X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=tools%2Fgold%2Fgold-plugin.cpp;h=9d6540d2d47d5b73050e56733aa7f1d9ec384589;hp=119631cfa7e0fed63e686d304aae84481371a046;hb=e272236d69961cf3686d1d4e5720bc87ec996cd4;hpb=438900938c3ac9d7fac2dd5d2c85ca4b9b2e35f7 diff --git a/tools/gold/gold-plugin.cpp b/tools/gold/gold-plugin.cpp index 119631cfa7e..9d6540d2d47 100644 --- a/tools/gold/gold-plugin.cpp +++ b/tools/gold/gold-plugin.cpp @@ -13,62 +13,70 @@ //===----------------------------------------------------------------------===// #include "llvm/Config/config.h" // plugin-api.h requires HAVE_STDINT_H -#include "plugin-api.h" -#include "llvm-c/lto.h" -#include "llvm/ADT/OwningPtr.h" -#include "llvm/Support/Errno.h" -#include "llvm/Support/FileSystem.h" +#include "llvm/ADT/DenseSet.h" +#include "llvm/ADT/StringSet.h" +#include "llvm/Bitcode/ReaderWriter.h" +#include "llvm/CodeGen/Analysis.h" +#include "llvm/CodeGen/CommandFlags.h" +#include "llvm/IR/Constants.h" +#include "llvm/IR/LLVMContext.h" +#include "llvm/IR/Module.h" +#include "llvm/IR/Verifier.h" +#include "llvm/Linker/Linker.h" +#include "llvm/MC/SubtargetFeature.h" +#include "llvm/Object/IRObjectFile.h" +#include "llvm/PassManager.h" +#include "llvm/Support/FormattedStream.h" +#include "llvm/Support/Host.h" #include "llvm/Support/MemoryBuffer.h" -#include "llvm/Support/Path.h" -#include "llvm/Support/Program.h" -#include "llvm/Support/ToolOutputFile.h" -#include "llvm/Support/system_error.h" -#include -#include -#include -#include +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Target/TargetLibraryInfo.h" +#include "llvm/Transforms/IPO.h" +#include "llvm/Transforms/IPO/PassManagerBuilder.h" +#include "llvm/Transforms/Utils/GlobalStatus.h" +#include "llvm/Transforms/Utils/ModuleUtils.h" +#include "llvm/Transforms/Utils/ValueMapper.h" #include +#include +#include #include -// Support Windows/MinGW crazyness. -#ifdef _WIN32 -# include -# define lseek _lseek -# define read _read +#ifndef LDPO_PIE +// FIXME: remove this declaration when we stop maintaining Ubuntu Quantal and +// Precise and Debian Wheezy (binutils 2.23 is required) +# define LDPO_PIE 3 #endif using namespace llvm; namespace { - ld_plugin_status discard_message(int level, const char *format, ...) { - // Die loudly. Recent versions of Gold pass ld_plugin_message as the first - // callback in the transfer vector. This should never be called. - abort(); - } +struct claimed_file { + void *handle; + std::vector syms; +}; +} - ld_plugin_add_symbols add_symbols = NULL; - ld_plugin_get_symbols get_symbols = NULL; - ld_plugin_add_input_file add_input_file = NULL; - ld_plugin_add_input_library add_input_library = NULL; - ld_plugin_set_extra_library_path set_extra_library_path = NULL; - ld_plugin_get_view get_view = NULL; - ld_plugin_message message = discard_message; - - int api_version = 0; - int gold_version = 0; - - struct claimed_file { - void *handle; - std::vector syms; - }; - - lto_codegen_model output_type = LTO_CODEGEN_PIC_MODEL_STATIC; - std::string output_name = ""; - std::list Modules; - std::vector Cleanup; - lto_code_gen_t code_gen = NULL; +static ld_plugin_status discard_message(int level, const char *format, ...) { + // Die loudly. Recent versions of Gold pass ld_plugin_message as the first + // callback in the transfer vector. This should never be called. + abort(); } +static ld_plugin_get_input_file get_input_file = nullptr; +static ld_plugin_release_input_file release_input_file = nullptr; +static ld_plugin_add_symbols add_symbols = nullptr; +static ld_plugin_get_symbols get_symbols = nullptr; +static ld_plugin_add_input_file add_input_file = nullptr; +static ld_plugin_set_extra_library_path set_extra_library_path = nullptr; +static ld_plugin_get_view get_view = nullptr; +static ld_plugin_message message = discard_message; +static Reloc::Model RelocationModel = Reloc::Default; +static std::string output_name = ""; +static