diff options
Diffstat (limited to 'src')
-rw-r--r-- | src/.clang-format | 1 | ||||
-rw-r--r-- | src/Makefile.am | 2 | ||||
-rw-r--r-- | src/Makefile.test.include | 10 | ||||
-rw-r--r-- | src/qt/forms/signverifymessagedialog.ui | 18 | ||||
-rw-r--r-- | src/script/descriptor.cpp | 66 | ||||
-rw-r--r-- | src/script/descriptor.h | 78 | ||||
-rw-r--r-- | src/test/fs_tests.cpp | 2 | ||||
-rw-r--r-- | src/test/fuzz/FuzzedDataProvider.h | 245 | ||||
-rw-r--r-- | src/test/fuzz/eval_script.cpp | 30 | ||||
-rw-r--r-- | src/test/util_tests.cpp | 124 | ||||
-rw-r--r-- | src/util/spanparsing.cpp | 67 | ||||
-rw-r--r-- | src/util/spanparsing.h | 50 | ||||
-rw-r--r-- | src/wallet/test/wallet_tests.cpp | 78 |
13 files changed, 672 insertions, 99 deletions
diff --git a/src/.clang-format b/src/.clang-format index 38e19edf2c..aae039dd77 100644 --- a/src/.clang-format +++ b/src/.clang-format @@ -5,6 +5,7 @@ AlignEscapedNewlinesLeft: true AlignTrailingComments: true AllowAllParametersOfDeclarationOnNextLine: false AllowShortBlocksOnASingleLine: false +AllowShortCaseLabelsOnASingleLine: true AllowShortFunctionsOnASingleLine: All AllowShortIfStatementsOnASingleLine: true AllowShortLoopsOnASingleLine: false diff --git a/src/Makefile.am b/src/Makefile.am index 84254e45d1..eec84122ae 100644 --- a/src/Makefile.am +++ b/src/Makefile.am @@ -208,6 +208,7 @@ BITCOIN_CORE_H = \ util/bytevectorhash.h \ util/error.h \ util/fees.h \ + util/spanparsing.h \ util/system.h \ util/macros.h \ util/memory.h \ @@ -505,6 +506,7 @@ libbitcoin_util_a_SOURCES = \ util/moneystr.cpp \ util/rbf.cpp \ util/threadnames.cpp \ + util/spanparsing.cpp \ util/strencodings.cpp \ util/string.cpp \ util/time.cpp \ diff --git a/src/Makefile.test.include b/src/Makefile.test.include index 48df50d100..b8957e52bd 100644 --- a/src/Makefile.test.include +++ b/src/Makefile.test.include @@ -17,6 +17,7 @@ FUZZ_TARGETS = \ test/fuzz/bloomfilter_deserialize \ test/fuzz/coins_deserialize \ test/fuzz/diskblockindex_deserialize \ + test/fuzz/eval_script \ test/fuzz/inv_deserialize \ test/fuzz/messageheader_deserialize \ test/fuzz/netaddr_deserialize \ @@ -59,7 +60,8 @@ FUZZ_SUITE = \ test/setup_common.h \ test/setup_common.cpp \ test/fuzz/fuzz.cpp \ - test/fuzz/fuzz.h + test/fuzz/fuzz.h \ + test/fuzz/FuzzedDataProvider.h FUZZ_SUITE_LD_COMMON = \ $(LIBBITCOIN_SERVER) \ @@ -298,6 +300,12 @@ test_fuzz_diskblockindex_deserialize_CXXFLAGS = $(AM_CXXFLAGS) $(PIE_FLAGS) test_fuzz_diskblockindex_deserialize_LDFLAGS = $(RELDFLAGS) $(AM_LDFLAGS) $(LIBTOOL_APP_LDFLAGS) test_fuzz_diskblockindex_deserialize_LDADD = $(FUZZ_SUITE_LD_COMMON) +test_fuzz_eval_script_SOURCES = $(FUZZ_SUITE) test/fuzz/eval_script.cpp +test_fuzz_eval_script_CPPFLAGS = $(AM_CPPFLAGS) $(BITCOIN_INCLUDES) +test_fuzz_eval_script_CXXFLAGS = $(AM_CXXFLAGS) $(PIE_FLAGS) +test_fuzz_eval_script_LDFLAGS = $(RELDFLAGS) $(AM_LDFLAGS) $(LIBTOOL_APP_LDFLAGS) +test_fuzz_eval_script_LDADD = $(FUZZ_SUITE_LD_COMMON) + test_fuzz_txoutcompressor_deserialize_SOURCES = $(FUZZ_SUITE) test/fuzz/deserialize.cpp test_fuzz_txoutcompressor_deserialize_CPPFLAGS = $(AM_CPPFLAGS) $(BITCOIN_INCLUDES) -DTXOUTCOMPRESSOR_DESERIALIZE=1 test_fuzz_txoutcompressor_deserialize_CXXFLAGS = $(AM_CXXFLAGS) $(PIE_FLAGS) diff --git a/src/qt/forms/signverifymessagedialog.ui b/src/qt/forms/signverifymessagedialog.ui index c9ddd757c1..8a7bdfdbc6 100644 --- a/src/qt/forms/signverifymessagedialog.ui +++ b/src/qt/forms/signverifymessagedialog.ui @@ -285,10 +285,24 @@ </layout> </item> <item> - <widget class="QPlainTextEdit" name="messageIn_VM"/> + <widget class="QPlainTextEdit" name="messageIn_VM"> + <property