glibc/sysdeps/unix/sysv/linux/sysconf.c

128 lines
3.3 KiB
C
Raw Normal View History

/* Get file-specific information about a file. Linux version.
Copyright (C) 2003-2022 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
<https://www.gnu.org/licenses/>. */
sysconf: Add _SC_MINSIGSTKSZ/_SC_SIGSTKSZ [BZ #20305] Add _SC_MINSIGSTKSZ for the minimum signal stack size derived from AT_MINSIGSTKSZ, which is the minimum number of bytes of free stack space required in order to gurantee successful, non-nested handling of a single signal whose handler is an empty function, and _SC_SIGSTKSZ which is the suggested minimum number of bytes of stack space required for a signal stack. If AT_MINSIGSTKSZ isn't available, sysconf (_SC_MINSIGSTKSZ) returns MINSIGSTKSZ. On Linux/x86 with XSAVE, the signal frame used by kernel is composed of the following areas and laid out as: ------------------------------ | alignment padding | ------------------------------ | xsave buffer | ------------------------------ | fsave header (32-bit only) | ------------------------------ | siginfo + ucontext | ------------------------------ Compute AT_MINSIGSTKSZ value as size of xsave buffer + size of fsave header (32-bit only) + size of siginfo and ucontext + alignment padding. If _SC_SIGSTKSZ_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are redefined as /* Default stack size for a signal handler: sysconf (SC_SIGSTKSZ). */ # undef SIGSTKSZ # define SIGSTKSZ sysconf (_SC_SIGSTKSZ) /* Minimum stack size for a signal handler: SIGSTKSZ. */ # undef MINSIGSTKSZ # define MINSIGSTKSZ SIGSTKSZ Compilation will fail if the source assumes constant MINSIGSTKSZ or SIGSTKSZ. The reason for not simply increasing the kernel's MINSIGSTKSZ #define (apart from the fact that it is rarely used, due to glibc's shadowing definitions) was that userspace binaries will have baked in the old value of the constant and may be making assumptions about it. For example, the type (char [MINSIGSTKSZ]) changes if this #define changes. This could be a problem if an newly built library tries to memcpy() or dump such an object defined by and old binary. Bounds-checking and the stack sizes passed to things like sigaltstack() and makecontext() could similarly go wrong.
2021-02-01 19:00:38 +00:00
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
#include <sysdep.h>
#include <time.h>
#include <unistd.h>
#include <sys/resource.h>
#include <sys/param.h>
#include <not-cancel.h>
#include <ldsodefs.h>
sysconf: Add _SC_MINSIGSTKSZ/_SC_SIGSTKSZ [BZ #20305] Add _SC_MINSIGSTKSZ for the minimum signal stack size derived from AT_MINSIGSTKSZ, which is the minimum number of bytes of free stack space required in order to gurantee successful, non-nested handling of a single signal whose handler is an empty function, and _SC_SIGSTKSZ which is the suggested minimum number of bytes of stack space required for a signal stack. If AT_MINSIGSTKSZ isn't available, sysconf (_SC_MINSIGSTKSZ) returns MINSIGSTKSZ. On Linux/x86 with XSAVE, the signal frame used by kernel is composed of the following areas and laid out as: ------------------------------ | alignment padding | ------------------------------ | xsave buffer | ------------------------------ | fsave header (32-bit only) | ------------------------------ | siginfo + ucontext | ------------------------------ Compute AT_MINSIGSTKSZ value as size of xsave buffer + size of fsave header (32-bit only) + size of siginfo and ucontext + alignment padding. If _SC_SIGSTKSZ_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are redefined as /* Default stack size for a signal handler: sysconf (SC_SIGSTKSZ). */ # undef SIGSTKSZ # define SIGSTKSZ sysconf (_SC_SIGSTKSZ) /* Minimum stack size for a signal handler: SIGSTKSZ. */ # undef MINSIGSTKSZ # define MINSIGSTKSZ SIGSTKSZ Compilation will fail if the source assumes constant MINSIGSTKSZ or SIGSTKSZ. The reason for not simply increasing the kernel's MINSIGSTKSZ #define (apart from the fact that it is rarely used, due to glibc's shadowing definitions) was that userspace binaries will have baked in the old value of the constant and may be making assumptions about it. For example, the type (char [MINSIGSTKSZ]) changes if this #define changes. This could be a problem if an newly built library tries to memcpy() or dump such an object defined by and old binary. Bounds-checking and the stack sizes passed to things like sigaltstack() and makecontext() could similarly go wrong.
