer<ELFT>::setReservedSymbolSections() {
if (ElfSym::GlobalOffsetTable) {
// The _GLOBAL_OFFSET_TABLE_ symbol is defined by target convention usually
// to the start of the .got or .got.plt section.
InputSection *GotSection = In.GotPlt;
if (!Target->GotBaseSymInGotPlt)
GotSection = In.MipsGot ? cast<InputSection>(In.MipsGot)
: cast<InputSection>(In.Got);
ElfSym::GlobalOffsetTable->Section = GotSection;
}
// .rela_iplt_{start,end} mark the start and the end of .rela.plt section.
if (ElfSym::RelaIpltStart && !In.RelaIplt->empty()) {
ElfSym::RelaIpltStart->Section = In.RelaIplt;
ElfSym::RelaIpltEnd->Section = In.RelaIplt;
ElfSym::RelaIpltEnd->Value = In.RelaIplt->getSize();
}
PhdrEntry *Last = nullptr;
PhdrEntry *LastRO = nullptr;
for (PhdrEntry *P : Phdrs) {
if (P->p_type != PT_LOAD)
continue;
Last = P;
if (!(P->p_flags & PF_W))
LastRO = P;
}
if (LastRO) {
// _etext is the first location after the last read-only loadable segment.
if (ElfSym::Etext1)
ElfSym::Etext1->Section = LastRO->LastSec;
if (ElfSym::Etext2)
ElfSym::Etext2->Section = LastRO->LastSec;
}
if (Last) {
// _edata points to the end of the last mapped initialized section.
OutputSection *Edata = nullptr;
for (OutputSection *OS : OutputSections) {
if (OS->Type != SHT_NOBITS)
Edata = OS;
if (OS == Last->LastSec)
break;
}
if (ElfSym::Edata1)
ElfSym::Edata1->Section = Edata;
if (ElfSym::Edata2)
ElfSym::Edata2->Section = Edata;
// _end is the first location after the uninitialized data region.
if (ElfSym::End1)
ElfSym::End1->Section = Last->LastSec;
if (ElfSym::End2)
ElfSym::End2->Section = Last->LastSec;
}
if (ElfSym::Bss)
ElfSym::Bss->Section = findSection(".bss");
// Setup MIPS _gp_disp/__gnu_local_gp symbols which should
// be equal to the _gp symbol's value.
if (ElfSym::MipsGp) {
// Find GP-relative section with the lowest address
// and use this address to calculate default _gp value.
for (OutputSection *OS : OutputSections) {
if (OS->Flags & SHF_MIPS_GPREL) {
ElfSym::MipsGp->Section = OS;
ElfSym::MipsGp->Value = 0x7ff0;
break;
}
}
}
}
// We want to find how similar two ranks are.
// The more branches in getSectionRank that match, the more similar they are.
// Since each branch corresponds to a bit flag, we can just use
// countLeadingZeros.
static int getRankProximityAux(OutputSection *A, OutputSection *B) {
return countLeadingZeros(A->SortRank ^ B->SortRank);
}
static int getRankProximity(OutputSection *A, BaseCommand *B) {
if (auto *Sec = dyn_cast<OutputSection>(B))
return getRankProximityAux(A, Sec);
return -1;
}
// When placing orphan sections, we want to place them after symbol assignments
// so that an orphan after
// begin_foo = .;
// foo : { *(foo) }
// end_foo = .;
// doesn't break the intended meaning of the begin/end symbols.
// We don't want to go over sections since findOrphanPos is the
// one in charge of deciding the order of the sections.
// We don't want to go over changes to '.', since doing so in
// rx_sec : { *(rx_sec) }
// . = ALIGN(0x1000);
// /* The RW PT_LOAD starts here*/
// rw_sec : { *(rw_sec) }
// would mean that the RW PT_LOAD would become unaligned.
static bool shouldSkip(BaseCommand *Cmd) {
if (auto *Assign = dyn_cast<SymbolAssignment>(Cmd))
return Assign->Name != ".";
return false;
}
// We want to place orphan sections so that they share as much
// characteristics with their neighbors as possible. For example, if
// both are rw, or both are tls.
template <typename ELFT>
static std::vector<BaseCommand *>::iterator
findOrphanPos(std::vector<BaseCommand *>::iterator B,
std::vector<BaseCommand *>::iterator E) {
OutputSection *Sec = cast<OutputSection>(*E);
// Find the first element that has as close a rank as possible.
auto I = std::max_element(B, E, [=](BaseCommand *A, BaseCommand *B) {
return getRankProximity(Sec, A) < getRankProximity(Sec, B);
});
if (I == E)
return E;
// Consider all existing sections with the same proximity.
int Proximity = getRankProximity(Sec, *I);
for (; I != E; ++I) {
auto *CurSec = dyn_cast<OutputSection>(*I);
if (!CurSec)
continue;
if (getRankProximity(Sec, CurSec) != Proximity ||
Sec->SortRank < CurSec->SortRank)
break;
}
auto IsOutputSec = [](BaseCommand *Cmd) { return isa<OutputSection>(Cmd); };
auto J = std::find_if(llvm::make_reverse_iterator(I),
llvm::make_reverse_iterator(B), IsOutputSec);
I = J.base();
// As a special case, if the orphan section is the last section, put
// it at the very end, past any other commands.
// This matches bfd's behavior and is convenient when the linker script fully
// specifies the start of the file, but doesn't care about the end (the non
// alloc sections for example).
auto NextSec = std::find_if(I, E, IsOutputSec);
if (NextSec == E)
return E;
while (I != E && shouldSkip(*I))
++I;
return I;
}
// Builds section order for handling --symbol-ordering-file.
static DenseMap<const InputSectionBase *, int> buildSectionOrder() {
DenseMap<const InputSectionBase *, int> SectionOrder;
// Use the rarely used option -call-graph-ordering-file to sort sections.
if (!Config->CallGraphProfile.empty())
return computeCallGraphProfileOrder();
if (Config->SymbolOrderingFile.empty())
return SectionOrder;
struct SymbolOrderEntry {
int Priority;
bool Present;
};
// Build a map from symbols to their priorities. Symbols that didn't
// appear in the symbol ordering file have the lowest priority 0.
// All explicitly mentioned symbols have negative (higher) priorities.
DenseMap<StringRef, SymbolOrderEntry> SymbolOrder;
int Priority = -Config->SymbolOrderingFile.size();
for (StringRef S : Config->SymbolOrderingFile)
SymbolOrder.insert({S, {Priority++, false}});
// Build a map from sections to their priorities.
auto AddSym = [&](Symbol &Sym) {
auto It = SymbolOrder.find(Sym.getName());
if (It == SymbolOrder.end())
return;
SymbolOrderEntry &Ent = It->second;
Ent.Present = true;
maybeWarnUnorderableSymbol(&Sym);
if (auto *D = dyn_cast<Defined>(&Sym)) {
if (auto *Sec = dyn_cast_or_null<InputSectionBase>(D->Section)) {
int &Priority = SectionOrder[cast<InputSectionBase>(Sec->Repl)];
Priority = std::min(Priority, Ent.Priority);
}
}
};
// We want both global and local symbols. We get the global ones from the
// symbol table and iterate the object files for the local ones.
for (Symbol *Sym : Symtab->getSymbols())
if (!Sym->isLazy())
AddSym(*Sym);
for (InputFile *File : ObjectFiles)
for (Symbol *Sym : File->getSymbols())
if (Sym->isLocal())
AddSym(*Sym);
if (Config->WarnSymbolOrdering)
for (auto OrderEntry : SymbolOrder)
if (!OrderEntry.second.Present)
warn("symbol ordering file: no such symbol: " + OrderEntry.first);
return SectionOrder;
}
// Sorts the sections in ISD according to the provided section order.
static void
sortISDBySectionOrder(InputSectionDescription *ISD,
const DenseMap<const InputSectionBase *, int> &Order) {
std::vector<InputSection *> UnorderedSections;
std::vector<std::pair<InputSection *, int>> OrderedSections;
uint64_t UnorderedSize = 0;
for (InputSection *IS : ISD->Sections) {
auto I = Order.find(IS);
if (I == Order.end()) {
UnorderedSections.push_back(IS);
UnorderedSize += IS->getSize();
continue;
}
OrderedSections.push_back({IS, I->second});
}
llvm::sort(OrderedSections, [&](std::pair<InputSection *, int> A,
std::pair<InputSection *, int> B) {
return A.second < B.second;
});
// Find an insertion point for the ordered section list in the unordered
// section list. On targets with limited-range branches, this is the mid-point
// of the unordered section list. This decreases the likelihood that a range
// extension thunk will be needed to enter or exit the ordered region. If the
// ordered section list is a list of hot functions, we can generally expect
// the ordered functions to be called more often than the unordered functions,
// making it more likely that any particular call will be within range, and
// therefore reducing the number of thunks required.