name="toolTip"> + <string>The signed message to verify</string> + </property> + <property name="placeholderText"> + <string>The signed message to verify</string> + </property> + </widget> </item> <item> - <widget class="QValidatedLineEdit" name="signatureIn_VM"/> + <widget class="QValidatedLineEdit" name="signatureIn_VM"> + <property name="toolTip"> + <string>The signature given when the message was signed</string> + </property> + <property name="placeholderText"> + <string>The signature given when the message was signed</string> + </property> + </widget> </item> <item> <layout class="QHBoxLayout" name="horizontalLayout_2_VM"> diff --git a/src/script/descriptor.cpp b/src/script/descriptor.cpp index b223349eb1..ed1bd4cda9 100644 --- a/src/script/descriptor.cpp +++ b/src/script/descriptor.cpp @@ -11,6 +11,7 @@ #include <span.h> #include <util/bip32.h> +#include <util/spanparsing.h> #include <util/system.h> #include <util/strencodings.h> @@ -640,63 +641,6 @@ enum class ParseScriptContext { P2WSH, }; -/** Parse a constant. If successful, sp is updated to skip the constant and return true. */ -bool Const(const std::string& str, Span<const char>& sp) -{ - if ((size_t)sp.size() >= str.size() && std::equal(str.begin(), str.end(), sp.begin())) { - sp = sp.subspan(str.size()); - return true; - } - return false; -} - -/** Parse a function call. If successful, sp is updated to be the function's argument(s). */ -bool Func(const std::string& str, Span<const char>& sp) -{ - if ((size_t)sp.size() >= str.size() + 2 && sp[str.size()] == '(' && sp[sp.size() - 1] == ')' && std::equal(str.begin(), str.end(), sp.begin())) { - sp = sp.subspan(str.size() + 1, sp.size() - str.size() - 2); - return true; - } - return false; -} - -/** Return the expression that sp begins with, and update sp to skip it. */ -Span<const char> Expr(Span<const char>& sp) -{ - int level = 0; - auto it = sp.begin(); - while (it != sp.end()) { - if (*it == '(') { - ++level; - } else if (level && *it == ')') { - --level; - } else if (level == 0 && (*it == ')' || *it == ',')) { - break; - } - ++it; - } - Span<const char> ret = sp.first(it - sp.begin()); - sp = sp.subspan(it - sp.begin()); - return ret; -} - -/** Split a string on every instance of sep, returning a vector. */ -std::vector<Span<const char>> Split(const Span<const char>& sp, char sep) -{ - std::vector<Span<const char>> ret; - auto it = sp.begin(); - auto start = it; - while (it != sp.end()) { - if (*it == sep) { - ret.emplace_back(start, it); - start = it + 1; - } - ++it; - } - ret.emplace_back(start, it); - return ret; -} - /** Parse a key path, being passed a split list of elements (the first element is ignored). */ NODISCARD bool ParseKeyPath(const std::vector<Span<const char>>& split, KeyPath& out, std::string& error) { @@ -723,6 +667,8 @@ NODISCARD bool ParseKeyPath(const std::vector<Span<const char>>& split, KeyPath& /** Parse a public key that excludes origin information. */ std::unique_ptr<PubkeyProvider> ParsePubkeyInner(const Span<const char>& sp, bool permit_uncompressed, FlatSigningProvider& out, std::string& error) { + using namespace spanparsing; + auto split = Split(sp, '/'); std::string str(split[0].begin(), split[0].end()); if (str.size() == 0) { @@ -782,6 +728,8 @@ std::unique_ptr<PubkeyProvider> ParsePubkeyInner(const Span<const char>& sp, boo /** Parse a public key including origin information (if enabled). */ std::unique_ptr<PubkeyProvider> ParsePubkey(const Span<const char>& sp, bool permit_uncompressed, FlatSigningProvider& out, std::string& error) { + using namespace spanparsing; + auto origin_split = Split(sp, ']'); if (origin_split.size() > 