From 64924422a99690d147a166b4de3103f3bf3eaf6c Mon Sep 17 00:00:00 2001 From: Joseph Myers Date: Thu, 16 Feb 2023 23:02:40 +0000 Subject: C2x strtol binary constant handling C2x adds binary integer constants starting with 0b or 0B, and supports those constants in strtol-family functions when the base passed is 0 or 2. Implement that strtol support for glibc. As discussed at , this is incompatible with previous C standard versions, in that such an input string starting with 0b or 0B was previously required to be parsed as 0 (with the rest of the string unprocessed). Thus, as proposed there, this patch adds 20 new __isoc23_* functions with appropriate header redirection support. This patch does *not* do anything about scanf %i (which will need 12 new functions per long double variant, so 12, 24 or 36 depending on the glibc configuration), instead leaving that for a future patch. The function names would remain as __isoc23_* even if C2x ends up published in 2024 rather than 2023. Making this change leads to the question of what should happen to internal uses of these functions in glibc and its tests. The header redirection (which applies for _GNU_SOURCE or any other feature test macros enabling C2x features) has the effect of redirecting internal uses but without those uses then ending up at a hidden alias (see the comment in include/stdio.h about interaction with libc_hidden_proto). It seems desirable for the default for internal uses to be the same versions used by normal code using _GNU_SOURCE, so rather than doing anything to disable that redirection, similar macro definitions to those in include/stdio.h are added to the include/ headers for the new functions. Given that the default for uses in glibc is for the redirections to apply, the next question is whether the C2x semantics are correct for all those uses. Uses with the base fixed to 10, 16 or any other value other than 0 or 2 can be ignored. I think this leaves the following internal uses to consider (an important consideration for review of this patch will be both whether this list is complete and whether my conclusions on all entries in it are correct): benchtests/bench-malloc-simple.c benchtests/bench-string.h elf/sotruss-lib.c math/libm-test-support.c nptl/perf.c nscd/nscd_conf.c nss/nss_files/files-parse.c posix/tst-fnmatch.c posix/wordexp.c resolv/inet_addr.c rt/tst-mqueue7.c soft-fp/testit.c stdlib/fmtmsg.c support/support_test_main.c support/test-container.c sysdeps/pthread/tst-mutex10.c I think all of these places are OK with the new semantics, except for resolv/inet_addr.c, where the POSIX semantics of inet_addr do not allow for binary constants; thus, I changed that file (to use __strtoul_internal, whose semantics are unchanged) and added a test for this case. In the case of posix/wordexp.c I think accepting binary constants is OK since POSIX explicitly allows additional forms of shell arithmetic expressions, and in stdlib/fmtmsg.c SEV_LEVEL is not in POSIX so again I think accepting binary constants is OK. Functions such as __strtol_internal, which are only exported for compatibility with old binaries from when those were used in inline functions in headers, have unchanged semantics; the __*_l_internal versions (purely internal to libc and not exported) have a new argument to specify whether to accept binary constants. As well as for the standard functions, the header redirection also applies to the *_l versions (GNU extensions), and to legacy functions such as strtoq, to avoid confusing inconsistency (the *q functions redirect to __isoc23_*ll rather than needing their own __isoc23_* entry points). For the functions that are only declared with _GNU_SOURCE, this means the old versions are no longer available for normal user programs at all. An internal __GLIBC_USE_C2X_STRTOL macro is used to control the redirections in the headers, and cases in glibc that wish to avoid the redirections - the function implementations themselves and the tests of the old versions of the GNU functions - then undefine and redefine that macro to allow the old versions to be accessed. (There would of course be greater complexity should we wish to make any of the old versions into compat symbols / avoid them being defined at all for new glibc ABIs.) strtol_l.c has some similarity to strtol.c