std::list Modules; +static std::vector Cleanup; +static llvm::TargetOptions TargetOpts; + namespace options { enum generate_bc { BC_NO, BC_ALSO, BC_ONLY }; static bool generate_api_file = false; @@ -83,11 +91,11 @@ namespace options { // as plugin exclusive to pass to the code generator. // For example, "generate-api-file" and "as"options are for the plugin // use only and will not be passed. - static std::vector extra; + static std::vector extra; static void process_plugin_option(const char* opt_) { - if (opt_ == NULL) + if (opt_ == nullptr) return; llvm::StringRef opt = opt_; @@ -109,14 +117,20 @@ namespace options { llvm::StringRef path = opt.substr(strlen("also-emit-llvm=")); generate_bc_file = BC_ALSO; if (!bc_path.empty()) { - (*message)(LDPL_WARNING, "Path to the output IL file specified twice. " - "Discarding %s", opt_); + message(LDPL_WARNING, "Path to the output IL file specified twice. " + "Discarding %s", + opt_); } else { bc_path = path; } } else { // Save this option to pass to the code generator. - extra.push_back(opt); + // ParseCommandLineOptions() expects argv[0] to be program name. Lazily + // add that. + if (extra.empty()) + extra.push_back("LLVMgold"); + + extra.push_back(opt_); } } } @@ -128,6 +142,12 @@ static ld_plugin_status cleanup_hook(void); extern "C" ld_plugin_status onload(ld_plugin_tv *tv); ld_plugin_status onload(ld_plugin_tv *tv) { + InitializeAllTargetInfos(); + InitializeAllTargets(); + InitializeAllTargetMCs(); + InitializeAllAsmParsers(); + InitializeAllAsmPrinters(); + // We're given a pointer to the first transfer vector. We read through them // until we find one where tv_tag == LDPT_NULL. The REGISTER_* tagged values // contain pointers to functions that we need to call to register our own @@ -135,15 +155,10 @@ ld_plugin_status onload(ld_plugin_tv *tv) { // for services. bool registeredClaimFile = false; + bool RegisteredAllSymbolsRead = false; for (; tv->tv_tag != LDPT_NULL; ++tv) { switch (tv->tv_tag) { - case LDPT_API_VERSION: - api_version = tv->tv_u.tv_val; - break; - case LDPT_GOLD_VERSION: // major * 100 + minor - gold_version = tv->tv_u.tv_val; - break; case LDPT_OUTPUT_NAME: output_name = tv->tv_u.tv_string; break; @@ -151,20 +166,16 @@ ld_plugin_status onload(ld_plugin_tv *tv) { switch (tv->tv_u.tv_val) { case LDPO_REL: // .o case LDPO_DYN: // .so - // FIXME: Replace 3 with LDPO_PIE once that is in a released binutils. - case 3: // position independent executable - output_type = LTO_CODEGEN_PIC_MODEL_DYNAMIC; + case LDPO_PIE: // position independent executable + RelocationModel = Reloc::PIC_; break; case LDPO_EXEC: // .exe - output_type = LTO_CODEGEN_PIC_MODEL_STATIC; + RelocationModel = Reloc::Static; break; default: - (*message)(LDPL_ERROR, "Unknown output file type %d", - tv->tv_u.tv_val); + message(LDPL_ERROR, "Unknown output file type %d", tv->tv_u.tv_val); return LDPS_ERR; } - // TODO: add an option to disable PIC. - //output_type = LTO_CODEGEN_PIC_MODEL_DYNAMIC_NO_PIC; break; case LDPT_OPTION: options::process_plugin_option(tv->tv_u.tv_string); @@ -173,7 +184,7 @@ ld_plugin_status onload(ld_plugin_tv *tv) { ld_plugin_register_claim_file callback; callback = tv->tv_u.tv_register_claim_file; - if ((*callback)(claim_file_hook) != LDPS_OK) + if (callback(claim_file_hook) != LDPS_OK) return LDPS_ERR; registeredClaimFile = true; @@ -182,18 +193,24 @@ ld_plugin_status onload(ld_plugin_tv *tv) { ld_plugin_register_all_symbols_read callback; callback = tv->tv_u.tv_register_all_symbols_read; - if ((*callback)(all_symbols_read_hook) != LDPS_OK) + if (callback(all_symbols_read_hook) != LDPS_OK) return LDPS_ERR; - code_gen = lto_codegen_create(); + RegisteredAllSymbolsRead = true; } break; case LDPT_REGISTER_CLEANUP_HOOK: { ld_plugin_register_cleanup callback; callback = tv->tv_u.tv_register_cleanup; - if ((*callback)(cleanup_hook) != LDPS_OK) + if (callback(cleanup_hook) != LDPS_OK) return