aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ip_gre.c1
-rw-r--r--net/ipv4/ip_input.c15
-rw-r--r--net/ipv4/ip_output.c10
-rw-r--r--net/ipv4/ipip.c1
-rw-r--r--net/ipv4/netfilter.c15
-rw-r--r--net/ipv4/netfilter/Kconfig10
-rw-r--r--net/ipv4/netfilter/Makefile1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_proto_sctp.c1
-rw-r--r--net/ipv4/netfilter/ip_nat_standalone.c109
-rw-r--r--net/ipv4/netfilter/ipt_policy.c170
-rw-r--r--net/ipv4/raw.c1
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv4/xfrm4_input.c31
-rw-r--r--net/ipv4/xfrm4_output.c72
15 files changed, 392 insertions, 48 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 912c42f57c7..de16e944777 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -832,6 +832,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
skb->h.raw = skb->nh.raw;
skb->nh.raw = skb_push(skb, gre_hlen);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED);
dst_release(skb->dst);
skb->dst = &rt->u.dst;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e45846ae570..18d7fad474d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -185,7 +185,6 @@ int ip_call_ra_chain(struct sk_buff *skb)
raw_rcv(last, skb2);
}
last = sk;
- nf_reset(skb);
}
}
@@ -204,10 +203,6 @@ static inline int ip_local_deliver_finish(struct sk_buff *skb)
__skb_pull(skb, ihl);
- /* Free reference early: we don't need it any more, and it may
- hold ip_conntrack module loaded indefinitely. */
- nf_reset(skb);
-
/* Point into the IP datagram, just past the header. */
skb->h.raw = skb->data;
@@ -232,10 +227,12 @@ static inline int ip_local_deliver_finish(struct sk_buff *skb)
if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
int ret;
- if (!ipprot->no_policy &&
- !xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- kfree_skb(skb);
- goto out;
+ if (!ipprot->no_policy) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+ kfree_skb(skb);
+ goto out;
+ }
+ nf_reset(skb);
}
ret = ipprot->handler(skb);
if (ret < 0) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8b1c9bd0091..c2169b47ddf 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -85,6 +85,8 @@
int sysctl_ip_default_ttl = IPDEFTTL;
+static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*));
+
/* Generate a checksum for an outgoing IP datagram. */
__inline__ void ip_send_check(struct iphdr *iph)
{
@@ -202,6 +204,11 @@ static inline int ip_finish_output2(struct sk_buff *skb)
static inline int ip_finish_output(struct sk_buff *skb)
{
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
+ /* Policy lookup after SNAT yielded a new policy */
+ if (skb->dst->xfrm != NULL)
+ return xfrm4_output_finish(skb);
+#endif
if (skb->len > dst_mtu(skb->dst) &&
!(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
return ip_fragment(skb, ip_finish_output2);
@@ -409,7 +416,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
* single device frame, and queue such a frame for sending.
*/
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
+static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
{
struct iphdr *iph;
int raw = 0;
@@ -1391,7 +1398,6 @@ void __init ip_init(void)
#endif
}
-EXPORT_SYMBOL(ip_fragment);
EXPORT_SYMBOL(ip_generic_getfrag);
EXPORT_SYMBOL(ip_queue_xmit);
EXPORT_SYMBOL(ip_send_check);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 35571cff81c..bbd85f5ec98 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -621,6 +621,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
skb->h.raw = skb->nh.raw;
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED);
dst_release(skb->dst);
skb->dst = &rt->u.dst;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index ae0779d82c5..3321092b091 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -7,11 +7,13 @@
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
+#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <net/route.h>
-#include <linux/ip.h>
+#include <net/xfrm.h>
+#include <net/ip.h>
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff **pskb)
@@ -33,7 +35,6 @@ int ip_route_me_harder(struct sk_buff **pskb)
#ifdef CONFIG_IP_ROUTE_FWMARK
fl.nl_u.ip4_u.fwmark = (*pskb)->nfmark;
#endif
- fl.proto = iph->protocol;
if (ip_route_output_key(&rt, &fl) != 0)
return -1;
@@ -60,6 +61,13 @@ int ip_route_me_harder(struct sk_buff **pskb)
if ((*pskb)->dst->error)
return -1;
+#ifdef CONFIG_XFRM
+ if (!(IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+ xfrm_decode_session(*pskb, &fl, AF_INET) == 0)
+ if (xfrm_lookup(&(*pskb)->dst, &fl, (*pskb)->sk, 0))
+ return -1;
+#endif
+
/* Change in oif may mean change in hh_len. */
hh_len = (*pskb)->dst->dev->hard_header_len;
if (skb_headroom(*pskb) < hh_len) {
@@ -78,6 +86,9 @@ int ip_route_me_harder(struct sk_buff **pskb)
}
EXPORT_SYMBOL(ip_route_me_harder);
+void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
+EXPORT_SYMBOL(ip_nat_decode_session);
+
/*
* Extra routing may needed on local out, as the QUEUE target never
* returns control to the table.
