Merge pull request #1301 from AFLplusplus/dev

v4.00c release

.custom-format.py

@@ -6,7 +6,7 @@
 # Written and maintaned by Andrea Fioraldi <andreafioraldi@gmail.com>
 #
 # Copyright 2015, 2016, 2017 Google Inc. All rights reserved.
-# Copyright 2019-2020 AFLplusplus Project. All rights reserved.
+# Copyright 2019-2022 AFLplusplus Project. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -33,13 +33,13 @@ if CLANG_FORMAT_BIN is None:
         o, _ = p.communicate()
         o = str(o, "utf-8")
         o = re.sub(r".*ersion ", "", o)
-        #o = o[len("clang-format version "):].strip()
-        o = o[:o.find(".")]
+        # o = o[len("clang-format version "):].strip()
+        o = o[: o.find(".")]
         o = int(o)
     except:
-        print ("clang-format-11 is needed. Aborted.")
+        print("clang-format-11 is needed. Aborted.")
         exit(1)
-    #if o < 7:
+    # if o < 7:
     #    if subprocess.call(['which', 'clang-format-7'], stdout=subprocess.PIPE) == 0:
     #        CLANG_FORMAT_BIN = 'clang-format-7'
     #    elif subprocess.call(['which', 'clang-format-8'], stdout=subprocess.PIPE) == 0:
@@ -52,8 +52,8 @@ if CLANG_FORMAT_BIN is None:
     #        print ("clang-format 7 or above is needed. Aborted.")
     #        exit(1)
     else:
-        CLANG_FORMAT_BIN = 'clang-format-11'
-            
+        CLANG_FORMAT_BIN = "clang-format-11"
+
 COLUMN_LIMIT = 80
 for line in fmt.split("\n"):
     line = line.split(":")
@@ -69,26 +69,47 @@ def custom_format(filename):
     in_define = False
     last_line = None
     out = ""
-    
+
     for line in src.split("\n"):
         if line.lstrip().startswith("#"):
-            if line[line.find("#")+1:].lstrip().startswith("define"):
+            if line[line.find("#") + 1 :].lstrip().startswith("define"):
                 in_define = True
-        
-        if "/*" in line and not line.strip().startswith("/*") and line.endswith("*/") and len(line) < (COLUMN_LIMIT-2):
+
+        if (
+            "/*" in line
+            and not line.strip().startswith("/*")
+            and line.endswith("*/")
+            and len(line) < (COLUMN_LIMIT - 2)
+        ):
             cmt_start = line.rfind("/*")
-            line = line[:cmt_start] + " " * (COLUMN_LIMIT-2 - len(line)) + line[cmt_start:]
+            line = (
+                line[:cmt_start]
+                + " " * (COLUMN_LIMIT - 2 - len(line))
+                + line[cmt_start:]
+            )
 
         define_padding = 0
         if last_line is not None and in_define and last_line.endswith("\\"):
             last_line = last_line[:-1]
-            define_padding = max(0, len(last_line[last_line.rfind("\n")+1:]))
+            define_padding = max(0, len(last_line[last_line.rfind("\n") + 1 :]))
 
-        if last_line is not None and last_line.strip().endswith("{") and line.strip() != "":
+        if (
+            last_line is not None
+            and last_line.strip().endswith("{")
+            and line.strip() != ""
+        ):
             line = (" " * define_padding + "\\" if in_define else "") + "\n" + line
-        elif last_line is not None and last_line.strip().startswith("}") and line.strip() != "":
+        elif (
+            last_line is not None
+            and last_line.strip().startswith("}")
+            and line.strip() != ""
+        ):
             line = (" " * define_padding + "\\" if in_define else "") + "\n" + line
-        elif line.strip().startswith("}") and last_line is not None and last_line.strip() != "":
+        elif (
+            line.strip().startswith("}")
+            and last_line is not None
+            and last_line.strip() != ""
+        ):
             line = (" " * define_padding + "\\" if in_define else "") + "\n" + line
 
         if not line.endswith("\\"):
@@ -97,14 +118,15 @@ def custom_format(filename):
         out += line + "\n"
         last_line = line
 
-    return (out)
+    return out
+
 
 args = sys.argv[1:]
 if len(args) == 0:
-    print ("Usage: ./format.py [-i] <filename>")
-    print ()
-    print (" The -i option, if specified, let the script to modify in-place")
-    print (" the source files. By default the results are written to stdout.")
+    print("Usage: ./format.py [-i] <filename>")
+    print()
+    print(" The -i option, if specified, let the script to modify in-place")
+    print(" the source files. By default the results are written to stdout.")
     print()
     exit(1)
 
@@ -120,4 +142,3 @@ for filename in args:
             f.write(code)
     else:
         print(code)
-

.github/FUNDING.yml

@@ -0,0 +1,13 @@
+# These are supported funding model platforms
+
+# Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+github: AFLplusplus
+patreon: # Replace with a single Patreon username
+open_collective: AFLplusplusEU
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/bug_report.md

@@ -8,10 +8,11 @@ assignees: ''
 ---
 
 **IMPORTANT**
-1. You have verified that the issue to be present in the current `dev` branch
-2. Please supply the command line options and relevant environment variables, e.g. a copy-paste of the contents of `out/default/fuzzer_setup`
+1. You have verified that the issue to be present in the current `dev` branch.
+2. Please supply the command line options and relevant environment variables,
+   e.g., a copy-paste of the contents of `out/default/fuzzer_setup`.
 
-Thank you for making afl++ better!
+Thank you for making AFL++ better!
 
 **Describe the bug**
 A clear and concise description of what the bug is.

.github/workflows/build_aflplusplus_docker.yaml

@@ -0,0 +1,25 @@
+name: Publish Docker Images
+
+on:
+  push:
+    branches: [ stable ]
+#    paths:
+#    - Dockerfile
+
+jobs:
+  push_to_registry:
+    name: Push Docker images to Dockerhub
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@master
+    - name: Login to Dockerhub
+      uses: docker/login-action@v1
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
+    - name: Publish aflpp to Registry
+      uses: docker/build-push-action@v2
+      with:
+        context: .
+        push: true
+        tags: aflplusplus/aflplusplus:latest

.github/workflows/ci.yml

@@ -7,22 +7,47 @@ on:
     branches: [ stable, dev ]
 
 jobs:
-  build:
+  linux:
     runs-on: '${{ matrix.os }}'
     strategy:
       matrix:
         os: [ubuntu-20.04, ubuntu-18.04]
+    env:
+      AFL_SKIP_CPUFREQ: 1
+      AFL_I_DONT_CARE_ABOUT_MISSING_CRASHES: 1
     steps:
       - uses: actions/checkout@v2
       - name: debug
-        run: apt-cache search plugin-dev | grep gcc- ; echo ; apt-cache search clang-format- | grep clang-format-
+        run: apt-cache search plugin-dev | grep gcc-; echo; apt-cache search clang-format- | grep clang-format-
+      - name: update
+        run: sudo apt-get update && sudo apt-get upgrade -y
       - name: install packages
-        run: sudo apt-get install -y -m -f --install-suggests build-essential git libtool libtool-bin automake bison libglib2.0-0 clang llvm-dev libc++-dev findutils libcmocka-dev python3-dev python3-setuptools
+        run: sudo apt-get install -y -m -f --install-suggests build-essential git libtool libtool-bin automake bison libglib2.0-0 clang llvm-dev libc++-dev findutils libcmocka-dev python3-dev python3-setuptools ninja-build
       - name: compiler installed
-        run: gcc -v ; echo ; clang -v
+        run: gcc -v; echo; clang -v
       - name: install gcc plugin
         run: sudo apt-get install -y -m -f --install-suggests $(readlink /usr/bin/gcc)-plugin-dev
       - name: build afl++
         run: make distrib ASAN_BUILD=1
       - name: run tests
-        run: sudo -E ./afl-system-config ; export AFL_SKIP_CPUFREQ=1 ; make tests
+        run: sudo -E ./afl-system-config; make tests
+  macos:
+    runs-on: macOS-latest
+    env:
+      AFL_MAP_SIZE: 65536
+      AFL_SKIP_CPUFREQ: 1
+      AFL_I_DONT_CARE_ABOUT_MISSING_CRASHES: 1
+    steps:
+      - uses: actions/checkout@v2
+      - name: install
+        run: brew install make gcc
+      - name: fix install
+        run: cd /usr/local/bin; ln -s gcc-11 gcc; ln -s g++-11 g++; which gcc; gcc -v
+      - name: build
+        run: export PATH=/usr/local/Cellar/llvm/*/":$PATH"; export CC=/usr/local/Cellar/llvm/*/bin/clang; export CXX="$CC"++; export LLVM_CONFIG=/usr/local/Cellar/llvm/*/bin/llvm-config; sudo -E ./afl-system-config; gmake ASAN_BUILD=1
+      - name: frida
+        run: export CC=/usr/local/Cellar/llvm/*/bin/clang; export CXX="$CC"++; cd frida_mode; gmake
+      - name: run tests
+        run: sudo -E ./afl-system-config; export CC=/usr/local/Cellar/llvm/*/bin/clang; export CXX="$CC"++; export PATH=/usr/local/Cellar/llvm/*/":/usr/local/bin:$PATH"; export LLVM_CONFIG=/usr/local/Cellar/llvm/*/bin/llvm-config; gmake tests
+      - name: force frida test for MacOS
+        run: export AFL_PATH=`pwd`; /usr/local/bin/gcc -o test-instr test-instr.c; mkdir in; echo > in/in; AFL_NO_UI=1 ./afl-fuzz -O -i in -o out -V 5 -- ./test-instr

.github/workflows/rust_custom_mutator.yml

@@ -0,0 +1,30 @@
+name: Rust Custom Mutators
+
+on:
+  push:
+    branches: [ stable, dev ]
+  pull_request:
+    branches: [ stable, dev ]
+
+jobs:
+  test:
+    name: Test Rust Custom Mutator Support
+    runs-on: '${{ matrix.os }}'
+    defaults:
+      run:
+        working-directory: custom_mutators/rust
+    strategy:
+      matrix:
+        os: [ubuntu-20.04]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Install Rust Toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+      - name: Check Code Compiles
+        run: cargo check
+      - name: Run General Tests
+        run: cargo test
+      - name: Run Tests for afl_internals feature flag
+        run: cd custom_mutator && cargo test --features=afl_internals

.gitignore

@@ -30,6 +30,7 @@ afl-g++-fast
 afl-gotcpu
 afl-ld
 afl-ld-lto
+afl-cs-proxy
 afl-qemu-trace
 afl-showmap
 afl-tmin
@@ -54,6 +55,7 @@ afl-showmap.8
 afl-system-config.8
 afl-tmin.8
 afl-whatsup.8
+afl-persistent-config.8
 afl-c++
 afl-cc
 afl-lto
@@ -65,7 +67,6 @@ qemu_mode/qemu-*
 qemu_mode/qemuafl
 unicorn_mode/samples/*/\.test-*
 unicorn_mode/samples/*/output/
-unicorn_mode/unicornafl
 test/unittests/unit_maybe_alloc
 test/unittests/unit_preallocable
 test/unittests/unit_list
@@ -83,3 +84,16 @@ libAFLDriver.a
 libAFLQemuDriver.a
 test/.afl_performance
 gmon.out
+afl-frida-trace.so
+utils/afl_network_proxy/afl-network-client
+utils/afl_network_proxy/afl-network-server
+utils/plot_ui/afl-plot-ui
+*.o.tmp
+utils/afl_proxy/afl-proxy
+utils/optimin/build
+utils/optimin/optimin
+utils/persistent_mode/persistent_demo
+utils/persistent_mode/persistent_demo_new
+utils/persistent_mode/test-instr
+!coresight_mode
+!coresight_mode/coresight-trace

.gitmodules

@@ -7,3 +7,24 @@
 [submodule "qemu_mode/qemuafl"]
 	path = qemu_mode/qemuafl
 	url = https://github.com/AFLplusplus/qemuafl
+[submodule "custom_mutators/gramatron/json-c"]
+	path = custom_mutators/gramatron/json-c
+	url = https://github.com/json-c/json-c
+[submodule "utils/optimin/EvalMaxSAT"]
+	path = utils/optimin/EvalMaxSAT
+	url = https://github.com/FlorentAvellaneda/EvalMaxSAT
+[submodule "coresight_mode/patchelf"]
+	path = coresight_mode/patchelf
+	url = https://github.com/NixOS/patchelf.git
+[submodule "coresight_mode/coresight-trace"]
+	path = coresight_mode/coresight-trace
+	url = https://github.com/RICSecLab/coresight-trace.git
+[submodule "nyx_mode/libnyx"]
+	path = nyx_mode/libnyx
+	url = https://github.com/nyx-fuzz/libnyx.git
+[submodule "nyx_mode/QEMU-Nyx"]
+	path = nyx_mode/QEMU-Nyx
+	url = https://github.com/nyx-fuzz/qemu-nyx.git
+[submodule "nyx_mode/packer"]
+	path = nyx_mode/packer
+	url = https://github.com/nyx-fuzz/packer.git

Android.bp

@@ -1,8 +1,13 @@
+//
+// NOTE: This file is outdated. None of the AFL++ team uses Android hence
+//       we need users to keep this updated.
+//       In the current state it will likely fail, please send fixes!
+//       Also, this should build frida_mode.
+//
+
+
 cc_defaults {
   name: "afl-defaults",
-  sanitize: {
-    never: true,
-  },
 
   local_include_dirs: [
     "include",
@@ -23,18 +28,44 @@ cc_defaults {
     "-DBIN_PATH=\"out/host/linux-x86/bin\"",
     "-DDOC_PATH=\"out/host/linux-x86/shared/doc/afl\"",
     "-D__USE_GNU",
-    "-D__aarch64__",
     "-DDEBUG_BUILD",
     "-U_FORTIFY_SOURCE",
     "-ggdb3",
     "-g",
     "-O0",
     "-fno-omit-frame-pointer",
+    "-fPIC",
   ],
+
+  target: {
+    android_arm64: {
+      cflags: [
+        "-D__ANDROID__",
+      ],
+    },
+    android_arm: {
+      cflags: [
+        "-D__ANDROID__",
+      ],
+    },
+    android_x86_64: {
+      cflags: [
+        "-D__ANDROID__",
+      ],
+    },
+    android_x86: {
+      cflags: [
+        "-D__ANDROID__",
+      ],
+    },
+  },
 }
 
 cc_binary {
   name: "afl-fuzz",
+  sanitize: {
+    never: true,
+  },
   host_supported: true,
   compile_multilib: "64",
 
@@ -128,7 +159,6 @@ cc_binary_host {
   ],
 
   cflags: [
-    "-D__ANDROID__",
     "-DAFL_PATH=\"out/host/linux-x86/lib64\"",
     "-DAFL_CLANG_FLTO=\"-flto=full\"",
     "-DUSE_BINDIR=1",
@@ -153,7 +183,7 @@ cc_binary_host {
 }
 
 cc_library_static {
-  name: "afl-llvm-rt",
+  name: "afl-compiler-rt",
   compile_multilib: "64",
   vendor_available: true,
   host_supported: true,
@@ -199,9 +229,11 @@ cc_library_headers {
 
   export_include_dirs: [
     "include",
+    "instrumentation",
   ],
 }
 
+/*
 cc_prebuilt_library_static {
   name: "libfrida-gum",
   compile_multilib: "64",
@@ -249,7 +281,7 @@ cc_binary {
   ],
 
   static_libs: [
-    "afl-llvm-rt",
+    "afl-compiler-rt",
     "libfrida-gum",
   ],
 
@@ -267,6 +299,119 @@ cc_binary {
     "utils/afl_frida/android",
   ],
 }
+*/
+
+cc_binary {
+  name: "afl-fuzz-32",
+  sanitize: {
+    never: true,
+  },
+  host_supported: true,
+  compile_multilib: "32",
+
+  defaults: [
+    "afl-defaults",
+  ],
+
+  srcs: [
+    "src/afl-fuzz*.c",
+    "src/afl-common.c",
+    "src/afl-sharedmem.c",
+    "src/afl-forkserver.c",
+    "src/afl-performance.c",
+  ],
+}
+
+cc_binary_host {
+  name: "afl-cc-32",
+  compile_multilib: "32",
+  static_executable: true,
+
+  defaults: [
+    "afl-defaults",
+  ],
+
+  cflags: [
+    "-DAFL_PATH=\"out/host/linux-x86/lib64\"",
+    "-DAFL_CLANG_FLTO=\"-flto=full\"",
+    "-DUSE_BINDIR=1",
+    "-DLLVM_BINDIR=\"prebuilts/clang/host/linux-x86/clang-r383902b/bin\"",
+    "-DLLVM_LIBDIR=\"prebuilts/clang/host/linux-x86/clang-r383902b/lib64\"",
+    "-DCLANGPP_BIN=\"prebuilts/clang/host/linux-x86/clang-r383902b/bin/clang++\"",
+    "-DAFL_REAL_LD=\"prebuilts/clang/host/linux-x86/clang-r383902b/bin/ld.lld\"",
+    "-DLLVM_LTO=1",
+    "-DLLVM_MAJOR=11",
+    "-DLLVM_MINOR=2",
+  ],
+
+  srcs: [
+    "src/afl-cc.c",
+    "src/afl-common.c",
+  ],
+
+  symlinks: [
+    "afl-clang-fast-32",
+    "afl-clang-fast++-32",
+  ],
+}
+
+cc_library_static {
+  name: "afl-compiler-rt-32",
+  compile_multilib: "32",
+  vendor_available: true,
+  host_supported: true,
+  recovery_available: true,
+  sdk_version: "9",
+
+  apex_available: [
+    "com.android.adbd",
+    "com.android.appsearch",
+    "com.android.art",
+    "com.android.bluetooth.updatable",
+    "com.android.cellbroadcast",
+    "com.android.conscrypt",
+    "com.android.extservices",
+    "com.android.cronet",
+    "com.android.neuralnetworks",
+    "com.android.media",
+    "com.android.media.swcodec",
+    "com.android.mediaprovider",
+    "com.android.permission",
+    "com.android.runtime",
+    "com.android.resolv",
+    "com.android.tethering",
+    "com.android.wifi",
+    "com.android.sdkext",
+    "com.android.os.statsd",
+    "//any",
+  ],
+
+  defaults: [
+    "afl-defaults",
+  ],
+
+  srcs: [
+    "instrumentation/afl-compiler-rt.o.c",
+  ],
+}
+
+/*
+cc_prebuilt_library_static {
+  name: "libfrida-gum-32",
+  compile_multilib: "32",
+  strip: {
+    none: true,
+  },
+
+  srcs: [
+    "utils/afl_frida/android/arm/libfrida-gum.a",
+  ],
+
+  export_include_dirs: [
+    "utils/afl_frida/android/arm",
+  ],
+}
+*/
 
 subdirs = [
   "custom_mutators",

CITATION.cff

@@ -0,0 +1,31 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - given-names: Marc
+    family-names: Heuse
+    email: mh@mh-sec.de
+  - given-names: Heiko
+    family-names: Eißfeldt
+    email: heiko.eissfeldt@hexco.de
+  - given-names: Andrea
+    family-names: Fioraldi
+    email: andreafioraldi@gmail.com
+  - given-names: Dominik
+    family-names: Meier
+    email: mail@dmnk.co
+title: "AFL++"
+version: 3.14
+type: software
+date-released: 2021-07-19
+url: "https://github.com/AFLplusplus/AFLplusplus"
+keywords:
+  - fuzzing
+  - fuzzer
+  - fuzz-testing
+  - instrumentation
+  - afl-fuzz
+  - qemu
+  - llvm
+  - unicorn-emulator
+  - securiy
+license: AGPL-3.0-or-later

CONTRIBUTING.md

@@ -1,4 +1,6 @@
-# How to submit a Pull Request to AFLplusplus
+# Contributing to AFL++
+
+## How to submit a pull request
 
 All contributions (pull requests) must be made against our `dev` branch.
 
