Index: tools/llvm-cfi-verify/CMakeLists.txt =================================================================== --- tools/llvm-cfi-verify/CMakeLists.txt +++ tools/llvm-cfi-verify/CMakeLists.txt @@ -13,4 +13,5 @@ add_llvm_tool(llvm-cfi-verify llvm-cfi-verify.cpp + FileVerifier.cpp ) Index: tools/llvm-cfi-verify/FileVerifier.h =================================================================== --- /dev/null +++ tools/llvm-cfi-verify/FileVerifier.h @@ -0,0 +1,148 @@ +//===- FileVerifier.h -------------------------------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CFI_VERIFY_FILE_VERIFIER_H +#define LLVM_CFI_VERIFY_FILE_VERIFIER_H + +#include "llvm/BinaryFormat/ELF.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCDisassembler/MCDisassembler.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrDesc.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCObjectFileInfo.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Object/Binary.h" +#include "llvm/Object/COFF.h" +#include "llvm/Object/ELFObjectFile.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Error.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/raw_ostream.h" + +#include +#include +#include +#include + +namespace llvm { +namespace cfi_verify { + +// This class is used to verify CFI instrumentation of a single file. +class FileVerifier { +public: + // A metadata struct for an instruction. + struct Instr { + uint64_t VMAddress; // Virtual memory address of this instruction. + MCInst Instruction; // Instruction. + uint64_t InstructionSize; // Size of this instruction. + std::string SectionName; // Section this instruction is found in. + bool Bad; // Is this instruction bad (in which case, Instr::Instruction is + // invalid). + }; + + // Construct a FileVerifier from a file path. + static Expected Create(StringRef Filename); + + // Construct and take ownership of the supplied object. Do not use this + // constructor, prefer to use FileVerifier::Create instead. + FileVerifier(object::OwningBinary Binary); + FileVerifier() = delete; + FileVerifier(const FileVerifier &) = delete; + FileVerifier(FileVerifier &&Other) = default; + + Error printIndirectCFInstructions() const; + + // Returns the instruction at the provided address. Returns nullptr if there + // is no instruction at the provided address. + const Instr *getInstruction(uint64_t Address) const; + + // Returns the instruction at the provided adress, dying if the instruction is + // not found. + const Instr &getInstructionOrDie(uint64_t Address) const; + + // Returns a pointer to the previous/next instruction in sequence, + // respectively. Retusn nullptr if the next/prev instruction doesn't exist, or + // if the provided instruction doesn't exist. + const Instr *getPrevInstructionSequential(const Instr &InstrMeta) const; + const Instr *getNextInstructionSequential(const Instr &InstrMeta) const; + + // Returns the list of indirect instructions. + const std::vector &getIndirectInstructions() const; + +protected: + // Add an instruction to this object. + void addInstruction(const Instr &Instruction); + + // Disassemble and parse the provided bytes into this object. Instruction + // address calculation is done relative to the provided SectionAddress, and + // instruction metadata is populated with the given section name. + void parseSectionContents(ArrayRef SectionBytes, + uint64_t SectionAddress, StringRef SectionName); + + // Constructs and initialises members required for disassembly. + Error initialiseDisassemblyMembers(); + + // Parses code sections from the internal object file. Saves them into the + // internal members. Should only be called once by Create(). + Error parseCodeSections(); + +private: + // Members that describe the input file. + object::OwningBinary Binary; + const object::ObjectFile *Object = nullptr; + Triple ObjectTriple; + std::string ArchName; + std::string MCPU; + const Target *ObjectTarget = nullptr; + SubtargetFeatures Features; + + // Members required for disassembly. + std::unique_ptr RegisterInfo; + std::unique_ptr AsmInfo; + std::unique_ptr SubtargetInfo; + std::unique_ptr MII; + MCObjectFileInfo MOFI; + std::unique_ptr Context; + std::unique_ptr Disassembler; + std::unique_ptr MIA; + std::unique_ptr Printer; + + // A mapping between the virtual memory address to the instruction metadata + // struct. + std::map Instructions; + + // Contains a mapping between a specific address, and a list of instructions + // that use this address as a branch target (including call instructions). + std::unordered_map> StaticBranchTargetings; + + // A list of addresses of indirect control flow instructions. + std::set IndirectInstructions; +}; + +class UnsupportedDisassembly : public ErrorInfo { +public: + static char ID; + + void log(raw_ostream &OS) const override; + std::error_code convertToErrorCode() const override; +}; + +} // namespace cfi_verify +} // namespace llvm + +#endif // LLVM_CFI_VERIFY_FILE_VERIFIER_H Index: tools/llvm-cfi-verify/FileVerifier.cpp =================================================================== --- /dev/null +++ tools/llvm-cfi-verify/FileVerifier.cpp @@ -0,0 +1,280 @@ +#include "FileVerifier.h" + +#include "llvm/BinaryFormat/ELF.h" +#include "llvm/MC/MCAsmInfo.h" +#include "llvm/MC/MCContext.h" +#include "llvm/MC/MCDisassembler/MCDisassembler.h" +#include "llvm/MC/MCInst.h" +#include "llvm/MC/MCInstPrinter.h" +#include "llvm/MC/MCInstrAnalysis.h" +#include "llvm/MC/MCInstrDesc.h" +#include "llvm/MC/MCInstrInfo.h" +#include "llvm/MC/MCObjectFileInfo.h" +#include "llvm/MC/MCRegisterInfo.h" +#include "llvm/MC/MCSubtargetInfo.h" +#include "llvm/Object/Binary.h" +#include "llvm/Object/COFF.h" +#include "llvm/Object/ELFObjectFile.h" +#include "llvm/Object/ObjectFile.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Error.h" +#include "llvm/Support/FormatVariadic.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Support/raw_ostream.h" + +#include + +using Instr = llvm::cfi_verify::FileVerifier::Instr; + +namespace llvm { +namespace cfi_verify { + +Expected FileVerifier::Create(StringRef Filename) { + // Open the filename provided. + Expected> BinaryOrErr = + object::createBinary(Filename); + if (!BinaryOrErr) + return BinaryOrErr.takeError(); + + // Construct the object and allow it to take ownership of the binary. + object::OwningBinary Binary = std::move(BinaryOrErr.get()); + FileVerifier Verifier(std::move(Binary)); + + Verifier.Object = dyn_cast(Verifier.Binary.getBinary()); + if (!Verifier.Object) + return make_error(); + + Verifier.ObjectTriple = Verifier.Object->makeTriple(); + Verifier.Features = Verifier.Object->getFeatures(); + + // Init the rest of the object. + auto InitResponse = Verifier.initialiseDisassemblyMembers(); + if (InitResponse) + return std::move(InitResponse); + + auto SectionParseResponse = Verifier.parseCodeSections(); + if (SectionParseResponse) + return std::move(SectionParseResponse); + + return std::move(Verifier); +} + +FileVerifier::FileVerifier(object::OwningBinary Binary) + : Binary(std::move(Binary)) {} + +Error FileVerifier::printIndirectCFInstructions() const { + for (const auto &Address : IndirectInstructions) { + const auto &InstructionKV = Instructions.find(Address); + if (InstructionKV == Instructions.end()) + return make_error( + formatv("No instruction found at address {0:x}", Address), + inconvertibleErrorCode()); + + const auto &InstrMeta = InstructionKV->second; + outs() << format_hex(Address, 2) << " [" << InstrMeta.SectionName + << "] = " << MII->getName(InstrMeta.Instruction.getOpcode()) << " "; + InstrMeta.Instruction.print(outs()); + outs() << "\n"; + } + + return Error::success(); +} + +const Instr * +FileVerifier::getPrevInstructionSequential(const Instr &InstrMeta) const { + std::map::const_iterator KV = + Instructions.find(InstrMeta.VMAddress); + if (KV == Instructions.end() || KV == Instructions.begin()) + return nullptr; + + if ((--KV)->second.Bad) + return nullptr; + + return &KV->second; +} + +const Instr * +FileVerifier::getNextInstructionSequential(const Instr &InstrMeta) const { + std::map::const_iterator KV = + Instructions.find(InstrMeta.VMAddress); + + if (KV++ == Instructions.end() || KV == Instructions.end()) + return nullptr; + + if (KV->second.Bad) + return nullptr; + + return &KV->second; +} + +const Instr *FileVerifier::getInstruction(uint64_t Address) const { + const auto &InstrKV = Instructions.find(Address); + if (InstrKV == Instructions.end()) + return nullptr; + + return &InstrKV->second; +} + +const Instr &FileVerifier::getInstructionOrDie(uint64_t Address) const { + const auto &InstrKV = Instructions.find(Address); + assert(InstrKV != Instructions.end() && "Address doesn't exist."); + return InstrKV->second; +} + +Error FileVerifier::initialiseDisassemblyMembers() { + std::string TripleName = ObjectTriple.getTriple(); + ArchName = ""; + MCPU = ""; + + std::string ErrorString; + + ObjectTarget = + TargetRegistry::lookupTarget(ArchName, ObjectTriple, ErrorString); + + if (!ObjectTarget) + return make_error(Twine("Couldn't find target \"") + + ObjectTriple.getTriple() + + "\", failed with error: " + ErrorString, + inconvertibleErrorCode()); + + RegisterInfo.reset(ObjectTarget->createMCRegInfo(TripleName)); + if (!RegisterInfo) + return make_error("Failed to initialise RegisterInfo.", + inconvertibleErrorCode()); + + AsmInfo.reset(ObjectTarget->createMCAsmInfo(*RegisterInfo, TripleName)); + if (!AsmInfo) + return make_error("Failed to initialise AsmInfo.", + inconvertibleErrorCode()); + + SubtargetInfo.reset(ObjectTarget->createMCSubtargetInfo( + TripleName, MCPU, Features.getString())); + if (!SubtargetInfo) + return make_error("Failed to initialise SubtargetInfo.", + inconvertibleErrorCode()); + + MII.reset(ObjectTarget->createMCInstrInfo()); + if (!MII) + return make_error("Failed to initialise MII.", + inconvertibleErrorCode()); + + Context.reset(new MCContext(AsmInfo.get(), RegisterInfo.get(), &MOFI)); + + Disassembler.reset( + ObjectTarget->createMCDisassembler(*SubtargetInfo, *Context)); + + if (!Disassembler) + return make_error("No disassembler available for target", + inconvertibleErrorCode()); + + MIA.reset(ObjectTarget->createMCInstrAnalysis(MII.get())); + + Printer.reset(ObjectTarget->createMCInstPrinter( + ObjectTriple, AsmInfo->getAssemblerDialect(), *AsmInfo, *MII, + *RegisterInfo)); + + return Error::success(); +} + +Error FileVerifier::parseCodeSections() { + for (const object::SectionRef &Section : Object->sections()) { + // Ensure only executable sections get analysed. + if (!(object::ELFSectionRef(Section).getFlags() & ELF::SHF_EXECINSTR)) + continue; + + StringRef SectionContents; + if (Section.getContents(SectionContents)) + return make_error("Failed to retrieve section contents", + inconvertibleErrorCode()); + + StringRef SectionName; + if (Section.getName(SectionName)) + SectionName = "UNKNOWN"; + + ArrayRef SectionBytes((const uint8_t *)SectionContents.data(), + Section.getSize()); + parseSectionContents(SectionBytes, Section.getAddress(), SectionName); + } + return Error::success(); +} + +void FileVerifier::parseSectionContents(ArrayRef SectionBytes, + uint64_t SectionAddress, + StringRef SectionName) { + MCInst Instruction; + Instr InstrMeta; + uint64_t InstructionSize; + + for (uint64_t Byte = 0; Byte < SectionBytes.size();) { + bool BadInstruction = false; + + SectionBytes.drop_front(Byte); + + // Disassemble the instruction. + if (Disassembler->getInstruction(Instruction, InstructionSize, + SectionBytes.drop_front(Byte), 0, nulls(), + outs()) != MCDisassembler::Success) + BadInstruction = true; + + Byte += InstructionSize; + + uint64_t VMAddress = SectionAddress + Byte - InstructionSize; + InstrMeta.Instruction = Instruction; + InstrMeta.VMAddress = VMAddress; + InstrMeta.InstructionSize = InstructionSize; + InstrMeta.SectionName = SectionName; + InstrMeta.Bad = false; + + if (BadInstruction) { + InstrMeta.Bad = true; + addInstruction(InstrMeta); + continue; + } + + addInstruction(InstrMeta); + + // Skip additional parsing for instructions that do not affect the control + // flow. + const auto &InstrDesc = MII->get(Instruction.getOpcode()); + if (!InstrDesc.mayAffectControlFlow(Instruction, *RegisterInfo)) + continue; + + uint64_t Target; + if (MIA->evaluateBranch(Instruction, VMAddress, InstructionSize, Target)) { + // If the target can be evaluated, it's not indirect. + StaticBranchTargetings[Target].push_back(VMAddress); + continue; + } + + // Skip instructions that do not operate on register operands. + bool UsesRegisterOperand = false; + for (const auto &Operand : Instruction) { + if (Operand.isReg()) + UsesRegisterOperand = true; + } + + if (!UsesRegisterOperand) + continue; + + IndirectInstructions.insert(VMAddress); + } +} + +void FileVerifier::addInstruction(const Instr &Instruction) { + Instructions[Instruction.VMAddress] = Instruction; +} + +char UnsupportedDisassembly::ID; +void UnsupportedDisassembly::log(raw_ostream &OS) const { + OS << "Dissassembling of non-objects not currently supported.\n"; +} + +std::error_code UnsupportedDisassembly::convertToErrorCode() const { + return std::error_code(); +} + +} // namespace cfi_verify +} // namespace llvm Index: tools/llvm-cfi-verify/llvm-cfi-verify.cpp =================================================================== --- tools/llvm-cfi-verify/llvm-cfi-verify.cpp +++ tools/llvm-cfi-verify/llvm-cfi-verify.cpp @@ -17,67 +17,22 @@ // //===----------------------------------------------------------------------===// -#include "llvm/MC/MCAsmInfo.h" -#include "llvm/MC/MCContext.h" -#include "llvm/MC/MCDisassembler/MCDisassembler.h" -#include "llvm/MC/MCInst.h" -#include "llvm/MC/MCInstPrinter.h" -#include "llvm/MC/MCInstrAnalysis.h" -#include "llvm/MC/MCInstrDesc.h" -#include "llvm/MC/MCInstrInfo.h" -#include "llvm/MC/MCObjectFileInfo.h" -#include "llvm/MC/MCRegisterInfo.h" -#include "llvm/MC/MCSubtargetInfo.h" -#include "llvm/Object/Binary.h" -#include "llvm/Object/COFF.h" -#include "llvm/Object/ObjectFile.h" -#include "llvm/Support/Casting.h" +#include "FileVerifier.h" + +#include "llvm/BinaryFormat/ELF.h" #include "llvm/Support/CommandLine.h" -#include "llvm/Support/MemoryBuffer.h" -#include "llvm/Support/TargetRegistry.h" -#include "llvm/Support/TargetSelect.h" -#include "llvm/Support/raw_ostream.h" +#include "llvm/Support/Error.h" -#include #include using namespace llvm; using namespace llvm::object; +using namespace llvm::cfi_verify; -cl::opt ArgDumpSymbols("sym", cl::desc("Dump the symbol table.")); cl::opt InputFilename(cl::Positional, cl::desc(""), cl::Required); -static void printSymbols(const ObjectFile *Object) { - for (const SymbolRef &Symbol : Object->symbols()) { - outs() << "Symbol [" << format_hex_no_prefix(Symbol.getValue(), 2) - << "] = "; - - auto SymbolName = Symbol.getName(); - if (SymbolName) - outs() << *SymbolName; - else - outs() << "UNKNOWN"; - - if (Symbol.getFlags() & SymbolRef::SF_Hidden) - outs() << " .hidden"; - - outs() << " (Section = "; - - auto SymbolSection = Symbol.getSection(); - if (SymbolSection) { - StringRef SymbolSectionName; - if ((*SymbolSection)->getName(SymbolSectionName)) - outs() << "UNKNOWN)"; - else - outs() << SymbolSectionName << ")"; - } else { - outs() << "N/A)"; - } - - outs() << "\n"; - } -} +ExitOnError ExitOnErr; int main(int argc, char **argv) { cl::ParseCommandLineOptions(argc, argv); @@ -87,155 +42,8 @@ InitializeAllAsmParsers(); InitializeAllDisassemblers(); - Expected> BinaryOrErr = createBinary(InputFilename); - if (!BinaryOrErr) { - errs() << "Failed to open file.\n"; - return EXIT_FAILURE; - } - - Binary &Binary = *BinaryOrErr.get().getBinary(); - ObjectFile *Object = dyn_cast(&Binary); - if (!Object) { - errs() << "Disassembling of non-objects not currently supported.