2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* NET An implementation of the SOCKET network access protocol.
|
|
|
|
|
* This is the master header file for the Linux NET layer,
|
|
|
|
|
* or, in plain English: the networking handling part of the
|
|
|
|
|
* kernel.
|
|
|
|
|
*
|
|
|
|
|
* Version: @(#)net.h 1.0.3 05/25/93
|
|
|
|
|
*
|
|
|
|
|
* Authors: Orest Zborowski, <obz@Kodak.COM>
|
2005-05-06 07:16:16 +08:00
|
|
|
* Ross Biro
|
2005-04-17 06:20:36 +08:00
|
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef _LINUX_NET_H
|
|
|
|
|
#define _LINUX_NET_H
|
|
|
|
|
|
2008-03-23 08:18:47 +08:00
|
|
|
#include <linux/socket.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/socket.h>
|
|
|
|
|
|
2008-03-23 08:18:47 +08:00
|
|
|
#define NPROTO AF_MAX
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#define SYS_SOCKET 1 /* sys_socket(2) */
|
|
|
|
|
#define SYS_BIND 2 /* sys_bind(2) */
|
|
|
|
|
#define SYS_CONNECT 3 /* sys_connect(2) */
|
|
|
|
|
#define SYS_LISTEN 4 /* sys_listen(2) */
|
|
|
|
|
#define SYS_ACCEPT 5 /* sys_accept(2) */
|
|
|
|
|
#define SYS_GETSOCKNAME 6 /* sys_getsockname(2) */
|
|
|
|
|
#define SYS_GETPEERNAME 7 /* sys_getpeername(2) */
|
|
|
|
|
#define SYS_SOCKETPAIR 8 /* sys_socketpair(2) */
|
|
|
|
|
#define SYS_SEND 9 /* sys_send(2) */
|
|
|
|
|
#define SYS_RECV 10 /* sys_recv(2) */
|
|
|
|
|
#define SYS_SENDTO 11 /* sys_sendto(2) */
|
|
|
|
|
#define SYS_RECVFROM 12 /* sys_recvfrom(2) */
|
|
|
|
|
#define SYS_SHUTDOWN 13 /* sys_shutdown(2) */
|
|
|
|
|
#define SYS_SETSOCKOPT 14 /* sys_setsockopt(2) */
|
|
|
|
|
#define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */
|
|
|
|
|
#define SYS_SENDMSG 16 /* sys_sendmsg(2) */
|
|
|
|
|
#define SYS_RECVMSG 17 /* sys_recvmsg(2) */
|
flag parameters: paccept
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>
2008-07-24 12:29:20 +08:00
|
|
|
#define SYS_PACCEPT 18 /* sys_paccept(2) */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
typedef enum {
|
|
|
|
|
SS_FREE = 0, /* not allocated */
|
|
|
|
|
SS_UNCONNECTED, /* unconnected to any socket */
|
|
|
|
|
SS_CONNECTING, /* in process of connecting */
|
|
|
|
|
SS_CONNECTED, /* connected to socket */
|
|
|
|
|
SS_DISCONNECTING /* in process of disconnecting */
|
|
|
|
|
} socket_state;
|
|
|
|
|
|
|
|
|
|
#define __SO_ACCEPTCON (1 << 16) /* performed a listen */
|
|
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
2006-04-25 21:46:09 +08:00
|
|
|
#include <linux/stringify.h>
|
2006-12-29 13:21:55 +08:00
|
|
|
#include <linux/random.h>
|
2008-08-26 22:29:22 +08:00
|
|
|
#include <linux/wait.h>
|
|
|
|
|
#include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */
|
|
|
|
|
|
|
|
|
|
struct poll_table_struct;
|
|
|
|
|
struct pipe_inode_info;
|
|
|
|
|
struct inode;
|
|
|
|
|
struct net;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#define SOCK_ASYNC_NOSPACE 0
|
|
|
|
|
#define SOCK_ASYNC_WAITDATA 1
|
|
|
|
|
#define SOCK_NOSPACE 2
|
|
|
|
|
#define SOCK_PASSCRED 3
|
[AF_UNIX]: Datagram getpeersec
This patch implements an API whereby an application can determine the
label of its peer's Unix datagram sockets via the auxiliary data mechanism of
recvmsg.
Patch purpose:
This patch enables a security-aware application to retrieve the
security context of the peer of a Unix datagram socket. The application
can then use this security context to determine the security context for
processing on behalf of the peer who sent the packet.