@@ -15,10 +17,43 @@ project, or added a file in a directory we already format, otherwise run:
 ./.custom-format.py -i file-that-you-have-created.c
 ```
 
-Regarding the coding style, please follow the AFL style.
-No camel case at all and use AFL's macros wherever possible
-(e.g. WARNF, FATAL, MAP_SIZE, ...).
+Regarding the coding style, please follow the AFL style. No camel case at all
+and use AFL's macros wherever possible (e.g., WARNF, FATAL, MAP_SIZE, ...).
 
-Remember that AFLplusplus has to build and run on many platforms, so
-generalize your Makefiles/GNUmakefile (or your patches to our pre-existing
-Makefiles) to be as generic as possible.
+Remember that AFL++ has to build and run on many platforms, so generalize your
+Makefiles/GNUmakefile (or your patches to our pre-existing Makefiles) to be as
+generic as possible.
+
+## How to contribute to the docs
+
+We welcome contributions to our docs.
+
+Before creating a new file, please check if your content matches an existing
+file in one the following folders:
+
+* [docs/](docs/) (this is where you can find most of our docs content)
+* [frida_mode/](frida_mode/)
+* [instrumentation/](instrumentation/)
+* [qemu_mode/](qemu_mode/)
+* [unicorn_mode/](unicorn_mode/)
+
+When working on the docs, please keep the following guidelines in mind:
+
+* Edit or create Markdown files and use Markdown markup.
+  * Do: fuzzing_gui_program.md
+  * Don't: fuzzing_gui_program.txt
+* Use underscore in file names.
+  * Do: fuzzing_network_service.md
+  * Don't: fuzzing-network-service.md
+* Use a maximum of 80 characters per line to make reading in a console easier.
+* Make all pull requests against `dev`, see
+  [#how-to-submit-a-pull-request-to-afl](#how-to-submit-a-pull-request-to-afl).
+
+And finally, here are some best practices for writing docs content:
+
+* Use clear and simple language.
+* Structure your content with headings and paragraphs.
+* Use bulleted lists to present similar content in a way that makes it easy to
+  scan.
+* Use numbered lists for procedures or prioritizing.
+* Link to related content, for example, prerequisites or in-depth discussions.

Dockerfile

@@ -11,9 +11,13 @@ LABEL "about"="AFLplusplus docker image"
 
 ARG DEBIAN_FRONTEND=noninteractive
 
+env NO_ARCH_OPT 1
+
 RUN apt-get update && \
     apt-get -y install --no-install-suggests --no-install-recommends \
     automake \
+    cmake \
+    meson \
     ninja-build \
     bison flex \
     build-essential \
@@ -35,7 +39,7 @@ RUN echo "deb http://ppa.launchpad.net/ubuntu-toolchain-r/test/ubuntu focal main
 
 RUN apt-get update && apt-get full-upgrade -y && \
     apt-get -y install --no-install-suggests --no-install-recommends \
-    gcc-10 g++-10 gcc-10-plugin-dev gcc-10-multilib gdb lcov \
+    gcc-10 g++-10 gcc-10-plugin-dev gcc-10-multilib gcc-multilib gdb lcov \
     clang-12 clang-tools-12 libc++1-12 libc++-12-dev \
     libc++abi1-12 libc++abi-12-dev libclang1-12 libclang-12-dev \
     libclang-common-12-dev libclang-cpp12 libclang-cpp12-dev liblld-12 \
@@ -48,19 +52,22 @@ RUN update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-10 0
 
 ENV LLVM_CONFIG=llvm-config-12
 ENV AFL_SKIP_CPUFREQ=1
+ENV AFL_TRY_AFFINITY=1
+ENV AFL_I_DONT_CARE_ABOUT_MISSING_CRASHES=1
 
-RUN git clone https://github.com/vanhauser-thc/afl-cov /afl-cov
+RUN git clone --depth=1 https://github.com/vanhauser-thc/afl-cov /afl-cov
 RUN cd /afl-cov && make install && cd ..
 
 COPY . /AFLplusplus
 WORKDIR /AFLplusplus
 
-RUN export REAL_CXX=g++-10 && export CC=gcc-10 && \
-    export CXX=g++-10 && make clean && \
-    make distrib CFLAGS="-O3 -funroll-loops -D_FORTIFY_SOURCE=2" && make install && make clean
+RUN export CC=gcc-10 && export CXX=g++-10 && make clean && \
+    make distrib && make install && make clean
 
-RUN echo 'alias joe="jupp --wordwrap"' >> ~/.bashrc
-RUN echo 'export PS1="[afl++]$PS1"' >> ~/.bashrc
+RUN sh -c 'echo set encoding=utf-8 > /root/.vimrc'
+RUN echo '. /etc/bash_completion' >> ~/.bashrc
+RUN echo 'alias joe="joe --wordwrap --joe_state -nobackup"' >> ~/.bashrc
+RUN echo "export PS1='"'[afl++ \h] \w$(__git_ps1) \$ '"'" >> ~/.bashrc
 ENV IS_DOCKER="1"
 
 # Disabled until we have the container ready

GNUmakefile

@@ -10,7 +10,7 @@
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 
 # For Heiko:
@@ -24,7 +24,7 @@ BIN_PATH    = $(PREFIX)/bin
 HELPER_PATH = $(PREFIX)/lib/afl
 DOC_PATH    = $(PREFIX)/share/doc/afl
 MISC_PATH   = $(PREFIX)/share/afl
-MAN_PATH    = $(PREFIX)/man/man8
+MAN_PATH    = $(PREFIX)/share/man/man8
 
 PROGNAME    = afl
 VERSION     = $(shell grep '^$(HASH)define VERSION ' ../config.h | cut -d '"' -f2)
@@ -32,12 +32,17 @@ VERSION     = $(shell grep '^$(HASH)define VERSION ' ../config.h | cut -d '"' -f
 # PROGS intentionally omit afl-as, which gets installed elsewhere.
 
 PROGS       = afl-fuzz afl-showmap afl-tmin afl-gotcpu afl-analyze
-SH_PROGS    = afl-plot afl-cmin afl-cmin.bash afl-whatsup afl-system-config
+SH_PROGS    = afl-plot afl-cmin afl-cmin.bash afl-whatsup afl-system-config afl-persistent-config afl-cc
 MANPAGES=$(foreach p, $(PROGS) $(SH_PROGS), $(p).8) afl-as.8
 ASAN_OPTIONS=detect_leaks=0
 
+SYS = $(shell uname -s)
+ARCH = $(shell uname -m)
+
+$(info [*] Compiling afl++ for OS $(SYS) on ARCH $(ARCH))
+
 ifdef NO_SPLICING
-  override CFLAGS += -DNO_SPLICING
+  override CFLAGS_OPT += -DNO_SPLICING
 endif
 
 ifdef ASAN_BUILD
@@ -57,8 +62,6 @@ ifdef MSAN_BUILD
   override LDFLAGS += -fsanitize=memory
 endif
 
-
-
 ifeq "$(findstring android, $(shell $(CC) --version 2>/dev/null))" ""
 ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -flto=full -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1"
 	CFLAGS_FLTO ?= -flto=full
@@ -77,24 +80,24 @@ ifeq "$(shell echo 'int main() {return 0; }' | $(CC) -fno-move-loop-invariants -
 	SPECIAL_PERFORMANCE += -fno-move-loop-invariants -fdisable-tree-cunrolli
 endif
 
-ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -march=native -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1"
-  ifndef SOURCE_DATE_EPOCH
-    HAVE_MARCHNATIVE = 1
-    CFLAGS_OPT += -march=native
-  endif
-endif
+#ifeq "$(shell echo 'int main() {return 0; }' | $(CC) $(CFLAGS) -Werror -x c - -march=native -o .test 2>/dev/null && echo 1 || echo 0 ; rm -f .test )" "1"
+#  ifndef SOURCE_DATE_EPOCH
+#    HAVE_MARCHNATIVE = 1
+#    CFLAGS_OPT += -march=native
+#  endif
+#endif
 
-ifneq "$(shell uname)" "Darwin"
-  ifeq "$(HAVE_MARCHNATIVE)" "1"
-    SPECIAL_PERFORMANCE += -march=native
-  endif
+ifneq "$(SYS)" "Darwin"
+  #ifeq "$(HAVE_MARCHNATIVE)" "1"
+  #  SPECIAL_PERFORMANCE += -march=native
+  #endif
  # OS X does not like _FORTIFY_SOURCE=2
   ifndef DEBUG
     CFLAGS_OPT += -D_FORTIFY_SOURCE=2
   endif
 endif
 
-ifeq "$(shell uname)" "SunOS"
+ifeq "$(SYS)" "SunOS"
   CFLAGS_OPT += -Wno-format-truncation
   LDFLAGS = -lkstat -lrt
 endif
@@ -112,20 +115,19 @@ endif
 
 ifdef PROFILING
   $(info Compiling with profiling information, for analysis: gprof ./afl-fuzz gmon.out > prof.txt)
-  CFLAGS_OPT += -pg -DPROFILING=1
-  LDFLAGS += -pg
+  override CFLAGS_OPT += -pg -DPROFILING=1
+  override LDFLAGS += -pg
 endif
 
 ifdef INTROSPECTION
   $(info Compiling with introspection documentation)
-  CFLAGS_OPT += -DINTROSPECTION=1
+  override CFLAGS_OPT += -DINTROSPECTION=1
 endif
 
-
-ifneq "$(shell uname -m)" "x86_64"
- ifneq "$(patsubst i%86,i386,$(shell uname -m))" "i386"
-  ifneq "$(shell uname -m)" "amd64"
-   ifneq "$(shell uname -m)" "i86pc"
+ifneq "$(ARCH)" "x86_64"
+ ifneq "$(patsubst i%86,i386,$(ARCH))" "i386"
+  ifneq "$(ARCH)" "amd64"
+   ifneq "$(ARCH)" "i86pc"
 	AFL_NO_X86=1
    endif
   endif
@@ -134,7 +136,7 @@ endif
 
 ifdef DEBUG
   $(info Compiling DEBUG version of binaries)
-  CFLAGS += -ggdb3 -O0 -Wall -Wextra -Werror
+  override CFLAGS += -ggdb3 -O0 -Wall -Wextra -Werror $(CFLAGS_OPT)
 else
   CFLAGS ?= -O3 -funroll-loops $(CFLAGS_OPT)
 endif
@@ -143,30 +145,30 @@ override CFLAGS += -g -Wno-pointer-sign -Wno-variadic-macros -Wall -Wextra -Wpoi
 			  -I include/ -DAFL_PATH=\"$(HELPER_PATH)\" \
 			  -DBIN_PATH=\"$(BIN_PATH)\" -DDOC_PATH=\"$(DOC_PATH)\"
 
-ifeq "$(shell uname -s)" "FreeBSD"
+ifeq "$(SYS)" "FreeBSD"
   override CFLAGS  += -I /usr/local/include/
-  LDFLAGS += -L /usr/local/lib/
+  override LDFLAGS += -L /usr/local/lib/
 endif
 
-ifeq "$(shell uname -s)" "DragonFly"
+ifeq "$(SYS)" "DragonFly"
   override CFLAGS  += -I /usr/local/include/
-  LDFLAGS += -L /usr/local/lib/
+  override LDFLAGS += -L /usr/local/lib/
 endif
 
-ifeq "$(shell uname -s)" "OpenBSD"
+ifeq "$(SYS)" "OpenBSD"
   override CFLAGS  += -I /usr/local/include/ -mno-retpoline
-  LDFLAGS += -Wl,-z,notext -L /usr/local/lib/
+  override LDFLAGS += -Wl,-z,notext -L /usr/local/lib/
 endif
 
-ifeq "$(shell uname -s)" "NetBSD"
+ifeq "$(SYS)" "NetBSD"
   override CFLAGS  += -I /usr/pkg/include/
-  LDFLAGS += -L /usr/pkg/lib/
+  override LDFLAGS += -L /usr/pkg/lib/
 endif
 
-ifeq "$(shell uname -s)" "Haiku"
+ifeq "$(SYS)" "Haiku"
   SHMAT_OK=0
   override CFLAGS  += -DUSEMMAP=1 -Wno-error=format -fPIC
-  LDFLAGS += -Wno-deprecated-declarations -lgnu
+  override LDFLAGS += -Wno-deprecated-declarations -lgnu -lnetwork
   SPECIAL_PERFORMANCE += -DUSEMMAP=1
 endif
 
@@ -238,26 +240,26 @@ else
     BUILD_DATE ?= $(shell date "+%Y-%m-%d")
 endif
 
-ifneq "$(filter Linux GNU%,$(shell uname))" ""
+ifneq "$(filter Linux GNU%,$(SYS))" ""
  ifndef DEBUG
   override CFLAGS += -D_FORTIFY_SOURCE=2
  endif
-  LDFLAGS += -ldl -lrt -lm
+  override LDFLAGS += -ldl -lrt -lm
 endif
 
-ifneq "$(findstring FreeBSD, $(shell uname))" ""
+ifneq "$(findstring FreeBSD, $(SYS))" ""
   override CFLAGS  += -pthread
-  LDFLAGS += -lpthread
+  override LDFLAGS += -lpthread
 endif
 
-ifneq "$(findstring NetBSD, $(shell uname))" ""
+ifneq "$(findstring NetBSD, $(SYS))" ""
   override CFLAGS  += -pthread
-  LDFLAGS += -lpthread
+  override LDFLAGS += -lpthread
 endif
 
-ifneq "$(findstring OpenBSD, $(shell uname))" ""
+ifneq "$(findstring OpenBSD, $(SYS))" ""
   override CFLAGS  += -pthread
-  LDFLAGS += -lpthread
+  override LDFLAGS += -lpthread
 endif
 
 COMM_HDR    = include/alloc-inl.h include/config.h include/debug.h include/types.h
@@ -304,15 +306,18 @@ endif
 
 .PHONY: all
 all:	test_x86 test_shm test_python ready $(PROGS) afl-as llvm gcc_plugin test_build all_done
+	-$(MAKE) -C utils/aflpp_driver
 
 .PHONY: llvm
 llvm:
-	-$(MAKE) -j -f GNUmakefile.llvm
+	-$(MAKE) -j4 -f GNUmakefile.llvm
 	@test -e afl-cc || { echo "[-] Compiling afl-cc failed. You seem not to have a working compiler." ; exit 1; }
 
 .PHONY: gcc_plugin
 gcc_plugin:
+ifneq "$(SYS)" "Darwin"
 	-$(MAKE) -f GNUmakefile.gcc_plugin
+endif
 
 .PHONY: man
 man:    $(MANPAGES)
@@ -340,14 +345,15 @@ performance-test:	source-only
 help:
 	@echo "HELP --- the following make targets exist:"
 	@echo "=========================================="
-	@echo "all: just the main afl++ binaries"
-	@echo "binary-only: everything for binary-only fuzzing: qemu_mode, unicorn_mode, libdislocator, libtokencap"
-	@echo "source-only: everything for source code fuzzing: gcc_plugin, libdislocator, libtokencap"
+	@echo "all: the main afl++ binaries and llvm/gcc instrumentation"
+	@echo "binary-only: everything for binary-only fuzzing: frida_mode, nyx_mode, qemu_mode, frida_mode, unicorn_mode, coresight_mode, libdislocator, libtokencap"
+	@echo "source-only: everything for source code fuzzing: nyx_mode, libdislocator, libtokencap"
 	@echo "distrib: everything (for both binary-only and source code fuzzing)"
 	@echo "man: creates simple man pages from the help option of the programs"
 	@echo "install: installs everything you have compiled with the build option above"
 	@echo "clean: cleans everything compiled (not downloads when on a checkout)"
 	@echo "deepclean: cleans everything including downloads"
+	@echo "uninstall: uninstall afl++ from the system"
 	@echo "code-format: format the code, do this before you commit and send a PR please!"
 	@echo "tests: this runs the test framework. It is more catered for the developers, but if you run into problems this helps pinpointing the problem"
 	@echo "unit: perform unit tests (based on cmocka and GNU linker)"
@@ -434,8 +440,8 @@ afl-showmap: src/afl-showmap.c src/afl-common.o src/afl-sharedmem.o src/afl-fork
 afl-tmin: src/afl-tmin.c src/afl-common.o src/afl-sharedmem.o src/afl-forkserver.o src/afl-performance.o $(COMM_HDR) | test_x86
 	$(CC) $(CFLAGS) $(COMPILE_STATIC) $(CFLAGS_FLTO) src/$@.c src/afl-common.o src/afl-sharedmem.o src/afl-forkserver.o src/afl-performance.o -o $@ $(LDFLAGS)
 
-afl-analyze: src/afl-analyze.c src/afl-common.o src/afl-sharedmem.o src/afl-performance.o $(COMM_HDR) | test_x86
-	$(CC) $(CFLAGS) $(COMPILE_STATIC) $(CFLAGS_FLTO) src/$@.c src/afl-common.o src/afl-sharedmem.o src/afl-performance.o -o $@ $(LDFLAGS)
+afl-analyze: src/afl-analyze.c src/afl-common.o src/afl-sharedmem.o src/afl-performance.o src/afl-forkserver.o $(COMM_HDR) | test_x86
+	$(CC) $(CFLAGS) $(COMPILE_STATIC) $(CFLAGS_FLTO) src/$@.c src/afl-common.o src/afl-sharedmem.o src/afl-performance.o src/afl-forkserver.o -o $@ $(LDFLAGS)
 
 afl-gotcpu: src/afl-gotcpu.c src/afl-common.o $(COMM_HDR) | test_x86
 	$(CC) $(CFLAGS) $(COMPILE_STATIC) $(CFLAGS_FLTO) src/$@.c src/afl-common.o -o $@ $(LDFLAGS)
@@ -487,7 +493,7 @@ unit_clean:
 	@rm -f ./test/unittests/unit_preallocable ./test/unittests/unit_list ./test/unittests/unit_maybe_alloc test/unittests/*.o
 
 .PHONY: unit
-ifneq "$(shell uname)" "Darwin"
+ifneq "$(SYS)" "Darwin"
 unit:	unit_maybe_alloc unit_preallocable unit_list unit_clean unit_rand unit_hash
 else
 unit:
@@ -501,25 +507,28 @@ code-format:
 	./.custom-format.py -i instrumentation/*.h
 	./.custom-format.py -i instrumentation/*.cc
 	./.custom-format.py -i instrumentation/*.c
+	./.custom-format.py -i *.h
+	./.custom-format.py -i *.c
 	@#./.custom-format.py -i custom_mutators/*/*.c* # destroys libfuzzer :-(
 	@#./.custom-format.py -i custom_mutators/*/*.h # destroys honggfuzz :-(
 	./.custom-format.py -i utils/*/*.c*
 	./.custom-format.py -i utils/*/*.h
 	./.custom-format.py -i test/*.c
+	./.custom-format.py -i frida_mode/src/*.c
+	./.custom-format.py -i frida_mode/include/*.h
+	-./.custom-format.py -i frida_mode/src/*/*.c
 	./.custom-format.py -i qemu_mode/libcompcov/*.c
 	./.custom-format.py -i qemu_mode/libcompcov/*.cc
 	./.custom-format.py -i qemu_mode/libcompcov/*.h
 	./.custom-format.py -i qemu_mode/libqasan/*.c
 	./.custom-format.py -i qemu_mode/libqasan/*.h
-	./.custom-format.py -i *.h
-	./.custom-format.py -i *.c
 
 
 .PHONY: test_build
 ifndef AFL_NO_X86
 test_build: afl-cc afl-gcc afl-as afl-showmap
 	@echo "[*] Testing the CC wrapper afl-cc and its instrumentation output..."
-	@unset AFL_MAP_SIZE AFL_USE_UBSAN AFL_USE_CFISAN AFL_USE_ASAN AFL_USE_MSAN; ASAN_OPTIONS=detect_leaks=0 AFL_INST_RATIO=100 AFL_PATH=. ./afl-cc test-instr.c -o test-instr 2>&1 || (echo "Oops, afl-cc failed"; exit 1 )
+	@unset AFL_MAP_SIZE AFL_USE_UBSAN AFL_USE_CFISAN AFL_USE_LSAN AFL_USE_ASAN AFL_USE_MSAN; ASAN_OPTIONS=detect_leaks=0 AFL_INST_RATIO=100 AFL_PATH=. ./afl-cc test-instr.c -o test-instr 2>&1 || (echo "Oops, afl-cc failed"; exit 1 )
 	ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr0 ./test-instr < /dev/null
 	echo 1 | ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr1 ./test-instr
 	@rm -f test-instr
@@ -527,12 +536,12 @@ test_build: afl-cc afl-gcc afl-as afl-showmap
 	@echo
 	@echo "[+] All right, the instrumentation of afl-cc seems to be working!"
 #	@echo "[*] Testing the CC wrapper afl-gcc and its instrumentation output..."
-#	@unset AFL_MAP_SIZE AFL_USE_UBSAN AFL_USE_CFISAN AFL_USE_ASAN AFL_USE_MSAN; AFL_CC=$(CC) ASAN_OPTIONS=detect_leaks=0 AFL_INST_RATIO=100 AFL_PATH=. ./afl-gcc test-instr.c -o test-instr 2>&1 || (echo "Oops, afl-gcc failed"; exit 1 )
+#	@unset AFL_MAP_SIZE AFL_USE_UBSAN AFL_USE_CFISAN AFL_USE_LSAN AFL_USE_ASAN AFL_USE_MSAN; AFL_CC=$(CC) ASAN_OPTIONS=detect_leaks=0 AFL_INST_RATIO=100 AFL_PATH=. ./afl-gcc test-instr.c -o test-instr 2>&1 || (echo "Oops, afl-gcc failed"; exit 1 )
 #	ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr0 ./test-instr < /dev/null
 #	echo 1 | ASAN_OPTIONS=detect_leaks=0 ./afl-showmap -m none -q -o .test-instr1 ./test-instr
 #	@rm -f test-instr
 #	@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!"
@@ -548,68 +557,110 @@ all_done: test_build
 	@test -e SanitizerCoverageLTO.so && echo "[+] LLVM LTO mode for 'afl-cc' successfully built!" || echo "[-] LLVM LTO mode for 'afl-cc'  failed to build, this would need LLVM 11+, see instrumentation/README.lto.md how to build it"
 	@test -e afl-gcc-pass.so && echo "[+] gcc_plugin for 'afl-cc' successfully built!" || echo "[-] gcc_plugin for 'afl-cc'  failed to build, unless you really need it that is fine - or read instrumentation/README.gcc_plugin.md how to build it"
 	@echo "[+] All done! Be sure to review the README.md - it's pretty short and useful."
-	@if [ "`uname`" = "Darwin" ]; then printf "\nWARNING: Fuzzing on MacOS X is slow because of the unusually high overhead of\nfork() on this OS. Consider using Linux or *BSD. You can also use VirtualBox\n(virtualbox.org) to put AFL inside a Linux or *BSD VM.\n\n"; fi
+	@if [ "$(SYS)" = "Darwin" ]; then printf "\nWARNING: Fuzzing on MacOS X is slow because of the unusually high overhead of\nfork() on this OS. Consider using Linux or *BSD for fuzzing software not\nspecifically for MacOS.\n\n"; fi
 	@! tty <&1 >/dev/null || printf "\033[0;30mNOTE: If you can read this, your terminal probably uses white background.\nThis will make the UI hard to read. See docs/status_screen.md for advice.\033[0m\n" 2>/dev/null
 
 .NOTPARALLEL: clean all
 
 .PHONY: clean
 clean:
-	rm -f $(PROGS) libradamsa.so afl-fuzz-document afl-as as afl-g++ afl-clang afl-clang++ *.o src/*.o *~ a.out core core.[1-9][0-9]* *.stackdump .test .test1 .test2 test-instr .test-instr0 .test-instr1 afl-qemu-trace afl-gcc-fast afl-gcc-pass.so afl-g++-fast ld *.so *.8 test/unittests/*.o test/unittests/unit_maybe_alloc test/unittests/preallocable .afl-* afl-gcc afl-g++ afl-clang afl-clang++ test/unittests/unit_hash test/unittests/unit_rand
+	rm -rf $(PROGS) afl-fuzz-document afl-as as afl-g++ afl-clang afl-clang++ *.o src/*.o *~ a.out core core.[1-9][0-9]* *.stackdump .test .test1 .test2 test-instr .test-instr0 .test-instr1 afl-cs-proxy afl-qemu-trace afl-gcc-fast afl-g++-fast ld *.so *.8 test/unittests/*.o test/unittests/unit_maybe_alloc test/unittests/preallocable .afl-* afl-gcc afl-g++ afl-clang afl-clang++ test/unittests/unit_hash test/unittests/unit_rand *.dSYM
 	-$(MAKE) -f GNUmakefile.llvm clean
 	-$(MAKE) -f GNUmakefile.gcc_plugin clean
-	$(MAKE) -C utils/libdislocator clean
-	$(MAKE) -C utils/libtokencap clean
-	$(MAKE) -C utils/afl_network_proxy clean
-	$(MAKE) -C utils/socket_fuzzing clean
-	$(MAKE) -C utils/argv_fuzzing clean
-	$(MAKE) -C qemu_mode/unsigaction clean
-	$(MAKE) -C qemu_mode/libcompcov clean
-	$(MAKE) -C qemu_mode/libqasan clean
+	-$(MAKE) -C utils/libdislocator clean
+	-$(MAKE) -C utils/libtokencap clean
+	$(MAKE) -C utils/aflpp_driver clean
+	-$(MAKE) -C utils/afl_network_proxy clean
+	-$(MAKE) -C utils/socket_fuzzing clean
+	-$(MAKE) -C utils/argv_fuzzing clean
+	-$(MAKE) -C utils/plot_ui clean
+	-$(MAKE) -C qemu_mode/unsigaction clean
+	-$(MAKE) -C qemu_mode/libcompcov clean
+	-$(MAKE) -C qemu_mode/libqasan clean
+	-$(MAKE) -C frida_mode clean
+	rm -rf nyx_mode/packer/linux_initramfs/init.cpio.gz nyx_mode/libnyx/libnyx/target/release/* nyx_mode/QEMU-Nyx/x86_64-softmmu/qemu-system-x86_64
 ifeq "$(IN_REPO)" "1"
-	test -e qemu_mode/qemuafl/Makefile && $(MAKE) -C qemu_mode/qemuafl clean || true
-	test -e unicorn_mode/unicornafl/Makefile && $(MAKE) -C unicorn_mode/unicornafl clean || true
+	-test -e coresight_mode/coresight-trace/Makefile && $(MAKE) -C coresight_mode/coresight-trace clean || true
+	-test -e qemu_mode/qemuafl/Makefile && $(MAKE) -C qemu_mode/qemuafl clean || true
+	-test -e unicorn_mode/unicornafl/Makefile && $(MAKE) -C unicorn_mode/unicornafl clean || true
+	-test -e nyx_mode/QEMU-Nyx/Makefile && $(MAKE) -C nyx_mode/QEMU-Nyx clean || true
 else
+	rm -rf coresight_mode/coresight_trace
 	rm -rf qemu_mode/qemuafl
 	rm -rf unicorn_mode/unicornafl
 endif
 
 .PHONY: deepclean
 deepclean:	clean
+	rm -rf coresight_mode/coresight-trace
 	rm -rf unicorn_mode/unicornafl
 	rm -rf qemu_mode/qemuafl
-# NEVER EVER ACTIVATE THAT!!!!! git reset --hard >/dev/null 2>&1 || true
+	rm -rf nyx_mode/libnyx nyx_mode/packer nyx_mode/QEMU-Nyx
+ifeq "$(IN_REPO)" "1"
+	git checkout coresight_mode/coresight-trace
+	git checkout unicorn_mode/unicornafl
+	git checkout qemu_mode/qemuafl
+	git checkout nyx_mode/libnyx
+	git checkout nyx_mode/packer
+	git checkout nyx_mode/QEMU-Nyx
+endif
 
 .PHONY: distrib
 distrib: all
-	-$(MAKE) -j -f GNUmakefile.llvm
+	-$(MAKE) -j4 -f GNUmakefile.llvm
+ifneq "$(SYS)" "Darwin"
 	-$(MAKE) -f GNUmakefile.gcc_plugin
-	$(MAKE) -C utils/libdislocator
-	$(MAKE) -C utils/libtokencap
-	-$(MAKE) -C utils/aflpp_driver
-	$(MAKE) -C utils/afl_network_proxy
-	$(MAKE) -C utils/socket_fuzzing
-	$(MAKE) -C utils/argv_fuzzing
+endif
+	-$(MAKE) -C utils/libdislocator
+	-$(MAKE) -C utils/libtokencap
+	-$(MAKE) -C utils/afl_network_proxy
+	-$(MAKE) -C utils/socket_fuzzing
+	-$(MAKE) -C utils/argv_fuzzing
+	# -$(MAKE) -C utils/plot_ui
+	-$(MAKE) -C frida_mode
+ifneq "$(SYS)" "Darwin"
+ifeq "$(ARCH)" "aarch64"
+	-$(MAKE) -C coresight_mode
+endif
+ifeq "$(SYS)" "Linux"
+	-cd nyx_mode && ./build_nyx_support.sh
+endif
 	-cd qemu_mode && sh ./build_qemu_support.sh
 	-cd unicorn_mode && unset CFLAGS && sh ./build_unicorn_support.sh
+endif
 
 .PHONY: binary-only
 binary-only: test_shm test_python ready $(PROGS)
-	$(MAKE) -C utils/libdislocator
-	$(MAKE) -C utils/libtokencap
-	$(MAKE) -C utils/afl_network_proxy
-	$(MAKE) -C utils/socket_fuzzing
-	$(MAKE) -C utils/argv_fuzzing
+	-$(MAKE) -C utils/libdislocator
+	-$(MAKE) -C utils/libtokencap
+	-$(MAKE) -C utils/afl_network_proxy
+	-$(MAKE) -C utils/socket_fuzzing
+	-$(MAKE) -C utils/argv_fuzzing
+	# -$(MAKE) -C utils/plot_ui
+	-$(MAKE) -C frida_mode
+ifneq "$(SYS)" "Darwin"
+ifeq "$(ARCH)" "aarch64"
+	-$(MAKE) -C coresight_mode
+endif
+ifeq "$(SYS)" "Linux"
+	-cd nyx_mode && ./build_nyx_support.sh
+endif
 	-cd qemu_mode && sh ./build_qemu_support.sh
 	-cd unicorn_mode && unset CFLAGS && sh ./build_unicorn_support.sh
+endif
 
 .PHONY: source-only
 source-only: all
-	-$(MAKE) -j -f GNUmakefile.llvm
+	-$(MAKE) -j4 -f GNUmakefile.llvm
+ifneq "$(SYS)" "Darwin"
 	-$(MAKE) -f GNUmakefile.gcc_plugin
-	$(MAKE) -C utils/libdislocator
-	$(MAKE) -C utils/libtokencap
-	-$(MAKE) -C utils/aflpp_driver
+endif
+	-$(MAKE) -C utils/libdislocator
+	-$(MAKE) -C utils/libtokencap
+	# -$(MAKE) -C utils/plot_ui
+ifeq "$(SYS)" "Linux"
+	-cd nyx_mode && ./build_nyx_support.sh
+endif
 
 %.8:	%
 	@echo .TH $* 8 $(BUILD_DATE) "afl++" > $@
@@ -638,6 +689,7 @@ install: all $(MANPAGES)
 	@rm -f $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt.o $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt-32.o $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt-64.o $${DESTDIR}$(HELPER_PATH)/afl-gcc-rt.o
 	install -m 755 $(PROGS) $(SH_PROGS) $${DESTDIR}$(BIN_PATH)
 	@if [ -f afl-qemu-trace ]; then install -m 755 afl-qemu-trace $${DESTDIR}$(BIN_PATH); fi
+	@if [ -f utils/plot_ui/afl-plot-ui ]; then install -m 755 utils/plot_ui/afl-plot-ui $${DESTDIR}$(BIN_PATH); fi
 	@if [ -f libdislocator.so ]; then set -e; install -m 755 libdislocator.so $${DESTDIR}$(HELPER_PATH); fi
 	@if [ -f libtokencap.so ]; then set -e; install -m 755 libtokencap.so $${DESTDIR}$(HELPER_PATH); fi
 	@if [ -f libcompcov.so ]; then set -e; install -m 755 libcompcov.so $${DESTDIR}$(HELPER_PATH); fi
@@ -645,11 +697,15 @@ install: all $(MANPAGES)
 	@if [ -f afl-fuzz-document ]; then set -e; install -m 755 afl-fuzz-document $${DESTDIR}$(BIN_PATH); fi
 	@if [ -f socketfuzz32.so -o -f socketfuzz64.so ]; then $(MAKE) -C utils/socket_fuzzing install; fi
 	@if [ -f argvfuzz32.so -o -f argvfuzz64.so ]; then $(MAKE) -C utils/argv_fuzzing install; fi
+	@if [ -f afl-frida-trace.so ]; then install -m 755 afl-frida-trace.so $${DESTDIR}$(HELPER_PATH); fi
+	@if [ -f libnyx.so ]; then install -m 755 libnyx.so $${DESTDIR}$(HELPER_PATH); fi
 	@if [ -f utils/afl_network_proxy/afl-network-server ]; then $(MAKE) -C utils/afl_network_proxy install; fi
 	@if [ -f utils/aflpp_driver/libAFLDriver.a ]; then set -e; install -m 644 utils/aflpp_driver/libAFLDriver.a $${DESTDIR}$(HELPER_PATH); fi
 	@if [ -f utils/aflpp_driver/libAFLQemuDriver.a ]; then set -e; install -m 644 utils/aflpp_driver/libAFLQemuDriver.a $${DESTDIR}$(HELPER_PATH); fi
 	-$(MAKE) -f GNUmakefile.llvm install
+ifneq "$(SYS)" "Darwin"
 	-$(MAKE) -f GNUmakefile.gcc_plugin install
+endif
 	ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-gcc
 	ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-g++
 	ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-clang
@@ -661,3 +717,16 @@ install: all $(MANPAGES)
 	install -m 644 docs/*.md $${DESTDIR}$(DOC_PATH)
 	cp -r testcases/ $${DESTDIR}$(MISC_PATH)
 	cp -r dictionaries/ $${DESTDIR}$(MISC_PATH)
+
+.PHONY: uninstall
+uninstall:
+	-cd $${DESTDIR}$(BIN_PATH) && rm -f $(PROGS) $(SH_PROGS) afl-cs-proxy afl-qemu-trace afl-plot-ui afl-fuzz-document afl-network-server afl-g* afl-plot.sh afl-as afl-ld-lto afl-c* afl-lto*
+	-cd $${DESTDIR}$(HELPER_PATH) && rm -f afl-g*.*o afl-llvm-*.*o afl-compiler-*.*o libdislocator.so libtokencap.so libcompcov.so libqasan.so afl-frida-trace.so libnyx.so socketfuzz*.so argvfuzz*.so libAFLDriver.a libAFLQemuDriver.a as afl-as SanitizerCoverage*.so compare-transform-pass.so cmplog-*-pass.so split-*-pass.so dynamic_list.txt
+	-rm -rf $${DESTDIR}$(MISC_PATH)/testcases $${DESTDIR}$(MISC_PATH)/dictionaries
+	-sh -c "ls docs/*.md | sed 's|^docs/|$${DESTDIR}$(DOC_PATH)/|' | xargs rm -f"
+	-cd $${DESTDIR}$(MAN_PATH) && rm -f $(MANPAGES)
+	-rmdir $${DESTDIR}$(BIN_PATH) 2>/dev/null
+	-rmdir $${DESTDIR}$(HELPER_PATH) 2>/dev/null
+	-rmdir $${DESTDIR}$(MISC_PATH) 2>/dev/null
+	-rmdir $${DESTDIR}$(DOC_PATH) 2>/dev/null
+	-rmdir $${DESTDIR}$(MAN_PATH) 2>/dev/null

GNUmakefile.gcc_plugin

@@ -11,13 +11,13 @@
 # from Laszlo Szekeres.
 #
 # Copyright 2015 Google Inc. All rights reserved.
-# Copyright 2019-2020 AFLplusplus Project. All rights reserved.
+# Copyright 2019-2022 AFLplusplus Project. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 #TEST_MMAP=1
 PREFIX      ?= /usr/local
@@ -41,6 +41,8 @@ CXXEFLAGS   := $(CXXFLAGS) -Wall -std=c++11
 CC          ?= gcc
 CXX         ?= g++
 
+SYS = $(shell uname -s)
+
 ifeq "clang" "$(CC)"
         CC  = gcc
         CXX = g++
@@ -75,30 +77,30 @@ ifeq "$(TEST_MMAP)" "1"
 	override CFLAGS_SAFE += -DUSEMMAP=1
 endif
 
-ifneq "$(shell uname -s)" "Haiku"
-ifneq "$(shell uname -s)" "OpenBSD"
+ifneq "$(SYS)" "Haiku"
+ifneq "$(SYS)" "OpenBSD"
   	LDFLAGS += -lrt
 endif
 else
 	CFLAGS_SAFE += -DUSEMMAP=1
 endif
 
-ifeq "$(shell uname -s)" "OpenBSD"
+ifeq "$(SYS)" "OpenBSD"
     CC  = egcc
     CXX = eg++
     PLUGIN_FLAGS += -I/usr/local/include
 endif
 
-ifeq "$(shell uname -s)" "DragonFly"
+ifeq "$(SYS)" "DragonFly"
   	PLUGIN_FLAGS += -I/usr/local/include
 endif
 
-ifeq "$(shell uname -s)" "SunOS"
+ifeq "$(SYS)" "SunOS"
   	PLUGIN_FLAGS += -I/usr/include/gmp
 endif
 
 
-PROGS        = ./afl-gcc-pass.so
+PROGS        = ./afl-gcc-pass.so ./afl-compiler-rt.o ./afl-compiler-rt-32.o ./afl-compiler-rt-64.o
 
 .PHONY: all
 all: test_shm test_deps $(PROGS) test_build all_done
@@ -128,6 +130,17 @@ test_deps:
 afl-common.o: ./src/afl-common.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) -c $< -o $@ $(LDFLAGS)
 
+./afl-compiler-rt.o: instrumentation/afl-compiler-rt.o.c
+	$(CC) $(CFLAGS_SAFE) $(CPPFLAGS) -O3 -Wno-unused-result -fPIC -c $< -o $@
+
+./afl-compiler-rt-32.o: instrumentation/afl-compiler-rt.o.c
+	@printf "[*] Building 32-bit variant of the runtime (-m32)... "
+	@$(CC) $(CFLAGS_SAFE) $(CPPFLAGS) -O3 -Wno-unused-result -m32 -fPIC -c $< -o $@ 2>/dev/null; if [ "$$?" = "0" ]; then echo "success!"; ln -sf afl-compiler-rt-32.o afl-llvm-rt-32.o; else echo "failed (that's fine)"; fi
+
+./afl-compiler-rt-64.o: instrumentation/afl-compiler-rt.o.c
+	@printf "[*] Building 64-bit variant of the runtime (-m64)... "
+	@$(CC) $(CFLAGS_SAFE) $(CPPFLAGS) -O3 -Wno-unused-result -m64 -fPIC -c $< -o $@ 2>/dev/null; if [ "$$?" = "0" ]; then echo "success!"; ln -sf afl-compiler-rt-64.o afl-llvm-rt-64.o; else echo "failed (that's fine)"; fi
+
 ./afl-gcc-pass.so: instrumentation/afl-gcc-pass.so.cc | test_deps
 	$(CXX) $(CXXEFLAGS) $(PLUGIN_FLAGS) -shared $< -o $@
 	ln -sf afl-cc afl-gcc-fast

GNUmakefile.llvm

@@ -12,7 +12,7 @@
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 
 # For Heiko:
@@ -30,11 +30,13 @@ BUILD_DATE  ?= $(shell date -u -d "@$(SOURCE_DATE_EPOCH)" "+%Y-%m-%d" 2>/dev/nul
 
 VERSION     = $(shell grep '^$(HASH)define VERSION ' ./config.h | cut -d '"' -f2)
 
-ifeq "$(shell uname)" "OpenBSD"
+SYS = $(shell uname -s)
+
+ifeq "$(SYS)" "OpenBSD"
   LLVM_CONFIG ?= $(BIN_PATH)/llvm-config
   HAS_OPT = $(shell test -x $(BIN_PATH)/opt && echo 0 || echo 1)
   ifeq "$(HAS_OPT)" "1"
-    $(warning llvm_mode needs a complete llvm installation (versions 3.4 up to 12) -> e.g. "pkg_add llvm-7.0.1p9")
+    $(warning llvm_mode needs a complete llvm installation (versions 6.0 up to 13) -> e.g. "pkg_add llvm-7.0.1p9")
   endif
 else
   LLVM_CONFIG ?= llvm-config
@@ -43,22 +45,27 @@ endif
 LLVMVER  = $(shell $(LLVM_CONFIG) --version 2>/dev/null | sed 's/git//' | sed 's/svn//' )
 LLVM_MAJOR = $(shell $(LLVM_CONFIG) --version 2>/dev/null | sed 's/\..*//' )
 LLVM_MINOR = $(shell $(LLVM_CONFIG) --version 2>/dev/null | sed 's/.*\.//' | sed 's/git//' | sed 's/svn//' | sed 's/ .*//' )
-LLVM_UNSUPPORTED = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^3\.[0-3]|^1[3-9]' && echo 1 || echo 0 )
+LLVM_UNSUPPORTED = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^[0-2]\.|^3.[0-7]\.' && echo 1 || echo 0 )
+LLVM_TOO_NEW = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^1[4-9]' && echo 1 || echo 0 )
 LLVM_NEW_API = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^1[0-9]' && echo 1 || echo 0 )
 LLVM_10_OK = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^1[1-9]|^10\.[1-9]|^10\.0.[1-9]' && echo 1 || echo 0 )
 LLVM_HAVE_LTO = $(shell $(LLVM_CONFIG) --version 2>/dev/null | egrep -q '^1[1-9]' && echo 1 || echo 0 )
 LLVM_BINDIR = $(shell $(LLVM_CONFIG) --bindir 2>/dev/null)
 LLVM_LIBDIR = $(shell $(LLVM_CONFIG) --libdir 2>/dev/null)
 LLVM_STDCXX = gnu++11
-LLVM_APPLE_XCODE = $(shell clang -v 2>&1 | grep -q Apple && echo 1 || echo 0)
+LLVM_APPLE_XCODE = $(shell $(CC) -v 2>&1 | grep -q Apple && echo 1 || echo 0)
 LLVM_LTO   = 0
 
 ifeq "$(LLVMVER)" ""
-  $(warning [!] llvm_mode needs llvm-config, which was not found)
+  $(warning [!] llvm_mode needs llvm-config, which was not found. Set LLVM_CONFIG to its path and retry.)
 endif
 
 ifeq "$(LLVM_UNSUPPORTED)" "1"
-  $(warning llvm_mode only supports llvm versions 3.4 up to 12)
+  $(error llvm_mode only supports llvm from version 3.8 onwards)
+endif
+
+ifeq "$(LLVM_TOO_NEW)" "1"
+  $(warning you are using an in-development llvm version - this might break llvm_mode!)
 endif
 
 LLVM_TOO_OLD=1
@@ -270,13 +277,15 @@ CLANG_LFL    = `$(LLVM_CONFIG) --ldflags` $(LDFLAGS)
 
 
 # User teor2345 reports that this is required to make things work on MacOS X.
-ifeq "$(shell uname)" "Darwin"
+ifeq "$(SYS)" "Darwin"
   CLANG_LFL += -Wl,-flat_namespace -Wl,-undefined,suppress
+  override LLVM_HAVE_LTO := 0
+  override LLVM_LTO := 0
 else
   CLANG_CPPFL += -Wl,-znodelete
 endif
 
-ifeq "$(shell uname)" "OpenBSD"
+ifeq "$(SYS)" "OpenBSD"
   CLANG_LFL += `$(LLVM_CONFIG) --libdir`/libLLVM.so
   CLANG_CPPFL += -mno-retpoline
   CFLAGS += -mno-retpoline
@@ -299,7 +308,7 @@ ifeq "$(TEST_MMAP)" "1"
 endif
 
 PROGS_ALWAYS = ./afl-cc ./afl-compiler-rt.o ./afl-compiler-rt-32.o ./afl-compiler-rt-64.o 
-PROGS        = $(PROGS_ALWAYS) ./afl-llvm-pass.so ./SanitizerCoveragePCGUARD.so ./split-compares-pass.so ./split-switches-pass.so ./cmplog-routines-pass.so ./cmplog-instructions-pass.so ./afl-llvm-dict2file.so ./compare-transform-pass.so ./libLLVMInsTrim.so ./afl-ld-lto ./afl-llvm-lto-instrumentlist.so ./afl-llvm-lto-instrumentation.so ./SanitizerCoverageLTO.so
+PROGS        = $(PROGS_ALWAYS) ./afl-llvm-pass.so ./SanitizerCoveragePCGUARD.so ./split-compares-pass.so ./split-switches-pass.so ./cmplog-routines-pass.so ./cmplog-instructions-pass.so ./cmplog-switches-pass.so ./afl-llvm-dict2file.so ./compare-transform-pass.so ./afl-ld-lto ./afl-llvm-lto-instrumentlist.so ./SanitizerCoverageLTO.so
 
 # If prerequisites are not given, warn, do not build anything, and exit with code 0
 ifeq "$(LLVMVER)" ""
@@ -339,7 +348,7 @@ no_build:
 test_deps:
 	@echo "[*] Checking for working 'llvm-config'..."
  ifneq "$(LLVM_APPLE_XCODE)" "1"
-	@type $(LLVM_CONFIG) >/dev/null 2>&1 || ( echo "[-] Oops, can't find 'llvm-config'. Install clang or set \$$LLVM_CONFIG or \$$PATH beforehand."; echo "    (Sometimes, the binary will be named llvm-config-3.5 or something like that.)"; exit 1 )
+	@type $(LLVM_CONFIG) >/dev/null 2>&1 || ( echo "[-] Oops, can't find 'llvm-config'. Install clang or set \$$LLVM_CONFIG or \$$PATH beforehand."; echo "    (Sometimes, the binary will be named llvm-config-11 or something like that.)"; exit 1 )
  endif
 	@echo "[*] Checking for working '$(CC)'..."
 	@type $(CC) >/dev/null 2>&1 || ( echo "[-] Oops, can't find '$(CC)'. Make sure that it's in your \$$PATH (or set \$$CC and \$$CXX)."; exit 1 )
@@ -377,18 +386,15 @@ endif
 instrumentation/afl-llvm-common.o: instrumentation/afl-llvm-common.cc instrumentation/afl-llvm-common.h
 	$(CXX) $(CFLAGS) $(CPPFLAGS) `$(LLVM_CONFIG) --cxxflags` -fno-rtti -fPIC -std=$(LLVM_STDCXX) -c $< -o $@ 
 
-./libLLVMInsTrim.so: instrumentation/LLVMInsTrim.so.cc instrumentation/MarkNodes.cc instrumentation/afl-llvm-common.o | test_deps
-	-$(CXX) $(CLANG_CPPFL) -DLLVMInsTrim_EXPORTS -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< instrumentation/MarkNodes.cc -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
-
 ./afl-llvm-pass.so: instrumentation/afl-llvm-pass.so.cc instrumentation/afl-llvm-common.o | test_deps
 ifeq "$(LLVM_MIN_4_0_1)" "0"
 	$(info [!] N-gram branch coverage instrumentation is not available for llvm version $(LLVMVER))
 endif
-	$(CXX) $(CLANG_CPPFL) -DLLVMInsTrim_EXPORTS -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
+	$(CXX) $(CLANG_CPPFL) -Wdeprecated -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
 
 ./SanitizerCoveragePCGUARD.so: instrumentation/SanitizerCoveragePCGUARD.so.cc instrumentation/afl-llvm-common.o | test_deps
