af_inet.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

/*
 * 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 1.136 2001/11/06 22:21:08 davem Exp $
 *
 * Authors:	Ross Biro, <[e-mail]>
 *		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/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>

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

#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/brlock.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/udp.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>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif
#include <linux/if_bridge.h>
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif
#ifdef CONFIG_NET_DIVERT
#include <linux/divert.h>
#endif /* CONFIG_NET_DIVERT */
#if defined(CONFIG_NET_RADIO) || defined(CONFIG_NET_PCMCIA_RADIO)
#include <linux/wireless.h>		/* Note : will define WIRELESS_EXT */
#endif	/* CONFIG_NET_RADIO || CONFIG_NET_PCMCIA_RADIO */

struct linux_mib net_statistics[NR_CPUS*2];

#ifdef INET_REFCNT_DEBUG
atomic_t inet_sock_nr;
#endif

extern int raw_get_info(char *, char **, off_t, int);
extern int snmp_get_info(char *, char **, off_t, int);
extern int netstat_get_info(char *, char **, off_t, int);
extern int afinet_get_info(char *, char **, off_t, int);
extern int tcp_get_info(char *, char **, off_t, int);
extern int udp_get_info(char *, char **, off_t, int);
extern void ip_mc_drop_socket(struct sock *sk);

#ifdef CONFIG_DLCI
extern int dlci_ioctl(unsigned int, void*);
#endif

#ifdef CONFIG_DLCI_MODULE
int (*dlci_ioctl_hook)(unsigned int, void *);
#endif

#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
int (*br_ioctl_hook)(unsigned long);
#endif

#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
int (*vlan_ioctl_hook)(unsigned long arg);
#endif

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

/* New destruction routine */

void inet_sock_destruct(struct sock *sk)
{
	__skb_queue_purge(&sk->receive_queue);
	__skb_queue_purge(&sk->error_queue);

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

	BUG_TRAP(atomic_read(&sk->rmem_alloc) == 0);
	BUG_TRAP(atomic_read(&sk->wmem_alloc) == 0);
	BUG_TRAP(sk->wmem_queued == 0);
	BUG_TRAP(sk->forward_alloc == 0);

	if (sk->protinfo.af_inet.opt)
		kfree(sk->protinfo.af_inet.opt);
	dst_release(sk->dst_cache);
#ifdef INET_REFCNT_DEBUG
	atomic_dec(&inet_sock_nr);
	printk(KERN_DEBUG "INET socket %p released, %d are still alive\n", sk, atomic_read(&inet_sock_nr));
#endif
}

void inet_sock_release(struct sock *sk)
{
	if (sk->prot->destroy)
		sk->prot->destroy(sk);

	/* Observation: when inet_sock_release is called, processes have
	 * no access to socket. But net still has.
	 * Step one, detach it from networking:
	 *
	 * A. Remove from hash tables.
	 */

	sk->prot->unhash(sk);

	/* In this point socket cannot receive new packets,
	 * but it is possible that some packets are in flight
	 * because some CPU runs receiver and did hash table lookup
	 * before we unhashed socket. They will achieve receive queue
	 * and will be purged by socket destructor.
	 *
	 * Also we still have packets pending on receive
	 * queue and probably, our own packets waiting in device queues.
	 * sock_destroy will drain receive queue, but transmitted
	 * packets will delay socket destruction until the last reference
	 * will be released.
	 */

	sock_orphan(sk);

#ifdef INET_REFCNT_DEBUG
	if (atomic_read(&sk->refcnt) != 1) {
		printk(KERN_DEBUG "Destruction inet %p delayed, c=%d\n", sk, atomic_read(&sk->refcnt));
	}
#endif
	sock_put(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.
 */
 

/*
 *	Set socket options on an inet socket.
 */
 
int inet_setsockopt(struct socket *sock, int level, int optname,
		    char *optval, int optlen)
{
	struct sock *sk=sock->sk;

	return sk->prot->setsockopt(sk,level,optname,optval,optlen);
}

/*
 *	Get a socket option on an AF_INET socket.
 *
 *	FIX: POSIX 1003.1g is very ambiguous here. It states that
 *	asynchronous errors should be reported by getsockopt. We assume
 *	this means if you specify SO_ERROR (otherwise whats the point of it).
 */

int inet_getsockopt(struct socket *sock, int level, int optname,
		    char *optval, int *optlen)
{
	struct sock *sk=sock->sk;

	return sk->prot->getsockopt(sk,level,optname,optval,optlen);
}

/*
 *	Automatically bind an unbound socket.
 */

static int inet_autobind(struct sock *sk)
{
	/* We may need to bind the socket. */
	lock_sock(sk);
	if (sk->num == 0) {
		if (sk->prot->get_port(sk, 0) != 0) {
			release_sock(sk);
			return -EAGAIN;
		}
		sk->sport = htons(sk->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->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 = tcp_listen_start(sk);
		if (err)
			goto out;
	}
	sk->max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}

