Index: test/tools/llvm-objcopy/basic-copy.test =================================================================== --- test/tools/llvm-objcopy/basic-copy.test +++ test/tools/llvm-objcopy/basic-copy.test @@ -22,11 +22,6 @@ # CHECK: Type: SHT_NULL -# CHECK: Name: .shstrtab -# CHECK-NEXT: Type: SHT_STRTAB -# CHECK-NEXT: Flags [ -# CHECK-NEXT: ] - # CHECK: Name: .bss # CHECK-NEXT: Type: SHT_NOBITS # CHECK-NEXT: Flags [ @@ -45,3 +40,18 @@ # CHECK-NEXT: Address: # CHECK-NEXT: Offset: [[OFFSET]] # CHECK-NEXT: Size: 4 + +# CHECK: Name: .symtab +# CHECK-NEXT: Type: SHT_SYMTAB +# CHECK-NEXT: Flags [ +# CHECK-NEXT: ] + +# CHECK: Name: .strtab +# CHECK-NEXT: Type: SHT_STRTAB +# CHECK-NEXT: Flags [ +# CHECK-NEXT: ] + +# CHECK: Name: .shstrtab +# CHECK-NEXT: Type: SHT_STRTAB +# CHECK-NEXT: Flags [ +# CHECK-NEXT: ] Index: test/tools/llvm-objcopy/symbol-copy.test =================================================================== --- /dev/null +++ test/tools/llvm-objcopy/symbol-copy.test @@ -0,0 +1,91 @@ +# RUN: yaml2obj %s > %t +# RUN: llvm-objcopy %t %t2 +# RUN: llvm-readobj -symbols %t2 | FileCheck %s + +!ELF +FileHeader: + Class: ELFCLASS64 + Data: ELFDATA2LSB + Type: ET_EXEC + Machine: EM_X86_64 +Sections: + - Name: .text + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC, SHF_EXECINSTR ] + Address: 0x1000 + AddressAlign: 0x0000000000000010 + Content: "0000000000000000" + - Name: .data + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC ] + Address: 0x2000 + AddressAlign: 0x0000000000000010 + Content: "0000000000000000" +Symbols: + Global: + - Name: _start + Type: STT_FUNC + Section: .text + Value: 0x1000 + Size: 4 + - Name: foo + Type: STT_FUNC + Section: .text + Section: .text + Value: 0x1004 + - Name: bar + Type: STT_OBJECT + Section: .data + Value: 0x2000 + Size: 4 + - Name: baz + Type: STT_OBJECT + Section: .data + Value: 0x2004 + Size: 4 + +#CHECK: Symbols [ +#CHECK-NEXT: Symbol { +#CHECK-NEXT: Name: +#CHECK-NEXT: Value: 0x0 +#CHECK-NEXT: Size: 0 +#CHECK-NEXT: Binding: Local +#CHECK-NEXT: Type: None +#CHECK-NEXT: Other: 0 +#CHECK-NEXT: Section: Undefined +#CHECK-NEXT: } +#CHECK-NEXT: Symbol { +#CHECK-NEXT: Name: _start +#CHECK-NEXT: Value: 0x1000 +#CHECK-NEXT: Size: 4 +#CHECK-NEXT: Binding: Global +#CHECK-NEXT: Type: Function +#CHECK-NEXT: Other: 0 +#CHECK-NEXT: Section: .text +#CHECK-NEXT: } +#CHECK-NEXT: Symbol { +#CHECK-NEXT: Name: foo +#CHECK-NEXT: Value: 0x1004 +#CHECK-NEXT: Size: 0 +#CHECK-NEXT: Binding: Global +#CHECK-NEXT: Type: Function +#CHECK-NEXT: Other: 0 +#CHECK-NEXT: Section: .text +#CHECK-NEXT: } +#CHECK-NEXT: Symbol { +#CHECK-NEXT: Name: bar +#CHECK-NEXT: Value: 0x2000 +#CHECK-NEXT: Size: 4 +#CHECK-NEXT: Binding: Global +#CHECK-NEXT: Type: Object +#CHECK-NEXT: Other: 0 +#CHECK-NEXT: Section: .data +#CHECK-NEXT: } +#CHECK-NEXT: Symbol { +#CHECK-NEXT: Name: baz +#CHECK-NEXT: Value: 0x2004 +#CHECK-NEXT: Size: 4 +#CHECK-NEXT: Binding: Global +#CHECK-NEXT: Type: Object +#CHECK-NEXT: Other: 0 +#CHECK-NEXT: Section: .data Index: tools/llvm-objcopy/Object.h =================================================================== --- tools/llvm-objcopy/Object.h +++ tools/llvm-objcopy/Object.h @@ -108,6 +108,36 @@ } }; +struct Symbol { + uint8_t Binding; + SectionBase *DefinedIn; + uint32_t Index; + llvm::StringRef Name; + uint32_t NameIndex; + uint64_t Size; + uint8_t Type; + uint64_t