2) { error = "Multiple ']' characters found for a single pubkey"; @@ -816,6 +764,8 @@ std::unique_ptr<PubkeyProvider> ParsePubkey(const Span<const char>& sp, bool per /** Parse a script in a particular context. */ std::unique_ptr<DescriptorImpl> ParseScript(Span<const char>& sp, ParseScriptContext ctx, FlatSigningProvider& out, std::string& error) { + using namespace spanparsing; + auto expr = Expr(sp); bool sorted_multi = false; if (Func("pk", expr)) { @@ -1012,6 +962,8 @@ std::unique_ptr<DescriptorImpl> InferScript(const CScript& script, ParseScriptCo /** Check a descriptor checksum, and update desc to be the checksum-less part. */ bool CheckChecksum(Span<const char>& sp, bool require_checksum, std::string& error, std::string* out_checksum = nullptr) { + using namespace spanparsing; + auto check_split = Split(sp, '#'); if (check_split.size() > 2) { error = "Multiple '#' symbols"; diff --git a/src/script/descriptor.h b/src/script/descriptor.h index 0195ca0939..5a1b55259a 100644 --- a/src/script/descriptor.h +++ b/src/script/descriptor.h @@ -11,22 +11,24 @@ #include <vector> -// Descriptors are strings that describe a set of scriptPubKeys, together with -// all information necessary to solve them. By combining all information into -// one, they avoid the need to separately import keys and scripts. -// -// Descriptors may be ranged, which occurs when the public keys inside are -// specified in the form of HD chains (xpubs). -// -// Descriptors always represent public information - public keys and scripts - -// but in cases where private keys need to be conveyed along with a descriptor, -// they can be included inside by changing public keys to private keys (WIF -// format), and changing xpubs by xprvs. -// -// Reference documentation about the descriptor language can be found in -// doc/descriptors.md. - -/** Interface for parsed descriptor objects. */ + +/** \brief Interface for parsed descriptor objects. + * + * Descriptors are strings that describe a set of scriptPubKeys, together with + * all information necessary to solve them. By combining all information into + * one, they avoid the need to separately import keys and scripts. + * + * Descriptors may be ranged, which occurs when the public keys inside are + * specified in the form of HD chains (xpubs). + * + * Descriptors always represent public information - public keys and scripts - + * but in cases where private keys need to be conveyed along with a descriptor, + * they can be included inside by changing public keys to private keys (WIF + * format), and changing xpubs by xprvs. + * + * Reference documentation about the descriptor language can be found in + * doc/descriptors.md. + */ struct Descriptor { virtual ~Descriptor() = default; @@ -45,51 +47,51 @@ struct Descriptor { /** Expand a descriptor at a specified position. * - * pos: the position at which to expand the descriptor. If IsRange() is false, this is ignored. - * provider: the provider to query for private keys in case of hardened derivation. - * output_scripts: the expanded scriptPubKeys will be put here. - * out: scripts and public keys necessary for solving the expanded scriptPubKeys will be put here (may be equal to provider). - * cache: vector which will be overwritten with cache data necessary to evaluate the descriptor at this point without access to private keys. + * @param[in] pos: The position at which to expand the descriptor. If IsRange() is false, this is ignored. + * @param[in] provider: The provider to query for private keys in case of hardened derivation. + * @param[out] output_scripts: The expanded