 ifeq "$(LLVM_10_OK)" "1"
-	-$(CXX) $(CLANG_CPPFL) -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
+	-$(CXX) $(CLANG_CPPFL) -Wdeprecated -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
 endif
 
 ./afl-llvm-lto-instrumentlist.so: instrumentation/afl-llvm-lto-instrumentlist.so.cc instrumentation/afl-llvm-common.o
@@ -402,11 +408,6 @@ ifeq "$(LLVM_LTO)" "1"
 endif
 
 ./SanitizerCoverageLTO.so: instrumentation/SanitizerCoverageLTO.so.cc
-ifeq "$(LLVM_LTO)" "1"
-	$(CXX) $(CLANG_CPPFL) -Wno-writable-strings -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
-endif
-
-./afl-llvm-lto-instrumentation.so: instrumentation/afl-llvm-lto-instrumentation.so.cc instrumentation/afl-llvm-common.o
 ifeq "$(LLVM_LTO)" "1"
 	$(CXX) $(CLANG_CPPFL) -Wno-writable-strings -fno-rtti -fPIC -std=$(LLVM_STDCXX) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
 	$(CLANG_BIN) $(CFLAGS_SAFE) $(CPPFLAGS) -Wno-unused-result -O0 $(AFL_CLANG_FLTO) -fPIC -c instrumentation/afl-llvm-rt-lto.o.c -o ./afl-llvm-rt-lto.o
@@ -429,6 +430,9 @@ endif
 ./cmplog-instructions-pass.so:	instrumentation/cmplog-instructions-pass.cc instrumentation/afl-llvm-common.o | test_deps
 	$(CXX) $(CLANG_CPPFL) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
 
+./cmplog-switches-pass.so:	instrumentation/cmplog-switches-pass.cc instrumentation/afl-llvm-common.o | test_deps
+	$(CXX) $(CLANG_CPPFL) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
+
 afl-llvm-dict2file.so:	instrumentation/afl-llvm-dict2file.so.cc instrumentation/afl-llvm-common.o | test_deps
 	$(CXX) $(CLANG_CPPFL) -shared $< -o $@ $(CLANG_LFL) instrumentation/afl-llvm-common.o
 
@@ -471,7 +475,7 @@ install: all
 	@if [ -f ./afl-cc ]; then set -e; install -m 755 ./afl-cc $${DESTDIR}$(BIN_PATH); ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-c++; fi
 	@rm -f $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt*.o $${DESTDIR}$(HELPER_PATH)/afl-gcc-rt*.o
 	@if [ -f ./afl-compiler-rt.o ]; then set -e; install -m 755 ./afl-compiler-rt.o $${DESTDIR}$(HELPER_PATH); ln -sf afl-compiler-rt.o $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt.o ;fi
-	@if [ -f ./afl-lto ]; then set -e; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-lto; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-lto++; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-clang-lto; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-clang-lto++; install -m 755 ./afl-llvm-lto-instrumentation.so ./afl-llvm-rt-lto*.o ./afl-llvm-lto-instrumentlist.so $${DESTDIR}$(HELPER_PATH); fi
+	@if [ -f ./afl-lto ]; then set -e; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-lto; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-lto++; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-clang-lto; ln -sf afl-cc $${DESTDIR}$(BIN_PATH)/afl-clang-lto++; install -m 755 ./afl-llvm-rt-lto*.o ./afl-llvm-lto-instrumentlist.so $${DESTDIR}$(HELPER_PATH); fi
 	@if [ -f ./afl-ld-lto ]; then set -e; install -m 755 ./afl-ld-lto $${DESTDIR}$(BIN_PATH); fi
 	@if [ -f ./afl-compiler-rt-32.o ]; then set -e; install -m 755 ./afl-compiler-rt-32.o $${DESTDIR}$(HELPER_PATH); ln -sf afl-compiler-rt-32.o $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt-32.o ;fi
 	@if [ -f ./afl-compiler-rt-64.o ]; then set -e; install -m 755 ./afl-compiler-rt-64.o $${DESTDIR}$(HELPER_PATH); ln -sf afl-compiler-rt-64.o $${DESTDIR}$(HELPER_PATH)/afl-llvm-rt-64.o ; fi
@@ -502,6 +506,8 @@ install: all
 	@echo .SH LICENSE >> ./$@
 	@echo Apache License Version 2.0, January 2004 >> ./$@
 	@ln -sf afl-cc.8 ./afl-c++.8
+	@ln -sf afl-cc.8 ./afl-clang-fast.8
+	@ln -sf afl-cc.8 ./afl-clang-fast++.8
 ifneq "$(AFL_CLANG_FLTO)" ""
 ifeq "$(LLVM_LTO)" "1"
 	@ln -sf afl-cc.8 ./afl-clang-lto.8

QuickStartGuide.md

@@ -1 +0,0 @@
-docs/QuickStartGuide.md

TODO.md

@@ -1,34 +1,32 @@
 # TODO list for AFL++
 
-## Roadmap 3.00+
+## Should
 
- - AFL_MAP_SIZE for qemu_mode and unicorn_mode
- - CPU affinity for many cores? There seems to be an issue > 96 cores
+ - better autodetection of shifting runtime timeout values
+ - Update afl->pending_not_fuzzed for MOpt
  - afl-plot to support multiple plot_data
+ - parallel builds for source-only targets
+ - get rid of check_binary, replace with more forkserver communication
+
+## Maybe
+
  - afl_custom_fuzz_splice_optin()
- - intel-pt tracer
+ - afl_custom_splice()
+ - cmdline option from-to range for mutations
 
 ## Further down the road
 
-afl-fuzz:
- - setting min_len/max_len/start_offset/end_offset limits for mutation output
- - add __sanitizer_cov_trace_cmp* support via shmem
-
-llvm_mode:
- - add __sanitizer_cov_trace_cmp* support
-
-qemu_mode:
+QEMU mode/FRIDA mode:
  - non colliding instrumentation
  - rename qemu specific envs to AFL_QEMU (AFL_ENTRYPOINT, AFL_CODE_START/END,
    AFL_COMPCOV_LEVEL?)
- - add AFL_QEMU_EXITPOINT (maybe multiple?), maybe pointless as we have
+ - add AFL_QEMU_EXITPOINT (maybe multiple?), maybe pointless as there is
    persistent mode
- - add/implement AFL_QEMU_INST_LIBLIST and AFL_QEMU_NOINST_PROGRAM
- - add/implement AFL_QEMU_INST_REGIONS as a list of _START/_END addresses
 
 ## Ideas
 
  - LTO/sancov: write current edge to prev_loc and use that information when
-   using cmplog or __sanitizer_cov_trace_cmp*. maybe we can deduct by follow
-   up edge numbers that both following cmp paths have been found and then
-   disable working on this edge id -> cmplog_intelligence branch
+   using cmplog or __sanitizer_cov_trace_cmp*. maybe we can deduct by follow up
+   edge numbers that both following cmp paths have been found and then disable
+   working on this edge id -> cmplog_intelligence branch
+ - use cmplog colorization taint result for havoc locations?

afl-cmin

@@ -106,6 +106,7 @@ function usage() {
 "  -f file       - location read by the fuzzed program (stdin)\n" \
 "  -m megs       - memory limit for child process ("mem_limit" MB)\n" \
 "  -t msec       - run time limit for child process (none)\n" \
+"  -O            - use binary-only instrumentation (FRIDA mode)\n" \
 "  -Q            - use binary-only instrumentation (QEMU mode)\n" \
 "  -U            - use unicorn-based instrumentation (unicorn mode)\n" \
 "\n" \
@@ -118,11 +119,14 @@ function usage() {
 "Environment variables used:\n" \
 "AFL_ALLOW_TMP: allow unsafe use of input/output directories under {/var}/tmp\n" \
 "AFL_CRASH_EXITCODE: optional child exit code to be interpreted as crash\n" \
-"AFL_FORKSRV_INIT_TMOUT: time the fuzzer waits for the target to come up, initially\n" \
+"AFL_FORKSRV_INIT_TMOUT: time the fuzzer waits for the forkserver to come up\n" \
 "AFL_KEEP_TRACES: leave the temporary <out_dir>/.traces directory\n" \
-"AFL_KILL_SIGNAL: Signal ID delivered to child processes on timeout, etc. (default: SIGKILL)\n"
-"AFL_PATH: path for the afl-showmap binary if not found anywhere else\n" \
-"AFL_SKIP_BIN_CHECK: skip check for target binary\n"
+"AFL_KILL_SIGNAL: Signal delivered to child processes on timeout (default: SIGKILL)\n" \
+"AFL_NO_FORKSRV: run target via execve instead of using the forkserver\n" \
+"AFL_PATH: path for the afl-showmap binary if not found anywhere in PATH\n" \
+"AFL_PRINT_FILENAMES: If set, the filename currently processed will be " \
+      "printed to stdout\n" \
+"AFL_SKIP_BIN_CHECK: skip afl instrumentation checks for target binary\n"
    exit 1
 }
 
@@ -140,7 +144,7 @@ BEGIN {
   # process options
   Opterr = 1    # default is to diagnose
   Optind = 1    # skip ARGV[0]
-  while ((_go_c = getopt(ARGC, ARGV, "hi:o:f:m:t:eCQU?")) != -1) {
+  while ((_go_c = getopt(ARGC, ARGV, "hi:o:f:m:t:eCOQU?")) != -1) {
     if (_go_c == "i") {
       if (!Optarg) usage()
       if (in_dir) { print "Option "_go_c" is only allowed once" > "/dev/stderr"}
@@ -180,6 +184,12 @@ BEGIN {
       extra_par = extra_par " -e"
       continue
     } else 
+    if (_go_c == "O") {
+      if (frida_mode) { print "Option "_go_c" is only allowed once" > "/dev/stderr"}
+      extra_par = extra_par " -O"
+      frida_mode = 1
+      continue
+    } else 
     if (_go_c == "Q") {
       if (qemu_mode) { print "Option "_go_c" is only allowed once" > "/dev/stderr"}
       extra_par = extra_par " -Q"
@@ -243,7 +253,7 @@ BEGIN {
   if (!stdin_file) {
     found_atat = 0
     for (prog_args_ind in prog_args) {
-      if ("@@" == prog_args[prog_args_ind]) {
+      if (match(prog_args[prog_args_ind], "@@") != 0) {
         found_atat = 1
         break
       }
@@ -275,7 +285,7 @@ BEGIN {
     target_bin = tnew
   }
 
-  if (!ENVIRON["AFL_SKIP_BIN_CHECK"] && !qemu_mode && !unicorn_mode) {
+  if (!ENVIRON["AFL_SKIP_BIN_CHECK"] && !qemu_mode && !frida_mode && !unicorn_mode) {
     if (0 != system( "grep -q __AFL_SHM_ID "target_bin )) {
       print "[-] Error: binary '"target_bin"' doesn't appear to be instrumented." > "/dev/stderr"
       exit 1
@@ -287,9 +297,13 @@ BEGIN {
     exit 1
   }
 
-  if (0 == system( "test -d "in_dir"/queue" )) {
-    in_dir = in_dir "/queue"
-  }
+  #if (0 == system( "test -d "in_dir"/default" )) {
+  #  in_dir = in_dir "/default"
+  #}
+  #
+  #if (0 == system( "test -d "in_dir"/queue" )) {
+  #  in_dir = in_dir "/queue"
+  #}
 
   system("rm -rf "trace_dir" 2>/dev/null");
   system("rm "out_dir"/id[:_]* 2>/dev/null")
@@ -342,28 +356,35 @@ BEGIN {
   } else {
     stat_format = "-f '%z %N'" # *BSD, MacOS
   }
-  cmdline = "cd "in_dir" && find . \\( ! -name . -a -type d -prune \\) -o -type f -exec stat "stat_format" \\{\\} \\; | sort -k1n -k2r"
-  cmdline = "ls "in_dir" | (cd "in_dir" && xargs stat "stat_format" 2>/dev/null) | sort -k1n -k2r"
+  cmdline = "(cd "in_dir" && find . \\( ! -name \".*\" -a -type d \\) -o -type f -exec stat "stat_format" \\{\\} + | sort -k1n -k2r)"
+  #cmdline = "ls "in_dir" | (cd "in_dir" && xargs stat "stat_format" 2>/dev/null) | sort -k1n -k2r"
+  #cmdline = "(cd "in_dir" && stat "stat_format" *) | sort -k1n -k2r"
+  #cmdline = "(cd "in_dir" && ls | xargs stat "stat_format" ) | sort -k1n -k2r"
   while (cmdline | getline) {
     sub(/^[0-9]+ (\.\/)?/,"",$0)
-    infilesSmallToBig[i++] = $0
+    infilesSmallToBigFull[i] = $0
+    sub(/.*\//, "", $0)
+    infilesSmallToBig[i] = $0
+    infilesSmallToBigMap[infilesSmallToBig[i]] = infilesSmallToBigFull[i]
+    infilesSmallToBigFullMap[infilesSmallToBigFull[i]] = infilesSmallToBig[i]
+    i++
   }
   in_count = i
 
-  first_file = infilesSmallToBig[0]
+  first_file = infilesSmallToBigFull[0]
   
-  # Make sure that we're not dealing with a directory.
+  #if (0 == system("test -d ""\""in_dir"/"first_file"\"")) {
+  #  print "[-] Error: The input directory is empty or contains subdirectories - please fix." > "/dev/stderr"
+  #  exit 1
+  #}
 
-  if (0 == system("test -d "in_dir"/"first_file)) {
-    print "[-] Error: The input directory is empty or contains subdirectories - please fix." > "/dev/stderr"
-    exit 1
-  }
-
-  if (0 == system("ln "in_dir"/"first_file" "trace_dir"/.link_test")) {
+  system(">\""in_dir"/.afl-cmin.test\"")
+  if (0 == system("ln \""in_dir"/.afl-cmin.test\" "trace_dir"/.link_test")) {
     cp_tool = "ln"
   } else {
     cp_tool = "cp"
   }
+  system("rm -f \""in_dir"/.afl-cmin.test\"")
 
   if (!ENVIRON["AFL_SKIP_BIN_CHECK"]) {
     # Make sure that we can actually get anything out of afl-showmap before we
@@ -374,8 +395,8 @@ BEGIN {
     if (!stdin_file) {
       system( "AFL_CMIN_ALLOW_ANY=1 "AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"/.run_test\" -Z "extra_par" -- \""target_bin"\" "prog_args_string" <\""in_dir"/"first_file"\"")
     } else {
-      system("cp "in_dir"/"first_file" "stdin_file)
-      system( "AFL_CMIN_ALLOW_ANY=1 "AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"/.run_test\" -Z "extra_par" -A \""stdin_file"\" -- \""target_bin"\" "prog_args_string" </dev/null")
+      system("cp \""in_dir"/"first_file"\" "stdin_file)
+      system( "AFL_CMIN_ALLOW_ANY=1 "AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"/.run_test\" -Z "extra_par" -H \""stdin_file"\" -- \""target_bin"\" "prog_args_string" </dev/null")
     }
 
     first_count = 0
@@ -411,8 +432,8 @@ BEGIN {
     retval = system( AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"\" -Z "extra_par" -i \""in_dir"\" -- \""target_bin"\" "prog_args_string)
   } else {
     print "    Processing "in_count" files (forkserver mode)..."
-#    print AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"\" -Z "extra_par" -i \""in_dir"\" -- \""target_bin"\" "prog_args_string" </dev/null"
-    retval = system( AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"\" -Z "extra_par" -i \""in_dir"\" -- \""target_bin"\" "prog_args_string" </dev/null")
+#    print AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"\" -Z "extra_par" -i \""in_dir"\" -H \""stdin_file"\" -- \""target_bin"\" "prog_args_string" </dev/null"
+    retval = system( AFL_CMIN_CRASHES_ONLY"\""showmap"\" -m "mem_limit" -t "timeout" -o \""trace_dir"\" -Z "extra_par" -i \""in_dir"\" -H \""stdin_file"\" -- \""target_bin"\" "prog_args_string" </dev/null")
   }
 
   if (retval && !AFL_CMIN_CRASHES_ONLY) {
@@ -496,7 +517,8 @@ BEGIN {
 
     # copy file unless already done
     if (! (fn in file_already_copied)) {
-      system(cp_tool" "in_dir"/"fn" "out_dir"/"fn)
+      realfile = infilesSmallToBigMap[fn]
+      system(cp_tool" \""in_dir"/"realfile"\" \""out_dir"/"fn"\"")
       file_already_copied[fn] = ""
       ++out_count
       #printf "tuple nr %d (%d cnt=%d) -> %s\n",tcnt,key,key_count[key],fn > trace_dir"/.log"

afl-cmin.bash

@@ -11,7 +11,7 @@
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 # This tool tries to find the smallest subset of files in the input directory
 # that still trigger the full range of instrumentation data points seen in
@@ -53,7 +53,7 @@ unset IN_DIR OUT_DIR STDIN_FILE EXTRA_PAR MEM_LIMIT_GIVEN \
 
 export AFL_QUIET=1
 
-while getopts "+i:o:f:m:t:eQUCh" opt; do
+while getopts "+i:o:f:m:t:eOQUCh" opt; do
 
   case "$opt" in 
 
@@ -83,6 +83,10 @@ while getopts "+i:o:f:m:t:eQUCh" opt; do
     "C")
          export AFL_CMIN_CRASHES_ONLY=1
          ;;
+    "O")
+         EXTRA_PAR="$EXTRA_PAR -O"
+         FRIDA_MODE=1
+         ;;         
     "Q")
          EXTRA_PAR="$EXTRA_PAR -Q"
          QEMU_MODE=1
@@ -118,6 +122,7 @@ Execution control settings:
   -f file       - location read by the fuzzed program (stdin)
   -m megs       - memory limit for child process ($MEM_LIMIT MB)
   -t msec       - run time limit for child process (none)
+  -O            - use binary-only instrumentation (FRIDA mode)
   -Q            - use binary-only instrumentation (QEMU mode)
   -U            - use unicorn-based instrumentation (Unicorn mode)
   
@@ -130,6 +135,7 @@ For additional tips, please consult README.md.
 
 Environment variables used:
 AFL_KEEP_TRACES: leave the temporary <out_dir>\.traces directory
+AFL_NO_FORKSRV: run target via execve instead of using the forkserver
 AFL_PATH: last resort location to find the afl-showmap binary
 AFL_SKIP_BIN_CHECK: skip check for target binary
 _EOF_
@@ -209,7 +215,7 @@ if [ ! -f "$TARGET_BIN" -o ! -x "$TARGET_BIN" ]; then
 
 fi
 
-if [ "$AFL_SKIP_BIN_CHECK" = "" -a "$QEMU_MODE" = "" -a "$UNICORN_MODE" = "" ]; then
+if [ "$AFL_SKIP_BIN_CHECK" = "" -a "$QEMU_MODE" = "" -a "$FRIDA_MODE" = "" -a "$UNICORN_MODE" = "" ]; then
 
   if ! grep -qF "__AFL_SHM_ID" "$TARGET_BIN"; then
     echo "[-] Error: binary '$TARGET_BIN' doesn't appear to be instrumented." 1>&2
@@ -223,6 +229,7 @@ if [ ! -d "$IN_DIR" ]; then
   exit 1
 fi
 
+test -d "$IN_DIR/default" && IN_DIR="$IN_DIR/default"
 test -d "$IN_DIR/queue" && IN_DIR="$IN_DIR/queue"
 
 find "$OUT_DIR" -name 'id[:_]*' -maxdepth 1 -exec rm -- {} \; 2>/dev/null
@@ -303,7 +310,7 @@ if [ "$STDIN_FILE" = "" ]; then
 else
 
   cp "$IN_DIR/$FIRST_FILE" "$STDIN_FILE"
-  AFL_CMIN_ALLOW_ANY=1 "$SHOWMAP" -m "$MEM_LIMIT" -t "$TIMEOUT" -o "$TRACE_DIR/.run_test" -Z $EXTRA_PAR -A "$STDIN_FILE" -- "$@" </dev/null
+  AFL_CMIN_ALLOW_ANY=1 "$SHOWMAP" -m "$MEM_LIMIT" -t "$TIMEOUT" -o "$TRACE_DIR/.run_test" -Z $EXTRA_PAR -H "$STDIN_FILE" -- "$@" </dev/null
 
 fi
 
@@ -353,7 +360,7 @@ echo "[*] Obtaining traces for input files in '$IN_DIR'..."
 
       cp "$IN_DIR/$fn" "$STDIN_FILE"
 
-      "$SHOWMAP" -m "$MEM_LIMIT" -t "$TIMEOUT" -o "$TRACE_DIR/$fn" -Z $EXTRA_PAR -A "$STDIN_FILE" -- "$@" </dev/null
+      "$SHOWMAP" -m "$MEM_LIMIT" -t "$TIMEOUT" -o "$TRACE_DIR/$fn" -Z $EXTRA_PAR -H "$STDIN_FILE" -- "$@" </dev/null
 
     done
 

afl-persistent-config

@@ -0,0 +1,133 @@
+#!/bin/bash
+# written by jhertz
+# 
+
+test "$1" = "-h" -o "$1" = "-hh" && {
+  echo 'afl-persistent-config'
+  echo
+  echo $0
+  echo
+  echo afl-persistent-config has no command line options
+  echo
+  echo afl-persistent-config permanently reconfigures the system to a high performance fuzzing state.
+  echo "WARNING: this reduces the security of the system!"
+  echo
+  echo Note that there is also afl-system-config which sets additional runtime
+  echo configuration options.
+  exit 0
+}
+
+echo
+echo "WARNING: This scripts makes permanent configuration changes to the system to"
+echo "         increase the performance for fuzzing. As a result, the system also"
+echo "         becomes less secure against attacks! If you use this script, setup"
+echo "         strong firewall rules and only make SSH available as a network"
+echo "         service!"
+echo
+echo -n "Type \"YES\" to continue: "
+read ANSWER
+if [[ "$ANSWER" != "YES" ]]; then
+  echo Input was not YES, aborting ...
+  exit 1
+fi
+
+echo
+PLATFORM=`uname -s`
+
+# check that we're on Mac
+if [[ "$PLATFORM" = "Darwin" ]] ; then
+
+  # check if UID == 0
+  if [[ "$EUID" -ne 0 ]]; then
+    echo "You need to be root to do this. E.g. use \"sudo\""
+    exit 1
+  fi
+
+  # check if SIP is disabled
+  if [[ ! $(csrutil status | grep "disabled") ]]; then
+    echo "SIP needs to be disabled. Restart and press Command-R at reboot, Utilities => Terminal => enter \"csrutil disable\""
+    exit 1
+  fi
+
+  echo "Checks passed."
+
+  echo "Installing /Library/LaunchDaemons/shm_setup.plist"
+
+  cat << EOF > /Library/LaunchDaemons/shm_setup.plist
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+  <dict>
+    <key>Label</key>
+    <string>shmemsetup</string>
+    <key>UserName</key>
+    <string>root</string>
+    <key>GroupName</key>
+    <string>wheel</string>
+    <key>ProgramArguments</key>
+    <array>
+      <string>/usr/sbin/sysctl</string>
+      <string>-w</string>
+      <string>kern.sysv.shmmax=524288000</string>
+      <string>kern.sysv.shmmin=1</string>
+      <string>kern.sysv.shmmni=128</string>
+      <string>kern.sysv.shmseg=48</string>
+      <string>kern.sysv.shmall=131072000</string>
+    </array>
+    <key>KeepAlive</key>
+    <false/>
+    <key>RunAtLoad</key>
+    <true/>
+  </dict>
+</plist>
+EOF
+
+  echo
+  echo "Reboot and enjoy your fuzzing"
+  exit 0
+fi
+
+if [[ "$PLATFORM" = "Linux" ]] ; then
+
+  # check if UID == 0
+  if [[ "$EUID" -ne 0 ]]; then
+    echo "You need to be root to do this. E.g. use \"sudo\""
+    exit 1
+  fi
+
+  echo "Checks passed."
+
+  test -d /etc/sysctl.d || echo Error: /etc/sysctl.d directory not found, cannot install shmem config
+  test -d /etc/sysctl.d -a '!' -e /etc/sysctl.d/99-fuzzing && {
+    echo "Installing /etc/sysctl.d/99-fuzzing"
+    cat << EOF > /etc/sysctl.d/99-fuzzing
+kernel.core_uses_pid=0
+kernel.core_pattern=core
+kernel.randomize_va_space=0
+kernel.sched_child_runs_first=1
+kernel.sched_autogroup_enabled=1
+kernel.sched_migration_cost_ns=50000000
+kernel.sched_latency_ns=250000000
+EOF
+  }
+
+  egrep -q '^GRUB_CMDLINE_LINUX_DEFAULT=' /etc/default/grub 2>/dev/null || echo Error: /etc/default/grub with GRUB_CMDLINE_LINUX_DEFAULT is not present, cannot set boot options
+  egrep -q '^GRUB_CMDLINE_LINUX_DEFAULT=' /etc/default/grub 2>/dev/null && {
+    egrep '^GRUB_CMDLINE_LINUX_DEFAULT=' /etc/default/grub | egrep -q hardened_usercopy=off || {
+      echo "Configuring performance boot options"
+      LINE=`egrep '^GRUB_CMDLINE_LINUX_DEFAULT=' /etc/default/grub | sed 's/^GRUB_CMDLINE_LINUX_DEFAULT=//' | tr -d '"'`
+      OPTIONS="$LINE 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 srbds=off noexec=off noexec32=off tsx=on tsx=on tsx_async_abort=off mitigations=off audit=0 hardened_usercopy=off ssbd=force-off"
+      echo Setting boot options in /etc/default/grub to GRUB_CMDLINE_LINUX_DEFAULT=\"$OPTIONS\"
+      sed -i "s|^GRUB_CMDLINE_LINUX_DEFAULT=.*|GRUB_CMDLINE_LINUX_DEFAULT=\"$OPTIONS\"|" /etc/default/grub
+    }
+  }
+
+  echo
+  echo "Reboot and enjoy your fuzzing"
+  exit 0
+fi
+
+
+
+echo "Error: Unknown platform \"$PLATFORM\", currently supported are Linux and MacOS."
+exit 1

afl-plot

@@ -12,7 +12,7 @@
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 
 get_abs_path() {
@@ -22,16 +22,28 @@ get_abs_path() {
 echo "progress plotting utility for afl-fuzz by Michal Zalewski"
 echo
 
-if [ ! "$#" = "2" ]; then
+GRAPHICAL="0"
+
+if [ "$1"  = "-g" ] || [ "$1" = "--graphical" ]; then
+GRAPHICAL="1"
+shift
+fi
+
+if [ "$#" != "2" ]; then
 
   cat 1>&2 <<_EOF_
-$0 afl_state_dir graph_output_dir
+$0 [ -g | --graphical ] afl_state_dir graph_output_dir
 
-This program generates gnuplot images from afl-fuzz output data. Usage:
+This program generates gnuplot images from afl-fuzz output data.
 
-The afl_state_dir parameter should point to an existing state directory for any
-active or stopped instance of afl-fuzz; while graph_output_dir should point to
-an empty directory where this tool can write the resulting plots to.
+Usage:
+
+    afl_state_dir       should point to an existing state directory for any
+                        active or stopped instance of afl-fuzz
+    graph_output_dir    should point to an empty directory where this
+                        tool can write the resulting plots to
+    -g, --graphical     (optional) display the plots in a graphical window
+                        (you should have built afl-plot-ui to use this option)
 
 The program will put index.html and three PNG images in the output directory;
 you should be able to view it with any web browser of your choice.
@@ -99,21 +111,13 @@ if [ ! -d "$outputdir" ]; then
 
 fi
 
-rm -f "$outputdir/high_freq.png" "$outputdir/low_freq.png" "$outputdir/exec_speed.png"
+rm -f "$outputdir/high_freq.png" "$outputdir/low_freq.png" "$outputdir/exec_speed.png" "$outputdir/edges.png"
 mv -f "$outputdir/index.html" "$outputdir/index.html.orig" 2>/dev/null
 
-echo "[*] Generating plots..."
-
-(
-
-cat <<_EOF_
-set terminal png truecolor enhanced size 1000,300 butt
-
-set output '$outputdir/high_freq.png'
-
-set xdata time
-set timefmt '%s'
-set format x "%b %d\n%H:%M"
+GNUPLOT_SETUP="
+#set xdata time
+#set timefmt '%s'
+#set format x \"%b %d\n%H:%M\"
 set tics font 'small'
 unset mxtics
 unset mytics
@@ -127,34 +131,167 @@ set key outside
 set autoscale xfixmin
 set autoscale xfixmax
 
-set xlabel "all times in UTC" font "small"
+set xlabel \"relative time in seconds\" font \"small\"
+"
 
-set ytics auto
-plot '$inputdir/plot_data' using 1:4 with filledcurve x1 title 'total paths' linecolor rgb '#000000' fillstyle transparent solid 0.2 noborder, \\
-     '' using 1:3 with filledcurve x1 title 'current path' linecolor rgb '#f0f0f0' fillstyle transparent solid 0.5 noborder, \\
-     '' using 1:5 with lines title 'pending paths' linecolor rgb '#0090ff' linewidth 3, \\
+PLOT_HF="
+set terminal png truecolor enhanced size 1000,300 butt
+set output '$outputdir/high_freq.png'
+
+$GNUPLOT_SETUP
+
+plot '$inputdir/plot_data' using 1:4 with filledcurve x1 title 'corpus count' linecolor rgb '#000000' fillstyle transparent solid 0.2 noborder, \\
+     '' using 1:3 with filledcurve x1 title 'current fuzz item' linecolor rgb '#f0f0f0' fillstyle transparent solid 0.5 noborder, \\
+     '' using 1:5 with lines title 'pending items' linecolor rgb '#0090ff' linewidth 3, \\
      '' using 1:6 with lines title 'pending favs' linecolor rgb '#c00080' linewidth 3, \\
      '' using 1:2 with lines title 'cycles done' linecolor rgb '#c000f0' linewidth 3
+"
 
+PLOT_LF="
 set terminal png truecolor enhanced size 1000,200 butt
 set output '$outputdir/low_freq.png'
 
-set ytics 1
+$GNUPLOT_SETUP
+
 plot '$inputdir/plot_data' using 1:8 with filledcurve x1 title '' linecolor rgb '#c00080' fillstyle transparent solid 0.2 noborder, \\
      '' using 1:8 with lines title ' uniq crashes' linecolor rgb '#c00080' linewidth 3, \\
      '' using 1:9 with lines title 'uniq hangs' linecolor rgb '#c000f0' linewidth 3, \\
      '' using 1:10 with lines title 'levels' linecolor rgb '#0090ff' linewidth 3
+"
 
+PLOT_ES="
 set terminal png truecolor enhanced size 1000,200 butt
 set output '$outputdir/exec_speed.png'
 
-set ytics auto
+$GNUPLOT_SETUP
+
 plot '$inputdir/plot_data' using 1:11 with filledcurve x1 title '' linecolor rgb '#0090ff' fillstyle transparent solid 0.2 noborder, \\
      '$inputdir/plot_data' using 1:11 with lines title '    execs/sec' linecolor rgb '#0090ff' linewidth 3 smooth bezier;
+"
+
+PLOT_EG="
+set terminal png truecolor enhanced size 1000,300 butt
+set output '$outputdir/edges.png'
+
+$GNUPLOT_SETUP
+
+plot '$inputdir/plot_data' using 1:13 with lines title '        edges' linecolor rgb '#0090ff' linewidth 3
+"
+
+if [ "$#" = "2" ] && [ "$GRAPHICAL" = "1" ]; then
+
+afl-plot-ui -h > /dev/null 2>&1
+
+if [ "$?" != "0" ]; then
+
+cat 1>&2 <<_EOF_
+You do not seem to have the afl-plot-ui utility installed. If you have installed afl-plot-ui, make sure the afl-plot-ui executable is in your PATH.
+If you are still facing any problems, please open an issue at https://github.com/AFLplusplus/AFLplusplus/issues.
+
+No plots have been generated. Please rerun without the "-g" or "--graphical" flag to generate the plots.
+_EOF_
+
+exit 1
+
+fi
+
+rm -rf "$outputdir/.tmp"
+mkdir -p "$outputdir/.tmp"
+mkfifo "$outputdir/.tmp/win_ids" || exit 1
+
+afl-plot-ui > "$outputdir/.tmp/win_ids" &
+W_IDS=$(cat "$outputdir/.tmp/win_ids")
+
+rm -rf "$outputdir/.tmp"
+
+W_ID1=$(echo "$W_IDS" | head -n 1)
+W_ID2=$(echo "$W_IDS" | head -n 2 | tail -n 1)
+W_ID3=$(echo "$W_IDS" | head -n 3 | tail -n 1)
+W_ID4=$(echo "$W_IDS" | tail -n 1)
+
+echo "[*] Generating plots..."
+
+(
+
+cat << _EOF_
+
+$PLOT_HF
+set term x11 window "$W_ID3"
+set output
+replot
+pause mouse close
 
 _EOF_
 
-) | gnuplot 
+) | gnuplot 2> /dev/null &
+
+(
+
+cat << _EOF_
+
+$PLOT_LF
+set term x11 window "$W_ID4"
+set output
+replot
+pause mouse close
+
+_EOF_
+
+) | gnuplot 2> /dev/null &
+
+(
+
+cat << _EOF_
+
+$PLOT_ES
+set term x11 window "$W_ID2"
+set output
+replot
+pause mouse close
+
+_EOF_
+
+) | gnuplot 2> /dev/null &
+
+(
+
+cat << _EOF_
+
+$PLOT_EG
+set term x11 window "$W_ID1"
+set output
+replot
+pause mouse close
+
+_EOF_
+
+) | gnuplot 2> /dev/null &
+
+sleep 1
+
+else
+
+echo "[*] Generating plots..."
+
+(
+
+cat << _EOF_
+
+$PLOT_HF
+
+$PLOT_LF
+
+$PLOT_ES
+
+$PLOT_EG
+
+_EOF_
+
+) | gnuplot
+
+echo "[?] You can also use -g flag to view the plots in an GUI window, and interact with the plots (if you have built afl-plot-ui). Run \"afl-plot-h\" to know more."
+
+fi
 
 if [ ! -s "$outputdir/exec_speed.png" ]; then
 
@@ -172,6 +309,7 @@ cat >"$outputdir/index.html" <<_EOF_
 <tr><td><b>Generated on:</b></td><td>`date`</td></tr>
 </table>
 <p>
+<img src="edges.png" width=1000 height=300>
 <img src="high_freq.png" width=1000 height=300><p>
 <img src="low_freq.png" width=1000 height=200><p>
 <img src="exec_speed.png" width=1000 height=200>
@@ -183,7 +321,7 @@ _EOF_
 # sensitive, this seems like a reasonable trade-off.
 
 chmod 755 "$outputdir"
-chmod 644 "$outputdir/high_freq.png" "$outputdir/low_freq.png" "$outputdir/exec_speed.png" "$outputdir/index.html"
+chmod 644 "$outputdir/high_freq.png" "$outputdir/low_freq.png" "$outputdir/exec_speed.png" "$outputdir/edges.png" "$outputdir/index.html"
 
 echo "[+] All done - enjoy your charts!"
 

afl-system-config

@@ -6,28 +6,36 @@ test "$1" = "-h" -o "$1" = "-hh" && {
   echo
   echo afl-system-config has no command line options
   echo
-  echo afl-system reconfigures the system to a high performance fuzzing state
-  echo WARNING: this reduces the security of the system
+  echo afl-system-config reconfigures the system to a high performance fuzzing state.
+  echo "WARNING: this reduces the security of the system!"
   echo
-  exit 1
+  echo Note that there is also afl-persistent-config which sets additional permanent
+  echo configuration options.
+  exit 0
 }
 
 DONE=
 PLATFORM=`uname -s`
 echo This reconfigures the system to have a better fuzzing performance.
+echo "WARNING: this reduces the security of the system!"
+echo
 if [ '!' "$EUID" = 0 ] && [ '!' `id -u` = 0 ] ; then
 	echo "Warning: you need to be root to run this!"
 	# we do not exit as other mechanisms exist that allows to do this than
 	# being root. let the errors speak for themselves.
 fi
+sleep 1
 if [ "$PLATFORM" = "Linux" ] ; then
 {
-  sysctl -w kernel.core_pattern=core
+  sysctl -w kernel.core_uses_pid=0
+  # Arch Linux requires core_pattern to be empty :(
+  test -e /etc/arch-release && sysctl -w kernel.core_pattern=
+  test -e /etc/arch-release || sysctl -w kernel.core_pattern=core
   sysctl -w kernel.randomize_va_space=0
   sysctl -w kernel.sched_child_runs_first=1
   sysctl -w kernel.sched_autogroup_enabled=1
-  sysctl -w kernel.sched_migration_cost_ns=50000000
-  sysctl -w kernel.sched_latency_ns=250000000
+  sysctl -w kernel.sched_migration_cost_ns=50000000 2>/dev/null
+  sysctl -w kernel.sched_latency_ns=250000000 2>/dev/null
   echo never > /sys/kernel/mm/transparent_hugepage/enabled
   test -e /sys/devices/system/cpu/cpufreq/scaling_governor && echo performance | tee /sys/devices/system/cpu/cpufreq/scaling_governor
   test -e /sys/devices/system/cpu/cpufreq/policy0/scaling_governor && echo performance | tee /sys/devices/system/cpu/cpufreq/policy*/scaling_governor
@@ -35,12 +43,17 @@ if [ "$PLATFORM" = "Linux" ] ; then
   test -e /sys/devices/system/cpu/intel_pstate/no_turbo && echo 0 > /sys/devices/system/cpu/intel_pstate/no_turbo
   test -e /sys/devices/system/cpu/cpufreq/boost && echo 1 > /sys/devices/system/cpu/cpufreq/boost
   test -e /sys/devices/system/cpu/intel_pstate/max_perf_pct && echo 100 > /sys/devices/system/cpu/intel_pstate/max_perf_pct
+  test -n "$(which auditctl)" && auditctl -a never,task >/dev/null 2>&1
 } > /dev/null
   echo Settings applied.
+  echo
   dmesg | egrep -q 'nospectre_v2|spectre_v2=off' || {
     echo It is recommended to boot the kernel with lots of security off - if you are running a machine that is in a secured network - so set this:
-    echo '  /etc/default/grub: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"'
+    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
   DONE=1
 fi
 if [ "$PLATFORM" = "FreeBSD" ] ; then
@@ -49,48 +62,71 @@ if [ "$PLATFORM" = "FreeBSD" ] ; then
   sysctl kern.elf64.aslr.enable=0
 } > /dev/null
   echo Settings applied.
+  echo
+  cat <<EOF
+In order to suppress core file generation during fuzzing it is recommended to set
+me:\\
+	:coredumpsize=0:
+in the ~/.login_conf file for the user used for fuzzing.
+EOF
   echo It is recommended to boot the kernel with lots of security off - if you are running a machine that is in a secured network - so set this:
   echo '  sysctl hw.ibrs_disable=1'
   echo 'Setting kern.pmap.pg_ps_enabled=0 into /boot/loader.conf might be helpful too.'
+  echo
   DONE=1
 fi
 if [ "$PLATFORM" = "OpenBSD" ] ; then
-  echo
   echo 'System security features cannot be disabled on OpenBSD.'
+  echo
   DONE=1
 fi
 if [ "$PLATFORM" = "DragonFly" ] ; then
+  #/sbin/sysctl kern.corefile=/dev/null
+  #echo Settings applied.
+  cat <<EOF
+In order to suppress core file generation during fuzzing it is recommended to set
+me:\\
+	:coredumpsize=0:
+in the ~/.login_conf file for the user used for fuzzing.
+EOF
   echo
-  echo 'System security features cannot be disabled on DragonFly.'
   DONE=1
 fi
 if [ "$PLATFORM" = "NetBSD" ] ; then
 {
-  #echo It is recommended to enable unprivileged users to set cpu affinity
-  #echo to be able to use afl-gotcpu meaningfully.
   /sbin/sysctl -w security.models.extensions.user_set_cpu_affinity=1
 } > /dev/null
   echo Settings applied.
+  echo
   DONE=1
 fi
 if [ "$PLATFORM" = "Darwin" ] ; then
+  sysctl kern.sysv.shmmax=524288000
+  sysctl kern.sysv.shmmin=1
+  sysctl kern.sysv.shmseg=48
+  sysctl kern.sysv.shmall=131072000
+  echo Settings applied.
+  echo
   if [ $(launchctl list 2>/dev/null | grep -q '\.ReportCrash$') ] ; then
-    echo We unload the default crash reporter here
+    echo
+    echo Unloading the default crash reporter
     SL=/System/Library; PL=com.apple.ReportCrash
-    launchctl unload -w ${SL}/LaunchAgents/${PL}.plist
-    sudo launchctl unload -w ${SL}/LaunchDaemons/${PL}.Root.plist
-    echo Settings applied.
-  else
-    echo Nothing to do.
+    launchctl unload -w ${SL}/LaunchAgents/${PL}.plist >/dev/null 2>&1
+    sudo launchctl unload -w ${SL}/LaunchDaemons/${PL}.Root.plist >/dev/null 2>&1
+    echo
   fi
+  echo It is recommended to disable System Integration Protection for increased performance.
+  echo
   DONE=1
 fi
 if [ "$PLATFORM" = "Haiku" ] ; then
-  SETTINGS=~/config/settings/system/debug_server/settings
+  DEBUG_SERVER_DIR=~/config/settings/system/debug_server
+  [ ! -d ${DEBUG_SERVER_DIR} ] && mkdir -p ${DEBUG_SERVER_DIR}
+  SETTINGS=${DEBUG_SERVER_DIR}/settings
   [ -r ${SETTINGS} ] && grep -qE "default_action\s+kill" ${SETTINGS} && { echo "Nothing to do"; } || { \
-    echo We change the debug_server default_action from user to silenty kill; \
+    echo We change the debug_server default_action from user to silently kill; \
     [ ! -r ${SETTINGS} ] && echo "default_action kill" >${SETTINGS} || { mv ${SETTINGS} s.tmp; sed -e "s/default_action\s\s*user/default_action kill/" s.tmp > ${SETTINGS}; rm s.tmp; }; \
-    echo Settings applied.; \
+    echo Settings applied.; echo; \
   }
   DONE=1
 fi

afl-whatsup

@@ -6,13 +6,13 @@
 # Originally written by Michal Zalewski
 #
 # Copyright 2015 Google Inc. All rights reserved.
-# Copyright 2019-2020 AFLplusplus Project. All rights reserved.
+# Copyright 2019-2022 AFLplusplus Project. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at:
 #
-#   http://www.apache.org/licenses/LICENSE-2.0
+#   https://www.apache.org/licenses/LICENSE-2.0
 #
 # This tool summarizes the status of any locally-running synchronized
 # instances of afl-fuzz.
@@ -21,32 +21,41 @@
 echo "$0 status check tool for afl-fuzz by Michal Zalewski"
 echo
 test "$1" = "-h" -o "$1" = "-hh" && {
-  echo $0 [-s] output_directory
+  echo "Usage: $0 [-s] [-d] afl_output_directory"
   echo
