fuzz: use a more standard approach to allow local builds of fuzzers

fuzz: use a more standard approach to allow local builds of fuzzers

This is taken from the (improved since we started fuzzing) guide on ideal
integrations. Rather than have our own wonky targets for building outside the
fuzzer universe, we have a driver program we carry along and use when we're
not using LibFuzzer. This will let us jettison a fair amount of goo.

contrib/fuzz/standalone_fuzz_target_runner.cc is
https://github.com/google/oss-fuzz/ file
projects/example/my-api-repo/standalone from git revision
c4579d9358a73ea5dbcc99cb985de1f2bf76dcf7, reformatted with out
clang-format settings and a no-check-code comment added. It allows
running a single test input through a fuzzer, rather than performing
ongoing fuzzing as libfuzzer would.

contrib/fuzz/FuzzedDataProvider.h is
https://github.com/llvm/llvm-project/ file
/compiler-rt/include/fuzzer/FuzzedDataProvider.h from git revision
a44ef027ebca1598892ea9b104d6189aeb3bc2f0, reformatted with our
clang-format settings and a no-check-code comment added. We can
discard this if we instead want to add an hghave check for a new
enough llvm that includes FuzzedDataProvder.h in the fuzzer headers.

Differential Revision: https://phab.mercurial-scm.org/D7564

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/contrib/fuzz/FuzzedDataProvider.h	Fri Dec 06 15:19:47 2019 -0500
@@ -0,0 +1,368 @@
+//===- FuzzedDataProvider.h - Utility header for fuzz targets ---*- C++ -* ===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+// A single header library providing an utility class to break up an array of
+// bytes. Whenever run on the same input, provides the same output, as long as
+// its methods are called in the same order, with the same arguments.
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_FUZZER_FUZZED_DATA_PROVIDER_H_
+#define LLVM_FUZZER_FUZZED_DATA_PROVIDER_H_
+
+#include <algorithm>
+#include <climits>
+#include <cstddef>
+#include <cstdint>
+#include <cstring>
+#include <initializer_list>
+#include <string>
+#include <type_traits>
+#include <utility>
+#include <vector>
+
+// In addition to the comments below, the API is also briefly documented at
+// https://github.com/google/fuzzing/blob/master/docs/split-inputs.md#fuzzed-data-provider
+class FuzzedDataProvider
+{
+      public:
+	// |data| is an array of length |size| that the FuzzedDataProvider wraps
+	// to provide more granular access. |data| must outlive the
+	// FuzzedDataProvider.
+	FuzzedDataProvider(const uint8_t *data, size_t size)
+	    : data_ptr_(data), remaining_bytes_(size)
+	{
+	}
+	~FuzzedDataProvider() = default;
+
+	// Returns a std::vector containing |num_bytes| of input data. If fewer
+	// than |num_bytes| of data remain, returns a shorter std::vector
+	// containing all of the data that's left. Can be used with any byte
+	// sized type, such as char, unsigned char, uint8_t, etc.
+	template <typename T> std::vector<T> ConsumeBytes(size_t num_bytes)
+	{
+		num_bytes = std::min(num_bytes, remaining_bytes_);
+		return ConsumeBytes<T>(num_bytes, num_bytes);
+	}
+
+	// Similar to |ConsumeBytes|, but also appends the terminator value at
+	// the end of the resulting vector. Useful, when a mutable
+	// null-terminated C-string is needed, for example. But that is a rare
+	// case. Better avoid it, if possible, and prefer using |ConsumeBytes|
+	// or |ConsumeBytesAsString| methods.
+	template <typename T>
+	std::vector<T> ConsumeBytesWithTerminator(size_t num_bytes,
+	                                          T terminator = 0)
+	{
+		num_bytes = std::min(num_bytes, remaining_bytes_);
+		std::vector<T> result =
+		    ConsumeBytes<T>(num_bytes + 1, num_bytes);
+		result.back() = terminator;
+		return result;
+	}
+
+	// Returns a std::string containing |num_bytes| of input data. Using
+	// this and
+	// |.c_str()| on the resulting string is the best way to get an
+	// immutable null-terminated C string. If fewer than |num_bytes| of data
+	// remain, returns a shorter std::string containing all of the data
+	// that's left.
+	std::string ConsumeBytesAsString(size_t num_bytes)
+	{
+		static_assert(sizeof(std::string::value_type) ==
+		                  sizeof(uint8_t),
+		              "ConsumeBytesAsString cannot convert the data to "
+		              "a string.");
+
+		num_bytes = std::min(num_bytes, remaining_bytes_);
+		std::string result(
+		    reinterpret_cast<const std::string::value_type *>(
+		        data_ptr_),
+		    num_bytes);
+		Advance(num_bytes);
+		return result;
+	}
+
+	// Returns a number in the range [min, max] by consuming bytes from the
+	// input data. The value might not be uniformly distributed in the given