2021-02-01 19:00:38 +00:00
#include <sysconf-sigstksz.h>
/* Legacy value of ARG_MAX. The macro is now not defined since the
actual value varies based on the stack size. */
#define legacy_ARG_MAX 131072
linux: sysconf: limit _SC_MAX_ARG to 6 MiB (BZ #25305) Since Linux 4.13, kernel limits the maximum command line arguments length to 6 MiB [1]. Normally the limit is still quarter of the maximum stack size but if that limit exceeds 6 MiB it's clamped down. glibc's __sysconf implementation for Linux platform is not aware of this limitation and for stack sizes of over 24 MiB it returns higher ARG_MAX than Linux will actually accept. This can be verified by executing the following application on Linux 4.13 or newer: #include <stdio.h> #include <string.h> #include <sys/resource.h> #include <sys/time.h> #include <unistd.h> int main(void) { const struct rlimit rlim = { 40 * 1024 * 1024, 40 * 1024 * 1024 }; if (setrlimit(RLIMIT_STACK, &rlim) < 0) { perror("setrlimit: RLIMIT_STACK"); return 1; } printf("ARG_MAX : %8ld\n", sysconf(_SC_ARG_MAX)); printf("63 * 100 KiB: %8ld\n", 63L * 100 * 1024); printf("6 MiB : %8ld\n", 6L * 1024 * 1024); char str[100 * 1024], *argv[64], *envp[1]; memset(&str, 'A', sizeof str); str[sizeof str - 1] = '\0'; for (size_t i = 0; i < sizeof argv / sizeof *argv - 1; ++i) { argv[i] = str; } argv[sizeof argv / sizeof *argv - 1] = envp[0] = 0; execve("/bin/true", argv, envp); perror("execve"); return 1; } On affected systems the program will report ARG_MAX as 10 MiB but despite that executing /bin/true with a bit over 6 MiB of command line arguments will fail with E2BIG error. Expected result is that ARG_MAX is reported as 6 MiB. Update the __sysconf function to clamp ARG_MAX value to 6 MiB if it would otherwise exceed it. This resolves bug #25305 which was market WONTFIX as suggested solution was to cap ARG_MAX at 128 KiB. As an aside and point of comparison, bionic (a libc implementation for Android systems) decided to resolve this issue by always returning 128 KiB ignoring any potential xargs regressions [2]. On older kernels this results in returning overly conservative value but that's a safer option than being aggressive and returning invalid value on recent systems. It's also worth noting that at this point all supported Linux releases have the 6 MiB barrier so only someone running an unsupported kernel version would get incorrectly truncated result. Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org> [1] See https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=da029c11e6b12f321f36dac8771e833b65cec962 [2] See https://android.googlesource.com/platform/bionic/+/baed51ee3a13dae4b87b11870bdf7f10bdc9efc1
2021-04-07 15:10:58 +00:00
/* Newer kernels (4.13) limit the maximum command line arguments lengths to
6MiB. */
#define maximum_ARG_MAX (6 * 1024 * 1024)
static long int posix_sysconf (int name);
/* Get the value of the system variable NAME. */
long int
__sysconf (int name)
{
const char *procfname = NULL;
switch (name)
{
case _SC_MONOTONIC_CLOCK:
case _SC_CPUTIME:
case _SC_THREAD_CPUTIME:
return _POSIX_VERSION;
case _SC_ARG_MAX:
{
struct rlimit rlimit;
/* Use getrlimit to get the stack limit. */
if (__getrlimit (RLIMIT_STACK, &rlimit) == 0)
linux: sysconf: limit _SC_MAX_ARG to 6 MiB (BZ #25305) Since Linux 4.13, kernel limits the maximum command line arguments length to 6 MiB [1]. Normally the limit is still quarter of the maximum stack size but if that limit exceeds 6 MiB it's clamped down. glibc's __sysconf implementation for Linux platform is not aware of this limitation and for stack sizes of over 24 MiB it returns higher ARG_MAX than Linux will actually accept. This can be verified by executing the following application on Linux 4.13 or newer: #include <stdio.h> #include <string.h> #include <sys/resource.h> #include <sys/time.h> #include <unistd.h> int main(void) { const struct rlimit rlim = { 40 * 1024 * 1024, 40 * 1024 * 1024 }; if (setrlimit(RLIMIT_STACK, &rlim) < 0) { perror("setrlimit: RLIMIT_STACK"); return 1; } printf("ARG_MAX : %8ld\n", sysconf(_SC_ARG_MAX)); printf("63 * 100 KiB: %8ld\n", 63L * 100 * 1024); printf("6 MiB : %8ld\n", 6L * 1024 * 1024); char str[100 * 1024], *argv[64], *envp[1]; memset(&str, 'A', sizeof str); str[sizeof str - 1] = '\0'; for (size_t i = 0; i < sizeof argv / sizeof *argv - 1; ++i) { argv[i] = str; } argv[sizeof argv / sizeof *argv - 1] = envp[0] = 0; execve("/bin/true", argv, envp); perror("execve"); return 1; } On affected systems the program will report ARG_MAX as 10 MiB but despite that executing /bin/true with a bit over 6 MiB of command line arguments will fail with E2BIG error. Expected result is that ARG_MAX is reported as 6 MiB. Update the __sysconf function to clamp ARG_MAX value to 6 MiB if it would otherwise exceed it. This resolves bug #25305 which was market WONTFIX as suggested solution was to cap ARG_MAX at 128 KiB. As an aside and point of comparison, bionic (a libc implementation for Android systems) decided to resolve this issue by always returning 128 KiB ignoring any potential xargs regressions [2]. On older kernels this results in returning overly conservative value but that's a safer option than being aggressive and returning invalid value on recent systems. It's also worth noting that at this point all supported Linux releases have the 6 MiB barrier so only someone running an unsupported kernel version would get incorrectly truncated result. Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org> [1] See https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=da029c11e6b12f321f36dac8771e833b65cec962 [2] See https://android.googlesource.com/platform/bionic/+/baed51ee3a13dae4b87b11870bdf7f10bdc9efc1
2021-04-07 15:10:58 +00:00
{
const long int limit = MAX (legacy_ARG_MAX, rlimit.rlim_cur / 4);
return MIN (limit, maximum_ARG_MAX);
}
return legacy_ARG_MAX;
}
case _SC_NGROUPS_MAX:
/* Try to read the information from the /proc/sys/kernel/ngroups_max
file. */
procfname = "/proc/sys/kernel/ngroups_max";
break;
case _SC_SIGQUEUE_MAX:
{
struct rlimit rlimit;
if (__getrlimit (RLIMIT_SIGPENDING, &rlimit) == 0)
return rlimit.rlim_cur;
/* The /proc/sys/kernel/rtsig-max file contains the answer. */
procfname = "/proc/sys/kernel/rtsig-max";
}
break;
sysconf: Add _SC_MINSIGSTKSZ/_SC_SIGSTKSZ [BZ #20305] Add _SC_MINSIGSTKSZ for the minimum signal stack size derived from AT_MINSIGSTKSZ, which is the minimum number of bytes of free stack space required in order to gurantee successful, non-nested handling of a single signal whose handler is an empty function, and _SC_SIGSTKSZ which is the suggested minimum number of bytes of stack space required for a signal stack. If AT_MINSIGSTKSZ isn't available, sysconf (_SC_MINSIGSTKSZ) returns MINSIGSTKSZ. On Linux/x86 with XSAVE, the signal frame used by kernel is composed of the following areas and laid out as: ------------------------------ | alignment padding | ------------------------------ | xsave buffer | ------------------------------ | fsave header (32-bit only) | ------------------------------ | siginfo + ucontext | ------------------------------ Compute AT_MINSIGSTKSZ value as size of xsave buffer + size of fsave header (32-bit only) + size of siginfo and ucontext + alignment padding. If _SC_SIGSTKSZ_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are redefined as /* Default stack size for a signal handler: sysconf (SC_SIGSTKSZ). */ # undef SIGSTKSZ # define SIGSTKSZ sysconf (_SC_SIGSTKSZ) /* Minimum stack size for a signal handler: SIGSTKSZ. */ # undef MINSIGSTKSZ # define MINSIGSTKSZ SIGSTKSZ Compilation will fail if the source assumes constant MINSIGSTKSZ or SIGSTKSZ. The reason for not simply increasing the kernel's MINSIGSTKSZ #define (apart from the fact that it is rarely used, due to glibc's shadowing definitions) was that userspace binaries will have baked in the old value of the constant and may be making assumptions about it. For example, the type (char [MINSIGSTKSZ]) changes if this #define changes. This could be a problem if an newly built library tries to memcpy() or dump such an object defined by and old binary. Bounds-checking and the stack sizes passed to things like sigaltstack() and makecontext() could similarly go wrong.