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 88a60650e6b..a9893ec03e0 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -487,6 +487,16 @@ config IP_NF_MATCH_STRING
To compile it as a module, choose M here. If unsure, say N.
+config IP_NF_MATCH_POLICY
+ tristate "IPsec policy match support"
+ depends on IP_NF_IPTABLES && XFRM
+ help
+ Policy matching allows you to match packets based on the
+ IPsec policy that was used during decapsulation/will
+ be used during encapsulation.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
# `filter', generic and specific targets
config IP_NF_FILTER
tristate "Packet filtering"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index d0a447e520a..549b01a648b 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -72,6 +72,7 @@ obj-$(CONFIG_IP_NF_MATCH_TCPMSS) += ipt_tcpmss.o
obj-$(CONFIG_IP_NF_MATCH_REALM) += ipt_realm.o
obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o
obj-$(CONFIG_IP_NF_MATCH_PHYSDEV) += ipt_physdev.o
+obj-$(CONFIG_IP_NF_MATCH_POLICY) += ipt_policy.o
obj-$(CONFIG_IP_NF_MATCH_COMMENT) += ipt_comment.o
obj-$(CONFIG_IP_NF_MATCH_STRING) += ipt_string.o
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c
index 977fb59d456..0b25050981a 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c
@@ -16,6 +16,7 @@
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/timer.h>
+#include <linux/interrupt.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/in.h>
diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c
index f04111f74e0..8b8a1f00bbf 100644
--- a/net/ipv4/netfilter/ip_nat_standalone.c
+++ b/net/ipv4/netfilter/ip_nat_standalone.c
@@ -55,6 +55,44 @@
: ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN" \
: "*ERROR*")))
+#ifdef CONFIG_XFRM
+static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
+{
+ struct ip_conntrack *ct;
+ struct ip_conntrack_tuple *t;
+ enum ip_conntrack_info ctinfo;
+ enum ip_conntrack_dir dir;
+ unsigned long statusbit;
+
+ ct = ip_conntrack_get(skb, &ctinfo);
+ if (ct == NULL)
+ return;
+ dir = CTINFO2DIR(ctinfo);
+ t = &ct->tuplehash[dir].tuple;
+
+ if (dir == IP_CT_DIR_ORIGINAL)
+ statusbit = IPS_DST_NAT;
+ else
+ statusbit = IPS_SRC_NAT;
+
+ if (ct->status & statusbit) {
+ fl->fl4_dst = t->dst.ip;
+ if (t->dst.protonum == IPPROTO_TCP ||
+ t->dst.protonum == IPPROTO_UDP)
+ fl->fl_ip_dport = t->dst.u.tcp.port;
+ }
+
+ statusbit ^= IPS_NAT_MASK;
+
+ if (ct->status & statusbit) {
+ fl->fl4_src = t->src.ip;
+ if (t->dst.protonum == IPPROTO_TCP ||
+ t->dst.protonum == IPPROTO_UDP)
+ fl->fl_ip_sport = t->src.u.tcp.port;
+ }
+}
+#endif
+
static unsigned int
ip_nat_fn(unsigned int hooknum,
struct sk_buff **pskb,
@@ -162,18 +200,20 @@ ip_nat_in(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- u_int32_t saddr, daddr;
+ struct ip_conntrack *ct;
+ enum ip_conntrack_info ctinfo;
unsigned int ret;
- saddr = (*pskb)->nh.iph->saddr;
- daddr = (*pskb)->nh.iph->daddr;
-
ret = ip_nat_fn(hooknum, pskb, in, out, okfn);
if (ret != NF_DROP && ret != NF_STOLEN
- && ((*pskb)->nh.iph->saddr != saddr
- || (*pskb)->nh.iph->daddr != daddr)) {
- dst_release((*pskb)->dst);
- (*pskb)->dst = NULL;
+ && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) {
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+ if (ct->tuplehash[dir].tuple.src.ip !=
+ ct->tuplehash[!dir].tuple.dst.ip) {
+ dst_release((*pskb)->dst);
+ (*pskb)->dst = NULL;
+ }
}
return ret;
}
@@ -185,12 +225,30 @@ ip_nat_out(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
+ struct ip_conntrack *ct;
+ enum ip_conntrack_info ctinfo;
+ unsigned int ret;
+
/* root is playing with raw sockets. */
if ((*pskb)->len < sizeof(struct iphdr)
|| (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr))
