[mirror_ubuntu-bionic-kernel.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 void ipv4_print_tuple(struct seq_file *s,
			    const struct nf_conntrack_tuple *tuple)
{
	seq_printf(s, "src=%pI4 dst=%pI4 ",
		   &tuple->src.u3.ip, &tuple->dst.u3.ip);
}

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 */
		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 struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
	{
		.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));
	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;

	/* We only do TCP and SCTP at the moment: is there a better way? */
	if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != 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;
}

static int ipv4_nlattr_tuple_size(void)
{
	return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1);
}
#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,
	.name		 = "ipv4",
	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
	.invert_tuple	 = ipv4_invert_tuple,
	.print_tuple	 = ipv4_print_tuple,
	.get_l4proto	 = ipv4_get_l4proto,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
	.nlattr_tuple_size = ipv4_nlattr_tuple_size,
	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
	.nla_policy	 = ipv4_nla_policy,
#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)
{
	int ret = 0;

	ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
					    ARRAY_SIZE(builtin_l4proto4));
	if (ret < 0)
		return ret;
	ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4);
	if (ret < 0) {
		pr_err("nf_conntrack_ipv4: pernet registration failed\n");
		nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
						ARRAY_SIZE(builtin_l4proto4));
	}
	return ret;
}

static void ipv4_net_exit(struct net *net)
{
	nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
	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();

	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
824f1fbe	66	static void ipv4_print_tuple(struct seq_file *s,
9fb9cbb1 YK	67	const struct nf_conntrack_tuple *tuple)
9fb9cbb1 YK	68	{
824f1fbe JP	69	seq_printf(s, "src=%pI4 dst=%pI4 ",
824f1fbe JP	70	&tuple->src.u3.ip, &tuple->dst.u3.ip);
9fb9cbb1 YK	71	}
9fb9cbb1 YK	72
ffc30690 YK	73	static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
ffc30690 YK	74	unsigned int dataoff, u_int8_t protonum)
9fb9cbb1	75	{
32948588 JE	76	const struct iphdr *iph;
32948588 JE	77	struct iphdr _iph;
ffc30690 YK	78
	79	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
	80	if (iph == NULL)
8430eac2	81	return -NF_ACCEPT;
ffc30690	82
0fb96701 PM	83	/* Conntrack defragments packets, we might still see fragments
	84	* inside ICMP packets though. */
	85	if (iph->frag_off & htons(IP_OFFSET))
8430eac2	86	return -NF_ACCEPT;
9fb9cbb1	87
ffc30690 YK	88	*dataoff = nhoff + (iph->ihl << 2);
ffc30690 YK	89	*protonum = iph->protocol;
9fb9cbb1	90
07153c6e JK	91	/* Check bogus IP headers */
	92	if (*dataoff > skb->len) {
	93	pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
	94	"nhoff %u, ihl %u, skblen %u\n",
	95	nhoff, iph->ihl << 2, skb->len);
	96	return -NF_ACCEPT;
	97	}
	98
9fb9cbb1 YK	99	return NF_ACCEPT;
	100	}
	101
06198b34	102	static unsigned int ipv4_helper(void *priv,
12f7a505	103	struct sk_buff *skb,
238e54c9	104	const struct nf_hook_state *state)
9fb9cbb1 YK	105	{
	106	struct nf_conn *ct;
	107	enum ip_conntrack_info ctinfo;