in gnulib, but has already diverged some way (and isn't listed at all at https://sourceware.org/glibc/wiki/SharedSourceFiles unlike strtoll.c and strtoul.c); I haven't made any attempts at gnulib compatibility in the changes to that file. I note incidentally that inttypes.h and wchar.h are missing the __nonnull present on declarations of this family of functions in stdlib.h; I didn't make any changes in that regard for the new declarations added. --- wcsmbs/wchar.h | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) (limited to 'wcsmbs/wchar.h') diff --git a/wcsmbs/wchar.h b/wcsmbs/wchar.h index 69e920b..cde0d32 100644 --- a/wcsmbs/wchar.h +++ b/wcsmbs/wchar.h @@ -467,6 +467,67 @@ extern unsigned long long int wcstouq (const wchar_t *__restrict __nptr, int __base) __THROW; #endif /* Use GNU. */ +/* Versions of the above functions that handle '0b' and '0B' prefixes + in base 0 or 2. */ +#if __GLIBC_USE (C2X_STRTOL) +# ifdef __REDIRECT +extern long int __REDIRECT_NTH (wcstol, (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstol); +extern unsigned long int __REDIRECT_NTH (wcstoul, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstoul); +__extension__ +extern long long int __REDIRECT_NTH (wcstoll, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstoll); +__extension__ +extern unsigned long long int __REDIRECT_NTH (wcstoull, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstoull); +# ifdef __USE_GNU +__extension__ +extern long long int __REDIRECT_NTH (wcstoq, (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstoll); +__extension__ +extern unsigned long long int __REDIRECT_NTH (wcstouq, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base), __isoc23_wcstoull); +# endif +# else +extern long int __isoc23_wcstol (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, int __base) + __THROW; +extern unsigned long int __isoc23_wcstoul (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base) + __THROW; +__extension__ +extern long long int __isoc23_wcstoll (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base) + __THROW; +__extension__ +extern unsigned long long int __isoc23_wcstoull (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base) + __THROW; +# define wcstol __isoc23_wcstol +# define wcstoul __isoc23_wcstoul +# define wcstoll __isoc23_wcstoll +# define wcstoull __isoc23_wcstoull +# ifdef __USE_GNU +# define wcstoq __isoc23_wcstoll +# define wcstouq __isoc23_wcstoull +# endif +# endif +#endif + #ifdef __USE_GNU /* Parallel versions of the functions above which take the locale to use as an additional parameter. These are GNU extensions inspired @@ -490,6 +551,56 @@ extern unsigned long long int wcstoull_l (const wchar_t *__restrict __nptr, int __base, locale_t __loc) __THROW; +/* Versions of the above functions that handle '0b' and '0B' prefixes + in base 0 or 2. */ +# if __GLIBC_USE (C2X_STRTOL) +# ifdef __REDIRECT +extern long int __REDIRECT_NTH (wcstol_l, (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc), + __isoc23_wcstol_l); +extern unsigned long int __REDIRECT_NTH (wcstoul_l, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc), + __isoc23_wcstoul_l); +__extension__ +extern long long int __REDIRECT_NTH (wcstoll_l, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc), + __isoc23_wcstoll_l); +__extension__ +extern unsigned long long int __REDIRECT_NTH (wcstoull_l, + (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc), + __isoc23_wcstoull_l); +# else +extern long int __isoc23_wcstol_l (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, int __base, + locale_t __loc) __THROW; +extern unsigned long int __isoc23_wcstoul_l (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc) + __THROW; +__extension__ +extern long long int __isoc23_wcstoll_l (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc) + __THROW; +__extension__ +extern unsigned long long int __isoc23_wcstoull_l (const wchar_t *__restrict __nptr, + wchar_t **__restrict __endptr, + int __base, locale_t __loc) + __THROW; +# define wcstol_l __isoc23_wcstol_l +# define wcstoul_l __isoc23_wcstoul_l +# define wcstoll_l __isoc23_wcstoll_l +# define wcstoull_l __isoc23_wcstoull_l +# endif +# endif + extern double wcstod_l (const wchar_t *__restrict __nptr, wchar_t **__restrict __endptr, locale_t __loc) __THROW; -- cgit v1.1