LDPS_ERR; } break; + case LDPT_GET_INPUT_FILE: + get_input_file = tv->tv_u.tv_get_input_file; + break; + case LDPT_RELEASE_INPUT_FILE: + release_input_file = tv->tv_u.tv_release_input_file; + break; case LDPT_ADD_SYMBOLS: add_symbols = tv->tv_u.tv_add_symbols; break; @@ -203,9 +220,6 @@ ld_plugin_status onload(ld_plugin_tv *tv) { case LDPT_ADD_INPUT_FILE: add_input_file = tv->tv_u.tv_add_input_file; break; - case LDPT_ADD_INPUT_LIBRARY: - add_input_library = tv->tv_u.tv_add_input_file; - break; case LDPT_SET_EXTRA_LIBRARY_PATH: set_extra_library_path = tv->tv_u.tv_set_extra_library_path; break; @@ -221,30 +235,50 @@ ld_plugin_status onload(ld_plugin_tv *tv) { } if (!registeredClaimFile) { - (*message)(LDPL_ERROR, "register_claim_file not passed to LLVMgold."); + message(LDPL_ERROR, "register_claim_file not passed to LLVMgold."); return LDPS_ERR; } if (!add_symbols) { - (*message)(LDPL_ERROR, "add_symbols not passed to LLVMgold."); + message(LDPL_ERROR, "add_symbols not passed to LLVMgold."); + return LDPS_ERR; + } + + if (!RegisteredAllSymbolsRead) + return LDPS_OK; + + if (!get_input_file) { + message(LDPL_ERROR, "get_input_file not passed to LLVMgold."); + return LDPS_ERR; + } + if (!release_input_file) { + message(LDPL_ERROR, "relesase_input_file not passed to LLVMgold."); return LDPS_ERR; } return LDPS_OK; } -/// claim_file_hook - called by gold to see whether this file is one that -/// our plugin can handle. We'll try to open it and register all the symbols -/// with add_symbol if possible. +static const GlobalObject *getBaseObject(const GlobalValue &GV) { + if (auto *GA = dyn_cast(&GV)) + return GA->getBaseObject(); + return cast(&GV); +} + +/// Called by gold to see whether this file is one that our plugin can handle. +/// We'll try to open it and register all the symbols with add_symbol if +/// possible. static ld_plugin_status claim_file_hook(const ld_plugin_input_file *file, int *claimed) { - lto_module_t M; - const void *view; - OwningPtr buffer; + LLVMContext Context; + MemoryBufferRef BufferRef; + std::unique_ptr Buffer; if (get_view) { + const void *view; if (get_view(file->handle, &view) != LDPS_OK) { - (*message)(LDPL_ERROR, "Failed to get a view of %s", file->name); + message(LDPL_ERROR, "Failed to get a view of %s", file->name); return LDPS_ERR; } + BufferRef = MemoryBufferRef(StringRef((const char *)view, file->filesize), ""); } else { int64_t offset = 0; // Gold has found what might be IR part-way inside of a file, such as @@ -252,163 +286,514 @@ static ld_plugin_status claim_file_hook(const ld_plugin_input_file *file, if (file->offset) { offset = file->offset; } - if (error_code ec = MemoryBuffer::getOpenFileSlice( - file->fd, file->name, buffer, file->filesize, offset)) { - (*message)(LDPL_ERROR, ec.message().c_str()); + ErrorOr> BufferOrErr = + MemoryBuffer::getOpenFileSlice(file->fd, file->name, file->filesize, + offset); + if (std::error_code EC = BufferOrErr.getError()) { + message(LDPL_ERROR, EC.message().c_str()); return LDPS_ERR; } - view = buffer->getBufferStart(); + Buffer = std::move(BufferOrErr.get()); + BufferRef = Buffer->getMemBufferRef(); } - if (!lto_module_is_object_file_in_memory(view, file->filesize)) + ErrorOr> ObjOrErr = + object::IRObjectFile::createIRObjectFile(BufferRef, Context); + std::error_code EC = ObjOrErr.getError(); + if (EC == BitcodeError::InvalidBitcodeSignature || + EC == object::object_error::invalid_file_type || + EC == object::object_error::bitcode_section_not_found) return LDPS_OK; - M = lto_module_create_from_memory(view, file->filesize); - if (!M) { - if (const char* msg = lto_get_error_message()) { - (*message)(LDPL_ERROR, - "LLVM gold plugin has failed to create LTO module: %s", - msg); - return LDPS_ERR; - } - return LDPS_OK; + *claimed = 1; + + if (EC) { + message(LDPL_ERROR, "LLVM gold plugin has failed to create LTO module: %s", + EC.message().c_str()); + return LDPS_ERR; } + std::unique_ptr Obj = std::move(*ObjOrErr); - *claimed = 1; Modules.resize(Modules.size() + 1); claimed_file &cf = Modules.back(); - if (!options::triple.empty()) - lto_module_set_target_triple(M, options::triple.c_str()); - cf.handle = file->handle; - unsigned sym_count = lto_module_get_num_symbols(M); - cf.syms.reserve(sym_count); - for (unsigned i = 0; i != sym_count; ++i) { - lto_symbol_attributes attrs = lto_module_get_symbol_attribute(M, i); - if ((attrs & LTO_SYMBOL_SCOPE_MASK) == LTO_SYMBOL_SCOPE_INTERNAL) + for (auto &Sym : Obj->symbols()) { + uint32_t Symflags = Sym.getFlags(); + if (!