32948588 JE	108	const struct nf_conn_help *help;
32948588 JE	109	const struct nf_conntrack_helper *helper;
9fb9cbb1 YK	110
9fb9cbb1 YK	111	/* This is where we call the helper: as the packet goes out. */
3db05fea	112	ct = nf_ct_get(skb, &ctinfo);
fb048833	113	if (!ct \|\| ctinfo == IP_CT_RELATED_REPLY)
12f7a505	114	return NF_ACCEPT;
dc808fe2 HW	115
dc808fe2 HW	116	help = nfct_help(ct);
3c158f7f	117	if (!help)
12f7a505	118	return NF_ACCEPT;
dd13b010	119
e2361cb9	120	/* rcu_read_lock()ed by nf_hook_thresh */
3c158f7f PM	121	helper = rcu_dereference(help->helper);
3c158f7f PM	122	if (!helper)
12f7a505	123	return NF_ACCEPT;
dd13b010	124
b20ab9cc PNA	125	return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
b20ab9cc PNA	126	ct, ctinfo);
12f7a505 PNA	127	}
12f7a505 PNA	128
06198b34	129	static unsigned int ipv4_confirm(void *priv,
12f7a505	130	struct sk_buff *skb,
238e54c9	131	const struct nf_hook_state *state)
12f7a505 PNA	132	{
	133	struct nf_conn *ct;
	134	enum ip_conntrack_info ctinfo;
	135
	136	ct = nf_ct_get(skb, &ctinfo);
	137	if (!ct \|\| ctinfo == IP_CT_RELATED_REPLY)
	138	goto out;
dd13b010	139
42c1edd3 JA	140	/* adjust seqs for loopback traffic only in outgoing direction */
	141	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
	142	!nf_is_loopback_packet(skb)) {
41d73ec0	143	if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
1db7a748	144	NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
dd13b010	145	return NF_DROP;
1db7a748	146	}
dd13b010 PM	147	}
	148	out:
	149	/* We've seen it coming out the other side: confirm it */
	150	return nf_conntrack_confirm(skb);
9fb9cbb1 YK	151	}
9fb9cbb1 YK	152
06198b34	153	static unsigned int ipv4_conntrack_in(void *priv,
3db05fea	154	struct sk_buff *skb,
238e54c9	155	const struct nf_hook_state *state)
9fb9cbb1	156	{
082a758f	157	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
9fb9cbb1 YK	158	}
9fb9cbb1 YK	159
06198b34	160	static unsigned int ipv4_conntrack_local(void *priv,
3db05fea	161	struct sk_buff *skb,
238e54c9	162	const struct nf_hook_state *state)
9fb9cbb1 YK	163	{
9fb9cbb1 YK	164	/* root is playing with raw sockets. */
3db05fea	165	if (skb->len < sizeof(struct iphdr) \|\|
88843104	166	ip_hdrlen(skb) < sizeof(struct iphdr))
9fb9cbb1	167	return NF_ACCEPT;
7b4fdf77 FW	168
	169	if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
	170	return NF_ACCEPT;
	171
082a758f	172	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
9fb9cbb1 YK	173	}
	174
	175	/* Connection tracking may drop packets, but never alters them, so
	176	make it the first hook. */
1999414a	177	static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
964ddaa1 PM	178	{
964ddaa1 PM	179	.hook = ipv4_conntrack_in,
57750a22	180	.pf = NFPROTO_IPV4,
6e23ae2a	181	.hooknum = NF_INET_PRE_ROUTING,
964ddaa1 PM	182	.priority = NF_IP_PRI_CONNTRACK,
964ddaa1 PM	183	},
964ddaa1 PM	184	{
964ddaa1 PM	185	.hook = ipv4_conntrack_local,
57750a22	186	.pf = NFPROTO_IPV4,
6e23ae2a	187	.hooknum = NF_INET_LOCAL_OUT,
964ddaa1 PM	188	.priority = NF_IP_PRI_CONNTRACK,
964ddaa1 PM	189	},
12f7a505 PNA	190	{
12f7a505 PNA	191	.hook = ipv4_helper,
12f7a505 PNA	192	.pf = NFPROTO_IPV4,
	193	.hooknum = NF_INET_POST_ROUTING,
	194	.priority = NF_IP_PRI_CONNTRACK_HELPER,
	195	},
964ddaa1 PM	196	{
964ddaa1 PM	197	.hook = ipv4_confirm,
57750a22	198	.pf = NFPROTO_IPV4,
