fix:

arch/x86/ia32/built-in.o: In function `ia32_sys_call_table':
(.rodata+0xa38): undefined reference to `compat_sys_signalfd4'

on !CONFIG_SIGNALFD.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

GEN     .version
  CHK     include/linux/compile.h
  UPD     include/linux/compile.h
  CC      init/version.o
  LD      init/built-in.o
  LD      vmlinux
arch/x86/kernel/built-in.o: In function `sys_call_table':
(.rodata+0x8a4): undefined reference to `sys_epoll_create1'
make: *** [vmlinux] Error 1

Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Davide Libenzi <davidel@xmailserver.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 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 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>

Add missing cond_syscall() entry for compat_sys_epoll_pwait.

Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: <stable@kernel.org>		[2.6.25.x, 2.6.26.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This is the new timerfd API as it is implemented by the following patch:

int timerfd_create(int clockid, int flags);
int timerfd_settime(int ufd, int flags,
		    const struct itimerspec *utmr,
		    struct itimerspec *otmr);
int timerfd_gettime(int ufd, struct itimerspec *otmr);

The timerfd_create() API creates an un-programmed timerfd fd.  The "clockid"
parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME.

The timerfd_settime() API give new settings by the timerfd fd, by optionally
retrieving the previous expiration time (in case the "otmr" parameter is not
NULL).

The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit
is set in the "flags" parameter.  Otherwise it's a relative time.

The timerfd_gettime() API returns the next expiration time of the timer, or
{0, 0} if the timerfd has not been set yet.

Like the previous timerfd API implementation, read(2) and poll(2) are
supported (with the same interface).  Here's a simple test program I used to
exercise the new timerfd APIs:

http://www.xmailserver.org/timerfd-test2.c

[akpm@linux-foundation.org: coding-style cleanups]
[akpm@linux-foundation.org: fix ia64 build]
[akpm@linux-foundation.org: fix m68k build]
[akpm@linux-foundation.org: fix mips build]
[akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds]
[heiko.carstens@de.ibm.com: fix s390]
[akpm@linux-foundation.org: fix powerpc build]
[akpm@linux-foundation.org: fix sparc64 more]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Using 64k pages on 64-bit PowerPC systems makes life difficult for
emulators that are trying to emulate an ISA, such as x86, which use a
smaller page size, since the emulator can no longer use the MMU and
the normal system calls for controlling page protections.  Of course,
the emulator can emulate the MMU by checking and possibly remapping
the address for each memory access in software, but that is pretty
slow.

This provides a facility for such programs to control the access
permissions on individual 4k sub-pages of 64k pages.  The idea is
that the emulator supplies an array of protection masks to apply to a
specified range of virtual addresses.  These masks are applied at the
level where hardware PTEs are inserted into the hardware page table
based on the Linux PTEs, so the Linux PTEs are not affected.  Note
that this new mechanism does not allow any access that would otherwise
be prohibited; it can only prohibit accesses that would otherwise be
allowed.  This new facility is only available on 64-bit PowerPC and
only when the kernel is configured for 64k pages.

The masks are supplied using a new subpage_prot system call, which
takes a starting virtual address and length, and a pointer to an array
of protection masks in memory.  The array has a 32-bit word per 64k
page to be protected; each 32-bit word consists of 16 2-bit fields,
for which 0 allows any access (that is otherwise allowed), 1 prevents
write accesses, and 2 or 3 prevent any access.

Implicit in this is that the regions of the address space that are
protected are switched to use 4k hardware pages rather than 64k
hardware pages (on machines with hardware 64k page support).  In fact
the whole process is switched to use 4k hardware pages when the
subpage_prot system call is used, but this could be improved in future
to switch only the affected segments.

The subpage protection bits are stored in a 3 level tree akin to the
page table tree.  The top level of this tree is stored in a structure
that is appended to the top level of the page table tree, i.e., the
pgd array.  Since it will often only be 32-bit addresses (below 4GB)
that are protected, the pointers to the first four bottom level pages
are also stored in this structure (each bottom level page contains the
protection bits for 1GB of address space), so the protection bits for
addresses below 4GB can be accessed with one fewer loads than those
for higher addresses.

Signed-off-by: Paul Mackerras <paulus@samba.org>

Add some missing cond_syscall() entries for this case.

Signed-off-by: David S. Miller <davem@davemloft.net>