(Symflags & object::BasicSymbolRef::SF_Global)) + continue; + + if (Symflags & object::BasicSymbolRef::SF_FormatSpecific) continue; cf.syms.push_back(ld_plugin_symbol()); ld_plugin_symbol &sym = cf.syms.back(); - sym.name = const_cast(lto_module_get_symbol_name(M, i)); - sym.name = strdup(sym.name); - sym.version = NULL; + sym.version = nullptr; - int scope = attrs & LTO_SYMBOL_SCOPE_MASK; - switch (scope) { - case LTO_SYMBOL_SCOPE_HIDDEN: + SmallString<64> Name; + { + raw_svector_ostream OS(Name); + Sym.printName(OS); + } + sym.name = strdup(Name.c_str()); + + const GlobalValue *GV = Obj->getSymbolGV(Sym.getRawDataRefImpl()); + + sym.visibility = LDPV_DEFAULT; + if (GV) { + switch (GV->getVisibility()) { + case GlobalValue::DefaultVisibility: + sym.visibility = LDPV_DEFAULT; + break; + case GlobalValue::HiddenVisibility: sym.visibility = LDPV_HIDDEN; break; - case LTO_SYMBOL_SCOPE_PROTECTED: + case GlobalValue::ProtectedVisibility: sym.visibility = LDPV_PROTECTED; break; - case 0: // extern - case LTO_SYMBOL_SCOPE_DEFAULT: - sym.visibility = LDPV_DEFAULT; - break; - default: - (*message)(LDPL_ERROR, "Unknown scope attribute: %d", scope); - return LDPS_ERR; + } } - int definition = attrs & LTO_SYMBOL_DEFINITION_MASK; - sym.comdat_key = NULL; - switch (definition) { - case LTO_SYMBOL_DEFINITION_REGULAR: - sym.def = LDPK_DEF; - break; - case LTO_SYMBOL_DEFINITION_UNDEFINED: - sym.def = LDPK_UNDEF; - break; - case LTO_SYMBOL_DEFINITION_TENTATIVE: - sym.def = LDPK_COMMON; - break; - case LTO_SYMBOL_DEFINITION_WEAK: - sym.comdat_key = sym.name; - sym.def = LDPK_WEAKDEF; - break; - case LTO_SYMBOL_DEFINITION_WEAKUNDEF: + if (Symflags & object::BasicSymbolRef::SF_Undefined) { + sym.def = LDPK_UNDEF; + if (GV && GV->hasExternalWeakLinkage()) sym.def = LDPK_WEAKUNDEF; - break; - default: - (*message)(LDPL_ERROR, "Unknown definition attribute: %d", definition); - return LDPS_ERR; + } else { + sym.def = LDPK_DEF; + if (GV) { + assert(!GV->hasExternalWeakLinkage() && + !GV->hasAvailableExternallyLinkage() && "Not a declaration!"); + if (GV->hasCommonLinkage()) + sym.def = LDPK_COMMON; + else if (GV->isWeakForLinker()) + sym.def = LDPK_WEAKDEF; + } } sym.size = 0; + sym.comdat_key = nullptr; + if (GV) { + const GlobalObject *Base = getBaseObject(*GV); + if (!Base) + message(LDPL_FATAL, "Unable to determine comdat of alias!"); + const Comdat *C = Base->getComdat(); + if (C) + sym.comdat_key = strdup(C->getName().str().c_str()); + else if (Base->hasWeakLinkage() || Base->hasLinkOnceLinkage()) + sym.comdat_key = strdup(sym.name); + } sym.resolution = LDPR_UNKNOWN; } - cf.syms.reserve(cf.syms.size()); - if (!cf.syms.empty()) { - if ((*add_symbols)(cf.handle, cf.syms.size(), &cf.syms[0]) != LDPS_OK) { - (*message)(LDPL_ERROR, "Unable to add symbols!"); + if (add_symbols(cf.handle, cf.syms.size(), &cf.syms[0]) != LDPS_OK) { + message(LDPL_ERROR, "Unable to add symbols!"); return LDPS_ERR; } } - if (code_gen) - lto_codegen_add_module(code_gen, M); + return LDPS_OK; +} - lto_module_dispose(M); +static void keepGlobalValue(GlobalValue &GV, + std::vector &KeptAliases) { + assert(!GV.hasLocalLinkage()); + + if (auto *GA = dyn_cast(&GV)) + KeptAliases.push_back(GA); + + switch (GV.getLinkage()) { + default: + break; + case GlobalValue::LinkOnceAnyLinkage: + GV.setLinkage(GlobalValue::WeakAnyLinkage); + break; + case