[mirror_ubuntu-kernels.git] / net / ipv6 / ip6_input.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	IPv6 input
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Ian P. Morris		<I.P.Morris@soton.ac.uk>
 *
 *	Based in linux/net/ipv4/ip_input.c
 */
/* Changes
 *
 *	Mitsuru KANDA @USAGI and
 *	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/icmpv6.h>
#include <linux/mroute6.h>
#include <linux/slab.h>
#include <linux/indirect_call_wrapper.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/xfrm.h>
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>

INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
				struct sk_buff *skb)
{
	void (*edemux)(struct sk_buff *skb);

	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
		const struct inet6_protocol *ipprot;

		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
			INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
					udp_v6_early_demux, skb);
	}
	if (!skb_valid_dst(skb))
		ip6_route_input(skb);
}

int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	/* if ingress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	skb = l3mdev_ip6_rcv(skb);
	if (!skb)
		return NET_RX_SUCCESS;
	ip6_rcv_finish_core(net, sk, skb);

	return dst_input(skb);
}

static void ip6_sublist_rcv_finish(struct list_head *head)
{
	struct sk_buff *skb, *next;

	list_for_each_entry_safe(skb, next, head, list)
		dst_input(skb);
}

static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
				struct list_head *head)
{
	struct dst_entry *curr_dst = NULL;
	struct sk_buff *skb, *next;
	struct list_head sublist;

	INIT_LIST_HEAD(&sublist);
	list_for_each_entry_safe(skb, next, head, list) {
		struct dst_entry *dst;

		skb_list_del_init(skb);
		/* if ingress device is enslaved to an L3 master device pass the
		 * skb to its handler for processing
		 */
		skb = l3mdev_ip6_rcv(skb);
		if (!skb)
			continue;
		ip6_rcv_finish_core(net, sk, skb);
		dst = skb_dst(skb);
		if (curr_dst != dst) {
			/* dispatch old sublist */
			if (!list_empty(&sublist))
				ip6_sublist_rcv_finish(&sublist);
			/* start new sublist */
			INIT_LIST_HEAD(&sublist);
			curr_dst = dst;
		}
		list_add_tail(&skb->list, &sublist);
	}
	/* dispatch final sublist */
	ip6_sublist_rcv_finish(&sublist);
}

static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
				    struct net *net)
{
	const struct ipv6hdr *hdr;
	u32 pkt_len;
	struct inet6_dev *idev;

	if (skb->pkt_type == PACKET_OTHERHOST) {
		kfree_skb(skb);
		return NULL;
	}

	rcu_read_lock();

	idev = __in6_dev_get(skb->dev);

	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
	    !idev || unlikely(idev->cnf.disable_ipv6)) {
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));

	/*
	 * Store incoming device index. When the packet will
	 * be queued, we cannot refer to skb->dev anymore.
	 *
	 * BTW, when we send a packet for our own local address on a
	 * non-loopback interface (e.g. ethX), it is being delivered
	 * via the loopback interface (lo) here; skb->dev = loopback_dev.
	 * It, however, should be considered as if it is being
	 * arrived via the sending interface (ethX), because of the
	 * nature of scoping architecture. --yoshfuji
	 */
	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;

	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
		goto err;

	hdr = ipv6_hdr(skb);

	if (hdr->version != 6)
		goto err;

	__IP6_ADD_STATS(net, idev,
			IPSTATS_MIB_NOECTPKTS +
				(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
	/*
	 * RFC4291 2.5.3
	 * The loopback address must not be used as the source address in IPv6
	 * packets that are sent outside of a single node. [..]
	 * A packet received on an interface with a destination address
	 * of loopback must be dropped.
	 */
	if ((ipv6_addr_loopback(&hdr->saddr) ||
	     ipv6_addr_loopback(&hdr->daddr)) &&
	    !(dev->flags & IFF_LOOPBACK) &&
	    !netif_is_l3_master(dev))
		goto err;

	/* RFC4291 Errata ID: 3480
	 * Interface-Local scope spans only a single interface on a
	 * node and is useful only for loopback transmission of
	 * multicast.  Packets with interface-local scope received
	 * from another node must be discarded.
	 */
	if (!(skb->pkt_type == PACKET_LOOPBACK ||
	      dev->flags & IFF_LOOPBACK) &&
	    ipv6_addr_is_multicast(&hdr->daddr) &&
	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
		goto err;

