diff options
Diffstat (limited to 'contrib/llvm/tools/lld/ELF/Writer.cpp')
| -rw-r--r-- | contrib/llvm/tools/lld/ELF/Writer.cpp | 2654 |
1 files changed, 1400 insertions, 1254 deletions
diff --git a/contrib/llvm/tools/lld/ELF/Writer.cpp b/contrib/llvm/tools/lld/ELF/Writer.cpp index 5c64bedb15ac..b8c8891648a4 100644 --- a/contrib/llvm/tools/lld/ELF/Writer.cpp +++ b/contrib/llvm/tools/lld/ELF/Writer.cpp @@ -1,9 +1,8 @@ //===- Writer.cpp ---------------------------------------------------------===// // -// The LLVM Linker -// -// This file is distributed under the University of Illinois Open Source -// License. See LICENSE.TXT for details. +// 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 // //===----------------------------------------------------------------------===// @@ -11,7 +10,6 @@ #include "AArch64ErrataFix.h" #include "CallGraphSort.h" #include "Config.h" -#include "Filesystem.h" #include "LinkerScript.h" #include "MapFile.h" #include "OutputSections.h" @@ -20,11 +18,15 @@ #include "Symbols.h" #include "SyntheticSections.h" #include "Target.h" +#include "lld/Common/Filesystem.h" #include "lld/Common/Memory.h" #include "lld/Common/Strings.h" #include "lld/Common/Threads.h" #include "llvm/ADT/StringMap.h" #include "llvm/ADT/StringSwitch.h" +#include "llvm/Support/RandomNumberGenerator.h" +#include "llvm/Support/SHA1.h" +#include "llvm/Support/xxhash.h" #include <climits> using namespace llvm; @@ -40,31 +42,32 @@ namespace { // The writer writes a SymbolTable result to a file. template <class ELFT> class Writer { public: - Writer() : Buffer(errorHandler().OutputBuffer) {} - typedef typename ELFT::Shdr Elf_Shdr; - typedef typename ELFT::Ehdr Elf_Ehdr; - typedef typename ELFT::Phdr Elf_Phdr; + Writer() : buffer(errorHandler().outputBuffer) {} + using Elf_Shdr = typename ELFT::Shdr; + using Elf_Ehdr = typename ELFT::Ehdr; + using Elf_Phdr = typename ELFT::Phdr; void run(); private: void copyLocalSymbols(); void addSectionSymbols(); - void forEachRelSec(llvm::function_ref<void(InputSectionBase &)> Fn); + void forEachRelSec(llvm::function_ref<void(InputSectionBase &)> fn); void sortSections(); void resolveShfLinkOrder(); - void maybeAddThunks(); + void finalizeAddressDependentContent(); void sortInputSections(); void finalizeSections(); void checkExecuteOnly(); void setReservedSymbolSections(); - std::vector<PhdrEntry *> createPhdrs(); - void removeEmptyPTLoad(); - void addPtArmExid(std::vector<PhdrEntry *> &Phdrs); + std::vector<PhdrEntry *> createPhdrs(Partition &part); + void removeEmptyPTLoad(std::vector<PhdrEntry *> &phdrEntry); + void addPhdrForSection(Partition &part, unsigned shType, unsigned pType, + unsigned pFlags); void assignFileOffsets(); void assignFileOffsetsBinary(); - void setPhdrs(); + void setPhdrs(Partition &part); void checkSections(); void fixSectionAlignments(); void openFile(); @@ -74,36 +77,34 @@ private: void writeSectionsBinary(); void writeBuildId(); - std::unique_ptr<FileOutputBuffer> &Buffer; + std::unique_ptr<FileOutputBuffer> &buffer; void addRelIpltSymbols(); void addStartEndSymbols(); - void addStartStopSymbols(OutputSection *Sec); - - std::vector<PhdrEntry *> Phdrs; + void addStartStopSymbols(OutputSection *sec); - uint64_t FileSize; - uint64_t SectionHeaderOff; + uint64_t fileSize; + uint64_t sectionHeaderOff; }; } // anonymous namespace -static bool isSectionPrefix(StringRef Prefix, StringRef Name) { - return Name.startswith(Prefix) || Name == Prefix.drop_back(); +static bool isSectionPrefix(StringRef prefix, StringRef name) { + return name.startswith(prefix) || name == prefix.drop_back(); } -StringRef elf::getOutputSectionName(const InputSectionBase *S) { - if (Config->Relocatable) - return S->Name; +StringRef elf::getOutputSectionName(const InputSectionBase *s) { + if (config->relocatable) + return s->name; // This is for --emit-relocs. If .text.foo is emitted as .text.bar, we want // to emit .rela.text.foo as .rela.text.bar for consistency (this is not // technically required, but not doing it is odd). This code guarantees that. - if (auto *IS = dyn_cast<InputSection>(S)) { - if (InputSectionBase *Rel = IS->getRelocatedSection()) { - OutputSection *Out = Rel->getOutputSection(); - if (S->Type == SHT_RELA) - return Saver.save(".rela" + Out->Name); - return Saver.save(".rel" + Out->Name); + if (auto *isec = dyn_cast<InputSection>(s)) { + if (InputSectionBase *rel = isec->getRelocatedSection()) { + OutputSection *out = rel->getOutputSection(); + if (s->type == SHT_RELA) + return saver.save(".rela" + out->name); + return saver.save(".rel" + out->name); } } @@ -113,97 +114,133 @@ StringRef elf::getOutputSectionName(const InputSectionBase *S) { // When enabled, this allows identifying the hot code region (.text.hot) in // the final binary which can be selectively mapped to huge pages or mlocked, // for instance. - if (Config->ZKeepTextSectionPrefix) - for (StringRef V : + if (config->zKeepTextSectionPrefix) + for (StringRef v : {".text.hot.", ".text.unlikely.", ".text.startup.", ".text.exit."}) - if (isSectionPrefix(V, S->Name)) - return V.drop_back(); + if (isSectionPrefix(v, s->name)) + return v.drop_back(); - for (StringRef V : + for (StringRef v : {".text.", ".rodata.", ".data.rel.ro.", ".data.", ".bss.rel.ro.", ".bss.", ".init_array.", ".fini_array.", ".ctors.", ".dtors.", ".tbss.", ".gcc_except_table.", ".tdata.", ".ARM.exidx.", ".ARM.extab."}) - if (isSectionPrefix(V, S->Name)) - return V.drop_back(); + if (isSectionPrefix(v, s->name)) + return v.drop_back(); // CommonSection is identified as "COMMON" in linker scripts. // By default, it should go to .bss section. - if (S->Name == "COMMON") + if (s->name == "COMMON") return ".bss"; - return S->Name; + return s->name; } static bool needsInterpSection() { - return !SharedFiles.empty() && !Config->DynamicLinker.empty() && - Script->needsInterpSection(); + return !sharedFiles.empty() && !config->dynamicLinker.empty() && + script->needsInterpSection(); } template <class ELFT> void elf::writeResult() { Writer<ELFT>().run(); } -template <class ELFT> void Writer<ELFT>::removeEmptyPTLoad() { - llvm::erase_if(Phdrs, [&](const PhdrEntry *P) { - if (P->p_type != PT_LOAD) +template <class ELFT> +void Writer<ELFT>::removeEmptyPTLoad(std::vector<PhdrEntry *> &phdrs) { + llvm::erase_if(phdrs, [&](const PhdrEntry *p) { + if (p->p_type != PT_LOAD) return false; - if (!P->FirstSec) + if (!p->firstSec) return true; - uint64_t Size = P->LastSec->Addr + P->LastSec->Size - P->FirstSec->Addr; - return Size == 0; + uint64_t size = p->lastSec->addr + p->lastSec->size - p->firstSec->addr; + return size == 0; }); } -template <class ELFT> static void combineEhFrameSections() { - for (InputSectionBase *&S : InputSections) { - EhInputSection *ES = dyn_cast<EhInputSection>(S); - if (!ES || !ES->Live) +template <class ELFT> static void copySectionsIntoPartitions() { + std::vector<InputSectionBase *> newSections; + for (unsigned part = 2; part != partitions.size() + 1; ++part) { + for (InputSectionBase *s : inputSections) { + if (!(s->flags & SHF_ALLOC) || !s->isLive()) + continue; + InputSectionBase *copy; + if (s->type == SHT_NOTE) + copy = make<InputSection>(cast<InputSection>(*s)); + else if (auto *es = dyn_cast<EhInputSection>(s)) + copy = make<EhInputSection>(*es); + else + continue; + copy->partition = part; + newSections.push_back(copy); + } + } + + inputSections.insert(inputSections.end(), newSections.begin(), + newSections.end()); +} + +template <class ELFT> static void combineEhSections() { + for (InputSectionBase *&s : inputSections) { + // Ignore dead sections and the partition end marker (.part.end), + // whose partition number is out of bounds. + if (!s->isLive() || s->partition == 255) continue; - In.EhFrame->addSection<ELFT>(ES); - S = nullptr; + Partition &part = s->getPartition(); + if (auto *es = dyn_cast<EhInputSection>(s)) { + part.ehFrame->addSection<ELFT>(es); + s = nullptr; + } else if (s->kind() == SectionBase::Regular && part.armExidx && + part.armExidx->addSection(cast<InputSection>(s))) { + s = nullptr; + } } - std::vector<InputSectionBase *> &V = InputSections; - V.erase(std::remove(V.begin(), V.end(), nullptr), V.end()); + std::vector<InputSectionBase *> &v = inputSections; + v.erase(std::remove(v.begin(), v.end(), nullptr), v.end()); } -static Defined *addOptionalRegular(StringRef Name, SectionBase *Sec, - uint64_t Val, uint8_t StOther = STV_HIDDEN, - uint8_t Binding = STB_GLOBAL) { - Symbol *S = Symtab->find(Name); - if (!S || S->isDefined()) +static Defined *addOptionalRegular(StringRef name, SectionBase *sec, + uint64_t val, uint8_t stOther = STV_HIDDEN, + uint8_t binding = STB_GLOBAL) { + Symbol *s = symtab->find(name); + if (!s || s->isDefined()) return nullptr; - return Symtab->addDefined(Name, StOther, STT_NOTYPE, Val, - /*Size=*/0, Binding, Sec, - /*File=*/nullptr); + + s->resolve(Defined{/*file=*/nullptr, name, binding, stOther, STT_NOTYPE, val, + /*size=*/0, sec}); + return cast<Defined>(s); } -static Defined *addAbsolute(StringRef Name) { - return Symtab->addDefined(Name, STV_HIDDEN, STT_NOTYPE, 0, 0, STB_GLOBAL, - nullptr, nullptr); +static Defined *addAbsolute(StringRef name) { + Symbol *sym = symtab->addSymbol(Defined{nullptr, name, STB_GLOBAL, STV_HIDDEN, + STT_NOTYPE, 0, 0, nullptr}); + return cast<Defined>(sym); } // The linker is expected to define some symbols depending on // the linking result. This function defines such symbols. void elf::addReservedSymbols() { - if (Config->EMachine == EM_MIPS) { + if (config->emachine == EM_MIPS) { // Define _gp for MIPS. st_value of _gp symbol will be updated by Writer // so that it points to an absolute address which by default is relative // to GOT. Default offset is 0x7ff0. // See "Global Data Symbols" in Chapter 6 in the following document: // ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf - ElfSym::MipsGp = addAbsolute("_gp"); + ElfSym::mipsGp = addAbsolute("_gp"); // On MIPS O32 ABI, _gp_disp is a magic symbol designates offset between // start of function and 'gp' pointer into GOT. - if (Symtab->find("_gp_disp")) - ElfSym::MipsGpDisp = addAbsolute("_gp_disp"); + if (symtab->find("_gp_disp")) + ElfSym::mipsGpDisp = addAbsolute("_gp_disp"); // The __gnu_local_gp is a magic symbol equal to the current value of 'gp' // pointer. This symbol is used in the code generated by .cpload pseudo-op // in case of using -mno-shared option. // https://sourceware.org/ml/binutils/2004-12/msg00094.html - if (Symtab->find("__gnu_local_gp")) - ElfSym::MipsLocalGp = addAbsolute("__gnu_local_gp"); + if (symtab->find("__gnu_local_gp")) + ElfSym::mipsLocalGp = addAbsolute("__gnu_local_gp"); + } else if (config->emachine == EM_PPC) { + // glibc *crt1.o has a undefined reference to _SDA_BASE_. Since we don't + // support Small Data Area, define it arbitrarily as 0. + addOptionalRegular("_SDA_BASE_", nullptr, 0, STV_HIDDEN); } // The Power Architecture 64-bit v2 ABI defines a TableOfContents (TOC) which @@ -214,56 +251,62 @@ void elf::addReservedSymbols() { // the .got section. // We do not allow _GLOBAL_OFFSET_TABLE_ to be defined by input objects as the // correctness of some relocations depends on its value. - StringRef GotTableSymName = - (Config->EMachine == EM_PPC64) ? ".TOC." : "_GLOBAL_OFFSET_TABLE_"; - if (Symbol *S = Symtab->find(GotTableSymName)) { - if (S->isDefined()) - error(toString(S->File) + " cannot redefine linker defined symbol '" + - GotTableSymName + "'"); - else - ElfSym::GlobalOffsetTable = Symtab->addDefined( - GotTableSymName, STV_HIDDEN, STT_NOTYPE, Target->GotBaseSymOff, - /*Size=*/0, STB_GLOBAL, Out::ElfHeader, - /*File=*/nullptr); + StringRef gotSymName = + (config->emachine == EM_PPC64) ? ".TOC." : "_GLOBAL_OFFSET_TABLE_"; + + if (Symbol *s = symtab->find(gotSymName)) { + if (s->isDefined()) { + error(toString(s->file) + " cannot redefine linker defined symbol '" + + gotSymName + "'"); + return; + } + + uint64_t gotOff = 0; + if (config->emachine == EM_PPC64) + gotOff = 0x8000; + + s->resolve(Defined{/*file=*/nullptr, gotSymName, STB_GLOBAL, STV_HIDDEN, + STT_NOTYPE, gotOff, /*size=*/0, Out::elfHeader}); + ElfSym::globalOffsetTable = cast<Defined>(s); } // __ehdr_start is the location of ELF file headers. Note that we define // this symbol unconditionally even when using a linker script, which // differs from the behavior implemented by GNU linker which only define // this symbol if ELF headers are in the memory mapped segment. - addOptionalRegular("__ehdr_start", Out::ElfHeader, 0, STV_HIDDEN); + addOptionalRegular("__ehdr_start", Out::elfHeader, 0, STV_HIDDEN); // __executable_start is not documented, but the expectation of at // least the Android libc is that it points to the ELF header. - addOptionalRegular("__executable_start", Out::ElfHeader, 0, STV_HIDDEN); + addOptionalRegular("__executable_start", Out::elfHeader, 0, STV_HIDDEN); // __dso_handle symbol is passed to cxa_finalize as a marker to identify // each DSO. The address of the symbol doesn't matter as long as they are // different in different DSOs, so we chose the start address of the DSO. - addOptionalRegular("__dso_handle", Out::ElfHeader, 0, STV_HIDDEN); + addOptionalRegular("__dso_handle", Out::elfHeader, 0, STV_HIDDEN); // If linker script do layout we do not need to create any standart symbols. - if (Script->HasSectionsCommand) + if (script->hasSectionsCommand) return; - auto Add = [](StringRef S, int64_t Pos) { - return addOptionalRegular(S, Out::ElfHeader, Pos, STV_DEFAULT); + auto add = [](StringRef s, int64_t pos) { + return addOptionalRegular(s, Out::elfHeader, pos, STV_DEFAULT); }; - ElfSym::Bss = Add("__bss_start", 0); - ElfSym::End1 = Add("end", -1); - ElfSym::End2 = Add("_end", -1); - ElfSym::Etext1 = Add("etext", -1); - ElfSym::Etext2 = Add("_etext", -1); - ElfSym::Edata1 = Add("edata", -1); - ElfSym::Edata2 = Add("_edata", -1); + ElfSym::bss = add("__bss_start", 0); + ElfSym::end1 = add("end", -1); + ElfSym::end2 = add("_end", -1); + ElfSym::etext1 = add("etext", -1); + ElfSym::etext2 = add("_etext", -1); + ElfSym::edata1 = add("edata", -1); + ElfSym::edata2 = add("_edata", -1); } -static OutputSection *findSection(StringRef Name) { - for (BaseCommand *Base : Script->SectionCommands) - if (auto *Sec = dyn_cast<OutputSection>(Base)) - if (Sec->Name == Name) - return Sec; +static OutputSection *findSection(StringRef name, unsigned partition = 1) { + for (BaseCommand *base : script->sectionCommands) + if (auto *sec = dyn_cast<OutputSection>(base)) + if (sec->name == name && sec->partition == partition) + return sec; return nullptr; } @@ -271,202 +314,263 @@ static OutputSection *findSection(StringRef Name) { template <class ELFT> static void createSyntheticSections() { // Initialize all pointers with NULL. This is needed because // you can call lld::elf::main more than once as a library. - memset(&Out::First, 0, sizeof(Out)); + memset(&Out::first, 0, sizeof(Out)); - auto Add = [](InputSectionBase *Sec) { InputSections.push_back(Sec); }; + auto add = [](InputSectionBase *sec) { inputSections.push_back(sec); }; - In.DynStrTab = make<StringTableSection>(".dynstr", true); - In.Dynamic = make<DynamicSection<ELFT>>(); - if (Config->AndroidPackDynRelocs) { - In.RelaDyn = make<AndroidPackedRelocationSection<ELFT>>( - Config->IsRela ? ".rela.dyn" : ".rel.dyn"); - } else { - In.RelaDyn = make<RelocationSection<ELFT>>( - Config->IsRela ? ".rela.dyn" : ".rel.dyn", Config->ZCombreloc); - } - In.ShStrTab = make<StringTableSection>(".shstrtab", false); + in.shStrTab = make<StringTableSection>(".shstrtab", false); - Out::ProgramHeaders = make<OutputSection>("", 0, SHF_ALLOC); - Out::ProgramHeaders->Alignment = Config->Wordsize; + Out::programHeaders = make<OutputSection>("", 0, SHF_ALLOC); + Out::programHeaders->alignment = config->wordsize; - if (needsInterpSection()) { - In.Interp = createInterpSection(); - Add(In.Interp); + if (config->strip != StripPolicy::All) { + in.strTab = make<StringTableSection>(".strtab", false); + in.symTab = make<SymbolTableSection<ELFT>>(*in.strTab); + in.symTabShndx = make<SymtabShndxSection>(); } - if (Config->Strip != StripPolicy::All) { - In.StrTab = make<StringTableSection>(".strtab", false); - In.SymTab = make<SymbolTableSection<ELFT>>(*In.StrTab); - In.SymTabShndx = make<SymtabShndxSection>(); - } - - if (Config->BuildId != BuildIdKind::None) { - In.BuildId = make<BuildIdSection>(); - Add(In.BuildId); - } - - In.Bss = make<BssSection>(".bss", 0, 1); - Add(In.Bss); + in.bss = make<BssSection>(".bss", 0, 1); + add(in.bss); // If there is a SECTIONS command and a .data.rel.ro section name use name // .data.rel.ro.bss so that we match in the .data.rel.ro output section. // This makes sure our relro is contiguous. - bool HasDataRelRo = Script->HasSectionsCommand && findSection(".data.rel.ro"); - In.BssRelRo = - make<BssSection>(HasDataRelRo ? ".data.rel.ro.bss" : ".bss.rel.ro", 0, 1); - Add(In.BssRelRo); + bool