LinkerScript.cpp | Explore in Territory

//===- LinkerScript.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
//
//===----------------------------------------------------------------------===//
//
// This file contains the parser/evaluator of the linker script.
//
//===----------------------------------------------------------------------===//

#include "LinkerScript.h"
#include "Config.h"
#include "InputFiles.h"
#include "InputSection.h"
#include "OutputSections.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "Writer.h"
#include "lld/Common/CommonLinkerContext.h"
#include "lld/Common/Strings.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/TimeProfiler.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <limits>
#include <string>
#include <vector>

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

static bool isSectionPrefix(StringRef prefix, StringRef name) { … }

StringRef LinkerScript::getOutputSectionName(const InputSectionBase *s) const { … }

uint64_t ExprValue::getValue() const { … }

uint64_t ExprValue::getSecAddr() const { … }

uint64_t ExprValue::getSectionOffset() const { … }

OutputDesc *LinkerScript::createOutputSection(StringRef name,
                                              StringRef location) { … }

OutputDesc *LinkerScript::getOrCreateOutputSection(StringRef name) { … }

// Expands the memory region by the specified size.
static void expandMemoryRegion(MemoryRegion *memRegion, uint64_t size,
                               StringRef secName) { … }

void LinkerScript::expandMemoryRegions(uint64_t size) { … }

void LinkerScript::expandOutputSection(uint64_t size) { … }

void LinkerScript::setDot(Expr e, const Twine &loc, bool inSec) { … }

// Used for handling linker symbol assignments, for both finalizing
// their values and doing early declarations. Returns true if symbol
// should be defined from linker script.
static bool shouldDefineSym(SymbolAssignment *cmd) { … }

// Called by processSymbolAssignments() to assign definitions to
// linker-script-defined symbols.
void LinkerScript::addSymbol(SymbolAssignment *cmd) { … }

// This function is called from LinkerScript::declareSymbols.
// It creates a placeholder symbol if needed.
static void declareSymbol(SymbolAssignment *cmd) { … }

SymbolAssignmentMap;

// Collect section/value pairs of linker-script-defined symbols. This is used to
// check whether symbol values converge.
static SymbolAssignmentMap
getSymbolAssignmentValues(ArrayRef<SectionCommand *> sectionCommands) { … }

// Returns the lexicographical smallest (for determinism) Defined whose
// section/value has changed.
static const Defined *
getChangedSymbolAssignment(const SymbolAssignmentMap &oldValues) { … }

// Process INSERT [AFTER|BEFORE] commands. For each command, we move the
// specified output section to the designated place.
void LinkerScript::processInsertCommands() { … }

// Symbols defined in script should not be inlined by LTO. At the same time
// we don't know their final values until late stages of link. Here we scan
// over symbol assignment commands and create placeholder symbols if needed.
void LinkerScript::declareSymbols() { … }

// This function is called from assignAddresses, while we are
// fixing the output section addresses. This function is supposed
// to set the final value for a given symbol assignment.
void LinkerScript::assignSymbol(SymbolAssignment *cmd, bool inSec) { … }

static inline StringRef getFilename(const InputFile *file) { … }

bool InputSectionDescription::matchesFile(const InputFile *file) const { … }

bool SectionPattern::excludesFile(const InputFile *file) const { … }

bool LinkerScript::shouldKeep(InputSectionBase *s) { … }

// A helper function for the SORT() command.
static bool matchConstraints(ArrayRef<InputSectionBase *> sections,
                             ConstraintKind kind) { … }

static void sortSections(MutableArrayRef<InputSectionBase *> vec,
                         SortSectionPolicy k) { … }

// Sort sections as instructed by SORT-family commands and --sort-section
// option. Because SORT-family commands can be nested at most two depth
// (e.g. SORT_BY_NAME(SORT_BY_ALIGNMENT(.text.*))) and because the command
// line option is respected even if a SORT command is given, the exact
// behavior we have here is a bit complicated. Here are the rules.
//
// 1. If two SORT commands are given, --sort-section is ignored.
// 2. If one SORT command is given, and if it is not SORT_NONE,
//    --sort-section is handled as an inner SORT command.
// 3. If one SORT command is given, and if it is SORT_NONE, don't sort.
// 4. If no SORT command is given, sort according to --sort-section.
static void sortInputSections(MutableArrayRef<InputSectionBase *> vec,
                              SortSectionPolicy outer,
                              SortSectionPolicy inner) { … }

// Compute and remember which sections the InputSectionDescription matches.
SmallVector<InputSectionBase *, 0>
LinkerScript::computeInputSections(const InputSectionDescription *cmd,
                                   ArrayRef<InputSectionBase *> sections,
                                   const SectionBase &outCmd) { … }

void LinkerScript::discard(InputSectionBase &s) { … }

void LinkerScript::discardSynthetic(OutputSection &outCmd) { … }

SmallVector<InputSectionBase *, 0>
LinkerScript::createInputSectionList(OutputSection &outCmd) { … }