/*
 *	Create an inet socket.
 */

static int inet_create(struct socket *sock, int protocol)
{
	struct sock *sk;
        struct list_head *p;
        struct inet_protosw *answer;

	sock->state = SS_UNCONNECTED;
	sk = sk_alloc(PF_INET, GFP_KERNEL, 1);
	if (sk == NULL) 
		goto do_oom;
  
	/* Look for the requested type/protocol pair. */
	answer = NULL;
	br_read_lock_bh(BR_NETPROTO_LOCK);
	list_for_each(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;
		}
		answer = NULL;
	}
	br_read_unlock_bh(BR_NETPROTO_LOCK);

	if (!answer)
		goto free_and_badtype;
	if (answer->capability > 0 && !capable(answer->capability))
		goto free_and_badperm;
	if (!protocol)
		goto free_and_noproto;

	sock->ops = answer->ops;
	sk->prot = answer->prot;
	sk->no_check = answer->no_check;
	if (INET_PROTOSW_REUSE & answer->flags)
		sk->reuse = 1;

	if (SOCK_RAW == sock->type) {
		sk->num = protocol;
		if (IPPROTO_RAW == protocol)
			sk->protinfo.af_inet.hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		sk->protinfo.af_inet.pmtudisc = IP_PMTUDISC_DONT;
	else
		sk->protinfo.af_inet.pmtudisc = IP_PMTUDISC_WANT;

	sk->protinfo.af_inet.id = 0;

	sock_init_data(sock,sk);

	sk->destruct = inet_sock_destruct;

	sk->zapped	= 0;
	sk->family	= PF_INET;
	sk->protocol	= protocol;

	sk->backlog_rcv = sk->prot->backlog_rcv;

	sk->protinfo.af_inet.ttl	= sysctl_ip_default_ttl;

	sk->protinfo.af_inet.mc_loop	= 1;
	sk->protinfo.af_inet.mc_ttl	= 1;
	sk->protinfo.af_inet.mc_index	= 0;
	sk->protinfo.af_inet.mc_list	= NULL;

#ifdef INET_REFCNT_DEBUG
	atomic_inc(&inet_sock_nr);
#endif

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

		/* Add to protocol hash chains. */
		sk->prot->hash(sk);
	}

	if (sk->prot->init) {
		int err = sk->prot->init(sk);
		if (err != 0) {
			inet_sock_release(sk);
			return err;
		}
	}
	return 0;

free_and_badtype:
	sk_free(sk);
	return -ESOCKTNOSUPPORT;

free_and_badperm:
	sk_free(sk);
	return -EPERM;

free_and_noproto:
	sk_free(sk);
	return -EPROTONOSUPPORT;

do_oom:
	return -ENOBUFS;
}


/*
 *	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 (sk->linger && !(current->flags & PF_EXITING))
			timeout = sk->lingertime;
		sock->sk = NULL;
		sk->prot->close(sk, timeout);
	}
	return(0);
}

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

static 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;
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if(sk->prot->bind)
		return sk->prot->bind(sk, uaddr, addr_len);

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	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)
	 */
	if (sysctl_ip_nonlocal_bind == 0 && 
	    sk->protinfo.af_inet.freebind == 0 &&
	    addr->sin_addr.s_addr != INADDR_ANY &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		return -EADDRNOTAVAIL;

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

	/*      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->state != TCP_CLOSE)			||
	    (sk->num != 0))
		goto out;

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

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

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

int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
		       int addr_len, int flags)
{
	struct sock *sk=sock->sk;

	if (uaddr->sa_family == AF_UNSPEC)
		return sk->prot->disconnect(sk, flags);

	if (sk->num==0 && inet_autobind(sk) != 0)
		return -EAGAIN;
	return sk->prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DECLARE_WAITQUEUE(wait, current);

	__set_current_state(TASK_INTERRUPTIBLE);
	add_wait_queue(sk->sleep, &wait);

	/* Basic assumption: if someone sets sk->err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1<<sk->state)&(TCPF_SYN_SENT|TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	remove_wait_queue(sk->sleep, &wait);
	return timeo;
}

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
 
int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr,
			int addr_len, int flags)
{
	struct sock *sk=sock->sk;
	int err;
	long timeo;

	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->prot->disconnect(sk, flags);