void SymbolTable<ELFT>::addLazyArchive(ArchiveFile *F,
const object::Archive::Symbol Sym) {
Symbol *S;
bool WasInserted;
std::tie(S, WasInserted) = insert(Sym.getName());
if (WasInserted) {
replaceBody<LazyArchive>(S, *F, Sym, SymbolBody::UnknownType);
return;
}
if (!S->body()->isUndefined())
return;
// Weak undefined symbols should not fetch members from archives. If we were
// to keep old symbol we would not know that an archive member was available
// if a strong undefined symbol shows up afterwards in the link. If a strong
// undefined symbol never shows up, this lazy symbol will get to the end of
// the link and must be treated as the weak undefined one. We already marked
// this symbol as used when we added it to the symbol table, but we also need
// to preserve its type. FIXME: Move the Type field to Symbol.
if (S->isWeak()) {
replaceBody<LazyArchive>(S, *F, Sym, S->body()->Type);
return;
}
MemoryBufferRef MBRef = F->getMember(&Sym);
if (!MBRef.getBuffer().empty())
addFile(createObjectFile(MBRef, F->getName()));
}
template <class ELFT> static ELFFile<ELFT> createELFObj(MemoryBufferRef MB) {
std::error_code EC;
ELFFile<ELFT> F(MB.getBuffer(), EC);
if (EC)
fatal(EC, "failed to read " + MB.getBufferIdentifier());
return F;
}
ErrorOr<std::unique_ptr<ObjectFile>>
ObjectFile::createELFObjectFile(MemoryBufferRef Obj) {
std::pair<unsigned char, unsigned char> Ident =
getElfArchType(Obj.getBuffer());
std::size_t MaxAlignment =
1ULL << countTrailingZeros(uintptr_t(Obj.getBufferStart()));
if (MaxAlignment < 2)
return object_error::parse_failed;
std::error_code EC;
std::unique_ptr<ObjectFile> R;
if (Ident.first == ELF::ELFCLASS32) {
if (Ident.second == ELF::ELFDATA2LSB)
R.reset(new ELFObjectFile<ELFType<support::little, false>>(Obj, EC));
else if (Ident.second == ELF::ELFDATA2MSB)
R.reset(new ELFObjectFile<ELFType<support::big, false>>(Obj, EC));
else
return object_error::parse_failed;
} else if (Ident.first == ELF::ELFCLASS64) {
if (Ident.second == ELF::ELFDATA2LSB)
R.reset(new ELFObjectFile<ELFType<support::little, true>>(Obj, EC));
else if (Ident.second == ELF::ELFDATA2MSB)
R.reset(new ELFObjectFile<ELFType<support::big, true>>(Obj, EC));
else
return object_error::parse_failed;
} else {
return object_error::parse_failed;
}
if (EC)
return EC;
return std::move(R);
}
Error PDBFile::parseFileHeaders() {
std::error_code EC;
MemoryBufferRef BufferRef = *Context->Buffer;
// Make sure the file is sufficiently large to hold a super block.
// Do this before attempting to read the super block.
if (BufferRef.getBufferSize() < sizeof(SuperBlock))
return make_error<RawError>(raw_error_code::corrupt_file,
"Does not contain superblock");
Context->SB =
reinterpret_cast<const SuperBlock *>(BufferRef.getBufferStart());
const SuperBlock *SB = Context->SB;
// Check the magic bytes.
if (memcmp(SB->MagicBytes, Magic, sizeof(Magic)) != 0)
return make_error<RawError>(raw_error_code::corrupt_file,
"MSF magic header doesn't match");
// We don't support blocksizes which aren't a multiple of four bytes.
if (SB->BlockSize % sizeof(support::ulittle32_t) != 0)
return make_error<RawError>(raw_error_code::corrupt_file,
"Block size is not multiple of 4.");
switch (SB->BlockSize) {
case 512: case 1024: case 2048: case 4096:
break;
default:
// An invalid block size suggests a corrupt PDB file.
return make_error<RawError>(raw_error_code::corrupt_file,
"Unsupported block size.");
}
if (BufferRef.getBufferSize() % SB->BlockSize != 0)
return make_error<RawError>(raw_error_code::corrupt_file,
"File size is not a multiple of block size");
// We don't support directories whose sizes aren't a multiple of four bytes.
if (SB->NumDirectoryBytes % sizeof(support::ulittle32_t) != 0)
return make_error<RawError>(raw_error_code::corrupt_file,
"Directory size is not multiple of 4.");
// The number of blocks which comprise the directory is a simple function of
// the number of bytes it contains.
uint64_t NumDirectoryBlocks = getNumDirectoryBlocks();
// The block map, as we understand it, is a block which consists of a list of
// block numbers.
