af_inet.c

linux 内核源代码

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		PF_INET protocol family socket handler.
 *
 * Version:	$Id: af_inet.c,v 1.137 2002/02/01 22:01:03 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Florian La Roche, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *
 * Changes (see also sock.c)
 *
 *		piggy,
 *		Karl Knutson	:	Socket protocol table
 *		A.N.Kuznetsov	:	Socket death error in accept().
 *		John Richardson :	Fix non blocking error in connect()
 *					so sockets that fail to connect
 *					don't return -EINPROGRESS.
 *		Alan Cox	:	Asynchronous I/O support
 *		Alan Cox	:	Keep correct socket pointer on sock
 *					structures
 *					when accept() ed
 *		Alan Cox	:	Semantics of SO_LINGER aren't state
 *					moved to close when you look carefully.
 *					With this fixed and the accept bug fixed
 *					some RPC stuff seems happier.
 *		Niibe Yutaka	:	4.4BSD style write async I/O
 *		Alan Cox,
 *		Tony Gale 	:	Fixed reuse semantics.
 *		Alan Cox	:	bind() shouldn't abort existing but dead
 *					sockets. Stops FTP netin:.. I hope.
 *		Alan Cox	:	bind() works correctly for RAW sockets.
 *					Note that FreeBSD at least was broken
 *					in this respect so be careful with
 *					compatibility tests...
 *		Alan Cox	:	routing cache support
 *		Alan Cox	:	memzero the socket structure for
 *					compactness.
 *		Matt Day	:	nonblock connect error handler
 *		Alan Cox	:	Allow large numbers of pending sockets
 *					(eg for big web sites), but only if
 *					specifically application requested.
 *		Alan Cox	:	New buffering throughout IP. Used
 *					dumbly.
 *		Alan Cox	:	New buffering now used smartly.
 *		Alan Cox	:	BSD rather than common sense
 *					interpretation of listen.
 *		Germano Caronni	:	Assorted small races.
 *		Alan Cox	:	sendmsg/recvmsg basic support.
 *		Alan Cox	:	Only sendmsg/recvmsg now supported.
 *		Alan Cox	:	Locked down bind (see security list).
 *		Alan Cox	:	Loosened bind a little.
 *		Mike McLagan	:	ADD/DEL DLCI Ioctls
 *	Willy Konynenberg	:	Transparent proxying support.
 *		David S. Miller	:	New socket lookup architecture.
 *					Some other random speedups.
 *		Cyrus Durgin	:	Cleaned up file for kmod hacks.
 *		Andi Kleen	:	Fix inet_stream_connect TCP race.
 *
 *		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.
 */

#include <linux/err.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>

#include <asm/uaccess.h>
#include <asm/system.h>

#include <linux/inet.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/inet_connection_sock.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif

DEFINE_SNMP_STAT(struct linux_mib, net_statistics) __read_mostly;

extern void ip_mc_drop_socket(struct sock *sk);

/* The inetsw table contains everything that inet_create needs to
 * build a new socket.
 */
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);

/* New destruction routine */

void inet_sock_destruct(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_error_queue);

	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
		printk("Attempt to release TCP socket in state %d %p\n",
		       sk->sk_state, sk);
		return;
	}
	if (!sock_flag(sk, SOCK_DEAD)) {
		printk("Attempt to release alive inet socket %p\n", sk);
		return;
	}

	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
	BUG_TRAP(!sk->sk_wmem_queued);
	BUG_TRAP(!sk->sk_forward_alloc);

	kfree(inet->opt);
	dst_release(sk->sk_dst_cache);
	sk_refcnt_debug_dec(sk);
}

/*
 *	The routines beyond this point handle the behaviour of an AF_INET
 *	socket object. Mostly it punts to the subprotocols of IP to do
 *	the work.
 */

/*
 *	Automatically bind an unbound socket.
 */

static int inet_autobind(struct sock *sk)
{
	struct inet_sock *inet;
	/* We may need to bind the socket. */
	lock_sock(sk);
	inet = inet_sk(sk);
	if (!inet->num) {
		if (sk->sk_prot->get_port(sk, 0)) {
			release_sock(sk);
			return -EAGAIN;
		}
		inet->sport = htons(inet->num);
	}
	release_sock(sk);
	return 0;
}

