CbC/CbC_llvm: lld/MachO/SyntheticSections.h comparison

comparison lld/MachO/SyntheticSections.h @ 207:2e18cbf3894f

LLVM12

author	Shinji KONO <kono@ie.u-ryukyu.ac.jp>
date	Tue, 08 Jun 2021 06:07:14 +0900
parents	0572611fdcc8
children	5f17cb93ff66

comparison

equal deleted inserted replaced

-:0572611fdcc8
+:2e18cbf3894f
 //===----------------------------------------------------------------------===//
 #ifndef LLD_MACHO_SYNTHETIC_SECTIONS_H
 #define LLD_MACHO_SYNTHETIC_SECTIONS_H
+#include "Config.h"
 #include "ExportTrie.h"
 #include "InputSection.h"
 #include "OutputSection.h"
+#include "OutputSegment.h"
 #include "Target.h"
+#include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/SetVector.h"
+#include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
+namespace llvm {
+class DWARFUnit;
+} // namespace llvm
 namespace lld {
 namespace macho {
-namespace section_names {
+class Defined;
-constexpr const char *pageZero = "__pagezero";
-constexpr const char *header = "__mach_header";
-constexpr const char *binding = "__binding";
-constexpr const char *lazyBinding = "__lazy_binding";
-constexpr const char *export_ = "__export";
-constexpr const char *symbolTable = "__symbol_table";
-constexpr const char *stringTable = "__string_table";
-constexpr const char *got = "__got";
-} // namespace section_names
 class DylibSymbol;
 class LoadCommand;
+class ObjFile;
+class UnwindInfoSection;
 class SyntheticSection : public OutputSection {
 public:
 SyntheticSection(const char *segname, const char *name);
 virtual ~SyntheticSection() = default;
 static bool classof(const OutputSection *sec) {
 return sec->kind() == SyntheticKind;
 }
+const StringRef segname;
+// This fake InputSection makes it easier for us to write code that applies
+// generically to both user inputs and synthetics.
+InputSection *isec;
+};
+// All sections in __LINKEDIT should inherit from this.
+class LinkEditSection : public SyntheticSection {
+public:
+LinkEditSection(const char *segname, const char *name)
+: SyntheticSection(segname, name) {
+align = target->wordSize;
+}
+virtual void finalizeContents() {}
+// Sections in __LINKEDIT are special: their offsets are recorded in the
+// load commands like LC_DYLD_INFO_ONLY and LC_SYMTAB, instead of in section
+// headers.
+bool isHidden() const override final { return true; }
+virtual uint64_t getRawSize() const = 0;
+// codesign (or more specifically libstuff) checks that each section in
+// __LINKEDIT ends where the next one starts -- no gaps are permitted. We
+// therefore align every section's start and end points to WordSize.
+//
+// NOTE: This assumes that the extra bytes required for alignment can be
+// zero-valued bytes.
+uint64_t getSize() const override final {
+return llvm::alignTo(getRawSize(), align);
+}
 };
 // The header of the Mach-O file, which must have a file offset of zero.
 class MachHeaderSection : public SyntheticSection {
 public:
 MachHeaderSection();
+bool isHidden() const override { return true; }
+uint64_t getSize() const override;
+void writeTo(uint8_t *buf) const override;
 void addLoadCommand(LoadCommand *);
-bool isHidden() const override { return true; }
-size_t getSize() const override;
+protected:
-void writeTo(uint8_t *buf) const override;
-private:
 std::vector<LoadCommand *> loadCommands;
 uint32_t sizeOfCmds = 0;
 };
 // A hidden section that exists solely for the purpose of creating the
 // __PAGEZERO segment, which is used to catch null pointer dereferences.
 class PageZeroSection : public SyntheticSection {
 public:
 PageZeroSection();
 bool isHidden() const override { return true; }
-size_t getSize() const override { return ImageBase; }
+uint64_t getSize() const override { return target->pageZeroSize; }
 uint64_t getFileSize() const override { return 0; }
 void writeTo(uint8_t *buf) const override {}
 };
-// This section will be populated by dyld with addresses to non-lazily-loaded
+// This is the base class for the GOT and TLVPointer sections, which are nearly
-// dylib symbols.