// It is unclear what would happen if the number of blocks couldn't fit on a
// single block.
if (NumDirectoryBlocks > SB->BlockSize / sizeof(support::ulittle32_t))
return make_error<RawError>(raw_error_code::corrupt_file,
"Too many directory blocks.");
// Make sure the directory block array fits within the file.
if (auto EC = checkOffset(BufferRef, getDirectoryBlockArray()))
return EC;
return Error::success();
}
std::unique_ptr<InputFile> LazyArchive::getFile() {
MemoryBufferRef MBRef = File->getMember(&Sym);
// getMember returns an empty buffer if the member was already
// read from the library.
if (MBRef.getBuffer().empty())
return std::unique_ptr<InputFile>(nullptr);
return createObjectFile(MBRef, File->getName());
}
static std::error_code checkOffset(MemoryBufferRef M, uintptr_t Addr,
const uint64_t Size) {
if (Addr + Size < Addr || Addr + Size < Size ||
Addr + Size > uintptr_t(M.getBufferEnd()) ||
Addr < uintptr_t(M.getBufferStart())) {
return std::make_error_code(std::errc::bad_address);
}
return std::error_code();
}
static std::error_code checkOffset(MemoryBufferRef M, uintptr_t Addr,
const uint64_t Size) {
if (Addr + Size < Addr || Addr + Size < Size ||
Addr + Size > uintptr_t(M.getBufferEnd()) ||
Addr < uintptr_t(M.getBufferStart())) {
return object_error::unexpected_eof;
}
return std::error_code();
}
static Error checkOffset(MemoryBufferRef M, uintptr_t Addr,
const uint64_t Size) {
if (Addr + Size < Addr || Addr + Size < Size ||
Addr + Size > uintptr_t(M.getBufferEnd()) ||
Addr < uintptr_t(M.getBufferStart())) {
return make_error<RawError>(raw_error_code::corrupt_file,
"Invalid buffer address");
}
return Error::success();
}
ErrorOr<std::unique_ptr<SymbolicFile>> SymbolicFile::createSymbolicFile(
MemoryBufferRef Object, sys::fs::file_magic Type, LLVMContext *Context) {
StringRef Data = Object.getBuffer();
if (Type == sys::fs::file_magic::unknown)
Type = sys::fs::identify_magic(Data);
switch (Type) {
case sys::fs::file_magic::bitcode:
if (Context)
return IRObjectFile::create(Object, *Context);
// Fallthrough
case sys::fs::file_magic::unknown:
case sys::fs::file_magic::archive:
case sys::fs::file_magic::macho_universal_binary:
case sys::fs::file_magic::windows_resource:
return object_error::invalid_file_type;
case sys::fs::file_magic::elf:
case sys::fs::file_magic::elf_executable:
case sys::fs::file_magic::elf_shared_object:
case sys::fs::file_magic::elf_core:
case sys::fs::file_magic::macho_executable:
case sys::fs::file_magic::macho_fixed_virtual_memory_shared_lib:
case sys::fs::file_magic::macho_core:
case sys::fs::file_magic::macho_preload_executable:
case sys::fs::file_magic::macho_dynamically_linked_shared_lib:
case sys::fs::file_magic::macho_dynamic_linker:
case sys::fs::file_magic::macho_bundle:
case sys::fs::file_magic::macho_dynamically_linked_shared_lib_stub:
case sys::fs::file_magic::macho_dsym_companion:
case sys::fs::file_magic::macho_kext_bundle:
case sys::fs::file_magic::pecoff_executable:
return ObjectFile::createObjectFile(Object, Type);
case sys::fs::file_magic::coff_import_library:
return std::unique_ptr<SymbolicFile>(new COFFImportFile(Object));
case sys::fs::file_magic::elf_relocatable:
case sys::fs::file_magic::macho_object:
case sys::fs::file_magic::coff_object: {
ErrorOr<std::unique_ptr<ObjectFile>> Obj =
ObjectFile::createObjectFile(Object, Type);
if (!Obj || !Context)
return std::move(Obj);
ErrorOr<MemoryBufferRef> BCData =
IRObjectFile::findBitcodeInObject(*Obj->get());
if (!BCData)
return std::move(Obj);
return IRObjectFile::create(
MemoryBufferRef(BCData->getBuffer(), Object.getBufferIdentifier()),
*Context);
}
}
llvm_unreachable("Unexpected Binary File Type");
}
static std::unique_ptr<InputFile> createFile(MemoryBufferRef MB) {
// File type is detected by contents, not by file extension.
