diff options
103 files changed, 3267 insertions, 2515 deletions
diff --git a/GNUmakefile b/GNUmakefile index 376f6e9a..0a6f3950 100644 --- a/GNUmakefile +++ b/GNUmakefile @@ -541,7 +541,7 @@ test_build: afl-cc afl-gcc afl-as afl-showmap # echo 1 | ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr1 ./test-instr # @rm -f test-instr # @cmp -s .test-instr0 .test-instr1; DR="$$?"; rm -f .test-instr0 .test-instr1; if [ "$$DR" = "0" ]; then echo; echo "Oops, the instrumentation of afl-gcc does not seem to be behaving correctly!"; \ -# gcc -v 2>&1 | grep -q -- --with-as= && ( echo; echo "Gcc is configured not to use an external assembler with the -B option."; echo "See docs/INSTALL.md section 5 how to build a -B enabled gcc." ) || \ +# gcc -v 2>&1 | grep -q -- --with-as= && ( echo; echo "Gcc is configured not to use an external assembler with the -B option." ) || \ # ( echo; echo "Please post to https://github.com/AFLplusplus/AFLplusplus/issues to troubleshoot the issue." ); echo; exit 0; fi # @echo # @echo "[+] All right, the instrumentation of afl-gcc seems to be working!" diff --git a/QuickStartGuide.md b/QuickStartGuide.md deleted file mode 120000 index 8136d85e..00000000 --- a/QuickStartGuide.md +++ /dev/null @@ -1 +0,0 @@ -docs/QuickStartGuide.md \ No newline at end of file diff --git a/README.md b/README.md index 1f1fd3b2..575a6a1a 100644 --- a/README.md +++ b/README.md @@ -1,1441 +1,224 @@ # American Fuzzy Lop plus plus (AFL++) - <img align="right" src="https://raw.githubusercontent.com/andreafioraldi/AFLplusplus-website/master/static/logo_256x256.png" alt="AFL++ Logo"> +<img align="right" src="https://raw.githubusercontent.com/andreafioraldi/AFLplusplus-website/master/static/logo_256x256.png" alt="AFL++ logo"> - Release Version: [3.14c](https://github.com/AFLplusplus/AFLplusplus/releases) +Release version: [3.14c](https://github.com/AFLplusplus/AFLplusplus/releases) - Github Version: 3.15a +GitHub version: 3.15a - Repository: [https://github.com/AFLplusplus/AFLplusplus](https://github.com/AFLplusplus/AFLplusplus) - - AFL++ is maintained by: - - * Marc "van Hauser" Heuse <mh@mh-sec.de>, - * Heiko "hexcoder-" Eißfeldt <heiko.eissfeldt@hexco.de>, - * Andrea Fioraldi <andreafioraldi@gmail.com> and - * Dominik Maier <mail@dmnk.co>. - - Originally developed by Michał "lcamtuf" Zalewski. - - AFL++ is a superior fork to Google's AFL - more speed, more and better - mutations, more and better instrumentation, custom module support, etc. - - If you want to use AFL++ for your academic work, check the [papers page](https://aflplus.plus/papers/) - on the website. To cite our work, look at the [Cite](#cite) section. - For comparisons use the fuzzbench `aflplusplus` setup, or use `afl-clang-fast` - with `AFL_LLVM_CMPLOG=1`. - -## Major behaviour changes in AFL++ 3.00 onwards: - -With AFL++ 3.13-3.20 we introduce frida_mode (-O) to have an alternative for -binary-only fuzzing. It is slower than Qemu mode but works on MacOS, Android, -iOS etc. - -With AFL++ 3.15 we introduced the following changes from previous behaviours: - * Also -M main mode does not do deterministic fuzzing by default anymore - * afl-cmin and afl-showmap -Ci now descent into subdirectories like - afl-fuzz -i does (but note that afl-cmin.bash does not) - -With AFL++ 3.14 we introduced the following changes from previous behaviours: - * afl-fuzz: deterministic fuzzing it not a default for -M main anymore - * afl-cmin/afl-showmap -i now descends into subdirectories (afl-cmin.bash - however does not) - -With AFL++ 3.10 we introduced the following changes from previous behaviours: - * The '+' feature of the '-t' option now means to auto-calculate the timeout - with the value given being the maximum timeout. The original meaning of - "skipping timeouts instead of abort" is now inherent to the -t option. - -With AFL++ 3.00 we introduced changes that break some previous AFL and AFL++ -behaviours and defaults: - * There are no llvm_mode and gcc_plugin subdirectories anymore and there is - only one compiler: afl-cc. All previous compilers now symlink to this one. - All instrumentation source code is now in the `instrumentation/` folder. - * The gcc_plugin was replaced with a new version submitted by AdaCore that - supports more features. Thank you! - * qemu_mode got upgraded to QEMU 5.1, but to be able to build this a current - ninja build tool version and python3 setuptools are required. - qemu_mode also got new options like snapshotting, instrumenting specific - shared libraries, etc. Additionally QEMU 5.1 supports more CPU targets so - this is really worth it. - * When instrumenting targets, afl-cc will not supersede optimizations anymore - if any were given. This allows to fuzz targets build regularly like those - for debug or release versions. - * afl-fuzz: - * if neither -M or -S is specified, `-S default` is assumed, so more - fuzzers can easily be added later - * `-i` input directory option now descends into subdirectories. It also - does not fatal on crashes and too large files, instead it skips them - and uses them for splicing mutations - * -m none is now default, set memory limits (in MB) with e.g. -m 250 - * deterministic fuzzing is now disabled by default (unless using -M) and - can be enabled with -D - * a caching of testcases can now be performed and can be modified by - editing config.h for TESTCASE_CACHE or by specifying the env variable - `AFL_TESTCACHE_SIZE` (in MB). Good values are between 50-500 (default: 50). - * -M mains do not perform trimming - * examples/ got renamed to utils/ - * libtokencap/ libdislocator/ and qdbi_mode/ were moved to utils/ - * afl-cmin/afl-cmin.bash now search first in PATH and last in AFL_PATH - - -## Contents - - 1. [Features](#important-features-of-afl) - 2. [How to compile and install AFL++](#building-and-installing-afl) - 3. [How to fuzz a target](#how-to-fuzz-with-afl) - 4. [Fuzzing binary-only targets](#fuzzing-binary-only-targets) - 5. [Good examples and writeups of AFL++ usages](#good-examples-and-writeups) - 6. [CI Fuzzing](#ci-fuzzing) - 7. [Branches](#branches) - 8. [Want to help?](#help-wanted) - 9. [Detailed help and description of AFL++](#challenges-of-guided-fuzzing) - -## Important features of AFL++ - - AFL++ supports llvm from 3.8 up to version 13, very fast binary fuzzing with QEMU 5.1 - with laf-intel and redqueen, frida mode, unicorn mode, gcc plugin, full *BSD, - Mac OS, Solaris and Android support and much, much, much more. - - | Feature/Instrumentation | afl-gcc | llvm | gcc_plugin | frida_mode | qemu_mode |unicorn_mode | - | -------------------------|:-------:|:---------:|:----------:|:----------------:|:----------------:|:----------------:| - | Threadsafe counters | | x(3) | | | | | - | NeverZero | x86[_64]| x(1) | x | x | x | x | - | Persistent Mode | | x | x | x86[_64]/arm64 | x86[_64]/arm[64] | x | - | LAF-Intel / CompCov | | x | | | x86[_64]/arm[64] | x86[_64]/arm[64] | - | CmpLog | | x | | x86[_64]/arm64 | x86[_64]/arm[64] | | - | Selective Instrumentation| | x | x | x | x | | - | Non-Colliding Coverage | | x(4) | | | (x)(5) | | - | Ngram prev_loc Coverage | | x(6) | | | | | - | Context Coverage | | x(6) | | | | | - | Auto Dictionary | | x(7) | | | | | - | Snapshot LKM Support | | (x)(8) | (x)(8) | | (x)(5) | | - | Shared Memory Testcases | | x | x | x86[_64]/arm64 | x | x | - - 1. default for LLVM >= 9.0, env var for older version due an efficiency bug in previous llvm versions - 2. GCC creates non-performant code, hence it is disabled in gcc_plugin - 3. with `AFL_LLVM_THREADSAFE_INST`, disables NeverZero - 4. with pcguard mode and LTO mode for LLVM 11 and newer - 5. upcoming, development in the branch - 6. not compatible with LTO instrumentation and needs at least LLVM v4.1 - 7. automatic in LTO mode with LLVM 11 and newer, an extra pass for all LLVM versions that write to a file to use with afl-fuzz' `-x` - 8. the snapshot LKM is currently unmaintained due to too many kernel changes coming too fast :-( - - Among others, the following features and patches have been integrated: - - * NeverZero patch for afl-gcc, instrumentation, qemu_mode and unicorn_mode which prevents a wrapping map value to zero, increases coverage - * Persistent mode, deferred forkserver and in-memory fuzzing for qemu_mode - * Unicorn mode which allows fuzzing of binaries from completely different platforms (integration provided by domenukk) - * The new CmpLog instrumentation for LLVM and QEMU inspired by [Redqueen](https://www.syssec.ruhr-uni-bochum.de/media/emma/veroeffentlichungen/2018/12/17/NDSS19-Redqueen.pdf) - * Win32 PE binary-only fuzzing with QEMU and Wine - * AFLfast's power schedules by Marcel Böhme: [https://github.com/mboehme/aflfast](https://github.com/mboehme/aflfast) - * The MOpt mutator: [https://github.com/puppet-meteor/MOpt-AFL](https://github.com/puppet-meteor/MOpt-AFL) - * LLVM mode Ngram coverage by Adrian Herrera [https://github.com/adrianherrera/afl-ngram-pass](https://github.com/adrianherrera/afl-ngram-pass) - * LAF-Intel/CompCov support for instrumentation, qemu_mode and unicorn_mode (with enhanced capabilities) - * Radamsa and honggfuzz mutators (as custom mutators). - * QBDI mode to fuzz android native libraries via Quarkslab's [QBDI](https://github.com/QBDI/QBDI) framework - * Frida and ptrace mode to fuzz binary-only libraries, etc. - - So all in all this is the best-of AFL that is out there :-) - - For new versions and additional information, check out: - [https://github.com/AFLplusplus/AFLplusplus](https://github.com/AFLplusplus/AFLplusplus) - - To compare notes with other users or get notified about major new features, - send a mail to <afl-users+subscribe@googlegroups.com>. - - See [docs/QuickStartGuide.md](docs/QuickStartGuide.md) if you don't have time to - read this file - however this is not recommended! - -## Branches +Repository: +[https://github.com/AFLplusplus/AFLplusplus](https://github.com/AFLplusplus/AFLplusplus) - The following branches exist: +AFL++ is maintained by: - * [stable/trunk](https://github.com/AFLplusplus/AFLplusplus/) : stable state of AFL++ - it is synced from dev from time to - time when we are satisfied with its stability - * [dev](https://github.com/AFLplusplus/AFLplusplus/tree/dev) : development state of AFL++ - bleeding edge and you might catch a - checkout which does not compile or has a bug. *We only accept PRs in dev!!* - * [release](https://github.com/AFLplusplus/AFLplusplus/tree/release) : the latest release - * (any other) : experimental branches to work on specific features or testing - new functionality or changes. +* Marc "van Hauser" Heuse <mh@mh-sec.de>, +* Heiko "hexcoder-" Eißfeldt <heiko.eissfeldt@hexco.de>, +* Andrea Fioraldi <andreafioraldi@gmail.com> and +* Dominik Maier <mail@dmnk.co>. - For releases, please see the [Releases](https://github.com/AFLplusplus/AFLplusplus/releases) tab. +Originally developed by Michał "lcamtuf" Zalewski. -## Help wanted +AFL++ is a superior fork to Google's AFL - more speed, more and better +mutations, more and better instrumentation, custom module support, etc. -We have several ideas we would like to see in AFL++ to make it even better. -However, we already work on so many things that we do not have the time for -all the big ideas. +You are free to copy, modify, and distribute AFL++ with attribution under the +terms of the Apache-2.0 License. See the [LICENSE](LICENSE) for details. -This can be your way to support and contribute to AFL++ - extend it to do -something cool. +## Getting started -We have an idea list in [docs/ideas.md](docs/ideas.md). +Here is some information to get you started: -For everyone who wants to contribute (and send pull requests) please read -[CONTRIBUTING.md](CONTRIBUTING.md) before your submit. +* For releases, please see the + [Releases](https://github.com/AFLplusplus/AFLplusplus/releases) tab and + [branches](docs/branches.md). Also take a look at the list of + [important changes in AFL++](docs/important_changes.md). +* If you want to use AFL++ for your academic work, check the + [papers page](https://aflplus.plus/papers/) on the website. +* To cite our work, look at the [Cite](#cite) section. +* For comparisons, use the fuzzbench `aflplusplus` setup, or use + `afl-clang-fast` with `AFL_LLVM_CMPLOG=1`. You can find the `aflplusplus` + default configuration on Google's + [fuzzbench](https://github.com/google/fuzzbench/tree/master/fuzzers/aflplusplus). +* To get you started with tutorials, go to + [docs/tutorials.md](docs/tutorials.md). ## Building and installing AFL++ -An easy way to install AFL++ with everything compiled is available via docker: -You can use the [Dockerfile](Dockerfile) (which has gcc-10 and clang-11 - -hence afl-clang-lto is available!) or just pull directly from the docker hub: +To have AFL++ easily available with everything compiled, pull the image +directly from the Docker Hub: + ```shell docker pull aflplusplus/aflplusplus docker run -ti -v /location/of/your/target:/src aflplusplus/aflplusplus ``` -This image is automatically generated when a push to the stable repo happens. -You will find your target source code in /src in the container. - -If you want to build AFL++ yourself you have many options. -The easiest choice is to build and install everything: - -```shell -sudo apt-get update -sudo apt-get install -y build-essential python3-dev automake git flex bison libglib2.0-dev libpixman-1-dev python3-setuptools -# try to install llvm 11 and install the distro default if that fails -sudo apt-get install -y lld-11 llvm-11 llvm-11-dev clang-11 || sudo apt-get install -y lld llvm llvm-dev clang -sudo apt-get install -y gcc-$(gcc --version|head -n1|sed 's/.* //'|sed 's/\..*//')-plugin-dev libstdc++-$(gcc --version|head -n1|sed 's/.* //'|sed 's/\..*//')-dev -git clone https://github.com/AFLplusplus/AFLplusplus -cd AFLplusplus -make distrib -sudo make install -``` -It is recommended to install the newest available gcc, clang and llvm-dev -possible in your distribution! - -Note that "make distrib" also builds instrumentation, qemu_mode, unicorn_mode and -more. If you just want plain AFL++ then do "make all", however compiling and -using at least instrumentation is highly recommended for much better results - -hence in this case - -```shell -make source-only -``` -is what you should choose. - -These build targets exist: -* all: just the main AFL++ binaries -* binary-only: everything for binary-only fuzzing: qemu_mode, unicorn_mode, libdislocator, libtokencap -* source-only: everything for source code fuzzing: instrumentation, libdislocator, libtokencap -* distrib: everything (for both binary-only and source code fuzzing) -* man: creates simple man pages from the help option of the programs -* install: installs everything you have compiled with the build options above -* clean: cleans everything compiled, not downloads (unless not on a checkout) -* deepclean: cleans everything including downloads -* code-format: format the code, do this before you commit and send a PR please! -* tests: runs test cases to ensure that all features are still working as they should -* unit: perform unit tests (based on cmocka) -* help: shows these build options +This image is automatically generated when a push to the stable repo happens +(see [docs/branches.md](docs/branches.md)). You will find your target source +code in `/src` in the container. -[Unless you are on Mac OS X](https://developer.apple.com/library/archive/qa/qa1118/_index.html) you can also build statically linked versions of the -AFL++ binaries by passing the STATIC=1 argument to make: +To build AFL++ yourself, continue at [docs/INSTALL.md](docs/INSTALL.md). -```shell -make STATIC=1 -``` +## Quick start: Fuzzing with AFL++ -These build options exist: +*NOTE: Before you start, please read about the [common sense risks of +fuzzing](docs/common_sense_risks.md).* -* STATIC - compile AFL++ static -* ASAN_BUILD - compiles with memory sanitizer for debug purposes -* DEBUG - no optimization, -ggdb3, all warnings and -Werror -* PROFILING - compile with profiling information (gprof) -* INTROSPECTION - compile afl-fuzz with mutation introspection -* NO_PYTHON - disable python support -* NO_SPLICING - disables splicing mutation in afl-fuzz, not recommended for normal fuzzing -* AFL_NO_X86 - if compiling on non-intel/amd platforms -* LLVM_CONFIG - if your distro doesn't use the standard name for llvm-config (e.g. Debian) +This is a quick start for fuzzing targets with the source code available. To +read about the process in detail, see +[docs/fuzzing_expert.md](docs/fuzzing_expert.md). -e.g.: `make ASAN_BUILD=1` +To learn about fuzzing other targets, see: +* Binary-only targets: + [docs/fuzzing_binary-only_targets.md](docs/fuzzing_binary-only_targets.md) +* Network services: + [docs/best_practices.md#fuzzing-a-network-service](docs/best_practices.md#fuzzing-a-network-service) +* GUI programs: + [docs/best_practices.md#fuzzing-a-gui-program](docs/best_practices.md#fuzzing-a-gui-program) -## Good examples and writeups +Step-by-step quick start: -Here are some good writeups to show how to effectively use AFL++: +1. Compile the program or library to be fuzzed using `afl-cc`. A common way to + do this would be: - * [https://aflplus.plus/docs/tutorials/libxml2_tutorial/](https://aflplus.plus/docs/tutorials/libxml2_tutorial/) - * [https://bananamafia.dev/post/gb-fuzz/](https://bananamafia.dev/post/gb-fuzz/) - * [https://securitylab.github.com/research/fuzzing-challenges-solutions-1](https://securitylab.github.com/research/fuzzing-challenges-solutions-1) - * [https://securitylab.github.com/research/fuzzing-software-2](https://securitylab.github.com/research/fuzzing-software-2) - * [https://securitylab.github.com/research/fuzzing-sockets-FTP](https://securitylab.github.com/research/fuzzing-sockets-FTP) - * [https://securitylab.github.com/research/fuzzing-sockets-FreeRDP](https://securitylab.github.com/research/fuzzing-sockets-FreeRDP) - * [https://securitylab.github.com/research/fuzzing-apache-1](https://securitylab.github.com/research/fuzzing-apache-1) + CC=/path/to/afl-cc CXX=/path/to/afl-c++ ./configure --disable-shared + make clean all -If you do not want to follow a tutorial but rather try an exercise type of -training then we can highly recommend the following: - * [https://github.com/antonio-morales/Fuzzing101](https://github.com/antonio-morales/Fuzzing101) +2. Get a small but valid input file that makes sense to the program. When + fuzzing verbose syntax (SQL, HTTP, etc), create a dictionary as described in + [dictionaries/README.md](dictionaries/README.md), too. -If you are interested in fuzzing structured data (where you define what the -structure is), these links have you covered: - * Superion for AFL++: [https://github.com/adrian-rt/superion-mutator](https://github.com/adrian-rt/superion-mutator) - * libprotobuf for AFL++: [https://github.com/P1umer/AFLplusplus-protobuf-mutator](https://github.com/P1umer/AFLplusplus-protobuf-mutator) - * libprotobuf raw: [https://github.com/bruce30262/libprotobuf-mutator_fuzzing_learning/tree/master/4_libprotobuf_aflpp_custom_mutator](https://github.com/bruce30262/libprotobuf-mutator_fuzzing_learning/tree/master/4_libprotobuf_aflpp_custom_mutator) - * libprotobuf for old AFL++ API: [https://github.com/thebabush/afl-libprotobuf-mutator](https://github.com/thebabush/afl-libprotobuf-mutator) - -If you find other good ones, please send them to us :-) - -## How to fuzz with AFL++ - -The following describes how to fuzz with a target if source code is available. -If you have a binary-only target please skip to [#Instrumenting binary-only apps](#Instrumenting binary-only apps) - -Fuzzing source code is a three-step process. - -1. Compile the target with a special compiler that prepares the target to be - fuzzed efficiently. This step is called "instrumenting a target". -2. Prepare the fuzzing by selecting and optimizing the input corpus for the - target. -3. Perform the fuzzing of the target by randomly mutating input and assessing - if a generated input was processed in a new path in the target binary. - -### 1. Instrumenting that target - -#### a) Selecting the best AFL++ compiler for instrumenting the target - -AFL++ comes with a central compiler `afl-cc` that incorporates various different -kinds of compiler targets and and instrumentation options. -The following evaluation flow will help you to select the best possible. - -It is highly recommended to have the newest llvm version possible installed, -anything below 9 is not recommended. +3. If the program reads from stdin, run `afl-fuzz` like so: ``` -+--------------------------------+ -| clang/clang++ 11+ is available | --> use LTO mode (afl-clang-lto/afl-clang-lto++) -+--------------------------------+ see [instrumentation/README.lto.md](instrumentation/README.lto.md) - | - | if not, or if the target fails with LTO afl-clang-lto/++ - | - v -+---------------------------------+ -| clang/clang++ 3.8+ is available | --> use LLVM mode (afl-clang-fast/afl-clang-fast++) -+---------------------------------+ see [instrumentation/README.llvm.md](instrumentation/README.llvm.md) - | - | if not, or if the target fails with LLVM afl-clang-fast/++ - | - v - +--------------------------------+ - | gcc 5+ is available | -> use GCC_PLUGIN mode (afl-gcc-fast/afl-g++-fast) - +--------------------------------+ see [instrumentation/README.gcc_plugin.md](instrumentation/README.gcc_plugin.md) and - [instrumentation/README.instrument_list.md](instrumentation/README.instrument_list.md) - | - | if not, or if you do not have a gcc with plugin support - | - v - use GCC mode (afl-gcc/afl-g++) (or afl-clang/afl-clang++ for clang) + ./afl-fuzz -i seeds_dir -o output_dir -- \ + /path/to/tested/program [...program's cmdline...] ``` -Clickable README links for the chosen compiler: - - * [LTO mode - afl-clang-lto](instrumentation/README.lto.md) - * [LLVM mode - afl-clang-fast](instrumentation/README.llvm.md) - * [GCC_PLUGIN mode - afl-gcc-fast](instrumentation/README.gcc_plugin.md) - * GCC/CLANG modes (afl-gcc/afl-clang) have no README as they have no own features - -You can select the mode for the afl-cc compiler by: - 1. use a symlink to afl-cc: afl-gcc, afl-g++, afl-clang, afl-clang++, - afl-clang-fast, afl-clang-fast++, afl-clang-lto, afl-clang-lto++, - afl-gcc-fast, afl-g++-fast (recommended!) - 2. using the environment variable AFL_CC_COMPILER with MODE - 3. passing --afl-MODE command line options to the compiler via CFLAGS/CXXFLAGS/CPPFLAGS - -MODE can be one of: LTO (afl-clang-lto*), LLVM (afl-clang-fast*), GCC_PLUGIN -(afl-g*-fast) or GCC (afl-gcc/afl-g++) or CLANG(afl-clang/afl-clang++). - -Because no AFL specific command-line options are accepted (beside the ---afl-MODE command), the compile-time tools make fairly broad use of environment -variables, which can be listed with `afl-cc -hh` or by reading [docs/env_variables.md](docs/env_variables.md). - -#### b) Selecting instrumentation options - -The following options are available when you instrument with LTO mode (afl-clang-fast/afl-clang-lto): - - * Splitting integer, string, float and switch comparisons so AFL++ can easier - solve these. This is an important option if you do not have a very good - and large input corpus. This technique is called laf-intel or COMPCOV. - To use this set the following environment variable before compiling the - target: `export AFL_LLVM_LAF_ALL=1` - You can read more about this in [instrumentation/README.laf-intel.md](instrumentation/README.laf-intel.md) - * A different technique (and usually a better one than laf-intel) is to - instrument the target so that any compare values in the target are sent to - AFL++ which then tries to put these values into the fuzzing data at different - locations. This technique is very fast and good - if the target does not - transform input data before comparison. Therefore this technique is called - `input to state` or `redqueen`. - If you want to use this technique, then you have to compile the target - twice, once specifically with/for this mode, and pass this binary to afl-fuzz - via the `-c` parameter. - Note that you can compile also just a cmplog binary and use that for both - however there will be a performance penality. - You can read more about this in [instrumentation/README.cmplog.md](instrumentation/README.cmplog.md) - -If you use LTO, LLVM or GCC_PLUGIN mode (afl-clang-fast/afl-clang-lto/afl-gcc-fast) -you have the option to selectively only instrument parts of the target that you -are interested in: - - * To instrument only those parts of the target that you are interested in - create a file with all the filenames of the source code that should be - instrumented. - For afl-clang-lto and afl-gcc-fast - or afl-clang-fast if a mode other than - DEFAULT/PCGUARD is used or you have llvm > 10.0.0 - just put one - filename or function per line (no directory information necessary for - filenames9, and either set `export AFL_LLVM_ALLOWLIST=allowlist.txt` **or** - `export AFL_LLVM_DENYLIST=denylist.txt` - depending on if you want per - default to instrument unless noted (DENYLIST) or not perform instrumentation - unless requested (ALLOWLIST). - **NOTE:** During optimization functions might be inlined and then would not match! - See [instrumentation/README.instrument_list.md](instrumentation/README.instrument_list.md) - -There are many more options and modes available however these are most of the -time less effective. See: - * [instrumentation/README.ctx.md](instrumentation/README.ctx.md) - * [instrumentation/README.ngram.md](instrumentation/README.ngram.md) - -AFL++ performs "never zero" counting in its bitmap. You can read more about this -here: - * [instrumentation/README.neverzero.md](instrumentation/README.neverzero.md) - -#### c) Sanitizers - -It is possible to use sanitizers when instrumenting targets for fuzzing, -which allows you to find bugs that would not necessarily result in a crash. - -Note that sanitizers have a huge impact on CPU (= less executions per second) -and RAM usage. Also you should only run one afl-fuzz instance per sanitizer type. -This is enough because a use-after-free bug will be picked up, e.g. by -ASAN (address sanitizer) anyway when syncing to other fuzzing instances, -so not all fuzzing instances need to be instrumented with ASAN. - -The following sanitizers have built-in support in AFL++: - * ASAN = Address SANitizer, finds memory corruption vulnerabilities like - use-after-free, NULL pointer dereference, buffer overruns, etc. - Enabled with `export AFL_USE_ASAN=1` before compiling. - * MSAN = Memory SANitizer, finds read access to uninitialized memory, eg. - a local variable that is defined and read before it is even set. - Enabled with `export AFL_USE_MSAN=1` before compiling. - * UBSAN = Undefined Behaviour SANitizer, finds instances where - by the - C and C++ standards - undefined behaviour happens, e.g. adding two - signed integers together where the result is larger than a signed integer - can hold. - Enabled with `export AFL_USE_UBSAN=1` before compiling. - * CFISAN = Control Flow Integrity SANitizer, finds instances where the - control flow is found to be illegal. Originally this was rather to - prevent return oriented programming exploit chains from functioning, - in fuzzing this is mostly reduced to detecting type confusion - vulnerabilities - which is however one of the most important and dangerous - C++ memory corruption classes! - Enabled with `export AFL_USE_CFISAN=1` before compiling. - * LSAN = Leak SANitizer, finds memory leaks in a program. This is not really - a security issue, but for developers this can be very valuable. - Note that unlike the other sanitizers above this needs - `__AFL_LEAK_CHECK();` added to all areas of the target source code where you - find a leak check necessary! - Enabled with `export AFL_USE_LSAN=1` before compiling. - -It is possible to further modify the behaviour of the sanitizers at run-time -by setting `ASAN_OPTIONS=...`, `LSAN_OPTIONS` etc. - the available parameters -can be looked up in the sanitizer documentation of llvm/clang. -afl-fuzz however requires some specific parameters important for fuzzing to be -set. If you want to set your own, it might bail and report what it is missing. - -Note that some sanitizers cannot be used together, e.g. ASAN and MSAN, and -others often cannot work together because of target weirdness, e.g. ASAN and -CFISAN. You might need to experiment which sanitizers you can combine in a -target (which means more instances can be run without a sanitized target, -which is more effective). - -#### d) Modify the target - -If the target has features that make fuzzing more difficult, e.g. -checksums, HMAC, etc. then modify the source code so that checks for these -values are removed. -This can even be done safely for source code used in operational products -by eliminating these checks within these AFL specific blocks: - -``` -#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION - // say that the checksum or HMAC was fine - or whatever is required - // to eliminate the need for the fuzzer to guess the right checksum - return 0; -#endif -``` - -All AFL++ compilers will set this preprocessor definition automatically. - -#### e) Instrument the target - -In this step the target source code is compiled so that it can be fuzzed. - -Basically you have to tell the target build system that the selected AFL++ -compiler is used. Also - if possible - you should always configure the -build system such that the target is compiled statically and not dynamically. -How to do this is described below. - -The #1 rule when instrumenting a target is: avoid instrumenting shared -libraries at all cost. You would need to set LD_LIBRARY_PATH to point to -these, you could accidently type "make install" and install them system wide - -so don't. Really don't. -**Always compile libraries you want to have instrumented as static and link -these to the target program!** - -Then build the target. (Usually with `make`) - -**NOTES** - -1. sometimes configure and build systems are fickle and do not like - stderr output (and think this means a test failure) - which is something - AFL++ likes to do to show statistics. It is recommended to disable AFL++ - instrumentation reporting via `export AFL_QUIET=1`. + To add a dictionary, add `-x /path/to/dictionary.txt` to afl-fuzz. -2. sometimes configure and build systems error on warnings - these should be - disabled (e.g. `--disable-werror` for some configure scripts). - -3. in case the configure/build system complains about AFL++'s compiler and - aborts then set `export AFL_NOOPT=1` which will then just behave like the - real compiler. This option has to be unset again before building the target! - -##### configure - -For `configure` build systems this is usually done by: -`CC=afl-clang-fast CXX=afl-clang-fast++ ./configure --disable-shared` - -Note that if you are using the (better) afl-clang-lto compiler you also have to -set AR to llvm-ar[-VERSION] and RANLIB to llvm-ranlib[-VERSION] - as is -described in [instrumentation/README.lto.md](instrumentation/README.lto.md). - -##### cmake - -For `cmake` build systems this is usually done by: -`mkdir build; cd build; cmake -DCMAKE_C_COMPILER=afl-cc -DCMAKE_CXX_COMPILER=afl-c++ ..` - -Note that if you are using the (better) afl-clang-lto compiler you also have to -set AR to llvm-ar[-VERSION] and RANLIB to llvm-ranlib[-VERSION] - as is -described in [instrumentation/README.lto.md](instrumentation/README.lto.md). - -##### meson - -For meson you have to set the AFL++ compiler with the very first command! -`CC=afl-cc CXX=afl-c++ meson` - -##### other build systems or if configure/cmake didn't work - -Sometimes cmake and configure do not pick up the AFL++ compiler, or the -ranlib/ar that is needed - because this was just not foreseen by the developer -of the target. Or they have non-standard options. Figure out if there is a -non-standard way to set this, otherwise set up the build normally and edit the -generated build environment afterwards manually to point it to the right compiler -(and/or ranlib and ar). - -#### f) Better instrumentation - -If you just fuzz a target program as-is you are wasting a great opportunity for -much more fuzzing speed. - -This variant requires the usage of afl-clang-lto, afl-clang-fast or afl-gcc-fast. - -It is the so-called `persistent mode`, which is much, much faster but -requires that you code a source file that is specifically calling the target -functions that you want to fuzz, plus a few specific AFL++ functions around -it. See [instrumentation/README.persistent_mode.md](instrumentation/README.persistent_mode.md) for details. - -Basically if you do not fuzz a target in persistent mode then you are just -doing it for a hobby and not professionally :-). - -#### g) libfuzzer fuzzer harnesses with LLVMFuzzerTestOneInput() - -libfuzzer `LLVMFuzzerTestOneInput()` harnesses are the defacto standard -for fuzzing, and they can be used with AFL++ (and honggfuzz) as well! -Compiling them is as simple as: -``` -afl-clang-fast++ -fsanitize=fuzzer -o harness harness.cpp targetlib.a -``` -You can even use advanced libfuzzer features like `FuzzedDataProvider`, -`LLVMFuzzerMutate()` etc. and they will work! - -The generated binary is fuzzed with afl-fuzz like any other fuzz target. - -Bonus: the target is already optimized for fuzzing due to persistent mode and -shared-memory testcases and hence gives you the fastest speed possible. - -For more information see [utils/aflpp_driver/README.md](utils/aflpp_driver/README.md) - -### 2. Preparing the fuzzing campaign - -As you fuzz the target with mutated input, having as diverse inputs for the -target as possible improves the efficiency a lot. - -#### a) Collect inputs - -Try to gather valid inputs for the target from wherever you can. E.g. if it is -the PNG picture format try to find as many png files as possible, e.g. from -reported bugs, test suites, random downloads from the internet, unit test -case data - from all kind of PNG software. - -If the input format is not known, you can also modify a target program to write -normal data it receives and processes to a file and use these. - -#### b) Making the input corpus unique - -Use the AFL++ tool `afl-cmin` to remove inputs from the corpus that do not -produce a new path in the target. - -Put all files from step a) into one directory, e.g. INPUTS. - -If the target program is to be called by fuzzing as `bin/target -d INPUTFILE` -the run afl-cmin like this: -`afl-cmin -i INPUTS -o INPUTS_UNIQUE -- bin/target -d @@` -Note that the INPUTFILE argument that the target program would read from has to be set as `@@`. - -If the target reads from stdin instead, just omit the `@@` as this is the -default. - -This step is highly recommended! - -#### c) Minimizing all corpus files - -The shorter the input files that still traverse the same path -within the target, the better the fuzzing will be. This minimization -is done with `afl-tmin` however it is a long process as this has to -be done for every file: - -``` -mkdir input -cd INPUTS_UNIQUE -for i in *; do - afl-tmin -i "$i" -o "../input/$i" -- bin/target -d @@ -done -``` - -This step can also be parallelized, e.g. with `parallel`. -Note that this step is rather optional though. - -#### Done! - -The INPUTS_UNIQUE/ directory from step b) - or even better the directory input/ -if you minimized the corpus in step c) - is the resulting input corpus directory -to be used in fuzzing! :-) - -### 3. Fuzzing the target - -In this final step we fuzz the target. -There are not that many important options to run the target - unless you want -to use many CPU cores/threads for the fuzzing, which will make the fuzzing much -more useful. - -If you just use one CPU for fuzzing, then you are fuzzing just for fun and not -seriously :-) - -#### a) Running afl-fuzz - -Before you do even a test run of afl-fuzz execute `sudo afl-system-config` (on -the host if you execute afl-fuzz in a docker container). This reconfigures the -system for optimal speed - which afl-fuzz checks and bails otherwise. -Set `export AFL_SKIP_CPUFREQ=1` for afl-fuzz to skip this check if you cannot -run afl-system-config with root privileges on the host for whatever reason. - -Note there is also `sudo afl-persistent-config` which sets additional permanent -boot options for a much better fuzzing performance. - -Note that both scripts improve your fuzzing performance but also decrease your -system protection against attacks! So set strong firewall rules and only -expose SSH as a network service if you use these (which is highly recommended). - -If you have an input corpus from step 2 then specify this directory with the `-i` -option. Otherwise create a new directory and create a file with any content -as test data in there. - -If you do not want anything special, the defaults are already usually best, -hence all you need is to specify the seed input directory with the result of -step [2a. Collect inputs](#a-collect-inputs): -`afl-fuzz -i input -o output -- bin/target -d @@` -Note that the directory specified with -o will be created if it does not exist. - -It can be valuable to run afl-fuzz in a screen or tmux shell so you can log off, -or afl-fuzz is not aborted if you are running it in a remote ssh session where -the connection fails in between. -Only do that though once you have verified that your fuzzing setup works! -Simply run it like `screen -dmS afl-main -- afl-fuzz -M main-$HOSTNAME -i ...