hasDataRelRo = + script->hasSectionsCommand && findSection(".data.rel.ro", 0); + in.bssRelRo = + make<BssSection>(hasDataRelRo ? ".data.rel.ro.bss" : ".bss.rel.ro", 0, 1); + add(in.bssRelRo); // Add MIPS-specific sections. - if (Config->EMachine == EM_MIPS) { - if (!Config->Shared && Config->HasDynSymTab) { - In.MipsRldMap = make<MipsRldMapSection>(); - Add(In.MipsRldMap); + if (config->emachine == EM_MIPS) { + if (!config->shared && config->hasDynSymTab) { + in.mipsRldMap = make<MipsRldMapSection>(); + add(in.mipsRldMap); } - if (auto *Sec = MipsAbiFlagsSection<ELFT>::create()) - Add(Sec); - if (auto *Sec = MipsOptionsSection<ELFT>::create()) - Add(Sec); - if (auto *Sec = MipsReginfoSection<ELFT>::create()) - Add(Sec); + if (auto *sec = MipsAbiFlagsSection<ELFT>::create()) + add(sec); + if (auto *sec = MipsOptionsSection<ELFT>::create()) + add(sec); + if (auto *sec = MipsReginfoSection<ELFT>::create()) + add(sec); } - if (Config->HasDynSymTab) { - In.DynSymTab = make<SymbolTableSection<ELFT>>(*In.DynStrTab); - Add(In.DynSymTab); + for (Partition &part : partitions) { + auto add = [&](InputSectionBase *sec) { + sec->partition = part.getNumber(); + inputSections.push_back(sec); + }; + + if (!part.name.empty()) { + part.elfHeader = make<PartitionElfHeaderSection<ELFT>>(); + part.elfHeader->name = part.name; + add(part.elfHeader); - InX<ELFT>::VerSym = make<VersionTableSection<ELFT>>(); - Add(InX<ELFT>::VerSym); + part.programHeaders = make<PartitionProgramHeadersSection<ELFT>>(); + add(part.programHeaders); + } - if (!Config->VersionDefinitions.empty()) { - In.VerDef = make<VersionDefinitionSection>(); - Add(In.VerDef); + if (config->buildId != BuildIdKind::None) { + part.buildId = make<BuildIdSection>(); + add(part.buildId); } - InX<ELFT>::VerNeed = make<VersionNeedSection<ELFT>>(); - Add(InX<ELFT>::VerNeed); + part.dynStrTab = make<StringTableSection>(".dynstr", true); + part.dynSymTab = make<SymbolTableSection<ELFT>>(*part.dynStrTab); + part.dynamic = make<DynamicSection<ELFT>>(); + if (config->androidPackDynRelocs) { + part.relaDyn = make<AndroidPackedRelocationSection<ELFT>>( + config->isRela ? ".rela.dyn" : ".rel.dyn"); + } else { + part.relaDyn = make<RelocationSection<ELFT>>( + config->isRela ? ".rela.dyn" : ".rel.dyn", config->zCombreloc); + } + + if (needsInterpSection()) + add(createInterpSection()); + + if (config->hasDynSymTab) { + part.dynSymTab = make<SymbolTableSection<ELFT>>(*part.dynStrTab); + add(part.dynSymTab); + + part.verSym = make<VersionTableSection>(); + add(part.verSym); + + if (!config->versionDefinitions.empty()) { + part.verDef = make<VersionDefinitionSection>(); + add(part.verDef); + } + + part.verNeed = make<VersionNeedSection<ELFT>>(); + add(part.verNeed); + + if (config->gnuHash) { + part.gnuHashTab = make<GnuHashTableSection>(); + add(part.gnuHashTab); + } + + if (config->sysvHash) { + part.hashTab = make<HashTableSection>(); + add(part.hashTab); + } - if (Config->GnuHash) { - In.GnuHashTab = make<GnuHashTableSection>(); - Add(In.GnuHashTab); + add(part.dynamic); + add(part.dynStrTab); + add(part.relaDyn); } - if (Config->SysvHash) { - In.HashTab = make<HashTableSection>(); - Add(In.HashTab); + if (config->relrPackDynRelocs) { + part.relrDyn = make<RelrSection<ELFT>>(); + add(part.relrDyn); } - Add(In.Dynamic); - Add(In.DynStrTab); - Add(In.RelaDyn); + if (!config->relocatable) { + if (config->ehFrameHdr) { + part.ehFrameHdr = make<EhFrameHeader>(); + add(part.ehFrameHdr); + } + part.ehFrame = make<EhFrameSection>(); + add(part.ehFrame); + } + + if (config->emachine == EM_ARM && !config->relocatable) { + // The ARMExidxsyntheticsection replaces all the individual .ARM.exidx + // InputSections. + part.armExidx = make<ARMExidxSyntheticSection>(); + add(part.armExidx); + } } - if (Config->RelrPackDynRelocs) { - In.RelrDyn = make<RelrSection<ELFT>>(); - Add(In.RelrDyn); + if (partitions.size() != 1) { + // Create the partition end marker. This needs to be in partition number 255 + // so that it is sorted after all other partitions. It also has other + // special handling (see createPhdrs() and combineEhSections()). + in.partEnd = make<BssSection>(".part.end", config->maxPageSize, 1); + in.partEnd->partition = 255; + add(in.partEnd); + + in.partIndex = make<PartitionIndexSection>(); + addOptionalRegular("__part_index_begin", in.partIndex, 0); + addOptionalRegular("__part_index_end", in.partIndex, + in.partIndex->getSize()); + add(in.partIndex); } // Add .got. MIPS' .got is so different from the other archs, // it has its own class. - if (Config->EMachine == EM_MIPS) { - In.MipsGot = make<MipsGotSection>(); - Add(In.MipsGot); + if (config->emachine == EM_MIPS) { + in.mipsGot = make<MipsGotSection>(); + add(in.mipsGot); } else { - In.Got = make<GotSection>(); - Add(In.Got); + in.got = make<GotSection>(); + add(in.got); } - if (Config->EMachine == EM_PPC64) { - In.PPC64LongBranchTarget = make<PPC64LongBranchTargetSection>(); - Add(In.PPC64LongBranchTarget); + if (config->emachine == EM_PPC) { + in.ppc32Got2 = make<PPC32Got2Section>(); + add(in.ppc32Got2); } - In.GotPlt = make<GotPltSection>(); - Add(In.GotPlt); - In.IgotPlt = make<IgotPltSection>(); - Add(In.IgotPlt); + if (config->emachine == EM_PPC64) { + in.ppc64LongBranchTarget = make<PPC64LongBranchTargetSection>(); + add(in.ppc64LongBranchTarget); + } - if (Config->GdbIndex) { - In.GdbIndex = GdbIndexSection::create<ELFT>(); - Add(In.GdbIndex); + if (config->emachine == EM_RISCV) { + in.riscvSdata = make<RISCVSdataSection>(); + add(in.riscvSdata); } + in.gotPlt = make<GotPltSection>(); + add(in.gotPlt); + in.igotPlt = make<IgotPltSection>(); + add(in.igotPlt); + + // _GLOBAL_OFFSET_TABLE_ is defined relative to either .got.plt or .got. Treat + // it as a relocation and ensure the referenced section is created. + if (ElfSym::globalOffsetTable && config->emachine != EM_MIPS) { + if (target->gotBaseSymInGotPlt) + in.gotPlt->hasGotPltOffRel = true; + else + in.got->hasGotOffRel = true; + } + + if (config->gdbIndex) + add(GdbIndexSection::create<ELFT>()); + // We always need to add rel[a].plt to output if it has entries. // Even for static linking it can contain R_[*]_IRELATIVE relocations. - In.RelaPlt = make<RelocationSection<ELFT>>( - Config->IsRela ? ".rela.plt" : ".rel.plt", false /*Sort*/); - Add(In.RelaPlt); + in.relaPlt = make<RelocationSection<ELFT>>( + config->isRela ? ".rela.plt" : ".rel.plt", /*sort=*/false); + add(in.relaPlt); - // The RelaIplt immediately follows .rel.plt (.rel.dyn for ARM) to ensure + // The relaIplt immediately follows .rel.plt (.rel.dyn for ARM) to ensure // that the IRelative relocations are processed last by the dynamic loader. // We cannot place the iplt section in .rel.dyn when Android relocation // packing is enabled because that would cause a section type mismatch. // However, because the Android dynamic loader reads .rel.plt after .rel.dyn, // we can get the desired behaviour by placing the iplt section in .rel.plt. - In.RelaIplt = make<RelocationSection<ELFT>>( - (Config->EMachine == EM_ARM && !Config->AndroidPackDynRelocs) + in.relaIplt = make<RelocationSection<ELFT>>( + (config->emachine == EM_ARM && !config->androidPackDynRelocs) ? ".rel.dyn" - : In.RelaPlt->Name, - false /*Sort*/); - Add(In.RelaIplt); + : in.relaPlt->name, + /*sort=*/false); + add(in.relaIplt); + + in.plt = make<PltSection>(false); + add(in.plt); + in.iplt = make<PltSection>(true); + add(in.iplt); - In.Plt = make<PltSection>(false); - Add(In.Plt); - In.Iplt = make<PltSection>(true); - Add(In.Iplt); + if (config->andFeatures) + add(make<GnuPropertySection>()); // .note.GNU-stack is always added when we are creating a re-linkable // object file. Other linkers are using the presence of this marker // section to control the executable-ness of the stack area, but that // is irrelevant these days. Stack area should always be non-executable // by default. So we emit this section unconditionally. - if (Config->Relocatable) - Add(make<GnuStackSection>()); + if (config->relocatable) + add(make<GnuStackSection>()); - if (!Config->Relocatable) { - if (Config->EhFrameHdr) { - In.EhFrameHdr = make<EhFrameHeader>(); - Add(In.EhFrameHdr); - } - In.EhFrame = make<EhFrameSection>(); - Add(In.EhFrame); - } - - if (In.SymTab) - Add(In.SymTab); - if (In.SymTabShndx) - Add(In.SymTabShndx); - Add(In.ShStrTab); - if (In.StrTab) - Add(In.StrTab); - - if (Config->EMachine == EM_ARM && !Config->Relocatable) - // Add a sentinel to terminate .ARM.exidx. It helps an unwinder - // to find the exact address range of the last entry. - Add(make<ARMExidxSentinelSection>()); + if (in.symTab) + add(in.symTab); + if (in.symTabShndx) + add(in.symTabShndx); + add(in.shStrTab); + if (in.strTab) + add(in.strTab); } // The main function of the writer. template <class ELFT> void Writer<ELFT>::run() { + // Make copies of any input sections that need to be copied into each + // partition. + copySectionsIntoPartitions<ELFT>(); + // Create linker-synthesized sections such as .got or .plt. // Such sections are of type input section. createSyntheticSections<ELFT>(); - if (!Config->Relocatable) - combineEhFrameSections<ELFT>(); + // Some input sections that are used for exception handling need to be moved + // into synthetic sections. Do that now so that they aren't assigned to + // output sections in the usual way. + if (!config->relocatable) + combineEhSections<ELFT>(); // We want to process linker script commands. When SECTIONS command // is given we let it create sections. - Script->processSectionCommands(); + script->processSectionCommands(); // Linker scripts controls how input sections are assigned to output sections. // Input sections that were not handled by scripts are called "orphans", and // they are assigned to output sections by the default rule. Process that. - Script->addOrphanSections(); + script->addOrphanSections(); - if (Config->Discard != DiscardPolicy::All) + if (config->discard != DiscardPolicy::All) copyLocalSymbols(); - if (Config->CopyRelocs) + if (config->copyRelocs) addSectionSymbols(); // Now that we have a complete set of output sections. This function @@ -478,33 +582,35 @@ template <class ELFT> void Writer<ELFT>::run() { if (errorCount()) return; - Script->assignAddresses(); + script->assignAddresses(); // If -compressed-debug-sections is specified, we need to compress // .debug_* sections. Do it right now because it changes the size of // output sections. - for (OutputSection *Sec : OutputSections) - Sec->maybeCompress<ELFT>(); + for (OutputSection *sec : outputSections) + sec->maybeCompress<ELFT>(); - Script->allocateHeaders(Phdrs); + script->allocateHeaders(mainPart->phdrs); // Remove empty PT_LOAD to avoid causing the dynamic linker to try to mmap a // 0 sized region. This has to be done late since only after assignAddresses // we know the size of the sections. - removeEmptyPTLoad(); + for (Partition &part : partitions) + removeEmptyPTLoad(part.phdrs); - if (!Config->OFormatBinary) + if (!config->oFormatBinary) assignFileOffsets(); else assignFileOffsetsBinary(); - setPhdrs(); + for (Partition &part : partitions) + setPhdrs(part); - if (Config->Relocatable) - for (OutputSection *Sec : OutputSections) - Sec->Addr = 0; + if (config->relocatable) + for (OutputSection *sec : outputSections) + sec->addr = 0; - if (Config->CheckSections) + if (config->checkSections) checkSections(); // It does not make sense try to open the file if we have error already. @@ -515,7 +621,7 @@ template <class ELFT> void Writer<ELFT>::run() { if (errorCount()) return; - if (!Config->OFormatBinary) { + if (!config->oFormatBinary) { writeTrapInstr(); writeHeader(); writeSections(); @@ -535,21 +641,20 @@ template <class ELFT> void Writer<ELFT>::run() { if (errorCount()) return; - if (auto E = Buffer->commit()) - error("failed to write to the output file: " + toString(std::move(E))); + if (auto e = buffer->commit()) + error("failed to write to the output file: " + toString(std::move(e))); } -static bool shouldKeepInSymtab(SectionBase *Sec, StringRef SymName, - const Symbol &B) { - if (B.isSection()) +static bool shouldKeepInSymtab(const Defined &sym) { + if (sym.isSection()) return false; - if (Config->Discard == DiscardPolicy::None) + if (config->discard == DiscardPolicy::None) return true; // If -emit-reloc is given, all symbols including local ones need to be // copied because they may be referenced by relocations. - if (Config->EmitRelocs) + if (config->emitRelocs) return true; // In ELF assembly .L symbols are normally discarded by the assembler. @@ -557,61 +662,62 @@ static bool shouldKeepInSymtab(SectionBase *Sec, StringRef SymName, // * --discard-locals is used. // * The symbol is in a SHF_MERGE section, which is normally the reason for // the assembler keeping the .L symbol. - if (!SymName.startswith(".L") && !SymName.empty()) + StringRef name = sym.getName(); + bool isLocal = name.startswith(".L") || name.empty(); + if (!isLocal) return true; - if (Config->Discard == DiscardPolicy::Locals) + if (config->discard == DiscardPolicy::Locals) return false; - return !Sec || !(Sec->Flags & SHF_MERGE); + SectionBase *sec = sym.section; + return !sec || !(sec->flags & SHF_MERGE); } -static bool includeInSymtab(const Symbol &B) { - if (!B.isLocal() && !B.IsUsedInRegularObj) +static bool includeInSymtab(const Symbol &b) { + if (!b.isLocal() && !b.isUsedInRegularObj) return false; - if (auto *D = dyn_cast<Defined>(&B)) { + if (auto *d = dyn_cast<Defined>(&b)) { // Always include absolute symbols. - SectionBase *Sec = D->Section; - if (!Sec) + SectionBase *sec = d->section; + if (!sec) return true; - Sec = Sec->Repl; + sec = sec->repl; // Exclude symbols pointing to garbage-collected sections. - if (isa<InputSectionBase>(Sec) && !Sec->Live) + if (isa<InputSectionBase>(sec) && !sec->isLive()) return false; - if (auto *S = dyn_cast<MergeInputSection>(Sec)) - if (!S->getSectionPiece(D->Value)->Live) + if (auto *s = dyn_cast<MergeInputSection>(sec)) + if (!s->getSectionPiece(d->value)->live) return false; return true; } - return B.Used; + return b.used; } // Local symbols are not in the linker's symbol table. This function scans // each object file's symbol table to copy local symbols to the output. template <class ELFT> void Writer<ELFT>::copyLocalSymbols() { - if (!In.SymTab) + if (!in.symTab) return; - for (InputFile *File : ObjectFiles) { - ObjFile<ELFT> *F = cast<ObjFile<ELFT>>(File); - for (Symbol *B : F->getLocalSymbols()) { - if (!B->isLocal()) - fatal(toString(F) + + for (InputFile *file : objectFiles) { + ObjFile<ELFT> *f = cast<ObjFile<ELFT>>(file); + for (Symbol *b : f->getLocalSymbols()) { + if (!b->isLocal()) + fatal(toString(f) + ": broken object: getLocalSymbols returns a non-local symbol"); - auto *DR = dyn_cast<Defined>(B); + auto *dr = dyn_cast<Defined>(b); // No reason to keep local undefined symbol in symtab. - if (!DR) + if (!dr) continue; - if (!includeInSymtab(*B)) + if (!includeInSymtab(*b)) continue; - - SectionBase *Sec = DR->Section; - if (!shouldKeepInSymtab(Sec, B->getName(), *B)) + if (!shouldKeepInSymtab(*dr)) continue; - In.SymTab->addSymbol(B); + in.symTab->addSymbol(b); } } } @@ -621,33 +727,33 @@ template <class ELFT> void Writer<ELFT>::copyLocalSymbols() { // referring to a section (that happens if the section is a synthetic one), we // don't create a section symbol for that section. template <class ELFT> void Writer<ELFT>::addSectionSymbols() { - for (BaseCommand *Base : Script->SectionCommands) { - auto *Sec = dyn_cast<OutputSection>(Base); - if (!Sec) + for (BaseCommand *base : script->sectionCommands) { + auto *sec = dyn_cast<OutputSection>(base); + if (!sec) continue; - auto I = llvm::find_if(Sec->SectionCommands, [](BaseCommand *Base) { - if (auto *ISD = dyn_cast<InputSectionDescription>(Base)) - return !ISD->Sections.empty(); + auto i = llvm::find_if(sec->sectionCommands, [](BaseCommand *base) { + if (auto *isd = dyn_cast<InputSectionDescription>(base)) + return !isd->sections.empty(); return false; }); - if (I == Sec->SectionCommands.end()) + if (i == sec->sectionCommands.end()) continue; - InputSection *IS = cast<InputSectionDescription>(*I)->Sections[0]; + InputSection *isec = cast<InputSectionDescription>(*i)->sections[0]; // Relocations are not using REL[A] section symbols. - if (IS->Type == SHT_REL || IS->Type == SHT_RELA) + if (isec->type == SHT_REL || isec->type == SHT_RELA) continue; // Unlike other synthetic sections, mergeable output sections contain data // copied from input sections, and there may be a relocation pointing to its // contents if -r or -emit-reloc are given. - if (isa<SyntheticSection>(IS) && !(IS->Flags & SHF_MERGE)) + if (isa<SyntheticSection>(isec) && !