From 6184832ea98050c91cdefa5059e18e78c39b14de Mon Sep 17 00:00:00 2001 From: Dominik Maier Date: Sun, 23 Aug 2020 10:59:56 +0200 Subject: added more env var docs, fsrv fixes for cmin, tmin --- docs/Changelog.md | 4 ++++ docs/env_variables.md | 15 +++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'docs') diff --git a/docs/Changelog.md b/docs/Changelog.md index 8bbb4e19..f7bc9600 100644 --- a/docs/Changelog.md +++ b/docs/Changelog.md @@ -14,6 +14,10 @@ sending a mail to . - Fix for auto dictionary entries found during fuzzing to not throw out a -x dictionary - added total execs done to plot file + - AFL_MAX_DET_EXTRAS env variable added to control the amount of deterministic + dict entries without recompiling. + - AFL_FORKSRV_INIT_TMOUT env variable added to control the time to wait for + the forkserver to come up without the need to increase the overall timeout. - llvm_mode: - Ported SanCov to LTO, and made it the default for LTO. better instrumentation locations diff --git a/docs/env_variables.md b/docs/env_variables.md index 94c34400..e8129a3f 100644 --- a/docs/env_variables.md +++ b/docs/env_variables.md @@ -278,6 +278,14 @@ checks or alter some of the more exotic semantics of the tool: don't want AFL to spend too much time classifying that stuff and just rapidly put all timeouts in that bin. + - Setting AFL_FORKSRV_INIT_TMOUT allows yout to specify a different timeout + to wait for the forkserver to spin up. The default is the `-t` value times + `FORK_WAIT_MULT` from `config.h` (usually 10), so for a `-t 100`, the + default would wait `1000` milis. Setting a different time here is useful + if the target has a very slow startup time, for example when doing + full-system fuzzing or emulation, but you don't want the actual runs + to wait too long for timeouts. + - AFL_NO_ARITH causes AFL to skip most of the deterministic arithmetics. This can be useful to speed up the fuzzing of text-based file formats. @@ -361,6 +369,13 @@ checks or alter some of the more exotic semantics of the tool: for an existing out folder, even if a different `-i` was provided. Without this setting, afl-fuzz will refuse execution for a long-fuzzed out dir. + - Setting AFL_MAX_DET_EXRAS will change the threshold at what number of elements + in the `-x` dictionary and LTO autodict (combined) the probabilistic mode will + kick off. In probabilistic mode, not all dictionary entires will be used all + of the times for fuzzing mutations to not make fuzzing slower by it. + The default count is `200` element. So for the 200 + 1st element, there is a + 1 in 201 chance, that one of the dictionary entry will not be used directly. + - Setting AFL_NO_FORKSRV disables the forkserver optimization, reverting to fork + execve() call for every tested input. This is useful mostly when working with unruly libraries that create threads or do other crazy -- cgit 1.4.1 From c7f0d3066875bca0ec28e9429df40293339dc05c Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 24 Aug 2020 17:32:41 +0200 Subject: added afl_custom_fuzz_count --- GNUmakefile | 12 ++--- docs/Changelog.md | 3 ++ docs/custom_mutators.md | 9 ++++ include/afl-fuzz.h | 20 ++++++++ src/afl-forkserver.c | 2 +- src/afl-fuzz-extras.c | 4 +- src/afl-fuzz-mutators.c | 5 ++ src/afl-fuzz-one.c | 129 +++++++++++++++++++++++++++--------------------- src/afl-fuzz-python.c | 44 +++++++++++++++++ 9 files changed, 162 insertions(+), 66 deletions(-) (limited to 'docs') diff --git a/GNUmakefile b/GNUmakefile index 3c5e10ed..cae172dd 100644 --- a/GNUmakefile +++ b/GNUmakefile @@ -37,18 +37,18 @@ MANPAGES=$(foreach p, $(PROGS) $(SH_PROGS), $(p).8) afl-as.8 ASAN_OPTIONS=detect_leaks=0 ifeq "$(findstring android, $(shell $(CC) --version 2>/dev/null))" "" -ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto=full -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" + ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto=full -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" CFLAGS_FLTO ?= -flto=full -else - ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto=thin -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" - CFLAGS_FLTO ?= -flto=thin else - ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" + ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto=thin -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" + CFLAGS_FLTO ?= -flto=thin + else + ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" CFLAGS_FLTO ?