` -and it will start away in a screen session. To enter this session simply type -`screen -r afl-main`. You see - it makes sense to name the screen session -same as the afl-fuzz -M/-S naming :-) -For more information on screen or tmux please check their documentation. - -If you need to stop and re-start the fuzzing, use the same command line options -(or even change them by selecting a different power schedule or another -mutation mode!) and switch the input directory with a dash (`-`): -`afl-fuzz -i - -o output -- bin/target -d @@` - -Memory limits are not enforced by afl-fuzz by default and the system may run -out of memory. You can decrease the memory with the `-m` option, the value is -in MB. If this is too small for the target, you can usually see this by -afl-fuzz bailing with the message that it could not connect to the forkserver. - -Adding a dictionary is helpful. See the directory [dictionaries/](dictionaries/) if -something is already included for your data format, and tell afl-fuzz to load -that dictionary by adding `-x dictionaries/FORMAT.dict`. With afl-clang-lto -you have an autodictionary generation for which you need to do nothing except -to use afl-clang-lto as the compiler. You also have the option to generate -a dictionary yourself, see [utils/libtokencap/README.md](utils/libtokencap/README.md). - -afl-fuzz has a variety of options that help to workaround target quirks like -specific locations for the input file (`-f`), performing deterministic -fuzzing (`-D`) and many more. Check out `afl-fuzz -h`. - -We highly recommend that you set a memory limit for running the target with `-m` -which defines the maximum memory in MB. This prevents a potential -out-of-memory problem for your system plus helps you detect missing `malloc()` -failure handling in the target. -Play around with various -m values until you find one that safely works for all -your input seeds (if you have good ones and then double or quadrouple that. - -By default afl-fuzz never stops fuzzing. To terminate AFL++ simply press Control-C -or send a signal SIGINT. You can limit the number of executions or approximate runtime -in seconds with options also. - -When you start afl-fuzz you will see a user interface that shows what the status -is: - - -All labels are explained in [docs/status_screen.md](docs/status_screen.md). - -#### b) Using multiple cores - -If you want to seriously fuzz then use as many cores/threads as possible to -fuzz your target. - -On the same machine - due to the design of how AFL++ works - there is a maximum -number of CPU cores/threads that are useful, use more and the overall performance -degrades instead. This value depends on the target, and the limit is between 32 -and 64 cores per machine. - -If you have the RAM, it is highly recommended run the instances with a caching -of the testcases. Depending on the average testcase size (and those found -during fuzzing) and their number, a value between 50-500MB is recommended. -You can set the cache size (in MB) by setting the environment variable `AFL_TESTCACHE_SIZE`. - -There should be one main fuzzer (`-M main-$HOSTNAME` option) and as many secondary -fuzzers (eg `-S variant1`) as you have cores that you use. -Every -M/-S entry needs a unique name (that can be whatever), however the same --o output directory location has to be used for all instances. - -For every secondary fuzzer there should be a variation, e.g.: - * one should fuzz the target that was compiled differently: with sanitizers - activated (`export AFL_USE_ASAN=1 ; export AFL_USE_UBSAN=1 ; - export AFL_USE_CFISAN=1`) - * one or two should fuzz the target with CMPLOG/redqueen (see above), at - least one cmplog instance should follow transformations (`-l AT`) - * one to three fuzzers should fuzz a target compiled with laf-intel/COMPCOV - (see above). Important note: If you run more than one laf-intel/COMPCOV - fuzzer and you want them to share their intermediate results, the main - fuzzer (`-M`) must be one of the them! (Although this is not really - recommended.) - -All other secondaries should be used like this: - * A quarter to a third with the MOpt mutator enabled: `-L 0` - * run with a different power schedule, recommended are: - `fast (default), explore, coe, lin, quad, exploit and rare` - which you can set with e.g. `-p explore` - * a few instances should use the old queue cycling with `-Z` - -Also it is recommended to set `export AFL_IMPORT_FIRST=1` to load testcases -from other fuzzers in the campaign first. - -If you have a large corpus, a corpus from a previous run or are fuzzing in -a CI, then also set `export AFL_CMPLOG_ONLY_NEW=1` and `export AFL_FAST_CAL=1`. - -You can also use different fuzzers. -If you are using AFL spinoffs or AFL conforming fuzzers, then just use the -same -o directory and give it a unique `-S` name. -Examples are: - * [Fuzzolic](https://github.com/season-lab/fuzzolic) - * [symcc](https://github.com/eurecom-s/symcc/) - * [Eclipser](https://github.com/SoftSec-KAIST/Eclipser/) - * [AFLsmart](https://github.com/aflsmart/aflsmart) - * [FairFuzz](https://github.com/carolemieux/afl-rb) - * [Neuzz](https://github.com/Dongdongshe/neuzz) - * [Angora](https://github.com/AngoraFuzzer/Angora) - -A long list can be found at [https://github.com/Microsvuln/Awesome-AFL](https://github.com/Microsvuln/Awesome-AFL) - -However you can also sync AFL++ with honggfuzz, libfuzzer with `-entropic=1`, etc. -Just show the main fuzzer (-M) with the `-F` option where the queue/work -directory of a different fuzzer is, e.g. `-F /src/target/honggfuzz`. -Using honggfuzz (with `-n 1` or `-n 2`) and libfuzzer in parallel is highly -recommended! - -#### c) Using multiple machines for fuzzing - -Maybe you have more than one machine you want to fuzz the same target on. -Simply start the `afl-fuzz` (and perhaps libfuzzer, honggfuzz, ...) -orchestra as you like, just ensure that your have one and only one `-M` -instance per server, and that its name is unique, hence the recommendation -for `-M main-$HOSTNAME`. - -Now there are three strategies on how you can sync between the servers: - * never: sounds weird, but this makes every server an island and has the - chance the each follow different paths into the target. You can make - this even more interesting by even giving different seeds to each server. - * regularly (~4h): this ensures that all fuzzing campaigns on the servers - "see" the same thing. It is like fuzzing on a huge server. - * in intervals of 1/10th of the overall expected runtime of the fuzzing you - sync. This tries a bit to combine both. have some individuality of the - paths each campaign on a server explores, on the other hand if one - gets stuck where another found progress this is handed over making it - unstuck. - -The syncing process itself is very simple. -As the `-M main-$HOSTNAME` instance syncs to all `-S` secondaries as well -as to other fuzzers, you have to copy only this directory to the other -machines. - -Lets say all servers have the `-o out` directory in /target/foo/out, and -you created a file `servers.txt` which contains the hostnames of all -participating servers, plus you have an ssh key deployed to all of them, -then run: -```bash -for FROM in `cat servers.txt`; do - for TO in `cat servers.txt`; do - rsync -rlpogtz --rsh=ssh $FROM:/target/foo/out/main-$FROM $TO:target/foo/out/ - done -done -``` -You can run this manually, per cron job - as you need it. -There is a more complex and configurable script in `utils/distributed_fuzzing`. + If the program takes input from a file, you can put `@@` in the program's + command line; AFL will put an auto-generated file name in there for you. -#### d) The status of the fuzz campaign +4. Investigate anything shown in red in the fuzzer UI by promptly consulting + [docs/status_screen.md](docs/status_screen.md). -AFL++ comes with the `afl-whatsup` script to show the status of the fuzzing -campaign. +5. You will find found crashes and hangs in the subdirectories `crashes/` and + `hangs/` in the `-o output_dir` directory. You can replay the crashes by + feeding them to the target, e.g.: `cat output_dir/crashes/id:000000,* | + /path/to/tested/program [...program's cmdline...]` You can generate cores or + use gdb directly to follow up the crashes. -Just supply the directory that afl-fuzz is given with the -o option and -you will see a detailed status of every fuzzer in that campaign plus -a summary. - -To have only the summary use the `-s` switch e.g.: `afl-whatsup -s out/` - -If you have multiple servers then use the command after a sync, or you have -to execute this script per server. - -#### e) Stopping fuzzing, restarting fuzzing, adding new seeds - -To stop an afl-fuzz run, simply press Control-C. - -To restart an afl-fuzz run, just reuse the same command line but replace the -`-i directory` with `-i -` or set `AFL_AUTORESUME=1`. - -If you want to add new seeds to a fuzzing campaign you can run a temporary -fuzzing instance, e.g. when your main fuzzer is using `-o out` and the new -seeds are in `newseeds/` directory: -``` -AFL_BENCH_JUST_ONE=1 AFL_FAST_CAL=1 afl-fuzz -i newseeds -o out -S newseeds -- ./target -``` - -#### f) Checking the coverage of the fuzzing - -The `paths found` value is a bad indicator for checking how good the coverage is. - -A better indicator - if you use default llvm instrumentation with at least -version 9 - is to use `afl-showmap` with the collect coverage option `-C` on -the output directory: -``` -$ afl-showmap -C -i out -o /dev/null -- ./target -params @@ -... -[*] Using SHARED MEMORY FUZZING feature. -[*] Target map size: 9960 -[+] Processed 7849 input files. -[+] Captured 4331 tuples (highest value 255, total values 67130596) in '/dev/nul -l'. -[+] A coverage of 4331 edges were achieved out of 9960 existing (43.48%) with 7849 input files. -``` -It is even better to check out the exact lines of code that have been reached - -and which have not been found so far. - -An "easy" helper script for this is [https://github.com/vanhauser-thc/afl-cov](https://github.com/vanhauser-thc/afl-cov), -just follow the README of that separate project. - -If you see that an important area or a feature has not been covered so far then -try to find an input that is able to reach that and start a new secondary in -that fuzzing campaign with that seed as input, let it run for a few minutes, -then terminate it. The main node will pick it up and make it available to the -other secondary nodes over time. Set `export AFL_NO_AFFINITY=1` or -`export AFL_TRY_AFFINITY=1` if you have no free core. - -Note that in nearly all cases you can never reach full coverage. A lot of -functionality is usually dependent on exclusive options that would need individual -fuzzing campaigns each with one of these options set. E.g. if you fuzz a library to -convert image formats and your target is the png to tiff API then you will not -touch any of the other library APIs and features. - -#### g) How long to fuzz a target? - -This is a difficult question. -Basically if no new path is found for a long time (e.g. for a day or a week) -then you can expect that your fuzzing won't be fruitful anymore. -However often this just means that you should switch out secondaries for -others, e.g. custom mutator modules, sync to very different fuzzers, etc. - -Keep the queue/ directory (for future fuzzings of the same or similar targets) -and use them to seed other good fuzzers like libfuzzer with the -entropic -switch or honggfuzz. - -#### h) Improve the speed! - - * Use [persistent mode](instrumentation/README.persistent_mode.md) (x2-x20 speed increase) - * If you do not use shmem persistent mode, use `AFL_TMPDIR` to point the input file on a tempfs location, see [docs/env_variables.md](docs/env_variables.md) - * Linux: Improve kernel performance: modify `/etc/default/grub`, set `GRUB_CMDLINE_LINUX_DEFAULT="ibpb=off ibrs=off kpti=off l1tf=off mds=off mitigations=off no_stf_barrier noibpb noibrs nopcid nopti nospec_store_bypass_disable nospectre_v1 nospectre_v2 pcid=off pti=off spec_store_bypass_disable=off spectre_v2=off stf_barrier=off"`; then `update-grub` and `reboot` (warning: makes the system more insecure) - you can also just run `sudo afl-persistent-config` - * Linux: Running on an `ext2` filesystem with `noatime` mount option will be a bit faster than on any other journaling filesystem - * Use your cores! [3.b) Using multiple cores/threads](#b-using-multiple-coresthreads) - * Run `sudo afl-system-config` before starting the first afl-fuzz instance after a reboot - -### The End - -Check out the [docs/FAQ](docs/FAQ.md) if it maybe answers your question (that -you might not even have known you had ;-) ). - -This is basically all you need to know to professionally run fuzzing campaigns. -If you want to know more, the rest of this README and the tons of texts in -[docs/](docs/) will have you covered. - -Note that there are also a lot of tools out there that help fuzzing with AFL++ -(some might be deprecated or unsupported): - -Speeding up fuzzing: - * [libfiowrapper](https://github.com/marekzmyslowski/libfiowrapper) - if the function you want to fuzz requires loading a file, this allows using the shared memory testcase feature :-) - recommended. - -Minimization of test cases: - * [afl-pytmin](https://github.com/ilsani/afl-pytmin) - a wrapper for afl-tmin that tries to speed up the process of minimization of a single test case by using many CPU cores. - * [afl-ddmin-mod](https://github.com/MarkusTeufelberger/afl-ddmin-mod) - a variation of afl-tmin based on the ddmin algorithm. - * [halfempty](https://github.com/googleprojectzero/halfempty) - is a fast utility for minimizing test cases by Tavis Ormandy based on parallelization. - -Distributed execution: - * [disfuzz-afl](https://github.com/MartijnB/disfuzz-afl) - distributed fuzzing for AFL. - * [AFLDFF](https://github.com/quantumvm/AFLDFF) - AFL distributed fuzzing framework. - * [afl-launch](https://github.com/bnagy/afl-launch) - a tool for the execution of many AFL instances. - * [afl-mothership](https://github.com/afl-mothership/afl-mothership) - management and execution of many synchronized AFL fuzzers on AWS cloud. - * [afl-in-the-cloud](https://github.com/abhisek/afl-in-the-cloud) - another script for running AFL in AWS. - -Deployment, management, monitoring, reporting - * [afl-utils](https://gitlab.com/rc0r/afl-utils) - a set of utilities for automatic processing/analysis of crashes and reducing the number of test cases. - * [afl-other-arch](https://github.com/shellphish/afl-other-arch) - is a set of patches and scripts for easily adding support for various non-x86 architectures for AFL. - * [afl-trivia](https://github.com/bnagy/afl-trivia) - a few small scripts to simplify the management of AFL. - * [afl-monitor](https://github.com/reflare/afl-monitor) - a script for monitoring AFL. - * [afl-manager](https://github.com/zx1340/afl-manager) - a web server on Python for managing multi-afl. - * [afl-remote](https://github.com/block8437/afl-remote) - a web server for the remote management of AFL instances. - * [afl-extras](https://github.com/fekir/afl-extras) - shell scripts to parallelize afl-tmin, startup, and data collection. - -Crash processing - * [afl-crash-analyzer](https://github.com/floyd-fuh/afl-crash-analyzer) - another crash analyzer for AFL. - * [fuzzer-utils](https://github.com/ThePatrickStar/fuzzer-utils) - a set of scripts for the analysis of results. - * [atriage](https://github.com/Ayrx/atriage) - a simple triage tool. - * [afl-kit](https://github.com/kcwu/afl-kit) - afl-cmin on Python. - * [AFLize](https://github.com/d33tah/aflize) - a tool that automatically generates builds of debian packages suitable for AFL. - * [afl-fid](https://github.com/FoRTE-Research/afl-fid) - a set of tools for working with input data. - -## CI Fuzzing - -Some notes on CI Fuzzing - this fuzzing is different to normal fuzzing -campaigns as these are much shorter runnings. - -1. Always: - * LTO has a much longer compile time which is diametrical to short fuzzing - - hence use afl-clang-fast instead. - * If you compile with CMPLOG then you can save fuzzing time and reuse that - compiled target for both the -c option and the main fuzz target. - This will impact the speed by ~15% though. - * `AFL_FAST_CAL` - Enable fast calibration, this halfs the time the saturated - corpus needs to be loaded. - * `AFL_CMPLOG_ONLY_NEW` - only perform cmplog on new found paths, not the - initial corpus as this very likely has been done for them already. - * Keep the generated corpus, use afl-cmin and reuse it every time! - -2. Additionally randomize the AFL++ compilation options, e.g. - * 40% for `AFL_LLVM_CMPLOG` - * 10% for `AFL_LLVM_LAF_ALL` - -3. Also randomize the afl-fuzz runtime options, e.g. - * 65% for `AFL_DISABLE_TRIM` - * 50% use a dictionary generated by `AFL_LLVM_DICT2FILE` - * 40% use MOpt (`-L 0`) - * 40% for `AFL_EXPAND_HAVOC_NOW` - * 20% for old queue processing (`-Z`) - * for CMPLOG targets, 60% for `-l 2`, 40% for `-l 3` - -4. Do *not* run any `-M` modes, just running `-S` modes is better for CI fuzzing. - `-M` enables old queue handling etc. which is good for a fuzzing campaign but - not good for short CI runs. - -How this can look like can e.g. be seen at AFL++'s setup in Google's [oss-fuzz](https://github.com/google/oss-fuzz/blob/master/infra/base-images/base-builder/compile_afl) -and [clusterfuzz](https://github.com/google/clusterfuzz/blob/master/src/python/bot/fuzzers/afl/launcher.py). - -## Fuzzing binary-only targets - -When source code is *NOT* available, AFL++ offers various support for fast, -on-the-fly instrumentation of black-box binaries. - -If you do not have to use Unicorn the following setup is recommended to use -qemu_mode: - * run 1 afl-fuzz -Q instance with CMPLOG (`-c 0` + `AFL_COMPCOV_LEVEL=2`) - * run 1 afl-fuzz -Q instance with QASAN (`AFL_USE_QASAN=1`) - * run 1 afl-fuzz -Q instance with LAF (`AFL_PRELOAD=libcmpcov.so` + `AFL_COMPCOV_LEVEL=2`) -Alternatively you can use frida_mode, just switch `-Q` with `-O` and remove the -LAF instance. - -Then run as many instances as you have cores left with either -Q mode or - better - -use a binary rewriter like afl-dyninst, retrowrite, zafl, etc. - -For Qemu and Frida mode, check out the persistent mode, it gives a huge speed -improvement if it is possible to use. - -### QEMU - -For linux programs and its libraries this is accomplished with a version of -QEMU running in the lesser-known "user space emulation" mode. -QEMU is a project separate from AFL, but you can conveniently build the -feature by doing: -```shell -cd qemu_mode -./build_qemu_support.sh -``` -For additional instructions and caveats, see [qemu_mode/README.md](qemu_mode/README.md). -If possible you should use the persistent mode, see [qemu_mode/README.persistent.md](qemu_mode/README.persistent.md). -The mode is approximately 2-5x slower than compile-time instrumentation, and is -less conducive to parallelization. - -If [afl-dyninst](https://github.com/vanhauser-thc/afl-dyninst) works for -your binary, then you can use afl-fuzz normally and it will have twice -the speed compared to qemu_mode (but slower than qemu persistent mode). -Note that several other binary rewriters exist, all with their advantages and -caveats. - -### Frida - -Frida mode is sometimes faster and sometimes slower than Qemu mode. -It is also newer, lacks COMPCOV, but supports MacOS. - -```shell -cd frida_mode -make -``` -For additional instructions and caveats, see [frida_mode/README.md](frida_mode/README.md). -If possible you should use the persistent mode, see [qemu_frida/README.persistent.md](qemu_frida/README.persistent.md). -The mode is approximately 2-5x slower than compile-time instrumentation, and is -less conducive to parallelization. - -### Unicorn - -For non-Linux binaries you can use AFL++'s unicorn mode which can emulate -anything you want - for the price of speed and user written scripts. -See [unicorn_mode](unicorn_mode/README.md). - -It can be easily built by: -```shell -cd unicorn_mode -./build_unicorn_support.sh -``` - -### Shared libraries - -If the goal is to fuzz a dynamic library then there are two options available. -For both you need to write a small harness that loads and calls the library. -Faster is the frida solution: [utils/afl_frida/README.md](utils/afl_frida/README.md) - -Another, less precise and slower option is using ptrace with debugger interrupt -instrumentation: [utils/afl_untracer/README.md](utils/afl_untracer/README.md). - -### More - -A more comprehensive description of these and other options can be found in -[docs/binaryonly_fuzzing.md](docs/binaryonly_fuzzing.md). - -## Challenges of guided fuzzing - -Fuzzing is one of the most powerful and proven strategies for identifying -security issues in real-world software; it is responsible for the vast -majority of remote code execution and privilege escalation bugs found to date -in security-critical software. - -Unfortunately, fuzzing is also relatively shallow; blind, random mutations -make it very unlikely to reach certain code paths in the tested code, leaving -some vulnerabilities firmly outside the reach of this technique. - -There have been numerous attempts to solve this problem. One of the early -approaches - pioneered by Tavis Ormandy - is corpus distillation. The method -relies on coverage signals to select a subset of interesting seeds from a -massive, high-quality corpus of candidate files, and then fuzz them by -traditional means. The approach works exceptionally well but requires such -a corpus to be readily available. In addition, block coverage measurements -provide only a very simplistic understanding of the program state and are less -useful for guiding the fuzzing effort in the long haul. - -Other, more sophisticated research has focused on techniques such as program -flow analysis ("concolic execution"), symbolic execution, or static analysis. -All these methods are extremely promising in experimental settings, but tend -to suffer from reliability and performance problems in practical uses - and -currently do not offer a viable alternative to "dumb" fuzzing techniques. - -## Background: The afl-fuzz approach - -American Fuzzy Lop is a brute-force fuzzer coupled with an exceedingly simple -but rock-solid instrumentation-guided genetic algorithm. It uses a modified -form of edge coverage to effortlessly pick up subtle, local-scale changes to -program control flow. - -Simplifying a bit, the overall algorithm can be summed up as: - - 1) Load user-supplied initial test cases into the queue, - - 2) Take the next input file from the queue, - - 3) Attempt to trim the test case to the smallest size that doesn't alter - the measured behavior of the program, - - 4) Repeatedly mutate the file using a balanced and well-researched variety - of traditional fuzzing strategies, - - 5) If any of the generated mutations resulted in a new state transition - recorded by the instrumentation, add mutated output as a new entry in the - queue. - - 6) Go to 2. - -The discovered test cases are also periodically culled to eliminate ones that -have been obsoleted by newer, higher-coverage finds; and undergo several other -instrumentation-driven effort minimization steps. - -As a side result of the fuzzing process, the tool creates a small, -self-contained corpus of interesting test cases. These are extremely useful -for seeding other, labor- or resource-intensive testing regimes - for example, -for stress-testing browsers, office applications, graphics suites, or -closed-source tools. - -The fuzzer is thoroughly tested to deliver out-of-the-box performance far -superior to blind fuzzing or coverage-only tools. - -## Help: Choosing initial test cases - -To operate correctly, the fuzzer requires one or more starting file that -contains a good example of the input data normally expected by the targeted -application. There are two basic rules: - - - Keep the files small. Under 1 kB is ideal, although not strictly necessary. - For a discussion of why size matters, see [perf_tips.md](docs/perf_tips.md). - - - Use multiple test cases only if they are functionally different from - each other. There is no point in using fifty different vacation photos - to fuzz an image library. - -You can find many good examples of starting files in the testcases/ subdirectory -that comes with this tool. - -PS. If a large corpus of data is available for screening, you may want to use -the afl-cmin utility to identify a subset of functionally distinct files that -exercise different code paths in the target binary. - -## Help: Interpreting output - -See the [docs/status_screen.md](docs/status_screen.md) file for information on -how to interpret the displayed stats and monitor the health of the process. Be -sure to consult this file especially if any UI elements are highlighted in red. - -The fuzzing process will continue until you press Ctrl-C. At a minimum, you want -to allow the fuzzer to complete one queue cycle, which may take anywhere from a -couple of hours to a week or so. - -There are three subdirectories created within the output directory and updated -in real-time: - - - queue/ - test cases for every distinctive execution path, plus all the - starting files given by the user. This is the synthesized corpus - mentioned in section 2. - - Before using this corpus for any other purposes, you can shrink - it to a smaller size using the afl-cmin tool. The tool will find - a smaller subset of files offering equivalent edge coverage. - - - crashes/ - unique test cases that cause the tested program to receive a - fatal signal (e.g., SIGSEGV, SIGILL, SIGABRT). The entries are - grouped by the received signal. - - - hangs/ - unique test cases that cause the tested program to time out. The - default time limit before something is classified as a hang is - the larger of 1 second and the value of the -t parameter. - The value can be fine-tuned by setting AFL_HANG_TMOUT, but this - is rarely necessary. - -Crashes and hangs are considered "unique" if the associated execution paths -involve any state transitions not seen in previously-recorded faults. If a -single bug can be reached in multiple ways, there will be some count inflation -early in the process, but this should quickly taper off. - -The file names for crashes and hangs are correlated with the parent, non-faulting -queue entries. This should help with debugging. - -When you can't reproduce a crash found by afl-fuzz, the most likely cause is -that you are not setting the same memory limit as used by the tool. Try: - -```shell -LIMIT_MB=50 -( ulimit -Sv $[LIMIT_MB << 10]; /path/to/tested_binary ... ) -``` - -Change LIMIT_MB to match the -m parameter passed to afl-fuzz. On OpenBSD, -also change -Sv to -Sd. - -Any existing output directory can be also used to resume aborted jobs; try: - -```shell -./afl-fuzz -i- -o existing_output_dir [...etc...] -``` - -If you have gnuplot installed, you can also generate some pretty graphs for any -active fuzzing task using afl-plot. For an example of how this looks like, -see [http://lcamtuf.coredump.cx/afl/plot/](http://lcamtuf.coredump.cx/afl/plot/). - -You can also manually build and install afl-plot-ui, which is a helper utility -for showing the graphs generated by afl-plot in a graphical window using GTK. -You can build and install it as follows - -```shell -sudo apt install libgtk-3-0 libgtk-3-dev pkg-config -cd utils/plot_ui -make -cd ../../ -sudo make install -``` - -## Help: Crash triage - -The coverage-based grouping of crashes usually produces a small data set that -can be quickly triaged manually or with a very simple GDB or Valgrind script. -Every crash is also traceable to its parent non-crashing test case in the -queue, making it easier to diagnose faults. - -Having said that, it's important to acknowledge that some fuzzing crashes can be -difficult to quickly evaluate for exploitability without a lot of debugging and -code analysis work. To assist with this task, afl-fuzz supports a very unique -"crash exploration" mode enabled with the -C flag. - -In this mode, the fuzzer takes one or more crashing test cases as the input -and uses its feedback-driven fuzzing strategies to very quickly enumerate all -code paths that can be reached in the program while keeping it in the -crashing state. - -Mutations that do not result in a crash are rejected; so are any changes that -do not affect the execution path. - -The output is a small corpus of files that can be very rapidly examined to see -what degree of control the attacker has over the faulting address, or whether -it is possible to get past an initial out-of-bounds read - and see what lies -beneath. - -Oh, one more thing: for test case minimization, give afl-tmin a try. The tool -can be operated in a very simple way: - -```shell -./afl-tmin -i test_case -o minimized_result -- /path/to/program [...] -``` - -The tool works with crashing and non-crashing test cases alike. In the crash -mode, it will happily accept instrumented and non-instrumented binaries. In the -non-crashing mode, the minimizer relies on standard AFL++ instrumentation to make -the file simpler without altering the execution path. - -The minimizer accepts the -m, -t, -f and @@ syntax in a manner compatible with -afl-fuzz. - -Another tool in AFL++ is the afl-analyze tool. It takes an input -file, attempts to sequentially flip bytes, and observes the behavior of the -tested program. It then color-codes the input based on which sections appear to -be critical, and which are not; while not bulletproof, it can often offer quick -insights into complex file formats. More info about its operation can be found -near the end of [docs/technical_details.md](docs/technical_details.md). - -## Going beyond crashes - -Fuzzing is a wonderful and underutilized technique for discovering non-crashing -design and implementation errors, too. Quite a few interesting bugs have been -found by modifying the target programs to call abort() when say: - - - Two bignum libraries produce different outputs when given the same - fuzzer-generated input, - - - An image library produces different outputs when asked to decode the same - input image several times in a row, - - - A serialization / deserialization library fails to produce stable outputs - when iteratively serializing and deserializing fuzzer-supplied data, - - - A compression library produces an output inconsistent with the input file - when asked to compress and then decompress a particular blob. - -Implementing these or similar sanity checks usually takes very little time; -if you are the maintainer of a particular package, you can make this code -conditional with `#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION` (a flag also -shared with libfuzzer and honggfuzz) or `#ifdef __AFL_COMPILER` (this one is -just for AFL). - -## Common-sense risks - -Please keep in mind that, similarly to many other computationally-intensive -tasks, fuzzing may put a strain on your hardware and on the OS. In particular: - - - Your CPU will run hot and will need adequate cooling. In most cases, if - cooling is insufficient or stops working properly, CPU speeds will be - automatically throttled. That said, especially when fuzzing on less - suitable hardware (laptops, smartphones, etc), it's not entirely impossible - for something to blow up. - - - Targeted programs may end up erratically grabbing gigabytes of memory or - filling up disk space with junk files. AFL++ tries to enforce basic memory - limits, but can't prevent each and every possible mishap. The bottom line - is that you shouldn't be fuzzing on systems where the prospect of data loss - is not an acceptable risk. - - - Fuzzing involves billions of reads and writes to the filesystem. On modern - systems, this will be usually heavily cached, resulting in fairly modest - "physical" I/O - but there are many factors that may alter this equation. - It is your responsibility to monitor for potential trouble; with very heavy - I/O, the lifespan of many HDDs and SSDs may be reduced. - - A good way to monitor disk I/O on Linux is the 'iostat' command: - -```shell - $ iostat -d 3 -x -k [...optional disk ID...] -``` - - Using the `AFL_TMPDIR` environment variable and a RAM-disk you can have the - heavy writing done in RAM to prevent the aforementioned wear and tear. For - example the following line will run a Docker container with all this preset: - - ```shell - # docker run -ti --mount type=tmpfs,destination=/ramdisk -e AFL_TMPDIR=/ramdisk aflplusplus/aflplusplus - ``` - -## Known limitations & areas for improvement - -Here are some of the most important caveats for AFL: - - - AFL++ detects faults by checking for the first spawned process dying due to - a signal (SIGSEGV, SIGABRT, etc). Programs that install custom handlers for - these signals may need to have the relevant code commented out. In the same - vein, faults in child processes spawned by the fuzzed target may evade - detection unless you manually add some code to catch that. - - - As with any other brute-force tool, the fuzzer offers limited coverage if - encryption, checksums, cryptographic signatures, or compression are used to - wholly wrap the actual data format to be tested. +## Contact - To work around this, you can comment out the relevant checks (see - utils/libpng_no_checksum/ for inspiration); if this is not possible, - you can also write a postprocessor, one of the hooks of custom mutators. - See [docs/custom_mutators.md](docs/custom_mutators.md) on how to use - `AFL_CUSTOM_MUTATOR_LIBRARY` +Questions? Concerns? Bug reports? - - There are some unfortunate trade-offs with ASAN and 64-bit binaries. This - isn't due to any specific fault of afl-fuzz. +* The contributors can be reached via + [https://github.com/AFLplusplus/AFLplusplus](https://github.com/AFLplusplus/AFLplusplus). +* Take a look at our [FAQ](docs/FAQ.md). If you find an interesting or + important question missing, submit it via + [https://github.com/AFLplusplus/AFLplusplus/discussions](https://github.com/AFLplusplus/AFLplusplus/discussions). +* There is a mailing list for the AFL/AFL++ project + ([browse archive](https://groups.google.com/group/afl-users)). To compare + notes with other users or to get notified about major new features, send an + email to <afl-users+subscribe@googlegroups.com>. +* Or join the [Awesome Fuzzing](https://discord.gg/gCraWct) Discord server. - - There is no direct support for fuzzing network services, background - daemons, or interactive apps that require UI interaction to work. You may - need to make simple code changes to make them behave in a more traditional - way. Preeny may offer a relatively simple option, too - see: - [https://github.com/zardus/preeny](https://github.com/zardus/preeny) +## Help wanted - Some useful tips for modifying network-based services can be also found at: - [https://www.fastly.com/blog/how-to-fuzz-server-american-fuzzy-lop](https://www.fastly.com/blog/how-to-fuzz-server-american-fuzzy-lop) +We have several [ideas](docs/ideas.md) we would like to see in AFL++ to make it +even better. However, we already work on so many things that we do not have the +time for all the big ideas. - - Occasionally, sentient machines rise against their creators. If this - happens to you, please consult [http://lcamtuf.coredump.cx/prep/](http://lcamtuf.coredump.cx/prep/). +This can be your way to support and contribute to AFL++ - extend it to do +something cool. -Beyond this, see INSTALL for platform-specific tips. +For everyone who wants to contribute (and send pull requests), please read our +[contributing guidelines](CONTRIBUTING.md) before your submit. ## Special thanks -Many of the improvements to the original AFL and AFL++ wouldn't be possible -without feedback, bug reports, or patches from: - -``` - Jann Horn Hanno Boeck - Felix Groebert Jakub Wilk - Richard W. M. Jones Alexander Cherepanov - Tom Ritter Hovik Manucharyan - Sebastian Roschke Eberhard Mattes - Padraig Brady Ben Laurie - @dronesec Luca Barbato - Tobias Ospelt Thomas Jarosch - Martin Carpenter Mudge Zatko - Joe Zbiciak Ryan Govostes - Michael Rash William Robinet - Jonathan Gray Filipe Cabecinhas - Nico Weber Jodie Cunningham - Andrew Griffiths Parker Thompson - Jonathan Neuschaefer Tyler Nighswander - Ben Nagy Samir Aguiar - Aidan Thornton Aleksandar Nikolich - Sam Hakim Laszlo Szekeres - David A. Wheeler Turo Lamminen - Andreas Stieger Richard Godbee - Louis Dassy teor2345 - Alex Moneger Dmitry Vyukov - Keegan McAllister Kostya Serebryany - Richo Healey Martijn Bogaard - rc0r Jonathan Foote - Christian Holler Dominique Pelle - Jacek Wielemborek Leo Barnes - Jeremy Barnes Jeff Trull - Guillaume Endignoux ilovezfs - Daniel Godas-Lopez Franjo Ivancic - Austin Seipp Daniel Komaromy - Daniel Binderman Jonathan