	/* If enabled, drop unicast packets that were encapsulated in link-layer
	 * multicast or broadcast to protected against the so-called "hole-196"
	 * attack in 802.11 wireless.
	 */
	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	    (skb->pkt_type == PACKET_BROADCAST ||
	     skb->pkt_type == PACKET_MULTICAST) &&
	    idev->cnf.drop_unicast_in_l2_multicast)
		goto err;

	/* RFC4291 2.7
	 * Nodes must not originate a packet to a multicast address whose scope
	 * field contains the reserved value 0; if such a packet is received, it
	 * must be silently dropped.
	 */
	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
		goto err;

	/*
	 * RFC4291 2.7
	 * Multicast addresses must not be used as source addresses in IPv6
	 * packets or appear in any Routing header.
	 */
	if (ipv6_addr_is_multicast(&hdr->saddr))
		goto err;

	skb->transport_header = skb->network_header + sizeof(*hdr);
	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);

	pkt_len = ntohs(hdr->payload_len);

	/* pkt_len may be zero if Jumbo payload option is present */
	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
		if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
			__IP6_INC_STATS(net,
					idev, IPSTATS_MIB_INTRUNCATEDPKTS);
			goto drop;
		}
		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
			goto drop;
		}
		hdr = ipv6_hdr(skb);
	}

	if (hdr->nexthdr == NEXTHDR_HOP) {
		if (ipv6_parse_hopopts(skb) < 0) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
			rcu_read_unlock();
			return NULL;
		}
	}

	rcu_read_unlock();

	/* Must drop socket now because of tproxy. */
	skb_orphan(skb);

	return skb;
err:
	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
	rcu_read_unlock();
	kfree_skb(skb);
	return NULL;
}

int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
	struct net *net = dev_net(skb->dev);

	skb = ip6_rcv_core(skb, dev, net);
	if (skb == NULL)
		return NET_RX_DROP;
	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip6_rcv_finish);
}

static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
			    struct net *net)
{
	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
		     head, dev, NULL, ip6_rcv_finish);
	ip6_list_rcv_finish(net, NULL, head);
}

/* Receive a list of IPv6 packets */
void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
		   struct net_device *orig_dev)
{
	struct net_device *curr_dev = NULL;
	struct net *curr_net = NULL;
	struct sk_buff *skb, *next;
	struct list_head sublist;

	INIT_LIST_HEAD(&sublist);
	list_for_each_entry_safe(skb, next, head, list) {
		struct net_device *dev = skb->dev;
		struct net *net = dev_net(dev);

		skb_list_del_init(skb);
		skb = ip6_rcv_core(skb, dev, net);
		if (skb == NULL)
			continue;

		if (curr_dev != dev || curr_net != net) {
			/* dispatch old sublist */
			if (!list_empty(&sublist))
				ip6_sublist_rcv(&sublist, curr_dev, curr_net);
			/* start new sublist */
			INIT_LIST_HEAD(&sublist);
			curr_dev = dev;
			curr_net = net;
		}
		list_add_tail(&skb->list, &sublist);
	}
	/* dispatch final sublist */
	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
}

INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));

/*
 *	Deliver the packet to the host
 */
void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
			      bool have_final)
{
	const struct inet6_protocol *ipprot;
	struct inet6_dev *idev;
	unsigned int nhoff;
	bool raw;

	/*
	 *	Parse extension headers
	 */

resubmit:
	idev = ip6_dst_idev(skb_dst(skb));
	nhoff = IP6CB(skb)->nhoff;
	if (!have_final) {
		if (!pskb_pull(skb, skb_transport_offset(skb)))
			goto discard;
		nexthdr = skb_network_header(skb)[nhoff];
	}

resubmit_final:
	raw = raw6_local_deliver(skb, nexthdr);
	ipprot = rcu_dereference(inet6_protos[nexthdr]);
	if (ipprot) {
		int ret;

		if (have_final) {
			if (!(ipprot->flags & INET6_PROTO_FINAL)) {
				/* Once we've seen a final protocol don't
				 * allow encapsulation on any non-final
				 * ones. This allows foo in UDP encapsulation
				 * to work.
				 */
				goto discard;
			}
		} else if (ipprot->flags & INET6_PROTO_FINAL) {
			const struct ipv6hdr *hdr;
			int sdif = inet6_sdif(skb);
			struct net_device *dev;