return NF_ACCEPT;
- return ip_nat_fn(hooknum, pskb, in, out, okfn);
+ ret = ip_nat_fn(hooknum, pskb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_STOLEN
+ && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) {
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+ if (ct->tuplehash[dir].tuple.src.ip !=
+ ct->tuplehash[!dir].tuple.dst.ip
+#ifdef CONFIG_XFRM
+ || ct->tuplehash[dir].tuple.src.u.all !=
+ ct->tuplehash[!dir].tuple.dst.u.all
+#endif
+ )
+ return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
+ }
+ return ret;
}
static unsigned int
@@ -200,7 +258,8 @@ ip_nat_local_fn(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- u_int32_t saddr, daddr;
+ struct ip_conntrack *ct;
+ enum ip_conntrack_info ctinfo;
unsigned int ret;
/* root is playing with raw sockets. */
@@ -208,14 +267,20 @@ ip_nat_local_fn(unsigned int hooknum,
|| (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr))
return NF_ACCEPT;
- saddr = (*pskb)->nh.iph->saddr;
- daddr = (*pskb)->nh.iph->daddr;
-
ret = ip_nat_fn(hooknum, pskb, in, out, okfn);
if (ret != NF_DROP && ret != NF_STOLEN
- && ((*pskb)->nh.iph->saddr != saddr
- || (*pskb)->nh.iph->daddr != daddr))
- return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
+ && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) {
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+ if (ct->tuplehash[dir].tuple.dst.ip !=
+ ct->tuplehash[!dir].tuple.src.ip
+#ifdef CONFIG_XFRM
+ || ct->tuplehash[dir].tuple.dst.u.all !=
+ ct->tuplehash[dir].tuple.src.u.all
+#endif
+ )
+ return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
+ }
return ret;
}
@@ -303,10 +368,14 @@ static int init_or_cleanup(int init)
if (!init) goto cleanup;
+#ifdef CONFIG_XFRM
+ BUG_ON(ip_nat_decode_session != NULL);
+ ip_nat_decode_session = nat_decode_session;
+#endif
ret = ip_nat_rule_init();
if (ret < 0) {
printk("ip_nat_init: can't setup rules.\n");
- goto cleanup_nothing;
+ goto cleanup_decode_session;
}
ret = nf_register_hook(&ip_nat_in_ops);
if (ret < 0) {
@@ -354,7 +423,11 @@ static int init_or_cleanup(int init)
nf_unregister_hook(&ip_nat_in_ops);
cleanup_rule_init:
ip_nat_rule_cleanup();
- cleanup_nothing:
+ cleanup_decode_session:
+#ifdef CONFIG_XFRM
+ ip_nat_decode_session = NULL;
+ synchronize_net();
+#endif
return ret;
}
diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c
new file mode 100644
index 00000000000..709debcc69c
--- /dev/null
+++ b/net/ipv4/netfilter/ipt_policy.c
@@ -0,0 +1,170 @@
+/* IP tables module for matching IPsec policy
+ *
+ * Copyright (c) 2004,2005 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/kernel.h>
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <net/xfrm.h>
+
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv4/ipt_policy.h>
+
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("IPtables IPsec policy matching module");
+MODULE_LICENSE("GPL");
+
+
+static inline int
+match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e)
+{
+#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x))
+
+ return MATCH(saddr, x->props.saddr.a4 & e->smask) &&
+ MATCH(daddr, x->id.daddr.a4 & e->dmask) &&
+ MATCH(proto, x->id.proto) &&
+ MATCH(mode, x->props.mode) &&
+ MATCH(spi, x->id.spi) &&
+ MATCH(reqid, x->props.reqid);
+}
+
+static int
+match_policy_in(const struct sk_buff *skb, const struct ipt_policy_info *info)
+{
+ const struct ipt_policy_elem *e;
+ struct sec_path *sp = skb->sp;
+ int strict = info->flags & IPT_POLICY_MATCH_STRICT;
+ int i, pos;
+
+ if (sp == NULL)
+ return -1;
+ if (strict && info->len != sp->len)
+ return 0;
+
+ for (i = sp->len - 1; i >= 0; i--) {
+ pos = strict ? i - sp->len + 1 : 0;
+ if (pos >= info->len)
+ return 0;
