fuzz: new target to fuzz jsonescapeu8fast

This code just feels complicated enough we should go ahead and give it
a dedicated fuzzer: we've found bugs in similar things before.

Differential Revision: https://phab.mercurial-scm.org/D7034

contrib/fuzz/jsonescapeu8fast.cc

@@ -0,0 +1,57 b''
+#include <Python.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "pyutil.h"
+
+#include <fuzzer/FuzzedDataProvider.h>
+#include <iostream>
+#include <string>
+
+extern "C" {
+
+static PyCodeObject *code;
+
+extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
+{
+	contrib::initpy(*argv[0]);
+	code = (PyCodeObject *)Py_CompileString(R"py(
+from parsers import jsonescapeu8fast
+
+try:
+    jsonescapeu8fast(data, paranoid)
+except Exception as e:
+    pass
+    # uncomment this print if you're editing this Python code
+    # to debug failures.
+    # print(e)
+)py",
+	                                        "fuzzer", Py_file_input);
+	if (!code) {
+		std::cerr << "failed to compile Python code!" << std::endl;
+	}
+	return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size)
+{
+	FuzzedDataProvider provider(Data, Size);
+	bool paranoid = provider.ConsumeBool();
+	std::string remainder = provider.ConsumeRemainingBytesAsString();
+
+	PyObject *mtext = PyBytes_FromStringAndSize(
+	    (const char *)remainder.c_str(), remainder.size());
+	PyObject *locals = PyDict_New();
+	PyDict_SetItemString(locals, "data", mtext);
+	PyDict_SetItemString(locals, "paranoid", paranoid ? Py_True : Py_False);
+	PyObject *res = PyEval_EvalCode(code, contrib::pyglobals(), locals);
+	if (!res) {
+		PyErr_Print();
+	}
+	Py_XDECREF(res);
+	Py_DECREF(locals);
+	Py_DECREF(mtext);
+	return 0; // Non-zero return values are reserved for future use.
+}
+}

contrib/fuzz/Makefile

@@ -1,176 +1,184 b''
 CC = clang
 CXX = clang++
 
 all: bdiff mpatch xdiff
 
 fuzzutil.o: fuzzutil.cc fuzzutil.h
 	$(CXX) $(CXXFLAGS) -g -O1 \
 	  -std=c++17 \
 	  -I../../mercurial -c -o fuzzutil.o fuzzutil.cc
 
 fuzzutil-oss-fuzz.o: fuzzutil.cc fuzzutil.h
 	$(CXX) $(CXXFLAGS) -std=c++17 \
 	  -I../../mercurial -c -o fuzzutil-oss-fuzz.o fuzzutil.cc
 
 pyutil.o: pyutil.cc pyutil.h
 	$(CXX) $(CXXFLAGS) -g -O1 \
 	  `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial -c -o pyutil.o pyutil.cc
 
 bdiff.o: ../../mercurial/bdiff.c
 	$(CC) $(CFLAGS) -fsanitize=fuzzer-no-link,address -c -o bdiff.o \
 	  ../../mercurial/bdiff.c
 
 bdiff: bdiff.cc bdiff.o fuzzutil.o
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
 	  -std=c++17 \
 	  -I../../mercurial bdiff.cc bdiff.o fuzzutil.o -o bdiff
 
 bdiff-oss-fuzz.o: ../../mercurial/bdiff.c
 	$(CC) $(CFLAGS) -c -o bdiff-oss-fuzz.o ../../mercurial/bdiff.c
 
 bdiff_fuzzer: bdiff.cc bdiff-oss-fuzz.o fuzzutil-oss-fuzz.o
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial bdiff.cc \
 	  bdiff-oss-fuzz.o fuzzutil-oss-fuzz.o -lFuzzingEngine -o \
 	  $$OUT/bdiff_fuzzer
 
 mpatch.o: ../../mercurial/mpatch.c
 	$(CC) -g -O1 -fsanitize=fuzzer-no-link,address -c -o mpatch.o \
 	  ../../mercurial/mpatch.c
 
 mpatch: CXXFLAGS += -std=c++17
 mpatch: mpatch.cc mpatch.o fuzzutil.o
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
 	  -I../../mercurial mpatch.cc mpatch.o fuzzutil.o -o mpatch
 
 mpatch-oss-fuzz.o: ../../mercurial/mpatch.c
 	$(CC) $(CFLAGS) -c -o mpatch-oss-fuzz.o ../../mercurial/mpatch.c
 