			/* Only do this once for first final protocol */
			have_final = true;

			/* Free reference early: we don't need it any more,
			   and it may hold ip_conntrack module loaded
			   indefinitely. */
			nf_reset(skb);

			skb_postpull_rcsum(skb, skb_network_header(skb),
					   skb_network_header_len(skb));
			hdr = ipv6_hdr(skb);

			/* skb->dev passed may be master dev for vrfs. */
			if (sdif) {
				dev = dev_get_by_index_rcu(net, sdif);
				if (!dev)
					goto discard;
			} else {
				dev = skb->dev;
			}

			if (ipv6_addr_is_multicast(&hdr->daddr) &&
			    !ipv6_chk_mcast_addr(dev, &hdr->daddr,
						 &hdr->saddr) &&
			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
				goto discard;
		}
		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
				      skb);
		if (ret > 0) {
			if (ipprot->flags & INET6_PROTO_FINAL) {
				/* Not an extension header, most likely UDP
				 * encapsulation. Use return value as nexthdr
				 * protocol not nhoff (which presumably is
				 * not set by handler).
				 */
				nexthdr = ret;
				goto resubmit_final;
			} else {
				goto resubmit;
			}
		} else if (ret == 0) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
		}
	} else {
		if (!raw) {
			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				__IP6_INC_STATS(net, idev,
						IPSTATS_MIB_INUNKNOWNPROTOS);
				icmpv6_send(skb, ICMPV6_PARAMPROB,
					    ICMPV6_UNK_NEXTHDR, nhoff);
			}
			kfree_skb(skb);
		} else {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
			consume_skb(skb);
		}
	}
	return;

discard:
	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
	kfree_skb(skb);
}

static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	rcu_read_lock();
	ip6_protocol_deliver_rcu(net, skb, 0, false);
	rcu_read_unlock();

	return 0;
}


int ip6_input(struct sk_buff *skb)
{
	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
		       ip6_input_finish);
}
EXPORT_SYMBOL_GPL(ip6_input);

int ip6_mc_input(struct sk_buff *skb)
{
	int sdif = inet6_sdif(skb);
	const struct ipv6hdr *hdr;
	struct net_device *dev;
	bool deliver;

	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
			 __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
			 skb->len);

	/* skb->dev passed may be master dev for vrfs. */
	if (sdif) {
		rcu_read_lock();
		dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
		if (!dev) {
			rcu_read_unlock();
			kfree_skb(skb);
			return -ENODEV;
		}
	} else {
		dev = skb->dev;
	}

	hdr = ipv6_hdr(skb);
	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	if (sdif)
		rcu_read_unlock();

#ifdef CONFIG_IPV6_MROUTE
	/*
	 *      IPv6 multicast router mode is now supported ;)
	 */
	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
	    !(ipv6_addr_type(&hdr->daddr) &
	      (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
		/*
		 * Okay, we try to forward - split and duplicate
		 * packets.
		 */
		struct sk_buff *skb2;
		struct inet6_skb_parm *opt = IP6CB(skb);

		/* Check for MLD */
		if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
			/* Check if this is a mld message */
			u8 nexthdr = hdr->nexthdr;
			__be16 frag_off;
			int offset;

			/* Check if the value of Router Alert
			 * is for MLD (0x0000).
			 */
			if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
				deliver = false;

				if (!ipv6_ext_hdr(nexthdr)) {
					/* BUG */
					goto out;
				}
				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
							  &nexthdr, &frag_off);
				if (offset < 0)
					goto out;

				if (ipv6_is_mld(skb, nexthdr, offset))
					deliver = true;

				goto out;
			}
			/* unknown RA - process it normally */
		}

		if (deliver)
			skb2 = skb_clone(skb, GFP_ATOMIC);
		else {
			skb2 = skb;
			skb = NULL;
		}

		if (skb2) {
			ip6_mr_input(skb2);
		}
	}
out:
#endif
	if (likely(deliver))
		ip6_input(skb);
	else {
		/* discard */
		kfree_skb(skb);
	}