Patch design and implementation:
The design and implementation is very similar to the UDP case for INET
sockets. Basically we build upon the existing Unix domain socket API for
retrieving user credentials. Linux offers the API for obtaining user
credentials via ancillary messages (i.e., out of band/control messages
that are bundled together with a normal message). To retrieve the security
context, the application first indicates to the kernel such desire by
setting the SO_PASSSEC option via getsockopt. Then the application
retrieves the security context using the auxiliary data mechanism.
An example server application for Unix datagram socket should look like this:
toggle = 1;
toggle_len = sizeof(toggle);
setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len);
recvmsg(sockfd, &msg_hdr, 0);
if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) {
cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr);
if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) &&
cmsg_hdr->cmsg_level == SOL_SOCKET &&
cmsg_hdr->cmsg_type == SCM_SECURITY) {
memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext));
}
}
sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow
a server socket to receive security context of the peer.
Testing:
We have tested the patch by setting up Unix datagram client and server
applications. We verified that the server can retrieve the security context
using the auxiliary data mechanism of recvmsg.
Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com>
Acked-by: Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 03:27:47 +08:00
|
|
|
#define SOCK_PASSSEC 4
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#ifndef ARCH_HAS_SOCKET_TYPES
|
2005-05-01 23:59:25 +08:00
|
|
|
/**
|
|
|
|
|
* enum sock_type - Socket types
|
|
|
|
|
* @SOCK_STREAM: stream (connection) socket
|
|
|
|
|
* @SOCK_DGRAM: datagram (conn.less) socket
|
|
|
|
|
* @SOCK_RAW: raw socket
|
|
|
|
|
* @SOCK_RDM: reliably-delivered message
|
|
|
|
|
* @SOCK_SEQPACKET: sequential packet socket
|
2005-11-07 17:01:05 +08:00
|
|
|
* @SOCK_DCCP: Datagram Congestion Control Protocol socket
|
2005-05-01 23:59:25 +08:00
|
|
|
* @SOCK_PACKET: linux specific way of getting packets at the dev level.
|
|
|
|
|
* For writing rarp and other similar things on the user level.
|
|
|
|
|
*
|
2005-04-17 06:20:36 +08:00
|
|
|
* When adding some new socket type please
|
|
|
|
|
* grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS
|
|
|
|
|
* overrides this enum for binary compat reasons.
|
|
|
|
|
*/
|
|
|
|
|
enum sock_type {
|
|
|
|
|
SOCK_STREAM = 1,
|
|
|
|
|
SOCK_DGRAM = 2,
|
|
|
|
|
SOCK_RAW = 3,
|
|
|
|
|
SOCK_RDM = 4,
|
|
|
|
|
SOCK_SEQPACKET = 5,
|
2005-08-10 11:14:34 +08:00
|
|
|
SOCK_DCCP = 6,
|
2005-04-17 06:20:36 +08:00
|
|
|
SOCK_PACKET = 10,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define SOCK_MAX (SOCK_PACKET + 1)
|
flag parameters: socket and socketpair
This patch adds support for flag values which are ORed to the type passwd
to socket and socketpair. The additional code is minimal. The flag
values in this implementation can and must match the O_* flags. This
avoids overhead in the conversion.
