xref: /freebsd/contrib/llvm-project/lld/ELF/SymbolTable.h (revision bdd1243df58e60e85101c09001d9812a789b6bc4)
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"
15*bdd1243dSDimitry Andric #include "llvm/Support/Compiler.h"
160b57cec5SDimitry Andric 
17*bdd1243dSDimitry Andric namespace lld::elf {
180b57cec5SDimitry Andric 
1981ad6265SDimitry Andric class InputFile;
2081ad6265SDimitry Andric class SharedFile;
2181ad6265SDimitry 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:
36*bdd1243dSDimitry Andric   ArrayRef<Symbol *> getSymbols() 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 
42*bdd1243dSDimitry Andric   template <typename T> Symbol *addSymbol(const T &newSym) {
43*bdd1243dSDimitry Andric     Symbol *sym = insert(newSym.getName());
44*bdd1243dSDimitry Andric     sym->resolve(newSym);
45*bdd1243dSDimitry Andric     return sym;
46*bdd1243dSDimitry Andric   }
4781ad6265SDimitry Andric   Symbol *addAndCheckDuplicate(const Defined &newSym);
480b57cec5SDimitry Andric 
490b57cec5SDimitry Andric   void scanVersionScript();
500b57cec5SDimitry Andric 
510b57cec5SDimitry Andric   Symbol *find(StringRef name);
520b57cec5SDimitry Andric 
530b57cec5SDimitry Andric   void handleDynamicList();
540b57cec5SDimitry Andric 
550b57cec5SDimitry Andric   // Set of .so files to not link the same shared object file more than once.
5604eeddc0SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, SharedFile *> soNames;
570b57cec5SDimitry Andric 
580b57cec5SDimitry Andric   // Comdat groups define "link once" sections. If two comdat groups have the
590b57cec5SDimitry Andric   // same name, only one of them is linked, and the other is ignored. This map
600b57cec5SDimitry Andric   // is used to uniquify them.
610b57cec5SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, const InputFile *> comdatGroups;
620b57cec5SDimitry Andric 
630b57cec5SDimitry Andric private:
640eae32dcSDimitry Andric   SmallVector<Symbol *, 0> findByVersion(SymbolVersion ver);
650eae32dcSDimitry Andric   SmallVector<Symbol *, 0> findAllByVersion(SymbolVersion ver,
666e75b2fbSDimitry Andric                                             bool includeNonDefault);
670b57cec5SDimitry Andric 
680eae32dcSDimitry Andric   llvm::StringMap<SmallVector<Symbol *, 0>> &getDemangledSyms();
696e75b2fbSDimitry Andric   bool assignExactVersion(SymbolVersion ver, uint16_t versionId,
706e75b2fbSDimitry Andric                           StringRef versionName, bool includeNonDefault);
716e75b2fbSDimitry Andric   void assignWildcardVersion(SymbolVersion ver, uint16_t versionId,
726e75b2fbSDimitry Andric                              bool includeNonDefault);
730b57cec5SDimitry Andric 
740b57cec5SDimitry Andric   // The order the global symbols are in is not defined. We can use an arbitrary
750b57cec5SDimitry Andric   // order, but it has to be reproducible. That is true even when cross linking.
760b57cec5SDimitry Andric   // The default hashing of StringRef produces different results on 32 and 64
770b57cec5SDimitry Andric   // bit systems so we use a map to a vector. That is arbitrary, deterministic
780b57cec5SDimitry Andric   // but a bit inefficient.
790b57cec5SDimitry Andric   // FIXME: Experiment with passing in a custom hashing or sorting the symbols
800b57cec5SDimitry Andric   // once symbol resolution is finished.
810b57cec5SDimitry Andric   llvm::DenseMap<llvm::CachedHashStringRef, int> symMap;
820eae32dcSDimitry Andric   SmallVector<Symbol *, 0> symVector;
830b57cec5SDimitry Andric 
840b57cec5SDimitry Andric   // A map from demangled symbol names to their symbol objects.
850b57cec5SDimitry Andric   // This mapping is 1:N because two symbols with different versions
860b57cec5SDimitry Andric   // can have the same name. We use this map to handle "extern C++ {}"
870b57cec5SDimitry Andric   // directive in version scripts.
88*bdd1243dSDimitry Andric   std::optional<llvm::StringMap<SmallVector<Symbol *, 0>>> demangledSyms;
890b57cec5SDimitry Andric };
900b57cec5SDimitry Andric 
91*bdd1243dSDimitry Andric LLVM_LIBRARY_VISIBILITY extern SymbolTable symtab;
920b57cec5SDimitry Andric 
93*bdd1243dSDimitry Andric } // namespace lld::elf
940b57cec5SDimitry Andric 
950b57cec5SDimitry Andric #endif
96