+// functionally identical -- they will both be populated by dyld with addresses
-class GotSection : public SyntheticSection {
+// to non-lazily-loaded dylib symbols. The main difference is that the
-public:
+// TLVPointerSection stores references to thread-local variables.
-GotSection();
+class NonLazyPointerSectionBase : public SyntheticSection {
+public:
-const llvm::SetVector<const DylibSymbol *> &getEntries() const {
+NonLazyPointerSectionBase(const char *segname, const char *name);
-return entries;
-}
+const llvm::SetVector<const Symbol *> &getEntries() const { return entries; }
 bool isNeeded() const override { return !entries.empty(); }
-size_t getSize() const override { return entries.size() * WordSize; }
+uint64_t getSize() const override {
+return entries.size() * target->wordSize;
-void writeTo(uint8_t *buf) const override {
+}
-// Nothing to write, GOT contains all zeros at link time; it's populated at
-// runtime by dyld.
+void writeTo(uint8_t *buf) const override;
-}
+void addEntry(Symbol *sym);
-void addEntry(DylibSymbol &sym);
+uint64_t getVA(uint32_t gotIndex) const {
-private:
+return addr + gotIndex * target->wordSize;
-llvm::SetVector<const DylibSymbol *> entries;
+}
+private:
+llvm::SetVector<const Symbol *> entries;
+};
+class GotSection : public NonLazyPointerSectionBase {
+public:
+GotSection()
+: NonLazyPointerSectionBase(segment_names::dataConst,
+section_names::got) {
+// TODO: section_64::reserved1 should be an index into the indirect symbol
+// table, which we do not currently emit
+}
+};
+class TlvPointerSection : public NonLazyPointerSectionBase {
+public:
+TlvPointerSection()
+: NonLazyPointerSectionBase(segment_names::data,
+section_names::threadPtrs) {}
+};
+struct Location {
+const InputSection *isec;
+uint64_t offset;
+Location(const InputSection *isec, uint64_t offset)
+: isec(isec), offset(offset) {}
+uint64_t getVA() const { return isec->getVA() + offset; }
+};
+// Stores rebase opcodes, which tell dyld where absolute addresses have been
+// encoded in the binary. If the binary is not loaded at its preferred address,
+// dyld has to rebase these addresses by adding an offset to them.
+class RebaseSection : public LinkEditSection {
+public:
+RebaseSection();
+void finalizeContents() override;
+uint64_t getRawSize() const override { return contents.size(); }
+bool isNeeded() const override { return !locations.empty(); }
+void writeTo(uint8_t *buf) const override;
+void addEntry(const InputSection *isec, uint64_t offset) {
+if (config->isPic)
+locations.push_back({isec, offset});
+}
+private:
+std::vector<Location> locations;
+SmallVector<char, 128> contents;
+};
+struct BindingEntry {
+const DylibSymbol *dysym;
+int64_t addend;
+Location target;
+BindingEntry(const DylibSymbol *dysym, int64_t addend, Location target)
+: dysym(dysym), addend(addend), target(std::move(target)) {}
 };
 // Stores bind opcodes for telling dyld which symbols to load non-lazily.
-class BindingSection : public SyntheticSection {
+class BindingSection : public LinkEditSection {
 public:
 BindingSection();
-void finalizeContents();
+void finalizeContents() override;
-size_t getSize() const override { return contents.size(); }
+uint64_t getRawSize() const override { return contents.size(); }
-// Like other sections in __LINKEDIT, the binding section is special: its
+bool isNeeded() const override { return !bindings.empty(); }
-// offsets are recorded in the LC_DYLD_INFO_ONLY load command, instead of in
+void writeTo(uint8_t *buf) const override;
-// section headers.