2021-02-01 19:00:38 +00:00
case _SC_MINSIGSTKSZ:
assert (GLRO(dl_minsigstacksize) != 0);
return GLRO(dl_minsigstacksize);
case _SC_SIGSTKSZ:
return sysconf_sigstksz ();
default:
break;
}
if (procfname != NULL)
{
int fd = __open_nocancel (procfname, O_RDONLY | O_CLOEXEC);
if (fd != -1)
{
/* This is more than enough, the file contains a single integer. */
char buf[32];
ssize_t n;
Consolidate non cancellable read call This patch consolidates all the non cancellable read calls to use the __read_nocancel identifier. For non cancellable targets it will be just a macro to call the default respective symbol while on Linux will be a internal one. Also, since it is used on libcrypto it is also exported in GLIBC_PRIVATE namespace. Checked on x86_64-linux-gnu, x86_64-linux-gnu-x32, and i686-linux-gnu. * sysdeps/generic/not-cancel.h (read_not_cancel): Remove macro. (__read_nocancel): New macro. * sysdeps/unix/sysv/linux/Versions (libc) [GLIBC_PRIVATE]: Add __read_nocancel. * sysdeps/unix/sysv/linux/not-cancel.h (__read_nocancel): Remove macro. (__read_nocancel): New prototype. * sysdeps/unix/sysv/linux/read.c (__read_nocancel): New function. * catgets/open_catalog.c (__open_catalog): Replace read_not_cancel with __read_nocancel. * intl/loadmsgcat.c (read): Likewise. * libio/fileops.c (_IO_file_read): Likewise. * locale/loadlocale.c (_nl_load_locale): Likewise. * login/utmp_file.c (getutent_r_file): Likewise. (internal_getut_r): Likewise. (getutline_r_file): Likewise. * sysdeps/unix/sysv/linux/fips-private.h (fips_enable_p): Likewise. * sysdeps/unix/sysv/linux/gethostid.c (gethostid): Likewise. * sysdeps/unix/sysv/linux/getloadavg.c (getloadavg): Likewise. * sysdeps/unix/sysv/linux/getlogin_r.c (__getlogin_r_loginuid): Likewise. * sysdeps/unix/sysv/linux/getsysstats.c (next_line): Likewise. * sysdeps/unix/sysv/linux/i386/smp.h (is_smp_system): Likewise. * sysdeps/unix/sysv/linux/ia64/has_cpuclock.c (has_cpuclock): Likewise. * sysdeps/unix/sysv/linux/libc_fatal.c (backtrace_and_maps): Likewise. * sysdeps/unix/sysv/linux/malloc-sysdep.h (check_may_shrink_heap): Likewise. * sysdeps/unix/sysv/linux/pthread_getname.c (pthread_getname_np): Likewise. * sysdeps/unix/sysv/linux/sysconf.c (__sysconf): Likewise.