Metzman - Vegard Nossum Jan Kneschke - Kurt Roeckx Marcel Boehme - Van-Thuan Pham Abhik Roychoudhury - Joshua J. Drake Toby Hutton - Rene Freingruber Sergey Davidoff - Sami Liedes Craig Young - Andrzej Jackowski Daniel Hodson - Nathan Voss Dominik Maier - Andrea Biondo Vincent Le Garrec - Khaled Yakdan Kuang-che Wu - Josephine Calliotte Konrad Welc - Thomas Rooijakkers David Carlier - Ruben ten Hove Joey Jiao - fuzzah -``` - -Thank you! -(For people sending pull requests - please add yourself to this list :-) +Many of the improvements to the original AFL and AFL++ wouldn't be possible +without feedback, bug reports, or patches from our contributors. + +Thank you! (For people sending pull requests - please add yourself to this list +:-) + +<details> + + <summary>List of contributors</summary> + + ``` + Jann Horn Hanno Boeck + Felix Groebert Jakub Wilk + Richard W. M. Jones Alexander Cherepanov + Tom Ritter Hovik Manucharyan + Sebastian Roschke Eberhard Mattes + Padraig Brady Ben Laurie + @dronesec Luca Barbato + Tobias Ospelt Thomas Jarosch + Martin Carpenter Mudge Zatko + Joe Zbiciak Ryan Govostes + Michael Rash William Robinet + Jonathan Gray Filipe Cabecinhas + Nico Weber Jodie Cunningham + Andrew Griffiths Parker Thompson + Jonathan Neuschaefer Tyler Nighswander + Ben Nagy Samir Aguiar + Aidan Thornton Aleksandar Nikolich + Sam Hakim Laszlo Szekeres + David A. Wheeler Turo Lamminen + Andreas Stieger Richard Godbee + Louis Dassy teor2345 + Alex Moneger Dmitry Vyukov + Keegan McAllister Kostya Serebryany + Richo Healey Martijn Bogaard + rc0r Jonathan Foote + Christian Holler Dominique Pelle + Jacek Wielemborek Leo Barnes + Jeremy Barnes Jeff Trull + Guillaume Endignoux ilovezfs + Daniel Godas-Lopez Franjo Ivancic + Austin Seipp Daniel Komaromy + Daniel Binderman Jonathan Metzman + Vegard Nossum Jan Kneschke + Kurt Roeckx Marcel Boehme + Van-Thuan Pham Abhik Roychoudhury + Joshua J. Drake Toby Hutton + Rene Freingruber Sergey Davidoff + Sami Liedes Craig Young + Andrzej Jackowski Daniel Hodson + Nathan Voss Dominik Maier + Andrea Biondo Vincent Le Garrec + Khaled Yakdan Kuang-che Wu + Josephine Calliotte Konrad Welc + Thomas Rooijakkers David Carlier + Ruben ten Hove Joey Jiao + fuzzah + ``` + +</details> ## Cite -If you use AFLpluplus to compare to your work, please use either `afl-clang-lto` -or `afl-clang-fast` with `AFL_LLVM_CMPLOG=1` for building targets and -`afl-fuzz` with the command line option `-l 2` for fuzzing. -The most effective setup is the `aflplusplus` default configuration on Google's [fuzzbench](https://github.com/google/fuzzbench/tree/master/fuzzers/aflplusplus). +If you use AFL++ in scientific work, consider citing +[our paper](https://www.usenix.org/conference/woot20/presentation/fioraldi) +presented at WOOT'20: -If you use AFLplusplus in scientific work, consider citing [our paper](https://www.usenix.org/conference/woot20/presentation/fioraldi) presented at WOOT'20: + Andrea Fioraldi, Dominik Maier, Heiko Eißfeldt, and Marc Heuse. “AFL++: Combining incremental steps of fuzzing research”. In 14th USENIX Workshop on Offensive Technologies (WOOT 20). USENIX Association, Aug. 2020. -+ Andrea Fioraldi, Dominik Maier, Heiko Eißfeldt, and Marc Heuse. “AFL++: Combining incremental steps of fuzzing research”. In 14th USENIX Workshop on Offensive Technologies (WOOT 20). USENIX Association, Aug. 2020. +<details> -Bibtex: - -```bibtex -@inproceedings {AFLplusplus-Woot20, - author = {Andrea Fioraldi and Dominik Maier and Heiko Ei{\ss}feldt and Marc Heuse}, - title = {{AFL++}: Combining Incremental Steps of Fuzzing Research}, - booktitle = {14th {USENIX} Workshop on Offensive Technologies ({WOOT} 20)}, - year = {2020}, - publisher = {{USENIX} Association}, - month = aug, -} -``` - -## Contact - -Questions? Concerns? Bug reports? The contributors can be reached via -[https://github.com/AFLplusplus/AFLplusplus](https://github.com/AFLplusplus/AFLplusplus) +<summary>BibTeX</summary> -There is also a mailing list for the AFL/AFL++ project; to join, send a mail to -<afl-users+subscribe@googlegroups.com>. Or, if you prefer to browse archives -first, try: [https://groups.google.com/group/afl-users](https://groups.google.com/group/afl-users) + ```bibtex + @inproceedings {AFLplusplus-Woot20, + author = {Andrea Fioraldi and Dominik Maier and Heiko Ei{\ss}feldt and Marc Heuse}, + title = {{AFL++}: Combining Incremental Steps of Fuzzing Research}, + booktitle = {14th {USENIX} Workshop on Offensive Technologies ({WOOT} 20)}, + year = {2020}, + publisher = {{USENIX} Association}, + month = aug, + } + ``` +</details> diff --git a/afl-system-config b/afl-system-config index dbdbbf1f..3c14ba55 100755 --- a/afl-system-config +++ b/afl-system-config @@ -52,7 +52,7 @@ if [ "$PLATFORM" = "Linux" ] ; then echo ' /etc/default/grub:GRUB_CMDLINE_LINUX_DEFAULT="ibpb=off ibrs=off kpti=0 l1tf=off mds=off mitigations=off no_stf_barrier noibpb noibrs nopcid nopti nospec_store_bypass_disable nospectre_v1 nospectre_v2 pcid=off pti=off spec_store_bypass_disable=off spectre_v2=off stf_barrier=off srbds=off noexec=off noexec32=off tsx=on tsx_async_abort=off arm64.nopauth audit=0 hardened_usercopy=off ssbd=force-off"' echo } - echo If you run fuzzing instances in docker, run them with \"--security-opt seccomp=unconfined\" for more speed + echo If you run fuzzing instances in docker, run them with \"--security-opt seccomp=unconfined\" for more speed. echo DONE=1 fi diff --git a/custom_mutators/grammar_mutator/grammar_mutator b/custom_mutators/grammar_mutator/grammar_mutator -Subproject eedf07ddb0fb1f437f5e76b77cfd4064cf6a5d6 +Subproject b79d51a8daccbd7a693f9b6765c81ead14f28e2 diff --git a/custom_mutators/libfuzzer/FuzzerLoop.cpp b/custom_mutators/libfuzzer/FuzzerLoop.cpp index 08fda520..6716dbf5 100644 --- a/custom_mutators/libfuzzer/FuzzerLoop.cpp +++ b/custom_mutators/libfuzzer/FuzzerLoop.cpp @@ -1086,6 +1086,7 @@ ATTRIBUTE_INTERFACE size_t LLVMFuzzerMutate(uint8_t *Data, size_t Size, size_t MaxSize) { assert(fuzzer::F); + fuzzer::F->GetMD().StartMutationSequence(); size_t r = fuzzer::F->GetMD().DefaultMutate(Data, Size, MaxSize); #ifdef INTROSPECTION introspection_ptr = fuzzer::F->GetMD().WriteMutationSequence(); diff --git a/custom_mutators/libfuzzer/libfuzzer.inc b/custom_mutators/libfuzzer/libfuzzer.inc index 01f21dbe..8c4bdbf6 100644 --- a/custom_mutators/libfuzzer/libfuzzer.inc +++ b/custom_mutators/libfuzzer/libfuzzer.inc @@ -2,7 +2,7 @@ extern "C" ATTRIBUTE_INTERFACE void LLVMFuzzerMyInit(int (*Callback)(const uint8_t *Data, size_t Size), unsigned int Seed) { - Random Rand(Seed); + auto *Rand = new Random(Seed); FuzzingOptions Options; Options.Verbosity = 3; Options.MaxLen = 1024000; @@ -30,7 +30,7 @@ LLVMFuzzerMyInit(int (*Callback)(const uint8_t *Data, size_t Size), unsigned int struct EntropicOptions Entropic; Entropic.Enabled = Options.Entropic; EF = new ExternalFunctions(); - auto *MD = new MutationDispatcher(Rand, Options); + auto *MD = new MutationDispatcher(*Rand, Options); auto *Corpus = new InputCorpus(Options.OutputCorpus, Entropic); auto *F = new Fuzzer(Callback, *Corpus, *MD, Options); } diff --git a/custom_mutators/symcc/symcc.c b/custom_mutators/symcc/symcc.c index 19218449..86f23343 100644 --- a/custom_mutators/symcc/symcc.c +++ b/custom_mutators/symcc/symcc.c @@ -129,7 +129,7 @@ uint8_t afl_custom_queue_new_entry(my_mutator_t * data, int pid = fork(); - if (pid == -1) return; + if (pid == -1) return 0; if (pid) { @@ -147,7 +147,7 @@ uint8_t afl_custom_queue_new_entry(my_mutator_t * data, if (r <= 0) { close(pipefd[1]); - return; + return 0; } diff --git a/docs/Changelog.md b/docs/Changelog.md index 0ffbef05..04b2fb2e 100644 --- a/docs/Changelog.md +++ b/docs/Changelog.md @@ -15,10 +15,19 @@ sending a mail to <afl-users+subscribe@googlegroups.com>. information on how to deal with instrumenting libraries - fix a regression introduced in 3.10 that resulted in less coverage being detected. thanks to Collin May for reporting! - + - fix -n dumb mode (nobody should use this) + - fix stability issue with LTO and cmplog + - better banner + - frida_mode: David Carlier added Android support :) + - afl-showmap, afl-tmin and afl-analyze: + - honor persistent mode for more speed. thanks to dloffre-snl for + reporting! + - fix bug where targets are not killed on timeouts + - Prevent accidently killing non-afl/fuzz services when aborting + afl-showmap and other tools. - afl-cc: - fix for shared linking on MacOS - - llvm and LTO mode verified to work with new llvm 14-dev + - llvm and LTO mode modified to work with new llvm 14-dev (again) - added the very good grammar mutator "GramaTron" to the custom_mutators - added optimin, a faster and better corpus minimizer by @@ -30,6 +39,7 @@ sending a mail to <afl-users+subscribe@googlegroups.com>. - fix AFL_PRELOAD issues on MacOS - removed utils/afl_frida because frida_mode/ is now so much better - added uninstall target to makefile (todo: update new readme!) + - removed indirections in rust callbacks for unicornafl ### Version ++3.14c (release) diff --git a/docs/FAQ.md b/docs/FAQ.md index 0e816062..68ca3bad 100644 --- a/docs/FAQ.md +++ b/docs/FAQ.md @@ -1,243 +1,153 @@ -# Frequently asked questions about AFL++ - -## Contents - - * [What is the difference between AFL and AFL++?](#what-is-the-difference-between-afl-and-afl) - * [I got a weird compile error from clang](#i-got-a-weird-compile-error-from-clang) - * [How to improve the fuzzing speed?](#how-to-improve-the-fuzzing-speed) - * [How do I fuzz a network service?](#how-do-i-fuzz-a-network-service) - * [How do I fuzz a GUI program?](#how-do-i-fuzz-a-gui-program) - * [What is an edge?](#what-is-an-edge) - * [Why is my stability below 100%?](#why-is-my-stability-below-100) - * [How can I improve the stability value?](#how-can-i-improve-the-stability-value) +# Frequently asked questions (FAQ) If you find an interesting or important question missing, submit it via -[https://github.com/AFLplusplus/AFLplusplus/issues](https://github.com/AFLplusplus/AFLplusplus/issues) - -## What is the difference between AFL and AFL++? - -American Fuzzy Lop (AFL) was developed by Michał "lcamtuf" Zalewski starting in -2013/2014, and when he left Google end of 2017 he stopped developing it. - -At the end of 2019 the Google fuzzing team took over maintenance of AFL, however -it is only accepting PRs from the community and is not developing enhancements -anymore. - -In the second quarter of 2019, 1 1/2 year later when no further development of -AFL had happened and it became clear there would none be coming, AFL++ -was born, where initially community patches were collected and applied -for bug fixes and enhancements. Then from various AFL spin-offs - mostly academic -research - features were integrated. This already resulted in a much advanced -AFL. - -Until the end of 2019 the AFL++ team had grown to four active developers which -then implemented their own research and features, making it now by far the most -flexible and feature rich guided fuzzer available as open source. -And in independent fuzzing benchmarks it is one of the best fuzzers available, -e.g. [Fuzzbench Report](https://www.fuzzbench.com/reports/2020-08-03/index.html) - -## I got a weird compile error from clang - -If you see this kind of error when trying to instrument a target with afl-cc/ -afl-clang-fast/afl-clang-lto: -``` -/prg/tmp/llvm-project/build/bin/clang-13: symbol lookup error: /usr/local/bin/../lib/afl//cmplog-instructions-pass.so: undefined symbol: _ZNK4llvm8TypeSizecvmEv -clang-13: error: unable to execute command: No such file or directory -clang-13: error: clang frontend command failed due to signal (use -v to see invocation) -clang version 13.0.0 (https://github.com/llvm/llvm-project 1d7cf550721c51030144f3cd295c5789d51c4aad) -Target: x86_64-unknown-linux-gnu -Thread model: posix -InstalledDir: /prg/tmp/llvm-project/build/bin -clang-13: note: diagnostic msg: -******************** -``` -Then this means that your OS updated the clang installation from an upgrade -package and because of that the AFL++ llvm plugins do not match anymore. - -Solution: `git pull ; make clean install` of AFL++ - -## How to improve the fuzzing speed? - - 1. Use [llvm_mode](../instrumentation/README.llvm.md): afl-clang-lto (llvm >= 11) or afl-clang-fast (llvm >= 9 recommended) - 2. Use [persistent mode](../instrumentation/README.persistent_mode.md) (x2-x20 speed increase) - 3. Use the [AFL++ snapshot module](https://github.com/AFLplusplus/AFL-Snapshot-LKM) (x2 speed increase) - 4. If you do not use shmem persistent mode, use `AFL_TMPDIR` to put the input file directory on a tempfs location, see [docs/env_variables.md](docs/env_variables.md) - 5. Improve Linux kernel performance: modify `/etc/default/grub`, set `GRUB_CMDLINE_LINUX_DEFAULT="ibpb=off ibrs=off kpti=off l1tf=off mds=off mitigations=off no_stf_barrier noibpb noibrs nopcid nopti nospec_store_bypass_disable nospectre_v1 nospectre_v2 pcid=off pti=off spec_store_bypass_disable=off spectre_v2=off stf_barrier=off"`; then `update-grub` and `reboot` (warning: makes the system less secure) - 6. Running on an `ext2` filesystem with `noatime` mount option will be a bit faster than on any other journaling filesystem - 7. Use your cores! [README.md:3.b) Using multiple cores/threads](../README.md#b-using-multiple-coresthreads) - -## How do I fuzz a network service? - -The short answer is - you cannot, at least not "out of the box". - -Using a network channel is inadequate for several reasons: -- it has a slow-down of x10-20 on the fuzzing speed -- it does not scale to fuzzing multiple instances easily, -- instead of one initial data packet often a back-and-forth interplay of packets is needed for stateful protocols (which is totally unsupported by most coverage aware fuzzers). - -The established method to fuzz network services is to modify the source code -to read from a file or stdin (fd 0) (or even faster via shared memory, combine -this with persistent mode [instrumentation/README.persistent_mode.md](../instrumentation/README.persistent_mode.md) -and you have a performance gain of x10 instead of a performance loss of over -x10 - that is a x100 difference!). - -If modifying the source is not an option (e.g. because you only have a binary -and perform binary fuzzing) you can also use a shared library with AFL_PRELOAD -to emulate the network. This is also much faster than the real network would be. -See [utils/socket_fuzzing/](../utils/socket_fuzzing/). - -There is an outdated AFL++ branch that implements networking if you are -desperate though: [https://github.com/AFLplusplus/AFLplusplus/tree/networking](https://github.com/AFLplusplus/AFLplusplus/tree/networking) - -however a better option is AFLnet ([https://github.com/aflnet/aflnet](https://github.com/aflnet/aflnet)) -which allows you to define network state with different type of data packets. - -## How do I fuzz a GUI program? - -If the GUI program can read the fuzz data from a file (via the command line, -a fixed location or via an environment variable) without needing any user -interaction then it would be suitable for fuzzing. - -Otherwise it is not possible without modifying the source code - which is a -very good idea anyway as the GUI functionality is a huge CPU/time overhead -for the fuzzing. - -So create a new `main()` that just reads the test case and calls the -functionality for processing the input that the GUI program is using. - -## What is an "edge"? - -A program contains `functions`, `functions` contain the compiled machine code. -The compiled machine code in a `function` can be in a single or many `basic blocks`. -A `basic block` is the largest possible number of subsequent machine code -instructions that has exactly one entrypoint (which can be be entered by multiple other basic blocks) -and runs linearly without branching or jumping to other addresses (except at the end). -``` -function() { - A: - some - code - B: - if (x) goto C; else goto D; - C: - some code - goto E - D: - some code - goto B - E: - return -} -``` -Every code block between two jump locations is a `basic block`. - -An `edge` is then the unique relationship between two directly connected `basic blocks` (from the -code example above): -``` - Block A - | +[https://github.com/AFLplusplus/AFLplusplus/discussions](https://github.com/AFLplusplus/AFLplusplus/discussions). + +## General + +<details> + <summary id="what-is-the-difference-between-afl-and-aflplusplus">What is the difference between AFL and AFL++?</summary><p> + + AFL++ is a superior fork to Google's AFL - more speed, more and better mutations, more and better instrumentation, custom module support, etc. + + American Fuzzy Lop (AFL) was developed by Michał "lcamtuf" Zalewski starting in 2013/2014, and when he left Google end of 2017 he stopped developing it. + + At the end of 2019, the Google fuzzing team took over maintenance of AFL, however it is only accepting PRs from the community and is not developing enhancements anymore. + + In the second quarter of 2019, 1 1/2 years later, when no further development of AFL had happened and it became clear there would none be coming, AFL++ was born, where initially community patches were collected and applied for bug fixes and enhancements. + Then from various AFL spin-offs - mostly academic research - features were integrated. + This already resulted in a much advanced AFL. + + Until the end of 2019, the AFL++ team had grown to four active developers which then implemented their own research and features, making it now by far the most flexible and feature rich guided fuzzer available as open source. + And in independent fuzzing benchmarks it is one of the best fuzzers available, e.g. [Fuzzbench Report](https://www.fuzzbench.com/reports/2020-08-03/index.html). +</p></details> + +<details> + <summary id="where-can-i-find-tutorials">Where can I find tutorials?</summary><p> + + We compiled a list of tutorials and exercises, see [tutorials.md](tutorials.md). +</p></details> + +<details> + <summary id="what-is-an-edge">What is an "edge"?</summary><p> + + A program contains `functions`, `functions` contain the compiled machine code. + The compiled machine code in a `function` can be in a single or many `basic blocks`. + A `basic block` is the largest possible number of subsequent machine code instructions that has exactly one entrypoint (which can be be entered by multiple other basic blocks) and runs linearly without branching or jumping to other addresses (except at the end). + + ``` + function() { + A: + some + code + B: + if (x) goto C; else goto D; + C: + some code + goto E + D: + some code + goto B + E: + return + } + ``` + + Every code block between two jump locations is a `basic block`. + + An `edge` is then the unique relationship between two directly connected `basic blocks` (from the code example above): + + ``` + Block A + | + v + Block B <------+ + / \ | + v v | + Block C Block D --+ + \ v - Block B <------+ - / \ | - v v | - Block C Block D --+ - \ - v - Block E -``` -Every line between two blocks is an `edge`. -Note that a few basic block loop to itself, this too would be an edge. - -## Why is my stability below 100%? - -Stability is measured by how many percent of the edges in the target are -"stable". Sending the same input again and again should take the exact same -path through the target every time. If that is the case, the stability is 100%. - -If however randomness happens, e.g. a thread reading other external data, -reaction to timing, etc. then in some of the re-executions with the same data -the edge coverage result will be different accross runs. -Those edges that change are then flagged "unstable". - -The more "unstable" edges, the more difficult for AFL++ to identify valid new -paths. - -A value above 90% is usually fine and a value above 80% is also still ok, and -even a value above 20% can still result in successful finds of bugs. -However, it is recommended that for values below 90% or 80% you should take -countermeasures to improve stability. - -## How can I improve the stability value? - -For fuzzing a 100% stable target that covers all edges is the best case. -A 90% stable target that covers all edges is however better than a 100% stable -target that ignores 10% of the edges. - -With instability you basically have a partial coverage loss on an edge, with -ignored functions you have a full loss on that edges. - -There are functions that are unstable, but also provide value to coverage, eg -init functions that use fuzz data as input for example. -If however a function that has nothing to do with the input data is the -source of instability, e.g. checking jitter, or is a hash map function etc. -then it should not be instrumented. - -To be able to exclude these functions (based on AFL++'s measured stability) -the following process will allow to identify functions with variable edges. - -Four steps are required to do this and it also requires quite some knowledge -of coding and/or disassembly and is effectively possible only with -afl-clang-fast PCGUARD and afl-clang-lto LTO instrumentation. - - 1. First step: Instrument to be able to find the responsible function(s). - - a) For LTO instrumented binaries this can be documented during compile - time, just set `export AFL_LLVM_DOCUMENT_IDS=/path/to/a/file`. - This file will have one assigned edge ID and the corresponding - function per line. - - b) For PCGUARD instrumented binaries it is much more difficult. Here you - can either modify the __sanitizer_cov_trace_pc_guard function in - instrumentation/afl-llvm-rt.o.c to write a backtrace to a file if the ID in - __afl_area_ptr[*guard] is one of the unstable edge IDs. - (Example code is already there). - Then recompile and reinstall llvm_mode and rebuild your target. - Run the recompiled target with afl-fuzz for a while and then check the - file that you wrote with the backtrace information. - Alternatively you can use `gdb` to hook __sanitizer_cov_trace_pc_guard_init - on start, check to which memory address the edge ID value is written - and set a write breakpoint to that address (`watch 0x.....`). - - c) in all other instrumentation types this is not possible. So just - recompile with the two mentioned above. This is just for - identifying the functions that have unstable edges. - - 2. Second step: Identify which edge ID numbers are unstable - - run the target with `export AFL_DEBUG=1` for a few minutes then terminate. - The out/fuzzer_stats file will then show the edge IDs that were identified - as unstable in the `var_bytes` entry. You can match these numbers - directly to the data you created in the first step. - Now you know which functions are responsible for the instability - - 3. Third step: create a text file with the filenames/functions - - Identify which source code files contain the functions that you need to - remove from instrumentation, or just specify the functions you want to - skip for instrumentation. Note that optimization might inline functions! - - Simply follow this document on how to do this: [instrumentation/README.instrument_list.md](../instrumentation/README.instrument_list.md) - If PCGUARD is used, then you need to follow this guide (needs llvm 12+!): - [http://clang.llvm.org/docs/SanitizerCoverage.html#partially-disabling-instrumentation](http://clang.llvm.org/docs/SanitizerCoverage.html#partially-disabling-instrumentation) - - Only exclude those functions from instrumentation that provide no value - for coverage - that is if it does not process any fuzz data directly - or indirectly (e.g. hash maps, thread management etc.). - If however a function directly or indirectly handles fuzz data then you - should not put the function in a deny instrumentation list and rather - live with the instability it comes with. - - 4. Fourth step: recompile the target - - Recompile, fuzz it, be happy :) - - This link explains this process for [Fuzzbench](https://github.com/google/fuzzbench/issues/677) + Block E + ``` + + Every line between two blocks is an `edge`. + Note that a few basic block loop to itself, this too would be an edge. +</p></details> + +## Targets + +<details> + <summary id="how-can-i-fuzz-a-binary-only-target">How can I fuzz a binary-only target?</summary><p> + + AFL++ is a great fuzzer if you have the source code available. + + However, if there is only the binary program and no source code available, then the standard non-instrumented mode is not effective. + + To learn how these binaries can be fuzzed, read [binaryonly_fuzzing.md](binaryonly_fuzzing.md). +</p></details> + +<details> + <summary id="how-can-i-fuzz-a-network-service">How can I fuzz a network service?</summary><p> + + The short answer is - you cannot, at least not "out of the box". + + For more information on fuzzing network services, see [best_practices.md#fuzzing-a-network-service](best_practices.md#fuzzing-a-network-service). +</p></details> + +<details> + <summary id="how-can-i-fuzz-a-gui-program">How can I fuzz a GUI program?</summary><p> + + Not all GUI programs are suitable for fuzzing. If the GUI program can read the fuzz data from a file without needing any user interaction, then it would be suitable for fuzzing. + + For more information on fuzzing GUI programs, see [best_practices.md#fuzzing-a-gui-program](best_practices.md#fuzzing-a-gui-program). +</p></details> + +## Performance + +<details> + <summary id="how-can-i-improve-the-fuzzing-speed">How can I improve the fuzzing speed?</summary><p> + + There are a few things you can do to improve the fuzzing speed, see [best_practices.md#improving-speed](best_practices.md#improving-speed). +</p></details> + +<details> + <summary id="why-is-my-stability-below-100percent">Why is my stability below 100%?</summary><p> + + Stability is measured by how many percent of the edges in the target are "stable". + Sending the same input again and again should take the exact same path through the target every time. + If that is the case, the stability is 100%. + + If however randomness happens, e.g. a thread reading other external data, reaction to timing, etc., then in some of the re-executions with the same data the edge coverage result will be different accross runs. + Those edges that change are then flagged "unstable". + + The more "unstable" edges, the more difficult for AFL++ to identify valid new paths. + + A value above 90% is usually fine and a value above 80% is also still ok, and even a value above 20% can still result in successful finds of bugs. + However, it is recommended that for values below 90% or 80% you should take countermeasures to improve stability. + + For more information on stability and how to improve the stability value, see [best_practices.md#improving-stability](best_practices.md#improving-stability). +</p></details> + +## Troubleshooting + +<details> + <summary id="i-got-a-weird-compile-error-from-clang">I got a weird compile error from clang.</summary><p> + + If you see this kind of error when trying to instrument a target with afl-cc/afl-clang-fast/afl-clang-lto: + + ``` + /prg/tmp/llvm-project/build/bin/clang-13: symbol lookup error: /usr/local/bin/../lib/afl//cmplog-instructions-pass.so: undefined symbol: _ZNK4llvm8TypeSizecvmEv + clang-13: error: unable to execute command: No such file or directory + clang-13: error: clang frontend command failed due to signal (use -v to see invocation) + clang version 13.0.0 (https://github.com/llvm/llvm-project 1d7cf550721c51030144f3cd295c5789d51c4aad) + Target: x86_64-unknown-linux-gnu + Thread model: posix + InstalledDir: /prg/tmp/llvm-project/build/bin + clang-13: note: diagnostic msg: + ******************** + ``` + + Then this means that your OS updated the clang installation from an upgrade package and because of that the AFL++ llvm plugins do not match anymore. + + Solution: `git pull ; make clean install` of AFL++. +</p></details> \ No newline at end of file diff --git a/docs/INSTALL.md b/docs/INSTALL.md index 17af532a..960de1af 100644 --- a/docs/INSTALL.md +++ b/docs/INSTALL.md @@ -1,83 +1,89 @@ -# Installation instructions +# Building and installing AFL++ - This document provides basic installation instructions and discusses known - issues for a variety of platforms. See README.md for the general instruction - manual. +## Linux on x86 -## 1. Linux on x86 ---------------- +An easy way to install AFL++ with everything compiled is available via docker: +You can use the [Dockerfile](../Dockerfile) (which has gcc-10 and clang-11 - hence afl-clang-lto is available!) or just pull directly from the Docker Hub: -This platform is expected to work well. Compile the program with: - -```bash -make +```shell +docker pull aflplusplus/aflplusplus +docker run -ti -v /location/of/your/target:/src aflplusplus/aflplusplus ``` -You can start using the fuzzer without installation, but it is also possible to -install it with: - -```bash +This image is automatically generated when a push to the stable repo happens. +You will find your target source code in /src in the container. + +If you want to build AFL++ yourself, you have many options. +The easiest choice is to build and install everything: + +```shell +sudo apt-get update +sudo apt-get install -y build-essential python3-dev automake git flex bison libglib2.0-dev libpixman-1-dev python3-setuptools +# try to install llvm 11 and install the distro default if that fails +sudo apt-get install -y lld-11 llvm-11 llvm-11-dev clang-11 || sudo apt-get install -y lld llvm llvm-dev clang +sudo apt-get install -y gcc-$(gcc --version|head -n1|sed 's/.* //'|sed 's/\..*//')-plugin-dev libstdc++-$(gcc --version|head -n1|sed 's/.* //'|sed 's/\..*//')-dev +sudo apt-get install -y ninja-build # for qemu_mode +git clone https://github.com/AFLplusplus/AFLplusplus +cd AFLplusplus +make distrib sudo make install ``` -There are no special dependencies to speak of; you will need GNU make and a -working compiler (gcc or clang). Some of the optional scripts bundled with the -program may depend on bash, gdb, and similar basic tools. - -If you are using clang, please review README.llvm.md; the LLVM -integration mode can offer substantial performance gains compared to the -traditional approach. +It is recommended to install the newest available gcc, clang and llvm-dev possible in your distribution! -Likewise, if you are using GCC, please review instrumentation/README.gcc_plugin.md. +Note that "make distrib" also builds instrumentation, qemu_mode, unicorn_mode and more. +If you just want plain AFL++, then do "make all". However, compiling and using at least instrumentation is highly recommended for much better results - hence in this case choose: -You may have to change several settings to get optimal results (most notably, -disable crash reporting utilities and switch to a different CPU governor), but -afl-fuzz will guide you through that if necessary. - -## 2. OpenBSD, FreeBSD, NetBSD on x86 - -Similarly to Linux, these platforms are expected to work well and are -regularly tested. Compile everything with GNU make: - -```bash -gmake +```shell +make source-only ``` -Note that BSD make will *not* work; if you do not have gmake on your system, -please install it first. As on Linux, you can use the fuzzer itself without -installation, or install it with: - -``` -sudo gmake install +These build targets exist: + +* all: just the main AFL++ binaries +* binary-only: everything for binary-only fuzzing: qemu_mode, unicorn_mode, libdislocator, libtokencap +* source-only: everything for source code fuzzing: instrumentation, libdislocator, libtokencap +* distrib: everything (for both binary-only and source code fuzzing) +* man: creates simple man pages from the help option of the programs +* install: installs everything you have compiled with the build options above +* clean: cleans everything compiled, not downloads (unless not on a checkout) +* deepclean: cleans everything including downloads +* code-format: format the code, do this before you commit and send a PR please! +* tests: runs test cases to ensure that all features are still working as they should +* unit: perform unit tests (based on cmocka) +* help: shows these build options + +[Unless you are on Mac OS X](https://developer.apple.com/library/archive/qa/qa1118/_index.html), you can also build statically linked versions of the AFL++ binaries by passing the `STATIC=1` argument to make: + +```shell +make STATIC=1 ``` -Keep in mind that if you are using csh as your shell, the syntax of some of the -shell commands given in the README.md and other docs will be different. - -The `llvm` requires a dynamically linked, fully-operational installation of -clang. At least on FreeBSD, the clang binaries are static and do not include -some of the essential tools, so if you want to make it work, you may need to -follow the instructions in README.llvm.md. +These build options exist: -Beyond that, everything should work as advertised. +* STATIC - compile AFL++ static +* ASAN_BUILD - compiles with memory sanitizer for debug purposes +* DEBUG - no optimization, -ggdb3, all warnings and -Werror +* PROFILING - compile with profiling information (gprof) +* INTROSPECTION - compile afl-fuzz with mutation introspection +* NO_PYTHON - disable python support +* NO_SPLICING - disables splicing mutation in afl-fuzz, not recommended for normal fuzzing +* AFL_NO_X86 - if compiling on non-intel/amd platforms +* LLVM_CONFIG - if your distro doesn't use the standard name for llvm-config (e.g. Debian) -The QEMU mode is currently supported only on Linux. I think it's just a QEMU -problem, I couldn't get a vanilla copy of user-mode emulation support working -correctly on BSD at all. +e.g.: `make ASAN_BUILD=1` -## 3. MacOS X on x86 and arm64 (M1) +## MacOS X on x86 and arm64 (M1) -MacOS X should work, but there are some gotchas due to the idiosyncrasies of -the platform. On top of this, I have limited release testing capabilities -and depend mostly on user feedback. +MacOS X should work, but there are some gotchas due to the idiosyncrasies of the platform. +On top of this, we have limited release testing capabilities and depend mostly on user feedback. -To build AFL, install llvm (and perhaps gcc) from brew and follow the general -instructions for Linux. If possible avoid Xcode at all cost. +To build AFL, install llvm (and perhaps gcc) from brew and follow the general instructions for Linux. +If possible, avoid Xcode at all cost. `brew install wget git make cmake llvm gdb` -Be sure to setup PATH to point to the correct clang binaries and use the -freshly installed clang, clang++ and gmake, e.g.: +Be sure to setup `PATH` to point to the correct clang binaries and use the freshly installed clang, clang++ and gmake, e.g.: ``` export PATH="/usr/local/Cellar/llvm/12.0.1/bin/:$PATH" @@ -90,19 +96,20 @@ cd .. gmake install ``` -afl-gcc will fail unless you have GCC installed, but that is using outdated -instrumentation anyway. You don't want that. -Note that afl-clang-lto, afl-gcc-fast and qemu_mode are not working on MacOS. +`afl-gcc` will fail unless you have GCC installed, but that is using outdated instrumentation anyway. +You don't want that. +Note that `afl-clang-lto`, `afl-gcc-fast` and `qemu_mode` are not working on MacOS. + +The crash reporting daemon that comes by default with MacOS X will cause problems with fuzzing. +You need to turn it off: -The crash reporting daemon that comes by default with MacOS X will cause -problems with fuzzing. You need to turn it off: ``` launchctl unload -w /System/Library/LaunchAgents/com.apple.ReportCrash.plist sudo launchctl unload -w /System/Library/LaunchDaemons/com.apple.ReportCrash.Root.plist ``` -The `fork()` semantics on OS X are a bit unusual compared to other unix systems -and definitely don't look POSIX-compliant. This means two things: +The `fork()` semantics on OS X are a bit unusual compared to other unix systems and definitely don't look POSIX-compliant. +This means two things: - Fuzzing will be probably slower than on Linux. In fact, some folks report considerable performance gains by running the jobs inside a Linux VM on @@ -111,13 +118,11 @@ and definitely don't look POSIX-compliant. This means two things: AFL forkserver. If you run into any problems, set `AFL_NO_FORKSRV=1` in the environment before starting afl-fuzz. -User emulation mode of QEMU does not appear to be supported on MacOS X, so -black-box instrumentation mode (`-Q`) will not work. -However Frida mode (`-O`) should work on x86 and arm64 MacOS boxes. +User emulation mode of QEMU does not appear to be supported on MacOS X, so black-box instrumentation mode (`-Q`) will not work. +However, Frida mode (`-O`) should work on x86 and arm64 MacOS boxes. -MacOS X supports SYSV shared memory used by AFL's instrumentation, but the -default settings aren't usable with AFL++. The default settings on 10.14 seem -to be: +MacOS X supports SYSV shared memory used by AFL's instrumentation, but the default settings aren't usable with AFL++. +The default settings on 10.14 seem to be: ```bash $ ipcs -M @@ -130,16 +135,14 @@ shminfo: shmall: 1024 (max amount of shared memory in pages) ``` -To temporarily change your settings to something minimally usable