[GitHub/LineageOS/android_kernel_motorola_exynos9610.git] / net / ipv4 / netfilter / nf_conntrack_l3proto_ipv4.c


/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
 * (C) 2006-2012 Patrick McHardy <kaber@trash.net>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/types.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/icmp.h>
#include <linux/sysctl.h>
#include <net/route.h>
#include <net/ip.h>

#include <linux/netfilter_ipv4.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#include <net/netfilter/nf_log.h>

static int conntrack4_net_id __read_mostly;
static DEFINE_MUTEX(register_ipv4_hooks);

struct conntrack4_net {
	unsigned int users;
};

static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
			      struct nf_conntrack_tuple *tuple)
{
	const __be32 *ap;
	__be32 _addrs[2];
	ap = skb_header_pointer(skb, nhoff + offsetof(struct iphdr, saddr),
				sizeof(u_int32_t) * 2, _addrs);
	if (ap == NULL)
		return false;

	tuple->src.u3.ip = ap[0];
	tuple->dst.u3.ip = ap[1];

	return true;
}

static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
			      const struct nf_conntrack_tuple *orig)
{
	tuple->src.u3.ip = orig->dst.u3.ip;
	tuple->dst.u3.ip = orig->src.u3.ip;

	return true;
}

static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
			    unsigned int *dataoff, u_int8_t *protonum)
{
	const struct iphdr *iph;
	struct iphdr _iph;

	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
	if (iph == NULL)
		return -NF_ACCEPT;

	/* Conntrack defragments packets, we might still see fragments
	 * inside ICMP packets though. */
	if (iph->frag_off & htons(IP_OFFSET))
		return -NF_ACCEPT;

	*dataoff = nhoff + (iph->ihl << 2);
	*protonum = iph->protocol;

	/* Check bogus IP headers */
	if (*dataoff > skb->len) {
		pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
			 "nhoff %u, ihl %u, skblen %u\n",
			 nhoff, iph->ihl << 2, skb->len);
		return -NF_ACCEPT;
	}

	return NF_ACCEPT;
}

static unsigned int ipv4_helper(void *priv,
				struct sk_buff *skb,
				const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	const struct nf_conn_help *help;
	const struct nf_conntrack_helper *helper;

	/* This is where we call the helper: as the packet goes out. */
	ct = nf_ct_get(skb, &ctinfo);
	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
		return NF_ACCEPT;

	help = nfct_help(ct);
	if (!help)
		return NF_ACCEPT;

	/* rcu_read_lock()ed by nf_hook_thresh */
	helper = rcu_dereference(help->helper);
	if (!helper)
		return NF_ACCEPT;

	return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
			    ct, ctinfo);
}

static unsigned int ipv4_confirm(void *priv,
				 struct sk_buff *skb,
				 const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;

	ct = nf_ct_get(skb, &ctinfo);
	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
		goto out;

	/* adjust seqs for loopback traffic only in outgoing direction */
	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
	    !nf_is_loopback_packet(skb)) {
		if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
			return NF_DROP;
		}
	}
out:
	/* We've seen it coming out the other side: confirm it */
	return nf_conntrack_confirm(skb);
}

static unsigned int ipv4_conntrack_in(void *priv,
				      struct sk_buff *skb,
				      const struct nf_hook_state *state)
{
	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}

static unsigned int ipv4_conntrack_local(void *priv,
					 struct sk_buff *skb,
					 const struct nf_hook_state *state)
{
	/* root is playing with raw sockets. */
	if (skb->len < sizeof(struct iphdr) ||
	    ip_hdrlen(skb) < sizeof(struct iphdr))
		return NF_ACCEPT;

	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
		enum ip_conntrack_info ctinfo;
		struct nf_conn *tmpl;

		tmpl = nf_ct_get(skb, &ctinfo);
		if (tmpl && nf_ct_is_template(tmpl)) {
			/* when skipping ct, clear templates to avoid fooling
			 * later targets/matches
			 */
			skb->_nfct = 0;
			nf_ct_put(tmpl);
		}
		return NF_ACCEPT;
	}

