af_inet6.c

Linux Kernel 2.6.9 for OMAP1710

/*
 *	PF_INET6 socket protocol family
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>	
 *
 *	Adapted from linux/net/ipv4/af_inet.c
 *
 *	$Id: af_inet6.c,v 1.66 2002/02/01 22:01:04 davem Exp $
 *
 * 	Fixes:
 *	piggy, Karl Knutson	:	Socket protocol table
 * 	Hideaki YOSHIFUJI	:	sin6_scope_id support
 * 	Arnaldo Melo		: 	check proc_net_create return, cleanups
 *
 *	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/module.h>
#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/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>
#include <linux/smp_lock.h>

#include <net/ip.h>
#include <net/ipv6.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/ipip.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#ifdef CONFIG_IPV6_TUNNEL
#include <net/ip6_tunnel.h>
#endif

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

MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");

/* IPv6 procfs goodies... */

#ifdef CONFIG_PROC_FS
extern int raw6_proc_init(void);
extern void raw6_proc_exit(void);
extern int tcp6_proc_init(void);
extern void tcp6_proc_exit(void);
extern int udp6_proc_init(void);
extern void udp6_proc_exit(void);
extern int ipv6_misc_proc_init(void);
extern void ipv6_misc_proc_exit(void);
extern int ac6_proc_init(void);
extern void ac6_proc_exit(void);
extern int if6_proc_init(void);
extern void if6_proc_exit(void);
#endif

int sysctl_ipv6_bindv6only;

#ifdef INET_REFCNT_DEBUG
atomic_t inet6_sock_nr;
#endif

/* The inetsw table contains everything that inet_create needs to
 * build a new socket.
 */
static struct list_head inetsw6[SOCK_MAX];
static spinlock_t inetsw6_lock = SPIN_LOCK_UNLOCKED;

static void inet6_sock_destruct(struct sock *sk)
{
	inet_sock_destruct(sk);

#ifdef INET_REFCNT_DEBUG
	atomic_dec(&inet6_sock_nr);
#endif
}

static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
	const int offset = sk->sk_prot->slab_obj_size - sizeof(struct ipv6_pinfo);

	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}

static int inet6_create(struct socket *sock, int protocol)
{
	struct inet_opt *inet;
	struct ipv6_pinfo *np;
	struct sock *sk;
	struct tcp6_sock* tcp6sk;
	struct list_head *p;
	struct inet_protosw *answer;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
	int rc;

	/* Look for the requested type/protocol pair. */
	answer = NULL;
	rcu_read_lock();
	list_for_each_rcu(p, &inetsw6[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;
	}

	rc = -ESOCKTNOSUPPORT;
	if (!answer)
		goto out_rcu_unlock;
	rc = -EPERM;
	if (answer->capability > 0 && !capable(answer->capability))
		goto out_rcu_unlock;
	rc = -EPROTONOSUPPORT;
	if (!protocol)
		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);

	rc = -ENOBUFS;
	sk = sk_alloc(PF_INET6, GFP_KERNEL,
		      answer_prot->slab_obj_size,
		      answer_prot->slab);
	if (sk == NULL)
		goto out;

	sock_init_data(sock, sk);
	sk_set_owner(sk, THIS_MODULE);

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

	inet = inet_sk(sk);

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

	sk->sk_destruct		= inet6_sock_destruct;
	sk->sk_family		= PF_INET6;
	sk->sk_protocol		= protocol;

	sk->sk_backlog_rcv	= answer->prot->backlog_rcv;

	tcp6sk		= (struct tcp6_sock *)sk;
	tcp6sk->pinet6 = np = inet6_sk_generic(sk);
	np->hop_limit	= -1;
	np->mcast_hops	= -1;
	np->mc_loop	= 1;
	np->pmtudisc	= IPV6_PMTUDISC_WANT;
	np->ipv6only	= sysctl_ipv6_bindv6only;
	
	/* Init the ipv4 part of the socket since we can have sockets
	 * using v6 API for ipv4.
	 */
	inet->uc_ttl	= -1;