with AFL++, -run these commands as root: +To temporarily change your settings to something minimally usable with AFL++, run these commands as root: ```bash sysctl kern.sysv.shmmax=8388608 sysctl kern.sysv.shmall=4096 ``` -If you're running more than one instance of AFL you likely want to make `shmall` -bigger and increase `shmseg` as well: +If you're running more than one instance of AFL, you likely want to make `shmall` bigger and increase `shmseg` as well: ```bash sysctl kern.sysv.shmmax=8388608 @@ -147,91 +150,4 @@ sysctl kern.sysv.shmseg=48 sysctl kern.sysv.shmall=98304 ``` -See http://www.spy-hill.com/help/apple/SharedMemory.html for documentation for -these settings and how to make them permanent. - -## 4. Linux or *BSD on non-x86 systems - -Standard build will fail on non-x86 systems, but you should be able to -leverage two other options: - - - The LLVM mode (see README.llvm.md), which does not rely on - x86-specific assembly shims. It's fast and robust, but requires a - complete installation of clang. - - The QEMU mode (see qemu_mode/README.md), which can be also used for - fuzzing cross-platform binaries. It's slower and more fragile, but - can be used even when you don't have the source for the tested app. - -If you're not sure what you need, you need the LLVM mode, which is built by -default. - -...and compile your target program with afl-clang-fast or afl-clang-fast++ -instead of the traditional afl-gcc or afl-clang wrappers. - -## 5. Solaris on x86 - -The fuzzer reportedly works on Solaris, but I have not tested this first-hand, -and the user base is fairly small, so I don't have a lot of feedback. - -To get the ball rolling, you will need to use GNU make and GCC or clang. I'm -being told that the stock version of GCC that comes with the platform does not -work properly due to its reliance on a hardcoded location for 'as' (completely -ignoring the `-B` parameter or `$PATH`). - -To fix this, you may want to build stock GCC from the source, like so: - -```sh -./configure --prefix=$HOME/gcc --with-gnu-as --with-gnu-ld \ - --with-gmp-include=/usr/include/gmp --with-mpfr-include=/usr/include/mpfr -make -sudo make install -``` - -Do *not* specify `--with-as=/usr/gnu/bin/as` - this will produce a GCC binary that -ignores the `-B` flag and you will be back to square one. - -Note that Solaris reportedly comes with crash reporting enabled, which causes -problems with crashes being misinterpreted as hangs, similarly to the gotchas -for Linux and MacOS X. AFL does not auto-detect crash reporting on this -particular platform, but you may need to run the following command: - -```sh -coreadm -d global -d global-setid -d process -d proc-setid \ - -d kzone -d log -``` - -User emulation mode of QEMU is not available on Solaris, so black-box -instrumentation mode (`-Q`) will not work. - -## 6. Everything else - -You're on your own. On POSIX-compliant systems, you may be able to compile and -run the fuzzer; and the LLVM and GCC plugin modes may offer a way to instrument -non-x86 code. - -The fuzzer will run on Windows in WSL only. It will not work under Cygwin on in the normal Windows world. It -could be ported to the latter platform fairly easily, but it's a pretty bad -idea, because Cygwin is extremely slow. It makes much more sense to use -VirtualBox or so to run a hardware-accelerated Linux VM; it will run around -20x faster or so. If you have a *really* compelling use case for Cygwin, let -me know. - -Although Android on x86 should theoretically work, the stock kernel may have -SHM support compiled out, and if so, you may have to address that issue first. -It's possible that all you need is this workaround: - - https://github.com/pelya/android-shmem - -Joshua J. Drake notes that the Android linker adds a shim that automatically -intercepts `SIGSEGV` and related signals. To fix this issue and be able to see -crashes, you need to put this at the beginning of the fuzzed program: - -```sh - signal(SIGILL, SIG_DFL); - signal(SIGABRT, SIG_DFL); - signal(SIGBUS, SIG_DFL); - signal(SIGFPE, SIG_DFL); - signal(SIGSEGV, SIG_DFL); -``` - -You may need to `#include <signal.h>` first. +See [http://www.spy-hill.com/help/apple/SharedMemory.html](http://www.spy-hill.com/help/apple/SharedMemory.html) for documentation for these settings and how to make them permanent. \ No newline at end of file diff --git a/docs/QuickStartGuide.md b/docs/QuickStartGuide.md deleted file mode 100644 index 2d056ecf..00000000 --- a/docs/QuickStartGuide.md +++ /dev/null @@ -1,50 +0,0 @@ -# AFL quick start guide - -You should read [README.md](../README.md) - it's pretty short. If you really can't, here's -how to hit the ground running: - -1) Compile AFL with 'make'. If build fails, see [INSTALL.md](INSTALL.md) for tips. - -2) Find or write a reasonably fast and simple program that takes data from - a file or stdin, processes it in a test-worthy way, then exits cleanly. - If testing a network service, modify it to run in the foreground and read - from stdin. When fuzzing a format that uses checksums, comment out the - checksum verification code, too. - - If this is not possible (e.g. in -Q(emu) mode) then use - AFL_CUSTOM_MUTATOR_LIBRARY to calculate the values with your own library. - - The program must crash properly when a fault is encountered. Watch out for - custom SIGSEGV or SIGABRT handlers and background processes. For tips on - detecting non-crashing flaws, see section 11 in [README.md](README.md) . - -3) Compile the program / library to be fuzzed using afl-cc. A common way to - do this would be: - - CC=/path/to/afl-cc CXX=/path/to/afl-c++ ./configure --disable-shared - make clean all - -4) Get a small but valid input file that makes sense to the program. When - fuzzing verbose syntax (SQL, HTTP, etc), create a dictionary as described in - dictionaries/README.md, too. - -5) If the program reads from stdin, run 'afl-fuzz' like so: - - ./afl-fuzz -i testcase_dir -o findings_dir -- \ - /path/to/tested/program [...program's cmdline...] - - If the program takes input from a file, you can put @@ in the program's - command line; AFL will put an auto-generated file name in there for you. - -6) Investigate anything shown in red in the fuzzer UI by promptly consulting - [status_screen.md](status_screen.md). - -8) There is a basic docker build with 'docker build -t aflplusplus .' - -That's it. Sit back, relax, and - time permitting - try to skim through the -following files: - - - README.md - A general introduction to AFL, - - docs/perf_tips.md - Simple tips on how to fuzz more quickly, - - docs/status_screen.md - An explanation of the tidbits shown in the UI, - - docs/parallel_fuzzing.md - Advice on running AFL on multiple cores. diff --git a/docs/afl-fuzz_approach.md b/docs/afl-fuzz_approach.md new file mode 100644 index 00000000..5652816b --- /dev/null +++ b/docs/afl-fuzz_approach.md @@ -0,0 +1,37 @@ +# The afl-fuzz approach + +American Fuzzy Lop is a brute-force fuzzer coupled with an exceedingly simple +but rock-solid instrumentation-guided genetic algorithm. It uses a modified +form of edge coverage to effortlessly pick up subtle, local-scale changes to +program control flow. + +Simplifying a bit, the overall algorithm can be summed up as: + + 1) Load user-supplied initial test cases into the queue, + + 2) Take the next input file from the queue, + + 3) Attempt to trim the test case to the smallest size that doesn't alter + the measured behavior of the program, + + 4) Repeatedly mutate the file using a balanced and well-researched variety + of traditional fuzzing strategies, + + 5) If any of the generated mutations resulted in a new state transition + recorded by the instrumentation, add mutated output as a new entry in the + queue. + + 6) Go to 2. + +The discovered test cases are also periodically culled to eliminate ones that +have been obsoleted by newer, higher-coverage finds; and undergo several other +instrumentation-driven effort minimization steps. + +As a side result of the fuzzing process, the tool creates a small, +self-contained corpus of interesting test cases. These are extremely useful +for seeding other, labor- or resource-intensive testing regimes - for example, +for stress-testing browsers, office applications, graphics suites, or +closed-source tools. + +The fuzzer is thoroughly tested to deliver out-of-the-box performance far +superior to blind fuzzing or coverage-only tools. \ No newline at end of file diff --git a/docs/best_practices.md b/docs/best_practices.md new file mode 100644 index 00000000..0708d49d --- /dev/null +++ b/docs/best_practices.md @@ -0,0 +1,120 @@ +# Best practices + +## Contents + +### Targets + + * [Fuzzing a binary-only target](#fuzzing-a-binary-only-target) + * [Fuzzing a GUI program](#fuzzing-a-gui-program) + * [Fuzzing a network service](#fuzzing-a-network-service) + +### Improvements + + * [Improving speed](#improving-speed) + * [Improving stability](#improving-stability) + +## Targets + +### Fuzzing a binary-only target + +For a comprehensive guide, see [binaryonly_fuzzing.md](binaryonly_fuzzing.md). + +### Fuzzing a GUI program + +If the GUI program can read the fuzz data from a file (via the command line, a fixed location or via an environment variable) without needing any user interaction, then it would be suitable for fuzzing. + +Otherwise, it is not possible without modifying the source code - which is a very good idea anyway as the GUI functionality is a huge CPU/time overhead for the fuzzing. + +So create a new `main()` that just reads the test case and calls the functionality for processing the input that the GUI program is using. + +### Fuzzing a network service + +Fuzzing a network service does not work "out of the box". + +Using a network channel is inadequate for several reasons: +- it has a slow-down of x10-20 on the fuzzing speed +- it does not scale to fuzzing multiple instances easily, +- instead of one initial data packet often a back-and-forth interplay of packets is needed for stateful protocols (which is totally unsupported by most coverage aware fuzzers). + +The established method to fuzz network services is to modify the source code +to read from a file or stdin (fd 0) (or even faster via shared memory, combine +this with persistent mode [instrumentation/README.persistent_mode.md](../instrumentation/README.persistent_mode.md) +and you have a performance gain of x10 instead of a performance loss of over +x10 - that is a x100 difference!). + +If modifying the source is not an option (e.g. because you only have a binary +and perform binary fuzzing) you can also use a shared library with AFL_PRELOAD +to emulate the network. This is also much faster than the real network would be. +See [utils/socket_fuzzing/](../utils/socket_fuzzing/). + +There is an outdated AFL++ branch that implements networking if you are +desperate though: [https://github.com/AFLplusplus/AFLplusplus/tree/networking](https://github.com/AFLplusplus/AFLplusplus/tree/networking) - +however a better option is AFLnet ([https://github.com/aflnet/aflnet](https://github.com/aflnet/aflnet)) +which allows you to define network state with different type of data packets. + +## Improvements + +### Improving speed + +1. Use [llvm_mode](../instrumentation/README.llvm.md): afl-clang-lto (llvm >= 11) or afl-clang-fast (llvm >= 9 recommended). +2. Use [persistent mode](../instrumentation/README.persistent_mode.md) (x2-x20 speed increase). +3. Use the [AFL++ snapshot module](https://github.com/AFLplusplus/AFL-Snapshot-LKM) (x2 speed increase). +4. If you do not use shmem persistent mode, use `AFL_TMPDIR` to put the input file directory on a tempfs location, see [env_variables.md](env_variables.md). +5. Improve Linux kernel performance: modify `/etc/default/grub`, set `GRUB_CMDLINE_LINUX_DEFAULT="ibpb=off ibrs=off kpti=off l1tf=off mds=off mitigations=off no_stf_barrier noibpb noibrs nopcid nopti nospec_store_bypass_disable nospectre_v1 nospectre_v2 pcid=off pti=off spec_store_bypass_disable=off spectre_v2=off stf_barrier=off"`; then `update-grub` and `reboot` (warning: makes the system less secure). +6. Running on an `ext2` filesystem with `noatime` mount option will be a bit faster than on any other journaling filesystem. +7. Use your cores! [fuzzing_expert.md:b) Using multiple cores](fuzzing_expert.md#b-using-multiple-cores). + +### Improving stability + +For fuzzing a 100% stable target that covers all edges is the best case. +A 90% stable target that covers all edges is however better than a 100% stable target that ignores 10% of the edges. + +With instability, you basically have a partial coverage loss on an edge, with ignored functions you have a full loss on that edges. + +There are functions that are unstable, but also provide value to coverage, e.g., init functions that use fuzz data as input. +If however a function that has nothing to do with the input data is the source of instability, e.g., checking jitter, or is a hash map function etc., then it should not be instrumented. + +To be able to exclude these functions (based on AFL++'s measured stability), the following process will allow to identify functions with variable edges. + +Four steps are required to do this and it also requires quite some knowledge of coding and/or disassembly and is effectively possible only with `afl-clang-fast` `PCGUARD` and `afl-clang-lto` `LTO` instrumentation. + + 1. Instrument to be able to find the responsible function(s): + + a) For LTO instrumented binaries, this can be documented during compile time, just set `export AFL_LLVM_DOCUMENT_IDS=/path/to/a/file`. + This file will have one assigned edge ID and the corresponding function per line. + + b) For PCGUARD instrumented binaries, it is much more difficult. Here you can either modify the `__sanitizer_cov_trace_pc_guard` function in `instrumentation/afl-llvm-rt.o.c` to write a backtrace to a file if the ID in `__afl_area_ptr[*guard]` is one of the unstable edge IDs. + (Example code is already there). + Then recompile and reinstall `llvm_mode` and rebuild your target. + Run the recompiled target with `afl-fuzz` for a while and then check the file that you wrote with the backtrace information. + Alternatively, you can use `gdb` to hook `__sanitizer_cov_trace_pc_guard_init` on start, check to which memory address the edge ID value is written, and set a write breakpoint to that address (`watch 0x.....`). + + c) In other instrumentation types, this is not possible. + So just recompile with the two mentioned above. + This is just for identifying the functions that have unstable edges. + + 2. Identify which edge ID numbers are unstable. + + Run the target with `export AFL_DEBUG=1` for a few minutes then terminate. + The out/fuzzer_stats file will then show the edge IDs that were identified + as unstable in the `var_bytes` entry. You can match these numbers + directly to the data you created in the first step. + Now you know which functions are responsible for the instability + + 3. Create a text file with the filenames/functions + + Identify which source code files contain the functions that you need to remove from instrumentation, or just specify the functions you want to skip for instrumentation. + Note that optimization might inline functions! + + Follow this document on how to do this: [instrumentation/README.instrument_list.md](../instrumentation/README.instrument_list.md). + If `PCGUARD` is used, then you need to follow this guide (needs llvm 12+!): + [http://clang.llvm.org/docs/SanitizerCoverage.html#partially-disabling-instrumentation](http://clang.llvm.org/docs/SanitizerCoverage.html#partially-disabling-instrumentation) + + Only exclude those functions from instrumentation that provide no value for coverage - that is if it does not process any fuzz data directly or indirectly (e.g. hash maps, thread management etc.). + If however a function directly or indirectly handles fuzz data, then you should not put the function in a deny instrumentation list and rather live with the instability it comes with. + + 4. Recompile the target + + Recompile, fuzz it, be happy :) + + This link explains this process for [Fuzzbench](https://github.com/google/fuzzbench/issues/677). diff --git a/docs/beyond_crashes.md b/docs/beyond_crashes.md new file mode 100644 index 00000000..4836419c --- /dev/null +++ b/docs/beyond_crashes.md @@ -0,0 +1,23 @@ +# Going beyond crashes + +Fuzzing is a wonderful and underutilized technique for discovering non-crashing +design and implementation errors, too. Quite a few interesting bugs have been +found by modifying the target programs to call abort() when say: + + - Two bignum libraries produce different outputs when given the same + fuzzer-generated input, + + - An image library produces different outputs when asked to decode the same + input image several times in a row, + + - A serialization / deserialization library fails to produce stable outputs + when iteratively serializing and deserializing fuzzer-supplied data, + + - A compression library produces an output inconsistent with the input file + when asked to compress and then decompress a particular blob. + +Implementing these or similar sanity checks usually takes very little time; +if you are the maintainer of a particular package, you can make this code +conditional with `#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION` (a flag also +shared with libfuzzer and honggfuzz) or `#ifdef __AFL_COMPILER` (this one is +just for AFL). \ No newline at end of file diff --git a/docs/binaryonly_fuzzing.md b/docs/binaryonly_fuzzing.md index 90ea3b66..de360543 100644 --- a/docs/binaryonly_fuzzing.md +++ b/docs/binaryonly_fuzzing.md @@ -96,12 +96,22 @@ It is slower than AFL FRIDA (see above). +## ZAFL + ZAFL is a static rewriting platform supporting x86-64 C/C++, stripped/unstripped, + and PIE/non-PIE binaries. Beyond conventional instrumentation, ZAFL's API enables + transformation passes (e.g., laf-Intel, context sensitivity, InsTrim, etc.). + + Its baseline instrumentation speed typically averages 90-95% of afl-clang-fast's. + + [https://git.zephyr-software.com/opensrc/zafl](https://git.zephyr-software.com/opensrc/zafl) + + ## DYNINST Dyninst is a binary instrumentation framework similar to Pintool and Dynamorio (see far below). However whereas Pintool and Dynamorio work at runtime, dyninst instruments the target at load time, and then let it run - - or save the binary with the changes. + or save the binary with the changes. This is great for some things, e.g. fuzzing, and not so effective for others, e.g. malware analysis. @@ -116,13 +126,10 @@ The speed decrease is about 15-35%, depending on the optimization options used with afl-dyninst. - So if Dyninst works, it is the best option available. Otherwise it just - doesn't work well. - [https://github.com/vanhauser-thc/afl-dyninst](https://github.com/vanhauser-thc/afl-dyninst) -## RETROWRITE, ZAFL, ... other binary rewriter +## RETROWRITE 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++ @@ -131,7 +138,6 @@ It is at about 80-85% performance. - [https://git.zephyr-software.com/opensrc/zafl](https://git.zephyr-software.com/opensrc/zafl) [https://github.com/HexHive/retrowrite](https://github.com/HexHive/retrowrite) diff --git a/docs/branches.md b/docs/branches.md new file mode 100644 index 00000000..ae147b08 --- /dev/null +++ b/docs/branches.md @@ -0,0 +1,11 @@ +# Branches + +The following branches exist: + +* [release](https://github.com/AFLplusplus/AFLplusplus/tree/release): the latest release +* [stable/trunk](https://github.com/AFLplusplus/AFLplusplus/): stable state of AFL++ - it is synced from dev from time to time when we are satisfied with its stability +* [dev](https://github.com/AFLplusplus/AFLplusplus/tree/dev): development state of AFL++ - bleeding edge and you might catch a checkout which does not compile or has a bug. *We only accept PRs in dev!!* +* (any other): experimental branches to work on specific features or testing new functionality or changes. + +For releases, please see the [Releases](https://github.com/AFLplusplus/AFLplusplus/releases) tab. +Also take a look at the list of [important changes in AFL++](important_changes.md). \ No newline at end of file diff --git a/docs/choosing_testcases.md b/docs/choosing_testcases.md new file mode 100644 index 00000000..25002929 --- /dev/null +++ b/docs/choosing_testcases.md @@ -0,0 +1,19 @@ +# Choosing initial test cases + +To operate correctly, the fuzzer requires one or more starting file that +contains a good example of the input data normally expected by the targeted +application. There are two basic rules: + + - Keep the files small. Under 1 kB is ideal, although not strictly necessary. + For a discussion of why size matters, see [perf_tips.md](perf_tips.md). + + - Use multiple test cases only if they are functionally different from + each other. There is no point in using fifty different vacation photos + to fuzz an image library. + +You can find many good examples of starting files in the testcases/ subdirectory +that comes with this tool. + +PS. If a large corpus of data is available for screening, you may want to use +the afl-cmin utility to identify a subset of functionally distinct files that +exercise different code paths in the target binary. \ No newline at end of file diff --git a/docs/ci_fuzzing.md b/docs/ci_fuzzing.md new file mode 100644 index 00000000..8d1a2f99 --- /dev/null +++ b/docs/ci_fuzzing.md @@ -0,0 +1,29 @@ +# CI Fuzzing + +Some notes on CI Fuzzing - this fuzzing is different to normal fuzzing campaigns as these are much shorter runnings. + +1. Always: + * LTO has a much longer compile time which is diametrical to short fuzzing - hence use afl-clang-fast instead. + * If you compile with CMPLOG then you can save fuzzing time and reuse that compiled target for both the -c option and the main fuzz target. + This will impact the speed by ~15% though. + * `AFL_FAST_CAL` - Enable fast calibration, this halfs the time the saturated corpus needs to be loaded. + * `AFL_CMPLOG_ONLY_NEW` - only perform cmplog on new found paths, not the initial corpus as this very likely has been done for them already. + * Keep the generated corpus, use afl-cmin and reuse it every time! + +2. Additionally randomize the AFL++ compilation options, e.g. + * 40% for `AFL_LLVM_CMPLOG` + * 10% for `AFL_LLVM_LAF_ALL` + +3. Also randomize the afl-fuzz runtime options, e.g. + * 65% for `AFL_DISABLE_TRIM` + * 50% use a dictionary generated by `AFL_LLVM_DICT2FILE` + * 40% use MOpt (`-L 0`) + * 40% for `AFL_EXPAND_HAVOC_NOW` + * 20% for old queue processing (`-Z`) + * for CMPLOG targets, 60% for `-l 2`, 40% for `-l 3` + +4. Do *not* run any `-M` modes, just running `-S` modes is better for CI fuzzing. +`-M` enables old queue handling etc. which is good for a fuzzing campaign but not good for short CI runs. + +How this can look like can e.g. be seen at AFL++'s setup in Google's [oss-fuzz](https://github.com/google/oss-fuzz/blob/master/infra/base-images/base-builder/compile_afl) +and [clusterfuzz](https://github.com/google/clusterfuzz/blob/master/src/clusterfuzz/_internal/bot/fuzzers/afl/launcher.py). diff --git a/docs/common_sense_risks.md b/docs/common_sense_risks.md new file mode 100644 index 00000000..a8d68d7a --- /dev/null +++ b/docs/common_sense_risks.md @@ -0,0 +1,36 @@ +# Common sense risks + +Please keep in mind that, similarly to many other computationally-intensive +tasks, fuzzing may put a strain on your hardware and on the OS. In particular: + + - Your CPU will run hot and will need adequate cooling. In most cases, if + cooling is insufficient or stops working properly, CPU speeds will be + automatically throttled. That said, especially when fuzzing on less + suitable hardware (laptops, smartphones, etc), it's not entirely impossible + for something to blow up. + + - Targeted programs may end up erratically grabbing gigabytes of memory or + filling up disk space with junk files. AFL++ tries to enforce basic memory + limits, but can't prevent each and every possible mishap. The bottom line + is that you shouldn't be fuzzing on systems where the prospect of data loss + is not an acceptable risk. + + - Fuzzing involves billions of reads and writes to the filesystem. On modern + systems, this will be usually heavily cached, resulting in fairly modest + "physical" I/O - but there are many factors that may alter this equation. + It is your responsibility to monitor for potential trouble; with very heavy + I/O, the lifespan of many HDDs and SSDs may be reduced. + + A good way to monitor disk I/O on Linux is the 'iostat' command: + +```shell + $ iostat -d 3 -x -k [...optional disk ID...] +``` + + Using the `AFL_TMPDIR` environment variable and a RAM-disk you can have the + heavy writing done in RAM to prevent the aforementioned wear and tear. For + example the following line will run a Docker container with all this preset: + + ```shell + # docker run -ti --mount type=tmpfs,destination=/ramdisk -e AFL_TMPDIR=/ramdisk aflplusplus/aflplusplus + ``` \ No newline at end of file diff --git a/docs/env_variables.md b/docs/env_variables.md index 0686f1a8..5f5c2510 100644 --- a/docs/env_variables.md +++ b/docs/env_variables.md @@ -2,7 +2,7 @@ This document discusses the environment variables used by American Fuzzy Lop++ to expose various exotic functions that may be (rarely) useful for power - users or for some types of custom fuzzing setups. See [README.md](README.md) for the general + users or for some types of custom fuzzing setups. See [../README.md](../README.md) for the general instruction manual. Note that most tools will warn on any unknown AFL environment variables. @@ -422,7 +422,7 @@ checks or alter some of the more exotic semantics of the tool: - Setting `AFL_FORCE_UI` will force painting the UI on the screen even if no valid terminal was detected (for virtual consoles) - - If you are using persistent mode (you should, see [instrumentation/README.persistent_mode.md](instrumentation/README.persistent_mode.md)) + - If you are using persistent mode (you should, see [instrumentation/README.persistent_mode.md](../instrumentation/README.persistent_mode.md)) some targets keep inherent state due which a detected crash testcase does not crash the target again when the testcase is given. To be able to still re-trigger these crashes you can use the `AFL_PERSISTENT_RECORD` variable diff --git a/docs/features.md b/docs/features.md new file mode 100644 index 00000000..c0956703 --- /dev/null +++ b/docs/features.md @@ -0,0 +1,46 @@ +# Important features of AFL++ + + AFL++ supports llvm from 3.8 up to version 12, very fast binary fuzzing with QEMU 5.1 + with laf-intel and redqueen, frida mode, unicorn mode, gcc plugin, full *BSD, + Mac OS, Solaris and Android support and much, much, much more. + + | Feature/Instrumentation | afl-gcc | llvm | gcc_plugin | frida_mode | qemu_mode |unicorn_mode | + | -------------------------|:-------:|:---------:|:----------:|:----------------:|:----------------:|:----------------:| + | Threadsafe counters | | x(3) | | | | | + | NeverZero | x86[_64]| x(1) | x | x | x | x | + | Persistent Mode | | x | x | x86[_64]/arm64 | x86[_64]/arm[64] | x | + | LAF-Intel / CompCov | | x | | | x86[_64]/arm[64] | x86[_64]/arm[64] | + | CmpLog | | x | | x86[_64]/arm64 | x86[_64]/arm[64] | | + | Selective Instrumentation| | x | x | x | x | | + | Non-Colliding Coverage | | x(4) | | | (x)(5) | | + | Ngram prev_loc Coverage | | x(6) | | | | | + | Context Coverage | | x(6) | | | | | + | Auto Dictionary | | x(7) | | | | | + | Snapshot LKM Support | | (x)(8) | (x)(8) | | (x)(5) | | + | Shared Memory Testcases | | x | x | x86[_64]/arm64 | x | x | + + 1. default for LLVM >= 9.0, env var for older version due an efficiency bug in previous llvm versions + 2. GCC creates non-performant code, hence it is disabled in gcc_plugin + 3. with `AFL_LLVM_THREADSAFE_INST`, disables NeverZero + 4. with pcguard mode and LTO mode for LLVM 11 and newer + 5. upcoming, development in the branch + 6. not compatible with LTO instrumentation and needs at least LLVM v4.1 + 7. automatic in LTO mode with LLVM 11 and newer, an extra pass for all LLVM versions that write to a file to use with afl-fuzz' `-x` + 8. the snapshot LKM is currently unmaintained due to too many kernel changes coming too fast :-( + + Among others, the following features and patches have been integrated: + + * NeverZero patch for afl-gcc, instrumentation, qemu_mode and unicorn_mode which prevents a wrapping map value to zero, increases coverage + * Persistent mode, deferred forkserver and in-memory fuzzing for qemu_mode + * Unicorn mode which allows fuzzing of binaries from completely different platforms (integration provided by domenukk) + * The new CmpLog instrumentation for LLVM and QEMU inspired by [Redqueen](https://www.syssec.ruhr-uni-bochum.de/media/emma/veroeffentlichungen/2018/12/17/NDSS19-Redqueen.pdf) + * Win32 PE binary-only fuzzing with QEMU and Wine + * AFLfast's power schedules by Marcel Böhme: [https://github.com/mboehme/aflfast](https://github.com/mboehme/aflfast) + * The MOpt mutator: [https://github.com/puppet-meteor/MOpt-AFL](https://github.com/puppet-meteor/MOpt-AFL) + * LLVM mode Ngram coverage by Adrian Herrera [https://github.com/adrianherrera/afl-ngram-pass](https://github.com/adrianherrera/afl-ngram-pass) + * LAF-Intel/CompCov support for instrumentation, qemu_mode and unicorn_mode (with enhanced capabilities) + * Radamsa and honggfuzz mutators (as custom mutators). + * QBDI mode to fuzz android native libraries via Quarkslab's [QBDI](https://github.com/QBDI/QBDI) framework + * Frida and ptrace mode to fuzz binary-only libraries, etc. + + So all in all this is the best-of AFL that is out there :-) \ No newline at end of file diff --git a/docs/fuzzing_binary-only_targets.md b/docs/fuzzing_binary-only_targets.md new file mode 100644 index 00000000..ea262f6e --- /dev/null +++ b/docs/fuzzing_binary-only_targets.md @@ -0,0 +1,83 @@ +# Fuzzing binary-only targets + +When source code is *NOT* available, AFL++ offers various support for fast, +on-the-fly instrumentation of black-box binaries. + +If you do not have to use Unicorn the following setup is recommended to use +qemu_mode: + * run 1 afl-fuzz -Q instance with CMPLOG (`-c 0` + `AFL_COMPCOV_LEVEL=2`) + * run 1 afl-fuzz -Q instance with QASAN (`AFL_USE_QASAN=1`) + * run 1 afl-fuzz -Q instance with LAF (`AFL_PRELOAD=libcmpcov.so` + `AFL_COMPCOV_LEVEL=2`) +Alternatively you can use frida_mode, just switch `-Q` with `-O` and remove the +LAF instance. + +Then run as many instances as you have cores left with either -Q mode or - better - +use a binary rewriter like afl-dyninst, retrowrite, zafl, etc. + +For Qemu and Frida mode, check out the persistent mode, it gives a huge speed +improvement if it is possible to use. + +### QEMU + +For linux programs and its libraries this is accomplished with a version of +QEMU running in the lesser-known "user space emulation" mode. +QEMU is a project separate from AFL, but you can conveniently build the +feature by doing: + +```shell +cd qemu_mode +./build_qemu_support.sh +``` + +For additional instructions and caveats, see [qemu_mode/README.md](../qemu_mode/README.md). +If possible you should use the persistent mode, see [qemu_mode/README.persistent.md](../qemu_mode/README.persistent.md). +The mode is approximately 2-5x slower than compile-time instrumentation, and is +less conducive to parallelization. + +If [afl-dyninst](https://github.com/vanhauser-thc/afl-dyninst) works for +your binary, then you can use afl-fuzz normally and it will have twice +the speed compared to qemu_mode (but slower than qemu persistent mode). +Note that several other binary rewriters exist, all with their advantages and +caveats. + +### Frida + +Frida mode is sometimes faster and sometimes slower than Qemu mode. +It is also newer, lacks COMPCOV, but supports MacOS. + +```shell +cd frida_mode +make +``` + +For additional instructions and caveats, see [frida_mode/README.md](../frida_mode/README.md). +If possible you should use the persistent mode, see [qemu_frida/README.md](../qemu_frida/README.md). +The mode is approximately 2-5x slower than compile-time instrumentation, and is +less conducive to parallelization. + +### Unicorn + +For non-Linux binaries you can use AFL++'s unicorn mode which can emulate +anything you want - for the price of speed and user written scripts. +See [unicorn_mode/README.md](../unicorn_mode/README.md). + +It can be easily built by: +```shell +cd unicorn_mode +./build_unicorn_support.sh +``` + +### Shared libraries + +If the goal is to fuzz a dynamic library then there are two options available. +For both you need to write a small harness that loads and calls the library. +Then you fuzz this with either frida_mode or qemu_mode, and either use +`AFL_INST_LIBS=1` or `AFL_QEMU/FRIDA_INST_RANGES`. + +Another, less precise and slower option is using ptrace with debugger interrupt +instrumentation: [utils/afl_untracer/README.md](../utils/afl_untracer/README.md). + +### More + +A more comprehensive description of these and other options can be found in +[binaryonly_fuzzing.md](binaryonly_fuzzing.md). \ No newline at end of file diff --git a/docs/fuzzing_expert.md b/docs/fuzzing_expert.md new file mode 100644 index 00000000..96193f88 --- /dev/null +++ b/docs/fuzzing_expert.md @@ -0,0 +1,628 @@ +# Fuzzing with AFL++ + +The following describes how to fuzz with a target if source code is available. +If you have a binary-only target please skip to [#Instrumenting binary-only apps](#Instrumenting binary-only apps) + +Fuzzing source code is a three-step process. + +1. Compile the target with a special compiler that prepares the target to be + fuzzed efficiently. This step is called "instrumenting a target". +2. Prepare the fuzzing by selecting and optimizing the input corpus for the + target. +3. Perform the fuzzing of the target by randomly mutating input and assessing + if a generated input was processed in a new path in the target binary. + +### 1. Instrumenting that target + +#### a) Selecting the best AFL++ compiler for instrumenting the target + +AFL++ comes with a central compiler `afl-cc` that incorporates various different +kinds of compiler targets and and instrumentation options. +The following evaluation flow will help you to select the best possible. + +It is highly recommended to have the newest llvm version possible installed, +anything below 9 is not recommended. + +``` ++--------------------------------+ +| clang/clang++ 11+ is available | --> use LTO mode (afl-clang-lto/afl-clang-lto++) ++--------------------------------+ see [instrumentation/README.lto.md](instrumentation/README.lto.md) + | + | if not, or if the target fails with LTO afl-clang-lto/++ + | + v ++---------------------------------+ +| clang/clang++ 3.8+ is available | --> use LLVM mode (afl-clang-fast/afl-clang-fast++) ++---------------------------------+ see [instrumentation/README.llvm.md](instrumentation/README.llvm.md) + | + | if not, or if the target fails with LLVM afl-clang-fast/++ + | + v + +--------------------------------+ + | gcc 5+ is available | -> use GCC_PLUGIN mode (afl-gcc-fast/afl-g++-fast) + +--------------------------------+ see [instrumentation/README.gcc_plugin.md](instrumentation/README.gcc_plugin.md) and + [instrumentation/README.instrument_list.md](instrumentation/README.instrument_list.md) + | + | if not, or if you do not have a gcc with plugin support + | + v + use GCC mode (afl-gcc/afl-g++) (or afl-clang/afl-clang++ for clang) +``` + +Clickable README links for the chosen compiler: + + * [LTO mode - afl-clang-lto](../instrumentation/README.lto.md) + * [LLVM mode - afl-clang-fast](../instrumentation/README.llvm.md) + * [GCC_PLUGIN mode - afl-gcc-fast](../instrumentation/README.gcc_plugin.md) + * GCC/CLANG modes (afl-gcc/afl-clang) have no README as they have no own features + +You can select the mode for the afl-cc compiler by: + 1. use a symlink to afl-cc: afl-gcc, afl-g++, afl-clang, afl-clang++, + afl-clang-fast, afl-clang-fast++, afl-clang-lto, afl-clang-lto++, + afl-gcc-fast, afl-g++-fast (recommended!) + 2. using the environment variable AFL_CC_COMPILER with MODE + 3. passing --afl-MODE command line options to the compiler via CFLAGS/CXXFLAGS/CPPFLAGS + +MODE can be one of: LTO (afl-clang-lto*), LLVM (afl-clang-fast*), GCC_PLUGIN +(afl-g*-fast) or GCC (afl-gcc/afl-g++) or CLANG(afl-clang/afl-clang++). + +Because no AFL specific command-line options are accepted (beside the +--afl-MODE command), the compile-time tools make fairly broad use of environment +variables, which can be listed with `afl-cc -hh` or by reading [env_variables.md](env_variables.md). + +#### b) Selecting instrumentation options + +The following options are available when you instrument with LTO mode (afl-clang-fast/afl-clang-lto): + + * Splitting integer, string, float and switch comparisons so AFL++ can easier + solve these. This is an important option if you do not have a very good + and large input corpus. This technique is called laf-intel or COMPCOV. + To use this set the following environment variable before compiling the + target: `export AFL_LLVM_LAF_ALL=1` + You can read more about this in [instrumentation/README.laf-intel.md](../instrumentation/README.laf-intel.md) + * A different technique (and usually a better one than laf-intel) is to + instrument the target so that any compare values in the target are sent to + AFL++ which then tries to put these values into the fuzzing data at different + locations. This technique is very fast and good - if the target does not + transform input data before comparison. Therefore this technique is called + `input to state` or `redqueen`. + If you want to use this technique, then you have to compile the target + twice, once specifically with/for this mode, and pass this binary to afl-fuzz + via the `-c` parameter. + Note that you can compile also just a cmplog binary and use that for both + however there will be a performance penality. + You can read more about this in [instrumentation/README.cmplog.md](../instrumentation/README.cmplog.md) + +If you use LTO, LLVM or GCC_PLUGIN mode (afl-clang-fast/afl-clang-lto/afl-gcc-fast) +you have the option to selectively only instrument parts of the target that you +are interested in: + + * To instrument only those parts of the target that you are interested in + create a file with all the filenames of the source code that should be + instrumented. + For afl-clang-lto and afl-gcc-fast - or afl-clang-fast if a mode other than + DEFAULT/PCGUARD is used or you have llvm > 10.0.0 - just put one + filename or function per line (no directory information necessary for + filenames9, and either set `export AFL_LLVM_ALLOWLIST=allowlist.txt` **or** + `export AFL_LLVM_DENYLIST=denylist.txt` - depending on if you want per + default to instrument unless noted (DENYLIST) or not perform instrumentation + unless requested (ALLOWLIST). + **NOTE:** During optimization functions might be inlined and then would not match! + See [instrumentation/README.instrument_list.md](../instrumentation/README.instrument_list.md) + +There are many more options and modes available however these are most of the +time less effective. See: + * [instrumentation/README.ctx.md](../instrumentation/README.ctx.md) + * [instrumentation/README.ngram.md](../instrumentation/README.ngram.md) + +AFL++ performs "never zero" counting in its bitmap. You can read more about this +here: + * [instrumentation/README.neverzero.md](../instrumentation/README.neverzero.md) + +#### c) Sanitizers + +It is possible to use sanitizers when instrumenting targets for fuzzing, +which allows you to find bugs that would not necessarily result in a crash. + +Note that sanitizers have a huge impact on CPU (= less executions per second) +and RAM usage. Also you should only run one afl-fuzz instance per sanitizer type. +This is enough because a use-after-free bug will be picked up, e.g. by +ASAN (address sanitizer) anyway when syncing to other fuzzing instances, +so not all fuzzing instances need to be instrumented with ASAN. + +The following sanitizers have built-in support in AFL++: + * ASAN = Address SANitizer, finds memory corruption vulnerabilities like + use-after-free, NULL pointer dereference, buffer overruns, etc. + Enabled with `export AFL_USE_ASAN=1` before compiling. + * MSAN = Memory SANitizer, finds read access to uninitialized memory, eg. + a local variable that is defined and read before it is even set. + Enabled with `export AFL_USE_MSAN=1` before compiling. + * UBSAN = Undefined Behaviour SANitizer, finds instances where - by the + C and C++ standards - undefined behaviour happens, e.g. adding two + signed integers together where the result is larger than a signed integer + can hold. + Enabled with `export AFL_USE_UBSAN=1` before compiling. + * CFISAN = Control Flow Integrity SANitizer, finds instances where the + control flow is found to be illegal. Originally this was rather to + prevent return oriented programming exploit chains from functioning, + in fuzzing this is mostly reduced to detecting type confusion + vulnerabilities - which is however one of the most important and dangerous + C++ memory corruption classes! + Enabled with `export AFL_USE_CFISAN=1` before compiling. + * LSAN = Leak SANitizer, finds memory leaks in a program. This is not really + a security issue, but for developers this can be very valuable. + Note that unlike the other sanitizers above this needs + `__AFL_LEAK_CHECK();` added to all areas of the target source code where you + find a leak check necessary! + Enabled with `export AFL_USE_LSAN=1` before compiling. + +It is possible to further modify the behaviour of the sanitizers at run-time +by setting `ASAN_OPTIONS=...