Index: head/contrib/llvm/tools/lld/ELF/LinkerScript.cpp =================================================================== --- head/contrib/llvm/tools/lld/ELF/LinkerScript.cpp (revision 328545) +++ head/contrib/llvm/tools/lld/ELF/LinkerScript.cpp (revision 328546) @@ -1,1023 +1,1030 @@ //===- 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 "OutputSections.h" #include "Strings.h" #include "SymbolTable.h" #include "Symbols.h" #include "SyntheticSections.h" #include "Target.h" #include "Writer.h" #include "lld/Common/Memory.h" #include "lld/Common/Threads.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/StringRef.h" #include "llvm/BinaryFormat/ELF.h" #include "llvm/Support/Casting.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; static uint64_t getOutputSectionVA(SectionBase *InputSec, StringRef Loc) { if (OutputSection *OS = InputSec->getOutputSection()) return OS->Addr; error(Loc + ": unable to evaluate expression: input section " + InputSec->Name + " has no output section assigned"); return 0; } uint64_t ExprValue::getValue() const { if (Sec) return alignTo(Sec->getOffset(Val) + getOutputSectionVA(Sec, Loc), Alignment); return alignTo(Val, Alignment); } uint64_t ExprValue::getSecAddr() const { if (Sec) return Sec->getOffset(0) + getOutputSectionVA(Sec, Loc); return 0; } uint64_t ExprValue::getSectionOffset() const { // If the alignment is trivial, we don't have to compute the full // value to know the offset. This allows this function to succeed in // cases where the output section is not yet known. if (Alignment == 1) return Val; return getValue() - getSecAddr(); } OutputSection *LinkerScript::createOutputSection(StringRef Name, StringRef Location) { OutputSection *&SecRef = NameToOutputSection[Name]; OutputSection *Sec; if (SecRef && SecRef->Location.empty()) { // There was a forward reference. Sec = SecRef; } else { Sec = make(Name, SHT_NOBITS, 0); if (!SecRef) SecRef = Sec; } Sec->Location = Location; return Sec; } OutputSection *LinkerScript::getOrCreateOutputSection(StringRef Name) { OutputSection *&CmdRef = NameToOutputSection[Name]; if (!CmdRef) CmdRef = make(Name, SHT_PROGBITS, 0); return CmdRef; } void LinkerScript::setDot(Expr E, const Twine &Loc, bool InSec) { uint64_t Val = E().getValue(); if (Val < Dot && InSec) error(Loc + ": unable to move location counter backward for: " + Ctx->OutSec->Name); Dot = Val; // Update to location counter means update to section size. if (InSec) Ctx->OutSec->Size = Dot - Ctx->OutSec->Addr; } // This function is called from processSectionCommands, // while we are fixing the output section layout. 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. Symbol *B = Symtab->find(Cmd->Name); if (Cmd->Provide && (!B || B->isDefined())) return; // Define a symbol. Symbol *Sym; uint8_t Visibility = Cmd->Hidden ? STV_HIDDEN : STV_DEFAULT; std::tie(Sym, std::ignore) = Symtab->insert(Cmd->Name, /*Type*/ 0, Visibility, /*CanOmitFromDynSym*/ false, /*File*/ nullptr); ExprValue Value = Cmd->Expression(); SectionBase *Sec = Value.isAbsolute() ? nullptr : Value.Sec; // When this function is called, section addresses have not been // fixed yet. So, we may or may not know the value of the RHS // expression. // // For example, if an expression is `x = 42`, we know x is always 42. // However, if an expression is `x = .`, there's no way to know its // value at the moment. // // 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.Sec ? 0 : Value.getValue(); replaceSymbol(Sym, nullptr, Cmd->Name, STB_GLOBAL, Visibility, STT_NOTYPE, SymValue, 0, Sec); Cmd->Sym = cast(Sym); } // This function is called from assignAddresses, while we are // fixing the output section addresses. This function is supposed // to set the final value for a given symbol assignment. void LinkerScript::assignSymbol(SymbolAssignment *Cmd, bool InSec) { if (Cmd->Name == ".") { setDot(Cmd->Expression, Cmd->Location, InSec); return; } if (!Cmd->Sym) return; ExprValue V = Cmd->Expression(); if (V.isAbsolute()) { Cmd->Sym->Section = nullptr; Cmd->Sym->Value = V.getValue(); } else { Cmd->Sym->Section = V.Sec; Cmd->Sym->Value = V.getSectionOffset(); } } static std::string getFilename(InputFile *File) { if (!File) return ""; if (File->ArchiveName.empty()) return File->getName(); return (File->ArchiveName + "(" + File->getName() + ")").str(); } bool LinkerScript::shouldKeep(InputSectionBase *S) { if (KeptSections.empty()) return false; std::string Filename = getFilename(S->File); for (InputSectionDescription *ID : KeptSections) if (ID->FilePat.match(Filename)) 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, [](InputSection *Sec) { return Sec->Flags & SHF_WRITE; }); return (IsRW && Kind == ConstraintKind::ReadWrite) || (!IsRW && Kind == ConstraintKind::ReadOnly); } static void sortSections(MutableArrayRef Vec, SortSectionPolicy K) { if (K != SortSectionPolicy::Default && K != SortSectionPolicy::None) std::stable_sort(Vec.begin(), Vec.end(), getComparator(K)); } // 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. // 5. If no SORT commands are given and --sort-section is not specified, // apply sorting provided by --symbol-ordering-file if any exist. static void sortInputSections( MutableArrayRef Vec, const SectionPattern &Pat, const DenseMap &Order) { if (Pat.SortOuter == SortSectionPolicy::None) return; if (Pat.SortOuter == SortSectionPolicy::Default && Config->SortSection == SortSectionPolicy::Default) { // If -symbol-ordering-file was given, sort accordingly. // Usually, Order is empty. if (!Order.empty()) sortByOrder(Vec, [&](InputSectionBase *S) { return Order.lookup(S); }); return; } if (Pat.SortInner == SortSectionPolicy::Default) sortSections(Vec, Config->SortSection); else sortSections(Vec, Pat.SortInner); sortSections(Vec, Pat.SortOuter); } // Compute and remember which sections the InputSectionDescription matches. std::vector LinkerScript::computeInputSections(const InputSectionDescription *Cmd, const DenseMap &Order) { 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 (!Sec->Live || 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; std::string Filename = getFilename(Sec->File); if (!Cmd->FilePat.match(Filename) || Pat.ExcludedFilePat.match(Filename) || !Pat.SectionPat.match(Sec->Name)) continue; // It is safe to assume that Sec is an InputSection // because mergeable or EH input sections have already been // handled and eliminated. Ret.push_back(cast(Sec)); Sec->Assigned = true; } sortInputSections(MutableArrayRef(Ret).slice(SizeBefore), Pat, Order); } return Ret; } void LinkerScript::discard(ArrayRef V) { for (InputSection *S : V) { if (S == InX::ShStrTab || S == InX::Dynamic || S == InX::DynSymTab || S == InX::DynStrTab) error("discarding " + S->Name + " section is not allowed"); S->Assigned = false; S->Live = false; discard(S->DependentSections); } } std::vector LinkerScript::createInputSectionList( OutputSection &OutCmd, const DenseMap &Order) { std::vector Ret; for (BaseCommand *Base : OutCmd.SectionCommands) { if (auto *Cmd = dyn_cast(Base)) { Cmd->Sections = computeInputSections(Cmd, Order); Ret.insert(Ret.end(), Cmd->Sections.begin(), Cmd->Sections.end()); } } return Ret; } void LinkerScript::processSectionCommands() { // 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; // Ctx captures the local AddressState and makes it accessible deliberately. // This is needed as there are some cases where we cannot just // thread the current state through to a lambda function created by the // script parser. auto Deleter = make_unique(); Ctx = Deleter.get(); Ctx->OutSec = Aether; size_t I = 0; DenseMap Order = buildSectionOrder(); // Add input sections to output sections. for (BaseCommand *Base : SectionCommands) { // Handle symbol assignments outside of any output section. if (auto *Cmd = dyn_cast(Base)) { addSymbol(Cmd); continue; } if (auto *Sec = dyn_cast(Base)) { std::vector V = createInputSectionList(*Sec, Order); // The output section name `/DISCARD/' is special. // Any input section assigned to it is discarded. if (Sec->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 SectionCommands many more times, the easy // way to "make it as if it wasn't present" is to make it empty. if (!matchConstraints(V, Sec->Constraint)) { for (InputSectionBase *S : V) S->Assigned = false; Sec->SectionCommands.clear(); continue; } // A directive may contain symbol definitions like this: // ".foo : { ...; bar = .; }". Handle them. for (BaseCommand *Base : Sec->SectionCommands) 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 (Sec->SubalignExpr) { uint32_t Subalign = Sec->SubalignExpr().getValue(); for (InputSectionBase *S : V) S->Alignment = Subalign; } // Add input sections to an output section. for (InputSection *S : V) Sec->addSection(S); Sec->SectionIndex = I++; if (Sec->Noload) Sec->Type = SHT_NOBITS; } } Ctx = nullptr; } static OutputSection *findByName(ArrayRef Vec, StringRef Name) { for (BaseCommand *Base : Vec) if (auto *Sec = dyn_cast(Base)) if (Sec->Name == Name) return Sec; return nullptr; } static OutputSection *createSection(InputSectionBase *IS, StringRef OutsecName) { OutputSection *Sec = Script->createOutputSection(OutsecName, ""); Sec->addSection(cast(IS)); return Sec; } static OutputSection *addInputSec(StringMap &Map, InputSectionBase *IS, StringRef OutsecName) { // Sections with SHT_GROUP or SHF_GROUP attributes reach here only when the -r // option is given. A section with SHT_GROUP defines a "section group", and // its members have SHF_GROUP attribute. Usually these flags have already been // stripped by InputFiles.cpp as section groups are processed and uniquified. // However, for the -r option, we want to pass through all section groups // as-is because adding/removing members or merging them with other groups // change their semantics. if (IS->Type == SHT_GROUP || (IS->Flags & SHF_GROUP)) return createSection(IS, OutsecName); // Imagine .zed : { *(.foo) *(.bar) } script. Both foo and bar may have // relocation sections .rela.foo and .rela.bar for example. Most tools do // not allow multiple REL[A] sections for output section. Hence we // should combine these relocation sections into single output. // We skip synthetic sections because it can be .rela.dyn/.rela.plt or any // other REL[A] sections created by linker itself. if (!isa(IS) && (IS->Type == SHT_REL || IS->Type == SHT_RELA)) { auto *Sec = cast(IS); OutputSection *Out = Sec->getRelocatedSection()->getOutputSection(); if (Out->RelocationSection) { Out->RelocationSection->addSection(Sec); return nullptr; } Out->RelocationSection = createSection(IS, OutsecName); return Out->RelocationSection; } // When control reaches here, mergeable sections have already been merged into // synthetic sections. For relocatable case we want to create one output // section per syntetic section so that they have a valid sh_entsize. if (Config->Relocatable && (IS->Flags & SHF_MERGE)) return createSection(IS, 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. OutputSection *&Sec = Map[OutsecName]; if (Sec) { Sec->addSection(cast(IS)); return nullptr; } Sec = createSection(IS, OutsecName); return Sec; } // Add sections that didn't match any sections command. void LinkerScript::addOrphanSections() { unsigned End = SectionCommands.size(); StringMap Map; std::vector V; for (InputSectionBase *S : InputSections) { if (!S->Live || S->Parent) continue; StringRef Name = getOutputSectionName(S); if (Config->OrphanHandling == OrphanHandlingPolicy::Error) error(toString(S) + " is being placed in '" + Name + "'"); else if (Config->OrphanHandling == OrphanHandlingPolicy::Warn) warn(toString(S) + " is being placed in '" + Name + "'"); if (OutputSection *Sec = findByName(makeArrayRef(SectionCommands).slice(0, End), Name)) { Sec->addSection(cast(S)); continue; } if (OutputSection *OS = addInputSec(Map, S, Name)) V.push_back(OS); assert(S->getOutputSection()->SectionIndex == INT_MAX); } // If no SECTIONS command was given, we should insert sections commands // before others, so that we can handle scripts which refers them, // for example: "foo = ABSOLUTE(ADDR(.text)));". // When SECTIONS command is present we just add all orphans to the end. if (HasSectionsCommand) SectionCommands.insert(SectionCommands.end(), V.begin(), V.end()); else SectionCommands.insert(SectionCommands.begin(), V.begin(), V.end()); } uint64_t LinkerScript::advance(uint64_t Size, unsigned Alignment) { bool IsTbss = (Ctx->OutSec->Flags & SHF_TLS) && Ctx->OutSec->Type == SHT_NOBITS; uint64_t Start = IsTbss ? Dot + Ctx->ThreadBssOffset : Dot; Start = alignTo(Start, Alignment); uint64_t End = Start + Size; if (IsTbss) Ctx->ThreadBssOffset = End - Dot; else Dot = End; return End; } void LinkerScript::output(InputSection *S) { uint64_t Before = advance(0, 1); uint64_t Pos = advance(S->getSize(), S->Alignment); S->OutSecOff = Pos - S->getSize() - Ctx->OutSec->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) } Ctx->OutSec->Size = Pos - Ctx->OutSec->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 (Ctx->LMARegion) + Ctx->LMARegion->CurPos += Pos - Before; + // FIXME: should we also produce overflow errors for LMARegion? + if (Ctx->MemRegion) { uint64_t &CurOffset = Ctx->MemRegion->CurPos; CurOffset += Pos - Before; uint64_t CurSize = CurOffset - Ctx->MemRegion->Origin; if (CurSize > Ctx->MemRegion->Length) { uint64_t OverflowAmt = CurSize - Ctx->MemRegion->Length; error("section '" + Ctx->OutSec->Name + "' will not fit in region '" + Ctx->MemRegion->Name + "': overflowed by " + Twine(OverflowAmt) + " bytes"); } } } void LinkerScript::switchTo(OutputSection *Sec) { if (Ctx->OutSec == Sec) return; Ctx->OutSec = Sec; Ctx->OutSec->Addr = advance(0, Ctx->OutSec->Alignment); } // 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(OutputSection *Sec) { // If a memory region name was specified in the output section command, // then try to find that region first. if (!Sec->MemoryRegionName.empty()) { if (MemoryRegion *M = MemoryRegions.lookup(Sec->MemoryRegionName)) return M; error("memory region '" + Sec->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 (MemoryRegions.empty()) return nullptr; // See if a region can be found by matching section flags. for (auto &Pair : 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(OutputSection *Sec) { if (!(Sec->Flags & SHF_ALLOC)) Dot = 0; else if (Sec->AddrExpr) setDot(Sec->AddrExpr, Sec->Location, false); Ctx->MemRegion = Sec->MemRegion; + Ctx->LMARegion = Sec->LMARegion; if (Ctx->MemRegion) Dot = Ctx->MemRegion->CurPos; switchTo(Sec); if (Sec->LMAExpr) Ctx->LMAOffset = Sec->LMAExpr().getValue() - Dot; if (MemoryRegion *MR = Sec->LMARegion) - Ctx->LMAOffset = MR->Origin - Dot; + Ctx->LMAOffset = MR->CurPos - Dot; // 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 (Ctx->LMAOffset) Ctx->OutSec->LMAOffset = Ctx->LMAOffset; // The Size previously denoted how many InputSections had been added to this // section, and was used for sorting SHF_LINK_ORDER sections. Reset it to // compute the actual size value. Sec->Size = 0; // We visited SectionsCommands from processSectionCommands to // layout sections. Now, we visit SectionsCommands again to fix // section offsets. for (BaseCommand *Base : Sec->SectionCommands) { // This handles the assignments to symbol or to the dot. if (auto *Cmd = dyn_cast(Base)) { assignSymbol(Cmd, true); continue; } // Handle BYTE(), SHORT(), LONG(), or QUAD(). if (auto *Cmd = dyn_cast(Base)) { Cmd->Offset = Dot - Ctx->OutSec->Addr; Dot += Cmd->Size; if (Ctx->MemRegion) Ctx->MemRegion->CurPos += Cmd->Size; + if (Ctx->LMARegion) + Ctx->LMARegion->CurPos += Cmd->Size; Ctx->OutSec->Size = Dot - Ctx->OutSec->Addr; continue; } // Handle ASSERT(). if (auto *Cmd = dyn_cast(Base)) { Cmd->Expression(); continue; } // 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 (InputSection *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(Ctx->OutSec == Sec->getParent()); output(Sec); } } } 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. llvm::erase_if(SectionCommands, [&](BaseCommand *Base) { if (auto *Sec = dyn_cast(Base)) return !Sec->Live; return false; }); } static bool isAllSectionDescription(const OutputSection &Cmd) { for (BaseCommand *Base : Cmd.SectionCommands) if (!isa(*Base)) return false; return true; } void LinkerScript::adjustSectionsBeforeSorting() { // If the output section contains only symbol assignments, create a // corresponding output section. The issue is what to do with linker script // like ".foo : { symbol = 42; }". One option would be to convert it to // "symbol = 42;". That is, move the symbol out of the empty section // description. That seems to be what bfd does for this simple case. The // problem is that this is not completely general. bfd will give up and // create a dummy section too if there is a ". = . + 1" inside the section // for example. // Given that we want to create the section, we have to worry what impact // it will have on the link. For example, if we just create a section with // 0 for flags, it would change which PT_LOADs are created. // We could remember that that particular section is dummy and ignore it in // other parts of the linker, but unfortunately there are quite a few places // that would need to change: // * The program header creation. // * The orphan section placement. // * The address assignment. // The other option is to pick flags that minimize the impact the section // will have on the rest of the linker. That is why we copy the flags from // the previous sections. Only a few flags are needed to keep the impact low. uint64_t Flags = SHF_ALLOC; for (BaseCommand *Cmd : SectionCommands) { auto *Sec = dyn_cast(Cmd); if (!Sec) continue; if (Sec->Live) { Flags = Sec->Flags & (SHF_ALLOC | SHF_WRITE | SHF_EXECINSTR); continue; } if (isAllSectionDescription(*Sec)) continue; Sec->Live = true; Sec->Flags = Flags; } } void LinkerScript::adjustSectionsAfterSorting() { // Try and find an appropriate memory region to assign offsets in. for (BaseCommand *Base : SectionCommands) { if (auto *Sec = dyn_cast(Base)) { if (!Sec->Live) continue; if (!Sec->LMARegionName.empty()) { if (MemoryRegion *M = MemoryRegions.lookup(Sec->LMARegionName)) Sec->LMARegion = M; else error("memory region '" + Sec->LMARegionName + "' not declared"); } Sec->MemRegion = findMemoryRegion(Sec); // Handle align (e.g. ".foo : ALIGN(16) { ... }"). if (Sec->AlignExpr) Sec->Alignment = std::max(Sec->Alignment, Sec->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(PhdrsCommands.begin(), PhdrsCommands.end(), [](const PhdrsCommand &Cmd) { return Cmd.Type == PT_LOAD; }); if (FirstPtLoad != 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 : SectionCommands) { auto *Sec = dyn_cast(Base); if (!Sec) continue; if (Sec->Phdrs.empty()) { // To match the bfd linker script behaviour, only propagate program // headers to sections that are allocated. if (Sec->Flags & SHF_ALLOC) Sec->Phdrs = DefPhdrs; } else { DefPhdrs = Sec->Phdrs; } } } static OutputSection *findFirstSection(PhdrEntry *Load) { for (OutputSection *Sec : OutputSections) if (Sec->PtLoad == Load) return Sec; return nullptr; } // Try to find an address for the file and program headers output sections, // which were unconditionally added to the first PT_LOAD segment earlier. // // When using the default layout, we check if the headers fit below the first // allocated section. When using a linker script, we also check if the headers // are covered by the output section. This allows omitting the headers by not // leaving enough space for them in the linker script; this pattern is common // in embedded systems. // // If there isn't enough space for these sections, we'll remove them from the // PT_LOAD segment, and we'll also remove the PT_PHDR segment. void LinkerScript::allocateHeaders(std::vector &Phdrs) { uint64_t Min = std::numeric_limits::max(); for (OutputSection *Sec : OutputSections) if (Sec->Flags & SHF_ALLOC) Min = std::min(Min, Sec->Addr); auto It = llvm::find_if( Phdrs, [](const PhdrEntry *E) { return E->p_type == PT_LOAD; }); if (It == Phdrs.end()) return; PhdrEntry *FirstPTLoad = *It; uint64_t HeaderSize = getHeaderSize(); // When linker script with SECTIONS is being used, don't output headers // unless there's a space for them. uint64_t Base = HasSectionsCommand ? alignDown(Min, Config->MaxPageSize) : 0; if (HeaderSize <= Min - Base || Script->hasPhdrsCommands()) { Min = alignDown(Min - HeaderSize, Config->MaxPageSize); Out::ElfHeader->Addr = Min; Out::ProgramHeaders->Addr = Min + Out::ElfHeader->Size; return; } Out::ElfHeader->PtLoad = nullptr; Out::ProgramHeaders->PtLoad = nullptr; FirstPTLoad->FirstSec = findFirstSection(FirstPTLoad); llvm::erase_if(Phdrs, [](const PhdrEntry *E) { return E->p_type == PT_PHDR; }); } LinkerScript::AddressState::AddressState() { for (auto &MRI : Script->MemoryRegions) { MemoryRegion *MR = MRI.second; MR->CurPos = MR->Origin; } } static uint64_t getInitialDot() { // By default linker scripts use an initial value of 0 for '.', // but prefer -image-base if set. if (Script->HasSectionsCommand) return Config->ImageBase ? *Config->ImageBase : 0; uint64_t StartAddr = UINT64_MAX; // 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); return std::min(StartAddr, Target->getImageBase() + elf::getHeaderSize()); } // Here we assign addresses as instructed by linker script SECTIONS // sub-commands. Doing that allows us to use final VA values, so here // we also handle rest commands like symbol assignments and ASSERTs. void LinkerScript::assignAddresses() { Dot = getInitialDot(); auto Deleter = make_unique(); Ctx = Deleter.get(); ErrorOnMissingSection = true; switchTo(Aether); for (BaseCommand *Base : SectionCommands) { if (auto *Cmd = dyn_cast(Base)) { assignSymbol(Cmd, false); continue; } if (auto *Cmd = dyn_cast(Base)) { Cmd->Expression(); continue; } assignOffsets(cast(Base)); } Ctx = nullptr; } // 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 : PhdrsCommands) { PhdrEntry *Phdr = make(Cmd.Type, Cmd.Flags ? *Cmd.Flags : PF_R); 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; } Ret.push_back(Phdr); } // Add output sections to program headers. for (OutputSection *Sec : OutputSections) { // Assign headers specified by linker script for (size_t Id : getPhdrIndices(Sec)) { Ret[Id]->add(Sec); if (!PhdrsCommands[Id].Flags.hasValue()) Ret[Id]->p_flags |= Sec->getPhdrFlags(); } } return Ret; } // Returns true if we should emit an .interp section. // // We usually do. But if PHDRS commands are given, and // no PT_INTERP is there, there's no place to emit an // .interp, so we don't do that in that case. bool LinkerScript::needsInterpSection() { if (PhdrsCommands.empty()) return true; for (PhdrsCommand &Cmd : PhdrsCommands) if (Cmd.Type == PT_INTERP) return true; return false; } ExprValue LinkerScript::getSymbolValue(StringRef Name, const Twine &Loc) { if (Name == ".") { if (Ctx) return {Ctx->OutSec, false, Dot - Ctx->OutSec->Addr, Loc}; error(Loc + ": unable to get location counter value"); return 0; } if (Symbol *Sym = Symtab->find(Name)) { if (auto *DS = dyn_cast(Sym)) return {DS->Section, false, DS->Value, Loc}; if (auto *SS = dyn_cast(Sym)) if (!ErrorOnMissingSection || SS->CopyRelSec) return {SS->CopyRelSec, false, 0, Loc}; } error(Loc + ": symbol not found: " + Name); return 0; } // Returns the index of the segment named Name. static Optional getPhdrIndex(ArrayRef Vec, StringRef Name) { for (size_t I = 0; I < Vec.size(); ++I) if (Vec[I].Name == Name) return I; return None; } // 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 *Cmd) { std::vector Ret; for (StringRef S : Cmd->Phdrs) { if (Optional Idx = getPhdrIndex(PhdrsCommands, S)) Ret.push_back(*Idx); else if (S != "NONE") error(Cmd->Location + ": section header '" + S + "' is not listed in PHDRS"); } return Ret; } Index: head/contrib/llvm/tools/lld/ELF/LinkerScript.h =================================================================== --- head/contrib/llvm/tools/lld/ELF/LinkerScript.h (revision 328545) +++ head/contrib/llvm/tools/lld/ELF/LinkerScript.h (revision 328546) @@ -1,296 +1,297 @@ //===- 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/Common/LLVM.h" #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/DenseSet.h" #include "llvm/ADT/MapVector.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/MemoryBuffer.h" #include #include #include #include #include namespace lld { namespace elf { class Defined; class Symbol; class InputSectionBase; class InputSection; class OutputSection; class InputSectionBase; class SectionBase; // This represents an r-value in the linker script. struct ExprValue { ExprValue(SectionBase *Sec, bool ForceAbsolute, uint64_t Val, const Twine &Loc) : Sec(Sec), ForceAbsolute(ForceAbsolute), Val(Val), Loc(Loc.str()) {} ExprValue(uint64_t Val) : ExprValue(nullptr, false, Val, "") {} bool isAbsolute() const { return ForceAbsolute || Sec == nullptr; } uint64_t getValue() const; uint64_t getSecAddr() const; uint64_t getSectionOffset() const; // If a value is relative to a section, it has a non-null Sec. SectionBase *Sec; // True if this expression is enclosed in ABSOLUTE(). // This flag affects the return value of getValue(). bool ForceAbsolute; uint64_t Val; uint64_t Alignment = 1; // Original source location. Used for error messages. std::string Loc; }; // 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) ByteKind // 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) { return C->Kind == AssignmentKind; } // The LHS of an expression. Name is either a symbol name or ".". StringRef Name; Defined *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 { MemoryRegion(StringRef Name, uint64_t Origin, uint64_t Length, uint32_t Flags, uint32_t NegFlags) : Name(Name), Origin(Origin), Length(Length), Flags(Flags), NegFlags(NegFlags) {} std::string Name; uint64_t Origin; uint64_t Length; uint32_t Flags; uint32_t NegFlags; uint64_t CurPos = 0; }; // 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; }; class ThunkSection; struct InputSectionDescription : BaseCommand { InputSectionDescription(StringRef FilePattern) : BaseCommand(InputSectionKind), FilePat(FilePattern) {} static bool classof(const BaseCommand *C) { return C->Kind == InputSectionKind; } StringMatcher FilePat; // Input sections that matches at least one of SectionPatterns // will be associated with this InputSectionDescription. std::vector SectionPatterns; std::vector Sections; // Temporary record of synthetic ThunkSection instances and the pass that // they were created in. This is used to insert newly created ThunkSections // into Sections at the end of a createThunks() pass. std::vector> ThunkSections; }; // Represents an ASSERT(). struct AssertCommand : BaseCommand { AssertCommand(Expr E) : BaseCommand(AssertKind), Expression(E) {} static bool classof(const BaseCommand *C) { return C->Kind == AssertKind; } Expr Expression; }; // Represents BYTE(), SHORT(), LONG(), or QUAD(). struct ByteCommand : BaseCommand { ByteCommand(Expr E, unsigned Size) : BaseCommand(ByteKind), Expression(E), Size(Size) {} static bool classof(const BaseCommand *C) { return C->Kind == ByteKind; } Expr Expression; unsigned