6e23ae2a	199	.hooknum = NF_INET_POST_ROUTING,
964ddaa1 PM	200	.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
964ddaa1 PM	201	},
12f7a505 PNA	202	{
12f7a505 PNA	203	.hook = ipv4_helper,
12f7a505 PNA	204	.pf = NFPROTO_IPV4,
	205	.hooknum = NF_INET_LOCAL_IN,
	206	.priority = NF_IP_PRI_CONNTRACK_HELPER,
	207	},
964ddaa1 PM	208	{
964ddaa1 PM	209	.hook = ipv4_confirm,
57750a22	210	.pf = NFPROTO_IPV4,
6e23ae2a	211	.hooknum = NF_INET_LOCAL_IN,
964ddaa1 PM	212	.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
964ddaa1 PM	213	},
9fb9cbb1 YK	214	};
9fb9cbb1 YK	215
9fb9cbb1 YK	216	/* Fast function for those who don't want to parse /proc (and I don't
	217	blame them). */
	218	/* Reversing the socket's dst/src point of view gives us the reply
	219	mapping. */
	220	static int
	221	getorigdst(struct sock sk, int optval, void __user user, int *len)
	222	{
32948588 JE	223	const struct inet_sock *inet = inet_sk(sk);
32948588 JE	224	const struct nf_conntrack_tuple_hash *h;
9fb9cbb1	225	struct nf_conntrack_tuple tuple;
e905a9ed	226
443a70d5	227	memset(&tuple, 0, sizeof(tuple));
c720c7e8 ED	228	tuple.src.u3.ip = inet->inet_rcv_saddr;
	229	tuple.src.u.tcp.port = inet->inet_sport;
	230	tuple.dst.u3.ip = inet->inet_daddr;
	231	tuple.dst.u.tcp.port = inet->inet_dport;
9fb9cbb1	232	tuple.src.l3num = PF_INET;
54981279	233	tuple.dst.protonum = sk->sk_protocol;
9fb9cbb1	234
54981279 RL	235	/* We only do TCP and SCTP at the moment: is there a better way? */
	236	if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) {
	237	pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n");
9fb9cbb1 YK	238	return -ENOPROTOOPT;
	239	}
	240
	241	if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
5b5e0928	242	pr_debug("SO_ORIGINAL_DST: len %d not %zu\n",
0d53778e	243	*len, sizeof(struct sockaddr_in));
9fb9cbb1 YK	244	return -EINVAL;
	245	}
	246
308ac914	247	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
9fb9cbb1 YK	248	if (h) {
	249	struct sockaddr_in sin;
	250	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
	251
	252	sin.sin_family = AF_INET;
	253	sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
	254	.tuple.dst.u.tcp.port;
	255	sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
	256	.tuple.dst.u3.ip;
6c813c3f	257	memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
9fb9cbb1	258
cffee385 HH	259	pr_debug("SO_ORIGINAL_DST: %pI4 %u\n",
cffee385 HH	260	&sin.sin_addr.s_addr, ntohs(sin.sin_port));
9fb9cbb1 YK	261	nf_ct_put(ct);
	262	if (copy_to_user(user, &sin, sizeof(sin)) != 0)
	263	return -EFAULT;
	264	else
	265	return 0;
	266	}
cffee385 HH	267	pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n",
	268	&tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port),
	269	&tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port));
9fb9cbb1 YK	270	return -ENOENT;
	271	}
	272
24de3d37	273	#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
c1d10adb PNA	274
	275	#include <linux/netfilter/nfnetlink.h>
	276	#include <linux/netfilter/nfnetlink_conntrack.h>
	277
fdf70832	278	static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
c1d10adb PNA	279	const struct nf_conntrack_tuple *tuple)
c1d10adb PNA	280	{
930345ea JB	281	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) \|\|
930345ea JB	282	nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
d317e4f6	283	goto nla_put_failure;
