1 //===- SymbolTable.h --------------------------------------------*- C++ -*-===//
2 //
3 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4 // See https://llvm.org/LICENSE.txt for license information.
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6 //
7 //===----------------------------------------------------------------------===//
8 
9 #ifndef LLD_ELF_SYMBOL_TABLE_H
10 #define LLD_ELF_SYMBOL_TABLE_H
11 
12 #include "Symbols.h"
13 #include "llvm/ADT/CachedHashString.h"
14 #include "llvm/ADT/DenseMap.h"
15 #include "llvm/Support/Compiler.h"
16 
17 namespace lld::elf {
18 
19 class InputFile;
20 class SharedFile;
21 
22 // SymbolTable is a bucket of all known symbols, including defined,
23 // undefined, or lazy symbols (the last one is symbols in archive
24 // files whose archive members are not yet loaded).
25 //
26 // We put all symbols of all files to a SymbolTable, and the
27 // SymbolTable selects the "best" symbols if there are name
28 // conflicts. For example, obviously, a defined symbol is better than
29 // an undefined symbol. Or, if there's a conflict between a lazy and a
30 // undefined, it'll read an archive member to read a real definition
31 // to replace the lazy symbol. The logic is implemented in the
32 // add*() functions, which are called by input files as they are parsed. There
33 // is one add* function per symbol type.
34 class SymbolTable {
35 public:
36   ArrayRef<Symbol *> getSymbols() const { return symVector; }
37 
38   void wrap(Symbol *sym, Symbol *real, Symbol *wrap);
39 
40   Symbol *insert(StringRef name);
41 
42   template <typename T> Symbol *addSymbol(const T &newSym) {
43     Symbol *sym = insert(newSym.getName());
44     sym->resolve(newSym);
45     return sym;
46   }
47   Symbol *addAndCheckDuplicate(const Defined &newSym);
48 
49   void scanVersionScript();
50 
51   Symbol *find(StringRef name);
52 
53   void handleDynamicList();
54 
55   // Set of .so files to not link the same shared object file more than once.
56   llvm::DenseMap<llvm::CachedHashStringRef, SharedFile *> soNames;
57 
58   // Comdat groups define "link once" sections. If two comdat groups have the
59   // same name, only one of them is linked, and the other is ignored. This map
60   // is used to uniquify them.
61   llvm::DenseMap<llvm::CachedHashStringRef, const InputFile *> comdatGroups;
62 
63 private:
64   SmallVector<Symbol *, 0> findByVersion(SymbolVersion ver);
65   SmallVector<Symbol *, 0> findAllByVersion(SymbolVersion ver,
66                                             bool includeNonDefault);
67 
68   llvm::StringMap<SmallVector<Symbol *, 0>> &getDemangledSyms();
69   bool assignExactVersion(SymbolVersion ver, uint16_t versionId,
70                           StringRef versionName, bool includeNonDefault);
71   void assignWildcardVersion(SymbolVersion ver, uint16_t versionId,
72                              bool includeNonDefault);
73 
74   // The order the global symbols are in is not defined. We can use an arbitrary
75   // order, but it has to be reproducible. That is true even when cross linking.
76   // The default hashing of StringRef produces different results on 32 and 64
77   // bit systems so we use a map to a vector. That is arbitrary, deterministic
78   // but a bit inefficient.
79   // FIXME: Experiment with passing in a custom hashing or sorting the symbols
80   // once symbol resolution is finished.
81   llvm::DenseMap<llvm::CachedHashStringRef, int> symMap;
82   SmallVector<Symbol *, 0> symVector;
83 
84   // A map from demangled symbol names to their symbol objects.
85   // This mapping is 1:N because two symbols with different versions
86   // can have the same name. We use this map to handle "extern C++ {}"
87   // directive in version scripts.
88   std::optional<llvm::StringMap<SmallVector<Symbol *, 0>>> demangledSyms;
89 };
90 
91 LLVM_LIBRARY_VISIBILITY extern SymbolTable symtab;
92 
93 } // namespace lld::elf
94 
95 #endif
96