(isec->flags & SHF_MERGE)) continue; - auto *Sym = - make<Defined>(IS->File, "", STB_LOCAL, /*StOther=*/0, STT_SECTION, - /*Value=*/0, /*Size=*/0, IS); - In.SymTab->addSymbol(Sym); + auto *sym = + make<Defined>(isec->file, "", STB_LOCAL, /*stOther=*/0, STT_SECTION, + /*value=*/0, /*size=*/0, isec); + in.symTab->addSymbol(sym); } } @@ -657,25 +763,25 @@ template <class ELFT> void Writer<ELFT>::addSectionSymbols() { // // This function returns true if a section needs to be put into a // PT_GNU_RELRO segment. -static bool isRelroSection(const OutputSection *Sec) { - if (!Config->ZRelro) +static bool isRelroSection(const OutputSection *sec) { + if (!config->zRelro) return false; - uint64_t Flags = Sec->Flags; + uint64_t flags = sec->flags; // Non-allocatable or non-writable sections don't need RELRO because // they are not writable or not even mapped to memory in the first place. // RELRO is for sections that are essentially read-only but need to // be writable only at process startup to allow dynamic linker to // apply relocations. - if (!(Flags & SHF_ALLOC) || !(Flags & SHF_WRITE)) + if (!(flags & SHF_ALLOC) || !(flags & SHF_WRITE)) return false; // Once initialized, TLS data segments are used as data templates // for a thread-local storage. For each new thread, runtime // allocates memory for a TLS and copy templates there. No thread // are supposed to use templates directly. Thus, it can be in RELRO. - if (Flags & SHF_TLS) + if (flags & SHF_TLS) return true; // .init_array, .preinit_array and .fini_array contain pointers to @@ -684,15 +790,15 @@ static bool isRelroSection(const OutputSection *Sec) { // to change at runtime. But if you are an attacker, you could do // interesting things by manipulating pointers in .fini_array, for // example. So they are put into RELRO. - uint32_t Type = Sec->Type; - if (Type == SHT_INIT_ARRAY || Type == SHT_FINI_ARRAY || - Type == SHT_PREINIT_ARRAY) + uint32_t type = sec->type; + if (type == SHT_INIT_ARRAY || type == SHT_FINI_ARRAY || + type == SHT_PREINIT_ARRAY) return true; // .got contains pointers to external symbols. They are resolved by // the dynamic linker when a module is loaded into memory, and after // that they are not expected to change. So, it can be in RELRO. - if (In.Got && Sec == In.Got->getParent()) + if (in.got && sec == in.got->getParent()) return true; // .toc is a GOT-ish section for PowerPC64. Their contents are accessed @@ -700,30 +806,30 @@ static bool isRelroSection(const OutputSection *Sec) { // for accessing .got as well, .got and .toc need to be close enough in the // virtual address space. Usually, .toc comes just after .got. Since we place // .got into RELRO, .toc needs to be placed into RELRO too. - if (Sec->Name.equals(".toc")) + if (sec->name.equals(".toc")) return true; // .got.plt contains pointers to external function symbols. They are // by default resolved lazily, so we usually cannot put it into RELRO. // However, if "-z now" is given, the lazy symbol resolution is // disabled, which enables us to put it into RELRO. - if (Sec == In.GotPlt->getParent()) - return Config->ZNow; + if (sec == in.gotPlt->getParent()) + return config->zNow; // .dynamic section contains data for the dynamic linker, and // there's no need to write to it at runtime, so it's better to put // it into RELRO. - if (Sec == In.Dynamic->getParent()) + if (sec->name == ".dynamic") return true; // Sections with some special names are put into RELRO. This is a // bit unfortunate because section names shouldn't be significant in // ELF in spirit. But in reality many linker features depend on // magic section names. - StringRef S = Sec->Name; - return S == ".data.rel.ro" || S == ".bss.rel.ro" || S == ".ctors" || - S == ".dtors" || S == ".jcr" || S == ".eh_frame" || - S == ".openbsd.randomdata"; + StringRef s = sec->name; + return s == ".data.rel.ro" || s == ".bss.rel.ro" || s == ".ctors" || + s == ".dtors" || s == ".jcr" || s == ".eh_frame" || + s == ".openbsd.randomdata"; } // We compute a rank for each section. The rank indicates where the @@ -734,16 +840,18 @@ static bool isRelroSection(const OutputSection *Sec) { // * It is easy to check if a give branch was taken. // * It is easy two see how similar two ranks are (see getRankProximity). enum RankFlags { - RF_NOT_ADDR_SET = 1 << 18, - RF_NOT_ALLOC = 1 << 17, - RF_NOT_INTERP = 1 << 16, - RF_NOT_NOTE = 1 << 15, - RF_WRITE = 1 << 14, - RF_EXEC_WRITE = 1 << 13, - RF_EXEC = 1 << 12, - RF_RODATA = 1 << 11, - RF_NON_TLS_BSS = 1 << 10, - RF_NON_TLS_BSS_RO = 1 << 9, + RF_NOT_ADDR_SET = 1 << 27, + RF_NOT_ALLOC = 1 << 26, + RF_PARTITION = 1 << 18, // Partition number (8 bits) + RF_NOT_PART_EHDR = 1 << 17, + RF_NOT_PART_PHDR = 1 << 16, + RF_NOT_INTERP = 1 << 15, + RF_NOT_NOTE = 1 << 14, + RF_WRITE = 1 << 13, + RF_EXEC_WRITE = 1 << 12, + RF_EXEC = 1 << 11, + RF_RODATA = 1 << 10, + RF_NOT_RELRO = 1 << 9, RF_NOT_TLS = 1 << 8, RF_BSS = 1 << 7, RF_PPC_NOT_TOCBSS = 1 << 6, @@ -755,33 +863,41 @@ enum RankFlags { RF_MIPS_NOT_GOT = 1 << 0 }; -static unsigned getSectionRank(const OutputSection *Sec) { - unsigned Rank = 0; +static unsigned getSectionRank(const OutputSection *sec) { + unsigned rank = sec->partition * RF_PARTITION; // We want to put section specified by -T option first, so we // can start assigning VA starting from them later. - if (Config->SectionStartMap.count(Sec->Name)) - return Rank; - Rank |= RF_NOT_ADDR_SET; + if (config->sectionStartMap.count(sec->name)) + return rank; + rank |= RF_NOT_ADDR_SET; // Allocatable sections go first to reduce the total PT_LOAD size and // so debug info doesn't change addresses in actual code. - if (!(Sec->Flags & SHF_ALLOC)) - return Rank | RF_NOT_ALLOC; + if (!(sec->flags & SHF_ALLOC)) + return rank | RF_NOT_ALLOC; + + if (sec->type == SHT_LLVM_PART_EHDR) + return rank; + rank |= RF_NOT_PART_EHDR; + + if (sec->type == SHT_LLVM_PART_PHDR) + return rank; + rank |= RF_NOT_PART_PHDR; // Put .interp first because some loaders want to see that section // on the first page of the executable file when loaded into memory. - if (Sec->Name == ".interp") - return Rank; - Rank |= RF_NOT_INTERP; + if (sec->name == ".interp") + return rank; + rank |= RF_NOT_INTERP; // Put .note sections (which make up one PT_NOTE) at the beginning so that // they are likely to be included in a core file even if core file size is // limited. In particular, we want a .note.gnu.build-id and a .note.tag to be // included in a core to match core files with executables. - if (Sec->Type == SHT_NOTE) - return Rank; - Rank |= RF_NOT_NOTE; + if (sec->type == SHT_NOTE) + return rank; + rank |= RF_NOT_NOTE; // Sort sections based on their access permission in the following // order: R, RX, RWX, RW. This order is based on the following @@ -794,116 +910,105 @@ static unsigned getSectionRank(const OutputSection *Sec) { // between .text and .data. // * Writable sections come last, such that .bss lands at the very // end of the last PT_LOAD. - bool IsExec = Sec->Flags & SHF_EXECINSTR; - bool IsWrite = Sec->Flags & SHF_WRITE; + bool isExec = sec->flags & SHF_EXECINSTR; + bool isWrite = sec->flags & SHF_WRITE; - if (IsExec) { - if (IsWrite) - Rank |= RF_EXEC_WRITE; + if (isExec) { + if (isWrite) + rank |= RF_EXEC_WRITE; else - Rank |= RF_EXEC; - } else if (IsWrite) { - Rank |= RF_WRITE; - } else if (Sec->Type == SHT_PROGBITS) { + rank |= RF_EXEC; + } else if (isWrite) { + rank |= RF_WRITE; + } else if (sec->type == SHT_PROGBITS) { // Make non-executable and non-writable PROGBITS sections (e.g .rodata // .eh_frame) closer to .text. They likely contain PC or GOT relative // relocations and there could be relocation overflow if other huge sections // (.dynstr .dynsym) were placed in between. - Rank |= RF_RODATA; + rank |= RF_RODATA; } - // If we got here we know that both A and B are in the same PT_LOAD. + // Place RelRo sections first. After considering SHT_NOBITS below, the + // ordering is PT_LOAD(PT_GNU_RELRO(.data.rel.ro .bss.rel.ro) | .data .bss), + // where | marks where page alignment happens. An alternative ordering is + // PT_LOAD(.data | PT_GNU_RELRO( .data.rel.ro .bss.rel.ro) | .bss), but it may + // waste more bytes due to 2 alignment places. + if (!isRelroSection(sec)) + rank |= RF_NOT_RELRO; - bool IsTls = Sec->Flags & SHF_TLS; - bool IsNoBits = Sec->Type == SHT_NOBITS; - - // The first requirement we have is to put (non-TLS) nobits sections last. The - // reason is that the only thing the dynamic linker will see about them is a - // p_memsz that is larger than p_filesz. Seeing that it zeros the end of the - // PT_LOAD, so that has to correspond to the nobits sections. - bool IsNonTlsNoBits = IsNoBits && !IsTls; - if (IsNonTlsNoBits) - Rank |= RF_NON_TLS_BSS; - - // We place nobits RelRo sections before plain r/w ones, and non-nobits RelRo - // sections after r/w ones, so that the RelRo sections are contiguous. - bool IsRelRo = isRelroSection(Sec); - if (IsNonTlsNoBits && !IsRelRo) - Rank |= RF_NON_TLS_BSS_RO; - if (!IsNonTlsNoBits && IsRelRo) - Rank |= RF_NON_TLS_BSS_RO; + // If we got here we know that both A and B are in the same PT_LOAD. // The TLS initialization block needs to be a single contiguous block in a R/W // PT_LOAD, so stick TLS sections directly before the other RelRo R/W - // sections. The TLS NOBITS sections are placed here as they don't take up - // virtual address space in the PT_LOAD. - if (!IsTls) - Rank |= RF_NOT_TLS; + // sections. Since p_filesz can be less than p_memsz, place NOBITS sections + // after PROGBITS. + if (!(sec->flags & SHF_TLS)) + rank |= RF_NOT_TLS; - // Within the TLS initialization block, the non-nobits sections need to appear - // first. - if (IsNoBits) - Rank |= RF_BSS; + // Within TLS sections, or within other RelRo sections, or within non-RelRo + // sections, place non-NOBITS sections first. + if (sec->type == SHT_NOBITS) + rank |= RF_BSS; // Some architectures have additional ordering restrictions for sections // within the same PT_LOAD. - if (Config->EMachine == EM_PPC64) { + if (config->emachine == EM_PPC64) { // PPC64 has a number of special SHT_PROGBITS+SHF_ALLOC+SHF_WRITE sections // that we would like to make sure appear is a specific order to maximize // their coverage by a single signed 16-bit offset from the TOC base // pointer. Conversely, the special .tocbss section should be first among // all SHT_NOBITS sections. This will put it next to the loaded special // PPC64 sections (and, thus, within reach of the TOC base pointer). - StringRef Name = Sec->Name; - if (Name != ".tocbss") - Rank |= RF_PPC_NOT_TOCBSS; + StringRef name = sec->name; + if (name != ".tocbss") + rank |= RF_PPC_NOT_TOCBSS; - if (Name == ".toc1") - Rank |= RF_PPC_TOCL; + if (name == ".toc1") + rank |= RF_PPC_TOCL; - if (Name == ".toc") - Rank |= RF_PPC_TOC; + if (name == ".toc") + rank |= RF_PPC_TOC; - if (Name == ".got") - Rank |= RF_PPC_GOT; + if (name == ".got") + rank |= RF_PPC_GOT; - if (Name == ".branch_lt") - Rank |= RF_PPC_BRANCH_LT; + if (name == ".branch_lt") + rank |= RF_PPC_BRANCH_LT; } - if (Config->EMachine == EM_MIPS) { + if (config->emachine == EM_MIPS) { // All sections with SHF_MIPS_GPREL flag should be grouped together // because data in these sections is addressable with a gp relative address. - if (Sec->Flags & SHF_MIPS_GPREL) - Rank |= RF_MIPS_GPREL; + if (sec->flags & SHF_MIPS_GPREL) + rank |= RF_MIPS_GPREL; - if (Sec->Name != ".got") - Rank |= RF_MIPS_NOT_GOT; + if (sec->name != ".got") + rank |= RF_MIPS_NOT_GOT; } - return Rank; + return rank; } -static bool compareSections(const BaseCommand *ACmd, const BaseCommand *BCmd) { - const OutputSection *A = cast<OutputSection>(ACmd); - const OutputSection *B = cast<OutputSection>(BCmd); +static bool compareSections(const BaseCommand *aCmd, const BaseCommand *bCmd) { + const OutputSection *a = cast<OutputSection>(aCmd); + const OutputSection *b = cast<OutputSection>(bCmd); - if (A->SortRank != B->SortRank) - return A->SortRank < B->SortRank; + if (a->sortRank != b->sortRank) + return a->sortRank < b->sortRank; - if (!(A->SortRank & RF_NOT_ADDR_SET)) - return Config->SectionStartMap.lookup(A->Name) < - Config->SectionStartMap.lookup(B->Name); + if (!(a->sortRank & RF_NOT_ADDR_SET)) + return config->sectionStartMap.lookup(a->name) < + config->sectionStartMap.lookup(b->name); return false; } -void PhdrEntry::add(OutputSection *Sec) { - LastSec = Sec; - if (!FirstSec) - FirstSec = Sec; - p_align = std::max(p_align, Sec->Alignment); +void PhdrEntry::add(OutputSection *sec) { + lastSec = sec; + if (!firstSec) + firstSec = sec; + p_align = std::max(p_align, sec->alignment); if (p_type == PT_LOAD) - Sec->PtLoad = this; + sec->ptLoad = this; } // The beginning and the ending of .rel[a].plt section are marked @@ -913,35 +1018,40 @@ void PhdrEntry::add(OutputSection *Sec) { // need these symbols, since IRELATIVE relocs are resolved through GOT // and PLT. For details, see http://www.airs.com/blog/archives/403. template <class ELFT> void Writer<ELFT>::addRelIpltSymbols() { - if (Config->Relocatable || needsInterpSection()) + if (config->relocatable || needsInterpSection()) return; // By default, __rela_iplt_{start,end} belong to a dummy section 0 // because .rela.plt might be empty and thus removed from output. - // We'll override Out::ElfHeader with In.RelaIplt later when we are + // We'll override Out::elfHeader with In.relaIplt later when we are // sure that .rela.plt exists in output. - ElfSym::RelaIpltStart = addOptionalRegular( - Config->IsRela ? "__rela_iplt_start" : "__rel_iplt_start", - Out::ElfHeader, 0, STV_HIDDEN, STB_WEAK); + ElfSym::relaIpltStart = addOptionalRegular( + config->isRela ? "__rela_iplt_start" : "__rel_iplt_start", + Out::elfHeader, 0, STV_HIDDEN, STB_WEAK); - ElfSym::RelaIpltEnd = addOptionalRegular( - Config->IsRela ? "__rela_iplt_end" : "__rel_iplt_end", - Out::ElfHeader, 0, STV_HIDDEN, STB_WEAK); + ElfSym::relaIpltEnd = addOptionalRegular( + config->isRela ? "__rela_iplt_end" : "__rel_iplt_end", + Out::elfHeader, 0, STV_HIDDEN, STB_WEAK); } template <class ELFT> void Writer<ELFT>::forEachRelSec( - llvm::function_ref<void(InputSectionBase &)> Fn) { + llvm::function_ref<void(InputSectionBase &)> fn) { // Scan all relocations. Each relocation goes through a series // of tests to determine if it needs special treatment, such as // creating GOT, PLT, copy relocations, etc. // Note that relocations for non-alloc sections are directly // processed by InputSection::relocateNonAlloc. - for (InputSectionBase *IS : InputSections) - if (IS->Live && isa<InputSection>(IS) && (IS->Flags & SHF_ALLOC)) - Fn(*IS); - for (EhInputSection *ES : In.EhFrame->Sections) - Fn(*ES); + for (InputSectionBase *isec : inputSections) + if (isec->isLive() && isa<InputSection>(isec) && (isec->flags & SHF_ALLOC)) + fn(*isec); + for (Partition &part : partitions) { + for (EhInputSection *es : part.ehFrame->sections) + fn(*es); + if (part.armExidx && part.armExidx->isLive()) + for (InputSection *ex : part.armExidx->exidxSections) + fn(*ex); + } } // This function generates assignments for predefined symbols (e.g. _end or @@ -950,76 +1060,78 @@ void Writer<ELFT>::forEachRelSec( // time any references to these symbols are processed and is equivalent to // defining these symbols explicitly in the linker script. template <class ELFT> void Writer<ELFT>::setReservedSymbolSections() { - if (ElfSym::GlobalOffsetTable) { + if (ElfSym::globalOffsetTable) { // The _GLOBAL_OFFSET_TABLE_ symbol is defined by target convention usually // to the start of the .got or .got.plt section. - InputSection *GotSection = In.GotPlt; - if (!Target->GotBaseSymInGotPlt) - GotSection = In.MipsGot ? cast<InputSection>(In.MipsGot) - : cast<InputSection>(In.Got); - ElfSym::GlobalOffsetTable->Section = GotSection; + InputSection *gotSection = in.gotPlt; + if (!target->gotBaseSymInGotPlt) + gotSection = in.mipsGot ? cast<InputSection>(in.mipsGot) + : cast<InputSection>(in.got); + ElfSym::globalOffsetTable->section = gotSection; } // .rela_iplt_{start,end} mark the start and the end of .rela.plt section. - if (ElfSym::RelaIpltStart && !In.RelaIplt->empty()) { - ElfSym::RelaIpltStart->Section = In.RelaIplt; - ElfSym::RelaIpltEnd->Section = In.RelaIplt; - ElfSym::RelaIpltEnd->Value = In.RelaIplt->getSize(); + if (ElfSym::relaIpltStart && in.relaIplt->isNeeded()) { + ElfSym::relaIpltStart->section = in.relaIplt; + ElfSym::relaIpltEnd->section = in.relaIplt; + ElfSym::relaIpltEnd->value = in.relaIplt->getSize(); } - PhdrEntry *Last = nullptr; - PhdrEntry *LastRO = nullptr; + PhdrEntry *last = nullptr; + PhdrEntry *lastRO = nullptr; - for (PhdrEntry *P : Phdrs) { - if (P->p_type != PT_LOAD) - continue; - Last = P; - if (!(P->p_flags & PF_W)) - LastRO = P; + for (Partition &part : partitions) { + for (PhdrEntry *p : part.phdrs) { + if (p->p_type != PT_LOAD) + continue; + last = p; + if (!