blob: 02ab6d18e53710dba4dacc7ff2263f1a1cbce297 [file] [log] [blame]
//===- MarkLive.cpp -------------------------------------------------------===//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
// This file implements --gc-sections, which is a feature to remove unused
// sections from output. Unused sections are sections that are not reachable
// from known GC-root symbols or sections. Naturally the feature is
// implemented as a mark-sweep garbage collector.
// Here's how it works. Each InputSectionBase has a "Live" bit. The bit is off
// by default. Starting with GC-root symbols or sections, markLive function
// defined in this file visits all reachable sections to set their Live
// bits. Writer will then ignore sections whose Live bits are off, so that
// such sections are not included into output.
#include "MarkLive.h"
#include "InputSection.h"
#include "LinkerScript.h"
#include "OutputSections.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Object/ELF.h"
#include <functional>
#include <vector>
using namespace llvm;
using namespace llvm::ELF;
using namespace llvm::object;
namespace endian = llvm::support::endian;
namespace lld {
namespace elf {
namespace {
template <class ELFT> class MarkLive {
MarkLive(unsigned partition) : partition(partition) {}
void run();
void moveToMain();
void enqueue(InputSectionBase *sec, uint64_t offset);
void markSymbol(Symbol *sym);
void mark();
template <class RelTy>
void resolveReloc(InputSectionBase &sec, RelTy &rel, bool isLSDA);
template <class RelTy>
void scanEhFrameSection(EhInputSection &eh, ArrayRef<RelTy> rels);
// The index of the partition that we are currently processing.
unsigned partition;
// A list of sections to visit.
SmallVector<InputSection *, 256> queue;
// There are normally few input sections whose names are valid C
// identifiers, so we just store a std::vector instead of a multimap.
DenseMap<StringRef, std::vector<InputSectionBase *>> cNamedSections;
} // namespace
template <class ELFT>
static uint64_t getAddend(InputSectionBase &sec,
const typename ELFT::Rel &rel) {
return target->getImplicitAddend( + rel.r_offset,
template <class ELFT>
static uint64_t getAddend(InputSectionBase &sec,
const typename ELFT::Rela &rel) {
return rel.r_addend;
template <class ELFT>
template <class RelTy>
void MarkLive<ELFT>::resolveReloc(InputSectionBase &sec, RelTy &rel,
bool isLSDA) {
Symbol &sym = sec.getFile<ELFT>()->getRelocTargetSym(rel);
// If a symbol is referenced in a live section, it is used.
sym.used = true;
if (auto *d = dyn_cast<Defined>(&sym)) {
auto *relSec = dyn_cast_or_null<InputSectionBase>(d->section);
if (!relSec)
uint64_t offset = d->value;
if (d->isSection())
offset += getAddend<ELFT>(sec, rel);
if (!isLSDA || !(relSec->flags & SHF_EXECINSTR))
enqueue(relSec, offset);
if (auto *ss = dyn_cast<SharedSymbol>(&sym))
if (!ss->isWeak())
ss->getFile().isNeeded = true;
for (InputSectionBase *sec : cNamedSections.lookup(sym.getName()))
enqueue(sec, 0);
// The .eh_frame section is an unfortunate special case.
// The section is divided in CIEs and FDEs and the relocations it can have are
// * CIEs can refer to a personality function.
// * FDEs can refer to a LSDA
// * FDEs refer to the function they contain information about
// The last kind of relocation cannot keep the referred section alive, or they
// would keep everything alive in a common object file. In fact, each FDE is
// alive if the section it refers to is alive.
// To keep things simple, in here we just ignore the last relocation kind. The
// other two keep the referred section alive.
