Release 4.11 net/ipv6/ipv6_sockglue.c

/*
 *      IPv6 BSD socket options interface
 *      Linux INET6 implementation
 *
 *      Authors:
 *      Pedro Roque             <roque@di.fc.ul.pt>
 *
 *      Based on linux/net/ipv4/ip_sockglue.c
 *
 *      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       Truncate getsockopt returns
 *      o       Return an optlen of the truncated length if need be
 *
 *      Changes:
 *      David L Stevens <dlstevens@us.ibm.com>:
 *              - 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/mroute6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>
#include <linux/slab.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 <net/compat.h>
#include <net/seg6.h>

#include <linux/uaccess.h>


struct ip6_ra_chain *ip6_ra_chain;

DEFINE_RWLOCK(ip6_ra_lock);



int ip6_ra_control(struct sock *sk, int sel)
{
	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)->inet_num != IPPROTO_RAW)
		return -ENOPROTOOPT;

	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);

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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
205
96.70%
3
37.50%
David S. Miller
3
1.42%
1
12.50%
Eric Dumazet
1
0.47%
1
12.50%
Hideaki Yoshifuji / 吉藤英明
1
0.47%
1
12.50%
Arnaldo Carvalho de Melo
1
0.47%
1
12.50%
Ian Morris
1
0.47%
1
12.50%
Total
212
100.00%
8
100.00%



struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
					   struct ipv6_txoptions *opt)
{
	if (inet_sk(sk)->is_icsk) {
		if (opt &&
		    !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
		    inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) {
			struct inet_connection_sock *icsk = inet_csk(sk);
			icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
		}
	}
	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
		   opt);
	sk_dst_reset(sk);

	return opt;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hideaki Yoshifuji / 吉藤英明
115
93.50%
1
33.33%
Eric Dumazet
8
6.50%
2
66.67%
Total
123
100.00%
3
100.00%



static bool setsockopt_needs_rtnl(int optname)
{
	switch (optname) {
	case IPV6_ADDRFORM:
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	case IPV6_JOIN_ANYCAST:
	case IPV6_LEAVE_ANYCAST:
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	case MCAST_MSFILTER:
		return true;
	}
	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Marcelo Ricardo Leitner
54
94.74%
3
75.00%
Américo Wang
3
5.26%
1
25.00%
Total
57
100.00%
4
100.00%



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

	if (!optval)
		val = 0;
	else {
		if (optlen >= sizeof(int)) {
			if (get_user(val, (int __user *) optval))
				return -EFAULT;
		} else
			val = 0;
	}

	valbool = (val != 0);

	if (ip6_mroute_opt(optname))
		return ip6_mroute_setsockopt(sk, optname, optval, optlen);

	if (needs_rtnl)
		rtnl_lock();
	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->sk_type == SOCK_RAW)
				break;

			if (sk->sk_protocol == IPPROTO_UDP ||
			    sk->sk_protocol == IPPROTO_UDPLITE) {
				struct udp_sock *up = udp_sk(sk);
				if (up->pending == AF_INET6) {
					retv = -EBUSY;
					break;
				}
			} else if (sk->sk_protocol != IPPROTO_TCP)
				break;

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

			if (ipv6_only_sock(sk) ||
			    !ipv6_addr_v4mapped(&sk->sk_v6_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_inuse_add(net, sk->sk_prot, -1);
				sock_prot_inuse_add(net, &tcp_prot, 1);
				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_inuse_add(net, sk->sk_prot, -1);
				sock_prot_inuse_add(net, prot, 1);
				local_bh_enable();
				sk->sk_prot = prot;
				sk->sk_socket->ops = &inet_dgram_ops;
				sk->sk_family = PF_INET;
			}
			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
				   NULL);
			if (opt) {
				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
				txopt_put(opt);
			}
			pktopt = xchg(&np->pktoptions, NULL);
			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 (optlen < sizeof(int) ||
		    inet_sk(sk)->inet_num)
			goto e_inval;
		sk->sk_ipv6only = valbool;
		retv = 0;
		break;

	case IPV6_RECVPKTINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_2292PKTINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxoinfo = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPLIMIT:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPLIMIT:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxohlim = valbool;
		retv = 0;
		break;

	case IPV6_RECVRTHDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.srcrt = valbool;
		retv = 0;
		break;

	case IPV6_2292RTHDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.osrcrt = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.ohopopts = valbool;
		retv = 0;
		break;

	case IPV6_RECVDSTOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_2292DSTOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.odstopts = valbool;
		retv = 0;
		break;

	case IPV6_TCLASS:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val < -1 || val > 0xff)
			goto e_inval;
		/* RFC 3542, 6.5: default traffic class of 0x0 */
		if (val == -1)
			val = 0;
		np->tclass = val;
		retv = 0;
		break;

	case IPV6_RECVTCLASS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxtclass = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_RECVPATHMTU:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxpmtu = valbool;
		retv = 0;
		break;

	case IPV6_TRANSPARENT:
		if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
			retv = -EPERM;
			break;
		}
		if (optlen < sizeof(int))
			goto e_inval;
		/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
		inet_sk(sk)->transparent = valbool;
		retv = 0;
		break;

	case IPV6_RECVORIGDSTADDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxorigdstaddr = valbool;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
	case IPV6_RTHDRDSTOPTS:
	case IPV6_RTHDR:
	case IPV6_DSTOPTS:
	{
		struct ipv6_txoptions *opt;

