https://gcc.gnu.org/g:b6a8e6e78926adb220210b0a740c82f73610b33d
commit r13-10315-gb6a8e6e78926adb220210b0a740c82f73610b33d Author: Jonathan Wakely <[email protected]> Date: Fri Jan 9 13:39:49 2026 +0000 libstdc++: Fix chrono::current_zone() for three-level names [PR122567] chrono::current_zone() fails if /etc/localtime is a symlink to a zone with three components, like "America/Indiana/Indianapolis", because we only try to find "Indianapolis" and "Indiana/Indianapolis" but neither of those is a valid zone name. We need to try up to three components to handle all valid cases, such as "UTC", "America/Indianapolis", and "America/Indiana/Indianapolis". It's also possible that users could provide a custom tzdata.zi file which includes zones with names using more than three levels, so loop over all filename components of the path that /etc/localtime points to. This also replaces std::filesystem::read_symlink with a plain readlink call and find+substr operations on a std::string_view, which is approximately twice as fast as using std::filesystem::path and std::string. By default we use a fixed char[128] buffer for readlink to write into, but if that doesn't fit we use a std::string as a dynamic buffer that grows as needed. We could use ::stat to find the exact length of the symlink and avoid looping with an increasingly large std::string capacity, but it's already expected to be rare for the char[128] buffer to be exceeded, so needing to double the std::string capacity more than once (i.e. to 512 or more) should be exceedingly rare. Adding a call to ::stat would perform a third filesystem operation when two readlink calls should be sufficient for the vast majority of realistic cases. One consequence of not using filesystem::path is that redundant consecutive slashes in the pathname aren't automatically ignored, e.g. /usr/share/zoneinfo/Europe//London worked fine with the old implementation because we manually concatenated the path components, i.e. "Europe" + '/' + "London". So that this continues to work there is a new loop to remove redundant slashes from the string being processed. That adds a slower, allocating path, but is unlikely to be needed in practice (the systemd spec for /etc/localtime explicitly says it should end with a time zone name, so "Europe//London" would be invalid anyway, even if it points to a valid file). Again, this loop is expected to be rare so optimizing this case further isn't important. While manually testing this I noticed that we will interpret a bogus symlink such as /usr/share/zoneinfo/America/Europe/London as a valid timezone, even though it's a dangling symlink. We find a name match for "Europe/London" before we get to the "America" component. This seems unlikely to matter in practice, and was a pre-existing problem. There's no testcase for current_zone() correctly handling three-level names or symlinks with unusual targets. It cannot be tested without changing the target of /etc/localtime which requires root access. I'm still considering whether we want to cache the result of current_zone(), either globally or in the tzdb object. Just returning a cached variable takes 20-30ns instead of more than 700ns to access the filesystem and read the symlink. Using ::lstat to check the symlink's mtime would add some overhead though. libstdc++-v3/ChangeLog: PR libstdc++/122567 * src/c++20/tzdb.cc (tzdb::current_zone): Loop over all trailing components of /etc/localtime path. Use readlink instead of std::filesystem::read_symlink. Reviewed-by: Tomasz Kamiński <[email protected]> (cherry picked from commit 20a6ff7a4877a25ba78461a19417e956bd6c0095) Diff: --- libstdc++-v3/src/c++20/tzdb.cc | 105 ++++++++++++++++++++++++++++++++++------- 1 file changed, 87 insertions(+), 18 deletions(-) diff --git a/libstdc++-v3/src/c++20/tzdb.cc b/libstdc++-v3/src/c++20/tzdb.cc index 83848cf67020..4cfa4b60543d 100644 --- a/libstdc++-v3/src/c++20/tzdb.cc +++ b/libstdc++-v3/src/c++20/tzdb.cc @@ -35,7 +35,11 @@ #include <atomic> // atomic<T*>, atomic<int> #include <memory> // atomic<shared_ptr<T>> #include <mutex> // mutex -#include <filesystem> // filesystem::read_symlink +#include <iomanip> // quoted + +#if defined(_GLIBCXX_HAVE_READLINK) && defined(_GLIBCXX_HAVE_UNISTD_H) +# include <unistd.h> // readlink +#endif #ifdef _AIX # include <cstdlib> // getenv @@ -1737,28 +1741,88 @@ namespace std::chrono tzdb::current_zone() const { // TODO cache this function's result? + // Could check the modification time of /etc/localtime, and not re-read + // it if it hasn't changed. reload_tzdb() could clear the cache too, + // to have a way to force a re-read. #ifndef _AIX - // Repeat the preprocessor condition used by filesystem::read_symlink, - // to avoid a dependency on src/c++17/fs_ops.o if it won't work anyway. -#if defined(_GLIBCXX_HAVE_READLINK) && defined(_GLIBCXX_HAVE_SYS_STAT_H) - error_code ec; - // This should be a symlink to e.g. /usr/share/zoneinfo/Europe/London - auto path = filesystem::read_symlink("/etc/localtime", ec); - if (!ec) +#if defined(_GLIBCXX_HAVE_READLINK) && defined(_GLIBCXX_HAVE_UNISTD_H) + string_view str; + char buf[128]; // strlen("../usr/share/zoneinfo/...") is usually < 55 + string dynbuf; + // /etc/localtime should be a symlink that ends with a zone name, + // e.g. /etc/localtime -> /usr/share/zoneinfo/Europe/London + // https://www.freedesktop.org/software/systemd/man/latest/localtime.html + // This should work on GNU/Linux, macOS, NetBSD, and OpenBSD. + // Some FreeBSD systems also use a symlink for /etc/localtime. + // Use readlink directly to avoid std::filesystem overhead. + if (auto n = ::readlink("/etc/localtime", buf, sizeof(buf)); n > 0) { - auto first = path.begin(), last = path.end(); - if (std::distance(first, last) > 2) + if (static_cast<size_t>(n) < sizeof(buf)) + str = string_view(buf, n); + else [[unlikely]] { - --last; - string name = last->string(); - if (auto tz = do_locate_zone(this->zones, this->links, name)) - return tz; - --last; - name = last->string() + '/' + name; - if (auto tz = do_locate_zone(this->zones, this->links, name)) + // We read the symlink but it didn't fit in buf[], use dynbuf. + do + { + n *= 2; + dynbuf.resize(n); + // In gcc-14 and later this uses dynbuf.__resize_and_overwrite: + { + auto n2 = ::readlink("/etc/localtime", dynbuf.data(), n); + if (n2 == -1) // symlink removed or replaced by file?! + __throw_runtime_error("tzdb: error reading /etc/localtime"); + dynbuf.resize(n2 < n ? n2 : 0); + } + } + while (dynbuf.empty()); + str = dynbuf; + } + } + + if (!str.empty()) + { + // Remove any redundant slashes so we can match zone names. + // e.g. /usr/share/zoneinfo/Europe//London is a valid symlink, + // but won't match against "Europe/London". + if (auto pos = str.rfind("//"); pos != str.npos) [[unlikely]] + { + if (str.data() != dynbuf.data()) + dynbuf = str; + string::size_type spos = pos; + do + { + dynbuf.erase(spos, 1); + spos = dynbuf.rfind("//", spos); + } + while (spos != dynbuf.npos); + str = dynbuf; + } + + // Check the trailing components of the path against known zone names. + // Valid IANA times zones can have one, two, or three parts, e.g. + // "UTC", "Europe/London", and "America/Indiana/Indianapolis". + // Custom tzdata.zi files could in theory use four or more parts. + + auto pos = str.rfind('/'); + while (pos != str.npos && pos != 0) + { + if (auto tz = do_locate_zone(this->zones, this->links, + str.substr(pos + 1))) return tz; + pos = str.rfind('/', pos - 1); } + // If we didn't match yet, try once more so that we will match + // a symlink to a relative path such as "Europe/London" + // or symlink to an absolute path such as "/Europe/London". + // Both cases seem unlikely because it would require either + // /etc/Europe or /Europe to be a directory (or a symlink to one) + // containing the TZif files, but it's theoretically possible. + // If pos==npos then pos+1 wraps to 0 and we use the whole string. + // If pos==0 then substr(1) discards the leading slash. + if (auto tz = do_locate_zone(this->zones, this->links, + str.substr(pos + 1))) + return tz; } #endif // Otherwise, look for a file naming the time zone. @@ -1795,7 +1859,12 @@ namespace std::chrono return tz; } } -#else + + // FIXME: For DragonFly BSD /etc/localtime is a copy of one of the + // zone files in /usr/share/zoneinfo so we need to compare its contents + // to each one until we find a match. + +#else // _AIX // AIX stores current zone in $TZ in /etc/environment but the value // is typically a POSIX time zone name, not IANA zone. // https://developer.ibm.com/articles/au-aix-posix/
