Index: vendor/lld/dist/ELF/LinkerScript.cpp =================================================================== --- vendor/lld/dist/ELF/LinkerScript.cpp (revision 319237) +++ vendor/lld/dist/ELF/LinkerScript.cpp (revision 319238) @@ -1,1156 +1,1163 @@ //===- LinkerScript.cpp ---------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file contains the parser/evaluator of the linker script. // //===----------------------------------------------------------------------===// #include "LinkerScript.h" #include "Config.h" #include "InputSection.h" #include "Memory.h" #include "OutputSections.h" #include "Strings.h" #include "SymbolTable.h" #include "Symbols.h" #include "SyntheticSections.h" #include "Target.h" #include "Threads.h" #include "Writer.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/Casting.h" #include "llvm/Support/ELF.h" #include "llvm/Support/Endian.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/Path.h" #include #include #include #include #include #include #include #include using namespace llvm; using namespace llvm::ELF; using namespace llvm::object; using namespace llvm::support::endian; using namespace lld; using namespace lld::elf; LinkerScript *elf::Script; uint64_t ExprValue::getValue() const { if (Sec) { if (Sec->getOutputSection()) - return Sec->getOffset(Val) + Sec->getOutputSection()->Addr; + return alignTo(Sec->getOffset(Val) + Sec->getOutputSection()->Addr, + Alignment); error("unable to evaluate expression: input section " + Sec->Name + " has no output section assigned"); } - return Val; + return alignTo(Val, Alignment); } uint64_t ExprValue::getSecAddr() const { if (Sec) return Sec->getOffset(0) + Sec->getOutputSection()->Addr; return 0; } template static SymbolBody *addRegular(SymbolAssignment *Cmd) { Symbol *Sym; uint8_t Visibility = Cmd->Hidden ? STV_HIDDEN : STV_DEFAULT; std::tie(Sym, std::ignore) = Symtab::X->insert( Cmd->Name, /*Type*/ 0, Visibility, /*CanOmitFromDynSym*/ false, /*File*/ nullptr); Sym->Binding = STB_GLOBAL; ExprValue Value = Cmd->Expression(); SectionBase *Sec = Value.isAbsolute() ? nullptr : Value.Sec; // We want to set symbol values early if we can. This allows us to use symbols // as variables in linker scripts. Doing so allows us to write expressions // like this: `alignment = 16; . = ALIGN(., alignment)` uint64_t SymValue = Value.isAbsolute() ? Value.getValue() : 0; replaceBody(Sym, Cmd->Name, /*IsLocal=*/false, Visibility, STT_NOTYPE, SymValue, 0, Sec, nullptr); return Sym->body(); } OutputSection *LinkerScript::getOutputSection(const Twine &Loc, StringRef Name) { for (OutputSection *Sec : *OutputSections) if (Sec->Name == Name) return Sec; static OutputSection Dummy("", 0, 0); if (ErrorOnMissingSection) error(Loc + ": undefined section " + Name); return &Dummy; } // This function is essentially the same as getOutputSection(Name)->Size, // but it won't print out an error message if a given section is not found. // // Linker script does not create an output section if its content is empty. // We want to allow SIZEOF(.foo) where .foo is a section which happened to // be empty. That is why this function is different from getOutputSection(). uint64_t LinkerScript::getOutputSectionSize(StringRef Name) { for (OutputSection *Sec : *OutputSections) if (Sec->Name == Name) return Sec->Size; return 0; } void LinkerScript::setDot(Expr E, const Twine &Loc, bool InSec) { uint64_t Val = E().getValue(); if (Val < Dot) { if (InSec) error(Loc + ": unable to move location counter backward for: " + CurOutSec->Name); else error(Loc + ": unable to move location counter backward"); } Dot = Val; // Update to location counter means update to section size. if (InSec) CurOutSec->Size = Dot - CurOutSec->Addr; } // Sets value of a symbol. Two kinds of symbols are processed: synthetic // symbols, whose value is an offset from beginning of section and regular // symbols whose value is absolute. void LinkerScript::assignSymbol(SymbolAssignment *Cmd, bool InSec) { if (Cmd->Name == ".") { setDot(Cmd->Expression, Cmd->Location, InSec); return; } if (!Cmd->Sym) return; auto *Sym = cast(Cmd->Sym); ExprValue V = Cmd->Expression(); if (V.isAbsolute()) { Sym->Value = V.getValue(); } else { Sym->Section = V.Sec; if (Sym->Section->Flags & SHF_ALLOC) - Sym->Value = V.Val; + Sym->Value = alignTo(V.Val, V.Alignment); else Sym->Value = V.getValue(); } } static SymbolBody *findSymbol(StringRef S) { switch (Config->EKind) { case ELF32LEKind: return Symtab::X->find(S); case ELF32BEKind: return Symtab::X->find(S); case ELF64LEKind: return Symtab::X->find(S); case ELF64BEKind: return Symtab::X->find(S); default: llvm_unreachable("unknown Config->EKind"); } } static SymbolBody *addRegularSymbol(SymbolAssignment *Cmd) { switch (Config->EKind) { case ELF32LEKind: return addRegular(Cmd); case ELF32BEKind: return addRegular(Cmd); case ELF64LEKind: return addRegular(Cmd); case ELF64BEKind: return addRegular(Cmd); default: llvm_unreachable("unknown Config->EKind"); } } void LinkerScript::addSymbol(SymbolAssignment *Cmd) { if (Cmd->Name == ".") return; // If a symbol was in PROVIDE(), we need to define it only when // it is a referenced undefined symbol. SymbolBody *B = findSymbol(Cmd->Name); if (Cmd->Provide && (!B || B->isDefined())) return; Cmd->Sym = addRegularSymbol(Cmd); } bool SymbolAssignment::classof(const BaseCommand *C) { return C->Kind == AssignmentKind; } bool OutputSectionCommand::classof(const BaseCommand *C) { return C->Kind == OutputSectionKind; } // Fill [Buf, Buf + Size) with Filler. // This is used for linker script "=fillexp" command. static void fill(uint8_t *Buf, size_t Size, uint32_t Filler) { size_t I = 0; for (; I + 4 < Size; I += 4) memcpy(Buf + I, &Filler, 4); memcpy(Buf + I, &Filler, Size - I); } bool InputSectionDescription::classof(const BaseCommand *C) { return C->Kind == InputSectionKind; } bool AssertCommand::classof(const BaseCommand *C) { return C->Kind == AssertKind; } bool BytesDataCommand::classof(const BaseCommand *C) { return C->Kind == BytesDataKind; } static StringRef basename(InputSectionBase *S) { if (S->File) return sys::path::filename(S->File->getName()); return ""; } bool LinkerScript::shouldKeep(InputSectionBase *S) { for (InputSectionDescription *ID : Opt.KeptSections) if (ID->FilePat.match(basename(S))) for (SectionPattern &P : ID->SectionPatterns) if (P.SectionPat.match(S->Name)) return true; return false; } // A helper function for the SORT() command. static std::function getComparator(SortSectionPolicy K) { switch (K) { case SortSectionPolicy::Alignment: return [](InputSectionBase *A, InputSectionBase *B) { // ">" is not a mistake. Sections with larger alignments are placed // before sections with smaller alignments in order to reduce the // amount of padding necessary. This is compatible with GNU. return A->Alignment > B->Alignment; }; case SortSectionPolicy::Name: return [](InputSectionBase *A, InputSectionBase *B) { return A->Name < B->Name; }; case SortSectionPolicy::Priority: return [](InputSectionBase *A, InputSectionBase *B) { return getPriority(A->Name) < getPriority(B->Name); }; default: llvm_unreachable("unknown sort policy"); } } // A helper function for the SORT() command. static bool matchConstraints(ArrayRef Sections, ConstraintKind Kind) { if (Kind == ConstraintKind::NoConstraint) return true; bool IsRW = llvm::any_of(Sections, [](InputSectionBase *Sec) { return static_cast(Sec)->Flags & SHF_WRITE; }); return (IsRW && Kind == ConstraintKind::ReadWrite) || (!IsRW && Kind == ConstraintKind::ReadOnly); } static void sortSections(InputSection **Begin, InputSection **End, SortSectionPolicy K) { if (K != SortSectionPolicy::Default && K != SortSectionPolicy::None) std::stable_sort(Begin, End, getComparator(K)); } // Compute and remember which sections the InputSectionDescription matches. std::vector LinkerScript::computeInputSections(const InputSectionDescription *Cmd) { std::vector Ret; // Collects all sections that satisfy constraints of Cmd. for (const SectionPattern &Pat : Cmd->SectionPatterns) { size_t SizeBefore = Ret.size(); for (InputSectionBase *Sec : InputSections) { + if (!isa(Sec)) + continue; + if (Sec->Assigned) continue; // For -emit-relocs we have to ignore entries like // .rela.dyn : { *(.rela.data) } // which are common because they are in the default bfd script. if (Sec->Type == SHT_REL || Sec->Type == SHT_RELA) continue; StringRef Filename = basename(Sec); if (!Cmd->FilePat.match(Filename) || Pat.ExcludedFilePat.match(Filename) || !Pat.SectionPat.match(Sec->Name)) continue; Ret.push_back(cast(Sec)); Sec->Assigned = true; } // Sort sections as instructed by SORT-family commands and --sort-section // option. Because SORT-family commands can be nested at most two depth // (e.g. SORT_BY_NAME(SORT_BY_ALIGNMENT(.text.*))) and because the command // line option is respected even if a SORT command is given, the exact // behavior we have here is a bit complicated. Here are the rules. // // 1. If two SORT commands are given, --sort-section is ignored. // 2. If one SORT command is given, and if it is not SORT_NONE, // --sort-section is handled as an inner SORT command. // 3. If one SORT command is given, and if it is SORT_NONE, don't sort. // 4. If no SORT command is given, sort according to --sort-section. InputSection **Begin = Ret.data() + SizeBefore; InputSection **End = Ret.data() + Ret.size(); if (Pat.SortOuter != SortSectionPolicy::None) { if (Pat.SortInner == SortSectionPolicy::Default) sortSections(Begin, End, Config->SortSection); else sortSections(Begin, End, Pat.SortInner); sortSections(Begin, End, Pat.SortOuter); } } return Ret; } void LinkerScript::discard(ArrayRef V) { for (InputSectionBase *S : V) { S->Live = false; if (S == InX::ShStrTab) error("discarding .shstrtab section is not allowed"); discard(S->DependentSections); } } std::vector LinkerScript::createInputSectionList(OutputSectionCommand &OutCmd) { std::vector Ret; for (BaseCommand *Base : OutCmd.Commands) { auto *Cmd = dyn_cast(Base); if (!Cmd) continue; Cmd->Sections = computeInputSections(Cmd); Ret.insert(Ret.end(), Cmd->Sections.begin(), Cmd->Sections.end()); } return Ret; } void LinkerScript::processCommands(OutputSectionFactory &Factory) { // A symbol can be assigned before any section is mentioned in the linker // script. In an DSO, the symbol values are addresses, so the only important // section values are: // * SHN_UNDEF // * SHN_ABS // * Any value meaning a regular section. // To handle that, create a dummy aether section that fills the void before // the linker scripts switches to another section. It has an index of one // which will map to whatever the first actual section is. Aether = make("", 0, SHF_ALLOC); Aether->SectionIndex = 1; CurOutSec = Aether; Dot = 0; for (size_t I = 0; I < Opt.Commands.size(); ++I) { // Handle symbol assignments outside of any output section. if (auto *Cmd = dyn_cast(Opt.Commands[I])) { addSymbol(Cmd); continue; } if (auto *Cmd = dyn_cast(Opt.Commands[I])) { std::vector V = createInputSectionList(*Cmd); // The output section name `/DISCARD/' is special. // Any input section assigned to it is discarded. if (Cmd->Name == "/DISCARD/") { discard(V); continue; } // This is for ONLY_IF_RO and ONLY_IF_RW. An output section directive // ".foo : ONLY_IF_R[OW] { ... }" is handled only if all member input // sections satisfy a given constraint. If not, a directive is handled // as if it wasn't present from the beginning. // // Because we'll iterate over Commands many more times, the easiest // way to "make it as if it wasn't present" is to just remove it. if (!matchConstraints(V, Cmd->Constraint)) { for (InputSectionBase *S : V) S->Assigned = false; Opt.Commands.erase(Opt.Commands.begin() + I); --I; continue; } // A directive may contain symbol definitions like this: // ".foo : { ...; bar = .; }". Handle them. for (BaseCommand *Base : Cmd->Commands) if (auto *OutCmd = dyn_cast(Base)) addSymbol(OutCmd); // Handle subalign (e.g. ".foo : SUBALIGN(32) { ... }"). If subalign // is given, input sections are aligned to that value, whether the // given value is larger or smaller than the original section alignment. if (Cmd->SubalignExpr) { uint32_t Subalign = Cmd->SubalignExpr().getValue(); for (InputSectionBase *S : V) S->Alignment = Subalign; } // Add input sections to an output section. for (InputSectionBase *S : V) Factory.addInputSec(S, Cmd->Name, Cmd->Sec); if (OutputSection *Sec = Cmd->Sec) { assert(Sec->SectionIndex == INT_MAX); Sec->SectionIndex = I; SecToCommand[Sec] = Cmd; } } } CurOutSec = nullptr; } void LinkerScript::fabricateDefaultCommands() { std::vector Commands; // Define start address uint64_t StartAddr = Config->ImageBase + elf::getHeaderSize(); // The Sections with -T
have been sorted in order of ascending // address. We must lower StartAddr if the lowest -T
as // calls to setDot() must be monotonically increasing. for (auto& KV : Config->SectionStartMap) StartAddr = std::min(StartAddr, KV.second); Commands.push_back( make(".", [=] { return StartAddr; }, "")); // For each OutputSection that needs a VA fabricate an OutputSectionCommand // with an InputSectionDescription describing the InputSections for (OutputSection *Sec : *OutputSections) { auto *OSCmd = make(Sec->Name); OSCmd->Sec = Sec; SecToCommand[Sec] = OSCmd; // Prefer user supplied address over additional alignment constraint auto I = Config->SectionStartMap.find(Sec->Name); if (I != Config->SectionStartMap.end()) Commands.push_back( make(".", [=] { return I->second; }, "")); else if (Sec->PageAlign) OSCmd->AddrExpr = [=] { return alignTo(Script->getDot(), Config->MaxPageSize); }; Commands.push_back(OSCmd); if (Sec->Sections.size()) { auto *ISD = make(""); OSCmd->Commands.push_back(ISD); for (InputSection *ISec : Sec->Sections) { ISD->Sections.push_back(ISec); ISec->Assigned = true; } } } // SECTIONS commands run before other non SECTIONS commands Commands.insert(Commands.end(), Opt.Commands.begin(), Opt.Commands.end()); Opt.Commands = std::move(Commands); } // Add sections that didn't match any sections command. void LinkerScript::addOrphanSections(OutputSectionFactory &Factory) { for (InputSectionBase *S : InputSections) { if (!S->Live || S->OutSec) continue; StringRef Name = getOutputSectionName(S->Name); auto I = std::find_if( Opt.Commands.begin(), Opt.Commands.end(), [&](BaseCommand *Base) { if (auto *Cmd = dyn_cast(Base)) return Cmd->Name == Name; return false; }); if (I == Opt.Commands.end()) { Factory.addInputSec(S, Name); } else { auto *Cmd = cast(*I); Factory.addInputSec(S, Name, Cmd->Sec); if (OutputSection *Sec = Cmd->Sec) { SecToCommand[Sec] = Cmd; unsigned Index = std::distance(Opt.Commands.begin(), I); assert(Sec->SectionIndex == INT_MAX || Sec->SectionIndex == Index); Sec->SectionIndex = Index; } auto *ISD = make(""); ISD->Sections.push_back(cast(S)); Cmd->Commands.push_back(ISD); } } } uint64_t LinkerScript::advance(uint64_t Size, unsigned Align) { bool IsTbss = (CurOutSec->Flags & SHF_TLS) && CurOutSec->Type == SHT_NOBITS; uint64_t Start = IsTbss ? Dot + ThreadBssOffset : Dot; Start = alignTo(Start, Align); uint64_t End = Start + Size; if (IsTbss) ThreadBssOffset = End - Dot; else Dot = End; return End; } void LinkerScript::output(InputSection *S) { uint64_t Pos = advance(S->getSize(), S->Alignment); S->OutSecOff = Pos - S->getSize() - CurOutSec->Addr; // Update output section size after adding each section. This is so that // SIZEOF works correctly in the case below: // .foo { *(.aaa) a = SIZEOF(.foo); *(.bbb) } CurOutSec->Size = Pos - CurOutSec->Addr; // If there is a memory region associated with this input section, then // place the section in that region and update the region index. if (CurMemRegion) { CurMemRegion->Offset += CurOutSec->Size; uint64_t CurSize = CurMemRegion->Offset - CurMemRegion->Origin; if (CurSize > CurMemRegion->Length) { uint64_t OverflowAmt = CurSize - CurMemRegion->Length; error("section '" + CurOutSec->Name + "' will not fit in region '" + CurMemRegion->Name + "': overflowed by " + Twine(OverflowAmt) + " bytes"); } } } void LinkerScript::switchTo(OutputSection *Sec) { if (CurOutSec == Sec) return; CurOutSec = Sec; CurOutSec->Addr = advance(0, CurOutSec->Alignment); // If neither AT nor AT> is specified for an allocatable section, the linker // will set the LMA such that the difference between VMA and LMA for the // section is the same as the preceding output section in the same region // https://sourceware.org/binutils/docs-2.20/ld/Output-Section-LMA.html if (LMAOffset) CurOutSec->LMAOffset = LMAOffset(); } void LinkerScript::process(BaseCommand &Base) { // This handles the assignments to symbol or to the dot. if (auto *Cmd = dyn_cast(&Base)) { assignSymbol(Cmd, true); return; } // Handle BYTE(), SHORT(), LONG(), or QUAD(). if (auto *Cmd = dyn_cast(&Base)) { Cmd->Offset = Dot - CurOutSec->Addr; Dot += Cmd->Size; CurOutSec->Size = Dot - CurOutSec->Addr; return; } // Handle ASSERT(). if (auto *Cmd = dyn_cast(&Base)) { Cmd->Expression(); return; } // Handle a single input section description command. // It calculates and assigns the offsets for each section and also // updates the output section size. auto &Cmd = cast(Base); for (InputSectionBase *Sec : Cmd.Sections) { // We tentatively added all synthetic sections at the beginning and removed // empty ones afterwards (because there is no way to know whether they were // going be empty or not other than actually running linker scripts.) // We need to ignore remains of empty sections. if (auto *S = dyn_cast(Sec)) if (S->empty()) continue; if (!Sec->Live) continue; assert(CurOutSec == Sec->OutSec); output(cast(Sec)); } } // This function searches for a memory region to place the given output // section in. If found, a pointer to the appropriate memory region is // returned. Otherwise, a nullptr is returned. MemoryRegion *LinkerScript::findMemoryRegion(OutputSectionCommand *Cmd) { // If a memory region name was specified in the output section command, // then try to find that region first. if (!Cmd->MemoryRegionName.empty()) { auto It = Opt.MemoryRegions.find(Cmd->MemoryRegionName); if (It != Opt.MemoryRegions.end()) return &It->second; error("memory region '" + Cmd->MemoryRegionName + "' not declared"); return nullptr; } // If at least one memory region is defined, all sections must // belong to some memory region. Otherwise, we don't need to do // anything for memory regions. if (Opt.MemoryRegions.empty()) return nullptr; OutputSection *Sec = Cmd->Sec; // See if a region can be found by matching section flags. for (auto &Pair : Opt.MemoryRegions) { MemoryRegion &M = Pair.second; if ((M.Flags & Sec->Flags) && (M.NegFlags & Sec->Flags) == 0) return &M; } // Otherwise, no suitable region was found. if (Sec->Flags & SHF_ALLOC) error("no memory region specified for section '" + Sec->Name + "'"); return nullptr; } // This function assigns offsets to input sections and an output section // for a single sections command (e.g. ".text { *(.text); }"). void LinkerScript::assignOffsets(OutputSectionCommand *Cmd) { OutputSection *Sec = Cmd->Sec; if (!Sec) return; if (Cmd->AddrExpr && (Sec->Flags & SHF_ALLOC)) setDot(Cmd->AddrExpr, Cmd->Location, false); if (Cmd->LMAExpr) { uint64_t D = Dot; LMAOffset = [=] { return Cmd->LMAExpr().getValue() - D; }; } CurMemRegion = Cmd->MemRegion; if (CurMemRegion) Dot = CurMemRegion->Offset; switchTo(Sec); // We do not support custom layout for compressed debug sectons. // At this point we already know their size and have compressed content. if (CurOutSec->Flags & SHF_COMPRESSED) return; for (BaseCommand *C : Cmd->Commands) process(*C); } void LinkerScript::removeEmptyCommands() { // It is common practice to use very generic linker scripts. So for any // given run some of the output sections in the script will be empty. // We could create corresponding empty output sections, but that would // clutter the output. // We instead remove trivially empty sections. The bfd linker seems even // more aggressive at removing them. auto Pos = std::remove_if( Opt.Commands.begin(), Opt.Commands.end(), [&](BaseCommand *Base) { if (auto *Cmd = dyn_cast(Base)) return std::find(OutputSections->begin(), OutputSections->end(), Cmd->Sec) == OutputSections->end(); return false; }); Opt.Commands.erase(Pos, Opt.Commands.end()); } static bool isAllSectionDescription(const OutputSectionCommand &Cmd) { for (BaseCommand *Base : Cmd.Commands) if (!isa(*Base)) return false; return true; } void LinkerScript::adjustSectionsBeforeSorting() { // If the output section contains only symbol assignments, create a // corresponding output section. The bfd linker seems to only create them if // '.' is assigned to, but creating these section should not have any bad // consequeces and gives us a section to put the symbol in. uint64_t Flags = SHF_ALLOC; for (int I = 0, E = Opt.Commands.size(); I != E; ++I) { auto *Cmd = dyn_cast(Opt.Commands[I]); if (!Cmd) continue; if (OutputSection *Sec = Cmd->Sec) { Flags = Sec->Flags; continue; } if (isAllSectionDescription(*Cmd)) continue; auto *OutSec = make(Cmd->Name, SHT_PROGBITS, Flags); OutSec->SectionIndex = I; OutputSections->push_back(OutSec); Cmd->Sec = OutSec; SecToCommand[OutSec] = Cmd; } } void LinkerScript::adjustSectionsAfterSorting() { placeOrphanSections(); // Try and find an appropriate memory region to assign offsets in. for (BaseCommand *Base : Opt.Commands) { if (auto *Cmd = dyn_cast(Base)) { Cmd->MemRegion = findMemoryRegion(Cmd); // Handle align (e.g. ".foo : ALIGN(16) { ... }"). if (Cmd->AlignExpr) Cmd->Sec->updateAlignment(Cmd->AlignExpr().getValue()); } } // If output section command doesn't specify any segments, // and we haven't previously assigned any section to segment, // then we simply assign section to the very first load segment. // Below is an example of such linker script: // PHDRS { seg PT_LOAD; } // SECTIONS { .aaa : { *(.aaa) } } std::vector DefPhdrs; auto FirstPtLoad = std::find_if(Opt.PhdrsCommands.begin(), Opt.PhdrsCommands.end(), [](const PhdrsCommand &Cmd) { return Cmd.Type == PT_LOAD; }); if (FirstPtLoad != Opt.PhdrsCommands.end()) DefPhdrs.push_back(FirstPtLoad->Name); // Walk the commands and propagate the program headers to commands that don't // explicitly specify them. for (BaseCommand *Base : Opt.Commands) { auto *Cmd = dyn_cast(Base); if (!Cmd) continue; if (Cmd->Phdrs.empty()) Cmd->Phdrs = DefPhdrs; else DefPhdrs = Cmd->Phdrs; } removeEmptyCommands(); } // When placing orphan sections, we want to place them after symbol assignments // so that an orphan after // begin_foo = .; // foo : { *(foo) } // end_foo = .; // doesn't break the intended meaning of the begin/end symbols. // We don't want to go over sections since Writer::sortSections is the // one in charge of deciding the order of the sections. // We don't want to go over alignments, since doing so in // rx_sec : { *(rx_sec) } // . = ALIGN(0x1000); // /* 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 (isa(Cmd)) return false; if (auto *Assign = dyn_cast(Cmd)) return Assign->Name != "."; return true; } // Orphan sections are sections present in the input files which are // not explicitly placed into the output file by the linker script. // // When the control reaches this function, Opt.Commands contains // output section commands for non-orphan sections only. This function // adds new elements for orphan sections so that all sections are // explicitly handled by Opt.Commands. // // Writer::sortSections has already sorted output sections. // What we need to do is to scan OutputSections vector and // Opt.Commands in parallel to find orphan sections. If there is an // output section that doesn't have a corresponding entry in // Opt.Commands, we will insert a new entry to Opt.Commands. // // There is some ambiguity as to where exactly a new entry should be // inserted, because Opt.Commands contains not only output section // commands but also other types of commands such as symbol assignment // expressions. There's no correct answer here due to the lack of the // formal specification of the linker script. We use heuristics to // determine whether a new output command should be added before or // after another commands. For the details, look at shouldSkip // function. void LinkerScript::placeOrphanSections() { // The OutputSections are already in the correct order. // This loops creates or moves commands as needed so that they are in the // correct order. int CmdIndex = 0; // 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(Opt.Commands.begin(), Opt.Commands.end(), [](BaseCommand *Cmd) { return !shouldSkip(Cmd); }); if (FirstSectionOrDotAssignment != Opt.Commands.end()) { CmdIndex = FirstSectionOrDotAssignment - Opt.Commands.begin(); if (isa(**FirstSectionOrDotAssignment)) ++CmdIndex; } for (OutputSection *Sec : *OutputSections) { StringRef Name = Sec->Name; // Find the last spot where we can insert a command and still get the // correct result. auto CmdIter = Opt.Commands.begin() + CmdIndex; auto E = Opt.Commands.end(); while (CmdIter != E && shouldSkip(*CmdIter)) { ++CmdIter; ++CmdIndex; } // If there is no command corresponding to this output section, // create one and put a InputSectionDescription in it so that both // representations agree on which input sections to use. OutputSectionCommand *Cmd = getCmd(Sec); if (!Cmd) { Cmd = make(Name); Opt.Commands.insert(CmdIter, Cmd); ++CmdIndex; Cmd->Sec = Sec; SecToCommand[Sec] = Cmd; auto *ISD = make(""); for (InputSection *IS : Sec->Sections) ISD->Sections.push_back(IS); Cmd->Commands.push_back(ISD); continue; } // Continue from where we found it. while (*CmdIter != Cmd) { ++CmdIter; ++CmdIndex; } ++CmdIndex; } } void LinkerScript::processNonSectionCommands() { for (BaseCommand *Base : Opt.Commands) { if (auto *Cmd = dyn_cast(Base)) assignSymbol(Cmd, false); else if (auto *Cmd = dyn_cast(Base)) Cmd->Expression(); } } // Do a last effort at synchronizing the linker script "AST" and the section // list. This is needed to account for last minute changes, like adding a // .ARM.exidx terminator and sorting SHF_LINK_ORDER sections. // // FIXME: We should instead create the "AST" earlier and the above changes would // be done directly in the "AST". // // This can only handle new sections being added and sections being reordered. void LinkerScript::synchronize() { for (BaseCommand *Base : Opt.Commands) { auto *Cmd = dyn_cast(Base); if (!Cmd) continue; ArrayRef Sections = Cmd->Sec->Sections; std::vector ScriptSections; DenseSet ScriptSectionsSet; for (BaseCommand *Base : Cmd->Commands) { auto *ISD = dyn_cast(Base); if (!ISD) continue; for (InputSection *&IS : ISD->Sections) { if (IS->Live) { ScriptSections.push_back(&IS); ScriptSectionsSet.insert(IS); } } } std::vector Missing; for (InputSection *IS : Sections) if (!ScriptSectionsSet.count(IS)) Missing.push_back(IS); if (!Missing.empty()) { auto ISD = make(""); ISD->Sections = Missing; Cmd->Commands.push_back(ISD); for (InputSection *&IS : ISD->Sections) if (IS->Live) ScriptSections.push_back(&IS); } assert(ScriptSections.size() == Sections.size()); for (int I = 0, N = Sections.size(); I < N; ++I) *ScriptSections[I] = Sections[I]; } } static bool allocateHeaders(std::vector &Phdrs, ArrayRef OutputSections, uint64_t Min) { auto FirstPTLoad = std::find_if(Phdrs.begin(), Phdrs.end(), [](const PhdrEntry &E) { return E.p_type == PT_LOAD; }); if (FirstPTLoad == Phdrs.end()) return false; uint64_t HeaderSize = getHeaderSize(); if (HeaderSize <= Min || Script->hasPhdrsCommands()) { Min = alignDown(Min - HeaderSize, Config->MaxPageSize); Out::ElfHeader->Addr = Min; Out::ProgramHeaders->Addr = Min + Out::ElfHeader->Size; return true; } assert(FirstPTLoad->First == Out::ElfHeader); OutputSection *ActualFirst = nullptr; for (OutputSection *Sec : OutputSections) { if (Sec->FirstInPtLoad == Out::ElfHeader) { ActualFirst = Sec; break; } } if (ActualFirst) { for (OutputSection *Sec : OutputSections) if (Sec->FirstInPtLoad == Out::ElfHeader) Sec->FirstInPtLoad = ActualFirst; FirstPTLoad->First = ActualFirst; } else { Phdrs.erase(FirstPTLoad); } auto PhdrI = std::find_if(Phdrs.begin(), Phdrs.end(), [](const PhdrEntry &E) { return E.p_type == PT_PHDR; }); if (PhdrI != Phdrs.end()) Phdrs.erase(PhdrI); return false; } void LinkerScript::assignAddresses(std::vector &Phdrs) { // Assign addresses as instructed by linker script SECTIONS sub-commands. Dot = 0; ErrorOnMissingSection = true; switchTo(Aether); for (BaseCommand *Base : Opt.Commands) { if (auto *Cmd = dyn_cast(Base)) { assignSymbol(Cmd, false); continue; } if (auto *Cmd = dyn_cast(Base)) { Cmd->Expression(); continue; } auto *Cmd = cast(Base); assignOffsets(Cmd); } uint64_t MinVA = std::numeric_limits::max(); for (OutputSection *Sec : *OutputSections) { if (Sec->Flags & SHF_ALLOC) MinVA = std::min(MinVA, Sec->Addr); else Sec->Addr = 0; } allocateHeaders(Phdrs, *OutputSections, MinVA); } // Creates program headers as instructed by PHDRS linker script command. std::vector LinkerScript::createPhdrs() { std::vector Ret; // Process PHDRS and FILEHDR keywords because they are not // real output sections and cannot be added in the following loop. for (const PhdrsCommand &Cmd : Opt.PhdrsCommands) { Ret.emplace_back(Cmd.Type, Cmd.Flags == UINT_MAX ? PF_R : Cmd.Flags); PhdrEntry &Phdr = Ret.back(); if (Cmd.HasFilehdr) Phdr.add(Out::ElfHeader); if (Cmd.HasPhdrs) Phdr.add(Out::ProgramHeaders); if (Cmd.LMAExpr) { Phdr.p_paddr = Cmd.LMAExpr().getValue(); Phdr.HasLMA = true; } } // Add output sections to program headers. for (OutputSection *Sec : *OutputSections) { if (!(Sec->Flags & SHF_ALLOC)) break; // Assign headers specified by linker script for (size_t Id : getPhdrIndices(Sec)) { Ret[Id].add(Sec); if (Opt.PhdrsCommands[Id].Flags == UINT_MAX) Ret[Id].p_flags |= Sec->getPhdrFlags(); } } return Ret; } bool LinkerScript::ignoreInterpSection() { // Ignore .interp section in case we have PHDRS specification // and PT_INTERP isn't listed. if (Opt.PhdrsCommands.empty()) return false; for (PhdrsCommand &Cmd : Opt.PhdrsCommands) if (Cmd.Type == PT_INTERP) return false; return true; } OutputSectionCommand *LinkerScript::getCmd(OutputSection *Sec) const { auto I = SecToCommand.find(Sec); if (I == SecToCommand.end()) return nullptr; return I->second; } uint32_t OutputSectionCommand::getFiller() { if (Filler) return *Filler; if (Sec->Flags & SHF_EXECINSTR) return Target->TrapInstr; return 0; } static void writeInt(uint8_t *Buf, uint64_t Data, uint64_t Size) { if (Size == 1) *Buf = Data; else if (Size == 2) write16(Buf, Data, Config->Endianness); else if (Size == 4) write32(Buf, Data, Config->Endianness); else if (Size == 8) write64(Buf, Data, Config->Endianness); else llvm_unreachable("unsupported Size argument"); } template void OutputSectionCommand::writeTo(uint8_t *Buf) { Sec->Loc = Buf; // We may have already rendered compressed content when using // -compress-debug-sections option. Write it together with header. if (!Sec->CompressedData.empty()) { memcpy(Buf, Sec->ZDebugHeader.data(), Sec->ZDebugHeader.size()); memcpy(Buf + Sec->ZDebugHeader.size(), Sec->CompressedData.data(), Sec->CompressedData.size()); return; } + + if (Sec->Type == SHT_NOBITS) + return; // Write leading padding. ArrayRef Sections = Sec->Sections; uint32_t Filler = getFiller(); if (Filler) fill(Buf, Sections.empty() ? Sec->Size : Sections[0]->OutSecOff, Filler); parallelForEachN(0, Sections.size(), [=](size_t I) { InputSection *IS = Sections[I]; IS->writeTo(Buf); // Fill gaps between sections. if (Filler) { uint8_t *Start = Buf + IS->OutSecOff + IS->getSize(); uint8_t *End; if (I + 1 == Sections.size()) End = Buf + Sec->Size; else End = Buf + Sections[I + 1]->OutSecOff; fill(Start, End - Start, Filler); } }); // Linker scripts may have BYTE()-family commands with which you // can write arbitrary bytes to the output. Process them if any. for (BaseCommand *Base : Commands) if (auto *Data = dyn_cast(Base)) writeInt(Buf + Data->Offset, Data->Expression().getValue(), Data->Size); } bool LinkerScript::hasLMA(OutputSection *Sec) { if (OutputSectionCommand *Cmd = getCmd(Sec)) if (Cmd->LMAExpr) return true; return false; } ExprValue LinkerScript::getSymbolValue(const Twine &Loc, StringRef S) { if (S == ".") return {CurOutSec, Dot - CurOutSec->Addr}; if (SymbolBody *B = findSymbol(S)) { if (auto *D = dyn_cast(B)) return {D->Section, D->Value}; if (auto *C = dyn_cast(B)) return {InX::Common, C->Offset}; } error(Loc + ": symbol not found: " + S); return 0; } bool LinkerScript::isDefined(StringRef S) { return findSymbol(S) != nullptr; } // Returns indices of ELF headers containing specific section. Each index is a // zero based number of ELF header listed within PHDRS {} script block. std::vector LinkerScript::getPhdrIndices(OutputSection *Sec) { if (OutputSectionCommand *Cmd = getCmd(Sec)) { std::vector Ret; for (StringRef PhdrName : Cmd->Phdrs) Ret.push_back(getPhdrIndex(Cmd->Location, PhdrName)); return Ret; } return {}; } size_t LinkerScript::getPhdrIndex(const Twine &Loc, StringRef PhdrName) { size_t I = 0; for (PhdrsCommand &Cmd : Opt.PhdrsCommands) { if (Cmd.Name == PhdrName) return I; ++I; } error(Loc + ": section header '" + PhdrName + "' is not listed in PHDRS"); return 0; } template void OutputSectionCommand::writeTo(uint8_t *Buf); template void OutputSectionCommand::writeTo(uint8_t *Buf); template void OutputSectionCommand::writeTo(uint8_t *Buf); template void OutputSectionCommand::writeTo(uint8_t *Buf); Index: vendor/lld/dist/ELF/LinkerScript.h =================================================================== --- vendor/lld/dist/ELF/LinkerScript.h (revision 319237) +++ vendor/lld/dist/ELF/LinkerScript.h (revision 319238) @@ -1,289 +1,294 @@ //===- LinkerScript.h -------------------------------------------*- C++ -*-===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #ifndef LLD_ELF_LINKER_SCRIPT_H #define LLD_ELF_LINKER_SCRIPT_H #include "Config.h" #include "Strings.h" #include "Writer.h" #include "lld/Core/LLVM.h" #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/DenseSet.