The internal functions sock_alloc_fd and sock_map_fd get a new parameters
and all callers are changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#define PORT 57392
/* For Linux these must be the same. */
#define SOCK_CLOEXEC O_CLOEXEC
int
main (void)
{
int fd;
fd = socket (PF_INET, SOCK_STREAM, 0);
if (fd == -1)
{
puts ("socket(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("socket(0) set close-on-exec flag");
return 1;
}
close (fd);
fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0);
if (fd == -1)
{
puts ("socket(SOCK_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (fd);
int fds[2];
if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1)
{
puts ("socketpair(0) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
coe = fcntl (fds[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1)
{
puts ("socketpair(SOCK_CLOEXEC) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
coe = fcntl (fds[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
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: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:17 +08:00
|
|
|
/* Mask which covers at least up to SOCK_MASK-1. The
|
|
|
|
|
* remaining bits are used as flags. */
|
|
|
|
|
#define SOCK_TYPE_MASK 0xf
|
|
|
|
|
|
|
|
|
|
/* Flags for socket, socketpair, paccept */
|
|
|
|
|
#define SOCK_CLOEXEC O_CLOEXEC
|
2008-07-24 12:29:21 +08:00
|
|
|
#ifndef SOCK_NONBLOCK
|
|
|
|
|
#define SOCK_NONBLOCK O_NONBLOCK
|
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#endif /* ARCH_HAS_SOCKET_TYPES */
|
|
|
|
|
|
2007-11-13 10:10:39 +08:00
|
|
|
enum sock_shutdown_cmd {
|
|
|
|
|
SHUT_RD = 0,
|
|
|
|
|
SHUT_WR = 1,
|
|
|
|
|
SHUT_RDWR = 2,
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
|
* struct socket - general BSD socket
|
2005-05-01 23:59:25 +08:00
|
|
|
* @state: socket state (%SS_CONNECTED, etc)
|
2008-07-08 18:03:01 +08:00
|
|
|
* @type: socket type (%SOCK_STREAM, etc)
|
2005-05-01 23:59:25 +08:00
|
|
|
* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
|
|
|
|
|
* @ops: protocol specific socket operations
|
|
|
|
|
* @fasync_list: Asynchronous wake up list
|
|
|
|
|
* @file: File back pointer for gc
|
|
|
|
|
* @sk: internal networking protocol agnostic socket representation
|
|
|
|
|
* @wait: wait queue for several uses
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
struct socket {
|
|
|
|
|
socket_state state;
|
2008-07-08 18:03:01 +08:00
|
|
|
short type;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long flags;
|
2005-12-23 04:49:22 +08:00
|
|
|
const struct proto_ops *ops;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct fasync_struct *fasync_list;
|
|
|
|
|
struct file *file;
|
|
|
|
|
struct sock *sk;
|
|
|
|
|
wait_queue_head_t wait;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct vm_area_struct;
|
|
|
|
|
struct page;
|
|
|
|
|
struct kiocb;
|
|
|
|
|
struct sockaddr;
|
|
|
|
|
struct msghdr;
|
|
|
|
|
struct module;
|
|
|
|
|
|
|
|
|
|
struct proto_ops {
|
|
|
|
|
int family;
|
|
|
|
|
struct module *owner;
|
|
|
|
|
int (*release) (struct socket *sock);
|
|
|
|
|
int (*bind) (struct socket *sock,
|
|
|
|
|
struct sockaddr *myaddr,
|
|
|
|
|
int sockaddr_len);
|
|
|
|
|
int (*connect) (struct socket *sock,
|
|
|
|
|
struct sockaddr *vaddr,
|
|
|
|
|
int sockaddr_len, int flags);
|
|
|
|
|
int (*socketpair)(struct socket *sock1,
|
|
|
|
|
struct socket *sock2);
|
|
|
|
|
int (*accept) (struct socket *sock,
|
|
|
|
|
struct socket *newsock, int flags);
|
|
|
|
|
int (*getname) (struct socket *sock,
|
|
|
|
|
struct sockaddr *addr,
|
|
|
|
|
int *sockaddr_len, int peer);
|
|
|
|
|
unsigned int (*poll) (struct file *file, struct socket *sock,
|
|
|
|
|
struct poll_table_struct *wait);
|
|
|
|
|
int (*ioctl) (struct socket *sock, unsigned int cmd,
|
|
|
|
|
unsigned long arg);
|
2006-03-22 15:58:08 +08:00
|
|
|
int (*compat_ioctl) (struct socket *sock, unsigned int cmd,