//
// For example, imagine that you have 8MB of hot code and 32MB of cold code.
// If the layout is:
//
// 8MB hot
// 32MB cold
//
// only the first 8-16MB of the cold code (depending on which hot function it
// is actually calling) can call the hot code without a range extension thunk.
// However, if we use this layout:
//
// 16MB cold
// 8MB hot
// 16MB cold
//
// both the last 8-16MB of the first block of cold code and the first 8-16MB
// of the second block of cold code can call the hot code without a thunk. So
// we effectively double the amount of code that could potentially call into
// the hot code without a thunk.
size_t InsPt = 0;
if (Target->getThunkSectionSpacing() && !OrderedSections.empty()) {
uint64_t UnorderedPos = 0;
for (; InsPt != UnorderedSections.size(); ++InsPt) {
UnorderedPos += UnorderedSections[InsPt]->getSize();
if (UnorderedPos > UnorderedSize / 2)
break;
}
}
ISD->Sections.clear();
for (InputSection *IS : makeArrayRef(UnorderedSections).slice(0, InsPt))
ISD->Sections.push_back(IS);
for (std::pair<InputSection *, int> P : OrderedSections)
ISD->Sections.push_back(P.first);
for (InputSection *IS : makeArrayRef(UnorderedSections).slice(InsPt))
ISD->Sections.push_back(IS);
}
static void sortSection(OutputSection *Sec,
const DenseMap<const InputSectionBase *, int> &Order) {
StringRef Name = Sec->Name;
// Sort input sections by section name suffixes for
// __attribute__((init_priority(N))).
if (Name == ".init_array" || Name == ".fini_array") {
if (!Script->HasSectionsCommand)
Sec->sortInitFini();
return;
}
// Sort input sections by the special rule for .ctors and .dtors.
if (Name == ".ctors" || Name == ".dtors") {
if (!Script->HasSectionsCommand)
Sec->sortCtorsDtors();
return;
}
// Never sort these.
if (Name == ".init" || Name == ".fini")
return;
// Sort input sections by priority using the list provided
// by --symbol-ordering-file.
if (!Order.empty())
for (BaseCommand *B : Sec->SectionCommands)
if (auto *ISD = dyn_cast<InputSectionDescription>(B))
sortISDBySectionOrder(ISD, Order);
}
// If no layout was provided by linker script, we want to apply default
// sorting for special input sections. This also handles --symbol-ordering-file.
template <class ELFT> void Writer<ELFT>::sortInputSections() {
// Build the order once since it is expensive.
DenseMap<const InputSectionBase *, int> Order = buildSectionOrder();
for (BaseCommand *Base : Script->SectionCommands)
if (auto *Sec = dyn_cast<OutputSection>(Base))
sortSection(Sec, Order);
}
template <class ELFT> void Writer<ELFT>::sortSections() {
Script->adjustSectionsBeforeSorting();
// Don't sort if using -r. It is not necessary and we want to preserve the
// relative order for SHF_LINK_ORDER sections.
if (Config->Relocatable)
return;
sortInputSections();
for (BaseCommand *Base : Script->SectionCommands) {
auto *OS = dyn_cast<OutputSection>(Base);
if (!OS)
continue;
OS->SortRank = getSectionRank(OS);
// We want to assign rude approximation values to OutSecOff fields
// to know the relative order of the input sections. We use it for
// sorting SHF_LINK_ORDER sections. See resolveShfLinkOrder().
uint64_t I = 0;
for (InputSection *Sec : getInputSections(OS))
Sec->OutSecOff = I++;
}
if (!Script->HasSectionsCommand) {
// We know that all the OutputSections are contiguous in this case.
auto IsSection = [](BaseCommand *Base) { return isa<OutputSection>(Base); };
std::stable_sort(
llvm::find_if(Script->SectionCommands, IsSection),
llvm::find_if(llvm::reverse(Script->SectionCommands), IsSection).base(),
compareSections);
return;
}
// Orphan sections are sections present in the input files which are
// not explicitly placed into the output file by the linker script.
//
// The sections in the linker script are already in the correct
// order. We have to figuere out where to insert the orphan
// sections.
//
// The order of the sections in the script is arbitrary and may not agree with
// compareSections. This means that we cannot easily define a strict weak
// ordering. To see why, consider a comparison of a section in the script and
// one not in the script. We have a two simple options:
// * Make them equivalent (a is not less than b, and b is not less than a).
// The problem is then that equivalence has to be transitive and we can
// have sections a, b and c with only b in a script and a less than c
// which breaks this property.
// * Use compareSectionsNonScript. Given that the script order doesn't have
// to match, we can end up with sections a, b, c, d where b and c are in the
// script and c is compareSectionsNonScript less than b. In which case d
// can be equivalent to c, a to b and d < a. As a concrete example:
// .a (rx) # not in script
// .b (rx) # in script
// .c (ro) # in script
// .d (ro) # not in script
//
// The way we define an order then is:
// * Sort only the orphan sections. They are in the end right now.
// * Move each orphan section to its preferred position. We try
// to put each section in the last position where it can share
// a PT_LOAD.
//
// There is some ambiguity as to where exactly a new entry should be
// inserted, because Commands contains not only output section
// commands but also other types of commands such as symbol assignment
// expressions. There's no correct answer here due to the lack of the
// formal specification of the linker script. We use heuristics to
// determine whether a new output command should be added before or
// after another commands. For the details, look at shouldSkip
// function.
auto I = Script->SectionCommands.begin();
auto E = Script->SectionCommands.end();
auto NonScriptI = std::find_if(I, E, [](BaseCommand *Base) {
if (auto *Sec = dyn_cast<OutputSection>(Base))
return Sec->SectionIndex == UINT32_MAX;
return false;
});
// Sort the orphan sections.
std::stable_sort(NonScriptI, E, compareSections);
// As a horrible special case, skip the first . assignment if it is before any
// section. We do this because it is common to set a load address by starting
// the script with ". = 0xabcd" and the expectation is that every section is
// after that.
auto FirstSectionOrDotAssignment =
std::find_if(I, E, [](BaseCommand *Cmd) { return !shouldSkip(Cmd); });
if (FirstSectionOrDotAssignment != E &&
isa<SymbolAssignment>(**FirstSectionOrDotAssignment))
++FirstSectionOrDotAssignment;
I = FirstSectionOrDotAssignment;
while (NonScriptI != E) {
auto Pos = findOrphanPos<ELFT>(I, NonScriptI);
OutputSection *Orphan = cast<OutputSection>(*NonScriptI);
// As an optimization, find all sections with the same sort rank
// and insert them with one rotate.
unsigned Rank = Orphan->SortRank;
auto End = std::find_if(NonScriptI + 1, E, [=](BaseCommand *Cmd) {
return cast<OutputSection>(Cmd)->SortRank != Rank;
});
std::rotate(Pos, NonScriptI, End);
NonScriptI = End;
}
Script->adjustSectionsAfterSorting();
}
static bool compareByFilePosition(InputSection *A, InputSection *B) {
// Synthetic, i. e. a sentinel section, should go last.
if (A->kind() == InputSectionBase::Synthetic ||
B->kind() == InputSectionBase::Synthetic)
return A->kind() != InputSectionBase::Synthetic;
InputSection *LA = A->getLinkOrderDep();
InputSection *LB = B->getLinkOrderDep();
OutputSection *AOut = LA->getParent();
OutputSection *BOut = LB->getParent();
if (AOut != BOut)
return AOut->SectionIndex < BOut->SectionIndex;
return LA->OutSecOff < LB->OutSecOff;
}
// This function is used by the --merge-exidx-entries to detect duplicate
// .ARM.exidx sections. It is Arm only.