/*
 *	Move a socket into listening state.
 */
int inet_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	unsigned char old_state;
	int err;

	lock_sock(sk);

	err = -EINVAL;
	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
		goto out;

	old_state = sk->sk_state;
	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
		goto out;

	/* Really, if the socket is already in listen state
	 * we can only allow the backlog to be adjusted.
	 */
	if (old_state != TCP_LISTEN) {
		err = inet_csk_listen_start(sk, backlog);
		if (err)
			goto out;
	}
	sk->sk_max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}

u32 inet_ehash_secret __read_mostly;
EXPORT_SYMBOL(inet_ehash_secret);

/*
 * inet_ehash_secret must be set exactly once
 * Instead of using a dedicated spinlock, we (ab)use inetsw_lock
 */
void build_ehash_secret(void)
{
	u32 rnd;
	do {
		get_random_bytes(&rnd, sizeof(rnd));
	} while (rnd == 0);
	spin_lock_bh(&inetsw_lock);
	if (!inet_ehash_secret)
		inet_ehash_secret = rnd;
	spin_unlock_bh(&inetsw_lock);
}
EXPORT_SYMBOL(build_ehash_secret);

/*
 *	Create an inet socket.
 */

static int inet_create(struct net *net, struct socket *sock, int protocol)
{
	struct sock *sk;
	struct list_head *p;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
	int try_loading_module = 0;
	int err;

	if (net != &init_net)
		return -EAFNOSUPPORT;

	if (sock->type != SOCK_RAW &&
	    sock->type != SOCK_DGRAM &&
	    !inet_ehash_secret)
		build_ehash_secret();

	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
	answer = NULL;
lookup_protocol:
	err = -ESOCKTNOSUPPORT;
	rcu_read_lock();
	list_for_each_rcu(p, &inetsw[sock->type]) {
		answer = list_entry(p, struct inet_protosw, list);

		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
		err = -EPROTONOSUPPORT;
		answer = NULL;
	}

	if (unlikely(answer == NULL)) {
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

	err = -EPERM;
	if (answer->capability > 0 && !capable(answer->capability))
		goto out_rcu_unlock;

	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

	BUG_TRAP(answer_prot->slab != NULL);

	err = -ENOBUFS;
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
	if (sk == NULL)
		goto out;

	err = 0;
	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = 1;

	inet = inet_sk(sk);
	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

	if (SOCK_RAW == sock->type) {
		inet->num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->id = 0;

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_family	   = PF_INET;
	sk->sk_protocol	   = protocol;
	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
	inet->mc_index	= 0;
	inet->mc_list	= NULL;

	sk_refcnt_debug_inc(sk);

	if (inet->num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->sport = htons(inet->num);
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {
		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}


/*
 *	The peer socket should always be NULL (or else). When we call this
 *	function we are destroying the object and from then on nobody
 *	should refer to it.
 */
int inet_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (sk) {
		long timeout;

		/* Applications forget to leave groups before exiting */
		ip_mc_drop_socket(sk);

		/* If linger is set, we don't return until the close
		 * is complete.  Otherwise we return immediately. The
		 * actually closing is done the same either way.
		 *
		 * If the close is due to the process exiting, we never
		 * linger..
		 */
		timeout = 0;
		if (sock_flag(sk, SOCK_LINGER) &&
		    !(current->flags & PF_EXITING))
			timeout = sk->sk_lingertime;
		sock->sk = NULL;
		sk->sk_prot->close(sk, timeout);
	}
	return 0;
}

/* It is off by default, see below. */
int sysctl_ip_nonlocal_bind __read_mostly;

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
	    !inet->freebind &&
	    addr->sin_addr.s_addr != INADDR_ANY &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	err = -EACCES;
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->num)
		goto out_release_sock;

	inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->saddr = 0;  /* Use device */

	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
		inet->saddr = inet->rcv_saddr = 0;
		err = -EADDRINUSE;
		goto out_release_sock;
	}

	if (inet->rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->sport = htons(inet->num);
	inet->daddr = 0;
	inet->dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}

int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
		       int addr_len, int flags)