/* Obtain the correct destination MAC address, while preserving the original
* source MAC address. If we already know this address, we just copy it. If we
* don't, we use the neighbour framework to find out. In both cases, we make
* sure that br_handle_frame_finish() is called afterwards.
*/
static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct neighbour *neigh;
struct dst_entry *dst;
skb->dev = bridge_parent(skb->dev);
if (!skb->dev)
goto free_skb;
dst = skb_dst(skb);
neigh = dst_get_neighbour(dst);
if (neigh->hh.hh_len) {
neigh_hh_bridge(&neigh->hh, skb);
skb->dev = nf_bridge->physindev;
return br_handle_frame_finish(skb);
} else {
/* the neighbour function below overwrites the complete
* MAC header, so we save the Ethernet source address and
* protocol number. */
skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), skb->nf_bridge->data, ETH_HLEN-ETH_ALEN);
/* tell br_dev_xmit to continue with forwarding */
nf_bridge->mask |= BRNF_BRIDGED_DNAT;
return neigh->output(neigh, skb);
}
free_skb:
kfree_skb(skb);
return 0;
}
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
#if !defined(CONFIG_IMQ) && !defined(CONFIG_IMQ_MODULE)
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
#endif
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
((mroute6_socket(dev_net(dev), skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
/* Do not check for IFF_ALLMULTI; multicast routing
is not supported in any case.
*/
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
IP6_INC_STATS(dev_net(dev), idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
}
IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
skb->len);
}
rcu_read_lock();
neigh = dst_get_neighbour(dst);
if (neigh) {
int res = neigh_output(neigh, skb);
rcu_read_unlock();
return res;
}
rcu_read_unlock();
IP6_INC_STATS(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
int arp_bind_neighbour(struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
struct neighbour *n = dst_get_neighbour(dst);
if (dev == NULL)
return -EINVAL;
if (n == NULL) {
n = __arp_bind_neighbour(dst, ((struct rtable *)dst)->rt_gateway);
if (IS_ERR(n))
return PTR_ERR(n);
dst_set_neighbour(dst, n);
}
return 0;
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
#endif
int err;
if (*dst == NULL)
*dst = ip6_route_output(net, sk, fl6);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl6->saddr)) {
struct rt6_info *rt = (struct rt6_info *) *dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
}
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
rcu_read_lock();
n = dst_get_neighbour(*dst);
if (n && !(n->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
rcu_read_unlock();
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(net, sk, &fl_gw6);
if ((err = (*dst)->error))
goto out_err_release;
}
} else {
rcu_read_unlock();
}
#endif
return 0;
out_err_release:
if (err == -ENETUNREACH)
IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
return err;
}
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
struct neighbour *n;
u32 mtu;
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (opt->ra) {
u8 *ptr = skb_network_header(skb) + opt->ra;
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
/* XXX: idev->cnf.proxy_ndp? */
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
n = dst_get_neighbour(dst);
if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct rt6_info *rt;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if ((rt->rt6i_flags & RTF_GATEWAY))
target = (struct in6_addr*)&n->primary_key;
else
target = &hdr->daddr;
if (!rt->rt6i_peer)
rt6_bind_peer(rt, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
ndisc_send_redirect(skb, n, target);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0);
goto error;
}
}
mtu = dst_mtu(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb->len > mtu && !skb_is_gso(skb)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = ipv6_hdr(skb);
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
static void CVE_2015_2922_linux3_2_25_ndisc_router_discovery(struct sk_buff *skb)
{
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
struct neighbour *neigh = NULL;
struct inet6_dev *in6_dev;
struct rt6_info *rt = NULL;
int lifetime;
struct ndisc_options ndopts;
int optlen;
unsigned int pref = 0;
__u8 * opt = (__u8 *)(ra_msg + 1);
optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg);
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: source address is not link-local.\n");
return;
}
if (optlen < 0) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: packet too short\n");
return;
}
#ifdef CONFIG_IPV6_NDISC_NODETYPE
if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: from host or unauthorized router\n");
return;
}
#endif
/*
* set the RA_RECV flag in the interface
*/
in6_dev = __in6_dev_get(skb->dev);
if (in6_dev == NULL) {
ND_PRINTK0(KERN_ERR
"ICMPv6 RA: can't find inet6 device for %s.\n",
skb->dev->name);
return;
}
if (!ndisc_parse_options(opt, optlen, &ndopts)) {
ND_PRINTK2(KERN_WARNING
"ICMP6 RA: invalid ND options\n");
return;
}
if (!accept_ra(in6_dev))
goto skip_linkparms;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific parameters from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT)
goto skip_linkparms;
#endif
if (in6_dev->if_flags & IF_RS_SENT) {
/*
* flag that an RA was received after an RS was sent
* out on this interface.
