ipv6_sockglue.c

linux 内核源代码

/*
 *	IPv6 BSD socket options interface
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	Based on linux/net/ipv4/ip_sockglue.c
 *
 *	$Id: ipv6_sockglue.c,v 1.41 2002/02/01 22:01:04 davem Exp $
 *
 *	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.
 *
 *	FIXME: Make the setsockopt code POSIX compliant: That is
 *
 *	o	Return -EINVAL for setsockopt of short lengths
 *	o	Truncate getsockopt returns
 *	o	Return an optlen of the truncated length if need be
 *
 *	Changes:
 *	David L Stevens <[e-mail]>:
 *		- added multicast source filtering API for MLDv2
 */

#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>

#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <net/xfrm.h>

#include <asm/uaccess.h>

DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly;

static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb,
						    int proto)
{
	struct inet6_protocol *ops = NULL;

	for (;;) {
		struct ipv6_opt_hdr *opth;
		int len;

		if (proto != NEXTHDR_HOP) {
			ops = rcu_dereference(inet6_protos[proto]);

			if (unlikely(!ops))
				break;

			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
				break;
		}

		if (unlikely(!pskb_may_pull(skb, 8)))
			break;

		opth = (void *)skb->data;
		len = opth->hdrlen * 8 + 8;

		if (unlikely(!pskb_may_pull(skb, len)))
			break;

		proto = opth->nexthdr;
		__skb_pull(skb, len);
	}

	return ops;
}

static int ipv6_gso_send_check(struct sk_buff *skb)
{
	struct ipv6hdr *ipv6h;
	struct inet6_protocol *ops;
	int err = -EINVAL;

	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
		goto out;

	ipv6h = ipv6_hdr(skb);
	__skb_pull(skb, sizeof(*ipv6h));
	err = -EPROTONOSUPPORT;

	rcu_read_lock();
	ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
	if (likely(ops && ops->gso_send_check)) {
		skb_reset_transport_header(skb);
		err = ops->gso_send_check(skb);
	}
	rcu_read_unlock();

out:
	return err;
}

static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct ipv6hdr *ipv6h;
	struct inet6_protocol *ops;

	if (!(features & NETIF_F_V6_CSUM))
		features &= ~NETIF_F_SG;

	if (unlikely(skb_shinfo(skb)->gso_type &
		     ~(SKB_GSO_UDP |
		       SKB_GSO_DODGY |
		       SKB_GSO_TCP_ECN |
		       SKB_GSO_TCPV6 |
		       0)))
		goto out;

	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
		goto out;

	ipv6h = ipv6_hdr(skb);
	__skb_pull(skb, sizeof(*ipv6h));
	segs = ERR_PTR(-EPROTONOSUPPORT);

	rcu_read_lock();
	ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
	if (likely(ops && ops->gso_segment)) {
		skb_reset_transport_header(skb);
		segs = ops->gso_segment(skb, features);
	}
	rcu_read_unlock();

	if (unlikely(IS_ERR(segs)))
		goto out;

	for (skb = segs; skb; skb = skb->next) {
		ipv6h = ipv6_hdr(skb);
		ipv6h->payload_len = htons(skb->len - skb->mac_len -
					   sizeof(*ipv6h));
	}

out:
	return segs;
}

static struct packet_type ipv6_packet_type = {
	.type = __constant_htons(ETH_P_IPV6),
	.func = ipv6_rcv,
	.gso_send_check = ipv6_gso_send_check,
	.gso_segment = ipv6_gso_segment,
};

struct ip6_ra_chain *ip6_ra_chain;
DEFINE_RWLOCK(ip6_ra_lock);

int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *))
{
	struct ip6_ra_chain *ra, *new_ra, **rap;

	/* RA packet may be delivered ONLY to IPPROTO_RAW socket */
	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW)
		return -EINVAL;

	new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;

	write_lock_bh(&ip6_ra_lock);
	for (rap = &ip6_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
		if (ra->sk == sk) {
			if (sel>=0) {
				write_unlock_bh(&ip6_ra_lock);
				kfree(new_ra);
				return -EADDRINUSE;
			}

