1 | //===- SymbolRemappingReader.h - Read symbol remapping file -----*- 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 | // This file contains definitions needed for reading and applying symbol |
10 | // remapping files. |
11 | // |
12 | // Support is provided only for the Itanium C++ name mangling scheme for now. |
13 | // |
14 | // NOTE: If you are making changes to this file format, please remember |
15 | // to document them in the Clang documentation at |
16 | // tools/clang/docs/UsersManual.rst. |
17 | // |
18 | // File format |
19 | // ----------- |
20 | // |
21 | // The symbol remappings are written as an ASCII text file. Blank lines and |
22 | // lines starting with a # are ignored. All other lines specify a kind of |
23 | // mangled name fragment, along with two fragments of that kind that should |
24 | // be treated as equivalent, separated by spaces. |
25 | // |
26 | // See http://itanium-cxx-abi.github.io/cxx-abi/abi.html#mangling for a |
27 | // description of the Itanium name mangling scheme. |
28 | // |
29 | // The accepted fragment kinds are: |
30 | // |
31 | // * name A <name>, such as 6foobar or St3__1 |
32 | // * type A <type>, such as Ss or N4llvm9StringRefE |
33 | // * encoding An <encoding> (a complete mangling without the leading _Z) |
34 | // |
35 | // For example: |
36 | // |
37 | // # Ignore int / long differences to treat symbols from 32-bit and 64-bit |
38 | // # builds with differing size_t / ptrdiff_t / intptr_t as equivalent. |
39 | // type i l |
40 | // type j m |
41 | // |
42 | // # Ignore differences between libc++ and libstdc++, and between libstdc++'s |
43 | // # C++98 and C++11 ABIs. |
44 | // name 3std St3__1 |
45 | // name 3std St7__cxx11 |
46 | // |
47 | // # Remap a function overload to a specialization of a template (including |
48 | // # any local symbols declared within it). |
49 | // encoding N2NS1fEi N2NS1fIiEEvT_ |
50 | // |
51 | // # Substitutions must be remapped separately from namespace 'std' for now. |
52 | // name Sa NSt3__19allocatorE |
53 | // name Sb NSt3__112basic_stringE |
54 | // type Ss NSt3__112basic_stringIcSt11char_traitsIcESaE |
55 | // # ... |
56 | // |
57 | //===----------------------------------------------------------------------===// |
58 | |
59 | #ifndef LLVM_PROFILEDATA_SYMBOLREMAPPINGREADER_H |
60 | #define LLVM_PROFILEDATA_SYMBOLREMAPPINGREADER_H |
61 | |
62 | #include "llvm/ADT/StringRef.h" |
63 | #include "llvm/ProfileData/ItaniumManglingCanonicalizer.h" |
64 | #include "llvm/Support/Error.h" |
65 | |
66 | namespace llvm { |
67 | |
68 | class MemoryBuffer; |
69 | |
70 | class SymbolRemappingParseError : public ErrorInfo<SymbolRemappingParseError> { |
71 | public: |
72 | SymbolRemappingParseError(StringRef File, int64_t Line, const Twine &Message) |
73 | : File(File), Line(Line), Message(Message.str()) {} |
74 | |
75 | void log(llvm::raw_ostream &OS) const override { |
76 | OS << File << ':' << Line << ": " << Message; |
77 | } |
78 | std::error_code convertToErrorCode() const override { |
79 | return llvm::inconvertibleErrorCode(); |
80 | } |
81 | |
82 | StringRef getFileName() const { return File; } |
83 | int64_t getLineNum() const { return Line; } |
84 | StringRef getMessage() const { return Message; } |
85 | |
86 | static char ID; |
87 | |
88 | private: |
89 | std::string File; |
90 | int64_t Line; |
91 | std::string Message; |
92 | }; |
93 | |
94 | /// Reader for symbol remapping files. |
95 | /// |
96 | /// Remaps the symbol names in profile data to match those in the program |
97 | /// according to a set of rules specified in a given file. |
98 | class SymbolRemappingReader { |
99 | public: |
100 | /// Read remappings from the given buffer, which must live as long as |
101 | /// the remapper. |
102 | Error read(MemoryBuffer &B); |
103 | |
104 | /// A Key represents an equivalence class of symbol names. |
105 | using Key = uintptr_t; |
106 | |
107 | /// Construct a key for the given symbol, or return an existing one if an |
108 | /// equivalent name has already been inserted. The symbol name must live |
109 | /// as long as the remapper. |
110 | /// |
111 | /// The result will be Key() if the name cannot be remapped (typically |
112 | /// because it is not a valid mangled name). |
113 | Key insert(StringRef FunctionName) { |
114 | return Canonicalizer.canonicalize(Mangling: FunctionName); |
115 | } |
116 | |
117 | /// Map the given symbol name into the key for the corresponding equivalence |
118 | /// class. |
119 | /// |
120 | /// The result will typically be Key() if no equivalent symbol has been |
121 | /// inserted, but this is not guaranteed: a Key different from all keys ever |
122 | /// returned by \c insert may be returned instead. |
123 | Key lookup(StringRef FunctionName) { |
124 | return Canonicalizer.lookup(Mangling: FunctionName); |
125 | } |
126 | |
127 | private: |
128 | ItaniumManglingCanonicalizer Canonicalizer; |
129 | }; |
130 | |
131 | } // end namespace llvm |
132 | |
133 | #endif // LLVM_PROFILEDATA_SYMBOLREMAPPINGREADER_H |
134 | |