   echo Options:
-  echo   -s  -  skip details and output summary results only
+  echo "  -s  -  skip details and output summary results only"
+  echo "  -d  -  include dead fuzzer stats"
   echo
   exit 1
 }
 
-if [ "$1" = "-s" ]; then
+unset SUMMARY_ONLY
+unset PROCESS_DEAD
 
-  SUMMARY_ONLY=1
-  DIR="$2"
+while [ "$1" = "-s" -o "$1" = "-d" ]; do
 
-else
+  if [ "$1" = "-s" ]; then
+    SUMMARY_ONLY=1
+  fi
 
-  unset SUMMARY_ONLY
-  DIR="$1"
+  if [ "$1" = "-d" ]; then
+    PROCESS_DEAD=1
+  fi
+  
+  shift
 
-fi
+done
+
+DIR="$1"
 
 if [ "$DIR" = "" ]; then
 
-  echo "Usage: $0 [ -s ] afl_sync_dir" 1>&2
+  echo "Usage: $0 [-s] [-d] afl_output_directory" 1>&2
   echo 1>&2
-  echo "The -s option causes the tool to skip all the per-fuzzer trivia and show" 1>&2
-  echo "just the summary results. See docs/parallel_fuzzing.md for additional tips." 1>&2
+  echo Options: 1>&2
+  echo "  -s  -  skip details and output summary results only" 1>&2
+  echo "  -d  -  include dead fuzzer stats" 1>&2
   echo 1>&2
   exit 1
 
@@ -82,9 +91,9 @@ TOTAL_CRASHES=0
 TOTAL_PFAV=0
 TOTAL_PENDING=0
 
-# Time since last path / crash / hang, formatted as string
+# Time since last find / crash / hang, formatted as string
 FMT_TIME="0 days 0 hours"
-FMT_PATH="${RED}none seen yet${NC}"
+FMT_FIND="${RED}none seen yet${NC}"
 FMT_CRASH="none seen yet"
 FMT_HANG="none seen yet"
 
@@ -126,14 +135,14 @@ fmt_duration()
 
 FIRST=true
 TOTAL_WCOP=
-TOTAL_LAST_PATH=0
+TOTAL_LAST_FIND=0
 
 for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
 
   sed 's/^command_line.*$/_skip:1/;s/[ ]*:[ ]*/="/;s/$/"/' "$i" >"$TMP"
   . "$TMP"
 
-  RUN_UNIX=$((CUR_TIME - start_time))
+  RUN_UNIX=$run_time
   RUN_DAYS=$((RUN_UNIX / 60 / 60 / 24))
   RUN_HRS=$(((RUN_UNIX / 60 / 60) % 24))
 
@@ -160,7 +169,13 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
     fi
 
     DEAD_CNT=$((DEAD_CNT + 1))
-    continue
+    last_find=0
+
+    if [ "$PROCESS_DEAD" = "" ]; then
+
+      continue
+
+    fi
 
   fi
 
@@ -168,17 +183,17 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
 
   EXEC_SEC=0
   test -z "$RUN_UNIX" -o "$RUN_UNIX" = 0 || EXEC_SEC=$((execs_done / RUN_UNIX))
-  PATH_PERC=$((cur_path * 100 / paths_total))
+  PATH_PERC=$((cur_item * 100 / corpus_count))
 
   TOTAL_TIME=$((TOTAL_TIME + RUN_UNIX))
   TOTAL_EPS=$((TOTAL_EPS + EXEC_SEC))
   TOTAL_EXECS=$((TOTAL_EXECS + execs_done))
-  TOTAL_CRASHES=$((TOTAL_CRASHES + unique_crashes))
+  TOTAL_CRASHES=$((TOTAL_CRASHES + saved_crashes))
   TOTAL_PENDING=$((TOTAL_PENDING + pending_total))
   TOTAL_PFAV=$((TOTAL_PFAV + pending_favs))
 
-  if [ "$last_path" -gt "$TOTAL_LAST_PATH" ]; then
-    TOTAL_LAST_PATH=$last_path
+  if [ "$last_find" -gt "$TOTAL_LAST_FIND" ]; then
+    TOTAL_LAST_FIND=$last_find
   fi
 
   if [ "$SUMMARY_ONLY" = "" ]; then
@@ -195,7 +210,7 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
       echo "  ${RED}slow execution, $EXEC_SEC execs/sec${NC}"
     fi
 
-    fmt_duration $last_path && FMT_PATH=$DUR_STRING
+    fmt_duration $last_find && FMT_FIND=$DUR_STRING
     fmt_duration $last_crash && FMT_CRASH=$DUR_STRING
     fmt_duration $last_hang && FMT_HANG=$DUR_STRING
     FMT_CWOP="not available"
@@ -205,7 +220,7 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
       test "$cycles_wo_finds" -gt 50 && FMT_CWOP="${RED}$cycles_wo_finds${NC}"
     }
 
-    echo "  last_path       : $FMT_PATH"
+    echo "  last_find       : $FMT_FIND"
     echo "  last_crash      : $FMT_CRASH"
     echo "  last_hang       : $FMT_HANG"
     echo "  cycles_wo_finds : $FMT_CWOP"
@@ -214,12 +229,12 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
     MEM_USAGE=$(ps aux | grep $fuzzer_pid | grep -v grep | awk '{print $4}')
 
     echo "  cpu usage $CPU_USAGE%, memory usage $MEM_USAGE%"
-    echo "  cycle $((cycles_done + 1)), lifetime speed $EXEC_SEC execs/sec, path $cur_path/$paths_total (${PATH_PERC}%)"
+    echo "  cycles $((cycles_done + 1)), lifetime speed $EXEC_SEC execs/sec, items $cur_item/$corpus_count (${PATH_PERC}%)"
 
-    if [ "$unique_crashes" = "0" ]; then
+    if [ "$saved_crashes" = "0" ]; then
       echo "  pending $pending_favs/$pending_total, coverage $bitmap_cvg, no crashes yet"
     else
-      echo "  pending $pending_favs/$pending_total, coverage $bitmap_cvg, crash count $unique_crashes (!)"
+      echo "  pending $pending_favs/$pending_total, coverage $bitmap_cvg, crashes saved $saved_crashes (!)"
     fi
 
     echo
@@ -228,7 +243,7 @@ for i in `find . -maxdepth 2 -iname fuzzer_stats | sort`; do
 
 done
 
-# Formatting for total time, time since last path, crash, and hang
+# Formatting for total time, time since last find, crash, and hang
 fmt_duration $((CUR_TIME - TOTAL_TIME)) && FMT_TIME=$DUR_STRING
 # Formatting for total execution
 FMT_EXECS="0 millions"
@@ -248,17 +263,28 @@ TOTAL_DAYS=$((TOTAL_TIME / 60 / 60 / 24))
 TOTAL_HRS=$(((TOTAL_TIME / 60 / 60) % 24))
 
 test -z "$TOTAL_WCOP" && TOTAL_WCOP="not available"
-fmt_duration $TOTAL_LAST_PATH && TOTAL_LAST_PATH=$DUR_STRING
+fmt_duration $TOTAL_LAST_FIND && TOTAL_LAST_FIND=$DUR_STRING
 
 test "$TOTAL_TIME" = "0" && TOTAL_TIME=1
 
+if [ "$PROCESS_DEAD" = "" ]; then
+
+  TXT="excluded from stats"
+
+else
+
+  TXT="included in stats"
+  ALIVE_CNT=$(($ALIVE_CNT - $DEAD_CNT))
+
+fi
+
 echo "Summary stats"
 echo "============="
 echo
 echo "       Fuzzers alive : $ALIVE_CNT"
 
 if [ ! "$DEAD_CNT" = "0" ]; then
-  echo "      Dead or remote : $DEAD_CNT (excluded from stats)"
+  echo "      Dead or remote : $DEAD_CNT ($TXT)"
 fi
 
 echo "      Total run time : $FMT_TIME"
@@ -267,15 +293,15 @@ echo "    Cumulative speed : $TOTAL_EPS execs/sec"
 if [ "$ALIVE_CNT" -gt "0" ]; then
   echo "       Average speed : $((TOTAL_EPS / ALIVE_CNT)) execs/sec"
 fi
-echo "       Pending paths : $TOTAL_PFAV faves, $TOTAL_PENDING total"
+echo "       Pending items : $TOTAL_PFAV faves, $TOTAL_PENDING total"
 
 if [ "$ALIVE_CNT" -gt "1" ]; then
   echo "  Pending per fuzzer : $((TOTAL_PFAV/ALIVE_CNT)) faves, $((TOTAL_PENDING/ALIVE_CNT)) total (on average)"
 fi
 
-echo "       Crashes found : $TOTAL_CRASHES locally unique"
+echo "       Crashes saved : $TOTAL_CRASHES"
 echo "Cycles without finds : $TOTAL_WCOP"
-echo "  Time without finds : $TOTAL_LAST_PATH"
+echo "  Time without finds : $TOTAL_LAST_FIND"
 echo
 
 exit 0

coresight_mode/.gitignore

@@ -0,0 +1,2 @@
+.local
+glibc*

coresight_mode/GNUmakefile

@@ -0,0 +1,62 @@
+#!/usr/bin/env make
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2021 Ricerca Security, Inc. All rights reserved.
+
+SHELL:=bash
+PREFIX?=$(shell pwd)/.local
+
+CS_TRACE:=coresight-trace
+
+PATCHELF?=$(PREFIX)/bin/patchelf
+
+PATCH_DIR:=patches
+
+GLIBC_VER:=2.33
+GLIBC_NAME:=glibc-$(GLIBC_VER)
+GLIBC_URL_BASE:=http://ftp.gnu.org/gnu/glibc
+GLIBC_LDSO?=$(PREFIX)/lib/ld-linux-aarch64.so.1
+
+OUTPUT?="$(TARGET).patched"
+
+all: build
+
+build:
+	git submodule update --init --recursive $(CS_TRACE)
+	$(MAKE) -C $(CS_TRACE)
+	cp $(CS_TRACE)/cs-proxy ../afl-cs-proxy
+
+patch: | $(PATCHELF) $(GLIBC_LDSO)
+	@if test -z "$(TARGET)"; then echo "TARGET is not set"; exit 1; fi
+	$(PATCHELF) \
+	  --set-interpreter $(GLIBC_LDSO) \
+	  --set-rpath $(dir $(GLIBC_LDSO)) \
+	  --output $(OUTPUT) \
+	  $(TARGET)
+
+$(PATCHELF): patchelf
+	git submodule update --init $<
+	cd $< && \
+	  ./bootstrap.sh && \
+	  ./configure --prefix=$(PREFIX) && \
+	  $(MAKE) && \
+	  $(MAKE) check && \
+	  $(MAKE) install
+
+$(GLIBC_LDSO): | $(GLIBC_NAME).tar.xz
+	tar -xf $(GLIBC_NAME).tar.xz
+	for file in $(shell find $(PATCH_DIR) -maxdepth 1 -type f); do \
+	  patch -p1 < $$file ; \
+	done
+	mkdir -p $(GLIBC_NAME)/build
+	cd $(GLIBC_NAME)/build && \
+	  ../configure --prefix=$(PREFIX) && \
+	  $(MAKE) && \
+	  $(MAKE) install
+
+$(GLIBC_NAME).tar.xz:
+	wget -O $@ $(GLIBC_URL_BASE)/$@
+
+clean:
+	$(MAKE) -C $(CS_TRACE) clean
+
+.PHONY: all build patch clean

coresight_mode/Makefile

@@ -0,0 +1,21 @@
+#!/usr/bin/env make
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2021 Ricerca Security, Inc. All rights reserved.
+
+all:
+	@echo trying to use GNU make...
+	@gmake all || echo please install GNUmake
+
+build:
+	@echo trying to use GNU make...
+	@gmake build || echo please install GNUmake
+
+patch:
+	@echo trying to use GNU make...
+	@gmake patch || echo please install GNUmake
+
+clean:
+	@echo trying to use GNU make...
+	@gmake clean || echo please install GNUmake
+
+.PHONY: all build patch clean

coresight_mode/README.md

@@ -0,0 +1,70 @@
+# AFL++ CoreSight mode
+
+CoreSight mode enables binary-only fuzzing on ARM64 Linux using CoreSight (ARM's hardware tracing technology).
+
+NOTE: CoreSight mode is in the early development stage. Not applicable for production use.
+Currently the following hardware boards are supported:
+* NVIDIA Jetson TX2 (NVIDIA Parker)
+* NVIDIA Jetson Nano (NVIDIA Tegra X1)
+* GIGABYTE R181-T90 (Marvell ThunderX2 CN99XX)
+
+## Getting started
+
+Please read the [RICSec/coresight-trace README](https://github.com/RICSecLab/coresight-trace/blob/master/README.md) and check the prerequisites (capstone) before getting started.
+
+CoreSight mode supports the AFL++ fork server mode to reduce `exec` system call
+overhead. To support it for binary-only fuzzing, it needs to modify the target
+ELF binary to re-link to the patched glibc. We employ this design from
+[PTrix](https://github.com/junxzm1990/afl-pt).
+
+Check out all the git submodules in the `cs_mode` directory:
+
+```bash
+git submodule update --init --recursive
+```
+
+### Build coresight-trace
+
+There are some notes on building coresight-trace. Refer to the [README](https://github.com/RICSecLab/coresight-trace/blob/master/README.md) for the details. Run make in the `cs_mode` directory:
+
+```bash
+make build
+```
+
+Make sure `cs-proxy` is placed in the AFL++ root directory as `afl-cs-proxy`.
+
+### Patch COTS binary
+
+The fork server mode requires patchelf and the patched glibc. The dependency build can be done by just run make:
+
+```bash
+make patch TARGET=$BIN
+```
+
+The above make command builds and installs the dependencies to `$PREFIX` (default to `$PWD/.local`) at the first time. Then, it runs `patchelf` to `$BIN` with output `$OUTPUT` (`$BIN.patched` by default).
+
+### Run afl-fuzz
+
+Run `afl-fuzz` with `-A` option to use CoreSight mode.
+
+```bash
+sudo afl-fuzz -A -i input -o output -- $OUTPUT @@
+```
+
+## Environment Variables
+
+There are AFL++ CoreSight mode-specific environment variables for run-time configuration.
+
+* `AFL_CS_CUSTOM_BIN` overrides the proxy application path. `afl-cs-proxy` will be used if not defined.
+
+* `AFLCS_COV` specifies coverage type on CoreSight trace decoding. `edge` and `path` is supported. The default value is `edge`.
+* `AFLCS_UDMABUF` is the u-dma-buf device number used to store trace data in the DMA region. The default value is `0`.
+
+## TODO List
+
+* Eliminate modified glibc dependency
+* Support parallel fuzzing
+
+## Acknowledgements
+
+This project has received funding from the Acquisition, Technology & Logistics Agency (ATLA) under the National Security Technology Research Promotion Fund 2021 (JPJ004596).

coresight_mode/patches/0001-Add-AFL-forkserver.patch

@@ -0,0 +1,117 @@
+diff --git a/glibc-2.33/elf/rtld.c b/glibc-2.33/elf/rtld.c
+index 596b6ac3..2ee270d4 100644
+--- a/glibc-2.33/elf/rtld.c
++++ b/glibc-2.33/elf/rtld.c
+@@ -169,6 +169,99 @@ uintptr_t __pointer_chk_guard_local
+ strong_alias (__pointer_chk_guard_local, __pointer_chk_guard)
+ #endif
+ 
++#define AFLCS_RTLD 1
++
++#if AFLCS_RTLD
++
++#include <sys/shm.h>
++#include <sys/types.h>
++#include <sys/wait.h>
++#include <dlfcn.h>
++#include <signal.h>
++
++#include <asm/unistd.h>
++#include <unistd.h>
++
++#define FORKSRV_FD 198
++
++#define AFLCS_ENABLE "__AFLCS_ENABLE"
++
++/* We use this additional AFLCS_# AFLCS_#+1 pair to communicate with proxy */
++#define AFLCS_FORKSRV_FD (FORKSRV_FD - 3)
++#define AFLCS_RTLD_SNIPPET do { __cs_start_forkserver(); } while(0)
++
++/* Fork server logic, invoked before we return from _dl_start. */
++
++static void __cs_start_forkserver(void) {
++  int status;
++  pid_t child_pid;
++  static char tmp[4] = {0, 0, 0, 0};
++
++  if (!getenv(AFLCS_ENABLE)) {
++    return;
++  }
++
++  if (write(AFLCS_FORKSRV_FD + 1, tmp, 4) != 4) {
++    _exit(-1);
++  }
++
++  /* All right, let's await orders... */
++  while (1) {
++    /* Whoops, parent dead? */
++    if (read(AFLCS_FORKSRV_FD, tmp, 4) != 4) {
++      _exit(1);
++    }
++
++    child_pid = INLINE_SYSCALL(clone, 5,
++        CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID | SIGCHLD, 0,
++        NULL, NULL, &THREAD_SELF->tid);
++    if (child_pid < 0) {
++      _exit(4);
++    }
++    if (!child_pid) {
++      /* Child process. Wait for parent start tracing */
++      kill(getpid(), SIGSTOP);
++      /* Close descriptors and run free. */
++      close(AFLCS_FORKSRV_FD);
++      close(AFLCS_FORKSRV_FD + 1);
++      return;
++    }
++
++    /* Parent. */
++    if (write(AFLCS_FORKSRV_FD + 1, &child_pid, 4) != 4) {
++      _exit(5);
++    }
++
++    /* Wait until SIGCONT is signaled. */
++    if (waitpid(child_pid, &status, WCONTINUED) < 0) {
++      _exit(6);
++    }
++    if (!WIFCONTINUED(status)) {
++      /* Relay status to proxy. */
++      if (write(AFLCS_FORKSRV_FD + 1, &status, 4) != 4) {
++        _exit(7);
++      }
++      continue;
++    }
++    while (1) {
++      /* Get status. */
++      if (waitpid(child_pid, &status, WUNTRACED) < 0) {
++        _exit(8);
++      }
++      /* Relay status to proxy. */
++      if (write(AFLCS_FORKSRV_FD + 1, &status, 4) != 4) {
++        _exit(9);
++      }
++      if (!(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP)) {
++        /* The child process is exited. */
++        break;
++      }
++    }
++  }
++}
++
++#endif /* AFLCS_RTLD */
++
+ /* Check that AT_SECURE=0, or that the passed name does not contain
+    directories and is not overly long.  Reject empty names
+    unconditionally.  */
+@@ -588,6 +681,12 @@ _dl_start (void *arg)
+ # define ELF_MACHINE_START_ADDRESS(map, start) (start)
+ #endif
+ 
++    /* AFL-CS-START */
++#if AFLCS_RTLD
++    AFLCS_RTLD_SNIPPET;
++#endif
++    /* AFL-CS-END */
++
+     return ELF_MACHINE_START_ADDRESS (GL(dl_ns)[LM_ID_BASE]._ns_loaded, entry);
+   }
+ }

custom_mutators/Android.bp

@@ -10,6 +10,8 @@ cc_library_shared {
     "-fPIC",
     "-fpermissive",
     "-std=c++11",
+    "-Wno-unused-parameter",
+    "-Wno-unused-variable",
   ],
 
   srcs: [
@@ -77,6 +79,8 @@ cc_library_shared {
     "-O0",
     "-funroll-loops",
     "-fPIC",
+    "-Wno-unused-parameter",
+    "-Wno-unused-function",
   ],
 
   srcs: [
@@ -99,6 +103,8 @@ cc_library_shared {
     "-O0",
     "-funroll-loops",
     "-fPIC",
+    "-Wno-unused-parameter",
+    "-Wno-pointer-sign",
   ],
 
   srcs: [

custom_mutators/README.md

@@ -1,12 +1,21 @@
 # Custom Mutators
 
-Custom mutators enhance and alter the mutation strategies of afl++.
+Custom mutators enhance and alter the mutation strategies of AFL++.
 For further information and documentation on how to write your own, read [the docs](../docs/custom_mutators.md).
 
-## The afl++ Grammar Mutator
+## Examples
 
-If you use git to clone afl++, then the following will incorporate our
+The `./examples` folder contains examples for custom mutators in python and C.
+
+## Rust
+
+In `./rust`, you will find rust bindings, including a simple example in `./rust/example` and an example for structured fuzzing, based on lain, in`./rust/example_lain`.
+
+## The AFL++ Grammar Mutator
+
+If you use git to clone AFL++, then the following will incorporate our
 excellent grammar custom mutator:
+
 ```sh
 git submodule update --init
 ```
@@ -32,7 +41,7 @@ Multiple custom mutators can be used by separating their paths with `:` in the e
 
 ### Superion Mutators
 
-Adrian Tiron ported the Superion grammar fuzzer to afl++, it is WIP and
+Adrian Tiron ported the Superion grammar fuzzer to AFL++, it is WIP and
 requires cmake (among other things):
 [https://github.com/adrian-rt/superion-mutator](https://github.com/adrian-rt/superion-mutator)
 
@@ -44,5 +53,8 @@ transforms protobuf raw:
 https://github.com/bruce30262/libprotobuf-mutator_fuzzing_learning/tree/master/4_libprotobuf_aflpp_custom_mutator
 
 has a transform function you need to fill for your protobuf format, however
-needs to be ported to the updated afl++ custom mutator API (not much work):
+needs to be ported to the updated AFL++ custom mutator API (not much work):
 https://github.com/thebabush/afl-libprotobuf-mutator
+
+same as above but is for current AFL++:
+https://github.com/P1umer/AFLplusplus-protobuf-mutator

custom_mutators/examples/XmlMutatorMin.py

@@ -12,12 +12,13 @@ import random, re, io
 # The XmlMutatorMin class #
 ###########################
 
+
 class XmlMutatorMin:
 
     """
-        Optionals parameters:
-            seed        Seed used by the PRNG (default: "RANDOM")
-            verbose     Verbosity (default: False)
+    Optionals parameters:
+        seed        Seed used by the PRNG (default: "RANDOM")
+        verbose     Verbosity (default: False)
     """
 
     def __init__(self, seed="RANDOM", verbose=False):
@@ -41,7 +42,12 @@ class XmlMutatorMin:
         self.tree = None
 
         # High-level mutators (no database needed)
-        hl_mutators_delete = ["del_node_and_children", "del_node_but_children", "del_attribute", "del_content"]  # Delete items
+        hl_mutators_delete = [
+            "del_node_and_children",
+            "del_node_but_children",
+            "del_attribute",
+            "del_content",
+        ]  # Delete items
         hl_mutators_fuzz = ["fuzz_attribute"]  # Randomly change attribute values
 
         # Exposed mutators
@@ -74,7 +80,9 @@ class XmlMutatorMin:
 
         """ Serialize a XML document. Basic wrapper around lxml.tostring() """
 
-        return ET.tostring(tree, with_tail=False, xml_declaration=True, encoding=tree.docinfo.encoding)
+        return ET.tostring(
+            tree, with_tail=False, xml_declaration=True, encoding=tree.docinfo.encoding
+        )
 
     def __ver(self, version):
 
@@ -161,7 +169,7 @@ class XmlMutatorMin:
             # Randomly pick one the function calls
             (func, args) = random.choice(l)
             # Split by "," and randomly pick one of the arguments
-            value = random.choice(args.split(','))
+            value = random.choice(args.split(","))
             # Remove superfluous characters
             unclean_value = value
             value = value.strip(" ").strip("'")
@@ -170,49 +178,49 @@ class XmlMutatorMin:
             value = attrib_value
 
         # For each type, define some possible replacement values
-        choices_number =    ( \
-                                "0", \
-                                "11111", \
-                                "-128", \
-                                "2", \
-                                "-1", \
-                                "1/3", \
-                                "42/0", \
-                                "1094861636 idiv 1.0", \
-                                "-1123329771506872 idiv 3.8", \
-                                "17=$numericRTF", \
-                                str(3 + random.randrange(0, 100)), \
-                            )
+        choices_number = (
+            "0",
+            "11111",
+            "-128",
+            "2",
+            "-1",
+            "1/3",
+            "42/0",
+            "1094861636 idiv 1.0",
+            "-1123329771506872 idiv 3.8",
+            "17=$numericRTF",
+            str(3 + random.randrange(0, 100)),
+        )
 
-        choices_letter =    ( \
-                                "P" * (25 * random.randrange(1, 100)), \
-                                "%s%s%s%s%s%s", \
-                                "foobar", \
-                            )
+        choices_letter = (
+            "P" * (25 * random.randrange(1, 100)),
+            "%s%s%s%s%s%s",
+            "foobar",
+        )
 
-        choices_alnum =     ( \
-                                "Abc123", \
-                                "020F0302020204030204", \
-                                "020F0302020204030204" * (random.randrange(5, 20)), \
-                            )
+        choices_alnum = (
+            "Abc123",
+            "020F0302020204030204",
+            "020F0302020204030204" * (random.randrange(5, 20)),
+        )
 
         # Fuzz the value
-        if random.choice((True,False)) and value == "":
+        if random.choice((True, False)) and value == "":
 
             # Empty
             new_value = value
 
-        elif random.choice((True,False)) and value.isdigit():
+        elif random.choice((True, False)) and value.isdigit():
 
             # Numbers
             new_value = random.choice(choices_number)
 
-        elif random.choice((True,False)) and value.isalpha():
+        elif random.choice((True, False)) and value.isalpha():
 
             # Letters
             new_value = random.choice(choices_letter)
 
-        elif random.choice((True,False)) and value.isalnum():
+        elif random.choice((True, False)) and value.isalnum():
 
             # Alphanumeric
             new_value = random.choice(choices_alnum)
@@ -232,22 +240,25 @@ class XmlMutatorMin:
 
         # Log something
         if self.verbose:
-            print("Fuzzing attribute #%i '%s' of tag #%i '%s'" % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag))
+            print(
+                "Fuzzing attribute #%i '%s' of tag #%i '%s'"
+                % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag)
+            )
 
         # Modify the attribute
         rand_elem.set(rand_attrib, new_value.decode("utf-8"))
 
     def __del_node_and_children(self):
 
-        """ High-level minimizing mutator
-            Delete a random node and its children (i.e. delete a random tree) """
+        """High-level minimizing mutator
+        Delete a random node and its children (i.e. delete a random tree)"""
 
         self.__del_node(True)
 
     def __del_node_but_children(self):
 
-        """ High-level minimizing mutator
-            Delete a random node but its children (i.e. link them to the parent of the deleted node) """
+        """High-level minimizing mutator
+        Delete a random node but its children (i.e. link them to the parent of the deleted node)"""
 
         self.__del_node(False)
 
@@ -270,7 +281,10 @@ class XmlMutatorMin:
         # Log something
         if self.verbose:
             but_or_and = "and" if delete_children else "but"
-            print("Deleting tag #%i '%s' %s its children" % (rand_elem_id, rand_elem.tag, but_or_and))
+            print(
+                "Deleting tag #%i '%s' %s its children"
+                % (rand_elem_id, rand_elem.tag, but_or_and)
+            )
 
         if delete_children is False:
             # Link children of the random (soon to be deleted) node to its parent
@@ -282,8 +296,8 @@ class XmlMutatorMin:
 
     def __del_content(self):
 
-        """ High-level minimizing mutator
-            Delete the attributes and children of a random node """
+        """High-level minimizing mutator
+        Delete the attributes and children of a random node"""
 
         # Select a node to modify
         (rand_elem_id, rand_elem) = self.__pick_element()
@@ -297,8 +311,8 @@ class XmlMutatorMin:
 
     def __del_attribute(self):
 
-        """ High-level minimizing mutator
-            Delete a random attribute from a random node """
+        """High-level minimizing mutator
+        Delete a random attribute from a random node"""
 
         # Select a node to modify
         (rand_elem_id, rand_elem) = self.__pick_element()
@@ -318,7 +332,10 @@ class XmlMutatorMin:
 
         # Log something
         if self.verbose:
-            print("Deleting attribute #%i '%s' of tag #%i '%s'" % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag))
+            print(
+                "Deleting attribute #%i '%s' of tag #%i '%s'"
+                % (rand_attrib_id, rand_attrib, rand_elem_id, rand_elem.tag)
+            )
 
         # Delete the attribute
         rand_elem.attrib.pop(rand_attrib)
@@ -329,4 +346,3 @@ class XmlMutatorMin:
 
         # High-level mutation
         self.__exec_among(self, self.hl_mutators_all, min, max)
-

custom_mutators/examples/common.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # encoding: utf-8
-'''
+"""
 Module containing functions shared between multiple AFL modules
 
 @author:     Christian Holler (:decoder)
@@ -12,7 +12,7 @@ License, v. 2.0. If a copy of the MPL was not distributed with this
 file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 @contact:    choller@mozilla.com
-'''
+"""
 
 from __future__ import print_function
 import random
@@ -23,18 +23,18 @@ import re
 def randel(l):
     if not l:
         return None
-    return l[random.randint(0, len(l)-1)]
+    return l[random.randint(0, len(l) - 1)]
 
 
 def randel_pop(l):
     if not l:
         return None
-    return l.pop(random.randint(0, len(l)-1))
+    return l.pop(random.randint(0, len(l) - 1))
 
 
 def write_exc_example(data, exc):
-    exc_name = re.sub(r'[^a-zA-Z0-9]', '_', repr(exc))
+    exc_name = re.sub(r"[^a-zA-Z0-9]", "_", repr(exc))
 
     if not os.path.exists(exc_name):
-        with open(exc_name, 'w') as f:
+        with open(exc_name, "w") as f:
             f.write(data)

custom_mutators/examples/example.c

@@ -349,12 +349,15 @@ uint8_t afl_custom_queue_get(my_mutator_t *data, const uint8_t *filename) {
  * @param data pointer returned in afl_custom_init for this fuzz case
  * @param filename_new_queue File name of the new queue entry
  * @param filename_orig_queue File name of the original queue entry
+ * @return if the file contents was modified return 1 (True), 0 (False)
+ *         otherwise
  */
-void afl_custom_queue_new_entry(my_mutator_t * data,
-                                const uint8_t *filename_new_queue,
-                                const uint8_t *filename_orig_queue) {
+uint8_t afl_custom_queue_new_entry(my_mutator_t * data,
+                                   const uint8_t *filename_new_queue,
+                                   const uint8_t *filename_orig_queue) {
 
   /* Additional analysis on the original or new test case */
+  return 0;
 
 }
 

custom_mutators/examples/example.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # encoding: utf-8
-'''
+"""
 Example Python Module for AFLFuzz
 
 @author:     Christian Holler (:decoder)
@@ -12,7 +12,7 @@ License, v. 2.0. If a copy of the MPL was not distributed with this
 file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 @contact:    choller@mozilla.com
-'''
+"""
 
 import random
 
@@ -26,12 +26,12 @@ COMMANDS = [
 
 
 def init(seed):
-    '''
+    """
     Called once when AFLFuzz starts up. Used to seed our RNG.
 
     @type seed: int
     @param seed: A 32-bit random value
-    '''
+    """
     random.seed(seed)
 
 
@@ -40,7 +40,7 @@ def deinit():
 
 
 def fuzz(buf, add_buf, max_size):
-    '''
+    """
     Called per fuzzing iteration.
 
     @type buf: bytearray
@@ -55,13 +55,14 @@ def fuzz(buf, add_buf, max_size):
 
     @rtype: bytearray
     @return: A new bytearray containing the mutated data
-    '''
+    """
     ret = bytearray(100)
 
     ret[:3] = random.choice(COMMANDS)
 
     return ret
 
+
 # Uncomment and implement the following methods if you want to use a custom
 # trimming algorithm. See also the documentation for a better API description.
 

custom_mutators/examples/post_library_gif.so.c

@@ -45,6 +45,7 @@
    1) If you don't want to modify the test case, simply set `*out_buf = in_buf`
       and return the original `len`.
 
+   NOTE: the following is currently NOT true, we abort in this case!
    2) If you want to skip this test case altogether and have AFL generate a
       new one, return 0 or set `*out_buf = NULL`.
       Use this sparingly - it's faster than running the target program
@@ -53,14 +54,14 @@
    3) If you want to modify the test case, allocate an appropriately-sized
       buffer, move the data into that buffer, make the necessary changes, and
       then return the new pointer as out_buf. Return an appropriate len
-   afterwards.
+      afterwards.
 
       Note that the buffer will *not* be freed for you. To avoid memory leaks,
       you need to free it or reuse it on subsequent calls (as shown below).
 
       *** Feel free to reuse the original 'in_buf' BUFFER and return it. ***
 
-    Aight. The example below shows a simple postprocessor that tries to make
+    Alright. The example below shows a simple postprocessor that tries to make
     sure that all input files start with "GIF89a".
 
     PS. If you don't like C, you can try out the unix-based wrapper from

custom_mutators/examples/simple-chunk-replace.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # encoding: utf-8
-'''
+"""
 Simple Chunk Cross-Over Replacement Module for AFLFuzz
 
 @author:     Christian Holler (:decoder)
@@ -12,24 +12,24 @@ License, v. 2.0. If a copy of the MPL was not distributed with this
 file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 @contact:    choller@mozilla.com
-'''
+"""
 
 import random
 
 
 def init(seed):
-    '''
+    """
     Called once when AFLFuzz starts up. Used to seed our RNG.
 
     @type seed: int
     @param seed: A 32-bit random value
-    '''
+    """
     # Seed our RNG
     random.seed(seed)
 
 
 def fuzz(buf, add_buf, max_size):
-    '''
+    """
     Called per fuzzing iteration.
 
     @type buf: bytearray
@@ -44,7 +44,7 @@ def fuzz(buf, add_buf, max_size):
 
     @rtype: bytearray
     @return: A new bytearray containing the mutated data
-    '''
+    """
     # Make a copy of our input buffer for returning
     ret = bytearray(buf)
 
@@ -58,7 +58,9 @@ def fuzz(buf, add_buf, max_size):
     rand_dst_idx = random.randint(0, len(buf))
 
     # Make the chunk replacement
-    ret[rand_dst_idx:rand_dst_idx + fragment_len] = add_buf[rand_src_idx:rand_src_idx + fragment_len]
+    ret[rand_dst_idx : rand_dst_idx + fragment_len] = add_buf[
+        rand_src_idx : rand_src_idx + fragment_len
+    ]
 
     # Return data
     return ret

custom_mutators/examples/wrapper_afl_min.py

@@ -27,7 +27,7 @@ def log(text):
 
 def init(seed):
     """
-          Called once when AFL starts up. Seed is used to identify the AFL instance in log files
+    Called once when AFL starts up. Seed is used to identify the AFL instance in log files
     """
 
     global __mutator__
@@ -72,7 +72,10 @@ def fuzz(buf, add_buf, max_size):
     if via_buffer:
         try:
             __mutator__.init_from_string(buf_str)
-            log("fuzz(): Mutator successfully initialized with AFL buffer (%d bytes)" % len(buf_str))
+            log(
+                "fuzz(): Mutator successfully initialized with AFL buffer (%d bytes)"
+                % len(buf_str)
+            )
         except Exception:
             via_buffer = False
             log("fuzz(): Can't initialize mutator with AFL buffer")
@@ -104,7 +107,7 @@ def fuzz(buf, add_buf, max_size):
 
 
 # Main (for debug)
-if __name__ == '__main__':
+if __name__ == "__main__":
 
     __log__ = True
     __log_file__ = "/dev/stdout"
@@ -112,7 +115,9 @@ if __name__ == '__main__':
 
     init(__seed__)
 
-    in_1 = bytearray("<foo ddd='eeee'>ffff<a b='c' d='456' eee='ffffff'>zzzzzzzzzzzz</a><b yyy='YYY' zzz='ZZZ'></b></foo>")
+    in_1 = bytearray(
+        "<foo ddd='eeee'>ffff<a b='c' d='456' eee='ffffff'>zzzzzzzzzzzz</a><b yyy='YYY' zzz='ZZZ'></b></foo>"
+    )
     in_2 = bytearray("<abc abc123='456' abcCBA='ppppppppppppppppppppppppppppp'/>")
     out = fuzz(in_1, in_2)
     print(out)

custom_mutators/gramatron/JSONC_VERSION

@@ -0,0 +1 @@
+af8dd4a307e7b837f9fa2959549548ace4afe08b

custom_mutators/gramatron/README.md

@@ -0,0 +1,49 @@
+# GramaTron
+
+GramaTron is a coverage-guided fuzzer that uses grammar automatons to perform
+grammar-aware fuzzing.  Technical details about our framework are available in
+the [ISSTA'21 paper](https://nebelwelt.net/files/21ISSTA.pdf). The artifact to
+reproduce the experiments presented in the paper are present in `artifact/`.
+Instructions to run a sample campaign and incorporate new grammars is presented
+below:
+
+## Compiling
+
+Execute `./build_gramatron_mutator.sh`.
+
+## Running
+
+You have to set the grammar file to use with `GRAMATRON_AUTOMATION`:
+
+```
+export AFL_DISABLE_TRIM=1
+export AFL_CUSTOM_MUTATOR_ONLY=1
+export AFL_CUSTOM_MUTATOR_LIBRARY=./gramatron.so
+export GRAMATRON_AUTOMATION=grammars/ruby/source_automata.json
+afl-fuzz -i in -o out -- ./target
+```
+
+## Adding and testing a new grammar
+
+- Specify in a JSON format for CFG. Examples are correspond `source.json` files.
+- Run the automaton generation script (in `src/gramfuzz-mutator/preprocess`)
+  which will place the generated automaton in the same folder.
+
+  ```
+  ./preprocess/prep_automaton.sh <grammar_file> <start_symbol> [stack_limit]
+
+  E.g., ./preprocess/prep_automaton.sh ~/grammars/ruby/source.json PROGRAM
+  ```
+
+- If the grammar has no self-embedding rules, then you do not need to pass the
+  stack limit parameter. However, if it does have self-embedding rules, then you
+  need to pass the stack limit parameter. We recommend starting with `5` and
+  then increasing it if you need more complexity.
+- To sanity-check that the automaton is generating inputs as expected, you can
+  use the `test` binary housed in `src/gramfuzz-mutator`.
+
+  ```
+  ./test SanityCheck <automaton_file>
+
+  E.g., ./test SanityCheck ~/grammars/ruby/source_automata.json
+  ```

custom_mutators/gramatron/build_gramatron_mutator.sh

@@ -0,0 +1,149 @@
+#!/bin/sh
+#
+# american fuzzy lop++ - gramatron build script
+# ------------------------------------------------
+#
+# Originally written by Nathan Voss <njvoss99@gmail.com>
+#
+# Adapted from code by Andrew Griffiths <agriffiths@google.com> and
+#                      Michal Zalewski
+#
+# Adapted for AFLplusplus by Dominik Maier <mail@dmnk.co>
+#
+# Copyright 2017 Battelle Memorial Institute. All rights reserved.
+# Copyright 2019-2022 AFLplusplus Project. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at:
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# This script downloads, patches, and builds a version of Unicorn with
+# minor tweaks to allow Unicorn-emulated binaries to be run under
+# afl-fuzz.
+#
+# The modifications reside in patches/*. The standalone Unicorn library
+# will be written to /usr/lib/libunicornafl.so, and the Python bindings
