This commit introduces basic annotations for `std::basic_string`, mirroring the approach used in `std::vector` and `std::deque`. Initially, only long strings with the default allocator will be annotated. Short strings (_SSO - short string optimization_) and strings with non-default allocators will be annotated in the near future, with separate commits dedicated to enabling them. The process will be similar to the workflow employed for enabling annotations in `std::deque`. **Please note**: these annotations function effectively only when libc++ and libc++abi dylibs are instrumented (with ASan). This aligns with the prevailing behavior of Memory Sanitizer. To avoid breaking everything, this commit also appends `_LIBCPP_INSTRUMENTED_WITH_ASAN` to `__config_site` whenever libc++ is compiled with ASan. If this macro is not defined, string annotations are not enabled. However, linking a binary that does **not** annotate strings with a dynamic library that annotates strings, is not permitted. Originally proposed here: https://reviews.llvm.org/D132769 Related patches on Phabricator: - Turning on annotations for short strings: https://reviews.llvm.org/D147680 - Turning on annotations for all allocators: https://reviews.llvm.org/D146214 This PR is a part of a series of patches extending AddressSanitizer C++ container overflow detection capabilities by adding annotations, similar to those existing in `std::vector` and `std::deque` collections. These enhancements empower ASan to effectively detect instances where the instrumented program attempts to access memory within a collection's internal allocation that remains unused. This includes cases where access occurs before or after the stored elements in `std::deque`, or between the `std::basic_string`'s size (including the null terminator) and capacity bounds. The introduction of these annotations was spurred by a real-world software bug discovered by Trail of Bits, involving an out-of-bounds memory access during the comparison of two strings using the `std::equals` function. This function was taking iterators (`iter1_begin`, `iter1_end`, `iter2_begin`) to perform the comparison, using a custom comparison function. When the `iter1` object exceeded the length of `iter2`, an out-of-bounds read could occur on the `iter2` object. Container sanitization, upon enabling these annotations, would effectively identify and flag this potential vulnerability. This Pull Request introduces basic annotations for `std::basic_string`. Long strings exhibit structural similarities to `std::vector` and will be annotated accordingly. Short strings are already implemented, but will be turned on separately in a forthcoming commit. Look at [a comment](https://github.com/llvm/llvm-project/pull/72677#issuecomment-1850554465) below to read about SSO issues at current moment. Due to the functionality introduced in [D132522](https://github.com/llvm/llvm-project/commit/dd1b7b797a116eed588fd752fbe61d34deeb24e4), the `__sanitizer_annotate_contiguous_container` function now offers compatibility with all allocators. However, enabling this support will be done in a subsequent commit. For the time being, only strings with the default allocator will be annotated. If you have any questions, please email: - advenam.tacet@trailofbits.com - disconnect3d@trailofbits.com
244 lines
8.8 KiB
C++
244 lines
8.8 KiB
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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// UNSUPPORTED: c++03, c++11, c++14, c++17, c++20
|
|
|
|
// <string>
|
|
|
|
// constexpr basic_string(basic_string&& str, size_type pos, const Allocator& a = Allocator());
|
|
// constexpr basic_string(basic_string&& str, size_type pos, size_type n, const Allocator& a = Allocator());
|
|
|
|
#include <cassert>
|
|
#include <stdexcept>
|
|
#include <string>
|
|
|
|
#include "constexpr_char_traits.h"
|
|
#include "count_new.h"
|
|
#include "make_string.h"
|
|
#include "min_allocator.h"
|
|
#include "test_allocator.h"
|
|
#include "test_macros.h"
|
|
#include "asan_testing.h"
|
|
|
|
#define STR(string) MAKE_CSTRING(typename S::value_type, string)
|
|
|
|
constexpr struct should_throw_exception_t {
|
|
} should_throw_exception;
