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>

Use sockaddr_storage{} for generic socket address storage
and ensures proper alignment.
Use sockaddr{} for pointers to omit several casts.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds support for getsockopt for MCAST_MSFILTER for
both IPv4 and IPv6. It depends on the previous setsockopt patch,
and uses the same method.

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1) added missing "__user" for kgsr and kgf pointers
2) verify read for only GROUP_FILTER_SIZE(0). The group_filter
        structure definition (via RFC) includes space for one source
        in the source list array, but that source need not be present.
        So, sizeof(group_filter) > GROUP_FILTER_SIZE(0). Fixed
        the user read-check for minimum length to use the smaller size.
3) remove unneeded "&" for gf_slist addresses

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add support on 64-bit kernels for seting 32-bit compatible MCAST*
socket options.

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IPv4 and IPv6 hook values are identical, yet some code tries to figure
out the "correct" value by looking at the address family. Introduce NF_INET_*
values for both IPv4 and IPv6. The old values are kept in a #ifndef __KERNEL__
section for userspace compatibility.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

When used function put_cmsg() to copy kernel information to user 
application memory, if the memory length given by user application is 
not enough, by the bad length calculate of msg.msg_controllen, 
put_cmsg() function may cause the msg.msg_controllen to be a large 
value, such as 0xFFFFFFF0, so the following put_cmsg() can also write 
data to usr application memory even usr has no valid memory to store 
this. This may cause usr application memory overflow.

int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
{
    struct cmsghdr __user *cm
        = (__force struct cmsghdr __user *)msg->msg_control;
    struct cmsghdr cmhdr;
    int cmlen = CMSG_LEN(len);
    ~~~~~~~~~~~~~~~~~~~~~
    int err;

    if (MSG_CMSG_COMPAT & msg->msg_flags)
        return put_cmsg_compat(msg, level, type, len, data);

    if (cm==NULL || msg->msg_controllen < sizeof(*cm)) {
        msg->msg_flags |= MSG_CTRUNC;
        return 0; /* XXX: return error? check spec. */
    }
    if (msg->msg_controllen < cmlen) {
    ~~~~~~~~~~~~~~~~~~~~~~~~
        msg->msg_flags |= MSG_CTRUNC;
        cmlen = msg->msg_controllen;
    }
    cmhdr.cmsg_level = level;
    cmhdr.cmsg_type = type;
    cmhdr.cmsg_len = cmlen;

    err = -EFAULT;
    if (copy_to_user(cm, &cmhdr, sizeof cmhdr))
        goto out;
    if (copy_to_user(CMSG_DATA(cm), data, cmlen - sizeof(struct cmsghdr)))
        goto out;
    cmlen = CMSG_SPACE(len);
~~~~~~~~~~~~~~~~~~~~~~~~~~~
    If MSG_CTRUNC flags is set, msg->msg_controllen is less than 
CMSG_SPACE(len), "msg->msg_controllen -= cmlen" will cause unsinged int 
type msg->msg_controllen to be a large value.
~~~~~~~~~~~~~~~~~~~~~~~~~~~
    msg->msg_control += cmlen;
    msg->msg_controllen -= cmlen;
    ~~~~~~~~~~~~~~~~~~~~~
    err = 0;
out:
    return err;
}

The same promble exists in put_cmsg_compat(). This patch can fix this 
problem.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Part two in the O_CLOEXEC saga: adding support for file descriptors received
through Unix domain sockets.

The patch is once again pretty minimal, it introduces a new flag for recvmsg
and passes it just like the existing MSG_CMSG_COMPAT flag.  I think this bit
is not used otherwise but the networking people will know better.

This new flag is not recognized by recvfrom and recv.  These functions cannot
be used for that purpose and the asymmetry this introduces is not worse than
the already existing MSG_CMSG_COMPAT situations.

The patch must be applied on the patch which introduced O_CLOEXEC.  It has to
remove static from the new get_unused_fd_flags function but since scm.c cannot
live in a module the function still hasn't to be exported.