+# will be installed system-wide.
+#
+# You must make sure that Unicorn Engine is not already installed before
+# running this script. If it is, please uninstall it first.
+
+JSONC_VERSION="$(cat ./JSONC_VERSION)"
+JSONC_REPO="https://github.com/json-c/json-c"
+
+echo "================================================="
+echo "Gramatron Mutator build script"
+echo "================================================="
+echo
+
+echo "[*] Performing basic sanity checks..."
+
+PLT=`uname -s`
+
+if [ ! -f "../../config.h" ]; then
+
+  echo "[-] Error: key files not found - wrong working directory?"
+  exit 1
+
+fi
+
+if [ ! -f "../../src/afl-performance.o" ]; then
+
+  echo "[-] Error: you must build afl-fuzz first and not do a \"make clean\""
+  exit 1
+
+fi
+
+PYTHONBIN=`command -v python3 || command -v python || command -v python2 || echo python3`
+MAKECMD=make
+TARCMD=tar
+
+if [ "$PLT" = "Darwin" ]; then
+  CORES=`sysctl -n hw.ncpu`
+  TARCMD=tar
+fi
+
+if [ "$PLT" = "FreeBSD" ]; then
+  MAKECMD=gmake
+  CORES=`sysctl -n hw.ncpu`
+  TARCMD=gtar
+fi
+
+if [ "$PLT" = "NetBSD" ] || [ "$PLT" = "OpenBSD" ]; then
+  MAKECMD=gmake
+  CORES=`sysctl -n hw.ncpu`
+  TARCMD=gtar
+fi
+
+PREREQ_NOTFOUND=
+for i in git $MAKECMD $TARCMD; do
+
+  T=`command -v "$i" 2>/dev/null`
+
+  if [ "$T" = "" ]; then
+
+    echo "[-] Error: '$i' not found. Run 'sudo apt-get install $i' or similar."
+    PREREQ_NOTFOUND=1
+
+  fi
+
+done
+
+test -z "$CC" && export CC=cc
+
+if echo "$CC" | grep -qF /afl-; then
+
+  echo "[-] Error: do not use afl-gcc or afl-clang to compile this tool."
+  PREREQ_NOTFOUND=1
+
+fi
+
+if [ "$PREREQ_NOTFOUND" = "1" ]; then
+  exit 1
+fi
+
+echo "[+] All checks passed!"
+
+echo "[*] Making sure json-c is checked out"
+
+git status 1>/dev/null 2>/dev/null
+if [ $? -eq 0 ]; then
+  echo "[*] initializing json-c submodule"
+  git submodule init || exit 1
+  git submodule update ./json-c 2>/dev/null # ignore errors
+else
+  echo "[*] cloning json-c"
+  test -d json-c || {
+    CNT=1
+    while [ '!' -d json-c -a "$CNT" -lt 4 ]; do
+      echo "Trying to clone json-c (attempt $CNT/3)"
+      git clone "$JSONC_REPO" 
+      CNT=`expr "$CNT" + 1`
+    done
+  }
+fi
+
+test -d json-c || { echo "[-] not checked out, please install git or check your internet connection." ; exit 1 ; }
+echo "[+] Got json-c."
+
+test -e json-c/.libs/libjson-c.a || {
+  cd "json-c" || exit 1
+  echo "[*] Checking out $JSONC_VERSION"
+  sh -c 'git stash && git stash drop' 1>/dev/null 2>/dev/null
+  git checkout "$JSONC_VERSION" || exit 1
+  sh autogen.sh || exit 1
+  export CFLAGS=-fPIC
+  ./configure --disable-shared || exit 1
+  make || exit 1
+  cd ..
+}
+
+echo
+echo
+echo "[+] Json-c successfully prepared!"
+echo "[+] Builing gramatron now."
+$CC -O3 -g -fPIC -Wno-unused-result -Wl,--allow-multiple-definition -I../../include -o gramatron.so -shared -I. -I/prg/dev/include gramfuzz.c gramfuzz-helpers.c gramfuzz-mutators.c gramfuzz-util.c hashmap.c ../../src/afl-performance.o json-c/.libs/libjson-c.a || exit 1
+echo
+echo "[+] gramatron successfully built!"

custom_mutators/gramatron/gramfuzz-helpers.c

@@ -0,0 +1,336 @@
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <assert.h>
+#include "afl-fuzz.h"
+#include "gramfuzz.h"
+
+/*Slices from beginning till idx*/
+Array *slice(Array *input, int idx) {
+
+  // printf("\nSlice idx:%d", idx);
+  terminal *origptr;
+  terminal *term_ptr;
+  Array *   sliced = (Array *)malloc(sizeof(Array));
+  initArray(sliced, input->size);
+  // Populate dynamic array members
+  if (idx == 0) { return sliced; }
+  for (int x = 0; x < idx; x++) {
+
+    origptr = &input->start[x];
+    insertArray(sliced, origptr->state, origptr->symbol, origptr->symbol_len,
+                origptr->trigger_idx);
+
+  }
+
+  return sliced;
+
+}
+
+/* Slices from idx till end*/
+Array *slice_inverse(Array *input, int idx) {
+
+  // printf("\nSlice idx:%d", idx);
+  terminal *origptr;
+  terminal *term_ptr;
+  Array *   sliced = (Array *)malloc(sizeof(Array));
+  initArray(sliced, input->size);
+  for (int x = idx; x < input->used; x++) {
+
+    origptr = &input->start[x];
+    insertArray(sliced, origptr->state, origptr->symbol, origptr->symbol_len,
+                origptr->trigger_idx);
+
+  }
+
+  return sliced;
+
+}
+
+/*Carves with `start` included and `end` excluded*/
+Array *carve(Array *input, int start, int end) {
+
+  terminal *origptr;
+  terminal *term_ptr;
+  Array *   sliced = (Array *)malloc(sizeof(Array));
+  initArray(sliced, input->size);
+  for (int x = start; x < end; x++) {
+
+    origptr = &input->start[x];
+    insertArray(sliced, origptr->state, origptr->symbol, origptr->symbol_len,
+                origptr->trigger_idx);
+
+  }
+
+  return sliced;
+
+}
+
+/*Concats prefix + feature *mult*/
+void concatPrefixFeature(Array *prefix, Array *feature) {
+
+  // XXX: Currently we have hardcoded the multiplication threshold for adding
+  // the recursive feature. Might want to fix it to choose a random number upper
+  // bounded by a static value instead.
+  terminal *featureptr;
+  int       len = rand_below(global_afl, RECUR_THRESHOLD);
+  for (int x = 0; x < len; x++) {
+
+    for (int y = 0; y < feature->used; y++) {
+
+      featureptr = &feature->start[y];
+      insertArray(prefix, featureptr->state, featureptr->symbol,
+                  featureptr->symbol_len, featureptr->trigger_idx);
+
+    }
+
+  }
+
+}
+
+void concatPrefixFeatureBench(Array *prefix, Array *feature) {
+
+  // XXX: Currently we have hardcoded the multiplication threshold for adding
+  // the recursive feature. Might want to fix it to choose a random number upper
+  // bounded by a static value instead.
+  terminal *featureptr;
+  int       len =
+      5;  // 5 is the number of times we compare performing random recursion.
+  for (int x = 0; x < len; x++) {
+
+    for (int y = 0; y < feature->used; y++) {
+
+      featureptr = &feature->start[y];
+      insertArray(prefix, featureptr->state, featureptr->symbol,
+                  featureptr->symbol_len, featureptr->trigger_idx);
+
+    }
+
+  }
+
+}
+
+Array *spliceGF(Array *orig, Array *toSplice, int idx) {
+
+  terminal *toSplicePtr;
+  terminal *tempPtr;
+  // Iterate through the splice candidate from the `idx` till end
+  for (int x = idx; x < toSplice->used; x++) {
+
+    toSplicePtr = &toSplice->start[x];
+    insertArray(orig, toSplicePtr->state, toSplicePtr->symbol,
+                toSplicePtr->symbol_len, toSplicePtr->trigger_idx);
+
+  }
+
+  return orig;
+
+}
+
+Array *gen_input(state *pda, Array *input) {
+
+  state *   state_ptr;
+  trigger * trigger_ptr;
+  terminal *term_ptr;
+  int       offset = 0;
+  int       randval, error;
+  // Generating an input for the first time
+  if (input == NULL) {
+
+    input = (Array *)calloc(1, sizeof(Array));
+    initArray(input, INIT_SIZE);
+    curr_state = init_state;
+
+  }
+
+  while (curr_state != final_state) {
+
+    // Retrieving the state from the pda
+    state_ptr = pda + curr_state;
+
+    // Get a random trigger
+    randval = rand_below(global_afl, state_ptr->trigger_len);
+    trigger_ptr = (state_ptr->ptr) + randval;
+
+    // Insert into the dynamic array
+    insertArray(input, curr_state, trigger_ptr->term, trigger_ptr->term_len,
+                randval);
+    curr_state = trigger_ptr->dest;
+    offset += 1;
+
+  }
+
+  return input;
+
+}
+
+Array *gen_input_count(state *pda, Array *input, int *mut_count) {
+
+  state *   state_ptr;
+  trigger * trigger_ptr;
+  terminal *term_ptr;
+  int       offset = 0;
+  int       randval, error;
+  // Generating an input for the first time
+  if (input == NULL) {
+
+    input = (Array *)calloc(1, sizeof(Array));
+    initArray(input, INIT_SIZE);
+    curr_state = init_state;
+
+  }
+
+  while (curr_state != final_state) {
+
+    *mut_count += 1;
+    // Retrieving the state from the pda
+    state_ptr = pda + curr_state;
+
+    // Get a random trigger
+    randval = rand_below(global_afl, state_ptr->trigger_len);
+    trigger_ptr = (state_ptr->ptr) + randval;
+
+    // Insert into the dynamic array
+    insertArray(input, curr_state, trigger_ptr->term, trigger_ptr->term_len,
+                randval);
+    curr_state = trigger_ptr->dest;
+    offset += 1;
+
+  }
+
+  return input;
+
+}
+
+/*Creates a candidate from walk with state hashmap and
+ * recursion hashmap
+ */
+
+Candidate *gen_candidate(Array *input) {
+
+  terminal *  term_ptr;
+  IdxMap_new *idxmapPtr;
+  // Declare the State Hash Table
+  IdxMap_new *idxmapStart =
+      (IdxMap_new *)malloc(sizeof(IdxMap_new) * numstates);
+  for (int x = 0; x < numstates; x++) {
+
+    idxmapPtr = &idxmapStart[x];
+    utarray_new(idxmapPtr->nums, &ut_int_icd);
+
+  }
+
+  char *     trigger;
+  int        state;
+  char *     key;
+  Candidate *candidate = (Candidate *)malloc(sizeof(Candidate));
+  candidate->walk = input;
+  int offset = 0, error;
+
+  // Generate statemap for splicing
+  while (offset < input->used) {
+
+    term_ptr = &input->start[offset];
+    state = term_ptr->state;
+    // char *statenum = state + 1;
+    // int num = atoi(statenum);
+    idxmapPtr = &idxmapStart[state];
+    utarray_push_back(idxmapPtr->nums, &offset);
+    offset += 1;
+
+  }
+
+  candidate->statemap = idxmapStart;
+  return candidate;
+
+}
+
+char *get_state(char *trigger) {
+
+  // Get the state from transition
+  int trigger_idx = 0;
+  printf("\nTrigger:%s", trigger);
+  char *state = (char *)malloc(sizeof(char) * 10);
+  while (trigger[trigger_idx] != '_') {
+
+    state[trigger_idx] = trigger[trigger_idx];
+    trigger_idx += 1;
+
+  }
+
+  printf("\nTrigger Idx:%d", trigger_idx);
+  state[trigger_idx] = '\0';
+  return state;
+
+}
+
+void print_repr(Array *input, char *prefix) {
+
+  size_t    offset = 0;
+  terminal *term_ptr;
+  char      geninput[input->used * 100];
+  if (!input->used) {
+
+    printf("\n=============");
+    printf("\n%s:%s", prefix, "");
+    printf("\n=============");
+    return;
+
+  }
+
+  // This is done to create a null-terminated initial string
+  term_ptr = &input->start[offset];
+  strcpy(geninput, term_ptr->symbol);
+  offset += 1;
+
+  while (offset < input->used) {
+
+    term_ptr = &input->start[offset];
+    strcat(geninput, term_ptr->symbol);
+    offset += 1;
+
+  }
+
+  printf("\n=============");
+  printf("\n%s:%s", prefix, geninput);
+  printf("\n=============");
+
+}
+
+// int main(int argc, char*argv[]) {
+
+//     char *mode;
+//     if (argc == 1) {
+
+//         printf("\nUsage: ./gramfuzzer <mode>");
+//         return -1;
+//     }
+//     if (argc >= 2) {
+
+//         mode = argv[1];
+//         printf("\nMode:%s", mode);
+//     }
+//     if (! strcmp(mode, "Generate")) {
+
+//         GenInputBenchmark();
+//     }
+//     else if (! strcmp(mode, "RandomMutation")) {
+
+//         RandomMutationBenchmark();
+//     }
+//     else if (! strcmp(mode, "Splice")) {
+
+//         SpliceMutationBenchmark();
+//     }
+//     else if (! strcmp(mode, "Recursive")) {
+
+//         RandomRecursiveBenchmark();
+//     }
+//     else {
+
+//         printf("\nUnrecognized mode");
+//         return -1;
+//     }
+//     return 0;
+// }
+

custom_mutators/gramatron/gramfuzz-mutators.c

@@ -0,0 +1,247 @@
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <assert.h>
+#include "afl-fuzz.h"
+#include "gramfuzz.h"
+
+Array *performRandomMutation(state *pda, Array *input) {
+
+  terminal *term_ptr;
+  // terminal *prev_ptr;
+  Array *mutated;
+  Array *sliced;
+
+  // Get offset at which to generate new input and slice it
+  int idx = rand_below(global_afl, input->used);
+  sliced = slice(input, idx);
+  // print_repr(sliced, "Slice");
+
+  // prev_ptr = & input->start[idx - 1];
+  // printf("\nState:%s Symbol:%s", prev_ptr->state, prev_ptr->symbol);
+  // Reset current state to that of the slice's last member
+  term_ptr = &input->start[idx];
+  curr_state = term_ptr->state;
+  // printf("\nState:%s Symbol:%s", curr_state, term_ptr->symbol);
+
+  // Set the next available cell to the one adjacent to this chosen point
+  mutated = gen_input(pda, sliced);
+  return mutated;
+
+}
+
+// Tries to perform splice operation between two automaton walks
+UT_icd intpair_icd = {sizeof(intpair_t), NULL, NULL, NULL};
+
+Array *performSpliceOne(Array *originput, IdxMap_new *statemap_orig,
+                        Array *splicecand) {
+
+  UT_array * stateptr, *pairs;
+  intpair_t  ip;
+  intpair_t *cand;
+
+  terminal *term_ptr;
+  Array *   prefix;
+  int       state;
+
+  // Initialize the dynamic holding the splice indice pairs
+  utarray_new(pairs, &intpair_icd);
+  // print_repr(originput, "Orig");
+  // print_repr(splicecand, "SpliceCand");
+
+  // Iterate through the splice candidate identifying potential splice points
+  // and pushing pair (orig_idx, splice_idx) to a dynamic array
+  for (int x = 0; x < splicecand->used; x++) {
+
+    term_ptr = &splicecand->start[x];
+    stateptr = statemap_orig[term_ptr->state].nums;
+    int length = utarray_len(stateptr);
+    if (length) {
+
+      int *splice_idx = (int *)utarray_eltptr(stateptr, rand_below(global_afl, length));
+      ip.orig_idx = *splice_idx;
+      ip.splice_idx = x;
+      utarray_push_back(pairs, &ip);
+
+    }
+
+  }
+
+  // Pick a random pair
+  int length = utarray_len(pairs);
+  cand = (intpair_t *)utarray_eltptr(pairs, rand_below(global_afl, length));
+  // printf("\n Orig_idx:%d Splice_idx:%d", cand->orig_idx, cand->splice_idx);
+
+  // Perform the splicing
+  prefix = slice(originput, cand->orig_idx);
+  Array *spliced = spliceGF(prefix, splicecand, cand->splice_idx);
+  // print_repr(spliced, "Spliced");
+  //
+  utarray_free(pairs);
+
+  return spliced;
+
+}
+
+UT_array **get_dupes(Array *input, int *recur_len) {
+
+  // Variables related to finding duplicates
+  int         offset = 0;
+  int         state;
+  terminal *  term_ptr;
+  IdxMap_new *idxMapPtr;
+  UT_array ** recurIdx;
+
+  // Declare the Recursive Map Table
+  IdxMap_new *idxmapStart =
+      (IdxMap_new *)malloc(sizeof(IdxMap_new) * numstates);
+  //
+  // UT_array *(recurIdx[numstates]);
+  recurIdx = malloc(sizeof(UT_array *) * numstates);
+
+  for (int x = 0; x < numstates; x++) {
+
+    idxMapPtr = &idxmapStart[x];
+    utarray_new(idxMapPtr->nums, &ut_int_icd);
+
+  }
+
+  // Obtain frequency distribution of states
+  while (offset < input->used) {
+
+    term_ptr = &input->start[offset];
+    state = term_ptr->state;
+    // int num = atoi(state + 1);
+    idxMapPtr = &idxmapStart[state];
+    utarray_push_back(idxMapPtr->nums, &offset);
+    offset += 1;
+
+  }
+
+  // Retrieve the duplicated states
+  offset = 0;
+  while (offset < numstates) {
+
+    idxMapPtr = &idxmapStart[offset];
+    int length = utarray_len(idxMapPtr->nums);
+    if (length >= 2) {
+
+      recurIdx[*recur_len] = idxMapPtr->nums;
+      *recur_len += 1;
+
+    }
+
+    // else {
+
+    //     utarray_free(idxMapPtr->nums);
+    // }
+    offset += 1;
+
+  }
+
+  if (*recur_len) {
+
+    // Declare the return struct
+    // We use this struct so that we save the reference to IdxMap_new and free
+    // it after we have used it in doMult
+    // Get_Dupes_Ret* getdupesret =
+    // (Get_Dupes_Ret*)malloc(sizeof(Get_Dupes_Ret));
+    return recurIdx;
+    // getdupesret->idxmap = idxmapStart;
+    // getdupesret->recurIdx = recurIdx;
+    // return getdupesret;
+
+  } else {
+
+    return NULL;
+
+  }
+
+}
+
+Array *doMult(Array *input, UT_array **recur, int recurlen) {
+
+  int       offset = 0;
+  int       idx = rand_below(global_afl, recurlen);
+  UT_array *recurMap = recur[idx];
+  UT_array *recurPtr;
+  Array *   prefix;
+  Array *   postfix;
+  Array *   feature;
+
+  // Choose two indices to get the recursive feature
+  int recurIndices = utarray_len(recurMap);
+  int firstIdx = 0;
+  int secondIdx = 0;
+  getTwoIndices(recurMap, recurIndices, &firstIdx, &secondIdx);
+
+  // Perform the recursive mut
+  // print_repr(input, "Orig");
+  prefix = slice(input, firstIdx);
+  // print_repr(prefix, "Prefix");
+  if (firstIdx < secondIdx) {
+
+    feature = carve(input, firstIdx, secondIdx);
+
+  } else {
+
+    feature = carve(input, secondIdx, firstIdx);
+
+  }
+
+  // print_repr(feature, "Feature");
+  concatPrefixFeature(prefix, feature);
+
+  // GC allocated structures
+  free(feature->start);
+  free(feature);
+  // for(int x = 0; x < recurlen; x++) {
+
+  //     utarray_free(recur[x]);
+  // }
+  // free(recur);
+  // print_repr(prefix, "Concat");
+  return spliceGF(prefix, input, secondIdx);
+
+}
+
+void getTwoIndices(UT_array *recur, int recurlen, int *firstIdx,
+                   int *secondIdx) {
+
+  int ArrayRecurIndices[recurlen];
+  int offset = 0, *p;
+  // Unroll into an array
+  for (p = (int *)utarray_front(recur); p != NULL;
+       p = (int *)utarray_next(recur, p)) {
+
+    ArrayRecurIndices[offset] = *p;
+    offset += 1;
+
+  }
+
+  /*Source:
+   * https://www.geeksforgeeks.org/shuffle-a-given-array-using-fisher-yates-shuffle-algorithm/
+   */
+  for (int i = offset - 1; i > 0; i--) {
+
+    // Pick a random index from 0 to i
+    int j = rand_below(global_afl, i + 1);
+
+    // Swap arr[i] with the element at random index
+    swap(&ArrayRecurIndices[i], &ArrayRecurIndices[j]);
+
+  }
+
+  *firstIdx = ArrayRecurIndices[0];
+  *secondIdx = ArrayRecurIndices[1];
+
+}
+
+void swap(int *a, int *b) {
+
+  int temp = *a;
+  *a = *b;
+  *b = temp;
+
+}
+

custom_mutators/gramatron/gramfuzz-util.c

@@ -0,0 +1,268 @@
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <assert.h>
+#include "afl-fuzz.h"
+#include "gramfuzz.h"
+#ifdef _GNU_SOURCE
+  #undef _GNU_SOURCE
+#endif
+#define _GNU_SOURCE
+#include <sys/mman.h>
+
+/* Dynamic Array for adding to the input repr
+ * */
+void initArray(Array *a, size_t initialSize) {
+
+  a->start = (terminal *)calloc(1, sizeof(terminal) * initialSize);
+  a->used = 0;
+  a->size = initialSize;
+  a->inputlen = 0;
+
+}
+
+void insertArray(Array *a, int state, char *symbol, size_t symbol_len,
+                 int trigger_idx) {
+
+  // a->used is the number of used entries, because a->array[a->used++] updates
+  // a->used only *after* the array has been accessed. Therefore a->used can go
+  // up to a->size
+  terminal *term_ptr;
+  if (a->used == a->size) {
+
+    a->size = a->size * sizeof(terminal);
+    a->start = (terminal *)realloc(a->start, a->size * sizeof(terminal));
+
+  }
+
+  // Add the element
+  term_ptr = &a->start[a->used];
+  term_ptr->state = state;
+  term_ptr->symbol = symbol;
+  term_ptr->symbol_len = symbol_len;
+  term_ptr->trigger_idx = trigger_idx;
+
+  // Increment the pointer
+  a->used += 1;
+  a->inputlen += symbol_len;
+
+}
+
+void freeArray(Array *a) {
+
+  terminal *ptr;
+  for (int x = 0; x < a->used; x++) {
+
+    ptr = &a->start[x];
+    free(ptr);
+
+  }
+
+  a->start = NULL;
+  a->used = a->size = 0;
+
+}
+
+/* Dynamic array for adding indices of states/recursive features
+ * Source:
+ * https://stackoverflow.com/questions/3536153/c-dynamically-growing-array
+ */
+void initArrayIdx(IdxMap *a, size_t initialSize) {
+
+  a->array = (int *)malloc(initialSize * sizeof(int));
+  a->used = 0;
+  a->size = initialSize;
+
+}
+
+void insertArrayIdx(IdxMap *a, int idx) {
+
+  // a->used is the number of used entries, because a->array[a->used++] updates
+  // a->used only *after* the array has been accessed. Therefore a->used can go
+  // up to a->size
+  if (a->used == a->size) {
+
+    a->size *= 2;
+    a->array = (int *)realloc(a->array, a->size * sizeof(int));
+
+  }
+
+  a->array[a->used++] = idx;
+
+}
+
+void freeArrayIdx(IdxMap *a) {
+
+  free(a->array);
+  a->array = NULL;
+  a->used = a->size = 0;
+
+}
+
+/* Dynamic array for adding potential splice points
+ */
+void initArraySplice(SpliceCandArray *a, size_t initialSize) {
+
+  a->start = (SpliceCand *)malloc(initialSize * sizeof(SpliceCand));
+  a->used = 0;
+  a->size = initialSize;
+
+}
+
+void insertArraySplice(SpliceCandArray *a, Candidate *candidate, int idx) {
+
+  // a->used is the number of used entries, because a->array[a->used++] updates
+  // a->used only *after* the array has been accessed. Therefore a->used can go
+  // up to a->size
+  SpliceCand *candptr;
+  if (a->used == a->size) {
+
+    a->size = a->size * sizeof(SpliceCand);
+    a->start = (SpliceCand *)realloc(a->start, a->size * sizeof(SpliceCand));
+
+  }
+
+  // Add the element
+  candptr = &a->start[a->used];
+  candptr->splice_cand = candidate;
+  candptr->idx = idx;
+  a->used += 1;
+
+}
+
+void freeArraySplice(IdxMap *a) {
+
+  free(a->array);
+  a->array = NULL;
+  a->used = a->size = 0;
+
+}
+
+int fact(int n) {
+
+  int i, f = 1;
+  for (i = 1; i <= n; i++) {
+
+    f *= i;
+
+  }
+
+  return f;
+
+}
+
+/* Uses the walk to create the input in-memory */
+u8 *unparse_walk(Array *input) {
+
+  terminal *term_ptr;
+  int       offset = 0;
+  u8 *      unparsed = (u8 *)malloc(input->inputlen + 1);
+  term_ptr = &input->start[offset];
+  strcpy(unparsed, term_ptr->symbol);
+  offset += 1;
+  while (offset < input->used) {
+
+    term_ptr = &input->start[offset];
+    strcat(unparsed, term_ptr->symbol);
+    offset += 1;
+
+  }
+
+  return unparsed;
+
+}
+
+/*Dump the input representation into a file*/
+void write_input(Array *input, u8 *fn) {
+
+  FILE *fp;
+  // If file already exists, then skip creating the file
+  if (access(fn, F_OK) != -1) { return; }
+
+  fp = fopen(fn, "wbx+");
+  // If the input has already been flushed, then skip silently
+  if (fp == NULL) {
+
+    fprintf(stderr, "\n File '%s' could not be open, exiting\n", fn);
+    exit(1);
+
+  }
+
+  // Write the length parameters
+  fwrite(&input->used, sizeof(size_t), 1, fp);
+  fwrite(&input->size, sizeof(size_t), 1, fp);
+  fwrite(&input->inputlen, sizeof(size_t), 1, fp);
+
+  // Write the dynamic array to file
+  fwrite(input->start, input->size * sizeof(terminal), 1, fp);
+  // printf("\nUsed:%zu Size:%zu Inputlen:%zu", input->used, input->size,
+  // input->inputlen);
+  fclose(fp);
+
+}
+
+Array *parse_input(state *pda, FILE *fp) {
+
+  terminal *term;
+  state *   state_ptr;
+  trigger * trigger;
+  int       trigger_idx;
+  Array *   input = (Array *)calloc(1, sizeof(Array));
+
+  // Read the length parameters
+  fread(&input->used, sizeof(size_t), 1, fp);
+  fread(&input->size, sizeof(size_t), 1, fp);
+  fread(&input->inputlen, sizeof(size_t), 1, fp);
+
+  terminal *start_ptr = (terminal *)calloc(input->size, sizeof(terminal));
+  if (!start_ptr) {
+
+    fprintf(stderr, "alloc failed!\n");
+    return NULL;
+
+  }
+
+  // Read the dynamic array to memory
+  fread(start_ptr, input->size * sizeof(terminal), 1, fp);
+  // Update the pointers to the terminals since they would have
+  // changed
+  int idx = 0;
+  while (idx < input->used) {
+
+    terminal *term = &start_ptr[idx];
+    // Find the state
+    state_ptr = pda + term->state;
+    // Find the trigger and update the terminal address
+    trigger_idx = term->trigger_idx;
+    trigger = (state_ptr->ptr) + trigger_idx;
+    term->symbol = trigger->term;
+    idx += 1;
+
+  }
+
+  input->start = start_ptr;
+  // printf("\nUsed:%zu Size:%zu Inputlen:%zu", input->used, input->size,
+  // input->inputlen);
+
+  return input;
+
+}
+
+// Read the input representation into memory
+Array *read_input(state *pda, u8 *fn) {
+
+  FILE *fp;
+  fp = fopen(fn, "rb");
+  if (fp == NULL) {
+
+    fprintf(stderr, "\n File '%s' does not exist, exiting\n", fn);
+    exit(1);
+
+  }
+
+  Array *res = parse_input(pda, fp);
+  fclose(fp);
+  return res;
+
+}
+

custom_mutators/gramatron/gramfuzz.c

@@ -0,0 +1,429 @@
+// This simple example just creates random buffer <= 100 filled with 'A'
+// needs -I /path/to/AFLplusplus/include
+//#include "custom_mutator_helpers.h"
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+
+#include "afl-fuzz.h"
+#include "gramfuzz.h"
+
+#define MUTATORS 4  // Specify the total number of mutators
+
+typedef struct my_mutator {
+
+  afl_state_t *afl;
+
+  u8 *   mutator_buf;
+  u8 *   unparsed_input;
+  Array *mutated_walk;
+  Array *orig_walk;
+
+  IdxMap_new *statemap;  // Keeps track of the statemap
+  UT_array ** recurIdx;
+  // Get_Dupes_Ret* getdupesret; // Recursive feature map
+  int recurlen;
+
+  int mut_alloced;
+  int orig_alloced;
+  int mut_idx;  // Signals the current mutator being used, used to cycle through
+                // each mutator
+
+  unsigned int seed;
+
+} my_mutator_t;
+
+state *create_pda(u8 *automaton_file) {
+
+  struct json_object *parsed_json;
+  state *             pda;
+  json_object *       source_obj, *attr;
+  int                 arraylen, ii, ii2, trigger_len, error;
+
+  printf("\n[GF] Automaton file passed:%s", automaton_file);
+  // parsed_json =
+  // json_object_from_file("./gramfuzz/php_gnf_processed_full.json");
+  parsed_json = json_object_from_file(automaton_file);
+
+  // Getting final state
+  source_obj = json_object_object_get(parsed_json, "final_state");
+  printf("\t\nFinal=%s\n", json_object_get_string(source_obj));
+  final_state = atoi(json_object_get_string(source_obj));
+
+  // Getting initial state
+  source_obj = json_object_object_get(parsed_json, "init_state");
+  init_state = atoi(json_object_get_string(source_obj));
+  printf("\tInit=%s\n", json_object_get_string(source_obj));
+
+  // Getting number of states
+  source_obj = json_object_object_get(parsed_json, "numstates");
+  numstates = atoi(json_object_get_string(source_obj)) + 1;
+  printf("\tNumStates=%d\n", numstates);
+
+  // Allocate state space for each pda state
+  pda = (state *)calloc(atoi(json_object_get_string(source_obj)) + 1,
+                        sizeof(state));
+
+  // Getting PDA representation
+  source_obj = json_object_object_get(parsed_json, "pda");
+  enum json_type type;
+  json_object_object_foreach(source_obj, key, val) {
+
+    state *  state_ptr;
+    trigger *trigger_ptr;
+    int      offset;
+
+    // Get the correct offset into the pda to store state information
+    state_ptr = pda;
+    offset = atoi(key);
+    state_ptr += offset;
+    // Store state string
+    state_ptr->state_name = offset;
+
+    // Create trigger array of structs
+    trigger_len = json_object_array_length(val);
+    state_ptr->trigger_len = trigger_len;
+    trigger_ptr = (trigger *)calloc(trigger_len, sizeof(trigger));
+    state_ptr->ptr = trigger_ptr;
+
+    for (ii = 0; ii < trigger_len; ii++) {
+
+      json_object *obj = json_object_array_get_idx(val, ii);
+      // Get all the trigger trigger attributes
+      attr = json_object_array_get_idx(obj, 0);
+      (trigger_ptr)->id = strdup(json_object_get_string(attr));
+
+      attr = json_object_array_get_idx(obj, 1);
+      trigger_ptr->dest = atoi(json_object_get_string(attr));
+
+      attr = json_object_array_get_idx(obj, 2);
+      if (!strcmp("\\n", json_object_get_string(attr))) {
+
+        trigger_ptr->term = strdup("\n");
+
+      } else {
+
+        trigger_ptr->term = strdup(json_object_get_string(attr));
+
+      }
+
+      trigger_ptr->term_len = strlen(trigger_ptr->term);
+      trigger_ptr++;
+
+    }
+
+  }
+
+  // Delete the JSON object
+  json_object_put(parsed_json);
+
+  return pda;
+
+}
+
+my_mutator_t *afl_custom_init(afl_state_t *afl, unsigned int seed) {
+
+  my_mutator_t *data = calloc(1, sizeof(my_mutator_t));
+  if (!data) {
+
+    perror("afl_custom_init alloc");
+    return NULL;
+
+  }
+
+  if ((data->mutator_buf = malloc(MAX_FILE)) == NULL) {
+
+    perror("mutator_buf alloc");
+    return NULL;
+
+  }
+
+  data->afl = afl;
+  global_afl = afl;  // dirty
+  data->seed = seed;
+
+  data->mut_alloced = 0;
+  data->orig_alloced = 0;
+  data->mut_idx = 0;
+  data->recurlen = 0;
+
+  // data->mutator_buf = NULL;
+  // data->unparsed_input = NULL;
+  // data->mutated_walk = NULL;
+  // data->orig_walk = NULL;
+  //
+  // data->statemap = NULL;  // Keeps track of the statemap
+  // data->recur_idx = NULL; // Will keep track of recursive feature indices
+  // u32 recur_len = 0;       // The number of recursive features
+  // data->mutator_buf = NULL;
+
+  char *automaton_file = getenv("GRAMATRON_AUTOMATION");
+  if (automaton_file) {
+
+    pda = create_pda(automaton_file);
+
+  } else {
+
+    fprintf(stderr,
+            "\nError: GrammaTron needs an automation json file set in "
+            "GRAMATRON_AUTOMATION\n");
+    exit(-1);
+
+  }
+
+  return data;
+
+}
+
+size_t afl_custom_fuzz(my_mutator_t *data, uint8_t *buf, size_t buf_size,
+                       u8 **out_buf, uint8_t *add_buf, size_t add_buf_size,
+                       size_t max_size) {
+
+  u8 *unparsed_input;
+
+  // Pick a mutator
+  // int choice = rand() % MUTATORS;
+  // data->mut_idx = 1;
+  // GC old mutant
+  if (data->mut_alloced) {
+
+    free(data->mutated_walk->start);
+    free(data->mutated_walk);
+    data->mut_alloced = 0;
+
+  };
+
+  // printf("\nChoice:%d", choice);
+
+  if (data->mut_idx == 0) {  // Perform random mutation
+    data->mutated_walk = performRandomMutation(pda, data->orig_walk);
+    data->mut_alloced = 1;
+
+  } else if (data->mut_idx == 1 &&
+
+             data->recurlen) {  // Perform recursive mutation
+    data->mutated_walk =
+        doMult(data->orig_walk, data->recurIdx, data->recurlen);
+    data->mut_alloced = 1;
+
+  } else if (data->mut_idx == 2) {  // Perform splice mutation
+
+    // we cannot use the supplied splice data so choose a new random file
+    u32                 tid = rand_below(global_afl, data->afl->queued_items);
+    struct queue_entry *q = data->afl->queue_buf[tid];
+
+    // Read the input representation for the splice candidate
+    u8 *   automaton_fn = alloc_printf("%s.aut", q->fname);
+    Array *spliceCandidate = read_input(pda, automaton_fn);
+
+    if (spliceCandidate) {
+
+      data->mutated_walk =
+          performSpliceOne(data->orig_walk, data->statemap, spliceCandidate);
+      data->mut_alloced = 1;
+      free(spliceCandidate->start);
+      free(spliceCandidate);
+
+    } else {
+
+      data->mutated_walk = gen_input(pda, NULL);
+      data->mut_alloced = 1;
+
+    }
+
+    ck_free(automaton_fn);
+
+  } else {  // Generate an input from scratch
+
+    data->mutated_walk = gen_input(pda, NULL);
+    data->mut_alloced = 1;
+
+  }
+
+  // Cycle to the next mutator
+  if (data->mut_idx == MUTATORS - 1)
+    data->mut_idx =
+        0;  // Wrap around if we have reached end of the mutator list
+  else
+    data->mut_idx += 1;
+
+  // Unparse the mutated automaton walk
+  if (data->unparsed_input) { free(data->unparsed_input); }
+  data->unparsed_input = unparse_walk(data->mutated_walk);
+  *out_buf = data->unparsed_input;
+
+  return data->mutated_walk->inputlen;
+
+}
+
+/**
+ * Create the automaton-based representation for the corresponding input
+ *
+ * @param data pointer returned in afl_custom_init for this fuzz case
+ * @param filename_new_queue File name of the new queue entry
+ * @param filename_orig_queue File name of the original queue entry
+ */
+u8 afl_custom_queue_new_entry(my_mutator_t * data,
+                              const uint8_t *filename_new_queue,
+                              const uint8_t *filename_orig_queue) {
+
+  // get the filename
+  u8 *   automaton_fn, *unparsed_input;
+  Array *new_input;
+  s32    fd;
+
+  automaton_fn = alloc_printf("%s.aut", filename_new_queue);
+  // Check if this method is being called during initialization
+
+  // fprintf(stderr, "new: %s, old: %s, auto: %s\n",
+  // filename_new_queue,filename_orig_queue,automaton_fn);
+
+  if (filename_orig_queue) {
+
+    write_input(data->mutated_walk, automaton_fn);
+
+  } else {
+
+    new_input = gen_input(pda, NULL);
+    write_input(new_input, automaton_fn);
+
+    // Update the placeholder file
+    if (unlink(filename_new_queue)) {
+
+      PFATAL("Unable to delete '%s'", filename_new_queue);
+
+    }
+
+    unparsed_input = unparse_walk(new_input);
+    fd = open(filename_new_queue, O_WRONLY | O_CREAT | O_TRUNC,
+              S_IRUSR | S_IWUSR);
+    if (fd < 0) { PFATAL("Failed to update file '%s'", filename_new_queue); }
+    int written = write(fd, unparsed_input, new_input->inputlen + 1);
+    close(fd);
+
+    free(new_input->start);
+    free(new_input);
+    free(unparsed_input);
+
+  }
+
+  ck_free(automaton_fn);
+
+  return 1;
+
+}
+
+/**
+ * Get the corresponding tree representation for the candidate that is to be
+ * mutated
+ *
+ * @param[in] data pointer returned in afl_custom_init for this fuzz case
+ * @param filename File name of the test case in the queue entry
+ * @return Return True(1) if the fuzzer will fuzz the queue entry, and
+ *     False(0) otherwise.
+ */
+uint8_t afl_custom_queue_get(my_mutator_t *data, const uint8_t *filename) {
+
+  // get the filename
+  u8 *        automaton_fn = alloc_printf("%s.aut", filename);
+  IdxMap_new *statemap_ptr;
+  terminal *  term_ptr;
+  int         state;
+
+  // TODO: I don't think we need to update pointers when reading back
+  // Probably build two different versions of read_input one for flushing
+  // inputs to disk and the other that
+  if (data->orig_alloced) {
+
+    free(data->orig_walk->start);
+    free(data->orig_walk);
+    data->orig_alloced = 0;
+
+  }
+
+  if (data->statemap) {
+
+    for (int x = 0; x < numstates; x++) {
+
+      utarray_free(data->statemap[x].nums);
+
+    }
+
+    free(data->statemap);
+
+  }
+
+  if (data->recurIdx) {
+
+    data->recurlen = 0;
+    free(data->recurIdx);
+
+  }
+
+  data->orig_walk = read_input(pda, automaton_fn);
+  data->orig_alloced = 1;
+
+  // Create statemap for the fuzz candidate
+  IdxMap_new *statemap_start =
+      (IdxMap_new *)malloc(sizeof(IdxMap_new) * numstates);
+  for (int x = 0; x < numstates; x++) {
+
+    statemap_ptr = &statemap_start[x];
+    utarray_new(statemap_ptr->nums, &ut_int_icd);
+
+  }
+
+  int offset = 0;
+  while (offset < data->orig_walk->used) {
+
+    term_ptr = &data->orig_walk->start[offset];
+    state = term_ptr->state;
+    statemap_ptr = &statemap_start[state];
+    utarray_push_back(statemap_ptr->nums, &offset);
+    offset += 1;
+
+  }
+
+  data->statemap = statemap_start;
+
+  // Create recursive feature map (if it exists)
+  data->recurIdx = malloc(sizeof(UT_array *) * numstates);
+  // Retrieve the duplicated states
+  offset = 0;
+  while (offset < numstates) {
+
+    statemap_ptr = &data->statemap[offset];
+    int length = utarray_len(statemap_ptr->nums);
+    if (length >= 2) {
+
+      data->recurIdx[data->recurlen] = statemap_ptr->nums;
+      data->recurlen += 1;
+
+    }
+
+    offset += 1;
