This patch introduces the new syscall inotify_init1 (note: the 1 stands for
the one parameter the syscall takes, as opposed to no parameter before). The
values accepted for this parameter are function-specific and defined in the
inotify.h header. Here the values must match the O_* flags, though. In this
patch CLOEXEC support is introduced.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_inotify_init1
# ifdef __x86_64__
# define __NR_inotify_init1 294
# elif defined __i386__
# define __NR_inotify_init1 332
# else
# error "need __NR_inotify_init1"
# endif
#endif
#define IN_CLOEXEC O_CLOEXEC
int
main (void)
{
int fd;
fd = syscall (__NR_inotify_init1, 0);
if (fd == -1)
{
puts ("inotify_init1(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("inotify_init1(0) set close-on-exit");
return 1;
}
close (fd);
fd = syscall (__NR_inotify_init1, IN_CLOEXEC);
if (fd == -1)
{
puts ("inotify_init1(IN_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit");
return 1;
}
close (fd);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch introduces the new syscall pipe2 which is like pipe but it also
takes an additional parameter which takes a flag value. This patch implements
the handling of O_CLOEXEC for the flag. I did not add support for the new
syscall for the architectures which have a special sys_pipe implementation. I
think the maintainers of those archs have the chance to go with the unified
implementation but that's up to them.
The implementation introduces do_pipe_flags. I did that instead of changing
all callers of do_pipe because some of the callers are written in assembler.
I would probably screw up changing the assembly code. To avoid breaking code
do_pipe is now a small wrapper around do_pipe_flags. Once all callers are
changed over to do_pipe_flags the old do_pipe function can be removed.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_pipe2
# ifdef __x86_64__
# define __NR_pipe2 293
# elif defined __i386__
# define __NR_pipe2 331
# else
# error "need __NR_pipe2"
# endif
#endif
int
main (void)
{
int fd[2];
if (syscall (__NR_pipe2, fd, 0) != 0)
{
puts ("pipe2(0) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int coe = fcntl (fd[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
printf ("pipe2(0) set close-on-exit for fd[%d]\n", i);
return 1;
}
}
close (fd[0]);
close (fd[1]);
if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0)
{
puts ("pipe2(O_CLOEXEC) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
int coe = fcntl (fd[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i);
return 1;
}
}
close (fd[0]);
close (fd[1]);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds the new dup3 syscall. It extends the old dup2 syscall by one
parameter which is meant to hold a flag value. Support for the O_CLOEXEC flag
is added in this patch.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <time.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_dup3
# ifdef __x86_64__
# define __NR_dup3 292
# elif defined __i386__
# define __NR_dup3 330
# else
# error "need __NR_dup3"
# endif
#endif
int
main (void)
{
int fd = syscall (__NR_dup3, 1, 4, 0);
if (fd == -1)
{
puts ("dup3(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("dup3(0) set close-on-exec flag");
return 1;
}
close (fd);
fd = syscall (__NR_dup3, 1, 4, O_CLOEXEC);
if (fd == -1)
{
puts ("dup3(O_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("dup3(O_CLOEXEC) set close-on-exec flag");
return 1;
}
close (fd);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds the new epoll_create2 syscall. It extends the old epoll_create
syscall by one parameter which is meant to hold a flag value. In this
patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec
flag for the returned file descriptor to be set.
A new name EPOLL_CLOEXEC is introduced which in this implementation must
have the same value as O_CLOEXEC.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <time.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_epoll_create2
# ifdef __x86_64__
# define __NR_epoll_create2 291
# elif defined __i386__
# define __NR_epoll_create2 329
# else
# error "need __NR_epoll_create2"
# endif
#endif
#define EPOLL_CLOEXEC O_CLOEXEC
int
main (void)
{
int fd = syscall (__NR_epoll_create2, 1, 0);
if (fd == -1)
{
puts ("epoll_create2(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("epoll_create2(0) set close-on-exec flag");
return 1;
}
close (fd);
fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC);
if (fd == -1)
{
puts ("epoll_create2(EPOLL_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag");
return 1;
}
close (fd);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds the new eventfd2 syscall. It extends the old eventfd
syscall by one parameter which is meant to hold a flag value. In this
patch the only flag support is EFD_CLOEXEC which causes the close-on-exec
flag for the returned file descriptor to be set.
A new name EFD_CLOEXEC is introduced which in this implementation must
have the same value as O_CLOEXEC.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_eventfd2
# ifdef __x86_64__
# define __NR_eventfd2 290
# elif defined __i386__
# define __NR_eventfd2 328
# else
# error "need __NR_eventfd2"
# endif
#endif
#define EFD_CLOEXEC O_CLOEXEC
int
main (void)
{
int fd = syscall (__NR_eventfd2, 1, 0);
if (fd == -1)
{
puts ("eventfd2(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("eventfd2(0) sets close-on-exec flag");
return 1;
}
close (fd);
fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC);
if (fd == -1)
{
puts ("eventfd2(EFD_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (fd);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds the new signalfd4 syscall. It extends the old signalfd
syscall by one parameter which is meant to hold a flag value. In this
patch the only flag support is SFD_CLOEXEC which causes the close-on-exec
flag for the returned file descriptor to be set.