	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}

/* Connection tracking may drop packets, but never alters them, so
   make it the first hook. */
static const struct nf_hook_ops ipv4_conntrack_ops[] = {
	{
		.hook		= ipv4_conntrack_in,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_PRE_ROUTING,
		.priority	= NF_IP_PRI_CONNTRACK,
	},
	{
		.hook		= ipv4_conntrack_local,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_CONNTRACK,
	},
	{
		.hook		= ipv4_helper,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
	},
	{
		.hook		= ipv4_confirm,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
	},
	{
		.hook		= ipv4_helper,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
	},
	{
		.hook		= ipv4_confirm,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
	},
};

/* Fast function for those who don't want to parse /proc (and I don't
   blame them). */
/* Reversing the socket's dst/src point of view gives us the reply
   mapping. */
static int
getorigdst(struct sock *sk, int optval, void __user *user, int *len)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct nf_conntrack_tuple_hash *h;
	struct nf_conntrack_tuple tuple;

	memset(&tuple, 0, sizeof(tuple));

	lock_sock(sk);
	tuple.src.u3.ip = inet->inet_rcv_saddr;
	tuple.src.u.tcp.port = inet->inet_sport;
	tuple.dst.u3.ip = inet->inet_daddr;
	tuple.dst.u.tcp.port = inet->inet_dport;
	tuple.src.l3num = PF_INET;
	tuple.dst.protonum = sk->sk_protocol;
	release_sock(sk);

	/* We only do TCP and SCTP at the moment: is there a better way? */
	if (tuple.dst.protonum != IPPROTO_TCP &&
	    tuple.dst.protonum != IPPROTO_SCTP) {
		pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n");
		return -ENOPROTOOPT;
	}

	if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
		pr_debug("SO_ORIGINAL_DST: len %d not %zu\n",
			 *len, sizeof(struct sockaddr_in));
		return -EINVAL;
	}

	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
	if (h) {
		struct sockaddr_in sin;
		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

		sin.sin_family = AF_INET;
		sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
			.tuple.dst.u.tcp.port;
		sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
			.tuple.dst.u3.ip;
		memset(sin.sin_zero, 0, sizeof(sin.sin_zero));

		pr_debug("SO_ORIGINAL_DST: %pI4 %u\n",
			 &sin.sin_addr.s_addr, ntohs(sin.sin_port));
		nf_ct_put(ct);
		if (copy_to_user(user, &sin, sizeof(sin)) != 0)
			return -EFAULT;
		else
			return 0;
	}
	pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n",
		 &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port),
		 &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port));
	return -ENOENT;
}

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
				const struct nf_conntrack_tuple *tuple)
{
	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) ||
	    nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -1;
}

static const struct nla_policy ipv4_nla_policy[CTA_IP_MAX+1] = {
	[CTA_IP_V4_SRC]	= { .type = NLA_U32 },
	[CTA_IP_V4_DST]	= { .type = NLA_U32 },
};

static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
				struct nf_conntrack_tuple *t)
{
	if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
		return -EINVAL;

	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);

	return 0;
}
#endif

static struct nf_sockopt_ops so_getorigdst = {
	.pf		= PF_INET,
	.get_optmin	= SO_ORIGINAL_DST,
	.get_optmax	= SO_ORIGINAL_DST+1,
	.get		= getorigdst,
	.owner		= THIS_MODULE,
};

static int ipv4_hooks_register(struct net *net)
{
	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
	int err = 0;

	mutex_lock(&register_ipv4_hooks);

	cnet->users++;
	if (cnet->users > 1)
		goto out_unlock;

	err = nf_defrag_ipv4_enable(net);
	if (err) {
		cnet->users = 0;
		goto out_unlock;
	}

	err = nf_register_net_hooks(net, ipv4_conntrack_ops,
				    ARRAY_SIZE(ipv4_conntrack_ops));

	if (err)
		cnet->users = 0;
 out_unlock:
	mutex_unlock(&register_ipv4_hooks);
	return err;
}

static void ipv4_hooks_unregister(struct net *net)
{
	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);

	mutex_lock(&register_ipv4_hooks);
	if (cnet->users && (--cnet->users == 0))
		nf_unregister_net_hooks(net, ipv4_conntrack_ops,
					ARRAY_SIZE(ipv4_conntrack_ops));
	mutex_unlock(&register_ipv4_hooks);
}

struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
	.l3proto	 = PF_INET,
	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
	.invert_tuple	 = ipv4_invert_tuple,
	.get_l4proto	 = ipv4_get_l4proto,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
	.nla_policy	 = ipv4_nla_policy,
	.nla_size	 = NLA_ALIGN(NLA_HDRLEN + sizeof(u32)) + /* CTA_IP_V4_SRC */
			   NLA_ALIGN(NLA_HDRLEN + sizeof(u32)),  /* CTA_IP_V4_DST */
#endif
	.net_ns_get	 = ipv4_hooks_register,
	.net_ns_put	 = ipv4_hooks_unregister,
	.me		 = THIS_MODULE,
};

module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
		  &nf_conntrack_htable_size, 0600);

MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
MODULE_ALIAS("ip_conntrack");
MODULE_LICENSE("GPL");

static struct nf_conntrack_l4proto *builtin_l4proto4[] = {
	&nf_conntrack_l4proto_tcp4,
	&nf_conntrack_l4proto_udp4,
	&nf_conntrack_l4proto_icmp,
#ifdef CONFIG_NF_CT_PROTO_DCCP
	&nf_conntrack_l4proto_dccp4,
#endif
#ifdef CONFIG_NF_CT_PROTO_SCTP
	&nf_conntrack_l4proto_sctp4,
#endif
#ifdef CONFIG_NF_CT_PROTO_UDPLITE
	&nf_conntrack_l4proto_udplite4,
#endif
};

static int ipv4_net_init(struct net *net)
{
	return nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
					     ARRAY_SIZE(builtin_l4proto4));
}

static void ipv4_net_exit(struct net *net)
{
	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
					ARRAY_SIZE(builtin_l4proto4));
}

static struct pernet_operations ipv4_net_ops = {
	.init = ipv4_net_init,
	.exit = ipv4_net_exit,
	.id = &conntrack4_net_id,
	.size = sizeof(struct conntrack4_net),
};

static int __init nf_conntrack_l3proto_ipv4_init(void)
{
	int ret = 0;

	need_conntrack();

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	if (WARN_ON(nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1) !=
	    nf_conntrack_l3proto_ipv4.nla_size))
		return -EINVAL;
#endif
	ret = nf_register_sockopt(&so_getorigdst);
	if (ret < 0) {
		pr_err("Unable to register netfilter socket option\n");
		return ret;
	}

	ret = register_pernet_subsys(&ipv4_net_ops);
	if (ret < 0) {
		pr_err("nf_conntrack_ipv4: can't register pernet ops\n");
		goto cleanup_sockopt;
	}

	ret = nf_ct_l4proto_register(builtin_l4proto4,
				     ARRAY_SIZE(builtin_l4proto4));
	if (ret < 0)
		goto cleanup_pernet;

	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
	if (ret < 0) {
		pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
		goto cleanup_l4proto;
	}

	return ret;
cleanup_l4proto:
	nf_ct_l4proto_unregister(builtin_l4proto4,
				 ARRAY_SIZE(builtin_l4proto4));
 cleanup_pernet:
	unregister_pernet_subsys(&ipv4_net_ops);
 cleanup_sockopt:
	nf_unregister_sockopt(&so_getorigdst);
	return ret;
}

static void __exit nf_conntrack_l3proto_ipv4_fini(void)
{
	synchronize_net();
	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
	nf_ct_l4proto_unregister(builtin_l4proto4,
				 ARRAY_SIZE(builtin_l4proto4));
	unregister_pernet_subsys(&ipv4_net_ops);
	nf_unregister_sockopt(&so_getorigdst);
}