*/
in6_dev->if_flags |= IF_RA_RCVD;
}
/*
* Remember the managed/otherconf flags from most recently
* received RA message (RFC 2462) -- yoshfuji
*/
in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED |
IF_RA_OTHERCONF)) |
(ra_msg->icmph.icmp6_addrconf_managed ?
IF_RA_MANAGED : 0) |
(ra_msg->icmph.icmp6_addrconf_other ?
IF_RA_OTHERCONF : 0);
if (!in6_dev->cnf.accept_ra_defrtr)
goto skip_defrtr;
if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0))
goto skip_defrtr;
lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
#ifdef CONFIG_IPV6_ROUTER_PREF
pref = ra_msg->icmph.icmp6_router_pref;
/* 10b is handled as if it were 00b (medium) */
if (pref == ICMPV6_ROUTER_PREF_INVALID ||
!in6_dev->cnf.accept_ra_rtr_pref)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
if (rt)
neigh = dst_get_neighbour(&rt->dst);
if (rt && lifetime == 0) {
neigh_clone(neigh);
ip6_del_rt(rt);
rt = NULL;
}
if (rt == NULL && lifetime) {
ND_PRINTK3(KERN_DEBUG
"ICMPv6 RA: adding default router.\n");
rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref);
if (rt == NULL) {
ND_PRINTK0(KERN_ERR
"ICMPv6 RA: %s() failed to add default route.\n",
__func__);
return;
}
neigh = dst_get_neighbour(&rt->dst);
if (neigh == NULL) {
ND_PRINTK0(KERN_ERR
"ICMPv6 RA: %s() got default router without neighbour.\n",
__func__);
dst_release(&rt->dst);
return;
}
neigh->flags |= NTF_ROUTER;
} else if (rt) {
rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
}
if (rt)
rt->rt6i_expires = jiffies + (HZ * lifetime);
if (ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
if (rt)
dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
}
skip_defrtr:
/*
* Update Reachable Time and Retrans Timer
*/
if (in6_dev->nd_parms) {
unsigned long rtime = ntohl(ra_msg->retrans_timer);
if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) {
rtime = (rtime*HZ)/1000;
if (rtime < HZ/10)
rtime = HZ/10;
in6_dev->nd_parms->retrans_time = rtime;
in6_dev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
}
rtime = ntohl(ra_msg->reachable_time);
if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) {
rtime = (rtime*HZ)/1000;
if (rtime < HZ/10)
rtime = HZ/10;
if (rtime != in6_dev->nd_parms->base_reachable_time) {
in6_dev->nd_parms->base_reachable_time = rtime;
in6_dev->nd_parms->gc_staletime = 3 * rtime;
in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime);
in6_dev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
}
}
}
skip_linkparms:
/*
* Process options.