|
|
|
|
|
unsigned long arg);
|
2005-04-17 06:20:36 +08:00
|
|
|
int (*listen) (struct socket *sock, int len);
|
|
|
|
|
int (*shutdown) (struct socket *sock, int flags);
|
|
|
|
|
int (*setsockopt)(struct socket *sock, int level,
|
|
|
|
|
int optname, char __user *optval, int optlen);
|
|
|
|
|
int (*getsockopt)(struct socket *sock, int level,
|
|
|
|
|
int optname, char __user *optval, int __user *optlen);
|
2006-03-21 14:45:21 +08:00
|
|
|
int (*compat_setsockopt)(struct socket *sock, int level,
|
|
|
|
|
int optname, char __user *optval, int optlen);
|
|
|
|
|
int (*compat_getsockopt)(struct socket *sock, int level,
|
|
|
|
|
int optname, char __user *optval, int __user *optlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
int (*sendmsg) (struct kiocb *iocb, struct socket *sock,
|
|
|
|
|
struct msghdr *m, size_t total_len);
|
|
|
|
|
int (*recvmsg) (struct kiocb *iocb, struct socket *sock,
|
|
|
|
|
struct msghdr *m, size_t total_len,
|
|
|
|
|
int flags);
|
|
|
|
|
int (*mmap) (struct file *file, struct socket *sock,
|
|
|
|
|
struct vm_area_struct * vma);
|
|
|
|
|
ssize_t (*sendpage) (struct socket *sock, struct page *page,
|
|
|
|
|
int offset, size_t size, int flags);
|
2007-11-07 15:30:13 +08:00
|
|
|
ssize_t (*splice_read)(struct socket *sock, loff_t *ppos,
|
|
|
|
|
struct pipe_inode_info *pipe, size_t len, unsigned int flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct net_proto_family {
|
|
|
|
|
int family;
|
2007-10-09 14:24:22 +08:00
|
|
|
int (*create)(struct net *net, struct socket *sock, int protocol);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct module *owner;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct iovec;
|
|
|
|
|
struct kvec;
|
|
|
|
|
|
2007-11-26 20:10:50 +08:00
|
|
|
enum {
|
|
|
|
|
SOCK_WAKE_IO,
|
|
|
|
|
SOCK_WAKE_WAITD,
|
|
|
|
|
SOCK_WAKE_SPACE,
|
|
|
|
|
SOCK_WAKE_URG,
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int sock_wake_async(struct socket *sk, int how, int band);
|
2006-08-10 12:03:17 +08:00
|
|
|
extern int sock_register(const struct net_proto_family *fam);
|
|
|
|
|
extern void sock_unregister(int family);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int sock_create(int family, int type, int proto,
|
|
|
|
|
struct socket **res);
|
|
|
|
|
extern int sock_create_kern(int family, int type, int proto,
|
|
|
|
|
struct socket **res);
|
|
|
|
|
extern int sock_create_lite(int family, int type, int proto,
|
|
|
|
|
struct socket **res);
|
|
|
|
|
extern void sock_release(struct socket *sock);
|
|
|
|
|
extern int sock_sendmsg(struct socket *sock, struct msghdr *msg,
|
|
|
|
|
size_t len);
|
|
|
|
|
extern int sock_recvmsg(struct socket *sock, struct msghdr *msg,
|
|
|
|
|
size_t size, int flags);
|
flag parameters: socket and socketpair
This patch adds support for flag values which are ORed to the type passwd
to socket and socketpair. The additional code is minimal. The flag
values in this implementation can and must match the O_* flags. This
avoids overhead in the conversion.
The internal functions sock_alloc_fd and sock_map_fd get a new parameters
and all callers are changed.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>
#define PORT 57392
/* For Linux these must be the same. */
#define SOCK_CLOEXEC O_CLOEXEC
int
main (void)
{
int fd;
fd = socket (PF_INET, SOCK_STREAM, 0);
if (fd == -1)
{
puts ("socket(0) failed");
return 1;
}
int coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
puts ("socket(0) set close-on-exec flag");
return 1;
}
close (fd);
fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0);
if (fd == -1)
{
puts ("socket(SOCK_CLOEXEC) failed");
return 1;
}
coe = fcntl (fd, F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag");
return 1;
}
close (fd);
int fds[2];
if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1)
{
