1 //===- llvm/MC/MCSymbolizer.h - MCSymbolizer class --------------*- 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 the declaration of the MCSymbolizer class, which is used 10 // to symbolize instructions decoded from an object, that is, transform their 11 // immediate operands to MCExprs. 12 // 13 //===----------------------------------------------------------------------===// 14 15 #ifndef LLVM_MC_MCDISASSEMBLER_MCSYMBOLIZER_H 16 #define LLVM_MC_MCDISASSEMBLER_MCSYMBOLIZER_H 17 18 #include "llvm/ADT/ArrayRef.h" 19 #include "llvm/MC/MCDisassembler/MCRelocationInfo.h" 20 #include <cstdint> 21 #include <memory> 22 #include <utility> 23 24 namespace llvm { 25 26 class MCContext; 27 class MCInst; 28 class raw_ostream; 29 30 /// Symbolize and annotate disassembled instructions. 31 /// 32 /// For now this mimics the old symbolization logic (from both ARM and x86), that 33 /// relied on user-provided (C API) callbacks to do the actual symbol lookup in 34 /// the object file. This was moved to MCExternalSymbolizer. 35 /// A better API would not rely on actually calling the two methods here from 36 /// inside each disassembler, but would use the instr info to determine what 37 /// operands are actually symbolizable, and in what way. I don't think this 38 /// information exists right now. 39 class MCSymbolizer { 40 protected: 41 MCContext &Ctx; 42 std::unique_ptr<MCRelocationInfo> RelInfo; 43 44 public: 45 /// Construct an MCSymbolizer, taking ownership of \p RelInfo. 46 MCSymbolizer(MCContext &Ctx, std::unique_ptr<MCRelocationInfo> RelInfo) 47 : Ctx(Ctx), RelInfo(std::move(RelInfo)) { 48 } 49 50 MCSymbolizer(const MCSymbolizer &) = delete; 51 MCSymbolizer &operator=(const MCSymbolizer &) = delete; 52 virtual ~MCSymbolizer(); 53 54 /// Try to add a symbolic operand instead of \p Value to the MCInst. 55 /// 56 /// Instead of having a difficult to read immediate, a symbolic operand would 57 /// represent this immediate in a more understandable way, for instance as a 58 /// symbol or an offset from a symbol. Relocations can also be used to enrich 59 /// the symbolic expression. 60 /// \param Inst - The MCInst where to insert the symbolic operand. 61 /// \param cStream - Stream to print comments and annotations on. 62 /// \param Value - Operand value, pc-adjusted by the caller if necessary. 63 /// \param Address - Load address of the instruction. 64 /// \param IsBranch - Is the instruction a branch? 65 /// \param Offset - Byte offset of the operand inside the inst. 66 /// \param OpSize - Size of the operand in bytes. 67 /// \param InstSize - Size of the instruction in bytes. 68 /// \return Whether a symbolic operand was added. 69 virtual bool tryAddingSymbolicOperand(MCInst &Inst, raw_ostream &cStream, 70 int64_t Value, uint64_t Address, 71 bool IsBranch, uint64_t Offset, 72 uint64_t OpSize, uint64_t InstSize) = 0; 73 74 /// Try to add a comment on the PC-relative load. 75 /// For instance, in Mach-O, this is used to add annotations to instructions 76 /// that use C string literals, as found in __cstring. 77 virtual void tryAddingPcLoadReferenceComment(raw_ostream &cStream, 78 int64_t Value, 79 uint64_t Address) = 0; 80 81 /// Get the MCSymbolizer's list of addresses that were referenced by 82 /// symbolizable operands but not resolved to a symbol. The caller (some 83 /// code that is disassembling a section or other chunk of code) would 84 /// typically create a synthetic label at each address and add them to its 85 /// list of symbols in the section, before creating a new MCSymbolizer with 86 /// the enhanced symbol list and retrying disassembling the section. 87 /// The returned array is unordered and may have duplicates. 88 /// The returned ArrayRef stops being valid on any call to or destruction of 89 /// the MCSymbolizer object. 90 virtual ArrayRef<uint64_t> getReferencedAddresses() const { return {}; } 91 }; 92 93 } // end namespace llvm 94 95 #endif // LLVM_MC_MCDISASSEMBLER_MCSYMBOLIZER_H 96