(p->p_flags & PF_W)) + lastRO = p; + } } - if (LastRO) { + if (lastRO) { // _etext is the first location after the last read-only loadable segment. - if (ElfSym::Etext1) - ElfSym::Etext1->Section = LastRO->LastSec; - if (ElfSym::Etext2) - ElfSym::Etext2->Section = LastRO->LastSec; + if (ElfSym::etext1) + ElfSym::etext1->section = lastRO->lastSec; + if (ElfSym::etext2) + ElfSym::etext2->section = lastRO->lastSec; } - if (Last) { + if (last) { // _edata points to the end of the last mapped initialized section. - OutputSection *Edata = nullptr; - for (OutputSection *OS : OutputSections) { - if (OS->Type != SHT_NOBITS) - Edata = OS; - if (OS == Last->LastSec) + OutputSection *edata = nullptr; + for (OutputSection *os : outputSections) { + if (os->type != SHT_NOBITS) + edata = os; + if (os == last->lastSec) break; } - if (ElfSym::Edata1) - ElfSym::Edata1->Section = Edata; - if (ElfSym::Edata2) - ElfSym::Edata2->Section = Edata; + if (ElfSym::edata1) + ElfSym::edata1->section = edata; + if (ElfSym::edata2) + ElfSym::edata2->section = edata; // _end is the first location after the uninitialized data region. - if (ElfSym::End1) - ElfSym::End1->Section = Last->LastSec; - if (ElfSym::End2) - ElfSym::End2->Section = Last->LastSec; + if (ElfSym::end1) + ElfSym::end1->section = last->lastSec; + if (ElfSym::end2) + ElfSym::end2->section = last->lastSec; } - if (ElfSym::Bss) - ElfSym::Bss->Section = findSection(".bss"); + if (ElfSym::bss) + ElfSym::bss->section = findSection(".bss"); // Setup MIPS _gp_disp/__gnu_local_gp symbols which should // be equal to the _gp symbol's value. - if (ElfSym::MipsGp) { + if (ElfSym::mipsGp) { // Find GP-relative section with the lowest address // and use this address to calculate default _gp value. - for (OutputSection *OS : OutputSections) { - if (OS->Flags & SHF_MIPS_GPREL) { - ElfSym::MipsGp->Section = OS; - ElfSym::MipsGp->Value = 0x7ff0; + for (OutputSection *os : outputSections) { + if (os->flags & SHF_MIPS_GPREL) { + ElfSym::mipsGp->section = os; + ElfSym::mipsGp->value = 0x7ff0; break; } } @@ -1030,14 +1142,13 @@ template <class ELFT> void Writer<ELFT>::setReservedSymbolSections() { // The more branches in getSectionRank that match, the more similar they are. // Since each branch corresponds to a bit flag, we can just use // countLeadingZeros. -static int getRankProximityAux(OutputSection *A, OutputSection *B) { - return countLeadingZeros(A->SortRank ^ B->SortRank); +static int getRankProximityAux(OutputSection *a, OutputSection *b) { + return countLeadingZeros(a->sortRank ^ b->sortRank); } -static int getRankProximity(OutputSection *A, BaseCommand *B) { - if (auto *Sec = dyn_cast<OutputSection>(B)) - return getRankProximityAux(A, Sec); - return -1; +static int getRankProximity(OutputSection *a, BaseCommand *b) { + auto *sec = dyn_cast<OutputSection>(b); + return (sec && sec->hasInputSections) ? getRankProximityAux(a, sec) : -1; } // When placing orphan sections, we want to place them after symbol assignments @@ -1054,137 +1165,142 @@ static int getRankProximity(OutputSection *A, BaseCommand *B) { // /* The RW PT_LOAD starts here*/ // rw_sec : { *(rw_sec) } // would mean that the RW PT_LOAD would become unaligned. -static bool shouldSkip(BaseCommand *Cmd) { - if (auto *Assign = dyn_cast<SymbolAssignment>(Cmd)) - return Assign->Name != "."; +static bool shouldSkip(BaseCommand *cmd) { + if (auto *assign = dyn_cast<SymbolAssignment>(cmd)) + return assign->name != "."; return false; } // We want to place orphan sections so that they share as much // characteristics with their neighbors as possible. For example, if // both are rw, or both are tls. -template <typename ELFT> static std::vector<BaseCommand *>::iterator -findOrphanPos(std::vector<BaseCommand *>::iterator B, - std::vector<BaseCommand *>::iterator E) { - OutputSection *Sec = cast<OutputSection>(*E); +findOrphanPos(std::vector<BaseCommand *>::iterator b, + std::vector<BaseCommand *>::iterator e) { + OutputSection *sec = cast<OutputSection>(*e); // Find the first element that has as close a rank as possible. - auto I = std::max_element(B, E, [=](BaseCommand *A, BaseCommand *B) { - return getRankProximity(Sec, A) < getRankProximity(Sec, B); + auto i = std::max_element(b, e, [=](BaseCommand *a, BaseCommand *b) { + return getRankProximity(sec, a) < getRankProximity(sec, b); }); - if (I == E) - return E; + if (i == e) + return e; // Consider all existing sections with the same proximity. - int Proximity = getRankProximity(Sec, *I); - for (; I != E; ++I) { - auto *CurSec = dyn_cast<OutputSection>(*I); - if (!CurSec) + int proximity = getRankProximity(sec, *i); + for (; i != e; ++i) { + auto *curSec = dyn_cast<OutputSection>(*i); + if (!curSec || !curSec->hasInputSections) continue; - if (getRankProximity(Sec, CurSec) != Proximity || - Sec->SortRank < CurSec->SortRank) + if (getRankProximity(sec, curSec) != proximity || + sec->sortRank < curSec->sortRank) break; } - auto IsOutputSec = [](BaseCommand *Cmd) { return isa<OutputSection>(Cmd); }; - auto J = std::find_if(llvm::make_reverse_iterator(I), - llvm::make_reverse_iterator(B), IsOutputSec); - I = J.base(); + auto isOutputSecWithInputSections = [](BaseCommand *cmd) { + auto *os = dyn_cast<OutputSection>(cmd); + return os && os->hasInputSections; + }; + auto j = std::find_if(llvm::make_reverse_iterator(i), + llvm::make_reverse_iterator(b), + isOutputSecWithInputSections); + i = j.base(); // As a special case, if the orphan section is the last section, put // it at the very end, past any other commands. // This matches bfd's behavior and is convenient when the linker script fully // specifies the start of the file, but doesn't care about the end (the non // alloc sections for example). - auto NextSec = std::find_if(I, E, IsOutputSec); - if (NextSec == E) - return E; + auto nextSec = std::find_if(i, e, isOutputSecWithInputSections); + if (nextSec == e) + return e; - while (I != E && shouldSkip(*I)) - ++I; - return I; + while (i != e && shouldSkip(*i)) + ++i; + return i; } // Builds section order for handling --symbol-ordering-file. static DenseMap<const InputSectionBase *, int> buildSectionOrder() { - DenseMap<const InputSectionBase *, int> SectionOrder; + DenseMap<const InputSectionBase *, int> sectionOrder; // Use the rarely used option -call-graph-ordering-file to sort sections. - if (!Config->CallGraphProfile.empty()) + if (!config->callGraphProfile.empty()) return computeCallGraphProfileOrder(); - if (Config->SymbolOrderingFile.empty()) - return SectionOrder; + if (config->symbolOrderingFile.empty()) + return sectionOrder; struct SymbolOrderEntry { - int Priority; - bool Present; + int priority; + bool present; }; // Build a map from symbols to their priorities. Symbols that didn't // appear in the symbol ordering file have the lowest priority 0. // All explicitly mentioned symbols have negative (higher) priorities. - DenseMap<StringRef, SymbolOrderEntry> SymbolOrder; - int Priority = -Config->SymbolOrderingFile.size(); - for (StringRef S : Config->SymbolOrderingFile) - SymbolOrder.insert({S, {Priority++, false}}); + DenseMap<StringRef, SymbolOrderEntry> symbolOrder; + int priority = -config->symbolOrderingFile.size(); + for (StringRef s : config->symbolOrderingFile) + symbolOrder.insert({s, {priority++, false}}); // Build a map from sections to their priorities. - auto AddSym = [&](Symbol &Sym) { - auto It = SymbolOrder.find(Sym.getName()); - if (It == SymbolOrder.end()) + auto addSym = [&](Symbol &sym) { + auto it = symbolOrder.find(sym.getName()); + if (it == symbolOrder.end()) return; - SymbolOrderEntry &Ent = It->second; - Ent.Present = true; + SymbolOrderEntry &ent = it->second; + ent.present = true; - maybeWarnUnorderableSymbol(&Sym); + maybeWarnUnorderableSymbol(&sym); - if (auto *D = dyn_cast<Defined>(&Sym)) { - if (auto *Sec = dyn_cast_or_null<InputSectionBase>(D->Section)) { - int &Priority = SectionOrder[cast<InputSectionBase>(Sec->Repl)]; - Priority = std::min(Priority, Ent.Priority); + if (auto *d = dyn_cast<Defined>(&sym)) { + if (auto *sec = dyn_cast_or_null<InputSectionBase>(d->section)) { + int &priority = sectionOrder[cast<InputSectionBase>(sec->repl)]; + priority = std::min(priority, ent.priority); } } }; // We want both global and local symbols. We get the global ones from the // symbol table and iterate the object files for the local ones. - for (Symbol *Sym : Symtab->getSymbols()) - if (!Sym->isLazy()) - AddSym(*Sym); - for (InputFile *File : ObjectFiles) - for (Symbol *Sym : File->getSymbols()) - if (Sym->isLocal()) - AddSym(*Sym); + symtab->forEachSymbol([&](Symbol *sym) { + if (!sym->isLazy()) + addSym(*sym); + }); + + for (InputFile *file : objectFiles) + for (Symbol *sym : file->getSymbols()) + if (sym->isLocal()) + addSym(*sym); - if (Config->WarnSymbolOrdering) - for (auto OrderEntry : SymbolOrder) - if (!OrderEntry.second.Present) - warn("symbol ordering file: no such symbol: " + OrderEntry.first); + if (config->warnSymbolOrdering) + for (auto orderEntry : symbolOrder) + if (!orderEntry.second.present) + warn("symbol ordering file: no such symbol: " + orderEntry.first); - return SectionOrder; + return sectionOrder; } // Sorts the sections in ISD according to the provided section order. static void -sortISDBySectionOrder(InputSectionDescription *ISD, - const DenseMap<const InputSectionBase *, int> &Order) { - std::vector<InputSection *> UnorderedSections; - std::vector<std::pair<InputSection *, int>> OrderedSections; - uint64_t UnorderedSize = 0; - - for (InputSection *IS : ISD->Sections) { - auto I = Order.find(IS); - if (I == Order.end()) { - UnorderedSections.push_back(IS); - UnorderedSize += IS->getSize(); +sortISDBySectionOrder(InputSectionDescription *isd, + const DenseMap<const InputSectionBase *, int> &order) { + std::vector<InputSection *> unorderedSections; + std::vector<std::pair<InputSection *, int>> orderedSections; + uint64_t unorderedSize = 0; + + for (InputSection *isec : isd->sections) { + auto i = order.find(isec); + if (i == order.end()) { + unorderedSections.push_back(isec); + unorderedSize += isec->getSize(); continue; } - OrderedSections.push_back({IS, I->second}); + orderedSections.push_back({isec, i->second}); } - llvm::sort(OrderedSections, [&](std::pair<InputSection *, int> A, - std::pair<InputSection *, int> B) { - return A.second < B.second; + llvm::sort(orderedSections, [&](std::pair<InputSection *, int> a, + std::pair<InputSection *, int> b) { + return a.second < b.second; }); // Find an insertion point for the ordered section list in the unordered @@ -1214,96 +1330,114 @@ sortISDBySectionOrder(InputSectionDescription *ISD, // of the second block of cold code can call the hot code without a thunk. So // we effectively double the amount of code that could potentially call into // the hot code without a thunk. - size_t InsPt = 0; - if (Target->getThunkSectionSpacing() && !OrderedSections.empty()) { - uint64_t UnorderedPos = 0; - for (; InsPt != UnorderedSections.size(); ++InsPt) { - UnorderedPos += UnorderedSections[InsPt]->getSize(); - if (UnorderedPos > UnorderedSize / 2) + size_t insPt = 0; + if (target->getThunkSectionSpacing() && !orderedSections.empty()) { + uint64_t unorderedPos = 0; + for (; insPt != unorderedSections.size(); ++insPt) { + unorderedPos += unorderedSections[insPt]->getSize(); + if (unorderedPos > unorderedSize / 2) break; } } - ISD->Sections.clear(); - for (InputSection *IS : makeArrayRef(UnorderedSections).slice(0, InsPt)) - ISD->Sections.push_back(IS); - for (std::pair<InputSection *, int> P : OrderedSections) - ISD->Sections.push_back(P.first); - for (InputSection *IS : makeArrayRef(UnorderedSections).slice(InsPt)) - ISD->Sections.push_back(IS); + isd->sections.clear(); + for (InputSection *isec : makeArrayRef(unorderedSections).slice(0, insPt)) + isd->sections.push_back(isec); + for (std::pair<InputSection *, int> p : orderedSections) + isd->sections.push_back(p.first); + for (InputSection *isec : makeArrayRef(unorderedSections).slice(insPt)) + isd->sections.push_back(isec); } -static void sortSection(OutputSection *Sec, - const DenseMap<const InputSectionBase *, int> &Order) { - StringRef Name = Sec->Name; +static void sortSection(OutputSection *sec, + const DenseMap<const InputSectionBase *, int> &order) { + StringRef name = sec->name; // Sort input sections by section name suffixes for // __attribute__((init_priority(N))). - if (Name == ".init_array" || Name == ".fini_array") { - if (!Script->HasSectionsCommand) - Sec->sortInitFini(); + if (name == ".init_array" || name == ".fini_array") { + if (!script->hasSectionsCommand) + sec->sortInitFini(); return; } // Sort input sections by the special rule for .ctors and .dtors. - if (Name == ".ctors" || Name == ".dtors") { - if (!Script->HasSectionsCommand) - Sec->sortCtorsDtors(); + if (name == ".ctors" || name == ".dtors") { + if (!script->hasSectionsCommand) + sec->sortCtorsDtors(); return; } // Never sort these. - if (Name == ".init" || Name == ".fini") + if (name == ".init" || name == ".fini") return; + // .toc is allocated just after .got and is accessed using GOT-relative + // relocations. Object files compiled with small code model have an + // addressable range of [.got, .got + 0xFFFC] for GOT-relative relocations. + // To reduce the risk of relocation overflow, .toc contents are sorted so that + // sections having smaller relocation offsets are at beginning of .toc + if (config->emachine == EM_PPC64 && name == ".toc") { + if (script->hasSectionsCommand) + return; + assert(sec->sectionCommands.size() == 1); + auto *isd = cast<InputSectionDescription>(sec->sectionCommands[0]); + llvm::stable_sort(isd->sections, + [](const InputSection *a, const InputSection *b) -> bool { + return a->file->ppc64SmallCodeModelTocRelocs && + !b->file->ppc64SmallCodeModelTocRelocs; + }); + return; + } + // Sort input sections by priority using the list provided // by --symbol-ordering-file. - if (!Order.empty()) - for (BaseCommand *B : Sec->SectionCommands) - if (auto *ISD = dyn_cast<InputSectionDescription>(B)) - sortISDBySectionOrder(ISD, Order); + if (!order.empty()) + for (BaseCommand *b : sec->sectionCommands) + if (auto *isd = dyn_cast<InputSectionDescription>(b)) + sortISDBySectionOrder(isd, order); } // If no layout was provided by linker script, we want to apply default // sorting for special input sections. This also handles --symbol-ordering-file. template <class ELFT> void Writer<ELFT>::sortInputSections() { // Build the order once since it is expensive. - DenseMap<const InputSectionBase *, int> Order = buildSectionOrder(); - for (BaseCommand *Base : Script->SectionCommands) - if (auto *Sec = dyn_cast<OutputSection>(Base)) - sortSection(Sec, Order); + DenseMap<const InputSectionBase *, int> order = buildSectionOrder(); + for (BaseCommand *base : script->sectionCommands) + if (auto *sec = dyn_cast<OutputSection>(base)) + sortSection(sec, order); } template <class ELFT> void Writer<ELFT>::sortSections() { - Script->adjustSectionsBeforeSorting(); + script->adjustSectionsBeforeSorting(); // Don't sort if using -r. It is not necessary and we want to preserve the // relative order for SHF_LINK_ORDER sections. - if (Config->Relocatable) + if (config->relocatable) return; sortInputSections(); - for (BaseCommand *Base : Script->SectionCommands) { - auto *OS = dyn_cast<OutputSection>(Base); - if (!OS) + for (BaseCommand *base : script->sectionCommands) { + auto *os = dyn_cast<OutputSection>(base); + if (!os) continue; - OS->SortRank = getSectionRank(OS); + os->sortRank = getSectionRank(os); - // We want to assign rude approximation values to OutSecOff fields + // We want to assign rude approximation values to outSecOff fields // to know the relative order of the input sections. We use it for // sorting SHF_LINK_ORDER sections. See resolveShfLinkOrder(). - uint64_t I = 0; - for (InputSection *Sec : getInputSections(OS)) - Sec->OutSecOff = I++; + uint64_t i = 0; + for (InputSection *sec : getInputSections(os)) + sec->outSecOff = i++; } - if (!Script->HasSectionsCommand) { + if (!script->hasSectionsCommand) { // We know that all the OutputSections are contiguous in this case. - auto IsSection = [](BaseCommand *Base) { return isa<OutputSection>(Base); }; + auto isSection = [](BaseCommand *base) { return isa<OutputSection>(base); }; std::stable_sort( - llvm::find_if(Script->SectionCommands, IsSection), - llvm::find_if(llvm::reverse(Script->SectionCommands), IsSection).base(), + llvm::find_if(script->sectionCommands, isSection), + llvm::find_if(llvm::reverse(script->sectionCommands), isSection).base(), compareSections); return; } @@ -1347,211 +1481,127 @@ template <class ELFT> void Writer<ELFT>::sortSections() { // after another commands. For the details, look at shouldSkip // function. - auto I = Script->SectionCommands.begin(); - auto E = Script->SectionCommands.end(); - auto NonScriptI = std::find_if(I, E, [](BaseCommand *Base) { - if (auto *Sec = dyn_cast<OutputSection>(Base)) - return Sec->SectionIndex == UINT32_MAX; + auto i = script->sectionCommands.begin(); + auto e = script->sectionCommands.end(); + auto nonScriptI = std::find_if(i, e, [](BaseCommand *base) { + if (auto *sec = dyn_cast<OutputSection>(base)) + return sec->sectionIndex == UINT32_MAX; return false; }); // Sort the orphan sections. - std::stable_sort(NonScriptI, E, compareSections); + std::stable_sort(nonScriptI, e, compareSections); // As a horrible special case, skip the first . assignment if it is before any // section. We do this because it is common to set a load address by starting // the script with ". = 0xabcd" and the expectation is that every section is // after that. - auto FirstSectionOrDotAssignment = - std::find_if(I, E, [](BaseCommand *Cmd) { return !shouldSkip(Cmd); }); - if (FirstSectionOrDotAssignment != E && - isa<SymbolAssignment>(**FirstSectionOrDotAssignment)) - ++FirstSectionOrDotAssignment; - I = FirstSectionOrDotAssignment; + auto firstSectionOrDotAssignment = + std::find_if(i, e, [](BaseCommand *cmd) { return !shouldSkip(cmd); }); + if (firstSectionOrDotAssignment != e && + isa<SymbolAssignment>(**firstSectionOrDotAssignment)) + ++firstSectionOrDotAssignment; + i = firstSectionOrDotAssignment; - while (NonScriptI != E) { - auto Pos = findOrphanPos<ELFT>(I, NonScriptI); - OutputSection *Orphan = cast<OutputSection>(*NonScriptI); + while (nonScriptI != e) { + auto pos = findOrphanPos(i, nonScriptI); + OutputSection *orphan = cast<OutputSection>(*nonScriptI); // As an optimization, find all sections with the same sort rank // and insert them with one rotate. - unsigned Rank = Orphan->SortRank; - auto End = std::find_if(NonScriptI + 1, E, [=](BaseCommand *Cmd) { - return cast<OutputSection>(Cmd)->SortRank != Rank; + unsigned rank = orphan->sortRank; + auto end = std::find_if(nonScriptI + 1, e, [=](BaseCommand *cmd) { + return cast<OutputSection>(cmd)->sortRank != rank; }); - std::rotate(Pos, NonScriptI, End); - NonScriptI = End; + std::rotate(pos, nonScriptI, end); + nonScriptI = end; } - Script->adjustSectionsAfterSorting(); + script->adjustSectionsAfterSorting(); } -static bool compareByFilePosition(InputSection *A, InputSection *B) { - // Synthetic, i. e. a sentinel section, should go last. - if (A->kind() == InputSectionBase::Synthetic || - B->kind() == InputSectionBase::Synthetic) - return A->kind() != InputSectionBase::Synthetic; - - InputSection *LA = A->getLinkOrderDep(); - InputSection *LB = B->getLinkOrderDep(); - OutputSection *AOut = LA->getParent(); - OutputSection *BOut = LB->getParent(); - - if (AOut != BOut) - return AOut->SectionIndex < BOut->SectionIndex; - return LA->OutSecOff < LB->OutSecOff; -} - -// This function is used by the --merge-exidx-entries to detect duplicate -// .ARM.exidx sections. It is Arm only. -// -// The .ARM.exidx section is of the form: -// | PREL31 offset to function | Unwind instructions for function | -// where the unwind instructions are either a small number of unwind -// instructions inlined into the table entry, the special CANT_UNWIND value of -// 0x1 or a PREL31 offset into a .ARM.extab Section that contains unwind -// instructions. -// -// We return true if all the unwind instructions in the .ARM.exidx entries of -// Cur can be merged into the last entry of Prev. -static bool isDuplicateArmExidxSec(InputSection *Prev, InputSection *Cur) { - - // References to .ARM.Extab Sections have bit 31 clear and are not the - // special EXIDX_CANTUNWIND bit-pattern. - auto IsExtabRef = [](uint32_t Unwind) { - return (Unwind & 0x80000000) == 0 && Unwind != 0x1; - }; - - struct ExidxEntry { - ulittle32_t Fn; - ulittle32_t Unwind; - }; - - // Get the last table Entry from the previous .ARM.exidx section. - const ExidxEntry &PrevEntry = Prev->getDataAs<ExidxEntry>().back(); - if (IsExtabRef(PrevEntry.Unwind)) - return false; - - // We consider the unwind instructions of an .ARM.exidx table entry - // a duplicate if the previous unwind instructions if: - // - Both are the special EXIDX_CANTUNWIND. - // - Both are the same inline unwind instructions. - // We do not attempt to follow and check links into .ARM.extab tables as - // consecutive identical entries are rare and the effort to check that they - // are identical is high. +static bool compareByFilePosition(InputSection *a, InputSection *b) { + InputSection *la = a->getLinkOrderDep(); + InputSection *lb = b->getLinkOrderDep(); + OutputSection *aOut = la->getParent(); + OutputSection *bOut = lb->getParent(); - for (const ExidxEntry Entry : Cur->getDataAs<ExidxEntry>()) - if (IsExtabRef(Entry.Unwind) || Entry.Unwind != PrevEntry.Unwind) - return false; - - // All table entries in this .ARM.exidx Section can be merged into the - // previous Section. - return true; + if (aOut != bOut) + return aOut->sectionIndex < bOut->sectionIndex; + return la->outSecOff < lb->outSecOff; } template <class ELFT> void Writer<ELFT>::resolveShfLinkOrder() { - for (OutputSection *Sec : OutputSections) { - if (!(Sec->Flags & SHF_LINK_ORDER)) + for (OutputSection *sec : outputSections) { + if (!(sec->flags & SHF_LINK_ORDER)) continue; // Link order may be distributed across several InputSectionDescriptions // but sort must consider them all at once. - std::vector<InputSection **> ScriptSections; - std::vector<InputSection *> Sections; - for (BaseCommand *Base : Sec->SectionCommands) { - if (auto *ISD = dyn_cast<InputSectionDescription>(Base)) { - for (InputSection *&IS : ISD->Sections) { - ScriptSections.push_back(&IS); - Sections.push_back(IS); + std::vector<InputSection **> scriptSections; + std::vector<InputSection *> sections; + for (BaseCommand *base : sec->sectionCommands) { + if (auto *isd = dyn_cast<InputSectionDescription>(base)) { + for (InputSection *&isec : isd->sections) { + scriptSections.push_back(&isec); + sections.push_back(isec); } } } - std::stable_sort(Sections.begin(), Sections.end(), compareByFilePosition); - - if (!Config->Relocatable && Config->EMachine == EM_ARM && - Sec->Type == SHT_ARM_EXIDX) { - - if (auto *Sentinel = dyn_cast<ARMExidxSentinelSection>(Sections.back())) { - assert(Sections.size() >= 2 && - "We should create a sentinel section only if there are " - "alive regular exidx sections."); - - // The last executable section is required to fill the sentinel. - // Remember it here so that we don't have to find it again. - Sentinel->Highest = Sections[Sections.size() - 2]->getLinkOrderDep(); - } - // The EHABI for the Arm Architecture permits consecutive identical - // table entries to be merged. We use a simple implementation that - // removes a .ARM.exidx Input Section if it can be merged into the - // previous one. This does not require any rewriting of InputSection - // contents but misses opportunities for fine grained deduplication - // where only a subset of the InputSection contents can be merged. - if (Config->MergeArmExidx) { - size_t Prev = 0; - // The last one is a sentinel entry which should not be removed. - for (size_t I = 1; I < Sections.size() - 1; ++I) { - if (isDuplicateArmExidxSec(Sections[Prev], Sections[I])) - Sections[I] = nullptr; - else - Prev = I; - } - } - } + // The ARM.exidx section use SHF_LINK_ORDER, but we have consolidated + // this processing inside the ARMExidxsyntheticsection::finalizeContents(). + if (!config->relocatable && config->emachine == EM_ARM && + sec->type == SHT_ARM_EXIDX) + continue; - for (int I = 0, N = Sections.size(); I < N; ++I) - *ScriptSections[I] = Sections[I]; + llvm::stable_sort(sections, compareByFilePosition); - // Remove the Sections we marked as duplicate earlier. - for (BaseCommand *Base : Sec->SectionCommands) - if (auto *ISD = dyn_cast<InputSectionDescription>(Base)) - llvm::erase_if(ISD->Sections, [](InputSection *IS) { return !IS; }); + for (int i = 0, n = sections.size(); i < n; ++i) + *scriptSections[i] = sections[i]; } } -// For most RISC ISAs, we need to generate content that depends on the address -// of InputSections. For example some architectures such as AArch64 use small -// displacements for jump instructions that is the linker's responsibility for -// creating range extension thunks for. As the generation of the content may -// also alter InputSection addresses we must converge to a fixed point. -template <class ELFT> void Writer<ELFT>::maybeAddThunks() { - if (!Target->NeedsThunks && !Config->AndroidPackDynRelocs && - !Config->RelrPackDynRelocs) - return; - - ThunkCreator TC; - AArch64Err843419Patcher A64P; +// We need to generate and finalize the content that depends on the address of +// InputSections. As the generation of the content may also alter InputSection +// addresses we must converge to a fixed point. We do that here. See the comment +// in Writer<ELFT>::finalizeSections(). +template <class ELFT> void Writer<ELFT>::finalizeAddressDependentContent() { + ThunkCreator tc; + AArch64Err843419Patcher a64p; + // For some targets, like x86, this loop iterates only once. for (;;) { - bool Changed = false; + bool changed = false; - Script->assignAddresses(); + script->assignAddresses(); - if (Target->NeedsThunks) - Changed |= TC.createThunks(OutputSections); + if (target->needsThunks) + changed |= tc.createThunks(outputSections); - if (Config->FixCortexA53Errata843419) { - if (Changed) - Script->assignAddresses(); - Changed |= A64P.createFixes(); + if (config->fixCortexA53Errata843419) { + if (changed) + script->assignAddresses(); + changed |= a64p.createFixes(); } - if (In.MipsGot) - In.MipsGot->updateAllocSize(); - - Changed |= In.RelaDyn->updateAllocSize(); + if (in.mipsGot) + in.mipsGot->updateAllocSize(); - if (In.RelrDyn) - Changed |= In.RelrDyn->updateAllocSize(); + for (Partition &part : partitions) { + changed |= part.relaDyn->updateAllocSize(); + if (part.relrDyn) + changed |= part.relrDyn->updateAllocSize(); + } - if (!Changed) + if (!changed) return; } } -static void finalizeSynthetic(SyntheticSection *Sec) { - if (Sec && !Sec->empty() && Sec->getParent()) - Sec->finalizeContents(); +static void finalizeSynthetic(SyntheticSection *sec) { + if (sec && sec->isNeeded() && sec->getParent()) + sec->finalizeContents(); } // In order to allow users to manipulate linker-synthesized sections, @@ -1570,108 +1620,136 @@ static void removeUnusedSyntheticSections() { // All input synthetic sections that can be empty are placed after // all regular ones. We iterate over them all and exit at first // non-synthetic. - for (InputSectionBase *S : llvm::reverse(InputSections)) { - SyntheticSection *SS = dyn_cast<SyntheticSection>(S); - if (!SS) + for (InputSectionBase *s : llvm::reverse(inputSections)) { + SyntheticSection *ss = dyn_cast<SyntheticSection>(s); + if (!ss) return; - OutputSection *OS = SS->getParent(); - if (!OS || !SS->empty()) + OutputSection *os = ss->getParent(); + if (!os || ss->isNeeded()) continue; // If we reach here, then SS is an unused synthetic section and we want to // remove it from corresponding input section description of output section. - for (BaseCommand *B : OS->SectionCommands) - if (auto *ISD = dyn_cast<InputSectionDescription>(B)) - llvm::erase_if(ISD->Sections, - [=](InputSection *IS) { return IS == SS; }); + for (BaseCommand *b : os->sectionCommands) + if (auto *isd = dyn_cast<InputSectionDescription>(b)) + llvm::erase_if(isd->sections, + [=](InputSection *isec) { return isec == ss; }); } } // Returns true if a symbol can be replaced at load-time by a symbol // with the same name defined in other ELF executable or DSO. -static bool computeIsPreemptible(const Symbol &B) { - assert(!B.isLocal()); +static bool computeIsPreemptible(const Symbol &b) { + assert(!b.isLocal()); // Only symbols that appear in dynsym can be preempted. - if (!B.includeInDynsym()) + if (!b.includeInDynsym()) return false; // Only default visibility symbols can be preempted. - if (B.Visibility != STV_DEFAULT) + if (b.visibility != STV_DEFAULT) return false; // At this point copy relocations have not been created yet, so any // symbol that is not defined locally is preemptible. - if (!B.isDefined()) + if (!b.isDefined()) return true; // If we have a dynamic list it specifies which local symbols are preemptible. - if (Config->HasDynamicList) + if (config->hasDynamicList) return false; - if (!Config->Shared) + if (!config->shared) return false; // -Bsymbolic means that definitions are not preempted. - if (Config->Bsymbolic || (Config->BsymbolicFunctions && B.isFunc())) + if (config->bsymbolic || (config->bsymbolicFunctions && b.isFunc())) return false; return true; } // Create output section objects and add them to OutputSections. template <class ELFT> void Writer<ELFT>::finalizeSections() { - Out::PreinitArray = findSection(".preinit_array"); - Out::InitArray = findSection(".init_array"); - Out::FiniArray = findSection(".fini_array"); + Out::preinitArray = findSection(".preinit_array"); + Out::initArray = findSection(".init_array"); + Out::finiArray = findSection(".fini_array"); // The linker needs to define SECNAME_start, SECNAME_end and SECNAME_stop // symbols for sections, so that the runtime can get the start and end // addresses of each section by section name. Add such symbols. - if (!Config->Relocatable) { + if (!config->relocatable) { addStartEndSymbols(); - for (BaseCommand *Base : Script->SectionCommands) - if (auto *Sec = dyn_cast<OutputSection>(Base)) - addStartStopSymbols(Sec); + for (BaseCommand *base : script->sectionCommands) + if (auto *sec = dyn_cast<OutputSection>(base)) + addStartStopSymbols(sec); } // Add _DYNAMIC symbol. Unlike GNU gold, our _DYNAMIC symbol has no type. // It should be okay as no one seems to care about the type. // Even the author of gold doesn't remember why gold behaves that way. // https://sourceware.org/ml/binutils/2002-03/msg00360.html - if (In.Dynamic->Parent) - Symtab->addDefined("_DYNAMIC", STV_HIDDEN, STT_NOTYPE, 0 /*Value*/, - /*Size=*/0, STB_WEAK, In.Dynamic, - /*File=*/nullptr); + if (mainPart->dynamic->parent) + symtab->addSymbol(Defined{/*file=*/nullptr, "_DYNAMIC", STB_WEAK, + STV_HIDDEN, STT_NOTYPE, + /*value=*/0, /*size=*/0, mainPart->dynamic}); // Define __rel[a]_iplt_{start,end} symbols if needed. addRelIpltSymbols(); // RISC-V's gp can address +/- 2 KiB, set it to .sdata + 0x800 if not defined. - if (Config->EMachine == EM_RISCV) - if (!dyn_cast_or_null<Defined>(Symtab->find("__global_pointer$"))) - addOptionalRegular("__global_pointer$", findSection(".sdata"), 0x800); + // This symbol should only be defined in an executable. + if (config->emachine == EM_RISCV && !config->shared) + ElfSym::riscvGlobalPointer = + addOptionalRegular("__global_pointer$", findSection(".sdata"), 0x800, + STV_DEFAULT, STB_GLOBAL); + + if (config->emachine == EM_X86_64) { + // On targets that support TLSDESC, _TLS_MODULE_BASE_ is defined in such a + // way that: + // + // 1) Without relaxation: it produces a dynamic TLSDESC relocation that + // computes 0. + // 2) With LD->LE relaxation: _TLS_MODULE_BASE_@tpoff = 0 (lowest address in + // the TLS block). + // + // 2) is special cased in @tpoff computation. To satisfy 1), we define it as + // an absolute symbol of zero. This is different from GNU linkers which + // define _TLS_MODULE_BASE_ relative to the first TLS section. + Symbol *s = symtab->find("_TLS_MODULE_BASE_"); + if (s && s->isUndefined()) { + s->resolve(Defined{/*file=*/nullptr, s->getName(), STB_GLOBAL, STV_HIDDEN, + STT_TLS, /*value=*/0, 0, + /*section=*/nullptr}); + ElfSym::tlsModuleBase = cast<Defined>(s); + } + } // This responsible for splitting up .eh_frame section into // pieces. The relocation scan uses those pieces, so this has to be // earlier. - finalizeSynthetic(In.EhFrame); + for (Partition &part : partitions) + finalizeSynthetic(part.ehFrame); - for (Symbol *S : Symtab->getSymbols()) - S->IsPreemptible |= computeIsPreemptible(*S); + symtab->forEachSymbol([](Symbol *s) { + if (!s->isPreemptible) + s->isPreemptible = computeIsPreemptible(*s); + }); // Scan relocations. This must be done after every symbol is declared so that // we can correctly decide if a dynamic relocation is needed. - if (!Config->Relocatable) + if (!config->relocatable) { forEachRelSec(scanRelocations<ELFT>); + reportUndefinedSymbols<ELFT>(); + } addIRelativeRelocs(); - if (In.Plt && !In.Plt->empty()) - In.Plt->addSymbols(); - if (In.Iplt && !In.Iplt->empty()) - In.Iplt->addSymbols(); + if (in.plt && in.plt->isNeeded()) + in.plt->addSymbols(); + if (in.iplt && in.iplt->isNeeded()) + in.iplt->addSymbols(); - if (!Config->AllowShlibUndefined) { + if (!config->allowShlibUndefined) { // Error on undefined symbols in a shared object, if all of its DT_NEEDED // entires are seen. These cases would otherwise lead to runtime errors // reported by the dynamic linker. @@ -1679,41 +1757,53 @@ template <class ELFT> void Writer<ELFT>::finalizeSections() { // ld.bfd traces all DT_NEEDED to emulate the logic of the dynamic linker to // catch more cases. That is too much for us. Our approach resembles the one // used in ld.gold, achieves a good balance to be useful but not too smart. - for (InputFile *File : SharedFiles) { - SharedFile<ELFT> *F = cast<SharedFile<ELFT>>(File); - F->AllNeededIsKnown = llvm::all_of(F->DtNeeded, [&](StringRef