llvm/lld/MachO/ICF.cpp

//===- ICF.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 "ICF.h"
#include "ConcatOutputSection.h"
#include "Config.h"
#include "InputSection.h"
#include "SymbolTable.h"
#include "Symbols.h"
#include "UnwindInfoSection.h"

#include "lld/Common/CommonLinkerContext.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/Parallel.h"
#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/xxhash.h"

#include <atomic>

usingnamespacellvm;
usingnamespacelld;
usingnamespacelld::macho;

static constexpr bool verboseDiagnostics = …;

class ICF { … };

ICF::ICF(std::vector<ConcatInputSection *> &inputs) { … }

// ICF = Identical Code Folding
//
// We only fold __TEXT,__text, so this is really "code" folding, and not
// "COMDAT" folding. String and scalar constant literals are deduplicated
// elsewhere.
//
// Summary of segments & sections:
//
// The __TEXT segment is readonly at the MMU. Some sections are already
// deduplicated elsewhere (__TEXT,__cstring & __TEXT,__literal*) and some are
// synthetic and inherently free of duplicates (__TEXT,__stubs &
// __TEXT,__unwind_info). Note that we don't yet run ICF on __TEXT,__const,
// because doing so induces many test failures.
//
// The __LINKEDIT segment is readonly at the MMU, yet entirely synthetic, and
// thus ineligible for ICF.
//
// The __DATA_CONST segment is read/write at the MMU, but is logically const to
// the application after dyld applies fixups to pointer data. We currently
// fold only the __DATA_CONST,__cfstring section.
//
// The __DATA segment is read/write at the MMU, and as application-writeable
// data, none of its sections are eligible for ICF.
//
// Please see the large block comment in lld/ELF/ICF.cpp for an explanation
// of the segregation algorithm.
//
// FIXME(gkm): implement keep-unique attributes
// FIXME(gkm): implement address-significance tables for MachO object files

// Compare "non-moving" parts of two ConcatInputSections, namely everything
// except references to other ConcatInputSections.
bool ICF::equalsConstant(const ConcatInputSection *ia,
                         const ConcatInputSection *ib) { … }

// Compare the "moving" parts of two ConcatInputSections -- i.e. everything not
// handled by equalsConstant().
bool ICF::equalsVariable(const ConcatInputSection *ia,
                         const ConcatInputSection *ib) { … }

// Find the first InputSection after BEGIN whose equivalence class differs
size_t ICF::findBoundary(size_t begin, size_t end) { … }

// Invoke FUNC on subranges with matching equivalence class
void ICF::forEachClassRange(size_t begin, size_t end,
                            llvm::function_ref<void(size_t, size_t)> func) { … }

// Given a range of identical icfInputs, replace address significant functions
// with a thunk that is just a direct branch to the first function in the
// series. This way we keep only one main body of the function but we still
// retain the address uniqueness of relevant functions by having them be a
// direct branch thunk rather than containing a full copy of the actual function
// body.
void ICF::applySafeThunksToRange(size_t begin, size_t end) { … }

// Split icfInputs into shards, then parallelize invocation of FUNC on subranges
// with matching equivalence class
void ICF::forEachClass(llvm::function_ref<void(size_t, size_t)> func) { … }

void ICF::run() { … }

// Split an equivalence class into smaller classes.
void ICF::segregate(size_t begin, size_t end, EqualsFn equals) { … }

void macho::markSymAsAddrSig(Symbol *s) { … }

void macho::markAddrSigSymbols() { … }

void macho::foldIdenticalSections(bool onlyCfStrings) { … }