+
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.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>
+
+int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
+ struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo);
+EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook);
-static int ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
- struct nf_conntrack_tuple *tuple)
+static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
+ struct nf_conntrack_tuple *tuple)
{
- __be32 _addrs[2], *ap;
+ 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 0;
+ return false;
tuple->src.u3.ip = ap[0];
tuple->dst.u3.ip = ap[1];
- return 1;
+ return true;
}
-static int ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
- const struct nf_conntrack_tuple *orig)
+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 1;
+ return true;
}
static int ipv4_print_tuple(struct seq_file *s,
const struct nf_conntrack_tuple *tuple)
{
- return seq_printf(s, "src=%u.%u.%u.%u dst=%u.%u.%u.%u ",
- NIPQUAD(tuple->src.u3.ip),
- NIPQUAD(tuple->dst.u3.ip));
-}
-
-static int ipv4_print_conntrack(struct seq_file *s,
- const struct nf_conn *conntrack)
-{
- return 0;
-}
-
-/* Returns new sk_buff, or NULL */
-static struct sk_buff *
-nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
-{
- skb_orphan(skb);
-
- local_bh_disable();
- skb = ip_defrag(skb, user);
- local_bh_enable();
-
- if (skb)
- ip_send_check(ip_hdr(skb));
-
- return skb;
+ return 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)
{
- struct iphdr _iph, *iph;
+ const struct iphdr *iph;
+ struct iphdr _iph;
iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
if (iph == NULL)
return -NF_DROP;
- /* Never happen */
- if (iph->frag_off & htons(IP_OFFSET)) {
- if (net_ratelimit()) {
- printk(KERN_ERR "ipv4_get_l4proto: Frag of proto %u\n",
- iph->protocol);
- }
+ /* Conntrack defragments packets, we might still see fragments
+ * inside ICMP packets though. */
+ if (iph->frag_off & htons(IP_OFFSET))
return -NF_DROP;
- }
*dataoff = nhoff + (iph->ihl << 2);
*protonum = iph->protocol;
}
static unsigned int ipv4_confirm(unsigned int hooknum,
- struct sk_buff **pskb,
+ struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- /* We've seen it coming out the other side: confirm it */
- return nf_conntrack_confirm(pskb);
-}
-
-static unsigned int ipv4_conntrack_help(unsigned int hooknum,
- struct sk_buff **pskb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
- struct nf_conn_help *help;
- struct nf_conntrack_helper *helper;
+ const struct nf_conn_help *help;
+ const struct nf_conntrack_helper *helper;
+ unsigned int ret;
/* This is where we call the helper: as the packet goes out. */
- ct = nf_ct_get(*pskb, &ctinfo);
+ ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
- return NF_ACCEPT;
+ goto out;
help = nfct_help(ct);
if (!help)
- return NF_ACCEPT;
+ goto out;
+
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
- return NF_ACCEPT;
- return helper->help(pskb, skb_network_offset(*pskb) + ip_hdrlen(*pskb),
- ct, ctinfo);
-}
+ goto out;
-static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
- struct sk_buff **pskb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- /* Previously seen (loopback)? Ignore. Do this before
- fragment check. */
- if ((*pskb)->nfct)
- return NF_ACCEPT;
+ ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
+ ct, ctinfo);
+ if (ret != NF_ACCEPT) {
+ nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL,
+ "nf_ct_%s: dropping packet", helper->name);
+ return ret;
+ }
- /* Gather fragments. */
- if (ip_hdr(*pskb)->frag_off & htons(IP_MF | IP_OFFSET)) {
- *pskb = nf_ct_ipv4_gather_frags(*pskb,
- hooknum == NF_IP_PRE_ROUTING ?
- IP_DEFRAG_CONNTRACK_IN :
- IP_DEFRAG_CONNTRACK_OUT);
- if (!*pskb)
- return NF_STOLEN;
+ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) {
+ typeof(nf_nat_seq_adjust_hook) seq_adjust;
+
+ seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
+ if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
+ NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+ return NF_DROP;
+ }
}
- return NF_ACCEPT;
+out:
+ /* We've seen it coming out the other side: confirm it */
+ return nf_conntrack_confirm(skb);
}
static unsigned int ipv4_conntrack_in(unsigned int hooknum,
- struct sk_buff **pskb,
+ struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return nf_conntrack_in(PF_INET, hooknum, pskb);
+ return nf_conntrack_in(dev_net(in), PF_INET, hooknum, skb);
}
static unsigned int ipv4_conntrack_local(unsigned int hooknum,
- struct sk_buff **pskb,
+ struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
/* root is playing with raw sockets. */
- if ((*pskb)->len < sizeof(struct iphdr)
- || ip_hdrlen(*pskb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("ipt_hook: happy cracking.\n");
+ if (skb->len < sizeof(struct iphdr) ||
+ ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
- return nf_conntrack_in(PF_INET, hooknum, pskb);
+ return nf_conntrack_in(dev_net(out), PF_INET, hooknum, skb);
}
/* Connection tracking may drop packets, but never alters them, so
make it the first hook. */
-static struct nf_hook_ops ipv4_conntrack_ops[] = {
- {
- .hook = ipv4_conntrack_defrag,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_PRE_ROUTING,
- .priority = NF_IP_PRI_CONNTRACK_DEFRAG,
- },
+static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
{
.hook = ipv4_conntrack_in,
.owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_PRE_ROUTING,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_CONNTRACK,
},
{