module_init(nf_conntrack_l3proto_ipv4_init);
module_exit(nf_conntrack_l3proto_ipv4_fini);
Commit	Line	Data
73e4022f	1
9fb9cbb1 YK	2	/* (C) 1999-2001 Paul `Rusty' Russell
9fb9cbb1 YK	3	* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
f229f6ce	4	* (C) 2006-2012 Patrick McHardy <kaber@trash.net>
9fb9cbb1 YK	5	*
	6	* This program is free software; you can redistribute it and/or modify
	7	* it under the terms of the GNU General Public License version 2 as
	8	* published by the Free Software Foundation.
9fb9cbb1 YK	9	*/
9fb9cbb1 YK	10
9fb9cbb1 YK	11	#include <linux/types.h>
	12	#include <linux/ip.h>
	13	#include <linux/netfilter.h>
	14	#include <linux/module.h>
	15	#include <linux/skbuff.h>
	16	#include <linux/icmp.h>
	17	#include <linux/sysctl.h>
0ae2cfe7	18	#include <net/route.h>
9fb9cbb1 YK	19	#include <net/ip.h>
	20
	21	#include <linux/netfilter_ipv4.h>
	22	#include <net/netfilter/nf_conntrack.h>
	23	#include <net/netfilter/nf_conntrack_helper.h>
605dcad6	24	#include <net/netfilter/nf_conntrack_l4proto.h>
9fb9cbb1	25	#include <net/netfilter/nf_conntrack_l3proto.h>
5d0aa2cc	26	#include <net/netfilter/nf_conntrack_zones.h>
9fb9cbb1	27	#include <net/netfilter/nf_conntrack_core.h>
41d73ec0	28	#include <net/netfilter/nf_conntrack_seqadj.h>
9fb9cbb1	29	#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
dd13b010	30	#include <net/netfilter/nf_nat_helper.h>
73e4022f	31	#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
74f7a655	32	#include <net/netfilter/nf_log.h>
dd13b010	33
0c66dc1e FW	34	static int conntrack4_net_id __read_mostly;
	35	static DEFINE_MUTEX(register_ipv4_hooks);
	36
	37	struct conntrack4_net {
	38	unsigned int users;
	39	};
	40
8ce8439a JE	41	static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
8ce8439a JE	42	struct nf_conntrack_tuple *tuple)
9fb9cbb1	43	{
32948588 JE	44	const __be32 *ap;
32948588 JE	45	__be32 _addrs[2];
9fb9cbb1 YK	46	ap = skb_header_pointer(skb, nhoff + offsetof(struct iphdr, saddr),
	47	sizeof(u_int32_t) * 2, _addrs);
	48	if (ap == NULL)
8ce8439a	49	return false;
9fb9cbb1 YK	50
	51	tuple->src.u3.ip = ap[0];
	52	tuple->dst.u3.ip = ap[1];
	53
8ce8439a	54	return true;
9fb9cbb1 YK	55	}
9fb9cbb1 YK	56
8ce8439a JE	57	static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
8ce8439a JE	58	const struct nf_conntrack_tuple *orig)
9fb9cbb1 YK	59	{
	60	tuple->src.u3.ip = orig->dst.u3.ip;
	61	tuple->dst.u3.ip = orig->src.u3.ip;
	62
8ce8439a	63	return true;
9fb9cbb1 YK	64	}
9fb9cbb1 YK	65
ffc30690 YK	66	static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
ffc30690 YK	67	unsigned int dataoff, u_int8_t protonum)
9fb9cbb1	68	{
32948588 JE	69	const struct iphdr *iph;
32948588 JE	70	struct iphdr _iph;
ffc30690 YK	71
	72	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
	73	if (iph == NULL)
8430eac2	74	return -NF_ACCEPT;
ffc30690	75
0fb96701 PM	76	/* Conntrack defragments packets, we might still see fragments
	77	* inside ICMP packets though. */
	78	if (iph->frag_off & htons(IP_OFFSET))
8430eac2	79	return -NF_ACCEPT;
9fb9cbb1	80
ffc30690 YK	81	*dataoff = nhoff + (iph->ihl << 2);
ffc30690 YK	82	*protonum = iph->protocol;
9fb9cbb1	83
07153c6e JK	84	/* Check bogus IP headers */
	85	if (*dataoff > skb->len) {
	86	pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
	87	"nhoff %u, ihl %u, skblen %u\n",
	88	nhoff, iph->ihl << 2, skb->len);
	89	return -NF_ACCEPT;
	90	}
	91
9fb9cbb1 YK	92	return NF_ACCEPT;
	93	}
	94