//
// The .ARM.exidx section is of the form:
// | PREL31 offset to function | Unwind instructions for function |
// where the unwind instructions are either a small number of unwind
// instructions inlined into the table entry, the special CANT_UNWIND value of
// 0x1 or a PREL31 offset into a .ARM.extab Section that contains unwind
// instructions.
//
// We return true if all the unwind instructions in the .ARM.exidx entries of
// Cur can be merged into the last entry of Prev.
static bool isDuplicateArmExidxSec(InputSection *Prev, InputSection *Cur) {
// References to .ARM.Extab Sections have bit 31 clear and are not the
// special EXIDX_CANTUNWIND bit-pattern.
auto IsExtabRef = [](uint32_t Unwind) {
return (Unwind & 0x80000000) == 0 && Unwind != 0x1;
};
struct ExidxEntry {
ulittle32_t Fn;
ulittle32_t Unwind;
};
// Get the last table Entry from the previous .ARM.exidx section.
const ExidxEntry &PrevEntry = Prev->getDataAs<ExidxEntry>().back();
if (IsExtabRef(PrevEntry.Unwind))
return false;
// We consider the unwind instructions of an .ARM.exidx table entry
// a duplicate if the previous unwind instructions if:
// - Both are the special EXIDX_CANTUNWIND.
// - Both are the same inline unwind instructions.
// We do not attempt to follow and check links into .ARM.extab tables as
// consecutive identical entries are rare and the effort to check that they
// are identical is high.
for (const ExidxEntry Entry : Cur->getDataAs<ExidxEntry>())
if (IsExtabRef(Entry.Unwind) || Entry.Unwind != PrevEntry.Unwind)
return false;
// All table entries in this .ARM.exidx Section can be merged into the
// previous Section.
return true;
}
template <class ELFT> void Writer<ELFT>::resolveShfLinkOrder() {
for (OutputSection *Sec : OutputSections) {
if (!(Sec->Flags & SHF_LINK_ORDER))
continue;
// Link order may be distributed across several InputSectionDescriptions
// but sort must consider them all at once.
std::vector<InputSection **> ScriptSections;
std::vector<InputSection *> Sections;
for (BaseCommand *Base : Sec->SectionCommands) {
if (auto *ISD = dyn_cast<InputSectionDescription>(Base)) {
for (InputSection *&IS : ISD->Sections) {
ScriptSections.push_back(&IS);
Sections.push_back(IS);
}
}
}
std::stable_sort(Sections.begin(), Sections.end(), compareByFilePosition);
if (!Config->Relocatable && Config->EMachine == EM_ARM &&
Sec->Type == SHT_ARM_EXIDX) {
if (auto *Sentinel = dyn_cast<ARMExidxSentinelSection>(Sections.back())) {
assert(Sections.size() >= 2 &&
"We should create a sentinel section only if there are "
"alive regular exidx sections.");
// The last executable section is required to fill the sentinel.
// Remember it here so that we don't have to find it again.
Sentinel->Highest = Sections[Sections.size() - 2]->getLinkOrderDep();
}
// The EHABI for the Arm Architecture permits consecutive identical
// table entries to be merged. We use a simple implementation that
// removes a .ARM.exidx Input Section if it can be merged into the
// previous one. This does not require any rewriting of InputSection
// contents but misses opportunities for fine grained deduplication
// where only a subset of the InputSection contents can be merged.
if (Config->MergeArmExidx) {
size_t Prev = 0;
// The last one is a sentinel entry which should not be removed.
for (size_t I = 1; I < Sections.size() - 1; ++I) {
if (isDuplicateArmExidxSec(Sections[Prev], Sections[I]))
Sections[I] = nullptr;
else
Prev = I;
}
}
}
for (int I = 0, N = Sections.size(); I < N; ++I)
*ScriptSections[I] = Sections[I];
// Remove the Sections we marked as duplicate earlier.
for (BaseCommand *Base : Sec->SectionCommands)
if (auto *ISD = dyn_cast<InputSectionDescription>(Base))
llvm::erase_if(ISD->Sections, [](InputSection *IS) { return !IS; });
}
}
// For most RISC ISAs, we need to generate content that depends on the address
// of InputSections. For example some architectures such as AArch64 use small
// displacements for jump instructions that is the linker's responsibility for
// creating range extension thunks for. As the generation of the content may
// also alter InputSection addresses we must converge to a fixed point.
template <class ELFT> void Writer<ELFT>::maybeAddThunks() {
if (!Target->NeedsThunks && !Config->AndroidPackDynRelocs &&
!Config->RelrPackDynRelocs)
return;
ThunkCreator TC;
AArch64Err843419Patcher A64P;
for (;;) {
bool Changed = false;
Script->assignAddresses();
if (Target->NeedsThunks)
Changed |= TC.createThunks(OutputSections);
if (Config->FixCortexA53Errata843419) {
if (Changed)
Script->assignAddresses();
Changed |= A64P.createFixes();
}
if (In.MipsGot)
In.MipsGot->updateAllocSize();
Changed |= In.RelaDyn->updateAllocSize();
if (In.RelrDyn)
Changed |= In.RelrDyn->updateAllocSize();
if (!Changed)
return;
}
}
static void finalizeSynthetic(SyntheticSection *Sec) {
if (Sec && !Sec->empty() && Sec->getParent())
Sec->finalizeContents();
}
// In order to allow users to manipulate linker-synthesized sections,
// we had to add synthetic sections to the input section list early,
// even before we make decisions whether they are needed. This allows
// users to write scripts like this: ".mygot : { .got }".
//
// Doing it has an unintended side effects. If it turns out that we
// don't need a .got (for example) at all because there's no
// relocation that needs a .got, we don't want to emit .got.