2017-07-03 17:20:46 +00:00
n = TEMP_FAILURE_RETRY (__read_nocancel (fd, buf, sizeof (buf) - 1));
Consolidate non cancellable close call This patch consolidates all the non cancellable close calls to use the __close_nocancel{_nostatus} identifier. For non cancellable targets it will be just a macro to call the default respective symbol while on Linux will be a internal one. Also, since it is used on libcrypto it is also exported in GLIBC_PRIVATE namespace. Checked on x86_64-linux-gnu, x86_64-linux-gnu-x32, and i686-linux-gnu. * sysdeps/generic/not-cancel.h (close_not_cancel): Remove macro. (close_not_cancel_no_status): Likewise. (__close_nocancel): New macro. (__close_nocancel_no_status): Likewise. * sysdeps/unix/sysv/linux/not-cancel.h (__close_nocancel): Remove macro. (close_not_cancel): Likewise. (close_not_cancel_no_status): Likewise. (__close_nocancel): New prototype. (__close_nocancel_no_status): New function. * sysdeps/unix/sysv/linux/close.c (__close_nocancel): New function. * catgets/open_catalog.c (__open_catalog): Replace close_not_cancel{_no_status) with __close_nocancel{_nostatus}. * gmon/gmon.c (write_gmon): Likewise. * iconv/gconv_cache.c (__gconv_load_cache): Likewise. * intl/loadmsgcat.c (close): Likewise. * io/ftw.c (open_dir_stream): Likewise. (ftw_startup): Likewise. * libio/fileops.c (_IO_file_open): Likewise. (_IO_file_close_mmap): Likewise. (_IO_file_close): Likewise. * libio/iopopen.c (_IO_dup2): Likewise. * locale/loadarchive.c (_nl_load_locale_from_archive): Likewise. * locale/loadlocale.c (_nl_load_locale): Likewise. * login/utmp_file.c (pututline_file): Likewise. (endutent_file): Likewise. * misc/daemon.c (daemon): Likewise. * nscd/nscd_getai.c (__nscd_getai): Likewise. * nscd/nscd_getgr_r.c (nscd_getgr_r): Likewise. * nscd/nscd_gethst_r.c (nscd_gethst_r): Likewise. * nscd/nscd_getpw_r.c (nscd_getpw_r): Likewise. * nscd/nscd_getserv_r.c (nscd_getserv_r): Likewise. * nscd/nscd_helper.c (open_socket): Likewise. (__nscd_open_socket): Likewise. * nscd/nscd_initgroups.c (__nscd_getgrouplist): Likewise. * nscd/nscd_netgroup.c (__nscd_setnetgrent): Likewise. (__nscd_innetgr): Likewise. * nss/nss_db/db-open.c (internal_setent): Likewise. * resolv/res-close.c (__res_iclose): Likewise. * sunrpc/pm_getmaps.c (pmap_getmaps): Likewise. * sysdeps/posix/closedir.c (__closedir): Likewise. * sysdeps/posix/getaddrinfo.c (getaddrinfo): Likewise. * sysdeps/posix/getcwd.c (__getcwd): Likewise. * sysdeps/posix/opendir.c (tryopen_o_directory): Likewise. (opendir_tail): Likewise. * sysdeps/posix/spawni.c (__spawni_child): Likewise. * sysdeps/unix/sysv/linux/check_native.c (__check_native): Likewise. * sysdeps/unix/sysv/linux/check_pf.c (__check_pf): Likewise. * sysdeps/unix/sysv/linux/fips-private.h (fips_enabled_p): Likewise. * sysdeps/unix/sysv/linux/gethostid.c (sethostid): Likewise. (gethostid): Likewise. * sysdeps/unix/sysv/linux/getloadavg.c (getloadavg): Likewise. * sysdeps/unix/sysv/linux/getlogin_r.c (__getlogin_r_loginuid): Likewise. * sysdeps/unix/sysv/linux/getsysstats.c (__get_nprocs): Likewise. * sysdeps/unix/sysv/linux/grantpt.c (close_all_fds): Likewise. * sysdeps/unix/sysv/linux/i386/smp.h (is_smp_system): Likewise. * sysdeps/unix/sysv/linux/ia64/has_cpuclock.c (has_cpuclock): Likewise. * sysdeps/unix/sysv/linux/if_index.c (__if_nametoindex): Likewise. * sysdeps/unix/sysv/linux/libc_fatal.c (backtrace_and_maps): Likewise. * sysdeps/unix/sysv/linux/malloc-sysdep.h (check_may_shrink_heap): Likewise. * sysdeps/unix/sysv/linux/mq_notify.c (init_mq_netlink): Likewise. * sysdeps/unix/sysv/linux/pthread_getname.c (pthread_getname_np): Likewise. * sysdeps/unix/sysv/linux/pthread_setname.c (pthread_setname_np): Likewise. * sysdeps/unix/sysv/linux/spawni.c (__spawni_child): Likewise. * sysdeps/unix/sysv/linux/sysconf.c (__sysconf): Likewise.
2017-07-03 18:22:58 +00:00
__close_nocancel_nostatus (fd);
if (n > 0)
{
/* Terminate the string. */
buf[n] = '\0';
char *endp;
long int res = strtol (buf, &endp, 10);
if (endp != buf && (*endp == '\0' || *endp == '\n'))
return res;
}
}
}
return posix_sysconf (name);
}
/* Now the POSIX version. */
#undef __sysconf
#define __sysconf static posix_sysconf
#include <sysdeps/posix/sysconf.c>