mirror of
https://github.com/postgres/postgres.git
synced 2026-03-07 15:50:44 -05:00
253cf661c2
Per the letter of the C11 standard, one must #define
__STDC_WANT_LIB_EXT1__ as 1 before including <string.h> in order to
have access to memset_s(). It appears that many platforms are lenient
about this, because we weren't doing it and yet the code appeared to
work anyway. But we now find that with -std=c11, macOS is strict and
doesn't declare memset_s, leading to compile failures since we try to
use it anyway. (Given the lack of prior reports, perhaps this is new
behavior in the latest SDK? No matter, we're clearly in the wrong.)
In addition to the immediate problem, which could be fixed merely by
adding the needed #define to explicit_bzero.c, it seems possible that
our configure-time probe for memset_s() could fail in case a platform
implements the function in some odd way due to this spec requirement.
This concern can be fixed in largely the same way that we dealt with
strchrnul() in
|
||
|---|---|---|
| .. | ||
| .gitignore | ||
| bsearch_arg.c | ||
| chklocale.c | ||
| dirent.c | ||
| dirmod.c | ||
| explicit_bzero.c | ||
| getopt.c | ||
| getopt_long.c | ||
| getpeereid.c | ||
| inet_aton.c | ||
| inet_net_ntop.c | ||
| kill.c | ||
| Makefile | ||
| meson.build | ||
| mkdtemp.c | ||
| noblock.c | ||
| open.c | ||
| path.c | ||
| pg_bitutils.c | ||
| pg_crc32c_armv8.c | ||
| pg_crc32c_armv8_choose.c | ||
| pg_crc32c_sb8.c | ||
| pg_crc32c_sse42.c | ||
| pg_crc32c_sse42_choose.c | ||
| pg_strong_random.c | ||
| pgcheckdir.c | ||
| pgmkdirp.c | ||
| pgsleep.c | ||
| pgstrcasecmp.c | ||
| pgstrsignal.c | ||
| pqsignal.c | ||
| preadv.c | ||
| pthread-win32.h | ||
| pthread_barrier_wait.c | ||
| pwritev.c | ||
| qsort.c | ||
| qsort_arg.c | ||
| quotes.c | ||
| README | ||
| snprintf.c | ||
| strerror.c | ||
| strlcat.c | ||
| strlcpy.c | ||
| strnlen.c | ||
| strtof.c | ||
| system.c | ||
| tar.c | ||
| thread.c | ||
| win32.ico | ||
| win32common.c | ||
| win32dlopen.c | ||
| win32env.c | ||
| win32error.c | ||
| win32fdatasync.c | ||
| win32fseek.c | ||
| win32gai_strerror.c | ||
| win32getrusage.c | ||
| win32gettimeofday.c | ||
| win32link.c | ||
| win32ntdll.c | ||
| win32pread.c | ||
| win32pwrite.c | ||
| win32security.c | ||
| win32setlocale.c | ||
| win32stat.c | ||
| win32ver.rc | ||
src/port/README
libpgport
=========
libpgport must have special behavior. It supplies functions to both
libraries and applications. However, there are two complexities:
1) Libraries need to use object files that are compiled with exactly
the same flags as the library. libpgport might not use the same flags,
so it is necessary to recompile the object files for individual
libraries. This is done by removing -lpgport from the link line:
# Need to recompile any libpgport object files
LIBS := $(filter-out -lpgport, $(LIBS))
and adding infrastructure to recompile the object files:
OBJS= execute.o typename.o descriptor.o data.o error.o prepare.o memory.o \
connect.o misc.o path.o exec.o \
$(filter strlcat.o, $(LIBOBJS))
The problem is that there is no testing of which object files need to be
added, but missing functions usually show up when linking user
applications.
2) For applications, we use -lpgport before -lpq, so the static files
from libpgport are linked first. This avoids having applications
dependent on symbols that are _used_ by libpq, but not intended to be
exported by libpq. libpq's libpgport usage changes over time, so such a
dependency is a problem. Windows, Linux, AIX, and macOS use an export
list to control the symbols exported by libpq.