Here's a test program to make sure the code works.  It's so much longer than
the actual patch...

#include <errno.h>
#include <error.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <sys/socket.h>
#include <sys/un.h>

#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#endif
#ifndef MSG_CMSG_CLOEXEC
# define MSG_CMSG_CLOEXEC 0x40000000
#endif

int
main (int argc, char *argv[])
{
  if (argc > 1)
    {
      int fd = atol (argv[1]);
      printf ("child: fd = %d\n", fd);
      if (fcntl (fd, F_GETFD) == 0 || errno != EBADF)
        {
          puts ("file descriptor valid in child");
          return 1;
        }
      return 0;

    }

  struct sockaddr_un sun;
  strcpy (sun.sun_path, "./testsocket");
  sun.sun_family = AF_UNIX;

  char databuf[] = "hello";
  struct iovec iov[1];
  iov[0].iov_base = databuf;
  iov[0].iov_len = sizeof (databuf);

  union
  {
    struct cmsghdr hdr;
    char bytes[CMSG_SPACE (sizeof (int))];
  } buf;
  struct msghdr msg = { .msg_iov = iov, .msg_iovlen = 1,
                        .msg_control = buf.bytes,
                        .msg_controllen = sizeof (buf) };
  struct cmsghdr *cmsg = CMSG_FIRSTHDR (&msg);

  cmsg->cmsg_level = SOL_SOCKET;
  cmsg->cmsg_type = SCM_RIGHTS;
  cmsg->cmsg_len = CMSG_LEN (sizeof (int));

  msg.msg_controllen = cmsg->cmsg_len;

  pid_t child = fork ();
  if (child == -1)
    error (1, errno, "fork");
  if (child == 0)
    {
      int sock = socket (PF_UNIX, SOCK_STREAM, 0);
      if (sock < 0)
        error (1, errno, "socket");

      if (bind (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0)
        error (1, errno, "bind");
      if (listen (sock, SOMAXCONN) < 0)
        error (1, errno, "listen");

      int conn = accept (sock, NULL, NULL);
      if (conn == -1)
        error (1, errno, "accept");

      *(int *) CMSG_DATA (cmsg) = sock;
      if (sendmsg (conn, &msg, MSG_NOSIGNAL) < 0)
        error (1, errno, "sendmsg");

      return 0;
    }

  /* For a test suite this should be more robust like a
     barrier in shared memory.  */
  sleep (1);

  int sock = socket (PF_UNIX, SOCK_STREAM, 0);
  if (sock < 0)
    error (1, errno, "socket");

  if (connect (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0)
    error (1, errno, "connect");
  unlink (sun.sun_path);

  *(int *) CMSG_DATA (cmsg) = -1;

  if (recvmsg (sock, &msg, MSG_CMSG_CLOEXEC) < 0)
    error (1, errno, "recvmsg");

  int fd = *(int *) CMSG_DATA (cmsg);
  if (fd == -1)
    error (1, 0, "no descriptor received");

  char fdname[20];
  snprintf (fdname, sizeof (fdname), "%d", fd);
  execl ("/proc/self/exe", argv[0], fdname, NULL);
  puts ("execl failed");
  return 1;
}

[akpm@linux-foundation.org: Fix fastcall inconsistency noted by Michael Buesch]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Michael Buesch <mb@bu3sch.de>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Now that network timestamps use ktime_t infrastructure, we can add a new
SOL_SOCKET sockopt  SO_TIMESTAMPNS.

This command is similar to SO_TIMESTAMP, but permits transmission of
a 'timespec struct' instead of a 'timeval struct' control message.
(nanosecond resolution instead of microsecond)

Control message is labelled SCM_TIMESTAMPNS instead of SCM_TIMESTAMP

A socket cannot mix SO_TIMESTAMP and SO_TIMESTAMPNS : the two modes are
mutually exclusive.

sock_recv_timestamp() became too big to be fully inlined so I added a
__sock_recv_timestamp() helper function.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
CC: linux-arch@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>