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/MemoryBuffer.h" #include #include #include #include #include namespace lld { namespace elf { class DefinedCommon; class SymbolBody; class InputSectionBase; class InputSection; class OutputSection; class OutputSectionFactory; class InputSectionBase; class SectionBase; struct ExprValue { SectionBase *Sec; uint64_t Val; bool ForceAbsolute; + uint64_t Alignment = 1; + ExprValue(SectionBase *Sec, bool ForceAbsolute, uint64_t Val, + uint64_t Alignment) + : Sec(Sec), Val(Val), ForceAbsolute(ForceAbsolute), Alignment(Alignment) { + } ExprValue(SectionBase *Sec, bool ForceAbsolute, uint64_t Val) : Sec(Sec), Val(Val), ForceAbsolute(ForceAbsolute) {} ExprValue(SectionBase *Sec, uint64_t Val) : ExprValue(Sec, false, Val) {} ExprValue(uint64_t Val) : ExprValue(nullptr, Val) {} bool isAbsolute() const { return ForceAbsolute || Sec == nullptr; } uint64_t getValue() const; uint64_t getSecAddr() const; }; // This represents an expression in the linker script. // ScriptParser::readExpr reads an expression and returns an Expr. // Later, we evaluate the expression by calling the function. typedef std::function Expr; // This enum is used to implement linker script SECTIONS command. // https://sourceware.org/binutils/docs/ld/SECTIONS.html#SECTIONS enum SectionsCommandKind { AssignmentKind, // . = expr or = expr OutputSectionKind, InputSectionKind, AssertKind, // ASSERT(expr) BytesDataKind // BYTE(expr), SHORT(expr), LONG(expr) or QUAD(expr) }; struct BaseCommand { BaseCommand(int K) : Kind(K) {} int Kind; }; // This represents ". = " or " = ". struct SymbolAssignment : BaseCommand { SymbolAssignment(StringRef Name, Expr E, std::string Loc) : BaseCommand(AssignmentKind), Name(Name), Expression(E), Location(Loc) {} static bool classof(const BaseCommand *C); // The LHS of an expression. Name is either a symbol name or ".". StringRef Name; SymbolBody *Sym = nullptr; // The RHS of an expression. Expr Expression; // Command attributes for PROVIDE, HIDDEN and PROVIDE_HIDDEN. bool Provide = false; bool Hidden = false; // Holds file name and line number for error reporting. std::string Location; }; // Linker scripts allow additional constraints to be put on ouput sections. // If an output section is marked as ONLY_IF_RO, the section is created // only if its input sections are read-only. Likewise, an output section // with ONLY_IF_RW is created if all input sections are RW. enum class ConstraintKind { NoConstraint, ReadOnly, ReadWrite }; // This struct is used to represent the location and size of regions of // target memory. Instances of the struct are created by parsing the // MEMORY command. struct MemoryRegion { std::string Name; uint64_t Origin; uint64_t Length; uint64_t Offset; uint32_t Flags; uint32_t NegFlags; }; struct OutputSectionCommand : BaseCommand { OutputSectionCommand(StringRef Name) : BaseCommand(OutputSectionKind), Name(Name) {} static bool classof(const BaseCommand *C); OutputSection *Sec = nullptr; MemoryRegion *MemRegion = nullptr; StringRef Name; Expr AddrExpr; Expr AlignExpr; Expr LMAExpr; Expr SubalignExpr; std::vector Commands; std::vector Phdrs; llvm::Optional Filler; ConstraintKind Constraint = ConstraintKind::NoConstraint; std::string Location; std::string MemoryRegionName; template void writeTo(uint8_t *Buf); uint32_t getFiller(); }; // This struct represents one section match pattern in SECTIONS() command. // It can optionally have negative match pattern for EXCLUDED_FILE command. // Also it may be surrounded with SORT() command, so contains sorting rules. struct SectionPattern { SectionPattern(StringMatcher &&Pat1, StringMatcher &&Pat2) : ExcludedFilePat(Pat1), SectionPat(Pat2) {} StringMatcher ExcludedFilePat; StringMatcher SectionPat; SortSectionPolicy SortOuter; SortSectionPolicy SortInner; }; struct InputSectionDescription : BaseCommand { InputSectionDescription(StringRef FilePattern) : BaseCommand(InputSectionKind), FilePat(FilePattern) {} static bool classof(const BaseCommand *C); StringMatcher FilePat; // Input sections that matches at least one of SectionPatterns // will be associated with this InputSectionDescription. std::vector SectionPatterns; std::vector Sections; }; // Represents an ASSERT(). struct AssertCommand : BaseCommand { AssertCommand(Expr E) : BaseCommand(AssertKind), Expression(E) {} static bool classof(const BaseCommand *C); Expr Expression; }; // Represents BYTE(), SHORT(), LONG(), or QUAD(). struct BytesDataCommand : BaseCommand { BytesDataCommand(Expr E, unsigned Size) : BaseCommand(BytesDataKind), Expression(E), Size(Size) {} static bool classof(const BaseCommand *C); Expr Expression; unsigned Offset; unsigned Size; }; struct PhdrsCommand { StringRef Name; unsigned Type; bool HasFilehdr; bool HasPhdrs; unsigned Flags; Expr LMAExpr; }; // ScriptConfiguration holds linker script parse results. struct ScriptConfiguration { // Used to assign addresses to sections. std::vector Commands; // Used to assign sections to headers. std::vector PhdrsCommands; bool HasSections = false; // List of section patterns specified with KEEP commands. They will // be kept even if they are unused and --gc-sections is specified. std::vector KeptSections; // A map from memory region name to a memory region descriptor. llvm::DenseMap MemoryRegions; // A list of symbols referenced by the script. std::vector ReferencedSymbols; }; class LinkerScript final { llvm::DenseMap SecToCommand; void assignSymbol(SymbolAssignment *Cmd, bool InSec); void setDot(Expr E, const Twine &Loc, bool InSec); std::vector computeInputSections(const InputSectionDescription *); std::vector createInputSectionList(OutputSectionCommand &Cmd); std::vector getPhdrIndices(OutputSection *Sec); size_t getPhdrIndex(const Twine &Loc, StringRef PhdrName); MemoryRegion *findMemoryRegion(OutputSectionCommand *Cmd); void switchTo(OutputSection *Sec); uint64_t advance(uint64_t Size, unsigned Align); void output(InputSection *Sec); void process(BaseCommand &Base); OutputSection *Aether; bool ErrorOnMissingSection = false; uint64_t Dot; uint64_t ThreadBssOffset = 0; std::function LMAOffset; OutputSection *CurOutSec = nullptr; MemoryRegion *CurMemRegion = nullptr; public: OutputSectionCommand *getCmd(OutputSection *Sec) const; bool hasPhdrsCommands() { return !Opt.PhdrsCommands.empty(); } uint64_t getDot() { return Dot; } OutputSection *getOutputSection(const Twine &Loc, StringRef S); uint64_t getOutputSectionSize(StringRef S); void discard(ArrayRef V); ExprValue getSymbolValue(const Twine &Loc, StringRef S); bool isDefined(StringRef S); std::vector *OutputSections; void fabricateDefaultCommands(); void addOrphanSections(OutputSectionFactory &Factory); void removeEmptyCommands(); void adjustSectionsBeforeSorting(); void adjustSectionsAfterSorting(); std::vector createPhdrs(); bool ignoreInterpSection(); bool hasLMA(OutputSection *Sec); bool shouldKeep(InputSectionBase *S); void assignOffsets(OutputSectionCommand *Cmd); void placeOrphanSections(); void processNonSectionCommands(); void synchronize(); void assignAddresses(std::vector &Phdrs); void addSymbol(SymbolAssignment *Cmd); void processCommands(OutputSectionFactory &Factory); // Parsed linker script configurations are set to this struct. ScriptConfiguration Opt; }; extern LinkerScript *Script; } // end namespace elf } // end namespace lld #endif // LLD_ELF_LINKER_SCRIPT_H Index: vendor/lld/dist/ELF/MapFile.cpp =================================================================== --- vendor/lld/dist/ELF/MapFile.cpp (revision 319237) +++ vendor/lld/dist/ELF/MapFile.cpp (revision 319238) @@ -1,153 +1,150 @@ //===- MapFile.cpp --------------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file implements the -Map option. It shows lists in order and // hierarchically the output sections, input sections, input files and // symbol: // // Address Size Align Out In Symbol // 00201000 00000015 4 .text // 00201000 0000000e 4 test.o:(.text) // 0020100e 00000000 0 local // 00201005 00000000 0 f(int) // //===----------------------------------------------------------------------===// #include "MapFile.h" #include "InputFiles.h" #include "LinkerScript.h" #include "OutputSections.h" #include "Strings.h" #include "SymbolTable.h" #include "Threads.h" #include "llvm/Support/raw_ostream.h" using namespace llvm; using namespace llvm::object; using namespace lld; using namespace lld::elf; typedef DenseMap> SymbolMapTy; // Print out the first three columns of a line. template static void writeHeader(raw_ostream &OS, uint64_t Addr, uint64_t Size, uint64_t Align) { int W = ELFT::Is64Bits ? 16 : 8; OS << format("%0*llx %0*llx %5lld ", W, Addr, W, Size, Align); } static std::string indent(int Depth) { return std::string(Depth * 8, ' '); } // Returns a list of all symbols that we want to print out. template std::vector getSymbols() { std::vector V; for (elf::ObjectFile *File : Symtab::X->getObjectFiles()) for (SymbolBody *B : File->getSymbols()) if (B->File == File && !B->isSection()) if (auto *Sym = dyn_cast(B)) if (Sym->Section) V.push_back(Sym); return V; } // Returns a map from sections to their symbols. template SymbolMapTy getSectionSyms(ArrayRef Syms) { SymbolMapTy Ret; for (DefinedRegular *S : Syms) Ret[S->Section].push_back(S); // Sort symbols by address. We want to print out symbols in the // order in the output file rather than the order they appeared // in the input files. for (auto &It : Ret) { SmallVectorImpl &V = It.second; std::sort(V.begin(), V.end(), [](DefinedRegular *A, DefinedRegular *B) { return A->getVA() < B->getVA(); }); } return Ret; } // Construct a map from symbols to their stringified representations. // Demangling symbols (which is what toString() does) is slow, so // we do that in batch using parallel-for. template DenseMap getSymbolStrings(ArrayRef Syms) { std::vector Str(Syms.size()); parallelForEachN(0, Syms.size(), [&](size_t I) { raw_string_ostream OS(Str[I]); writeHeader(OS, Syms[I]->getVA(), Syms[I]->template getSize(), 0); OS << indent(2) << toString(*Syms[I]); }); DenseMap Ret; for (size_t I = 0, E = Syms.size(); I < E; ++I) Ret[Syms[I]] = std::move(Str[I]); return Ret; } template -void elf::writeMapFile(llvm::ArrayRef Script) { +void elf::writeMapFile(llvm::ArrayRef Script) { if (Config->MapFile.empty()) return; // Open a map file for writing. std::error_code EC; raw_fd_ostream OS(Config->MapFile, EC, sys::fs::F_None); if (EC) { error("cannot open " + Config->MapFile + ": " + EC.message()); return; } // Collect symbol info that we want to print out. std::vector Syms = getSymbols(); SymbolMapTy SectionSyms = getSectionSyms(Syms); DenseMap SymStr = getSymbolStrings(Syms); // Print out the header line. int W = ELFT::Is64Bits ? 16 : 8; OS << left_justify("Address", W) << ' ' << left_justify("Size", W) << " Align Out In Symbol\n"; // Print out file contents. - for (BaseCommand *Base : Script) { - auto *Cmd = dyn_cast(Base); - if (!Cmd) - continue; + for (OutputSectionCommand *Cmd : Script) { OutputSection *OSec = Cmd->Sec; writeHeader(OS, OSec->Addr, OSec->Size, OSec->Alignment); OS << OSec->Name << '\n'; // Dump symbols for each input section. for (BaseCommand *Base : Cmd->Commands) { auto *ISD = dyn_cast(Base); if (!ISD) continue; for (InputSection *IS : ISD->Sections) { writeHeader(OS, OSec->Addr + IS->OutSecOff, IS->getSize(), IS->Alignment); OS << indent(1) << toString(IS) << '\n'; for (DefinedRegular *Sym : SectionSyms[IS]) OS << SymStr[Sym] << '\n'; } } } } -template void elf::writeMapFile(ArrayRef); -template void elf::writeMapFile(ArrayRef); -template void elf::writeMapFile(ArrayRef); -template void elf::writeMapFile(ArrayRef); +template void elf::writeMapFile(ArrayRef); +template void elf::writeMapFile(ArrayRef); +template void elf::writeMapFile(ArrayRef); +template void elf::writeMapFile(ArrayRef); Index: vendor/lld/dist/ELF/MapFile.h =================================================================== --- vendor/lld/dist/ELF/MapFile.h (revision 319237) +++ vendor/lld/dist/ELF/MapFile.h (revision 319238) @@ -1,22 +1,23 @@ //===- MapFile.h ------------------------------------------------*- C++ -*-===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #ifndef LLD_ELF_MAPFILE_H #define LLD_ELF_MAPFILE_H #include namespace lld { namespace elf { -struct BaseCommand; -template void writeMapFile(llvm::ArrayRef Script); +struct OutputSectionCommand; +template +void writeMapFile(llvm::ArrayRef Script); } } #endif Index: vendor/lld/dist/ELF/OutputSections.cpp =================================================================== --- vendor/lld/dist/ELF/OutputSections.cpp (revision 319237) +++ vendor/lld/dist/ELF/OutputSections.cpp (revision 319238) @@ -1,444 +1,444 @@ //===- OutputSections.cpp -------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #include "OutputSections.h" #include "Config.h" #include "LinkerScript.h" #include "Memory.h" #include "Strings.h" #include "SymbolTable.h" #include "SyntheticSections.h" #include "Target.h" #include "Threads.h" #include "llvm/Support/Compression.h" #include "llvm/Support/Dwarf.h" #include "llvm/Support/MD5.h" #include "llvm/Support/MathExtras.h" #include "llvm/Support/SHA1.h" using namespace llvm; using namespace llvm::dwarf; using namespace llvm::object; using namespace llvm::support::endian; using namespace llvm::ELF; using namespace lld; using namespace lld::elf; uint8_t Out::First; OutputSection *Out::Opd; uint8_t *Out::OpdBuf; PhdrEntry *Out::TlsPhdr; OutputSection *Out::DebugInfo; OutputSection *Out::ElfHeader; OutputSection *Out::ProgramHeaders; OutputSection *Out::PreinitArray; OutputSection *Out::InitArray; OutputSection *Out::FiniArray; uint32_t OutputSection::getPhdrFlags() const { uint32_t Ret = PF_R; if (Flags & SHF_WRITE) Ret |= PF_W; if (Flags & SHF_EXECINSTR) Ret |= PF_X; return Ret; } template void OutputSection::writeHeaderTo(typename ELFT::Shdr *Shdr) { Shdr->sh_entsize = Entsize; Shdr->sh_addralign = Alignment; Shdr->sh_type = Type; Shdr->sh_offset = Offset; Shdr->sh_flags = Flags; Shdr->sh_info = Info; Shdr->sh_link = Link; Shdr->sh_addr = Addr; Shdr->sh_size = Size; Shdr->sh_name = ShName; } OutputSection::OutputSection(StringRef Name, uint32_t Type, uint64_t Flags) : SectionBase(Output, Name, Flags, /*Entsize*/ 0, /*Alignment*/ 1, Type, /*Info*/ 0, /*Link*/ 0), SectionIndex(INT_MAX) {} static bool compareByFilePosition(InputSection *A, InputSection *B) { // Synthetic doesn't have link order dependecy, stable_sort will keep it last if (A->kind() == InputSectionBase::Synthetic || B->kind() == InputSectionBase::Synthetic) return false; auto *LA = cast(A->getLinkOrderDep()); auto *LB = cast(B->getLinkOrderDep()); OutputSection *AOut = LA->OutSec; OutputSection *BOut = LB->OutSec; if (AOut != BOut) return AOut->SectionIndex < BOut->SectionIndex; return LA->OutSecOff < LB->OutSecOff; } // Compress section contents if this section contains debug info. template void OutputSection::maybeCompress() { typedef typename ELFT::Chdr Elf_Chdr; // Compress only DWARF debug sections. if (!Config->CompressDebugSections || (Flags & SHF_ALLOC) || !Name.startswith(".debug_")) return; // Create a section header. ZDebugHeader.resize(sizeof(Elf_Chdr)); auto *Hdr = reinterpret_cast(ZDebugHeader.data()); Hdr->ch_type = ELFCOMPRESS_ZLIB; Hdr->ch_size = Size; Hdr->ch_addralign = Alignment; // Write section contents to a temporary buffer and compress it. std::vector Buf(Size); Script->getCmd(this)->writeTo(Buf.data()); if (Error E = zlib::compress(toStringRef(Buf), CompressedData)) fatal("compress failed: " + llvm::toString(std::move(E))); // Update section headers. Size = sizeof(Elf_Chdr) + CompressedData.size(); Flags |= SHF_COMPRESSED; } template static void finalizeShtGroup(OutputSection *Sec) { // sh_link field for SHT_GROUP sections should contain the section index of // the symbol table. Sec->Link = InX::SymTab->OutSec->SectionIndex; - // sh_link then contain index of an entry in symbol table section which + // sh_info then contain index of an entry in symbol table section which // provides signature of the section group. elf::ObjectFile *Obj = Sec->Sections[0]->getFile(); assert(Config->Relocatable && Sec->Sections.size() == 1); ArrayRef Symbols = Obj->getSymbols(); Sec->Info = InX::SymTab->getSymbolIndex(Symbols[Sec->Sections[0]->Info - 1]); } template void OutputSection::finalize() { if ((this->Flags & SHF_LINK_ORDER) && !this->Sections.empty()) { std::sort(Sections.begin(), Sections.end(), compareByFilePosition); assignOffsets(); // We must preserve the link order dependency of sections with the // SHF_LINK_ORDER flag. The dependency is indicated by the sh_link field. We // need to translate the InputSection sh_link to the OutputSection sh_link, // all InputSections in the OutputSection have the same dependency. if (auto *D = this->Sections.front()->getLinkOrderDep()) this->Link = D->OutSec->SectionIndex; } uint32_t Type = this->Type; if (Type == SHT_GROUP) { finalizeShtGroup(this); return; } if (!Config->CopyRelocs || (Type != SHT_RELA && Type != SHT_REL)) return; InputSection *First = Sections[0]; if (isa(First)) return; this->Link = InX::SymTab->OutSec->SectionIndex; // sh_info for SHT_REL[A] sections should contain the section header index of // the section to which the relocation applies. InputSectionBase *S = First->getRelocatedSection(); this->Info = S->OutSec->SectionIndex; } static uint64_t updateOffset(uint64_t Off, InputSection *S) { Off = alignTo(Off, S->Alignment); S->OutSecOff = Off; return Off + S->getSize(); } void OutputSection::addSection(InputSection *S) { assert(S->Live); Sections.push_back(S); S->OutSec = this; this->updateAlignment(S->Alignment); // The actual offsets will be computed by assignAddresses. For now, use // crude approximation so that it is at least easy for other code to know the // section order. It is also used to calculate the output section size early // for compressed debug sections. this->Size = updateOffset(Size, S); // If this section contains a table of fixed-size entries, sh_entsize // holds the element size. Consequently, if this contains two or more // input sections, all of them must have the same sh_entsize. However, // you can put different types of input sections into one output // sectin by using linker scripts. I don't know what to do here. // Probably we sholuld handle that as an error. But for now we just // pick the largest sh_entsize. this->Entsize = std::max(this->Entsize, S->Entsize); } // This function is called after we sort input sections // and scan relocations to setup sections' offsets. void OutputSection::assignOffsets() { uint64_t Off = 0; for (InputSection *S : Sections) Off = updateOffset(Off, S); this->Size = Off; } void OutputSection::sort(std::function Order) { typedef std::pair Pair; auto Comp = [](const Pair &A, const Pair &B) { return A.first < B.first; }; std::vector V; for (InputSection *S : Sections) V.push_back({Order(S), S}); std::stable_sort(V.begin(), V.end(), Comp); Sections.clear(); for (Pair &P : V) Sections.push_back(P.second); } // Sorts input sections by section name suffixes, so that .foo.N comes // before .foo.M if N < M. Used to sort .{init,fini}_array.N sections. // We want to keep the original order if the priorities are the same // because the compiler keeps the original initialization order in a // translation unit and we need to respect that. // For more detail, read the section of the GCC's manual about init_priority. void OutputSection::sortInitFini() { // Sort sections by priority. sort([](InputSectionBase *S) { return getPriority(S->Name); }); } // Returns true if S matches /Filename.?\.o$/. static bool isCrtBeginEnd(StringRef S, StringRef Filename) { if (!S.endswith(".o")) return false; S = S.drop_back(2); if (S.endswith(Filename)) return true; return !S.empty() && S.drop_back().endswith(Filename); } static bool isCrtbegin(StringRef S) { return isCrtBeginEnd(S, "crtbegin"); } static bool isCrtend(StringRef S) { return isCrtBeginEnd(S, "crtend"); } // .ctors and .dtors are sorted by this priority from highest to lowest. // // 1. The section was contained in crtbegin (crtbegin contains // some sentinel value in its .ctors and .dtors so that the runtime // can find the beginning of the sections.) // // 2. The section has an optional priority value in the form of ".ctors.N" // or ".dtors.N" where N is a number. Unlike .