+ e = &info->pol[pos];
+
+ if (match_xfrm_state(sp->x[i].xvec, e)) {
+ if (!strict)
+ return 1;
+ } else if (strict)
+ return 0;
+ }
+
+ return strict ? 1 : 0;
+}
+
+static int
+match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info)
+{
+ const struct ipt_policy_elem *e;
+ struct dst_entry *dst = skb->dst;
+ int strict = info->flags & IPT_POLICY_MATCH_STRICT;
+ int i, pos;
+
+ if (dst->xfrm == NULL)
+ return -1;
+
+ for (i = 0; dst && dst->xfrm; dst = dst->child, i++) {
+ pos = strict ? i : 0;
+ if (pos >= info->len)
+ return 0;
+ e = &info->pol[pos];
+
+ if (match_xfrm_state(dst->xfrm, e)) {
+ if (!strict)
+ return 1;
+ } else if (strict)
+ return 0;
+ }
+
+ return strict ? 1 : 0;
+}
+
+static int match(const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const void *matchinfo, int offset, int *hotdrop)
+{
+ const struct ipt_policy_info *info = matchinfo;
+ int ret;
+
+ if (info->flags & IPT_POLICY_MATCH_IN)
+ ret = match_policy_in(skb, info);
+ else
+ ret = match_policy_out(skb, info);
+
+ if (ret < 0)
+ ret = info->flags & IPT_POLICY_MATCH_NONE ? 1 : 0;
+ else if (info->flags & IPT_POLICY_MATCH_NONE)
+ ret = 0;
+
+ return ret;
+}
+
+static int checkentry(const char *tablename, const struct ipt_ip *ip,
+ void *matchinfo, unsigned int matchsize,
+ unsigned int hook_mask)
+{
+ struct ipt_policy_info *info = matchinfo;
+
+ if (matchsize != IPT_ALIGN(sizeof(*info))) {
+ printk(KERN_ERR "ipt_policy: matchsize %u != %zu\n",
+ matchsize, IPT_ALIGN(sizeof(*info)));
+ return 0;
+ }
+ if (!(info->flags & (IPT_POLICY_MATCH_IN|IPT_POLICY_MATCH_OUT))) {
+ printk(KERN_ERR "ipt_policy: neither incoming nor "
+ "outgoing policy selected\n");
+ return 0;
+ }
+ if (hook_mask & (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_LOCAL_IN)
+ && info->flags & IPT_POLICY_MATCH_OUT) {
+ printk(KERN_ERR "ipt_policy: output policy not valid in "
+ "PRE_ROUTING and INPUT\n");
+ return 0;
+ }
+ if (hook_mask & (1 << NF_IP_POST_ROUTING | 1 << NF_IP_LOCAL_OUT)
+ && info->flags & IPT_POLICY_MATCH_IN) {
+ printk(KERN_ERR "ipt_policy: input policy not valid in "
+ "POST_ROUTING and OUTPUT\n");
+ return 0;
+ }
+ if (info->len > IPT_POLICY_MAX_ELEM) {
+ printk(KERN_ERR "ipt_policy: too many policy elements\n");
+ return 0;
+ }
+
+ return 1;
+}
+
+static struct ipt_match policy_match = {
+ .name = "policy",
+ .match = match,
+ .checkentry = checkentry,
+ .me = THIS_MODULE,
+};
+
+static int __init init(void)
+{
+ return ipt_register_match(&policy_match);
+}
+
+static void __exit fini(void)
+{
+ ipt_unregister_match(&policy_match);
+}
+
+module_init(init);
+module_exit(fini);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4b0d7e4d626..165a4d81efa 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -255,6 +255,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
kfree_skb(skb);
return NET_RX_DROP;
}
+ nf_reset(skb);
skb_push(skb, skb->data - skb->nh.raw);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e9f83e5b28c..6ea353907af 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1080,6 +1080,7 @@ process:
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
+ nf_reset(skb);
if (sk_filter(sk, skb, 0))
goto discard_and_relse;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 223abaa72bc..00840474a44 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -989,6 +989,7 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
kfree_skb(skb);
return -1;
}
+ nf_reset(skb);
if (up->encap_type) {
/*
@@ -1149,6 +1150,7 @@ int udp_rcv(struct sk_buff *skb)
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
+ nf_reset(skb);
/* No socket. Drop packet silently, if checksum is wrong */
if (udp_checksum_complete(skb))