scriptPubKeys. + * @param[out] out: Scripts and public keys necessary for solving the expanded scriptPubKeys (may be equal to `provider`). + * @param[out] cache: Cache data necessary to evaluate the descriptor at this point without access to private keys. */ virtual bool Expand(int pos, const SigningProvider& provider, std::vector<CScript>& output_scripts, FlatSigningProvider& out, std::vector<unsigned char>* cache = nullptr) const = 0; /** Expand a descriptor at a specified position using cached expansion data. * - * pos: the position at which to expand the descriptor. If IsRange() is false, this is ignored. - * cache: vector from which cached expansion data will be read. - * output_scripts: the expanded scriptPubKeys will be put here. - * out: scripts and public keys necessary for solving the expanded scriptPubKeys will be put here (may be equal to provider). + * @param[in] pos: The position at which to expand the descriptor. If IsRange() is false, this is ignored. + * @param[in] cache: Cached expansion data. + * @param[out] output_scripts: The expanded scriptPubKeys. + * @param[out] out: Scripts and public keys necessary for solving the expanded scriptPubKeys (may be equal to `provider`). */ virtual bool ExpandFromCache(int pos, const std::vector<unsigned char>& cache, std::vector<CScript>& output_scripts, FlatSigningProvider& out) const = 0; /** Expand the private key for a descriptor at a specified position, if possible. * - * pos: the position at which to expand the descriptor. If IsRange() is false, this is ignored. - * provider: the provider to query for the private keys. - * out: any private keys available for the specified pos will be placed here. + * @param[in] pos: The position at which to expand the descriptor. If IsRange() is false, this is ignored. + * @param[in] provider: The provider to query for the private keys. + * @param[out] out: Any private keys available for the specified `pos`. */ virtual void ExpandPrivate(int pos, const SigningProvider& provider, FlatSigningProvider& out) const = 0; }; -/** Parse a descriptor string. Included private keys are put in out. +/** Parse a `descriptor` string. Included private keys are put in `out`. * - * If the descriptor has a checksum, it must be valid. If require_checksum + * If the descriptor has a checksum, it must be valid. If `require_checksum` * is set, the checksum is mandatory - otherwise it is optional. * * If a parse error occurs, or the checksum is missing/invalid, or anything - * else is wrong, nullptr is returned. + * else is wrong, `nullptr` is returned. */ std::unique_ptr<Descriptor> Parse(const std::string& descriptor, FlatSigningProvider& out, std::string& error, bool require_checksum = false); -/** Get the checksum for a descriptor. +/** Get the checksum for a `descriptor`. * - * If it already has one, and it is correct, return the checksum in the input. - * If it already has one that is wrong, return "". - * If it does not already have one, return the checksum that would need to be added. + * - If it already has one, and it is correct, return the checksum in the input. + * - If it already has one that is wrong, return "". + * - If it does not already have one, return the checksum that would need to be added. */ std::string GetDescriptorChecksum(const std::string& descriptor); -/** Find a descriptor for the specified script, using information from provider where possible. +/** Find a descriptor for the specified `script`, using information from `provider` where possible. * * A non-ranged descriptor which only generates the specified script will be returned in all * circumstances. @@ -98,9 +100,9 @@ std::string GetDescriptorChecksum(const std::string& descriptor); * descriptor. * * - If all information for solving `script` is present in `provider`, a descriptor will be returned - * which is `IsSolvable()` and encapsulates said information. + * which is IsSolvable() and encapsulates said information. * - Failing that, if `script` corresponds to a known address type, an "addr()" descriptor will be - * returned (which is not `IsSolvable()`). + * returned (which is not IsSolvable()). * - Failing that, a "raw()" descriptor is returned. */ std::unique_ptr<Descriptor> InferDescriptor(const CScript& script, const SigningProvider& provider); diff --git a/src/test/fs_tests.cpp b/src/test/fs_tests.cpp index 6d5a6641f0..b504a3cbb1 100644 --- a/src/test/fs_tests.cpp +++ b/src/test/fs_tests.cpp @@ -15,7 +15,7 @@ BOOST_AUTO_TEST_CASE(fsbridge_fstream) fs::path tmpfolder = GetDataDir(); // tmpfile1 should be the same as tmpfile2 fs::path tmpfile1 = tmpfolder / "fs_tests_₿_🏃"; - fs::path tmpfile2 = tmpfolder / L"fs_tests_₿_🏃"; + fs::path tmpfile2 = tmpfolder / "fs_tests_₿_🏃"; { fsbridge::ofstream file(tmpfile1); file << "bitcoin"; diff --git a/src/test/fuzz/FuzzedDataProvider.h b/src/test/fuzz/FuzzedDataProvider.h new file mode 100644 index 0000000000..1b5b4bb012 --- /dev/null +++ b/src/test/fuzz/FuzzedDataProvider.h @@ -0,0 +1,245 @@ +//===- 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 <limits.h> +#include <stddef.h> +#include <stdint.h> + +#include <algorithm> +#include <cstring> +#include <initializer_list> +#include <string> +#include <type_traits> +#include <utility> +#include <vector> + +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_); + } + + // Prefer using |ConsumeRemainingBytes| unless you actually need a std::string + // object. + // Returns a std::vector containing all remaining bytes of the input data. + 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 a value selected from a 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) { + // static_assert(list.size() > 0, "The array must be non empty."); + return *(list.begin() + ConsumeIntegralInRange<size_t>(0, list.size() - 1)); + } + + // Return 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))); + } + + // 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); + 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_ diff --git a/src/test/fuzz/eval_script.cpp b/src/test/fuzz/eval_script.cpp new file mode 100644 index 0000000000..9444cd489e --- /dev/null +++ b/src/test/fuzz/eval_script.cpp @@ -0,0 +1,30 @@ +// Copyright (c) 2009-2019 The Bitcoin Core developers +// Distributed under the MIT software license, see the accompanying +// file COPYING or http://www.opensource.org/licenses/mit-license.php. + +#include <script/interpreter.h> +#include <test/fuzz/FuzzedDataProvider.h> +#include <test/fuzz/fuzz.h> + +#include <limits> + +void test_one_input(const std::vector<uint8_t>& buffer) +{ + FuzzedDataProvider fuzzed_data_provider(buffer.data(), buffer.size()); + const unsigned int flags = fuzzed_data_provider.ConsumeIntegral<unsigned int>(); + const std::vector<uint8_t> script_bytes = [&] { + if (fuzzed_data_provider.remaining_bytes() != 0) { + return fuzzed_data_provider.ConsumeRemainingBytes<uint8_t>(); + } else { + // Avoid UBSan warning: + // test/fuzz/FuzzedDataProvider.h:212:17: runtime error: null pointer passed as argument 1, which is declared to never be null + // /usr/include/string.h:43:28: note: nonnull attribute specified here + return std::vector<uint8_t>(); + } + }(); + const CScript script(script_bytes.begin(), script_bytes.end()); + for (const auto sig_version : {SigVersion::BASE, SigVersion::WITNESS_V0}) { + std::vector<std::vector<unsigned char>> stack; + (void)EvalScript(stack, script, flags, BaseSignatureChecker(), sig_version, nullptr); + } +} diff --git a/src/test/util_tests.cpp b/src/test/util_tests.cpp index d0cd4b0a03..31a66b6fa9 100644 --- a/src/test/util_tests.cpp +++ b/src/test/util_tests.cpp @@ -12,6 +12,7 @@ #include <util/strencodings.h> #include <util/string.h> #include <util/time.h> +#include <util/spanparsing.h> #include <stdint.h> #include <thread> @@ -1572,4 +1573,127 @@ BOOST_AUTO_TEST_CASE(test_Capitalize) BOOST_CHECK_EQUAL(Capitalize("\x00\xfe\xff"), "\x00\xfe\xff"); } +static std::string SpanToStr(Span<const char>& span) +{ + return std::string(span.begin(), span.end()); +} + +BOOST_AUTO_TEST_CASE(test_spanparsing) +{ + using namespace spanparsing; + std::string input; + Span<const char> sp; + bool success; + + // Const(...): parse a constant, update span to skip it if successful + input = "MilkToastHoney"; + sp = MakeSpan(input); + success = Const("", sp); // empty + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), "MilkToastHoney"); + + success = Const("Milk", sp); + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), "ToastHoney"); + + success = Const("Bread", sp); + BOOST_CHECK(!success); + + success = Const("Toast", sp); + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), "Honey"); + + success = Const("Honeybadger", sp); + BOOST_CHECK(!success); + + success = Const("Honey", sp); + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), ""); + + // Func(...): parse a function call, update span to argument if successful + input = "Foo(Bar(xy,z()))"; + sp = MakeSpan(input); + + success = Func("FooBar", sp); + BOOST_CHECK(!success); + + success = Func("Foo(", sp); + BOOST_CHECK(!success); + + success = Func("Foo", sp); + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), "Bar(xy,z())"); + + success = Func("Bar", sp); + BOOST_CHECK(success); + BOOST_CHECK_EQUAL(SpanToStr(sp), "xy,z()"); + + success = Func("xy", sp); + BOOST_CHECK(!success); + + // Expr(...): return expression that span begins with, update span to skip it + Span<const char> result; + + input = "(n*(n-1))/2"; + sp = MakeSpan(input); + result = Expr(sp); + BOOST_CHECK_EQUAL(SpanToStr(result), "(n*(n-1))/2"); + BOOST_CHECK_EQUAL(SpanToStr(sp), ""); + + input = "foo,bar"; + sp = MakeSpan(input); + result = Expr(sp); + BOOST_CHECK_EQUAL(SpanToStr(result), "foo"); + BOOST_CHECK_EQUAL(SpanToStr(sp), ",bar"); + + input = "(aaaaa,bbbbb()),c"; + sp = MakeSpan(input); + result = Expr(sp); + BOOST_CHECK_EQUAL(SpanToStr(result), "(aaaaa,bbbbb())"); + BOOST_CHECK_EQUAL(SpanToStr(sp), ",c"); + + input = "xyz)foo"; + sp = MakeSpan(input); + result = Expr(sp); + BOOST_CHECK_EQUAL(SpanToStr(result), "xyz"); + BOOST_CHECK_EQUAL(SpanToStr(sp), ")foo"); + + input = "((a),(b),(c)),xxx"; + sp = MakeSpan(input); + result = Expr(sp); + BOOST_CHECK_EQUAL(SpanToStr(result), "((a),(b),(c))"); + BOOST_CHECK_EQUAL(SpanToStr(sp), ",xxx"); + + // Split(...): split a string on every instance of sep, return vector + std::vector<Span<const char>> results; + + input = "xxx"; + results = Split(MakeSpan(input), 'x'); + BOOST_CHECK_EQUAL(results.size(), 4); + BOOST_CHECK_EQUAL(SpanToStr(results[0]), ""); + BOOST_CHECK_EQUAL(SpanToStr(results[1]), ""); + BOOST_CHECK_EQUAL(SpanToStr(results[2]), ""); + BOOST_CHECK_EQUAL(SpanToStr(results[3]), ""); + + input = "one#two#three"; + results = Split(MakeSpan(input), '-'); + BOOST_CHECK_EQUAL(results.size(), 1); + BOOST_CHECK_EQUAL(SpanToStr(results[0]), "one#two#three"); + + input = "one#two#three"; + results = Split(MakeSpan(input), '#'); + BOOST_CHECK_EQUAL(results.size(), 3); + BOOST_CHECK_EQUAL(SpanToStr(results[0]), "one"); + BOOST_CHECK_EQUAL(SpanToStr(results[1]), "two"); + BOOST_CHECK_EQUAL(SpanToStr(results[2]), "three"); + + input = "*foo*bar*"; + results = Split(MakeSpan(input), '*'); + BOOST_CHECK_EQUAL(results.size(), 4); + BOOST_CHECK_EQUAL(SpanToStr(results[0]), ""); + BOOST_CHECK_EQUAL(SpanToStr(results[1]), "foo"); + BOOST_CHECK_EQUAL(SpanToStr(results[2]), "bar"); + BOOST_CHECK_EQUAL(SpanToStr(results[3]), ""); +} + BOOST_AUTO_TEST_SUITE_END() diff --git a/src/util/spanparsing.cpp b/src/util/spanparsing.cpp new file mode 100644 index 0000000000..0c8575399a --- /dev/null +++ b/src/util/spanparsing.cpp @@ -0,0 +1,67 @@ +// Copyright (c) 2018 The Bitcoin Core developers +// Distributed under the MIT software license, see the accompanying +// file COPYING or http://www.opensource.org/licenses/mit-license.php. + +#include <util/spanparsing.h> + +#include <span.h> + +#include <string> +#include <vector> + +namespace spanparsing { + +bool Const(const std::string& str, Span<const char>& sp) +{ + if ((size_t)sp.size() >= str.size() && std::equal(str.begin(), str.end(), sp.begin())) { + sp = sp.subspan(str.size()); + return true; + } + return false; +} + +bool Func(const std::string& str, Span<const char>& sp) +{ + if ((size_t)sp.size() >= str.size() + 2 && sp[str.size()] == '(' && sp[sp.size() - 1] == ')' && std::equal(str.begin(), str.end(), sp.begin())) { + sp = sp.subspan(str.size() + 1, sp.size() - str.size() - 2); + return true; + } + return false; +} + +Span<const char> Expr(Span<const char>& sp) +{ + int level = 0; + auto it = sp.begin(); + while (it != sp.end()) { + if (*it == '(') { + ++level; + } else if (level && *it == ')') { + --level; + } else if (level == 0 && (*it == ')' || *it == ',')) { + break; + } + ++it; + } + Span<const char> ret = sp.first(it - sp.begin()); + sp = sp.subspan(it - sp.begin()); + return ret; +} + +std::vector<Span<const char>> Split(const Span<const char>& sp, char sep) +{ + std::vector<Span<const char>> ret; + auto it = sp.begin(); + auto start = it; + while (it != sp.end()) { + if (*it == sep) { + ret.emplace_back(start, it); + start = it + 1; + } + ++it; + } + ret.emplace_back(start, it); + return ret; +} + +} // namespace spanparsing diff --git a/src/util/spanparsing.h b/src/util/spanparsing.h new file mode 100644 index 0000000000..63f54758bd --- /dev/null +++ b/src/util/spanparsing.h @@ -0,0 +1,50 @@ +// Copyright (c) 2018 The Bitcoin Core developers +// Distributed under the MIT software license, see the accompanying +// file COPYING or http://www.opensource.org/licenses/mit-license.php. + +#ifndef BITCOIN_UTIL_SPANPARSING_H +#define BITCOIN_UTIL_SPANPARSING_H + +#include <span.h> + +#include <string> +#include <vector> + +namespace spanparsing { + +/** Parse a constant. + * + * If sp's initial part matches str, sp is updated to skip that part, and true is returned. + * Otherwise sp is unmodified and false is returned. + */ +bool Const(const std::string& str, Span<const char>& sp); + +/** Parse a function call. + * + * If sp's initial part matches str + "(", and sp ends with ")", sp is updated to be the + * section between the braces, and true is returned. Otherwise sp is unmodified and false + * is returned. + */ +bool Func(const std::string& str, Span<const char>& sp); + +/** Extract the expression that sp begins with. + * + * This function will return the initial part of sp, up to (but not including) the first + * comma or closing brace, skipping ones that are surrounded by braces. So for example, + * for "foo(bar(1),2),3" the initial part "foo(bar(1),2)" will be returned. sp will be + * updated to skip the initial part that is returned. + */ +Span<const char> Expr(Span<const char>& sp); + +/** Split a string on every instance of sep, returning a vector. + * + * If sep does not occur in sp, a singleton with the entirety of sp is returned. + * + * Note that this function does not care about braces, so splitting + * "foo(bar(1),2),3) on ',' will return {"foo(bar(1)", "2)", "3)"}. + */ +std::vector<Span<const char>> Split(const Span<const char>& sp, char sep); + +} // namespace spanparsing + +#endif // BITCOIN_UTIL_SPANPARSING_H diff --git a/src/wallet/test/wallet_tests.cpp b/src/wallet/test/wallet_tests.cpp index fc3be2b6ab..73523ca36d 100644 --- a/src/wallet/test/wallet_tests.cpp +++ b/src/wallet/test/wallet_tests.cpp @@ -338,6 +338,84 @@ BOOST_AUTO_TEST_CASE(LoadReceiveRequests) BOOST_CHECK_EQUAL(values[1], "val_rr1"); } +// Test some watch-only wallet methods by the procedure of loading (LoadWatchOnly), +// checking (HaveWatchOnly), getting (GetWatchPubKey) and removing (RemoveWatchOnly) a +// given PubKey, resp. its corresponding P2PK Script. Results of the the impact on +// the address -> PubKey map is dependent on whether the PubKey is a point on the curve +static void TestWatchOnlyPubKey(CWallet& wallet, const CPubKey& add_pubkey) +{ + CScript p2pk = GetScriptForRawPubKey(add_pubkey); + CKeyID add_address = add_pubkey.GetID(); + CPubKey found_pubkey; + LOCK(wallet.cs_wallet); + + // all Scripts (i.e. also all PubKeys) are added to the general watch-only set + BOOST_CHECK(!wallet.HaveWatchOnly(p2pk)); + wallet.LoadWatchOnly(p2pk); + BOOST_CHECK(wallet.HaveWatchOnly(p2pk)); + + // only PubKeys on the curve shall be added to the watch-only address -> PubKey map + bool is_pubkey_fully_valid = add_pubkey.IsFullyValid(); + if (is_pubkey_fully_valid) { + BOOST_CHECK(wallet.GetWatchPubKey(add_address, found_pubkey)); + BOOST_CHECK(found_pubkey == add_pubkey); + } else { + BOOST_CHECK(!wallet.GetWatchPubKey(add_address, found_pubkey)); + BOOST_CHECK(found_pubkey == CPubKey()); // passed key is unchanged + } + + wallet.RemoveWatchOnly(p2pk); + BOOST_CHECK(!wallet.HaveWatchOnly(p2pk)); + + if (is_pubkey_fully_valid) { + BOOST_CHECK(!wallet.GetWatchPubKey(add_address, found_pubkey)); + BOOST_CHECK(found_pubkey == add_pubkey); // passed key is unchanged + } +} + +// Cryptographically invalidate a PubKey whilst keeping length and first byte +static void PollutePubKey(CPubKey& pubkey) +{ + std::vector<unsigned char> pubkey_raw(pubkey.begin(), pubkey.end()); + std::fill(pubkey_raw.begin()+1, pubkey_raw.end(), 0); + pubkey = CPubKey(pubkey_raw); + assert(!pubkey.IsFullyValid()); + assert(pubkey.IsValid()); +} + +// Test watch-only wallet logic for PubKeys +BOOST_AUTO_TEST_CASE(WatchOnlyPubKeys) +{ + CKey key; + CPubKey pubkey; + + BOOST_CHECK(!m_wallet.HaveWatchOnly()); + + // uncompressed valid PubKey + key.MakeNewKey(false); + pubkey = key.GetPubKey(); + assert(!pubkey.IsCompressed()); + TestWatchOnlyPubKey(m_wallet, pubkey); + + // uncompressed cryptographically invalid PubKey + PollutePubKey(pubkey); + TestWatchOnlyPubKey(m_wallet, pubkey); + + // compressed valid PubKey + key.MakeNewKey(true); + pubkey = key.GetPubKey(); + assert(pubkey.IsCompressed()); + TestWatchOnlyPubKey(m_wallet, pubkey); + + // compressed cryptographically invalid PubKey + PollutePubKey(pubkey); + TestWatchOnlyPubKey(m_wallet, pubkey); + + // invalid empty PubKey + pubkey = CPubKey(); + TestWatchOnlyPubKey(m_wallet, pubkey); +} + class ListCoinsTestingSetup : public TestChain100Setup { public: |