{init,fini}_array, // they are compared as string rather than number. // // 3. The section is just ".ctors" or ".dtors". // // 4. The section was contained in crtend, which contains an end marker. // // In an ideal world, we don't need this function because .init_array and // .ctors are duplicate features (and .init_array is newer.) However, there // are too many real-world use cases of .ctors, so we had no choice to // support that with this rather ad-hoc semantics. static bool compCtors(const InputSection *A, const InputSection *B) { bool BeginA = isCrtbegin(A->File->getName()); bool BeginB = isCrtbegin(B->File->getName()); if (BeginA != BeginB) return BeginA; bool EndA = isCrtend(A->File->getName()); bool EndB = isCrtend(B->File->getName()); if (EndA != EndB) return EndB; StringRef X = A->Name; StringRef Y = B->Name; assert(X.startswith(".ctors") || X.startswith(".dtors")); assert(Y.startswith(".ctors") || Y.startswith(".dtors")); X = X.substr(6); Y = Y.substr(6); if (X.empty() && Y.empty()) return false; return X < Y; } // Sorts input sections by the special rules for .ctors and .dtors. // Unfortunately, the rules are different from the one for .{init,fini}_array. // Read the comment above. void OutputSection::sortCtorsDtors() { std::stable_sort(Sections.begin(), Sections.end(), compCtors); } static SectionKey createKey(InputSectionBase *C, StringRef OutsecName) { // The ELF spec just says // ---------------------------------------------------------------- // In the first phase, input sections that match in name, type and // attribute flags should be concatenated into single sections. // ---------------------------------------------------------------- // // However, it is clear that at least some flags have to be ignored for // section merging. At the very least SHF_GROUP and SHF_COMPRESSED have to be // ignored. We should not have two output .text sections just because one was // in a group and another was not for example. // // It also seems that that wording was a late addition and didn't get the // necessary scrutiny. // // Merging sections with different flags is expected by some users. One // reason is that if one file has // // int *const bar __attribute__((section(".foo"))) = (int *)0; // // gcc with -fPIC will produce a read only .foo section. But if another // file has // // int zed; // int *const bar __attribute__((section(".foo"))) = (int *)&zed; // // gcc with -fPIC will produce a read write section. // // Last but not least, when using linker script the merge rules are forced by // the script. Unfortunately, linker scripts are name based. This means that // expressions like *(.foo*) can refer to multiple input sections with // different flags. We cannot put them in different output sections or we // would produce wrong results for // // start = .; *(.foo.*) end = .; *(.bar) // // and a mapping of .foo1 and .bar1 to one section and .foo2 and .bar2 to // another. The problem is that there is no way to layout those output // sections such that the .foo sections are the only thing between the start // and end symbols. // // Given the above issues, we instead merge sections by name and error on // incompatible types and flags. uint32_t Alignment = 0; uint64_t Flags = 0; if (Config->Relocatable && (C->Flags & SHF_MERGE)) { Alignment = std::max(C->Alignment, C->Entsize); Flags = C->Flags & (SHF_MERGE | SHF_STRINGS); } return SectionKey{OutsecName, Flags, Alignment}; } OutputSectionFactory::OutputSectionFactory( std::vector &OutputSections) : OutputSections(OutputSections) {} static uint64_t getIncompatibleFlags(uint64_t Flags) { return Flags & (SHF_ALLOC | SHF_TLS); } // We allow sections of types listed below to merged into a // single progbits section. This is typically done by linker // scripts. Merging nobits and progbits will force disk space // to be allocated for nobits sections. Other ones don't require // any special treatment on top of progbits, so there doesn't // seem to be a harm in merging them. static bool canMergeToProgbits(unsigned Type) { return Type == SHT_NOBITS || Type == SHT_PROGBITS || Type == SHT_INIT_ARRAY || Type == SHT_PREINIT_ARRAY || Type == SHT_FINI_ARRAY || Type == SHT_NOTE; } static void reportDiscarded(InputSectionBase *IS) { if (!Config->PrintGcSections) return; message("removing unused section from '" + IS->Name + "' in file '" + IS->File->getName()); } void OutputSectionFactory::addInputSec(InputSectionBase *IS, StringRef OutsecName) { SectionKey Key = createKey(IS, OutsecName); OutputSection *&Sec = Map[Key]; return addInputSec(IS, OutsecName, Sec); } void OutputSectionFactory::addInputSec(InputSectionBase *IS, StringRef OutsecName, OutputSection *&Sec) { if (!IS->Live) { reportDiscarded(IS); return; } uint64_t Flags = IS->Flags; if (!Config->Relocatable) Flags &= ~(uint64_t)SHF_GROUP; if (Sec) { if (getIncompatibleFlags(Sec->Flags) != getIncompatibleFlags(IS->Flags)) error("incompatible section flags for " + Sec->Name + "\n>>> " + toString(IS) + ": 0x" + utohexstr(IS->Flags) + "\n>>> output section " + Sec->Name + ": 0x" + utohexstr(Sec->Flags)); if (Sec->Type != IS->Type) { if (canMergeToProgbits(Sec->Type) && canMergeToProgbits(IS->Type)) Sec->Type = SHT_PROGBITS; else error("section type mismatch for " + IS->Name + "\n>>> " + toString(IS) + ": " + getELFSectionTypeName(Config->EMachine, IS->Type) + "\n>>> output section " + Sec->Name + ": " + getELFSectionTypeName(Config->EMachine, Sec->Type)); } Sec->Flags |= Flags; } else { Sec = make(OutsecName, IS->Type, Flags); OutputSections.push_back(Sec); } Sec->addSection(cast(IS)); } OutputSectionFactory::~OutputSectionFactory() {} SectionKey DenseMapInfo::getEmptyKey() { return SectionKey{DenseMapInfo::getEmptyKey(), 0, 0}; } SectionKey DenseMapInfo::getTombstoneKey() { return SectionKey{DenseMapInfo::getTombstoneKey(), 0, 0}; } unsigned DenseMapInfo::getHashValue(const SectionKey &Val) { return hash_combine(Val.Name, Val.Flags, Val.Alignment); } bool DenseMapInfo::isEqual(const SectionKey &LHS, const SectionKey &RHS) { return DenseMapInfo::isEqual(LHS.Name, RHS.Name) && LHS.Flags == RHS.Flags && LHS.Alignment == RHS.Alignment; } uint64_t elf::getHeaderSize() { if (Config->OFormatBinary) return 0; return Out::ElfHeader->Size + Out::ProgramHeaders->Size; } template void OutputSection::writeHeaderTo(ELF32LE::Shdr *Shdr); template void OutputSection::writeHeaderTo(ELF32BE::Shdr *Shdr); template void OutputSection::writeHeaderTo(ELF64LE::Shdr *Shdr); template void OutputSection::writeHeaderTo(ELF64BE::Shdr *Shdr); template void OutputSection::finalize(); template void OutputSection::finalize(); template void OutputSection::finalize(); template void OutputSection::finalize(); template void OutputSection::maybeCompress(); template void OutputSection::maybeCompress(); template void OutputSection::maybeCompress(); template void OutputSection::maybeCompress(); Index: vendor/lld/dist/ELF/ScriptParser.cpp =================================================================== --- vendor/lld/dist/ELF/ScriptParser.cpp (revision 319237) +++ vendor/lld/dist/ELF/ScriptParser.cpp (revision 319238) @@ -1,1189 +1,1193 @@ //===- ScriptParser.cpp ---------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file contains a recursive-descendent parser for linker scripts. // Parsed results are stored to Config and Script global objects. // //===----------------------------------------------------------------------===// #include "ScriptParser.h" #include "Config.h" #include "Driver.h" #include "InputSection.h" #include "LinkerScript.h" #include "Memory.h" #include "OutputSections.h" #include "ScriptLexer.h" #include "Symbols.h" #include "Target.h" #include "llvm/ADT/SmallString.h" #include "llvm/ADT/StringRef.h" #include "llvm/ADT/StringSwitch.h" #include "llvm/Support/Casting.h" #include "llvm/Support/ELF.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/Path.h" #include #include #include using namespace llvm; using namespace llvm::ELF; using namespace llvm::support::endian; using namespace lld; using namespace lld::elf; static bool isUnderSysroot(StringRef Path); namespace { class ScriptParser final : ScriptLexer { public: ScriptParser(MemoryBufferRef MB) : ScriptLexer(MB), IsUnderSysroot(isUnderSysroot(MB.getBufferIdentifier())) {} void readLinkerScript(); void readVersionScript(); void readDynamicList(); private: void addFile(StringRef Path); void readAsNeeded(); void readEntry(); void readExtern(); void readGroup(); void readInclude(); void readMemory(); void readOutput(); void readOutputArch(); void readOutputFormat(); void readPhdrs(); void readSearchDir(); void readSections(); void readVersion(); void readVersionScriptCommand(); SymbolAssignment *readAssignment(StringRef Name); BytesDataCommand *readBytesDataCommand(StringRef Tok); uint32_t readFill(); uint32_t parseFill(StringRef Tok); OutputSectionCommand *readOutputSectionDescription(StringRef OutSec); std::vector readOutputSectionPhdrs(); InputSectionDescription *readInputSectionDescription(StringRef Tok); StringMatcher readFilePatterns(); std::vector readInputSectionsList(); InputSectionDescription *readInputSectionRules(StringRef FilePattern); unsigned readPhdrType(); SortSectionPolicy readSortKind(); SymbolAssignment *readProvideHidden(bool Provide, bool Hidden); SymbolAssignment *readProvideOrAssignment(StringRef Tok); void readSort(); AssertCommand *readAssert(); Expr readAssertExpr(); uint64_t readMemoryAssignment(StringRef, StringRef, StringRef); std::pair readMemoryAttributes(); Expr readExpr(); Expr readExpr1(Expr Lhs, int MinPrec); StringRef readParenLiteral(); Expr readPrimary(); Expr readTernary(Expr Cond); Expr readParenExpr(); // For parsing version script. std::vector readVersionExtern(); void readAnonymousDeclaration(); void readVersionDeclaration(StringRef VerStr); std::pair, std::vector> readSymbols(); bool IsUnderSysroot; }; } // namespace static bool isUnderSysroot(StringRef Path) { if (Config->Sysroot == "") return false; for (; !Path.empty(); Path = sys::path::parent_path(Path)) if (sys::fs::equivalent(Config->Sysroot, Path)) return true; return false; } // Some operations only support one non absolute value. Move the // absolute one to the right hand side for convenience. static void moveAbsRight(ExprValue &A, ExprValue &B) { if (A.isAbsolute()) std::swap(A, B); if (!B.isAbsolute()) error("At least one side of the expression must be absolute"); } static ExprValue add(ExprValue A, ExprValue B) { moveAbsRight(A, B); return {A.Sec, A.ForceAbsolute, A.Val + B.getValue()}; } static ExprValue sub(ExprValue A, ExprValue B) { return {A.Sec, A.Val - B.getValue()}; } static ExprValue mul(ExprValue A, ExprValue B) { return A.getValue() * B.getValue(); } static ExprValue div(ExprValue A, ExprValue B) { if (uint64_t BV = B.getValue()) return A.getValue() / BV; error("division by zero"); return 0; } static ExprValue bitAnd(ExprValue A, ExprValue B) { moveAbsRight(A, B); return {A.Sec, A.ForceAbsolute, (A.getValue() & B.getValue()) - A.getSecAddr()}; } static ExprValue bitOr(ExprValue A, ExprValue B) { moveAbsRight(A, B); return {A.Sec, A.ForceAbsolute, (A.getValue() | B.getValue()) - A.getSecAddr()}; } void ScriptParser::readDynamicList() { expect("{"); readAnonymousDeclaration(); if (!atEOF()) setError("EOF expected, but got " + next()); } void ScriptParser::readVersionScript() { readVersionScriptCommand(); if (!atEOF()) setError("EOF expected, but got " + next()); } void ScriptParser::readVersionScriptCommand() { if (consume("{")) { readAnonymousDeclaration(); return; } while (!atEOF() && !Error && peek() != "}") { StringRef VerStr = next(); if (VerStr == "{") { setError("anonymous version definition is used in " "combination with other version definitions"); return; } expect("{"); readVersionDeclaration(VerStr); } } void ScriptParser::readVersion() { expect("{"); readVersionScriptCommand(); expect("}"); } void ScriptParser::readLinkerScript() { while (!atEOF()) { StringRef Tok = next(); if (Tok == ";") continue; if (Tok == "ASSERT") { Script->Opt.Commands.push_back(readAssert()); } else if (Tok == "ENTRY") { readEntry(); } else if (Tok == "EXTERN") { readExtern(); } else if (Tok == "GROUP" || Tok == "INPUT") { readGroup(); } else if (Tok == "INCLUDE") { readInclude(); } else if (Tok == "MEMORY") { readMemory(); } else if (Tok == "OUTPUT") { readOutput(); } else if (Tok == "OUTPUT_ARCH") { readOutputArch(); } else if (Tok == "OUTPUT_FORMAT") { readOutputFormat(); } else if (Tok == "PHDRS") { readPhdrs(); } else if (Tok == "SEARCH_DIR") { readSearchDir(); } else if (Tok == "SECTIONS") { readSections(); } else if (Tok == "VERSION") { readVersion(); } else if (SymbolAssignment *Cmd = readProvideOrAssignment(Tok)) { Script->Opt.Commands.push_back(Cmd); } else { setError("unknown directive: " + Tok); } } } void ScriptParser::addFile(StringRef S) { if (IsUnderSysroot && S.startswith("/")) { SmallString<128> PathData; StringRef Path = (Config->Sysroot + S).toStringRef(PathData); if (sys::fs::exists(Path)) { Driver->addFile(Saver.save(Path), /*WithLOption=*/false); return; } } if (sys::path::is_absolute(S)) { Driver->addFile(S, /*WithLOption=*/false); } else if (S.startswith("=")) { if (Config->Sysroot.empty()) Driver->addFile(S.substr(1), /*WithLOption=*/false); else Driver->addFile(Saver.save(Config->Sysroot + "/" + S.substr(1)), /*WithLOption=*/false); } else if (S.startswith("-l")) { Driver->addLibrary(S.substr(2)); } else if (sys::fs::exists(S)) { Driver->addFile(S, /*WithLOption=*/false); } else { if (Optional Path = findFromSearchPaths(S)) Driver->addFile(Saver.save(*Path), /*WithLOption=*/true); else setError("unable to find " + S); } } void ScriptParser::readAsNeeded() { expect("("); bool Orig = Config->AsNeeded; Config->AsNeeded = true; while (!Error && !consume(")")) addFile(unquote(next())); Config->AsNeeded = Orig; } void ScriptParser::readEntry() { // -e takes predecence over ENTRY(). expect("("); StringRef Tok = next(); if (Config->Entry.empty()) Config->Entry = Tok; expect(")"); } void ScriptParser::readExtern() { expect("("); while (!Error && !consume(")")) Config->Undefined.push_back(next()); } void ScriptParser::readGroup() { expect("("); while (!Error && !consume(")")) { if (consume("AS_NEEDED")) readAsNeeded(); else addFile(unquote(next())); } } void ScriptParser::readInclude() { StringRef Tok = unquote(next()); // https://sourceware.org/binutils/docs/ld/File-Commands.html: // The file will be searched for in the current directory, and in any // directory specified with the -L option. if (sys::fs::exists(Tok)) { if (Optional MB = readFile(Tok)) tokenize(*MB); return; } if (Optional Path = findFromSearchPaths(Tok)) { if (Optional MB = readFile(*Path)) tokenize(*MB); return; } setError("cannot open " + Tok); } void ScriptParser::readOutput() { // -o takes predecence over OUTPUT(). expect("("); StringRef Tok = next(); if (Config->OutputFile.empty()) Config->OutputFile = unquote(Tok); expect(")"); } void ScriptParser::readOutputArch() { // OUTPUT_ARCH is ignored for now. expect("("); while (!Error && !consume(")")) skip(); } void ScriptParser::readOutputFormat() { // Error checking only for now. expect("("); skip(); if (consume(")")) return; expect(","); skip(); expect(","); skip(); expect(")"); } void ScriptParser::readPhdrs() { expect("{"); while (!Error && !consume("}")) { Script->Opt.PhdrsCommands.push_back( {next(), PT_NULL, false, false, UINT_MAX, nullptr}); PhdrsCommand &PhdrCmd = Script->Opt.PhdrsCommands.back(); PhdrCmd.Type = readPhdrType(); while (!Error && !consume(";")) { if (consume("FILEHDR")) PhdrCmd.HasFilehdr = true; else if (consume("PHDRS")) PhdrCmd.HasPhdrs = true; else if (consume("AT")) PhdrCmd.LMAExpr = readParenExpr(); else if (consume("FLAGS")) PhdrCmd.Flags = readParenExpr()().getValue(); else setError("unexpected header attribute: " + next()); } } } void ScriptParser::readSearchDir() { expect("("); StringRef Tok = next(); if (!Config->Nostdlib) Config->SearchPaths.push_back(unquote(Tok)); expect(")"); } void ScriptParser::readSections() { Script->Opt.HasSections = true; // -no-rosegment is used to avoid placing read only non-executable sections in // their own segment. We do the same if SECTIONS command is present in linker // script. See comment for computeFlags(). Config->SingleRoRx = true; expect("{"); while (!Error && !consume("}")) { StringRef Tok = next(); BaseCommand *Cmd = readProvideOrAssignment(Tok); if (!Cmd) { if (Tok == "ASSERT") Cmd = readAssert(); else Cmd = readOutputSectionDescription(Tok); } Script->Opt.Commands.push_back(Cmd); } } static int precedence(StringRef Op) { return StringSwitch(Op) .Cases("*", "/", 5) .Cases("+", "-", 4) .Cases("<<", ">>", 3) .Cases("<", "<=", ">", ">=", "==", "!