file_magic Magic = identify_magic(MB.getBuffer());
if (Magic == file_magic::archive)
return std::unique_ptr<InputFile>(new ArchiveFile(MB));
if (Magic == file_magic::bitcode)
return std::unique_ptr<InputFile>(new BitcodeFile(MB));
if (Config->OutputFile == "")
Config->OutputFile = getOutputPath(MB.getBufferIdentifier());
return std::unique_ptr<InputFile>(new ObjectFile<llvm::object::ELF64LE>(MB));
}
void notifyObjectCompiled(const Module *M, MemoryBufferRef Obj) override {
const std::string &ModuleID = M->getModuleIdentifier();
std::string CacheName;
if (!getCacheFilename(ModuleID, CacheName))
return;
if (!CacheDir.empty()) { // Create user-defined cache dir.
SmallString<128> dir(sys::path::parent_path(CacheName));
sys::fs::create_directories(Twine(dir));
}
std::error_code EC;
raw_fd_ostream outfile(CacheName, EC, sys::fs::F_None);
outfile.write(Obj.getBufferStart(), Obj.getBufferSize());
outfile.close();
}
static uint8_t getBitcodeMachineKind(MemoryBufferRef MB) {
Triple T(getBitcodeTargetTriple(MB, Driver->Context));
switch (T.getArch()) {
case Triple::aarch64:
return EM_AARCH64;
case Triple::arm:
return EM_ARM;
case Triple::mips:
case Triple::mipsel:
case Triple::mips64:
case Triple::mips64el:
return EM_MIPS;
case Triple::ppc:
return EM_PPC;
case Triple::ppc64:
return EM_PPC64;
case Triple::x86:
return T.isOSIAMCU() ? EM_IAMCU : EM_386;
case Triple::x86_64:
return EM_X86_64;
default:
fatal(MB.getBufferIdentifier() +
": could not infer e_machine from bitcode target triple " + T.str());
}
}
Optional<MemoryBufferRef> elf::readFile(StringRef Path) {
log(Path);
auto MBOrErr = MemoryBuffer::getFile(Path);
if (auto EC = MBOrErr.getError()) {
error("cannot open " + Path + ": " + EC.message());
return None;
}
std::unique_ptr<MemoryBuffer> &MB = *MBOrErr;
MemoryBufferRef MBRef = MB->getMemBufferRef();
make<std::unique_ptr<MemoryBuffer>>(std::move(MB)); // take MB ownership
if (Tar)
Tar->append(relativeToRoot(Path), MBRef.getBuffer());
return MBRef;
}
bool llvm::parseAssemblyInto(MemoryBufferRef F, Module &M, SMDiagnostic &Err) {
SourceMgr SM;
std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(F, false);
SM.AddNewSourceBuffer(std::move(Buf), SMLoc());
return LLParser(F.getBuffer(), SM, Err, &M).Run();
}
// Returns false if size is greater than the buffer size. And sets ec.