	return 0;
}
Commit	Line	Data
2874c5fd	1	// SPDX-License-Identifier: GPL-2.0-or-later
1da177e4 LT	2	/*
1da177e4 LT	3	* IPv6 input
1ab1457c	4	* Linux INET6 implementation
1da177e4 LT	5	*
	6	* Authors:
	7	* Pedro Roque <roque@di.fc.ul.pt>
	8	* Ian P. Morris <I.P.Morris@soton.ac.uk>
	9	*
1da177e4	10	* Based in linux/net/ipv4/ip_input.c
1da177e4 LT	11	*/
	12	/* Changes
	13	*
67ba4152 IM	14	* Mitsuru KANDA @USAGI and
67ba4152 IM	15	* YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
1da177e4 LT	16	*/
	17
	18	#include <linux/errno.h>
	19	#include <linux/types.h>
	20	#include <linux/socket.h>
	21	#include <linux/sockios.h>
1da177e4 LT	22	#include <linux/net.h>
	23	#include <linux/netdevice.h>
	24	#include <linux/in6.h>
	25	#include <linux/icmpv6.h>
7bc570c8	26	#include <linux/mroute6.h>
5a0e3ad6	27	#include <linux/slab.h>
0e219ae4	28	#include <linux/indirect_call_wrapper.h>
1da177e4 LT	29
	30	#include <linux/netfilter.h>
	31	#include <linux/netfilter_ipv6.h>
	32
	33	#include <net/sock.h>
	34	#include <net/snmp.h>
	35
	36	#include <net/ipv6.h>
	37	#include <net/protocol.h>
	38	#include <net/transp_v6.h>
	39	#include <net/rawv6.h>
	40	#include <net/ndisc.h>
	41	#include <net/ip6_route.h>
	42	#include <net/addrconf.h>
	43	#include <net/xfrm.h>
1f07d03e	44	#include <net/inet_ecn.h>
48fb6b55	45	#include <net/dst_metadata.h>
1da177e4	46
97ff7ffb PA	47	INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
97ff7ffb PA	48	INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
d8269e2c EC	49	static void ip6_rcv_finish_core(struct net net, struct sock sk,
d8269e2c EC	50	struct sk_buff *skb)
1da177e4	51	{
dddb64bc	52	void (edemux)(struct sk_buff skb);
dddb64bc	53
e21145a9	54	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
c7109986 ED	55	const struct inet6_protocol *ipprot;
c7109986 ED	56
c7109986	57	ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
dddb64bc	58	if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
97ff7ffb PA	59	INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
97ff7ffb PA	60	udp_v6_early_demux, skb);
c7109986	61	}
48fb6b55	62	if (!skb_valid_dst(skb))
1da177e4	63	ip6_route_input(skb);
d8269e2c EC	64	}
	65
	66	int ip6_rcv_finish(struct net net, struct sock sk, struct sk_buff *skb)
	67	{
	68	/* if ingress device is enslaved to an L3 master device pass the
	69	* skb to its handler for processing
	70	*/
	71	skb = l3mdev_ip6_rcv(skb);
	72	if (!skb)
	73	return NET_RX_SUCCESS;
	74	ip6_rcv_finish_core(net, sk, skb);
1da177e4 LT	75
	76	return dst_input(skb);
	77	}
	78
d8269e2c EC	79	static void ip6_sublist_rcv_finish(struct list_head *head)
	80	{
	81	struct sk_buff skb, next;
	82
	83	list_for_each_entry_safe(skb, next, head, list)
	84	dst_input(skb);
	85	}
	86
	87	static void ip6_list_rcv_finish(struct net net, struct sock sk,
	88	struct list_head *head)
	89	{
	90	struct dst_entry *curr_dst = NULL;
	91	struct sk_buff skb, next;
	92	struct list_head sublist;
	93
	94	INIT_LIST_HEAD(&sublist);
	95	list_for_each_entry_safe(skb, next, head, list) {
	96	struct dst_entry *dst;
	97
22f6bbb7	98	skb_list_del_init(skb);
d8269e2c EC	99	/* if ingress device is enslaved to an L3 master device pass the
	100	* skb to its handler for processing
	101	*/
	102	skb = l3mdev_ip6_rcv(skb);
	103	if (!skb)
	104	continue;
	105	ip6_rcv_finish_core(net, sk, skb);
	106	dst = skb_dst(skb);
	107	if (curr_dst != dst) {
	108	/* dispatch old sublist */
	109	if (!list_empty(&sublist))
	110	ip6_sublist_rcv_finish(&sublist);
	111	/* start new sublist */
	112	INIT_LIST_HEAD(&sublist);
	113	curr_dst = dst;
	114	}