Needed) { - return Symtab->SoNames.count(Needed); - }); - } - for (Symbol *Sym : Symtab->getSymbols()) - if (Sym->isUndefined() && !Sym->isWeak()) - if (auto *F = dyn_cast_or_null<SharedFile<ELFT>>(Sym->File)) - if (F->AllNeededIsKnown) - error(toString(F) + ": undefined reference to " + toString(*Sym)); + for (SharedFile *file : sharedFiles) + file->allNeededIsKnown = + llvm::all_of(file->dtNeeded, [&](StringRef needed) { + return symtab->soNames.count(needed); + }); + + symtab->forEachSymbol([](Symbol *sym) { + if (sym->isUndefined() && !sym->isWeak()) + if (auto *f = dyn_cast_or_null<SharedFile>(sym->file)) + if (f->allNeededIsKnown) + error(toString(f) + ": undefined reference to " + toString(*sym)); + }); } // Now that we have defined all possible global symbols including linker- // synthesized ones. Visit all symbols to give the finishing touches. - for (Symbol *Sym : Symtab->getSymbols()) { - if (!includeInSymtab(*Sym)) - continue; - if (In.SymTab) - In.SymTab->addSymbol(Sym); - - if (Sym->includeInDynsym()) { - In.DynSymTab->addSymbol(Sym); - if (auto *File = dyn_cast_or_null<SharedFile<ELFT>>(Sym->File)) - if (File->IsNeeded && !Sym->isUndefined()) - InX<ELFT>::VerNeed->addSymbol(Sym); + symtab->forEachSymbol([](Symbol *sym) { + if (!includeInSymtab(*sym)) + return; + if (in.symTab) + in.symTab->addSymbol(sym); + + if (sym->includeInDynsym()) { + partitions[sym->partition - 1].dynSymTab->addSymbol(sym); + if (auto *file = dyn_cast_or_null<SharedFile>(sym->file)) + if (file->isNeeded && !sym->isUndefined()) + addVerneed(sym); } + }); + + // We also need to scan the dynamic relocation tables of the other partitions + // and add any referenced symbols to the partition's dynsym. + for (Partition &part : MutableArrayRef<Partition>(partitions).slice(1)) { + DenseSet<Symbol *> syms; + for (const SymbolTableEntry &e : part.dynSymTab->getSymbols()) + syms.insert(e.sym); + for (DynamicReloc &reloc : part.relaDyn->relocs) + if (reloc.sym && !reloc.useSymVA && syms.insert(reloc.sym).second) + part.dynSymTab->addSymbol(reloc.sym); } // Do not proceed if there was an undefined symbol. if (errorCount()) return; - if (In.MipsGot) - In.MipsGot->build<ELFT>(); + if (in.mipsGot) + in.mipsGot->build(); removeUnusedSyntheticSections(); @@ -1721,116 +1811,147 @@ template <class ELFT> void Writer<ELFT>::finalizeSections() { // Now that we have the final list, create a list of all the // OutputSections for convenience. - for (BaseCommand *Base : Script->SectionCommands) - if (auto *Sec = dyn_cast<OutputSection>(Base)) - OutputSections.push_back(Sec); + for (BaseCommand *base : script->sectionCommands) + if (auto *sec = dyn_cast<OutputSection>(base)) + outputSections.push_back(sec); // Prefer command line supplied address over other constraints. - for (OutputSection *Sec : OutputSections) { - auto I = Config->SectionStartMap.find(Sec->Name); - if (I != Config->SectionStartMap.end()) - Sec->AddrExpr = [=] { return I->second; }; + for (OutputSection *sec : outputSections) { + auto i = config->sectionStartMap.find(sec->name); + if (i != config->sectionStartMap.end()) + sec->addrExpr = [=] { return i->second; }; } // This is a bit of a hack. A value of 0 means undef, so we set it // to 1 to make __ehdr_start defined. The section number is not // particularly relevant. - Out::ElfHeader->SectionIndex = 1; + Out::elfHeader->sectionIndex = 1; - for (size_t I = 0, E = OutputSections.size(); I != E; ++I) { - OutputSection *Sec = OutputSections[I]; - Sec->SectionIndex = I + 1; - Sec->ShName = In.ShStrTab->addString(Sec->Name); + for (size_t i = 0, e = outputSections.size(); i != e; ++i) { + OutputSection *sec = outputSections[i]; + sec->sectionIndex = i + 1; + sec->shName = in.shStrTab->addString(sec->name); } // Binary and relocatable output does not have PHDRS. // The headers have to be created before finalize as that can influence the // image base and the dynamic section on mips includes the image base. - if (!Config->Relocatable && !Config->OFormatBinary) { - Phdrs = Script->hasPhdrsCommands() ? Script->createPhdrs() : createPhdrs(); - addPtArmExid(Phdrs); - Out::ProgramHeaders->Size = sizeof(Elf_Phdr) * Phdrs.size(); + if (!config->relocatable && !config->oFormatBinary) { + for (Partition &part : partitions) { + part.phdrs = script->hasPhdrsCommands() ? script->createPhdrs() + : createPhdrs(part); + if (config->emachine == EM_ARM) { + // PT_ARM_EXIDX is the ARM EHABI equivalent of PT_GNU_EH_FRAME + addPhdrForSection(part, SHT_ARM_EXIDX, PT_ARM_EXIDX, PF_R); + } + if (config->emachine == EM_MIPS) { + // Add separate segments for MIPS-specific sections. + addPhdrForSection(part, SHT_MIPS_REGINFO, PT_MIPS_REGINFO, PF_R); + addPhdrForSection(part, SHT_MIPS_OPTIONS, PT_MIPS_OPTIONS, PF_R); + addPhdrForSection(part, SHT_MIPS_ABIFLAGS, PT_MIPS_ABIFLAGS, PF_R); + } + } + Out::programHeaders->size = sizeof(Elf_Phdr) * mainPart->phdrs.size(); // Find the TLS segment. This happens before the section layout loop so that - // Android relocation packing can look up TLS symbol addresses. - for (PhdrEntry *P : Phdrs) - if (P->p_type == PT_TLS) - Out::TlsPhdr = P; + // Android relocation packing can look up TLS symbol addresses. We only need + // to care about the main partition here because all TLS symbols were moved + // to the main partition (see MarkLive.cpp). + for (PhdrEntry *p : mainPart->phdrs) + if (p->p_type == PT_TLS) + Out::tlsPhdr = p; } // Some symbols are defined in term of program headers. Now that we // have the headers, we can find out which sections they point to. setReservedSymbolSections(); + finalizeSynthetic(in.bss); + finalizeSynthetic(in.bssRelRo); + finalizeSynthetic(in.symTabShndx); + finalizeSynthetic(in.shStrTab); + finalizeSynthetic(in.strTab); + finalizeSynthetic(in.got); + finalizeSynthetic(in.mipsGot); + finalizeSynthetic(in.igotPlt); + finalizeSynthetic(in.gotPlt); + finalizeSynthetic(in.relaIplt); + finalizeSynthetic(in.relaPlt); + finalizeSynthetic(in.plt); + finalizeSynthetic(in.iplt); + finalizeSynthetic(in.ppc32Got2); + finalizeSynthetic(in.riscvSdata); + finalizeSynthetic(in.partIndex); + // Dynamic section must be the last one in this list and dynamic - // symbol table section (DynSymTab) must be the first one. - finalizeSynthetic(In.DynSymTab); - finalizeSynthetic(In.Bss); - finalizeSynthetic(In.BssRelRo); - finalizeSynthetic(In.GnuHashTab); - finalizeSynthetic(In.HashTab); - finalizeSynthetic(In.SymTabShndx); - finalizeSynthetic(In.ShStrTab); - finalizeSynthetic(In.StrTab); - finalizeSynthetic(In.VerDef); - finalizeSynthetic(In.DynStrTab); - finalizeSynthetic(In.Got); - finalizeSynthetic(In.MipsGot); - finalizeSynthetic(In.IgotPlt); - finalizeSynthetic(In.GotPlt); - finalizeSynthetic(In.RelaDyn); - finalizeSynthetic(In.RelrDyn); - finalizeSynthetic(In.RelaIplt); - finalizeSynthetic(In.RelaPlt); - finalizeSynthetic(In.Plt); - finalizeSynthetic(In.Iplt); - finalizeSynthetic(In.EhFrameHdr); - finalizeSynthetic(InX<ELFT>::VerSym); - finalizeSynthetic(InX<ELFT>::VerNeed); - finalizeSynthetic(In.Dynamic); - - if (!Script->HasSectionsCommand && !Config->Relocatable) + // symbol table section (dynSymTab) must be the first one. + for (Partition &part : partitions) { + finalizeSynthetic(part.armExidx); + finalizeSynthetic(part.dynSymTab); + finalizeSynthetic(part.gnuHashTab); + finalizeSynthetic(part.hashTab); + finalizeSynthetic(part.verDef); + finalizeSynthetic(part.relaDyn); + finalizeSynthetic(part.relrDyn); + finalizeSynthetic(part.ehFrameHdr); + finalizeSynthetic(part.verSym); + finalizeSynthetic(part.verNeed); + finalizeSynthetic(part.dynamic); + } + + if (!script->hasSectionsCommand && !config->relocatable) fixSectionAlignments(); - // After link order processing .ARM.exidx sections can be deduplicated, which - // needs to be resolved before any other address dependent operation. + // SHFLinkOrder processing must be processed after relative section placements are + // known but before addresses are allocated. resolveShfLinkOrder(); - // Jump instructions in many ISAs have small displacements, and therefore they - // cannot jump to arbitrary addresses in memory. For example, RISC-V JAL - // instruction can target only +-1 MiB from PC. It is a linker's - // responsibility to create and insert small pieces of code between sections - // to extend the ranges if jump targets are out of range. Such code pieces are - // called "thunks". + // This is used to: + // 1) Create "thunks": + // Jump instructions in many ISAs have small displacements, and therefore + // they cannot jump to arbitrary addresses in memory. For example, RISC-V + // JAL instruction can target only +-1 MiB from PC. It is a linker's + // responsibility to create and insert small pieces of code between + // sections to extend the ranges if jump targets are out of range. Such + // code pieces are called "thunks". + // + // We add thunks at this stage. We couldn't do this before this point + // because this is the earliest point where we know sizes of sections and + // their layouts (that are needed to determine if jump targets are in + // range). + // + // 2) Update the sections. We need to generate content that depends on the + // address of InputSections. For example, MIPS GOT section content or + // android packed relocations sections content. // - // We add thunks at this stage. We couldn't do this before this point because - // this is the earliest point where we know sizes of sections and their - // layouts (that are needed to determine if jump targets are in range). - maybeAddThunks(); + // 3) Assign the final values for the linker script symbols. Linker scripts + // sometimes using forward symbol declarations. We want to set the correct + // values. They also might change after adding the thunks. + finalizeAddressDependentContent(); - // maybeAddThunks may have added local symbols to the static symbol table. - finalizeSynthetic(In.SymTab); - finalizeSynthetic(In.PPC64LongBranchTarget); + // finalizeAddressDependentContent may have added local symbols to the static symbol table. + finalizeSynthetic(in.symTab); + finalizeSynthetic(in.ppc64LongBranchTarget); // Fill other section headers. The dynamic table is finalized // at the end because some tags like RELSZ depend on result // of finalizing other sections. - for (OutputSection *Sec : OutputSections) - Sec->finalize<ELFT>(); + for (OutputSection *sec : outputSections) + sec->finalize(); } // Ensure data sections are not mixed with executable sections when // -execute-only is used. -execute-only is a feature to make pages executable // but not readable, and the feature is currently supported only on AArch64. template <class ELFT> void Writer<ELFT>::checkExecuteOnly() { - if (!Config->ExecuteOnly) + if (!config->executeOnly) return; - for (OutputSection *OS : OutputSections) - if (OS->Flags & SHF_EXECINSTR) - for (InputSection *IS : getInputSections(OS)) - if (!(IS->Flags & SHF_EXECINSTR)) - error("cannot place " + toString(IS) + " into " + toString(OS->Name) + + for (OutputSection *os : outputSections) + if (os->flags & SHF_EXECINSTR) + for (InputSection *isec : getInputSections(os)) + if (!(isec->flags & SHF_EXECINSTR)) + error("cannot place " + toString(isec) + " into " + toString(os->name) + ": -execute-only does not support intermingling data and code"); } @@ -1855,24 +1976,24 @@ template <class ELFT> void Writer<ELFT>::addStartEndSymbols() { // case, use the image base address as a last resort. OutputSection *Default = findSection(".text"); if (!Default) - Default = Out::ElfHeader; + Default = Out::elfHeader; - auto Define = [=](StringRef Start, StringRef End, OutputSection *OS) { - if (OS) { - addOptionalRegular(Start, OS, 0); - addOptionalRegular(End, OS, -1); + auto define = [=](StringRef start, StringRef end, OutputSection *os) { + if (os) { + addOptionalRegular(start, os, 0); + addOptionalRegular(end, os, -1); } else { - addOptionalRegular(Start, Default, 0); - addOptionalRegular(End, Default, 0); + addOptionalRegular(start, Default, 0); + addOptionalRegular(end, Default, 0); } }; - Define("__preinit_array_start", "__preinit_array_end", Out::PreinitArray); - Define("__init_array_start", "__init_array_end", Out::InitArray); - Define("__fini_array_start", "__fini_array_end", Out::FiniArray); + define("__preinit_array_start", "__preinit_array_end", Out::preinitArray); + define("__init_array_start", "__init_array_end", Out::initArray); + define("__fini_array_start", "__fini_array_end", Out::finiArray); - if (OutputSection *Sec = findSection(".ARM.exidx")) - Define("__exidx_start", "__exidx_end", Sec); + if (OutputSection *sec = findSection(".ARM.exidx")) + define("__exidx_start", "__exidx_end", sec); } // If a section name is valid as a C identifier (which is rare because of @@ -1881,22 +2002,22 @@ template <class ELFT> void Writer<ELFT>::addStartEndSymbols() { // respectively. This is not requested by the ELF standard, but GNU ld and // gold provide the feature, and used by many programs. template <class ELFT> -void Writer<ELFT>::addStartStopSymbols(OutputSection *Sec) { - StringRef S = Sec->Name; - if (!isValidCIdentifier(S)) +void Writer<ELFT>::addStartStopSymbols(OutputSection *sec) { + StringRef s = sec->name; + if (!isValidCIdentifier(s)) return; - addOptionalRegular(Saver.save("__start_" + S), Sec, 0, STV_PROTECTED); - addOptionalRegular(Saver.save("__stop_" + S), Sec, -1, STV_PROTECTED); + addOptionalRegular(saver.save("__start_" + s), sec, 0, STV_PROTECTED); + addOptionalRegular(saver.save("__stop_" + s), sec, -1, STV_PROTECTED); } -static bool needsPtLoad(OutputSection *Sec) { - if (!(Sec->Flags & SHF_ALLOC) || Sec->Noload) +static bool needsPtLoad(OutputSection *sec) { + if (!(sec->flags & SHF_ALLOC) || sec->noload) return false; // Don't allocate VA space for TLS NOBITS sections. The PT_TLS PHDR is // responsible for allocating space for them, not the PT_LOAD that // contains the TLS initialization image. - if ((Sec->Flags & SHF_TLS) && Sec->Type == SHT_NOBITS) + if ((sec->flags & SHF_TLS) && sec->type == SHT_NOBITS) return false; return true; } @@ -1905,46 +2026,93 @@ static bool needsPtLoad(OutputSection *Sec) { // linker scripts are designed for creating two PT_LOADs only, one RX and one // RW. This means that there is no alignment in the RO to RX transition and we // cannot create a PT_LOAD there. -static uint64_t computeFlags(uint64_t Flags) { - if (Config->Omagic) +static uint64_t computeFlags(uint64_t flags) { + if (config->omagic) return PF_R | PF_W | PF_X; - if (Config->ExecuteOnly && (Flags & PF_X)) - return Flags & ~PF_R; - if (Config->SingleRoRx && !(Flags & PF_W)) - return Flags | PF_X; - return Flags; + if (config->executeOnly && (flags & PF_X)) + return flags & ~PF_R; + if (config->singleRoRx && !(flags & PF_W)) + return flags | PF_X; + return flags; } // Decide which program headers to create and which sections to include in each // one. -template <class ELFT> std::vector<PhdrEntry *> Writer<ELFT>::createPhdrs() { - std::vector<PhdrEntry *> Ret; - auto AddHdr = [&](unsigned Type, unsigned Flags) -> PhdrEntry * { - Ret.push_back(make<PhdrEntry>(Type, Flags)); - return Ret.back(); +template <class ELFT> +std::vector<PhdrEntry *> Writer<ELFT>::createPhdrs(Partition &part) { + std::vector<PhdrEntry *> ret; + auto addHdr = [&](unsigned type, unsigned flags) -> PhdrEntry * { + ret.push_back(make<PhdrEntry>(type, flags)); + return ret.back(); }; + unsigned partNo = part.getNumber(); + bool isMain = partNo == 1; + // The first phdr entry is PT_PHDR which describes the program header itself. - AddHdr(PT_PHDR, PF_R)->add(Out::ProgramHeaders); + if (isMain) + addHdr(PT_PHDR, PF_R)->add(Out::programHeaders); + else + addHdr(PT_PHDR, PF_R)->add(part.programHeaders->getParent()); // PT_INTERP must be the second entry if exists. - if (OutputSection *Cmd = findSection(".interp")) - AddHdr(PT_INTERP, Cmd->getPhdrFlags())->add(Cmd); + if (OutputSection *cmd = findSection(".interp", partNo)) + addHdr(PT_INTERP, cmd->getPhdrFlags())->add(cmd); // Add the first PT_LOAD segment for regular output sections. - uint64_t Flags = computeFlags(PF_R); - PhdrEntry *Load = AddHdr(PT_LOAD, Flags); + uint64_t flags = computeFlags(PF_R); + PhdrEntry *load = nullptr; // Add the headers. We will remove them if they don't fit. - Load->add(Out::ElfHeader); - Load->add(Out::ProgramHeaders); + // In the other partitions the headers are ordinary sections, so they don't + // need to be added here. + if (isMain) { + load = addHdr(PT_LOAD, flags); + load->add(Out::elfHeader); + load->add(Out::programHeaders); + } + + // PT_GNU_RELRO includes all sections that should be marked as + // read-only by dynamic linker after proccessing relocations. + // Current dynamic loaders only support one PT_GNU_RELRO PHDR, give + // an error message if more than one PT_GNU_RELRO PHDR is required. + PhdrEntry *relRo = make<PhdrEntry>(PT_GNU_RELRO, PF_R); + bool inRelroPhdr = false; + OutputSection *relroEnd = nullptr; + for (OutputSection *sec : outputSections) { + if (sec->partition != partNo || !needsPtLoad(sec)) + continue; + if (isRelroSection(sec)) { + inRelroPhdr = true; + if (!relroEnd) + relRo->add(sec); + else + error("section: " + sec->name + " is not contiguous with other relro" + + " sections"); + } else if (inRelroPhdr) { + inRelroPhdr = false; + relroEnd = sec; + } + } - for (OutputSection *Sec : OutputSections) { - if (!