static bool checkSize(MemoryBufferRef M, std::error_code &EC, uint64_t Size) {
if (M.getBufferSize() < Size) {
EC = object_error::unexpected_eof;
return false;
}
return true;
}
bool llvm::parseAssemblyInto(MemoryBufferRef F, Module &M, SMDiagnostic &Err,
SlotMapping *Slots, bool UpgradeDebugInfo) {
SourceMgr SM;
std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(F);
SM.AddNewSourceBuffer(std::move(Buf), SMLoc());
return LLParser(F.getBuffer(), SM, Err, &M, Slots, UpgradeDebugInfo).Run();
}
// Split S into linker script tokens.
void ScriptParserBase::tokenize(MemoryBufferRef MB) {
std::vector<StringRef> Vec;
MBs.push_back(MB);
StringRef S = MB.getBuffer();
StringRef Begin = S;
for (;;) {
S = skipSpace(S);
if (S.empty())
break;
// Quoted token. Note that double-quote characters are parts of a token
// because, in a glob match context, only unquoted tokens are interpreted
// as glob patterns. Double-quoted tokens are literal patterns in that
// context.
if (S.startswith("\"")) {
size_t E = S.find("\"", 1);
if (E == StringRef::npos) {
StringRef Filename = MB.getBufferIdentifier();
size_t Lineno = Begin.substr(0, S.data() - Begin.data()).count('\n');
error(Filename + ":" + Twine(Lineno + 1) + ": unclosed quote");
return;
}
Vec.push_back(S.take_front(E + 1));
S = S.substr(E + 1);
continue;
}
// Unquoted token. This is more relaxed than tokens in C-like language,
// so that you can write "file-name.cpp" as one bare token, for example.
size_t Pos = S.find_first_not_of(
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
"0123456789_.$/\\~=+[]*?-:!<>^");
// A character that cannot start a word (which is usually a
// punctuation) forms a single character token.
if (Pos == 0)
Pos = 1;
Vec.push_back(S.substr(0, Pos));
S = S.substr(Pos);
}
Tokens.insert(Tokens.begin() + Pos, Vec.begin(), Vec.end());
}
// Parse the module summary index out of an IR file and return the summary
// index object if found, or nullptr if not.
Expected<std::unique_ptr<ModuleSummaryIndex>>
llvm::getModuleSummaryIndexForFile(StringRef Path) {
ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
MemoryBuffer::getFileOrSTDIN(Path);
std::error_code EC = FileOrErr.getError();
if (EC)
return errorCodeToError(EC);
MemoryBufferRef BufferRef = (FileOrErr.get())->getMemBufferRef();
if (IgnoreEmptyThinLTOIndexFile && !BufferRef.getBufferSize())
return nullptr;
Expected<std::unique_ptr<object::ModuleSummaryIndexObjectFile>> ObjOrErr =
object::ModuleSummaryIndexObjectFile::create(BufferRef);
if (!ObjOrErr)
return ObjOrErr.takeError();
object::ModuleSummaryIndexObjectFile &Obj = **ObjOrErr;
return Obj.takeIndex();
}
std::unique_ptr<Module> llvm::parseIR(MemoryBufferRef Buffer, SMDiagnostic &Err,
LLVMContext &Context) {
NamedRegionTimer T(TimeIRParsingName, TimeIRParsingGroupName,
TimePassesIsEnabled);
if (isBitcode((const unsigned char *)Buffer.getBufferStart(),
(const unsigned char *)Buffer.getBufferEnd())) {
ErrorOr<std::unique_ptr<Module>> ModuleOrErr =
parseBitcodeFile(Buffer, Context);
if (std::error_code EC = ModuleOrErr.getError()) {
Err = SMDiagnostic(Buffer.getBufferIdentifier(), SourceMgr::DK_Error,
EC.message());
return nullptr;
}
return std::move(ModuleOrErr.get());
}
return parseAssembly(Buffer, Err, Context);
}
static std::unique_ptr<InputFile> createELFFile(MemoryBufferRef MB) {
unsigned char Size;
unsigned char Endian;
std::tie(Size, Endian) = getElfArchType(MB.getBuffer());
if (Endian != ELFDATA2LSB && Endian != ELFDATA2MSB)