Value; +}; +// The symbol data changes from ELFT to ELFT so we need to template it. This +// lets us implement writeSection +template class SymbolTableSection : public SectionBase { +private: + std::vector FinalSymbols; + llvm::StringMap Symbols; + StringTableSection *SymbolNames; + +public: + void setStrTab(StringTableSection *StrTab) { SymbolNames = StrTab; } + void addSymbol(llvm::StringRef Name, uint8_t Bind, uint8_t Type, + SectionBase *DefinedIn, uint64_t Value, uint64_t Sz); + void removeSymbol(llvm::StringRef); + void finalize() override; + void writeSection(llvm::FileOutputBuffer &) const override; + static bool classof(const SectionBase *S) { + return S->Type == llvm::ELF::SHT_SYMTAB; + } +}; + template class Object { private: typedef std::unique_ptr SecPtr; @@ -117,12 +147,15 @@ typedef typename ELFT::Ehdr Elf_Ehdr; typedef typename ELFT::Phdr Elf_Phdr; - StringTableSection *SectionNames; + StringTableSection *SectionNames = nullptr; + SymbolTableSection *SymbolTable = nullptr; std::vector Sections; std::vector Segments; void sortSections(); void assignOffsets(); + SecPtr makeSection(const llvm::object::ELFFile &ElfFile, + const Elf_Shdr &Shdr); void readProgramHeaders(const llvm::object::ELFFile &ElfFile); void readSectionHeaders(const llvm::object::ELFFile &ElfFile); void writeHeader(llvm::FileOutputBuffer &Out) const; Index: tools/llvm-objcopy/Object.cpp =================================================================== --- tools/llvm-objcopy/Object.cpp +++ tools/llvm-objcopy/Object.cpp @@ -76,6 +76,77 @@ StrTabBuilder.write(Out.getBufferStart() + Offset); } +template +void SymbolTableSection::addSymbol(StringRef Name, uint8_t Bind, + uint8_t Type, SectionBase *DefinedIn, + uint64_t Value, uint64_t Sz) { + Symbol Sym; + Sym.Name = Name; + Sym.Binding = Bind; + Sym.Type = Type; + Sym.DefinedIn = DefinedIn; + Sym.Value = Value; + Sym.Size = Sz; + Sym.Index = Symbols.size(); + auto Res = Symbols.insert(std::make_pair(Name, Sym)); + if (Res.second) + Size += sizeof(typename ELFT::Sym); +} + +template +void SymbolTableSection::removeSymbol(StringRef Name) { + auto Iter = Symbols.find(Name); + if (Iter != std::end(Symbols)) { + Symbols.erase(Iter); + Size += sizeof(ELFT::Sym); + } +} + +template void SymbolTableSection::finalize() { + auto CompareBinding = [](const Symbol &a, const Symbol &b) { + return a.Binding < b.Binding; + }; + auto CompareIndex = [](const Symbol &a, const Symbol &b) { + return a.Index < b.Index; + }; + // Add all of our strings to SymbolNames and finalize the table + for (auto &Entry : Symbols) + SymbolNames->addString(Entry.second.Name); + SymbolNames->finalize(); + for (auto &Entry : Symbols) { + Entry.second.NameIndex = SymbolNames->findIndex(Entry.second.Name); + FinalSymbols.push_back(Entry.second); + } + Symbol DummyLocal; + DummyLocal.Binding = STB_LOCAL; + std::sort(std::begin(FinalSymbols), std::end(FinalSymbols), CompareIndex); + std::stable_sort(std::begin(FinalSymbols), std::end(FinalSymbols), + CompareBinding); + auto Iter = std::upper_bound(std::begin(FinalSymbols), std::end(FinalSymbols), + DummyLocal, CompareBinding); + Info = std::end(FinalSymbols) - Iter; + Link = SymbolNames->Index; +} + +template +void SymbolTableSection::writeSection(llvm::FileOutputBuffer &Out) const { + uint8_t *Buf = Out.getBufferStart(); + Buf += Offset; + typename ELFT::Sym *Sym = reinterpret_cast(Buf); + for (auto &Symbol : FinalSymbols) { + Sym->st_name = Symbol.NameIndex; + Sym->st_value = Symbol.Value; + Sym->st_size = Symbol.Size; + Sym->setBinding(Symbol.Binding); + Sym->setType(Symbol.Type); + if (Symbol.DefinedIn) + Sym->st_shndx = Symbol.DefinedIn->Index; + else + Sym->st_shndx = SHN_UNDEF; + ++Sym; + } +} + template void Object::readProgramHeaders(const ELFFile &ElfFile) { uint32_t Index = 0; @@ -101,6 +172,35 @@ } } +template +std::unique_ptr +Object::makeSection(const ELFFile &ElfFile, const Elf_Shdr &Shdr) { + ArrayRef Data; + switch (Shdr.sh_type) { + case SHT_STRTAB: + return make_unique(); + case SHT_SYMTAB: { + auto SymTab = make_unique>(); + StringRef StrTabData = unwrapOrError(ElfFile.getStringTableForSymtab(Shdr)); + for (const auto &Sym : unwrapOrError(ElfFile.symbols(&Shdr))) { + SectionBase *DefSection = nullptr; + if (Sym.st_shndx != SHN_UNDEF) + DefSection = Sections[Sym.st_shndx - 1].get(); + StringRef Name = unwrapOrError(Sym.getName(StrTabData)); + SymTab->addSymbol(Name, Sym.getBinding(), Sym.getType(), DefSection, + Sym.getValue(), Sym.st_size); + } + SymbolTable = SymTab.get(); + return SymTab; + } + case SHT_NOBITS: + return make_unique
(Data); + default: + Data = unwrapOrError(ElfFile.getSectionContents(&Shdr)); + return make_unique
(Data); + } +} + template void Object::readSectionHeaders(const ELFFile &ElfFile) { uint32_t Index = 0; @@ -109,12 +209,7 @@ ++Index; continue; } - if (Shdr.sh_type == SHT_STRTAB) - continue; - ArrayRef Data; - if (Shdr.sh_type != SHT_NOBITS) - Data = unwrapOrError(ElfFile.getSectionContents(&Shdr)); - SecPtr Sec = make_unique
(Data); + SecPtr Sec = makeSection(ElfFile, Shdr); Sec->Name = unwrapOrError(ElfFile.getSectionName(&Shdr)); Sec->Type = Shdr.sh_type; Sec->Flags = Shdr.sh_flags; @@ -126,9 +221,16 @@ Sec->Align = Shdr.sh_addralign; Sec->EntrySize = Shdr.sh_entsize; Sec->Index = Index++; - SectionNames->addString(Sec->Name); Sections.push_back(std::move(Sec)); } + if (SymbolTable) { + if (auto StrTab = dyn_cast( + Sections[SymbolTable->Link - 1].get())) { + SymbolTable->setStrTab(StrTab); + } else { + error("Symbol table has invalid string table"); + } + } } template size_t Object::totalSize() const { @@ -148,13 +250,11 @@ Entry = Ehdr.e_entry; Flags = Ehdr.e_flags; - Sections.push_back(make_unique()); - SectionNames = dyn_cast(Sections.back().get()); - SectionNames->Name = ".shstrtab"; - SectionNames->addString(SectionNames->Name); - readSectionHeaders(ElfFile); readProgramHeaders(ElfFile); + + SectionNames = + dyn_cast(Sections[Ehdr.e_shstrndx - 1].get()); } template void Object::sortSections() { @@ -208,6 +308,9 @@ assignOffsets(); // Finalize SectionNames first so that we can assign name indexes. + for (const auto &Section : Sections) { + SectionNames->addString(Section->Name); + } SectionNames->finalize(); // Finally now that all offsets and indexes have been set we can finalize any // reamining issues. @@ -239,7 +342,9 @@ Ehdr.e_phentsize = sizeof(Elf_Phdr); Ehdr.e_phnum = Segments.size(); Ehdr.e_shentsize = sizeof(Elf_Shdr); - Ehdr.e_shnum = Sections.size(); + // The first entry in the seciton header table is not in Sections but must be + // accounted for when writing out the size + Ehdr.e_shnum = Sections.size() + 1; Ehdr.e_shstrndx = SectionNames->Index; }