+	// range. If there's no input data left, always returns |min|. |min|
+	// must be less than or equal to |max|.
+	template <typename T> T ConsumeIntegralInRange(T min, T max)
+	{
+		static_assert(std::is_integral<T>::value,
+		              "An integral type is required.");
+		static_assert(sizeof(T) <= sizeof(uint64_t),
+		              "Unsupported integral type.");
+
+		if (min > max)
+			abort();
+
+		// Use the biggest type possible to hold the range and the
+		// result.
+		uint64_t range = static_cast<uint64_t>(max) - min;
+		uint64_t result = 0;
+		size_t offset = 0;
+
+		while (offset < sizeof(T) * CHAR_BIT && (range >> offset) > 0 &&
+		       remaining_bytes_ != 0) {
+			// Pull bytes off the end of the seed data.
+			// Experimentally, this seems to allow the fuzzer to
+			// more easily explore the input space. This makes
+			// sense, since it works by modifying inputs that caused
+			// new code to run, and this data is often used to
+			// encode length of data read by |ConsumeBytes|.
+			// Separating out read lengths makes it easier modify
+			// the contents of the data that is actually read.
+			--remaining_bytes_;
+			result =
+			    (result << CHAR_BIT) | data_ptr_[remaining_bytes_];
+			offset += CHAR_BIT;
+		}
+
+		// Avoid division by 0, in case |range + 1| results in overflow.
+		if (range != std::numeric_limits<decltype(range)>::max())
+			result = result % (range + 1);
+
+		return static_cast<T>(min + result);
+	}
+
+	// Returns a std::string of length from 0 to |max_length|. When it runs
+	// out of input data, returns what remains of the input. Designed to be
+	// more stable with respect to a fuzzer inserting characters than just
+	// picking a random length and then consuming that many bytes with
+	// |ConsumeBytes|.
+	std::string ConsumeRandomLengthString(size_t max_length)
+	{
+		// Reads bytes from the start of |data_ptr_|. Maps "\\" to "\",
+		// and maps "\" followed by anything else to the end of the
+		// string. As a result of this logic, a fuzzer can insert
+		// characters into the string, and the string will be lengthened
+		// to include those new characters, resulting in a more stable
+		// fuzzer than picking the length of a string independently from
+		// picking its contents.
+		std::string result;
+
+		// Reserve the anticipated capaticity to prevent several
+		// reallocations.
+		result.reserve(std::min(max_length, remaining_bytes_));
+		for (size_t i = 0; i < max_length && remaining_bytes_ != 0;
+		     ++i) {
+			char next = ConvertUnsignedToSigned<char>(data_ptr_[0]);
+			Advance(1);
+			if (next == '\\' && remaining_bytes_ != 0) {
+				next =
+				    ConvertUnsignedToSigned<char>(data_ptr_[0]);
+				Advance(1);
+				if (next != '\\')
+					break;
+			}
+			result += next;
+		}
+
+		result.shrink_to_fit();
+		return result;
+	}
+
+	// Returns a std::vector containing all remaining bytes of the input
+	// data.
+	template <typename T> std::vector<T> ConsumeRemainingBytes()
+	{
+		return ConsumeBytes<T>(remaining_bytes_);
+	}
+
+	// Returns a std::string containing all remaining bytes of the input
+	// data. Prefer using |ConsumeRemainingBytes| unless you actually need a
+	// std::string object.
+	std::string ConsumeRemainingBytesAsString()
+	{
+		return ConsumeBytesAsString(remaining_bytes_);
+	}
+
+	// Returns a number in the range [Type's min, Type's max]. The value
+	// might not be uniformly distributed in the given range. If there's no
+	// input data left, always returns |min|.
+	template <typename T> T ConsumeIntegral()
+	{
+		return ConsumeIntegralInRange(std::numeric_limits<T>::min(),
+		                              std::numeric_limits<T>::max());
+	}
+
+	// Reads one byte and returns a bool, or false when no data remains.
+	bool ConsumeBool()
+	{
+		return 1 & ConsumeIntegral<uint8_t>();
+	}
+
+	// Returns a copy of the value selected from the given fixed-size
+	// |array|.
+	template <typename T, size_t size>
+	T PickValueInArray(const T (&array)[size])
+	{
+		static_assert(size > 0, "The array must be non empty.");
+		return array[ConsumeIntegralInRange<size_t>(0, size - 1)];
+	}
+
+	template <typename T>
+	T PickValueInArray(std::initializer_list<const T> list)
+	{
+		// TODO(Dor1s): switch to static_assert once C++14 is allowed.
+		if (!list.size())
+			abort();
+
+		return *(list.begin() +
+		         ConsumeIntegralInRange<size_t>(0, list.size() - 1));
+	}
+
+	// Returns an enum value. The enum must start at 0 and be contiguous. It
+	// must also contain |kMaxValue| aliased to its largest (inclusive)
+	// value. Such as: enum class Foo { SomeValue, OtherValue, kMaxValue =
+	// OtherValue };
+	template <typename T> T ConsumeEnum()
+	{
+		static_assert(std::is_enum<T>::value,