		/* remove any sticky options header with a zero option
                 * length, per RFC3542.
                 */
		if (optlen == 0)
			optval = NULL;
		else if (!optval)
			goto e_inval;
		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
			 optlen & 0x7 || optlen > 8 * 255)
			goto e_inval;

		/* hop-by-hop / destination options are privileged option */
		retv = -EPERM;
		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
			break;

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

		/* routing header option needs extra check */
		retv = -EINVAL;
		if (optname == IPV6_RTHDR && opt && opt->srcrt) {
			struct ipv6_rt_hdr *rthdr = opt->srcrt;
			switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
			case IPV6_SRCRT_TYPE_2:
				if (rthdr->hdrlen != 2 ||
				    rthdr->segments_left != 1)
					goto sticky_done;

				break;
#endif
			case IPV6_SRCRT_TYPE_4:
			{
				struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)
							  opt->srcrt;

				if (!seg6_validate_srh(srh, optlen))
					goto sticky_done;
				break;
			}
			default:
				goto sticky_done;
			}
		}

		retv = 0;
		opt = ipv6_update_options(sk, opt);
sticky_done:
		if (opt) {
			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
			txopt_put(opt);
		}
		break;
	}

	case IPV6_PKTINFO:
	{
		struct in6_pktinfo pkt;

		if (optlen == 0)
			goto e_inval;
		else if (optlen < sizeof(struct in6_pktinfo) || !optval)
			goto e_inval;

		if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
				retv = -EFAULT;
				break;
		}
		if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
			goto e_inval;

		np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
		np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
		retv = 0;
		break;
	}

	case IPV6_2292PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi6 fl6;
		struct sockcm_cookie sockc_junk;
		struct ipcm6_cookie ipc6;

		memset(&fl6, 0, sizeof(fl6));
		fl6.flowi6_oif = sk->sk_bound_dev_if;
		fl6.flowi6_mark = sk->sk_mark;

		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)
			break;

		memset(opt, 0, sizeof(*opt));
		atomic_set(&opt->refcnt, 1);
		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);
		ipc6.opt = opt;

		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6, &sockc_junk);
		if (retv)
			goto done;
update:
		retv = 0;
		opt = ipv6_update_options(sk, opt);
done:
		if (opt) {
			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
			txopt_put(opt);
		}
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (optlen < sizeof(int))
			goto e_inval;
		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)
			break;
		if (optlen < sizeof(int))
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val != valbool)
			goto e_inval;
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_UNICAST_IF:
	{
		struct net_device *dev = NULL;
		int ifindex;

		if (optlen != sizeof(int))
			goto e_inval;

		ifindex = (__force int)ntohl((__force __be32)val);
		if (ifindex == 0) {
			np->ucast_oif = 0;
			retv = 0;
			break;
		}

		dev = dev_get_by_index(net, ifindex);
		retv = -EADDRNOTAVAIL;
		if (!dev)
			break;
		dev_put(dev);

		retv = -EINVAL;
		if (sk->sk_bound_dev_if)
			break;

		np->ucast_oif = ifindex;
		retv = 0;
		break;
	}

	case IPV6_MULTICAST_IF:
		if (sk->sk_type == SOCK_STREAM)
			break;
		if (optlen < sizeof(int))
			goto e_inval;

		if (val) {
			struct net_device *dev;
			int midx;

			rcu_read_lock();

			dev = dev_get_by_index_rcu(net, val);
			if (!dev) {
				rcu_read_unlock();
				retv = -ENODEV;
				break;
			}
			midx = l3mdev_master_ifindex_rcu(dev);

			rcu_read_unlock();

			if (sk->sk_bound_dev_if &&
			    sk->sk_bound_dev_if != val &&
			    (!midx || midx != sk->sk_bound_dev_if))
				goto e_inval;
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		if (optlen < sizeof(struct ipv6_mreq))
			goto e_inval;

		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
			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		break;
	}
	case IPV6_JOIN_ANYCAST:
	case IPV6_LEAVE_ANYCAST:
	{
		struct ipv6_mreq mreq;

		if (optlen < sizeof(struct ipv6_mreq))
			goto e_inval;

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

		if (optname == IPV6_JOIN_ANYCAST)
			retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		else
			retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		break;
	}
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct group_req greq;
		struct sockaddr_in6 *psin6;

		if (optlen < sizeof(struct group_req))
			goto e_inval;

		retv = -EFAULT;
		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
			break;
		if (greq.gr_group.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
		if (optname == MCAST_JOIN_GROUP)
			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
						 &psin6->sin6_addr);
		else
			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
						 &psin6->sin6_addr);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct group_source_req greqs;
		int omode, add;

		if (optlen < sizeof(struct group_source_req))
			goto e_inval;
		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
			retv = -EFAULT;
			break;
		}
		if (greqs.gsr_group.ss_family != AF_INET6 ||
		    greqs.gsr_source.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		if (optname == MCAST_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == MCAST_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else