fatal("invalid data encoding: " + MB.getBufferIdentifier());
if (Size == ELFCLASS32) {
if (Endian == ELFDATA2LSB)
return createELFFileAux<T<ELF32LE>>(MB);
return createELFFileAux<T<ELF32BE>>(MB);
}
if (Size == ELFCLASS64) {
if (Endian == ELFDATA2LSB)
return createELFFileAux<T<ELF64LE>>(MB);
return createELFFileAux<T<ELF64BE>>(MB);
}
fatal("invalid file class: " + MB.getBufferIdentifier());
}
static ELFKind getELFKind(MemoryBufferRef MB) {
unsigned char Size;
unsigned char Endian;
std::tie(Size, Endian) = getElfArchType(MB.getBuffer());
if (Endian != ELFDATA2LSB && Endian != ELFDATA2MSB)
fatal(MB.getBufferIdentifier() + ": invalid data encoding");
if (Size != ELFCLASS32 && Size != ELFCLASS64)
fatal(MB.getBufferIdentifier() + ": invalid file class");
size_t BufSize = MB.getBuffer().size();
if ((Size == ELFCLASS32 && BufSize < sizeof(Elf32_Ehdr)) ||
(Size == ELFCLASS64 && BufSize < sizeof(Elf64_Ehdr)))
fatal(MB.getBufferIdentifier() + ": file is too short");
if (Size == ELFCLASS32)
return (Endian == ELFDATA2LSB) ? ELF32LEKind : ELF32BEKind;
return (Endian == ELFDATA2LSB) ? ELF64LEKind : ELF64BEKind;
}
void SymbolTable<ELFT>::addLazyObject(StringRef Name, LazyObjectFile &Obj) {
Symbol *S;
bool WasInserted;
std::tie(S, WasInserted) = insert(Name);
if (WasInserted) {
replaceBody<LazyObject>(S, Name, Obj, SymbolBody::UnknownType);
return;
}
if (!S->body()->isUndefined())
return;
// See comment for addLazyArchive above.
if (S->isWeak()) {
replaceBody<LazyObject>(S, Name, Obj, S->body()->Type);
} else {
MemoryBufferRef MBRef = Obj.getBuffer();
if (!MBRef.getBuffer().empty())
addFile(createObjectFile(MBRef));
}
}
std::unique_ptr<Module>
llvm::parseAssembly(MemoryBufferRef F, SMDiagnostic &Err, LLVMContext &Context,
SlotMapping *Slots, bool UpgradeDebugInfo) {
std::unique_ptr<Module> M =
make_unique<Module>(F.getBufferIdentifier(), Context);
if (parseAssemblyInto(F, *M, Err, Slots, UpgradeDebugInfo))
return nullptr;
return M;
}
std::unique_ptr<Module> llvm::parseAssembly(MemoryBufferRef F,
SMDiagnostic &Err,
LLVMContext &Context) {
std::unique_ptr<Module> M =
make_unique<Module>(F.getBufferIdentifier(), Context);
if (parseAssemblyInto(F, *M, Err))
return nullptr;
return M;
}
// Returns a buffer pointing to a member file containing a given symbol.
std::pair<MemoryBufferRef, uint64_t>
ArchiveFile::getMember(const Archive::Symbol *Sym) {
Archive::Child C =
check(Sym->getMember(),
"could not get the member for symbol " + Sym->getName());
if (!Seen.insert(C.getChildOffset()).second)
return {MemoryBufferRef(), 0};
MemoryBufferRef Ret =
check(C.getMemoryBufferRef(),
"could not get the buffer for the member defining symbol " +
Sym->getName());
if (C.getParent()->isThin() && Driver->Cpio)
Driver->Cpio->append(relativeToRoot(check(C.getFullName())),
Ret.getBuffer());
if (C.getParent()->isThin())
return {Ret, 0};
return {Ret, C.getChildOffset()};
}
std::vector<StringRef> lld::args::getLines(MemoryBufferRef MB) {
SmallVector<StringRef, 0> Arr;
MB.getBuffer().split(Arr, '\n');
std::vector<StringRef> Ret;
for (StringRef S : Arr) {
S = S.trim();
if (!S.empty() && S[0] != '#')
Ret.push_back(S);
}
return Ret;
}
BitcodeFile::BitcodeFile(MemoryBufferRef MB, StringRef ArchiveName,
uint64_t OffsetInArchive)
: InputFile(BitcodeKind, MB) {
this->ArchiveName = ArchiveName;
// Here we pass a new MemoryBufferRef which is identified by ArchiveName
// (the fully resolved path of the archive) + member name + offset of the
// member in the archive.