= -flto + endif endif endif endif -endif ifeq "$(shell echo 'int main() {return 0; }' | $(CC) -fno-move-loop-invariants -fdisable-tree-cunrolli -x c - -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1" SPECIAL_PERFORMANCE += -fno-move-loop-invariants -fdisable-tree-cunrolli diff --git a/docs/Changelog.md b/docs/Changelog.md index f7bc9600..45fbd528 100644 --- a/docs/Changelog.md +++ b/docs/Changelog.md @@ -18,6 +18,9 @@ sending a mail to . dict entries without recompiling. - AFL_FORKSRV_INIT_TMOUT env variable added to control the time to wait for the forkserver to come up without the need to increase the overall timeout. + - custom mutators: + - added afl_custom_fuzz_count/fuzz_count function to allow specifying the + number of fuzz attempts for custom_fuzz - llvm_mode: - Ported SanCov to LTO, and made it the default for LTO. better instrumentation locations diff --git a/docs/custom_mutators.md b/docs/custom_mutators.md index a22c809b..75dbea21 100644 --- a/docs/custom_mutators.md +++ b/docs/custom_mutators.md @@ -32,6 +32,7 @@ performed with the custom mutator. C/C++: ```c void *afl_custom_init(afl_t *afl, unsigned int seed); +uint32_t afl_custom_fuzz_count(void *data, const u8 *buf, size_t buf_size); size_t afl_custom_fuzz(void *data, uint8_t *buf, size_t buf_size, u8 **out_buf, uint8_t *add_buf, size_t add_buf_size, size_t max_size); size_t afl_custom_post_process(void *data, uint8_t *buf, size_t buf_size, uint8_t **out_buf); int32_t afl_custom_init_trim(void *data, uint8_t *buf, size_t buf_size); @@ -49,6 +50,9 @@ Python: def init(seed): pass +def fuzz_count(buf, add_buf, max_size): + return cnt + def fuzz(buf, add_buf, max_size): return mutated_out @@ -88,6 +92,11 @@ def queue_new_entry(filename_new_queue, filename_orig_queue): This method determines whether the custom fuzzer should fuzz the current queue entry or not +- `fuzz_count` (optional): + + This method can be used to instruct afl-fuzz how often to perform a fuzz + attempt on this input data. + - `fuzz` (optional): This method performs custom mutations on a given input. It also accepts an diff --git a/include/afl-fuzz.h b/include/afl-fuzz.h index 1f1dda3a..01aa1a73 100644 --- a/include/afl-fuzz.h +++ b/include/afl-fuzz.h @@ -288,6 +288,7 @@ enum { enum { /* 00 */ PY_FUNC_INIT, + /* 01 */ PY_FUNC_FUZZ_COUNT, /* 01 */ PY_FUNC_FUZZ, /* 02 */ PY_FUNC_POST_PROCESS, /* 03 */ PY_FUNC_INIT_TRIM, @@ -679,6 +680,24 @@ struct custom_mutator { */ void *(*afl_custom_init)(afl_state_t *afl, unsigned int seed); + /** + * This method is called just before fuzzing a queue entry with the custom + * mutator, and receives the initial buffer. It should return the number of + * fuzzes to perform. + * + * A value of 0 means no fuzzing of this queue entry. + * + * The function is now allowed to change the data. + * + * (Optional) + * + * @param data pointer returned in afl_custom_init for this fuzz case + * @param buf Buffer containing the test case + * @param buf_size Size of the test case + * @return The amount of fuzzes to perform on this queue entry, 0 = skip + */ + u32 (*afl_custom_fuzz_count)(void *data, const u8 *buf, size_t buf_size); + /** * Perform custom mutations on a given input * @@ -867,6 +886,7 @@ u8 trim_case_custom(afl_state_t *, struct queue_entry *q, u8 *in_buf, struct custom_mutator *load_custom_mutator_py(afl_state_t *, char *); void finalize_py_module(void *); +u32 fuzz_count_py(void *, const u8 *, size_t); size_t post_process_py(void *, u8 *, size_t, u8 **); s32 init_trim_py(void *, u8 *, size_t); s32 post_trim_py(void *, u8); diff --git a/src/afl-forkserver.c b/src/afl-forkserver.c index c496975f..72f3dc3b 100644 --- a/src/afl-forkserver.c +++ b/src/afl-forkserver.c @@ -634,7 +634,7 @@ void afl_fsrv_start(afl_forkserver_t *fsrv, char **argv, if (fsrv->add_extra_func == NULL || fsrv->afl_ptr == NULL) { - // this is not afl-fuzz - we deny and return + // this is not afl-fuzz - or it is cmplog - we deny and return if (fsrv->use_shmem_fuzz) { status = (FS_OPT_ENABLED | FS_OPT_SHDMEM_FUZZ); diff --git a/src/afl-fuzz-extras.c b/src/afl-fuzz-extras.c index 8cc2425f..d6c368d1 100644 --- a/src/afl-fuzz-extras.c +++ b/src/afl-fuzz-extras.c @@ -251,7 +251,7 @@ static void extras_check_and_sort(afl_state_t *afl, u32 min_len, u32 max_len, if (afl->extras_cnt > afl->max_det_extras) { OKF("More than %d tokens - will use them probabilistically.", - afl->max_det_extras); + afl->max_det_extras); } @@ -406,7 +406,7 @@ void add_extra(afl_state_t *afl, u8 *mem, u32 len) { if (afl->extras_cnt == afl->max_det_extras + 1) { OKF("More than %d tokens - will use them probabilistically.", - afl->max_det_extras); + afl->max_det_extras); } diff --git a/src/afl-fuzz-mutators.c b/src/afl-fuzz-mutators.c index 22578df9..d24b7db9 100644 --- a/src/afl-fuzz-mutators.c +++ b/src/afl-fuzz-mutators.c @@ -166,6 +166,11 @@ struct custom_mutator *load_custom_mutator(afl_state_t *afl, const char *fn) { } + /* "afl_custom_fuzz_count", optional */ + mutator->afl_custom_fuzz_count = dlsym(dh, "afl_custom_fuzz_count"); + if (!mutator->afl_custom_fuzz_count) + ACTF("optional symbol 'afl_custom_fuzz_count' not found."); + /* "afl_custom_deinit", optional for backward compatibility */ mutator->afl_custom_deinit = dlsym(dh, "afl_custom_deinit"); if (!mutator->afl_custom_deinit) diff --git a/src/afl-fuzz-one.c b/src/afl-fuzz-one.c index c0c036db..03c0d3a1 100644 --- a/src/afl-fuzz-one.c +++ b/src/afl-fuzz-one.c @@ -1672,7 +1672,7 @@ custom_mutator_stage: if (afl->stage_max < HAVOC_MIN) { afl->stage_max = HAVOC_MIN; } - const u32 max_seed_size = MAX_FILE; + const u32 max_seed_size = MAX_FILE, saved_max = afl->stage_max; orig_hit_cnt = afl->queued_paths + afl->unique_crashes; @@ -1680,104 +1680,119 @@ custom_mutator_stage: if (el->afl_custom_fuzz) { + if (el->afl_custom_fuzz_count) + afl->stage_max = el->afl_custom_fuzz_count(el->data, out_buf, len); + else + afl->stage_max = saved_max; + has_custom_fuzz = true; afl->stage_short = el->name_short; - for (afl->stage_cur = 0; afl->stage_cur < afl->stage_max; - ++afl->stage_cur) { + if (afl->stage_max) { - struct queue_entry *target; - u32 tid; - u8 * new_buf; + for (afl->stage_cur = 0; afl->stage_cur < afl->stage_max; + ++afl->stage_cur) { - retry_external_pick: - /* Pick a random other queue entry for passing to external API */ + struct queue_entry *target; + u32 tid; + u8 * new_buf; - do { + retry_external_pick: + /* Pick a random other queue entry for passing to external API */ - tid = rand_below(afl, afl->queued_paths); + do { - } while (tid == afl->current_entry && afl->queued_paths > 1); + tid = rand_below(afl, afl->queued_paths); - target = afl->queue; + } while (tid == afl->current_entry && afl->queued_paths > 1); - while (tid >= 100) { + target = afl->queue; - target = target->next_100; - tid -= 100; + while (tid >= 100) { - } - - while (tid--) { + target = target->next_100; + tid -= 100; - target = target->next; + } - } + while (tid--) { - /* Make sure that the target has a reasonable length. */ + target = target->next; - while (target && (target->len < 2 || target == afl->queue_cur) && - afl->queued_paths > 3) { + } - target = target->next; - ++afl->splicing_with; + /* Make sure that the target has a reasonable length. */ - } + while (target && (target->len < 2 || target == afl->queue_cur) && + afl->queued_paths > 3) { - if (!target) { goto retry_external_pick; } + target = target->next; + ++afl->splicing_with; - /* Read the additional testcase into a new buffer. */ - fd = open(target->fname, O_RDONLY); - if (unlikely(fd < 0)) { PFATAL("Unable to open '%s'", target->fname); } + } - new_buf = afl_realloc(AFL_BUF_PARAM(out_scratch), target->len); - if (unlikely(!new_buf)) { PFATAL("alloc"); } - ck_read(fd, new_buf, target->len, target->fname); - close(fd); + if (!target) { goto retry_external_pick; } - u8 *mutated_buf = NULL; + /* Read the additional testcase into a new buffer. */ + fd = open(target->fname, O_RDONLY); + if (unlikely(fd < 0)) { - size_t mutated_size = - el->afl_custom_fuzz(el->data, out_buf, len, &mutated_buf, new_buf, - target->len, max_seed_size); + PFATAL("Unable to open '%s'", target->fname); - if (unlikely(!mutated_buf)) { + } - FATAL("Error in custom_fuzz. Size returned: %zd", mutated_size); + new_buf = afl_realloc(AFL_BUF_PARAM(out_scratch), target->len); + if (unlikely(!new_buf)) { PFATAL("alloc"); } + ck_read(fd, new_buf, target->len, target->fname); + close(fd); - } + u8 *mutated_buf = NULL; - if (mutated_size > 0) { + size_t mutated_size = + el->afl_custom_fuzz(el->data, out_buf, len, &mutated_buf, new_buf, + target->len, max_seed_size); - if (common_fuzz_stuff(afl, mutated_buf, (u32)mutated_size)) { + if (unlikely(!mutated_buf)) { - goto abandon_entry; + FATAL("Error in custom_fuzz. Size returned: %zd", mutated_size); } - /* If we're finding new stuff, let's run for a bit longer, limits - permitting. */ - - if (afl->queued_paths != havoc_queued) { + if (mutated_size > 0) { - if (perf_score <= afl->havoc_max_mult * 100) { + if (common_fuzz_stuff(afl, mutated_buf, (u32)mutated_size)) { - afl->stage_max *= 2; - perf_score *= 2; + goto abandon_entry; } - havoc_queued = afl->queued_paths; + /* If we're finding new stuff, let's run for a bit longer, limits + permitting. */ + + if (afl->queued_paths != havoc_queued) { + + if (perf_score <= afl->havoc_max_mult * 100) { + + afl->stage_max *= 2; + perf_score *= 2; + + } + + havoc_queued = afl->queued_paths; + + } } - } + /* `(afl->)out_buf` may have been changed by the call to custom_fuzz + */ + /* TODO: Only do this when `mutated_buf` == `out_buf`? Branch vs + * Memcpy. + */ + memcpy(out_buf, in_buf, len); - /* `(afl->)out_buf` may have been changed by the call to custom_fuzz */ - /* TODO: Only do this when `mutated_buf` == `out_buf`? Branch vs Memcpy. - */ - memcpy(out_buf, in_buf, len); + } } diff --git a/src/afl-fuzz-python.c b/src/afl-fuzz-python.c index e540f548..68540dd7 100644 --- a/src/afl-fuzz-python.c +++ b/src/afl-fuzz-python.c @@ -347,6 +347,12 @@ struct custom_mutator *load_custom_mutator_py(afl_state_t *afl, } + if (py_functions[PY_FUNC_FUZZ_COUNT]) { + + mutator->afl_custom_fuzz_count = fuzz_count_py; + + } + if (py_functions[PY_FUNC_POST_TRIM]) { mutator->afl_custom_post_trim = post_trim_py; @@ -477,6 +483,44 @@ s32 init_trim_py(void *py_mutator, u8 *buf, size_t buf_size) { } +u32 fuzz_count_py(void *py_mutator, const u8 *buf, size_t buf_size) { + + PyObject *py_args, *py_value; + + py_args = PyTuple_New(1); + py_value = PyByteArray_FromStringAndSize(buf, buf_size); + if (!py_value) { + + Py_DECREF(py_args); + FATAL("Failed to convert arguments"); + + } + + PyTuple_SetItem(py_args, 0, py_value); + + py_value = PyObject_CallObject( + ((py_mutator_t *)py_mutator)->py_functions[PY_FUNC_FUZZ_COUNT], py_args); + Py_DECREF(py_args); + + if (py_value != NULL) { + + #if PY_MAJOR_VERSION >= 3 + u32 retcnt = (u32)PyLong_AsLong(py_value); + #else + u32 retcnt = PyInt_AsLong(py_value); + #endif + Py_DECREF(py_value); + return