//
// To deal with the above problem, this function is called after
// scanRelocations is called to remove synthetic sections that turn
// out to be empty.
static void removeUnusedSyntheticSections() {
// All input synthetic sections that can be empty are placed after
// all regular ones. We iterate over them all and exit at first
// non-synthetic.
for (InputSectionBase *S : llvm::reverse(InputSections)) {
SyntheticSection *SS = dyn_cast<SyntheticSection>(S);
if (!SS)
return;
OutputSection *OS = SS->getParent();
if (!OS || !SS->empty())
continue;
// If we reach here, then SS is an unused synthetic section and we want to
// remove it from corresponding input section description of output section.
for (BaseCommand *B : OS->SectionCommands)
if (auto *ISD = dyn_cast<InputSectionDescription>(B))
llvm::erase_if(ISD->Sections,
[=](InputSection *IS) { return IS == SS; });
}
}
// Returns true if a symbol can be replaced at load-time by a symbol
// with the same name defined in other ELF executable or DSO.
static bool computeIsPreemptible(const Symbol &B) {
assert(!B.isLocal());
// Only symbols that appear in dynsym can be preempted.
if (!B.includeInDynsym())
return false;
// Only default visibility symbols can be preempted.
if (B.Visibility != STV_DEFAULT)
return false;
// At this point copy relocations have not been created yet, so any
// symbol that is not defined locally is preemptible.
if (!B.isDefined())
return true;
// If we have a dynamic list it specifies which local symbols are preemptible.
if (Config->HasDynamicList)
return false;
if (!Config->Shared)
return false;
// -Bsymbolic means that definitions are not preempted.
if (Config->Bsymbolic || (Config->BsymbolicFunctions && B.isFunc()))
return false;
return true;
}
// Create output section objects and add them to OutputSections.
template <class ELFT> void Writer<ELFT>::finalizeSections() {
Out::PreinitArray = findSection(".preinit_array");
Out::InitArray = findSection(".init_array");
Out::FiniArray = findSection(".fini_array");
// The linker needs to define SECNAME_start, SECNAME_end and SECNAME_stop
// symbols for sections, so that the runtime can get the start and end
// addresses of each section by section name. Add such symbols.
if (!Config->Relocatable) {
addStartEndSymbols();
for (BaseCommand *Base : Script->SectionCommands)
if (auto *Sec = dyn_cast<OutputSection>(Base))
addStartStopSymbols(Sec);
}
// Add _DYNAMIC symbol. Unlike GNU gold, our _DYNAMIC symbol has no type.
// It should be okay as no one seems to care about the type.
// Even the author of gold doesn't remember why gold behaves that way.
// https://sourceware.org/ml/binutils/2002-03/msg00360.html
if (In.Dynamic->Parent)
Symtab->addDefined("_DYNAMIC", STV_HIDDEN, STT_NOTYPE, 0 /*Value*/,
/*Size=*/0, STB_WEAK, In.Dynamic,
/*File=*/nullptr);
// Define __rel[a]_iplt_{start,end} symbols if needed.
addRelIpltSymbols();
// RISC-V's gp can address +/- 2 KiB, set it to .sdata + 0x800 if not defined.
if (Config->EMachine == EM_RISCV)
if (!dyn_cast_or_null<Defined>(Symtab->find("__global_pointer$")))
addOptionalRegular("__global_pointer$", findSection(".sdata"), 0x800);
// This responsible for splitting up .eh_frame section into
// pieces. The relocation scan uses those pieces, so this has to be
// earlier.
finalizeSynthetic(In.EhFrame);
- for (Symbol *S : Symtab->getSymbols()) {
- if (!S->IsPreemptible)
- S->IsPreemptible = computeIsPreemptible(*S);
- if (S->isGnuIFunc() && Config->ZIfuncnoplt)
- S->ExportDynamic = true;
- }
+ for (Symbol *S : Symtab->getSymbols())
+ S->IsPreemptible |= computeIsPreemptible(*S);
// Scan relocations. This must be done after every symbol is declared so that
// we can correctly decide if a dynamic relocation is needed.
if (!Config->Relocatable)
forEachRelSec(scanRelocations<ELFT>);
+
+ addIRelativeRelocs();
if (In.Plt && !In.Plt->empty())
In.Plt->addSymbols();
if (In.Iplt && !In.Iplt->empty())
In.Iplt->addSymbols();
if (!Config->AllowShlibUndefined) {
// Error on undefined symbols in a shared object, if all of its DT_NEEDED
// entires are seen. These cases would otherwise lead to runtime errors
// reported by the dynamic linker.
//
// ld.bfd traces all DT_NEEDED to emulate the logic of the dynamic linker to
// catch more cases. That is too much for us. Our approach resembles the one
// used in ld.gold, achieves a good balance to be useful but not too smart.
for (InputFile *File : SharedFiles) {
SharedFile<ELFT> *F = cast<SharedFile<ELFT>>(File);
F->AllNeededIsKnown = llvm::all_of(F->DtNeeded, [&](StringRef Needed) {
return Symtab->SoNames.count(Needed);
});
}
for (Symbol *Sym : Symtab->getSymbols())
if (Sym->isUndefined() && !Sym->isWeak())
if (auto *F = dyn_cast_or_null<SharedFile<ELFT>>(Sym->File))
if (F->AllNeededIsKnown)
error(toString(F) + ": undefined reference to " + toString(*Sym));
}
// Now that we have defined all possible global symbols including linker-
// synthesized ones. Visit all symbols to give the finishing touches.
for (Symbol *Sym : Symtab->getSymbols()) {
if (!includeInSymtab(*Sym))
continue;
if (In.SymTab)
In.SymTab->addSymbol(Sym);
if (Sym->includeInDynsym()) {
In.DynSymTab->addSymbol(Sym);
if (auto *File = dyn_cast_or_null<SharedFile<ELFT>>(Sym->File))
if (File->IsNeeded && !Sym->isUndefined())
InX<ELFT>::VerNeed->addSymbol(Sym);
}
}
// Do not proceed if there was an undefined symbol.
if (errorCount())
return;
if (In.MipsGot)
In.MipsGot->build<ELFT>();
removeUnusedSyntheticSections();
sortSections();
// Now that we have the final list, create a list of all the
// OutputSections for convenience.
for (BaseCommand *Base : Script->SectionCommands)
if (auto *Sec = dyn_cast<OutputSection>(Base))
OutputSections.push_back(Sec);
// Prefer command line supplied address over other constraints.
for (OutputSection *Sec : OutputSections) {
auto I = Config->SectionStartMap.find(Sec->Name);
if (I != Config->SectionStartMap.end())
Sec->AddrExpr = [=] { return I->second; };
}
// This is a bit of a hack. A value of 0 means undef, so we set it
// to 1 to make __ehdr_start defined. The section number is not
// particularly relevant.
Out::ElfHeader->SectionIndex = 1;
for (size_t I = 0, E = OutputSections.size(); I != E; ++I) {
OutputSection *Sec = OutputSections[I];
Sec->SectionIndex = I + 1;
Sec->ShName = In.ShStrTab->addString(Sec->Name);
}
// Binary and relocatable output does not have PHDRS.
// The headers have to be created before finalize as that can influence the
// image base and the dynamic section on mips includes the image base.
if (!Config->Relocatable && !Config->OFormatBinary) {
Phdrs = Script->hasPhdrsCommands() ? Script->createPhdrs() : createPhdrs();
addPtArmExid(Phdrs);
Out::ProgramHeaders->Size = sizeof(Elf_Phdr) * Phdrs.size();
// Find the TLS segment. This happens before the section layout loop so that
// Android relocation packing can look up TLS symbol addresses.
for (PhdrEntry *P : Phdrs)
if (P->p_type == PT_TLS)
Out::TlsPhdr = P;
}
// Some symbols are defined in term of program headers. Now that we
// have the headers, we can find out which sections they point to.
setReservedSymbolSections();
// Dynamic section must be the last one in this list and dynamic
// symbol table section (DynSymTab) must be the first one.
finalizeSynthetic(In.DynSymTab);
finalizeSynthetic(In.Bss);
finalizeSynthetic(In.BssRelRo);
finalizeSynthetic(In.GnuHashTab);
finalizeSynthetic(In.HashTab);
finalizeSynthetic(In.SymTabShndx);
finalizeSynthetic(In.ShStrTab);
finalizeSynthetic(In.StrTab);
finalizeSynthetic(In.VerDef);
finalizeSynthetic(In.DynStrTab);
finalizeSynthetic(In.Got);
finalizeSynthetic(In.MipsGot);
finalizeSynthetic(In.IgotPlt);
finalizeSynthetic(In.GotPlt);
finalizeSynthetic(In.RelaDyn);
finalizeSynthetic(In.RelrDyn);
finalizeSynthetic(In.RelaIplt);
finalizeSynthetic(In.RelaPlt);
finalizeSynthetic(In.Plt);
finalizeSynthetic(In.Iplt);
finalizeSynthetic(In.EhFrameHdr);
finalizeSynthetic(InX<ELFT>::VerSym);
finalizeSynthetic(InX<ELFT>::VerNeed);
finalizeSynthetic(In.Dynamic);
if (!Script->HasSectionsCommand && !Config->Relocatable)
fixSectionAlignments();
// After link order processing .ARM.exidx sections can be deduplicated, which
// needs to be resolved before any other address dependent operation.
resolveShfLinkOrder();
// Jump instructions in many ISAs have small displacements, and therefore they
// cannot jump to arbitrary addresses in memory. For example, RISC-V JAL
// instruction can target only +-1 MiB from PC. It is a linker's
// responsibility to create and insert small pieces of code between sections
// to extend the ranges if jump targets are out of range. Such code pieces are
// called "thunks".
