diff options
Diffstat (limited to 'include/llvm/MC/MCDisassembler')
| -rw-r--r-- | include/llvm/MC/MCDisassembler/MCDisassembler.h | 113 | ||||
| -rw-r--r-- | include/llvm/MC/MCDisassembler/MCExternalSymbolizer.h | 58 | ||||
| -rw-r--r-- | include/llvm/MC/MCDisassembler/MCRelocationInfo.h | 51 | ||||
| -rw-r--r-- | include/llvm/MC/MCDisassembler/MCSymbolizer.h | 85 |
4 files changed, 307 insertions, 0 deletions
diff --git a/include/llvm/MC/MCDisassembler/MCDisassembler.h b/include/llvm/MC/MCDisassembler/MCDisassembler.h new file mode 100644 index 0000000000000..9006d87abb43d --- /dev/null +++ b/include/llvm/MC/MCDisassembler/MCDisassembler.h @@ -0,0 +1,113 @@ +//===-- llvm/MC/MCDisassembler.h - Disassembler interface -------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +#ifndef LLVM_MC_MCDISASSEMBLER_MCDISASSEMBLER_H +#define LLVM_MC_MCDISASSEMBLER_MCDISASSEMBLER_H + +#include "llvm-c/Disassembler.h" +#include "llvm/MC/MCDisassembler/MCSymbolizer.h" +#include "llvm/Support/DataTypes.h" + +namespace llvm { + +template <typename T> class ArrayRef; +class MCInst; +class MCSubtargetInfo; +class raw_ostream; +class MCContext; + +/// Superclass for all disassemblers. Consumes a memory region and provides an +/// array of assembly instructions. +class MCDisassembler { +public: + /// Ternary decode status. Most backends will just use Fail and + /// Success, however some have a concept of an instruction with + /// understandable semantics but which is architecturally + /// incorrect. An example of this is ARM UNPREDICTABLE instructions + /// which are disassemblable but cause undefined behaviour. + /// + /// Because it makes sense to disassemble these instructions, there + /// is a "soft fail" failure mode that indicates the MCInst& is + /// valid but architecturally incorrect. + /// + /// The enum numbers are deliberately chosen such that reduction + /// from Success->SoftFail ->Fail can be done with a simple + /// bitwise-AND: + /// + /// LEFT & TOP = | Success Unpredictable Fail + /// --------------+----------------------------------- + /// Success | Success Unpredictable Fail + /// Unpredictable | Unpredictable Unpredictable Fail + /// Fail | Fail Fail Fail + /// + /// An easy way of encoding this is as 0b11, 0b01, 0b00 for + /// Success, SoftFail, Fail respectively. + enum DecodeStatus { + Fail = 0, + SoftFail = 1, + Success = 3 + }; + + MCDisassembler(const MCSubtargetInfo &STI, MCContext &Ctx) + : Ctx(Ctx), STI(STI), Symbolizer(), CommentStream(nullptr) {} + + virtual ~MCDisassembler(); + + /// Returns the disassembly of a single instruction. + /// + /// \param Instr - An MCInst to populate with the contents of the + /// instruction. + /// \param Size - A value to populate with the size of the instruction, or + /// the number of bytes consumed while attempting to decode + /// an invalid instruction. + /// \param Address - The address, in the memory space of region, of the first + /// byte of the instruction. + /// \param VStream - The stream to print warnings and diagnostic messages on. + /// \param CStream - The stream to print comments and annotations on. + /// \return - MCDisassembler::Success if the instruction is valid, + /// MCDisassembler::SoftFail if the instruction was + /// disassemblable but invalid, + /// MCDisassembler::Fail if the instruction was invalid. + virtual DecodeStatus getInstruction(MCInst &Instr, uint64_t &Size, + ArrayRef<uint8_t> Bytes, uint64_t Address, + raw_ostream &VStream, + raw_ostream &CStream) const = 0; + +private: + MCContext &Ctx; + +protected: + // Subtarget information, for instruction decoding predicates if required. + const MCSubtargetInfo &STI; + std::unique_ptr<MCSymbolizer> Symbolizer; + +public: + // Helpers around MCSymbolizer + bool