retcnt; + + } else { + + PyErr_Print(); + FATAL("Call failed"); + + } + +} + s32 post_trim_py(void *py_mutator, u8 success) { PyObject *py_args, *py_value; -- cgit 1.4.1 From 41bb359428e4559821c95831f25c772d1a8403d9 Mon Sep 17 00:00:00 2001 From: Raphaël Hertzog Date: Fri, 28 Aug 2020 23:04:25 +0200 Subject: Fix various spelling errors (#532) All those spelling errors have been caught by lintian's built-in spellchecker: https://lintian.debian.org/tags/spelling-error-in-binary.html --- docs/Changelog.md | 2 +- llvm_mode/afl-llvm-rt.o.c | 2 +- llvm_mode/split-compares-pass.so.cc | 8 ++++---- src/afl-fuzz.c | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'docs') diff --git a/docs/Changelog.md b/docs/Changelog.md index 45fbd528..cb6e14b8 100644 --- a/docs/Changelog.md +++ b/docs/Changelog.md @@ -416,7 +416,7 @@ sending a mail to . - big code refactoring: * all includes are now in include/ * all afl sources are now in src/ - see src/README.md - * afl-fuzz was splitted up in various individual files for including + * afl-fuzz was split up in various individual files for including functionality in other programs (e.g. forkserver, memory map, etc.) for better readability. * new code indention everywhere diff --git a/llvm_mode/afl-llvm-rt.o.c b/llvm_mode/afl-llvm-rt.o.c index d00fd26f..bdafbe0b 100644 --- a/llvm_mode/afl-llvm-rt.o.c +++ b/llvm_mode/afl-llvm-rt.o.c @@ -339,7 +339,7 @@ static void __afl_map_shm(void) { if (__afl_area_ptr == MAP_FAILED) { - fprintf(stderr, "can not aquire mmap for address %p\n", + fprintf(stderr, "can not acquire mmap for address %p\n", (void *)__afl_map_addr); exit(1); diff --git a/llvm_mode/split-compares-pass.so.cc b/llvm_mode/split-compares-pass.so.cc index 617b55de..2e57a30a 100644 --- a/llvm_mode/split-compares-pass.so.cc +++ b/llvm_mode/split-compares-pass.so.cc @@ -1272,7 +1272,7 @@ bool SplitComparesTransform::runOnModule(Module &M) { if (!be_quiet) { errs() << "Split-floatingpoint-compare-pass: " << count - << " FP comparisons splitted\n"; + << " FP comparisons split\n"; } @@ -1290,7 +1290,7 @@ bool SplitComparesTransform::runOnModule(Module &M) { count = splitIntCompares(M, bitw); if (!be_quiet) errs() << "Split-integer-compare-pass " << bitw << "bit: " << count - << " splitted\n"; + << " split\n"; bitw >>= 1; #if LLVM_VERSION_MAJOR > 3 || \ @@ -1301,7 +1301,7 @@ bool SplitComparesTransform::runOnModule(Module &M) { count = splitIntCompares(M, bitw); if (!be_quiet) errs() << "Split-integer-compare-pass " << bitw << "bit: " << count - << " splitted\n"; + << " split\n"; bitw >>= 1; #if LLVM_VERSION_MAJOR > 3 || \ @@ -1312,7 +1312,7 @@ bool SplitComparesTransform::runOnModule(Module &M) { count = splitIntCompares(M, bitw); if (!be_quiet) errs() << "Split-integer-compare-pass " << bitw << "bit: " << count - << " splitted\n"; + << " split\n"; bitw >>= 1; break; diff --git a/src/afl-fuzz.c b/src/afl-fuzz.c index 1abd49d8..5ad2ace9 100644 --- a/src/afl-fuzz.c +++ b/src/afl-fuzz.c @@ -191,7 +191,7 @@ static void usage(u8 *argv0, int more_help) { "AFL_QUIET: suppress forkserver status messages\n" "AFL_PRELOAD: LD_PRELOAD / DYLD_INSERT_LIBRARIES settings for target\n" "AFL_SHUFFLE_QUEUE: reorder the input queue randomly on startup\n" - "AFL_SKIP_BIN_CHECK: skip the check, if the target is an excutable\n" + "AFL_SKIP_BIN_CHECK: skip the check, if the target is an executable\n" "AFL_SKIP_CPUFREQ: do not warn about variable cpu clocking\n" "AFL_SKIP_CRASHES: during initial dry run do not terminate for crashing inputs\n" "AFL_TMPDIR: directory to use for input file generation (ramdisk recommended)\n" -- cgit 1.4.1 From 567042d14698a588f83c16e50c4e83143971fe46 Mon Sep 17 00:00:00 2001 From: hexcoder- Date: Mon, 31 Aug 2020 12:32:31 +0200 Subject: typos fixed. --- docs/binaryonly_fuzzing.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'docs') diff --git a/docs/binaryonly_fuzzing.md b/docs/binaryonly_fuzzing.md index a3d3330f..cb1288ef 100644 --- a/docs/binaryonly_fuzzing.md +++ b/docs/binaryonly_fuzzing.md @@ -6,14 +6,14 @@ However, if there is only the binary program and no source code available, then standard `afl-fuzz -n` (non-instrumented mode) is not effective. - The following is a description of how these binaries can be fuzzed with afl++ + The following is a description of how these binaries can be fuzzed with afl++. ## TL;DR: qemu_mode in persistent mode is the fastest - if the stability is high enough. Otherwise try retrowrite, afl-dyninst and if these - fail too then standard qemu_mode with AFL_ENTRYPOINT to where you need it. + fail too then try standard qemu_mode with AFL_ENTRYPOINT to where you need it. If your target is a library use examples/afl_frida/. @@ -29,10 +29,10 @@ The speed decrease is at about 50%. However various options exist to increase the speed: - - using AFL_ENTRYPOINT to move the forkserver to a later basic block in + - using AFL_ENTRYPOINT to move the forkserver entry to a later basic block in the binary (+5-10% speed) - using persistent mode [qemu_mode/README.persistent.md](../qemu_mode/README.persistent.md) - this will result in 150-300% overall speed - so 3-8x the original + this