`, `LSAN_OPTIONS` etc. - the available parameters +can be looked up in the sanitizer documentation of llvm/clang. +afl-fuzz however requires some specific parameters important for fuzzing to be +set. If you want to set your own, it might bail and report what it is missing. + +Note that some sanitizers cannot be used together, e.g. ASAN and MSAN, and +others often cannot work together because of target weirdness, e.g. ASAN and +CFISAN. You might need to experiment which sanitizers you can combine in a +target (which means more instances can be run without a sanitized target, +which is more effective). + +#### d) Modify the target + +If the target has features that make fuzzing more difficult, e.g. +checksums, HMAC, etc. then modify the source code so that checks for these +values are removed. +This can even be done safely for source code used in operational products +by eliminating these checks within these AFL specific blocks: + +``` +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + // say that the checksum or HMAC was fine - or whatever is required + // to eliminate the need for the fuzzer to guess the right checksum + return 0; +#endif +``` + +All AFL++ compilers will set this preprocessor definition automatically. + +#### e) Instrument the target + +In this step the target source code is compiled so that it can be fuzzed. + +Basically you have to tell the target build system that the selected AFL++ +compiler is used. Also - if possible - you should always configure the +build system such that the target is compiled statically and not dynamically. +How to do this is described below. + +The #1 rule when instrumenting a target is: avoid instrumenting shared +libraries at all cost. You would need to set LD_LIBRARY_PATH to point to +these, you could accidently type "make install" and install them system wide - +so don't. Really don't. +**Always compile libraries you want to have instrumented as static and link +these to the target program!** + +Then build the target. (Usually with `make`) + +**NOTES** + +1. sometimes configure and build systems are fickle and do not like + stderr output (and think this means a test failure) - which is something + AFL++ likes to do to show statistics. It is recommended to disable AFL++ + instrumentation reporting via `export AFL_QUIET=1`. + +2. sometimes configure and build systems error on warnings - these should be + disabled (e.g. `--disable-werror` for some configure scripts). + +3. in case the configure/build system complains about AFL++'s compiler and + aborts then set `export AFL_NOOPT=1` which will then just behave like the + real compiler. This option has to be unset again before building the target! + +##### configure + +For `configure` build systems this is usually done by: +`CC=afl-clang-fast CXX=afl-clang-fast++ ./configure --disable-shared` + +Note that if you are using the (better) afl-clang-lto compiler you also have to +set AR to llvm-ar[-VERSION] and RANLIB to llvm-ranlib[-VERSION] - as is +described in [instrumentation/README.lto.md](../instrumentation/README.lto.md). + +##### cmake + +For `cmake` build systems this is usually done by: +`mkdir build; cd build; cmake -DCMAKE_C_COMPILER=afl-cc -DCMAKE_CXX_COMPILER=afl-c++ ..` + +Note that if you are using the (better) afl-clang-lto compiler you also have to +set AR to llvm-ar[-VERSION] and RANLIB to llvm-ranlib[-VERSION] - as is +described in [instrumentation/README.lto.md](../instrumentation/README.lto.md). + +##### meson + +For meson you have to set the AFL++ compiler with the very first command! +`CC=afl-cc CXX=afl-c++ meson` + +##### other build systems or if configure/cmake didn't work + +Sometimes cmake and configure do not pick up the AFL++ compiler, or the +ranlib/ar that is needed - because this was just not foreseen by the developer +of the target. Or they have non-standard options. Figure out if there is a +non-standard way to set this, otherwise set up the build normally and edit the +generated build environment afterwards manually to point it to the right compiler +(and/or ranlib and ar). + +#### f) Better instrumentation + +If you just fuzz a target program as-is you are wasting a great opportunity for +much more fuzzing speed. + +This variant requires the usage of afl-clang-lto, afl-clang-fast or afl-gcc-fast. + +It is the so-called `persistent mode`, which is much, much faster but +requires that you code a source file that is specifically calling the target +functions that you want to fuzz, plus a few specific AFL++ functions around +it. See [instrumentation/README.persistent_mode.md](../instrumentation/README.persistent_mode.md) for details. + +Basically if you do not fuzz a target in persistent mode then you are just +doing it for a hobby and not professionally :-). + +#### g) libfuzzer fuzzer harnesses with LLVMFuzzerTestOneInput() + +libfuzzer `LLVMFuzzerTestOneInput()` harnesses are the defacto standard +for fuzzing, and they can be used with AFL++ (and honggfuzz) as well! +Compiling them is as simple as: +``` +afl-clang-fast++ -fsanitize=fuzzer -o harness harness.cpp targetlib.a +``` +You can even use advanced libfuzzer features like `FuzzedDataProvider`, +`LLVMFuzzerMutate()` etc. and they will work! + +The generated binary is fuzzed with afl-fuzz like any other fuzz target. + +Bonus: the target is already optimized for fuzzing due to persistent mode and +shared-memory testcases and hence gives you the fastest speed possible. + +For more information see [utils/aflpp_driver/README.md](../utils/aflpp_driver/README.md) + +### 2. Preparing the fuzzing campaign + +As you fuzz the target with mutated input, having as diverse inputs for the +target as possible improves the efficiency a lot. + +#### a) Collect inputs + +Try to gather valid inputs for the target from wherever you can. E.g. if it is +the PNG picture format try to find as many png files as possible, e.g. from +reported bugs, test suites, random downloads from the internet, unit test +case data - from all kind of PNG software. + +If the input format is not known, you can also modify a target program to write +normal data it receives and processes to a file and use these. + +#### b) Making the input corpus unique + +Use the AFL++ tool `afl-cmin` to remove inputs from the corpus that do not +produce a new path in the target. + +Put all files from step a) into one directory, e.g. INPUTS. + +If the target program is to be called by fuzzing as `bin/target -d INPUTFILE` +the run afl-cmin like this: +`afl-cmin -i INPUTS -o INPUTS_UNIQUE -- bin/target -d @@` +Note that the INPUTFILE argument that the target program would read from has to be set as `@@`. + +If the target reads from stdin instead, just omit the `@@` as this is the +default. + +This step is highly recommended! + +#### c) Minimizing all corpus files + +The shorter the input files that still traverse the same path +within the target, the better the fuzzing will be. This minimization +is done with `afl-tmin` however it is a long process as this has to +be done for every file: + +``` +mkdir input +cd INPUTS_UNIQUE +for i in *; do + afl-tmin -i "$i" -o "../input/$i" -- bin/target -d @@ +done +``` + +This step can also be parallelized, e.g. with `parallel`. +Note that this step is rather optional though. + +#### Done! + +The INPUTS_UNIQUE/ directory from step b) - or even better the directory input/ +if you minimized the corpus in step c) - is the resulting input corpus directory +to be used in fuzzing! :-) + +### 3. Fuzzing the target + +In this final step we fuzz the target. +There are not that many important options to run the target - unless you want +to use many CPU cores/threads for the fuzzing, which will make the fuzzing much +more useful. + +If you just use one CPU for fuzzing, then you are fuzzing just for fun and not +seriously :-) + +#### a) Running afl-fuzz + +Before you do even a test run of afl-fuzz execute `sudo afl-system-config` (on +the host if you execute afl-fuzz in a docker container). This reconfigures the +system for optimal speed - which afl-fuzz checks and bails otherwise. +Set `export AFL_SKIP_CPUFREQ=1` for afl-fuzz to skip this check if you cannot +run afl-system-config with root privileges on the host for whatever reason. + +Note there is also `sudo afl-persistent-config` which sets additional permanent +boot options for a much better fuzzing performance. + +Note that both scripts improve your fuzzing performance but also decrease your +system protection against attacks! So set strong firewall rules and only +expose SSH as a network service if you use these (which is highly recommended). + +If you have an input corpus from step 2 then specify this directory with the `-i` +option. Otherwise create a new directory and create a file with any content +as test data in there. + +If you do not want anything special, the defaults are already usually best, +hence all you need is to specify the seed input directory with the result of +step [2a. Collect inputs](#a-collect-inputs): +`afl-fuzz -i input -o output -- bin/target -d @@` +Note that the directory specified with -o will be created if it does not exist. + +It can be valuable to run afl-fuzz in a screen or tmux shell so you can log off, +or afl-fuzz is not aborted if you are running it in a remote ssh session where +the connection fails in between. +Only do that though once you have verified that your fuzzing setup works! +Simply run it like `screen -dmS afl-main -- afl-fuzz -M main-$HOSTNAME -i ...` +and it will start away in a screen session. To enter this session simply type +`screen -r afl-main`. You see - it makes sense to name the screen session +same as the afl-fuzz -M/-S naming :-) +For more information on screen or tmux please check their documentation. + +If you need to stop and re-start the fuzzing, use the same command line options +(or even change them by selecting a different power schedule or another +mutation mode!) and switch the input directory with a dash (`-`): +`afl-fuzz -i - -o output -- bin/target -d @@` + +Memory limits are not enforced by afl-fuzz by default and the system may run +out of memory. You can decrease the memory with the `-m` option, the value is +in MB. If this is too small for the target, you can usually see this by +afl-fuzz bailing with the message that it could not connect to the forkserver. + +Adding a dictionary is helpful. See the directory [dictionaries/](../dictionaries/) if +something is already included for your data format, and tell afl-fuzz to load +that dictionary by adding `-x dictionaries/FORMAT.dict`. With afl-clang-lto +you have an autodictionary generation for which you need to do nothing except +to use afl-clang-lto as the compiler. You also have the option to generate +a dictionary yourself, see [utils/libtokencap/README.md](../utils/libtokencap/README.md). + +afl-fuzz has a variety of options that help to workaround target quirks like +specific locations for the input file (`-f`), performing deterministic +fuzzing (`-D`) and many more. Check out `afl-fuzz -h`. + +We highly recommend that you set a memory limit for running the target with `-m` +which defines the maximum memory in MB. This prevents a potential +out-of-memory problem for your system plus helps you detect missing `malloc()` +failure handling in the target. +Play around with various -m values until you find one that safely works for all +your input seeds (if you have good ones and then double or quadrouple that. + +By default afl-fuzz never stops fuzzing. To terminate AFL++ simply press Control-C +or send a signal SIGINT. You can limit the number of executions or approximate runtime +in seconds with options also. + +When you start afl-fuzz you will see a user interface that shows what the status +is: + + +All labels are explained in [status_screen.md](status_screen.md). + +#### b) Using multiple cores + +If you want to seriously fuzz then use as many cores/threads as possible to +fuzz your target. + +On the same machine - due to the design of how AFL++ works - there is a maximum +number of CPU cores/threads that are useful, use more and the overall performance +degrades instead. This value depends on the target, and the limit is between 32 +and 64 cores per machine. + +If you have the RAM, it is highly recommended run the instances with a caching +of the testcases. Depending on the average testcase size (and those found +during fuzzing) and their number, a value between 50-500MB is recommended. +You can set the cache size (in MB) by setting the environment variable `AFL_TESTCACHE_SIZE`. + +There should be one main fuzzer (`-M main-$HOSTNAME` option) and as many secondary +fuzzers (eg `-S variant1`) as you have cores that you use. +Every -M/-S entry needs a unique name (that can be whatever), however the same +-o output directory location has to be used for all instances. + +For every secondary fuzzer there should be a variation, e.g.: + * one should fuzz the target that was compiled differently: with sanitizers + activated (`export AFL_USE_ASAN=1 ; export AFL_USE_UBSAN=1 ; + export AFL_USE_CFISAN=1`) + * one or two should fuzz the target with CMPLOG/redqueen (see above), at + least one cmplog instance should follow transformations (`-l AT`) + * one to three fuzzers should fuzz a target compiled with laf-intel/COMPCOV + (see above). Important note: If you run more than one laf-intel/COMPCOV + fuzzer and you want them to share their intermediate results, the main + fuzzer (`-M`) must be one of the them! (Although this is not really + recommended.) + +All other secondaries should be used like this: + * A quarter to a third with the MOpt mutator enabled: `-L 0` + * run with a different power schedule, recommended are: + `fast (default), explore, coe, lin, quad, exploit and rare` + which you can set with e.g. `-p explore` + * a few instances should use the old queue cycling with `-Z` + +Also it is recommended to set `export AFL_IMPORT_FIRST=1` to load testcases +from other fuzzers in the campaign first. + +If you have a large corpus, a corpus from a previous run or are fuzzing in +a CI, then also set `export AFL_CMPLOG_ONLY_NEW=1` and `export AFL_FAST_CAL=1`. + +You can also use different fuzzers. +If you are using AFL spinoffs or AFL conforming fuzzers, then just use the +same -o directory and give it a unique `-S` name. +Examples are: + * [Fuzzolic](https://github.com/season-lab/fuzzolic) + * [symcc](https://github.com/eurecom-s3/symcc/) + * [Eclipser](https://github.com/SoftSec-KAIST/Eclipser/) + * [AFLsmart](https://github.com/aflsmart/aflsmart) + * [FairFuzz](https://github.com/carolemieux/afl-rb) + * [Neuzz](https://github.com/Dongdongshe/neuzz) + * [Angora](https://github.com/AngoraFuzzer/Angora) + +A long list can be found at [https://github.com/Microsvuln/Awesome-AFL](https://github.com/Microsvuln/Awesome-AFL) + +However you can also sync AFL++ with honggfuzz, libfuzzer with `-entropic=1`, etc. +Just show the main fuzzer (-M) with the `-F` option where the queue/work +directory of a different fuzzer is, e.g. `-F /src/target/honggfuzz`. +Using honggfuzz (with `-n 1` or `-n 2`) and libfuzzer in parallel is highly +recommended! + +#### c) Using multiple machines for fuzzing + +Maybe you have more than one machine you want to fuzz the same target on. +Simply start the `afl-fuzz` (and perhaps libfuzzer, honggfuzz, ...) +orchestra as you like, just ensure that your have one and only one `-M` +instance per server, and that its name is unique, hence the recommendation +for `-M main-$HOSTNAME`. + +Now there are three strategies on how you can sync between the servers: + * never: sounds weird, but this makes every server an island and has the + chance the each follow different paths into the target. You can make + this even more interesting by even giving different seeds to each server. + * regularly (~4h): this ensures that all fuzzing campaigns on the servers + "see" the same thing. It is like fuzzing on a huge server. + * in intervals of 1/10th of the overall expected runtime of the fuzzing you + sync. This tries a bit to combine both. have some individuality of the + paths each campaign on a server explores, on the other hand if one + gets stuck where another found progress this is handed over making it + unstuck. + +The syncing process itself is very simple. +As the `-M main-$HOSTNAME` instance syncs to all `-S` secondaries as well +as to other fuzzers, you have to copy only this directory to the other +machines. + +Lets say all servers have the `-o out` directory in /target/foo/out, and +you created a file `servers.txt` which contains the hostnames of all +participating servers, plus you have an ssh key deployed to all of them, +then run: +```bash +for FROM in `cat servers.txt`; do + for TO in `cat servers.txt`; do + rsync -rlpogtz --rsh=ssh $FROM:/target/foo/out/main-$FROM $TO:target/foo/out/ + done +done +``` +You can run this manually, per cron job - as you need it. +There is a more complex and configurable script in `utils/distributed_fuzzing`. + +#### d) The status of the fuzz campaign + +AFL++ comes with the `afl-whatsup` script to show the status of the fuzzing +campaign. + +Just supply the directory that afl-fuzz is given with the -o option and +you will see a detailed status of every fuzzer in that campaign plus +a summary. + +To have only the summary use the `-s` switch e.g.: `afl-whatsup -s out/` + +If you have multiple servers then use the command after a sync, or you have +to execute this script per server. + +Another tool to inspect the current state and history of a specific instance +is afl-plot, which generates an index.html file and a graphs that show how +the fuzzing instance is performing. +The syntax is `afl-plot instance_dir web_dir`, e.g. `afl-plot out/default /srv/www/htdocs/plot` + +#### e) Stopping fuzzing, restarting fuzzing, adding new seeds + +To stop an afl-fuzz run, simply press Control-C. + +To restart an afl-fuzz run, just reuse the same command line but replace the +`-i directory` with `-i -` or set `AFL_AUTORESUME=1`. + +If you want to add new seeds to a fuzzing campaign you can run a temporary +fuzzing instance, e.g. when your main fuzzer is using `-o out` and the new +seeds are in `newseeds/` directory: +``` +AFL_BENCH_JUST_ONE=1 AFL_FAST_CAL=1 afl-fuzz -i newseeds -o out -S newseeds -- ./target +``` + +#### f) Checking the coverage of the fuzzing + +The `paths found` value is a bad indicator for checking how good the coverage is. + +A better indicator - if you use default llvm instrumentation with at least +version 9 - is to use `afl-showmap` with the collect coverage option `-C` on +the output directory: +``` +$ afl-showmap -C -i out -o /dev/null -- ./target -params @@ +... +[*] Using SHARED MEMORY FUZZING feature. +[*] Target map size: 9960 +[+] Processed 7849 input files. +[+] Captured 4331 tuples (highest value 255, total values 67130596) in '/dev/nul +l'. +[+] A coverage of 4331 edges were achieved out of 9960 existing (43.48%) with 7849 input files. +``` +It is even better to check out the exact lines of code that have been reached - +and which have not been found so far. + +An "easy" helper script for this is [https://github.com/vanhauser-thc/afl-cov](https://github.com/vanhauser-thc/afl-cov), +just follow the README of that separate project. + +If you see that an important area or a feature has not been covered so far then +try to find an input that is able to reach that and start a new secondary in +that fuzzing campaign with that seed as input, let it run for a few minutes, +then terminate it. The main node will pick it up and make it available to the +other secondary nodes over time. Set `export AFL_NO_AFFINITY=1` or +`export AFL_TRY_AFFINITY=1` if you have no free core. + +Note that in nearly all cases you can never reach full coverage. A lot of +functionality is usually dependent on exclusive options that would need individual +fuzzing campaigns each with one of these options set. E.g. if you fuzz a library to +convert image formats and your target is the png to tiff API then you will not +touch any of the other library APIs and features. + +#### g) How long to fuzz a target? + +This is a difficult question. +Basically if no new path is found for a long time (e.g. for a day or a week) +then you can expect that your fuzzing won't be fruitful anymore. +However often this just means that you should switch out secondaries for +others, e.g. custom mutator modules, sync to very different fuzzers, etc. + +Keep the queue/ directory (for future fuzzings of the same or similar targets) +and use them to seed other good fuzzers like libfuzzer with the -entropic +switch or honggfuzz. + +#### h) Improve the speed! + + * Use [persistent mode](../instrumentation/README.persistent_mode.md) (x2-x20 speed increase) + * If you do not use shmem persistent mode, use `AFL_TMPDIR` to point the input file on a tempfs location, see [env_variables.md](env_variables.md) + * Linux: Improve kernel performance: modify `/etc/default/grub`, set `GRUB_CMDLINE_LINUX_DEFAULT="ibpb=off ibrs=off kpti=off l1tf=off mds=off mitigations=off no_stf_barrier noibpb noibrs nopcid nopti nospec_store_bypass_disable nospectre_v1 nospectre_v2 pcid=off pti=off spec_store_bypass_disable=off spectre_v2=off stf_barrier=off"`; then `update-grub` and `reboot` (warning: makes the system more insecure) - you can also just run `sudo afl-persistent-config` + * Linux: Running on an `ext2` filesystem with `noatime` mount option will be a bit faster than on any other journaling filesystem + * Use your cores! [b) Using multiple cores](#b-using-multiple-cores) + * Run `sudo afl-system-config` before starting the first afl-fuzz instance after a reboot + +### The End + +Check out the [FAQ](FAQ.md) if it maybe answers your question (that +you might not even have known you had ;-) ). + +This is basically all you need to know to professionally run fuzzing campaigns. +If you want to know more, the tons of texts in [docs/](./) will have you covered. + +Note that there are also a lot of tools out there that help fuzzing with AFL++ +(some might be deprecated or unsupported), see [tools.md](tools.md). \ No newline at end of file diff --git a/docs/important_changes.md b/docs/important_changes.md new file mode 100644 index 00000000..0c5c2243 --- /dev/null +++ b/docs/important_changes.md @@ -0,0 +1,56 @@ +# Important changes in AFL++ + +This document lists important changes in AFL++, for example, major behaviour changes. + +## From version 3.00 onwards + +With AFL++ 3.13-3.20 we introduce frida_mode (-O) to have an alternative for +binary-only fuzzing. It is slower than Qemu mode but works on MacOS, Android, +iOS etc. + +With AFL++ 3.15 we introduced the following changes from previous behaviours: + * Also -M main mode does not do deterministic fuzzing by default anymore + * afl-cmin and afl-showmap -Ci now descent into subdirectories like + afl-fuzz -i does (but note that afl-cmin.bash does not) + +With AFL++ 3.14 we introduced the following changes from previous behaviours: + * afl-fuzz: deterministic fuzzing it not a default for -M main anymore + * afl-cmin/afl-showmap -i now descends into subdirectories (afl-cmin.bash + however does not) + +With AFL++ 3.10 we introduced the following changes from previous behaviours: + * The '+' feature of the '-t' option now means to auto-calculate the timeout + with the value given being the maximum timeout. The original meaning of + "skipping timeouts instead of abort" is now inherent to the -t option. + +With AFL++ 3.00 we introduced changes that break some previous AFL and AFL++ +behaviours and defaults: + * There are no llvm_mode and gcc_plugin subdirectories anymore and there is + only one compiler: afl-cc. All previous compilers now symlink to this one. + All instrumentation source code is now in the `instrumentation/` folder. + * The gcc_plugin was replaced with a new version submitted by AdaCore that + supports more features. Thank you! + * qemu_mode got upgraded to QEMU 5.1, but to be able to build this a current + ninja build tool version and python3 setuptools are required. + qemu_mode also got new options like snapshotting, instrumenting specific + shared libraries, etc. Additionally QEMU 5.1 supports more CPU targets so + this is really worth it. + * When instrumenting targets, afl-cc will not supersede optimizations anymore + if any were given. This allows to fuzz targets build regularly like those + for debug or release versions. + * afl-fuzz: + * if neither -M or -S is specified, `-S default` is assumed, so more + fuzzers can easily be added later + * `-i` input directory option now descends into subdirectories. It also + does not fatal on crashes and too large files, instead it skips them + and uses them for splicing mutations + * -m none is now default, set memory limits (in MB) with e.g. -m 250 + * deterministic fuzzing is now disabled by default (unless using -M) and + can be enabled with -D + * a caching of testcases can now be performed and can be modified by + editing config.h for TESTCASE_CACHE or by specifying the env variable + `AFL_TESTCACHE_SIZE` (in MB). Good values are between 50-500 (default: 50). + * -M mains do not perform trimming + * examples/ got renamed to utils/ + * libtokencap/ libdislocator/ and qdbi_mode/ were moved to utils/ + * afl-cmin/afl-cmin.bash now search first in PATH and last in AFL_PATH \ No newline at end of file diff --git a/docs/interpreting_output.md b/docs/interpreting_output.md new file mode 100644 index 00000000..327a0ac0 --- /dev/null +++ b/docs/interpreting_output.md @@ -0,0 +1,71 @@ +# Interpreting output + +See the [status_screen.md](status_screen.md) file for information on +how to interpret the displayed stats and monitor the health of the process. Be +sure to consult this file especially if any UI elements are highlighted in red. + +The fuzzing process will continue until you press Ctrl-C. At a minimum, you want +to allow the fuzzer to complete one queue cycle, which may take anywhere from a +couple of hours to a week or so. + +There are three subdirectories created within the output directory and updated +in real-time: + + - queue/ - test cases for every distinctive execution path, plus all the + starting files given by the user. This is the synthesized corpus + mentioned in section 2. + + Before using this corpus for any other purposes, you can shrink + it to a smaller size using the afl-cmin tool. The tool will find + a smaller subset of files offering equivalent edge coverage. + + - crashes/ - unique test cases that cause the tested program to receive a + fatal signal (e.g., SIGSEGV, SIGILL, SIGABRT). The entries are + grouped by the received signal. + + - hangs/ - unique test cases that cause the tested program to time out. The + default time limit before something is classified as a hang is + the larger of 1 second and the value of the -t parameter. + The value can be fine-tuned by setting AFL_HANG_TMOUT, but this + is rarely necessary. + +Crashes and hangs are considered "unique" if the associated execution paths +involve any state transitions not seen in previously-recorded faults. If a +single bug can be reached in multiple ways, there will be some count inflation +early in the process, but this should quickly taper off. + +The file names for crashes and hangs are correlated with the parent, non-faulting +queue entries. This should help with debugging. + +When you can't reproduce a crash found by afl-fuzz, the most likely cause is +that you are not setting the same memory limit as used by the tool. Try: + +```shell +LIMIT_MB=50 +( ulimit -Sv $[LIMIT_MB << 10]; /path/to/tested_binary ... ) +``` + +Change LIMIT_MB to match the -m parameter passed to afl-fuzz. On OpenBSD, +also change -Sv to -Sd. + +Any existing output directory can be also used to resume aborted jobs; try: + +```shell +./afl-fuzz -i- -o existing_output_dir [...etc...] +``` + +If you have gnuplot installed, you can also generate some pretty graphs for any +active fuzzing task using afl-plot. For an example of how this looks like, +see [http://lcamtuf.coredump.cx/afl/plot/](http://lcamtuf.coredump.cx/afl/plot/). + +You can also manually build and install afl-plot-ui, which is a helper utility +for showing the graphs generated by afl-plot in a graphical window using GTK. +You can build and install it as follows + +```shell +sudo apt install libgtk-3-0 libgtk-3-dev pkg-config +cd utils/plot_ui +make +cd ../../ +sudo make install +``` diff --git a/docs/known_limitations.md b/docs/known_limitations.md new file mode 100644 index 00000000..2d8f84a5 --- /dev/null +++ b/docs/known_limitations.md @@ -0,0 +1,36 @@ +# Known limitations & areas for improvement + +Here are some of the most important caveats for AFL: + + - AFL++ detects faults by checking for the first spawned process dying due to + a signal (SIGSEGV, SIGABRT, etc). Programs that install custom handlers for + these signals may need to have the relevant code commented out. In the same + vein, faults in child processes spawned by the fuzzed target may evade + detection unless you manually add some code to catch that. + + - As with any other brute-force tool, the fuzzer offers limited coverage if + encryption, checksums, cryptographic signatures, or compression are used to + wholly wrap the actual data format to be tested. + + To work around this, you can comment out the relevant checks (see + utils/libpng_no_checksum/ for inspiration); if this is not possible, + you can also write a postprocessor, one of the hooks of custom mutators. + See [custom_mutators.md](custom_mutators.md) on how to use + `AFL_CUSTOM_MUTATOR_LIBRARY` + + - There are some unfortunate trade-offs with ASAN and 64-bit binaries. This + isn't due to any specific fault of afl-fuzz. + + - There is no direct support for fuzzing network services, background + daemons, or interactive apps that require UI interaction to work. You may + need to make simple code changes to make them behave in a more traditional + way. Preeny may offer a relatively simple option, too - see: + [https://github.com/zardus/preeny](https://github.com/zardus/preeny) + + Some useful tips for modifying network-based services can be also found at: + [https://www.fastly.com/blog/how-to-fuzz-server-american-fuzzy-lop](https://www.fastly.com/blog/how-to-fuzz-server-american-fuzzy-lop) + + - Occasionally, sentient machines rise against their creators. If this + happens to you, please consult [http://lcamtuf.coredump.cx/prep/](http://lcamtuf.coredump.cx/prep/). + +Beyond this, see [INSTALL.md](INSTALL.md) for platform-specific tips. diff --git a/docs/life_pro_tips.md b/docs/life_pro_tips.md deleted file mode 100644 index 13ffcea0..00000000 --- a/docs/life_pro_tips.md +++ /dev/null @@ -1,87 +0,0 @@ -# AFL "Life Pro Tips" - -Bite-sized advice for those who understand the basics, but can't be bothered -to read or memorize every other piece of documentation for AFL. - -## Get more bang for your buck by using fuzzing dictionaries. - -See [dictionaries/README.md](../dictionaries/README.md) to learn how. - -## You can get the most out of your hardware by parallelizing AFL jobs. - -See [parallel_fuzzing.md](parallel_fuzzing.md) for step-by-step tips. - -## Improve the odds of spotting memory corruption bugs with libdislocator.so! - -It's easy. Consult [utils/libdislocator/README.md](../utils/libdislocator/README.md) for usage tips. - -## Want to understand how your target parses a particular input file? - -Try the bundled `afl-analyze` tool; it's got colors and all! - -## You can visually monitor the progress of your fuzzing jobs. - -Run the bundled `afl-plot` utility to generate browser-friendly graphs. - -## Need to monitor AFL jobs programmatically? -Check out the `fuzzer_stats` file in the AFL output dir or try `afl-whatsup`. - -## Puzzled by something showing up in red or purple in the AFL UI? -It could be important - consult docs/status_screen.md right away! - -## Know your target? Convert it to persistent mode for a huge performance gain! -Consult section #5 in README.llvm.md for tips. - -## Using clang? -Check out instrumentation/ for a faster alternative to afl-gcc! - -## Did you know that AFL can fuzz closed-source or cross-platform binaries? -Check out qemu_mode/README.md and unicorn_mode/README.md for more. - -## Did you know that afl-fuzz can minimize any test case for you? -Try the bundled `afl-tmin` tool - and get small repro files fast! - -## Not sure if a crash is exploitable? AFL can help you figure it out. Specify -`-C` to enable the peruvian were-rabbit mode. - -## Trouble dealing with a machine uprising? Relax, we've all been there. - -Find essential survival tips at http://lcamtuf.coredump.cx/prep/. - -## Want to automatically spot non-crashing memory handling bugs? - -Try running an AFL-generated corpus through ASAN, MSAN, or Valgrind. - -## Good selection of input files is critical to a successful fuzzing job. - -See docs/perf_tips.md for pro tips. - -## You can improve the odds of automatically spotting stack corruption issues. - -Specify `AFL_HARDEN=1` in the environment to enable hardening flags. - -## Bumping into problems with non-reproducible crashes? -It happens, but usually -isn't hard to diagnose. See section #7 in README.md for tips. - -## Fuzzing is not just about memory corruption issues in the codebase. -Add some -sanity-checking `assert()` / `abort()` statements to effortlessly catch logic bugs. - -## Hey kid... pssst... want to figure out how AFL really works? - -Check out docs/technical_details.md for all the gory details in one place! - -## There's a ton of third-party helper tools designed to work with AFL! - -Be sure to check out docs/sister_projects.md before writing your own. - -## Need to fuzz the command-line arguments of a particular program? - -You can find a simple solution in utils/argv_fuzzing. - -## Attacking a format that uses checksums? - -Remove the checksum-checking code or use a postprocessor! -See `afl_custom_post_process` in custom_mutators/examples/example.c for more. - diff --git a/docs/parallel_fuzzing.md b/docs/parallel_fuzzing.md index 90e12e89..e37276a5 100644 --- a/docs/parallel_fuzzing.md +++ b/docs/parallel_fuzzing.md @@ -4,7 +4,7 @@ This document talks about synchronizing afl-fuzz jobs on a single machine or across a fleet of systems. See README.md for the general instruction manual. Note that this document is rather outdated. please refer to the main document -section on multiple core usage [../README.md#Using multiple cores](../README.md#b-using-multiple-coresthreads) +section on multiple core usage [fuzzing_expert.md#Using multiple cores](fuzzing_expert.md#b-using-multiple-cores) for up to date strategies! ## 1) Introduction diff --git a/docs/rpc_statsd.md b/docs/rpc_statsd.md index 898ad099..9b3d8d40 100644 --- a/docs/rpc_statsd.md +++ b/docs/rpc_statsd.md @@ -1,143 +1,155 @@ -# Remote monitoring with StatsD +# Remote monitoring and metrics visualization -StatsD allows you to receive and aggregate metrics from a wide range of applications and retransmit them to the backend of your choice. -This enables you to create nice and readable dashboards containing all the information you need on your fuzzer instances. -No need to write your own statistics parsing system, deploy and maintain it to all your instances, sync with your graph rendering system... +AFL++ can send out metrics as StatsD messages. For remote monitoring and visualization of the metrics, you can set up a tool chain. For example, with Prometheus and Grafana. All tools are free and open source. -The available metrics are : +This enables you to create nice and readable dashboards containing all the information you need on your fuzzer instances. There is no need to write your own statistics parsing system, deploy and maintain it to all your instances, and sync with your graph rendering system. + +Compared to the default integrated UI of AFL++, this can help you to visualize trends and the fuzzing state over time. You might be able to see when the fuzzing process has reached a state of no progress and visualize what are the "best strategies" for your targets (according to your own criteria). You can do so without logging into each instance individually. + + + +This is an example visualization with Grafana. The dashboard can be imported with [this JSON template](resources/grafana-afl++.json). + +## AFL++ metrics and StatsD + +StatsD allows you to receive and aggregate metrics from a wide range of applications and retransmit them to a backend of your choice. + +From AFL++, StatsD can receive the following metrics: +- cur_path - cycle_done - cycles_wo_finds +- edges_found - execs_done - execs_per_sec -- paths_total +- havoc_expansion +- max_depth - paths_favored - paths_found - paths_imported -- max_depth -- cur_path +- paths_total - pending_favs - pending_total -- variable_paths +- slowest_exec_ms +- total_crashes - unique_crashes - unique_hangs -- total_crashes -- slowest_exec_ms -- edges_found - var_byte_count -- havoc_expansion +- variable_paths -Compared to the default integrated UI, these metrics give you the opportunity to visualize trends and fuzzing state over time. -By doing so, you might be able to see when the fuzzing process has reached a state of no progress, visualize what are the "best strategies" -(according to your own criteria) for your targets, etc. And doing so without requiring to log into each instance manually. +Depending on your StatsD server, you will be able to monitor, trigger alerts, or perform actions based on these metrics (for example: alert on slow exec/s for a new build, threshold of crashes, time since last crash > X, and so on). -An example visualisation may look like the following: - +## Setting environment variables in AFL++ -*Notes: The exact same dashboard can be imported with [this JSON template](resources/grafana-afl++.json).