-bool isHidden() const override { return true; }
+void addEntry(const DylibSymbol *dysym, const InputSection *isec,
-bool isNeeded() const override;
+uint64_t offset, int64_t addend = 0) {
-void writeTo(uint8_t *buf) const override;
+bindings.emplace_back(dysym, addend, Location(isec, offset));
+}
+private:
+std::vector<BindingEntry> bindings;
+SmallVector<char, 128> contents;
+};
+struct WeakBindingEntry {
+const Symbol *symbol;
+int64_t addend;
+Location target;
+WeakBindingEntry(const Symbol *symbol, int64_t addend, Location target)
+: symbol(symbol), addend(addend), target(std::move(target)) {}
+};
+// Stores bind opcodes for telling dyld which weak symbols need coalescing.
+// There are two types of entries in this section:
+//
+//   1) Non-weak definitions: This is a symbol definition that weak symbols in
+//   other dylibs should coalesce to.
+//
+//   2) Weak bindings: These tell dyld that a given symbol reference should
+//   coalesce to a non-weak definition if one is found. Note that unlike the
+//   entries in the BindingSection, the bindings here only refer to these
+//   symbols by name, but do not specify which dylib to load them from.
+class WeakBindingSection : public LinkEditSection {
+public:
+WeakBindingSection();
+void finalizeContents() override;
+uint64_t getRawSize() const override { return contents.size(); }
+bool isNeeded() const override {
+return !bindings.empty() || !definitions.empty();
+}
+void writeTo(uint8_t *buf) const override;
+void addEntry(const Symbol *symbol, const InputSection *isec, uint64_t offset,
+int64_t addend = 0) {
+bindings.emplace_back(symbol, addend, Location(isec, offset));
+}
+bool hasEntry() const { return !bindings.empty(); }
+void addNonWeakDefinition(const Defined *defined) {
+definitions.emplace_back(defined);
+}
+bool hasNonWeakDefinition() const { return !definitions.empty(); }
+private:
+std::vector<WeakBindingEntry> bindings;
+std::vector<const Defined *> definitions;
 SmallVector<char, 128> contents;
 };
 // The following sections implement lazy symbol binding -- very similar to the
 // PLT mechanism in ELF.
 //
-// ELF's .plt section is broken up into two sections in Mach-O: StubsSection and
+// ELF's .plt section is broken up into two sections in Mach-O: StubsSection
-// StubHelperSection. Calls to functions in dylibs will end up calling into
+// and StubHelperSection. Calls to functions in dylibs will end up calling into
 // StubsSection, which contains indirect jumps to addresses stored in the
 // LazyPointerSection (the counterpart to ELF's .plt.got).
 //
-// Initially, the LazyPointerSection contains addresses that point into one of
+// We will first describe how non-weak symbols are handled.
-// the entry points in the middle of the StubHelperSection. The code in
+//
+// At program start, the LazyPointerSection contains addresses that point into
+// one of the entry points in the middle of the StubHelperSection. The code in
 // StubHelperSection will push on the stack an offset into the
 // LazyBindingSection. The push is followed by a jump to the beginning of the
 // StubHelperSection (similar to PLT0), which then calls into dyld_stub_binder.
 // dyld_stub_binder is a non-lazily-bound symbol, so this call looks it up in
 // the GOT.
 //
 // The stub binder will look up the bind opcodes in the LazyBindingSection at
-// the given offset. The bind opcodes will tell the binder to update the address
+// the given offset. The bind opcodes will tell the binder to update the
-// in the LazyPointerSection to point to the symbol, so that subsequent calls
+// address in the LazyPointerSection to point to the symbol, so that subsequent
-// don't have to redo the symbol resolution. The binder will then jump to the
+// calls don't have to redo the symbol resolution. The binder will then jump to
-// resolved symbol.
+// the resolved symbol.