will result in 150-300% overall speed increase - so 3-8x the original qemu_mode speed! - using AFL_CODE_START/AFL_CODE_END to only instrument specific parts @@ -104,7 +104,7 @@ ## RETROWRITE - If you have an x86/x86_64 binary that still has it's symbols, is compiled + If you have an x86/x86_64 binary that still has its symbols, is compiled with position independant code (PIC/PIE) and does not use most of the C++ features then the retrowrite solution might be for you. It decompiles to ASM files which can then be instrumented with afl-gcc. @@ -148,7 +148,7 @@ ## CORESIGHT Coresight is ARM's answer to Intel's PT. - There is no implementation so far which handle coresight and getting + There is no implementation so far which handles coresight and getting it working on an ARM Linux is very difficult due to custom kernel building on embedded systems is difficult. And finding one that has coresight in the ARM chip is difficult too. -- cgit 1.4.1 From e7db4d4fe0c334404c531821ae52a5f20f9185a1 Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 31 Aug 2020 12:36:30 +0200 Subject: fix sync script, update remote sync documentation --- docs/parallel_fuzzing.md | 105 ++++++++++++++++------------ examples/distributed_fuzzing/sync_script.sh | 11 +-- 2 files changed, 68 insertions(+), 48 deletions(-) (limited to 'docs') diff --git a/docs/parallel_fuzzing.md b/docs/parallel_fuzzing.md index 2ab1466c..14c237c1 100644 --- a/docs/parallel_fuzzing.md +++ b/docs/parallel_fuzzing.md @@ -10,8 +10,8 @@ n-core system, you can almost always run around n concurrent fuzzing jobs with virtually no performance hit (you can use the afl-gotcpu tool to make sure). In fact, if you rely on just a single job on a multi-core system, you will -be underutilizing the hardware. So, parallelization is usually the right -way to go. +be underutilizing the hardware. So, parallelization is always the right way to +go. When targeting multiple unrelated binaries or using the tool in "non-instrumented" (-n) mode, it is perfectly fine to just start up several @@ -65,22 +65,7 @@ still perform deterministic checks; while the secondary instances will proceed straight to random tweaks. Note that you must always have one -M main instance! - -Note that running multiple -M instances is wasteful, although there is an -experimental support for parallelizing the deterministic checks. To leverage -that, you need to create -M instances like so: - -``` -./afl-fuzz -i testcase_dir -o sync_dir -M mainA:1/3 [...] -./afl-fuzz -i testcase_dir -o sync_dir -M mainB:2/3 [...] -./afl-fuzz -i testcase_dir -o sync_dir -M mainC:3/3 [...] -``` - -...where the first value after ':' is the sequential ID of a particular main -instance (starting at 1), and the second value is the total number of fuzzers to -distribute the deterministic fuzzing across. Note that if you boot up fewer -fuzzers than indicated by the second number passed to -M, you may end up with -poor coverage. +Running multiple -M instances is wasteful! You can also monitor the progress of your jobs from the command line with the provided afl-whatsup tool. When the instances are no longer finding new paths, @@ -99,61 +84,88 @@ example may be: This is not a concern if you use @@ without -f and let afl-fuzz come up with the file name. -## 3) Syncing with non-afl fuzzers or independant instances +## 3) Multiple -M mains + + +There is support for parallelizing the deterministic checks. +This is only needed where + + 1. many new paths are found fast over a long time and it looks unlikely that + main node will ever catch up, and + 2. deterministic fuzzing is actively helping path discovery (you can see this + in the main node for the first for lines in the "fuzzing strategy yields" + section. If the ration `found/attemps` is high, then it is effective. It + most commonly isn't.) + +Only if both are true it is beneficial to have more than one main. +You can leverage this by creating -M instances like so: + +``` +./afl-fuzz -i testcase_dir -o sync_dir -M mainA:1/3 [...] +./afl-fuzz -i testcase_dir -o sync_dir -M mainB:2/3 [...] +./afl-fuzz -i testcase_dir -o sync_dir -M mainC:3/3 [...] +``` + +... where the first value after ':' is the sequential ID of a particular main +instance (starting at 1), and the second value is the total number of fuzzers to +distribute the deterministic fuzzing across. Note that if you boot up fewer +fuzzers than indicated by the second number passed to -M, you may end up with +poor coverage. + +## 4) Syncing with non-afl fuzzers or independant instances A -M main node can be told with the `-F other_fuzzer_queue_directory` option to sync results from other fuzzers, e.g. libfuzzer or honggfuzz. Only the specified directory will by synced into afl, not subdirectories. -The specified directories do not need to exist yet at the start of afl. +The specified directory does not need to exist yet at the start of afl. -## 4) Multi-system parallelization +The `-F` option can be passed to the main node several times. + +## 5) Multi-system parallelization The basic operating principle for multi-system parallelization is similar to the mechanism