* +1. To enable the StatsD metrics collection on your fuzzer instances, set the environment variable `AFL_STATSD=1`. By default, AFL++ will send the metrics over UDP to 127.0.0.1:8125. -## How to use +2. To enable tags for each metric based on their format (banner and afl_version), set the environment variable `AFL_STATSD_TAGS_FLAVOR`. By default, no tags will be added to the metrics. -To enable the StatsD reporting on your fuzzer instances, you need to set the environment variable `AFL_STATSD=1`. + The available values are the following: + - `dogstatsd` + - `influxdb` + - `librato` + - `signalfx` + + For more information on environment variables, see [env_variables.md](env_variables.md). -Setting `AFL_STATSD_TAGS_FLAVOR` to the provider of your choice will assign tags / labels to each metric based on their format. -The possible values are `dogstatsd`, `librato`, `signalfx` or `influxdb`. -For more information on these env vars, check out `docs/env_variables.md`. + Note: When using multiple fuzzer instances with StatsD it is *strongly* recommended to set up `AFL_STATSD_TAGS_FLAVOR` to match your StatsD server. This will allow you to see individual fuzzer performance, detect bad ones, and see the progress of each strategy. -The simplest way of using this feature is to use any metric provider and change the host/port of your StatsD daemon, -with `AFL_STATSD_HOST` and `AFL_STATSD_PORT`, if required (defaults are `localhost` and port `8125`). -To get started, here are some instructions with free and open source tools. -The following setup is based on Prometheus, statsd_exporter and Grafana. -Grafana here is not mandatory, but gives you some nice graphs and features. +3. Optional: To set the host and port of your StatsD daemon, set `AFL_STATSD_HOST` and `AFL_STATSD_PORT`. The default values are `localhost` and `8125`. -Depending on your setup and infrastructure, you may want to run these applications not on your fuzzer instances. -Only one instance of these 3 application is required for all your fuzzers. +## Installing and setting up StatsD, Prometheus, and Grafana -To simplify everything, we will use Docker and docker-compose. -Make sure you have them both installed. On most common Linux distributions, it's as simple as: +The easiest way to install and set up the infrastructure is with Docker and Docker Compose. -```sh -curl -fsSL https://get.docker.com -o get-docker.sh -sh get-docker.sh -``` +Depending on your fuzzing setup and infrastructure, you may not want to run these applications on your fuzzer instances. This setup may be modified before use in a production environment; for example, adding passwords, creating volumes for storage, tweaking the metrics gathering to get host metrics (CPU, RAM, and so on). -Once that's done, we can create the infrastructure. -Create and move into the directory of your choice. This will store all the configurations files required. - -First, create a `docker-compose.yml` containing the following: -```yml -version: '3' - -networks: - statsd-net: - driver: bridge - -services: - prometheus: - image: prom/prometheus - container_name: prometheus - volumes: - - ./prometheus.yml:/prometheus.yml - command: - - '--config.file=/prometheus.yml' - restart: unless-stopped - ports: - - "9090:9090" - networks: - - statsd-net - - statsd_exporter: - image: prom/statsd-exporter - container_name: statsd_exporter - volumes: - - ./statsd_mapping.yml:/statsd_mapping.yml - command: - - "--statsd.mapping-config=/statsd_mapping.yml" - ports: - - "9102:9102/tcp" - - "8125:9125/udp" - networks: - - statsd-net - - grafana: - image: grafana/grafana - container_name: grafana - restart: unless-stopped - ports: - - "3000:3000" - networks: - - statsd-net -``` +For all your fuzzing instances, only one instance of Prometheus and Grafana is required. The [statsd exporter](https://registry.hub.docker.com/r/prom/statsd-exporter) converts the StatsD metrics to Prometheus. If you are using a provider that supports StatsD directly, you can skip this part of the setup." -Then `prometheus.yml` -```yml -global: - scrape_interval: 15s - evaluation_interval: 15s +You can create and move the infrastructure files into a directory of your choice. The directory will store all the required configuration files. -scrape_configs: - - job_name: 'fuzzing_metrics' - static_configs: - - targets: ['statsd_exporter:9102'] -``` +To install and set up Prometheus and Grafana: -And finally `statsd_mapping.yml` -```yml -mappings: -- match: "fuzzing.*" - name: "fuzzing" - labels: - type: "$1" -``` +1. Install Docker and Docker Compose: + + ```sh + curl -fsSL https://get.docker.com -o get-docker.sh + sh get-docker.sh + ``` -Run `docker-compose up -d`. +2. Create a `docker-compose.yml` containing the following: + ```yml + version: '3' -Everything should now be setup, you are now able to run your fuzzers with + networks: + statsd-net: + driver: bridge + + services: + prometheus: + image: prom/prometheus + container_name: prometheus + volumes: + - ./prometheus.yml:/prometheus.yml + command: + - '--config.file=/prometheus.yml' + restart: unless-stopped + ports: + - "9090:9090" + networks: + - statsd-net + + statsd_exporter: + image: prom/statsd-exporter + container_name: statsd_exporter + volumes: + - ./statsd_mapping.yml:/statsd_mapping.yml + command: + - "--statsd.mapping-config=/statsd_mapping.yml" + ports: + - "9102:9102/tcp" + - "8125:9125/udp" + networks: + - statsd-net + + grafana: + image: grafana/grafana + container_name: grafana + restart: unless-stopped + ports: + - "3000:3000" + networks: + - statsd-net + ``` + +3. Create a `prometheus.yml` containing the following: + + ```yml + global: + scrape_interval: 15s + evaluation_interval: 15s + + scrape_configs: + - job_name: 'fuzzing_metrics' + static_configs: + - targets: ['statsd_exporter:9102'] + ``` + +4. Create a `statsd_mapping.yml` containing the following: + ```yml + mappings: + - match: "fuzzing.*" + name: "fuzzing" + labels: + type: "$1" + ``` + +5. Run `docker-compose up -d`. + +## Running AFL++ with StatsD + +To run your fuzzing instances: ``` -AFL_STATSD_TAGS_FLAVOR=dogstatsd AFL_STATSD=1 afl-fuzz -M test-fuzzer-1 -i i -o o ./bin/my-application @@ -AFL_STATSD_TAGS_FLAVOR=dogstatsd AFL_STATSD=1 afl-fuzz -S test-fuzzer-2 -i i -o o ./bin/my-application @@ +AFL_STATSD_TAGS_FLAVOR=dogstatsd AFL_STATSD=1 afl-fuzz -M test-fuzzer-1 -i i -o o [./bin/my-application] @@ +AFL_STATSD_TAGS_FLAVOR=dogstatsd AFL_STATSD=1 afl-fuzz -S test-fuzzer-2 -i i -o o [./bin/my-application] @@ ... ``` - -This setup may be modified before use in a production environment. Depending on your needs: adding passwords, creating volumes for storage, -tweaking the metrics gathering to get host metrics (CPU, RAM ...). diff --git a/docs/tools.md b/docs/tools.md new file mode 100644 index 00000000..ba96d0ce --- /dev/null +++ b/docs/tools.md @@ -0,0 +1,33 @@ +# Tools that help fuzzing with AFL++ + +Speeding up fuzzing: + * [libfiowrapper](https://github.com/marekzmyslowski/libfiowrapper) - if the function you want to fuzz requires loading a file, this allows using the shared memory testcase feature :-) - recommended. + +Minimization of test cases: + * [afl-pytmin](https://github.com/ilsani/afl-pytmin) - a wrapper for afl-tmin that tries to speed up the process of minimization of a single test case by using many CPU cores. + * [afl-ddmin-mod](https://github.com/MarkusTeufelberger/afl-ddmin-mod) - a variation of afl-tmin based on the ddmin algorithm. + * [halfempty](https://github.com/googleprojectzero/halfempty) - is a fast utility for minimizing test cases by Tavis Ormandy based on parallelization. + +Distributed execution: + * [disfuzz-afl](https://github.com/MartijnB/disfuzz-afl) - distributed fuzzing for AFL. + * [AFLDFF](https://github.com/quantumvm/AFLDFF) - AFL distributed fuzzing framework. + * [afl-launch](https://github.com/bnagy/afl-launch) - a tool for the execution of many AFL instances. + * [afl-mothership](https://github.com/afl-mothership/afl-mothership) - management and execution of many synchronized AFL fuzzers on AWS cloud. + * [afl-in-the-cloud](https://github.com/abhisek/afl-in-the-cloud) - another script for running AFL in AWS. + +Deployment, management, monitoring, reporting + * [afl-utils](https://gitlab.com/rc0r/afl-utils) - a set of utilities for automatic processing/analysis of crashes and reducing the number of test cases. + * [afl-other-arch](https://github.com/shellphish/afl-other-arch) - is a set of patches and scripts for easily adding support for various non-x86 architectures for AFL. + * [afl-trivia](https://github.com/bnagy/afl-trivia) - a few small scripts to simplify the management of AFL. + * [afl-monitor](https://github.com/reflare/afl-monitor) - a script for monitoring AFL. + * [afl-manager](https://github.com/zx1340/afl-manager) - a web server on Python for managing multi-afl. + * [afl-remote](https://github.com/block8437/afl-remote) - a web server for the remote management of AFL instances. + * [afl-extras](https://github.com/fekir/afl-extras) - shell scripts to parallelize afl-tmin, startup, and data collection. + +Crash processing + * [afl-crash-analyzer](https://github.com/floyd-fuh/afl-crash-analyzer) - another crash analyzer for AFL. + * [fuzzer-utils](https://github.com/ThePatrickStar/fuzzer-utils) - a set of scripts for the analysis of results. + * [atriage](https://github.com/Ayrx/atriage) - a simple triage tool. + * [afl-kit](https://github.com/kcwu/afl-kit) - afl-cmin on Python. + * [AFLize](https://github.com/d33tah/aflize) - a tool that automatically generates builds of debian packages suitable for AFL. + * [afl-fid](https://github.com/FoRTE-Research/afl-fid) - a set of tools for working with input data. \ No newline at end of file diff --git a/docs/triaging_crashes.md b/docs/triaging_crashes.md new file mode 100644 index 00000000..21ccecaa --- /dev/null +++ b/docs/triaging_crashes.md @@ -0,0 +1,46 @@ +# Triaging crashes + +The coverage-based grouping of crashes usually produces a small data set that +can be quickly triaged manually or with a very simple GDB or Valgrind script. +Every crash is also traceable to its parent non-crashing test case in the +queue, making it easier to diagnose faults. + +Having said that, it's important to acknowledge that some fuzzing crashes can be +difficult to quickly evaluate for exploitability without a lot of debugging and +code analysis work. To assist with this task, afl-fuzz supports a very unique +"crash exploration" mode enabled with the -C flag. + +In this mode, the fuzzer takes one or more crashing test cases as the input +and uses its feedback-driven fuzzing strategies to very quickly enumerate all +code paths that can be reached in the program while keeping it in the +crashing state. + +Mutations that do not result in a crash are rejected; so are any changes that +do not affect the execution path. + +The output is a small corpus of files that can be very rapidly examined to see +what degree of control the attacker has over the faulting address, or whether +it is possible to get past an initial out-of-bounds read - and see what lies +beneath. + +Oh, one more thing: for test case minimization, give afl-tmin a try. The tool +can be operated in a very simple way: + +```shell +./afl-tmin -i test_case -o minimized_result -- /path/to/program [...] +``` + +The tool works with crashing and non-crashing test cases alike. In the crash +mode, it will happily accept instrumented and non-instrumented binaries. In the +non-crashing mode, the minimizer relies on standard AFL++ instrumentation to make +the file simpler without altering the execution path. + +The minimizer accepts the -m, -t, -f and @@ syntax in a manner compatible with +afl-fuzz. + +Another tool in AFL++ is the afl-analyze tool. It takes an input +file, attempts to sequentially flip bytes, and observes the behavior of the +tested program. It then color-codes the input based on which sections appear to +be critical, and which are not; while not bulletproof, it can often offer quick +insights into complex file formats. More info about its operation can be found +near the end of [technical_details.md](technical_details.md). \ No newline at end of file diff --git a/docs/tutorials.md b/docs/tutorials.md new file mode 100644 index 00000000..cc7ed130 --- /dev/null +++ b/docs/tutorials.md @@ -0,0 +1,26 @@ +# Tutorials + +Here are some good writeups to show how to effectively use AFL++: + +* [https://aflplus.plus/docs/tutorials/libxml2_tutorial/](https://aflplus.plus/docs/tutorials/libxml2_tutorial/) +* [https://bananamafia.dev/post/gb-fuzz/](https://bananamafia.dev/post/gb-fuzz/) +* [https://securitylab.github.com/research/fuzzing-challenges-solutions-1](https://securitylab.github.com/research/fuzzing-challenges-solutions-1) +* [https://securitylab.github.com/research/fuzzing-software-2](https://securitylab.github.com/research/fuzzing-software-2) +* [https://securitylab.github.com/research/fuzzing-sockets-FTP](https://securitylab.github.com/research/fuzzing-sockets-FTP) +* [https://securitylab.github.com/research/fuzzing-sockets-FreeRDP](https://securitylab.github.com/research/fuzzing-sockets-FreeRDP) +* [https://securitylab.github.com/research/fuzzing-apache-1](https://securitylab.github.com/research/fuzzing-apache-1) + +If you do not want to follow a tutorial but rather try an exercise type of +training, then we can highly recommend the following: + +* [https://github.com/antonio-morales/Fuzzing101](https://github.com/antonio-morales/Fuzzing101) + +If you are interested in fuzzing structured data (where you define what the +structure is), these links have you covered: + +* Superion for AFL++: [https://github.com/adrian-rt/superion-mutator](https://github.com/adrian-rt/superion-mutator) +* libprotobuf for AFL++: [https://github.com/P1umer/AFLplusplus-protobuf-mutator](https://github.com/P1umer/AFLplusplus-protobuf-mutator) +* libprotobuf raw: [https://github.com/bruce30262/libprotobuf-mutator_fuzzing_learning/tree/master/4_libprotobuf_aflpp_custom_mutator](https://github.com/bruce30262/libprotobuf-mutator_fuzzing_learning/tree/master/4_libprotobuf_aflpp_custom_mutator) +* libprotobuf for old AFL++ API: [https://github.com/thebabush/afl-libprotobuf-mutator](https://github.com/thebabush/afl-libprotobuf-mutator) + +If you find other good ones, please send them to us :-) \ No newline at end of file diff --git a/frida_mode/GNUmakefile b/frida_mode/GNUmakefile index 3e35e2f6..b5fee7a6 100644 --- a/frida_mode/GNUmakefile +++ b/frida_mode/GNUmakefile @@ -30,8 +30,7 @@ AFL_CFLAGS:=-Wno-unused-parameter \ LDFLAGS+=-shared \ -lpthread \ - -lresolv \ - -ldl + -lresolv ifdef DEBUG CFLAGS+=-Werror \ @@ -71,12 +70,33 @@ ifdef DEBUG endif LDFLAGS+= -z noexecstack \ -Wl,--gc-sections \ - -Wl,--exclude-libs,ALL + -Wl,--exclude-libs,ALL \ + -ldl \ + -lrt LDSCRIPT:=-Wl,--version-script=$(PWD)frida.map endif ifeq "$(shell uname)" "Linux" OS:=linux + ifneq "$(findstring musl, $(shell ldd --version 2>&1 | head -n 1))" "" + CFLAGS+= -D__MUSL__ + endif +endif + +ifneq "$(findstring android, $(shell $(CC) --version 2>/dev/null))" "" + OS:=android + ifneq "$(findstring aarch64, $(shell $(CC) --version 2>/dev/null))" "" + ARCH:=arm64 + endif + ifneq "$(findstring arm, $(shell $(CC) --version 2>/dev/null))" "" + ARCH:=arm + endif + ifneq "$(findstring x86_64, $(shell $(CC) --version 2>/dev/null))" "" + ARCH:=x86_64 + endif + ifneq "$(findstring i686, $(shell $(CC) --version 2>/dev/null))" "" + ARCH:=x86 + endif endif ifndef OS diff --git a/frida_mode/README.md b/frida_mode/README.md index 165f8089..bb194080 100644 --- a/frida_mode/README.md +++ b/frida_mode/README.md @@ -55,6 +55,20 @@ tests in 32-bit mode, run `make ARCH=x86 frida`. When switching between architectures it may be necessary to run `make clean` first for a given build target to remove previously generated binaries for a different architecture. +### Android + +In order to build, you need to download the Android SDK. + +``` +https://developer.android.com/ndk/downloads +``` + +Then creating locally a standalone chain as follow. + +``` +https://developer.android.com/ndk/guides/standalone_toolchain +``` + ## Usage FRIDA mode added some small modifications to `afl-fuzz` and similar tools @@ -274,6 +288,12 @@ ucomisd 2 ( 0.86%) * `AFL_FRIDA_STATS_INTERVAL` - The maximum frequency to output statistics information. Stats will be written whenever they are updated if the given interval has elapsed since last time they were written. +* `AFL_FRIDA_TRACEABLE` - Set the child process to be traceable by any process +to aid debugging and overcome the restrictions imposed by YAMA. Supported on +Linux only. Permits a non-root user to use `gcore` or similar to collect a core +dump of the instrumented target. Note that in order to capture the core dump you +must set a sufficient timeout (using `-t`) to avoid `afl-fuzz` killing the +process whilst it is being dumped. ## FASAN - Frida Address Sanitizer Mode Frida mode also supports FASAN. The design of this is actually quite simple and diff --git a/frida_mode/frida.map b/frida_mode/frida.map index 0fc48aa6..e2ae87a7 100644 --- a/frida_mode/frida.map +++ b/frida_mode/frida.map @@ -33,6 +33,7 @@ js_api_set_stats_interval; js_api_set_stderr; js_api_set_stdout; + js_api_set_traceable; local: *; diff --git a/frida_mode/include/entry.h b/frida_mode/include/entry.h index 3f0a4ecc..edc41467 100644 --- a/frida_mode/include/entry.h +++ b/frida_mode/include/entry.h @@ -4,6 +4,7 @@ #include "frida-gumjs.h" extern guint64 entry_point; +extern gboolean traceable; extern gboolean entry_compiled; extern gboolean entry_run; @@ -15,5 +16,7 @@ void entry_start(void); void entry_prologue(GumStalkerIterator *iterator, GumStalkerOutput *output); +void entry_on_fork(void); + #endif diff --git a/frida_mode/include/instrument.h b/frida_mode/include/instrument.h index 909b2a2c..cac5ee93 100644 --- a/frida_mode/include/instrument.h +++ b/frida_mode/include/instrument.h @@ -29,6 +29,7 @@ GumStalkerTransformer *instrument_get_transformer(void); /* Functions to be implemented by the different architectures */ gboolean instrument_is_coverage_optimize_supported(void); +void instrument_coverage_optimize_init(void); void instrument_coverage_optimize(const cs_insn * instr, GumStalkerOutput *output); diff --git a/frida_mode/include/ranges.h b/frida_mode/include/ranges.h index 0220a59d..3bd9eaa6 100644 --- a/frida_mode/include/ranges.h +++ b/frida_mode/include/ranges.h @@ -10,6 +10,8 @@ extern gboolean ranges_inst_jit; void ranges_config(void); void ranges_init(void); +void ranges_print_debug_maps(void); + gboolean range_is_excluded(GumAddress address); void ranges_exclude(); diff --git a/frida_mode/include/seccomp.h b/frida_mode/include/seccomp.h index 2c037ff7..7e8a7d25 100644 --- a/frida_mode/include/seccomp.h +++ b/frida_mode/include/seccomp.h @@ -1,15 +1,95 @@ #ifndef _SECCOMP_H #define _SECCOMP_H -#include <linux/seccomp.h> +#ifndef __APPLE__ -#include "frida-gumjs.h" + #include <stdint.h> + #include <linux/filter.h> -#define SECCOMP_SOCKET_SEND_FD 0x1D3 -#define SECCOMP_SOCKET_RECV_FD 0x1D4 + #include "frida-gumjs.h" -#define SECCOMP_OUTPUT_FILE_FD 0x1D5 -#define SECCOMP_PARENT_EVENT_FD 0x1D6 + /******************************************************************************/ + #define PR_SET_NO_NEW_PRIVS 38 + + #define SECCOMP_SET_MODE_STRICT 0 + #define SECCOMP_SET_MODE_FILTER 1 + #define SECCOMP_GET_ACTION_AVAIL 2 + #define SECCOMP_GET_NOTIF_SIZES 3 + + #define SECCOMP_IOC_MAGIC '!' + #define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) + #define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) + #define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) + #define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + + /* Flags for seccomp notification fd ioctl. */ + #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) + #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, struct seccomp_notif_resp) + #define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) + + #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) + #define SECCOMP_RET_ALLOW 0x7fff0000U + #define SECCOMP_RET_USER_NOTIF 0x7fc00000U + + #define SYS_seccomp __NR_seccomp + #ifndef __NR_seccomp + #if defined(__arm__) + #define __NR_seccomp 383 + #elif defined(__aarch64__) + #define __NR_seccomp 277 + #elif defined(__x86_64__) + #define __NR_seccomp 317 + #elif defined(__i386__) + #define __NR_seccomp 354 + #else + #pragma error "Unsupported architecture" + #endif + #endif + + #define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0) + +struct seccomp_notif_resp { + + __u64 id; + __s64 val; + __s32 error; + __u32 flags; + +}; + +struct seccomp_data { + + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; + +}; + +struct seccomp_notif { + + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; + +}; + +struct seccomp_notif_sizes { + + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; + +}; + + /******************************************************************************/ + + #define SECCOMP_SOCKET_SEND_FD 0x1D3 + #define SECCOMP_SOCKET_RECV_FD 0x1D4 + + #define SECCOMP_OUTPUT_FILE_FD 0x1D5 + #define SECCOMP_PARENT_EVENT_FD 0x1D6 enum { @@ -319,23 +399,19 @@ enum { }; -extern char *seccomp_filename; - typedef void (*seccomp_child_func_t)(int event_fd, void *ctx); typedef void (*seccomp_filter_callback_t)(struct seccomp_notif * req, struct seccomp_notif_resp *resp, GumReturnAddressArray * frames); -void seccomp_config(void); -void seccomp_init(void); -void seccomp_on_fork(void); -void seccomp_print(char *format, ...); - void seccomp_atomic_set(volatile bool *ptr, bool val); bool seccomp_atomic_try_set(volatile bool *ptr, bool val); void seccomp_atomic_wait(volatile bool *ptr, bool val); +void seccomp_callback_parent(void); +void seccomp_callback_initialize(void); + void seccomp_child_run(seccomp_child_func_t child_func, void *ctx, pid_t *child, int *event_fd); void seccomp_child_wait(int event_fd); @@ -349,6 +425,8 @@ int seccomp_filter_install(pid_t child); void seccomp_filter_child_install(void); void seccomp_filter_run(int fd, seccomp_filter_callback_t callback); +void seccomp_print(char *format, ...); + void seccomp_socket_create(int *sock); void seccomp_socket_send(int sockfd, int fd); int seccomp_socket_recv(int sockfd); @@ -356,4 +434,11 @@ int seccomp_socket_recv(int sockfd); char *seccomp_syscall_lookup(int id); #endif +extern char *seccomp_filename; + +void seccomp_config(void); +void seccomp_init(void); +void seccomp_on_fork(void); + +#endif diff --git a/frida_mode/many-linux/Dockerfile b/frida_mode/many-linux/Dockerfile index 170f0757..6d077dad 100644 --- a/frida_mode/many-linux/Dockerfile +++ b/frida_mode/many-linux/Dockerfile @@ -1,10 +1,6 @@ FROM fridadotre/manylinux-x86_64 -COPY realpath /bin/realpath -RUN chmod +x /bin/realpath - RUN yum -y install xz -RUN yum -y install vim-common WORKDIR /AFLplusplus ENV CFLAGS="\ diff --git a/frida_mode/many-linux/GNUmakefile b/frida_mode/many-linux/GNUmakefile index 03b619f6..9992d4fe 100644 --- a/frida_mode/many-linux/GNUmakefile +++ b/frida_mode/many-linux/GNUmakefile @@ -2,17 +2,22 @@ PWD:=$(shell pwd)/ ROOT:=$(PWD)../../ BUILD_DIR:=$(PWD)build/ -.PHONY: all clean shell +.PHONY: all build docker clean shell -all: - docker build --tag many-afl-frida . +all: docker docker run --rm \ -v $(ROOT):/AFLplusplus \ many-afl-frida \ make -C /AFLplusplus/frida_mode clean all -$(BUILD_DIR): - mkdir -p $@ +build: + docker run --rm \ + -v $(ROOT):/AFLplusplus \ + many-afl-frida \ + make -C /AFLplusplus/frida_mode + +docker: + docker build --tag many-afl-frida . clean: docker images --filter 'dangling=true' -q --no-trunc | xargs -L1 docker rmi --force diff --git a/frida_mode/many-linux/realpath b/frida_mode/many-linux/realpath deleted file mode 100755 index 1fdc49a7..00000000 --- a/frida_mode/many-linux/realpath +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/sh -readlink -f -- "$@" diff --git a/frida_mode/src/entry.c b/frida_mode/src/entry.c index 186ddd3a..c51e202f 100644 --- a/frida_mode/src/entry.c +++ b/frida_mode/src/entry.c @@ -1,5 +1,9 @@ #include <dlfcn.h> +#if defined(__linux__) && !defined(__ANDROID__) + #include <sys/prctl.h> +#endif + #include "frida-gumjs.h" #include "debug.h" @@ -16,6 +20,7 @@ extern void __afl_manual_init(); guint64 entry_point = 0; +gboolean traceable = FALSE; gboolean entry_compiled = FALSE; gboolean entry_run = FALSE; @@ -26,21 +31,48 @@ static void entry_launch(void) { /* Child here */ entry_run = TRUE; + entry_on_fork(); instrument_on_fork(); seccomp_on_fork(); stats_on_fork(); } +#if defined(__linux__) && !defined(__ANDROID__) +void entry_on_fork(void) { + + if (traceable) { + + if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY) < 0) { + + FATAL("Failed to PR_SET_PTRACER"); + + } + + } + +} + +#else +void entry_on_fork(void) { + + if (traceable) { WARNF("AFL_FRIDA_TRACEABLE unsupported"); } + +} + +#endif + void entry_config(void) { entry_point = util_read_address("AFL_ENTRYPOINT"); + if (getenv("AFL_FRIDA_TRACEABLE") != NULL) { traceable = TRUE; } } void entry_init(void) { OKF("entry_point: 0x%016" G_GINT64_MODIFIER "X", entry_point); + OKF("dumpable: [%c]", traceable ? 'X' : ' '); if (dlopen(NULL, RTLD_NOW) == NULL) { FATAL("Failed to dlopen: %d", errno); } diff --git a/frida_mode/src/instrument/instrument.c b/frida_mode/src/instrument/instrument.c index fd0982f8..81d85aa1 100644 --- a/frida_mode/src/instrument/instrument.c +++ b/frida_mode/src/instrument/instrument.c @@ -341,8 +341,14 @@ void instrument_init(void) { * parallel fuzzing. The seed itself, doesn't have to be random, it * just needs to be different for each instance. */ + guint64 tid; +#if defined(__APPLE__) + pthread_threadid_np(NULL, &tid); +#else + tid = syscall(SYS_gettid); +#endif instrument_hash_seed = g_get_monotonic_time() ^ - (((guint64)getpid()) << 32) ^ syscall(SYS_gettid); + (((guint64)getpid()) << 32) ^ tid; } @@ -350,6 +356,7 @@ void instrument_init(void) { instrument_hash_seed); instrument_hash_zero = instrument_get_offset_hash(0); + instrument_coverage_optimize_init(); instrument_debug_init(); instrument_coverage_init(); asan_init(); diff --git a/frida_mode/src/instrument/instrument_arm32.c b/frida_mode/src/instrument/instrument_arm32.c index 0e15940a..4b0a648e 100644 --- a/frida_mode/src/instrument/instrument_arm32.c +++ b/frida_mode/src/instrument/instrument_arm32.c @@ -22,6 +22,10 @@ void instrument_coverage_optimize(const cs_insn * instr, } +void instrument_coverage_optimize_init(void) { + WARNF("Optimized coverage not supported on this architecture"); +} + void instrument_flush(GumStalkerOutput *output) { gum_arm_writer_flush(output->writer.arm); diff --git a/frida_mode/src/instrument/instrument_arm64.c b/frida_mode/src/instrument/instrument_arm64.c index cf37e048..80d1d845 100644 --- a/frida_mode/src/instrument/instrument_arm64.c +++ b/frida_mode/src/instrument/instrument_arm64.c @@ -95,6 +95,9 @@ void instrument_coverage_optimize(const cs_insn * instr, } +void instrument_coverage_optimize_init(void) { +} + void instrument_flush(GumStalkerOutput *output) { gum_arm64_writer_flush(output->writer.arm64); diff --git a/frida_mode/src/instrument/instrument_coverage.c b/frida_mode/src/instrument/instrument_coverage.c index 46c816bc..513df29a 100644 --- a/frida_mode/src/instrument/instrument_coverage.c +++ b/frida_mode/src/instrument/instrument_coverage.c @@ -711,7 +711,6 @@ void instrument_coverage_normal_init(void) { void instrument_coverage_unstable_find_output(void) { - pid_t parent = getpid(); gchar *fds_name = g_strdup_printf("/proc/%d/fd/", getppid()); gchar *root = g_file_read_link("/proc/self/root", NULL); diff --git a/frida_mode/src/instrument/instrument_x64.c b/frida_mode/src/instrument/instrument_x64.c index fec8afbb..a7eb650a 100644 --- a/frida_mode/src/instrument/instrument_x64.c +++ b/frida_mode/src/instrument/instrument_x64.c @@ -1,105 +1,307 @@ +#include <fcntl.h> +#include <stddef.h> +#include <sys/mman.h> +#include <sys/shm.h> + +#if defined(__linux__) +#if !defined(__ANDROID__) +#include <asm/prctl.h> +#include <sys/syscall.h> +#else +#include <linux/ashmem.h> +#endif +#endif + #include "frida-gumjs.h" #include "config.h" +#include "debug.h" #include "instrument.h" +#include "ranges.h" #if defined(__x86_64__) -static GumAddress current_log_impl = GUM_ADDRESS(0); +#ifndef MAP_FIXED_NOREPLACE + #ifdef MAP_EXCL + #define MAP_FIXED_NOREPLACE MAP_EXCL | MAP_FIXED + #else + #define MAP_FIXED_NOREPLACE MAP_FIXED + #endif +#endif -static const guint8 afl_log_code[] = { +gboolean instrument_is_coverage_optimize_supported(void) { - 0x9c, /* pushfq */ - 0x51, /* push rcx */ - 0x52, /* push rdx */ + return true; - 0x48, 0x8b, 0x0d, 0x26, - 0x00, 0x00, 0x00, /* mov rcx, sym.