	115	list_add_tail(&skb->list, &sublist);
	116	}
	117	/* dispatch final sublist */
	118	ip6_sublist_rcv_finish(&sublist);
	119	}
	120
	121	static struct sk_buff ip6_rcv_core(struct sk_buff skb, struct net_device *dev,
	122	struct net *net)
1da177e4	123	{
b71d1d42	124	const struct ipv6hdr *hdr;
67ba4152	125	u32 pkt_len;
a11d206d	126	struct inet6_dev *idev;
1da177e4	127
a11d206d YH	128	if (skb->pkt_type == PACKET_OTHERHOST) {
a11d206d YH	129	kfree_skb(skb);
d8269e2c	130	return NULL;
a11d206d YH	131	}
	132
	133	rcu_read_lock();
1da177e4	134
a11d206d YH	135	idev = __in6_dev_get(skb->dev);
a11d206d YH	136
c2005eb0	137	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
1da177e4	138
778d80be YH	139	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL \|\|
778d80be YH	140	!idev \|\| unlikely(idev->cnf.disable_ipv6)) {
1d015503	141	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
71f6f6df	142	goto drop;
1da177e4 LT	143	}
1da177e4 LT	144
6b7fdc3a GC	145	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
6b7fdc3a GC	146
1da177e4 LT	147	/*
	148	* Store incoming device index. When the packet will
	149	* be queued, we cannot refer to skb->dev anymore.
	150	*
	151	* BTW, when we send a packet for our own local address on a
	152	* non-loopback interface (e.g. ethX), it is being delivered
de3cb747	153	* via the loopback interface (lo) here; skb->dev = loopback_dev.
1da177e4 LT	154	* It, however, should be considered as if it is being
	155	* arrived via the sending interface (ethX), because of the
	156	* nature of scoping architecture. --yoshfuji
	157	*/
48fb6b55	158	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
1da177e4	159
2889139a	160	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
1da177e4 LT	161	goto err;
1da177e4 LT	162
0660e03f	163	hdr = ipv6_hdr(skb);
1da177e4 LT	164
	165	if (hdr->version != 6)
	166	goto err;
	167
1d015503 ED	168	__IP6_ADD_STATS(net, idev,
1d015503 ED	169	IPSTATS_MIB_NOECTPKTS +
1f07d03e	170	(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
1d015503	171	max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
f630e43a YH	172	/*
f630e43a YH	173	* RFC4291 2.5.3
0aa8c13e FW	174	* The loopback address must not be used as the source address in IPv6
0aa8c13e FW	175	* packets that are sent outside of a single node. [..]
f630e43a YH	176	* A packet received on an interface with a destination address
	177	* of loopback must be dropped.
	178	*/
0aa8c13e FW	179	if ((ipv6_addr_loopback(&hdr->saddr) \|\|
0aa8c13e FW	180	ipv6_addr_loopback(&hdr->daddr)) &&
3ede0bbc RS	181	!(dev->flags & IFF_LOOPBACK) &&
3ede0bbc RS	182	!netif_is_l3_master(dev))
f630e43a YH	183	goto err;
f630e43a YH	184
1c4a154e HFS	185	/* RFC4291 Errata ID: 3480
	186	* Interface-Local scope spans only a single interface on a
	187	* node and is useful only for loopback transmission of
	188	* multicast. Packets with interface-local scope received
	189	* from another node must be discarded.
	190	*/
	191	if (!(skb->pkt_type == PACKET_LOOPBACK \|\|
	192	dev->flags & IFF_LOOPBACK) &&
	193	ipv6_addr_is_multicast(&hdr->daddr) &&
	194	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
	195	goto err;
	196
abbc3043 JB	197	/* If enabled, drop unicast packets that were encapsulated in link-layer
	198	* multicast or broadcast to protected against the so-called "hole-196"
	199	* attack in 802.11 wireless.
	200	*/
	201	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	202	(skb->pkt_type == PACKET_BROADCAST \|\|
	203	skb->pkt_type == PACKET_MULTICAST) &&
	204	idev->cnf.drop_unicast_in_l2_multicast)
	205	goto err;
	206
20314092 HFS	207	/* RFC4291 2.7