+//
+// With weak symbols, the situation is slightly different. Since there is no
+// "weak lazy" lookup, function calls to weak symbols are always non-lazily
+// bound. We emit both regular non-lazy bindings as well as weak bindings, in
+// order that the weak bindings may overwrite the non-lazy bindings if an
+// appropriate symbol is found at runtime. However, the bound addresses will
+// still be written (non-lazily) into the LazyPointerSection.
 class StubsSection : public SyntheticSection {
 public:
 StubsSection();
-size_t getSize() const override;
+uint64_t getSize() const override;
 bool isNeeded() const override { return !entries.empty(); }
-void writeTo(uint8_t *buf) const override;
+void finalize() override;
+void writeTo(uint8_t *buf) const override;
-const llvm::SetVector<DylibSymbol *> &getEntries() const { return entries; }
+const llvm::SetVector<Symbol *> &getEntries() const { return entries; }
+// Returns whether the symbol was added. Note that every stubs entry will
-void addEntry(DylibSymbol &sym);
+// have a corresponding entry in the LazyPointerSection.
+bool addEntry(Symbol *);
-private:
+uint64_t getVA(uint32_t stubsIndex) const {
-llvm::SetVector<DylibSymbol *> entries;
+// ConcatOutputSection::finalize() can seek the address of a
+// stub before its address is assigned. Before __stubs is
+// finalized, return a contrived out-of-range address.
+return isFinal ? addr + stubsIndex * target->stubSize
+: TargetInfo::outOfRangeVA;
+}
+bool isFinal = false; // is address assigned?
+private:
+llvm::SetVector<Symbol *> entries;
 };
 class StubHelperSection : public SyntheticSection {
 public:
 StubHelperSection();
-size_t getSize() const override;
+uint64_t getSize() const override;
 bool isNeeded() const override;
 void writeTo(uint8_t *buf) const override;
 void setup();
 DylibSymbol *stubBinder = nullptr;
+Defined *dyldPrivate = nullptr;
 };
 // This section contains space for just a single word, and will be used by dyld
 // to cache an address to the image loader it uses. Note that unlike the other
 // synthetic sections, which are OutputSections, the ImageLoaderCacheSection is
 // an InputSection that gets merged into the __data OutputSection.
 class ImageLoaderCacheSection : public InputSection {
 public:
 ImageLoaderCacheSection();
-size_t getSize() const override { return WordSize; }
+uint64_t getSize() const override { return target->wordSize; }
 };
+// Note that this section may also be targeted by non-lazy bindings. In
+// particular, this happens when branch relocations target weak symbols.
 class LazyPointerSection : public SyntheticSection {
 public:
 LazyPointerSection();
-size_t getSize() const override;
+uint64_t getSize() const override;
 bool isNeeded() const override;
 void writeTo(uint8_t *buf) const override;
 };
-class LazyBindingSection : public SyntheticSection {
+class LazyBindingSection : public LinkEditSection {
 public:
 LazyBindingSection();
-void finalizeContents();
+void finalizeContents() override;
-size_t getSize() const override { return contents.size(); }
+uint64_t getRawSize() const override { return contents.size(); }
+bool isNeeded() const override { return !entries.empty(); }
+void writeTo(uint8_t *buf) const override;
+// Note that every entry here will by referenced by a corresponding entry in
+// the StubHelperSection.
+void addEntry(DylibSymbol *dysym);
+const llvm::SetVector<DylibSymbol *> &getEntries() const { return entries; }
+private:
 uint32_t encode(const DylibSymbol &);
-// Like other sections in __LINKEDIT, the lazy binding section is special: its
-// offsets are recorded in the LC_DYLD_INFO_ONLY load command, instead of in
+llvm::SetVector<DylibSymbol *> entries;
-// section headers.
-bool isHidden() const override { return true; }
-bool isNeeded() const override;
-void writeTo(uint8_t *buf) const override;
-private:
 SmallVector<char, 128> contents;
 llvm::raw_svector_ostream os{contents};
 };
 // Stores a trie that describes the set of exported symbols.