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

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


#ifdef INET_REFCNT_DEBUG
	atomic_inc(&inet6_sock_nr);
	atomic_inc(&inet_sock_nr);
#endif
	if (inet->num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically shares.
		 */
		inet->sport = ntohs(inet->num);
		sk->sk_prot->hash(sk);
	}
	if (sk->sk_prot->init) {
		rc = sk->sk_prot->init(sk);
		if (rc) {
			sk_common_release(sk);
			goto out;
		}
	}
out:
	return rc;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}


/* bind for INET6 API */
int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in6 *addr=(struct sockaddr_in6 *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_opt *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	__u32 v4addr = 0;
	unsigned short snum;
	int addr_type = 0;
	int err = 0;

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

	if (addr_len < SIN6_LEN_RFC2133)
		return -EINVAL;
	addr_type = ipv6_addr_type(&addr->sin6_addr);
	if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
		return -EINVAL;

	snum = ntohs(addr->sin6_port);
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		return -EACCES;

	lock_sock(sk);

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

	/* Check if the address belongs to the host. */
	if (addr_type == IPV6_ADDR_MAPPED) {
		v4addr = addr->sin6_addr.s6_addr32[3];
		if (inet_addr_type(v4addr) != RTN_LOCAL) {
			err = -EADDRNOTAVAIL;
			goto out;
		}
	} else {
		if (addr_type != IPV6_ADDR_ANY) {
			struct net_device *dev = NULL;

			if (addr_type & IPV6_ADDR_LINKLOCAL) {
				if (addr_len >= sizeof(struct sockaddr_in6) &&
				    addr->sin6_scope_id) {
					/* Override any existing binding, if another one
					 * is supplied by user.
					 */
					sk->sk_bound_dev_if = addr->sin6_scope_id;
				}
				
				/* Binding to link-local address requires an interface */
				if (!sk->sk_bound_dev_if) {
					err = -EINVAL;
					goto out;
				}
				dev = dev_get_by_index(sk->sk_bound_dev_if);
				if (!dev) {
					err = -ENODEV;
					goto out;
				}
			}

			/* ipv4 addr of the socket is invalid.  Only the
			 * unspecified and mapped address have a v4 equivalent.
			 */
			v4addr = LOOPBACK4_IPV6;
			if (!(addr_type & IPV6_ADDR_MULTICAST))	{
				if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) {
					if (dev)
						dev_put(dev);
					err = -EADDRNOTAVAIL;
					goto out;
				}
			}
			if (dev)
				dev_put(dev);
		}
	}

	inet->rcv_saddr = v4addr;
	inet->saddr = v4addr;

	ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
		
	if (!(addr_type & IPV6_ADDR_MULTICAST))
		ipv6_addr_copy(&np->saddr, &addr->sin6_addr);

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

	if (addr_type != IPV6_ADDR_ANY)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->sport = ntohs(inet->num);
	inet->dport = 0;
	inet->daddr = 0;
out:
	release_sock(sk);
	return err;
}

int inet6_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (sk == NULL)
		return -EINVAL;

	/* Free mc lists */
	ipv6_sock_mc_close(sk);

	/* Free ac lists */
	ipv6_sock_ac_close(sk);

	return inet_release(sock);
}

int inet6_destroy_sock(struct sock *sk)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff *skb;
	struct ipv6_txoptions *opt;

	/*
	 *	Release destination entry
	 */

	sk_dst_reset(sk);

	/* Release rx options */

	if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
		kfree_skb(skb);

	/* Free flowlabels */
	fl6_free_socklist(sk);

	/* Free tx options */

	if ((opt = xchg(&np->opt, NULL)) != NULL)
		sock_kfree_s(sk, opt, opt->tot_len);

	return 0;
}

/*
 *	This does both peername and sockname.
 */
 
int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
		 int *uaddr_len, int peer)
{
	struct sockaddr_in6 *sin=(struct sockaddr_in6 *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_opt *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
  
	sin->sin6_family = AF_INET6;
	sin->sin6_flowinfo = 0;
	sin->sin6_scope_id = 0;
	if (peer) {
		if (!inet->dport)
			return -ENOTCONN;
		if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		    peer == 1)