06198b34	95	static unsigned int ipv4_helper(void *priv,
12f7a505	96	struct sk_buff *skb,
238e54c9	97	const struct nf_hook_state *state)
9fb9cbb1 YK	98	{
	99	struct nf_conn *ct;
	100	enum ip_conntrack_info ctinfo;
32948588 JE	101	const struct nf_conn_help *help;
32948588 JE	102	const struct nf_conntrack_helper *helper;
9fb9cbb1 YK	103
9fb9cbb1 YK	104	/* This is where we call the helper: as the packet goes out. */
3db05fea	105	ct = nf_ct_get(skb, &ctinfo);
fb048833	106	if (!ct \|\| ctinfo == IP_CT_RELATED_REPLY)
12f7a505	107	return NF_ACCEPT;
dc808fe2 HW	108
dc808fe2 HW	109	help = nfct_help(ct);
3c158f7f	110	if (!help)
12f7a505	111	return NF_ACCEPT;
dd13b010	112
e2361cb9	113	/* rcu_read_lock()ed by nf_hook_thresh */
3c158f7f PM	114	helper = rcu_dereference(help->helper);
3c158f7f PM	115	if (!helper)
12f7a505	116	return NF_ACCEPT;
dd13b010	117
b20ab9cc PNA	118	return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
b20ab9cc PNA	119	ct, ctinfo);
12f7a505 PNA	120	}
12f7a505 PNA	121
06198b34	122	static unsigned int ipv4_confirm(void *priv,
12f7a505	123	struct sk_buff *skb,
238e54c9	124	const struct nf_hook_state *state)
12f7a505 PNA	125	{
	126	struct nf_conn *ct;
	127	enum ip_conntrack_info ctinfo;
	128
	129	ct = nf_ct_get(skb, &ctinfo);
	130	if (!ct \|\| ctinfo == IP_CT_RELATED_REPLY)
	131	goto out;
dd13b010	132
42c1edd3 JA	133	/* adjust seqs for loopback traffic only in outgoing direction */
	134	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
	135	!nf_is_loopback_packet(skb)) {
41d73ec0	136	if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
1db7a748	137	NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
dd13b010	138	return NF_DROP;
1db7a748	139	}
dd13b010 PM	140	}
	141	out:
	142	/* We've seen it coming out the other side: confirm it */
	143	return nf_conntrack_confirm(skb);
9fb9cbb1 YK	144	}
9fb9cbb1 YK	145
06198b34	146	static unsigned int ipv4_conntrack_in(void *priv,
3db05fea	147	struct sk_buff *skb,
238e54c9	148	const struct nf_hook_state *state)
9fb9cbb1	149	{
082a758f	150	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
9fb9cbb1 YK	151	}
9fb9cbb1 YK	152
06198b34	153	static unsigned int ipv4_conntrack_local(void *priv,
3db05fea	154	struct sk_buff *skb,
238e54c9	155	const struct nf_hook_state *state)
9fb9cbb1 YK	156	{
9fb9cbb1 YK	157	/* root is playing with raw sockets. */
3db05fea	158	if (skb->len < sizeof(struct iphdr) \|\|
88843104	159	ip_hdrlen(skb) < sizeof(struct iphdr))
9fb9cbb1	160	return NF_ACCEPT;
7b4fdf77	161
2a55ad74 PA	162	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
	163	enum ip_conntrack_info ctinfo;
	164	struct nf_conn *tmpl;
	165
	166	tmpl = nf_ct_get(skb, &ctinfo);
	167	if (tmpl && nf_ct_is_template(tmpl)) {
	168	/* when skipping ct, clear templates to avoid fooling
	169	* later targets/matches
	170	*/
	171	skb->_nfct = 0;
	172	nf_ct_put(tmpl);
	173	}
7b4fdf77	174	return NF_ACCEPT;
2a55ad74	175	}
7b4fdf77	176
082a758f	177	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
9fb9cbb1 YK	178	}
	179
	180	/* Connection tracking may drop packets, but never alters them, so
	181	make it the first hook. */
591bb278	182	static const struct nf_hook_ops ipv4_conntrack_ops[] = {
964ddaa1 PM	183	{
964ddaa1 PM	184	.hook = ipv4_conntrack_in,
57750a22	185	.pf = NFPROTO_IPV4,
6e23ae2a	186	.hooknum = NF_INET_PRE_ROUTING,
964ddaa1 PM	187	.priority = NF_IP_PRI_CONNTRACK,
964ddaa1 PM	188	},
964ddaa1 PM	189	{
964ddaa1 PM	190	.hook = ipv4_conntrack_local,