+		              "|T| must be an enum type.");
+		return static_cast<T>(ConsumeIntegralInRange<uint32_t>(
+		    0, static_cast<uint32_t>(T::kMaxValue)));
+	}
+
+	// Returns a floating point number in the range [0.0, 1.0]. If there's
+	// no input data left, always returns 0.
+	template <typename T> T ConsumeProbability()
+	{
+		static_assert(std::is_floating_point<T>::value,
+		              "A floating point type is required.");
+
+		// Use different integral types for different floating point
+		// types in order to provide better density of the resulting
+		// values.
+		using IntegralType =
+		    typename std::conditional<(sizeof(T) <= sizeof(uint32_t)),
+		                              uint32_t, uint64_t>::type;
+
+		T result = static_cast<T>(ConsumeIntegral<IntegralType>());
+		result /=
+		    static_cast<T>(std::numeric_limits<IntegralType>::max());
+		return result;
+	}
+
+	// Returns a floating point value in the range [Type's lowest, Type's
+	// max] by consuming bytes from the input data. If there's no input data
+	// left, always returns approximately 0.
+	template <typename T> T ConsumeFloatingPoint()
+	{
+		return ConsumeFloatingPointInRange<T>(
+		    std::numeric_limits<T>::lowest(),
+		    std::numeric_limits<T>::max());
+	}
+
+	// Returns a floating point value in the given range by consuming bytes
+	// from the input data. If there's no input data left, returns |min|.
+	// Note that |min| must be less than or equal to |max|.
+	template <typename T> T ConsumeFloatingPointInRange(T min, T max)
+	{
+		if (min > max)
+			abort();
+
+		T range = .0;
+		T result = min;
+		constexpr T zero(.0);
+		if (max > zero && min < zero &&
+		    max > min + std::numeric_limits<T>::max()) {
+			// The diff |max - min| would overflow the given
+			// floating point type. Use the half of the diff as the
+			// range and consume a bool to decide whether the result
+			// is in the first of the second part of the diff.
+			range = (max / 2.0) - (min / 2.0);
+			if (ConsumeBool()) {
+				result += range;
+			}
+		} else {
+			range = max - min;
+		}
+
+		return result + range * ConsumeProbability<T>();
+	}
+
+	// Reports the remaining bytes available for fuzzed input.
+	size_t remaining_bytes()
+	{
+		return remaining_bytes_;
+	}
+
+      private:
+	FuzzedDataProvider(const FuzzedDataProvider &) = delete;
+	FuzzedDataProvider &operator=(const FuzzedDataProvider &) = delete;
+
+	void Advance(size_t num_bytes)
+	{
+		if (num_bytes > remaining_bytes_)
+			abort();
+
+		data_ptr_ += num_bytes;
+		remaining_bytes_ -= num_bytes;
+	}
+
+	template <typename T>
+	std::vector<T> ConsumeBytes(size_t size, size_t num_bytes_to_consume)
+	{
+		static_assert(sizeof(T) == sizeof(uint8_t),
+		              "Incompatible data type.");
+
+		// The point of using the size-based constructor below is to
+		// increase the odds of having a vector object with capacity
+		// being equal to the length. That part is always implementation
+		// specific, but at least both libc++ and libstdc++ allocate the
+		// requested number of bytes in that constructor, which seems to
+		// be a natural choice for other implementations as well. To
+		// increase the odds even more, we also call |shrink_to_fit|
+		// below.
+		std::vector<T> result(size);
+		if (size == 0) {
+			if (num_bytes_to_consume != 0)
+				abort();
+			return result;
+		}
+
+		std::memcpy(result.data(), data_ptr_, num_bytes_to_consume);
+		Advance(num_bytes_to_consume);
+
+		// Even though |shrink_to_fit| is also implementation specific,
+		// we expect it to provide an additional assurance in case
+		// vector's constructor allocated a buffer which is larger than
+		// the actual amount of data we put inside it.
+		result.shrink_to_fit();
+		return result;
+	}
+
+	template <typename TS, typename TU> TS ConvertUnsignedToSigned(TU value)
+	{
+		static_assert(sizeof(TS) == sizeof(TU),
+		              "Incompatible data types.");
+		static_assert(!std::numeric_limits<TU>::is_signed,
+		              "Source type must be unsigned.");
+
+		// TODO(Dor1s): change to `if constexpr` once C++17 becomes
+		// mainstream.
+		if (std::numeric_limits<TS>::is_modulo)
+			return static_cast<TS>(value);
+
+		// Avoid using implementation-defined unsigned to signer
+		// conversions. To learn more, see
+		// https://stackoverflow.com/questions/13150449.
+		if (value <= std::numeric_limits<TS>::max()) {
+			return static_cast<TS>(value);
+		} else {
+			constexpr auto TS_min = std::numeric_limits<TS>::min();
+			return TS_min + static_cast<char>(value - TS_min);
+		}
+	}
+
+	const uint8_t *data_ptr_;
+	size_t remaining_bytes_;
+};
+
+#endif // LLVM_FUZZER_FUZZED_DATA_PROVIDER_H_
+// no-check-code since this is from a third party