// Create output sections described by SECTIONS commands.
void LinkerScript::processSectionCommands() { … }

void LinkerScript::processSymbolAssignments() { … }

static OutputSection *findByName(ArrayRef<SectionCommand *> vec,
                                 StringRef name) { … }

static OutputDesc *createSection(InputSectionBase *isec, StringRef outsecName) { … }

static OutputDesc *addInputSec(StringMap<TinyPtrVector<OutputSection *>> &map,
                               InputSectionBase *isec, StringRef outsecName) { … }

// Add sections that didn't match any sections command.
void LinkerScript::addOrphanSections() { … }

void LinkerScript::diagnoseOrphanHandling() const { … }

void LinkerScript::diagnoseMissingSGSectionAddress() const { … }

// This function searches for a memory region to place the given output
// section in. If found, a pointer to the appropriate memory region is
// returned in the first member of the pair. Otherwise, a nullptr is returned.
// The second member of the pair is a hint that should be passed to the
// subsequent call of this method.
std::pair<MemoryRegion *, MemoryRegion *>
LinkerScript::findMemoryRegion(OutputSection *sec, MemoryRegion *hint) { … }

static OutputSection *findFirstSection(PhdrEntry *load) { … }

// Assign addresses to an output section and offsets to its input sections and
// symbol assignments. Return true if the output section's address has changed.
bool LinkerScript::assignOffsets(OutputSection *sec) { … }

static bool isDiscardable(const OutputSection &sec) { … }

static void maybePropagatePhdrs(OutputSection &sec,
                                SmallVector<StringRef, 0> &phdrs) { … }

void LinkerScript::adjustOutputSections() { … }

void LinkerScript::adjustSectionsAfterSorting() { … }

// When the SECTIONS command is used, try to find an address for the file and
// program headers output sections, which can be added to the first PT_LOAD
// segment when program headers are created.
//
// We check if the headers fit below the first allocated section. If there isn't
// enough space for these sections, we'll remove them from the PT_LOAD segment,
// and we'll also remove the PT_PHDR segment.
void LinkerScript::allocateHeaders(SmallVector<PhdrEntry *, 0> &phdrs) { … }

LinkerScript::AddressState::AddressState(const LinkerScript &script) { … }

// Here we assign addresses as instructed by linker script SECTIONS
// sub-commands. Doing that allows us to use final VA values, so here
// we also handle rest commands like symbol assignments and ASSERTs.
// Return an output section that has changed its address or null, and a symbol
// that has changed its section or value (or nullptr if no symbol has changed).
std::pair<const OutputSection *, const Defined *>
LinkerScript::assignAddresses() { … }

static bool hasRegionOverflowed(MemoryRegion *mr) { … }

// Spill input sections in reverse order of address assignment to (potentially)
// bring memory regions out of overflow. The size savings of a spill can only be
// estimated, since general linker script arithmetic may occur afterwards.
// Under-estimates may cause unnecessary spills, but over-estimates can always
// be corrected on the next pass.
bool LinkerScript::spillSections() { … }

// Erase any potential spill sections that were not used.
void LinkerScript::erasePotentialSpillSections() { … }

// Creates program headers as instructed by PHDRS linker script command.
SmallVector<PhdrEntry *, 0> LinkerScript::createPhdrs() { … }

// Returns true if we should emit an .interp section.
//
// We usually do. But if PHDRS commands are given, and
// no PT_INTERP is there, there's no place to emit an
// .interp, so we don't do that in that case.
bool LinkerScript::needsInterpSection() { … }

ExprValue LinkerScript::getSymbolValue(StringRef name, const Twine &loc) { … }

// Returns the index of the segment named Name.
static std::optional<size_t> getPhdrIndex(ArrayRef<PhdrsCommand> vec,
                                          StringRef name) { … }

// Returns indices of ELF headers containing specific section. Each index is a
// zero based number of ELF header listed within PHDRS {} script block.
SmallVector<size_t, 0> LinkerScript::getPhdrIndices(OutputSection *cmd) { … }

void LinkerScript::printMemoryUsage(raw_ostream& os) { … }

void LinkerScript::recordError(const Twine &msg) { … }

static void checkMemoryRegion(const MemoryRegion *region,
                              const OutputSection *osec, uint64_t addr) { … }

void LinkerScript::checkFinalScriptConditions() const { … }

void LinkerScript::addScriptReferencedSymbolsToSymTable() { … }

bool LinkerScript::shouldAddProvideSym(StringRef symName) { … }
llvm/lld/ELF/LinkerScript.cpp