//
// We add thunks at this stage. We couldn't do this before this point because
// this is the earliest point where we know sizes of sections and their
// layouts (that are needed to determine if jump targets are in range).
maybeAddThunks();
// maybeAddThunks may have added local symbols to the static symbol table.
finalizeSynthetic(In.SymTab);
finalizeSynthetic(In.PPC64LongBranchTarget);
// Fill other section headers. The dynamic table is finalized
// at the end because some tags like RELSZ depend on result
// of finalizing other sections.
for (OutputSection *Sec : OutputSections)
Sec->finalize<ELFT>();
}
// Ensure data sections are not mixed with executable sections when
// -execute-only is used. -execute-only is a feature to make pages executable
// but not readable, and the feature is currently supported only on AArch64.
template <class ELFT> void Writer<ELFT>::checkExecuteOnly() {
if (!Config->ExecuteOnly)
return;
for (OutputSection *OS : OutputSections)
if (OS->Flags & SHF_EXECINSTR)
for (InputSection *IS : getInputSections(OS))
if (!(IS->Flags & SHF_EXECINSTR))
error("cannot place " + toString(IS) + " into " + toString(OS->Name) +
": -execute-only does not support intermingling data and code");
}
// The linker is expected to define SECNAME_start and SECNAME_end
// symbols for a few sections. This function defines them.
template <class ELFT> void Writer<ELFT>::addStartEndSymbols() {
// If a section does not exist, there's ambiguity as to how we
// define _start and _end symbols for an init/fini section. Since
// the loader assume that the symbols are always defined, we need to
// always define them. But what value? The loader iterates over all
// pointers between _start and _end to run global ctors/dtors, so if
// the section is empty, their symbol values don't actually matter
// as long as _start and _end point to the same location.
//
// That said, we don't want to set the symbols to 0 (which is
// probably the simplest value) because that could cause some
// program to fail to link due to relocation overflow, if their
// program text is above 2 GiB. We use the address of the .text
// section instead to prevent that failure.
//
// In a rare sitaution, .text section may not exist. If that's the
// case, use the image base address as a last resort.
OutputSection *Default = findSection(".text");
if (!Default)
Default = Out::ElfHeader;
auto Define = [=](StringRef Start, StringRef End, OutputSection *OS) {
if (OS) {
addOptionalRegular(Start, OS, 0);
addOptionalRegular(End, OS, -1);
} else {
addOptionalRegular(Start, Default, 0);
addOptionalRegular(End, Default, 0);
}
};
Define("__preinit_array_start", "__preinit_array_end", Out::PreinitArray);
Define("__init_array_start", "__init_array_end", Out::InitArray);
Define("__fini_array_start", "__fini_array_end", Out::FiniArray);
if (OutputSection *Sec = findSection(".ARM.exidx"))
Define("__exidx_start", "__exidx_end", Sec);
}
// If a section name is valid as a C identifier (which is rare because of
// the leading '.'), linkers are expected to define __start_<secname> and
// __stop_<secname> symbols. They are at beginning and end of the section,
// respectively. This is not requested by the ELF standard, but GNU ld and
// gold provide the feature, and used by many programs.
template <class ELFT>
void Writer<ELFT>::addStartStopSymbols(OutputSection *Sec) {
StringRef S = Sec->Name;
if (!isValidCIdentifier(S))
return;
addOptionalRegular(Saver.save("__start_" + S), Sec, 0, STV_PROTECTED);
addOptionalRegular(Saver.save("__stop_" + S), Sec, -1, STV_PROTECTED);
}
static bool needsPtLoad(OutputSection *Sec) {
if (!(Sec->Flags & SHF_ALLOC) || Sec->Noload)
return false;
// Don't allocate VA space for TLS NOBITS sections. The PT_TLS PHDR is
// responsible for allocating space for them, not the PT_LOAD that
// contains the TLS initialization image.
if ((Sec->Flags & SHF_TLS) && Sec->Type == SHT_NOBITS)
return false;
return true;
}
// Linker scripts are responsible for aligning addresses. Unfortunately, most
// linker scripts are designed for creating two PT_LOADs only, one RX and one
// RW. This means that there is no alignment in the RO to RX transition and we
// cannot create a PT_LOAD there.
static uint64_t computeFlags(uint64_t Flags) {
if (Config->Omagic)
return PF_R | PF_W | PF_X;
if (Config->ExecuteOnly && (Flags & PF_X))
return Flags & ~PF_R;
if (Config->SingleRoRx && !(Flags & PF_W))
return Flags | PF_X;
return Flags;
}
// Decide which program headers to create and which sections to include in each
// one.
template <class ELFT> std::vector<PhdrEntry *> Writer<ELFT>::createPhdrs() {
std::vector<PhdrEntry *> Ret;
auto AddHdr = [&](unsigned Type, unsigned Flags) -> PhdrEntry * {
Ret.push_back(make<PhdrEntry>(Type, Flags));
return Ret.back();
};
// The first phdr entry is PT_PHDR which describes the program header itself.
AddHdr(PT_PHDR, PF_R)->add(Out::ProgramHeaders);
// PT_INTERP must be the second entry if exists.
if (OutputSection *Cmd = findSection(".interp"))
AddHdr(PT_INTERP, Cmd->getPhdrFlags())->add(Cmd);
// Add the first PT_LOAD segment for regular output sections.
uint64_t Flags = computeFlags(PF_R);
PhdrEntry *Load = AddHdr(PT_LOAD, Flags);
// Add the headers. We will remove them if they don't fit.
Load->add(Out::ElfHeader);
Load->add(Out::ProgramHeaders);
for (OutputSection *Sec : OutputSections) {
if (!(Sec->Flags & SHF_ALLOC))
break;
if (!needsPtLoad(Sec))
continue;
// Segments are contiguous memory regions that has the same attributes
// (e.g. executable or writable). There is one phdr for each segment.
// Therefore, we need to create a new phdr when the next section has
// different flags or is loaded at a discontiguous address or memory
// region using AT or AT> linker script command, respectively. At the same
// time, we don't want to create a separate load segment for the headers,
// even if the first output section has an AT or AT> attribute.
uint64_t NewFlags = computeFlags(Sec->getPhdrFlags());
if (((Sec->LMAExpr ||
(Sec->LMARegion && (Sec->LMARegion != Load->FirstSec->LMARegion))) &&
Load->LastSec != Out::ProgramHeaders) ||
Sec->MemRegion != Load->FirstSec->MemRegion || Flags != NewFlags) {
Load = AddHdr(PT_LOAD, NewFlags);
Flags = NewFlags;
}
Load->add(Sec);
}
// Add a TLS segment if any.