// A possible improvement would be to fully process .eh_frame in the middle of
// the gc pass. With that we would be able to also gc some sections holding
// LSDAs and personality functions if we found that they were unused.
template <class ELFT>
template <class RelTy>
void MarkLive<ELFT>::scanEhFrameSection(EhInputSection &eh,
ArrayRef<RelTy> rels) {
for (size_t i = 0, end = eh.pieces.size(); i < end; ++i) {
EhSectionPiece &piece = eh.pieces[i];
size_t firstRelI = piece.firstRelocation;
if (firstRelI == (unsigned)-1)
if (endian::read32<ELFT::TargetEndianness>( + 4) == 0) {
// This is a CIE, we only need to worry about the first relocation. It is
// known to point to the personality function.
resolveReloc(eh, rels[firstRelI], false);
// This is a FDE. The relocations point to the described function or to
// a LSDA. We only need to keep the LSDA alive, so ignore anything that
// points to executable sections.
uint64_t pieceEnd = piece.inputOff + piece.size;
for (size_t j = firstRelI, end2 = rels.size(); j < end2; ++j)
if (rels[j].r_offset < pieceEnd)
resolveReloc(eh, rels[j], true);
// Some sections are used directly by the loader, so they should never be
// garbage-collected. This function returns true if a given section is such
// section.
static bool isReserved(InputSectionBase *sec) {
switch (sec->type) {
case SHT_NOTE:
return true;
StringRef s = sec->name;
return s.startswith(".ctors") || s.startswith(".dtors") ||
s.startswith(".init") || s.startswith(".fini") ||
template <class ELFT>
void MarkLive<ELFT>::enqueue(InputSectionBase *sec, uint64_t offset) {
// Skip over discarded sections. This in theory shouldn't happen, because
// the ELF spec doesn't allow a relocation to point to a deduplicated
// COMDAT section directly. Unfortunately this happens in practice (e.g.
// .eh_frame) so we need to add a check.
if (sec == &InputSection::discarded)
// Usually, a whole section is marked as live or dead, but in mergeable
// (splittable) sections, each piece of data has independent liveness bit.
// So we explicitly tell it which offset is in use.
if (auto *ms = dyn_cast<MergeInputSection>(sec))
ms->getSectionPiece(offset)->live = true;
// Set Sec->Partition to the meet (i.e. the "minimum") of Partition and
// Sec->Partition in the following lattice: 1 < other < 0. If Sec->Partition
// doesn't change, we don't need to do anything.
if (sec->partition == 1 || sec->partition == partition)
sec->partition = sec->partition ? 1 : partition;
// Add input section to the queue.
if (InputSection *s = dyn_cast<InputSection>(sec))
template <class ELFT> void MarkLive<ELFT>::markSymbol(Symbol *sym) {
if (auto *d = dyn_cast_or_null<Defined>(sym))
if (auto *isec = dyn_cast_or_null<InputSectionBase>(d->section))
enqueue(isec, d->value);
// This is the main function of the garbage collector.
// Starting from GC-root sections, this function visits all reachable
// sections to set their "Live" bits.
template <class ELFT> void MarkLive<ELFT>::run() {
// Add GC root symbols.
// Preserve externally-visible symbols if the symbols defined by this
// file can interrupt other ELF file's symbols at runtime.
symtab->forEachSymbol([&](Symbol *sym) {
if (sym->includeInDynsym() && sym->partition == partition)
// If this isn't the main partition, that's all that we need to preserve.
if (partition != 1) {
for (StringRef s : config->undefined)
for (StringRef s : script->referencedSymbols)
// Preserve special sections and those which are specified in linker
// script KEEP command.
for (InputSectionBase *sec : inputSections) {
// Mark .eh_frame sections as live because there are usually no relocations
// that point to .eh_frames. Otherwise, the garbage collector would drop
// all of them. We also want to preserve personality routines and LSDA
// referenced by .eh_frame sections, so we scan them for that here.
if (auto *eh = dyn_cast<EhInputSection>(sec)) {
if (!eh->numRelocations)
if (eh->areRelocsRela)
scanEhFrameSection(*eh, eh->template relas<ELFT>());
scanEhFrameSection(*eh, eh->template rels<ELFT>());
if (sec->flags & SHF_LINK_ORDER)
if (isReserved(sec) || script->shouldKeep(sec)) {
enqueue(sec, 0);
} else if (isValidCIdentifier(sec->name)) {
cNamedSections["__start_" + sec->name)].push_back(sec);
cNamedSections["__stop_" + sec->name)].push_back(sec);
template <class ELFT> void MarkLive<ELFT>::mark() {
// Mark all reachable sections.