+
+  }
+
+  // data->getdupesret = get_dupes(data->orig_walk, &data->recurlen);
+
+  ck_free(automaton_fn);
+  return 1;
+
+}
+
+/**
+ * Deinitialize everything
+ *
+ * @param data The data ptr from afl_custom_init
+ */
+
+void afl_custom_deinit(my_mutator_t *data) {
+
+  free(data->mutator_buf);
+  free(data);
+
+}
+

custom_mutators/gramatron/gramfuzz.h

@@ -0,0 +1,255 @@
+#ifndef _GRAMFUZZ_H
+
+#define _GRAMFUZZ_H
+
+#include <json-c/json.h>
+#include <unistd.h>
+#include "hashmap.h"
+#include "uthash.h"
+#include "utarray.h"
+
+#define INIT_INPUTS 100  // No. of initial inputs to be generated
+
+// Set this as `numstates` + 1 where `numstates` is retrieved from gen automata
+// json #define STATES 63
+
+#define INIT_SIZE 100  // Initial size of the dynamic array holding the input
+
+#define SPLICE_CORPUS 10000
+#define RECUR_THRESHOLD 6
+#define SIZE_THRESHOLD 2048
+
+#define FLUSH_INTERVAL \
+  3600  // Inputs that gave new coverage will be dumped every FLUSH_INTERVAL
+        // seconds
+
+afl_state_t *global_afl;
+
+typedef struct trigger {
+
+  char * id;
+  int    dest;
+  char * term;
+  size_t term_len;
+
+} trigger;
+
+typedef struct state {
+
+  int      state_name;   // Integer State name
+  int      trigger_len;  // Number of triggers associated with this state
+  trigger *ptr;          // Pointer to beginning of the list of triggers
+
+} state;
+
+typedef struct terminal {
+
+  int    state;
+  int    trigger_idx;
+  size_t symbol_len;
+  char * symbol;
+
+} terminal;
+
+typedef struct buckethash {
+
+  int freq;
+
+} buckethash;
+
+int init_state;
+int curr_state;
+int final_state;
+int numstates;
+
+/*****************
+/ DYNAMIC ARRAY FOR WALKS
+*****************/
+
+typedef struct {
+
+  size_t    used;
+  size_t    size;
+  size_t    inputlen;
+  terminal *start;
+
+} Array;
+
+/*****************
+/ DYNAMIC ARRAY FOR STATEMAPS/RECURSION MAPS
+*****************/
+
+typedef struct {
+
+  int *  array;
+  size_t used;
+  size_t size;
+
+} IdxMap;
+
+typedef struct {
+
+  UT_array *nums;
+
+} IdxMap_new;
+
+typedef struct {
+
+  IdxMap_new *idxmap;
+  UT_array ** recurIdx;
+
+} Get_Dupes_Ret;
+
+/* Candidate Struct */
+typedef struct {
+
+  Array *     walk;
+  IdxMap_new *statemap;
+
+} Candidate;
+
+/* Splice Mutation helpers*/
+typedef struct {
+
+  Candidate *splice_cand;
+  int        idx;
+
+} SpliceCand;
+
+typedef struct {
+
+  SpliceCand *start;
+  size_t      used;
+  size_t      size;
+
+} SpliceCandArray;
+
+// Initialize dynamic array for potential splice points
+SpliceCand potential[SPLICE_CORPUS];
+
+typedef struct {
+
+  int orig_idx;
+  int splice_idx;
+
+} intpair_t;
+
+// Initialize dynamic array for potential splice points
+// SpliceCand potential[SPLICE_CORPUS];
+// IdxMap_new* rcuridx[STATES];
+
+/* Prototypes*/
+Array *    slice(Array *, int);
+state *    create_pda(u8 *);
+Array *    gen_input(state *, Array *);
+Array *    gen_input_count(state *, Array *, int *);
+int        updatebucket(map_t, int);
+void       itoa(int, char *, int);
+void       strrreverse(char *, char *);
+void       dbg_hashmap(map_t);
+void       print_repr(Array *, char *);
+int        isSatisfied(map_t);
+char *     get_state(char *);
+Candidate *gen_candidate(Array *);
+
+Array *spliceGF(Array *, Array *, int);
+Array *performSpliceOne(Array *, IdxMap_new *, Array *);
+/* Mutation Methods*/
+Array *    performRandomMutation(state *, Array *);
+Array *    performRandomMutationCount(state *, Array *, int *);
+Array *    performSpliceMutationBench(state *, Array *, Candidate **);
+UT_array **get_dupes(Array *, int *);
+Array *    doMult(Array *, UT_array **, int);
+Array *    doMultBench(Array *, UT_array **, int);
+
+/* Benchmarks*/
+void SpaceBenchmark(char *);
+void GenInputBenchmark(char *, char *);
+void RandomMutationBenchmark(char *, char *);
+void MutationAggrBenchmark(char *, char *);
+void SpliceMutationBenchmark(char *, char *);
+void SpliceMutationBenchmarkOne(char *, char *);
+void RandomRecursiveBenchmark(char *, char *);
+
+/* Testers */
+void SanityCheck(char *);
+
+/*Helpers*/
+void   initArray(Array *, size_t);
+void   insertArray(Array *, int, char *, size_t, int);
+void   freeArray(Array *);
+void   initArrayIdx(IdxMap *, size_t);
+void   insertArrayIdx(IdxMap *, int);
+void   freeArrayIdx(IdxMap *);
+void   initArraySplice(SpliceCandArray *, size_t);
+void   insertArraySplice(SpliceCandArray *, Candidate *, int);
+void   freeArraySplice(IdxMap *);
+void   getTwoIndices(UT_array *, int, int *, int *);
+void   swap(int *, int *);
+Array *slice_inverse(Array *, int);
+void   concatPrefixFeature(Array *, Array *);
+void   concatPrefixFeatureBench(Array *, Array *);
+Array *carve(Array *, int, int);
+int    fact(int);
+
+void                add_to_corpus(struct json_object *, Array *);
+struct json_object *term_to_json(terminal *);
+
+/* Gramatron specific prototypes */
+u8 *   unparse_walk(Array *);
+Array *performSpliceGF(state *, Array *, afl_state_t *);
+void   dump_input(u8 *, char *, int *);
+void   write_input(Array *, u8 *);
+Array *read_input(state *, u8 *);
+state *pda;
+
+// // AFL-specific struct
+// typedef uint8_t  u8;
+// typedef uint16_t u16;
+// typedef uint32_t u32;
+// #ifdef __x86_64__
+// typedef unsigned long long u64;
+// #else
+// typedef uint64_t u64;
+// #endif                                                    /* ^__x86_64__ */
+//
+// struct queue_entry {
+
+//   Array* walk;                           /* Pointer to the automaton walk*/
+//   u32 walk_len;                          /* Number of tokens in the input*/
+//   Candidate* cand;                     /* Preprocessed info about the
+//   candidate to allow for faster mutations*/
+//
+//   u8* fname;                          /* File name for the test case      */
+//   u32 len;                            /* Input length                     */
+//   UT_array** recur_idx;               /* Keeps track of recursive feature
+//   indices*/
+//
+//   u32 recur_len;                      /* The number of recursive features*/
+//
+//   u8  cal_failed,                     /* Calibration failed?              */
+//       trim_done,                      /* Trimmed?                         */
+//       was_fuzzed,                     /* Had any fuzzing done yet?        */
+//       passed_det,                     /* Deterministic stages passed?     */
+//       has_new_cov,                    /* Triggers new coverage?           */
+//       var_behavior,                   /* Variable behavior?               */
+//       favored,                        /* Currently favored?               */
+//       fs_redundant;                   /* Marked as redundant in the fs?   */
+//
+//   u32 bitmap_size,                    /* Number of bits set in bitmap     */
+//       exec_cksum;                     /* Checksum of the execution trace  */
+//
+//   u64 exec_us,                        /* Execution time (us)              */
+//       handicap,                       /* Number of queue cycles behind    */
+//       depth;                          /* Path depth                       */
+//
+//   u8* trace_mini;                     /* Trace bytes, if kept             */
+//   u32 tc_ref;                         /* Trace bytes ref count            */
+//
+//   struct queue_entry *next,           /* Next element, if any             */
+//                      *next_100;       /* 100 elements ahead               */
+//
+// };
+
+#endif
+

custom_mutators/gramatron/grammars/js/source.json

@@ -0,0 +1,606 @@
+{
+    "ARGLIST": [
+        "EXPR ',' ARGLIST",
+        "EXPR",
+        "EXPR ',' ARGLIST",
+        "EXPR"
+    ],
+    "ARGS": [
+        "'()'",
+        "'(' ARGLIST ')'",
+        "'()'",
+        "'(' ARGLIST ')'"
+    ],
+    "ARITHMETICOPERATION": [
+        "EXPR '/' EXPR",
+        "EXPR '*' EXPR",
+        "EXPR '+' EXPR",
+        "EXPR '-' EXPR",
+        "EXPR '%' EXPR",
+        "EXPR '**' EXPR",
+        "EXPR '++'"
+    ],
+    "ARRAY": [
+        "'[' ARRAYCONTENT ']'",
+        "'[]'"
+    ],
+    "ARRAYCONTENT": [
+        "EXPR ',' ARRAYCONTENT",
+        "EXPR"
+    ],
+    "BOOLEAN": [
+        "'true'",
+        "'false'"
+    ],
+    "BYTEWISEOPERATION": [
+        "EXPR '&' EXPR",
+        "EXPR '|' EXPR"
+    ],
+    "COMPARISONOPERATION": [
+        "EXPR '<' EXPR"
+    ],
+    "DECIMALDIGITS": [
+        "'20'",
+        "'1234'",
+        "'66'",
+        "'234_9'",
+        "'99999999999999999999'"
+    ],
+    "DECIMALNUMBER": [
+        "DECIMALDIGITS"
+    ],
+    "EXPR": [
+        "'(' EXPR ')'",
+        "VAR",
+        "'delete' SP EXPR",
+        "'new' SP IDENTIFIER ARGS",
+        "LITERAL",
+        "IDENTIFIER",
+        "METHODCALL",
+        "'(' ARITHMETICOPERATION ')'",
+        "'(' COMPARISONOPERATION ')'",
+        "'(' BYTEWISEOPERATION ')'",
+        "'(' LOGICALOPERATION ')'"
+    ],
+    "IDENTIFIER": [
+        "'Object'",
+        "VAR",
+        "'Function'",
+        "'main'",
+        "'opt'",
+        "'Boolean'",
+        "'Symbol'",
+        "'JSON'",
+        "'Error'",
+        "'EvalError'",
+        "'RangeError'",
+        "'ReferenceError'",
+        "'SyntaxError'",
+        "'TypeError'",
+        "'URIError'",
+        "'this'",
+        "'Number'",
+        "'Math'",
+        "'Date'",
+        "'String'",
+        "'RegExp'",
+        "'Array'",
+        "'Int8Array'",
+        "'Uint8Array'",
+        "'Uint8ClampedArray'",
+        "'Int16Array'",
+        "'Uint16Array'",
+        "'Int32Array'",
+        "'Uint32Array'",
+        "'Float32Array'",
+        "'Float64Array'",
+        "'DataView'",
+        "'ArrayBuffer'",
+        "'Map'",
+        "'Set'",
+        "'WeakMap'",
+        "'WeakSet'",
+        "'Promise'",
+        "'AsyncFunction'",
+        "'asyncGenerator'",
+        "'Reflect'",
+        "'Proxy'",
+        "'Intl'",
+        "'Intl.Collator'",
+        "'Intl.DateTimeFormat'",
+        "'Intl.NumberFormat'",
+        "'Intl.PluralRules'",
+        "'WebAssembly'",
+        "'WebAssembly.Module'",
+        "'WebAssembly.Instance'",
+        "'WebAssembly.Memory'",
+        "'WebAssembly.Table'",
+        "'WebAssembly.CompileError'",
+        "'WebAssembly.LinkError'",
+        "'WebAssembly.RuntimeError'",
+        "'arguments'",
+        "'Infinity'",
+        "'NaN'",
+        "'undefined'",
+        "'null'",
+        "'console'",
+        "' '"
+    ],
+    "IDENTIFIERLIST": [
+        "IDENTIFIER ',' IDENTIFIERLIST",
+        "'(' IDENTIFIERLIST '),' IDENTIFIERLIST",
+        "IDENTIFIER"
+    ],
+    "JSBLOCK": [
+        "JSSTATEMENT",
+        "JSSTATEMENT JSBLOCK"
+    ],
+    "JSSTATEMENT": [
+        "STATEMENT NEWLINE"
+    ],
+    "LITERAL": [
+        "'null'",
+        "BOOLEAN",
+        "NUMBER",
+        "ARRAY"
+    ],
+    "LOGICALOPERATION": [
+        "EXPR '&&' EXPR",
+        "EXPR '||' EXPR"
+    ],
+    "METHODCALL": [
+        "OBJECT PROPERTY METHODCALL1"
+    ],
+    "METHODCALL1": [
+        "'.' METHOD_NAME ARGS METHODCALL1",
+        "' '"
+    ],
+    "METHOD_NAME": [
+        "IDENTIFIER",
+        "'print'",
+        "'eval'",
+        "'uneval'",
+        "'isFinite'",
+        "'isNaN'",
+        "'parseFloat'",
+        "'parseInt'",
+        "'decodeURI'",
+        "'decodeURIComponent'",
+        "'encodeURI'",
+        "'encodeURIComponent'",
+        "'escape'",
+        "'unescape'",
+        "'assign'",
+        "'create'",
+        "'defineProperty'",
+        "'defineProperties'",
+        "'entries'",
+        "'freeze'",
+        "'getOwnPropertyDescriptor'",
+        "'getOwnPropertyDescriptors'",
+        "'getOwnPropertyNames'",
+        "'getOwnPropertySymbols'",
+        "'getPrototypeOf'",
+        "'is'",
+        "'isExtensible'",
+        "'isFrozen'",
+        "'isSealed'",
+        "'keys'",
+        "'preventExtensions'",
+        "'seal'",
+        "'setPrototypeOf'",
+        "'values'",
+        "'__defineGetter__'",
+        "'__defineSetter__'",
+        "'__lookupGetter__'",
+        "'__lookupSetter__'",
+        "'hasOwnProperty'",
+        "'isPrototypeOf'",
+        "'propertyIsEnumerable'",
+        "'toSource'",
+        "'toLocaleString'",
+        "'toString'",
+        "'unwatch'",
+        "'valueOf'",
+        "'watch'",
+        "'apply'",
+        "'bind'",
+        "'call'",
+        "'isGenerator'",
+        "'valueOf'",
+        "'for'",
+        "'keyFor'",
+        "'stringify'",
+        "'isInteger'",
+        "'isSafeInteger'",
+        "'toInteger'",
+        "'toExponential'",
+        "'toFixed'",
+        "'toLocaleString'",
+        "'toPrecision'",
+        "'abs'",
+        "'acos'",
+        "'acosh'",
+        "'asin'",
+        "'asinh'",
+        "'atan'",
+        "'atanh'",
+        "'atan2'",
+        "'cbrt'",
+        "'ceil'",
+        "'clz32'",
+        "'cos'",
+        "'cosh'",
+        "'exp'",
+        "'expm1'",
+        "'floor'",
+        "'fround'",
+        "'hypot'",
+        "'imul'",
+        "'log'",
+        "'log1p'",
+        "'log10'",
+        "'log2'",
+        "'max'",
+        "'min'",
+        "'pow'",
+        "'random'",
+        "'round'",
+        "'sign'",
+        "'sin'",
+        "'sinh'",
+        "'sqrt'",
+        "'tan'",
+        "'tanh'",
+        "'trunc'",
+        "'now'",
+        "'parse'",
+        "'UTC'",
+        "'getDate'",
+        "'getDay'",
+        "'getFullYear'",
+        "'getHours'",
+        "'getMilliseconds'",
+        "'getMinutes'",
+        "'getMonth'",
+        "'getSeconds'",
+        "'getTime'",
+        "'getTimezoneOffset'",
+        "'getUTCDate'",
+        "'getUTCDay'",
+        "'getUTCFullYear'",
+        "'getUTCHours'",
+        "'getUTCMilliseconds'",
+        "'getUTCMinutes'",
+        "'getUTCMonth'",
+        "'getUTCSeconds'",
+        "'getYear'",
+        "'setDate'",
+        "'setFullYear'",
+        "'setHours'",
+        "'setMilliseconds'",
+        "'setMinutes'",
+        "'setMonth'",
+        "'setSeconds'",
+        "'setTime'",
+        "'setUTCDate'",
+        "'setUTCFullYear'",
+        "'setUTCHours'",
+        "'setUTCMilliseconds'",
+        "'setUTCMinutes'",
+        "'setUTCMonth'",
+        "'setUTCSeconds'",
+        "'setYear'",
+        "'toDateString'",
+        "'toISOString'",
+        "'toJSON'",
+        "'toGMTString'",
+        "'toLocaleDateString'",
+        "'toLocaleFormat'",
+        "'toLocaleString'",
+        "'toLocaleTimeString'",
+        "'toTimeString'",
+        "'toUTCString'",
+        "'indexOf'",
+        "'substring'",
+        "'charAt'",
+        "'strcmp'",
+        "'fromCharCode'",
+        "'fromCodePoint'",
+        "'raw'",
+        "'charCodeAt'",
+        "'slice'",
+        "'codePointAt'",
+        "'concat'",
+        "'includes'",
+        "'endsWith'",
+        "'lastIndexOf'",
+        "'localeCompare'",
+        "'match'",
+        "'normalize'",
+        "'padEnd'",
+        "'padStart'",
+        "'quote'",
+        "'repeat'",
+        "'replace'",
+        "'search'",
+        "'split'",
+        "'startsWith'",
+        "'substr'",
+        "'toLocaleLowerCase'",
+        "'toLocaleUpperCase'",
+        "'toLowerCase'",
+        "'toUpperCase'",
+        "'trim'",
+        "'trimleft'",
+        "'trimright'",
+        "'anchor'",
+        "'big'",
+        "'blink'",
+        "'bold'",
+        "'fixed'",
+        "'fontcolor'",
+        "'fontsize'",
+        "'italics'",
+        "'link'",
+        "'small'",
+        "'strike'",
+        "'sub'",
+        "'sup'",
+        "'compile'",
+        "'exec'",
+        "'test'",
+        "'from'",
+        "'isArray'",
+        "'of'",
+        "'copyWithin'",
+        "'fill'",
+        "'pop'",
+        "'push'",
+        "'reverse'",
+        "'shift'",
+        "'sort'",
+        "'splice'",
+        "'unshift'",
+        "'concat'",
+        "'join'",
+        "'every'",
+        "'filter'",
+        "'findIndex'",
+        "'forEach'",
+        "'map'",
+        "'reduce'",
+        "'reduceRight'",
+        "'some'",
+        "'move'",
+        "'getInt8'",
+        "'getUint8'",
+        "'getInt16'",
+        "'getUint16'",
+        "'getInt32'",
+        "'getUint32'",
+        "'getFloat32'",
+        "'getFloat64'",
+        "'setInt8'",
+        "'setUint8'",
+        "'setInt16'",
+        "'setUint16'",
+        "'setInt32'",
+        "'setUint32'",
+        "'setFloat32'",
+        "'setFloat64'",
+        "'isView'",
+        "'transfer'",
+        "'clear'",
+        "'get'",
+        "'has'",
+        "'set'",
+        "'add'",
+        "'splat'",
+        "'check'",
+        "'extractLane'",
+        "'replaceLane'",
+        "'load'",
+        "'load1'",
+        "'load2'",
+        "'load3'",
+        "'store'",
+        "'store1'",
+        "'store2'",
+        "'store3'",
+        "'addSaturate'",
+        "'div'",
+        "'mul'",
+        "'neg'",
+        "'reciprocalApproximation'",
+        "'reciprocalSqrtApproximation'",
+        "'subSaturate'",
+        "'shuffle'",
+        "'swizzle'",
+        "'maxNum'",
+        "'minNum'",
+        "'select'",
+        "'equal'",
+        "'notEqual'",
+        "'lessThan'",
+        "'lessThanOrEqual'",
+        "'greaterThan'",
+        "'greaterThanOrEqual'",
+        "'and'",
+        "'or'",
+        "'xor'",
+        "'not'",
+        "'shiftLeftByScalar'",
+        "'shiftRightByScalar'",
+        "'allTrue'",
+        "'anyTrue'",
+        "'fromFloat32x4'",
+        "'fromFloat32x4Bits'",
+        "'fromFloat64x2Bits'",
+        "'fromInt32x4'",
+        "'fromInt32x4Bits'",
+        "'fromInt16x8Bits'",
+        "'fromInt8x16Bits'",
+        "'fromUint32x4'",
+        "'fromUint32x4Bits'",
+        "'fromUint16x8Bits'",
+        "'fromUint8x16Bits'",
+        "'neg'",
+        "'compareExchange'",
+        "'exchange'",
+        "'wait'",
+        "'wake'",
+        "'isLockFree'",
+        "'all'",
+        "'race'",
+        "'reject'",
+        "'resolve'",
+        "'catch'",
+        "'then'",
+        "'finally'",
+        "'next'",
+        "'throw'",
+        "'close'",
+        "'send'",
+        "'apply'",
+        "'construct'",
+        "'deleteProperty'",
+        "'ownKeys'",
+        "'getCanonicalLocales'",
+        "'supportedLocalesOf'",
+        "'resolvedOptions'",
+        "'formatToParts'",
+        "'resolvedOptions'",
+        "'instantiate'",
+        "'instantiateStreaming'",
+        "'compileStreaming'",
+        "'validate'",
+        "'customSections'",
+        "'exports'",
+        "'imports'",
+        "'grow'",
+        "'super'",
+        "'in'",
+        "'instanceof'",
+        "' '"
+    ],
+    "NEWLINE": [
+        "'\\n'"
+    ],
+    "NUMBER": [
+        "'1/2'",
+        "'1E2'",
+        "'1E02'",
+        "'1E+02'",
+        "'-1'",
+        "'-1.00'",
+        "'-1/2'",
+        "'-1E2'",
+        "'-1E02'",
+        "'-1E+02'",
+        "'1/0'",
+        "'0/0'",
+        "'-2147483648/-1'",
+        "'-9223372036854775808/-1'",
+        "'-0'",
+        "'-0.0'",
+        "'+0'"
+    ],
+    "OBJECT": [
+        "IDENTIFIER"
+    ],
+    "PROGRAM": [
+        "JSBLOCK"
+    ],
+    "PROPERTY": [
+        "'.length' PROPERTY",
+        "'.prototype' PROPERTY",
+        "'.constructor' PROPERTY",
+        "'.__proto__' PROPERTY",
+        "'.__noSuchMethod__' PROPERTY",
+        "'.__count__' PROPERTY",
+        "'.__parent__' PROPERTY",
+        "'.arguments' PROPERTY",
+        "'.arity' PROPERTY",
+        "'.caller' PROPERTY",
+        "'.name' PROPERTY",
+        "'.displayName' PROPERTY",
+        "'.iterator' PROPERTY",
+        "'.asyncIterator' PROPERTY",
+        "'.match' PROPERTY",
+        "'.replace' PROPERTY",
+        "'.search' PROPERTY",
+        "'.split' PROPERTY",
+        "'.hasInstance' PROPERTY",
+        "'.isConcatSpreadable' PROPERTY",
+        "'.unscopables' PROPERTY",
+        "'.species' PROPERTY",
+        "'.toPrimitive' PROPERTY",
+        "'.toStringTag' PROPERTY",
+        "'.fileName' PROPERTY",
+        "'.lineNumber' PROPERTY",
+        "'.columnNumber' PROPERTY",
+        "'.message' PROPERTY",
+        "'.name' PROPERTY",
+        "'.EPSILON' PROPERTY",
+        "'.MAX_SAFE_INTEGER' PROPERTY",
+        "'.MAX_VALUE' PROPERTY",
+        "'.MIN_SAFE_INTEGER' PROPERTY",
+        "'.MIN_VALUE' PROPERTY",
+        "'.NaN' PROPERTY",
+        "'.NEGATIVE_INFINITY' PROPERTY",
+        "'.POSITIVE_INFINITY' PROPERTY",
+        "'.E' PROPERTY",
+        "'.LN2' PROPERTY",
+        "'.LN10' PROPERTY",
+        "'.LOG2E' PROPERTY",
+        "'.LOG10E' PROPERTY",
+        "'.PI' PROPERTY",
+        "'.SQRT1_2' PROPERTY",
+        "'.SQRT2' PROPERTY",
+        "'.flags' PROPERTY",
+        "'.global' PROPERTY",
+        "'.ignoreCase' PROPERTY",
+        "'.multiline' PROPERTY",
+        "'.source' PROPERTY",
+        "'.sticky' PROPERTY",
+        "'.unicode' PROPERTY",
+        "'.buffer' PROPERTY",
+        "'.byteLength' PROPERTY",
+        "'.byteOffset' PROPERTY",
+        "'.BYTES_PER_ELEMENT' PROPERTY",
+        "'.compare' PROPERTY",
+        "'.format' PROPERTY",
+        "'.callee' PROPERTY",
+        "'.caller' PROPERTY",
+        "'.memory' PROPERTY",
+        "'.exports' PROPERTY",
+        "' '"
+    ],
+    "SP": [
+        "' '"
+    ],
+    "STATEMENT": [
+        "EXPR ';'",
+        "'var' SP VAR '=' EXPR ';'",
+        "'let' SP VAR '=' EXPR ';'",
+        "VAR '=' EXPR ';'",
+        "VAR PROPERTY '=' EXPR ';'",
+        "VAR '[' DECIMALNUMBER ']' '=' EXPR ';'",
+        "'const' SP VAR '=' EXPR ';'",
+        "'typeof' SP EXPR ';'",
+        "'void' SP EXPR ';'",
+        "'return' SP EXPR ';'",
+        "VAR ':'"
+    ],
+    "VAR": [
+        "'a'",
+        "'b'",
+        "'c'",
+        "'d'",
+        "'e'",
+        "'f'",
+        "'g'",
+        "'h'"
+    ]
+}

custom_mutators/gramatron/hashmap.c

@@ -0,0 +1,434 @@
+/*
+ * Generic map implementation.
+ */
+#include "hashmap.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#define INITIAL_SIZE (256)
+#define MAX_CHAIN_LENGTH (8)
+
+/* We need to keep keys and values */
+typedef struct _hashmap_element {
+
+  char *key;
+  int   in_use;
+  any_t data;
+
+} hashmap_element;
+
+/* A hashmap has some maximum size and current size,
+ * as well as the data to hold. */
+typedef struct _hashmap_map {
+
+  int              table_size;
+  int              size;
+  hashmap_element *data;
+
+} hashmap_map;
+
+/*
+ * Return an empty hashmap, or NULL on failure.
+ */
+map_t hashmap_new() {
+
+  hashmap_map *m = (hashmap_map *)malloc(sizeof(hashmap_map));
+  if (!m) goto err;
+
+  m->data = (hashmap_element *)calloc(INITIAL_SIZE, sizeof(hashmap_element));
+  if (!m->data) goto err;
+
+  m->table_size = INITIAL_SIZE;
+  m->size = 0;
+
+  return m;
+err:
+  if (m) hashmap_free(m);
+  return NULL;
+
+}
+
+/* The implementation here was originally done by Gary S. Brown.  I have
+   borrowed the tables directly, and made some minor changes to the
+   crc32-function (including changing the interface). //ylo */
+
+/* ============================================================= */
+/*  COPYRIGHT (C) 1986 Gary S. Brown.  You may use this program, or       */
+/*  code or tables extracted from it, as desired without restriction.     */
+/*                                                                        */
+/*  First, the polynomial itself and its table of feedback terms.  The    */
+/*  polynomial is                                                         */
+/*  X^32+X^26+X^23+X^22+X^16+X^12+X^11+X^10+X^8+X^7+X^5+X^4+X^2+X^1+X^0   */
+/*                                                                        */
+/*  Note that we take it "backwards" and put the highest-order term in    */
+/*  the lowest-order bit.  The X^32 term is "implied"; the LSB is the     */
+/*  X^31 term, etc.  The X^0 term (usually shown as "+1") results in      */
+/*  the MSB being 1.                                                      */
+/*                                                                        */
+/*  Note that the usual hardware shift register implementation, which     */
+/*  is what we're using (we're merely optimizing it by doing eight-bit    */
+/*  chunks at a time) shifts bits into the lowest-order term.  In our     */
+/*  implementation, that means shifting towards the right.  Why do we     */
+/*  do it this way?  Because the calculated CRC must be transmitted in    */
+/*  order from highest-order term to lowest-order term.  UARTs transmit   */
+/*  characters in order from LSB to MSB.  By storing the CRC this way,    */
+/*  we hand it to the UART in the order low-byte to high-byte; the UART   */
+/*  sends each low-bit to hight-bit; and the result is transmission bit   */
+/*  by bit from highest- to lowest-order term without requiring any bit   */
+/*  shuffling on our part.  Reception works similarly.                    */
+/*                                                                        */
+/*  The feedback terms table consists of 256, 32-bit entries.  Notes:     */
+/*                                                                        */
+/*      The table can be generated at runtime if desired; code to do so   */
+/*      is shown later.  It might not be obvious, but the feedback        */
+/*      terms simply represent the results of eight shift/xor opera-      */
+/*      tions for all combinations of data and CRC register values.       */
+/*                                                                        */
+/*      The values must be right-shifted by eight bits by the "updcrc"    */
+/*      logic; the shift must be unsigned (bring in zeroes).  On some     */
+/*      hardware you could probably optimize the shift in assembler by    */
+/*      using byte-swap instructions.                                     */
+/*      polynomial $edb88320                                              */
+/*                                                                        */
+/*  --------------------------------------------------------------------  */
+
+static unsigned long crc32_tab[] = {
+
+    0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L,
+    0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L,
+    0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L,
+    0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL,
+    0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L,
+    0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L,
+    0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L,
+    0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL,
+    0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L,
+    0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL,
+    0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L,
+    0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L,
+    0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L,
+    0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL,
+    0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL,
+    0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L,
+    0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL,
+    0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L,
+    0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L,
+    0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L,
+    0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL,
+    0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L,
+    0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L,
+    0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL,
+    0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L,
+    0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L,
+    0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L,
+    0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L,
+    0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L,
+    0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL,
+    0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL,
+    0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L,
+    0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L,
+    0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL,
+    0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL,
+    0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L,
+    0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL,
+    0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L,
+    0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL,
+    0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L,
+    0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL,
+    0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L,
+    0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L,
+    0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL,
+    0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L,
+    0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L,
+    0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L,
+    0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L,
+    0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L,
+    0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L,
+    0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL,
+    0x2d02ef8dL};
+
+/* Return a 32-bit CRC of the contents of the buffer. */
+
+unsigned long crc32(const unsigned char *s, unsigned int len) {
+
+  unsigned int  i;
+  unsigned long crc32val;
+
+  crc32val = 0;
+  for (i = 0; i < len; i++) {
+
+    crc32val = crc32_tab[(crc32val ^ s[i]) & 0xff] ^ (crc32val >> 8);
+
+  }
+
+  return crc32val;
+
+}
+
+/*
+ * Hashing function for a string
+ */
+unsigned int hashmap_hash_int(hashmap_map *m, char *keystring) {
+
+  unsigned long key = crc32((unsigned char *)(keystring), strlen(keystring));
+
+  /* Robert Jenkins' 32 bit Mix Function */
+  key += (key << 12);
+  key ^= (key >> 22);
+  key += (key << 4);
+  key ^= (key >> 9);
+  key += (key << 10);
+  key ^= (key >> 2);
+  key += (key << 7);
+  key ^= (key >> 12);
+
+  /* Knuth's Multiplicative Method */
+  key = (key >> 3) * 2654435761;
+
+  return key % m->table_size;
+
+}
+
+/*
+ * Return the integer of the location in data
+ * to store the point to the item, or MAP_FULL.
+ */
+int hashmap_hash(map_t in, char *key) {
+
+  int curr;
+  int i;
+
+  /* Cast the hashmap */
+  hashmap_map *m = (hashmap_map *)in;
+
+  /* If full, return immediately */
+  if (m->size >= (m->table_size / 2)) return MAP_FULL;
+
+  /* Find the best index */
+  curr = hashmap_hash_int(m, key);
+
+  /* Linear probing */
+  for (i = 0; i < MAX_CHAIN_LENGTH; i++) {
+
+    if (m->data[curr].in_use == 0) return curr;
+
+    if (m->data[curr].in_use == 1 && (strcmp(m->data[curr].key, key) == 0))
+      return curr;
+
+    curr = (curr + 1) % m->table_size;
+
+  }
+
+  return MAP_FULL;
+
+}
+
+/*
+ * Doubles the size of the hashmap, and rehashes all the elements
+ */
+int hashmap_rehash(map_t in) {
+
+  int              i;
+  int              old_size;
+  hashmap_element *curr;
+
+  /* Setup the new elements */
+  hashmap_map *    m = (hashmap_map *)in;
+  hashmap_element *temp =
+      (hashmap_element *)calloc(2 * m->table_size, sizeof(hashmap_element));
+  if (!temp) return MAP_OMEM;
+
+  /* Update the array */
+  curr = m->data;
+  m->data = temp;
+
+  /* Update the size */
+  old_size = m->table_size;
+  m->table_size = 2 * m->table_size;
+  m->size = 0;
+
+  /* Rehash the elements */
+  for (i = 0; i < old_size; i++) {
+
+    int status;
+
+    if (curr[i].in_use == 0) continue;
+
+    status = hashmap_put(m, curr[i].key, curr[i].data);
+    if (status != MAP_OK) return status;
+
+  }
+
+  free(curr);
+
+  return MAP_OK;
+
+}
+
+/*
+ * Add a pointer to the hashmap with some key
+ */
+int hashmap_put(map_t in, char *key, any_t value) {
+
+  int          index;
+  hashmap_map *m;
+
+  /* Cast the hashmap */
+  m = (hashmap_map *)in;
+
+  /* Find a place to put our value */
+  index = hashmap_hash(in, key);
+  while (index == MAP_FULL) {
+
+    if (hashmap_rehash(in) == MAP_OMEM) { return MAP_OMEM; }
+    index = hashmap_hash(in, key);
+
+  }
+
+  /* Set the data */
+  m->data[index].data = value;
+  m->data[index].key = key;
+  m->data[index].in_use = 1;
+  m->size++;
+
+  return MAP_OK;
+
+}
+
+/*
+ * Get your pointer out of the hashmap with a key
+ */
+int hashmap_get(map_t in, char *key, any_t *arg) {
+
+  int          curr;
+  int          i;
+  hashmap_map *m;
+
+  /* Cast the hashmap */
+  m = (hashmap_map *)in;
+
+  /* Find data location */
+  curr = hashmap_hash_int(m, key);
+
+  /* Linear probing, if necessary */
+  for (i = 0; i < MAX_CHAIN_LENGTH; i++) {
+
+    int in_use = m->data[curr].in_use;
+    if (in_use == 1) {
+
+      if (strcmp(m->data[curr].key, key) == 0) {
+
+        *arg = (m->data[curr].data);
+        return MAP_OK;
+
+      }
+
+    }
+
+    curr = (curr + 1) % m->table_size;
+
+  }
+
+  *arg = NULL;
+
+  /* Not found */
+  return MAP_MISSING;
+
+}
+
+/*
+ * Iterate the function parameter over each element in the hashmap.  The
+ * additional any_t argument is passed to the function as its first
+ * argument and the hashmap element is the second.
+ */
+int hashmap_iterate(map_t in, PFany f, any_t item) {
+
+  int i;
+
+  /* Cast the hashmap */
+  hashmap_map *m = (hashmap_map *)in;
+
+  /* On empty hashmap, return immediately */
+  if (hashmap_length(m) <= 0) return MAP_MISSING;
+
+  /* Linear probing */
+  for (i = 0; i < m->table_size; i++)
+    if (m->data[i].in_use != 0) {
+
+      any_t data = (any_t)(m->data[i].data);
+      int   status = f(item, data);
+      if (status != MAP_OK) { return status; }
+
+    }
+
+  return MAP_OK;
+
+}
+
+/*
+ * Remove an element with that key from the map
+ */
+int hashmap_remove(map_t in, char *key) {
+
+  int          i;
+  int          curr;
+  hashmap_map *m;
+
+  /* Cast the hashmap */
+  m = (hashmap_map *)in;
+
+  /* Find key */
+  curr = hashmap_hash_int(m, key);
+
+  /* Linear probing, if necessary */
+  for (i = 0; i < MAX_CHAIN_LENGTH; i++) {
+
+    int in_use = m->data[curr].in_use;
+    if (in_use == 1) {
+
+      if (strcmp(m->data[curr].key, key) == 0) {
+
+        /* Blank out the fields */
+        m->data[curr].in_use = 0;
+        m->data[curr].data = NULL;
+        m->data[curr].key = NULL;
+
+        /* Reduce the size */
+        m->size--;
+        return MAP_OK;
+
+      }
+
+    }
+
+    curr = (curr + 1) % m->table_size;
+
+  }
+
+  /* Data not found */