- .hook = ipv4_conntrack_defrag,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_LOCAL_OUT,
- .priority = NF_IP_PRI_CONNTRACK_DEFRAG,
- },
- {
.hook = ipv4_conntrack_local,
.owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_LOCAL_OUT,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_CONNTRACK,
},
{
- .hook = ipv4_conntrack_help,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_POST_ROUTING,
- .priority = NF_IP_PRI_CONNTRACK_HELPER,
- },
- {
- .hook = ipv4_conntrack_help,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_LOCAL_IN,
- .priority = NF_IP_PRI_CONNTRACK_HELPER,
- },
- {
.hook = ipv4_confirm,
.owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_POST_ROUTING,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
},
{
.hook = ipv4_confirm,
.owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_LOCAL_IN,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
},
};
.data = &nf_conntrack_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_COUNT,
.procname = "ip_conntrack_count",
- .data = &nf_conntrack_count,
+ .data = &init_net.ct.count,
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_BUCKETS,
.data = &nf_conntrack_htable_size,
.maxlen = sizeof(unsigned int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_CHECKSUM,
.procname = "ip_conntrack_checksum",
- .data = &nf_conntrack_checksum,
+ .data = &init_net.ct.sysctl_checksum,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.ctl_name = NET_IPV4_NF_CONNTRACK_LOG_INVALID,
.procname = "ip_conntrack_log_invalid",
- .data = &nf_ct_log_invalid,
+ .data = &init_net.ct.sysctl_log_invalid,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
+ .strategy = sysctl_intvec,
.extra1 = &log_invalid_proto_min,
.extra2 = &log_invalid_proto_max,
},
static int
getorigdst(struct sock *sk, int optval, void __user *user, int *len)
{
- struct inet_sock *inet = inet_sk(sk);
- struct nf_conntrack_tuple_hash *h;
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_tuple tuple;
- NF_CT_TUPLE_U_BLANK(&tuple);
+ memset(&tuple, 0, sizeof(tuple));
tuple.src.u3.ip = inet->rcv_saddr;
tuple.src.u.tcp.port = inet->sport;
tuple.dst.u3.ip = inet->daddr;
tuple.dst.u.tcp.port = inet->dport;
tuple.src.l3num = PF_INET;
- tuple.dst.protonum = IPPROTO_TCP;
+ tuple.dst.protonum = sk->sk_protocol;
- /* We only do TCP at the moment: is there a better way? */
- if (strcmp(sk->sk_prot->name, "TCP")) {
- pr_debug("SO_ORIGINAL_DST: Not a TCP socket\n");
+ /* 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;
}
return -EINVAL;
}
- h = nf_conntrack_find_get(&tuple);
+ h = nf_conntrack_find_get(sock_net(sk), &tuple);
if (h) {
struct sockaddr_in sin;
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
.tuple.dst.u3.ip;
memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
- pr_debug("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n",
- NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
+ 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 %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n",
- NIPQUAD(tuple.src.u3.ip), ntohs(tuple.src.u.tcp.port),
- NIPQUAD(tuple.dst.u3.ip), ntohs(tuple.dst.u.tcp.port));
+ 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;
}
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
-static int ipv4_tuple_to_nfattr(struct sk_buff *skb,
+static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple)
{
- NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t),
- &tuple->src.u3.ip);
- NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t),
- &tuple->dst.u3.ip);
+ NLA_PUT_BE32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip);
+ NLA_PUT_BE32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip);
return 0;
-nfattr_failure:
+nla_put_failure:
return -1;
}
-static const size_t cta_min_ip[CTA_IP_MAX] = {
- [CTA_IP_V4_SRC-1] = sizeof(u_int32_t),
- [CTA_IP_V4_DST-1] = sizeof(u_int32_t),
+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_nfattr_to_tuple(struct nfattr *tb[],
+static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
struct nf_conntrack_tuple *t)
{
- if (!tb[CTA_IP_V4_SRC-1] || !tb[CTA_IP_V4_DST-1])
+ if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
return -EINVAL;
- if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip))
- return -EINVAL;
-
- t->src.u3.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_SRC-1]);
- t->dst.u3.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_DST-1]);
+ t->src.u3.ip = nla_get_be32(tb[CTA_IP_V4_SRC]);
+ t->dst.u3.ip = nla_get_be32(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 = {
.get_optmin = SO_ORIGINAL_DST,
.get_optmax = SO_ORIGINAL_DST+1,
.get = &getorigdst,
+ .owner = THIS_MODULE,
};
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
.pkt_to_tuple = ipv4_pkt_to_tuple,
.invert_tuple = ipv4_invert_tuple,
.print_tuple = ipv4_print_tuple,
- .print_conntrack = ipv4_print_conntrack,
.get_l4proto = ipv4_get_l4proto,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
- .tuple_to_nfattr = ipv4_tuple_to_nfattr,
- .nfattr_to_tuple = ipv4_nfattr_to_tuple,
+ .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
#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
.ctl_table_path = nf_net_ipv4_netfilter_sysctl_path,
.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");
int ret = 0;
need_conntrack();
+ nf_defrag_ipv4_enable();
ret = nf_register_sockopt(&so_getorigdst);
if (ret < 0) {
module_init(nf_conntrack_l3proto_ipv4_init);
module_exit(nf_conntrack_l3proto_ipv4_fini);
+
+void need_ipv4_conntrack(void)
+{
+ return;
+}
+EXPORT_SYMBOL_GPL(need_ipv4_conntrack);