GlobalValue::LinkOnceODRLinkage: + GV.setLinkage(GlobalValue::WeakODRLinkage); + break; + } - return LDPS_OK; + assert(!GV.isDiscardableIfUnused()); } -/// all_symbols_read_hook - gold informs us that all symbols have been read. -/// At this point, we use get_symbols to see if any of our definitions have -/// been overridden by a native object file. Then, perform optimization and -/// codegen. -static ld_plugin_status all_symbols_read_hook(void) { - std::ofstream api_file; - assert(code_gen); - - if (options::generate_api_file) { - api_file.open("apifile.txt", std::ofstream::out | std::ofstream::trunc); - if (!api_file.is_open()) { - (*message)(LDPL_FATAL, "Unable to open apifile.txt for writing."); - abort(); +static void internalize(GlobalValue &GV) { + if (GV.isDeclarationForLinker()) + return; // We get here if there is a matching asm definition. + if (!GV.hasLocalLinkage()) + GV.setLinkage(GlobalValue::InternalLinkage); +} + +static void drop(GlobalValue &GV) { + if (auto *F = dyn_cast(&GV)) { + F->deleteBody(); + F->setComdat(nullptr); // Should deleteBody do this? + return; + } + + if (auto *Var = dyn_cast(&GV)) { + Var->setInitializer(nullptr); + Var->setLinkage( + GlobalValue::ExternalLinkage); // Should setInitializer do this? + Var->setComdat(nullptr); // and this? + return; + } + + auto &Alias = cast(GV); + Module &M = *Alias.getParent(); + PointerType &Ty = *cast(Alias.getType()); + GlobalValue::LinkageTypes L = Alias.getLinkage(); + auto *Var = + new GlobalVariable(M, Ty.getElementType(), /*isConstant*/ false, L, + /*Initializer*/ nullptr); + Var->takeName(&Alias); + Alias.replaceAllUsesWith(Var); + Alias.eraseFromParent(); +} + +static const char *getResolutionName(ld_plugin_symbol_resolution R) { + switch (R) { + case LDPR_UNKNOWN: + return "UNKNOWN"; + case LDPR_UNDEF: + return "UNDEF"; + case LDPR_PREVAILING_DEF: + return "PREVAILING_DEF"; + case LDPR_PREVAILING_DEF_IRONLY: + return "PREVAILING_DEF_IRONLY"; + case LDPR_PREEMPTED_REG: + return "PREEMPTED_REG"; + case LDPR_PREEMPTED_IR: + return "PREEMPTED_IR"; + case LDPR_RESOLVED_IR: + return "RESOLVED_IR"; + case LDPR_RESOLVED_EXEC: + return "RESOLVED_EXEC"; + case LDPR_RESOLVED_DYN: + return "RESOLVED_DYN"; + case LDPR_PREVAILING_DEF_IRONLY_EXP: + return "PREVAILING_DEF_IRONLY_EXP"; + } + llvm_unreachable("Unknown resolution"); +} + +static GlobalObject *makeInternalReplacement(GlobalObject *GO) { + Module *M = GO->getParent(); + GlobalObject *Ret; + if (auto *F = dyn_cast(GO)) { + if (F->isMaterializable()) { + if (F->materialize()) + message(LDPL_FATAL, "LLVM gold plugin has failed to read a function"); + } + + auto *NewF = Function::Create(F->getFunctionType(), F->getLinkage(), + F->getName(), M); + + ValueToValueMapTy VM; + Function::arg_iterator NewI = NewF->arg_begin(); + for (auto &Arg : F->args()) { + NewI->setName(Arg.getName()); + VM[&Arg] = NewI; + ++NewI; + } + + NewF->getBasicBlockList().splice(NewF->end(), F->getBasicBlockList()); + for (auto &BB : *NewF) { + for (auto &Inst : BB) + RemapInstruction(&Inst, VM, RF_IgnoreMissingEntries); + } + + Ret = NewF; + F->deleteBody(); + } else { + auto *Var = cast(GO); + Ret = new GlobalVariable( + *M, Var->getType()->getElementType(), Var->isConstant(), + Var->getLinkage(), Var->getInitializer(), Var->getName(), + nullptr, Var->getThreadLocalMode(), Var->getType()->getAddressSpace(), + Var->isExternallyInitialized()); + Var->setInitializer(nullptr); } + Ret->copyAttributesFrom(GO); + Ret->setLinkage(GlobalValue::InternalLinkage); + Ret->setComdat(GO->getComdat()); + + return Ret; +} + +namespace { +class LocalValueMaterializer : public ValueMaterializer { + DenseSet &Dropped; - for (std::list::iterator I = Modules.begin(), - E = Modules.end(); I != E; ++I) { - if (I->syms.empty()) +public: + LocalValueMaterializer(DenseSet &Dropped) : Dropped(Dropped) {} + Value *materializeValueFor(Value *V) override; +}; +} + +Value *LocalValueMaterializer::materializeValueFor(Value *V) { + auto *GV = dyn_cast(V); + if (!GV) + return nullptr; + if (!Dropped.count(GV)) + return nullptr; + assert(!isa(GV) && "Found alias point to weak alias."); + return makeInternalReplacement(cast(GV)); +} + +static Constant *mapConstantToLocalCopy(Constant *C, ValueToValueMapTy &VM, + LocalValueMaterializer *Materializer) { + return MapValue(C, VM, RF_IgnoreMissingEntries, nullptr, Materializer); +} + +static std::unique_ptr +getModuleForFile(LLVMContext &Context, claimed_file &F, raw_fd_ostream *ApiFile, + StringSet<> &Internalize, StringSet<> &Maybe) { + ld_plugin_input_file File; + if (get_input_file(F.handle, &File) != LDPS_OK) + message(LDPL_FATAL, "Failed to get file information"); + + if (get_symbols(F.handle, F.syms.size(), &F.syms[0]) != LDPS_OK) + message(LDPL_FATAL, "Failed to get symbol information"); + + const void *View; + if (get_view(F.handle, &View) != LDPS_OK) + message(LDPL_FATAL, "Failed to get a view of file"); + + llvm::ErrorOr MBOrErr = + object::IRObjectFile::findBitcodeInMemBuffer( + MemoryBufferRef(StringRef((const char *)View, File.filesize), "")); + if (std::error_code EC = MBOrErr.getError()) + message(LDPL_FATAL, "Could not read bitcode from file : %s", + EC.message().c_str()); + + std::unique_ptr Buffer = + MemoryBuffer::getMemBuffer(MBOrErr->getBuffer(), "", false); + + if (release_input_file(F.handle) != LDPS_OK) + message(LDPL_FATAL, "Failed to release file information"); + + ErrorOr MOrErr = getLazyBitcodeModule(std::move(Buffer), Context); + + if (std::error_code EC = MOrErr.getError()) + message(LDPL_FATAL, "Could not read bitcode from file : %s", + EC.message().c_str()); + + std::unique_ptr M(MOrErr.get()); + + SmallPtrSet Used; + collectUsedGlobalVariables(*M, Used, /*CompilerUsed*/ false); + + DenseSet Drop; + std::vector KeptAliases; + for (ld_plugin_symbol &Sym : F.syms) { + ld_plugin_symbol_resolution Resolution = + (ld_plugin_symbol_resolution)Sym.resolution; + + if (options::generate_api_file) + *ApiFile << Sym.name << ' ' << getResolutionName(Resolution) << '\n'; + + GlobalValue *GV = M->getNamedValue(Sym.name); + if (!GV) + continue; // Asm symbol. + + if (Resolution != LDPR_PREVAILING_DEF_IRONLY && GV->hasCommonLinkage()) { + // Common linkage is special. There is no single symbol that wins the + // resolution. Instead we have to collect the maximum alignment and size. + // The IR linker does that for us if we just pass it every common GV. + // We still have to keep track of LDPR_PREVAILING_DEF_IRONLY so we + // internalize once the IR linker has done its job. continue; - (*get_symbols)(I->handle, I->syms.size(), &I->syms[0]); - for (unsigned i = 0, e = I->syms.size(); i != e; i++) { - if (I->syms[i].resolution == LDPR_PREVAILING_DEF) { - lto_codegen_add_must_preserve_symbol(code_gen, I->syms[i].name); - - if (options::generate_api_file) - api_file << I->syms[i].name << "\n"; - } else if (I->syms[i].resolution == LDPR_PREVAILING_DEF_IRONLY_EXP) { - lto_codegen_add_dso_symbol(code_gen, I->syms[i].name); - - if (options::generate_api_file) - api_file << I->syms[i].name << " dso only\n"; + } + + switch (Resolution) { + case LDPR_UNKNOWN: + llvm_unreachable("Unexpected resolution"); + + case LDPR_RESOLVED_IR: + case LDPR_RESOLVED_EXEC: + case LDPR_RESOLVED_DYN: + case LDPR_UNDEF: + assert(GV->isDeclarationForLinker()); + break; + + case LDPR_PREVAILING_DEF_IRONLY: { + keepGlobalValue(*GV, KeptAliases); + if (!Used.count(GV)) { + // Since we use the regular lib/Linker, we cannot just internalize GV + // now or it will not be copied to the merged module. Instead we force + // it to be copied and then internalize it. + Internalize.insert(Sym.name); } + break; + } + + case LDPR_PREVAILING_DEF: + keepGlobalValue(*GV, KeptAliases); + break; + + case LDPR_PREEMPTED_IR: + // Gold might have selected a linkonce_odr and preempted a weak_odr. + // In