PhdrEntry *TlsHdr = make<PhdrEntry>(PT_TLS, PF_R);
for (OutputSection *Sec : OutputSections)
if (Sec->Flags & SHF_TLS)
TlsHdr->add(Sec);
if (TlsHdr->FirstSec)
Ret.push_back(TlsHdr);
// Add an entry for .dynamic.
if (OutputSection *Sec = In.Dynamic->getParent())
AddHdr(PT_DYNAMIC, Sec->getPhdrFlags())->add(Sec);
// PT_GNU_RELRO includes all sections that should be marked as
// read-only by dynamic linker after proccessing relocations.
// Current dynamic loaders only support one PT_GNU_RELRO PHDR, give
// an error message if more than one PT_GNU_RELRO PHDR is required.
PhdrEntry *RelRo = make<PhdrEntry>(PT_GNU_RELRO, PF_R);
bool InRelroPhdr = false;
bool IsRelroFinished = false;
for (OutputSection *Sec : OutputSections) {
if (!needsPtLoad(Sec))
continue;
if (isRelroSection(Sec)) {
InRelroPhdr = true;
if (!IsRelroFinished)
RelRo->add(Sec);
else
error("section: " + Sec->Name + " is not contiguous with other relro" +
" sections");
} else if (InRelroPhdr) {
InRelroPhdr = false;
IsRelroFinished = true;
}
}
if (RelRo->FirstSec)
Ret.push_back(RelRo);
// PT_GNU_EH_FRAME is a special section pointing on .eh_frame_hdr.
if (!In.EhFrame->empty() && In.EhFrameHdr && In.EhFrame->getParent() &&
In.EhFrameHdr->getParent())
AddHdr(PT_GNU_EH_FRAME, In.EhFrameHdr->getParent()->getPhdrFlags())
->add(In.EhFrameHdr->getParent());
// PT_OPENBSD_RANDOMIZE is an OpenBSD-specific feature. That makes
// the dynamic linker fill the segment with random data.
if (OutputSection *Cmd = findSection(".openbsd.randomdata"))
AddHdr(PT_OPENBSD_RANDOMIZE, Cmd->getPhdrFlags())->add(Cmd);
// PT_GNU_STACK is a special section to tell the loader to make the
// pages for the stack non-executable. If you really want an executable
// stack, you can pass -z execstack, but that's not recommended for
// security reasons.
unsigned Perm = PF_R | PF_W;
if (Config->ZExecstack)
Perm |= PF_X;
AddHdr(PT_GNU_STACK, Perm)->p_memsz = Config->ZStackSize;
// PT_OPENBSD_WXNEEDED is a OpenBSD-specific header to mark the executable
// is expected to perform W^X violations, such as calling mprotect(2) or
// mmap(2) with PROT_WRITE | PROT_EXEC, which is prohibited by default on
// OpenBSD.
if (Config->ZWxneeded)
AddHdr(PT_OPENBSD_WXNEEDED, PF_X);
// Create one PT_NOTE per a group of contiguous .note sections.
PhdrEntry *Note = nullptr;
for (OutputSection *Sec : OutputSections) {
if (Sec->Type == SHT_NOTE && (Sec->Flags & SHF_ALLOC)) {
if (!Note || Sec->LMAExpr)
Note = AddHdr(PT_NOTE, PF_R);
Note->add(Sec);
} else {
Note = nullptr;
}
}
return Ret;
}
template <class ELFT>
void Writer<ELFT>::addPtArmExid(std::vector<PhdrEntry *> &Phdrs) {
if (Config->EMachine != EM_ARM)
return;
auto I = llvm::find_if(OutputSections, [](OutputSection *Cmd) {
return Cmd->Type == SHT_ARM_EXIDX;
});
if (I == OutputSections.end())
return;
// PT_ARM_EXIDX is the ARM EHABI equivalent of PT_GNU_EH_FRAME
PhdrEntry *ARMExidx = make<PhdrEntry>(PT_ARM_EXIDX, PF_R);
ARMExidx->add(*I);
Phdrs.push_back(ARMExidx);
}
// The first section of each PT_LOAD, the first section in PT_GNU_RELRO and the
// first section after PT_GNU_RELRO have to be page aligned so that the dynamic
// linker can set the permissions.
template <class ELFT> void Writer<ELFT>::fixSectionAlignments() {
auto PageAlign = [](OutputSection *Cmd) {
if (Cmd && !Cmd->AddrExpr)
Cmd->AddrExpr = [=] {
return alignTo(Script->getDot(), Config->MaxPageSize);
};
};
for (const PhdrEntry *P : Phdrs)
if (P->p_type == PT_LOAD && P->FirstSec)
PageAlign(P->FirstSec);
for (const PhdrEntry *P : Phdrs) {
if (P->p_type != PT_GNU_RELRO)
continue;
if (P->FirstSec)
PageAlign(P->FirstSec);
// Find the first section after PT_GNU_RELRO. If it is in a PT_LOAD we
// have to align it to a page.
auto End = OutputSections.end();
auto I = std::find(OutputSections.begin(), End, P->LastSec);
if (I == End || (I + 1) == End)
continue;
OutputSection *Cmd = (*(I + 1));
if (needsPtLoad(Cmd))
PageAlign(Cmd);
}
}
// Compute an in-file position for a given section. The file offset must be the
// same with its virtual address modulo the page size, so that the loader can
// load executables without any address adjustment.
static uint64_t computeFileOffset(OutputSection *OS, uint64_t Off) {
// File offsets are not significant for .bss sections. By convention, we keep
// section offsets monotonically increasing rather than setting to zero.
if (OS->Type == SHT_NOBITS)
return Off;
// If the section is not in a PT_LOAD, we just have to align it.
if (!OS->PtLoad)
return alignTo(Off, OS->Alignment);
// The first section in a PT_LOAD has to have congruent offset and address
// module the page size.
OutputSection *First = OS->PtLoad->FirstSec;
if (OS == First) {
uint64_t Alignment = std::max<uint64_t>(OS->Alignment, Config->MaxPageSize);
return alignTo(Off, Alignment, OS->Addr);
}
// If two sections share the same PT_LOAD the file offset is calculated
// using this formula: Off2 = Off1 + (VA2 - VA1).
return First->Offset + OS->Addr - First->Addr;
}
// Set an in-file position to a given section and returns the end position of
// the section.
static uint64_t setFileOffset(OutputSection *OS, uint64_t Off) {
Off = computeFileOffset(OS, Off);
OS->Offset = Off;
if (OS->Type == SHT_NOBITS)
return Off;
return Off + OS->Size;
}
template <class ELFT> void Writer<ELFT>::assignFileOffsetsBinary() {
uint64_t Off = 0;
for (OutputSection *Sec : OutputSections)
if (Sec->Flags & SHF_ALLOC)
Off = setFileOffset(Sec, Off);
FileSize = alignTo(Off, Config->Wordsize);
}
static std::string rangeToString(uint64_t Addr, uint64_t Len) {
return "[0x" + utohexstr(Addr) + ", 0x" + utohexstr(Addr + Len - 1) + "]";
}
// Assign file offsets to output sections.
template <class ELFT> void Writer<ELFT>::assignFileOffsets() {
uint64_t Off = 0;
Off = setFileOffset(Out::ElfHeader, Off);
Off = setFileOffset(Out::ProgramHeaders, Off);
PhdrEntry *LastRX = nullptr;
for (PhdrEntry *P : Phdrs)
if (P->p_type == PT_LOAD && (P->p_flags & PF_X))
LastRX = P;
for (OutputSection *Sec : OutputSections) {
Off = setFileOffset(Sec, Off);
if (Script->HasSectionsCommand)
continue;
// If this is a last section of the last executable segment and that
// segment is the last loadable segment, align the offset of the
// following section to avoid loading non-segments parts of the file.
if (LastRX && LastRX->LastSec == Sec)
Off = alignTo(Off, Target->PageSize);
}
SectionHeaderOff = alignTo(Off, Config->Wordsize);
FileSize = SectionHeaderOff + (OutputSections.size() + 1) * sizeof(Elf_Shdr);
// Our logic assumes that sections have rising VA within the same segment.
