linux/net/ipv4/xfrm4_policy.c

390 lines
8.6 KiB
C
Raw Normal View History

/*
* xfrm4_policy.c
*
* Changes:
* Kazunori MIYAZAWA @USAGI
* YOSHIFUJI Hideaki @USAGI
* Split up af-specific portion
*
*/
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/inetdevice.h>
#include <linux/if_tunnel.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/l3mdev.h>
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
struct rtable *rt;
memset(fl4, 0, sizeof(*fl4));
fl4->daddr = daddr->a4;
fl4->flowi4_tos = tos;
fl4->flowi4_oif = oif;
if (saddr)
fl4->saddr = saddr->a4;
fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF;
rt = __ip_route_output_key(net, fl4);
if (!IS_ERR(rt))
return &rt->dst;
return ERR_CAST(rt);
}
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
struct flowi4 fl4;
return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr);
}
static int xfrm4_get_saddr(struct net *net, int oif,
xfrm_address_t *saddr, xfrm_address_t *daddr)
{
struct dst_entry *dst;
struct flowi4 fl4;
dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr);
if (IS_ERR(dst))
return -EHOSTUNREACH;
saddr->a4 = fl4.saddr;
dst_release(dst);
return 0;
}
static int xfrm4_get_tos(const struct flowi *fl)
{
return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
}
static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
return 0;
}
static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
struct rtable *rt = (struct rtable *)xdst->route;
const struct flowi4 *fl4 = &fl->u.ip4;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
xdst->u.dst.dev = dev;
dev_hold(dev);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt.rt_is_input = rt->rt_is_input;
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
xdst->u.rt.rt_table_id = rt->rt_table_id;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
return 0;
}
static void
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
const struct iphdr *iph = ip_hdr(skb);
u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
struct flowi4 *fl4 = &fl->u.ip4;
int oif = 0;
if (skb_dst(skb))
oif = l3mdev_fib_oif(skb_dst(skb)->dev);
memset(fl4, 0, sizeof(struct flowi4));
fl4->flowi4_mark = skb->mark;
fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
case IPPROTO_UDP:
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
case IPPROTO_UDPLITE:
case IPPROTO_TCP:
case IPPROTO_SCTP:
case IPPROTO_DCCP:
if (xprth + 4 < skb->data ||
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ports;
xprth = skb_network_header(skb) + iph->ihl * 4;
ports = (__be16 *)xprth;
fl4->fl4_sport = ports[!!reverse];
fl4->fl4_dport = ports[!reverse];
}
break;
case IPPROTO_ICMP:
if (xprth + 2 < skb->data ||
pskb_may_pull(skb, xprth + 2 - skb->data)) {
u8 *icmp;
xprth = skb_network_header(skb) + iph->ihl * 4;
icmp = xprth;
fl4->fl4_icmp_type = icmp[0];
fl4->fl4_icmp_code = icmp[1];
}
break;
case IPPROTO_ESP:
if (xprth + 4 < skb->data ||
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be32 *ehdr;
xprth = skb_network_header(skb) + iph->ihl * 4;
ehdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ehdr[0];
}
break;
case IPPROTO_AH:
if (xprth + 8 < skb->data ||
pskb_may_pull(skb, xprth + 8 - skb->data)) {
__be32 *ah_hdr;
xprth = skb_network_header(skb) + iph->ihl * 4;
ah_hdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ah_hdr[1];
}
break;
case IPPROTO_COMP:
if (xprth + 4 < skb->data ||
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ipcomp_hdr;
xprth = skb_network_header(skb) + iph->ihl * 4;
ipcomp_hdr = (__be16 *)xprth;
fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
}
break;
case IPPROTO_GRE:
if (xprth + 12 < skb->data ||
pskb_may_pull(skb, xprth + 12 - skb->data)) {
__be16 *greflags;
__be32 *gre_hdr;
xprth = skb_network_header(skb) + iph->ihl * 4;
greflags = (__be16 *)xprth;
gre_hdr = (__be32 *)xprth;
if (greflags[0] & GRE_KEY) {
if (greflags[0] & GRE_CSUM)
gre_hdr++;
fl4->fl4_gre_key = gre_hdr[1];
}
}
break;
default:
fl4->fl4_ipsec_spi = 0;
break;
}
}
fl4->flowi4_proto = iph->protocol;
fl4->daddr = reverse ? iph->saddr : iph->daddr;
fl4->saddr = reverse ? iph->daddr : iph->saddr;
fl4->flowi4_tos = iph->tos;
}
static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
xfrm4_policy_afinfo.garbage_collect(net);
return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
}
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->update_pmtu(path, sk, skb, mtu);
}
static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->redirect(path, sk, skb);
}
static void xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 12:51:05 +08:00
dst_destroy_metrics_generic(dst);
xfrm_dst_destroy(xdst);
}
static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int unregister)
{
if (!unregister)
return;
xfrm_dst_ifdown(dst, dev);
}