explained in section 2. The key difference is that you need to write a simple script that performs two actions: - Uses SSH with authorized_keys to connect to every machine and retrieve - a tar archive of the /path/to/sync_dir//queue/ directories for - every local to the machine. It's best to use a naming scheme - that includes host name in the fuzzer ID, so that you can do something - like: + a tar archive of the /path/to/sync_dir/ directory local to + the machine. + It is best to use a naming scheme that includes host name and it's being + a main node (e.g. main1, main2) in the fuzzer ID, so that you can do + something like: ```sh - for s in {1..10}; do - ssh user@host${s} "tar -czf - sync/host${s}_fuzzid*/[qf]*" >host${s}.tgz + for host in `cat HOSTLIST`; do + ssh user@$host "tar -czf - sync/$host_main*/" > $host.tgz done ``` - Distributes and unpacks these files on all the remaining machines, e.g.: ```sh - for s in {1..10}; do - for d in {1..10}; do + for srchost in `cat HOSTLIST`; do + for dsthost in `cat HOSTLIST`; do test "$s" = "$d" && continue - ssh user@host${d} 'tar -kxzf -' ".sync_tmp/${host}.tgz" + "cd '$SYNC_DIR' && tar -czf - ${host}_${MAIN_NAME}*/" > ".sync_tmp/${host}.tgz" done @@ -80,7 +83,7 @@ while :; do echo " Sending fuzzer data from ${src_host}.${FUZZ_DOMAIN}..." ssh -o 'passwordauthentication no' ${FUZZ_USER}@$dst_host \ - "cd '$SYNC_DIR' && tar -xkzf -" <".sync_tmp/${src_host}.tgz" + "cd '$SYNC_DIR' && tar -xkzf - " < ".sync_tmp/${src_host}.tgz" done -- cgit 1.4.1 From 6c980e2a023a8bb0af63bb0319a7869f455954ed Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 31 Aug 2020 12:56:14 +0200 Subject: rewrite documentation --- docs/custom_mutators.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'docs') diff --git a/docs/custom_mutators.md b/docs/custom_mutators.md index 75dbea21..a128f587 100644 --- a/docs/custom_mutators.md +++ b/docs/custom_mutators.md @@ -94,8 +94,11 @@ def queue_new_entry(filename_new_queue, filename_orig_queue): - `fuzz_count` (optional): - This method can be used to instruct afl-fuzz how often to perform a fuzz - attempt on this input data. + When a queue entry is selected to be fuzzed, afl-fuzz selects the number + of fuzzing attempts with this input based on a few factors. + If however the custom mutator wants to set this number instead on how often + it is called for a specific queue entry, use this function. + This function in mostly useful if **not** `AFL_CUSTOM_MUTATOR_ONLY` is used. - `fuzz` (optional): -- cgit 1.4.1 From 7fb72f10387979ac5e46fdfb8901e928901a94e7 Mon Sep 17 00:00:00 2001 From: hexcoder- Date: Mon, 31 Aug 2020 14:47:22 +0200 Subject: typos --- docs/parallel_fuzzing.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'docs') diff --git a/docs/parallel_fuzzing.md b/docs/parallel_fuzzing.md index 14c237c1..0c4cd237 100644 --- a/docs/parallel_fuzzing.md +++ b/docs/parallel_fuzzing.md @@ -206,9 +206,9 @@ in I/O wait state can mess things up. You can use screen, nohup, tmux, or something equivalent to run remote instances of afl-fuzz. If you redirect the program's output to a file, it will automatically switch from a fancy UI to more limited status reports. There is -also basic machine-readable information always written to the fuzzer_stats file -in the output directory. Locally, that information can be interpreted with -afl-whatsup. +also basic machine-readable information which is always written to the +fuzzer_stats file in the output directory. Locally, that information can be +interpreted with afl-whatsup. In principle, you can use the status screen of the main (-M) instance to monitor the overall fuzzing progress and decide when to stop. In this -- cgit 1.4.1 From 8253f9013418f2b8e94768c16a33e63a92e8e440 Mon Sep 17 00:00:00 2001 From: hexcoder- Date: Mon, 31 Aug 2020 15:16:55 +0200 Subject: typos/wording --- docs/env_variables.md | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'docs') diff --git a/docs/env_variables.md b/docs/env_variables.md index 7d4f6716..d377e83f 100644 --- a/docs/env_variables.md +++ b/docs/env_variables.md @@ -10,8 +10,8 @@ Because they can't directly accept command-line options, the compile-time tools make fairly broad use of environmental variables: - - Most afl tools do not print any ouput if stout/stderr are redirected. - If you want to have the output into a file then set the AFL_DEBUG + - Most afl tools do not print any output if stdout/stderr are redirected. + If you want to save the output in a file then set the AFL_DEBUG environment variable. This is sadly necessary for various build processes which fail otherwise. @@ -44,7 +44,7 @@ tools make fairly broad use of environmental variables: you instrument hand-written assembly when compiling clang code by plugging a normalizer into the chain. (There is no equivalent feature for GCC.) - - Setting AFL_INST_RATIO to a percentage between 0 and 100% controls the + - Setting AFL_INST_RATIO to a percentage between 0% and 100% controls the probability of instrumenting every branch. This is (very rarely) useful when dealing with exceptionally complex programs that saturate the output bitmap. Examples