57750a22	191	.pf = NFPROTO_IPV4,
6e23ae2a	192	.hooknum = NF_INET_LOCAL_OUT,
964ddaa1 PM	193	.priority = NF_IP_PRI_CONNTRACK,
964ddaa1 PM	194	},
12f7a505 PNA	195	{
12f7a505 PNA	196	.hook = ipv4_helper,
12f7a505 PNA	197	.pf = NFPROTO_IPV4,
	198	.hooknum = NF_INET_POST_ROUTING,
	199	.priority = NF_IP_PRI_CONNTRACK_HELPER,
	200	},
964ddaa1 PM	201	{
964ddaa1 PM	202	.hook = ipv4_confirm,
57750a22	203	.pf = NFPROTO_IPV4,
6e23ae2a	204	.hooknum = NF_INET_POST_ROUTING,
964ddaa1 PM	205	.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
964ddaa1 PM	206	},
12f7a505 PNA	207	{
12f7a505 PNA	208	.hook = ipv4_helper,
12f7a505 PNA	209	.pf = NFPROTO_IPV4,
	210	.hooknum = NF_INET_LOCAL_IN,
	211	.priority = NF_IP_PRI_CONNTRACK_HELPER,
	212	},
964ddaa1 PM	213	{
964ddaa1 PM	214	.hook = ipv4_confirm,
57750a22	215	.pf = NFPROTO_IPV4,
6e23ae2a	216	.hooknum = NF_INET_LOCAL_IN,
964ddaa1 PM	217	.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
964ddaa1 PM	218	},
9fb9cbb1 YK	219	};
9fb9cbb1 YK	220
9fb9cbb1 YK	221	/* Fast function for those who don't want to parse /proc (and I don't
	222	blame them). */
	223	/* Reversing the socket's dst/src point of view gives us the reply
	224	mapping. */
	225	static int
	226	getorigdst(struct sock sk, int optval, void __user user, int *len)
	227	{
32948588 JE	228	const struct inet_sock *inet = inet_sk(sk);
32948588 JE	229	const struct nf_conntrack_tuple_hash *h;
9fb9cbb1	230	struct nf_conntrack_tuple tuple;
e905a9ed	231
443a70d5	232	memset(&tuple, 0, sizeof(tuple));
516c855c PA	233
516c855c PA	234	lock_sock(sk);
c720c7e8 ED	235	tuple.src.u3.ip = inet->inet_rcv_saddr;
	236	tuple.src.u.tcp.port = inet->inet_sport;
	237	tuple.dst.u3.ip = inet->inet_daddr;
	238	tuple.dst.u.tcp.port = inet->inet_dport;
9fb9cbb1	239	tuple.src.l3num = PF_INET;
54981279	240	tuple.dst.protonum = sk->sk_protocol;
516c855c	241	release_sock(sk);
9fb9cbb1	242
54981279	243	/* We only do TCP and SCTP at the moment: is there a better way? */
516c855c PA	244	if (tuple.dst.protonum != IPPROTO_TCP &&
516c855c PA	245	tuple.dst.protonum != IPPROTO_SCTP) {
54981279	246	pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n");
9fb9cbb1 YK	247	return -ENOPROTOOPT;
	248	}
	249
	250	if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
5b5e0928	251	pr_debug("SO_ORIGINAL_DST: len %d not %zu\n",
0d53778e	252	*len, sizeof(struct sockaddr_in));
9fb9cbb1 YK	253	return -EINVAL;
	254	}
	255
308ac914	256	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
9fb9cbb1 YK	257	if (h) {
	258	struct sockaddr_in sin;
	259	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
	260
	261	sin.sin_family = AF_INET;
	262	sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
	263	.tuple.dst.u.tcp.port;
	264	sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
	265	.tuple.dst.u3.ip;
6c813c3f	266	memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
9fb9cbb1	267
cffee385 HH	268	pr_debug("SO_ORIGINAL_DST: %pI4 %u\n",
cffee385 HH	269	&sin.sin_addr.s_addr, ntohs(sin.sin_port));
9fb9cbb1 YK	270	nf_ct_put(ct);
	271	if (copy_to_user(user, &sin, sizeof(sin)) != 0)
	272	return -EFAULT;
	273	else
	274	return 0;
	275	}
cffee385 HH	276	pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n",
	277	&tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port),
	278	&tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port));
9fb9cbb1 YK	279	return -ENOENT;
	280	}
	281
24de3d37	282	#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