puts ("socketpair(0) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
coe = fcntl (fds[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if (coe & FD_CLOEXEC)
{
printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1)
{
puts ("socketpair(SOCK_CLOEXEC) failed");
return 1;
}
for (int i = 0; i < 2; ++i)
{
coe = fcntl (fds[i], F_GETFD);
if (coe == -1)
{
puts ("fcntl failed");
return 1;
}
if ((coe & FD_CLOEXEC) == 0)
{
printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i);
return 1;
}
close (fds[i]);
}
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: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:17 +08:00
|
|
|
extern int sock_map_fd(struct socket *sock, int flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern struct socket *sockfd_lookup(int fd, int *err);
|
|
|
|
|
#define sockfd_put(sock) fput(sock->file)
|
|
|
|
|
extern int net_ratelimit(void);
|
flag parameters: paccept
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>
2008-07-24 12:29:20 +08:00
|
|
|
extern long do_accept(int fd, struct sockaddr __user *upeer_sockaddr,
|
|
|
|
|
int __user *upeer_addrlen, int flags);
|
2006-10-17 15:09:42 +08:00
|
|
|
|
|
|
|
|
#define net_random() random32()
|
2006-11-15 13:12:29 +08:00
|
|
|
#define net_srandom(seed) srandom32((__force u32)seed)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
|
|
|
|
|
struct kvec *vec, size_t num, size_t len);
|
|
|
|
|
extern int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
|
|
|
|
|
struct kvec *vec, size_t num,
|
|
|
|
|
size_t len, int flags);
|
|
|
|
|
|
2006-08-08 11:57:31 +08:00
|
|
|
extern int kernel_bind(struct socket *sock, struct sockaddr *addr,
|
|
|
|
|
int addrlen);
|
|
|
|
|
extern int kernel_listen(struct socket *sock, int backlog);
|
|
|
|
|
extern int kernel_accept(struct socket *sock, struct socket **newsock,
|
|
|
|
|
int flags);
|
|
|
|
|
extern int kernel_connect(struct socket *sock, struct sockaddr *addr,
|
|
|
|
|
int addrlen, int flags);
|
|
|
|
|
extern int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
|
|
|
|
|
int *addrlen);
|
|
|
|
|
extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
|
|
|
|
|
int *addrlen);
|
|
|
|
|
extern int kernel_getsockopt(struct socket *sock, int level, int optname,
|
|
|
|
|
char *optval, int *optlen);
|
|
|
|
|
extern int kernel_setsockopt(struct socket *sock, int level, int optname,
|
|
|
|
|
char *optval, int optlen);
|
|
|
|
|
extern int kernel_sendpage(struct socket *sock, struct page *page, int offset,
|
|
|
|
|
size_t size, int flags);
|
|
|
|
|
extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
|
2007-11-13 10:10:39 +08:00
|
|
|
extern int kernel_sock_shutdown(struct socket *sock,
|
|
|
|
|
enum sock_shutdown_cmd how);
|
2006-08-08 11:57:31 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef CONFIG_SMP
|
|
|
|
|
#define SOCKOPS_WRAPPED(name) name
|
|
|
|
|
#define SOCKOPS_WRAP(name, fam)
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
|
|
#define SOCKOPS_WRAPPED(name) __unlocked_##name
|
|
|
|
|
|
|
|
|
|
#define SOCKCALL_WRAP(name, call, parms, args) \
|
|
|
|
|
static int __lock_##name##_##call parms \
|
|
|
|
|
{ \
|
|
|
|
|
int ret; \
|
|
|
|
|
lock_kernel(); \
|
|
|
|
|
ret = __unlocked_##name##_ops.call args ;\
|
|
|
|
|
unlock_kernel(); \
|
|
|
|
|
return ret; \
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define SOCKCALL_UWRAP(name, call, parms, args) \
|
|
|
|
|
static unsigned int __lock_##name##_##call parms \
|
|
|
|
|
{ \
|
|
|
|
|
int ret; \
|
|
|
|
|
lock_kernel(); \
|
|
|
|
|
ret = __unlocked_##name##_ops.call args ;\
|
|
|
|
|
unlock_kernel(); \
|
|
|
|
|
return ret; \
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#define SOCKOPS_WRAP(name, fam) \
|
|
|
|
|
SOCKCALL_WRAP(name, release, (struct socket *sock), (sock)) \
|
|
|
|
|
SOCKCALL_WRAP(name, bind, (struct socket *sock, struct sockaddr *uaddr, int addr_len), \
|
|
|
|
|
(sock, uaddr, addr_len)) \
