diff options
Diffstat (limited to 'llvm_mode/afl-llvm-common.cc')
| -rw-r--r-- | llvm_mode/afl-llvm-common.cc | 436 |
1 files changed, 375 insertions, 61 deletions
diff --git a/llvm_mode/afl-llvm-common.cc b/llvm_mode/afl-llvm-common.cc index 9a884ded..d9e63bd3 100644 --- a/llvm_mode/afl-llvm-common.cc +++ b/llvm_mode/afl-llvm-common.cc @@ -20,7 +20,10 @@ using namespace llvm; -static std::list<std::string> myInstrumentList; +static std::list<std::string> allowListFiles; +static std::list<std::string> allowListFunctions; +static std::list<std::string> denyListFiles; +static std::list<std::string> denyListFunctions; char *getBBName(const llvm::BasicBlock *BB) { @@ -57,15 +60,18 @@ bool isIgnoreFunction(const llvm::Function *F) { "asan.", "llvm.", "sancov.", - "__ubsan_handle_", + "__ubsan_", "ign.", "__afl_", "_fini", "__libc_csu", "__asan", "__msan", + "__cmplog", + "__sancov", "msan.", "LLVMFuzzer", + "__decide_deferred", "maybe_duplicate_stderr", "discard_output", "close_stdout", @@ -87,41 +93,246 @@ bool isIgnoreFunction(const llvm::Function *F) { void initInstrumentList() { - char *instrumentListFilename = getenv("AFL_LLVM_INSTRUMENT_FILE"); - if (!instrumentListFilename) - instrumentListFilename = getenv("AFL_LLVM_WHITELIST"); + char *allowlist = getenv("AFL_LLVM_ALLOWLIST"); + if (!allowlist) allowlist = getenv("AFL_LLVM_INSTRUMENT_FILE"); + if (!allowlist) allowlist = getenv("AFL_LLVM_WHITELIST"); + char *denylist = getenv("AFL_LLVM_DENYLIST"); + if (!denylist) denylist = getenv("AFL_LLVM_BLOCKLIST"); - if (instrumentListFilename) { + if (allowlist && denylist) + FATAL( + "You can only specify either AFL_LLVM_ALLOWLIST or AFL_LLVM_DENYLIST " + "but not both!"); + + if (allowlist) { std::string line; std::ifstream fileStream; - fileStream.open(instrumentListFilename); - if (!fileStream) - report_fatal_error("Unable to open AFL_LLVM_INSTRUMENT_FILE"); + fileStream.open(allowlist); + if (!fileStream) report_fatal_error("Unable to open AFL_LLVM_ALLOWLIST"); getline(fileStream, line); + while (fileStream) { - myInstrumentList.push_back(line); - getline(fileStream, line); + int is_file = -1; + std::size_t npos; + std::string original_line = line; + + line.erase(std::remove_if(line.begin(), line.end(), ::isspace), + line.end()); + + // remove # and following + if ((npos = line.find("#")) != std::string::npos) + line = line.substr(0, npos); + + if (line.compare(0, 4, "fun:") == 0) { + + is_file = 0; + line = line.substr(4); + + } else if (line.compare(0, 9, "function:") == 0) { + + is_file = 0; + line = line.substr(9); + + } else if (line.compare(0, 4, "src:") == 0) { + + is_file = 1; + line = line.substr(4); + + } else if (line.compare(0, 7, "source:") == 0) { + + is_file = 1; + line = line.substr(7); + + } + + if (line.find(":") != std::string::npos) { + + FATAL("invalid line in AFL_LLVM_ALLOWLIST: %s", original_line.c_str()); + + } + + if (line.length() > 0) { + + // if the entry contains / or . it must be a file + if (is_file == -1) + if (line.find("/") != std::string::npos || + line.find(".") != std::string::npos) + is_file = 1; + // otherwise it is a function + + if (is_file == 1) + allowListFiles.push_back(line); + else + allowListFunctions.push_back(line); + getline(fileStream, line); + + } } + if (debug) + SAYF(cMGN "[D] " cRST + "loaded allowlist with %zu file and %zu function entries\n", + allowListFiles.size(), allowListFunctions.size()); + } - if (debug) - SAYF(cMGN "[D] " cRST "loaded instrument list with %zu entries\n", - myInstrumentList.size()); + if (denylist) { + + std::string line; + std::ifstream fileStream; + fileStream.open(denylist); + if (!fileStream) report_fatal_error("Unable to open AFL_LLVM_DENYLIST"); + getline(fileStream, line); + + while (fileStream) { + + int is_file = -1; + std::size_t npos; + std::string original_line = line; + + line.erase(std::remove_if(line.begin(), line.end(), ::isspace), + line.end()); + + // remove # and following + if ((npos = line.find("#")) != std::string::npos) + line = line.substr(0, npos); + + if (line.compare(0, 4, "fun:") == 0) { + + is_file = 0; + line = line.substr(4); + + } else if (line.compare(0, 9, "function:") == 0) { + + is_file = 0; + line = line.substr(9); + + } else if (line.compare(0, 4, "src:") == 0) { + + is_file = 1; + line = line.substr(4); + + } else if (line.compare(0, 7, "source:") == 0) { + + is_file = 1; + line = line.substr(7); + + } + + if (line.find(":") != std::string::npos) { + + FATAL("invalid line in AFL_LLVM_DENYLIST: %s", original_line.c_str()); + + } + + if (line.length() > 