xfrm: dst_entries_init() per-net dst_ops Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops templates; their dst_entries counters will never be used. Move the xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init and dst_entries_destroy for each net namespace. The ipv4 and ipv6 xfrms each create dst_ops template, and perform dst_entries_init on the templates. The template values are copied to each net namespace's xfrm.xfrm*_dst_ops. The problem there is the dst_ops pcpuc_entries field is a percpu counter and cannot be used correctly by simply copying it to another object. The result of this is a very subtle bug; changes to the dst entries counter from one net namespace may sometimes get applied to a different net namespace dst entries counter. This is because of how the percpu counter works; it has a main count field as well as a pointer to the percpu variables. Each net namespace maintains its own main count variable, but all point to one set of percpu variables. When any net namespace happens to change one of the percpu variables to outside its small batch range, its count is moved to the net namespace's main count variable. So with multiple net namespaces operating concurrently, the dst_ops entries counter can stray from the actual value that it should be; if counts are consistently moved from one net namespace to another (which my testing showed is likely), then one net namespace winds up with a negative dst_ops count while another winds up with a continually increasing count, eventually reaching its gc_thresh limit, which causes all new traffic on the net namespace to fail with -ENOBUFS. Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2015-10-29 21:51:16 +08:00
static struct dst_ops xfrm4_dst_ops_template = {
.family = AF_INET,
.gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.redirect = xfrm4_redirect,
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 12:51:05 +08:00
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
.gc_thresh = INT_MAX,
};
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
xfrm: dst_entries_init() per-net dst_ops Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops templates; their dst_entries counters will never be used. Move the xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init and dst_entries_destroy for each net namespace. The ipv4 and ipv6 xfrms each create dst_ops template, and perform dst_entries_init on the templates. The template values are copied to each net namespace's xfrm.xfrm*_dst_ops. The problem there is the dst_ops pcpuc_entries field is a percpu counter and cannot be used correctly by simply copying it to another object. The result of this is a very subtle bug; changes to the dst entries counter from one net namespace may sometimes get applied to a different net namespace dst entries counter. This is because of how the percpu counter works; it has a main count field as well as a pointer to the percpu variables. Each net namespace maintains its own main count variable, but all point to one set of percpu variables. When any net namespace happens to change one of the percpu variables to outside its small batch range, its count is moved to the net namespace's main count variable. So with multiple net namespaces operating concurrently, the dst_ops entries counter can stray from the actual value that it should be; if counts are consistently moved from one net namespace to another (which my testing showed is likely), then one net namespace winds up with a negative dst_ops count while another winds up with a continually increasing count, eventually reaching its gc_thresh limit, which causes all new traffic on the net namespace to fail with -ENOBUFS. Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2015-10-29 21:51:16 +08:00
.dst_ops = &xfrm4_dst_ops_template,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
.decode_session = _decode_session4,
.get_tos = xfrm4_get_tos,
.init_path = xfrm4_init_path,
.fill_dst = xfrm4_fill_dst,
.blackhole_route = ipv4_blackhole_route,
};
#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm4_policy_table[] = {
{
.procname = "xfrm4_gc_thresh",
.data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
xfrm: dst_entries_init() per-net dst_ops Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops templates; their dst_entries counters will never be used. Move the xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init and dst_entries_destroy for each net namespace. The ipv4 and ipv6 xfrms each create dst_ops template, and perform dst_entries_init on the templates. The template values are copied to each net namespace's xfrm.xfrm*_dst_ops. The problem there is the dst_ops pcpuc_entries field is a percpu counter and cannot be used correctly by simply copying it to another object. The result of this is a very subtle bug; changes to the dst entries counter from one net namespace may sometimes get applied to a different net namespace dst entries counter. This is because of how the percpu counter works; it has a main count field as well as a pointer to the percpu variables. Each net namespace maintains its own main count variable, but all point to one set of percpu variables. When any net namespace happens to change one of the percpu variables to outside its small batch range, its count is moved to the net namespace's main count variable. So with multiple net namespaces operating concurrently, the dst_ops entries counter can stray from the actual value that it should be; if counts are consistently moved from one net namespace to another (which my testing showed is likely), then one net namespace winds up with a negative dst_ops count while another winds up with a continually increasing count, eventually reaching its gc_thresh limit, which causes all new traffic on the net namespace to fail with -ENOBUFS. Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2015-10-29 21:51:16 +08:00