--- a/contrib/fuzz/Makefile	Fri Dec 06 15:15:05 2019 -0500
+++ b/contrib/fuzz/Makefile	Fri Dec 06 15:19:47 2019 -0500
@@ -1,7 +1,14 @@
 CC = clang
 CXX = clang++
 
-LIB_FUZZING_ENGINE ?= -lFuzzingEngine
+# By default, use our own standalone_fuzz_target_runner.
+# This runner does no fuzzing, but simply executes the inputs
+# provided via parameters.
+# Run e.g. "make all LIB_FUZZING_ENGINE=/path/to/libFuzzer.a"
+# to link the fuzzer(s) against a real fuzzing engine.
+#
+# OSS-Fuzz will define its own value for LIB_FUZZING_ENGINE.
+LIB_FUZZING_ENGINE ?= standalone_fuzz_target_runner.o
 
 PYTHON_CONFIG ?= $$OUT/sanpy/bin/python-config
 
@@ -9,6 +16,8 @@
 
 all: bdiff mpatch xdiff
 
+standalone_fuzz_target_runner.o: standalone_fuzz_target_runner.cc
+
 pyutil.o: pyutil.cc pyutil.h
 	$(CXX) $(CXXFLAGS) -g -O1 \
 	  `$(PYTHON_CONFIG) --cflags` \