	208	* Nodes must not originate a packet to a multicast address whose scope
	209	* field contains the reserved value 0; if such a packet is received, it
	210	* must be silently dropped.
	211	*/
	212	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	213	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
	214	goto err;
	215
c457338d BH	216	/*
	217	* RFC4291 2.7
	218	* Multicast addresses must not be used as source addresses in IPv6
	219	* packets or appear in any Routing header.
	220	*/
	221	if (ipv6_addr_is_multicast(&hdr->saddr))
	222	goto err;
	223
b0e380b1	224	skb->transport_header = skb->network_header + sizeof(*hdr);
951dbc8a PM	225	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
951dbc8a PM	226
1da177e4 LT	227	pkt_len = ntohs(hdr->payload_len);
	228
	229	/* pkt_len may be zero if Jumbo payload option is present */
	230	if (pkt_len \|\| hdr->nexthdr != NEXTHDR_HOP) {
60e5c166	231	if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
1d015503 ED	232	__IP6_INC_STATS(net,
1d015503 ED	233	idev, IPSTATS_MIB_INTRUNCATEDPKTS);
60e5c166 MC	234	goto drop;
60e5c166 MC	235	}
1da177e4	236	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
1d015503	237	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
1da177e4 LT	238	goto drop;
1da177e4 LT	239	}
0660e03f	240	hdr = ipv6_hdr(skb);
1da177e4 LT	241	}
	242
	243	if (hdr->nexthdr == NEXTHDR_HOP) {
e5bbef20	244	if (ipv6_parse_hopopts(skb) < 0) {
1d015503	245	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
a11d206d	246	rcu_read_unlock();
d8269e2c	247	return NULL;
1da177e4	248	}
1da177e4 LT	249	}
1da177e4 LT	250
a11d206d YH	251	rcu_read_unlock();
a11d206d YH	252
71f9dacd HX	253	/* Must drop socket now because of tproxy. */
	254	skb_orphan(skb);
	255
d8269e2c	256	return skb;
1da177e4	257	err:
1d015503	258	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
1da177e4	259	drop:
a11d206d	260	rcu_read_unlock();
1da177e4	261	kfree_skb(skb);
d8269e2c EC	262	return NULL;
	263	}
	264
	265	int ipv6_rcv(struct sk_buff skb, struct net_device dev, struct packet_type pt, struct net_device orig_dev)
	266	{
	267	struct net *net = dev_net(skb->dev);
	268
	269	skb = ip6_rcv_core(skb, dev, net);
	270	if (skb == NULL)
	271	return NET_RX_DROP;
	272	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
	273	net, NULL, skb, dev, NULL,
	274	ip6_rcv_finish);
	275	}
	276
	277	static void ip6_sublist_rcv(struct list_head head, struct net_device dev,
	278	struct net *net)
	279	{
	280	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
	281	head, dev, NULL, ip6_rcv_finish);
	282	ip6_list_rcv_finish(net, NULL, head);
	283	}
	284
	285	/* Receive a list of IPv6 packets */
	286	void ipv6_list_rcv(struct list_head head, struct packet_type pt,
	287	struct net_device *orig_dev)
	288	{
	289	struct net_device *curr_dev = NULL;
	290	struct net *curr_net = NULL;
	291	struct sk_buff skb, next;
	292	struct list_head sublist;
	293
	294	INIT_LIST_HEAD(&sublist);
	295	list_for_each_entry_safe(skb, next, head, list) {
	296	struct net_device *dev = skb->dev;
	297	struct net *net = dev_net(dev);
	298
22f6bbb7	299	skb_list_del_init(skb);
d8269e2c EC	300	skb = ip6_rcv_core(skb, dev, net);
	301	if (skb == NULL)
	302	continue;
	303
	304	if (curr_dev != dev \|\| curr_net != net) {
	305	/* dispatch old sublist */
	306	if (!list_empty(&sublist))
	307	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
	308	/* start new sublist */
	309	INIT_LIST_HEAD(&sublist);
	310	curr_dev = dev;
	311	curr_net = net;
	312	}
	313	list_add_tail(&skb->list, &sublist);
	314	}
	315	/* dispatch final sublist */