*/
if (!neigh)
neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr,
skb->dev, 1);
if (neigh) {
u8 *lladdr = NULL;
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
skb->dev);
if (!lladdr) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: invalid link-layer address length\n");
goto out;
}
}
neigh_update(neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
NEIGH_UPDATE_F_ISROUTER);
}
if (!accept_ra(in6_dev))
goto out;
#ifdef CONFIG_IPV6_ROUTE_INFO
if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0))
goto skip_routeinfo;
if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_ri;
p;
p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) {
struct route_info *ri = (struct route_info *)p;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT &&
ri->prefix_len == 0)
continue;
#endif
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3,
&ipv6_hdr(skb)->saddr);
}
}
skip_routeinfo:
#endif
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific ndopts from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT)
goto out;
#endif
if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_pi;
p;
p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) {
addrconf_prefix_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3);
}
}
if (ndopts.nd_opts_mtu) {
__be32 n;
u32 mtu;
memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
mtu = ntohl(n);
if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: invalid mtu: %d\n",
mtu);
} else if (in6_dev->cnf.mtu6 != mtu) {
in6_dev->cnf.mtu6 = mtu;
if (rt)
dst_metric_set(&rt->dst, RTAX_MTU, mtu);
rt6_mtu_change(skb->dev, mtu);
}
}
if (ndopts.nd_useropts) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_useropts;
p;
p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
ndisc_ra_useropt(skb, p);
}
}
if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) {
ND_PRINTK2(KERN_WARNING
"ICMPv6 RA: invalid RA options");
}
out:
if (rt)
dst_release(&rt->dst);
else if (neigh)
neigh_release(neigh);
}
/* Create a child dst_entry with locked interface MTU, and attach it to `dst'.
This is needed on newer linux kernels and IP_ONLY_INTERCEPTOR builds,
where the IP stack fragments packets to path MTU after ssh_interceptor_send.
*/
static struct dst_entry *
interceptor_route_create_child_dst(struct dst_entry *dst, Boolean ipv6)
{
struct dst_entry *child;
#ifdef LINUX_HAS_DST_COPY_METRICS
SshUInt32 set;
struct rt6_info *rt6;
struct rtable *rt;
#endif /* LINUX_HAS_DST_COPY_METRICS */
/* Allocate a dst_entry and copy relevant fields from dst. */
child = SSH_DST_ALLOC(dst);
if (child == NULL)
return NULL;
child->input = dst->input;
child->output = dst->output;
/* Child is not added to dst hash, and linux native IPsec is disabled. */
child->flags |= (DST_NOHASH | DST_NOPOLICY | DST_NOXFRM);
/* Copy route metrics and lock MTU to interface MTU. */
#ifdef LINUX_HAS_DST_COPY_METRICS
if (ipv6 == TRUE)
{
rt6 = (struct rt6_info *)child;
memset(&rt6->rt6i_table, 0, sizeof(*rt6) - sizeof(struct dst_entry));
}
else
{
rt = (struct rtable *)child;
memset(&SSH_RTABLE_FIRST_MEMBER(rt), 0,
sizeof(*rt) - sizeof(struct dst_entry));
}
dst_copy_metrics(child, dst);
set = dst_metric(child, RTAX_LOCK);
set |= 1 << RTAX_MTU;
dst_metric_set(child, RTAX_LOCK, set);
#else /* LINUX_HAS_DST_COPY_METRICS */
memcpy(child->metrics, dst->metrics, sizeof(child->metrics));
child->metrics[RTAX_LOCK-1] |= 1 << RTAX_MTU;
#endif /* LINUX_HAS_DST_COPY_METRICS */
#ifdef CONFIG_NET_CLS_ROUTE
child->tclassid = dst->tclassid;
#endif /* CONFIG_NET_CLS_ROUTE */
#ifdef CONFIG_XFRM
child->xfrm = NULL;
#endif /* CONFIG_XFRM */
#ifdef LINUX_HAS_HH_CACHE
if (dst->hh)
{
atomic_inc(&dst->hh->hh_refcnt);
child->hh = dst->hh;
}
#endif /* LINUX_HAS_HH_CACHE */
#ifdef LINUX_HAS_DST_NEIGHBOUR_FUNCTIONS
if (dst_get_neighbour(dst) != NULL)
dst_set_neighbour(child, neigh_clone(dst_get_neighbour(dst)));
#else /* LINUX_HAS_DST_NEIGHBOUR_FUNCTIONS */
if (dst->neighbour != NULL)
child->neighbour = neigh_clone(dst->neighbour);
#endif /* LINUX_HAS_DST_NEIGHBOUR_FUNCTIONS */
if (dst->dev)
{
dev_hold(dst->dev);
child->dev = dst->dev;
}
SSH_ASSERT(dst->child == NULL);
dst->child = dst_clone(child);
SSH_DEBUG(SSH_D_MIDOK, ("Allocated child %p dst_entry for dst %p mtu %d",
child, dst, dst_mtu(dst)));
return child;
}