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos(S orig, typename S::size_type pos, S expected) {
|
|
#ifdef _LIBCPP_VERSION
|
|
ConstexprDisableAllocationGuard g;
|
|
#endif
|
|
S substr(std::move(orig), pos);
|
|
LIBCPP_ASSERT(orig.__invariants());
|
|
LIBCPP_ASSERT(orig.empty());
|
|
LIBCPP_ASSERT(substr.__invariants());
|
|
assert(substr == expected);
|
|
LIBCPP_ASSERT(is_string_asan_correct(orig));
|
|
LIBCPP_ASSERT(is_string_asan_correct(substr));
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos(S orig, typename S::size_type pos, should_throw_exception_t) {
|
|
#ifndef TEST_HAS_NO_EXCEPTIONS
|
|
if (!std::is_constant_evaluated()) {
|
|
try {
|
|
[[maybe_unused]] S substr = S(std::move(orig), pos);
|
|
assert(false);
|
|
} catch (const std::out_of_range&) {
|
|
}
|
|
}
|
|
#else
|
|
(void)orig;
|
|
(void)pos;
|
|
#endif
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void
|
|
test_string_pos_alloc(S orig, typename S::size_type pos, const typename S::allocator_type& alloc, S expected) {
|
|
S substr(std::move(orig), pos, alloc);
|
|
LIBCPP_ASSERT(orig.__invariants());
|
|
LIBCPP_ASSERT(substr.__invariants());
|
|
assert(substr == expected);
|
|
assert(substr.get_allocator() == alloc);
|
|
LIBCPP_ASSERT(is_string_asan_correct(orig));
|
|
LIBCPP_ASSERT(is_string_asan_correct(substr));
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos_alloc(
|
|
S orig, typename S::size_type pos, const typename S::allocator_type& alloc, should_throw_exception_t) {
|
|
#ifndef TEST_HAS_NO_EXCEPTIONS
|
|
if (!std::is_constant_evaluated()) {
|
|
try {
|
|
[[maybe_unused]] S substr = S(std::move(orig), pos, alloc);
|
|
assert(false);
|
|
} catch (const std::out_of_range&) {
|
|
}
|
|
}
|
|
#else
|
|
(void)orig;
|
|
(void)pos;
|
|
(void)alloc;
|
|
#endif
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos_n(S orig, typename S::size_type pos, typename S::size_type n, S expected) {
|
|
#ifdef _LIBCPP_VERSION
|
|
ConstexprDisableAllocationGuard g;
|
|
#endif
|
|
S substr(std::move(orig), pos, n);
|
|
LIBCPP_ASSERT(orig.__invariants());
|
|
LIBCPP_ASSERT(orig.empty());
|
|
LIBCPP_ASSERT(substr.__invariants());
|
|
assert(substr == expected);
|
|
LIBCPP_ASSERT(is_string_asan_correct(orig));
|
|
LIBCPP_ASSERT(is_string_asan_correct(substr));
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos_n(S orig, typename S::size_type pos, typename S::size_type n, should_throw_exception_t) {
|
|
#ifndef TEST_HAS_NO_EXCEPTIONS
|
|
if (!std::is_constant_evaluated()) {
|
|
try {
|
|
[[maybe_unused]] S substr = S(std::move(orig), pos, n);
|
|
assert(false);
|
|
} catch (const std::out_of_range&) {
|
|
}
|
|
}
|
|
#else
|
|
(void)orig;
|
|
(void)pos;
|
|
(void)n;
|
|
#endif
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos_n_alloc(
|
|
S orig, typename S::size_type pos, typename S::size_type n, const typename S::allocator_type& alloc, S expected) {
|
|
S substr(std::move(orig), pos, n, alloc);
|
|
LIBCPP_ASSERT(orig.__invariants());
|
|
LIBCPP_ASSERT(substr.__invariants());
|
|
assert(substr == expected);
|
|
assert(substr.get_allocator() == alloc);
|
|
LIBCPP_ASSERT(is_string_asan_correct(orig));
|
|
LIBCPP_ASSERT(is_string_asan_correct(substr));
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string_pos_n_alloc(
|
|
S orig,
|
|
typename S::size_type pos,
|
|
typename S::size_type n,
|
|
const typename S::allocator_type& alloc,
|
|
should_throw_exception_t) {
|
|
#ifndef TEST_HAS_NO_EXCEPTIONS
|
|
if (!std::is_constant_evaluated()) {
|
|
try {
|
|
[[maybe_unused]] S substr = S(std::move(orig), pos, n, alloc);
|
|
assert(false);
|
|
} catch (const std::out_of_range&) {
|
|
}
|
|
}
|
|
#else
|
|
(void)orig;
|
|
(void)pos;
|
|
(void)n;
|
|
(void)alloc;
|
|
#endif
|
|
}
|
|
|
|
template <class S>
|
|
constexpr void test_string(const typename S::allocator_type& alloc) {
|
|
test_string_pos<S>(STR(""), 0, STR(""));
|
|
test_string_pos<S>(STR(""), 1, should_throw_exception);
|
|
test_string_pos<S>(STR("Banane"), 1, STR("anane"));
|
|
test_string_pos<S>(STR("Banane"), 6, STR(""));
|
|
test_string_pos<S>(STR("Banane"), 7, should_throw_exception);
|
|
test_string_pos<S>(STR("long long string so no SSO"), 0, STR("long long string so no SSO"));
|
|