c1d10adb PNA	284	return 0;
c1d10adb PNA	285
df6fb868	286	nla_put_failure:
c1d10adb PNA	287	return -1;
	288	}
	289
f73e924c PM	290	static const struct nla_policy ipv4_nla_policy[CTA_IP_MAX+1] = {
	291	[CTA_IP_V4_SRC] = { .type = NLA_U32 },
	292	[CTA_IP_V4_DST] = { .type = NLA_U32 },
c1d10adb PNA	293	};
c1d10adb PNA	294
fdf70832	295	static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
c1d10adb PNA	296	struct nf_conntrack_tuple *t)
c1d10adb PNA	297	{
df6fb868	298	if (!tb[CTA_IP_V4_SRC] \|\| !tb[CTA_IP_V4_DST])
c1d10adb PNA	299	return -EINVAL;
c1d10adb PNA	300
67b61f6c JB	301	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
67b61f6c JB	302	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
c1d10adb PNA	303
	304	return 0;
	305	}
a400c30e HE	306
	307	static int ipv4_nlattr_tuple_size(void)
	308	{
	309	return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1);
	310	}
c1d10adb PNA	311	#endif
c1d10adb PNA	312
9fb9cbb1 YK	313	static struct nf_sockopt_ops so_getorigdst = {
	314	.pf = PF_INET,
	315	.get_optmin = SO_ORIGINAL_DST,
	316	.get_optmax = SO_ORIGINAL_DST+1,
5bd3a76f	317	.get = getorigdst,
16fcec35	318	.owner = THIS_MODULE,
9fb9cbb1 YK	319	};
9fb9cbb1 YK	320
0c66dc1e FW	321	static int ipv4_hooks_register(struct net *net)
	322	{
	323	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
	324	int err = 0;
	325
	326	mutex_lock(&register_ipv4_hooks);
	327
	328	cnet->users++;
	329	if (cnet->users > 1)
	330	goto out_unlock;
	331
834184b1 FW	332	err = nf_defrag_ipv4_enable(net);
	333	if (err) {
	334	cnet->users = 0;
	335	goto out_unlock;
	336	}
	337
0c66dc1e FW	338	err = nf_register_net_hooks(net, ipv4_conntrack_ops,
	339	ARRAY_SIZE(ipv4_conntrack_ops));
	340
	341	if (err)
	342	cnet->users = 0;
	343	out_unlock:
	344	mutex_unlock(&register_ipv4_hooks);
	345	return err;
	346	}
	347
	348	static void ipv4_hooks_unregister(struct net *net)
	349	{
	350	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
	351
	352	mutex_lock(&register_ipv4_hooks);
	353	if (cnet->users && (--cnet->users == 0))
	354	nf_unregister_net_hooks(net, ipv4_conntrack_ops,
	355	ARRAY_SIZE(ipv4_conntrack_ops));
	356	mutex_unlock(&register_ipv4_hooks);
	357	}
	358
61075af5	359	struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
9fb9cbb1 YK	360	.l3proto = PF_INET,
	361	.name = "ipv4",
	362	.pkt_to_tuple = ipv4_pkt_to_tuple,
	363	.invert_tuple = ipv4_invert_tuple,
	364	.print_tuple = ipv4_print_tuple,
ffc30690	365	.get_l4proto = ipv4_get_l4proto,
24de3d37	366	#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
fdf70832	367	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
a400c30e	368	.nlattr_tuple_size = ipv4_nlattr_tuple_size,
fdf70832	369	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
f73e924c	370	.nla_policy = ipv4_nla_policy,
c1d10adb	371	#endif
0c66dc1e FW	372	.net_ns_get = ipv4_hooks_register,
0c66dc1e FW	373	.net_ns_put = ipv4_hooks_unregister,
9fb9cbb1 YK	374	.me = THIS_MODULE,
	375	};
	376
fae718dd PM	377	module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
	378	&nf_conntrack_htable_size, 0600);
	379
32292a7f	380	MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
d2483dde	381	MODULE_ALIAS("ip_conntrack");
32292a7f PM	382	MODULE_LICENSE("GPL");
32292a7f PM	383
0e54d217 DC	384	static struct nf_conntrack_l4proto *builtin_l4proto4[] = {
	385	&nf_conntrack_l4proto_tcp4,