	316	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
1da177e4 LT	317	}
1da177e4 LT	318
0e219ae4 PA	319	INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
	320	INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
	321
1da177e4 LT	322	/*
	323	* Deliver the packet to the host
	324	*/
80bde363 PA	325	void ip6_protocol_deliver_rcu(struct net net, struct sk_buff skb, int nexthdr,
80bde363 PA	326	bool have_final)
1da177e4	327	{
41135cc8	328	const struct inet6_protocol *ipprot;
f9242b6b	329	struct inet6_dev *idev;
1da177e4	330	unsigned int nhoff;
a50feda5	331	bool raw;
1da177e4	332
1da177e4 LT	333	/*
	334	* Parse extension headers
	335	*/
	336
1b0ccfe5	337	resubmit:
adf30907	338	idev = ip6_dst_idev(skb_dst(skb));
951dbc8a	339	nhoff = IP6CB(skb)->nhoff;
80bde363 PA	340	if (!have_final) {
	341	if (!pskb_pull(skb, skb_transport_offset(skb)))
	342	goto discard;
	343	nexthdr = skb_network_header(skb)[nhoff];
	344	}
1da177e4	345
4c64242a	346	resubmit_final:
69d6da0b	347	raw = raw6_local_deliver(skb, nexthdr);
e5d08d71	348	ipprot = rcu_dereference(inet6_protos[nexthdr]);
53b24b8f	349	if (ipprot) {
1da177e4	350	int ret;
1ab1457c	351
1da44f9c TH	352	if (have_final) {
	353	if (!(ipprot->flags & INET6_PROTO_FINAL)) {
	354	/* Once we've seen a final protocol don't
	355	* allow encapsulation on any non-final
	356	* ones. This allows foo in UDP encapsulation
	357	* to work.
	358	*/
	359	goto discard;
	360	}
	361	} else if (ipprot->flags & INET6_PROTO_FINAL) {
b71d1d42	362	const struct ipv6hdr *hdr;
5226b6a9 MM	363	int sdif = inet6_sdif(skb);
5226b6a9 MM	364	struct net_device *dev;
1da177e4	365
1da44f9c TH	366	/* Only do this once for first final protocol */
	367	have_final = true;
	368
9fb9cbb1 YK	369	/* Free reference early: we don't need it any more,
	370	and it may hold ip_conntrack module loaded
	371	indefinitely. */
	372	nf_reset(skb);
	373
d56f90a7	374	skb_postpull_rcsum(skb, skb_network_header(skb),
cfe1fc77	375	skb_network_header_len(skb));
0660e03f	376	hdr = ipv6_hdr(skb);
5226b6a9 MM	377
	378	/* skb->dev passed may be master dev for vrfs. */
	379	if (sdif) {
	380	dev = dev_get_by_index_rcu(net, sdif);
	381	if (!dev)
	382	goto discard;
	383	} else {
	384	dev = skb->dev;
	385	}
	386
1da177e4	387	if (ipv6_addr_is_multicast(&hdr->daddr) &&
5226b6a9 MM	388	!ipv6_chk_mcast_addr(dev, &hdr->daddr,
5226b6a9 MM	389	&hdr->saddr) &&
daad1512	390	!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
1da177e4 LT	391	goto discard;
	392	}
	393	if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
1ab1457c	394	!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
1da177e4	395	goto discard;
1ab1457c	396
0e219ae4 PA	397	ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
0e219ae4 PA	398	skb);
4c64242a TH	399	if (ret > 0) {
	400	if (ipprot->flags & INET6_PROTO_FINAL) {
	401	/* Not an extension header, most likely UDP
	402	* encapsulation. Use return value as nexthdr
	403	* protocol not nhoff (which presumably is
	404	* not set by handler).
	405	*/
	406	nexthdr = ret;
	407	goto resubmit_final;
	408	} else {
	409	goto resubmit;
	410	}
	411	} else if (ret == 0) {
1d015503	412	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
4c64242a	413	}
1da177e4	414	} else {
69d6da0b	415	if (!raw) {
1da177e4	416	if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1d015503 ED	417	__IP6_INC_STATS(net, idev,
1d015503 ED	418	IPSTATS_MIB_INUNKNOWNPROTOS);
fad87aca	419	icmpv6_send(skb, ICMPV6_PARAMPROB,
3ffe533c	420	ICMPV6_UNK_NEXTHDR, nhoff);
1da177e4	421	}
d8c6f4b9 NH	422	kfree_skb(skb);
d8c6f4b9 NH	423	} else {