test_string_pos<S>(STR("long long string so no SSO"), 10, STR("string so no SSO"));
|
|
test_string_pos<S>(STR("long long string so no SSO"), 26, STR(""));
|
|
test_string_pos<S>(STR("long long string so no SSO"), 27, should_throw_exception);
|
|
|
|
test_string_pos_alloc<S>(STR(""), 0, alloc, STR(""));
|
|
test_string_pos_alloc<S>(STR(""), 1, alloc, should_throw_exception);
|
|
test_string_pos_alloc<S>(STR("Banane"), 1, alloc, STR("anane"));
|
|
test_string_pos_alloc<S>(STR("Banane"), 6, alloc, STR(""));
|
|
test_string_pos_alloc<S>(STR("Banane"), 7, alloc, should_throw_exception);
|
|
test_string_pos_alloc<S>(STR("long long string so no SSO"), 0, alloc, STR("long long string so no SSO"));
|
|
test_string_pos_alloc<S>(STR("long long string so no SSO"), 10, alloc, STR("string so no SSO"));
|
|
test_string_pos_alloc<S>(STR("long long string so no SSO"), 26, alloc, STR(""));
|
|
test_string_pos_alloc<S>(STR("long long string so no SSO"), 27, alloc, should_throw_exception);
|
|
|
|
test_string_pos_n<S>(STR(""), 0, 0, STR(""));
|
|
test_string_pos_n<S>(STR(""), 0, 1, STR(""));
|
|
test_string_pos_n<S>(STR(""), 1, 0, should_throw_exception);
|
|
test_string_pos_n<S>(STR(""), 1, 1, should_throw_exception);
|
|
test_string_pos_n<S>(STR("Banane"), 1, 10, STR("anane"));
|
|
test_string_pos_n<S>(STR("Banane"), 6, 0, STR(""));
|
|
test_string_pos_n<S>(STR("Banane"), 6, 5, STR(""));
|
|
test_string_pos_n<S>(STR("Banane"), 7, 10, should_throw_exception);
|
|
test_string_pos_n<S>(STR("long long string so no SSO"), 0, 10, STR("long long "));
|
|
test_string_pos_n<S>(STR("long long string so no SSO"), 10, 8, STR("string s"));
|
|
test_string_pos_n<S>(STR("long long string so no SSO"), 20, 10, STR("no SSO"));
|
|
test_string_pos_n<S>(STR("long long string so no SSO"), 26, 10, STR(""));
|
|
test_string_pos_n<S>(STR("long long string so no SSO"), 27, 10, should_throw_exception);
|
|
|
|
test_string_pos_n_alloc<S>(STR(""), 0, 0, alloc, STR(""));
|
|
test_string_pos_n_alloc<S>(STR(""), 0, 1, alloc, STR(""));
|
|
test_string_pos_n_alloc<S>(STR(""), 1, 0, alloc, should_throw_exception);
|
|
test_string_pos_n_alloc<S>(STR(""), 1, 1, alloc, should_throw_exception);
|
|
test_string_pos_n_alloc<S>(STR("Banane"), 1, 10, alloc, STR("anane"));
|
|
test_string_pos_n_alloc<S>(STR("Banane"), 6, 0, alloc, STR(""));
|
|
test_string_pos_n_alloc<S>(STR("Banane"), 6, 5, alloc, STR(""));
|
|
test_string_pos_n_alloc<S>(STR("Banane"), 7, 10, alloc, should_throw_exception);
|
|
test_string_pos_n_alloc<S>(STR("long long string so no SSO"), 0, 10, alloc, STR("long long "));
|
|
test_string_pos_n_alloc<S>(STR("long long string so no SSO"), 10, 8, alloc, STR("string s"));
|
|
test_string_pos_n_alloc<S>(STR("long long string so no SSO"), 20, 10, alloc, STR("no SSO"));
|
|
test_string_pos_n_alloc<S>(STR("long long string so no SSO"), 26, 10, alloc, STR(""));
|
|
test_string_pos_n_alloc<S>(STR("long long string so no SSO"), 27, 10, alloc, should_throw_exception);
|
|
}
|
|
|
|
template <class CharT, class CharTraits>
|
|
constexpr void test_allocators() {
|
|
test_string<std::basic_string<CharT, CharTraits, std::allocator<CharT>>>(std::allocator<CharT>{});
|
|
test_string<std::basic_string<CharT, CharTraits, min_allocator<CharT>>>(min_allocator<CharT>{});
|
|
test_string<std::basic_string<CharT, CharTraits, test_allocator<CharT>>>(test_allocator<CharT>{42});
|
|
}
|
|
|
|
template <class CharT>
|
|
constexpr bool test_char_traits() {
|
|
test_allocators<CharT, std::char_traits<CharT>>();
|
|
test_allocators<CharT, constexpr_char_traits<CharT>>();
|
|
|
|
return true;
|
|
}
|
|
|
|
int main(int, char**) {
|
|
// TODO: put these into a single function when we increase the constexpr step limit
|
|
test_char_traits<char>();
|
|
static_assert(test_char_traits<char>());
|
|
test_char_traits<char16_t>();
|
|
static_assert(test_char_traits<char16_t>());
|
|
test_char_traits<char32_t>();
|
|
static_assert(test_char_traits<char32_t>());
|
|
#ifndef TEST_HAS_NO_WIDE_CHARACTERS
|
|
test_char_traits<wchar_t>();
|
|
static_assert(test_char_traits<wchar_t>());
|
|
#endif
|
|
#ifndef TEST_HAS_NO_CHAR8_T
|
|
test_char_traits<char8_t>();
|
|
static_assert(test_char_traits<char8_t>());
|
|
#endif
|
|
|
|
return 0;
|
|
}
|