+  return MAP_MISSING;
+
+}
+
+/* Deallocate the hashmap */
+void hashmap_free(map_t in) {
+
+  hashmap_map *m = (hashmap_map *)in;
+  free(m->data);
+  free(m);
+
+}
+
+/* Return the length of the hashmap */
+int hashmap_length(map_t in) {
+
+  hashmap_map *m = (hashmap_map *)in;
+  if (m != NULL)
+    return m->size;
+  else
+    return 0;
+
+}
+

custom_mutators/gramatron/hashmap.h

@@ -0,0 +1,83 @@
+/*
+ * Generic hashmap manipulation functions
+ *
+ * Originally by Elliot C Back -
+ * http://elliottback.com/wp/hashmap-implementation-in-c/
+ *
+ * Modified by Pete Warden to fix a serious performance problem, support strings
+ * as keys and removed thread synchronization - http://petewarden.typepad.com
+ */
+#ifndef __HASHMAP_H__
+#define __HASHMAP_H__
+
+#define MAP_MISSING -3                                   /* No such element */
+#define MAP_FULL -2                                      /* Hashmap is full */
+#define MAP_OMEM -1                                        /* Out of Memory */
+#define MAP_OK 0                                                      /* OK */
+
+/*
+ * any_t is a pointer.  This allows you to put arbitrary structures in
+ * the hashmap.
+ */
+typedef void *any_t;
+
+/*
+ * PFany is a pointer to a function that can take two any_t arguments
+ * and return an integer. Returns status code..
+ */
+typedef int (*PFany)(any_t, any_t);
+
+/*
+ * map_t is a pointer to an internally maintained data structure.
+ * Clients of this package do not need to know how hashmaps are
+ * represented.  They see and manipulate only map_t's.
+ */
+typedef any_t map_t;
+
+/*
+ * Return an empty hashmap. Returns NULL if empty.
+ */
+extern map_t hashmap_new();
+
+/*
+ * Iteratively call f with argument (item, data) for
+ * each element data in the hashmap. The function must
+ * return a map status code. If it returns anything other
+ * than MAP_OK the traversal is terminated. f must
+ * not reenter any hashmap functions, or deadlock may arise.
+ */
+extern int hashmap_iterate(map_t in, PFany f, any_t item);
+
+/*
+ * Add an element to the hashmap. Return MAP_OK or MAP_OMEM.
+ */
+extern int hashmap_put(map_t in, char *key, any_t value);
+
+/*
+ * Get an element from the hashmap. Return MAP_OK or MAP_MISSING.
+ */
+extern int hashmap_get(map_t in, char *key, any_t *arg);
+
+/*
+ * Remove an element from the hashmap. Return MAP_OK or MAP_MISSING.
+ */
+extern int hashmap_remove(map_t in, char *key);
+
+/*
+ * Get any element. Return MAP_OK or MAP_MISSING.
+ * remove - should the element be removed from the hashmap
+ */
+extern int hashmap_get_one(map_t in, any_t *arg, int remove);
+
+/*
+ * Free the hashmap
+ */
+extern void hashmap_free(map_t in);
+
+/*
+ * Get the current size of a hashmap
+ */
+extern int hashmap_length(map_t in);
+
+#endif
+

custom_mutators/gramatron/preprocess/construct_automata.py

@@ -0,0 +1,275 @@
+import sys
+import json
+import re
+from collections import defaultdict
+# import pygraphviz as pgv
+
+gram_data = None
+state_count = 1
+pda = []
+worklist = []
+state_stacks = {} 
+
+# === If user provides upper bound on the stack size during FSA creation ===
+# Specifies the upper bound to which the stack is allowed to grow
+# If for any generated state, the stack size is >= stack_limit then this
+# state is not expanded further.
+stack_limit = None 
+# Holds the set of unexpanded rules owing to the user-passed stack constraint limit
+unexpanded_rules = set()
+
+def main(grammar, limit):
+    global worklist, gram_data, stack_limit
+    current = '0'
+    stack_limit = limit
+    if stack_limit:
+        print ('[X] Operating in bounded stack mode')
+
+    with open(grammar, 'r') as fd:
+        gram_data = json.load(fd)
+    start_symbol = gram_data["Start"][0]
+    worklist.append([current, [start_symbol]])
+    # print (grammar)
+    filename = (grammar.split('/')[-1]).split('.')[0]
+    
+
+    while worklist:
+        # Take an element from the worklist
+        # print ('================')
+        # print ('Worklist:', worklist)
+        element = worklist.pop(0)
+        prep_transitions(element)
+    
+    pda_file = filename + '_transition.json'
+    graph_file = filename + '.png'
+    # print ('XXXXXXXXXXXXXXXX')
+    # print ('PDA file:%s Png graph file:%s' % (pda_file, graph_file))
+    # XXX Commented out because visualization of current version of PHP causes segfault
+    # Create the graph and dump the transitions to a file
+    # create_graph(filename)
+    transformed = postprocess()
+    with open(filename + '_automata.json', 'w+') as fd:
+        json.dump(transformed, fd)
+    with open(filename + '_transition.json', 'w+') as fd:
+        json.dump(pda, fd)
+    if not unexpanded_rules:
+        print ('[X] No unexpanded rules, absolute FSA formed')
+        exit(0)
+    else:
+        print ('[X] Certain rules were not expanded due to stack size limit. Inexact approximation has been created and the disallowed rules have been put in {}_disallowed.json'.format(filename))
+        print ('[X] Number of unexpanded rules:', len(unexpanded_rules))
+        with open(filename + '_disallowed.json', 'w+') as fd:
+            json.dump(list(unexpanded_rules), fd)
+
+def create_graph(filename):
+    '''
+    Creates a DOT representation of the PDA
+    '''
+    global pda
+    G = pgv.AGraph(strict = False, directed = True)
+    for transition in pda:
+        print ('Transition:', transition)
+        G.add_edge(transition['source'], transition['dest'], 
+                label = 'Term:{}'.format(transition['terminal']))
+    G.layout(prog = 'dot')
+    print ('Do it up 2')
+    G.draw(filename + '.png')
+
+def prep_transitions(element):
+    '''
+    Generates transitions
+    '''
+    global gram_data, state_count, pda, worklist, state_stacks, stack_limit, unexpanded_rules
+    state = element[0]
+    try:
+        nonterminal = element[1][0] 
+    except IndexError:
+        # Final state was encountered, pop from worklist without doing anything
+        return
+    rules = gram_data[nonterminal]
+    count = 1
+    for rule in rules:
+        isRecursive  = False
+        # print ('Current state:', state)
+        terminal, ss, termIsRegex = tokenize(rule)
+        transition = get_template()
+        transition['trigger'] = '_'.join([state, str(count)])
+        transition['source'] = state
+        transition['dest'] = str(state_count) 
+        transition['ss'] = ss 
+        transition['terminal'] = terminal
+        transition['rule'] = "{} -> {}".format(nonterminal, rule )
+        if termIsRegex:
+            transition['termIsRegex'] = True
+        
+        # Creating a state stack for the new state
+        try:
+            state_stack = state_stacks[state][:]
+        except:
+            state_stack = []
+        if len(state_stack):
+            state_stack.pop(0)
+        if ss:
+            for symbol in ss[::-1]:
+                state_stack.insert(0, symbol)
+        transition['stack'] = state_stack 
+
+        # Check if a recursive transition state being created, if so make a backward
+        # edge and don't add anything to the worklist
+        # print (state_stacks)
+        if state_stacks:
+            for state_element, stack in state_stacks.items():
+                # print ('Stack:', sorted(stack))
+                # print ('State stack:', sorted(state_stack))
+                if sorted(stack) == sorted(state_stack):
+                    transition['dest'] = state_element
+                    # print ('Recursive:', transition)
+                    pda.append(transition)
+                    count += 1
+                    isRecursive = True
+                    break 
+        # If a recursive transition exercised don't add the same transition as a new
+        # edge, continue onto the next transitions
+        if isRecursive:
+            continue
+            
+        # If the generated state has a stack size > stack_limit then that state is abandoned
+        # and not added to the FSA or the worklist for further expansion
+        if stack_limit:
+            if (len(transition['stack']) > stack_limit):
+                unexpanded_rules.add(transition['rule'])
+                continue
+
+        # Create transitions for the non-recursive relations and add to the worklist
+        # print ('Normal:', transition)
+        # print ('State2:', state)
+        pda.append(transition)
+        worklist.append([transition['dest'], transition['stack']])
+        state_stacks[transition['dest']] = state_stack
+        state_count += 1
+        count += 1
+
+def tokenize(rule):
+    '''
+    Gets the terminal and the corresponding stack symbols from a rule in GNF form
+    '''
+    pattern = re.compile("([r])*\'([\s\S]+)\'([\s\S]*)")
+    terminal = None
+    ss = None
+    termIsRegex = False
+    match = pattern.match(rule)
+    if match.group(1):
+        termIsRegex = True
+    if match.group(2):
+        terminal = match.group(2)
+    else:
+        raise AssertionError("Rule is not in GNF form")
+
+    if match.group(3):
+        ss = (match.group(3)).split()
+
+    return terminal, ss, termIsRegex
+
+def get_template():
+    transition_template = {
+            'trigger':None,
+            'source': None,
+            'dest': None,
+            'termIsRegex': False,
+            'terminal' : None,
+            'stack': []
+            }
+    return transition_template
+
+def postprocess():
+    '''
+    Creates a representation to be passed on to the C-module
+    '''
+    global pda
+    final_struct = {}
+    memoized = defaultdict(list)
+    # Supporting data structures for if stack limit is imposed
+    culled_pda = []
+    culled_final = []
+    num_transitions = 0 # Keep track of number of transitions
+
+
+    states, final, initial = _get_states()
+
+    print (initial)
+    assert len(initial) == 1, 'More than one init state found'
+
+    # Cull transitions to states which were not expanded owing to the stack limit
+    if stack_limit:
+
+        blocklist = []
+        for final_state in final:
+            for transition in pda:
+                if (transition["dest"] == final_state) and (len(transition["stack"]) > 0):
+                    blocklist.append(transition["dest"])
+                    continue
+                else:
+                    culled_pda.append(transition)
+        
+        culled_final = [state for state in final if state not in blocklist]
+
+        assert len(culled_final) == 1, 'More than one final state found'
+
+        for transition in culled_pda:
+            state = transition["source"]
+            if transition["dest"] in blocklist:
+                    continue 
+            num_transitions += 1
+            memoized[state].append([transition["trigger"], transition["dest"], 
+                transition["terminal"]])
+        final_struct["init_state"] = initial
+        final_struct["final_state"] = culled_final[0]
+        # The reason we do this is because when states are culled, the indexing is
+        # still relative to the actual number of states hence we keep numstates recorded
+        # as the original number of states
+        print ('[X] Actual Number of states:', len(memoized.keys()))
+        print ('[X] Number of transitions:', num_transitions)
+        print ('[X] Original Number of states:', len(states))
+        final_struct["numstates"] = len(states) 
+        final_struct["pda"] = memoized
+        return final_struct
+    
+    # Running FSA construction in exact approximation mode and postprocessing it like so
+    for transition in pda:
+       state = transition["source"]
+       memoized[state].append([transition["trigger"], transition["dest"], 
+           transition["terminal"]])
+
+    final_struct["init_state"] = initial
+    final_struct["final_state"] = final[0]
+    print ('[X] Actual Number of states:', len(memoized.keys()))
+    final_struct["numstates"] = len(memoized.keys()) 
+    final_struct["pda"] = memoized
+    return final_struct
+
+
+def _get_states():
+    source = set()
+    dest = set()
+    global pda
+    for transition in pda:
+        source.add(transition["source"])
+        dest.add(transition["dest"])
+    source_copy = source.copy()
+    source_copy.update(dest)
+    return list(source_copy), list(dest.difference(source)), str(''.join(list(source.difference(dest))))
+
+if __name__ == '__main__':
+    import argparse
+    parser = argparse.ArgumentParser(description = 'Script to convert GNF grammar to PDA')
+    parser.add_argument(
+            '--gf',
+            type = str,
+            help = 'Location of GNF grammar')
+    parser.add_argument(
+            '--limit',
+            type = int,
+            default = None,
+            help = 'Specify the upper bound for the stack size')
+    args = parser.parse_args()
+    main(args.gf, args.limit)

custom_mutators/gramatron/preprocess/gnf_converter.py

@@ -0,0 +1,289 @@
+import sys
+import re
+import copy
+import json
+from string import ascii_uppercase
+from itertools import combinations
+from collections import defaultdict
+
+NONTERMINALSET = []
+COUNT = 1
+
+def main(grammar_file, out, start):
+    grammar = None
+    # If grammar file is a preprocessed NT file, then skip preprocessing
+    if '.json' in grammar_file:
+        with open(grammar_file, 'r') as fd:
+            grammar = json.load(fd)
+    elif '.g4' in grammar_file:
+        with open(grammar_file, 'r') as fd:
+            data = fd.readlines()
+        grammar = preprocess(data)
+    else:
+        raise('Unknwown file format passed. Accepts (.g4/.json)')
+
+    with open('debug_preprocess.json', 'w+') as fd:
+        json.dump(grammar, fd)
+    grammar = remove_unit(grammar) # eliminates unit productions
+    with open('debug_unit.json', 'w+') as fd:
+        json.dump(grammar, fd)
+    grammar = remove_mixed(grammar) # eliminate terminals existing with non-terminals
+    with open('debug_mixed.json', 'w+') as fd:
+        json.dump(grammar, fd)
+    grammar = break_rules(grammar) # eliminate rules with more than two non-terminals
+    with open('debug_break.json', 'w+') as fd:
+        json.dump(grammar, fd)
+    grammar = gnf(grammar)
+
+    # Dump GNF form of the grammar with only reachable rules 
+    # reachable_grammar = get_reachable(grammar, start)
+    # with open('debug_gnf_reachable.json', 'w+') as fd:
+    #     json.dump(reachable_grammar, fd)
+    with open('debug_gnf.json', 'w+') as fd:
+        json.dump(grammar, fd)
+
+    grammar["Start"] = [start]
+    with open(out, 'w+') as fd:
+        json.dump(grammar, fd)
+
+def get_reachable(grammar, start):
+    '''
+    Returns a grammar without dead rules
+    '''
+    reachable_nt = set()
+    worklist = list()
+    processed = set()
+    reachable_grammar = dict()
+    worklist.append(start)
+
+    while worklist:
+        nt = worklist.pop(0)
+        processed.add(nt)
+        reachable_grammar[nt] = grammar[nt]
+        rules = grammar[nt]
+        for rule in rules:
+            tokens = gettokens(rule)
+            for token in tokens:
+                if not isTerminal(token):
+                    if token not in processed:
+                        worklist.append(token)
+    return reachable_grammar
+
+
+def gettokens(rule):
+    pattern = re.compile("([^\s\"\']+)|\"([^\"]*)\"|\'([^\']*)\'")
+    return [matched.group(0) for matched in pattern.finditer(rule)]
+
+def gnf(grammar):
+    old_grammar = copy.deepcopy(grammar)
+    new_grammar = defaultdict(list)
+    isgnf = False
+    while not isgnf:
+        for lhs, rules in old_grammar.items():
+            for rule in rules:
+                tokens = gettokens(rule) 
+                if len(tokens) == 1 and isTerminal(rule):
+                    new_grammar[lhs].append(rule)
+                    continue
+                startoken = tokens[0]
+                endrule = tokens[1:]
+                if not isTerminal(startoken):
+                    newrules = []
+                    extendrules = old_grammar[startoken]
+                    for extension in extendrules:
+                        temprule = endrule[:]
+                        temprule.insert(0, extension)
+                        newrules.append(temprule)
+                    for newnew in newrules:
+                        new_grammar[lhs].append(' '.join(newnew))
+                else:
+                    new_grammar[lhs].append(rule)
+        isgnf = True
+        for lhs, rules in new_grammar.items():
+            for rule in rules:
+                # if "\' \'" or isTerminal(rule):
+                tokens = gettokens(rule)
+                if len(tokens) == 1 and isTerminal(rule):
+                    continue
+                startoken = tokens[0]
+                if not isTerminal(startoken):
+                    isgnf = False
+                    break
+        if not isgnf:
+            old_grammar = copy.deepcopy(new_grammar)
+            new_grammar = defaultdict(list)
+    return new_grammar
+                
+
+def preprocess(data):
+    productions = []
+    production = []
+    for line in data:
+        if line != '\n': 
+            production.append(line)
+        else:
+            productions.append(production)
+            production = []
+    final_rule_set = {}
+    for production in productions:
+        rules = []
+        init = production[0]
+        nonterminal = init.split(':')[0]
+        rules.append(strip_chars(init.split(':')[1]).strip('| '))
+        for production_rule in production[1:]:
+            rules.append(strip_chars(production_rule.split('|')[0]))
+        final_rule_set[nonterminal] = rules
+    # for line in data:
+    #     if line != '\n':
+    #         production.append(line)
+    return final_rule_set
+
+def remove_unit(grammar):
+    nounitproductions = False 
+    old_grammar = copy.deepcopy(grammar)
+    new_grammar = defaultdict(list)
+    while not nounitproductions:
+        for lhs, rules in old_grammar.items():
+            for rhs in rules:
+                # Checking if the rule is a unit production rule
+                if len(gettokens(rhs)) == 1:
+                    if not isTerminal(rhs):
+                        new_grammar[lhs].extend([rule for rule in old_grammar[rhs]])
+                    else:
+                        new_grammar[lhs].append(rhs)
+                else:
+                    new_grammar[lhs].append(rhs)
+        # Checking there are no unit productions left in the grammar 
+        nounitproductions = True
+        for lhs, rules in new_grammar.items():
+            for rhs in rules:
+                if len(gettokens(rhs)) == 1:
+                    if not isTerminal(rhs):
+                        nounitproductions = False
+                        break
+            if not nounitproductions:
+                break
+        # Unit productions are still there in the grammar -- repeat the process
+        if not nounitproductions:
+            old_grammar = copy.deepcopy(new_grammar)
+            new_grammar = defaultdict(list)
+    return new_grammar
+
+def isTerminal(rule):
+    # pattern = re.compile("([r]*\'[\s\S]+\')")
+    pattern = re.compile("\'(.*?)\'")
+    match = pattern.match(rule)
+    if match:
+        return True
+    else:
+        return False
+
+def remove_mixed(grammar):
+    '''
+    Remove rules where there are terminals mixed in with non-terminals
+    '''
+    new_grammar = defaultdict(list)
+    for lhs, rules in grammar.items():
+        for rhs in rules:
+            # tokens = rhs.split(' ')
+            regen_rule = []
+            tokens = gettokens(rhs)
+            if len(gettokens(rhs)) == 1:
+                new_grammar[lhs].append(rhs)
+                continue
+            for token in tokens:
+                # Identify if there is a terminal in the RHS
+                if isTerminal(token):
+                    # Check if a corresponding nonterminal already exists
+                    nonterminal = terminal_exist(token, new_grammar)
+                    if nonterminal:
+                        regen_rule.append(nonterminal)
+                    else:
+                        new_nonterm = get_nonterminal()
+                        new_grammar[new_nonterm].append(token)
+                        regen_rule.append(new_nonterm)
+                else:
+                    regen_rule.append(token)
+            new_grammar[lhs].append(' '.join(regen_rule))
+    return new_grammar
+
+def break_rules(grammar):
+    new_grammar = defaultdict(list)
+    old_grammar = copy.deepcopy(grammar)
+    nomulti = False
+    while not nomulti:
+        for lhs, rules in old_grammar.items():
+            for rhs in rules:
+                tokens = gettokens(rhs)
+                if len(tokens) > 2 and (not isTerminal(rhs)):
+                    split = tokens[:-1] 
+                    nonterminal = terminal_exist(' '.join(split), new_grammar)
+                    if nonterminal:
+                        newrule = ' '.join([nonterminal, tokens[-1]])
+                        new_grammar[lhs].append(newrule)
+                    else:
+                        nonterminal = get_nonterminal()
+                        new_grammar[nonterminal].append(' '.join(split))
+                        newrule = ' '.join([nonterminal, tokens[-1]])
+                        new_grammar[lhs].append(newrule)
+                else:
+                    new_grammar[lhs].append(rhs)
+        nomulti = True
+        for lhs, rules in new_grammar.items():
+            for rhs in rules:
+                # tokens = rhs.split(' ')
+                tokens = gettokens(rhs)
+                if len(tokens) > 2 and (not isTerminal(rhs)):
+                    nomulti = False
+                    break
+        if not nomulti:
+            old_grammar = copy.deepcopy(new_grammar)
+            new_grammar = defaultdict(list)
+    return new_grammar
+
+def strip_chars(rule):
+    return rule.strip('\n\t ')
+
+def get_nonterminal():
+    global NONTERMINALSET
+    if NONTERMINALSET:
+        return NONTERMINALSET.pop(0)
+    else:
+        _repopulate()
+        return NONTERMINALSET.pop(0)
+
+def _repopulate():
+    global COUNT
+    global NONTERMINALSET
+    NONTERMINALSET = [''.join(x) for x in list(combinations(ascii_uppercase, COUNT))]
+    COUNT += 1
+
+def terminal_exist(token, grammar):
+    for nonterminal, rules in grammar.items():
+        if token in rules:
+            return nonterminal
+    return None
+
+
+
+if __name__ == '__main__':
+    import argparse
+    parser = argparse.ArgumentParser(description = 'Script to convert grammar to GNF form')
+    parser.add_argument(
+            '--gf',
+            type = str,
+            required = True,
+            help = 'Location of grammar file')
+    parser.add_argument(
+            '--out',
+            type = str,
+            required = True,
+            help = 'Location of output file')
+    parser.add_argument(
+            '--start',
+            type = str,
+            required = True,
+            help = 'Start token')
+    args = parser.parse_args()
+
+    main(args.gf, args.out, args.start)

custom_mutators/gramatron/preprocess/prep_automaton.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+# This script creates a FSA describing the input grammar *.g4
+
+if [ ! "$#" -lt 4 ]; then
+  echo "Usage: ./prep_pda.sh <grammar_file> <start> [stack_limit]"         
+  exit 1
+fi
+
+GRAMMAR_FILE=$1
+GRAMMAR_DIR="$(dirname $GRAMMAR_FILE)"
+START="$2"
+STACK_LIMIT="$3"
+
+# Get filename
+FILE=$(basename -- "$GRAMMAR_FILE")
+echo "File:$FILE"
+FILENAME="${FILE%.*}"
+echo "Name:$FILENAME"
+
+
+# Create the GNF form of the grammar
+CMD="python gnf_converter.py --gf $GRAMMAR_FILE --out ${FILENAME}.json --start $START"
+$CMD
+
+# Generate grammar automaton 
+# Check if user provided a stack limit
+if [ -z "${STACK_LIMIT}" ]; then
+CMD="python3 construct_automata.py --gf ${FILENAME}.json" 
+else
+CMD="python construct_automata.py --gf ${FILENAME}.json --limit ${STACK_LIMIT}" 
+fi
+echo $CMD
+$CMD
+
+# Move PDA to the source dir of the grammar
+echo "Copying ${FILENAME}_automata.json to $GRAMMAR_DIR"
+mv "${FILENAME}_automata.json" $GRAMMAR_DIR/  

custom_mutators/gramatron/test.c

@@ -0,0 +1,154 @@
+/* This is the testing module for Gramatron
+ */
+#include "afl-fuzz.h"
+#include "gramfuzz.h"
+
+#define NUMINPUTS 50
+
+state *create_pda(u8 *automaton_file) {
+
+  struct json_object *parsed_json;
+  state *             pda;
+  json_object *       source_obj, *attr;
+  int                 arraylen, ii, ii2, trigger_len, error;
+
+  printf("\n[GF] Automaton file passed:%s", automaton_file);
+  // parsed_json =
+  // json_object_from_file("./gramfuzz/php_gnf_processed_full.json");
+  parsed_json = json_object_from_file(automaton_file);
+
+  // Getting final state
+  source_obj = json_object_object_get(parsed_json, "final_state");
+  printf("\t\nFinal=%s\n", json_object_get_string(source_obj));
+  final_state = atoi(json_object_get_string(source_obj));
+
+  // Getting initial state
+  source_obj = json_object_object_get(parsed_json, "init_state");
+  init_state = atoi(json_object_get_string(source_obj));
+  printf("\tInit=%s\n", json_object_get_string(source_obj));
+
+  // Getting number of states
+  source_obj = json_object_object_get(parsed_json, "numstates");
+  numstates = atoi(json_object_get_string(source_obj)) + 1;
+  printf("\tNumStates=%d\n", numstates);
+
+  // Allocate state space for each pda state
+  pda = (state *)calloc(atoi(json_object_get_string(source_obj)) + 1,
+                        sizeof(state));
+
+  // Getting PDA representation
+  source_obj = json_object_object_get(parsed_json, "pda");
+  enum json_type type;
+  json_object_object_foreach(source_obj, key, val) {
+
+    state *  state_ptr;
+    trigger *trigger_ptr;
+    int      offset;
+
+    // Get the correct offset into the pda to store state information
+    state_ptr = pda;
+    offset = atoi(key);
+    state_ptr += offset;
+
+    // Store state string
+    state_ptr->state_name = offset;
+
+    // Create trigger array of structs
+    trigger_len = json_object_array_length(val);
+    state_ptr->trigger_len = trigger_len;
+    trigger_ptr = (trigger *)calloc(trigger_len, sizeof(trigger));
+    state_ptr->ptr = trigger_ptr;
+    printf("\nName:%d Trigger:%d", offset, trigger_len);
+
+    for (ii = 0; ii < trigger_len; ii++) {
+
+      json_object *obj = json_object_array_get_idx(val, ii);
+      // Get all the trigger trigger attributes
+      attr = json_object_array_get_idx(obj, 0);
+      (trigger_ptr)->id = strdup(json_object_get_string(attr));
+
+      attr = json_object_array_get_idx(obj, 1);
+      trigger_ptr->dest = atoi(json_object_get_string(attr));
+
+      attr = json_object_array_get_idx(obj, 2);
+      if (!strcmp("\\n", json_object_get_string(attr))) {
+
+        trigger_ptr->term = strdup("\n");
+
+      } else {
+
+        trigger_ptr->term = strdup(json_object_get_string(attr));
+
+      }
+
+      trigger_ptr->term_len = strlen(trigger_ptr->term);
+      trigger_ptr++;
+
+    }
+
+  }
+
+  // Delete the JSON object
+  json_object_put(parsed_json);
+
+  return pda;
+
+}
+
+void SanityCheck(char *automaton_path) {
+
+  state *        pda = create_pda(automaton_path);
+  int            count = 0, state;
+  Get_Dupes_Ret *getdupesret;
+  IdxMap_new *   statemap;
+  IdxMap_new *   statemap_ptr;
+  terminal *     term_ptr;
+
+  while (count < NUMINPUTS) {
+
+    // Perform input generation
+    Array *generated = gen_input(pda, NULL);
+    print_repr(generated, "Gen");
+    count += 1;
+
+  }
+
+}
+
+int main(int argc, char *argv[]) {
+
+  char *         mode;
+  char *         automaton_path;
+  char *         output_dir = NULL;
+  struct timeval tv;
+  struct timeval tz;
+  // gettimeofday(&tv, &tz);
+  srand(1337);
+  if (argc == 3) {
+
+    mode = argv[1];
+    automaton_path = strdup(argv[2]);
+    printf("\nMode:%s Path:%s", mode, automaton_path);
+
+  } else {
+
+    printf("\nUsage: ./test <mode> <automaton_path>");
+    return -1;
+
+  }
+
+  if (!strcmp(mode, "SanityCheck")) {
+
+    SanityCheck(automaton_path);
+
+  } else {
+
+    printf("\nUnrecognized mode");
+    return -1;
+
+  }
+
+  return 0;
+
+}
+

custom_mutators/gramatron/test.h

@@ -0,0 +1,57 @@
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <json-c/json.h>
+#include <unistd.h>
+#include "hashmap.h"
+#include "uthash.h"
+#include "utarray.h"
+
+#define INIT_SIZE 100  // Initial size of the dynamic array holding the input
+
+typedef struct terminal {
+
+  int    state;
+  int    trigger_idx;
+  size_t symbol_len;
+  char * symbol;
+
+} terminal;
+
+typedef struct trigger {
+
+  char * id;
+  int    dest;
+  char * term;
+  size_t term_len;
+
+} trigger;
+
+typedef struct state {
+
+  int      state_name;   // Integer State name
+  int      trigger_len;  // Number of triggers associated with this state
+  trigger *ptr;          // Pointer to beginning of the list of triggers
+
+} state;
+
+typedef struct {
+
+  size_t    used;
+  size_t    size;
+  size_t    inputlen;
+  terminal *start;
+
+} Array;
+
+int init_state;
+int curr_state;
+int final_state;
+
+state *create_pda(char *);
+Array *gen_input(state *, Array *);
+void   print_repr(Array *, char *);
+void   initArray(Array *, size_t);
+void   insertArray(Array *, int, char *, size_t, int);
+

custom_mutators/gramatron/utarray.h

@@ -0,0 +1,392 @@
+/*
+Copyright (c) 2008-2018, Troy D. Hanson   http://troydhanson.github.com/uthash/
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
+IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
+OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+/* a dynamic array implementation using macros
+ */
+#ifndef UTARRAY_H
+#define UTARRAY_H
+
+#define UTARRAY_VERSION 2.1.0
+
+#include <stddef.h>                                               /* size_t */
+#include <string.h>                                          /* memset, etc */
+#include <stdlib.h>                                                 /* exit */
+
+#ifdef __GNUC__
+  #define UTARRAY_UNUSED __attribute__((__unused__))
+#else
+  #define UTARRAY_UNUSED
+#endif
+
+#ifdef oom
+  #error \
+      "The name of macro 'oom' has been changed to 'utarray_oom'. Please update your code."
+  #define utarray_oom() oom()
+#endif
+
+#ifndef utarray_oom
+  #define utarray_oom() exit(-1)
+#endif
+
+typedef void(ctor_f)(void *dst, const void *src);
+typedef void(dtor_f)(void *elt);
+typedef void(init_f)(void *elt);
+typedef struct {
+
+  size_t  sz;
+  init_f *init;
+  ctor_f *copy;
+  dtor_f *dtor;
+
+} UT_icd;
+
+typedef struct {
+
+  unsigned i, n;           /* i: index of next available slot, n: num slots */
+  UT_icd   icd;               /* initializer, copy and destructor functions */
+  char *   d;                                     /* n slots of size icd->sz*/
+
+} UT_array;
+
+#define utarray_init(a, _icd)       \
+  do {                              \
+                                    \
+    memset(a, 0, sizeof(UT_array)); \
+    (a)->icd = *(_icd);             \
+                                    \
+  } while (0)
+
+#define utarray_done(a)                            \
+  do {                                             \
+                                                   \
+    if ((a)->n) {                                  \
+                                                   \
+      if ((a)->icd.dtor) {                         \
+                                                   \
+        unsigned _ut_i;                            \
+        for (_ut_i = 0; _ut_i < (a)->i; _ut_i++) { \
+                                                   \
+          (a)->icd.dtor(utarray_eltptr(a, _ut_i)); \
+                                                   \
+        }                                          \
+                                                   \
+      }                                            \
+      free((a)->d);                                \
+                                                   \
+    }                                              \
+    (a)->n = 0;                                    \
+                                                   \
+  } while (0)
+
+#define utarray_new(a, _icd)                    \
+  do {                                          \
+                                                \
+    (a) = (UT_array *)malloc(sizeof(UT_array)); \
+    if ((a) == NULL) { utarray_oom(); }         \
+    utarray_init(a, _icd);                      \
+                                                \
+  } while (0)
+
+#define utarray_free(a) \
+  do {                  \
+                        \
+    utarray_done(a);    \
+    free(a);            \
+                        \
+  } while (0)
+
+#define utarray_reserve(a, by)                                     \
+  do {                                                             \
+                                                                   \
+    if (((a)->i + (by)) > (a)->n) {                                \
+                                                                   \
+      char *utarray_tmp;                                           \
+      while (((a)->i + (by)) > (a)->n) {                           \
+                                                                   \
+        (a)->n = ((a)->n ? (2 * (a)->n) : 8);                      \
+                                                                   \
+      }                                                            \
+      utarray_tmp = (char *)realloc((a)->d, (a)->n * (a)->icd.sz); \
+      if (utarray_tmp == NULL) { utarray_oom(); }                  \
+      (a)->d = utarray_tmp;                                        \
+                                                                   \
+    }                                                              \
+                                                                   \
+  } while (0)
+
+#define utarray_push_back(a, p)                             \
+  do {                                                      \
+                                                            \
+    utarray_reserve(a, 1);                                  \
+    if ((a)->icd.copy) {                                    \
+                                                            \
+      (a)->icd.copy(_utarray_eltptr(a, (a)->i++), p);       \
+                                                            \
+    } else {                                                \
+                                                            \