that case we have to make sure we don't end up internalizing it. + if (!GV->isDiscardableIfUnused()) + Maybe.erase(Sym.name); + + // fall-through + case LDPR_PREEMPTED_REG: + Drop.insert(GV); + break; + + case LDPR_PREVAILING_DEF_IRONLY_EXP: { + // We can only check for address uses after we merge the modules. The + // reason is that this GV might have a copy in another module + // and in that module the address might be significant, but that + // copy will be LDPR_PREEMPTED_IR. + if (GV->hasLinkOnceODRLinkage()) + Maybe.insert(Sym.name); + keepGlobalValue(*GV, KeptAliases); + break; + } } + + free(Sym.name); + free(Sym.comdat_key); + Sym.name = nullptr; + Sym.comdat_key = nullptr; } - if (options::generate_api_file) - api_file.close(); + ValueToValueMapTy VM; + LocalValueMaterializer Materializer(Drop); + for (GlobalAlias *GA : KeptAliases) { + // Gold told us to keep GA. It is possible that a GV usied in the aliasee + // expression is being dropped. If that is the case, that GV must be copied. + Constant *Aliasee = GA->getAliasee(); + Constant *Replacement = mapConstantToLocalCopy(Aliasee, VM, &Materializer); + if (Aliasee != Replacement) + GA->setAliasee(Replacement); + } - lto_codegen_set_pic_model(code_gen, output_type); - lto_codegen_set_debug_model(code_gen, LTO_DEBUG_MODEL_DWARF); - if (!options::mcpu.empty()) - lto_codegen_set_cpu(code_gen, options::mcpu.c_str()); + for (auto *GV : Drop) + drop(*GV); - // Pass through extra options to the code generator. - if (!options::extra.empty()) { - for (std::vector::iterator it = options::extra.begin(); - it != options::extra.end(); ++it) { - lto_codegen_debug_options(code_gen, (*it).c_str()); + return M; +} + +static void runLTOPasses(Module &M, TargetMachine &TM) { + PassManager passes; + PassManagerBuilder PMB; + PMB.LibraryInfo = new TargetLibraryInfo(Triple(TM.getTargetTriple())); + PMB.Inliner = createFunctionInliningPass(); + PMB.VerifyInput = true; + PMB.VerifyOutput = true; + PMB.populateLTOPassManager(passes, &TM); + passes.run(M); +} + +static void codegen(Module &M) { + const std::string &TripleStr = M.getTargetTriple(); + Triple TheTriple(TripleStr); + + std::string ErrMsg; + const Target *TheTarget = TargetRegistry::lookupTarget(TripleStr, ErrMsg); + if (!TheTarget) + message(LDPL_FATAL, "Target not found: %s", ErrMsg.c_str()); + + if (unsigned NumOpts = options::extra.size()) + cl::ParseCommandLineOptions(NumOpts, &options::extra[0]); + + SubtargetFeatures Features; + Features.getDefaultSubtargetFeatures(TheTriple); + for (const std::string &A : MAttrs) + Features.AddFeature(A); + + TargetOptions Options = InitTargetOptionsFromCodeGenFlags(); + std::unique_ptr TM(TheTarget->createTargetMachine( + TripleStr, options::mcpu, Features.getString(), Options, RelocationModel, + CodeModel::Default, CodeGenOpt::Aggressive)); + + runLTOPasses(M, *TM); + + PassManager CodeGenPasses; + CodeGenPasses.add(new DataLayoutPass()); + + SmallString<128> Filename; + int FD; + if (options::obj_path.empty()) { + std::error_code EC = + sys::fs::createTemporaryFile("lto-llvm", "o", FD, Filename); + if (EC) + message(LDPL_FATAL, "Could not create temorary file: %s", + EC.message().c_str()); + } else { + Filename = options::obj_path; + std::error_code EC = + sys::fs::openFileForWrite(Filename.c_str(), FD, sys::fs::F_None); + if (EC) + message(LDPL_FATAL, "Could not open file: %s", EC.message().c_str()); + } + + { + raw_fd_ostream OS(FD, true); + formatted_raw_ostream FOS(OS); + + if (TM->addPassesToEmitFile(CodeGenPasses, FOS, + TargetMachine::CGFT_ObjectFile)) + message(LDPL_FATAL, "Failed to setup codegen"); + CodeGenPasses.run(M); + } + + if (add_input_file(Filename.c_str()) != LDPS_OK) + message(LDPL_FATAL, + "Unable to add .o file to the link. File left behind in: %s", + Filename.c_str()); + + if (options::obj_path.empty()) + Cleanup.push_back(Filename.c_str()); +} + +/// gold informs us that all symbols have