// With use of linker scripts it is possible to violate this rule and get file
// offset overlaps or overflows. That should never happen with a valid script
// which does not move the location counter backwards and usually scripts do
// not do that. Unfortunately, there are apps in the wild, for example, Linux
// kernel, which control segment distribution explicitly and move the counter
// backwards, so we have to allow doing that to support linking them. We
// perform non-critical checks for overlaps in checkSectionOverlap(), but here
// we want to prevent file size overflows because it would crash the linker.
for (OutputSection *Sec : OutputSections) {
if (Sec->Type == SHT_NOBITS)
continue;
if ((Sec->Offset > FileSize) || (Sec->Offset + Sec->Size > FileSize))
error("unable to place section " + Sec->Name + " at file offset " +
rangeToString(Sec->Offset, Sec->Size) +
"; check your linker script for overflows");
}
}
// Finalize the program headers. We call this function after we assign
// file offsets and VAs to all sections.
template <class ELFT> void Writer<ELFT>::setPhdrs() {
for (PhdrEntry *P : Phdrs) {
OutputSection *First = P->FirstSec;
OutputSection *Last = P->LastSec;
if (First) {
P->p_filesz = Last->Offset - First->Offset;
if (Last->Type != SHT_NOBITS)
P->p_filesz += Last->Size;
P->p_memsz = Last->Addr + Last->Size - First->Addr;
P->p_offset = First->Offset;
P->p_vaddr = First->Addr;
if (!P->HasLMA)
P->p_paddr = First->getLMA();
}
if (P->p_type == PT_LOAD) {
P->p_align = std::max<uint64_t>(P->p_align, Config->MaxPageSize);
} else if (P->p_type == PT_GNU_RELRO) {
P->p_align = 1;
// The glibc dynamic loader rounds the size down, so we need to round up
// to protect the last page. This is a no-op on FreeBSD which always
// rounds up.
P->p_memsz = alignTo(P->p_memsz, Target->PageSize);
}
if (P->p_type == PT_TLS && P->p_memsz) {
// The TLS pointer goes after PT_TLS for variant 2 targets. At least glibc
// will align it, so round up the size to make sure the offsets are
// correct.
P->p_memsz = alignTo(P->p_memsz, P->p_align);
}
}
}
// A helper struct for checkSectionOverlap.
namespace {
struct SectionOffset {
OutputSection *Sec;
uint64_t Offset;
};
} // namespace
// Check whether sections overlap for a specific address range (file offsets,
// load and virtual adresses).
static void checkOverlap(StringRef Name, std::vector<SectionOffset> &Sections,
bool IsVirtualAddr) {
llvm::sort(Sections, [=](const SectionOffset &A, const SectionOffset &B) {
return A.Offset < B.Offset;
});
// Finding overlap is easy given a vector is sorted by start position.
// If an element starts before the end of the previous element, they overlap.
for (size_t I = 1, End = Sections.size(); I < End; ++I) {
SectionOffset A = Sections[I - 1];
SectionOffset B = Sections[I];
if (B.Offset >= A.Offset + A.Sec->Size)
continue;
// If both sections are in OVERLAY we allow the overlapping of virtual
// addresses, because it is what OVERLAY was designed for.
if (IsVirtualAddr && A.Sec->InOverlay && B.Sec->InOverlay)
continue;
errorOrWarn("section " + A.Sec->Name + " " + Name +
" range overlaps with " + B.Sec->Name + "\n>>> " + A.Sec->Name +
" range is " + rangeToString(A.Offset, A.Sec->Size) + "\n>>> " +
B.Sec->Name + " range is " +
rangeToString(B.Offset, B.Sec->Size));
}
}
// Check for overlapping sections and address overflows.
//
// In this function we check that none of the output sections have overlapping
// file offsets. For SHF_ALLOC sections we also check that the load address
// ranges and the virtual address ranges don't overlap
template <class ELFT> void Writer<ELFT>::checkSections() {
// First, check that section's VAs fit in available address space for target.
for (OutputSection *OS : OutputSections)
if ((OS->Addr + OS->Size < OS->Addr) ||
(!ELFT::Is64Bits && OS->Addr + OS->Size > UINT32_MAX))
errorOrWarn("section " + OS->Name + " at 0x" + utohexstr(OS->Addr) +
" of size 0x" + utohexstr(OS->Size) +
" exceeds available address space");
// Check for overlapping file offsets. In this case we need to skip any
// section marked as SHT_NOBITS. These sections don't actually occupy space in
// the file so Sec->Offset + Sec->Size can overlap with others. If --oformat
// binary is specified only add SHF_ALLOC sections are added to the output
// file so we skip any non-allocated sections in that case.
std::vector<SectionOffset> FileOffs;
for (OutputSection *Sec : OutputSections)
if (Sec->Size > 0 && Sec->Type != SHT_NOBITS &&
(!Config->OFormatBinary || (Sec->Flags & SHF_ALLOC)))
FileOffs.push_back({Sec, Sec->Offset});
checkOverlap("file", FileOffs, false);
// When linking with -r there is no need to check for overlapping virtual/load
// addresses since those addresses will only be assigned when the final
// executable/shared object is created.
if (Config->Relocatable)
return;
// Checking for overlapping virtual and load addresses only needs to take
// into account SHF_ALLOC sections since others will not be loaded.
// Furthermore, we also need to skip SHF_TLS sections since these will be
// mapped to other addresses at runtime and can therefore have overlapping
// ranges in the file.
std::vector<SectionOffset> VMAs;
for (OutputSection *Sec : OutputSections)
if (Sec->Size > 0 && (Sec->Flags & SHF_ALLOC) && !(Sec->Flags & SHF_TLS))
VMAs.push_back({Sec, Sec->Addr});
checkOverlap("virtual address", VMAs, true);
// Finally, check that the load addresses don't overlap. This will usually be
// the same as the virtual addresses but can be different when using a linker
// script with AT().
std::vector<SectionOffset> LMAs;
for (OutputSection *Sec : OutputSections)
if (Sec->Size > 0 && (Sec->Flags & SHF_ALLOC) && !(Sec->Flags & SHF_TLS))
LMAs.push_back({Sec, Sec->getLMA()});
checkOverlap("load address", LMAs, false);
}
// The entry point address is chosen in the following ways.
//
// 1. the '-e' entry command-line option;
// 2. the ENTRY(symbol) command in a linker control script;
// 3. the value of the symbol _start, if present;
// 4. the number represented by the entry symbol, if it is a number;
// 5. the address of the first byte of the .text section, if present;
// 6. the address 0.
static uint64_t getEntryAddr() {
// Case 1, 2 or 3
if (Symbol *B = Symtab->find(Config->Entry))
return B->getVA();
// Case 4
uint64_t Addr;
if (to_integer(Config->Entry, Addr))
return Addr;
// Case 5
if (OutputSection *Sec = findSection(".text")) {
if (Config->WarnMissingEntry)
warn("cannot find entry symbol " + Config->Entry + "; defaulting to 0x" +
utohexstr(Sec->Addr));
return Sec->Addr;
}
// Case 6
if (Config->WarnMissingEntry)
warn("cannot find entry symbol " + Config->Entry +
"; not setting start address");
return 0;
}
static uint16_t getELFType() {
if (Config->Pic)
return ET_DYN;
if (Config->Relocatable)
return ET_REL;
return ET_EXEC;
}
static uint8_t getAbiVersion() {
// MIPS non-PIC executable gets ABI version 1.
