InputSection.cpp | Explore in Territory

//===- InputSection.cpp ---------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//

#include "InputSection.h"
#include "Config.h"
#include "InputFiles.h"
#include "OutputSections.h"
#include "Relocations.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "lld/Common/CommonLinkerContext.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
#include <mutex>
#include <optional>
#include <vector>

usingnamespacellvm;
usingnamespacellvm::ELF;
usingnamespacellvm::object;
usingnamespacellvm::support;
usingnamespacellvm::support::endian;
usingnamespacellvm::sys;
usingnamespacelld;
usingnamespacelld::elf;

// Returns a string to construct an error message.
std::string lld::toString(const InputSectionBase *sec) { … }

template <class ELFT>
static ArrayRef<uint8_t> getSectionContents(ObjFile<ELFT> &file,
                                            const typename ELFT::Shdr &hdr) { … }

InputSectionBase::InputSectionBase(InputFile *file, uint64_t flags,
                                   uint32_t type, uint64_t entsize,
                                   uint32_t link, uint32_t info,
                                   uint32_t addralign, ArrayRef<uint8_t> data,
                                   StringRef name, Kind sectionKind)
    : … { … }

// SHF_INFO_LINK and SHF_GROUP are normally resolved and not copied to the
// output section. However, for relocatable linking without
// --force-group-allocation, the SHF_GROUP flag and section groups are retained.
static uint64_t getFlags(Ctx &ctx, uint64_t flags) { … }

template <class ELFT>
InputSectionBase::InputSectionBase(ObjFile<ELFT> &file,
                                   const typename ELFT::Shdr &hdr,
                                   StringRef name, Kind sectionKind)
    : InputSectionBase(&file, getFlags(file.ctx, hdr.sh_flags), hdr.sh_type,
                       hdr.sh_entsize, hdr.sh_link, hdr.sh_info,
                       hdr.sh_addralign, getSectionContents(file, hdr), name,
                       sectionKind) { … }

size_t InputSectionBase::getSize() const { … }

template <class ELFT>
static void decompressAux(const InputSectionBase &sec, uint8_t *out,
                          size_t size) { … }

void InputSectionBase::decompress() const { … }

template <class ELFT>
RelsOrRelas<ELFT> InputSectionBase::relsOrRelas(bool supportsCrel) const { … }

Ctx &SectionBase::getCtx() const { … }

uint64_t SectionBase::getOffset(uint64_t offset) const { … }

uint64_t SectionBase::getVA(uint64_t offset) const { … }

OutputSection *SectionBase::getOutputSection() { … }

// 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`.
template <typename ELFT> void InputSectionBase::parseCompressedHeader() { … }

InputSection *InputSectionBase::getLinkOrderDep() const { … }

// Find a symbol that encloses a given location.
Defined *InputSectionBase::getEnclosingSymbol(uint64_t offset,
                                              uint8_t type) const { … }

// Returns an object file location string. Used to construct an error message.
std::string InputSectionBase::getLocation(uint64_t offset) const { … }

// 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) const { … }

// 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) const { … }

PotentialSpillSection::PotentialSpillSection(const InputSectionBase &source,
                                             InputSectionDescription &isd)
    : … { … }

InputSection InputSection::discarded(nullptr, 0, 0, 0, ArrayRef<uint8_t>(), "");

InputSection::InputSection(InputFile *f, uint64_t flags, uint32_t type,
                           uint32_t addralign, ArrayRef<uint8_t> data,
                           StringRef name, Kind k)
    : … { … }

template <class ELFT>
InputSection::InputSection(ObjFile<ELFT> &f, const typename ELFT::Shdr &header,
                           StringRef name)
    : InputSectionBase(f, header, name, InputSectionBase::Regular) { … }

// Copy SHT_GROUP section contents. Used only for the -r option.
template <class ELFT> void InputSection::copyShtGroup(uint8_t *buf) { … }

InputSectionBase *InputSection::getRelocatedSection() const { … }

template <class ELFT, class RelTy>
void InputSection::copyRelocations(uint8_t *buf) { … }

// 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, class RelIt>
void InputSection::copyRelocations(uint8_t *buf,
                                   llvm::iterator_range<RelIt> rels) { … }

// 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) { … }

// The comment above getARMUndefinedRelativeWeakVA applies to this function.
static uint64_t getAArch64UndefinedRelativeWeakVA(uint64_t type, uint64_t p) { … }

static uint64_t getRISCVUndefinedRelativeWeakVA(uint64_t type, uint64_t p) { … }

// 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) { … }

// 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 the
// R_RISCV_PCREL_LO12 relocation.
static Relocation *getRISCVPCRelHi20(const InputSectionBase *loSec,
                                     const Relocation &loReloc) { … }

// 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(Ctx &ctx, const Symbol &s) { … }

uint64_t InputSectionBase::getRelocTargetVA(Ctx &ctx, const Relocation &r,
                                            uint64_t p) const { … }

// 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
// treatment 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, Relocs<RelTy> rels) { … }

template <class ELFT>
void InputSectionBase::relocate(uint8_t *buf, uint8_t *bufEnd) { … }

// 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,
    SmallVector<Relocation *, 0> &morestackCalls) { … }

static bool enclosingPrologueAttempted(uint64_t offset,
                                       const DenseSet<Defined *> &prologues) { … }

// 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) { … }

template <class ELFT> void InputSection::writeTo(uint8_t *buf) { … }

void InputSection::replace(InputSection *other) { … }

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 { … }

// .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() { … }

template <class ELFT, class RelTy>
void EhInputSection::split(ArrayRef<RelTy> rels) { … }

// Return the offset in an output section for a given input offset.
uint64_t EhInputSection::getParentOffset(uint64_t offset) const { … }

static size_t findNull(StringRef s, size_t entSize) { … }

// Split SHF_STRINGS section. Such section is a sequence of
// null-terminated strings.
void MergeInputSection::splitStrings(StringRef s, size_t entSize) { … }

// Split non-SHF_STRINGS section. Such section is a sequence of
// fixed size records.
void MergeInputSection::splitNonStrings(ArrayRef<uint8_t> data,
                                        size_t entSize) { … }

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)
    : … { … }

// 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() { … }

SectionPiece &MergeInputSection::getSectionPiece(uint64_t offset) { … }

// Return the offset in an output section for a given input offset.
uint64_t MergeInputSection::getParentOffset(uint64_t offset) const { … }

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 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 RelsOrRelas<ELF32LE>
InputSectionBase::relsOrRelas<ELF32LE>(bool) const;
template RelsOrRelas<ELF32BE>
InputSectionBase::relsOrRelas<ELF32BE>(bool) const;
template RelsOrRelas<ELF64LE>
InputSectionBase::relsOrRelas<ELF64LE>(bool) const;
template RelsOrRelas<ELF64BE>
InputSectionBase::relsOrRelas<ELF64BE>(bool) const;

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>();
llvm/lld/ELF/InputSection.cpp