// ThinLTO uses the MemoryBufferRef identifier to access its internal
// data structures and if two archives define two members with the same name,
// this causes a collision which result in only one of the objects being
// taken into consideration at LTO time (which very likely causes undefined
// symbols later in the link stage).
MemoryBufferRef MBRef(MB.getBuffer(),
Saver.save(ArchiveName + MB.getBufferIdentifier() +
utostr(OffsetInArchive)));
Obj = check(lto::InputFile::create(MBRef), toString(this));
Triple T(Obj->getTargetTriple());
EKind = getBitcodeELFKind(T);
EMachine = getBitcodeMachineKind(MB.getBufferIdentifier(), T);
}
std::unique_ptr<InputFile> Lazy::getMember() {
MemoryBufferRef MBRef = File->getMember(&Sym);
// getMember returns an empty buffer if the member was already
// read from the library.
if (MBRef.getBuffer().empty())
return std::unique_ptr<InputFile>(nullptr);
file_magic Magic = identify_magic(MBRef.getBuffer());
if (Magic == file_magic::coff_import_library)
return std::unique_ptr<InputFile>(new ImportFile(MBRef));
std::unique_ptr<InputFile> Obj;
if (Magic == file_magic::coff_object)
Obj.reset(new ObjectFile(MBRef));
else if (Magic == file_magic::bitcode)
Obj.reset(new BitcodeFile(MBRef));
else
error(Twine(File->getName()) + ": unknown file type");
Obj->setParentName(File->getName());
return Obj;
}
std::error_code PDBFile::parseFileHeaders() {
std::error_code EC;
MemoryBufferRef BufferRef = *Context->Buffer;
Context->SB =
reinterpret_cast<const SuperBlock *>(BufferRef.getBufferStart());
const SuperBlock *SB = Context->SB;
// Make sure the file is sufficiently large to hold a super block.
if (BufferRef.getBufferSize() < sizeof(SuperBlock))
return std::make_error_code(std::errc::illegal_byte_sequence);
// Check the magic bytes.
if (memcmp(SB->MagicBytes, Magic, sizeof(Magic)) != 0)
return std::make_error_code(std::errc::illegal_byte_sequence);
// We don't support blocksizes which aren't a multiple of four bytes.
if (SB->BlockSize == 0 || SB->BlockSize % sizeof(support::ulittle32_t) != 0)
return std::make_error_code(std::errc::not_supported);
// We don't support directories whose sizes aren't a multiple of four bytes.
if (SB->NumDirectoryBytes % sizeof(support::ulittle32_t) != 0)
return std::make_error_code(std::errc::not_supported);
// The number of blocks which comprise the directory is a simple function of
// the number of bytes it contains.
uint64_t NumDirectoryBlocks = getNumDirectoryBlocks();
// The block map, as we understand it, is a block which consists of a list of
// block numbers.
// It is unclear what would happen if the number of blocks couldn't fit on a
// single block.
if (NumDirectoryBlocks > SB->BlockSize / sizeof(support::ulittle32_t))
return std::make_error_code(std::errc::illegal_byte_sequence);
return std::error_code();
}
ErrorOr<MemoryBufferRef> IRObjectFile::findBitcodeInMemBuffer(MemoryBufferRef Object) {
sys::fs::file_magic Type = sys::fs::identify_magic(Object.getBuffer());
switch (Type) {
case sys::fs::file_magic::bitcode:
return Object;
case sys::fs::file_magic::elf_relocatable:
case sys::fs::file_magic::macho_object:
case sys::fs::file_magic::coff_object: {
ErrorOr<std::unique_ptr<ObjectFile>> ObjFile =
ObjectFile::createObjectFile(Object, Type);
if (!ObjFile)
return ObjFile.getError();
return findBitcodeInObject(*ObjFile->get());
}
default:
return object_error::invalid_file_type;
}
}