c1d10adb PNA	283
	284	#include <linux/netfilter/nfnetlink.h>
	285	#include <linux/netfilter/nfnetlink_conntrack.h>
	286
fdf70832	287	static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
c1d10adb PNA	288	const struct nf_conntrack_tuple *tuple)
c1d10adb PNA	289	{
930345ea JB	290	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) \|\|
930345ea JB	291	nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
d317e4f6	292	goto nla_put_failure;
c1d10adb PNA	293	return 0;
c1d10adb PNA	294
df6fb868	295	nla_put_failure:
c1d10adb PNA	296	return -1;
	297	}
	298
f73e924c PM	299	static const struct nla_policy ipv4_nla_policy[CTA_IP_MAX+1] = {
	300	[CTA_IP_V4_SRC] = { .type = NLA_U32 },
	301	[CTA_IP_V4_DST] = { .type = NLA_U32 },
c1d10adb PNA	302	};
c1d10adb PNA	303
fdf70832	304	static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
c1d10adb PNA	305	struct nf_conntrack_tuple *t)
c1d10adb PNA	306	{
df6fb868	307	if (!tb[CTA_IP_V4_SRC] \|\| !tb[CTA_IP_V4_DST])
c1d10adb PNA	308	return -EINVAL;
c1d10adb PNA	309
67b61f6c JB	310	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
67b61f6c JB	311	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
c1d10adb PNA	312
	313	return 0;
	314	}
	315	#endif
	316
9fb9cbb1 YK	317	static struct nf_sockopt_ops so_getorigdst = {
	318	.pf = PF_INET,
	319	.get_optmin = SO_ORIGINAL_DST,
	320	.get_optmax = SO_ORIGINAL_DST+1,
5bd3a76f	321	.get = getorigdst,
16fcec35	322	.owner = THIS_MODULE,
9fb9cbb1 YK	323	};
9fb9cbb1 YK	324
0c66dc1e FW	325	static int ipv4_hooks_register(struct net *net)
	326	{
	327	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
	328	int err = 0;
	329
	330	mutex_lock(&register_ipv4_hooks);
	331
	332	cnet->users++;
	333	if (cnet->users > 1)
	334	goto out_unlock;
	335
834184b1 FW	336	err = nf_defrag_ipv4_enable(net);
	337	if (err) {
	338	cnet->users = 0;
	339	goto out_unlock;
	340	}
	341
0c66dc1e FW	342	err = nf_register_net_hooks(net, ipv4_conntrack_ops,
	343	ARRAY_SIZE(ipv4_conntrack_ops));
	344
	345	if (err)
	346	cnet->users = 0;
	347	out_unlock:
	348	mutex_unlock(&register_ipv4_hooks);
	349	return err;
	350	}
	351
	352	static void ipv4_hooks_unregister(struct net *net)
	353	{
	354	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
	355
	356	mutex_lock(&register_ipv4_hooks);
	357	if (cnet->users && (--cnet->users == 0))
	358	nf_unregister_net_hooks(net, ipv4_conntrack_ops,
	359	ARRAY_SIZE(ipv4_conntrack_ops));
	360	mutex_unlock(&register_ipv4_hooks);
	361	}
	362
61075af5	363	struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
9fb9cbb1	364	.l3proto = PF_INET,
9fb9cbb1 YK	365	.pkt_to_tuple = ipv4_pkt_to_tuple,
9fb9cbb1 YK	366	.invert_tuple = ipv4_invert_tuple,
ffc30690	367	.get_l4proto = ipv4_get_l4proto,
24de3d37	368	#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
fdf70832 PM	369	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
fdf70832 PM	370	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
f73e924c	371	.nla_policy = ipv4_nla_policy,
0d035100 FW	372	.nla_size = NLA_ALIGN(NLA_HDRLEN + sizeof(u32)) + /* CTA_IP_V4_SRC */
0d035100 FW	373	NLA_ALIGN(NLA_HDRLEN + sizeof(u32)), /* CTA_IP_V4_DST */
c1d10adb	374	#endif
0c66dc1e FW	375	.net_ns_get = ipv4_hooks_register,
0c66dc1e FW	376	.net_ns_put = ipv4_hooks_unregister,
9fb9cbb1 YK	377	.me = THIS_MODULE,
	378	};
	379
fae718dd PM	380	module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
	381	&nf_conntrack_htable_size, 0600);
	382
