OpenCloudOS-Kernel/net/ipv4/xfrm4_policy.c

282 lines
6.1 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 <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
static struct dst_ops xfrm4_dst_ops;
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
xfrm_address_t *saddr,
xfrm_address_t *daddr)
{
struct flowi fl = {
.nl_u = {
.ip4_u = {
.tos = tos,
.daddr = daddr->a4,
},
},
};
struct dst_entry *dst;
struct rtable *rt;
int err;
if (saddr)
fl.fl4_src = saddr->a4;
err = __ip_route_output_key(net, &rt, &fl);
dst = &rt->u.dst;
if (err)
dst = ERR_PTR(err);
return dst;
}
static int xfrm4_get_saddr(struct net *net,
xfrm_address_t *saddr, xfrm_address_t *daddr)
{
struct dst_entry *dst;
struct rtable *rt;
dst = xfrm4_dst_lookup(net, 0, NULL, daddr);
if (IS_ERR(dst))
return -EHOSTUNREACH;
rt = (struct rtable *)dst;
saddr->a4 = rt->rt_src;
dst_release(dst);
return 0;
}
static struct dst_entry *
__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
{
struct dst_entry *dst;
read_lock_bh(&policy->lock);
for (dst = policy->bundles; dst; dst = dst->next) {
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/
xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
xdst->u.rt.fl.fl4_src == fl->fl4_src &&
xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
IPsec: correct semantics for SELinux policy matching Currently when an IPSec policy rule doesn't specify a security context, it is assumed to be "unlabeled" by SELinux, and so the IPSec policy rule fails to match to a flow that it would otherwise match to, unless one has explicitly added an SELinux policy rule allowing the flow to "polmatch" to the "unlabeled" IPSec policy rules. In the absence of such an explicitly added SELinux policy rule, the IPSec policy rule fails to match and so the packet(s) flow in clear text without the otherwise applicable xfrm(s) applied. The above SELinux behavior violates the SELinux security notion of "deny by default" which should actually translate to "encrypt by default" in the above case. This was first reported by Evgeniy Polyakov and the way James Morris was seeing the problem was when connecting via IPsec to a confined service on an SELinux box (vsftpd), which did not have the appropriate SELinux policy permissions to send packets via IPsec. With this patch applied, SELinux "polmatching" of flows Vs. IPSec policy rules will only come into play when there's a explicit context specified for the IPSec policy rule (which also means there's corresponding SELinux policy allowing appropriate domains/flows to polmatch to this context). Secondly, when a security module is loaded (in this case, SELinux), the security_xfrm_policy_lookup() hook can return errors other than access denied, such as -EINVAL. We were not handling that correctly, and in fact inverting the return logic and propagating a false "ok" back up to xfrm_lookup(), which then allowed packets to pass as if they were not associated with an xfrm policy. The solution for this is to first ensure that errno values are correctly propagated all the way back up through the various call chains from security_xfrm_policy_lookup(), and handled correctly. Then, flow_cache_lookup() is modified, so that if the policy resolver fails (typically a permission denied via the security module), the flow cache entry is killed rather than having a null policy assigned (which indicates that the packet can pass freely). This also forces any future lookups for the same flow to consult the security module (e.g. SELinux) for current security policy (rather than, say, caching the error on the flow cache entry). This patch: Fix the selinux side of things. This makes sure SELinux polmatching of flow contexts to IPSec policy rules comes into play only when an explicit context is associated with the IPSec policy rule. Also, this no longer defaults the context of a socket policy to the context of the socket since the "no explicit context" case is now handled properly. Signed-off-by: Venkat Yekkirala <vyekkirala@TrustedCS.com> Signed-off-by: James Morris <jmorris@namei.org>
2006-10-06 04:42:18 +08:00
xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
dst_clone(dst);
break;
}
}
read_unlock_bh(&policy->lock);
return dst;
}
static int xfrm4_get_tos(struct flowi *fl)
{
return fl->fl4_tos;
}
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)
{
struct rtable *rt = (struct rtable *)xdst->route;
xdst->u.rt.fl = rt->fl;
xdst->u.dst.dev = dev;
dev_hold(dev);
xdst->u.rt.idev = in_dev_get(dev);
if (!xdst->u.rt.idev)
return -ENODEV;
xdst->u.rt.peer = rt->peer;
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
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_src = rt->rt_src;
xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_spec_dst = rt->rt_spec_dst;
return 0;
}
static void
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
struct iphdr *iph = ip_hdr(skb);
u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
memset(fl, 0, sizeof(struct flowi));
if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
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 (pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ports = (__be16 *)xprth;
fl->fl_ip_sport = ports[!!reverse];
fl->fl_ip_dport = ports[!reverse];
}
break;
case IPPROTO_ICMP:
if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
u8 *icmp = xprth;
fl->fl_icmp_type = icmp[0];
fl->fl_icmp_code = icmp[1];
}
break;
case IPPROTO_ESP:
if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be32 *ehdr = (__be32 *)xprth;
fl->fl_ipsec_spi = ehdr[0];
}
break;
case IPPROTO_AH:
if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
__be32 *ah_hdr = (__be32*)xprth;
fl->fl_ipsec_spi = ah_hdr[1];
}
break;
case IPPROTO_COMP:
if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ipcomp_hdr = (__be16 *)xprth;
fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
}
break;
default:
fl->fl_ipsec_spi = 0;
break;
}
}
fl->proto = iph->protocol;
fl->fl4_dst = reverse ? iph->saddr : iph->daddr;
fl->fl4_src = reverse ? iph->daddr : iph->saddr;
fl->fl4_tos = iph->tos;
}
static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
xfrm4_policy_afinfo.garbage_collect(&init_net);
return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
}
static void xfrm4_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 xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt.idev))
in_dev_put(xdst->u.rt.idev);
if (likely(xdst->u.rt.peer))
inet_putpeer(xdst->u.rt.peer);
xfrm_dst_destroy(xdst);
}
static void xfrm4_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.rt.idev->dev == dev) {
struct in_device *loopback_idev =
in_dev_get(dev_net(dev)->loopback_dev);
BUG_ON(!loopback_idev);
do {
in_dev_put(xdst->u.rt.idev);
xdst->u.rt.idev = loopback_idev;
in_dev_hold(loopback_idev);
xdst = (struct xfrm_dst *)xdst->u.dst.child;
} while (xdst->u.dst.xfrm);
__in_dev_put(loopback_idev);
}
xfrm_dst_ifdown(dst, dev);
}
static struct dst_ops xfrm4_dst_ops = {
.family = AF_INET,
.protocol = __constant_htons(ETH_P_IP),
.gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
.gc_thresh = 1024,
.entries = ATOMIC_INIT(0),
};
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
.dst_ops = &xfrm4_dst_ops,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
.find_bundle = __xfrm4_find_bundle,
.decode_session = _decode_session4,
.get_tos = xfrm4_get_tos,
.init_path = xfrm4_init_path,
.fill_dst = xfrm4_fill_dst,
};
static void __init xfrm4_policy_init(void)
{
xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
}
static void __exit xfrm4_policy_fini(void)
{
xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
}
void __init xfrm4_init(void)
{
xfrm4_state_init();
xfrm4_policy_init();
}