&previous_pc */ - 0x48, 0x8b, 0x11, /* mov rdx, qword [rcx] */ - 0x48, 0x31, 0xfa, /* xor rdx, rdi */ +} - 0x48, 0x03, 0x15, 0x11, - 0x00, 0x00, 0x00, /* add rdx, sym._afl_area_ptr_ptr */ +static gboolean instrument_coverage_in_range(gssize offset) { - 0x80, 0x02, 0x01, /* add byte ptr [rdx], 1 */ - 0x80, 0x12, 0x00, /* adc byte ptr [rdx], 0 */ - 0x66, 0xd1, 0xcf, /* ror di, 1 */ - 0x48, 0x89, 0x39, /* mov qword [rcx], rdi */ + return (offset >= G_MININT32 && offset <= G_MAXINT32); - 0x5a, /* pop rdx */ - 0x59, /* pop rcx */ - 0x9d, /* popfq */ +} - 0xc3, /* ret */ + #pragma pack(push, 1) +typedef struct { - 0x90 + // cur_location = (block_address >> 4) ^ (block_address << 8); + // shared_mem[cur_location ^ prev_location]++; + // prev_location = cur_location >> 1; - /* Read-only data goes here: */ - /* uint8_t* __afl_area_ptr */ - /* uint64_t* &previous_pc */ + // => 0x7ffff6cfb086: lea rsp,[rsp-0x80] + // 0x7ffff6cfb08b: pushf + // 0x7ffff6cfb08c: push rsi + // 0x7ffff6cfb08d: mov rsi,0x228 + // 0x7ffff6cfb094: xchg QWORD PTR [rip+0x3136a5],rsi # 0x7ffff700e740 + // 0x7ffff6cfb09b: xor rsi,0x451 + // 0x7ffff6cfb0a2: add BYTE PTR [rsi+0x10000],0x1 + // 0x7ffff6cfb0a9: adc BYTE PTR [rsi+0x10000],0x0 + // 0x7ffff6cfb0b0: pop rsi + // 0x7ffff6cfb0b1: popf + // 0x7ffff6cfb0b2: lea rsp,[rsp+0x80] -}; -gboolean instrument_is_coverage_optimize_supported(void) { + uint8_t lea_rsp_rsp_sub_rz[5]; + uint8_t push_fq; + uint8_t push_rsi; - return true; + uint8_t mov_rsi_curr_loc_shr_1[7]; + uint8_t xchg_rsi_prev_loc_curr_loc[7]; + uint8_t xor_rsi_curr_loc[7]; + + uint8_t add_rsi_1[7]; + uint8_t adc_rsi_0[7]; + + uint8_t pop_rsi; + uint8_t pop_fq; + uint8_t lsa_rsp_rsp_add_rz[8]; + +} afl_log_code_asm_t; + + #pragma pack(pop) + +typedef union { + + afl_log_code_asm_t code; + uint8_t bytes[0]; + +} afl_log_code; + +static const afl_log_code_asm_t template = + { + + .lea_rsp_rsp_sub_rz = {0x48, 0x8D, 0x64, 0x24, 0x80}, + .push_fq = 0x9c, + .push_rsi = 0x56, + + .mov_rsi_curr_loc_shr_1 = {0x48, 0xC7, 0xC6}, + .xchg_rsi_prev_loc_curr_loc = {0x48, 0x87, 0x35}, + .xor_rsi_curr_loc = {0x48, 0x81, 0xF6}, + + .add_rsi_1 = {0x80, 0x86, 0x00, 0x00, 0x00, 0x00, 0x01}, + .adc_rsi_0 = {0x80, 0x96, 0x00, 0x00, 0x00, 0x00, 0x00}, + + .pop_rsi = 0x5E, + .pop_fq = 0x9D, + .lsa_rsp_rsp_add_rz = {0x48, 0x8D, 0xA4, 0x24, 0x80, 0x00, 0x00, 0x00}, } -static guint8 align_pad[] = {0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90}; +; -static void instrument_coverate_write_function(GumStalkerOutput *output) { +static gboolean instrument_coverage_find_low(const GumRangeDetails *details, + gpointer user_data) { - guint64 misalign = 0; - GumX86Writer *cw = output->writer.x86; + static GumAddress last_limit = (64ULL << 10); + gpointer * address = (gpointer *)user_data; - if (current_log_impl == 0 || - !gum_x86_writer_can_branch_directly_between(cw->pc, current_log_impl) || - !gum_x86_writer_can_branch_directly_between(cw->pc + 128, - current_log_impl)) { + if ((details->range->base_address - last_limit) > __afl_map_size) { - gconstpointer after_log_impl = cw->code + 1; + *address = GSIZE_TO_POINTER(last_limit); + return FALSE; - gum_x86_writer_put_jmp_near_label(cw, after_log_impl); + } - misalign = (cw->pc & 0x7); - if (misalign != 0) { + if (details->range->base_address > ((2ULL << 20) - __afl_map_size)) { - gum_x86_writer_put_bytes(cw, align_pad, 8 - misalign); + return FALSE; - } + } + + last_limit = details->range->base_address + details->range->size; + return TRUE; + +} + +static void instrument_coverage_optimize_map_mmap_anon(gpointer address) { + + __afl_area_ptr = + mmap(address, __afl_map_size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (__afl_area_ptr != address) { + + FATAL("Failed to map mmap __afl_area_ptr: %d", errno); + + } + +} + +static void instrument_coverage_optimize_map_mmap(char * shm_file_path, + gpointer address) { + + int shm_fd = -1; + + if (munmap(__afl_area_ptr, __afl_map_size) != 0) { + + FATAL("Failed to unmap previous __afl_area_ptr"); + + } + + __afl_area_ptr = NULL; + +#if !defined(__ANDROID__) + shm_fd = shm_open(shm_file_path, O_RDWR, DEFAULT_PERMISSION); + if (shm_fd == -1) { FATAL("shm_open() failed\n"); } +#else + shm_fd = open("/dev/ashmem", O_RDWR); + if (shm_fd == -1) { FATAL("open() failed\n"); } + if (ioctl(shm_fd, ASHMEM_SET_NAME, shm_file_path) == -1) { FATAL("ioctl(ASHMEM_SET_NAME) failed"); } + if (ioctl(shm_fd, ASHMEM_SET_SIZE, __afl_map_size) == -1) { FATAL("ioctl(ASHMEM_SET_SIZE) failed"); } + +#endif + + __afl_area_ptr = mmap(address, __afl_map_size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_SHARED, shm_fd, 0); + if (__afl_area_ptr != address) { + + FATAL("Failed to map mmap __afl_area_ptr: %d", errno); + + } + + if (close(shm_fd) != 0) { FATAL("Failed to close shm_fd"); } + +} - current_log_impl = cw->pc; - gum_x86_writer_put_bytes(cw, afl_log_code, sizeof(afl_log_code)); +static void instrument_coverage_optimize_map_shm(guint64 shm_env_val, + gpointer address) { - uint64_t *afl_prev_loc_ptr = &instrument_previous_pc; - gum_x86_writer_put_bytes(cw, (const guint8 *)&__afl_area_ptr, - sizeof(__afl_area_ptr)); - gum_x86_writer_put_bytes(cw, (const guint8 *)&afl_prev_loc_ptr, - sizeof(afl_prev_loc_ptr)); + if (shmdt(__afl_area_ptr) != 0) { - gum_x86_writer_put_label(cw, after_log_impl); + FATAL("Failed to detach previous __afl_area_ptr"); + + } + + __afl_area_ptr = shmat(shm_env_val, address, 0); + if (__afl_area_ptr != address) { + + FATAL("Failed to map shm __afl_area_ptr: %d", errno); } } +void instrument_coverage_optimize_init(void) { + + gpointer low_address = NULL; + + gum_process_enumerate_ranges(GUM_PAGE_NO_ACCESS, instrument_coverage_find_low, + &low_address); + + OKF("Low address: %p", low_address); + + if (low_address == 0 || + GPOINTER_TO_SIZE(low_address) > ((2UL << 20) - __afl_map_size)) { + + FATAL("Invalid low_address: %p", low_address); + + } + + ranges_print_debug_maps(); + + char *shm_env = getenv(SHM_ENV_VAR); + OKF("SHM_ENV_VAR: %s", shm_env); + + if (shm_env == NULL) { + + WARNF("SHM_ENV_VAR not set, using anonymous map for debugging purposes"); + + instrument_coverage_optimize_map_mmap_anon(low_address); + + } else { + + guint64 shm_env_val = g_ascii_strtoull(shm_env, NULL, 10); + + if (shm_env_val == 0) { + + instrument_coverage_optimize_map_mmap(shm_env, low_address); + + } else { + + instrument_coverage_optimize_map_shm(shm_env_val, low_address); + + } + + } + + OKF("__afl_area_ptr: %p", __afl_area_ptr); + OKF("instrument_previous_pc: %p", &instrument_previous_pc); + +} + void instrument_coverage_optimize(const cs_insn * instr, GumStalkerOutput *output) { + afl_log_code code = {0}; GumX86Writer *cw = output->writer.x86; guint64 area_offset = instrument_get_offset_hash(GUM_ADDRESS(instr->address)); - instrument_coverate_write_function(output); - - gum_x86_writer_put_lea_reg_reg_offset(cw, GUM_REG_RSP, GUM_REG_RSP, - -GUM_RED_ZONE_SIZE); - gum_x86_writer_put_push_reg(cw, GUM_REG_RDI); - gum_x86_writer_put_mov_reg_address(cw, GUM_REG_RDI, area_offset); - gum_x86_writer_put_call_address(cw, current_log_impl); - gum_x86_writer_put_pop_reg(cw, GUM_REG_RDI); - gum_x86_writer_put_lea_reg_reg_offset(cw, GUM_REG_RSP, GUM_REG_RSP, - GUM_RED_ZONE_SIZE); + GumAddress code_addr = 0; + + // gum_x86_writer_put_breakpoint(cw); + code_addr = cw->pc; + code.code = template; + + gssize curr_loc_shr_1_offset = + offsetof(afl_log_code, code.mov_rsi_curr_loc_shr_1) + + sizeof(code.code.mov_rsi_curr_loc_shr_1) - sizeof(guint32); + + *((guint32 *)&code.bytes[curr_loc_shr_1_offset]) = + (guint32)(area_offset >> 1); + + gssize prev_loc_value = + GPOINTER_TO_SIZE(&instrument_previous_pc) - + (code_addr + offsetof(afl_log_code, code.xchg_rsi_prev_loc_curr_loc) + + sizeof(code.code.xchg_rsi_prev_loc_curr_loc)); + gssize prev_loc_value_offset = + offsetof(afl_log_code, code.xchg_rsi_prev_loc_curr_loc) + + sizeof(code.code.xchg_rsi_prev_loc_curr_loc) - sizeof(gint); + if (!instrument_coverage_in_range(prev_loc_value)) { + + FATAL("Patch out of range (current_pc_value1): 0x%016lX", prev_loc_value); + + } + + *((gint *)&code.bytes[prev_loc_value_offset]) = (gint)prev_loc_value; + + gssize xor_curr_loc_offset = offsetof(afl_log_code, code.xor_rsi_curr_loc) + + sizeof(code.code.xor_rsi_curr_loc) - + sizeof(guint32); + + *((guint32 *)&code.bytes[xor_curr_loc_offset]) = (guint32)(area_offset); + + gssize add_rsi_1_offset = offsetof(afl_log_code, code.add_rsi_1) + + sizeof(code.code.add_rsi_1) - sizeof(guint32) - 1; + + *((guint32 *)&code.bytes[add_rsi_1_offset]) = + (guint32)GPOINTER_TO_SIZE(__afl_area_ptr); + + gssize adc_rsi_0_ffset = offsetof(afl_log_code, code.adc_rsi_0) + + sizeof(code.code.adc_rsi_0) - sizeof(guint32) - 1; + + *((guint32 *)&code.bytes[adc_rsi_0_ffset]) = + (guint32)GPOINTER_TO_SIZE(__afl_area_ptr); + + gum_x86_writer_put_bytes(cw, code.bytes, sizeof(afl_log_code)); } diff --git a/frida_mode/src/instrument/instrument_x86.c b/frida_mode/src/instrument/instrument_x86.c index 7bf48f96..1ff5c920 100644 --- a/frida_mode/src/instrument/instrument_x86.c +++ b/frida_mode/src/instrument/instrument_x86.c @@ -83,6 +83,9 @@ void instrument_coverage_optimize(const cs_insn * instr, } +void instrument_coverage_optimize_init(void) { +} + void instrument_flush(GumStalkerOutput *output) { gum_x86_writer_flush(output->writer.x86); diff --git a/frida_mode/src/js/api.js b/frida_mode/src/js/api.js index 40bb4a16..6f9f05d8 100644 --- a/frida_mode/src/js/api.js +++ b/frida_mode/src/js/api.js @@ -243,6 +243,12 @@ class Afl { const buf = Memory.allocUtf8String(file); Afl.jsApiSetStdOut(buf); } + /** + * See `AFL_FRIDA_TRACEABLE`. + */ + static setTraceable() { + Afl.jsApiSetTraceable(); + } static jsApiGetFunction(name, retType, argTypes) { const addr = Afl.module.getExportByName(name); return new NativeFunction(addr, retType, argTypes); @@ -286,6 +292,7 @@ Afl.jsApiSetStatsFile = Afl.jsApiGetFunction("js_api_set_stats_file", "void", [" Afl.jsApiSetStatsInterval = Afl.jsApiGetFunction("js_api_set_stats_interval", "void", ["uint64"]); Afl.jsApiSetStdErr = Afl.jsApiGetFunction("js_api_set_stderr", "void", ["pointer"]); Afl.jsApiSetStdOut = Afl.jsApiGetFunction("js_api_set_stdout", "void", ["pointer"]); +Afl.jsApiSetTraceable = Afl.jsApiGetFunction("js_api_set_traceable", "void", []); Afl.jsApiWrite = new NativeFunction( /* tslint:disable-next-line:no-null-keyword */ Module.getExportByName(null, "write"), "int", ["int", "pointer", "int"]); diff --git a/frida_mode/src/js/js_api.c b/frida_mode/src/js/js_api.c index 9dba79aa..f3d81a32 100644 --- a/frida_mode/src/js/js_api.c +++ b/frida_mode/src/js/js_api.c @@ -231,3 +231,9 @@ __attribute__((visibility("default"))) void js_api_set_stalker_ic_entries( } +__attribute__((visibility("default"))) void js_api_set_traceable(void) { + + traceable = TRUE; + +} + diff --git a/frida_mode/src/main.c b/frida_mode/src/main.c index c0de9c6b..c8183d8f 100644 --- a/frida_mode/src/main.c +++ b/frida_mode/src/main.c @@ -6,6 +6,7 @@ #ifdef __APPLE__ #include <mach/mach.h> #include <mach-o/dyld_images.h> + #include <crt_externs.h> #else #include <sys/wait.h> #include <sys/personality.h> @@ -90,6 +91,7 @@ static void embedded_init(void) { static void afl_print_cmdline(void) { +#if defined(__linux__) char * buffer = g_malloc0(PROC_MAX); gchar *fname = g_strdup_printf("/proc/%d/cmdline", getppid()); int fd = open(fname, O_RDONLY); @@ -123,6 +125,17 @@ static void afl_print_cmdline(void) { close(fd); g_free(fname); g_free(buffer); +#elif defined(__APPLE__) + int idx; + char **argv = *_NSGetArgv(); + int nargv = *_NSGetArgc(); + + for (idx = 0; idx < nargv; idx ++) { + + OKF("AFL - COMMANDLINE: argv[%d] = %s", idx, argv[idx]); + + } +#endif } diff --git a/frida_mode/src/prefetch.c b/frida_mode/src/prefetch.c index 0efbc9bf..c30ca65c 100644 --- a/frida_mode/src/prefetch.c +++ b/frida_mode/src/prefetch.c @@ -44,8 +44,9 @@ static void gum_afl_stalker_backpatcher_notify(GumStalkerObserver *self, sizeof(prefetch_data->backpatch_data) - prefetch_data->backpatch_size; if (sizeof(gsize) + size > remaining) { return; } - *(gsize *)(&prefetch_data->backpatch_data[prefetch_data->backpatch_size]) = - size; + gsize *dst_backpatch_size = (gsize *) + &prefetch_data->backpatch_data[prefetch_data->backpatch_size]; + *dst_backpatch_size = size; prefetch_data->backpatch_size += sizeof(gsize); memcpy(&prefetch_data->backpatch_data[prefetch_data->backpatch_size], @@ -115,7 +116,8 @@ static void prefetch_read_patches(void) { remaining > sizeof(gsize); remaining = prefetch_data->backpatch_size - offset) { - gsize size = *(gsize *)(&prefetch_data->backpatch_data[offset]); + gsize *src_backpatch_data = (gsize *)&prefetch_data->backpatch_data[offset]; + gsize size = *src_backpatch_data; offset += sizeof(gsize); if (prefetch_data->backpatch_size - offset < size) { diff --git a/frida_mode/src/ranges.c b/frida_mode/src/ranges.c index 5b6eb462..1b666fce 100644 --- a/frida_mode/src/ranges.c +++ b/frida_mode/src/ranges.c @@ -549,18 +549,19 @@ static GArray *merge_ranges(GArray *a) { } +void ranges_print_debug_maps(void) { + + gum_process_enumerate_ranges(GUM_PAGE_NO_ACCESS, print_ranges_callback, NULL); + +} + void ranges_config(void) { if (getenv("AFL_FRIDA_DEBUG_MAPS") != NULL) { ranges_debug_maps = TRUE; } if (getenv("AFL_INST_LIBS") != NULL) { ranges_inst_libs = TRUE; } if (getenv("AFL_FRIDA_INST_JIT") != NULL) { ranges_inst_jit = TRUE; } - if (ranges_debug_maps) { - - gum_process_enumerate_ranges(GUM_PAGE_NO_ACCESS, print_ranges_callback, - NULL); - - } + if (ranges_debug_maps) { ranges_print_debug_maps(); } include_ranges = collect_ranges("AFL_FRIDA_INST_RANGES"); exclude_ranges = collect_ranges("AFL_FRIDA_EXCLUDE_RANGES"); diff --git a/frida_mode/src/seccomp/seccomp.c b/frida_mode/src/seccomp/seccomp.c index 7683cd71..99111591 100644 --- a/frida_mode/src/seccomp/seccomp.c +++ b/frida_mode/src/seccomp/seccomp.c @@ -1,9 +1,3 @@ -#include <execinfo.h> -#include <fcntl.h> -#include <linux/seccomp.h> -#include <stdio.h> -#include <unistd.h> - #include "frida-gumjs.h" #include "debug.h" @@ -13,111 +7,15 @@ char *seccomp_filename = NULL; -static void seccomp_vprint(int fd, char *format, va_list ap) { - - char buffer[4096] = {0}; - int len; - - if (vsnprintf(buffer, sizeof(buffer) - 1, format, ap) < 0) { return; } - - len = strnlen(buffer, sizeof(buffer)); - IGNORED_RETURN(write(fd, buffer, len)); - -} - -void seccomp_print(char *format, ...) { - - va_list ap; - va_start(ap, format); - seccomp_vprint(SECCOMP_OUTPUT_FILE_FD, format, ap); - va_end(ap); - -} - -static void seccomp_filter_callback(struct seccomp_notif * req, - struct seccomp_notif_resp *resp, - GumReturnAddressArray * frames) { - - GumDebugSymbolDetails details = {0}; - if (req->data.nr == SYS_OPENAT) { - - seccomp_print("SYS_OPENAT: (%s)\n", (char *)req->data.args[1]); - - } - - seccomp_print( - "\nID (%#llx) for PID %d - %d (%s) [0x%llx 0x%llx 0x%llx 0x%llx 0x%llx " - "0x%llx ]\n", - req->id, req->pid, req->data.nr, seccomp_syscall_lookup(req->data.nr), - req->data.args[0], req->data.args[1], req->data.args[2], - req->data.args[3], req->data.args[4], req->data.args[5]); - - seccomp_print("FRAMES: (%u)\n", frames->len); - char **syms = backtrace_symbols(frames->items, frames->len); - if (syms == NULL) { FATAL("Failed to get symbols"); } - - for (guint i = 0; i < frames->len; i++) { - - if (gum_symbol_details_from_address(frames->items[i], &details)) { - - seccomp_print("\t%3d. %s!%s\n", i, details.module_name, - details.symbol_name); - - } else { - - seccomp_print("\t%3d. %s\n", i, syms[i]); - - } - - } - - free(syms); - - resp->error = 0; - resp->val = 0; - resp->id = req->id; - resp->flags = SECCOMP_USER_NOTIF_FLAG_CONTINUE; - -} - -static void seccomp_child(int signal_parent, void *ctx) { - - int sock_fd = *((int *)ctx); - int fd = seccomp_socket_recv(sock_fd); - - if (close(sock_fd) < 0) { FATAL("child - close"); } - - seccomp_event_signal(signal_parent); - seccomp_filter_child_install(); - seccomp_filter_run(fd, seccomp_filter_callback); - -} - void seccomp_on_fork(void) { - int sock[2] = {-1, -1}; - pid_t child = -1; - int child_fd = -1; - if (seccomp_filename == NULL) { return; } - seccomp_socket_create(sock); - seccomp_child_run(seccomp_child, sock, &child, &child_fd); - - if (dup2(child_fd, SECCOMP_PARENT_EVENT_FD) < 0) { FATAL("dup2"); } - - if (close(child_fd) < 0) { FATAL("seccomp_on_fork - close (1)"); } - - if (close(sock[STDIN_FILENO]) < 0) { FATAL("grandparent - close (2)"); } - - int fd = seccomp_filter_install(child); - seccomp_socket_send(sock[STDOUT_FILENO], fd); - - if (close(sock[STDOUT_FILENO]) < 0) { FATAL("grandparent - close (3)"); } - - if (close(fd) < 0) { FATAL("grandparent - close (4)"); } - - seccomp_child_wait(SECCOMP_PARENT_EVENT_FD); +#ifdef __APPLE__ + FATAL("Seccomp not supported on OSX"); +#else + seccomp_callback_parent(); +#endif } @@ -129,29 +27,15 @@ void seccomp_config(void) { void seccomp_init(void) { - char *path = NULL; - int fd; - OKF("Seccomp - file [%s]", seccomp_filename); if (seccomp_filename == NULL) { return; } - path = g_canonicalize_filename(seccomp_filename, g_get_current_dir()); - - OKF("Seccomp - path [%s]", path); - - fd = open(path, O_RDWR | O_CREAT | O_TRUNC, - S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); - - if (dup2(fd, SECCOMP_OUTPUT_FILE_FD) < 0) { - - FATAL("Failed to duplicate seccomp output file"); - - } - - if (close(fd) < 0) { FATAL("Failed to close seccomp output file fd"); } - - g_free(path); +#ifdef __APPLE__ + FATAL("Seccomp not supported on OSX"); +#else + seccomp_callback_initialize(); +#endif } diff --git a/frida_mode/src/seccomp/seccomp_atomic.c b/frida_mode/src/seccomp/seccomp_atomic.c index 1720a726..c2042f97 100644 --- a/frida_mode/src/seccomp/seccomp_atomic.c +++ b/frida_mode/src/seccomp/seccomp_atomic.c @@ -1,7 +1,9 @@ -#include <stdbool.h> -#include <stdio.h> +#if defined(__linux__) && !defined(__ANDROID__) -#include "debug.h" + #include <stdbool.h> + #include <stdio.h> + + #include "debug.h" void seccomp_atomic_set(volatile bool *ptr, bool val) { @@ -26,3 +28,5 @@ void seccomp_atomic_wait(volatile bool *ptr, bool val) { } +#endif + diff --git a/frida_mode/src/seccomp/seccomp_callback.c b/frida_mode/src/seccomp/seccomp_callback.c new file mode 100644 index 00000000..4232d842 --- /dev/null +++ b/frida_mode/src/seccomp/seccomp_callback.c @@ -0,0 +1,144 @@ +#if defined(__linux__) && !defined(__ANDROID__) + +#if !defined(__MUSL__) + #include <execinfo.h> +#endif + #include <fcntl.h> + + #include "seccomp.h" + + #include "debug.h" + +static void seccomp_callback_filter(struct seccomp_notif * req, + struct seccomp_notif_resp *resp, + GumReturnAddressArray * frames) { + + GumDebugSymbolDetails details = {0}; + if (req->data.nr == SYS_OPENAT) { + +#if UINTPTR_MAX == 0xffffffffffffffffu + seccomp_print("SYS_OPENAT: (%s)\n", (char *)req->data.args[1]); +#endif +#if UINTPTR_MAX == 0xffffffff + seccomp_print("SYS_OPENAT: (%s)\n", (char *)(__u32)req->data.args[1]); +#endif + } + + seccomp_print( + "\nID (%#llx) for PID %d - %d (%s) [0x%llx 0x%llx 0x%llx 0x%llx 0x%llx " + "0x%llx ]\n", + req->id, req->pid, req->data.nr, seccomp_syscall_lookup(req->data.nr), + req->data.args[0], req->data.args[1], req->data.args[2], + req->data.args[3], req->data.args[4], req->data.args[5]); + +#if !defined(__MUSL__) + seccomp_print("FRAMES: (%u)\n", frames->len); + char **syms = backtrace_symbols(frames->items, frames->len); + if (syms == NULL) { FATAL("Failed to get symbols"); } + + for (guint i = 0; i < frames->len; i++) { + + if (gum_symbol_details_from_address(frames->items[i], &details)) { + + seccomp_print("\t%3d. %s!%s\n", i, details.module_name, + details.symbol_name); + + } else { + + seccomp_print("\t%3d. %s\n", i, syms[i]); + + } + + } + + free(syms); +#else + void **syms = (void **)__builtin_frame_address(0); + void *framep = __builtin_frame_address(1); + int i = 0; + + syms = framep; + while (syms) { + + framep = *syms; + syms = framep; + + if (!syms) break; + + seccomp_print("\%3d. %s\n", i ++, (char *)framep); + + } +#endif + + resp->error = 0; + resp->val = 0; + resp->id = req->id; + resp->flags = SECCOMP_USER_NOTIF_FLAG_CONTINUE; + +} + +static void seccomp_callback_child(int signal_parent, void *ctx) { + + int sock_fd = *((int *)ctx); + int fd = seccomp_socket_recv(sock_fd); + + if (close(sock_fd) < 0) { FATAL("child - close"); } + + seccomp_event_signal(signal_parent); + seccomp_filter_child_install(); + seccomp_filter_run(fd, seccomp_callback_filter); + +} + +void seccomp_callback_parent(void) { + + int sock[2] = {-1, -1}; + pid_t child = -1; + int child_fd = -1; + + seccomp_socket_create(sock); + seccomp_child_run(seccomp_callback_child, sock, &child, &child_fd); + + if (dup2(child_fd, SECCOMP_PARENT_EVENT_FD) < 0) { FATAL("dup2"); } + + if (close(child_fd) < 0) { FATAL("seccomp_on_fork - close (1)"); } + + if (close(sock[STDIN_FILENO]) < 0) { FATAL("grandparent - close (2)"); } + + int fd = seccomp_filter_install(child); + seccomp_socket_send(sock[STDOUT_FILENO], fd); + + if (close(sock[STDOUT_FILENO]) < 0) { FATAL("grandparent - close (3)"); } + + if (close(fd) < 0) { FATAL("grandparent - close (4)"); } + + seccomp_child_wait(SECCOMP_PARENT_EVENT_FD); + +} + +void seccomp_callback_initialize(void) { + + char *path = NULL; + int fd; + + path = g_canonicalize_filename(seccomp_filename, g_get_current_dir()); + + OKF("Seccomp - path [%s]", path); + + fd = open(path, O_RDWR | O_CREAT | O_TRUNC, + S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); + + if (dup2(fd, SECCOMP_OUTPUT_FILE_FD) < 0) { + + FATAL("Failed to duplicate seccomp output file"); + + } + + if (close(fd) < 0) { FATAL("Failed to close seccomp output file fd"); } + + g_free(path); + +} + +#endif + diff --git a/frida_mode/src/seccomp/seccomp_child.c b/frida_mode/src/seccomp/seccomp_child.c index 4d494137..43a79894 100644 --- a/frida_mode/src/seccomp/seccomp_child.c +++ b/frida_mode/src/seccomp/seccomp_child.c @@ -1,18 +1,20 @@ -#include <fcntl.h> -#include <sched.h> -#include <signal.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/mman.h> -#include <sys/prctl.h> -#include <sys/types.h> -#include <unistd.h> +#if defined(__linux__) && !defined(__ANDROID__) -#include "debug.h" + #include <fcntl.h> + #include <sched.h> + #include <signal.h> + #include <stdio.h> + #include <stdlib.h> + #include <sys/mman.h> + #include <sys/prctl.h> + #include <sys/types.h> + #include <unistd.h> -#include "seccomp.h" + #include "debug.h" -#define SECCOMP_CHILD_STACK_SIZE (1UL << 20) + #include "seccomp.h" + + #define SECCOMP_CHILD_STACK_SIZE (1UL << 20) typedef void (*seccomp_child_func_t)(int event_fd, void *ctx); @@ -67,3 +69,5 @@ void seccomp_child_wait(int event_fd) { } +#endif + diff --git a/frida_mode/src/seccomp/seccomp_event.c b/frida_mode/src/seccomp/seccomp_event.c index ecb9be32..e2f592ca 100644 --- a/frida_mode/src/seccomp/seccomp_event.c +++ b/frida_mode/src/seccomp/seccomp_event.c @@ -1,15 +1,17 @@ -#include <stdint.h> -#include <stdio.h> -#include <sys/eventfd.h> -#include <unistd.h> +#if defined(__linux__) && !defined(__ANDROID__) -#include "debug.h" + #include <stdint.h> + #include <stdio.h> + #include <sys/syscall.h> + #include <unistd.h> -#include "seccomp.h" + #include "debug.h" + + #include "seccomp.h" int seccomp_event_create(void) { - int fd = eventfd(0, 0); + int fd = syscall(SYS_eventfd, 0, 0); if (fd < 0) { FATAL("seccomp_event_create"); } return fd; @@ -43,3 +45,5 @@ void seccomp_event_destroy(int fd) { } +#endif + diff --git a/frida_mode/src/seccomp/seccomp_filter.c b/frida_mode/src/seccomp/seccomp_filter.c index c16e7ebd..7ee5ead1 100644 --- a/frida_mode/src/seccomp/seccomp_filter.c +++ b/frida_mode/src/seccomp/seccomp_filter.c @@ -1,27 +1,30 @@ -#include <alloca.h> -#include <errno.h> -#include <execinfo.h> -#include <linux/filter.h> -#include <linux/seccomp.h> -#include <sys/ioctl.h> -#include <sys/prctl.h> -#include <sys/syscall.h> -#include <signal.h> -#include <stdbool.h> -#include <stddef.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> - -#include "debug.h" - -#include "frida-gumjs.h" - -#include "seccomp.h" -#include "util.h" - -#define SECCOMP_FILTER_NUM_FRAMES 512 +#if defined(__linux__) && !defined(__ANDROID__) + + #include <alloca.h> + #include <errno.h> +#if !defined(__MUSL__) + #include <execinfo.h> +#endif + #include <linux/filter.h> + #include <sys/ioctl.h> + #include <sys/prctl.h> + #include <sys/syscall.h> + #include <signal.h> + #include <stdbool.h> + #include <stddef.h> + #include <stdio.h> + #include <stdlib.h> + #include <string.h> + #include <unistd.h> + + #include "debug.h" + + #include "frida-gumjs.h" + + #include "seccomp.h" + #include "util.h" + + #define SECCOMP_FILTER_NUM_FRAMES 512 extern void gum_linux_parse_ucontext(const ucontext_t *uc, GumCpuContext *ctx); @@ -127,7 +130,10 @@ static GumBacktracer * seccomp_filter_backtracer = NULL; static void seccomp_filter_child_handler(int sig, siginfo_t *info, void *ucontext) { - GumCpuContext cpu_context; + UNUSED_PARAMETER(sig); + UNUSED_PARAMETER(info); + UNUSED_PARAMETER(ucontext); + if (seccomp_filter_backtracer == NULL) { seccomp_filter_backtracer = gum_backtracer_make_fuzzy(); @@ -150,7 +156,8 @@ static void seccomp_filter_parent_handler(int sig, siginfo_t *info, ucontext_t *uc = (ucontext_t *)ucontext; gum_linux_parse_ucontext(uc, &seccomp_filter_cpu_context); - if (tgkill(seccomp_filter_child, seccomp_filter_child, SIGUSR1) < 0) { + if (syscall(SYS_tgkill, seccomp_filter_child, seccomp_filter_child, SIGUSR1) < + 0) { FATAL("kill"); @@ -256,3 +263,5 @@ void seccomp_filter_run(int fd, seccomp_filter_callback_t callback) { } +#endif + diff --git a/frida_mode/src/seccomp/seccomp_print.c b/frida_mode/src/seccomp/seccomp_print.c new file mode 100644 index 00000000..3cea1239 --- /dev/null +++ b/frida_mode/src/seccomp/seccomp_print.c @@ -0,0 +1,30 @@ +#if defined(__linux__) && !defined(__ANDROID__) + + #include <stdarg.h> + + #include "seccomp.h" + #include "util.h" + +static void seccomp_print_v(int fd, char *format, va_list ap) { + + char buffer[4096] = {0}; + int len; + + if (vsnprintf(buffer, sizeof(buffer) - 1, format, ap) < 0) { return; } + + len = strnlen(buffer, sizeof(buffer)); + IGNORED_RETURN(write(fd, buffer, len)); + +} + +void seccomp_print(char *format, ...) { + + va_list ap; + va_start(ap, format); + seccomp_print_v(SECCOMP_OUTPUT_FILE_FD, format, ap); + va_end(ap); + +} + +#endif + diff --git a/frida_mode/src/seccomp/seccomp_socket.c b/frida_mode/src/seccomp/seccomp_socket.c index ca42e158..ef937420 100644 --- a/frida_mode/src/seccomp/seccomp_socket.c +++ b/frida_mode/src/seccomp/seccomp_socket.c @@ -1,11 +1,13 @@ -#include <stdio.h> -#include <string.h> -#include <sys/socket.h> -#include <unistd.h> +#if defined(__linux__) && !defined(__ANDROID__) -#include "debug.h" + #include <stdio.h> + #include <string.h> + #include <sys/socket.h> + #include <unistd.h> -#include "seccomp.h" + #include "debug.h" + + #include "seccomp.h" union cmsg { @@ -119,3 +121,5 @@ int seccomp_socket_recv(int sockfd) { } +#endif + diff --git a/frida_mode/src/seccomp/seccomp_syscall.c b/frida_mode/src/seccomp/seccomp_syscall.c index b2c084c8..8335b93c 100644 --- a/frida_mode/src/seccomp/seccomp_syscall.c +++ b/frida_mode/src/seccomp/seccomp_syscall.c @@ -1,9 +1,11 @@ -#include <limits.h> -#include <stdio.h> +#if defined(__linux__) && !defined(__ANDROID__) -#include "debug.h" + #include <limits.h> + #include <stdio.h> -#include "seccomp.h" + #include "debug.h" + + #include "seccomp.h" typedef struct { @@ -333,3 +335,5 @@ char *seccomp_syscall_lookup(int id) { } +#endif + diff --git a/frida_mode/test/freetype2/GNUmakefile b/frida_mode/test/freetype2/GNUmakefile new file mode 100644 index 00000000..891660ca --- /dev/null +++ b/frida_mode/test/freetype2/GNUmakefile @@ -0,0 +1,192 @@ +PWD:=$(shell pwd)/ +ROOT:=$(PWD)../../../ +BUILD_DIR:=$(PWD)build/ + +AFLPP_FRIDA_DRIVER_HOOK_OBJ=$(ROOT)frida_mode/build/frida_hook.so +AFLPP_QEMU_DRIVER_HOOK_OBJ=$(ROOT)frida_mode/build/qemu_hook.so + +# git clone git://git.sv.nongnu.org/freetype/freetype2.git +# git clone https://github.com/unicode-org/text-rendering-tests.git TRT +# wget https://github.com/libarchive/libarchive/releases/download/v3.4.3/libarchive-3.4.3.tar.xz + +# cp TRT/fonts/TestKERNOne.otf $OUT/seeds/ +# cp TRT/fonts/TestGLYFOne.ttf $OUT/seeds/ + +# $CXX $CXXFLAGS -std=c++11 -I include -I . src/tools/ftfuzzer/ftfuzzer.cc \ +# objs/.libs/libfreetype.a $FUZZER_LIB -L /usr/local/lib -larchive \ +# -o $OUT/ftfuzzer + +LIBARCHIVE_URL:=https://github.com/libarchive/libarchive/releases/download/v3.4.3/libarchive-3.4.3.tar.xz +LIBARCHIVE_BUILD_DIR:=$(BUILD_DIR)libarchive/ +LIBARCHIVE_TARBALL:=$(LIBARCHIVE_BUILD_DIR)libarchive-3.4.3.tar.xz +LIBARCHIVE_DIR:=$(LIBARCHIVE_BUILD_DIR)libarchive-3.4.3/ +LIBARCHIVE_LIB:=$(LIBARCHIVE_DIR).libs/libarchive.a + +FREETYPE2_GIT_REPO:=git://git.sv.nongnu.org/freetype/freetype2.git +FREETYPE2_BUILD_DIR:=$(BUILD_DIR)freetype2/ +FREETYPE2_DIR:=$(FREETYPE2_BUILD_DIR)freetype2/ +FREETYPE2_LIB:=$(FREETYPE2_DIR)objs/.libs/libfreetype.a + +HARNESS_URL:=https://raw.githubusercontent.com/llvm/llvm-project/main/compiler-rt/lib/fuzzer/standalone/StandaloneFuzzTargetMain.c +HARNESS_SRC:=$(BUILD_DIR)StandaloneFuzzTargetMain.c +HARNESS_OBJ:=$(BUILD_DIR)StandaloneFuzzTargetMain.o + +TRT_GIT_REPO:=https://github.com/unicode-org/text-rendering-tests.git +TRT_DIR:=$(BUILD_DIR)TRT/ + +FUZZER_SRC:=$(FREETYPE2_DIR)src/tools/ftfuzzer/ftfuzzer.cc + + +LDFLAGS += -lpthread + +TEST_BIN:=$(BUILD_DIR)test +ifeq "$(shell uname)" "Darwin" +TEST_BIN_LDFLAGS:=-undefined dynamic_lookup -Wl,-no_pie +endif + +TEST_DATA_DIR:=$(BUILD_DIR)in/ +TEST_DATA_FILE:=$(TEST_DATA_DIR)default_seed + +FRIDA_OUT:=$(BUILD_DIR)frida-out +QEMU_OUT:=$(BUILD_DIR)qemu-out + +ifndef ARCH + +ARCH=$(shell uname -m) +ifeq "$(ARCH)" "aarch64" + ARCH:=arm64 +endif + +ifeq "$(ARCH)" "i686" + ARCH:=x86 +endif +endif + +GET_SYMBOL_ADDR:=$(ROOT)frida_mode/util/get_symbol_addr.sh + +AFL_QEMU_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x4000000000) + +ifeq "$(ARCH)" "aarch64" + AFL_FRIDA_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x0000aaaaaaaaa000) +endif + +ifeq "$(ARCH)" "x86_64" + AFL_FRIDA_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x0000555555554000) +endif + +ifeq "$(ARCH)" "x86" + AFL_FRIDA_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x56555000) +endif + +.PHONY: all clean frida hook + +all: $(TEST_BIN) + make -C $(ROOT)frida_mode/ + +32: + CXXFLAGS="-m32" LDFLAGS="-m32" ARCH="x86" make all + +$(BUILD_DIR): + mkdir -p $@ + +########## LIBARCHIVE ####### + +$(LIBARCHIVE_BUILD_DIR): | $(BUILD_DIR) + mkdir -p $@ + +$(LIBARCHIVE_TARBALL): | $(LIBARCHIVE_BUILD_DIR) + wget -O $@ $(LIBARCHIVE_URL) + +$(LIBARCHIVE_DIR): | $(LIBARCHIVE_TARBALL) + tar Jxvf $(LIBARCHIVE_TARBALL) -C $(LIBARCHIVE_BUILD_DIR) + +$(LIBARCHIVE_DIR)Makefile: | $(LIBARCHIVE_DIR) + cd $(LIBARCHIVE_DIR) && ./configure --disable-shared + +$(LIBARCHIVE_LIB): $(LIBARCHIVE_DIR)Makefile + make -C $(LIBARCHIVE_DIR) clean all + +########## FREETYPE2 ####### + +$(FREETYPE2_BUILD_DIR): | $(BUILD_DIR) + mkdir -p $@ + +$(FREETYPE2_DIR): | $(FREETYPE2_BUILD_DIR) + git clone $(FREETYPE2_GIT_REPO) $@ + git -C $(FREETYPE2_DIR) checkout cd02d359a6d0455e9d16b87bf9665961c4699538 + +$(FREETYPE2_LIB): | $(FREETYPE2_DIR) + cd $(FREETYPE2_DIR) && ./autogen.sh + cd $(FREETYPE2_DIR) && ./configure --with-harfbuzz=no --with-bzip2=no --with-png=no --without-zlib + make -C $(FREETYPE2_DIR) all + +########## HARNESS ####### + +$(HARNESS_SRC): + wget -O $@ $(HARNESS_URL) + +$(HARNESS_OBJ): $(HARNESS_SRC) + $(CC) -o $@ -c $< + +########## TEST ####### + +$(TEST_BIN): $(LIBARCHIVE_LIB) $(FREETYPE2_LIB) $(HARNESS_OBJ) + $(CXX) \ + $(CXXFLAGS) \ + -std=c++11 \ + -I $(FREETYPE2_DIR)include \ + -I $(FREETYPE2_DIR) \ + -I $(LIBARCHIVE_DIR)/libarchive \ + $(FUZZER_SRC) \ + $(FREETYPE2_LIB) \ + $(LIBARCHIVE_LIB) \ + $(HARNESS_OBJ) \ + -o $@ + +########## DUMMY ####### + +$(TRT_DIR): | $(BUILD_DIR) + git clone $(TRT_GIT_REPO) $@ + +$(TEST_DATA_DIR): | $(TRT_DIR) + mkdir -p $@ + cp $(TRT_DIR)fonts/TestKERNOne.otf $@ + cp $(TRT_DIR)fonts/TestGLYFOne.ttf $@ + +$(TEST_DATA_FILE): | $(TEST_DATA_DIR) + dd if=/dev/zero bs=1048576 count=1 of=$@ + +###### TEST DATA ####### + +clean: + rm -rf $(BUILD_DIR) + +frida: $(TEST_BIN) $(AFLPP_FRIDA_DRIVER_HOOK_OBJ) $(TEST_DATA_FILE) + AFL_FRIDA_PERSISTENT_CNT=1000000 \ + AFL_FRIDA_PERSISTENT_HOOK=$(AFLPP_FRIDA_DRIVER_HOOK_OBJ) \ + AFL_FRIDA_PERSISTENT_ADDR=$(AFL_FRIDA_PERSISTENT_ADDR) \ + AFL_ENTRYPOINT=$(AFL_FRIDA_PERSISTENT_ADDR) \ + $(ROOT)afl-fuzz \ + -i $(TEST_DATA_DIR) \ + -o $(FRIDA_OUT) \ + -m none \ + -d \ + -O \ + -V 30 \ + -- \ + $(TEST_BIN) $(TEST_DATA_FILE) + +qemu: $(TEST_BIN) $(AFLPP_QEMU_DRIVER_HOOK_OBJ) $(TEST_DATA_FILE) + AFL_QEMU_PERSISTENT_CNT=1000000 \ + AFL_QEMU_PERSISTENT_HOOK=$(AFLPP_QEMU_DRIVER_HOOK_OBJ) \ + AFL_QEMU_PERSISTENT_ADDR=$(AFL_QEMU_PERSISTENT_ADDR) \ + AFL_ENTRYPOINT=$(AFL_QEMU_PERSISTENT_ADDR) \ + $(ROOT)afl-fuzz \ + -i $(TEST_DATA_DIR) \ + -o $(QEMU_OUT) \ + -m none \ + -d \ + -Q \ + -V 30 \ + -- \ + $(TEST_BIN) $(TEST_DATA_FILE) diff --git a/frida_mode/test/freetype2/Makefile b/frida_mode/test/freetype2/Makefile new file mode 100644 index 00000000..07b139e9 --- /dev/null +++ b/frida_mode/test/freetype2/Makefile @@ -0,0 +1,13 @@ +all: + @echo trying to use GNU make... + @gmake all || echo please install GNUmake + +32: + @echo trying to use GNU make... + @gmake 32 || echo please install GNUmake + +clean: + @gmake clean + +frida: + @gmake frida diff --git a/frida_mode/test/freetype2/get_symbol_addr.py b/frida_mode/test/freetype2/get_symbol_addr.py new file mode 100755 index 00000000..1c46e010 --- /dev/null +++ b/frida_mode/test/freetype2/get_symbol_addr.py @@ -0,0 +1,36 @@ +#!/usr/bin/python3 +import argparse +from elftools.elf.elffile import ELFFile + +def process_file(file, symbol, base): + with open(file, 'rb') as f: + elf = ELFFile(f) + symtab = elf.get_section_by_name('.symtab') + mains = symtab.get_symbol_by_name(symbol) + if len(mains) != 1: + print ("Failed to find main") + return 1 + + main_addr = mains[0]['st_value'] + main = base + main_addr + print ("0x%016x" % main) + return 0 + +def hex_value(x): + return int(x, 16) + +def main(): + parser = argparse.ArgumentParser(description='Process some integers.') + parser.add_argument('-f', '--file', dest='file', type=str, + help='elf file name', required=True) + parser.add_argument('-s', '--symbol', dest='symbol', type=str, + help='symbol name', required=True) + parser.add_argument('-b', '--base', dest='base', type=hex_value, + help='elf base address', required=True) + + args = parser.parse_args() + return process_file (args.file, args.symbol, args.base) + +if __name__ == "__main__": + ret = main() + exit(ret) diff --git a/frida_mode/test/libpcap/GNUmakefile b/frida_mode/test/libpcap/GNUmakefile index 6f2b58af..f8dc3db7 100644 --- a/frida_mode/test/libpcap/GNUmakefile +++ b/frida_mode/test/libpcap/GNUmakefile @@ -59,7 +59,7 @@ GET_SYMBOL_ADDR:=$(ROOT)frida_mode/util/get_symbol_addr.sh AFL_QEMU_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x4000000000) -ifeq "$(ARCH)" "aarch64" +ifeq "$(ARCH)" "arm64" AFL_FRIDA_PERSISTENT_ADDR=$(shell $(GET_SYMBOL_ADDR) $(TEST_BIN) LLVMFuzzerTestOneInput 0x0000aaaaaaaaa000) endif diff --git a/frida_mode/ts/lib/afl.ts b/frida_mode/ts/lib/afl.ts index 8a1ebf1b..538d9b70 100644 --- a/frida_mode/ts/lib/afl.ts +++ b/frida_mode/ts/lib/afl.ts @@ -284,6 +284,13 @@ class Afl { Afl.jsApiSetStdOut(buf); } + /** + * See `AFL_FRIDA_TRACEABLE`. + */ + public static setTraceable(): void { + Afl.jsApiSetTraceable(); + } + private static readonly jsApiAddExcludeRange = Afl.jsApiGetFunction( "js_api_add_exclude_range", "void", @@ -431,6 +438,11 @@ class Afl { "void", ["pointer"]); + private static readonly jsApiSetTraceable = Afl.jsApiGetFunction( + "js_api_set_traceable", + "void", + []); + private static readonly jsApiWrite = new NativeFunction( /* tslint:disable-next-line:no-null-keyword */ Module.getExportByName(null, "write"), diff --git a/frida_mode/ub1804/Dockerfile b/frida_mode/ub1804/Dockerfile new file mode 100644 index 00000000..e1f5a339 --- /dev/null +++ b/frida_mode/ub1804/Dockerfile @@ -0,0 +1,6 @@ +FROM ubuntu:xenial + +WORKDIR /AFLplusplus + +RUN apt-get update +RUN apt-get install -y make gcc g++ xz-utils curl wget clang zlib1g-dev \ No newline at end of file diff --git a/frida_mode/ub1804/GNUmakefile b/frida_mode/ub1804/GNUmakefile new file mode 100644 index 00000000..4247916e --- /dev/null +++ b/frida_mode/ub1804/GNUmakefile @@ -0,0 +1,37 @@ +PWD:=$(shell pwd)/ +ROOT:=$(PWD)../../ + +.PHONY: all build docker clean shell test + +all: docker + docker run --rm \ + -v $(ROOT):/AFLplusplus \ + ub1804-afl-frida \ + /bin/sh -c \ + 'make -C /AFLplusplus/ clean all && \ + make -C /AFLplusplus/frida_mode clean all' + +test: + docker run --rm \ + -v $(ROOT):/AFLplusplus \ + ub1804-afl-frida \ + /bin/sh -c \ + 'make -C /AFLplusplus/frida_mode/test/png clean all && \ + make -C /AFLplusplus/frida_mode/test/png/persistent/hook frida' + +build: + docker run --rm \ + -v $(ROOT):/AFLplusplus \ + ub1804-afl-frida \ + /bin/sh -c \ + 'make -C /AFLplusplus/ all && \ + make -C /AFLplusplus/frida_mode all' + +docker: + docker build --tag ub1804-afl-frida . + +clean: + docker images --filter 'dangling=true' -q --no-trunc | xargs -L1 docker rmi --force + +shell: + docker run -ti --rm ub1804-afl-frida /bin/bash diff --git a/frida_mode/ub1804/Makefile b/frida_mode/ub1804/Makefile new file mode 100644 index 00000000..f3c3cd55 --- /dev/null +++ b/frida_mode/ub1804/Makefile @@ -0,0 +1,9 @@ +all: + @echo trying to use GNU make... + @gmake all || echo please install GNUmake + +clean: + @gmake clean + +shell: + @gmake shell diff --git a/include/afl-fuzz.h b/include/afl-fuzz.h index 4b19e698..eaf55fb8 100644 --- a/include/afl-fuzz.h +++ b/include/afl-fuzz.h @@ -1130,7 +1130,6 @@ void get_core_count(afl_state_t *); void fix_up_sync(afl_state_t *); void check_asan_opts(afl_state_t *); void check_binary(afl_state_t *, u8 *); -void fix_up_banner(afl_state_t *, u8 *); void check_if_tty(afl_state_t *); void setup_signal_handlers(void); void save_cmdline(afl_state_t *, u32, char **); diff --git a/include/common.h b/include/common.h index 7bba9e91..2ca44301 100644 --- a/include/common.h +++ b/include/common.h @@ -38,6 +38,7 @@ #define STRINGIFY_VAL_SIZE_MAX (16) +u32 check_binary_signatures(u8 *fn); void detect_file_args(char **argv, u8 *prog_in, bool *use_stdin); void print_suggested_envs(char *mispelled_env); void check_environment_vars(char **env); diff --git a/include/config.h b/include/config.h index da74989e..4630da0c 100644 --- a/include/config.h +++ b/include/config.h @@ -237,11 +237,11 @@ (note that if this value is changed, several areas in afl-cc.c, afl-fuzz.c and afl-fuzz-state.c have to be changed as well! */ -#define MAX_FILE (1 * 1024 * 1024U) +#define MAX_FILE (1 * 1024 * 1024L) /* The same, for the test case minimizer: */ -#define TMIN_MAX_FILE (10 * 1024 * 1024) +#define TMIN_MAX_FILE (10 * 1024 * 1024L) /* Block normalization steps for afl-tmin: */ diff --git a/include/envs.h b/include/envs.h index e3957147..61267a0d 100644 --- a/include/envs.h +++ b/include/envs.h @@ -76,6 +76,7 @@ static char *afl_environment_variables[] = { "AFL_FRIDA_PERSISTENT_RET", "AFL_FRIDA_STATS_FILE", "AFL_FRIDA_STATS_INTERVAL", + "AFL_FRIDA_TRACEABLE", "AFL_FUZZER_ARGS", // oss-fuzz "AFL_GDB", "AFL_GCC_ALLOWLIST", diff --git a/instrumentation/README.laf-intel.md b/instrumentation/README.laf-intel.md index 229807e8..789055ed 100644 --- a/instrumentation/README.laf-intel.md +++ b/instrumentation/README.laf-intel.md @@ -3,9 +3,8 @@ ## Introduction This originally is the work of an individual nicknamed laf-intel. -His blog [Circumventing Fuzzing Roadblocks with Compiler Transformations] -(https://lafintel.wordpress.com/) and gitlab repo [laf-llvm-pass] -(https://gitlab.com/laf-intel/laf-llvm-pass/) +His blog [Circumventing Fuzzing Roadblocks with Compiler Transformations](https://lafintel.wordpress.com/) +and gitlab repo [laf-llvm-pass](https://gitlab.com/laf-intel/laf-llvm-pass/) describe some code transformations that help AFL++ to enter conditional blocks, where conditions consist of comparisons of large values. diff --git a/instrumentation/README.llvm.md b/instrumentation/README.llvm.md index 6e210a7c..5b1e60cc 100644 --- a/instrumentation/README.llvm.md +++ b/instrumentation/README.llvm.md @@ -2,7 +2,7 @@ (See [../README.md](../README.md) for the general instruction manual.) - (See [README.gcc_plugin.md](../README.gcc_plugin.md) for the GCC-based instrumentation.) + (See [README.gcc_plugin.md](README.gcc_plugin.md) for the GCC-based instrumentation.) ## 1) Introduction diff --git a/instrumentation/SanitizerCoverageLTO.so.cc b/instrumentation/SanitizerCoverageLTO.so.cc index e06f8b93..d90fa867 100644 --- a/instrumentation/SanitizerCoverageLTO.so.cc +++ b/instrumentation/SanitizerCoverageLTO.so.cc @@ -250,7 +250,7 @@ class ModuleSanitizerCoverage { Module * Mo = NULL; GlobalVariable * AFLMapPtr = NULL; Value * MapPtrFixed = NULL; - FILE * documentFile = NULL; + std::ofstream dFile; size_t found = 0; // afl++ END @@ -446,8 +446,8 @@ bool ModuleSanitizerCoverage::instrumentModule( if ((ptr = getenv("AFL_LLVM_DOCUMENT_IDS")) != NULL) { - if ((documentFile = fopen(ptr, "a")) == NULL) - WARNF("Cannot access document file %s", ptr); + dFile.open(ptr, std::ofstream::out | std::ofstream::app); + if (dFile.is_open()) WARNF("Cannot access document file %s", ptr); } @@ -1003,12 +1003,7 @@ bool ModuleSanitizerCoverage::instrumentModule( instrumentFunction(F, DTCallback, PDTCallback); // afl++ START - if (documentFile) { - - fclose(documentFile); - documentFile = NULL; - - } + if (dFile.is_open()) dFile.close(); if (!getenv("AFL_LLVM_LTO_DONTWRITEID") || dictionary.size() || map_addr) { @@ -1069,7 +1064,6 @@ bool ModuleSanitizerCoverage::instrumentModule( if (dictionary.size()) { size_t memlen = 0, count = 0, offset = 0; - char * ptr; // sort and unique the dictionary std::sort(dictionary.begin(), dictionary.end()); @@ -1089,13 +1083,7 @@ bool ModuleSanitizerCoverage::instrumentModule( if (count) { - if ((ptr = (char *)malloc(memlen + count)) == NULL) { - - fprintf(stderr, "Error: malloc for %lu bytes failed!