static int __net_init xfrm4_net_sysctl_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = xfrm4_policy_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL);
if (!table)
goto err_alloc;
table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh;
}
hdr = register_net_sysctl(net, "net/ipv4", table);
if (!hdr)
goto err_reg;
net->ipv4.xfrm4_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
xfrm: dst_entries_init() per-net dst_ops Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops templates; their dst_entries counters will never be used. Move the xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init and dst_entries_destroy for each net namespace. The ipv4 and ipv6 xfrms each create dst_ops template, and perform dst_entries_init on the templates. The template values are copied to each net namespace's xfrm.xfrm*_dst_ops. The problem there is the dst_ops pcpuc_entries field is a percpu counter and cannot be used correctly by simply copying it to another object. The result of this is a very subtle bug; changes to the dst entries counter from one net namespace may sometimes get applied to a different net namespace dst entries counter. This is because of how the percpu counter works; it has a main count field as well as a pointer to the percpu variables. Each net namespace maintains its own main count variable, but all point to one set of percpu variables. When any net namespace happens to change one of the percpu variables to outside its small batch range, its count is moved to the net namespace's main count variable. So with multiple net namespaces operating concurrently, the dst_ops entries counter can stray from the actual value that it should be; if counts are consistently moved from one net namespace to another (which my testing showed is likely), then one net namespace winds up with a negative dst_ops count while another winds up with a continually increasing count, eventually reaching its gc_thresh limit, which causes all new traffic on the net namespace to fail with -ENOBUFS. Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2015-10-29 21:51:16 +08:00
static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
{
struct ctl_table *table;
if (!net->ipv4.xfrm4_hdr)
return;
table = net->ipv4.xfrm4_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.xfrm4_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
xfrm: dst_entries_init() per-net dst_ops Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops templates; their dst_entries counters will never be used. Move the xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init and dst_entries_destroy for each net namespace. The ipv4 and ipv6 xfrms each create dst_ops template, and perform dst_entries_init on the templates. The template values are copied to each net namespace's xfrm.xfrm*_dst_ops. The problem there is the dst_ops pcpuc_entries field is a percpu counter and cannot be used correctly by simply copying it to another object. The result of this is a very subtle bug; changes to the dst entries counter from one net namespace may sometimes get applied to a different net namespace dst entries counter. This is because of how the percpu counter works; it has a main count field as well as a pointer to the percpu variables. Each net namespace maintains its own main count variable, but all point to one set of percpu variables. When any net namespace happens to change one of the percpu variables to outside its small batch range, its count is moved to the net namespace's main count variable. So with multiple net namespaces operating concurrently, the dst_ops entries counter can stray from the actual value that it should be; if counts are consistently moved from one net namespace to another (which my testing showed is likely), then one net namespace winds up with a negative dst_ops count while another winds up with a continually increasing count, eventually reaching its gc_thresh limit, which causes all new traffic on the net namespace to fail with -ENOBUFS. Signed-off-by: Dan Streetman <dan.streetman@canonical.com> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2015-10-29 21:51:16 +08:00
#else /* CONFIG_SYSCTL */
static int inline xfrm4_net_sysctl_init(struct net *net)
{
return 0;
}
static void inline xfrm4_net_sysctl_exit(struct net *net)
{
}
#endif
static int __net_init xfrm4_net_init(struct net *net)
{
int ret;
memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
sizeof(xfrm4_dst_ops_template));
ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
if (ret)
return ret;
ret = xfrm4_net_sysctl_init(net);
if (ret)
dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
return ret;
}
static void __net_exit xfrm4_net_exit(struct net *net)
{
xfrm4_net_sysctl_exit(net);
dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
}
static struct pernet_operations __net_initdata xfrm4_net_ops = {
.init = xfrm4_net_init,
.exit = xfrm4_net_exit,
};
static void __init xfrm4_policy_init(void)
{
xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
}
void __init xfrm4_init(void)
{
xfrm4_state_init();
xfrm4_policy_init();
xfrm4_protocol_init();
register_pernet_subsys(&xfrm4_net_ops);
}