+      memcpy(_utarray_eltptr(a, (a)->i++), p, (a)->icd.sz); \
+                                                            \
+    };                                                      \
+                                                            \
+  } while (0)
+
+#define utarray_pop_back(a)                          \
+  do {                                               \
+                                                     \
+    if ((a)->icd.dtor) {                             \
+                                                     \
+      (a)->icd.dtor(_utarray_eltptr(a, --((a)->i))); \
+                                                     \
+    } else {                                         \
+                                                     \
+      (a)->i--;                                      \
+                                                     \
+    }                                                \
+                                                     \
+  } while (0)
+
+#define utarray_extend_back(a)                            \
+  do {                                                    \
+                                                          \
+    utarray_reserve(a, 1);                                \
+    if ((a)->icd.init) {                                  \
+                                                          \
+      (a)->icd.init(_utarray_eltptr(a, (a)->i));          \
+                                                          \
+    } else {                                              \
+                                                          \
+      memset(_utarray_eltptr(a, (a)->i), 0, (a)->icd.sz); \
+                                                          \
+    }                                                     \
+    (a)->i++;                                             \
+                                                          \
+  } while (0)
+
+#define utarray_len(a) ((a)->i)
+
+#define utarray_eltptr(a, j) (((j) < (a)->i) ? _utarray_eltptr(a, j) : NULL)
+#define _utarray_eltptr(a, j) ((a)->d + ((a)->icd.sz * (j)))
+
+#define utarray_insert(a, p, j)                                   \
+  do {                                                            \
+                                                                  \
+    if ((j) > (a)->i) utarray_resize(a, j);                       \
+    utarray_reserve(a, 1);                                        \
+    if ((j) < (a)->i) {                                           \
+                                                                  \
+      memmove(_utarray_eltptr(a, (j) + 1), _utarray_eltptr(a, j), \
+              ((a)->i - (j)) * ((a)->icd.sz));                    \
+                                                                  \
+    }                                                             \
+    if ((a)->icd.copy) {                                          \
+                                                                  \
+      (a)->icd.copy(_utarray_eltptr(a, j), p);                    \
+                                                                  \
+    } else {                                                      \
+                                                                  \
+      memcpy(_utarray_eltptr(a, j), p, (a)->icd.sz);              \
+                                                                  \
+    };                                                            \
+    (a)->i++;                                                     \
+                                                                  \
+  } while (0)
+
+#define utarray_inserta(a, w, j)                                               \
+  do {                                                                         \
+                                                                               \
+    if (utarray_len(w) == 0) break;                                            \
+    if ((j) > (a)->i) utarray_resize(a, j);                                    \
+    utarray_reserve(a, utarray_len(w));                                        \
+    if ((j) < (a)->i) {                                                        \
+                                                                               \
+      memmove(_utarray_eltptr(a, (j) + utarray_len(w)), _utarray_eltptr(a, j), \
+              ((a)->i - (j)) * ((a)->icd.sz));                                 \
+                                                                               \
+    }                                                                          \
+    if ((a)->icd.copy) {                                                       \
+                                                                               \
+      unsigned _ut_i;                                                          \
+      for (_ut_i = 0; _ut_i < (w)->i; _ut_i++) {                               \
+                                                                               \
+        (a)->icd.copy(_utarray_eltptr(a, (j) + _ut_i),                         \
+                      _utarray_eltptr(w, _ut_i));                              \
+                                                                               \
+      }                                                                        \
+                                                                               \
+    } else {                                                                   \
+                                                                               \
+      memcpy(_utarray_eltptr(a, j), _utarray_eltptr(w, 0),                     \
+             utarray_len(w) * ((a)->icd.sz));                                  \
+                                                                               \
+    }                                                                          \
+    (a)->i += utarray_len(w);                                                  \
+                                                                               \
+  } while (0)
+
+#define utarray_resize(dst, num)                                   \
+  do {                                                             \
+                                                                   \
+    unsigned _ut_i;                                                \
+    if ((dst)->i > (unsigned)(num)) {                              \
+                                                                   \
+      if ((dst)->icd.dtor) {                                       \
+                                                                   \
+        for (_ut_i = (num); _ut_i < (dst)->i; ++_ut_i) {           \
+                                                                   \
+          (dst)->icd.dtor(_utarray_eltptr(dst, _ut_i));            \
+                                                                   \
+        }                                                          \
+                                                                   \
+      }                                                            \
+                                                                   \
+    } else if ((dst)->i < (unsigned)(num)) {                       \
+                                                                   \
+      utarray_reserve(dst, (num) - (dst)->i);                      \
+      if ((dst)->icd.init) {                                       \
+                                                                   \
+        for (_ut_i = (dst)->i; _ut_i < (unsigned)(num); ++_ut_i) { \
+                                                                   \
+          (dst)->icd.init(_utarray_eltptr(dst, _ut_i));            \
+                                                                   \
+        }                                                          \
+                                                                   \
+      } else {                                                     \
+                                                                   \
+        memset(_utarray_eltptr(dst, (dst)->i), 0,                  \
+               (dst)->icd.sz *((num) - (dst)->i));                 \
+                                                                   \
+      }                                                            \
+                                                                   \
+    }                                                              \
+    (dst)->i = (num);                                              \
+                                                                   \
+  } while (0)
+
+#define utarray_concat(dst, src)                 \
+  do {                                           \
+                                                 \
+    utarray_inserta(dst, src, utarray_len(dst)); \
+                                                 \
+  } while (0)
+
+#define utarray_erase(a, pos, len)                                        \
+  do {                                                                    \
+                                                                          \
+    if ((a)->icd.dtor) {                                                  \
+                                                                          \
+      unsigned _ut_i;                                                     \
+      for (_ut_i = 0; _ut_i < (len); _ut_i++) {                           \
+                                                                          \
+        (a)->icd.dtor(utarray_eltptr(a, (pos) + _ut_i));                  \
+                                                                          \
+      }                                                                   \
+                                                                          \
+    }                                                                     \
+    if ((a)->i > ((pos) + (len))) {                                       \
+                                                                          \
+      memmove(_utarray_eltptr(a, pos), _utarray_eltptr(a, (pos) + (len)), \
+              ((a)->i - ((pos) + (len))) * (a)->icd.sz);                  \
+                                                                          \
+    }                                                                     \
+    (a)->i -= (len);                                                      \
+                                                                          \
+  } while (0)
+
+#define utarray_renew(a, u) \
+  do {                      \
+                            \
+    if (a)                  \
+      utarray_clear(a);     \
+    else                    \
+      utarray_new(a, u);    \
+                            \
+  } while (0)
+
+#define utarray_clear(a)                            \
+  do {                                              \
+                                                    \
+    if ((a)->i > 0) {                               \
+                                                    \
+      if ((a)->icd.dtor) {                          \
+                                                    \
+        unsigned _ut_i;                             \
+        for (_ut_i = 0; _ut_i < (a)->i; _ut_i++) {  \
+                                                    \
+          (a)->icd.dtor(_utarray_eltptr(a, _ut_i)); \
+                                                    \
+        }                                           \
+                                                    \
+      }                                             \
+      (a)->i = 0;                                   \
+                                                    \
+    }                                               \
+                                                    \
+  } while (0)
+
+#define utarray_sort(a, cmp)                 \
+  do {                                       \
+                                             \
+    qsort((a)->d, (a)->i, (a)->icd.sz, cmp); \
+                                             \
+  } while (0)
+
+#define utarray_find(a, v, cmp) bsearch((v), (a)->d, (a)->i, (a)->icd.sz, cmp)
+
+#define utarray_front(a) (((a)->i) ? (_utarray_eltptr(a, 0)) : NULL)
+#define utarray_next(a, e)                                             \
+  (((e) == NULL) ? utarray_front(a)                                    \
+                 : (((a)->i != utarray_eltidx(a, e) + 1)               \
+                        ? _utarray_eltptr(a, utarray_eltidx(a, e) + 1) \
+                        : NULL))
+#define utarray_prev(a, e)                                             \
+  (((e) == NULL) ? utarray_back(a)                                     \
+                 : ((utarray_eltidx(a, e) != 0)                        \
+                        ? _utarray_eltptr(a, utarray_eltidx(a, e) - 1) \
+                        : NULL))
+#define utarray_back(a) (((a)->i) ? (_utarray_eltptr(a, (a)->i - 1)) : NULL)
+#define utarray_eltidx(a, e) (((char *)(e) - (a)->d) / (a)->icd.sz)
+
+/* last we pre-define a few icd for common utarrays of ints and strings */
+static void utarray_str_cpy(void *dst, const void *src) {
+
+  char **_src = (char **)src, **_dst = (char **)dst;
+  *_dst = (*_src == NULL) ? NULL : strdup(*_src);
+
+}
+
+static void utarray_str_dtor(void *elt) {
+
+  char **eltc = (char **)elt;
+  if (*eltc != NULL) free(*eltc);
+
+}
+
+static const UT_icd ut_str_icd UTARRAY_UNUSED = {
+
+    sizeof(char *), NULL, utarray_str_cpy, utarray_str_dtor};
+static const UT_icd ut_int_icd UTARRAY_UNUSED = {sizeof(int), NULL, NULL, NULL};
+static const UT_icd ut_ptr_icd UTARRAY_UNUSED = {sizeof(void *), NULL, NULL,
+                                                 NULL};
+
+#endif                                                         /* UTARRAY_H */
+

custom_mutators/grammar_mutator/GRAMMAR_VERSION

@@ -1 +1 @@
-b3c4fcf
+cbe5e32

custom_mutators/grammar_mutator/build_grammar_mutator.sh

@@ -14,7 +14,7 @@
 #                                <andreafioraldi@gmail.com>
 #
 # Copyright 2017 Battelle Memorial Institute. All rights reserved.
-# Copyright 2019-2020 AFLplusplus Project. All rights reserved.
+# Copyright 2019-2022 AFLplusplus Project. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -106,23 +106,23 @@ git status 1>/dev/null 2>/dev/null
 if [ $? -eq 0 ]; then
   echo "[*] initializing grammar mutator submodule"
   git submodule init || exit 1
-  git submodule update ./grammar-mutator 2>/dev/null # ignore errors
+  git submodule update ./grammar_mutator 2>/dev/null # ignore errors
 else
   echo "[*] cloning grammar mutator"
-  test -d grammar-mutator || {
+  test -d grammar_mutator || {
     CNT=1
-    while [ '!' -d grammar-mutator -a "$CNT" -lt 4 ]; do
-      echo "Trying to clone grammar-mutator (attempt $CNT/3)"
+    while [ '!' -d grammar_mutator -a "$CNT" -lt 4 ]; do
+      echo "Trying to clone grammar_mutator (attempt $CNT/3)"
       git clone "$GRAMMAR_REPO" 
       CNT=`expr "$CNT" + 1`
     done
   }
 fi
 
-test -d grammar-mutator || { echo "[-] not checked out, please install git or check your internet connection." ; exit 1 ; }
+test -d grammar_mutator || { echo "[-] not checked out, please install git or check your internet connection." ; exit 1 ; }
 echo "[+] Got grammar mutator."
 
-cd "grammar-mutator" || exit 1
+cd "grammar_mutator" || exit 1
 echo "[*] Checking out $GRAMMAR_VERSION"
 sh -c 'git stash && git stash drop' 1>/dev/null 2>/dev/null
 git checkout "$GRAMMAR_VERSION" || exit 1
@@ -134,7 +134,7 @@ echo
 echo
 echo "[+] All successfully prepared!"
 echo "[!] To build for your grammar just do:"
-echo "      cd grammar-mutator"
+echo "      cd grammar_mutator"
 echo "      make GRAMMAR_FILE=/path/to/your/grammar"
-echo "[+] You will find a JSON and RUBY grammar in grammar-mutator/grammars to play with."
+echo "[+] You will find a JSON and RUBY grammar in grammar_mutator/grammars to play with."
 echo

custom_mutators/honggfuzz/README.md

@@ -1,7 +1,7 @@
 # custum mutator: honggfuzz mangle
 
 this is the honggfuzz mutator in mangle.c as a custom mutator
-module for afl++. It is the original mangle.c, mangle.h and honggfuzz.h
+module for AFL++. It is the original mangle.c, mangle.h and honggfuzz.h
 with a lot of mocking around it :-)
 
 just type `make` to build

custom_mutators/honggfuzz/honggfuzz.c

@@ -65,9 +65,9 @@ my_mutator_t *afl_custom_init(afl_state_t *afl, unsigned int seed) {
 /* When a new queue entry is added we check if there are new dictionary
    entries to add to honggfuzz structure */
 
-void afl_custom_queue_new_entry(my_mutator_t * data,
-                                const uint8_t *filename_new_queue,
-                                const uint8_t *filename_orig_queue) {
+uint8_t afl_custom_queue_new_entry(my_mutator_t * data,
+                                   const uint8_t *filename_new_queue,
+                                   const uint8_t *filename_orig_queue) {
 
   if (run.global->mutate.dictionaryCnt >= 1024) return;
 
@@ -97,6 +97,8 @@ void afl_custom_queue_new_entry(my_mutator_t * data,
 
   }
 
+  return 0;
+
 }
 
 /* we could set only_printable if is_ascii is set ... let's see

custom_mutators/honggfuzz/honggfuzz.h

@@ -39,7 +39,7 @@
 #include "libhfcommon/util.h"
 
 #define PROG_NAME    "honggfuzz"
-#define PROG_VERSION "2.3"
+#define PROG_VERSION "2.4"
 
 /* Name of the template which will be replaced with the proper name of the file */
 #define _HF_FILE_PLACEHOLDER "___FILE___"
@@ -208,6 +208,7 @@ typedef struct {
         const char* crashDir;
         const char* covDirNew;
         bool        saveUnique;
+        bool        saveSmaller;
         size_t      dynfileqMaxSz;
         size_t      dynfileqCnt;
         dynfile_t*  dynfileqCurrent;
@@ -245,9 +246,9 @@ typedef struct {
     } timing;
     struct {
         struct {
-            uint8_t val[256];
+            uint8_t val[512];
             size_t  len;
-        } dictionary[1024];
+        } dictionary[8192];
         size_t      dictionaryCnt;
         const char* dictionaryFile;
         size_t      mutationsMax;
@@ -262,6 +263,7 @@ typedef struct {
     struct {
         bool        useVerifier;
         bool        exitUponCrash;
+        uint8_t     exitCodeUponCrash;
         const char* reportFile;
         size_t      dynFileIterExpire;
         bool        only_printable;
@@ -279,9 +281,9 @@ typedef struct {
         cmpfeedback_t*  cmpFeedbackMap;
         int             cmpFeedbackFd;
         bool            cmpFeedback;
-        const char*     blacklistFile;
-        uint64_t*       blacklist;
-        size_t          blacklistCnt;
+        const char*     blocklistFile;
+        uint64_t*       blocklist;
+        size_t          blocklistCnt;
         bool            skipFeedbackOnTimeout;
         uint64_t        maxCov[4];
         dynFileMethod_t dynFileMethod;

custom_mutators/honggfuzz/input.h

@@ -77,11 +77,11 @@ static inline uint64_t util_rndGet(uint64_t min, uint64_t max) {
 }
 static inline uint64_t util_rnd64() { return rand_below(afl_struct, 1 << 30); }
 
-static inline size_t input_getRandomInputAsBuf(run_t *run, const uint8_t **buf) {
-  *buf = queue_input;
+static inline const uint8_t* input_getRandomInputAsBuf(run_t* run, size_t* len) {
+  *len = queue_input_size;
   run->dynfile->data = queue_input;
   run->dynfile->size = queue_input_size;
-  return queue_input_size;
+  return queue_input;
 }
 static inline void input_setSize(run_t* run, size_t sz) {
   run->dynfile->size = sz;

custom_mutators/honggfuzz/libhfcommon

@@ -1 +0,0 @@
-.

custom_mutators/honggfuzz/libhfcommon/common.h

@@ -0,0 +1,3 @@
+#ifndef LOG_E
+  #define LOG_E LOG_F
+#endif

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();

custom_mutators/libfuzzer/README.md

@@ -11,9 +11,11 @@ Note that this is currently a simple implementation and it is missing two featur
   * Dictionary support
 
 To update the source, all that is needed is that FuzzerDriver.cpp has to receive
+
 ```
 #include "libfuzzer.inc"
 ```
+
 before the closing namespace bracket.
 
 It is also libfuzzer.inc where the configuration of the libfuzzer mutations
@@ -21,4 +23,4 @@ are done.
 
 > Original repository: https://github.com/llvm/llvm-project
 > Path: compiler-rt/lib/fuzzer/*.{h|cpp}
-> Source commit: df3e903655e2499968fc7af64fb5fa52b2ee79bb
+> Source commit: df3e903655e2499968fc7af64fb5fa52b2ee79bb

custom_mutators/libfuzzer/libfuzzer.cpp

@@ -78,9 +78,9 @@ extern "C" my_mutator_t *afl_custom_init(afl_state_t *afl, unsigned int seed) {
 /* When a new queue entry is added we check if there are new dictionary
    entries to add to honggfuzz structure */
 #if 0
-extern "C" void afl_custom_queue_new_entry(my_mutator_t * data,
-                                           const uint8_t *filename_new_queue,
-                                           const uint8_t *filename_orig_queue) {
+extern "C" uint8_t afl_custom_queue_new_entry(my_mutator_t * data,
+                                              const uint8_t *filename_new_queue,
+                                              const uint8_t *filename_orig_queue) {
 
   while (data->extras_cnt < afl_struct->extras_cnt) {
 
@@ -110,6 +110,8 @@ extern "C" void afl_custom_queue_new_entry(my_mutator_t * data,
 
   }
 
+  return 0;
+
 }
 
 #endif

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);
 }

custom_mutators/libprotobuf-mutator-example/Android.bp

@@ -8,6 +8,7 @@ cc_library_shared {
     "-O0",
     "-fPIC",
     "-Wall",
+    "-Wno-unused-parameter",
   ],
 
   srcs: [
@@ -29,4 +30,9 @@ cc_binary {
   srcs: [
     "vuln.c",
   ],
+
+  cflags: [
+    "-Wno-unused-result",
+    "-Wno-unused-parameter",
+  ],
 }

custom_mutators/libprotobuf-mutator-example/lpm_aflpp_custom_mutator_input.cc

@@ -99,10 +99,12 @@ extern "C" size_t afl_custom_fuzz(MyMutator *mutator, // return value from afl_c
     std::string s = ProtoToData(*p);
     // Copy to a new buffer ( mutated_out )
     size_t mutated_size = s.size() <= max_size ? s.size() : max_size; // check if raw data's size is larger than max_size
-    uint8_t *mutated_out = new uint8_t[mutated_size+1];
-    memcpy(mutated_out, s.c_str(), mutated_size); // copy the mutated data
+
+    delete[] mutator->mutated_out;
+    mutator->mutated_out = new uint8_t[mutated_size];
+    memcpy(mutator->mutated_out, s.c_str(), mutated_size); // copy the mutated data
     // Assign the mutated data and return mutated_size
-    *out_buf = mutated_out;
+    *out_buf = mutator->mutated_out;
     return mutated_size;
 }
 

custom_mutators/libprotobuf-mutator-example/lpm_aflpp_custom_mutator_input.h

@@ -2,4 +2,9 @@
 #include "test.pb.h"
 
 class MyMutator : public protobuf_mutator::Mutator {
+public:
+    uint8_t *mutated_out = nullptr; 
+    ~MyMutator() {
+        delete[] mutated_out;
+    }
 };

custom_mutators/radamsa/custom_mutator_helpers.h

@@ -1,342 +0,0 @@
-#ifndef CUSTOM_MUTATOR_HELPERS
-#define CUSTOM_MUTATOR_HELPERS
-
-#include "config.h"
-#include "types.h"
-#include <stdlib.h>
-
-#define INITIAL_GROWTH_SIZE (64)
-
-#define RAND_BELOW(limit) (rand() % (limit))
-
-/* Use in a struct: creates a name_buf and a name_size variable. */
-#define BUF_VAR(type, name) \
-  type * name##_buf;        \
-  size_t name##_size;
-/* this filles in `&structptr->something_buf, &structptr->something_size`. */
-#define BUF_PARAMS(struct, name) \
-  (void **)&struct->name##_buf, &struct->name##_size
-
-typedef struct {
-
-} afl_t;
-
-static void surgical_havoc_mutate(u8 *out_buf, s32 begin, s32 end) {
-
-  static s8  interesting_8[] = {INTERESTING_8};
-  static s16 interesting_16[] = {INTERESTING_8, INTERESTING_16};
-  static s32 interesting_32[] = {INTERESTING_8, INTERESTING_16, INTERESTING_32};
-
-  switch (RAND_BELOW(12)) {
-
-    case 0: {
-
-      /* Flip a single bit somewhere. Spooky! */
-
-      s32 bit_idx = ((RAND_BELOW(end - begin) + begin) << 3) + RAND_BELOW(8);
-
-      out_buf[bit_idx >> 3] ^= 128 >> (bit_idx & 7);
-
-      break;
-
-    }
-
-    case 1: {
-
-      /* Set byte to interesting value. */
-
-      u8 val = interesting_8[RAND_BELOW(sizeof(interesting_8))];
-      out_buf[(RAND_BELOW(end - begin) + begin)] = val;
-
-      break;
-
-    }
-
-    case 2: {
-
-      /* Set word to interesting value, randomly choosing endian. */
-
-      if (end - begin < 2) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 1) break;
-
-      switch (RAND_BELOW(2)) {
-
-        case 0:
-          *(u16 *)(out_buf + byte_idx) =
-              interesting_16[RAND_BELOW(sizeof(interesting_16) >> 1)];
-          break;
-        case 1:
-          *(u16 *)(out_buf + byte_idx) =
-              SWAP16(interesting_16[RAND_BELOW(sizeof(interesting_16) >> 1)]);
-          break;
-
-      }
-
-      break;
-
-    }
-
-    case 3: {
-
-      /* Set dword to interesting value, randomly choosing endian. */
-
-      if (end - begin < 4) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 3) break;
-
-      switch (RAND_BELOW(2)) {
-
-        case 0:
-          *(u32 *)(out_buf + byte_idx) =
-              interesting_32[RAND_BELOW(sizeof(interesting_32) >> 2)];
-          break;
-        case 1:
-          *(u32 *)(out_buf + byte_idx) =
-              SWAP32(interesting_32[RAND_BELOW(sizeof(interesting_32) >> 2)]);
-          break;
-
-      }
-
-      break;
-
-    }
-
-    case 4: {
-
-      /* Set qword to interesting value, randomly choosing endian. */
-
-      if (end - begin < 8) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 7) break;
-
-      switch (RAND_BELOW(2)) {
-
-        case 0:
-          *(u64 *)(out_buf + byte_idx) =
-              (s64)interesting_32[RAND_BELOW(sizeof(interesting_32) >> 2)];
-          break;
-        case 1:
-          *(u64 *)(out_buf + byte_idx) = SWAP64(
-              (s64)interesting_32[RAND_BELOW(sizeof(interesting_32) >> 2)]);
-          break;
-
-      }
-
-      break;
-
-    }
-
-    case 5: {
-
-      /* Randomly subtract from byte. */
-
-      out_buf[(RAND_BELOW(end - begin) + begin)] -= 1 + RAND_BELOW(ARITH_MAX);
-
-      break;
-
-    }
-
-    case 6: {
-
-      /* Randomly add to byte. */
-
-      out_buf[(RAND_BELOW(end - begin) + begin)] += 1 + RAND_BELOW(ARITH_MAX);
-
-      break;
-
-    }
-
-    case 7: {
-
-      /* Randomly subtract from word, random endian. */
-
-      if (end - begin < 2) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 1) break;
-
-      if (RAND_BELOW(2)) {
-
-        *(u16 *)(out_buf + byte_idx) -= 1 + RAND_BELOW(ARITH_MAX);
-
-      } else {
-
-        u16 num = 1 + RAND_BELOW(ARITH_MAX);
-
-        *(u16 *)(out_buf + byte_idx) =
-            SWAP16(SWAP16(*(u16 *)(out_buf + byte_idx)) - num);
-
-      }
-
-      break;
-
-    }
-
-    case 8: {
-
-      /* Randomly add to word, random endian. */
-
-      if (end - begin < 2) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 1) break;
-
-      if (RAND_BELOW(2)) {
-
-        *(u16 *)(out_buf + byte_idx) += 1 + RAND_BELOW(ARITH_MAX);
-
-      } else {
-
-        u16 num = 1 + RAND_BELOW(ARITH_MAX);
-
-        *(u16 *)(out_buf + byte_idx) =
-            SWAP16(SWAP16(*(u16 *)(out_buf + byte_idx)) + num);
-
-      }
-
-      break;
-
-    }
-
-    case 9: {
-
-      /* Randomly subtract from dword, random endian. */
-
-      if (end - begin < 4) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 3) break;
-
-      if (RAND_BELOW(2)) {
-
-        *(u32 *)(out_buf + byte_idx) -= 1 + RAND_BELOW(ARITH_MAX);
-
-      } else {
-
-        u32 num = 1 + RAND_BELOW(ARITH_MAX);
-
-        *(u32 *)(out_buf + byte_idx) =
-            SWAP32(SWAP32(*(u32 *)(out_buf + byte_idx)) - num);
-
-      }
-
-      break;
-
-    }
-
-    case 10: {
-
-      /* Randomly add to dword, random endian. */
-
-      if (end - begin < 4) break;
-
-      s32 byte_idx = (RAND_BELOW(end - begin) + begin);
-
-      if (byte_idx >= end - 3) break;
-
-      if (RAND_BELOW(2)) {
-
-        *(u32 *)(out_buf + byte_idx) += 1 + RAND_BELOW(ARITH_MAX);
-
-      } else {
-
-        u32 num = 1 + RAND_BELOW(ARITH_MAX);
-
-        *(u32 *)(out_buf + byte_idx) =
-            SWAP32(SWAP32(*(u32 *)(out_buf + byte_idx)) + num);
-
-      }
-
-      break;
-
-    }
-
-    case 11: {
-
-      /* Just set a random byte to a random value. Because,
-         why not. We use XOR with 1-255 to eliminate the
-         possibility of a no-op. */
-
-      out_buf[(RAND_BELOW(end - begin) + begin)] ^= 1 + RAND_BELOW(255);
-
-      break;
-
-    }
-
-  }
-
-}
-
-/* This function calculates the next power of 2 greater or equal its argument.
- @return The rounded up power of 2 (if no overflow) or 0 on overflow.
-*/
-static inline size_t next_pow2(size_t in) {
-
-  if (in == 0 || in > (size_t)-1)
-    return 0;                  /* avoid undefined behaviour under-/overflow */
-  size_t out = in - 1;
-  out |= out >> 1;
-  out |= out >> 2;
-  out |= out >> 4;
-  out |= out >> 8;
-  out |= out >> 16;
-  return out + 1;
-
-}
-
-/* This function makes sure *size is > size_needed after call.
- It will realloc *buf otherwise.
- *size will grow exponentially as per:
- https://blog.mozilla.org/nnethercote/2014/11/04/please-grow-your-buffers-exponentially/
- Will return NULL and free *buf if size_needed is <1 or realloc failed.
- @return For convenience, this function returns *buf.
- */
-static inline void *maybe_grow(void **buf, size_t *size, size_t size_needed) {
-
-  /* No need to realloc */
-  if (likely(size_needed && *size >= size_needed)) return *buf;
-
-  /* No initial size was set */
-  if (size_needed < INITIAL_GROWTH_SIZE) size_needed = INITIAL_GROWTH_SIZE;
-
-  /* grow exponentially */
-  size_t next_size = next_pow2(size_needed);
-
-  /* handle overflow */
-  if (!next_size) { next_size = size_needed; }
-
-  /* alloc */
-  *buf = realloc(*buf, next_size);
-  *size = *buf ? next_size : 0;
-
-  return *buf;
-
-}
-
-/* Swaps buf1 ptr and buf2 ptr, as well as their sizes */
-static inline void afl_swap_bufs(void **buf1, size_t *size1, void **buf2,
-                             size_t *size2) {
-
-  void * scratch_buf = *buf1;
-  size_t scratch_size = *size1;
-  *buf1 = *buf2;
-  *size1 = *size2;
-  *buf2 = scratch_buf;
-  *size2 = scratch_size;
-
-}
-
-#undef INITIAL_GROWTH_SIZE
-
-#endif
-

custom_mutators/radamsa/custom_mutator_helpers.h

@@ -0,0 +1 @@
+../examples/custom_mutator_helpers.h

custom_mutators/radamsa/libradamsa.c

@@ -4473,6 +4473,10 @@ static word prim_sys(word op, word a, word b, word c) {
         FD_CLOEXEC,
         F_DUPFD,
         F_DUPFD_CLOEXEC,
+#if defined(F_DUP2FD)
+        F_DUP2FD,
+        F_DUP2FD_CLOEXEC,
+#endif
         F_GETFD,
         F_SETFD,
         F_GETFL,

custom_mutators/rust/.gitignore

@@ -0,0 +1,10 @@
+# Generated by Cargo
+# will have compiled files and executables
+/target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk

custom_mutators/rust/Cargo.toml

@@ -0,0 +1,8 @@
+[workspace]
+members = [
+    "custom_mutator-sys",
+    "custom_mutator",
+    "example",
+    # Lain needs a nightly toolchain
+    # "example_lain",
+]

custom_mutators/rust/README.md

@@ -0,0 +1,11 @@
+# Rust Custom Mutators
+
+Bindings to create custom mutators in Rust.
+
+These bindings are documented with rustdoc. To view the documentation run
+```cargo doc -p custom_mutator --open```.
+
+A minimal example can be found in `example`. Build it using `cargo build --example example_mutator`. 
+
+An example using [lain](https://github.com/microsoft/lain) for structured fuzzing can be found in `example_lain`.
+Since lain requires a nightly rust toolchain, you need to set one up before you can play with it.

custom_mutators/rust/custom_mutator-sys/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "custom_mutator-sys"
+version = "0.1.0"
+authors = ["Julius Hohnerlein <julihoh@users.noreply.github.com>"]
+edition = "2018"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+
+[build-dependencies]
+bindgen = "0.56"

custom_mutators/rust/custom_mutator-sys/build.rs

@@ -0,0 +1,42 @@
+extern crate bindgen;
+
+use std::env;
+use std::path::PathBuf;
+
+// this code is largely taken straight from the handbook: https://github.com/fitzgen/bindgen-tutorial-bzip2-sys
+fn main() {
+    // Tell cargo to invalidate the built crate whenever the wrapper changes
+    println!("cargo:rerun-if-changed=wrapper.h");
+
+    // The bindgen::Builder is the main entry point
+    // to bindgen, and lets you build up options for
+    // the resulting bindings.
+    let bindings = bindgen::Builder::default()
+        // The input header we would like to generate
+        // bindings for.
+        .header("wrapper.h")
+        .whitelist_type("afl_state_t")
+        .blacklist_type(r"u\d+")
+        .opaque_type(r"_.*")
+        .opaque_type("FILE")
+        .opaque_type("in_addr(_t)?")
+        .opaque_type("in_port(_t)?")
+        .opaque_type("sa_family(_t)?")
+        .opaque_type("sockaddr_in(_t)?")
+        .opaque_type("time_t")
+        .rustfmt_bindings(true)
+        .size_t_is_usize(true)
+        // Tell cargo to invalidate the built crate whenever any of the
+        // included header files changed.
+        .parse_callbacks(Box::new(bindgen::CargoCallbacks))
+        // Finish the builder and generate the bindings.
+        .generate()
+        // Unwrap the Result and panic on failure.
+        .expect("Unable to generate bindings");
+
+    // Write the bindings to the $OUT_DIR/bindings.rs file.
+    let out_path = PathBuf::from(env::var("OUT_DIR").unwrap());
+    bindings
+        .write_to_file(out_path.join("bindings.rs"))
+        .expect("Couldn't write bindings!");
+}

custom_mutators/rust/custom_mutator-sys/src/lib.rs

@@ -0,0 +1,5 @@
+#![allow(non_upper_case_globals)]
+#![allow(non_camel_case_types)]
+#![allow(non_snake_case)]
+
+include!(concat!(env!("OUT_DIR"), "/bindings.rs"));

custom_mutators/rust/custom_mutator-sys/wrapper.h

@@ -0,0 +1,4 @@
+#include "../../../include/afl-fuzz.h"
+#include "../../../include/common.h"
+#include "../../../include/config.h"
+#include "../../../include/debug.h"

custom_mutators/rust/custom_mutator/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "custom_mutator"
+version = "0.1.0"
+authors = ["Julius Hohnerlein <julihoh@users.noreply.github.com>"]
+edition = "2018"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[features]
+afl_internals = ["custom_mutator-sys"]
+
+[dependencies]
+custom_mutator-sys = { path = "../custom_mutator-sys", optional=true }