=", 2) .Cases("&", "|", 1) .Default(-1); } StringMatcher ScriptParser::readFilePatterns() { std::vector V; while (!Error && !consume(")")) V.push_back(next()); return StringMatcher(V); } SortSectionPolicy ScriptParser::readSortKind() { if (consume("SORT") || consume("SORT_BY_NAME")) return SortSectionPolicy::Name; if (consume("SORT_BY_ALIGNMENT")) return SortSectionPolicy::Alignment; if (consume("SORT_BY_INIT_PRIORITY")) return SortSectionPolicy::Priority; if (consume("SORT_NONE")) return SortSectionPolicy::None; return SortSectionPolicy::Default; } // Reads SECTIONS command contents in the following form: // // ::= * // ::= ? // ::= "EXCLUDE_FILE" "(" + ")" // // For example, // // *(.foo EXCLUDE_FILE (a.o) .bar EXCLUDE_FILE (b.o) .baz) // // is parsed as ".foo", ".bar" with "a.o", and ".baz" with "b.o". // The semantics of that is section .foo in any file, section .bar in // any file but a.o, and section .baz in any file but b.o. std::vector ScriptParser::readInputSectionsList() { std::vector Ret; while (!Error && peek() != ")") { StringMatcher ExcludeFilePat; if (consume("EXCLUDE_FILE")) { expect("("); ExcludeFilePat = readFilePatterns(); } std::vector V; while (!Error && peek() != ")" && peek() != "EXCLUDE_FILE") V.push_back(next()); if (!V.empty()) Ret.push_back({std::move(ExcludeFilePat), StringMatcher(V)}); else setError("section pattern is expected"); } return Ret; } // Reads contents of "SECTIONS" directive. That directive contains a // list of glob patterns for input sections. The grammar is as follows. // // ::= // | "(" ")" // | "(" "(" ")" ")" // // ::= "SORT" | "SORT_BY_NAME" | "SORT_BY_ALIGNMENT" // | "SORT_BY_INIT_PRIORITY" | "SORT_NONE" // // is parsed by readInputSectionsList(). InputSectionDescription * ScriptParser::readInputSectionRules(StringRef FilePattern) { auto *Cmd = make(FilePattern); expect("("); while (!Error && !consume(")")) { SortSectionPolicy Outer = readSortKind(); SortSectionPolicy Inner = SortSectionPolicy::Default; std::vector V; if (Outer != SortSectionPolicy::Default) { expect("("); Inner = readSortKind(); if (Inner != SortSectionPolicy::Default) { expect("("); V = readInputSectionsList(); expect(")"); } else { V = readInputSectionsList(); } expect(")"); } else { V = readInputSectionsList(); } for (SectionPattern &Pat : V) { Pat.SortInner = Inner; Pat.SortOuter = Outer; } std::move(V.begin(), V.end(), std::back_inserter(Cmd->SectionPatterns)); } return Cmd; } InputSectionDescription * ScriptParser::readInputSectionDescription(StringRef Tok) { // Input section wildcard can be surrounded by KEEP. // https://sourceware.org/binutils/docs/ld/Input-Section-Keep.html#Input-Section-Keep if (Tok == "KEEP") { expect("("); StringRef FilePattern = next(); InputSectionDescription *Cmd = readInputSectionRules(FilePattern); expect(")"); Script->Opt.KeptSections.push_back(Cmd); return Cmd; } return readInputSectionRules(Tok); } void ScriptParser::readSort() { expect("("); expect("CONSTRUCTORS"); expect(")"); } AssertCommand *ScriptParser::readAssert() { return make(readAssertExpr()); } Expr ScriptParser::readAssertExpr() { expect("("); Expr E = readExpr(); expect(","); StringRef Msg = unquote(next()); expect(")"); return [=] { if (!E().getValue()) error(Msg); return Script->getDot(); }; } // Reads a FILL(expr) command. We handle the FILL command as an // alias for =fillexp section attribute, which is different from // what GNU linkers do. // https://sourceware.org/binutils/docs/ld/Output-Section-Data.html uint32_t ScriptParser::readFill() { expect("("); uint32_t V = parseFill(next()); expect(")"); return V; } OutputSectionCommand * ScriptParser::readOutputSectionDescription(StringRef OutSec) { OutputSectionCommand *Cmd = make(OutSec); Cmd->Location = getCurrentLocation(); // Read an address expression. // https://sourceware.org/binutils/docs/ld/Output-Section-Address.html if (peek() != ":") Cmd->AddrExpr = readExpr(); expect(":"); if (consume("AT")) Cmd->LMAExpr = readParenExpr(); if (consume("ALIGN")) Cmd->AlignExpr = readParenExpr(); if (consume("SUBALIGN")) Cmd->SubalignExpr = readParenExpr(); // Parse constraints. if (consume("ONLY_IF_RO")) Cmd->Constraint = ConstraintKind::ReadOnly; if (consume("ONLY_IF_RW")) Cmd->Constraint = ConstraintKind::ReadWrite; expect("{"); while (!Error && !consume("}")) { StringRef Tok = next(); if (Tok == ";") { // Empty commands are allowed. Do nothing here. } else if (SymbolAssignment *Assign = readProvideOrAssignment(Tok)) { Cmd->Commands.push_back(Assign); } else if (BytesDataCommand *Data = readBytesDataCommand(Tok)) { Cmd->Commands.push_back(Data); } else if (Tok == "ASSERT") { Cmd->Commands.push_back(readAssert()); expect(";"); } else if (Tok == "CONSTRUCTORS") { // CONSTRUCTORS is a keyword to make the linker recognize C++ ctors/dtors // by name. This is for very old file formats such as ECOFF/XCOFF. // For ELF, we should ignore. } else if (Tok == "FILL") { Cmd->Filler = readFill(); } else if (Tok == "SORT") { readSort(); } else if (peek() == "(") { Cmd->Commands.push_back(readInputSectionDescription(Tok)); } else { setError("unknown command " + Tok); } } if (consume(">")) Cmd->MemoryRegionName = next(); Cmd->Phdrs = readOutputSectionPhdrs(); if (consume("=")) Cmd->Filler = parseFill(next()); else if (peek().startswith("=")) Cmd->Filler = parseFill(next().drop_front()); // Consume optional comma following output section command. consume(","); return Cmd; } // Parses a given string as a octal/decimal/hexadecimal number and // returns it as a big-endian number. Used for `=`. // https://sourceware.org/binutils/docs/ld/Output-Section-Fill.html // // When reading a hexstring, ld.bfd handles it as a blob of arbitrary // size, while ld.gold always handles it as a 32-bit big-endian number. // We are compatible with ld.gold because it's easier to implement. uint32_t ScriptParser::parseFill(StringRef Tok) { uint32_t V = 0; if (!to_integer(Tok, V)) setError("invalid filler expression: " + Tok); uint32_t Buf; write32be(&Buf, V); return Buf; } SymbolAssignment *ScriptParser::readProvideHidden(bool Provide, bool Hidden) { expect("("); SymbolAssignment *Cmd = readAssignment(next()); Cmd->Provide = Provide; Cmd->Hidden = Hidden; expect(")"); expect(";"); return Cmd; } SymbolAssignment *ScriptParser::readProvideOrAssignment(StringRef Tok) { SymbolAssignment *Cmd = nullptr; if (peek() == "=" || peek() == "+=") { Cmd = readAssignment(Tok); expect(";"); } else if (Tok == "PROVIDE") { Cmd = readProvideHidden(true, false); } else if (Tok == "HIDDEN") { Cmd = readProvideHidden(false, true); } else if (Tok == "PROVIDE_HIDDEN") { Cmd = readProvideHidden(true, true); } return Cmd; } SymbolAssignment *ScriptParser::readAssignment(StringRef Name) { StringRef Op = next(); assert(Op == "=" || Op == "+="); Expr E = readExpr(); if (Op == "+=") { std::string Loc = getCurrentLocation(); E = [=] { return add(Script->getSymbolValue(Loc, Name), E()); }; } return make(Name, E, getCurrentLocation()); } // This is an operator-precedence parser to parse a linker // script expression. Expr ScriptParser::readExpr() { // Our lexer is context-aware. Set the in-expression bit so that // they apply different tokenization rules. bool Orig = InExpr; InExpr = true; Expr E = readExpr1(readPrimary(), 0); InExpr = Orig; return E; } static Expr combine(StringRef Op, Expr L, Expr R) { if (Op == "+") return [=] { return add(L(), R()); }; if (Op == "-") return [=] { return sub(L(), R()); }; if (Op == "*") return [=] { return mul(L(), R()); }; if (Op == "/") return [=] { return div(L(), R()); }; if (Op == "<<") return [=] { return L().getValue() << R().getValue(); }; if (Op == ">>") return [=] { return L().getValue() >> R().getValue(); }; if (Op == "<") return [=] { return L().getValue() < R().getValue(); }; if (Op == ">") return [=] { return L().getValue() > R().getValue(); }; if (Op == ">=") return [=] { return L().getValue() >= R().getValue(); }; if (Op == "<=") return [=] { return L().getValue() <= R().getValue(); }; if (Op == "==") return [=] { return L().getValue() == R().getValue(); }; if (Op == "!=") return [=] { return L().getValue() != R().getValue(); }; if (Op == "&") return [=] { return bitAnd(L(), R()); }; if (Op == "|") return [=] { return bitOr(L(), R()); }; llvm_unreachable("invalid operator"); } // This is a part of the operator-precedence parser. This function // assumes that the remaining token stream starts with an operator. Expr ScriptParser::readExpr1(Expr Lhs, int MinPrec) { while (!atEOF() && !Error) { // Read an operator and an expression. if (consume("?")) return readTernary(Lhs); StringRef Op1 = peek(); if (precedence(Op1) < MinPrec) break; skip(); Expr Rhs = readPrimary(); // Evaluate the remaining part of the expression first if the // next operator has greater precedence than the previous one. // For example, if we have read "+" and "3", and if the next // operator is "*", then we'll evaluate 3 * ... part first. while (!atEOF()) { StringRef Op2 = peek(); if (precedence(Op2) <= precedence(Op1)) break; Rhs = readExpr1(Rhs, precedence(Op2)); } Lhs = combine(Op1, Lhs, Rhs); } return Lhs; } uint64_t static getConstant(StringRef S) { if (S == "COMMONPAGESIZE") return Target->PageSize; if (S == "MAXPAGESIZE") return Config->MaxPageSize; error("unknown constant: " + S); return 0; } // Parses Tok as an integer. It recognizes hexadecimal (prefixed with // "0x" or suffixed with "H") and decimal numbers. Decimal numbers may // have "K" (Ki) or "M" (Mi) suffixes. static Optional parseInt(StringRef Tok) { // Negative number if (Tok.startswith("-")) { if (Optional Val = parseInt(Tok.substr(1))) return -*Val; return None; } // Hexadecimal uint64_t Val; if (Tok.startswith_lower("0x") && to_integer(Tok.substr(2), Val, 16)) return Val; if (Tok.endswith_lower("H") && to_integer(Tok.drop_back(), Val, 16)) return Val; // Decimal if (Tok.endswith_lower("K")) { if (!to_integer(Tok.drop_back(), Val, 10)) return None; return Val * 1024; } if (Tok.endswith_lower("M")) { if (!to_integer(Tok.drop_back(), Val, 10)) return None; return Val * 1024 * 1024; } if (!to_integer(Tok, Val, 10)) return None; return Val; } BytesDataCommand *ScriptParser::readBytesDataCommand(StringRef Tok) { int Size = StringSwitch(Tok) .Case("BYTE", 1) .Case("SHORT", 2) .Case("LONG", 4) .Case("QUAD", 8) .Default(-1); if (Size == -1) return nullptr; return make(readParenExpr(), Size); } StringRef ScriptParser::readParenLiteral() { expect("("); StringRef Tok = next(); expect(")"); return Tok; } Expr ScriptParser::readPrimary() { if (peek() == "(") return readParenExpr(); if (consume("~")) { Expr E = readPrimary(); return [=] { return ~E().getValue(); }; } if (consume("-")) { Expr E = readPrimary(); return [=] { return -E().getValue(); }; } StringRef Tok = next(); std::string Location = getCurrentLocation(); // Built-in functions are parsed here. // https://sourceware.org/binutils/docs/ld/Builtin-Functions.html. if (Tok == "ABSOLUTE") { Expr Inner = readParenExpr(); return [=] { ExprValue I = Inner(); I.ForceAbsolute = true; return I; }; } if (Tok == "ADDR") { StringRef Name = readParenLiteral(); return [=]() -> ExprValue { return {Script->getOutputSection(Location, Name), 0}; }; } if (Tok == "ALIGN") { expect("("); Expr E = readExpr(); if (consume(")")) return [=] { return alignTo(Script->getDot(), E().getValue()); }; expect(","); Expr E2 = readExpr(); expect(")"); - return [=] { return alignTo(E().getValue(), E2().getValue()); }; + return [=] { + ExprValue V = E(); + V.Alignment = E2().getValue(); + return V; + }; } if (Tok == "ALIGNOF") { StringRef Name = readParenLiteral(); return [=] { return Script->getOutputSection(Location, Name)->Alignment; }; } if (Tok == "ASSERT") return readAssertExpr(); if (Tok == "CONSTANT") { StringRef Name = readParenLiteral(); return [=] { return getConstant(Name); }; } if (Tok == "DATA_SEGMENT_ALIGN") { expect("("); Expr E = readExpr(); expect(","); readExpr(); expect(")"); return [=] { return alignTo(Script->getDot(), E().getValue()); }; } if (Tok == "DATA_SEGMENT_END") { expect("("); expect("."); expect(")"); return [] { return Script->getDot(); }; } if (Tok == "DATA_SEGMENT_RELRO_END") { // GNU linkers implements more complicated logic to handle // DATA_SEGMENT_RELRO_END. We instead ignore the arguments and // just align to the next page boundary for simplicity. expect("("); readExpr(); expect(","); readExpr(); expect(")"); return [] { return alignTo(Script->getDot(), Target->PageSize); }; } if (Tok == "DEFINED") { StringRef Name = readParenLiteral(); return [=] { return Script->isDefined(Name) ? 1 : 0; }; } if (Tok == "LENGTH") { StringRef Name = readParenLiteral(); if (Script->Opt.MemoryRegions.count(Name) == 0) setError("memory region not defined: " + Name); return [=] { return Script->Opt.MemoryRegions[Name].Length; }; } if (Tok == "LOADADDR") { StringRef Name = readParenLiteral(); return [=] { return Script->getOutputSection(Location, Name)->getLMA(); }; } if (Tok == "ORIGIN") { StringRef Name = readParenLiteral(); if (Script->Opt.MemoryRegions.count(Name) == 0) setError("memory region not defined: " + Name); return [=] { return Script->Opt.MemoryRegions[Name].Origin; }; } if (Tok == "SEGMENT_START") { expect("("); skip(); expect(","); Expr E = readExpr(); expect(")"); return [=] { return E(); }; } if (Tok == "SIZEOF") { StringRef Name = readParenLiteral(); return [=] { return Script->getOutputSectionSize(Name); }; } if (Tok == "SIZEOF_HEADERS") return [=] { return elf::getHeaderSize(); }; // Tok is the dot. if (Tok == ".") return [=] { return Script->getSymbolValue(Location, Tok); }; // Tok is a literal number. if (Optional Val = parseInt(Tok)) return [=] { return *Val; }; // Tok is a symbol name. if (!isValidCIdentifier(Tok)) setError("malformed number: " + Tok); Script->Opt.ReferencedSymbols.push_back(Tok); return [=] { return Script->getSymbolValue(Location, Tok); }; } Expr ScriptParser::readTernary(Expr Cond) { Expr L = readExpr(); expect(":"); Expr R = readExpr(); return [=] { return Cond().getValue() ? L() : R(); }; } Expr ScriptParser::readParenExpr() { expect("("); Expr E = readExpr(); expect(")"); return E; } std::vector ScriptParser::readOutputSectionPhdrs() { std::vector Phdrs; while (!Error && peek().startswith(":")) { StringRef Tok = next(); Phdrs.push_back((Tok.size() == 1) ? next() : Tok.substr(1)); } return Phdrs; } // Read a program header type name. The next token must be a // name of a program header type or a constant (e.g. "0x3"). unsigned ScriptParser::readPhdrType() { StringRef Tok = next(); if (Optional Val = parseInt(Tok)) return *Val; unsigned Ret = StringSwitch(Tok) .Case("PT_NULL", PT_NULL) .Case("PT_LOAD", PT_LOAD) .Case("PT_DYNAMIC", PT_DYNAMIC) .Case("PT_INTERP", PT_INTERP) .Case("PT_NOTE", PT_NOTE) .Case("PT_SHLIB", PT_SHLIB) .Case("PT_PHDR", PT_PHDR) .Case("PT_TLS", PT_TLS) .Case("PT_GNU_EH_FRAME", PT_GNU_EH_FRAME) .Case("PT_GNU_STACK", PT_GNU_STACK) .Case("PT_GNU_RELRO", PT_GNU_RELRO) .Case("PT_OPENBSD_RANDOMIZE", PT_OPENBSD_RANDOMIZE) .Case("PT_OPENBSD_WXNEEDED", PT_OPENBSD_WXNEEDED) .Case("PT_OPENBSD_BOOTDATA", PT_OPENBSD_BOOTDATA) .Default(-1); if (Ret == (unsigned)-1) { setError("invalid program header type: " + Tok); return PT_NULL; } return Ret; } // Reads an anonymous version declaration. void ScriptParser::readAnonymousDeclaration() { std::vector Locals; std::vector Globals; std::tie(Locals, Globals) = readSymbols(); for (SymbolVersion V : Locals) { if (V.Name == "*") Config->DefaultSymbolVersion = VER_NDX_LOCAL; else Config->VersionScriptLocals.push_back(V); } for (SymbolVersion V : Globals) Config->VersionScriptGlobals.push_back(V); expect(";"); } // Reads a non-anonymous version definition, // e.g. "VerStr { global: foo; bar; local: *; };". void ScriptParser::readVersionDeclaration(StringRef VerStr) { // Read a symbol list. std::vector Locals; std::vector Globals; std::tie(Locals, Globals) = readSymbols(); for (SymbolVersion V : Locals) { if (V.Name == "*") Config->DefaultSymbolVersion = VER_NDX_LOCAL; else Config->VersionScriptLocals.push_back(V); } // Create a new version definition and add that to the global symbols. VersionDefinition Ver; Ver.Name = VerStr; Ver.Globals = Globals; // User-defined version number starts from 2 because 0 and 1 are // reserved for VER_NDX_LOCAL and VER_NDX_GLOBAL, respectively. Ver.Id = Config->VersionDefinitions.size() + 2; Config->VersionDefinitions.push_back(Ver); // Each version may have a parent version. For example, "Ver2" // defined as "Ver2 { global: foo; local: *; } Ver1;" has "Ver1" // as a parent. This version hierarchy is, probably against your // instinct, purely for hint; the runtime doesn't care about it // at all. In LLD, we simply ignore it. if (peek() != ";") skip(); expect(";"); } // Reads a list of symbols, e.g. "{ global: foo; bar; local: *; };". std::pair, std::vector> ScriptParser::readSymbols() { std::vector Locals; std::vector Globals; std::vector *V = &Globals; while (!Error) { if (consume("}")) break; if (consumeLabel("local")) { V = &Locals; continue; } if (consumeLabel("global")) { V = &Globals; continue; } if (consume("extern")) { std::vector Ext = readVersionExtern(); V->insert(V->end(), Ext.begin(), Ext.end()); } else { StringRef Tok = next(); V->push_back({unquote(Tok), false, hasWildcard(Tok)}); } expect(";"); } return {Locals, Globals}; } // Reads an "extern C++" directive, e.g., // "extern "C++" { ns::*; "f(int, double)"; };" std::vector ScriptParser::readVersionExtern() { StringRef Tok = next(); bool IsCXX = Tok == "\"C++\""; if (!IsCXX && Tok != "\"C\"") setError("Unknown language"); expect("{"); std::vector Ret; while (!Error && peek() != "}") { StringRef Tok = next(); bool HasWildcard = !Tok.startswith("\"") && hasWildcard(Tok); Ret.push_back({unquote(Tok), IsCXX, HasWildcard}); expect(";"); } expect("}"); return Ret; } uint64_t ScriptParser::readMemoryAssignment(StringRef S1, StringRef S2, StringRef S3) { if (!consume(S1) && !consume(S2) && !consume(S3)) { setError("expected one of: " + S1 + ", " + S2 + ", or " + S3); return 0; } expect("="); return readExpr()().getValue(); } // Parse the MEMORY command as specified in: // https://sourceware.org/binutils/docs/ld/MEMORY.html // // MEMORY { name [(attr)] : ORIGIN = origin, LENGTH = len ... } void ScriptParser::readMemory() { expect("{"); while (!Error && !consume("}")) { StringRef Name = next(); uint32_t Flags = 0; uint32_t NegFlags = 0; if (consume("(")) { std::tie(Flags, NegFlags) = readMemoryAttributes(); expect(")"); } expect(":"); uint64_t Origin = readMemoryAssignment("ORIGIN", "org", "o"); expect(","); uint64_t Length = readMemoryAssignment("LENGTH", "len", "l"); // Add the memory region to the region map (if it doesn't already exist). auto It = Script->Opt.MemoryRegions.find(Name); if (It != Script->Opt.MemoryRegions.end()) setError("region '" + Name + "' already defined"); else Script->Opt.MemoryRegions[Name] = {Name, Origin, Length, Origin, Flags, NegFlags}; } } // This function parses the attributes used to match against section // flags when placing output sections in a memory region. These flags // are only used when an explicit memory region name is not used. std::pair ScriptParser::readMemoryAttributes() { uint32_t Flags = 0; uint32_t NegFlags = 0; bool Invert = false; for (char C : next().lower()) { uint32_t Flag = 