tryAddingSymbolicOperand(MCInst &Inst, + int64_t Value, + uint64_t Address, bool IsBranch, + uint64_t Offset, uint64_t InstSize) const; + + void tryAddingPcLoadReferenceComment(int64_t Value, uint64_t Address) const; + + /// Set \p Symzer as the current symbolizer. + /// This takes ownership of \p Symzer, and deletes the previously set one. + void setSymbolizer(std::unique_ptr<MCSymbolizer> Symzer); + + MCContext& getContext() const { return Ctx; } + + const MCSubtargetInfo& getSubtargetInfo() const { return STI; } + + // Marked mutable because we cache it inside the disassembler, rather than + // having to pass it around as an argument through all the autogenerated code. + mutable raw_ostream *CommentStream; +}; + +} // namespace llvm + +#endif diff --git a/include/llvm/MC/MCDisassembler/MCExternalSymbolizer.h b/include/llvm/MC/MCDisassembler/MCExternalSymbolizer.h new file mode 100644 index 0000000000000..bd3e5d4638e54 --- /dev/null +++ b/include/llvm/MC/MCDisassembler/MCExternalSymbolizer.h @@ -0,0 +1,58 @@ +//===-- llvm/MC/MCExternalSymbolizer.h - ------------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file contains the declaration of the MCExternalSymbolizer class, which +// enables library users to provide callbacks (through the C API) to do the +// symbolization externally. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_MC_MCDISASSEMBLER_MCEXTERNALSYMBOLIZER_H +#define LLVM_MC_MCDISASSEMBLER_MCEXTERNALSYMBOLIZER_H + +#include "llvm-c/Disassembler.h" +#include "llvm/MC/MCDisassembler/MCSymbolizer.h" +#include <memory> + +namespace llvm { + +/// \brief Symbolize using user-provided, C API, callbacks. +/// +/// See llvm-c/Disassembler.h. +class MCExternalSymbolizer : public MCSymbolizer { +protected: + /// \name Hooks for symbolic disassembly via the public 'C' interface. + /// @{ + /// The function to get the symbolic information for operands. + LLVMOpInfoCallback GetOpInfo; + /// The function to lookup a symbol name. + LLVMSymbolLookupCallback SymbolLookUp; + /// The pointer to the block of symbolic information for above call back. + void *DisInfo; + /// @} + +public: + MCExternalSymbolizer(MCContext &Ctx, + std::unique_ptr<MCRelocationInfo> RelInfo, + LLVMOpInfoCallback getOpInfo, + LLVMSymbolLookupCallback symbolLookUp, void *disInfo) + : MCSymbolizer(Ctx, std::move(RelInfo)), GetOpInfo(getOpInfo), + SymbolLookUp(symbolLookUp), DisInfo(disInfo) {} + + bool tryAddingSymbolicOperand(MCInst &MI, raw_ostream &CommentStream, + int64_t Value, uint64_t Address, bool IsBranch, + uint64_t Offset, uint64_t InstSize) override; + void tryAddingPcLoadReferenceComment(raw_ostream &CommentStream, + int64_t Value, + uint64_t Address) override; +}; + +} + +#endif diff --git a/include/llvm/MC/MCDisassembler/MCRelocationInfo.h b/include/llvm/MC/MCDisassembler/MCRelocationInfo.h new file mode 100644 index 0000000000000..25334f755ee6b --- /dev/null +++ b/include/llvm/MC/MCDisassembler/MCRelocationInfo.h @@ -0,0 +1,51 @@ +//==-- llvm/MC/MCRelocationInfo.h --------------------------------*- C++ -*-==// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file declares the MCRelocationInfo class, which provides methods to +// create MCExprs from relocations, either found in an object::ObjectFile +// (object::RelocationRef), or provided through the C API. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_MC_MCDISASSEMBLER_MCRELOCATIONINFO_H +#define LLVM_MC_MCDISASSEMBLER_MCRELOCATIONINFO_H + +#include "llvm/Support/Compiler.h" + +namespace llvm { + +namespace object { +class RelocationRef; +} +class MCExpr; +class MCContext; + +/// \brief Create MCExprs from relocations found in an object file. +class MCRelocationInfo { + MCRelocationInfo(const MCRelocationInfo &) = delete; + void operator=(const MCRelocationInfo &) = delete; + +protected: + MCContext &Ctx; + +public: + MCRelocationInfo(MCContext &Ctx); + virtual ~MCRelocationInfo(); + + /// \brief Create an MCExpr for the target-specific \p VariantKind. + /// The VariantKinds are defined in llvm-c/Disassembler.h. + /// Used by MCExternalSymbolizer. + /// \returns If possible, an MCExpr corresponding to VariantKind, else 0. + virtual const MCExpr *createExprForCAPIVariantKind(const MCExpr *SubExpr, + unsigned VariantKind); +}; + +} + +#endif diff --git a/include/llvm/MC/MCDisassembler/MCSymbolizer.h b/include/llvm/MC/MCDisassembler/MCSymbolizer.h new file mode 100644 index 0000000000000..713467c0a3e70 --- /dev/null +++ b/include/llvm/MC/MCDisassembler/MCSymbolizer.h @@ -0,0 +1,85 @@ +//===-- llvm/MC/MCSymbolizer.h - MCSymbolizer class -------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file contains the declaration of the MCSymbolizer class, which is used +// to symbolize instructions decoded from an object, that is, transform their +// immediate operands to MCExprs. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_MC_MCDISASSEMBLER_MCSYMBOLIZER_H +#define LLVM_MC_MCDISASSEMBLER_MCSYMBOLIZER_H + +#include "llvm/MC/MCDisassembler/MCRelocationInfo.h" +#include "llvm/Support/Compiler.h" +#include "llvm/Support/DataTypes.h" +#include <cassert> +#include <memory> + +namespace llvm { + +class MCContext; +class MCInst; +class raw_ostream; + +/// \brief Symbolize and annotate disassembled instructions. +/// +/// For now this mimics the old symbolization logic (from both ARM and x86), that +/// relied on user-provided (C API) callbacks to do the actual symbol lookup in +/// the object file. This was moved to MCExternalSymbolizer. +/// A better API would not rely on actually calling the two methods here from +/// inside each disassembler, but would use the instr info to determine what +/// operands are actually symbolizable, and in what way. I don't think this +/// information exists right now. +class MCSymbolizer { + MCSymbolizer(const MCSymbolizer &) = delete; + void operator=(const MCSymbolizer &) = delete; + +protected: + MCContext &Ctx; + std::unique_ptr<MCRelocationInfo> RelInfo; + +public: + /// \brief Construct an MCSymbolizer, taking ownership of \p RelInfo. + MCSymbolizer(MCContext &Ctx, std::unique_ptr<MCRelocationInfo> RelInfo) + : Ctx(Ctx), RelInfo(std::move(RelInfo)) { + } + + virtual ~MCSymbolizer(); + + /// \brief Try to add a symbolic operand instead of \p Value to the MCInst. + /// + /// Instead of having a difficult to read immediate, a symbolic operand would + /// represent this immediate in a more understandable way, for instance as a + /// symbol or an offset from a symbol. Relocations can also be used to enrich + /// the symbolic expression. + /// \param Inst - The MCInst where to insert the symbolic operand. + /// \param cStream - Stream to print comments and annotations on. + /// \param Value - Operand value, pc-adjusted by the caller if necessary. + /// \param Address - Load address of the instruction. + /// \param IsBranch - Is the instruction a branch? + /// \param Offset - Byte offset of the operand inside the inst. + /// \param InstSize - Size of the instruction in bytes. + /// \return Whether a symbolic operand was added. + virtual bool tryAddingSymbolicOperand(MCInst &Inst, raw_ostream &cStream, + int64_t Value, uint64_t Address, + bool IsBranch, uint64_t Offset, + uint64_t InstSize) = 0; + + /// \brief Try to add a comment on the PC-relative load. + /// For instance, in Mach-O, this is used to add annotations to instructions + /// that use C string literals, as found in __cstring. + virtual void tryAddingPcLoadReferenceComment(raw_ostream &cStream, + int64_t Value, + uint64_t Address) = 0; +}; + +} + +#endif |