Offset; unsigned Size; }; struct PhdrsCommand { StringRef Name; unsigned Type = llvm::ELF::PT_NULL; bool HasFilehdr = false; bool HasPhdrs = false; llvm::Optional Flags; Expr LMAExpr = nullptr; }; class LinkerScript final { // Temporary state used in processSectionCommands() and assignAddresses() // that must be reinitialized for each call to the above functions, and must // not be used outside of the scope of a call to the above functions. struct AddressState { AddressState(); uint64_t ThreadBssOffset = 0; OutputSection *OutSec = nullptr; MemoryRegion *MemRegion = nullptr; + MemoryRegion *LMARegion = nullptr; uint64_t LMAOffset = 0; }; llvm::DenseMap NameToOutputSection; void addSymbol(SymbolAssignment *Cmd); void assignSymbol(SymbolAssignment *Cmd, bool InSec); void setDot(Expr E, const Twine &Loc, bool InSec); std::vector computeInputSections(const InputSectionDescription *, const llvm::DenseMap &Order); std::vector createInputSectionList(OutputSection &Cmd, const llvm::DenseMap &Order); std::vector getPhdrIndices(OutputSection *Sec); MemoryRegion *findMemoryRegion(OutputSection *Sec); void switchTo(OutputSection *Sec); uint64_t advance(uint64_t Size, unsigned Align); void output(InputSection *Sec); void assignOffsets(OutputSection *Sec); // Ctx captures the local AddressState and makes it accessible // deliberately. This is needed as there are some cases where we cannot just // thread the current state through to a lambda function created by the // script parser. // This should remain a plain pointer as its lifetime is smaller than // LinkerScript. AddressState *Ctx = nullptr; OutputSection *Aether; uint64_t Dot; public: OutputSection *createOutputSection(StringRef Name, StringRef Location); OutputSection *getOrCreateOutputSection(StringRef Name); bool hasPhdrsCommands() { return !PhdrsCommands.empty(); } uint64_t getDot() { return Dot; } void discard(ArrayRef V); ExprValue getSymbolValue(StringRef Name, const Twine &Loc); void addOrphanSections(); void removeEmptyCommands(); void adjustSectionsBeforeSorting(); void adjustSectionsAfterSorting(); std::vector createPhdrs(); bool needsInterpSection(); bool shouldKeep(InputSectionBase *S); void assignAddresses(); void allocateHeaders(std::vector &Phdrs); void processSectionCommands(); // SECTIONS command list. std::vector SectionCommands; // PHDRS command list. std::vector PhdrsCommands; bool HasSectionsCommand = false; bool ErrorOnMissingSection = 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::MapVector MemoryRegions; // A list of symbols referenced by the script. std::vector ReferencedSymbols; }; extern LinkerScript *Script; } // end namespace elf } // end namespace lld #endif // LLD_ELF_LINKER_SCRIPT_H Index: head/contrib/llvm/tools/lld/ELF/Writer.cpp =================================================================== --- head/contrib/llvm/tools/lld/ELF/Writer.cpp (revision 328545) +++ head/contrib/llvm/tools/lld/ELF/Writer.cpp (revision 328546) @@ -1,2071 +1,2072 @@ //===- 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 "AArch64ErrataFix.h" #include "Config.h" #include "Filesystem.h" #include "LinkerScript.h" #include "MapFile.h" #include "OutputSections.h" #include "Relocations.h" #include "Strings.h" #include "SymbolTable.h" #include "Symbols.h" #include "SyntheticSections.h" #include "Target.h" #include "lld/Common/Memory.h" #include "lld/Common/Threads.h" #include "llvm/ADT/StringMap.h" #include "llvm/ADT/StringSwitch.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: Writer() : Buffer(errorHandler().OutputBuffer) {} typedef typename ELFT::Shdr Elf_Shdr; typedef typename ELFT::Ehdr Elf_Ehdr; typedef typename ELFT::Phdr Elf_Phdr; void run(); private: void copyLocalSymbols(); void addSectionSymbols(); void forEachRelSec(std::function Fn); void sortSections(); void resolveShfLinkOrder(); void sortInputSections(); void finalizeSections(); void setReservedSymbolSections(); std::vector createPhdrs(); void removeEmptyPTLoad(); void addPtArmExid(std::vector &Phdrs); void assignFileOffsets(); void assignFileOffsetsBinary(); void setPhdrs(); void fixSectionAlignments(); void openFile(); void writeTrapInstr(); void writeHeader(); void writeSections(); void writeSectionsBinary(); void writeBuildId(); std::unique_ptr &Buffer; void addRelIpltSymbols(); void addStartEndSymbols(); void addStartStopSymbols(OutputSection *Sec); uint64_t getEntryAddr(); std::vector Phdrs; uint64_t FileSize; uint64_t SectionHeaderOff; bool HasGotBaseSym = false; }; } // anonymous namespace StringRef elf::getOutputSectionName(InputSectionBase *S) { // ".zdebug_" is a prefix for ZLIB-compressed sections. // Because we decompressed input sections, we want to remove 'z'. if (S->Name.startswith(".zdebug_")) return Saver.save("." + S->Name.substr(2)); if (Config->Relocatable) return S->Name; // This is for --emit-relocs. If .text.foo is emitted as .text.bar, we want // to emit .rela.text.foo as .rela.text.bar for consistency (this is not // technically required, but not doing it is odd). This code guarantees that. if ((S->Type == SHT_REL || S->Type == SHT_RELA) && !isa(S)) { OutputSection *Out = cast(S)->getRelocatedSection()->getOutputSection(); if (S->Type == SHT_RELA) return Saver.save(".rela" + Out->Name); return Saver.save(".rel" + Out->Name); } for (StringRef V : {".text.", ".rodata.", ".data.rel.ro.", ".data.", ".bss.rel.ro.", ".bss.", ".init_array.", ".fini_array.", ".ctors.", ".dtors.", ".tbss.", ".gcc_except_table.", ".tdata.", ".ARM.exidx.", ".ARM.extab."}) { StringRef Prefix = V.drop_back(); if (S->Name.startswith(V) || S->Name == Prefix) return Prefix; } // CommonSection is identified as "COMMON" in linker scripts. // By default, it should go to .bss section. if (S->Name == "COMMON") return ".bss"; return S->Name; } static bool needsInterpSection() { return !SharedFiles.empty() && !Config->DynamicLinker.empty() && Script->needsInterpSection(); } template void elf::writeResult() { Writer().run(); } template void Writer::removeEmptyPTLoad() { llvm::erase_if(Phdrs, [&](const PhdrEntry *P) { if (P->p_type != PT_LOAD) return false; if (!P->FirstSec) return true; uint64_t Size = P->LastSec->Addr + P->LastSec->Size - P->FirstSec->Addr; return Size == 0; }); } template static void combineEhFrameSections() { for (InputSectionBase *&S : InputSections) { EhInputSection *ES = dyn_cast(S); if (!ES || !ES->Live) continue; InX::EhFrame->addSection(ES); S = nullptr; } std::vector &V = InputSections; V.erase(std::remove(V.begin(), V.end(), nullptr), V.end()); } static Defined *addOptionalRegular(StringRef Name, SectionBase *Sec, uint64_t Val, uint8_t StOther = STV_HIDDEN, uint8_t Binding = STB_GLOBAL) { Symbol *S = Symtab->find(Name); if (!S || S->isDefined()) return nullptr; Symbol *Sym = Symtab->addRegular(Name, StOther, STT_NOTYPE, Val, /*Size=*/0, Binding, Sec, /*File=*/nullptr); return cast(Sym); } // The linker is expected to define some symbols depending on // the linking result. This function defines such symbols. void elf::addReservedSymbols() { if (Config->EMachine == EM_MIPS) { // 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->addAbsolute("_gp", STV_HIDDEN, STB_GLOBAL); // On MIPS O32 ABI, _gp_disp is a magic symbol designates offset between // start of function and 'gp' pointer into GOT. if (Symtab->find("_gp_disp")) ElfSym::MipsGpDisp = Symtab->addAbsolute("_gp_disp", STV_HIDDEN, STB_GLOBAL); // The __gnu_local_gp is a magic symbol equal to the current value of 'gp' // pointer. This symbol is used in the code generated by .cpload pseudo-op // in case of using -mno-shared option. // https://sourceware.org/ml/binutils/2004-12/msg00094.html if (Symtab->find("__gnu_local_gp")) ElfSym::MipsLocalGp = Symtab->addAbsolute("__gnu_local_gp", STV_HIDDEN, STB_GLOBAL); } ElfSym::GlobalOffsetTable = addOptionalRegular( "_GLOBAL_OFFSET_TABLE_", Out::ElfHeader, Target->GotBaseSymOff); // __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. // __executable_start is not documented, but the expectation of at // least the android libc is that it points to the elf header too. // __dso_handle symbol is passed to cxa_finalize as a marker to identify // each DSO. The address of the symbol doesn't matter as long as they are // different in different DSOs, so we chose the start address of the DSO. for (const char *Name : {"__ehdr_start", "__executable_start", "__dso_handle"}) addOptionalRegular(Name, Out::ElfHeader, 0, STV_HIDDEN); // If linker script do layout we do not need to create any standart symbols. if (Script->HasSectionsCommand) return; auto Add = [](StringRef S, int64_t Pos) { return addOptionalRegular(S, Out::ElfHeader, Pos, STV_DEFAULT); }; ElfSym::Bss = Add("__bss_start", 0); ElfSym::End1 = Add("end", -1); ElfSym::End2 = Add("_end", -1); ElfSym::Etext1 = Add("etext", -1); ElfSym::Etext2 = Add("_etext", -1); ElfSym::Edata1 = Add("edata", -1); ElfSym::Edata2 = Add("_edata", -1); } static OutputSection *findSection(StringRef Name) { for (BaseCommand *Base : Script->SectionCommands) if (auto *Sec = dyn_cast(Base)) if (Sec->Name == Name) return Sec; return nullptr; } // Initialize Out members. template static void createSyntheticSections() { // Initialize all pointers with NULL. This is needed because // you can call lld::elf::main more than once as a library. memset(&Out::First, 0, sizeof(Out)); auto Add = [](InputSectionBase *Sec) { InputSections.push_back(Sec); }; InX::DynStrTab = make(".dynstr", true); InX::Dynamic = make>(); if (Config->AndroidPackDynRelocs) { InX::RelaDyn = make>( Config->IsRela ? ".rela.dyn" : ".rel.dyn"); } else { InX::RelaDyn = make>( Config->IsRela ? ".rela.dyn" : ".rel.dyn", Config->ZCombreloc); } InX::ShStrTab = make(".shstrtab", false); Out::ProgramHeaders = make("", 0, SHF_ALLOC); Out::ProgramHeaders->Alignment = Config->Wordsize; if (needsInterpSection()) { InX::Interp = createInterpSection(); Add(InX::Interp); } else { InX::Interp = nullptr; } 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::Bss = make(".bss", 0, 1); Add(InX::Bss); // If there is a SECTIONS command and a .data.rel.ro section name use name // .data.rel.ro.bss so that we match in the .data.rel.ro output section. // This makes sure our relro is contiguous. bool HasDataRelRo = Script->HasSectionsCommand && findSection(".data.rel.ro"); InX::BssRelRo = make( HasDataRelRo ? ".data.rel.ro.bss" : ".bss.rel.ro", 0, 1); Add(InX::BssRelRo); // Add MIPS-specific sections. if (Config->EMachine == EM_MIPS) { if (!Config->Shared && Config->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 (Config->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) { InX::HashTab = make(); Add(InX::HashTab); } Add(InX::Dynamic); Add(InX::DynStrTab); Add(InX::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 = createGdbIndex(); 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. InX::RelaPlt = make>( Config->IsRela ? ".rela.plt" : ".rel.plt", false /*Sort*/); Add(InX::RelaPlt); // The RelaIplt immediately follows .rel.plt (.rel.dyn for ARM) to ensure // that the IRelative relocations are processed last by the dynamic loader. // We cannot place the iplt section in .rel.dyn when Android relocation // packing is enabled because that would cause a section type mismatch. // However, because the Android dynamic loader reads .rel.plt after .rel.dyn, // we can get the desired behaviour by placing the iplt section in .rel.plt. InX::RelaIplt = make>( (Config->EMachine == EM_ARM && !Config->AndroidPackDynRelocs) ? ".rel.dyn" : InX::RelaPlt->Name, false /*Sort*/); Add(InX::RelaIplt); InX::Plt = make(Target->PltHeaderSize); Add(InX::Plt); InX::Iplt = make(0); Add(InX::Iplt); if (!Config->Relocatable) { if (Config->EhFrameHdr) { InX::EhFrameHdr = make(); Add(InX::EhFrameHdr); } InX::EhFrame = make(); Add(InX::EhFrame); } if (InX::SymTab) Add(InX::SymTab); Add(InX::ShStrTab); if (InX::StrTab) Add(InX::StrTab); if (Config->EMachine == EM_ARM && !Config->Relocatable) // Add a sentinel to terminate .ARM.exidx. It helps an unwinder // to find the exact address range of the last entry. Add(make()); } // 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(); if (!Config->Relocatable) combineEhFrameSections(); // We want to process linker script commands. When SECTIONS command // is given we let it create sections. Script->processSectionCommands(); // Linker scripts controls how input sections are assigned to output sections. // Input sections that were not handled by scripts are called "orphans", and // they are assigned to output sections by the default rule. Process that. Script->addOrphanSections(); 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; Script->assignAddresses(); // If -compressed-debug-sections is specified, we need to compress // .debug_* sections. Do it right now because it changes the size of // output sections. for (OutputSection *Sec : OutputSections) Sec->maybeCompress(); Script->allocateHeaders(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(); if (Config->Relocatable) { for (OutputSection *Sec : OutputSections) Sec->Addr = 0; } // 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) { writeTrapInstr(); writeHeader(); writeSections(); } else { writeSectionsBinary(); } // 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(); if (errorCount()) return; if (auto E = Buffer->commit()) error("failed to write to the output file: " + toString(std::move(E))); } static bool shouldKeepInSymtab(SectionBase *Sec, StringRef SymName, const Symbol &B) { if (B.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 Symbol &B) { if (!B.isLocal() && !B.IsUsedInRegularObj) return false; if (auto *D = dyn_cast(&B)) { // Always include absolute symbols. SectionBase *Sec = D->Section; if (!Sec) return true; Sec = Sec->Repl; // Exclude symbols pointing to garbage-collected sections. if (isa(Sec) && !Sec->Live) return false; if (auto *S = dyn_cast(Sec)) if (!S->getSectionPiece(D->Value)->Live) return false; return true; } return B.Used; } // Local symbols are not in the linker's symbol table. This function scans // each object file's symbol table to copy local symbols to the output. template void Writer::copyLocalSymbols() { if (!InX::SymTab) return; for (InputFile *File : ObjectFiles) { ObjFile *F = cast>(File); for (Symbol *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 a section symbol for each output section so that we can represent // relocations that point to the section. If we know that no relocation is // referring to a section (that happens if the section is a synthetic one), we // don't create a section symbol for that section. for (BaseCommand *Base : Script->SectionCommands) { auto *Sec = dyn_cast(Base); if (!Sec) continue; auto I = llvm::find_if(Sec->SectionCommands, [](BaseCommand *Base) { if (auto *ISD = dyn_cast(Base)) return !ISD->Sections.empty(); return false; }); if (I == Sec->SectionCommands.end()) continue; InputSection *IS = cast(*I)->Sections[0]; // Relocations are not using REL[A] section symbols. if (IS->Type == SHT_REL || IS->Type == SHT_RELA) continue; // Unlike other synthetic sections, mergeable output sections contain data // copied from input sections, and there may be a relocation pointing to its // contents if -r or -emit-reloc are given. if (isa(IS) && !(IS->Flags & SHF_MERGE)) continue; auto *Sym = make(IS->File, "", STB_LOCAL, /*StOther=*/0, STT_SECTION, /*Value=*/0, /*Size=*/0, IS); 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. static bool 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->getParent()) 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->getParent()) return Config->ZNow; // .dynamic section contains data for the dynamic linker, and // there's no need to write to it at runtime, so it's better to put // it into RELRO. if (Sec == InX::Dynamic->getParent()) return true; // Sections with some special names are put into RELRO. This is a // bit unfortunate because section names shouldn't be significant in // ELF in spirit. But in reality many linker features depend on // magic section names. StringRef S = Sec->Name; return S == ".data.rel.ro" || S == ".bss.rel.ro" || S == ".ctors" || S == ".dtors" || S == ".jcr" || S == ".eh_frame" || S == ".openbsd.randomdata"; } // 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 compareSections(const BaseCommand *ACmd, const BaseCommand *BCmd) { const OutputSection *A = cast(ACmd); const OutputSection *B = cast(BCmd); 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; } void PhdrEntry::add(OutputSection *Sec) { LastSec = Sec; if (!FirstSec) FirstSec = Sec; p_align = std::max(p_align, Sec->Alignment); if (p_type == PT_LOAD) Sec->PtLoad = this; } // 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 (!Config->Static) return; StringRef S = Config->IsRela ? "__rela_iplt_start" : "__rel_iplt_start"; addOptionalRegular(S, InX::RelaIplt, 0, STV_HIDDEN, STB_WEAK); S = Config->IsRela ? "__rela_iplt_end" : "__rel_iplt_end"; addOptionalRegular(S, InX::RelaIplt, -1, STV_HIDDEN, STB_WEAK); } template void Writer::forEachRelSec(std::function Fn) { // Scan all relocations. Each relocation goes through a series // of tests to determine if it needs special treatment, such as // creating GOT, PLT, copy relocations, etc. // Note that relocations for non-alloc sections are directly // processed by InputSection::relocateNonAlloc. for (InputSectionBase *IS : InputSections) if (IS->Live && isa(IS) && (IS->Flags & SHF_ALLOC)) Fn(*IS); for (EhInputSection *ES : InX::EhFrame->Sections) Fn(*ES); } // This function generates assignments for predefined symbols (e.g. _end or // _etext) and inserts them into the commands sequence to be processed at the // appropriate time. This ensures that the value is going to be correct by the // time any references to these symbols are processed and is equivalent to // defining these symbols explicitly in the linker script. template void Writer::setReservedSymbolSections() { if (ElfSym::GlobalOffsetTable) { // The _GLOBAL_OFFSET_TABLE_ symbol is defined by target convention to // be at some offset from the base of the .got section, usually 0 or the end // of the .got InputSection *GotSection = InX::MipsGot ? cast(InX::MipsGot) : cast(InX::Got); ElfSym::GlobalOffsetTable->Section = GotSection; } PhdrEntry *Last = nullptr; PhdrEntry *LastRO = nullptr; for (PhdrEntry *P : Phdrs) { if (P->p_type != PT_LOAD) continue; Last = P; if (!