32292a7f	383	MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
d2483dde	384	MODULE_ALIAS("ip_conntrack");
32292a7f PM	385	MODULE_LICENSE("GPL");
32292a7f PM	386
0e54d217 DC	387	static struct nf_conntrack_l4proto *builtin_l4proto4[] = {
	388	&nf_conntrack_l4proto_tcp4,
	389	&nf_conntrack_l4proto_udp4,
	390	&nf_conntrack_l4proto_icmp,
c51d3901 DC	391	#ifdef CONFIG_NF_CT_PROTO_DCCP
	392	&nf_conntrack_l4proto_dccp4,
	393	#endif
a85406af DC	394	#ifdef CONFIG_NF_CT_PROTO_SCTP
	395	&nf_conntrack_l4proto_sctp4,
	396	#endif
9b91c96c DC	397	#ifdef CONFIG_NF_CT_PROTO_UDPLITE
	398	&nf_conntrack_l4proto_udplite4,
	399	#endif
0e54d217 DC	400	};
0e54d217 DC	401
3ea04dd3 G	402	static int ipv4_net_init(struct net *net)
3ea04dd3 G	403	{
4d3a57f2 FW	404	return nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
4d3a57f2 FW	405	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3 G	406	}
	407
	408	static void ipv4_net_exit(struct net *net)
	409	{
0e54d217 DC	410	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
0e54d217 DC	411	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3 G	412	}
	413
	414	static struct pernet_operations ipv4_net_ops = {
	415	.init = ipv4_net_init,
	416	.exit = ipv4_net_exit,
0c66dc1e FW	417	.id = &conntrack4_net_id,
0c66dc1e FW	418	.size = sizeof(struct conntrack4_net),
3ea04dd3 G	419	};
3ea04dd3 G	420
32292a7f	421	static int __init nf_conntrack_l3proto_ipv4_init(void)
9fb9cbb1 YK	422	{
	423	int ret = 0;
	424
32292a7f	425	need_conntrack();
9fb9cbb1	426
0d035100 FW	427	#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	428	if (WARN_ON(nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1) !=
	429	nf_conntrack_l3proto_ipv4.nla_size))
	430	return -EINVAL;
	431	#endif
9fb9cbb1 YK	432	ret = nf_register_sockopt(&so_getorigdst);
9fb9cbb1 YK	433	if (ret < 0) {
09605cc1	434	pr_err("Unable to register netfilter socket option\n");
32292a7f	435	return ret;
9fb9cbb1 YK	436	}
9fb9cbb1 YK	437
3ea04dd3	438	ret = register_pernet_subsys(&ipv4_net_ops);
9fb9cbb1	439	if (ret < 0) {
3ea04dd3	440	pr_err("nf_conntrack_ipv4: can't register pernet ops\n");
9fb9cbb1 YK	441	goto cleanup_sockopt;
	442	}
	443
0e54d217 DC	444	ret = nf_ct_l4proto_register(builtin_l4proto4,
	445	ARRAY_SIZE(builtin_l4proto4));
	446	if (ret < 0)
0c66dc1e	447	goto cleanup_pernet;
c296bb4d	448
6330750d G	449	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
	450	if (ret < 0) {
	451	pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
0e54d217	452	goto cleanup_l4proto;
6330750d G	453	}
6330750d G	454
9fb9cbb1	455	return ret;
0e54d217 DC	456	cleanup_l4proto:
	457	nf_ct_l4proto_unregister(builtin_l4proto4,
	458	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3 G	459	cleanup_pernet:
3ea04dd3 G	460	unregister_pernet_subsys(&ipv4_net_ops);
9fb9cbb1 YK	461	cleanup_sockopt:
9fb9cbb1 YK	462	nf_unregister_sockopt(&so_getorigdst);
9fb9cbb1 YK	463	return ret;
	464	}
	465
65b4b4e8	466	static void __exit nf_conntrack_l3proto_ipv4_fini(void)
9fb9cbb1	467	{
32292a7f	468	synchronize_net();
6330750d	469	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
0e54d217 DC	470	nf_ct_l4proto_unregister(builtin_l4proto4,
0e54d217 DC	471	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3	472	unregister_pernet_subsys(&ipv4_net_ops);
32292a7f	473	nf_unregister_sockopt(&so_getorigdst);
9fb9cbb1 YK	474	}
9fb9cbb1 YK	475
65b4b4e8 AM	476	module_init(nf_conntrack_l3proto_ipv4_init);
65b4b4e8 AM	477	module_exit(nf_conntrack_l3proto_ipv4_fini);