-class ExportSection : public SyntheticSection {
+class ExportSection : public LinkEditSection {
 public:
 ExportSection();
-void finalizeContents();
+void finalizeContents() override;
-size_t getSize() const override { return size; }
+uint64_t getRawSize() const override { return size; }
-// Like other sections in __LINKEDIT, the export section is special: its
+void writeTo(uint8_t *buf) const override;
-// offsets are recorded in the LC_DYLD_INFO_ONLY load command, instead of in
-// section headers.
+bool hasWeakSymbol = false;
-bool isHidden() const override { return true; }
-void writeTo(uint8_t *buf) const override;
 private:
 TrieBuilder trieBuilder;
 size_t size = 0;
 };
+class FunctionStartsSection : public LinkEditSection {
+public:
+FunctionStartsSection();
+void finalizeContents() override;
+uint64_t getRawSize() const override { return contents.size(); }
+void writeTo(uint8_t *buf) const override;
+private:
+SmallVector<char, 128> contents;
+};
 // Stores the strings referenced by the symbol table.
-class StringTableSection : public SyntheticSection {
+class StringTableSection : public LinkEditSection {
 public:
 StringTableSection();
 // Returns the start offset of the added string.
 uint32_t addString(StringRef);
-size_t getSize() const override { return size; }
+uint64_t getRawSize() const override { return size; }
-// Like other sections in __LINKEDIT, the string table section is special: its
+void writeTo(uint8_t *buf) const override;
-// offsets are recorded in the LC_SYMTAB load command, instead of in section
-// headers.
+static constexpr size_t emptyStringIndex = 1;
-bool isHidden() const override { return true; }
-void writeTo(uint8_t *buf) const override;
+private:
+// ld64 emits string tables which start with a space and a zero byte. We
-private:
+// match its behavior here since some tools depend on it.
-// An n_strx value of 0 always indicates the empty string, so we must locate
+// Consequently, the empty string will be at index 1, not zero.
-// our non-empty string values at positive offsets in the string table.
+std::vector<StringRef> strings{" "};
-// Therefore we insert a dummy value at position zero.
+size_t size = 2;
-std::vector<StringRef> strings{"\0"};
-size_t size = 1;
 };
 struct SymtabEntry {
 Symbol *sym;
 size_t strx;
 };
-class SymtabSection : public SyntheticSection {
+struct StabsEntry {
-public:
+uint8_t type = 0;
+uint32_t strx = StringTableSection::emptyStringIndex;
+uint8_t sect = 0;
+uint16_t desc = 0;
+uint64_t value = 0;
+StabsEntry() = default;
+explicit StabsEntry(uint8_t type) : type(type) {}
+};
+// Symbols of the same type must be laid out contiguously: we choose to emit
+// all local symbols first, then external symbols, and finally undefined
+// symbols. For each symbol type, the LC_DYSYMTAB load command will record the
+// range (start index and total number) of those symbols in the symbol table.
+class SymtabSection : public LinkEditSection {
+public:
+void finalizeContents() override;
+uint32_t getNumSymbols() const;
+uint32_t getNumLocalSymbols() const {
+return stabs.size() + localSymbols.size();
+}
+uint32_t getNumExternalSymbols() const { return externalSymbols.size(); }
+uint32_t getNumUndefinedSymbols() const { return undefinedSymbols.size(); }
+private:
+void emitBeginSourceStab(llvm::DWARFUnit *compileUnit);
+void emitEndSourceStab();
+void emitObjectFileStab(ObjFile *);
+void emitEndFunStab(Defined *);
+void emitStabs();
+protected:
 SymtabSection(StringTableSection &);
-void finalizeContents();
-size_t getNumSymbols() const { return symbols.size(); }
-size_t getSize() const override;
-// Like other sections in __LINKEDIT, the symtab section is special: its
-// offsets are recorded in the LC_SYMTAB load command, instead of in section
-// headers.