(P->p_flags & PF_W)) LastRO = P; } if (LastRO) { // _etext is the first location after the last read-only loadable segment. if (ElfSym::Etext1) ElfSym::Etext1->Section = LastRO->LastSec; if (ElfSym::Etext2) ElfSym::Etext2->Section = LastRO->LastSec; } if (Last) { // _edata points to the end of the last mapped initialized section. OutputSection *Edata = nullptr; for (OutputSection *OS : OutputSections) { if (OS->Type != SHT_NOBITS) Edata = OS; if (OS == Last->LastSec) break; } if (ElfSym::Edata1) ElfSym::Edata1->Section = Edata; if (ElfSym::Edata2) ElfSym::Edata2->Section = Edata; // _end is the first location after the uninitialized data region. if (ElfSym::End1) ElfSym::End1->Section = Last->LastSec; if (ElfSym::End2) ElfSym::End2->Section = Last->LastSec; } if (ElfSym::Bss) ElfSym::Bss->Section = findSection(".bss"); // Setup MIPS _gp_disp/__gnu_local_gp symbols which should // be equal to the _gp symbol's value. if (ElfSym::MipsGp) { // Find GP-relative section with the lowest address // and use this address to calculate default _gp value. for (OutputSection *OS : OutputSections) { if (OS->Flags & SHF_MIPS_GPREL) { ElfSym::MipsGp->Section = OS; ElfSym::MipsGp->Value = 0x7ff0; break; } } } } // 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 int getRankProximityAux(OutputSection *A, OutputSection *B) { return countLeadingZeros(A->SortRank ^ B->SortRank); } static int getRankProximity(OutputSection *A, BaseCommand *B) { if (auto *Sec = dyn_cast(B)) if (Sec->Live) return getRankProximityAux(A, Sec); return -1; } // 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 findOrphanPos is the // one in charge of deciding the order of the sections. // We don't want to go over changes to '.', 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; } // 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 = cast(*E); // Find the first element that has as close a rank as possible. auto I = std::max_element(B, E, [=](BaseCommand *A, BaseCommand *B) { return getRankProximity(Sec, A) < getRankProximity(Sec, B); }); if (I == E) return E; // Consider all existing sections with the same proximity. int Proximity = getRankProximity(Sec, *I); for (; I != E; ++I) { auto *CurSec = dyn_cast(*I); if (!CurSec || !CurSec->Live) continue; if (getRankProximity(Sec, CurSec) != Proximity || Sec->SortRank < CurSec->SortRank) break; } auto IsLiveSection = [](BaseCommand *Cmd) { auto *OS = dyn_cast(Cmd); return OS && OS->Live; }; auto J = std::find_if(llvm::make_reverse_iterator(I), llvm::make_reverse_iterator(B), IsLiveSection); I = J.base(); // As a special case, if the orphan section is the last section, put // it at the very end, past any other commands. // This matches bfd's behavior and is convenient when the linker script fully // specifies the start of the file, but doesn't care about the end (the non // alloc sections for example). auto NextSec = std::find_if(I, E, IsLiveSection); if (NextSec == E) return E; while (I != E && shouldSkip(*I)) ++I; return I; } // If no layout was provided by linker script, we want to apply default // sorting for special input sections and handle --symbol-ordering-file. template void Writer::sortInputSections() { assert(!Script->HasSectionsCommand); // Sort input sections by priority using the list provided // by --symbol-ordering-file. DenseMap Order = buildSectionOrder(); if (!Order.empty()) for (BaseCommand *Base : Script->SectionCommands) if (auto *Sec = dyn_cast(Base)) if (Sec->Live) Sec->sort([&](InputSectionBase *S) { return Order.lookup(S); }); // Sort input sections by section name suffixes for // __attribute__((init_priority(N))). if (OutputSection *Sec = findSection(".init_array")) Sec->sortInitFini(); if (OutputSection *Sec = findSection(".fini_array")) Sec->sortInitFini(); // Sort input sections by the special rule for .ctors and .dtors. if (OutputSection *Sec = findSection(".ctors")) Sec->sortCtorsDtors(); if (OutputSection *Sec = findSection(".dtors")) Sec->sortCtorsDtors(); } template void Writer::sortSections() { Script->adjustSectionsBeforeSorting(); // Don't sort if using -r. It is not necessary and we want to preserve the // relative order for SHF_LINK_ORDER sections. if (Config->Relocatable) return; for (BaseCommand *Base : Script->SectionCommands) if (auto *Sec = dyn_cast(Base)) Sec->SortRank = getSectionRank(Sec); if (!Script->HasSectionsCommand) { sortInputSections(); // We know that all the OutputSections are contiguous in this case. auto E = Script->SectionCommands.end(); auto I = Script->SectionCommands.begin(); auto IsSection = [](BaseCommand *Base) { return isa(Base); }; I = std::find_if(I, E, IsSection); E = std::find_if(llvm::make_reverse_iterator(E), llvm::make_reverse_iterator(I), IsSection) .base(); std::stable_sort(I, E, compareSections); return; } // Orphan sections are sections present in the input files which are // not explicitly placed into the output file by the linker script. // // The sections in the linker script are already in the correct // order. We have to figuere out where to insert the orphan // sections. // // The order of the sections in the script is arbitrary and may not agree with // compareSections. 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: // * Sort only the orphan sections. They are in the end right now. // * Move each orphan section to its preferred position. We try // to put each section in the last position where it it can share // a PT_LOAD. // // There is some ambiguity as to where exactly a new entry should be // inserted, because 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. auto I = Script->SectionCommands.begin(); auto E = Script->SectionCommands.end(); auto NonScriptI = std::find_if(I, E, [](BaseCommand *Base) { if (auto *Sec = dyn_cast(Base)) return Sec->Live && Sec->SectionIndex == INT_MAX; return false; }); // Sort the orphan sections. std::stable_sort(NonScriptI, E, compareSections); // As a horrible special case, skip the first . assignment if it is before any // section. We do this because it is common to set a load address by starting // the script with ". = 0xabcd" and the expectation is that every section is // after that. auto FirstSectionOrDotAssignment = std::find_if(I, E, [](BaseCommand *Cmd) { return !shouldSkip(Cmd); }); if (FirstSectionOrDotAssignment != E && isa(**FirstSectionOrDotAssignment)) ++FirstSectionOrDotAssignment; I = FirstSectionOrDotAssignment; while (NonScriptI != E) { auto Pos = findOrphanPos(I, NonScriptI); OutputSection *Orphan = cast(*NonScriptI); // As an optimization, find all sections with the same sort rank // and insert them with one rotate. unsigned Rank = Orphan->SortRank; auto End = std::find_if(NonScriptI + 1, E, [=](BaseCommand *Cmd) { return cast(Cmd)->SortRank != Rank; }); std::rotate(Pos, NonScriptI, End); NonScriptI = End; } Script->adjustSectionsAfterSorting(); } static bool compareByFilePosition(InputSection *A, InputSection *B) { // Synthetic, i. e. a sentinel section, should go last. if (A->kind() == InputSectionBase::Synthetic || B->kind() == InputSectionBase::Synthetic) return A->kind() != InputSectionBase::Synthetic; InputSection *LA = A->getLinkOrderDep(); InputSection *LB = B->getLinkOrderDep(); OutputSection *AOut = LA->getParent(); OutputSection *BOut = LB->getParent(); if (AOut != BOut) return AOut->SectionIndex < BOut->SectionIndex; return LA->OutSecOff < LB->OutSecOff; } // This function is used by the --merge-exidx-entries to detect duplicate // .ARM.exidx sections. It is Arm only. // // The .ARM.exidx section is of the form: // | PREL31 offset to function | Unwind instructions for function | // where the unwind instructions are either a small number of unwind // instructions inlined into the table entry, the special CANT_UNWIND value of // 0x1 or a PREL31 offset into a .ARM.extab Section that contains unwind // instructions. // // We return true if all the unwind instructions in the .ARM.exidx entries of // Cur can be merged into the last entry of Prev. static bool isDuplicateArmExidxSec(InputSection *Prev, InputSection *Cur) { // References to .ARM.Extab Sections have bit 31 clear and are not the // special EXIDX_CANTUNWIND bit-pattern. auto IsExtabRef = [](uint32_t Unwind) { return (Unwind & 0x80000000) == 0 && Unwind != 0x1; }; struct ExidxEntry { ulittle32_t Fn; ulittle32_t Unwind; }; // Get the last table Entry from the previous .ARM.exidx section. const ExidxEntry &PrevEntry = *reinterpret_cast( Prev->Data.data() + Prev->getSize() - sizeof(ExidxEntry)); if (IsExtabRef(PrevEntry.Unwind)) return false; // We consider the unwind instructions of an .ARM.exidx table entry // a duplicate if the previous unwind instructions if: // - Both are the special EXIDX_CANTUNWIND. // - Both are the same inline unwind instructions. // We do not attempt to follow and check links into .ARM.extab tables as // consecutive identical entries are rare and the effort to check that they // are identical is high. if (isa(Cur)) // Exidx sentinel section has implicit EXIDX_CANTUNWIND; return PrevEntry.Unwind == 0x1; ArrayRef Entries( reinterpret_cast(Cur->Data.data()), Cur->getSize() / sizeof(ExidxEntry)); for (const ExidxEntry &Entry : Entries) if (IsExtabRef(Entry.Unwind) || Entry.Unwind != PrevEntry.Unwind) return false; // All table entries in this .ARM.exidx Section can be merged into the // previous Section. return true; } template void Writer::resolveShfLinkOrder() { for (OutputSection *Sec : OutputSections) { if (!