1d015503	424	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
d8c6f4b9 NH	425	consume_skb(skb);
d8c6f4b9 NH	426	}
1da177e4	427	}
80bde363	428	return;
1da177e4 LT	429
1da177e4 LT	430	discard:
1d015503	431	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
1da177e4	432	kfree_skb(skb);
80bde363 PA	433	}
	434
	435	static int ip6_input_finish(struct net net, struct sock sk, struct sk_buff *skb)
	436	{
	437	rcu_read_lock();
	438	ip6_protocol_deliver_rcu(net, skb, 0, false);
	439	rcu_read_unlock();
	440
1da177e4 LT	441	return 0;
	442	}
	443
	444
	445	int ip6_input(struct sk_buff *skb)
	446	{
29a26a56 EB	447	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
29a26a56 EB	448	dev_net(skb->dev), NULL, skb, skb->dev, NULL,
6e23ae2a	449	ip6_input_finish);
1da177e4	450	}
b4869aa2	451	EXPORT_SYMBOL_GPL(ip6_input);
1da177e4 LT	452
	453	int ip6_mc_input(struct sk_buff *skb)
	454	{
5226b6a9	455	int sdif = inet6_sdif(skb);
b71d1d42	456	const struct ipv6hdr *hdr;
5226b6a9	457	struct net_device *dev;
a50feda5	458	bool deliver;
1da177e4	459
c2005eb0	460	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
bdb7cc64	461	__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
edf391ff	462	skb->len);
1da177e4	463
5226b6a9 MM	464	/* skb->dev passed may be master dev for vrfs. */
	465	if (sdif) {
	466	rcu_read_lock();
	467	dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
	468	if (!dev) {
	469	rcu_read_unlock();
	470	kfree_skb(skb);
	471	return -ENODEV;
	472	}
	473	} else {
	474	dev = skb->dev;
	475	}
	476
0660e03f	477	hdr = ipv6_hdr(skb);
5226b6a9 MM	478	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	479	if (sdif)
	480	rcu_read_unlock();
1da177e4	481
7bc570c8	482	#ifdef CONFIG_IPV6_MROUTE
1da177e4	483	/*
7bc570c8	484	* IPv6 multicast router mode is now supported ;)
1da177e4	485	*/
53b7997f	486	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
ddf64354 HFS	487	!(ipv6_addr_type(&hdr->daddr) &
ddf64354 HFS	488	(IPV6_ADDR_LOOPBACK\|IPV6_ADDR_LINKLOCAL)) &&
7bc570c8 YH	489	likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
	490	/*
	491	* Okay, we try to forward - split and duplicate
	492	* packets.
	493	*/
	494	struct sk_buff *skb2;
	495	struct inet6_skb_parm *opt = IP6CB(skb);
	496
	497	/* Check for MLD */
dd3332bf	498	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
7bc570c8	499	/* Check if this is a mld message */
7bc570c8	500	u8 nexthdr = hdr->nexthdr;
75f2811c	501	__be16 frag_off;
7bc570c8 YH	502	int offset;
	503
	504	/* Check if the value of Router Alert
	505	* is for MLD (0x0000).
	506	*/
dd3332bf	507	if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
a50feda5	508	deliver = false;
aba6096b	509
7bc570c8 YH	510	if (!ipv6_ext_hdr(nexthdr)) {
7bc570c8 YH	511	/* BUG */
aba6096b	512	goto out;
7bc570c8 YH	513	}
7bc570c8 YH	514	offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
75f2811c	515	&nexthdr, &frag_off);
7bc570c8	516	if (offset < 0)
aba6096b	517	goto out;
7bc570c8	518
4c938d22 A	519	if (ipv6_is_mld(skb, nexthdr, offset))
4c938d22 A	520	deliver = true;
7bc570c8	521
4c938d22	522	goto out;
7bc570c8 YH	523	}
	524	/* unknown RA - process it normally */
	525	}
1da177e4	526
7bc570c8 YH	527	if (deliver)
	528	skb2 = skb_clone(skb, GFP_ATOMIC);
	529	else {
	530	skb2 = skb;
	531	skb = NULL;
	532	}
1ab1457c	533
7bc570c8	534	if (skb2) {
7bc570c8	535	ip6_mr_input(skb2);
1da177e4 LT	536	}
1da177e4 LT	537	}
7bc570c8	538	out:
aba6096b YH	539	#endif
aba6096b YH	540	if (likely(deliver))
1da177e4	541	ip6_input(skb);
aba6096b YH	542	else {
	543	/* discard */
	544	kfree_skb(skb);
1da177e4	545	}
1da177e4 LT	546
	547	return 0;
	548	}