include v8, ffmpeg, and perl. @@ -88,7 +88,7 @@ of the settings discussed in section #1, with the exception of: - TMPDIR and AFL_KEEP_ASSEMBLY, since no temporary assembly files are created. - - AFL_INST_RATIO, as we by default collision free instrumentation is used. + - AFL_INST_RATIO, as we by default use collision free instrumentation. Then there are a few specific features that are only available in llvm_mode: @@ -121,7 +121,7 @@ Then there are a few specific features that are only available in llvm_mode: None of the following options are necessary to be used and are rather for manual use (which only ever the author of this LTO implementation will use). - These are used if several seperated instrumentation are performed which + These are used if several seperated instrumentations are performed which are then later combined. - AFL_LLVM_DOCUMENT_IDS=file will document to a file which edge ID was given @@ -200,7 +200,7 @@ Then there are a few specific features that are only available in llvm_mode: ### INSTRUMENT LIST (selectively instrument files and functions) - This feature allows selectively instrumentation of the source + This feature allows selective instrumentation of the source - Setting AFL_LLVM_ALLOWLIST or AFL_LLVM_DENYLIST with a filenames and/or function will only instrument (or skip) those files that match the names @@ -371,10 +371,10 @@ checks or alter some of the more exotic semantics of the tool: - Setting AFL_MAX_DET_EXRAS will change the threshold at what number of elements in the `-x` dictionary and LTO autodict (combined) the probabilistic mode will - kick off. In probabilistic mode, not all dictionary entires will be used all - of the times for fuzzing mutations to not make fuzzing slower by it. - The default count is `200` element. So for the 200 + 1st element, there is a - 1 in 201 chance, that one of the dictionary entry will not be used directly. + kick off. In probabilistic mode, not all dictionary entries will be used all + the times for fuzzing mutations in order not to slow down fuzzing. + The default count is `200` elements. So for the 200 + 1st element, there is a + 1 in 201 chance, that one of the dictionary entries will not be used directly. - Setting AFL_NO_FORKSRV disables the forkserver optimization, reverting to fork + execve() call for every tested input. This is useful mostly when @@ -385,14 +385,14 @@ checks or alter some of the more exotic semantics of the tool: normally done when starting up the forkserver and causes a pretty significant performance drop. - - Setting AFL_MAX_DET_EXTRAS changes the count of dictionary enties/extras + - Setting AFL_MAX_DET_EXTRAS changes the count of dictionary entries/extras (default 200), after which the entries will be used probabilistically. So, if the dict/extras file (`-x`) contains more tokens than this threshold, not all of the tokens will be used in each fuzzing step, every time. Instead, there is a chance that the entry will be skipped during fuzzing. This makes sure that the fuzzer doesn't spend all its time only inserting the extras, but will still do other mutations. However, it decreases the - likelyhood for each token to be inserted, before the next queue entrie is fuzzed. + likelihood for each token to be inserted, before the next queue entry is fuzzed. Either way, all tokens will be used eventually, in a longer fuzzing campaign. - Outdated environment variables that are that not supported anymore: -- cgit 1.4.1 From 58cf030546b1fb2dbe9d5325c4e69c0611c4c35b Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 31 Aug 2020 16:34:57 +0200 Subject: fix for MacOS sudo --- GNUmakefile | 2 +- docs/parallel_fuzzing.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'docs') diff --git a/GNUmakefile b/GNUmakefile index c0614d4d..fb60f301 100644 --- a/GNUmakefile +++ b/GNUmakefile @@ -492,7 +492,7 @@ ifndef AFL_NO_X86 test_build: afl-gcc afl-as afl-showmap @echo "[*] Testing the CC wrapper and instrumentation output..." - @unset AFL_USE_ASAN AFL_USE_MSAN AFL_CC; AFL_DEBUG=1 AFL_INST_RATIO=100 AFL_PATH=. ./$(TEST_CC) $(CFLAGS) test-instr.c -o test-instr $(LDFLAGS) 2>&1 | grep 'afl-as' >/dev/null || (echo "Oops, afl-as did not get called from "$(TEST_CC)". This is normally achieved by "$(CC)" honoring the -B option."; exit 1 ) + @unset AFL_USE_ASAN AFL_USE_MSAN AFL_CC; AFL_DEBUG=1 AFL_INST_RATIO=100 AFL_AS_FORCE_INSTRUMENT=1 AFL_PATH=. ./$(TEST_CC) $(CFLAGS) test-instr.c -o test-instr $(LDFLAGS) 2>&1 | grep 'afl-as' >/dev/null || (echo "Oops, afl-as did not get called from "$(TEST_CC)". This is normally achieved by "$(CC)" honoring the -B option."; exit 1 ) ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr0 ./test-instr < /dev/null echo 1 | ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr1 ./test-instr @rm -f test-instr diff --git a/docs/parallel_fuzzing.md b/docs/parallel_fuzzing.md index 0c4cd237..12895ac3 100644 --- a/docs/parallel_fuzzing.md +++ b/docs/parallel_fuzzing.md @@ -195,7 +195,7 @@ to keep in mind: - Syncing is only necessary for the main nodes on a system. It is possible to run main-less with only secondaries. However then you need to find