 mpatch_fuzzer: mpatch.cc mpatch-oss-fuzz.o fuzzutil-oss-fuzz.o
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial mpatch.cc \
 	  mpatch-oss-fuzz.o fuzzutil-oss-fuzz.o -lFuzzingEngine -o \
 	  $$OUT/mpatch_fuzzer
 
 mpatch_corpus.zip:
 	python mpatch_corpus.py $$OUT/mpatch_fuzzer_seed_corpus.zip
 
 x%.o: ../../mercurial/thirdparty/xdiff/x%.c ../../mercurial/thirdparty/xdiff/*.h
 	$(CC) -g -O1 -fsanitize=fuzzer-no-link,address -c \
 	  -o $@ \
 	  $<
 
 xdiff: CXXFLAGS += -std=c++17
 xdiff: xdiff.cc xdiffi.o xprepare.o xutils.o fuzzutil.o
 	$(CXX) $(CXXFLAGS) -DHG_FUZZER_INCLUDE_MAIN=1 -g -O1 -fsanitize=fuzzer-no-link,address \
 	  -I../../mercurial xdiff.cc \
 	  xdiffi.o xprepare.o xutils.o fuzzutil.o -o xdiff
 
 fuzz-x%.o: ../../mercurial/thirdparty/xdiff/x%.c ../../mercurial/thirdparty/xdiff/*.h
 	$(CC) $(CFLAGS) -c \
 	  -o $@ \
 	  $<
 
 xdiff_fuzzer: xdiff.cc fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o fuzzutil-oss-fuzz.o
 	$(CXX) $(CXXFLAGS) -std=c++17 -I../../mercurial xdiff.cc \
 	  fuzz-xdiffi.o fuzz-xprepare.o fuzz-xutils.o fuzzutil-oss-fuzz.o \
 	  -lFuzzingEngine -o $$OUT/xdiff_fuzzer
 
 manifest.o: ../../mercurial/cext/manifest.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o manifest.o ../../mercurial/cext/manifest.c
 
 charencode.o: ../../mercurial/cext/charencode.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o charencode.o ../../mercurial/cext/charencode.c
 
 parsers.o: ../../mercurial/cext/parsers.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o parsers.o ../../mercurial/cext/parsers.c
 
 dirs.o: ../../mercurial/cext/dirs.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o dirs.o ../../mercurial/cext/dirs.c
 
 pathencode.o: ../../mercurial/cext/pathencode.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o pathencode.o ../../mercurial/cext/pathencode.c
 
 revlog.o: ../../mercurial/cext/revlog.c
 	$(CC) $(CFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -I../../mercurial \
 	  -c -o revlog.o ../../mercurial/cext/revlog.c
 
 dirs_fuzzer: dirs.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial dirs.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/dirs_fuzzer
 
 fncache_fuzzer: fncache.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial fncache.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/fncache_fuzzer
 
+jsonescapeu8fast_fuzzer: jsonescapeu8fast.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
+	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
+	  -Wno-register -Wno-macro-redefined \
+	  -I../../mercurial jsonescapeu8fast.cc \
+	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
+	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
+	  -o $$OUT/jsonescapeu8fast_fuzzer
+
 manifest_corpus.zip:
 	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
 
 manifest_fuzzer: manifest.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial manifest.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/manifest_fuzzer
 
 revlog_fuzzer: revlog.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial revlog.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/revlog_fuzzer
 
 revlog_corpus.zip:
 	python revlog_corpus.py $$OUT/revlog_fuzzer_seed_corpus.zip
 
 dirstate_fuzzer: dirstate.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial dirstate.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/dirstate_fuzzer
 
 dirstate_corpus.zip:
 	python dirstate_corpus.py $$OUT/dirstate_fuzzer_seed_corpus.zip
 
 fm1readmarkers_fuzzer: fm1readmarkers.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
 	  -I../../mercurial fm1readmarkers.cc \
 	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/fm1readmarkers_fuzzer
 
 fm1readmarkers_corpus.zip:
 	python fm1readmarkers_corpus.py $$OUT/fm1readmarkers_fuzzer_seed_corpus.zip
 
 clean:
 	$(RM) *.o *_fuzzer \
 	  bdiff \
 	  mpatch \
 	  xdiff
 
-oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer dirs_fuzzer fncache_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip dirstate_fuzzer dirstate_corpus.zip fm1readmarkers_fuzzer fm1readmarkers_corpus.zip
+oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer dirs_fuzzer fncache_fuzzer jsonescapeu8fast_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip dirstate_fuzzer dirstate_corpus.zip fm1readmarkers_fuzzer fm1readmarkers_corpus.zip
 
 .PHONY: all clean oss-fuzz