0; if (C == '!') Invert = !Invert; else if (C == 'w') Flag = SHF_WRITE; else if (C == 'x') Flag = SHF_EXECINSTR; else if (C == 'a') Flag = SHF_ALLOC; else if (C != 'r') setError("invalid memory region attribute"); if (Invert) NegFlags |= Flag; else Flags |= Flag; } return {Flags, NegFlags}; } void elf::readLinkerScript(MemoryBufferRef MB) { ScriptParser(MB).readLinkerScript(); } void elf::readVersionScript(MemoryBufferRef MB) { ScriptParser(MB).readVersionScript(); } void elf::readDynamicList(MemoryBufferRef MB) { ScriptParser(MB).readDynamicList(); } Index: vendor/lld/dist/ELF/Writer.cpp =================================================================== --- vendor/lld/dist/ELF/Writer.cpp (revision 319237) +++ vendor/lld/dist/ELF/Writer.cpp (revision 319238) @@ -1,1842 +1,1847 @@ //===- Writer.cpp ---------------------------------------------------------===// // // The LLVM Linker // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #include "Writer.h" #include "Config.h" #include "Filesystem.h" #include "LinkerScript.h" #include "MapFile.h" #include "Memory.h" #include "OutputSections.h" #include "Relocations.h" #include "Strings.h" #include "SymbolTable.h" #include "SyntheticSections.h" #include "Target.h" #include "Threads.h" #include "llvm/ADT/StringMap.h" #include "llvm/ADT/StringSwitch.h" #include "llvm/Support/FileOutputBuffer.h" #include "llvm/Support/raw_ostream.h" #include using namespace llvm; using namespace llvm::ELF; using namespace llvm::object; using namespace llvm::support; using namespace llvm::support::endian; using namespace lld; using namespace lld::elf; namespace { // The writer writes a SymbolTable result to a file. template class Writer { public: typedef typename ELFT::Shdr Elf_Shdr; typedef typename ELFT::Ehdr Elf_Ehdr; typedef typename ELFT::Phdr Elf_Phdr; void run(); private: void clearOutputSections(); void createSyntheticSections(); void copyLocalSymbols(); void addSectionSymbols(); void addReservedSymbols(); void createSections(); void forEachRelSec(std::function Fn); void sortSections(); void finalizeSections(); void addPredefinedSections(); std::vector createPhdrs(); void removeEmptyPTLoad(); void addPtArmExid(std::vector &Phdrs); void assignFileOffsets(); void assignFileOffsetsBinary(); void setPhdrs(); void fixSectionAlignments(); void fixPredefinedSymbols(); void openFile(); void writeHeader(); void writeSections(); void writeSectionsBinary(); void writeBuildId(); std::unique_ptr Buffer; std::vector OutputSections; + std::vector OutputSectionCommands; OutputSectionFactory Factory{OutputSections}; void addRelIpltSymbols(); void addStartEndSymbols(); void addStartStopSymbols(OutputSection *Sec); uint64_t getEntryAddr(); OutputSection *findSection(StringRef Name); OutputSection *findSectionInScript(StringRef Name); OutputSectionCommand *findSectionCommand(StringRef Name); std::vector Phdrs; uint64_t FileSize; uint64_t SectionHeaderOff; }; } // anonymous namespace StringRef elf::getOutputSectionName(StringRef Name) { if (Config->Relocatable) return Name; // If -emit-relocs is given (which is rare), we need to copy // relocation sections to the output. If input section .foo is // output as .bar, we want to rename .rel.foo .rel.bar as well. if (Config->EmitRelocs) { for (StringRef V : {".rel.", ".rela."}) { if (Name.startswith(V)) { StringRef Inner = getOutputSectionName(Name.substr(V.size() - 1)); return Saver.save(V.drop_back() + Inner); } } } 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."}) { StringRef Prefix = V.drop_back(); if (Name.startswith(V) || Name == Prefix) return Prefix; } // CommonSection is identified as "COMMON" in linker scripts. // By default, it should go to .bss section. if (Name == "COMMON") return ".bss"; // ".zdebug_" is a prefix for ZLIB-compressed sections. // Because we decompressed input sections, we want to remove 'z'. if (Name.startswith(".zdebug_")) return Saver.save("." + Name.substr(2)); return Name; } template static bool needsInterpSection() { return !Symtab::X->getSharedFiles().empty() && !Config->DynamicLinker.empty() && !Script->ignoreInterpSection(); } template void elf::writeResult() { Writer().run(); } template void Writer::removeEmptyPTLoad() { auto I = std::remove_if(Phdrs.begin(), Phdrs.end(), [&](const PhdrEntry &P) { if (P.p_type != PT_LOAD) return false; if (!P.First) return true; uint64_t Size = P.Last->Addr + P.Last->Size - P.First->Addr; return Size == 0; }); Phdrs.erase(I, Phdrs.end()); } // This function scans over the input sections and creates mergeable // synthetic sections. It removes MergeInputSections from array and // adds new synthetic ones. Each synthetic section is added to the // location of the first input section it replaces. static void combineMergableSections() { std::vector MergeSections; for (InputSectionBase *&S : InputSections) { MergeInputSection *MS = dyn_cast(S); if (!MS) continue; // We do not want to handle sections that are not alive, so just remove // them instead of trying to merge. if (!MS->Live) continue; StringRef OutsecName = getOutputSectionName(MS->Name); uint64_t Flags = MS->Flags & ~(uint64_t)SHF_GROUP; uint32_t Alignment = std::max(MS->Alignment, MS->Entsize); auto I = llvm::find_if(MergeSections, [=](MergeSyntheticSection *Sec) { return Sec->Name == OutsecName && Sec->Flags == Flags && Sec->Alignment == Alignment; }); if (I == MergeSections.end()) { MergeSyntheticSection *Syn = make(OutsecName, MS->Type, Flags, Alignment); MergeSections.push_back(Syn); I = std::prev(MergeSections.end()); S = Syn; } else { S = nullptr; } (*I)->addSection(MS); } std::vector &V = InputSections; V.erase(std::remove(V.begin(), V.end(), nullptr), V.end()); } template static void combineEhFrameSections() { for (InputSectionBase *&S : InputSections) { EhInputSection *ES = dyn_cast(S); if (!ES || !ES->Live) continue; In::EhFrame->addSection(ES); S = nullptr; } std::vector &V = InputSections; V.erase(std::remove(V.begin(), V.end(), nullptr), V.end()); } template void Writer::clearOutputSections() { // Clear the OutputSections to make sure it is not used anymore. Any // code from this point on should be using the linker script // commands. for (OutputSection *Sec : OutputSections) Sec->Sections.clear(); OutputSections.clear(); } // The main function of the writer. template void Writer::run() { // Create linker-synthesized sections such as .got or .plt. // Such sections are of type input section. createSyntheticSections(); combineMergableSections(); if (!Config->Relocatable) combineEhFrameSections(); // We need to create some reserved symbols such as _end. Create them. if (!Config->Relocatable) addReservedSymbols(); // Create output sections. Script->OutputSections = &OutputSections; if (Script->Opt.HasSections) { // If linker script contains SECTIONS commands, let it create sections. Script->processCommands(Factory); // Linker scripts may have left some input sections unassigned. // Assign such sections using the default rule. Script->addOrphanSections(Factory); } else { // If linker script does not contain SECTIONS commands, create // output sections by default rules. We still need to give the // linker script a chance to run, because it might contain // non-SECTIONS commands such as ASSERT. createSections(); Script->processCommands(Factory); } if (Config->Discard != DiscardPolicy::All) copyLocalSymbols(); if (Config->CopyRelocs) addSectionSymbols(); // Now that we have a complete set of output sections. This function // completes section contents. For example, we need to add strings // to the string table, and add entries to .got and .plt. // finalizeSections does that. finalizeSections(); if (ErrorCount) return; if (!Script->Opt.HasSections) { if (!Config->Relocatable) fixSectionAlignments(); Script->fabricateDefaultCommands(); } + for (BaseCommand *Base : Script->Opt.Commands) + if (auto *Cmd = dyn_cast(Base)) + OutputSectionCommands.push_back(Cmd); + // If -compressed-debug-sections is specified, we need to compress // .debug_* sections. Do it right now because it changes the size of // output sections. parallelForEach(OutputSections.begin(), OutputSections.end(), [](OutputSection *S) { S->maybeCompress(); }); if (Config->Relocatable) { assignFileOffsets(); } else { Script->synchronize(); Script->assignAddresses(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(); if (!Config->OFormatBinary) assignFileOffsets(); else assignFileOffsetsBinary(); setPhdrs(); fixPredefinedSymbols(); } // It does not make sense try to open the file if we have error already. if (ErrorCount) return; // Write the result down to a file. openFile(); if (ErrorCount) return; if (!Config->OFormatBinary) { writeHeader(); writeSections(); } else { writeSectionsBinary(); } clearOutputSections(); // Backfill .note.gnu.build-id section content. This is done at last // because the content is usually a hash value of the entire output file. writeBuildId(); if (ErrorCount) return; // Handle -Map option. - writeMapFile(Script->Opt.Commands); + writeMapFile(OutputSectionCommands); if (ErrorCount) return; if (auto EC = Buffer->commit()) error("failed to write to the output file: " + EC.message()); // Flush the output streams and exit immediately. A full shutdown // is a good test that we are keeping track of all allocated memory, // but actually freeing it is a waste of time in a regular linker run. if (Config->ExitEarly) exitLld(0); } // Initialize Out members. template void Writer::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)); auto Add = [](InputSectionBase *Sec) { InputSections.push_back(Sec); }; InX::DynStrTab = make(".dynstr", true); InX::Dynamic = make>(); In::RelaDyn = make>( Config->IsRela ? ".rela.dyn" : ".rel.dyn", Config->ZCombreloc); InX::ShStrTab = make(".shstrtab", false); Out::ElfHeader = make("", 0, SHF_ALLOC); Out::ElfHeader->Size = sizeof(Elf_Ehdr); Out::ProgramHeaders = make("", 0, SHF_ALLOC); Out::ProgramHeaders->updateAlignment(Config->Wordsize); if (needsInterpSection()) { InX::Interp = createInterpSection(); Add(InX::Interp); } else { InX::Interp = nullptr; } if (!Config->Relocatable) Add(createCommentSection()); if (Config->Strip != StripPolicy::All) { InX::StrTab = make(".strtab", false); InX::SymTab = make>(*InX::StrTab); } if (Config->BuildId != BuildIdKind::None) { InX::BuildId = make(); Add(InX::BuildId); } InX::Common = createCommonSection(); if (InX::Common) Add(InX::Common); InX::Bss = make(".bss"); Add(InX::Bss); InX::BssRelRo = make(".bss.rel.ro"); Add(InX::BssRelRo); // Add MIPS-specific sections. bool HasDynSymTab = !Symtab::X->getSharedFiles().empty() || Config->Pic || Config->ExportDynamic; if (Config->EMachine == EM_MIPS) { if (!Config->Shared && HasDynSymTab) { InX::MipsRldMap = make(); Add(InX::MipsRldMap); } if (auto *Sec = MipsAbiFlagsSection::create()) Add(Sec); if (auto *Sec = MipsOptionsSection::create()) Add(Sec); if (auto *Sec = MipsReginfoSection::create()) Add(Sec); } if (HasDynSymTab) { InX::DynSymTab = make>(*InX::DynStrTab); Add(InX::DynSymTab); In::VerSym = make>(); Add(In::VerSym); if (!Config->VersionDefinitions.empty()) { In::VerDef = make>(); Add(In::VerDef); } In::VerNeed = make>(); Add(In::VerNeed); if (Config->GnuHash) { InX::GnuHashTab = make(); Add(InX::GnuHashTab); } if (Config->SysvHash) { In::HashTab = make>(); Add(In::HashTab); } Add(InX::Dynamic); Add(InX::DynStrTab); Add(In::RelaDyn); } // Add .got. MIPS' .got is so different from the other archs, // it has its own class. if (Config->EMachine == EM_MIPS) { InX::MipsGot = make(); Add(InX::MipsGot); } else { InX::Got = make(); Add(InX::Got); } InX::GotPlt = make(); Add(InX::GotPlt); InX::IgotPlt = make(); Add(InX::IgotPlt); if (Config->GdbIndex) { InX::GdbIndex = make(); Add(InX::GdbIndex); } // 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>( Config->IsRela ? ".rela.plt" : ".rel.plt", false /*Sort*/); Add(In::RelaPlt); // The RelaIplt immediately follows .rel.plt (.rel.dyn for ARM) to ensure // that the IRelative relocations are processed last by the dynamic loader In::RelaIplt = make>( (Config->EMachine == EM_ARM) ? ".rel.dyn" : In::RelaPlt->Name, false /*Sort*/); Add(In::RelaIplt); InX::Plt = make(Target->PltHeaderSize); Add(InX::Plt); InX::Iplt = make(0); Add(InX::Iplt); if (!Config->Relocatable) { if (Config->EhFrameHdr) { In::EhFrameHdr = make>(); Add(In::EhFrameHdr); } In::EhFrame = make>(); Add(In::EhFrame); } if (InX::SymTab) Add(InX::SymTab); Add(InX::ShStrTab); if (InX::StrTab) Add(InX::StrTab); } static bool shouldKeepInSymtab(SectionBase *Sec, StringRef SymName, const SymbolBody &B) { if (B.isFile() || B.isSection()) return false; // If sym references a section in a discarded group, don't keep it. if (Sec == &InputSection::Discarded) return false; if (Config->Discard == DiscardPolicy::None) return true; // In ELF assembly .L symbols are normally discarded by the assembler. // If the assembler fails to do so, the linker discards them if // * --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()) return true; if (Config->Discard == DiscardPolicy::Locals) return false; return !Sec || !(Sec->Flags & SHF_MERGE); } static bool includeInSymtab(const SymbolBody &B) { if (!B.isLocal() && !B.symbol()->IsUsedInRegularObj) return false; if (auto *D = dyn_cast(&B)) { // Always include absolute symbols. SectionBase *Sec = D->Section; if (!Sec) return true; if (auto *IS = dyn_cast(Sec)) { Sec = IS->Repl; IS = cast(Sec); // Exclude symbols pointing to garbage-collected sections. if (!IS->Live) return false; } if (auto *S = dyn_cast(Sec)) if (!S->getSectionPiece(D->Value)->Live) return false; } return true; } // 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 void Writer::copyLocalSymbols() { if (!InX::SymTab) return; for (elf::ObjectFile *F : Symtab::X->getObjectFiles()) { for (SymbolBody *B : F->getLocalSymbols()) { if (!B->IsLocal) fatal(toString(F) + ": broken object: getLocalSymbols returns a non-local symbol"); auto *DR = dyn_cast(B); // No reason to keep local undefined symbol in symtab. if (!DR) continue; if (!includeInSymtab(*B)) continue; SectionBase *Sec = DR->Section; if (!shouldKeepInSymtab(Sec, B->getName(), *B)) continue; InX::SymTab->addSymbol(B); } } } template void Writer::addSectionSymbols() { // Create one STT_SECTION symbol for each output section we might // have a relocation with. for (OutputSection *Sec : OutputSections) { if (Sec->Sections.empty()) continue; InputSection *IS = Sec->Sections[0]; if (isa(IS) || IS->Type == SHT_REL || IS->Type == SHT_RELA) continue; auto *Sym = make("", /*IsLocal=*/true, /*StOther=*/0, STT_SECTION, /*Value=*/0, /*Size=*/0, IS, nullptr); InX::SymTab->addSymbol(Sym); } } // Today's loaders have a feature to make segments read-only after // processing dynamic relocations to enhance security. PT_GNU_RELRO // is defined for that. // // This function returns true if a section needs to be put into a // PT_GNU_RELRO segment. bool elf::isRelroSection(const OutputSection *Sec) { if (!Config->ZRelro) return false; 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)) 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) return true; // .init_array, .preinit_array and .fini_array contain pointers to // functions that are executed on process startup or exit. These // pointers are set by the static linker, and they are not expected // 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) 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 (InX::Got && Sec == InX::Got->OutSec) 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 == InX::GotPlt->OutSec) 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 == InX::Dynamic->OutSec) return true; // .bss.rel.ro is used for copy relocations for read-only symbols. // Since the dynamic linker needs to process copy relocations, the // section cannot be read-only, but once initialized, they shouldn't // change. if (Sec == InX::BssRelRo->OutSec) 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 == ".ctors" || S == ".dtors" || S == ".jcr" || S == ".eh_frame" || S == ".openbsd.randomdata"; } // We compute a rank for each section. The rank indicates where the // section should be placed in the file. Instead of using simple // numbers (0,1,2...), we use a series of flags. One for each decision // point when placing the section. // Using flags has two key properties: // * 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 << 16, RF_NOT_INTERP = 1 << 15, RF_NOT_ALLOC = 1 << 14, RF_WRITE = 1 << 13, RF_EXEC_WRITE = 1 << 12, RF_EXEC = 1 << 11, RF_NON_TLS_BSS = 1 << 10, RF_NON_TLS_BSS_RO = 1 << 9, RF_NOT_TLS = 1 << 8, RF_BSS = 1 << 7, RF_PPC_NOT_TOCBSS = 1 << 6, RF_PPC_OPD = 1 << 5, RF_PPC_TOCL = 1 << 4, RF_PPC_TOC = 1 << 3, RF_PPC_BRANCH_LT = 1 << 2, RF_MIPS_GPREL = 1 << 1, RF_MIPS_NOT_GOT = 1 << 0 }; static unsigned getSectionRank(const OutputSection *Sec) { unsigned Rank = 0; // 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; // 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; // 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; // Sort sections based on their access permission in the following // order: R, RX, RWX, RW. This order is based on the following // considerations: // * Read-only sections come first such that they go in the // PT_LOAD covering the program headers at the start of the file. // * Read-only, executable sections come next, unless the // -no-rosegment option is used. // * Writable, executable sections follow such that .plt on // architectures where it needs to be writable will be placed // 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; if (IsExec) { if (IsWrite) Rank |= RF_EXEC_WRITE; else if (!Config->SingleRoRx) Rank |= RF_EXEC; } else { if (IsWrite) Rank |= RF_WRITE; } // If we got here we know that both A and B are in the same PT_LOAD. 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; // 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; // Within the TLS initialization block, the non-nobits sections need to appear // first. if (IsNoBits) Rank |= RF_BSS; // // Some architectures have additional ordering restrictions for sections // // within the same PT_LOAD. 