if (Config->EMachine == EM_MIPS && getELFType() == ET_EXEC &&
(Config->EFlags & (EF_MIPS_PIC | EF_MIPS_CPIC)) == EF_MIPS_CPIC)
return 1;
return 0;
}
template <class ELFT> void Writer<ELFT>::writeHeader() {
uint8_t *Buf = Buffer->getBufferStart();
// For executable segments, the trap instructions are written before writing
// the header. Setting Elf header bytes to zero ensures that any unused bytes
// in header are zero-cleared, instead of having trap instructions.
memset(Buf, 0, sizeof(Elf_Ehdr));
memcpy(Buf, "\177ELF", 4);
// Write the ELF header.
auto *EHdr = reinterpret_cast<Elf_Ehdr *>(Buf);
EHdr->e_ident[EI_CLASS] = Config->Is64 ? ELFCLASS64 : ELFCLASS32;
EHdr->e_ident[EI_DATA] = Config->IsLE ? ELFDATA2LSB : ELFDATA2MSB;
EHdr->e_ident[EI_VERSION] = EV_CURRENT;
EHdr->e_ident[EI_OSABI] = Config->OSABI;
EHdr->e_ident[EI_ABIVERSION] = getAbiVersion();
EHdr->e_type = getELFType();
EHdr->e_machine = Config->EMachine;
EHdr->e_version = EV_CURRENT;
EHdr->e_entry = getEntryAddr();
EHdr->e_shoff = SectionHeaderOff;
EHdr->e_flags = Config->EFlags;
EHdr->e_ehsize = sizeof(Elf_Ehdr);
EHdr->e_phnum = Phdrs.size();
EHdr->e_shentsize = sizeof(Elf_Shdr);
if (!Config->Relocatable) {
EHdr->e_phoff = sizeof(Elf_Ehdr);
EHdr->e_phentsize = sizeof(Elf_Phdr);
}
// Write the program header table.
auto *HBuf = reinterpret_cast<Elf_Phdr *>(Buf + EHdr->e_phoff);
for (PhdrEntry *P : Phdrs) {
HBuf->p_type = P->p_type;
HBuf->p_flags = P->p_flags;
HBuf->p_offset = P->p_offset;
HBuf->p_vaddr = P->p_vaddr;
HBuf->p_paddr = P->p_paddr;
HBuf->p_filesz = P->p_filesz;
HBuf->p_memsz = P->p_memsz;
HBuf->p_align = P->p_align;
++HBuf;
}
// Write the section header table.
//
// The ELF header can only store numbers up to SHN_LORESERVE in the e_shnum
// and e_shstrndx fields. When the value of one of these fields exceeds
// SHN_LORESERVE ELF requires us to put sentinel values in the ELF header and
// use fields in the section header at index 0 to store
// the value. The sentinel values and fields are:
// e_shnum = 0, SHdrs[0].sh_size = number of sections.
// e_shstrndx = SHN_XINDEX, SHdrs[0].sh_link = .shstrtab section index.
auto *SHdrs = reinterpret_cast<Elf_Shdr *>(Buf + EHdr->e_shoff);
size_t Num = OutputSections.size() + 1;
if (Num >= SHN_LORESERVE)
SHdrs->sh_size = Num;
else
EHdr->e_shnum = Num;
uint32_t StrTabIndex = In.ShStrTab->getParent()->SectionIndex;
if (StrTabIndex >= SHN_LORESERVE) {
SHdrs->sh_link = StrTabIndex;
EHdr->e_shstrndx = SHN_XINDEX;
} else {
EHdr->e_shstrndx = StrTabIndex;
}
for (OutputSection *Sec : OutputSections)
Sec->writeHeaderTo<ELFT>(++SHdrs);
}
// Open a result file.
template <class ELFT> void Writer<ELFT>::openFile() {
uint64_t MaxSize = Config->Is64 ? INT64_MAX : UINT32_MAX;
if (MaxSize < FileSize) {
error("output file too large: " + Twine(FileSize) + " bytes");
return;
}
unlinkAsync(Config->OutputFile);
unsigned Flags = 0;
if (!Config->Relocatable)
Flags = FileOutputBuffer::F_executable;
Expected<std::unique_ptr<FileOutputBuffer>> BufferOrErr =
FileOutputBuffer::create(Config->OutputFile, FileSize, Flags);
if (!BufferOrErr)
error("failed to open " + Config->OutputFile + ": " +
llvm::toString(BufferOrErr.takeError()));
else
Buffer = std::move(*BufferOrErr);
}
template <class ELFT> void Writer<ELFT>::writeSectionsBinary() {
uint8_t *Buf = Buffer->getBufferStart();
for (OutputSection *Sec : OutputSections)
if (Sec->Flags & SHF_ALLOC)
Sec->writeTo<ELFT>(Buf + Sec->Offset);
}
static void fillTrap(uint8_t *I, uint8_t *End) {
for (; I + 4 <= End; I += 4)
memcpy(I, &Target->TrapInstr, 4);
}
// Fill the last page of executable segments with trap instructions
// instead of leaving them as zero. Even though it is not required by any
// standard, it is in general a good thing to do for security reasons.
//
// We'll leave other pages in segments as-is because the rest will be
// overwritten by output sections.
template <class ELFT> void Writer<ELFT>::writeTrapInstr() {
if (Script->HasSectionsCommand)
return;
// Fill the last page.
uint8_t *Buf = Buffer->getBufferStart();
for (PhdrEntry *P : Phdrs)
if (P->p_type == PT_LOAD && (P->p_flags & PF_X))
fillTrap(Buf + alignDown(P->p_offset + P->p_filesz, Target->PageSize),
Buf + alignTo(P->p_offset + P->p_filesz, Target->PageSize));
// Round up the file size of the last segment to the page boundary iff it is
// an executable segment to ensure that other tools don't accidentally
// trim the instruction padding (e.g. when stripping the file).
PhdrEntry *Last = nullptr;
for (PhdrEntry *P : Phdrs)
if (P->p_type == PT_LOAD)
Last = P;
if (Last && (Last->p_flags & PF_X))
Last->p_memsz = Last->p_filesz = alignTo(Last->p_filesz, Target->PageSize);
}
// Write section contents to a mmap'ed file.
template <class ELFT> void Writer<ELFT>::writeSections() {
uint8_t *Buf = Buffer->getBufferStart();
OutputSection *EhFrameHdr = nullptr;
if (In.EhFrameHdr && !In.EhFrameHdr->empty())
EhFrameHdr = In.EhFrameHdr->getParent();
// In -r or -emit-relocs mode, write the relocation sections first as in
// ELf_Rel targets we might find out that we need to modify the relocated
// section while doing it.
for (OutputSection *Sec : OutputSections)
if (Sec->Type == SHT_REL || Sec->Type == SHT_RELA)
Sec->writeTo<ELFT>(Buf + Sec->Offset);
for (OutputSection *Sec : OutputSections)
if (Sec != EhFrameHdr && Sec->Type != SHT_REL && Sec->Type != SHT_RELA)
Sec->writeTo<ELFT>(Buf + Sec->Offset);
// The .eh_frame_hdr depends on .eh_frame section contents, therefore
// it should be written after .eh_frame is written.
if (EhFrameHdr)
EhFrameHdr->writeTo<ELFT>(Buf + EhFrameHdr->Offset);
}
template <class ELFT> void Writer<ELFT>::writeBuildId() {
if (!In.BuildId || !In.BuildId->getParent())
return;
// Compute a hash of all sections of the output file.
uint8_t *Start = Buffer->getBufferStart();
uint8_t *End = Start + FileSize;
In.BuildId->writeBuildId({Start, End});
}
template void elf::writeResult<ELF32LE>();
template void elf::writeResult<ELF32BE>();
template void elf::writeResult<ELF64LE>();
template void elf::writeResult<ELF64BE>();