A new name SFD_CLOEXEC is introduced which in this implementation must
have the same value as O_CLOEXEC.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <signal.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/syscall.h>
#ifndef __NR_signalfd4
# ifdef __x86_64__
# define __NR_signalfd4 289
# elif defined __i386__
# define __NR_signalfd4 327
# else
# error "need __NR_signalfd4"
# endif
#endif
#define SFD_CLOEXEC O_CLOEXEC
int
main (void)
{
sigset_t ss;
sigemptyset (&ss);
sigaddset (&ss, SIGUSR1);
int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0);
if (fd == -1)
{
puts ("signalfd4(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("signalfd4(0) set close-on-exec flag");
return 1;
}
close (fd);
fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC);
if (fd == -1)
{
puts ("signalfd4(SFD_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (fd);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch is by far the most complex in the series. It adds a new syscall
paccept. This syscall differs from accept in that it adds (at the userlevel)
two additional parameters:
- a signal mask
- a flags value
The flags parameter can be used to set flag like SOCK_CLOEXEC. This is
imlpemented here as well. Some people argued that this is a property which
should be inherited from the file desriptor for the server but this is against
POSIX. Additionally, we really want the signal mask parameter as well
(similar to pselect, ppoll, etc). So an interface change in inevitable.
The flag value is the same as for socket and socketpair. I think diverging
here will only create confusion. Similar to the filesystem interfaces where
the use of the O_* constants differs, it is acceptable here.
The signal mask is handled as for pselect etc. The mask is temporarily
installed for the thread and removed before the call returns. I modeled the
code after pselect. If there is a problem it's likely also in pselect.
For architectures which use socketcall I maintained this interface instead of
adding a system call. The symmetry shouldn't be broken.
The following test must be adjusted for architectures other than x86 and
x86-64 and in case the syscall numbers changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <errno.h>
#include <fcntl.h>
#include <pthread.h>
#include <signal.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/syscall.h>
#ifndef __NR_paccept
# ifdef __x86_64__
# define __NR_paccept 288
# elif defined __i386__
# define SYS_PACCEPT 18
# define USE_SOCKETCALL 1
# else
# error "need __NR_paccept"
# endif
#endif
#ifdef USE_SOCKETCALL
# define paccept(fd, addr, addrlen, mask, flags) \
({ long args[6] = { \
(long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \
syscall (__NR_socketcall, SYS_PACCEPT, args); })
#else
# define paccept(fd, addr, addrlen, mask, flags) \
syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags)
#endif
#define PORT 57392
#define SOCK_CLOEXEC O_CLOEXEC
static pthread_barrier_t b;
static void *
tf (void *arg)
{
pthread_barrier_wait (&b);
int s = socket (AF_INET, SOCK_STREAM, 0);
struct sockaddr_in sin;
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
sin.sin_port = htons (PORT);
connect (s, (const struct sockaddr *) &sin, sizeof (sin));
close (s);
pthread_barrier_wait (&b);
s = socket (AF_INET, SOCK_STREAM, 0);
sin.sin_port = htons (PORT);
connect (s, (const struct sockaddr *) &sin, sizeof (sin));
close (s);
pthread_barrier_wait (&b);
pthread_barrier_wait (&b);
sleep (2);
pthread_kill ((pthread_t) arg, SIGUSR1);
return NULL;
}
static void
handler (int s)
{
}
int
main (void)
{
pthread_barrier_init (&b, NULL, 2);
struct sockaddr_in sin;
pthread_t th;
if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0)
{
puts ("pthread_create failed");
return 1;
}
int s = socket (AF_INET, SOCK_STREAM, 0);
int reuse = 1;
setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse));
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
sin.sin_port = htons (PORT);
bind (s, (struct sockaddr *) &sin, sizeof (sin));
listen (s, SOMAXCONN);
pthread_barrier_wait (&b);
int s2 = paccept (s, NULL, 0, NULL, 0);
if (s2 < 0)
{
puts ("paccept(0) failed");
return 1;
}
int coe = fcntl (s2, F_GETFD);
if (coe & FD_CLOEXEC)
{
puts ("paccept(0) set close-on-exec-flag");
return 1;
}
close (s2);
pthread_barrier_wait (&b);
s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC);
if (s2 < 0)
{
puts ("paccept(SOCK_CLOEXEC) failed");
return 1;
}
coe = fcntl (s2, F_GETFD);
if ((coe & FD_CLOEXEC) == 0)
{
puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (s2);
pthread_barrier_wait (&b);
struct sigaction sa;
sa.sa_handler = handler;
sa.sa_flags = 0;
sigemptyset (&sa.sa_mask);
sigaction (SIGUSR1, &sa, NULL);
sigset_t ss;
pthread_sigmask (SIG_SETMASK, NULL, &ss);
sigaddset (&ss, SIGUSR1);
pthread_sigmask (SIG_SETMASK, &ss, NULL);
sigdelset (&ss, SIGUSR1);
alarm (4);
pthread_barrier_wait (&b);
errno = 0 ;
s2 = paccept (s, NULL, 0, &ss, 0);
if (s2 != -1 || errno != EINTR)
{
puts ("paccept did not fail with EINTR");
return 1;
}
close (s);
puts ("OK");
return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
[akpm@linux-foundation.org: make it compile]
[akpm@linux-foundation.org: add sys_ni stub]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <linux-arch@vger.kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Roland McGrath <roland@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Wires up the new timerfd API to the x86 family.
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
sys_iopl is long gone and there is no reason to declare
sys_rt_sigaction here.
Remove it all together and fix the whitespace mess as well.
It's worth the trouble: 25897 -> 21337 bytes, the win is
larger than the memory of my first computer :)
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This brings x86_64 into line with all other architectures by only defining
cond_syscall() when __KERNEL__ is defined.
[ tglx: arch/x86 adaptation ]
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Move the headers to include/asm-x86 and fixup the
header install make rules
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