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; if (Name == ".opd") Rank |= RF_PPC_OPD; if (Name == ".toc1") Rank |= RF_PPC_TOCL; if (Name == ".toc") Rank |= RF_PPC_TOC; if (Name == ".branch_lt") Rank |= RF_PPC_BRANCH_LT; } 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->Name != ".got") Rank |= RF_MIPS_NOT_GOT; } return Rank; } static bool compareSectionsNonScript(const OutputSection *A, const OutputSection *B) { 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); return false; } // Output section ordering is determined by this function. static bool compareSections(const OutputSection *A, const OutputSection *B) { // For now, put sections mentioned in a linker script // first. Sections not on linker script will have a SectionIndex of // INT_MAX. int AIndex = A->SectionIndex; int BIndex = B->SectionIndex; if (AIndex != BIndex) return AIndex < BIndex; return compareSectionsNonScript(A, B); } void PhdrEntry::add(OutputSection *Sec) { Last = Sec; if (!First) First = Sec; p_align = std::max(p_align, Sec->Alignment); if (p_type == PT_LOAD) Sec->FirstInPtLoad = First; } template static Symbol *addRegular(StringRef Name, SectionBase *Sec, uint64_t Value, uint8_t StOther = STV_HIDDEN, uint8_t Binding = STB_WEAK) { // The linker generated symbols are added as STB_WEAK to allow user defined // ones to override them. return Symtab::X->addRegular(Name, StOther, STT_NOTYPE, Value, /*Size=*/0, Binding, Sec, /*File=*/nullptr); } template static DefinedRegular * addOptionalRegular(StringRef Name, SectionBase *Sec, uint64_t Val, uint8_t StOther = STV_HIDDEN, uint8_t Binding = STB_GLOBAL) { SymbolBody *S = Symtab::X->find(Name); if (!S) return nullptr; if (S->isInCurrentDSO()) return nullptr; return cast( addRegular(Name, Sec, Val, StOther, Binding)->body()); } // The beginning and the ending of .rel[a].plt section are marked // with __rel[a]_iplt_{start,end} symbols if it is a statically linked // executable. The runtime needs these symbols in order to resolve // all IRELATIVE relocs on startup. For dynamic executables, we don't // need these symbols, since IRELATIVE relocs are resolved through GOT // and PLT. For details, see http://www.airs.com/blog/archives/403. template void Writer::addRelIpltSymbols() { if (InX::DynSymTab) return; StringRef S = Config->IsRela ? "__rela_iplt_start" : "__rel_iplt_start"; addOptionalRegular(S, In::RelaIplt, 0, STV_HIDDEN, STB_WEAK); S = Config->IsRela ? "__rela_iplt_end" : "__rel_iplt_end"; addOptionalRegular(S, In::RelaIplt, -1, STV_HIDDEN, STB_WEAK); } // The linker is expected to define some symbols depending on // the linking result. This function defines such symbols. template void Writer::addReservedSymbols() { 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 = Symtab::X->addAbsolute("_gp", STV_HIDDEN, STB_LOCAL); // On MIPS O32 ABI, _gp_disp is a magic symbol designates offset between // start of function and 'gp' pointer into GOT. if (Symtab::X->find("_gp_disp")) ElfSym::MipsGpDisp = Symtab::X->addAbsolute("_gp_disp", STV_HIDDEN, STB_LOCAL); // 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::X->find("__gnu_local_gp")) ElfSym::MipsLocalGp = Symtab::X->addAbsolute("__gnu_local_gp", STV_HIDDEN, STB_LOCAL); } // In the assembly for 32 bit x86 the _GLOBAL_OFFSET_TABLE_ symbol // is magical and is used to produce a R_386_GOTPC relocation. // The R_386_GOTPC relocation value doesn't actually depend on the // symbol value, so it could use an index of STN_UNDEF which, according // to the spec, means the symbol value is 0. // Unfortunately both gas and MC keep the _GLOBAL_OFFSET_TABLE_ symbol in // the object file. // The situation is even stranger on x86_64 where the assembly doesn't // need the magical symbol, but gas still puts _GLOBAL_OFFSET_TABLE_ as // an undefined symbol in the .o files. // Given that the symbol is effectively unused, we just create a dummy // hidden one to avoid the undefined symbol error. Symtab::X->addIgnored("_GLOBAL_OFFSET_TABLE_"); // __tls_get_addr is defined by the dynamic linker for dynamic ELFs. For // static linking the linker is required to optimize away any references to // __tls_get_addr, so it's not defined anywhere. Create a hidden definition // to avoid the undefined symbol error. if (!InX::DynSymTab) Symtab::X->addIgnored("__tls_get_addr"); // __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); // If linker script do layout we do not need to create any standart symbols. if (Script->Opt.HasSections) return; auto Add = [](StringRef S) { return addOptionalRegular(S, Out::ElfHeader, 0, STV_DEFAULT); }; ElfSym::Bss = Add("__bss_start"); ElfSym::End1 = Add("end"); ElfSym::End2 = Add("_end"); ElfSym::Etext1 = Add("etext"); ElfSym::Etext2 = Add("_etext"); ElfSym::Edata1 = Add("edata"); ElfSym::Edata2 = Add("_edata"); } // Sort input sections by section name suffixes for // __attribute__((init_priority(N))). static void sortInitFini(OutputSection *S) { if (S) reinterpret_cast(S)->sortInitFini(); } // Sort input sections by the special rule for .ctors and .dtors. static void sortCtorsDtors(OutputSection *S) { if (S) reinterpret_cast(S)->sortCtorsDtors(); } // Sort input sections using the list provided by --symbol-ordering-file. template static void sortBySymbolsOrder(ArrayRef OutputSections) { if (Config->SymbolOrderingFile.empty()) return; // 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 SymbolOrder; int Priority = -Config->SymbolOrderingFile.size(); for (StringRef S : Config->SymbolOrderingFile) SymbolOrder.insert({S, Priority++}); // Build a map from sections to their priorities. DenseMap SectionOrder; for (elf::ObjectFile *File : Symtab::X->getObjectFiles()) { for (SymbolBody *Body : File->getSymbols()) { auto *D = dyn_cast(Body); if (!D || !D->Section) continue; int &Priority = SectionOrder[D->Section]; Priority = std::min(Priority, SymbolOrder.lookup(D->getName())); } } // Sort sections by priority. for (OutputSection *Base : OutputSections) if (auto *Sec = dyn_cast(Base)) Sec->sort([&](InputSectionBase *S) { return SectionOrder.lookup(S); }); } template void Writer::forEachRelSec(std::function Fn) { for (InputSectionBase *IS : InputSections) { if (!IS->Live) continue; // 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. if (!(IS->Flags & SHF_ALLOC)) continue; if (isa(IS) || isa(IS)) Fn(*IS); } if (!Config->Relocatable) { for (EhInputSection *ES : In::EhFrame->Sections) Fn(*ES); } } template void Writer::createSections() { for (InputSectionBase *IS : InputSections) if (IS) Factory.addInputSec(IS, getOutputSectionName(IS->Name)); sortBySymbolsOrder(OutputSections); sortInitFini(findSection(".init_array")); sortInitFini(findSection(".fini_array")); sortCtorsDtors(findSection(".ctors")); sortCtorsDtors(findSection(".dtors")); for (OutputSection *Sec : OutputSections) Sec->assignOffsets(); } // We want to find how similar two ranks are. // 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 unsigned getRankProximity(OutputSection *A, OutputSection *B) { return countLeadingZeros(A->SortRank ^ B->SortRank); } // 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 static std::vector::iterator findOrphanPos(std::vector::iterator B, std::vector::iterator E) { OutputSection *Sec = *E; // Find the first element that has as close a rank as possible. auto I = std::max_element(B, E, [=](OutputSection *A, OutputSection *B) { return getRankProximity(Sec, A) < getRankProximity(Sec, B); }); if (I == E) return E; // Consider all existing sections with the same proximity. unsigned Proximity = getRankProximity(Sec, *I); while (I != E && getRankProximity(Sec, *I) == Proximity && Sec->SortRank >= (*I)->SortRank) ++I; return I; } template void Writer::sortSections() { // 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) return; if (Script->Opt.HasSections) Script->adjustSectionsBeforeSorting(); for (OutputSection *Sec : OutputSections) Sec->SortRank = getSectionRank(Sec); if (!Script->Opt.HasSections) { std::stable_sort(OutputSections.begin(), OutputSections.end(), compareSectionsNonScript); return; } // The order of the sections in the script is arbitrary and may not agree with // compareSectionsNonScript. This means that we cannot easily define a // strict weak ordering. To see why, consider a comparison of a section in the // script and one not in the script. We have a two simple options: // * Make them equivalent (a is not less than b, and b is not less than a). // The problem is then that equivalence has to be transitive and we can // have sections a, b and c with only b in a script and a less than c // which breaks this property. // * Use compareSectionsNonScript. Given that the script order doesn't have // to match, we can end up with sections a, b, c, d where b and c are in the // script and c is compareSectionsNonScript less than b. In which case d // can be equivalent to c, a to b and d < a. As a concrete example: // .a (rx) # not in script // .b (rx) # in script // .c (ro) # in script // .d (ro) # not in script // // The way we define an order then is: // * First put script sections at the start and sort the script sections. // * Move each non-script section to its preferred position. We try // to put each section in the last position where it it can share // a PT_LOAD. std::stable_sort(OutputSections.begin(), OutputSections.end(), compareSections); auto I = OutputSections.begin(); auto E = OutputSections.end(); auto NonScriptI = std::find_if(OutputSections.begin(), E, [](OutputSection *S) { return S->SectionIndex == INT_MAX; }); while (NonScriptI != E) { auto Pos = findOrphanPos(I, NonScriptI); // As an optimization, find all sections with the same sort rank // and insert them with one rotate. unsigned Rank = (*NonScriptI)->SortRank; auto End = std::find_if(NonScriptI + 1, E, [=](OutputSection *Sec) { return Sec->SortRank != Rank; }); std::rotate(Pos, NonScriptI, End); NonScriptI = End; } Script->adjustSectionsAfterSorting(); } static void applySynthetic(const std::vector &Sections, std::function Fn) { for (SyntheticSection *SS : Sections) if (SS && SS->OutSec && !SS->empty()) { Fn(SS); SS->OutSec->assignOffsets(); } } // We need to add input synthetic sections early in createSyntheticSections() // to make them visible from linkescript side. But not all sections are always // required to be in output. For example we don't need dynamic section content // sometimes. This function filters out such unused sections from the output. static void removeUnusedSyntheticSections(std::vector &V) { // 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(S); if (!SS) return; if (!SS->empty() || !SS->OutSec) continue; SS->OutSec->Sections.erase(std::find(SS->OutSec->Sections.begin(), SS->OutSec->Sections.end(), SS)); SS->Live = false; // If there are no other sections in the output section, remove it from the // output. if (SS->OutSec->Sections.empty()) V.erase(std::find(V.begin(), V.end(), SS->OutSec)); } } // Create output section objects and add them to OutputSections. template void Writer::finalizeSections() { Out::DebugInfo = findSection(".debug_info"); 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) { addStartEndSymbols(); for (OutputSection *Sec : OutputSections) 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 (InX::DynSymTab) addRegular("_DYNAMIC", InX::Dynamic, 0); // Define __rel[a]_iplt_{start,end} symbols if needed. addRelIpltSymbols(); // This responsible for splitting up .eh_frame section into // pieces. The relocation scan uses those pieces, so this has to be // earlier. applySynthetic({In::EhFrame}, [](SyntheticSection *SS) { SS->finalizeContents(); }); // Scan relocations. This must be done after every symbol is declared so that // we can correctly decide if a dynamic relocation is needed. forEachRelSec(scanRelocations); if (InX::Plt && !InX::Plt->empty()) InX::Plt->addSymbols(); if (InX::Iplt && !InX::Iplt->empty()) InX::Iplt->addSymbols(); // Now that we have defined all possible global symbols including linker- // synthesized ones. Visit all symbols to give the finishing touches. for (Symbol *S : Symtab::X->getSymbols()) { SymbolBody *Body = S->body(); if (!includeInSymtab(*Body)) continue; if (InX::SymTab) InX::SymTab->addSymbol(Body); if (InX::DynSymTab && S->includeInDynsym()) { InX::DynSymTab->addSymbol(Body); if (auto *SS = dyn_cast(Body)) if (cast>(SS->File)->isNeeded()) In::VerNeed->addSymbol(SS); } } // Do not proceed if there was an undefined symbol. if (ErrorCount) return; - // So far we have added sections from input object files. - // This function adds linker-created Out::* sections. addPredefinedSections(); removeUnusedSyntheticSections(OutputSections); sortSections(); // This is a bit of a hack. A value of 0 means undef, so we set it // to 1 t make __ehdr_start defined. The section number is not // particularly relevant. Out::ElfHeader->SectionIndex = 1; unsigned I = 1; for (OutputSection *Sec : OutputSections) { Sec->SectionIndex = I++; Sec->ShName = InX::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(); } // Dynamic section must be the last one in this list and dynamic // symbol table section (DynSymTab) must be the first one. applySynthetic({InX::DynSymTab, InX::Bss, InX::BssRelRo, InX::GnuHashTab, In::HashTab, InX::SymTab, InX::ShStrTab, InX::StrTab, In::VerDef, InX::DynStrTab, InX::GdbIndex, InX::Got, InX::MipsGot, InX::IgotPlt, InX::GotPlt, In::RelaDyn, In::RelaIplt, In::RelaPlt, InX::Plt, InX::Iplt, In::EhFrameHdr, In::VerSym, In::VerNeed, InX::Dynamic}, [](SyntheticSection *SS) { SS->finalizeContents(); }); // Some architectures use small displacements for jump instructions. // It is linker's responsibility to create thunks containing long // jump instructions if jump targets are too far. Create thunks. if (Target->NeedsThunks) { // FIXME: only ARM Interworking and Mips LA25 Thunks are implemented, // these // do not require address information. To support range extension Thunks // we need to assign addresses so that we can tell if jump instructions // are out of range. This will need to turn into a loop that converges // when no more Thunks are added ThunkCreator TC; if (TC.createThunks(OutputSections)) applySynthetic({InX::MipsGot}, [](SyntheticSection *SS) { SS->updateAllocSize(); }); } // 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(); // createThunks may have added local symbols to the static symbol table applySynthetic({InX::SymTab, InX::ShStrTab, InX::StrTab}, [](SyntheticSection *SS) { SS->postThunkContents(); }); } template void Writer::addPredefinedSections() { // ARM ABI requires .ARM.exidx to be terminated by some piece of data. // We have the terminater synthetic section class. Add that at the end. auto *OS = dyn_cast_or_null(findSection(".ARM.exidx")); - if (OS && !OS->Sections.empty() && !Config->Relocatable) - OS->addSection(make()); + if (!OS || OS->Sections.empty() || Config->Relocatable) + return; + + auto *Sentinel = make(); + OS->addSection(Sentinel); + // If there are linker script commands existing at this point then add the + // sentinel to the last of these too. + if (OutputSectionCommand *C = Script->getCmd(OS)) { + auto ISD = std::find_if(C->Commands.rbegin(), C->Commands.rend(), + [](const BaseCommand *Base) { + return isa(Base); + }); + cast(*ISD)->Sections.push_back(Sentinel); + } } // The linker is expected to define SECNAME_start and SECNAME_end // symbols for a few sections. This function defines them. template void Writer::addStartEndSymbols() { auto Define = [&](StringRef Start, StringRef End, OutputSection *OS) { // These symbols resolve to the image base if the section does not exist. // A special value -1 indicates end of the section. if (OS) { addOptionalRegular(Start, OS, 0); addOptionalRegular(End, OS, -1); } else { if (Config->Pic) OS = Out::ElfHeader; addOptionalRegular(Start, OS, 0); addOptionalRegular(End, OS, 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); 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 // the leading '.'), linkers are expected to define __start_ and // __stop_ symbols. They are at beginning and end of the section, // respectively. This is not requested by the ELF standard, but GNU ld and // gold provide the feature, and used by many programs. template void Writer::addStartStopSymbols(OutputSection *Sec) { StringRef S = Sec->Name; if (!isValidCIdentifier(S)) return; addOptionalRegular(Saver.save("__start_" + S), Sec, 0, STV_DEFAULT); addOptionalRegular(Saver.save("__stop_" + S), Sec, -1, STV_DEFAULT); } template OutputSectionCommand *Writer::findSectionCommand(StringRef Name) { - for (BaseCommand *Base : Script->Opt.Commands) - if (auto *Cmd = dyn_cast(Base)) - if (Cmd->Name == Name) - return Cmd; + for (OutputSectionCommand *Cmd : OutputSectionCommands) + if (Cmd->Name == Name) + return Cmd; return nullptr; } template OutputSection *Writer::findSectionInScript(StringRef Name) { if (OutputSectionCommand *Cmd = findSectionCommand(Name)) return Cmd->Sec; return nullptr; } template OutputSection *Writer::findSection(StringRef Name) { for (OutputSection *Sec : OutputSections) if (Sec->Name == Name) return Sec; return nullptr; } static bool needsPtLoad(OutputSection *Sec) { if (!(Sec->Flags & SHF_ALLOC)) 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) return false; return true; } // Linker scripts are responsible for aligning addresses. Unfortunately, most // 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) return PF_R | PF_W | PF_X; 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 std::vector Writer::createPhdrs() { std::vector Ret; auto AddHdr = [&](unsigned Type, unsigned Flags) -> PhdrEntry * { Ret.emplace_back(Type, Flags); return &Ret.back(); }; // The first phdr entry is PT_PHDR which describes the program header itself. AddHdr(PT_PHDR, PF_R)->add(Out::ProgramHeaders); // PT_INTERP must be the second entry if exists. if (OutputSection *Sec = findSection(".interp")) AddHdr(PT_INTERP, Sec->getPhdrFlags())->add(Sec); // Add the first PT_LOAD segment for regular output sections. uint64_t Flags = computeFlags(PF_R); PhdrEntry *Load = AddHdr(PT_LOAD, Flags); // Add the headers. We will remove them if they don't fit. Load->add(Out::ElfHeader); Load->add(Out::ProgramHeaders); for (OutputSection *Sec : OutputSections) { if (!