From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 2181) id 013323858426; Wed, 13 Oct 2021 20:54:41 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 013323858426 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Jonathan Wakely To: gcc-cvs@gcc.gnu.org, libstdc++-cvs@gcc.gnu.org Subject: [gcc r11-9149] libstdc++: Fix dangling string_view in filesystem::path [PR102592] X-Act-Checkin: gcc X-Git-Author: Jonathan Wakely X-Git-Refname: refs/heads/releases/gcc-11 X-Git-Oldrev: 3eac45a2a13b959166806f132aea756026c9b8cb X-Git-Newrev: 9ef31bab15a426a6829acf0e7ae5420d3b10cbae Message-Id: <20211013205441.013323858426@sourceware.org> Date: Wed, 13 Oct 2021 20:54:41 +0000 (GMT) X-BeenThere: libstdc++-cvs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libstdc++-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 13 Oct 2021 20:54:41 -0000 https://gcc.gnu.org/g:9ef31bab15a426a6829acf0e7ae5420d3b10cbae commit r11-9149-g9ef31bab15a426a6829acf0e7ae5420d3b10cbae Author: Jonathan Wakely Date: Wed Oct 13 17:02:59 2021 +0100 libstdc++: Fix dangling string_view in filesystem::path [PR102592] When creating a path from a pair of non-contiguous iterators we pass the iterators to _S_convert(Iter, Iter). That function passes the iterators to __string_from_range to get a contiguous sequence of characters, and then calls _S_convert(const C*, const C*) to perform the encoding conversions. If the value type, C, is char8_t, then no conversion is needed and the _S_convert(const char8_t*, const char8_t*) specialization casts the pointer to const char* and returns a std::string_view that refs to the char8_t sequence. However, that sequence is owned by the std::u8string rvalue returned by __string_from_range, which goes out of scope when _S_convert(Iter, Iter) returns. That means the std::string_view is dangling and we get undefined behaviour when parsing it as a path. The same problem does not exist for the path members taking a "Source" argument, because those functions all convert a non-contiguous range into a basic_string immediately, using __effective_range(__source). That means that the rvalue string returned by that function is still in scope for the full expression, so the string_view does not dangle. The solution for the buggy functions is to do the same thing, and call __string_from_range immediately, so that the returned rvalue is still in scope for the lifetime of the string_view returned by _S_convert. To avoid reintroducing the same problem, remove the _S_convert(Iter, Iter) overload that calls __string_from_range and returns a dangling view. libstdc++-v3/ChangeLog: PR libstdc++/102592 * include/bits/fs_path.h (path::path(Iter, Iter, format)) (path::append(Iter, Iter), path::concat(Iter, Iter)): Call __string_from_range directly, instead of two-argument overload of _S_convert. (path::_S_convert(Iter, Iter)): Remove. * testsuite/27_io/filesystem/path/construct/102592.C: New test. (cherry picked from commit 85b24e32dc27ec2e70b853713e0713cbc1ff08c3) Diff: --- libstdc++-v3/include/bits/fs_path.h | 11 +++------ .../27_io/filesystem/path/construct/102592.C | 28 ++++++++++++++++++++++ 2 files changed, 31 insertions(+), 8 deletions(-) diff --git a/libstdc++-v3/include/bits/fs_path.h b/libstdc++-v3/include/bits/fs_path.h index 85c83412615..a1f780a9c9b 100644 --- a/libstdc++-v3/include/bits/fs_path.h +++ b/libstdc++-v3/include/bits/fs_path.h @@ -292,7 +292,7 @@ namespace __detail template> path(_InputIterator __first, _InputIterator __last, format = auto_format) - : _M_pathname(_S_convert(__first, __last)) + : _M_pathname(_S_convert(__detail::__string_from_range(__first, __last))) { _M_split_cmpts(); } template& append(_InputIterator __first, _InputIterator __last) { - _M_append(_S_convert(__first, __last)); + _M_append(_S_convert(__detail::__string_from_range(__first, __last))); return *this; } @@ -390,7 +390,7 @@ namespace __detail __detail::_Path2<_InputIterator>& concat(_InputIterator __first, _InputIterator __last) { - _M_concat(_S_convert(__first, __last)); + _M_concat(_S_convert(__detail::__string_from_range(__first, __last))); return *this; } @@ -602,11 +602,6 @@ namespace __detail static auto _S_convert(const _EcharT* __first, const _EcharT* __last); - template - static auto - _S_convert(_Iter __first, _Iter __last) - { return _S_convert(__detail::__string_from_range(__first, __last)); } - static string_type _S_convert_loc(const char* __first, const char* __last, const std::locale& __loc); diff --git a/libstdc++-v3/testsuite/27_io/filesystem/path/construct/102592.C b/libstdc++-v3/testsuite/27_io/filesystem/path/construct/102592.C new file mode 100644 index 00000000000..3bbd07e2494 --- /dev/null +++ b/libstdc++-v3/testsuite/27_io/filesystem/path/construct/102592.C @@ -0,0 +1,28 @@ +// { dg-options "-fchar8_t" } +// { dg-do run { target c++17 } } + +#include +#include +#include + +using __gnu_test::input_iterator_wrapper; +using __gnu_test::input_container; + +void test01() +{ + const char8_t src[] = u8"/long/path/to/a/file/to/avoid/small/string"; + input_container c1(src); // includes null terminator + std::filesystem::path p1(c1.begin()); // read up to null terminator + VERIFY( p1.u8string() == src ); + + std::u8string_view sv = src; + input_container c2(sv.data(), sv.data() + sv.size()); + std::filesystem::path p2(c2.begin(), c2.end()); // PR libstdc++/102592 + VERIFY( p2.u8string() == src ); + VERIFY( p1 == p2 ); +} + +int main() +{ + test01(); +}