			*rap = ra->next;
			write_unlock_bh(&ip6_ra_lock);

			if (ra->destructor)
				ra->destructor(sk);
			sock_put(sk);
			kfree(ra);
			return 0;
		}
	}
	if (new_ra == NULL) {
		write_unlock_bh(&ip6_ra_lock);
		return -ENOBUFS;
	}
	new_ra->sk = sk;
	new_ra->sel = sel;
	new_ra->destructor = destructor;
	new_ra->next = ra;
	*rap = new_ra;
	sock_hold(sk);
	write_unlock_bh(&ip6_ra_lock);
	return 0;
}

static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int optlen)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	int val, valbool;
	int retv = -ENOPROTOOPT;

	if (optval == NULL)
		val=0;
	else if (get_user(val, (int __user *) optval))
		return -EFAULT;

	valbool = (val!=0);

	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->sk_protocol != IPPROTO_UDP &&
			    sk->sk_protocol != IPPROTO_UDPLITE &&
			    sk->sk_protocol != IPPROTO_TCP)
				break;

			if (sk->sk_state != TCP_ESTABLISHED) {
				retv = -ENOTCONN;
				break;
			}

			if (ipv6_only_sock(sk) ||
			    !ipv6_addr_v4mapped(&np->daddr)) {
				retv = -EADDRNOTAVAIL;
				break;
			}

			fl6_free_socklist(sk);
			ipv6_sock_mc_close(sk);

			/*
			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
			 * remove it from the refcnt debug socks count in the
			 * original family...
			 */
			sk_refcnt_debug_dec(sk);

			if (sk->sk_protocol == IPPROTO_TCP) {
				struct inet_connection_sock *icsk = inet_csk(sk);

				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(&tcp_prot);
				local_bh_enable();
				sk->sk_prot = &tcp_prot;
				icsk->icsk_af_ops = &ipv4_specific;
				sk->sk_socket->ops = &inet_stream_ops;
				sk->sk_family = PF_INET;
				tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
			} else {
				struct proto *prot = &udp_prot;

				if (sk->sk_protocol == IPPROTO_UDPLITE)
					prot = &udplite_prot;
				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(prot);
				local_bh_enable();
				sk->sk_prot = prot;
				sk->sk_socket->ops = &inet_dgram_ops;
				sk->sk_family = PF_INET;
			}
			opt = xchg(&np->opt, NULL);
			if (opt)
				sock_kfree_s(sk, opt, opt->tot_len);
			pktopt = xchg(&np->pktoptions, NULL);
			if (pktopt)
				kfree_skb(pktopt);

			sk->sk_destruct = inet_sock_destruct;
			/*
			 * ... and add it to the refcnt debug socks count
			 * in the new family. -acme
			 */
			sk_refcnt_debug_inc(sk);
			module_put(THIS_MODULE);
			retv = 0;
			break;
		}
		goto e_inval;

	case IPV6_V6ONLY:
		if (inet_sk(sk)->num)
			goto e_inval;
		np->ipv6only = valbool;
		retv = 0;
		break;

	case IPV6_RECVPKTINFO:
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_2292PKTINFO:
		np->rxopt.bits.rxoinfo = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPLIMIT:
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPLIMIT:
		np->rxopt.bits.rxohlim = valbool;
		retv = 0;
		break;

	case IPV6_RECVRTHDR:
		np->rxopt.bits.srcrt = valbool;
		retv = 0;
		break;

	case IPV6_2292RTHDR:
		np->rxopt.bits.osrcrt = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPOPTS:
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPOPTS:
		np->rxopt.bits.ohopopts = valbool;
		retv = 0;
		break;

	case IPV6_RECVDSTOPTS:
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_2292DSTOPTS:
		np->rxopt.bits.odstopts = valbool;
		retv = 0;
		break;

	case IPV6_TCLASS:
		if (val < -1 || val > 0xff)
			goto e_inval;
		np->tclass = val;
		retv = 0;
		break;

	case IPV6_RECVTCLASS:
		np->rxopt.bits.rxtclass = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
	case IPV6_RTHDRDSTOPTS:
	case IPV6_RTHDR:
	case IPV6_DSTOPTS:
	{
		struct ipv6_txoptions *opt;
		if (optlen == 0)
			optval = NULL;