out which secondary took over the temporary role to be the main node. Look for - the `is_main` file in the fuzzer directories, eg. `sync-dir/hostname-*/is_main` + the `is_main_node` file in the fuzzer directories, eg. `sync-dir/hostname-*/is_main_node` It is *not* advisable to skip the synchronization script and run the fuzzers directly on a network filesystem; unexpected latency and unkillable processes -- cgit 1.4.1 From 192cadee3485eef1c69ca662323ac3e50669aee9 Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 31 Aug 2020 18:10:18 +0200 Subject: fix docs --- docs/env_variables.md | 7 ------- 1 file changed, 7 deletions(-) (limited to 'docs') diff --git a/docs/env_variables.md b/docs/env_variables.md index d377e83f..c47d10e8 100644 --- a/docs/env_variables.md +++ b/docs/env_variables.md @@ -369,13 +369,6 @@ checks or alter some of the more exotic semantics of the tool: for an existing out folder, even if a different `-i` was provided. Without this setting, afl-fuzz will refuse execution for a long-fuzzed out dir. - - Setting AFL_MAX_DET_EXRAS will change the threshold at what number of elements - in the `-x` dictionary and LTO autodict (combined) the probabilistic mode will - kick off. In probabilistic mode, not all dictionary entries will be used all - the times for fuzzing mutations in order not to slow down fuzzing. - The default count is `200` elements. So for the 200 + 1st element, there is a - 1 in 201 chance, that one of the dictionary entries will not be used directly. - - Setting AFL_NO_FORKSRV disables the forkserver optimization, reverting to fork + execve() call for every tested input. This is useful mostly when working with unruly libraries that create threads or do other crazy -- cgit 1.4.1 From e4de4e350009584f5cdb8cf4c47a79fff9358cad Mon Sep 17 00:00:00 2001 From: van Hauser Date: Mon, 31 Aug 2020 18:32:01 +0200 Subject: update gitignore --- .gitignore | 1 + docs/Changelog.md | 1 + llvm_mode/afl-clang-fast.c | 4 ++-- src/afl-showmap.c | 8 ++++---- src/afl-tmin.c | 2 +- 5 files changed, 9 insertions(+), 7 deletions(-) (limited to 'docs') diff --git a/.gitignore b/.gitignore index 4307fc4c..9c169c49 100644 --- a/.gitignore +++ b/.gitignore @@ -40,6 +40,7 @@ afl-cmin.8 afl-cmin.bash.8 afl-fuzz.8 afl-gcc.8 +afl-g++.8 afl-gcc-fast.8 afl-g++-fast.8 afl-gotcpu.8 diff --git a/docs/Changelog.md b/docs/Changelog.md index cb6e14b8..3966464e 100644 --- a/docs/Changelog.md +++ b/docs/Changelog.md @@ -10,6 +10,7 @@ sending a mail to . ### Version ++2.67d (develop) + - a few QOL changes for Apple and its outdated gmake - afl-fuzz: - Fix for auto dictionary entries found during fuzzing to not throw out a -x dictionary diff --git a/llvm_mode/afl-clang-fast.c b/llvm_mode/afl-clang-fast.c index 281d6b4b..ccdbca9d 100644 --- a/llvm_mode/afl-clang-fast.c +++ b/llvm_mode/afl-clang-fast.c @@ -670,11 +670,11 @@ static void edit_params(u32 argc, char **argv, char **envp) { } -#ifndef __APPLE__ + #ifndef __APPLE__ if (!shared_linking) cc_params[cc_par_cnt++] = alloc_printf("-Wl,--dynamic-list=%s/dynamic_list.txt", obj_path); -#endif + #endif #endif diff --git a/src/afl-showmap.c b/src/afl-showmap.c index ae33cc48..f4a7c336 100644 --- a/src/afl-showmap.c +++ b/src/afl-showmap.c @@ -636,10 +636,10 @@ static void usage(u8 *argv0) { "size\n" " the target was compiled for\n" "AFL_PRELOAD: LD_PRELOAD / DYLD_INSERT_LIBRARIES settings for target\n" - "AFL_QUIET: do not print extra informational output\n" - "AFL_FORKSRV_INIT_TMOUT: time the fuzzer waits for the target to come up, initially\n" - - ,argv0, MEM_LIMIT, doc_path); + "AFL_FORKSRV_INIT_TMOUT: time spent waiting for forkserver during " + "startup (in milliseconds)\n" + "AFL_QUIET: do not print extra informational output\n", + argv0, MEM_LIMIT, doc_path); exit(1); diff --git a/src/afl-tmin.c b/src/afl-tmin.c index f231cde9..e1d08054 100644 --- a/src/afl-tmin.c +++ b/src/afl-tmin.c @@ -846,7 +846,7 @@ static void usage(u8 *argv0) { " the target was compiled for\n" "AFL_PRELOAD: LD_PRELOAD / DYLD_INSERT_LIBRARIES settings for target\n" "AFL_TMIN_EXACT: require execution paths to match for crashing inputs\n" - "AFL_FORKSRV_INIT_TMOUT: time the fuzzer waits for the target to come up, initially\n" + "AFL_FORKSRV_INIT_TMOUT: time spent waiting for forkserver during startup (in milliseconds)\n" , argv0, EXEC_TIMEOUT, MEM_LIMIT, doc_path); -- cgit 1.4.1 From 338638b124f46ac9fda25efc0060910a781d199c Mon Sep 17 00:00:00 2001 From: ploppelop <70337824+ploppelop@users.noreply.github.com> Date: Mon, 31 Aug 2020 18:34:27 +0200 Subject: Update parallel_fuzzing.md fix multisystem example --- docs/parallel_fuzzing.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'docs') diff --git a/docs/parallel_fuzzing.md b/docs/parallel_fuzzing.md index 12895ac3..bf57ace8 100644 --- a/docs/parallel_fuzzing.md +++ b/docs/parallel_fuzzing.md @@ -146,7 +146,7 @@ write a simple script that performs two actions: ```sh for srchost in `cat HOSTLIST`; do for dsthost in `cat HOSTLIST`; do - test "$s" = "$d" && continue + test "$srchost" = "$dsthost" && continue ssh user@$srchost 'tar -kxzf -' < $dsthost.tgz done done -- cgit 1.4.1