xref: /freebsd/contrib/llvm-project/lld/ELF/SymbolTable.h (revision 81ad626541db97eb356e2c1d4a20eb2a26a766ab)
10b57cec5SDimitry Andric //===- SymbolTable.h --------------------------------------------*- C++ -*-===//
20b57cec5SDimitry Andric //
30b57cec5SDimitry Andric // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
40b57cec5SDimitry Andric // See https://llvm.org/LICENSE.txt for license information.
50b57cec5SDimitry Andric // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
60b57cec5SDimitry Andric //
70b57cec5SDimitry Andric //===----------------------------------------------------------------------===//
80b57cec5SDimitry Andric 
90b57cec5SDimitry Andric #ifndef LLD_ELF_SYMBOL_TABLE_H
100b57cec5SDimitry Andric #define LLD_ELF_SYMBOL_TABLE_H
110b57cec5SDimitry Andric 
120b57cec5SDimitry Andric #include "Symbols.h"
130b57cec5SDimitry Andric #include "llvm/ADT/CachedHashString.h"
140b57cec5SDimitry Andric #include "llvm/ADT/DenseMap.h"
150b57cec5SDimitry Andric 
160b57cec5SDimitry Andric namespace lld {
170b57cec5SDimitry Andric namespace elf {
180b57cec5SDimitry Andric 
19*81ad6265SDimitry Andric class InputFile;
20*81ad6265SDimitry Andric class SharedFile;
21*81ad6265SDimitry Andric 
220b57cec5SDimitry Andric // SymbolTable is a bucket of all known symbols, including defined,
230b57cec5SDimitry Andric // undefined, or lazy symbols (the last one is symbols in archive
240b57cec5SDimitry Andric // files whose archive members are not yet loaded).
250b57cec5SDimitry Andric //
260b57cec5SDimitry Andric // We put all symbols of all files to a SymbolTable, and the
270b57cec5SDimitry Andric // SymbolTable selects the "best" symbols if there are name
280b57cec5SDimitry Andric // conflicts. For example, obviously, a defined symbol is better than
290b57cec5SDimitry Andric // an undefined symbol. Or, if there's a conflict between a lazy and a
300b57cec5SDimitry Andric // undefined, it'll read an archive member to read a real definition
310b57cec5SDimitry Andric // to replace the lazy symbol. The logic is implemented in the
320b57cec5SDimitry Andric // add*() functions, which are called by input files as they are parsed. There
330b57cec5SDimitry Andric // is one add* function per symbol type.
340b57cec5SDimitry Andric class SymbolTable {
35480093f4SDimitry Andric public:
3604eeddc0SDimitry Andric   ArrayRef<Symbol *> symbols() const { return symVector; }
370b57cec5SDimitry Andric 
38480093f4SDimitry Andric   void wrap(Symbol *sym, Symbol *real, Symbol *wrap);
39480093f4SDimitry Andric 
400b57cec5SDimitry Andric   Symbol *insert(StringRef name);
410b57cec5SDimitry Andric 
4285868e8aSDimitry Andric   Symbol *addSymbol(const Symbol &newSym);
43*81ad6265SDimitry Andric   Symbol *addAndCheckDuplicate(const Defined &newSym);
440b57cec5SDimitry Andric 
450b57cec5SDimitry Andric   void scanVersionScript();
460b57cec5SDimitry Andric 
470b57cec5SDimitry Andric   Symbol *find(StringRef name);
480b57cec5SDimitry Andric 
490b57cec5SDimitry Andric   void handleDynamicList();
500b57cec5SDimitry Andric 
510b57cec5SDimitry Andric   // Set of .so files to not link the same shared object file more than once.
5204eeddc0SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, SharedFile *> soNames;
530b57cec5SDimitry Andric 
540b57cec5SDimitry Andric   // Comdat groups define "link once" sections. If two comdat groups have the
550b57cec5SDimitry Andric   // same name, only one of them is linked, and the other is ignored. This map
560b57cec5SDimitry Andric   // is used to uniquify them.
570b57cec5SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, const InputFile *> comdatGroups;
580b57cec5SDimitry Andric 
590b57cec5SDimitry Andric private:
600eae32dcSDimitry Andric   SmallVector<Symbol *, 0> findByVersion(SymbolVersion ver);
610eae32dcSDimitry Andric   SmallVector<Symbol *, 0> findAllByVersion(SymbolVersion ver,
626e75b2fbSDimitry Andric                                             bool includeNonDefault);
630b57cec5SDimitry Andric 
640eae32dcSDimitry Andric   llvm::StringMap<SmallVector<Symbol *, 0>> &getDemangledSyms();
656e75b2fbSDimitry Andric   bool assignExactVersion(SymbolVersion ver, uint16_t versionId,
666e75b2fbSDimitry Andric                           StringRef versionName, bool includeNonDefault);
676e75b2fbSDimitry Andric   void assignWildcardVersion(SymbolVersion ver, uint16_t versionId,
686e75b2fbSDimitry Andric                              bool includeNonDefault);
690b57cec5SDimitry Andric 
700b57cec5SDimitry Andric   // The order the global symbols are in is not defined. We can use an arbitrary
710b57cec5SDimitry Andric   // order, but it has to be reproducible. That is true even when cross linking.
720b57cec5SDimitry Andric   // The default hashing of StringRef produces different results on 32 and 64
730b57cec5SDimitry Andric   // bit systems so we use a map to a vector. That is arbitrary, deterministic
740b57cec5SDimitry Andric   // but a bit inefficient.
750b57cec5SDimitry Andric   // FIXME: Experiment with passing in a custom hashing or sorting the symbols
760b57cec5SDimitry Andric   // once symbol resolution is finished.
770b57cec5SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, int> symMap;
780eae32dcSDimitry Andric   SmallVector<Symbol *, 0> symVector;
790b57cec5SDimitry Andric 
800b57cec5SDimitry Andric   // A map from demangled symbol names to their symbol objects.
810b57cec5SDimitry Andric   // This mapping is 1:N because two symbols with different versions
820b57cec5SDimitry Andric   // can have the same name. We use this map to handle "extern C++ {}"
830b57cec5SDimitry Andric   // directive in version scripts.
840eae32dcSDimitry Andric   llvm::Optional<llvm::StringMap<SmallVector<Symbol *, 0>>> demangledSyms;
850b57cec5SDimitry Andric };
860b57cec5SDimitry Andric 
870eae32dcSDimitry Andric extern std::unique_ptr<SymbolTable> symtab;
880b57cec5SDimitry Andric 
890b57cec5SDimitry Andric } // namespace elf
900b57cec5SDimitry Andric } // namespace lld
910b57cec5SDimitry Andric 
920b57cec5SDimitry Andric #endif
93