\n"; - return EXIT_FAILURE; - } - - Triple TheTriple = Object->makeTriple(); - std::string TripleName = TheTriple.getTriple(); - std::string ArchName = ""; - std::string ErrorString; - - const Target *TheTarget = - TargetRegistry::lookupTarget(ArchName, TheTriple, ErrorString); - - if (!TheTarget) { - errs() << "Couldn't find target \"" << TheTriple.getTriple() - << "\", failed with error: " << ErrorString << ".\n"; - return EXIT_FAILURE; - } - - SubtargetFeatures Features = Object->getFeatures(); - - std::unique_ptr RegisterInfo( - TheTarget->createMCRegInfo(TripleName)); - if (!RegisterInfo) { - errs() << "Failed to initialise RegisterInfo.\n"; - return EXIT_FAILURE; - } - - std::unique_ptr AsmInfo( - TheTarget->createMCAsmInfo(*RegisterInfo, TripleName)); - if (!AsmInfo) { - errs() << "Failed to initialise AsmInfo.\n"; - return EXIT_FAILURE; - } - - std::string MCPU = ""; - std::unique_ptr SubtargetInfo( - TheTarget->createMCSubtargetInfo(TripleName, MCPU, Features.getString())); - if (!SubtargetInfo) { - errs() << "Failed to initialise SubtargetInfo.\n"; - return EXIT_FAILURE; - } - - std::unique_ptr MII(TheTarget->createMCInstrInfo()); - if (!MII) { - errs() << "Failed to initialise MII.\n"; - return EXIT_FAILURE; - } - - MCObjectFileInfo MOFI; - MCContext Context(AsmInfo.get(), RegisterInfo.get(), &MOFI); - - std::unique_ptr Disassembler( - TheTarget->createMCDisassembler(*SubtargetInfo, Context)); - - if (!Disassembler) { - errs() << "No disassembler available for target."; - return EXIT_FAILURE; - } - - std::unique_ptr MIA( - TheTarget->createMCInstrAnalysis(MII.get())); - - std::unique_ptr Printer( - TheTarget->createMCInstPrinter(TheTriple, AsmInfo->getAssemblerDialect(), - *AsmInfo, *MII, *RegisterInfo)); - - if (ArgDumpSymbols) - printSymbols(Object); - - for (const SectionRef &Section : Object->sections()) { - outs() << "Section [" << format_hex_no_prefix(Section.getAddress(), 2) - << "] = "; - StringRef SectionName; - - if (Section.getName(SectionName)) - outs() << "UNKNOWN.\n"; - else - outs() << SectionName << "\n"; - - StringRef SectionContents; - if (Section.getContents(SectionContents)) { - errs() << "Failed to retrieve section contents.\n"; - return EXIT_FAILURE; - } - - MCInst Instruction; - uint64_t InstructionSize; - - ArrayRef SectionBytes((const uint8_t *)SectionContents.data(), - Section.getSize()); - - for (uint64_t Byte = 0; Byte < Section.getSize();) { - bool BadInstruction = false; - - // Disassemble the instruction. - if (Disassembler->getInstruction( - Instruction, InstructionSize, SectionBytes.drop_front(Byte), 0, - nulls(), outs()) != MCDisassembler::Success) { - BadInstruction = true; - } - - Byte += InstructionSize; - - if (BadInstruction) - continue; - - // Skip instructions that do not affect the control flow. - const auto &InstrDesc = MII->get(Instruction.getOpcode()); - if (!InstrDesc.mayAffectControlFlow(Instruction, *RegisterInfo)) - continue; - - // Skip instructions that do not operate on register operands. - bool UsesRegisterOperand = false; - for (const auto &Operand : Instruction) { - if (Operand.isReg()) - UsesRegisterOperand = true; - } - - if (!UsesRegisterOperand) - continue; - - // Print the instruction address. - outs() << " " - << format_hex(Section.getAddress() + Byte - InstructionSize, 2) - << ": "; - - // Print the instruction bytes. - for (uint64_t i = 0; i < InstructionSize; ++i) { - outs() << format_hex_no_prefix(SectionBytes[Byte - InstructionSize + i], - 2) - << " "; - } - - // Print the instruction. - outs() << " | " << MII->getName(Instruction.getOpcode()) << " "; - Instruction.dump_pretty(outs(), Printer.get()); - - outs() << "\n"; - } - } + FileVerifier Verifier = ExitOnErr(FileVerifier::Create(InputFilename)); + ExitOnErr(Verifier.printIndirectCFInstructions()); return EXIT_SUCCESS; }