(Sec->Flags & SHF_ALLOC)) break; if (!needsPtLoad(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 // different flags or is loaded at a discontiguous address using AT linker // script command. uint64_t NewFlags = computeFlags(Sec->getPhdrFlags()); if (Script->hasLMA(Sec) || Flags != NewFlags) { Load = AddHdr(PT_LOAD, NewFlags); Flags = NewFlags; } Load->add(Sec); } // Add a TLS segment if any. PhdrEntry TlsHdr(PT_TLS, PF_R); for (OutputSection *Sec : OutputSections) if (Sec->Flags & SHF_TLS) TlsHdr.add(Sec); if (TlsHdr.First) Ret.push_back(std::move(TlsHdr)); // Add an entry for .dynamic. if (InX::DynSymTab) AddHdr(PT_DYNAMIC, InX::Dynamic->OutSec->getPhdrFlags()) ->add(InX::Dynamic->OutSec); // PT_GNU_RELRO includes all sections that should be marked as // read-only by dynamic linker after proccessing relocations. PhdrEntry RelRo(PT_GNU_RELRO, PF_R); for (OutputSection *Sec : OutputSections) if (needsPtLoad(Sec) && isRelroSection(Sec)) RelRo.add(Sec); if (RelRo.First) Ret.push_back(std::move(RelRo)); // PT_GNU_EH_FRAME is a special section pointing on .eh_frame_hdr. if (!In::EhFrame->empty() && In::EhFrameHdr && In::EhFrame->OutSec && In::EhFrameHdr->OutSec) AddHdr(PT_GNU_EH_FRAME, In::EhFrameHdr->OutSec->getPhdrFlags()) ->add(In::EhFrameHdr->OutSec); // PT_OPENBSD_RANDOMIZE is an OpenBSD-specific feature. That makes // the dynamic linker fill the segment with random data. if (OutputSection *Sec = findSection(".openbsd.randomdata")) AddHdr(PT_OPENBSD_RANDOMIZE, Sec->getPhdrFlags())->add(Sec); // 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; if (Config->ZExecstack) Perm = PF_R | PF_W | PF_X; else Perm = PF_R | PF_W; 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) { if (!Note || Script->hasLMA(Sec)) Note = AddHdr(PT_NOTE, PF_R); Note->add(Sec); } else { Note = nullptr; } } return Ret; } template void Writer::addPtArmExid(std::vector &Phdrs) { if (Config->EMachine != EM_ARM) return; auto I = std::find_if( OutputSections.begin(), OutputSections.end(), [](OutputSection *Sec) { return Sec->Type == SHT_ARM_EXIDX; }); if (I == OutputSections.end()) return; // PT_ARM_EXIDX is the ARM EHABI equivalent of PT_GNU_EH_FRAME PhdrEntry ARMExidx(PT_ARM_EXIDX, PF_R); ARMExidx.add(*I); Phdrs.push_back(ARMExidx); } // 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 void Writer::fixSectionAlignments() { for (const PhdrEntry &P : Phdrs) if (P.p_type == PT_LOAD && P.First) P.First->PageAlign = true; for (const PhdrEntry &P : Phdrs) { if (P.p_type != PT_GNU_RELRO) continue; if (P.First) P.First->PageAlign = true; // 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.Last); if (I == End || (I + 1) == End) continue; OutputSection *Sec = *(I + 1); if (needsPtLoad(Sec)) Sec->PageAlign = true; } } // Adjusts the file alignment for a given output section and returns // its new file offset. 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 getFileAlignment(uint64_t Off, OutputSection *Sec) { OutputSection *First = Sec->FirstInPtLoad; // If the section is not in a PT_LOAD, we just have to align it. if (!First) return alignTo(Off, Sec->Alignment); // The first section in a PT_LOAD has to have congruent offset and address // module the page size. if (Sec == First) return alignTo(Off, Config->MaxPageSize, Sec->Addr); // If two sections share the same PT_LOAD the file offset is calculated // using this formula: Off2 = Off1 + (VA2 - VA1). return First->Offset + Sec->Addr - First->Addr; } static uint64_t setOffset(OutputSection *Sec, uint64_t Off) { if (Sec->Type == SHT_NOBITS) { Sec->Offset = Off; return Off; } Off = getFileAlignment(Off, Sec); Sec->Offset = Off; return Off + Sec->Size; } template void Writer::assignFileOffsetsBinary() { uint64_t Off = 0; for (OutputSection *Sec : OutputSections) if (Sec->Flags & SHF_ALLOC) Off = setOffset(Sec, Off); FileSize = alignTo(Off, Config->Wordsize); } // Assign file offsets to output sections. template void Writer::assignFileOffsets() { uint64_t Off = 0; Off = setOffset(Out::ElfHeader, Off); Off = setOffset(Out::ProgramHeaders, Off); for (OutputSection *Sec : OutputSections) Off = setOffset(Sec, Off); SectionHeaderOff = alignTo(Off, Config->Wordsize); FileSize = SectionHeaderOff + (OutputSections.size() + 1) * sizeof(Elf_Shdr); } // Finalize the program headers. We call this function after we assign // file offsets and VAs to all sections. template void Writer::setPhdrs() { for (PhdrEntry &P : Phdrs) { OutputSection *First = P.First; OutputSection *Last = P.Last; 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(); } if (P.p_type == PT_LOAD) 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); } // The TLS pointer goes after PT_TLS. At least glibc will align it, // so round up the size to make sure the offsets are correct. if (P.p_type == PT_TLS) { Out::TlsPhdr = &P; if (P.p_memsz) P.p_memsz = alignTo(P.p_memsz, P.p_align); } } } // The entry point address is chosen in the following ways. // // 1. the '-e' entry command-line option; // 2. the ENTRY(symbol) command in a linker control script; // 3. the value of the symbol start, if present; // 4. the address of the first byte of the .text section, if present; // 5. the address 0. template uint64_t Writer::getEntryAddr() { // Case 1, 2 or 3. As a special case, if the symbol is actually // a number, we'll use that number as an address. if (SymbolBody *B = Symtab::X->find(Config->Entry)) return B->getVA(); uint64_t Addr; if (to_integer(Config->Entry, Addr)) return Addr; // Case 4 if (OutputSection *Sec = findSectionInScript(".text")) { if (Config->WarnMissingEntry) warn("cannot find entry symbol " + Config->Entry + "; defaulting to 0x" + utohexstr(Sec->Addr)); return Sec->Addr; } // Case 5 if (Config->WarnMissingEntry) warn("cannot find entry symbol " + Config->Entry + "; not setting start address"); return 0; } static uint16_t getELFType() { if (Config->Pic) return ET_DYN; if (Config->Relocatable) return ET_REL; return ET_EXEC; } // This function is called after we have assigned address and size // to each section. This function fixes some predefined // symbol values that depend on section address and size. template void Writer::fixPredefinedSymbols() { // _etext is the first location after the last read-only loadable segment. // _edata is the first location after the last read-write loadable segment. // _end is the first location after the uninitialized data region. PhdrEntry *Last = nullptr; PhdrEntry *LastRO = nullptr; PhdrEntry *LastRW = nullptr; for (PhdrEntry &P : Phdrs) { if (P.p_type != PT_LOAD) continue; Last = &P; if (P.p_flags & PF_W) LastRW = &P; else LastRO = &P; } auto Set = [](DefinedRegular *S, OutputSection *Sec, uint64_t Value) { if (S) { S->Section = Sec; S->Value = Value; } }; if (Last) { Set(ElfSym::End1, Last->First, Last->p_memsz); Set(ElfSym::End2, Last->First, Last->p_memsz); } if (LastRO) { Set(ElfSym::Etext1, LastRO->First, LastRO->p_filesz); Set(ElfSym::Etext2, LastRO->First, LastRO->p_filesz); } if (LastRW) { Set(ElfSym::Edata1, LastRW->First, LastRW->p_filesz); Set(ElfSym::Edata2, LastRW->First, LastRW->p_filesz); } if (ElfSym::Bss) ElfSym::Bss->Section = findSectionInScript(".bss"); // Setup MIPS _gp_disp/__gnu_local_gp symbols which should // be equal to the _gp symbol's value. if (Config->EMachine == EM_MIPS) { if (!ElfSym::MipsGp->Value) { // Find GP-relative section with the lowest address // and use this address to calculate default _gp value. uint64_t Gp = -1; for (const OutputSection *OS : OutputSections) if ((OS->Flags & SHF_MIPS_GPREL) && OS->Addr < Gp) Gp = OS->Addr; if (Gp != (uint64_t)-1) ElfSym::MipsGp->Value = Gp + 0x7ff0; } } } template void Writer::writeHeader() { uint8_t *Buf = Buffer->getBufferStart(); memcpy(Buf, "\177ELF", 4); // Write the ELF header. auto *EHdr = reinterpret_cast(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_type = getELFType(); EHdr->e_machine = Config->EMachine; EHdr->e_version = EV_CURRENT; EHdr->e_entry = getEntryAddr(); EHdr->e_shoff = SectionHeaderOff; EHdr->e_ehsize = sizeof(Elf_Ehdr); EHdr->e_phnum = Phdrs.size(); EHdr->e_shentsize = sizeof(Elf_Shdr); - EHdr->e_shnum = OutputSections.size() + 1; + EHdr->e_shnum = OutputSectionCommands.size() + 1; EHdr->e_shstrndx = InX::ShStrTab->OutSec->SectionIndex; if (Config->EMachine == EM_ARM) // We don't currently use any features incompatible with EF_ARM_EABI_VER5, // but we don't have any firm guarantees of conformance. Linux AArch64 // kernels (as of 2016) require an EABI version to be set. EHdr->e_flags = EF_ARM_EABI_VER5; else if (Config->EMachine == EM_MIPS) EHdr->e_flags = getMipsEFlags(); if (!Config->Relocatable) { EHdr->e_phoff = sizeof(Elf_Ehdr); EHdr->e_phentsize = sizeof(Elf_Phdr); } // Write the program header table. auto *HBuf = reinterpret_cast(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; } // Write the section header table. Note that the first table entry is null. auto *SHdrs = reinterpret_cast(Buf + EHdr->e_shoff); - for (OutputSection *Sec : OutputSections) - Sec->writeHeaderTo(++SHdrs); + for (OutputSectionCommand *Cmd : OutputSectionCommands) + Cmd->Sec->writeHeaderTo(++SHdrs); } // Open a result file. template void Writer::openFile() { if (!Config->Is64 && FileSize > UINT32_MAX) { error("output file too large: " + Twine(FileSize) + " bytes"); return; } unlinkAsync(Config->OutputFile); ErrorOr> BufferOrErr = FileOutputBuffer::create(Config->OutputFile, FileSize, FileOutputBuffer::F_executable); if (auto EC = BufferOrErr.getError()) error("failed to open " + Config->OutputFile + ": " + EC.message()); else Buffer = std::move(*BufferOrErr); } template void Writer::writeSectionsBinary() { uint8_t *Buf = Buffer->getBufferStart(); - for (BaseCommand *Base : Script->Opt.Commands) { - auto *Cmd = dyn_cast(Base); - if (!Cmd) - continue; + for (OutputSectionCommand *Cmd : OutputSectionCommands) { OutputSection *Sec = Cmd->Sec; if (Sec->Flags & SHF_ALLOC) Cmd->writeTo(Buf + Sec->Offset); } } // Write section contents to a mmap'ed file. template void Writer::writeSections() { uint8_t *Buf = Buffer->getBufferStart(); // PPC64 needs to process relocations in the .opd section // before processing relocations in code-containing sections. if (auto *OpdCmd = findSectionCommand(".opd")) { Out::Opd = OpdCmd->Sec; Out::OpdBuf = Buf + Out::Opd->Offset; OpdCmd->template writeTo(Buf + Out::Opd->Offset); } OutputSection *EhFrameHdr = (In::EhFrameHdr && !In::EhFrameHdr->empty()) ? In::EhFrameHdr->OutSec : nullptr; // 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 (BaseCommand *Base : Script->Opt.Commands) { - auto *Cmd = dyn_cast(Base); - if (!Cmd) - continue; + for (OutputSectionCommand *Cmd : OutputSectionCommands) { OutputSection *Sec = Cmd->Sec; if (Sec->Type == SHT_REL || Sec->Type == SHT_RELA) Cmd->writeTo(Buf + Sec->Offset); } - for (BaseCommand *Base : Script->Opt.Commands) { - auto *Cmd = dyn_cast(Base); - if (!Cmd) - continue; + for (OutputSectionCommand *Cmd : OutputSectionCommands) { OutputSection *Sec = Cmd->Sec; if (Sec != Out::Opd && Sec != EhFrameHdr && Sec->Type != SHT_REL && Sec->Type != SHT_RELA) Cmd->writeTo(Buf + Sec->Offset); } // The .eh_frame_hdr depends on .eh_frame section contents, therefore // it should be written after .eh_frame is written. if (EhFrameHdr) { OutputSectionCommand *Cmd = Script->getCmd(EhFrameHdr); Cmd->writeTo(Buf + EhFrameHdr->Offset); } } template void Writer::writeBuildId() { if (!InX::BuildId || !InX::BuildId->OutSec) return; // Compute a hash of all sections of the output file. uint8_t *Start = Buffer->getBufferStart(); uint8_t *End = Start + FileSize; InX::BuildId->writeBuildId({Start, End}); } template void elf::writeResult(); template void elf::writeResult(); template void elf::writeResult(); template void elf::writeResult(); Index: vendor/lld/dist/test/ELF/linkerscript/align.s =================================================================== --- vendor/lld/dist/test/ELF/linkerscript/align.s (revision 319237) +++ vendor/lld/dist/test/ELF/linkerscript/align.s (revision 319238) @@ -1,80 +1,80 @@ # REQUIRES: x86 # RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t ## Check that ALIGN command workable using location counter # RUN: echo "SECTIONS { \ # RUN: . = 0x10000; \ # RUN: .aaa : { *(.aaa) } \ # RUN: . = ALIGN(4096); \ # RUN: .bbb : { *(.bbb) } \ # RUN: . = ALIGN(4096 * 4); \ # RUN: .ccc : { *(.ccc) } \ # RUN: }" > %t.script # RUN: ld.lld -o %t1 --script %t.script %t # RUN: llvm-objdump -section-headers %t1 | FileCheck %s ## Check that the two argument version of ALIGN command works # RUN: echo "SECTIONS { \ # RUN: . = ALIGN(0x1234, 0x10000); \ # RUN: .aaa : { *(.aaa) } \ # RUN: . = ALIGN(., 4096); \ # RUN: .bbb : { *(.bbb) } \ # RUN: . = ALIGN(., 4096 * 4); \ # RUN: .ccc : { *(.ccc) } \ # RUN: }" > %t.script # RUN: ld.lld -o %t1 --script %t.script %t # RUN: llvm-objdump -section-headers %t1 | FileCheck %s # CHECK: Sections: # CHECK-NEXT: Idx Name Size Address Type # CHECK-NEXT: 0 00000000 0000000000000000 # CHECK-NEXT: 1 .aaa 00000008 0000000000010000 DATA # CHECK-NEXT: 2 .bbb 00000008 0000000000011000 DATA # CHECK-NEXT: 3 .ccc 00000008 0000000000014000 DATA ## Check output sections ALIGN modificator # RUN: echo "SECTIONS { \ # RUN: . = 0x10000; \ # RUN: .aaa : { *(.aaa) } \ # RUN: .bbb : ALIGN(4096) { *(.bbb) } \ # RUN: .ccc : ALIGN(4096 * 4) { *(.ccc) } \ # RUN: }" > %t2.script # RUN: ld.lld -o %t2 --script %t2.script %t # RUN: llvm-objdump -section-headers %t2 | FileCheck %s ## Check use of variables in align expressions: # RUN: echo "VAR = 0x1000; \ # RUN: __code_base__ = 0x10000; \ # RUN: SECTIONS { \ # RUN: . = __code_base__; \ # RUN: .aaa : { *(.aaa) } \ # RUN: .bbb : ALIGN(VAR) { *(.bbb) } \ # RUN: . = ALIGN(., VAR * 4); \ # RUN: .ccc : { *(.ccc) } \ # RUN: __start_bbb = ADDR(.bbb); \ # RUN: __end_bbb = ALIGN(__start_bbb + SIZEOF(.bbb), VAR); \ # RUN: }" > %t3.script # RUN: ld.lld -o %t3 --script %t3.script %t # RUN: llvm-objdump -section-headers %t3 | FileCheck %s # RUN: llvm-objdump -t %t3 | FileCheck -check-prefix SYMBOLS %s # SYMBOLS-LABEL: SYMBOL TABLE: # SYMBOLS-NEXT: 0000000000000000 *UND* 00000000 # SYMBOLS-NEXT: 0000000000014008 .text 00000000 _start # SYMBOLS-NEXT: 0000000000010000 *ABS* 00000000 __code_base__ # SYMBOLS-NEXT: 0000000000001000 *ABS* 00000000 VAR # SYMBOLS-NEXT: 0000000000011000 .bbb 00000000 __start_bbb -# SYMBOLS-NEXT: 0000000000012000 *ABS* 00000000 __end_bbb +# SYMBOLS-NEXT: 0000000000012000 .bbb 00000000 __end_bbb .global _start _start: nop .section .aaa, "a" .quad 0 .section .bbb, "a" .quad 0 .section .ccc, "a" .quad 0 Index: vendor/lld/dist/test/ELF/linkerscript/bss-fill.s =================================================================== --- vendor/lld/dist/test/ELF/linkerscript/bss-fill.s (nonexistent) +++ vendor/lld/dist/test/ELF/linkerscript/bss-fill.s (revision 319238) @@ -0,0 +1,7 @@ +# REQUIRES: x86 +# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o +# RUN: echo "SECTIONS { .bss : { . += 0x10000; *(.bss) } =0xFF };" > %t.script +# RUN: ld.lld -o %t --script %t.script %t.o + +.section .bss,"",@nobits +.short 0 Property changes on: vendor/lld/dist/test/ELF/linkerscript/bss-fill.s ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: vendor/lld/dist/test/ELF/linkerscript/merge-sections.s =================================================================== --- vendor/lld/dist/test/ELF/linkerscript/merge-sections.s (revision 319237) +++ vendor/lld/dist/test/ELF/linkerscript/merge-sections.s (revision 319238) @@ -1,52 +1,62 @@ # REQUIRES: x86 # RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t # RUN: echo "SECTIONS { \ # RUN: . = SIZEOF_HEADERS; \ # RUN: .foo : { begin = .; *(.foo.*) end = .;} \ # RUN: }" > %t.script # RUN: ld.lld -o %t1 --script %t.script %t -shared # RUN: llvm-readobj -s -t %t1 | FileCheck %s # CHECK: Name: .foo # CHECK-NEXT: Type: SHT_PROGBITS # CHECK-NEXT: Flags [ # CHECK-NEXT: SHF_ALLOC # CHECK-NEXT: SHF_MERGE # CHECK-NEXT: SHF_STRINGS # CHECK-NEXT: ] # CHECK-NEXT: Address: 0x[[ADDR1:.*]] # CHECK-NEXT: Offset: 0x[[ADDR1]] # CHECK-NEXT: Size: 14 # CHECK-NEXT: Link: 0 # CHECK-NEXT: Info: 0 # CHECK-NEXT: AddressAlignment: 2 # CHECK-NEXT: EntrySize: 0 # CHECK-NEXT: } # CHECK: Name: begin # CHECK-NEXT: Value: 0x[[ADDR1]] # CHECK: Name: end # 0x19E = begin + sizeof(.foo) = 0x190 + 0xE # CHECK-NEXT: Value: 0x19E +# Check that we don't crash with --gc-sections +# RUN: ld.lld --gc-sections -o %t2 --script %t.script %t -shared +# RUN: llvm-readobj -s -t %t2 | FileCheck %s --check-prefix=GC + +# GC: Name: .foo +# GC-NEXT: Type: SHT_PROGBITS +# GC-NEXT: Flags [ +# GC-NEXT: SHF_ALLOC +# GC-NEXT: ] + .section .foo.1a,"aMS",@progbits,1 .asciz "foo" .section .foo.1b,"aMS",@progbits,1 .asciz "foo" .section .foo.2a,"aM",@progbits,1 .byte 42 .section .foo.2b,"aM",@progbits,1 .byte 42 .section .foo.3a,"aM",@progbits,2 .align 2 .short 42 .section .foo.3b,"aM",@progbits,2 .align 2 .short 42 Index: vendor/lld/dist/test/ELF/linkerscript/symbol-reserved.s =================================================================== --- vendor/lld/dist/test/ELF/linkerscript/symbol-reserved.s (revision 319237) +++ vendor/lld/dist/test/ELF/linkerscript/symbol-reserved.s (revision 319238) @@ -1,16 +1,22 @@ # REQUIRES: x86 # RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t # RUN: echo "PROVIDE_HIDDEN(newsym = __ehdr_start + 5);" > %t.script # RUN: ld.lld -o %t1 %t.script %t # RUN: llvm-objdump -t %t1 | FileCheck %s # CHECK: 0000000000200005 .text 00000000 .hidden newsym # RUN: ld.lld -o %t1.so %t.script %t -shared # RUN: llvm-objdump -t %t1.so | FileCheck --check-prefix=SHARED %s # SHARED: 0000000000000005 .dynsym 00000000 .hidden newsym +# RUN: echo "PROVIDE_HIDDEN(newsym = ALIGN(__ehdr_start, CONSTANT(MAXPAGESIZE)) + 5);" > %t.script +# RUN: ld.lld -o %t1 %t.script %t +# RUN: llvm-objdump -t %t1 | FileCheck --check-prefix=ALIGNED %s + +# ALIGNED: 0000000000200005 .text 00000000 .hidden newsym + .global _start _start: lea newsym(%rip),%rax