		/* hop-by-hop / destination options are privileged option */
		retv = -EPERM;
		if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW))
			break;

		retv = -EINVAL;
		if (optlen & 0x7 || optlen > 8 * 255)
			break;

		opt = ipv6_renew_options(sk, np->opt, optname,
					 (struct ipv6_opt_hdr __user *)optval,
					 optlen);
		if (IS_ERR(opt)) {
			retv = PTR_ERR(opt);
			break;
		}

		/* routing header option needs extra check */
		if (optname == IPV6_RTHDR && opt && opt->srcrt) {
			struct ipv6_rt_hdr *rthdr = opt->srcrt;
			switch (rthdr->type) {
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
			case IPV6_SRCRT_TYPE_2:
				break;
#endif
			default:
				goto sticky_done;
			}

			if ((rthdr->hdrlen & 1) ||
			    (rthdr->hdrlen >> 1) != rthdr->segments_left)
				goto sticky_done;
		}

		retv = 0;
		if (inet_sk(sk)->is_icsk) {
			if (opt) {
				struct inet_connection_sock *icsk = inet_csk(sk);
				if (!((1 << sk->sk_state) &
				      (TCPF_LISTEN | TCPF_CLOSE))
				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
					icsk->icsk_ext_hdr_len =
						opt->opt_flen + opt->opt_nflen;
					icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
				}
			}
			opt = xchg(&np->opt, opt);
			sk_dst_reset(sk);
		} else {
			write_lock(&sk->sk_dst_lock);
			opt = xchg(&np->opt, opt);
			write_unlock(&sk->sk_dst_lock);
			sk_dst_reset(sk);
		}
sticky_done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}

	case IPV6_2292PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi fl;
		int junk;

		fl.fl6_flowlabel = 0;
		fl.oif = sk->sk_bound_dev_if;

		if (optlen == 0)
			goto update;

		/* 1K is probably excessive
		 * 1K is surely not enough, 2K per standard header is 16K.
		 */
		retv = -EINVAL;
		if (optlen > 64*1024)
			break;

		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
		retv = -ENOBUFS;
		if (opt == NULL)
			break;

		memset(opt, 0, sizeof(*opt));
		opt->tot_len = sizeof(*opt) + optlen;
		retv = -EFAULT;
		if (copy_from_user(opt+1, optval, optlen))
			goto done;

		msg.msg_controllen = optlen;
		msg.msg_control = (void*)(opt+1);

		retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk);
		if (retv)
			goto done;
update:
		retv = 0;
		if (inet_sk(sk)->is_icsk) {
			if (opt) {
				struct inet_connection_sock *icsk = inet_csk(sk);
				if (!((1 << sk->sk_state) &
				      (TCPF_LISTEN | TCPF_CLOSE))
				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
					icsk->icsk_ext_hdr_len =
						opt->opt_flen + opt->opt_nflen;
					icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
				}
			}
			opt = xchg(&np->opt, opt);
			sk_dst_reset(sk);
		} else {
			write_lock(&sk->sk_dst_lock);
			opt = xchg(&np->opt, opt);
			write_unlock(&sk->sk_dst_lock);
			sk_dst_reset(sk);
		}

done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (val > 255 || val < -1)
			goto e_inval;
		np->hop_limit = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_HOPS:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_MULTICAST_IF:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;

		if (val) {
			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
				goto e_inval;

			if (__dev_get_by_index(&init_net, val) == NULL) {
				retv = -ENODEV;
				break;
			}
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		retv = -EPROTO;
		if (inet_sk(sk)->is_icsk)
			break;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_ADD_MEMBERSHIP)
			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		else