been read. At this point, we use +/// get_symbols to see if any of our definitions have been overridden by a +/// native object file. Then, perform optimization and codegen. +static ld_plugin_status allSymbolsReadHook(raw_fd_ostream *ApiFile) { + if (Modules.empty()) + return LDPS_OK; + + LLVMContext Context; + std::unique_ptr Combined(new Module("ld-temp.o", Context)); + Linker L(Combined.get()); + + std::string DefaultTriple = sys::getDefaultTargetTriple(); + + StringSet<> Internalize; + StringSet<> Maybe; + for (claimed_file &F : Modules) { + std::unique_ptr M = + getModuleForFile(Context, F, ApiFile, Internalize, Maybe); + if (!options::triple.empty()) + M->setTargetTriple(options::triple.c_str()); + else if (M->getTargetTriple().empty()) { + M->setTargetTriple(DefaultTriple); } + + if (L.linkInModule(M.get())) + message(LDPL_FATAL, "Failed to link module"); + } + + for (const auto &Name : Internalize) { + GlobalValue *GV = Combined->getNamedValue(Name.first()); + if (GV) + internalize(*GV); + } + + for (const auto &Name : Maybe) { + GlobalValue *GV = Combined->getNamedValue(Name.first()); + if (!GV) + continue; + GV->setLinkage(GlobalValue::LinkOnceODRLinkage); + if (canBeOmittedFromSymbolTable(GV)) + internalize(*GV); } if (options::generate_bc_file != options::BC_NO) { @@ -419,52 +804,51 @@ static ld_plugin_status all_symbols_read_hook(void) { path = options::bc_path; else path = output_name + ".bc"; - bool err = lto_codegen_write_merged_modules(code_gen, path.c_str()); - if (err) - (*message)(LDPL_FATAL, "Failed to write the output file."); - if (options::generate_bc_file == options::BC_ONLY) { - lto_codegen_dispose(code_gen); - exit(0); - } - } - const char *objPath; - if (lto_codegen_compile_to_file(code_gen, &objPath)) { - (*message)(LDPL_ERROR, "Could not produce a combined object file\n"); - } - - lto_codegen_dispose(code_gen); - for (std::list::iterator I = Modules.begin(), - E = Modules.end(); I != E; ++I) { - for (unsigned i = 0; i != I->syms.size(); ++i) { - ld_plugin_symbol &sym = I->syms[i]; - free(sym.name); + { + std::error_code EC; + raw_fd_ostream OS(path, EC, sys::fs::OpenFlags::F_None); + if (EC) + message(LDPL_FATAL, "Failed to write the output file."); + WriteBitcodeToFile(L.getModule(), OS); } + if (options::generate_bc_file == options::BC_ONLY) + return LDPS_OK; } - if ((*add_input_file)(objPath) != LDPS_OK) { - (*message)(LDPL_ERROR, "Unable to add .o file to the link."); - (*message)(LDPL_ERROR, "File left behind in: %s", objPath); - return LDPS_ERR; - } + codegen(*L.getModule()); if (!options::extra_library_path.empty() && - set_extra_library_path(options::extra_library_path.c_str()) != LDPS_OK) { - (*message)(LDPL_ERROR, "Unable to set the extra library path."); - return LDPS_ERR; + set_extra_library_path(options::extra_library_path.c_str()) != LDPS_OK) + message(LDPL_FATAL, "Unable to set the extra library path."); + + return LDPS_OK; +} + +static ld_plugin_status all_symbols_read_hook(void) { + ld_plugin_status Ret; + if (!options::generate_api_file) { + Ret = allSymbolsReadHook(nullptr); + } else { + std::error_code EC; + raw_fd_ostream ApiFile("apifile.txt", EC, sys::fs::F_None); + if (EC) + message(LDPL_FATAL, "Unable to open apifile.txt for writing: %s", + EC.message().c_str()); + Ret = allSymbolsReadHook(&ApiFile); } - if (options::obj_path.empty()) - Cleanup.push_back(objPath); + if (options::generate_bc_file == options::BC_ONLY) + exit(0); - return LDPS_OK; + return Ret; } static ld_plugin_status cleanup_hook(void) { - for (int i = 0, e = Cleanup.size(); i != e; ++i) { - error_code EC = sys::fs::remove(Cleanup[i]); + for (std::string &Name : Cleanup) { + std::error_code EC = sys::fs::remove(Name); if (EC) - (*message)(LDPL_ERROR, "Failed to delete '%s': %s", Cleanup[i].c_str(), - EC.message().c_str()); + message(LDPL_ERROR, "Failed to delete '%s': %s", Name.c_str(), + EC.message().c_str()); } return LDPS_OK;