|
|
|
|
|
SOCKCALL_WRAP(name, connect, (struct socket *sock, struct sockaddr * uaddr, \
|
|
|
|
|
int addr_len, int flags), \
|
|
|
|
|
(sock, uaddr, addr_len, flags)) \
|
|
|
|
|
SOCKCALL_WRAP(name, socketpair, (struct socket *sock1, struct socket *sock2), \
|
|
|
|
|
(sock1, sock2)) \
|
|
|
|
|
SOCKCALL_WRAP(name, accept, (struct socket *sock, struct socket *newsock, \
|
|
|
|
|
int flags), (sock, newsock, flags)) \
|
|
|
|
|
SOCKCALL_WRAP(name, getname, (struct socket *sock, struct sockaddr *uaddr, \
|
|
|
|
|
int *addr_len, int peer), (sock, uaddr, addr_len, peer)) \
|
|
|
|
|
SOCKCALL_UWRAP(name, poll, (struct file *file, struct socket *sock, struct poll_table_struct *wait), \
|
|
|
|
|
(file, sock, wait)) \
|
|
|
|
|
SOCKCALL_WRAP(name, ioctl, (struct socket *sock, unsigned int cmd, \
|
|
|
|
|
unsigned long arg), (sock, cmd, arg)) \
|
2006-03-22 15:58:08 +08:00
|
|
|
SOCKCALL_WRAP(name, compat_ioctl, (struct socket *sock, unsigned int cmd, \
|
|
|
|
|
unsigned long arg), (sock, cmd, arg)) \
|
2005-04-17 06:20:36 +08:00
|
|
|
SOCKCALL_WRAP(name, listen, (struct socket *sock, int len), (sock, len)) \
|
|
|
|
|
SOCKCALL_WRAP(name, shutdown, (struct socket *sock, int flags), (sock, flags)) \
|
|
|
|
|
SOCKCALL_WRAP(name, setsockopt, (struct socket *sock, int level, int optname, \
|
|
|
|
|
char __user *optval, int optlen), (sock, level, optname, optval, optlen)) \
|
|
|
|
|
SOCKCALL_WRAP(name, getsockopt, (struct socket *sock, int level, int optname, \
|
|
|
|
|
char __user *optval, int __user *optlen), (sock, level, optname, optval, optlen)) \
|
|
|
|
|
SOCKCALL_WRAP(name, sendmsg, (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len), \
|
|
|
|
|
(iocb, sock, m, len)) \
|
|
|
|
|
SOCKCALL_WRAP(name, recvmsg, (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len, int flags), \
|
|
|
|
|
(iocb, sock, m, len, flags)) \
|
|
|
|
|
SOCKCALL_WRAP(name, mmap, (struct file *file, struct socket *sock, struct vm_area_struct *vma), \
|
|
|
|
|
(file, sock, vma)) \
|
|
|
|
|
\
|
2005-12-23 04:49:22 +08:00
|
|
|
static const struct proto_ops name##_ops = { \
|
2005-04-17 06:20:36 +08:00
|
|
|
.family = fam, \
|
|
|
|
|
.owner = THIS_MODULE, \
|
|
|
|
|
.release = __lock_##name##_release, \
|
|
|
|
|
.bind = __lock_##name##_bind, \
|
|
|
|
|
.connect = __lock_##name##_connect, \
|
|
|
|
|
.socketpair = __lock_##name##_socketpair, \
|
|
|
|
|
.accept = __lock_##name##_accept, \
|
|
|
|
|
.getname = __lock_##name##_getname, \
|
|
|
|
|
.poll = __lock_##name##_poll, \
|
|
|
|
|
.ioctl = __lock_##name##_ioctl, \
|
2006-03-22 15:58:08 +08:00
|
|
|
.compat_ioctl = __lock_##name##_compat_ioctl, \
|
2005-04-17 06:20:36 +08:00
|
|
|
.listen = __lock_##name##_listen, \
|
|
|
|
|
.shutdown = __lock_##name##_shutdown, \
|
|
|
|
|
.setsockopt = __lock_##name##_setsockopt, \
|
|
|
|
|
.getsockopt = __lock_##name##_getsockopt, \
|
|
|
|
|
.sendmsg = __lock_##name##_sendmsg, \
|
|
|
|
|
.recvmsg = __lock_##name##_recvmsg, \
|
|
|
|
|
.mmap = __lock_##name##_mmap, \
|
|
|
|
|
};
|
2006-03-22 15:58:08 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#define MODULE_ALIAS_NETPROTO(proto) \
|
|
|
|
|
MODULE_ALIAS("net-pf-" __stringify(proto))
|
|
|
|
|
|
2005-08-10 10:40:55 +08:00
|
|
|
#define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \
|
|
|
|
|
MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto))
|
|
|
|
|
|
2007-10-22 07:44:04 +08:00
|
|
|
#define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \
|
|
|
|
|
MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \
|
|
|
|
|
"-type-" __stringify(type))
|
|
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
|
#include <linux/sysctl.h>
|
2008-07-25 16:45:58 +08:00
|
|
|
extern struct ratelimit_state net_ratelimit_state;
|
2005-08-16 13:18:02 +08:00
|
|
|
#endif
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
#endif /* _LINUX_NET_H */
|