(Sec->Flags & SHF_LINK_ORDER)) continue; // Link order may be distributed across several InputSectionDescriptions // but sort must consider them all at once. std::vector ScriptSections; std::vector Sections; for (BaseCommand *Base : Sec->SectionCommands) { if (auto *ISD = dyn_cast(Base)) { for (InputSection *&IS : ISD->Sections) { ScriptSections.push_back(&IS); Sections.push_back(IS); } } } std::stable_sort(Sections.begin(), Sections.end(), compareByFilePosition); if (!Config->Relocatable && Config->EMachine == EM_ARM && Sec->Type == SHT_ARM_EXIDX) { if (!Sections.empty() && isa(Sections.back())) { assert(Sections.size() >= 2 && "We should create a sentinel section only if there are " "alive regular exidx sections."); // The last executable section is required to fill the sentinel. // Remember it here so that we don't have to find it again. auto *Sentinel = cast(Sections.back()); Sentinel->Highest = Sections[Sections.size() - 2]->getLinkOrderDep(); } if (Config->MergeArmExidx) { // The EHABI for the Arm Architecture permits consecutive identical // table entries to be merged. We use a simple implementation that // removes a .ARM.exidx Input Section if it can be merged into the // previous one. This does not require any rewriting of InputSection // contents but misses opportunities for fine grained deduplication // where only a subset of the InputSection contents can be merged. int Cur = 1; int Prev = 0; // The last one is a sentinel entry which should not be removed. int N = Sections.size() - 1; while (Cur < N) { if (isDuplicateArmExidxSec(Sections[Prev], Sections[Cur])) Sections[Cur] = nullptr; else Prev = Cur; ++Cur; } } } for (int I = 0, N = Sections.size(); I < N; ++I) *ScriptSections[I] = Sections[I]; // Remove the Sections we marked as duplicate earlier. for (BaseCommand *Base : Sec->SectionCommands) if (auto *ISD = dyn_cast(Base)) ISD->Sections.erase( std::remove(ISD->Sections.begin(), ISD->Sections.end(), nullptr), ISD->Sections.end()); } } static void applySynthetic(const std::vector &Sections, std::function Fn) { for (SyntheticSection *SS : Sections) if (SS && SS->getParent() && !SS->empty()) Fn(SS); } // In order to allow users to manipulate linker-synthesized sections, // we had to add synthetic sections to the input section list early, // even before we make decisions whether they are needed. This allows // users to write scripts like this: ".mygot : { .got }". // // Doing it has an unintended side effects. If it turns out that we // don't need a .got (for example) at all because there's no // relocation that needs a .got, we don't want to emit .got. // // To deal with the above problem, this function is called after // scanRelocations is called to remove synthetic sections that turn // out to be empty. static void removeUnusedSyntheticSections() { // All input synthetic sections that can be empty are placed after // all regular ones. We iterate over them all and exit at first // non-synthetic. for (InputSectionBase *S : llvm::reverse(InputSections)) { SyntheticSection *SS = dyn_cast(S); if (!SS) return; OutputSection *OS = SS->getParent(); if (!SS->empty() || !OS) continue; std::vector::iterator Empty = OS->SectionCommands.end(); for (auto I = OS->SectionCommands.begin(), E = OS->SectionCommands.end(); I != E; ++I) { BaseCommand *B = *I; if (auto *ISD = dyn_cast(B)) { llvm::erase_if(ISD->Sections, [=](InputSection *IS) { return IS == SS; }); if (ISD->Sections.empty()) Empty = I; } } if (Empty != OS->SectionCommands.end()) OS->SectionCommands.erase(Empty); // If there are no other sections in the output section, remove it from the // output. if (OS->SectionCommands.empty()) OS->Live = false; } } // Returns true if a symbol can be replaced at load-time by a symbol // with the same name defined in other ELF executable or DSO. static bool computeIsPreemptible(const Symbol &B) { assert(!B.isLocal()); // Only symbols that appear in dynsym can be preempted. if (!B.includeInDynsym()) return false; // Only default visibility symbols can be preempted. if (B.Visibility != STV_DEFAULT) return false; // At this point copy relocations have not been created yet, so any // symbol that is not defined locally is preemptible. if (!B.isDefined()) return true; // If we have a dynamic list it specifies which local symbols are preemptible. if (Config->HasDynamicList) return false; if (!Config->Shared) return false; // -Bsymbolic means that definitions are not preempted. if (Config->Bsymbolic || (Config->BsymbolicFunctions && B.isFunc())) return false; return true; } // 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 (BaseCommand *Base : Script->SectionCommands) if (auto *Sec = dyn_cast(Base)) addStartStopSymbols(Sec); } // Add _DYNAMIC symbol. Unlike GNU gold, our _DYNAMIC symbol has no type. // It should be okay as no one seems to care about the type. // Even the author of gold doesn't remember why gold behaves that way. // https://sourceware.org/ml/binutils/2002-03/msg00360.html if (InX::DynSymTab) Symtab->addRegular("_DYNAMIC", STV_HIDDEN, STT_NOTYPE, 0 /*Value*/, /*Size=*/0, STB_WEAK, InX::Dynamic, /*File=*/nullptr); // 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({InX::EhFrame}, [](SyntheticSection *SS) { SS->finalizeContents(); }); for (Symbol *S : Symtab->getSymbols()) S->IsPreemptible |= computeIsPreemptible(*S); // Scan relocations. This must be done after every symbol is declared so that // we can correctly decide if a dynamic relocation is needed. if (!Config->Relocatable) 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 *Sym : Symtab->getSymbols()) { if (!includeInSymtab(*Sym)) continue; if (InX::SymTab) InX::SymTab->addSymbol(Sym); if (InX::DynSymTab && Sym->includeInDynsym()) { InX::DynSymTab->addSymbol(Sym); if (auto *SS = dyn_cast(Sym)) if (cast>(Sym->File)->IsNeeded) In::VerNeed->addSymbol(SS); } } // Do not proceed if there was an undefined symbol. if (errorCount()) return; removeUnusedSyntheticSections(); sortSections(); Script->removeEmptyCommands(); // Now that we have the final list, create a list of all the // OutputSections for convenience. for (BaseCommand *Base : Script->SectionCommands) if (auto *Sec = dyn_cast(Base)) OutputSections.push_back(Sec); // Prefer command line supplied address over other constraints. for (OutputSection *Sec : OutputSections) { auto I = Config->SectionStartMap.find(Sec->Name); if (I != Config->SectionStartMap.end()) Sec->AddrExpr = [=] { return I->second; }; } // 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(); } // Some symbols are defined in term of program headers. Now that we // have the headers, we can find out which sections they point to. setReservedSymbolSections(); // 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, InX::HashTab, InX::SymTab, InX::ShStrTab, InX::StrTab, In::VerDef, InX::DynStrTab, InX::Got, InX::MipsGot, InX::IgotPlt, InX::GotPlt, InX::RelaDyn, InX::RelaIplt, InX::RelaPlt, InX::Plt, InX::Iplt, InX::EhFrameHdr, In::VerSym, In::VerNeed, InX::Dynamic}, [](SyntheticSection *SS) { SS->finalizeContents(); }); if (!Script->HasSectionsCommand && !Config->Relocatable) fixSectionAlignments(); // After link order processing .ARM.exidx sections can be deduplicated, which // needs to be resolved before any other address dependent operation. resolveShfLinkOrder(); // Some architectures need to generate content that depends on the address // of InputSections. For example some architectures use small displacements // for jump instructions that is is the linker's responsibility for creating // range extension thunks for. As the generation of the content may also // alter InputSection addresses we must converge to a fixed point. if (Target->NeedsThunks || Config->AndroidPackDynRelocs) { ThunkCreator TC; AArch64Err843419Patcher A64P; bool Changed; do { Script->assignAddresses(); Changed = false; if (Target->NeedsThunks) Changed |= TC.createThunks(OutputSections); if (Config->FixCortexA53Errata843419) { if (Changed) Script->assignAddresses(); Changed |= A64P.createFixes(); } if (InX::MipsGot) InX::MipsGot->updateAllocSize(); Changed |= InX::RelaDyn->updateAllocSize(); } while (Changed); } // 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}, [](SyntheticSection *SS) { SS->postThunkContents(); }); } // 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); } 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.push_back(make(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 *Cmd = findSection(".interp")) AddHdr(PT_INTERP, Cmd->getPhdrFlags())->add(Cmd); // Add the first PT_LOAD segment for regular output sections. uint64_t Flags = computeFlags(PF_R); PhdrEntry *Load = AddHdr(PT_LOAD, Flags); // 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 (Sec->LMAExpr || Flags != NewFlags) { + if (Sec->LMAExpr || Sec->MemRegion != Load->FirstSec->MemRegion || + Flags != NewFlags) { Load = AddHdr(PT_LOAD, NewFlags); Flags = NewFlags; } Load->add(Sec); } // Add a TLS segment if any. PhdrEntry *TlsHdr = make(PT_TLS, PF_R); for (OutputSection *Sec : OutputSections) if (Sec->Flags & SHF_TLS) TlsHdr->add(Sec); if (TlsHdr->FirstSec) Ret.push_back(TlsHdr); // Add an entry for .dynamic. if (InX::DynSymTab) AddHdr(PT_DYNAMIC, InX::Dynamic->getParent()->getPhdrFlags()) ->add(InX::Dynamic->getParent()); // PT_GNU_RELRO includes all sections that should be marked as // read-only by dynamic linker after proccessing relocations. // Current dynamic loaders only support one PT_GNU_RELRO PHDR, give // an error message if more than one PT_GNU_RELRO PHDR is required. PhdrEntry *RelRo = make(PT_GNU_RELRO, PF_R); bool InRelroPhdr = false; bool IsRelroFinished = false; for (OutputSection *Sec : OutputSections) { if (!needsPtLoad(Sec)) continue; if (isRelroSection(Sec)) { InRelroPhdr = true; if (!IsRelroFinished) RelRo->add(Sec); else error("section: " + Sec->Name + " is not contiguous with other relro" + " sections"); } else if (InRelroPhdr) { InRelroPhdr = false; IsRelroFinished = true; } } if (RelRo->FirstSec) Ret.push_back(RelRo); // PT_GNU_EH_FRAME is a special section pointing on .eh_frame_hdr. if (!InX::EhFrame->empty() && InX::EhFrameHdr && InX::EhFrame->getParent() && InX::EhFrameHdr->getParent()) AddHdr(PT_GNU_EH_FRAME, InX::EhFrameHdr->getParent()->getPhdrFlags()) ->add(InX::EhFrameHdr->getParent()); // PT_OPENBSD_RANDOMIZE is an OpenBSD-specific feature. That makes // the dynamic linker fill the segment with random data. if (OutputSection *Cmd = findSection(".openbsd.randomdata")) AddHdr(PT_OPENBSD_RANDOMIZE, Cmd->getPhdrFlags())->add(Cmd); // 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 || Sec->LMAExpr) 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 = llvm::find_if(OutputSections, [](OutputSection *Cmd) { return Cmd->Type == SHT_ARM_EXIDX; }); if (I == OutputSections.end()) return; // PT_ARM_EXIDX is the ARM EHABI equivalent of PT_GNU_EH_FRAME PhdrEntry *ARMExidx = make(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() { auto PageAlign = [](OutputSection *Cmd) { if (Cmd && !Cmd->AddrExpr) Cmd->AddrExpr = [=] { return alignTo(Script->getDot(), Config->MaxPageSize); }; }; for (const PhdrEntry *P : Phdrs) if (P->p_type == PT_LOAD && P->FirstSec) PageAlign(P->FirstSec); for (const PhdrEntry *P : Phdrs) { if (P->p_type != PT_GNU_RELRO) continue; if (P->FirstSec) PageAlign(P->FirstSec); // Find the first section after PT_GNU_RELRO. If it is in a PT_LOAD we // have to align it to a page. auto End = OutputSections.end(); auto I = std::find(OutputSections.begin(), End, P->LastSec); if (I == End || (I + 1) == End) continue; OutputSection *Cmd = (*(I + 1)); if (needsPtLoad(Cmd)) PageAlign(Cmd); } } // 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 *Cmd) { OutputSection *First = Cmd->PtLoad ? Cmd->PtLoad->FirstSec : nullptr; // The first section in a PT_LOAD has to have congruent offset and address // module the page size. if (Cmd == First) return alignTo(Off, std::max(Cmd->Alignment, Config->MaxPageSize), Cmd->Addr); // For SHT_NOBITS we don't want the alignment of the section to impact the // offset of the sections that follow. Since nothing seems to care about the // sh_offset of the SHT_NOBITS section itself, just ignore it. if (Cmd->Type == SHT_NOBITS) return Off; // If the section is not in a PT_LOAD, we just have to align it. if (!Cmd->PtLoad) return alignTo(Off, Cmd->Alignment); // If two sections share the same PT_LOAD the file offset is calculated // using this formula: Off2 = Off1 + (VA2 - VA1). return First->Offset + Cmd->Addr - First->Addr; } static uint64_t setOffset(OutputSection *Cmd, uint64_t Off) { Off = getFileAlignment(Off, Cmd); Cmd->Offset = Off; // For SHT_NOBITS we should not count the size. if (Cmd->Type == SHT_NOBITS) return Off; return Off + Cmd->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); PhdrEntry *LastRX = nullptr; for (PhdrEntry *P : Phdrs) if (P->p_type == PT_LOAD && (P->p_flags & PF_X)) LastRX = P; for (OutputSection *Sec : OutputSections) { Off = setOffset(Sec, Off); if (Script->HasSectionsCommand) continue; // If this is a last section of the last executable segment and that // segment is the last loadable segment, align the offset of the // following section to avoid loading non-segments parts of the file. if (LastRX && LastRX->LastSec == Sec) Off = alignTo(Off, Target->PageSize); } 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->FirstSec; OutputSection *Last = P->LastSec; if (First) { P->p_filesz = Last->Offset - First->Offset; if (Last->Type != SHT_NOBITS) P->p_filesz += Last->Size; P->p_memsz = Last->Addr + Last->Size - First->Addr; P->p_offset = First->Offset; P->p_vaddr = First->Addr; if (!P->HasLMA) P->p_paddr = First->getLMA(); } if (P->p_type == PT_LOAD) P->p_align = std::max(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 number represented by the entry symbol, if it is a number; // 5. the address of the first byte of the .text section, if present; // 6. the address 0. template uint64_t Writer::getEntryAddr() { // Case 1, 2 or 3 if (Symbol *B = Symtab->find(Config->Entry)) return B->getVA(); // Case 4 uint64_t Addr; if (to_integer(Config->Entry, Addr)) return Addr; // Case 5 if (OutputSection *Sec = findSection(".text")) { if (Config->WarnMissingEntry) warn("cannot find entry symbol " + Config->Entry + "; defaulting to 0x" + utohexstr(Sec->Addr)); return Sec->Addr; } // Case 6 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; } 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_flags = Config->EFlags; 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_shstrndx = InX::ShStrTab->getParent()->SectionIndex; 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); } // 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); unsigned Flags = 0; if (!Config->Relocatable) Flags = FileOutputBuffer::F_executable; Expected> BufferOrErr = FileOutputBuffer::create(Config->OutputFile, FileSize, Flags); if (!BufferOrErr) error("failed to open " + Config->OutputFile + ": " + llvm::toString(BufferOrErr.takeError())); else Buffer = std::move(*BufferOrErr); } template void Writer::writeSectionsBinary() { uint8_t *Buf = Buffer->getBufferStart(); for (OutputSection *Sec : OutputSections) if (Sec->Flags & SHF_ALLOC) Sec->writeTo(Buf + Sec->Offset); } static void fillTrap(uint8_t *I, uint8_t *End) { for (; I + 4 <= End; I += 4) memcpy(I, &Target->TrapInstr, 4); } // Fill the last page of executable segments with trap instructions // instead of leaving them as zero. Even though it is not required by any // standard, it is in general a good thing to do for security reasons. // // We'll leave other pages in segments as-is because the rest will be // overwritten by output sections. template void Writer::writeTrapInstr() { if (Script->HasSectionsCommand) return; // Fill the last page. uint8_t *Buf = Buffer->getBufferStart(); for (PhdrEntry *P : Phdrs) if (P->p_type == PT_LOAD && (P->p_flags & PF_X)) fillTrap(Buf + alignDown(P->p_offset + P->p_filesz, Target->PageSize), Buf + alignTo(P->p_offset + P->p_filesz, Target->PageSize)); // Round up the file size of the last segment to the page boundary iff it is // an executable segment to ensure that other tools don't accidentally // trim the instruction padding (e.g. when stripping the file). PhdrEntry *Last = nullptr; for (PhdrEntry *P : Phdrs) if (P->p_type == PT_LOAD) Last = P; if (Last && (Last->p_flags & PF_X)) Last->p_memsz = Last->p_filesz = alignTo(Last->p_filesz, Target->PageSize); } // 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 = findSection(".opd")) { Out::Opd = OpdCmd; Out::OpdBuf = Buf + Out::Opd->Offset; OpdCmd->template writeTo(Buf + Out::Opd->Offset); } OutputSection *EhFrameHdr = nullptr; if (InX::EhFrameHdr && !InX::EhFrameHdr->empty()) EhFrameHdr = InX::EhFrameHdr->getParent(); // In -r or -emit-relocs mode, write the relocation sections first as in // ELf_Rel targets we might find out that we need to modify the relocated // section while doing it. for (OutputSection *Sec : OutputSections) if (Sec->Type == SHT_REL || Sec->Type == SHT_RELA) Sec->writeTo(Buf + Sec->Offset); for (OutputSection *Sec : OutputSections) if (Sec != Out::Opd && Sec != EhFrameHdr && Sec->Type != SHT_REL && Sec->Type != SHT_RELA) Sec->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) EhFrameHdr->writeTo(Buf + EhFrameHdr->Offset); } template void Writer::writeBuildId() { if (!InX::BuildId || !InX::BuildId->getParent()) 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();