--- a/contrib/fuzz/bdiff.cc	Fri Dec 06 15:15:05 2019 -0500
+++ b/contrib/fuzz/bdiff.cc	Fri Dec 06 15:19:47 2019 -0500
@@ -9,7 +9,7 @@
 #include <memory>
 #include <stdlib.h>
 
-#include <fuzzer/FuzzedDataProvider.h>
+#include "FuzzedDataProvider.h"
 
 extern "C" {
 #include "bdiff.h"

--- a/contrib/fuzz/jsonescapeu8fast.cc	Fri Dec 06 15:15:05 2019 -0500
+++ b/contrib/fuzz/jsonescapeu8fast.cc	Fri Dec 06 15:19:47 2019 -0500
@@ -5,9 +5,9 @@
 
 #include "pyutil.h"
 
-#include <fuzzer/FuzzedDataProvider.h>
 #include <iostream>
 #include <string>
+#include "FuzzedDataProvider.h"
 
 extern "C" {
 

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/contrib/fuzz/standalone_fuzz_target_runner.cc	Fri Dec 06 15:19:47 2019 -0500
@@ -0,0 +1,41 @@
+// Copyright 2017 Google Inc. All Rights Reserved.
+// Licensed under the Apache License, Version 2.0 (the "License");
+
+// Example of a standalone runner for "fuzz targets".
+// It reads all files passed as parameters and feeds their contents
+// one by one into the fuzz target (LLVMFuzzerTestOneInput).
+// This runner does not do any fuzzing, but allows us to run the fuzz target
+// on the test corpus (e.g. "do_stuff_test_data") or on a single file,
+// e.g. the one that comes from a bug report.
+
+#include <cassert>
+#include <fstream>
+#include <iostream>
+#include <vector>
+
+// Forward declare the "fuzz target" interface.
+// We deliberately keep this inteface simple and header-free.
+extern "C" int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
+
+int main(int argc, char **argv)
+{
+	for (int i = 1; i < argc; i++) {
+		std::ifstream in(argv[i]);
+		in.seekg(0, in.end);
+		size_t length = in.tellg();
+		in.seekg(0, in.beg);
+		std::cout << "Reading " << length << " bytes from " << argv[i]
+		          << std::endl;
+		// Allocate exactly length bytes so that we reliably catch
+		// buffer overflows.
+		std::vector<char> bytes(length);
+		in.read(bytes.data(), bytes.size());
+		assert(in);
+		LLVMFuzzerTestOneInput(
+		    reinterpret_cast<const uint8_t *>(bytes.data()),
+		    bytes.size());
+		std::cout << "Execution successful" << std::endl;
+	}
+	return 0;
+}
+// no-check-code since this is from a third party

--- a/contrib/fuzz/xdiff.cc	Fri Dec 06 15:15:05 2019 -0500
+++ b/contrib/fuzz/xdiff.cc	Fri Dec 06 15:19:47 2019 -0500
@@ -10,7 +10,7 @@
 #include <inttypes.h>
 #include <stdlib.h>
 
-#include <fuzzer/FuzzedDataProvider.h>
+#include "FuzzedDataProvider.h"
 
 extern "C" {
 

--- a/tests/test-check-code.t	Fri Dec 06 15:15:05 2019 -0500
+++ b/tests/test-check-code.t	Fri Dec 06 15:19:47 2019 -0500
@@ -21,6 +21,8 @@
   Skipping contrib/automation/hgautomation/try_server.py it has no-che?k-code (glob)
   Skipping contrib/automation/hgautomation/windows.py it has no-che?k-code (glob)
   Skipping contrib/automation/hgautomation/winrm.py it has no-che?k-code (glob)
+  Skipping contrib/fuzz/FuzzedDataProvider.h it has no-che?k-code (glob)
+  Skipping contrib/fuzz/standalone_fuzz_target_runner.cc it has no-che?k-code (glob)
   Skipping contrib/packaging/hgpackaging/cli.py it has no-che?k-code (glob)
   Skipping contrib/packaging/hgpackaging/downloads.py it has no-che?k-code (glob)
   Skipping contrib/packaging/hgpackaging/inno.py it has no-che?k-code (glob)