	386	&nf_conntrack_l4proto_udp4,
	387	&nf_conntrack_l4proto_icmp,
c51d3901 DC	388	#ifdef CONFIG_NF_CT_PROTO_DCCP
	389	&nf_conntrack_l4proto_dccp4,
	390	#endif
a85406af DC	391	#ifdef CONFIG_NF_CT_PROTO_SCTP
	392	&nf_conntrack_l4proto_sctp4,
	393	#endif
9b91c96c DC	394	#ifdef CONFIG_NF_CT_PROTO_UDPLITE
	395	&nf_conntrack_l4proto_udplite4,
	396	#endif
0e54d217 DC	397	};
0e54d217 DC	398
3ea04dd3 G	399	static int ipv4_net_init(struct net *net)
	400	{
	401	int ret = 0;
	402
0e54d217 DC	403	ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
	404	ARRAY_SIZE(builtin_l4proto4));
	405	if (ret < 0)
	406	return ret;
6330750d	407	ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4);
3ea04dd3	408	if (ret < 0) {
6330750d	409	pr_err("nf_conntrack_ipv4: pernet registration failed\n");
0e54d217 DC	410	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
0e54d217 DC	411	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3	412	}
3ea04dd3 G	413	return ret;
	414	}
	415
	416	static void ipv4_net_exit(struct net *net)
	417	{
6330750d	418	nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
0e54d217 DC	419	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
0e54d217 DC	420	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3 G	421	}
	422
	423	static struct pernet_operations ipv4_net_ops = {
	424	.init = ipv4_net_init,
	425	.exit = ipv4_net_exit,
0c66dc1e FW	426	.id = &conntrack4_net_id,
0c66dc1e FW	427	.size = sizeof(struct conntrack4_net),
3ea04dd3 G	428	};
3ea04dd3 G	429
32292a7f	430	static int __init nf_conntrack_l3proto_ipv4_init(void)
9fb9cbb1 YK	431	{
	432	int ret = 0;
	433
32292a7f	434	need_conntrack();
9fb9cbb1 YK	435
	436	ret = nf_register_sockopt(&so_getorigdst);
	437	if (ret < 0) {
09605cc1	438	pr_err("Unable to register netfilter socket option\n");
32292a7f	439	return ret;
9fb9cbb1 YK	440	}
9fb9cbb1 YK	441
3ea04dd3	442	ret = register_pernet_subsys(&ipv4_net_ops);
9fb9cbb1	443	if (ret < 0) {
3ea04dd3	444	pr_err("nf_conntrack_ipv4: can't register pernet ops\n");
9fb9cbb1 YK	445	goto cleanup_sockopt;
	446	}
	447
0e54d217 DC	448	ret = nf_ct_l4proto_register(builtin_l4proto4,
	449	ARRAY_SIZE(builtin_l4proto4));
	450	if (ret < 0)
0c66dc1e	451	goto cleanup_pernet;
c296bb4d	452
6330750d G	453	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
	454	if (ret < 0) {
	455	pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
0e54d217	456	goto cleanup_l4proto;
6330750d G	457	}
6330750d G	458
9fb9cbb1	459	return ret;
0e54d217 DC	460	cleanup_l4proto:
	461	nf_ct_l4proto_unregister(builtin_l4proto4,
	462	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3 G	463	cleanup_pernet:
3ea04dd3 G	464	unregister_pernet_subsys(&ipv4_net_ops);
9fb9cbb1 YK	465	cleanup_sockopt:
9fb9cbb1 YK	466	nf_unregister_sockopt(&so_getorigdst);
9fb9cbb1 YK	467	return ret;
	468	}
	469
65b4b4e8	470	static void __exit nf_conntrack_l3proto_ipv4_fini(void)
9fb9cbb1	471	{
32292a7f	472	synchronize_net();
6330750d	473	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
0e54d217 DC	474	nf_ct_l4proto_unregister(builtin_l4proto4,
0e54d217 DC	475	ARRAY_SIZE(builtin_l4proto4));
3ea04dd3	476	unregister_pernet_subsys(&ipv4_net_ops);
32292a7f	477	nf_unregister_sockopt(&so_getorigdst);
9fb9cbb1 YK	478	}
9fb9cbb1 YK	479
65b4b4e8 AM	480	module_init(nf_conntrack_l3proto_ipv4_init);
65b4b4e8 AM	481	module_exit(nf_conntrack_l3proto_ipv4_fini);