(Sec->Flags & SHF_ALLOC)) + for (OutputSection *sec : outputSections) { + if (!(sec->flags & SHF_ALLOC)) break; - if (!needsPtLoad(Sec)) + if (!needsPtLoad(sec)) continue; + // Normally, sections in partitions other than the current partition are + // ignored. But partition number 255 is a special case: it contains the + // partition end marker (.part.end). It needs to be added to the main + // partition so that a segment is created for it in the main partition, + // which will cause the dynamic loader to reserve space for the other + // partitions. + if (sec->partition != partNo) { + if (isMain && sec->partition == 255) + addHdr(PT_LOAD, computeFlags(sec->getPhdrFlags()))->add(sec); + continue; + } + // Segments are contiguous memory regions that has the same attributes // (e.g. executable or writable). There is one phdr for each segment. // Therefore, we need to create a new phdr when the next section has @@ -1952,222 +2120,187 @@ template <class ELFT> std::vector<PhdrEntry *> Writer<ELFT>::createPhdrs() { // region using AT or AT> linker script command, respectively. At the same // time, we don't want to create a separate load segment for the headers, // even if the first output section has an AT or AT> attribute. - uint64_t NewFlags = computeFlags(Sec->getPhdrFlags()); - if (((Sec->LMAExpr || - (Sec->LMARegion && (Sec->LMARegion != Load->FirstSec->LMARegion))) && - Load->LastSec != Out::ProgramHeaders) || - Sec->MemRegion != Load->FirstSec->MemRegion || Flags != NewFlags) { - - Load = AddHdr(PT_LOAD, NewFlags); - Flags = NewFlags; + uint64_t newFlags = computeFlags(sec->getPhdrFlags()); + if (!load || + ((sec->lmaExpr || + (sec->lmaRegion && (sec->lmaRegion != load->firstSec->lmaRegion))) && + load->lastSec != Out::programHeaders) || + sec->memRegion != load->firstSec->memRegion || flags != newFlags || + sec == relroEnd) { + load = addHdr(PT_LOAD, newFlags); + flags = newFlags; } - Load->add(Sec); + load->add(sec); } // Add a TLS segment if any. - PhdrEntry *TlsHdr = make<PhdrEntry>(PT_TLS, PF_R); - for (OutputSection *Sec : OutputSections) - if (Sec->Flags & SHF_TLS) - TlsHdr->add(Sec); - if (TlsHdr->FirstSec) - Ret.push_back(TlsHdr); + PhdrEntry *tlsHdr = make<PhdrEntry>(PT_TLS, PF_R); + for (OutputSection *sec : outputSections) + if (sec->partition == partNo && sec->flags & SHF_TLS) + tlsHdr->add(sec); + if (tlsHdr->firstSec) + ret.push_back(tlsHdr); // Add an entry for .dynamic. - if (OutputSection *Sec = In.Dynamic->getParent()) - AddHdr(PT_DYNAMIC, Sec->getPhdrFlags())->add(Sec); + if (OutputSection *sec = part.dynamic->getParent()) + addHdr(PT_DYNAMIC, sec->getPhdrFlags())->add(sec); - // PT_GNU_RELRO includes all sections that should be marked as - // read-only by dynamic linker after proccessing relocations. - // Current dynamic loaders only support one PT_GNU_RELRO PHDR, give - // an error message if more than one PT_GNU_RELRO PHDR is required. - PhdrEntry *RelRo = make<PhdrEntry>(PT_GNU_RELRO, PF_R); - bool InRelroPhdr = false; - bool IsRelroFinished = false; - for (OutputSection *Sec : OutputSections) { - if (!needsPtLoad(Sec)) - continue; - if (isRelroSection(Sec)) { - InRelroPhdr = true; - if (!IsRelroFinished) - RelRo->add(Sec); - else - error("section: " + Sec->Name + " is not contiguous with other relro" + - " sections"); - } else if (InRelroPhdr) { - InRelroPhdr = false; - IsRelroFinished = true; - } - } - if (RelRo->FirstSec) - Ret.push_back(RelRo); + if (relRo->firstSec) + ret.push_back(relRo); // PT_GNU_EH_FRAME is a special section pointing on .eh_frame_hdr. - if (!In.EhFrame->empty() && In.EhFrameHdr && In.EhFrame->getParent() && - In.EhFrameHdr->getParent()) - AddHdr(PT_GNU_EH_FRAME, In.EhFrameHdr->getParent()->getPhdrFlags()) - ->add(In.EhFrameHdr->getParent()); + if (part.ehFrame->isNeeded() && part.ehFrameHdr && + part.ehFrame->getParent() && part.ehFrameHdr->getParent()) + addHdr(PT_GNU_EH_FRAME, part.ehFrameHdr->getParent()->getPhdrFlags()) + ->add(part.ehFrameHdr->getParent()); // PT_OPENBSD_RANDOMIZE is an OpenBSD-specific feature. That makes // the dynamic linker fill the segment with random data. - if (OutputSection *Cmd = findSection(".openbsd.randomdata")) - AddHdr(PT_OPENBSD_RANDOMIZE, Cmd->getPhdrFlags())->add(Cmd); + if (OutputSection *cmd = findSection(".openbsd.randomdata", partNo)) + addHdr(PT_OPENBSD_RANDOMIZE, cmd->getPhdrFlags())->add(cmd); // PT_GNU_STACK is a special section to tell the loader to make the // pages for the stack non-executable. If you really want an executable // stack, you can pass -z execstack, but that's not recommended for // security reasons. - unsigned Perm = PF_R | PF_W; - if (Config->ZExecstack) - Perm |= PF_X; - AddHdr(PT_GNU_STACK, Perm)->p_memsz = Config->ZStackSize; + unsigned perm = PF_R | PF_W; + if (config->zExecstack) + perm |= PF_X; + addHdr(PT_GNU_STACK, perm)->p_memsz = config->zStackSize; // PT_OPENBSD_WXNEEDED is a OpenBSD-specific header to mark the executable // is expected to perform W^X violations, such as calling mprotect(2) or // mmap(2) with PROT_WRITE | PROT_EXEC, which is prohibited by default on // OpenBSD. - if (Config->ZWxneeded) - AddHdr(PT_OPENBSD_WXNEEDED, PF_X); - - // Create one PT_NOTE per a group of contiguous .note sections. - PhdrEntry *Note = nullptr; - for (OutputSection *Sec : OutputSections) { - if (Sec->Type == SHT_NOTE && (Sec->Flags & SHF_ALLOC)) { - if (!Note || Sec->LMAExpr) - Note = AddHdr(PT_NOTE, PF_R); - Note->add(Sec); + if (config->zWxneeded) + addHdr(PT_OPENBSD_WXNEEDED, PF_X); + + // Create one PT_NOTE per a group of contiguous SHT_NOTE sections with the + // same alignment. + PhdrEntry *note = nullptr; + for (OutputSection *sec : outputSections) { + if (sec->partition != partNo) + continue; + if (sec->type == SHT_NOTE && (sec->flags & SHF_ALLOC)) { + if (!note || sec->lmaExpr || note->lastSec->alignment != sec->alignment) + note = addHdr(PT_NOTE, PF_R); + note->add(sec); } else { - Note = nullptr; + note = nullptr; } } - return Ret; + return ret; } template <class ELFT> -void Writer<ELFT>::addPtArmExid(std::vector<PhdrEntry *> &Phdrs) { - if (Config->EMachine != EM_ARM) - return; - auto I = llvm::find_if(OutputSections, [](OutputSection *Cmd) { - return Cmd->Type == SHT_ARM_EXIDX; +void Writer<ELFT>::addPhdrForSection(Partition &part, unsigned shType, + unsigned pType, unsigned pFlags) { + unsigned partNo = part.getNumber(); + auto i = llvm::find_if(outputSections, [=](OutputSection *cmd) { + return cmd->partition == partNo && cmd->type == shType; }); - if (I == OutputSections.end()) + if (i == outputSections.end()) return; - // PT_ARM_EXIDX is the ARM EHABI equivalent of PT_GNU_EH_FRAME - PhdrEntry *ARMExidx = make<PhdrEntry>(PT_ARM_EXIDX, PF_R); - ARMExidx->add(*I); - Phdrs.push_back(ARMExidx); + PhdrEntry *entry = make<PhdrEntry>(pType, pFlags); + entry->add(*i); + part.phdrs.push_back(entry); } // The first section of each PT_LOAD, the first section in PT_GNU_RELRO and the // first section after PT_GNU_RELRO have to be page aligned so that the dynamic // linker can set the permissions. template <class ELFT> void Writer<ELFT>::fixSectionAlignments() { - auto PageAlign = [](OutputSection *Cmd) { - if (Cmd && !Cmd->AddrExpr) - Cmd->AddrExpr = [=] { - return alignTo(Script->getDot(), Config->MaxPageSize); + auto pageAlign = [](OutputSection *cmd) { + if (cmd && !cmd->addrExpr) + cmd->addrExpr = [=] { + return alignTo(script->getDot(), config->maxPageSize); }; }; - for (const PhdrEntry *P : Phdrs) - if (P->p_type == PT_LOAD && P->FirstSec) - PageAlign(P->FirstSec); - - for (const PhdrEntry *P : Phdrs) { - if (P->p_type != PT_GNU_RELRO) - continue; - - if (P->FirstSec) - PageAlign(P->FirstSec); - - // Find the first section after PT_GNU_RELRO. If it is in a PT_LOAD we - // have to align it to a page. - auto End = OutputSections.end(); - auto I = std::find(OutputSections.begin(), End, P->LastSec); - if (I == End || (I + 1) == End) - continue; - - OutputSection *Cmd = (*(I + 1)); - if (needsPtLoad(Cmd)) - PageAlign(Cmd); + for (Partition &part : partitions) { + for (const PhdrEntry *p : part.phdrs) + if (p->p_type == PT_LOAD && p->firstSec) + pageAlign(p->firstSec); } } // Compute an in-file position for a given section. The file offset must be the // same with its virtual address modulo the page size, so that the loader can // load executables without any address adjustment. -static uint64_t computeFileOffset(OutputSection *OS, uint64_t Off) { +static uint64_t computeFileOffset(OutputSection *os, uint64_t off) { // File offsets are not significant for .bss sections. By convention, we keep // section offsets monotonically increasing rather than setting to zero. - if (OS->Type == SHT_NOBITS) - return Off; + if (os->type == SHT_NOBITS) + return off; // If the section is not in a PT_LOAD, we just have to align it. - if (!OS->PtLoad) - return alignTo(Off, OS->Alignment); + if (!os->ptLoad) + return alignTo(off, os->alignment); // The first section in a PT_LOAD has to have congruent offset and address // module the page size. - OutputSection *First = OS->PtLoad->FirstSec; - if (OS == First) { - uint64_t Alignment = std::max<uint64_t>(OS->Alignment, Config->MaxPageSize); - return alignTo(Off, Alignment, OS->Addr); + OutputSection *first = os->ptLoad->firstSec; + if (os == first) { + uint64_t alignment = std::max<uint64_t>(os->alignment, config->maxPageSize); + return alignTo(off, alignment, os->addr); } // If two sections share the same PT_LOAD the file offset is calculated // using this formula: Off2 = Off1 + (VA2 - VA1). - return First->Offset + OS->Addr - First->Addr; + return first->offset + os->addr - first->addr; } // Set an in-file position to a given section and returns the end position of // the section. -static uint64_t setFileOffset(OutputSection *OS, uint64_t Off) { - Off = computeFileOffset(OS, Off); - OS->Offset = Off; +static uint64_t setFileOffset(OutputSection *os, uint64_t off) { + off = computeFileOffset(os, off); + os->offset = off; - if (OS->Type == SHT_NOBITS) - return Off; - return Off + OS->Size; + if (os->type == SHT_NOBITS) + return off; + return off + os->size; } template <class ELFT> void Writer<ELFT>::assignFileOffsetsBinary() { - uint64_t Off = 0; - for (OutputSection *Sec : OutputSections) - if (Sec->Flags & SHF_ALLOC) - Off = setFileOffset(Sec, Off); - FileSize = alignTo(Off, Config->Wordsize); + uint64_t off = 0; + for (OutputSection *sec : outputSections) + if (sec->flags & SHF_ALLOC) + off = setFileOffset(sec, off); + fileSize = alignTo(off, config->wordsize); } -static std::string rangeToString(uint64_t Addr, uint64_t Len) { - return "[0x" + utohexstr(Addr) + ", 0x" + utohexstr(Addr + Len - 1) + "]"; +static std::string rangeToString(uint64_t addr, uint64_t len) { + return "[0x" + utohexstr(addr) + ", 0x" + utohexstr(addr + len - 1) + "]"; } // Assign file offsets to output sections. template <class ELFT> void Writer<ELFT>::assignFileOffsets() { - uint64_t Off = 0; - Off = setFileOffset(Out::ElfHeader, Off); - Off = setFileOffset(Out::ProgramHeaders, Off); - - PhdrEntry *LastRX = nullptr; - for (PhdrEntry *P : Phdrs) - if (P->p_type == PT_LOAD && (P->p_flags & PF_X)) - LastRX = P; - - for (OutputSection *Sec : OutputSections) { - Off = setFileOffset(Sec, Off); - if (Script->HasSectionsCommand) + uint64_t off = 0; + off = setFileOffset(Out::elfHeader, off); + off = setFileOffset(Out::programHeaders, off); + + PhdrEntry *lastRX = nullptr; + for (Partition &part : partitions) + for (PhdrEntry *p : part.phdrs) + if (p->p_type == PT_LOAD && (p->p_flags & PF_X)) + lastRX = p; + + for (OutputSection *sec : outputSections) { + off = setFileOffset(sec, off); + if (script->hasSectionsCommand) continue; // If this is a last section of the last executable segment and that // segment is the last loadable segment, align the offset of the // following section to avoid loading non-segments parts of the file. - if (LastRX && LastRX->LastSec == Sec) - Off = alignTo(Off, Target->PageSize); + if (lastRX && lastRX->lastSec == sec) + off = alignTo(off, config->commonPageSize); } - SectionHeaderOff = alignTo(Off, Config->Wordsize); - FileSize = SectionHeaderOff + (OutputSections.size() + 1) * sizeof(Elf_Shdr); + sectionHeaderOff = alignTo(off, config->wordsize); + fileSize = sectionHeaderOff + (outputSections.size() + 1) * sizeof(Elf_Shdr); // Our logic assumes that sections have rising VA within the same segment. // With use of linker scripts it is possible to violate this rule and get file @@ -2178,51 +2311,49 @@ template <class ELFT> void Writer<ELFT>::assignFileOffsets() { // backwards, so we have to allow doing that to support linking them. We // perform non-critical checks for overlaps in checkSectionOverlap(), but here // we want to prevent file size overflows because it would crash the linker. - for (OutputSection *Sec : OutputSections) { - if (Sec->Type == SHT_NOBITS) + for (OutputSection *sec : outputSections) { + if (sec->type == SHT_NOBITS) continue; - if ((Sec->Offset > FileSize) || (Sec->Offset + Sec->Size > FileSize)) - error("unable to place section " + Sec->Name + " at file offset " + - rangeToString(Sec->Offset, Sec->Size) + + if ((sec->offset > fileSize) || (sec->offset + sec->size > fileSize)) + error("unable to place section " + sec->name + " at file offset " + + rangeToString(sec->offset, sec->size) + "; check your linker script for overflows"); } } // Finalize the program headers. We call this function after we assign // file offsets and VAs to all sections. -template <class ELFT> void Writer<ELFT>::setPhdrs() { - for (PhdrEntry *P : Phdrs) { - OutputSection *First = P->FirstSec; - OutputSection *Last = P->LastSec; - - if (First) { - P->p_filesz = Last->Offset - First->Offset; - if (Last->Type != SHT_NOBITS) - P->p_filesz += Last->Size; - - P->p_memsz = Last->Addr + Last->Size - First->Addr; - P->p_offset = First->Offset; - P->p_vaddr = First->Addr; - - if (!P->HasLMA) - P->p_paddr = First->getLMA(); +template <class ELFT> void Writer<ELFT>::setPhdrs(Partition &part) { + for (PhdrEntry *p : part.phdrs) { + OutputSection *first = p->firstSec; + OutputSection *last = p->lastSec; + + if (first) { + p->p_filesz = last->offset - first->offset; + if (last->type != SHT_NOBITS) + p->p_filesz += last->size; + + p->p_memsz = last->addr + last->size - first->addr; + p->p_offset = first->offset; + p->p_vaddr = first->addr; + + // File offsets in partitions other than the main partition are relative + // to the offset of the ELF headers. Perform that adjustment now. + if (part.elfHeader) + p->p_offset -= part.elfHeader->getParent()->offset; + + if (!p->hasLMA) + p->p_paddr = first->getLMA(); } - if (P->p_type == PT_LOAD) { - P->p_align = std::max<uint64_t>(P->p_align, Config->MaxPageSize); - } else if (P->p_type == PT_GNU_RELRO) { - P->p_align = 1; + if (p->p_type == PT_LOAD) { + p->p_align = std::max<uint64_t>(p->p_align, config->maxPageSize); + } else if (p->p_type == PT_GNU_RELRO) { + p->p_align = 1; // The glibc dynamic loader rounds the size down, so we need to round up // to protect the last page. This is a no-op on FreeBSD which always // rounds up. - P->p_memsz = alignTo(P->p_memsz, Target->PageSize); - } - - if (P->p_type == PT_TLS && P->p_memsz) { - // The TLS pointer goes after PT_TLS for variant 2 targets. At least glibc - // will align it, so round up the size to make sure the offsets are - // correct. - P->p_memsz = alignTo(P->p_memsz, P->p_align); + p->p_memsz = alignTo(p->p_memsz, config->commonPageSize); } } } @@ -2230,37 +2361,37 @@ template <class ELFT> void Writer<ELFT>::setPhdrs() { // A helper struct for checkSectionOverlap. namespace { struct SectionOffset { - OutputSection *Sec; - uint64_t Offset; + OutputSection *sec; + uint64_t offset; }; } // namespace // Check whether sections overlap for a specific address range (file offsets, // load and virtual adresses). -static void checkOverlap(StringRef Name, std::vector<SectionOffset> &Sections, - bool IsVirtualAddr) { - llvm::sort(Sections, [=](const SectionOffset &A, const SectionOffset &B) { - return A.Offset < B.Offset; +static void checkOverlap(StringRef name, std::vector<SectionOffset> §ions, + bool isVirtualAddr) { + llvm::sort(sections, [=](const SectionOffset &a, const SectionOffset &b) { + return a.offset < b.offset; }); // Finding overlap is easy given a vector is sorted by start position. // If an element starts before the end of the previous element, they overlap. - for (size_t I = 1, End = Sections.size(); I < End; ++I) { - SectionOffset A = Sections[I - 1]; - SectionOffset B = Sections[I]; - if (B.Offset >= A.Offset + A.Sec->Size) + for (size_t i = 1, end = sections.size(); i < end; ++i) { + SectionOffset a = sections[i - 1]; + SectionOffset b = sections[i]; + if (b.offset >= a.offset + a.sec->size) continue; // If both sections are in OVERLAY we allow the overlapping of virtual // addresses, because it is what OVERLAY was designed for. - if (IsVirtualAddr && A.Sec->InOverlay && B.Sec->InOverlay) + if (isVirtualAddr && a.sec->inOverlay && b.sec->inOverlay) continue; - errorOrWarn("section " + A.Sec->Name + " " + Name + - " range overlaps with " + B.Sec->Name + "\n>>> " + A.Sec->Name + - " range is " + rangeToString(A.Offset, A.Sec->Size) + "\n>>> " + - B.Sec->Name + " range is " + - rangeToString(B.Offset, B.Sec->Size)); + errorOrWarn("section " + a.sec->name + " " + name + + " range overlaps with " + b.sec->name + "\n>>> " + a.sec->name + + " range is " + rangeToString(a.offset, a.sec->size) + "\n>>> " + + b.sec->name + " range is " + + rangeToString(b.offset, b.sec->size)); } } @@ -2271,11 +2402,11 @@ static void checkOverlap(StringRef Name, std::vector<SectionOffset> &Sections, // ranges and the virtual address ranges don't overlap template <class ELFT> void Writer<ELFT>::checkSections() { // First, check that section's VAs fit in available address space for target. - for (OutputSection *OS : OutputSections) - if ((OS->Addr + OS->Size < OS->Addr) || - (!ELFT::Is64Bits && OS->Addr + OS->Size > UINT32_MAX)) - errorOrWarn("section " + OS->Name + " at 0x" + utohexstr(OS->Addr) + - " of size 0x" + utohexstr(OS->Size) + + for (OutputSection *os : outputSections) + if ((os->addr + os->size < os->addr) || + (!ELFT::Is64Bits && os->addr + os->size > UINT32_MAX)) + errorOrWarn("section " + os->name + " at 0x" + utohexstr(os->addr) + + " of size 0x" + utohexstr(os->size) + " exceeds available address space"); // Check for overlapping file offsets. In this case we need to skip any @@ -2283,17 +2414,17 @@ template <class ELFT> void Writer<ELFT>::checkSections() { // the file so Sec->Offset + Sec->Size can overlap with others. If --oformat // binary is specified only add SHF_ALLOC sections are added to the output // file so we skip any non-allocated sections in that case. - std::vector<SectionOffset> FileOffs; - for (OutputSection *Sec : OutputSections) - if (Sec->Size > 0 && Sec->Type != SHT_NOBITS && - (!Config->OFormatBinary || (Sec->Flags & SHF_ALLOC))) - FileOffs.push_back({Sec, Sec->Offset}); - checkOverlap("file", FileOffs, false); + std::vector<SectionOffset> fileOffs; + for (OutputSection *sec : outputSections) + if (sec->size > 0 && sec->type != SHT_NOBITS && + (!config->oFormatBinary || (sec->flags & SHF_ALLOC))) + fileOffs.push_back({sec, sec->offset}); + checkOverlap("file", fileOffs, false); // When linking with -r there is no need to check for overlapping virtual/load // addresses since those addresses will only be assigned when the final // executable/shared object is created. - if (Config->Relocatable) + if (config->relocatable) return; // Checking for overlapping virtual and load addresses only needs to take @@ -2301,20 +2432,20 @@ template <class ELFT> void Writer<ELFT>::checkSections() { // Furthermore, we also need to skip SHF_TLS sections since these will be // mapped to other addresses at runtime and can therefore have overlapping // ranges in the file. - std::vector<SectionOffset> VMAs; - for (OutputSection *Sec : OutputSections) - if (Sec->Size > 0 && (Sec->Flags & SHF_ALLOC) && !(Sec->Flags & SHF_TLS)) - VMAs.push_back({Sec, Sec->Addr}); - checkOverlap("virtual address", VMAs, true); + std::vector<SectionOffset> vmas; + for (OutputSection *sec : outputSections) + if (sec->size > 0 && (sec->flags & SHF_ALLOC) && !(sec->flags & SHF_TLS)) + vmas.push_back({sec, sec->addr}); + checkOverlap("virtual address", vmas, true); // Finally, check that the load addresses don't overlap. This will usually be // the same as the virtual addresses but can be different when using a linker // script with AT(). - std::vector<SectionOffset> LMAs; - for (OutputSection *Sec : OutputSections) - if (Sec->Size > 0 && (Sec->Flags & SHF_ALLOC) && !(Sec->Flags & SHF_TLS)) - LMAs.push_back({Sec, Sec->getLMA()}); - checkOverlap("load address", LMAs, false); + std::vector<SectionOffset> lmas; + for (OutputSection *sec : outputSections) + if (sec->size > 0 && (sec->flags & SHF_ALLOC) && !(sec->flags & SHF_TLS)) + lmas.push_back({sec, sec->getLMA()}); + checkOverlap("load address", lmas, false); } // The entry point address is chosen in the following ways. @@ -2327,89 +2458,45 @@ template <class ELFT> void Writer<ELFT>::checkSections() { // 6. the address 0. static uint64_t getEntryAddr() { // Case 1, 2 or 3 - if (Symbol *B = Symtab->find(Config->Entry)) - return B->getVA(); + if (Symbol *b = symtab->find(config->entry)) + return b->getVA(); // Case 4 - uint64_t Addr; - if (to_integer(Config->Entry, Addr)) - return Addr; + uint64_t addr; + if (to_integer(config->entry, addr)) + return addr; // Case 5 - if (OutputSection *Sec = findSection(".text")) { - if (Config->WarnMissingEntry) - warn("cannot find entry symbol " + Config->Entry + "; defaulting to 0x" + - utohexstr(Sec->Addr)); - return Sec->Addr; + if (OutputSection *sec = findSection(".text")) { + if (config->warnMissingEntry) + warn("cannot find entry symbol " + config->entry + "; defaulting to 0x" + + utohexstr(sec->addr)); + return sec->addr; } // Case 6 - if (Config->WarnMissingEntry) - warn("cannot find entry symbol " + Config->Entry + + if (config->warnMissingEntry) + warn("cannot find entry symbol " + config->entry + "; not setting start address"); return 0; } static uint16_t getELFType() { - if (Config->Pic) + if (config->isPic) return ET_DYN; - if (Config->Relocatable) + if (config->relocatable) return ET_REL; return ET_EXEC; } -static uint8_t getAbiVersion() { - // MIPS non-PIC executable gets ABI version 1. - if (Config->EMachine == EM_MIPS && getELFType() == ET_EXEC && - (Config->EFlags & (EF_MIPS_PIC | EF_MIPS_CPIC)) == EF_MIPS_CPIC) - return 1; - return 0; -} - template <class ELFT> void Writer<ELFT>::writeHeader() { - uint8_t *Buf = Buffer->getBufferStart(); - - // For executable segments, the trap instructions are written before writing - // the header. Setting Elf header bytes to zero ensures that any unused bytes - // in header are zero-cleared, instead of having trap instructions. - memset(Buf, 0, sizeof(Elf_Ehdr)); - memcpy(Buf, "\177ELF", 4); - - // Write the ELF header. - auto *EHdr = reinterpret_cast<Elf_Ehdr *>(Buf); - EHdr->e_ident[EI_CLASS] = Config->Is64 ? ELFCLASS64 : ELFCLASS32; - EHdr->e_ident[EI_DATA] = Config->IsLE ? ELFDATA2LSB : ELFDATA2MSB; - EHdr->e_ident[EI_VERSION] = EV_CURRENT; - EHdr->e_ident[EI_OSABI] = Config->OSABI; - EHdr->e_ident[EI_ABIVERSION] = getAbiVersion(); - EHdr->e_type = getELFType(); - EHdr->e_machine = Config->EMachine; - EHdr->e_version = EV_CURRENT; - EHdr->e_entry = getEntryAddr(); - EHdr->e_shoff = SectionHeaderOff; - EHdr->e_flags = Config->EFlags; - EHdr->e_ehsize = sizeof(Elf_Ehdr); - EHdr->e_phnum = Phdrs.size(); - EHdr->e_shentsize = sizeof(Elf_Shdr); - - if (!Config->Relocatable) { - EHdr->e_phoff = sizeof(Elf_Ehdr); - EHdr->e_phentsize = sizeof(Elf_Phdr); - } - - // Write the program header table. - auto *HBuf = reinterpret_cast<Elf_Phdr *>(Buf + EHdr->e_phoff); - for (PhdrEntry *P : Phdrs) { - HBuf->p_type = P->p_type; - HBuf->p_flags = P->p_flags; - HBuf->p_offset = P->p_offset; - HBuf->p_vaddr = P->p_vaddr; - HBuf->p_paddr = P->p_paddr; - HBuf->p_filesz = P->p_filesz; - HBuf->p_memsz = P->p_memsz; - HBuf->p_align = P->p_align; - ++HBuf; - } + writeEhdr<ELFT>(Out::bufferStart, *mainPart); + writePhdrs<ELFT>(Out::bufferStart + sizeof(Elf_Ehdr), *mainPart); + + auto *eHdr = reinterpret_cast<Elf_Ehdr *>(Out::bufferStart); + eHdr->e_type = getELFType(); + eHdr->e_entry = getEntryAddr(); + eHdr->e_shoff = sectionHeaderOff; // Write the section header table. // @@ -2420,57 +2507,58 @@ template <class ELFT> void Writer<ELFT>::writeHeader() { // the value. The sentinel values and fields are: // e_shnum = 0, SHdrs[0].sh_size = number of sections. // e_shstrndx = SHN_XINDEX, SHdrs[0].sh_link = .shstrtab section index. - auto *SHdrs = reinterpret_cast<Elf_Shdr *>(Buf + EHdr->e_shoff); - size_t Num = OutputSections.size() + 1; - if (Num >= SHN_LORESERVE) - SHdrs->sh_size = Num; + auto *sHdrs = reinterpret_cast<Elf_Shdr *>(Out::bufferStart + eHdr->e_shoff); + size_t num = outputSections.size() + 1; + if (num >= SHN_LORESERVE) + sHdrs->sh_size = num; else - EHdr->e_shnum = Num; + eHdr->e_shnum = num; - uint32_t StrTabIndex = In.ShStrTab->getParent()->SectionIndex; - if (StrTabIndex >= SHN_LORESERVE) { - SHdrs->sh_link = StrTabIndex; - EHdr->e_shstrndx = SHN_XINDEX; + uint32_t strTabIndex = in.shStrTab->getParent()->sectionIndex; + if (strTabIndex >= SHN_LORESERVE) { + sHdrs->sh_link = strTabIndex; + eHdr->e_shstrndx = SHN_XINDEX; } else { - EHdr->e_shstrndx = StrTabIndex; + eHdr->e_shstrndx = strTabIndex; } - for (OutputSection *Sec : OutputSections) - Sec->writeHeaderTo<ELFT>(++SHdrs); + for (OutputSection *sec : outputSections) + sec->writeHeaderTo<ELFT>(++sHdrs); } // Open a result file. template <class ELFT> void Writer<ELFT>::openFile() { - uint64_t MaxSize = Config->Is64 ? INT64_MAX : UINT32_MAX; - if (MaxSize < FileSize) { - error("output file too large: " + Twine(FileSize) + " bytes"); + uint64_t maxSize = config->is64 ? INT64_MAX : UINT32_MAX; + if (fileSize != size_t(fileSize) || maxSize < fileSize) { + error("output file too large: " + Twine(fileSize) + " bytes"); return; } - unlinkAsync(Config->OutputFile); - unsigned Flags = 0; - if (!Config->Relocatable) - Flags = FileOutputBuffer::F_executable; - Expected<std::unique_ptr<FileOutputBuffer>> BufferOrErr = - FileOutputBuffer::create(Config->OutputFile, FileSize, Flags); + unlinkAsync(config->outputFile); + unsigned flags = 0; + if (!config->relocatable) + flags = FileOutputBuffer::F_executable; + Expected<std::unique_ptr<FileOutputBuffer>> bufferOrErr = + FileOutputBuffer::create(config->outputFile, fileSize, flags); - if (!BufferOrErr) - error("failed to open " + Config->OutputFile + ": " + - llvm::toString(BufferOrErr.takeError())); - else - Buffer = std::move(*BufferOrErr); + if (!bufferOrErr) { + error("failed to open " + config->outputFile + ": " + + llvm::toString(bufferOrErr.takeError())); + return; + } + buffer = std::move(*bufferOrErr); + Out::bufferStart = buffer->getBufferStart(); } template <class ELFT> void Writer<ELFT>::writeSectionsBinary() { - uint8_t *Buf = Buffer->getBufferStart(); - for (OutputSection *Sec : OutputSections) - if (Sec->Flags & SHF_ALLOC) - Sec->writeTo<ELFT>(Buf + Sec->Offset); + for (OutputSection *sec : outputSections) + if (sec->flags & SHF_ALLOC) + sec->writeTo<ELFT>(Out::bufferStart + sec->offset); } -static void fillTrap(uint8_t *I, uint8_t *End) { - for (; I + 4 <= End; I += 4) - memcpy(I, &Target->TrapInstr, 4); +static void fillTrap(uint8_t *i, uint8_t *end) { + for (; i + 4 <= end; i += 4) + memcpy(i, &target->trapInstr, 4); } // Fill the last page of executable segments with trap instructions @@ -2480,61 +2568,119 @@ static void fillTrap(uint8_t *I, uint8_t *End) { // We'll leave other pages in segments as-is because the rest will be // overwritten by output sections. template <class ELFT> void Writer<ELFT>::writeTrapInstr() { - if (Script->HasSectionsCommand) + if (script->hasSectionsCommand) return; - // Fill the last page. - uint8_t *Buf = Buffer->getBufferStart(); - for (PhdrEntry *P : Phdrs) - if (P->p_type == PT_LOAD && (P->p_flags & PF_X)) - fillTrap(Buf + alignDown(P->p_offset + P->p_filesz, Target->PageSize), - Buf + alignTo(P->p_offset + P->p_filesz, Target->PageSize)); - - // Round up the file size of the last segment to the page boundary iff it is - // an executable segment to ensure that other tools don't accidentally - // trim the instruction padding (e.g. when stripping the file). - PhdrEntry *Last = nullptr; - for (PhdrEntry *P : Phdrs) - if (P->p_type == PT_LOAD) - Last = P; - - if (Last && (Last->p_flags & PF_X)) - Last->p_memsz = Last->p_filesz = alignTo(Last->p_filesz, Target->PageSize); + for (Partition &part : partitions) { + // Fill the last page. + for (PhdrEntry *p : part.phdrs) + if (p->p_type == PT_LOAD && (p->p_flags & PF_X)) + fillTrap(Out::bufferStart + alignDown(p->firstSec->offset + p->p_filesz, + config->commonPageSize), + Out::bufferStart + alignTo(p->firstSec->offset + p->p_filesz, + config->commonPageSize)); + + // Round up the file size of the last segment to the page boundary iff it is + // an executable segment to ensure that other tools don't accidentally + // trim the instruction padding (e.g. when stripping the file). + PhdrEntry *last = nullptr; + for (PhdrEntry *p : part.phdrs) + if (p->p_type == PT_LOAD) + last = p; + + if (last && (last->p_flags & PF_X)) + last->p_memsz = last->p_filesz = + alignTo(last->p_filesz, config->commonPageSize); + } } // Write section contents to a mmap'ed file. template <class ELFT> void Writer<ELFT>::writeSections() { - uint8_t *Buf = Buffer->getBufferStart(); - - OutputSection *EhFrameHdr = nullptr; - if (In.EhFrameHdr && !In.EhFrameHdr->empty()) - EhFrameHdr = In.EhFrameHdr->getParent(); - // In -r or -emit-relocs mode, write the relocation sections first as in // ELf_Rel targets we might find out that we need to modify the relocated // section while doing it. - for (OutputSection *Sec : OutputSections) - if (Sec->Type == SHT_REL || Sec->Type == SHT_RELA) - Sec->writeTo<ELFT>(Buf + Sec->Offset); + for (OutputSection *sec : outputSections) + if (sec->type == SHT_REL || sec->type == SHT_RELA) + sec->writeTo<ELFT>(Out::bufferStart + sec->offset); + + for (OutputSection *sec : outputSections) + if (sec->type != SHT_REL && sec->type != SHT_RELA) + sec->writeTo<ELFT>(Out::bufferStart + sec->offset); +} + +// Split one uint8 array into small pieces of uint8 arrays. +static std::vector<ArrayRef<uint8_t>> split(ArrayRef<uint8_t> arr, + size_t chunkSize) { + std::vector<ArrayRef<uint8_t>> ret; + while (arr.size() > chunkSize) { + ret.push_back(arr.take_front(chunkSize)); + arr = arr.drop_front(chunkSize); + } + if (!arr.empty()) + ret.push_back(arr); + return ret; +} - for (OutputSection *Sec : OutputSections) - if (Sec != EhFrameHdr && Sec->Type != SHT_REL && Sec->Type != SHT_RELA) - Sec->writeTo<ELFT>(Buf + Sec->Offset); +// Computes a hash value of Data using a given hash function. +// In order to utilize multiple cores, we first split data into 1MB +// chunks, compute a hash for each chunk, and then compute a hash value +// of the hash values. +static void +computeHash(llvm::MutableArrayRef<uint8_t> hashBuf, + llvm::ArrayRef<uint8_t> data, + std::function<void(uint8_t *dest, ArrayRef<uint8_t> arr)> hashFn) { + std::vector<ArrayRef<uint8_t>> chunks = split(data, 1024 * 1024); + std::vector<uint8_t> hashes(chunks.size() * hashBuf.size()); + + // Compute hash values. + parallelForEachN(0, chunks.size(), [&](size_t i) { + hashFn(hashes.data() + i * hashBuf.size(), chunks[i]); + }); - // The .eh_frame_hdr depends on .eh_frame section contents, therefore - // it should be written after .eh_frame is written. - if (EhFrameHdr) - EhFrameHdr->writeTo<ELFT>(Buf + EhFrameHdr->Offset); + // Write to the final output buffer. + hashFn(hashBuf.data(), hashes); } template <class ELFT> void Writer<ELFT>::writeBuildId() { - if (!In.BuildId || !In.BuildId->getParent()) + if (!mainPart->buildId || !mainPart->buildId->getParent()) return; + if (config->buildId == BuildIdKind::Hexstring) { + for (Partition &part : partitions) + part.buildId->writeBuildId(config->buildIdVector); + return; + } + // Compute a hash of all sections of the output file. - uint8_t *Start = Buffer->getBufferStart(); - uint8_t *End = Start + FileSize; - In.BuildId->writeBuildId({Start, End}); + size_t hashSize = mainPart->buildId->hashSize; + std::vector<uint8_t> buildId(hashSize); + llvm::ArrayRef<uint8_t> buf{Out::bufferStart, size_t(fileSize)}; + + switch (config->buildId) { + case BuildIdKind::Fast: + computeHash(buildId, buf, [](uint8_t *dest, ArrayRef<uint8_t> arr) { + write64le(dest, xxHash64(arr)); + }); + break; + case BuildIdKind::Md5: + computeHash(buildId, buf, [&](uint8_t *dest, ArrayRef<uint8_t> arr) { + memcpy(dest, MD5::hash(arr).data(), hashSize); + }); + break; + case BuildIdKind::Sha1: + computeHash(buildId, buf, [&](uint8_t *dest, ArrayRef<uint8_t> arr) { + memcpy(dest, SHA1::hash(arr).data(), hashSize); + }); + break; + case BuildIdKind::Uuid: + if (auto ec = llvm::getRandomBytes(buildId.data(), hashSize)) + error("entropy source failure: " + ec.message()); + break; + default: + llvm_unreachable("unknown BuildIdKind"); + } + for (Partition &part : partitions) + part.buildId->writeBuildId(buildId); } template void elf::writeResult<ELF32LE>(); |