0) { + + // if the entry contains / or . it must be a file + if (is_file == -1) + if (line.find("/") != std::string::npos || + line.find(".") != std::string::npos) + is_file = 1; + // otherwise it is a function + + if (is_file == 1) + denyListFiles.push_back(line); + else + denyListFunctions.push_back(line); + getline(fileStream, line); + + } + + } + + if (debug) + SAYF(cMGN "[D] " cRST + "loaded denylist with %zu file and %zu function entries\n", + denyListFiles.size(), denyListFunctions.size()); + + } } -bool isInInstrumentList(llvm::Function *F) { +void scanForDangerousFunctions(llvm::Module *M) { - // is this a function with code? If it is external we dont instrument it - // anyway and cant be in the the instrument file list. Or if it is ignored. - if (!F->size() || isIgnoreFunction(F)) return false; + if (!M) return; + +#if LLVM_VERSION_MAJOR > 3 || \ + (LLVM_VERSION_MAJOR == 3 && LLVM_VERSION_MINOR >= 9) - // if we do not have a the instrument file list return true - if (myInstrumentList.empty()) return true; + for (GlobalIFunc &IF : M->ifuncs()) { + + StringRef ifunc_name = IF.getName(); + Constant *r = IF.getResolver(); + StringRef r_name = cast<Function>(r->getOperand(0))->getName(); + if (!be_quiet) + fprintf(stderr, + "Info: Found an ifunc with name %s that points to resolver " + "function %s, we will not instrument this, putting it into the " + "block list.\n", + ifunc_name.str().c_str(), r_name.str().c_str()); + denyListFunctions.push_back(r_name.str()); + + } + + GlobalVariable *GV = M->getNamedGlobal("llvm.global_ctors"); + if (GV && !GV->isDeclaration() && !GV->hasLocalLinkage()) { + + ConstantArray *InitList = dyn_cast<ConstantArray>(GV->getInitializer()); + + if (InitList) { + + for (unsigned i = 0, e = InitList->getNumOperands(); i != e; ++i) { + + if (ConstantStruct *CS = + dyn_cast<ConstantStruct>(InitList->getOperand(i))) { + + if (CS->getNumOperands() >= 2) { + + if (CS->getOperand(1)->isNullValue()) + break; // Found a null terminator, stop here. + + ConstantInt *CI = dyn_cast<ConstantInt>(CS->getOperand(0)); + int Priority = CI ? CI->getSExtValue() : 0; + + Constant *FP = CS->getOperand(1); + if (ConstantExpr *CE = dyn_cast<ConstantExpr>(FP)) + if (CE->isCast()) FP = CE->getOperand(0); + if (Function *F = dyn_cast<Function>(FP)) { + + if (!F->isDeclaration() && + strncmp(F->getName().str().c_str(), "__afl", 5) != 0) { + + if (!be_quiet) + fprintf(stderr, + "Info: Found constructor function %s with prio " + "%u, we will not instrument this, putting it into a " + "block list.\n", + F->getName().str().c_str(), Priority); + denyListFunctions.push_back(F->getName().str()); + + } + + } + + } + + } + + } + + } + + } + +#endif + +} + +static std::string getSourceName(llvm::Function *F) { // let's try to get the filename for the function auto bb = &F->getEntryBlock(); @@ -135,28 +346,56 @@ bool isInInstrumentList(llvm::Function *F) { DILocation *cDILoc = dyn_cast<DILocation>(Loc.getAsMDNode()); - unsigned int instLine = cDILoc->getLine(); - StringRef instFilename = cDILoc->getFilename(); + StringRef instFilename = cDILoc->getFilename(); if (instFilename.str().empty()) { /* If the original location is empty, try using the inlined location */ DILocation *oDILoc = cDILoc->getInlinedAt(); - if (oDILoc) { + if (oDILoc) { instFilename = oDILoc->getFilename(); } - instFilename = oDILoc->getFilename(); - instLine = oDILoc->getLine(); + } - } + return instFilename.str(); - } + } + +#else + if (!Loc.isUnknown()) { + + DILocation cDILoc(Loc.getAsMDNode(F->getContext())); + + StringRef instFilename = cDILoc.getFilename(); /* Continue only if we know where we actually are */ - if (!instFilename.str().empty()) { + return instFilename.str(); - for (std::list<std::string>::iterator it = myInstrumentList.begin(); - it != myInstrumentList.end(); ++it) { + } + +#endif + + return std::string(""); + +} + +bool isInInstrumentList(llvm::Function *F) { + + bool return_default = true; + + // is this a function with code? If it is external we don't instrument it + // anyway and it can't be in the instrument file list. Or if it is it is + // ignored. + if (!F->size() || isIgnoreFunction(F)) return false; + + if (!denyListFiles.empty() || !denyListFunctions.empty()) { + + if (!denyListFunctions.empty()) { + + std::string instFunction = F->getName().str(); + + for (std::list<std::string>::iterator it = denyListFunctions.begin(); + it != denyListFunctions.end(); ++it) { /* We don't check for filename equality here because * filenames might actually be full paths. Instead we @@ -164,16 +403,16 @@ bool isInInstrumentList(llvm::Function *F) { * specified in the list. We also allow UNIX-style pattern * matching */ - if (instFilename.str().length() >= it->length()) { + if (instFunction.length() >= it->length()) { - if (fnmatch(("*" + *it).c_str(), instFilename.str().c_str(), 0) == - 0) { + if (fnmatch(("*" + *it).c_str(), instFunction.c_str(), 0) == 0) { if (debug) SAYF(cMGN "[D] " cRST - "Function %s is in the list (%s), instrumenting ... \n", - F->getName().str().c_str(), instFilename.str().c_str()); - return true; + "Function %s is in the deny function list, " + "not instrumenting ... \n", + instFunction.c_str()); + return false; } @@ -183,22 +422,60 @@ bool isInInstrumentList(llvm::Function *F) { } + if (!denyListFiles.empty()) { + + std::string source_file = getSourceName(F); + + if (!source_file.empty()) { + + for (std::list<std::string>::iterator it = denyListFiles.begin(); + it != denyListFiles.end(); ++it) { + + /* We don't check for filename equality here because + * filenames might actually be full paths. Instead we + * check that the actual filename ends in the filename + * specified in the list. We also allow UNIX-style pattern + * matching */ + + if (source_file.length() >= it->length()) { + + if (fnmatch(("*" + *it).c_str(), source_file.c_str(), 0) == 0) { + + return false; + + } + + } + + } + + } else { + + // we could not find out the location. in this case we say it is not + // in the instrument file list + if (!be_quiet) + WARNF( + "No debug information found for function %s, will be " + "instrumented (recompile with -g -O[1-3]).", + F->getName().str().c_str()); + + } + + } + } -#else - if (!Loc.isUnknown()) { + // if we do not have a instrument file list return true + if (!allowListFiles.empty() || !allowListFunctions.empty()) { - DILocation cDILoc(Loc.getAsMDNode(F->getContext())); + return_default = false; - unsigned int instLine = cDILoc.getLineNumber(); - StringRef instFilename = cDILoc.getFilename(); + if (!allowListFunctions.empty()) { - (void)instLine; - /* Continue only if we know where we actually are */ - if (!instFilename.str().empty()) { + std::string instFunction = F->getName().str(); - for (std::list<std::string>::iterator it = myInstrumentList.begin(); - it != myInstrumentList.end(); ++it) { + for (std::list<std::string>::iterator it = allowListFunctions.begin(); + it != allowListFunctions.end(); ++it) { /* We don't check for filename equality here because * filenames might actually be full paths. Instead we @@ -206,11 +483,15 @@ bool isInInstrumentList(llvm::Function *F) { * specified in the list. We also allow UNIX-style pattern * matching */ - if (instFilename.str().length() >= it->length()) { + if (instFunction.length() >= it->length()) { - if (fnmatch(("*" + *it).c_str(), instFilename.str().c_str(), 0) == - 0) { + if (fnmatch(("*" + *it).c_str(), instFunction.c_str(), 0) == 0) { + if (debug) + SAYF(cMGN "[D] " cRST + "Function %s is in the allow function list, " + "instrumenting ... \n", + instFunction.c_str()); return true; } @@ -221,23 +502,56 @@ bool isInInstrumentList(llvm::Function *F) { } - } + if (!allowListFiles.empty()) { -#endif - else { + std::string source_file = getSourceName(F); - // we could not find out the location. in this case we say it is not - // in the the instrument file list - if (!be_quiet) - WARNF( - "No debug information found for function %s, will not be " - "instrumented (recompile with -g -O[1-3]).", - F->getName().str().c_str()); - return false; + if (!source_file.empty()) { + + for (std::list<std::string>::iterator it = allowListFiles.begin(); + it != allowListFiles.end(); ++it) { + + /* We don't check for filename equality here because + * filenames might actually be full paths. Instead we + * check that the actual filename ends in the filename + * specified in the list. We also allow UNIX-style pattern + * matching */ + + if (source_file.length() >= it->length()) { + + if (fnmatch(("*" + *it).c_str(), source_file.c_str(), 0) == 0) { + + if (debug) + SAYF(cMGN "[D] " cRST + "Function %s is in the allowlist (%s), " + "instrumenting ... \n", + F->getName().str().c_str(), source_file.c_str()); + return true; + + } + + } + + } + + } else { + + // we could not find out the location. In this case we say it is not + // in the instrument file list + if (!be_quiet) + WARNF( + "No debug information found for function %s, will not be " + "instrumented (recompile with -g -O[1-3]).", + F->getName().str().c_str()); + return false; + + } + + } } - return false; + return return_default; } |