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 2d3849c38a0..850d919591d 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -11,6 +11,8 @@
#include <linux/module.h>
#include <linux/string.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/xfrm.h>
@@ -45,6 +47,23 @@ static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq)
return xfrm_parse_spi(skb, nexthdr, spi, seq);
}
+#ifdef CONFIG_NETFILTER
+static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
+{
+ struct iphdr *iph = skb->nh.iph;
+
+ if (skb->dst == NULL) {
+ if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
+ skb->dev))
+ goto drop;
+ }
+ return dst_input(skb);
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+#endif
+
int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type)
{
int err;
@@ -137,6 +156,8 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type)
memcpy(skb->sp->x+skb->sp->len, xfrm_vec, xfrm_nr*sizeof(struct sec_decap_state));
skb->sp->len += xfrm_nr;
+ nf_reset(skb);
+
if (decaps) {
if (!(skb->dev->flags&IFF_LOOPBACK)) {
dst_release(skb->dst);
@@ -145,7 +166,17 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type)
netif_rx(skb);
return 0;
} else {
+#ifdef CONFIG_NETFILTER
+ __skb_push(skb, skb->data - skb->nh.raw);
+ skb->nh.iph->tot_len = htons(skb->len);
+ ip_send_check(skb->nh.iph);
+
+ NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+ xfrm4_rcv_encap_finish);
+ return 0;
+#else
return -skb->nh.iph->protocol;
+#endif
}
drop_unlock:
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 66620a95942..d4df0ddd424 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -8,8 +8,10 @@
* 2 of the License, or (at your option) any later version.
*/
+#include <linux/compiler.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
+#include <linux/netfilter_ipv4.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/xfrm.h>
@@ -95,7 +97,7 @@ out:
return ret;
}
-int xfrm4_output(struct sk_buff *skb)
+static int xfrm4_output_one(struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
struct xfrm_state *x = dst->xfrm;
@@ -113,27 +115,33 @@ int xfrm4_output(struct sk_buff *skb)
goto error_nolock;
}
- spin_lock_bh(&x->lock);
- err = xfrm_state_check(x, skb);
- if (err)
- goto error;
+ do {
+ spin_lock_bh(&x->lock);
+ err = xfrm_state_check(x, skb);
+ if (err)
+ goto error;
- xfrm4_encap(skb);
+ xfrm4_encap(skb);
- err = x->type->output(x, skb);
- if (err)
- goto error;
+ err = x->type->output(x, skb);
+ if (err)
+ goto error;
- x->curlft.bytes += skb->len;
- x->curlft.packets++;
+ x->curlft.bytes += skb->len;
+ x->curlft.packets++;
- spin_unlock_bh(&x->lock);
+ spin_unlock_bh(&x->lock);
- if (!(skb->dst = dst_pop(dst))) {
- err = -EHOSTUNREACH;
- goto error_nolock;
- }
- err = NET_XMIT_BYPASS;
+ if (!(skb->dst = dst_pop(dst))) {
+ err = -EHOSTUNREACH;
+ goto error_nolock;
+ }
+ dst = skb->dst;
+ x = dst->xfrm;
+ } while (x && !x->props.mode);
+
+ IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+ err = 0;
out_exit:
return err;
@@ -143,3 +151,33 @@ error_nolock:
kfree_skb(skb);
goto out_exit;
}
+
+int xfrm4_output_finish(struct sk_buff *skb)
+{
+ int err;
+
+ while (likely((err = xfrm4_output_one(skb)) == 0)) {
+ nf_reset(skb);
+
+ err = nf_hook(PF_INET, NF_IP_LOCAL_OUT, &skb, NULL,
+ skb->dst->dev, dst_output);
+ if (unlikely(err != 1))
+ break;
+
+ if (!skb->dst->xfrm)
+ return dst_output(skb);
+
+ err = nf_hook(PF_INET, NF_IP_POST_ROUTING, &skb, NULL,
+ skb->dst->dev, xfrm4_output_finish);
+ if (unlikely(err != 1))
+ break;
+ }
+
+ return err;
+}
+
+int xfrm4_output(struct sk_buff *skb)
+{
+ return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev,
+ xfrm4_output_finish);
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-24 01:03:55 +0000