\n", - memlen + count); - exit(-1); - - } + auto ptrhld = std::unique_ptr<char[]>(new char[memlen + count]); count = 0; @@ -1103,8 +1091,8 @@ bool ModuleSanitizerCoverage::instrumentModule( if (offset + token.length() < 0xfffff0 && count < MAX_AUTO_EXTRAS) { - ptr[offset++] = (uint8_t)token.length(); - memcpy(ptr + offset, token.c_str(), token.length()); + ptrhld.get()[offset++] = (uint8_t)token.length(); + memcpy(ptrhld.get() + offset, token.c_str(), token.length()); offset += token.length(); count++; @@ -1124,10 +1112,10 @@ bool ModuleSanitizerCoverage::instrumentModule( GlobalVariable *AFLInternalDictionary = new GlobalVariable( M, ArrayTy, true, GlobalValue::ExternalLinkage, ConstantDataArray::get(Ctx, - *(new ArrayRef<char>((char *)ptr, offset))), + *(new ArrayRef<char>(ptrhld.get(), offset))), "__afl_internal_dictionary"); AFLInternalDictionary->setInitializer(ConstantDataArray::get( - Ctx, *(new ArrayRef<char>((char *)ptr, offset)))); + Ctx, *(new ArrayRef<char>(ptrhld.get(), offset)))); AFLInternalDictionary->setConstant(true); GlobalVariable *AFLDictionary = new GlobalVariable( @@ -1509,12 +1497,12 @@ void ModuleSanitizerCoverage::InjectCoverageAtBlock(Function &F, BasicBlock &BB, // afl++ START ++afl_global_id; - if (documentFile) { + if (dFile.is_open()) { unsigned long long int moduleID = (((unsigned long long int)(rand() & 0xffffffff)) << 32) | getpid(); - fprintf(documentFile, "ModuleID=%llu Function=%s edgeID=%u\n", moduleID, - F.getName().str().c_str(), afl_global_id); + dFile << "ModuleID=" << moduleID << " Function=" << F.getName().str() + << " edgeID=" << afl_global_id << "\n"; } diff --git a/instrumentation/SanitizerCoveragePCGUARD.so.cc b/instrumentation/SanitizerCoveragePCGUARD.so.cc index 48ad2d02..013492f9 100644 --- a/instrumentation/SanitizerCoveragePCGUARD.so.cc +++ b/instrumentation/SanitizerCoveragePCGUARD.so.cc @@ -881,8 +881,6 @@ void ModuleSanitizerCoverage::InjectCoverageForIndirectCalls( Function &F, ArrayRef<Instruction *> IndirCalls) { if (IndirCalls.empty()) return; - assert(Options.TracePC || Options.TracePCGuard || - Options.Inline8bitCounters /*|| Options.InlineBoolFlag*/); for (auto I : IndirCalls) { IRBuilder<> IRB(I); diff --git a/instrumentation/afl-llvm-dict2file.so.cc b/instrumentation/afl-llvm-dict2file.so.cc index 4622e488..0a3e74b9 100644 --- a/instrumentation/afl-llvm-dict2file.so.cc +++ b/instrumentation/afl-llvm-dict2file.so.cc @@ -66,6 +66,9 @@ namespace { class AFLdict2filePass : public ModulePass { + std::ofstream of; + void dict2file(u8 *, u32); + public: static char ID; @@ -81,7 +84,7 @@ class AFLdict2filePass : public ModulePass { } // namespace -void dict2file(int fd, u8 *mem, u32 len) { +void AFLdict2filePass::dict2file(u8 *mem, u32 len) { u32 i, j, binary = 0; char line[MAX_AUTO_EXTRA * 8], tmp[8]; @@ -113,9 +116,8 @@ void dict2file(int fd, u8 *mem, u32 len) { line[j] = 0; strcat(line, "\"\n"); - if (write(fd, line, strlen(line)) <= 0) - PFATAL("Could not write to dictionary file"); - fsync(fd); + of << line; + of.flush(); if (!be_quiet) fprintf(stderr, "Found dictionary token: %s", line); @@ -125,7 +127,7 @@ bool AFLdict2filePass::runOnModule(Module &M) { DenseMap<Value *, std::string *> valueMap; char * ptr; - int fd, found = 0; + int found = 0; /* Show a banner */ setvbuf(stdout, NULL, _IONBF, 0); @@ -146,8 +148,8 @@ bool AFLdict2filePass::runOnModule(Module &M) { if (!ptr || *ptr != '/') FATAL("AFL_LLVM_DICT2FILE is not set to an absolute path: %s", ptr); - if ((fd = open(ptr, O_WRONLY | O_APPEND | O_CREAT | O_DSYNC, 0644)) < 0) - PFATAL("Could not open/create %s.", ptr); + of.open(ptr, std::ofstream::out | std::ofstream::app); + if (!of.is_open()) PFATAL("Could not open/create %s.", ptr); /* Instrument all the things! */ @@ -264,11 +266,11 @@ bool AFLdict2filePass::runOnModule(Module &M) { } - dict2file(fd, (u8 *)&val, len); + dict2file((u8 *)&val, len); found++; if (val2) { - dict2file(fd, (u8 *)&val2, len); + dict2file((u8 *)&val2, len); found++; } @@ -630,7 +632,7 @@ bool AFLdict2filePass::runOnModule(Module &M) { ptr = (char *)thestring.c_str(); - dict2file(fd, (u8 *)ptr, optLen); + dict2file((u8 *)ptr, optLen); found++; } @@ -641,7 +643,7 @@ bool AFLdict2filePass::runOnModule(Module &M) { } - close(fd); + of.close(); /* Say something nice. */ diff --git a/instrumentation/afl-llvm-lto-instrumentation.so.cc b/instrumentation/afl-llvm-lto-instrumentation.so.cc index e300044c..c2f61d34 100644 --- a/instrumentation/afl-llvm-lto-instrumentation.so.cc +++ b/instrumentation/afl-llvm-lto-instrumentation.so.cc @@ -28,6 +28,7 @@ #include <sys/time.h> #include <list> +#include <memory> #include <string> #include <fstream> #include <set> @@ -107,8 +108,8 @@ bool AFLLTOPass::runOnModule(Module &M) { // std::vector<CallInst *> calls; DenseMap<Value *, std::string *> valueMap; std::vector<BasicBlock *> BlockList; + std::ofstream dFile; char * ptr; - FILE * documentFile = NULL; size_t found = 0; srand((unsigned int)time(NULL)); @@ -136,8 +137,8 @@ bool AFLLTOPass::runOnModule(Module &M) { if ((ptr = getenv("AFL_LLVM_DOCUMENT_IDS")) != NULL) { - if ((documentFile = fopen(ptr, "a")) == NULL) - WARNF("Cannot access document file %s", ptr); + dFile.open(ptr, std::ofstream::out | std::ofstream::app); + if (!dFile.is_open()) WARNF("Cannot access document file %s", ptr); } @@ -242,8 +243,14 @@ bool AFLLTOPass::runOnModule(Module &M) { // the instrument file list check AttributeList Attrs = F.getAttributes(); +#if LLVM_VERSION_MAJOR < 14 if (Attrs.hasAttribute(-1, StringRef("skipinstrument"))) { +#else + if (Attrs.hasFnAttr(StringRef("skipinstrument"))) { + +#endif + if (debug) fprintf(stderr, "DEBUG: Function %s is not in a source file that was specified " @@ -844,10 +851,11 @@ bool AFLLTOPass::runOnModule(Module &M) { } - if (documentFile) { + if (dFile.is_open()) { - fprintf(documentFile, "ModuleID=%llu Function=%s edgeID=%u\n", - moduleID, F.getName().str().c_str(), afl_global_id); + dFile << "ModuleID=" << moduleID + << " Function=" << F.getName().str() + << " edgeID=" << afl_global_id << "\n"; } @@ -919,8 +927,7 @@ bool AFLLTOPass::runOnModule(Module &M) { } - if (documentFile) fclose(documentFile); - documentFile = NULL; + if (dFile.is_open()) dFile.close(); // save highest location ID to global variable // do this after each function to fail faster @@ -1015,13 +1022,7 @@ bool AFLLTOPass::runOnModule(Module &M) { if (count) { - if ((ptr = (char *)malloc(memlen + count)) == NULL) { - - fprintf(stderr, "Error: malloc for %zu bytes failed!\n", - memlen + count); - exit(-1); - - } + auto ptrhld = std::unique_ptr<char[]>(new char[memlen + count]); count = 0; @@ -1030,8 +1031,8 @@ bool AFLLTOPass::runOnModule(Module &M) { if (offset + token.length() < 0xfffff0 && count < MAX_AUTO_EXTRAS) { - ptr[offset++] = (uint8_t)token.length(); - memcpy(ptr + offset, token.c_str(), token.length()); + ptrhld.get()[offset++] = (uint8_t)token.length(); + memcpy(ptrhld.get() + offset, token.c_str(), token.length()); offset += token.length(); count++; @@ -1051,10 +1052,10 @@ bool AFLLTOPass::runOnModule(Module &M) { GlobalVariable *AFLInternalDictionary = new GlobalVariable( M, ArrayTy, true, GlobalValue::ExternalLinkage, ConstantDataArray::get(C, - *(new ArrayRef<char>((char *)ptr, offset))), + *(new ArrayRef<char>(ptrhld.get(), offset))), "__afl_internal_dictionary"); AFLInternalDictionary->setInitializer(ConstantDataArray::get( - C, *(new ArrayRef<char>((char *)ptr, offset)))); + C, *(new ArrayRef<char>(ptrhld.get(), offset)))); AFLInternalDictionary->setConstant(true); GlobalVariable *AFLDictionary = new GlobalVariable( diff --git a/instrumentation/afl-llvm-lto-instrumentlist.so.cc b/instrumentation/afl-llvm-lto-instrumentlist.so.cc index 416dbb88..ee2e5dd3 100644 --- a/instrumentation/afl-llvm-lto-instrumentlist.so.cc +++ b/instrumentation/afl-llvm-lto-instrumentlist.so.cc @@ -116,10 +116,15 @@ bool AFLcheckIfInstrument::runOnModule(Module &M) { auto & Ctx = F.getContext(); AttributeList Attrs = F.getAttributes(); - AttrBuilder NewAttrs; +#if LLVM_VERSION_MAJOR < 14 + AttrBuilder NewAttrs; NewAttrs.addAttribute("skipinstrument"); F.setAttributes( Attrs.addAttributes(Ctx, AttributeList::FunctionIndex, NewAttrs)); +#else + AttributeList NewAttrs = Attrs.addFnAttribute(Ctx, "skipinstrument"); + F.setAttributes(NewAttrs); +#endif } diff --git a/instrumentation/split-compares-pass.so.cc b/instrumentation/split-compares-pass.so.cc index 13f45b69..e63be98c 100644 --- a/instrumentation/split-compares-pass.so.cc +++ b/instrumentation/split-compares-pass.so.cc @@ -578,16 +578,16 @@ bool SplitComparesTransform::splitCompare(CmpInst *cmp_inst, Module &M, /* dependent on the cmp of the high parts go to the end or go on with * the comparison */ - auto term = bb->getTerminator(); - BranchInst *br = nullptr; + auto term = bb->getTerminator(); + if (pred == CmpInst::ICMP_EQ) { - br = BranchInst::Create(cmp_low_bb, end_bb, icmp_high, bb); + BranchInst::Create(cmp_low_bb, end_bb, icmp_high, bb); } else { - /* CmpInst::ICMP_NE */ - br = BranchInst::Create(end_bb, cmp_low_bb, icmp_high, bb); + // CmpInst::ICMP_NE + BranchInst::Create(end_bb, cmp_low_bb, icmp_high, bb); } diff --git a/qemu_mode/QEMUAFL_VERSION b/qemu_mode/QEMUAFL_VERSION index 215826cc..7bdedf7b 100644 --- a/qemu_mode/QEMUAFL_VERSION +++ b/qemu_mode/QEMUAFL_VERSION @@ -1 +1 @@ -a6758d1cc3 +71ed0d206f diff --git a/qemu_mode/libcompcov/libcompcov.so.c b/qemu_mode/libcompcov/libcompcov.so.c index 4fc84e62..24867cda 100644 --- a/qemu_mode/libcompcov/libcompcov.so.c +++ b/qemu_mode/libcompcov/libcompcov.so.c @@ -41,6 +41,13 @@ #error "Sorry, this library is Linux-specific for now!" #endif /* !__linux__ */ +#ifndef likely +# define likely(x) __builtin_expect((!!(x)),1) +#endif +#ifndef unlikely +# define unlikely(x) __builtin_expect((!!(x)),0) +#endif + /* Change this value to tune the compare coverage */ #define MAX_CMP_LENGTH 32 @@ -199,6 +206,7 @@ static u8 __compcov_is_in_bound(const void *ptr) { int strcmp(const char *str1, const char *str2) { + if (unlikely(!__libc_strcmp)) { __libc_strcmp = dlsym(RTLD_NEXT, "strcmp"); } void *retaddr = __builtin_return_address(0); if (__compcov_is_in_bound(retaddr) && @@ -227,6 +235,7 @@ int strcmp(const char *str1, const char *str2) { int strncmp(const char *str1, const char *str2, size_t len) { + if (unlikely(!__libc_strncmp)) { __libc_strncmp = dlsym(RTLD_NEXT, "strncmp"); } void *retaddr = __builtin_return_address(0); if (__compcov_is_in_bound(retaddr) && @@ -256,6 +265,7 @@ int strncmp(const char *str1, const char *str2, size_t len) { int strcasecmp(const char *str1, const char *str2) { + if (unlikely(!__libc_strcasecmp)) { __libc_strncasecmp = dlsym(RTLD_NEXT, "strcasecmp"); } void *retaddr = __builtin_return_address(0); if (__compcov_is_in_bound(retaddr) && @@ -286,6 +296,7 @@ int strcasecmp(const char *str1, const char *str2) { int strncasecmp(const char *str1, const char *str2, size_t len) { + if (unlikely(!__libc_strncasecmp)) { __libc_strncasecmp = dlsym(RTLD_NEXT, "strncasecmp"); } void *retaddr = __builtin_return_address(0); if (__compcov_is_in_bound(retaddr) && @@ -317,6 +328,7 @@ int strncasecmp(const char *str1, const char *str2, size_t len) { int memcmp(const void *mem1, const void *mem2, size_t len) { + if (unlikely(!__libc_memcmp)) { __libc_memcmp = dlsym(RTLD_NEXT, "memcmp"); } void *retaddr = __builtin_return_address(0); if (__compcov_is_in_bound(retaddr) && diff --git a/qemu_mode/qemuafl b/qemu_mode/qemuafl -Subproject a6758d1cc3e4dde88fca3f0b3a903581b7c8b2e +Subproject 71ed0d206fd3d877420dceb4993a1011a4637ae diff --git a/src/afl-analyze.c b/src/afl-analyze.c index e19df3ce..09b01541 100644 --- a/src/afl-analyze.c +++ b/src/afl-analyze.c @@ -120,6 +120,17 @@ static u8 count_class_lookup[256] = { #undef TIMES8 #undef TIMES4 +static void kill_child() { + + if (fsrv.child_pid > 0) { + + kill(fsrv.child_pid, fsrv.kill_signal); + fsrv.child_pid = -1; + + } + +} + static void classify_counts(u8 *mem) { u32 i = map_size; @@ -184,7 +195,7 @@ static void read_initial_file(void) { if (st.st_size >= TMIN_MAX_FILE) { - FATAL("Input file is too large (%u MB max)", TMIN_MAX_FILE / 1024 / 1024); + FATAL("Input file is too large (%ld MB max)", TMIN_MAX_FILE / 1024 / 1024); } @@ -1053,6 +1064,7 @@ int main(int argc, char **argv_orig, char **envp) { fsrv.target_path = find_binary(argv[optind]); fsrv.trace_bits = afl_shm_init(&shm, map_size, 0); detect_file_args(argv + optind, fsrv.out_file, &use_stdin); + signal(SIGALRM, kill_child); if (qemu_mode) { @@ -1093,6 +1105,7 @@ int main(int argc, char **argv_orig, char **envp) { parse_afl_kill_signal_env(getenv("AFL_KILL_SIGNAL"), SIGKILL); read_initial_file(); + (void)check_binary_signatures(fsrv.target_path); ACTF("Performing dry run (mem limit = %llu MB, timeout = %u ms%s)...", mem_limit, exec_tmout, edges_only ? ", edges only" : ""); diff --git a/src/afl-cc.c b/src/afl-cc.c index e49addc4..77407a98 100644 --- a/src/afl-cc.c +++ b/src/afl-cc.c @@ -1007,7 +1007,11 @@ static void edit_params(u32 argc, char **argv, char **envp) { } // prevent unnecessary build errors - cc_params[cc_par_cnt++] = "-Wno-unused-command-line-argument"; + if (compiler_mode != GCC_PLUGIN && compiler_mode != GCC) { + + cc_params[cc_par_cnt++] = "-Wno-unused-command-line-argument"; + + } if (preprocessor_only || have_c) { diff --git a/src/afl-common.c b/src/afl-common.c index 9ca2b3e8..db19f0a7 100644 --- a/src/afl-common.c +++ b/src/afl-common.c @@ -25,8 +25,12 @@ #include <stdlib.h> #include <stdio.h> +#define _GNU_SOURCE +#define __USE_GNU +#include <string.h> #include <strings.h> #include <math.h> +#include <sys/mman.h> #include "debug.h" #include "alloc-inl.h" @@ -51,6 +55,66 @@ u8 last_intr = 0; #define AFL_PATH "/usr/local/lib/afl/" #endif +u32 check_binary_signatures(u8 *fn) { + + int ret = 0, fd = open(fn, O_RDONLY); + if (fd < 0) { PFATAL("Unable to open '%s'", fn); } + struct stat st; + if (fstat(fd, &st) < 0) { PFATAL("Unable to fstat '%s'", fn); } + u32 f_len = st.st_size; + u8 *f_data = mmap(0, f_len, PROT_READ, MAP_PRIVATE, fd, 0); + if (f_data == MAP_FAILED) { PFATAL("Unable to mmap file '%s'", fn); } + close(fd); + + if (memmem(f_data, f_len, PERSIST_SIG, strlen(PERSIST_SIG) + 1)) { + + if (!be_quiet) { OKF(cPIN "Persistent mode binary detected."); } + setenv(PERSIST_ENV_VAR, "1", 1); + ret = 1; + + } else if (getenv("AFL_PERSISTENT")) { + + if (!be_quiet) { + + WARNF("AFL_PERSISTENT is no longer supported and may misbehave!"); + + } + + } else if (getenv("AFL_FRIDA_PERSISTENT_ADDR")) { + + if (!be_quiet) { + + OKF("FRIDA Persistent mode configuration options detected."); + + } + + setenv(PERSIST_ENV_VAR, "1", 1); + ret = 1; + + } + + if (memmem(f_data, f_len, DEFER_SIG, strlen(DEFER_SIG) + 1)) { + + if (!be_quiet) { OKF(cPIN "Deferred forkserver binary detected."); } + setenv(DEFER_ENV_VAR, "1", 1); + ret += 2; + + } else if (getenv("AFL_DEFER_FORKSRV")) { + + if (!be_quiet) { + + WARNF("AFL_DEFER_FORKSRV is no longer supported and may misbehave!"); + + } + + } + + if (munmap(f_data, f_len)) { PFATAL("unmap() failed"); } + + return ret; + +} + void detect_file_args(char **argv, u8 *prog_in, bool *use_stdin) { u32 i = 0; diff --git a/src/afl-forkserver.c b/src/afl-forkserver.c index c8c94c08..80b295e0 100644 --- a/src/afl-forkserver.c +++ b/src/afl-forkserver.c @@ -603,19 +603,31 @@ void afl_fsrv_start(afl_forkserver_t *fsrv, char **argv, /* Wait for the fork server to come up, but don't wait too long. */ rlen = 0; - if (fsrv->exec_tmout) { + if (fsrv->init_tmout) { u32 time_ms = read_s32_timed(fsrv->fsrv_st_fd, &status, fsrv->init_tmout, stop_soon_p); if (!time_ms) { - kill(fsrv->fsrv_pid, fsrv->kill_signal); + s32 tmp_pid = fsrv->fsrv_pid; + if (tmp_pid > 0) { + + kill(tmp_pid, fsrv->kill_signal); + fsrv->fsrv_pid = -1; + + } } else if (time_ms > fsrv->init_tmout) { fsrv->last_run_timed_out = 1; - kill(fsrv->fsrv_pid, fsrv->kill_signal); + s32 tmp_pid = fsrv->fsrv_pid; + if (tmp_pid > 0) { + + kill(tmp_pid, fsrv->kill_signal); + fsrv->fsrv_pid = -1; + + } } else { @@ -1248,7 +1260,14 @@ fsrv_run_result_t afl_fsrv_run_target(afl_forkserver_t *fsrv, u32 timeout, /* If there was no response from forkserver after timeout seconds, we kill the child. The forkserver should inform us afterwards */ - kill(fsrv->child_pid, fsrv->kill_signal); + s32 tmp_pid = fsrv->child_pid; + if (tmp_pid > 0) { + + kill(tmp_pid, fsrv->kill_signal); + fsrv->child_pid = -1; + + } + fsrv->last_run_timed_out = 1; if (read(fsrv->fsrv_st_fd, &fsrv->child_status, 4) < 4) { exec_ms = 0; } @@ -1282,7 +1301,7 @@ fsrv_run_result_t afl_fsrv_run_target(afl_forkserver_t *fsrv, u32 timeout, } - if (!WIFSTOPPED(fsrv->child_status)) { fsrv->child_pid = 0; } + if (!WIFSTOPPED(fsrv->child_status)) { fsrv->child_pid = -1; } fsrv->total_execs++; diff --git a/src/afl-fuzz-bitmap.c b/src/afl-fuzz-bitmap.c index 0ae4d607..316067e4 100644 --- a/src/afl-fuzz-bitmap.c +++ b/src/afl-fuzz-bitmap.c @@ -317,8 +317,9 @@ u8 *describe_op(afl_state_t *afl, u8 new_bits, size_t max_description_len) { } - sprintf(ret + strlen(ret), ",time:%llu", - get_cur_time() + afl->prev_run_time - afl->start_time); + sprintf(ret + strlen(ret), ",time:%llu,execs:%llu", + get_cur_time() + afl->prev_run_time - afl->start_time, + afl->fsrv.total_execs); if (afl->current_custom_fuzz && afl->current_custom_fuzz->afl_custom_describe) { diff --git a/src/afl-fuzz-init.c b/src/afl-fuzz-init.c index 9bb25785..1170715f 100644 --- a/src/afl-fuzz-init.c +++ b/src/afl-fuzz-init.c @@ -1325,8 +1325,8 @@ void pivot_inputs(afl_state_t *afl) { } - nfn = alloc_printf("%s/queue/id:%06u,time:0,orig:%s", afl->out_dir, id, - use_name); + nfn = alloc_printf("%s/queue/id:%06u,time:0,execs:%llu,orig:%s", + afl->out_dir, id, afl->fsrv.total_execs, use_name); #else @@ -2815,43 +2815,6 @@ void check_binary(afl_state_t *afl, u8 *fname) { } -/* Trim and possibly create a banner for the run. */ - -void fix_up_banner(afl_state_t *afl, u8 *name) { - - if (!afl->use_banner) { - - if (afl->sync_id) { - - afl->use_banner = afl->sync_id; - - } else { - - u8 *trim = strrchr(name, '/'); - if (!trim) { - - afl->use_banner = name; - - } else { - - afl->use_banner = trim + 1; - - } - - } - - } - - if (strlen(afl->use_banner) > 32) { - - u8 *tmp = ck_alloc(36); - sprintf(tmp, "%.32s...", afl->use_banner); - afl->use_banner = tmp; - - } - -} - /* Check if we're on TTY. */ void check_if_tty(afl_state_t *afl) { diff --git a/src/afl-fuzz-run.c b/src/afl-fuzz-run.c index 4173f4e1..da6ba7d9 100644 --- a/src/afl-fuzz-run.c +++ b/src/afl-fuzz-run.c @@ -291,8 +291,6 @@ static void write_with_gap(afl_state_t *afl, u8 *mem, u32 len, u32 skip_at, u8 calibrate_case(afl_state_t *afl, struct queue_entry *q, u8 *use_mem, u32 handicap, u8 from_queue) { - if (unlikely(afl->shm.cmplog_mode)) { q->exec_cksum = 0; } - u8 fault = 0, new_bits = 0, var_detected = 0, hnb = 0, first_run = (q->exec_cksum == 0); u64 start_us, stop_us, diff_us; @@ -300,6 +298,8 @@ u8 calibrate_case(afl_state_t *afl, struct queue_entry *q, u8 *use_mem, u32 use_tmout = afl->fsrv.exec_tmout; u8 *old_sn = afl->stage_name; + if (unlikely(afl->shm.cmplog_mode)) { q->exec_cksum = 0; } + /* Be a bit more generous about timeouts when resuming sessions, or when trying to calibrate already-added finds. This helps avoid trouble due to intermittent latency. */ @@ -343,6 +343,32 @@ u8 calibrate_case(afl_state_t *afl, struct queue_entry *q, u8 *use_mem, } + /* we need a dummy run if this is LTO + cmplog */ + if (unlikely(afl->shm.cmplog_mode)) { + + write_to_testcase(afl, use_mem, q->len); + + fault = fuzz_run_target(afl, &afl->fsrv, use_tmout); + + /* afl->stop_soon is set by the handler for Ctrl+C. When it's pressed, + we want to bail out quickly. */ + + if (afl->stop_soon || fault != afl->crash_mode) { goto abort_calibration; } + + if (!afl->non_instrumented_mode && !afl->stage_cur && + !count_bytes(afl, afl->fsrv.trace_bits)) { + + fault = FSRV_RUN_NOINST; + goto abort_calibration; + + } + +#ifdef INTROSPECTION + if (unlikely(!q->bitsmap_size)) q->bitsmap_size = afl->bitsmap_size; +#endif + + } + if (q->exec_cksum) { memcpy(afl->first_trace, afl->fsrv.trace_bits, afl->fsrv.map_size); diff --git a/src/afl-fuzz-stats.c b/src/afl-fuzz-stats.c index eb1fe2d9..0c06232b 100644 --- a/src/afl-fuzz-stats.c +++ b/src/afl-fuzz-stats.c @@ -441,9 +441,10 @@ void show_stats(afl_state_t *afl) { u64 cur_ms; u32 t_bytes, t_bits; - u32 banner_len, banner_pad; - u8 tmp[256]; - u8 time_tmp[64]; + static u8 banner[128]; + u32 banner_len, banner_pad; + u8 tmp[256]; + u8 time_tmp[64]; u8 val_buf[8][STRINGIFY_VAL_SIZE_MAX]; #define IB(i) (val_buf[(i)]) @@ -560,8 +561,9 @@ void show_stats(afl_state_t *afl) { /* Roughly every minute, update fuzzer stats and save auto tokens. */ - if (unlikely(afl->force_ui_update || - cur_ms - afl->stats_last_stats_ms > STATS_UPDATE_SEC * 1000)) { + if (unlikely(!afl->non_instrumented_mode && + (afl->force_ui_update || + cur_ms - afl->stats_last_stats_ms > STATS_UPDATE_SEC * 1000))) { afl->stats_last_stats_ms = cur_ms; write_stats_file(afl, t_bytes, t_byte_ratio, stab_ratio, @@ -655,26 +657,34 @@ void show_stats(afl_state_t *afl) { } /* Let's start by drawing a centered banner. */ + if (unlikely(!banner[0])) { - banner_len = (afl->crash_mode ? 24 : 22) + strlen(VERSION) + - strlen(afl->use_banner) + strlen(afl->power_name) + 3 + 5; - banner_pad = (79 - banner_len) / 2; - memset(tmp, ' ', banner_pad); + char *si = ""; + if (afl->sync_id) { si = afl->sync_id; } + memset(banner, 0, sizeof(banner)); + banner_len = (afl->crash_mode ? 20 : 18) + strlen(VERSION) + strlen(si) + + strlen(afl->power_name) + 4 + 6; -#ifdef HAVE_AFFINITY - sprintf( - tmp + banner_pad, - "%s " cLCY VERSION cLGN " (%s) " cPIN "[%s]" cBLU " {%d}", - afl->crash_mode ? cPIN "peruvian were-rabbit" : cYEL "american fuzzy lop", - afl->use_banner, afl->power_name, afl->cpu_aff); -#else - sprintf( - tmp + banner_pad, "%s " cLCY VERSION cLGN " (%s) " cPIN "[%s]", - afl->crash_mode ? cPIN "peruvian were-rabbit" : cYEL "american fuzzy lop", - afl->use_banner, afl->power_name); -#endif /* HAVE_AFFINITY */ + if (strlen(afl->use_banner) + banner_len > 75) { + + afl->use_banner += (strlen(afl->use_banner) + banner_len) - 76; + memset(afl->use_banner, '.', 3); + + } + + banner_len += strlen(afl->use_banner); + banner_pad = (79 - banner_len) / 2; + memset(banner, ' ', banner_pad); + + sprintf(banner + banner_pad, + "%s " cLCY VERSION cLBL " {%s} " cLGN "(%s) " cPIN "[%s]", + afl->crash_mode ? cPIN "peruvian were-rabbit" + : cYEL "american fuzzy lop", + si, afl->use_banner, afl->power_name); + + } - SAYF("\n%s\n", tmp); + SAYF("\n%s\n", banner); /* "Handy" shortcuts for drawing boxes... */ diff --git a/src/afl-fuzz.c b/src/afl-fuzz.c index 8ffc0e77..34f3377b 100644 --- a/src/afl-fuzz.c +++ b/src/afl-fuzz.c @@ -1189,7 +1189,17 @@ int main(int argc, char **argv_orig, char **envp) { } - if (afl->sync_id) { fix_up_sync(afl); } + if (afl->sync_id) { + + if (strlen(afl->sync_id) > 24) { + + FATAL("sync_id max length is 24 characters"); + + } + + fix_up_sync(afl); + + } if (!strcmp(afl->in_dir, afl->out_dir)) { @@ -1218,6 +1228,8 @@ int main(int argc, char **argv_orig, char **envp) { if (unlikely(afl->afl_env.afl_statsd)) { statsd_setup_format(afl); } + if (!afl->use_banner) { afl->use_banner = argv[optind]; } + if (strchr(argv[optind], '/') == NULL && !afl->unicorn_mode) { WARNF(cLRD @@ -1348,7 +1360,7 @@ int main(int argc, char **argv_orig, char **envp) { } else if (afl->q_testcase_max_cache_size < 2 * MAX_FILE) { - FATAL("AFL_TESTCACHE_SIZE must be set to %u or more, or 0 to disable", + FATAL("AFL_TESTCACHE_SIZE must be set to %ld or more, or 0 to disable", (2 * MAX_FILE) % 1048576 == 0 ? (2 * MAX_FILE) / 1048576 : 1 + ((2 * MAX_FILE) / 1048576)); @@ -1486,9 +1498,6 @@ int main(int argc, char **argv_orig, char **envp) { } save_cmdline(afl, argc, argv); - - fix_up_banner(afl, argv[optind]); - check_if_tty(afl); if (afl->afl_env.afl_force_ui) { afl->not_on_tty = 0; } @@ -1697,7 +1706,7 @@ int main(int argc, char **argv_orig, char **envp) { if (afl->non_instrumented_mode || afl->fsrv.qemu_mode || afl->fsrv.frida_mode || afl->unicorn_mode) { - map_size = afl->fsrv.map_size = MAP_SIZE; + map_size = afl->fsrv.real_map_size = afl->fsrv.map_size = MAP_SIZE; afl->virgin_bits = ck_realloc(afl->virgin_bits, map_size); afl->virgin_tmout = ck_realloc(afl->virgin_tmout, map_size); afl->virgin_crash = ck_realloc(afl->virgin_crash, map_size); @@ -1918,7 +1927,7 @@ int main(int argc, char **argv_orig, char **envp) { } - write_stats_file(afl, 0, 0, 0, 0); + if (!afl->non_instrumented_mode) { write_stats_file(afl, 0, 0, 0, 0); } maybe_update_plot_file(afl, 0, 0, 0); save_auto(afl); diff --git a/src/afl-showmap.c b/src/afl-showmap.c index 9122cd25..3826e385 100644 --- a/src/afl-showmap.c +++ b/src/afl-showmap.c @@ -77,7 +77,7 @@ static u32 tcnt, highest; /* tuple content information */ static u32 in_len; /* Input data length */ -static u32 map_size = MAP_SIZE; +static u32 map_size = MAP_SIZE, timed_out = 0; static bool quiet_mode, /* Hide non-essential messages? */ edges_only, /* Ignore hit counts? */ @@ -146,6 +146,18 @@ static const u8 count_class_binary[256] = { #undef TIMES8 #undef TIMES4 +static void kill_child() { + + timed_out = 1; + if (fsrv->child_pid > 0) { + + kill(fsrv->child_pid, fsrv->kill_signal); + fsrv->child_pid = -1; + + } + +} + static void classify_counts(afl_forkserver_t *fsrv) { u8 * mem = fsrv->trace_bits; @@ -242,9 +254,14 @@ static u32 write_results_to_file(afl_forkserver_t *fsrv, u8 *outfile) { if (cmin_mode && (fsrv->last_run_timed_out || (!caa && child_crashed != cco))) { - // create empty file to prevent error messages in afl-cmin - fd = open(outfile, O_WRONLY | O_CREAT | O_EXCL, DEFAULT_PERMISSION); - close(fd); + if (strcmp(outfile, "-")) { + + // create empty file to prevent error messages in afl-cmin + fd = open(outfile, O_WRONLY | O_CREAT | O_EXCL, DEFAULT_PERMISSION); + close(fd); + + } + return ret; } @@ -357,9 +374,10 @@ static void showmap_run_target_forkserver(afl_forkserver_t *fsrv, u8 *mem, if (!quiet_mode) { - if (fsrv->last_run_timed_out) { + if (timed_out || fsrv->last_run_timed_out) { SAYF(cLRD "\n+++ Program timed off +++\n" cRST); + timed_out = 0; } else if (stop_soon) { @@ -413,7 +431,7 @@ static u32 read_file(u8 *in_file) { if (!be_quiet && !quiet_mode) { - WARNF("Input file '%s' is too large, only reading %u bytes.", in_file, + WARNF("Input file '%s' is too large, only reading %ld bytes.", in_file, MAX_FILE); } @@ -521,6 +539,8 @@ static void showmap_run_target(afl_forkserver_t *fsrv, char **argv) { } + signal(SIGALRM, kill_child); + setitimer(ITIMER_REAL, &it, NULL); if (waitpid(fsrv->child_pid, &status, 0) <= 0) { FATAL("waitpid() failed"); } @@ -563,9 +583,10 @@ static void showmap_run_target(afl_forkserver_t *fsrv, char **argv) { if (!quiet_mode) { - if (fsrv->last_run_timed_out) { + if (timed_out || fsrv->last_run_timed_out) { SAYF(cLRD "\n+++ Program timed off +++\n" cRST); + timed_out = 0; } else if (stop_soon) { @@ -1189,6 +1210,8 @@ int main(int argc, char **argv_orig, char **envp) { } + if (in_dir) { (void)check_binary_signatures(fsrv->target_path); } + shm_fuzz = ck_alloc(sizeof(sharedmem_t)); /* initialize cmplog_mode */ diff --git a/src/afl-tmin.c b/src/afl-tmin.c index 792770e0..ce2a0b8f 100644 --- a/src/afl-tmin.c +++ b/src/afl-tmin.c @@ -120,6 +120,17 @@ static const u8 count_class_lookup[256] = { #undef TIMES8 #undef TIMES4 +static void kill_child() { + + if (fsrv->child_pid > 0) { + + kill(fsrv->child_pid, fsrv->kill_signal); + fsrv->child_pid = -1; + + } + +} + static sharedmem_t *deinit_shmem(afl_forkserver_t *fsrv, sharedmem_t * shm_fuzz) { @@ -221,7 +232,7 @@ static void read_initial_file(void) { if (st.st_size >= TMIN_MAX_FILE) { - FATAL("Input file is too large (%u MB max)", TMIN_MAX_FILE / 1024 / 1024); + FATAL("Input file is too large (%ld MB max)", TMIN_MAX_FILE / 1024 / 1024); } @@ -1125,6 +1136,7 @@ int main(int argc, char **argv_orig, char **envp) { fsrv->target_path = find_binary(argv[optind]); fsrv->trace_bits = afl_shm_init(&shm, map_size, 0); detect_file_args(argv + optind, out_file, &fsrv->use_stdin); + signal(SIGALRM, kill_child); if (fsrv->qemu_mode) { @@ -1209,6 +1221,7 @@ int main(int argc, char **argv_orig, char **envp) { fsrv->shmem_fuzz = map + sizeof(u32); read_initial_file(); + (void)check_binary_signatures(fsrv->target_path); if (!fsrv->qemu_mode && !unicorn_mode) { diff --git a/test/test-pre.sh b/test/test-pre.sh index 7819da47..e12d95be 100755 --- a/test/test-pre.sh +++ b/test/test-pre.sh @@ -88,6 +88,8 @@ unset AFL_QEMU_PERSISTENT_GPR unset AFL_QEMU_PERSISTENT_RET unset AFL_QEMU_PERSISTENT_HOOK unset AFL_QEMU_PERSISTENT_CNT +unset AFL_QEMU_PERSISTENT_MEM +unset AFL_QEMU_PERSISTENT_EXITS unset AFL_CUSTOM_MUTATOR_LIBRARY unset AFL_PYTHON_MODULE unset AFL_PRELOAD diff --git a/unicorn_mode/UNICORNAFL_VERSION b/unicorn_mode/UNICORNAFL_VERSION index 0db54339..d6acbf91 100644 --- a/unicorn_mode/UNICORNAFL_VERSION +++ b/unicorn_mode/UNICORNAFL_VERSION @@ -1 +1 @@ -c0e03d2c +94617f5b diff --git a/unicorn_mode/samples/speedtest/rust/src/main.rs b/unicorn_mode/samples/speedtest/rust/src/main.rs index 105ba4b4..89e10833 100644 --- a/unicorn_mode/samples/speedtest/rust/src/main.rs +++ b/unicorn_mode/samples/speedtest/rust/src/main.rs @@ -12,11 +12,11 @@ use std::{ use unicornafl::{ unicorn_const::{uc_error, Arch, Mode, Permission}, - RegisterX86::{self, *}, - Unicorn, UnicornHandle, + RegisterX86::*, + Unicorn, }; -const BINARY: &str = &"../target"; +const BINARY: &str = "../target"; // Memory map for the code to be tested // Arbitrary address where code to test will be loaded @@ -47,7 +47,7 @@ fn read_file(filename: &str) -> Result<Vec<u8>, io::Error> { fn parse_locs(loc_name: &str) -> Result<Vec<u64>, io::Error> { let contents = &read_file(&format!("../target.offsets.{}", loc_name))?; //println!("Read: {:?}", contents); - Ok(str_from_u8_unchecked(&contents) + Ok(str_from_u8_unchecked(contents) .split('\n') .map(|x| { //println!("Trying to convert {}", &x[2..]); @@ -87,8 +87,7 @@ fn main() { } fn fuzz(input_file: &str) -> Result<(), uc_error> { - let mut unicorn = Unicorn::new(Arch::X86, Mode::MODE_64, 0)?; - let mut uc: UnicornHandle<'_, _> = unicorn.borrow(); + let mut uc = Unicorn::new(Arch::X86, Mode::MODE_64, 0)?; let binary = read_file(BINARY).unwrap_or_else(|_| panic!("Could not read modem image: {}", BINARY)); @@ -105,7 +104,7 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { // Set the program counter to the start of the code let main_locs = parse_locs("main").unwrap(); //println!("Entry Point: {:x}", main_locs[0]); - uc.reg_write(RegisterX86::RIP as i32, main_locs[0])?; + uc.reg_write(RIP, main_locs[0])?; // Setup the stack. uc.mem_map( @@ -114,14 +113,14 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { Permission::READ | Permission::WRITE, )?; // Setup the stack pointer, but allocate two pointers for the pointers to input. - uc.reg_write(RSP as i32, STACK_ADDRESS + STACK_SIZE - 16)?; + uc.reg_write(RSP, STACK_ADDRESS + STACK_SIZE - 16)?; // Setup our input space, and push the pointer to it in the function params uc.mem_map(INPUT_ADDRESS, INPUT_MAX as usize, Permission::READ)?; // We have argc = 2 - uc.reg_write(RDI as i32, 2)?; + uc.reg_write(RDI, 2)?; // RSI points to our little 2 QWORD space at the beginning of the stack... - uc.reg_write(RSI as i32, STACK_ADDRESS + STACK_SIZE - 16)?; + uc.reg_write(RSI, STACK_ADDRESS + STACK_SIZE - 16)?; // ... which points to the Input. Write the ptr to mem in little endian. uc.mem_write( STACK_ADDRESS + STACK_SIZE - 16, @@ -133,13 +132,13 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { let already_allocated_malloc = already_allocated.clone(); // We use a very simple malloc/free stub here, // that only works for exactly one allocation at a time. - let hook_malloc = move |mut uc: UnicornHandle<'_, _>, addr: u64, size: u32| { + let hook_malloc = move |uc: &mut Unicorn<'_, _>, addr: u64, size: u32| { if already_allocated_malloc.get() { println!("Double malloc, not supported right now!"); abort(); } // read the first param - let malloc_size = uc.reg_read(RDI as i32).unwrap(); + let malloc_size = uc.reg_read(RDI).unwrap(); if malloc_size > HEAP_SIZE_MAX { println!( "Tried to allocate {} bytes, but we may only allocate up to {}", @@ -147,20 +146,20 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { ); abort(); } - uc.reg_write(RAX as i32, HEAP_ADDRESS).unwrap(); - uc.reg_write(RIP as i32, addr + size as u64).unwrap(); + uc.reg_write(RAX, HEAP_ADDRESS).unwrap(); + uc.reg_write(RIP, addr + size as u64).unwrap(); already_allocated_malloc.set(true); }; let already_allocated_free = already_allocated; // No real free, just set the "used"-flag to false. - let hook_free = move |mut uc: UnicornHandle<'_, _>, addr, size| { + let hook_free = move |uc: &mut Unicorn<'_, _>, addr, size| { if already_allocated_free.get() { println!("Double free detected. Real bug?"); abort(); } // read the first param - let free_ptr = uc.reg_read(RDI as i32).unwrap(); + let free_ptr = uc.reg_read(RDI).unwrap(); if free_ptr != HEAP_ADDRESS { println!( "Tried to free wrong mem region {:x} at code loc {:x}", @@ -168,7 +167,7 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { ); abort(); } - uc.reg_write(RIP as i32, addr + size as u64).unwrap(); + uc.reg_write(RIP, addr + size as u64).unwrap(); already_allocated_free.set(false); }; @@ -177,8 +176,8 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { */ // This is a fancy print function that we're just going to skip for fuzzing. - let hook_magicfn = move |mut uc: UnicornHandle<'_, _>, addr, size| { - uc.reg_write(RIP as i32, addr + size as u64).unwrap(); + let hook_magicfn = move |uc: &mut Unicorn<'_, _>, addr, size| { + uc.reg_write(RIP, addr + size as u64).unwrap(); }; for addr in parse_locs("malloc").unwrap() { @@ -195,7 +194,7 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { } let place_input_callback = - |uc: &mut UnicornHandle<'_, _>, afl_input: &mut [u8], _persistent_round| { + |uc: &mut Unicorn<'_, _>, afl_input: &mut [u8], _persistent_round| { // apply constraints to the mutated input if afl_input.len() > INPUT_MAX as usize { //println!("Skipping testcase with leng {}", afl_input.len()); @@ -209,9 +208,7 @@ fn fuzz(input_file: &str) -> Result<(), uc_error> { // return true if the last run should be counted as crash let crash_validation_callback = - |_uc: &mut UnicornHandle<'_, _>, result, _input: &[u8], _persistent_round| { - result != uc_error::OK - }; + |_uc: &mut Unicorn<'_, _>, result, _input: &[u8], _persistent_round| result != uc_error::OK; let end_addrs = parse_locs("main_ends").unwrap(); diff --git a/unicorn_mode/unicornafl b/unicorn_mode/unicornafl -Subproject 019b871539fe9ed3f41d882385a8b02c243d49a +Subproject d4915053d477dd827b3fe4b494173d3fbf9f456 diff --git a/utils/socket_fuzzing/README.md b/utils/socket_fuzzing/README.md index 84398a71..2805fa22 100644 --- a/utils/socket_fuzzing/README.md +++ b/utils/socket_fuzzing/README.md @@ -6,6 +6,6 @@ for sending input to stdin which the target binary will think is coming from a network socket. This is desock_dup.c from the amazing preeny project -https://github.com/zardus/preeny +[https://github.com/zardus/preeny](https://github.com/zardus/preeny) It is packaged in AFL++ to have it at hand if needed |