-bool isHidden() const override { return true; }
-void writeTo(uint8_t *buf) const override;
-private:
 StringTableSection &stringTableSection;
-std::vector<SymtabEntry> symbols;
+// STABS symbols are always local symbols, but we represent them with special
+// entries because they may use fields like n_sect and n_desc differently.
+std::vector<StabsEntry> stabs;
+std::vector<SymtabEntry> localSymbols;
+std::vector<SymtabEntry> externalSymbols;
+std::vector<SymtabEntry> undefinedSymbols;
+};
+template <class LP> SymtabSection *makeSymtabSection(StringTableSection &);
+// The indirect symbol table is a list of 32-bit integers that serve as indices
+// into the (actual) symbol table. The indirect symbol table is a
+// concatenation of several sub-arrays of indices, each sub-array belonging to
+// a separate section. The starting offset of each sub-array is stored in the
+// reserved1 header field of the respective section.
+//
+// These sub-arrays provide symbol information for sections that store
+// contiguous sequences of symbol references. These references can be pointers
+// (e.g. those in the GOT and TLVP sections) or assembly sequences (e.g.
+// function stubs).
+class IndirectSymtabSection : public LinkEditSection {
+public:
+IndirectSymtabSection();
+void finalizeContents() override;
+uint32_t getNumSymbols() const;
+uint64_t getRawSize() const override {
+return getNumSymbols() * sizeof(uint32_t);
+}
+bool isNeeded() const override;
+void writeTo(uint8_t *buf) const override;
+};
+// The code signature comes at the very end of the linked output file.
+class CodeSignatureSection : public LinkEditSection {
+public:
+static constexpr uint8_t blockSizeShift = 12;
+static constexpr size_t blockSize = (1 << blockSizeShift); // 4 KiB
+static constexpr size_t hashSize = 256 / 8;
+static constexpr size_t blobHeadersSize = llvm::alignTo<8>(
+sizeof(llvm::MachO::CS_SuperBlob) + sizeof(llvm::MachO::CS_BlobIndex));
+static constexpr uint32_t fixedHeadersSize =
+blobHeadersSize + sizeof(llvm::MachO::CS_CodeDirectory);
+uint32_t fileNamePad = 0;
+uint32_t allHeadersSize = 0;
+StringRef fileName;
+CodeSignatureSection();
+uint64_t getRawSize() const override;
+bool isNeeded() const override { return true; }
+void writeTo(uint8_t *buf) const override;
+uint32_t getBlockCount() const;
+void writeHashes(uint8_t *buf) const;
+};
+class BitcodeBundleSection : public SyntheticSection {
+public:
+BitcodeBundleSection();
+uint64_t getSize() const override { return xarSize; }
+void finalize() override;
+void writeTo(uint8_t *buf) const override;
+private:
+llvm::SmallString<261> xarPath;
+uint64_t xarSize;
 };
 struct InStruct {
+MachHeaderSection *header = nullptr;
+RebaseSection *rebase = nullptr;
+BindingSection *binding = nullptr;
+WeakBindingSection *weakBinding = nullptr;
+LazyBindingSection *lazyBinding = nullptr;
+ExportSection *exports = nullptr;
 GotSection *got = nullptr;
+TlvPointerSection *tlvPointers = nullptr;
 LazyPointerSection *lazyPointers = nullptr;
 StubsSection *stubs = nullptr;
 StubHelperSection *stubHelper = nullptr;
 ImageLoaderCacheSection *imageLoaderCache = nullptr;
+UnwindInfoSection *unwindInfo = nullptr;
 };
 extern InStruct in;
+extern std::vector<SyntheticSection *> syntheticSections;
+void createSyntheticSymbols();
 } // namespace macho
 } // namespace lld
 #endif

Mercurial > hg > CbC > CbC_llvm

comparison lld/MachO/SyntheticSections.h @ 207:2e18cbf3894f