LTO.cpp | Explore in Territory

//===-LTO.cpp - LLVM Link Time Optimizer ----------------------------------===//
//
// 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 implements functions and classes used to support LTO.
//
//===----------------------------------------------------------------------===//

#include "llvm/LTO/LTO.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/StableHashing.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/Analysis/StackSafetyAnalysis.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeReader.h"
#include "llvm/Bitcode/BitcodeWriter.h"
#include "llvm/CGData/CodeGenData.h"
#include "llvm/CodeGen/Analysis.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/IR/AutoUpgrade.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/RuntimeLibcalls.h"
#include "llvm/LTO/LTOBackend.h"
#include "llvm/Linker/IRMover.h"
#include "llvm/MC/TargetRegistry.h"
#include "llvm/Object/IRObjectFile.h"
#include "llvm/Support/Caching.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/SHA1.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/ThreadPool.h"
#include "llvm/Support/Threading.h"
#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/ToolOutputFile.h"
#include "llvm/Support/VCSRevision.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/MemProfContextDisambiguation.h"
#include "llvm/Transforms/IPO/WholeProgramDevirt.h"
#include "llvm/Transforms/Utils/FunctionImportUtils.h"
#include "llvm/Transforms/Utils/SplitModule.h"

#include <optional>
#include <set>

usingnamespacellvm;
usingnamespacelto;
usingnamespaceobject;

#define DEBUG_TYPE …

extern cl::opt<bool> UseNewDbgInfoFormat;

static cl::opt<bool>
    DumpThinCGSCCs("dump-thin-cg-sccs", cl::init(false), cl::Hidden,
                   cl::desc("Dump the SCCs in the ThinLTO index's callgraph"));

extern cl::opt<bool> CodeGenDataThinLTOTwoRounds;

namespace llvm {
/// Enable global value internalization in LTO.
cl::opt<bool> EnableLTOInternalization(
    "enable-lto-internalization", cl::init(true), cl::Hidden,
    cl::desc("Enable global value internalization in LTO"));

static cl::opt<bool>
    LTOKeepSymbolCopies("lto-keep-symbol-copies", cl::init(false), cl::Hidden,
                        cl::desc("Keep copies of symbols in LTO indexing"));

/// Indicate we are linking with an allocator that supports hot/cold operator
/// new interfaces.
extern cl::opt<bool> SupportsHotColdNew;

/// Enable MemProf context disambiguation for thin link.
extern cl::opt<bool> EnableMemProfContextDisambiguation;
} // namespace llvm

// Computes a unique hash for the Module considering the current list of
// export/import and other global analysis results.
// Returns the hash in its hexadecimal representation.
std::string llvm::computeLTOCacheKey(
    const Config &Conf, const ModuleSummaryIndex &Index, StringRef ModuleID,
    const FunctionImporter::ImportMapTy &ImportList,
    const FunctionImporter::ExportSetTy &ExportList,
    const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
    const GVSummaryMapTy &DefinedGlobals,
    const DenseSet<GlobalValue::GUID> &CfiFunctionDefs,
    const DenseSet<GlobalValue::GUID> &CfiFunctionDecls) { … }

std::string llvm::recomputeLTOCacheKey(const std::string &Key,
                                       StringRef ExtraID) { … }

static void thinLTOResolvePrevailingGUID(
    const Config &C, ValueInfo VI,
    DenseSet<GlobalValueSummary *> &GlobalInvolvedWithAlias,
    function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
        isPrevailing,
    function_ref<void(StringRef, GlobalValue::GUID, GlobalValue::LinkageTypes)>
        recordNewLinkage,
    const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) { … }

/// Resolve linkage for prevailing symbols in the \p Index.
//
// We'd like to drop these functions if they are no longer referenced in the
// current module. However there is a chance that another module is still
// referencing them because of the import. We make sure we always emit at least
// one copy.
void llvm::thinLTOResolvePrevailingInIndex(
    const Config &C, ModuleSummaryIndex &Index,
    function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
        isPrevailing,
    function_ref<void(StringRef, GlobalValue::GUID, GlobalValue::LinkageTypes)>
        recordNewLinkage,
    const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) { … }

static void thinLTOInternalizeAndPromoteGUID(
    ValueInfo VI, function_ref<bool(StringRef, ValueInfo)> isExported,
    function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
        isPrevailing) { … }

// Update the linkages in the given \p Index to mark exported values
// as external and non-exported values as internal.
void llvm::thinLTOInternalizeAndPromoteInIndex(
    ModuleSummaryIndex &Index,
    function_ref<bool(StringRef, ValueInfo)> isExported,
    function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
        isPrevailing) { … }

// Requires a destructor for std::vector<InputModule>.
InputFile::~InputFile() = default;

Expected<std::unique_ptr<InputFile>> InputFile::create(MemoryBufferRef Object) { … }

StringRef InputFile::getName() const { … }

BitcodeModule &InputFile::getSingleBitcodeModule() { … }

LTO::RegularLTOState::RegularLTOState(unsigned ParallelCodeGenParallelismLevel,
                                      const Config &Conf)
    : … { … }

LTO::ThinLTOState::ThinLTOState(ThinBackend BackendParam)
    : … { … }

LTO::LTO(Config Conf, ThinBackend Backend,
         unsigned ParallelCodeGenParallelismLevel, LTOKind LTOMode)
    : … { … }

// Requires a destructor for MapVector<BitcodeModule>.
LTO::~LTO() = default;

