linux/net/ipv6/xfrm6_policy.c

355 lines
8.4 KiB
C
Raw Normal View History

/*
* xfrm6_policy.c: based on xfrm4_policy.c
*
* Authors:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* IPv6 support
* YOSHIFUJI Hideaki
* Split up af-specific portion
*
*/
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <net/addrconf.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
#include <net/mip6.h>
#endif
static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
xfrm_address_t *saddr,
xfrm_address_t *daddr)
{
struct flowi fl = {};
struct dst_entry *dst;
int err;
memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst));
if (saddr)
memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src));
dst = ip6_route_output(net, NULL, &fl);
err = dst->error;
if (dst->error) {
dst_release(dst);
dst = ERR_PTR(err);
}
return dst;
}
static int xfrm6_get_saddr(struct net *net,
xfrm_address_t *saddr, xfrm_address_t *daddr)
{
struct dst_entry *dst;
struct net_device *dev;
dst = xfrm6_dst_lookup(net, 0, NULL, daddr);
if (IS_ERR(dst))
return -EHOSTUNREACH;
dev = ip6_dst_idev(dst)->dev;
ipv6_dev_get_saddr(dev_net(dev), dev,
(struct in6_addr *)&daddr->a6, 0,
(struct in6_addr *)&saddr->a6);
dst_release(dst);
return 0;
}
static int xfrm6_get_tos(const struct flowi *fl)
{
return 0;
}
static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
if (dst->ops->family == AF_INET6) {
struct rt6_info *rt = (struct rt6_info*)dst;
if (rt->rt6i_node)
path->path_cookie = rt->rt6i_node->fn_sernum;
}
path->u.rt6.rt6i_nfheader_len = nfheader_len;
return 0;
}
static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
struct flowi *fl)
{
struct rt6_info *rt = (struct rt6_info*)xdst->route;
xdst->u.dst.dev = dev;
dev_hold(dev);
xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
if (!xdst->u.rt6.rt6i_idev)
return -ENODEV;
xdst->u.rt6.rt6i_peer = rt->rt6i_peer;
if (rt->rt6i_peer)
atomic_inc(&rt->rt6i_peer->refcnt);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
if (rt->rt6i_node)
xdst->route_cookie = rt->rt6i_node->fn_sernum;
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
return 0;
}
static inline void
_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
{
int onlyproto = 0;
u16 offset = skb_network_header_len(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct ipv6_opt_hdr *exthdr;
const unsigned char *nh = skb_network_header(skb);
u8 nexthdr = nh[IP6CB(skb)->nhoff];
memset(fl, 0, sizeof(struct flowi));
fl->mark = skb->mark;
ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr);
ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr);
while (nh + offset + 1 < skb->data ||
pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
nh = skb_network_header(skb);
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
switch (nexthdr) {
case NEXTHDR_FRAGMENT:
onlyproto = 1;
case NEXTHDR_ROUTING:
case NEXTHDR_HOP:
case NEXTHDR_DEST:
offset += ipv6_optlen(exthdr);
nexthdr = exthdr->nexthdr;
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
break;
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>
2006-11-27 19:10:57 +00:00
case IPPROTO_UDPLITE:
case IPPROTO_TCP:
case IPPROTO_SCTP:
case IPPROTO_DCCP:
if (!onlyproto && (nh + offset + 4 < skb->data ||
pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
__be16 *ports = (__be16 *)exthdr;
fl->fl_ip_sport = ports[!!reverse];
fl->fl_ip_dport = ports[!reverse];
}
fl->proto = nexthdr;
return;
case IPPROTO_ICMPV6:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
u8 *icmp = (u8 *)exthdr;
fl->fl_icmp_type = icmp[0];
fl->fl_icmp_code = icmp[1];
}
fl->proto = nexthdr;
return;
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
case IPPROTO_MH:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
struct ip6_mh *mh;
mh = (struct ip6_mh *)exthdr;
fl->fl_mh_type = mh->ip6mh_type;
}
fl->proto = nexthdr;
return;
#endif
/* XXX Why are there these headers? */
case IPPROTO_AH:
case IPPROTO_ESP:
case IPPROTO_COMP:
default:
fl->fl_ipsec_spi = 0;
fl->proto = nexthdr;
return;
}
}
}
static inline int xfrm6_garbage_collect(struct dst_ops *ops)
{
struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
xfrm6_policy_afinfo.garbage_collect(net);
return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
}
static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->update_pmtu(path, mtu);
}
static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
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 04:51:05 +00:00
dst_destroy_metrics_generic(dst);
if (likely(xdst->u.rt6.rt6i_peer))
inet_putpeer(xdst->u.rt6.rt6i_peer);
xfrm_dst_destroy(xdst);
}
static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int unregister)
{
struct xfrm_dst *xdst;
if (!unregister)
return;
xdst = (struct xfrm_dst *)dst;
if (xdst->u.rt6.rt6i_idev->dev == dev) {
struct inet6_dev *loopback_idev =
in6_dev_get(dev_net(dev)->loopback_dev);
BUG_ON(!loopback_idev);
do {
in6_dev_put(xdst->u.rt6.rt6i_idev);
xdst->u.rt6.rt6i_idev = loopback_idev;
in6_dev_hold(loopback_idev);
xdst = (struct xfrm_dst *)xdst->u.dst.child;
} while (xdst->u.dst.xfrm);
__in6_dev_put(loopback_idev);
}
xfrm_dst_ifdown(dst, dev);
}
static struct dst_ops xfrm6_dst_ops = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
.gc = xfrm6_garbage_collect,
.update_pmtu = xfrm6_update_pmtu,
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 04:51:05 +00:00
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm6_dst_destroy,
.ifdown = xfrm6_dst_ifdown,
.local_out = __ip6_local_out,
.gc_thresh = 1024,
};
static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
.init_path = xfrm6_init_path,
.fill_dst = xfrm6_fill_dst,
};
static int __init xfrm6_policy_init(void)
{
return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo);
}
static void xfrm6_policy_fini(void)
{
xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo);
}
#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm6_policy_table[] = {
{
.procname = "xfrm6_gc_thresh",
.data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
static struct ctl_table_header *sysctl_hdr;
#endif
int __init xfrm6_init(void)
{
int ret;
unsigned int gc_thresh;
/*
* We need a good default value for the xfrm6 gc threshold.
* In ipv4 we set it to the route hash table size * 8, which
* is half the size of the maximaum route cache for ipv4. It
* would be good to do the same thing for v6, except the table is
* constructed differently here. Here each table for a net namespace
* can have FIB_TABLE_HASHSZ entries, so lets go with the same
* computation that we used for ipv4 here. Also, lets keep the initial
* gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults
* to that as a minimum as well
*/
gc_thresh = FIB6_TABLE_HASHSZ * 8;
xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh;
dst_entries_init(&xfrm6_dst_ops);
ret = xfrm6_policy_init();
if (ret) {
dst_entries_destroy(&xfrm6_dst_ops);
goto out;
}
ret = xfrm6_state_init();
if (ret)
goto out_policy;
#ifdef CONFIG_SYSCTL
sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path,
xfrm6_policy_table);
#endif
out:
return ret;
out_policy:
xfrm6_policy_fini();
goto out;
}
void xfrm6_fini(void)
{
#ifdef CONFIG_SYSCTL
if (sysctl_hdr)
unregister_net_sysctl_table(sysctl_hdr);
#endif
//xfrm6_input_fini();
xfrm6_policy_fini();
xfrm6_state_fini();
dst_entries_destroy(&xfrm6_dst_ops);
}