while (!queue.empty()) {
InputSectionBase &sec = *queue.pop_back_val();
if (sec.areRelocsRela) {
for (const typename ELFT::Rela &rel : sec.template relas<ELFT>())
resolveReloc(sec, rel, false);
} else {
for (const typename ELFT::Rel &rel : sec.template rels<ELFT>())
resolveReloc(sec, rel, false);
for (InputSectionBase *isec : sec.dependentSections)
enqueue(isec, 0);
// Move the sections for some symbols to the main partition, specifically ifuncs
// (because they can result in an IRELATIVE being added to the main partition's
// GOT, which means that the ifunc must be available when the main partition is
// loaded) and TLS symbols (because we only know how to correctly process TLS
// relocations for the main partition).
// We also need to move sections whose names are C identifiers that are referred
// to from __start_/__stop_ symbols because there will only be one set of
// symbols for the whole program.
template <class ELFT> void MarkLive<ELFT>::moveToMain() {
for (InputFile *file : objectFiles)
for (Symbol *s : file->getSymbols())
if (auto *d = dyn_cast<Defined>(s))
if ((d->type == STT_GNU_IFUNC || d->type == STT_TLS) && d->section &&
for (InputSectionBase *sec : inputSections) {
if (!sec->isLive() || !isValidCIdentifier(sec->name))
if (symtab->find(("__start_" + sec->name).str()) ||
symtab->find(("__stop_" + sec->name).str()))
enqueue(sec, 0);
// Before calling this function, Live bits are off for all
// input sections. This function make some or all of them on
// so that they are emitted to the output file.
template <class ELFT> void markLive() {
// If -gc-sections is not given, no sections are removed.
if (!config->gcSections) {
for (InputSectionBase *sec : inputSections)
// If a DSO defines a symbol referenced in a regular object, it is needed.
symtab->forEachSymbol([](Symbol *sym) {
if (auto *s = dyn_cast<SharedSymbol>(sym))
if (s->isUsedInRegularObj && !s->isWeak())
s->getFile().isNeeded = true;
// Otheriwse, do mark-sweep GC.
// The -gc-sections option works only for SHF_ALLOC sections
// (sections that are memory-mapped at runtime). So we can
// unconditionally make non-SHF_ALLOC sections alive except
// Usually, non-SHF_ALLOC sections are not removed even if they are
// unreachable through relocations because reachability is not
// a good signal whether they are garbage or not (e.g. there is
// usually no section referring to a .comment section, but we
// want to keep it.).
// Note on SHF_LINK_ORDER: Such sections contain metadata and they
// have a reverse dependency on the InputSection they are linked with.
// We are able to garbage collect them.
// Note on SHF_REL{,A}: Such sections reach here only when -r
// or -emit-reloc were given. And they are subject of garbage
// collection because, if we remove a text section, we also
// remove its relocation section.
for (InputSectionBase *sec : inputSections) {
bool isAlloc = (sec->flags & SHF_ALLOC);
bool isLinkOrder = (sec->flags & SHF_LINK_ORDER);
bool isRel = (sec->type == SHT_REL || sec->type == SHT_RELA);
if (!isAlloc && !isLinkOrder && !isRel)
// Follow the graph to mark all live sections.
for (unsigned curPart = 1; curPart <= partitions.size(); ++curPart)
// If we have multiple partitions, some sections need to live in the main
// partition even if they were allocated to a loadable partition. Move them
// there now.
if (partitions.size() != 1)
// Report garbage-collected sections.
if (config->printGcSections)
for (InputSectionBase *sec : inputSections)
if (!sec->isLive())
message("removing unused section " + toString(sec));
template void markLive<ELF32LE>();
template void markLive<ELF32BE>();
template void markLive<ELF64LE>();
template void markLive<ELF64BE>();
} // namespace elf
} // namespace lld