// Add the symbols in the given module to the GlobalResolutions map, and resolve
// their partitions.
void LTO::addModuleToGlobalRes(ArrayRef<InputFile::Symbol> Syms,
                               ArrayRef<SymbolResolution> Res,
                               unsigned Partition, bool InSummary) { … }

void LTO::releaseGlobalResolutionsMemory() { … }

static void writeToResolutionFile(raw_ostream &OS, InputFile *Input,
                                  ArrayRef<SymbolResolution> Res) { … }

Error LTO::add(std::unique_ptr<InputFile> Input,
               ArrayRef<SymbolResolution> Res) { … }

Error LTO::addModule(InputFile &Input, unsigned ModI,
                     const SymbolResolution *&ResI,
                     const SymbolResolution *ResE) { … }

// Checks whether the given global value is in a non-prevailing comdat
// (comdat containing values the linker indicated were not prevailing,
// which we then dropped to available_externally), and if so, removes
// it from the comdat. This is called for all global values to ensure the
// comdat is empty rather than leaving an incomplete comdat. It is needed for
// regular LTO modules, in case we are in a mixed-LTO mode (both regular
// and thin LTO modules) compilation. Since the regular LTO module will be
// linked first in the final native link, we want to make sure the linker
// doesn't select any of these incomplete comdats that would be left
// in the regular LTO module without this cleanup.
static void
handleNonPrevailingComdat(GlobalValue &GV,
                          std::set<const Comdat *> &NonPrevailingComdats) { … }

// Add a regular LTO object to the link.
// The resulting module needs to be linked into the combined LTO module with
// linkRegularLTO.
Expected<LTO::RegularLTOState::AddedModule>
LTO::addRegularLTO(BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
                   const SymbolResolution *&ResI,
                   const SymbolResolution *ResE) { … }

Error LTO::linkRegularLTO(RegularLTOState::AddedModule Mod,
                          bool LivenessFromIndex) { … }

// Add a ThinLTO module to the link.
Error LTO::addThinLTO(BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
                      const SymbolResolution *&ResI,
                      const SymbolResolution *ResE) { … }

unsigned LTO::getMaxTasks() const { … }

// If only some of the modules were split, we cannot correctly handle
// code that contains type tests or type checked loads.
Error LTO::checkPartiallySplit() { … }

Error LTO::run(AddStreamFn AddStream, FileCache Cache) { … }

void lto::updateMemProfAttributes(Module &Mod,
                                  const ModuleSummaryIndex &Index) { … }

Error LTO::runRegularLTO(AddStreamFn AddStream) { … }

SmallVector<const char *> LTO::getRuntimeLibcallSymbols(const Triple &TT) { … }

Error ThinBackendProc::emitFiles(
    const FunctionImporter::ImportMapTy &ImportList, llvm::StringRef ModulePath,
    const std::string &NewModulePath) const { … }

namespace {
class InProcessThinBackend : public ThinBackendProc { … };

/// This backend is utilized in the first round of a two-codegen round process.
/// It first saves optimized bitcode files to disk before the codegen process
/// begins. After codegen, it stores the resulting object files in a scratch
/// buffer. Note the codegen data stored in the scratch buffer will be extracted
/// and merged in the subsequent step.
class FirstRoundThinBackend : public InProcessThinBackend { … };

/// This backend operates in the second round of a two-codegen round process.
/// It starts by reading the optimized bitcode files that were saved during the
/// first round. The backend then executes the codegen only to further optimize
/// the code, utilizing the codegen data merged from the first round. Finally,
/// it writes the resulting object files as usual.
class SecondRoundThinBackend : public InProcessThinBackend { … };
} // end anonymous namespace

ThinBackend lto::createInProcessThinBackend(ThreadPoolStrategy Parallelism,
                                            lto::IndexWriteCallback OnWrite,
                                            bool ShouldEmitIndexFiles,
                                            bool ShouldEmitImportsFiles) { … }

StringLiteral lto::getThinLTODefaultCPU(const Triple &TheTriple) { … }

// Given the original \p Path to an output file, replace any path
// prefix matching \p OldPrefix with \p NewPrefix. Also, create the
// resulting directory if it does not yet exist.
std::string lto::getThinLTOOutputFile(StringRef Path, StringRef OldPrefix,
                                      StringRef NewPrefix) { … }

namespace {
class WriteIndexesThinBackend : public ThinBackendProc { … };
} // end anonymous namespace

ThinBackend lto::createWriteIndexesThinBackend(
    ThreadPoolStrategy Parallelism, std::string OldPrefix,
    std::string NewPrefix, std::string NativeObjectPrefix,
    bool ShouldEmitImportsFiles, raw_fd_ostream *LinkedObjectsFile,
    IndexWriteCallback OnWrite) { … }

Error LTO::runThinLTO(AddStreamFn AddStream, FileCache Cache,
                      const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) { … }

Expected<std::unique_ptr<ToolOutputFile>> lto::setupLLVMOptimizationRemarks(
    LLVMContext &Context, StringRef RemarksFilename, StringRef RemarksPasses,
    StringRef RemarksFormat, bool RemarksWithHotness,
    std::optional<uint64_t> RemarksHotnessThreshold, int Count) { … }

Expected<std::unique_ptr<ToolOutputFile>>
lto::setupStatsFile(StringRef StatsFilename) { … }

// Compute the ordering we will process the inputs: the rough heuristic here
// is to sort them per size so that the largest module get schedule as soon as
// possible. This is purely a compile-time optimization.
std::vector<int> lto::generateModulesOrdering(ArrayRef<BitcodeModule *> R) { … }
llvm/llvm/lib/LTO/LTO.cpp
