/* Replicate the checks that IPv6 does on packet reception and pass the packet
* to ip6tables.
*/
unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nf_bridge_info *nf_bridge;
if (br_validate_ipv6(skb))
return NF_DROP;
nf_bridge_put(skb->nf_bridge);
if (!nf_bridge_alloc(skb))
return NF_DROP;
if (!setup_pre_routing(skb))
return NF_DROP;
nf_bridge = nf_bridge_info_get(skb);
nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr;
skb->protocol = htons(ETH_P_IPV6);
NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb,
skb->dev, NULL,
br_nf_pre_routing_finish_ipv6);
return NF_STOLEN;
}
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct net_device *in;
if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
if (skb->protocol == htons(ETH_P_IP))
nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
if (skb->protocol == htons(ETH_P_IPV6))
nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
in = nf_bridge->physindev;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge_update_protocol(skb);
} else {
in = *((struct net_device **)(skb->cb));
}
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_FORWARD, net, sk, skb, in, skb->dev,
br_forward_finish);
return 0;
}
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct net_device *in;
if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
int frag_max_size;
if (skb->protocol == htons(ETH_P_IP)) {
frag_max_size = IPCB(skb)->frag_max_size;
BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
}
in = nf_bridge->physindev;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge_update_protocol(skb);
} else {
in = *((struct net_device **)(skb->cb));
}
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, sk, skb,
in, skb->dev, br_forward_finish, 1);
return 0;
}
/* Undo the changes made for ip6tables PREROUTING and continue the
* bridge PRE_ROUTING hook. */
static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct rtable *rt;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
skb->dev, NULL,
br_handle_frame_finish, 1);
return 0;
}
/* This is the 'purely bridged' case. For IP, we pass the packet to
* netfilter with indev and outdev set to the bridge device,
* but we are still able to filter on the 'real' indev/outdev
* because of the physdev module. For ARP, indev and outdev are the
* bridge ports. */
static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nf_bridge_info *nf_bridge;
struct net_device *parent;
u_int8_t pf;
if (!skb->nf_bridge)
return NF_ACCEPT;
/* Need exclusive nf_bridge_info since we might have multiple
* different physoutdevs. */
if (!nf_bridge_unshare(skb))
return NF_DROP;
nf_bridge = nf_bridge_info_get(skb);
if (!nf_bridge)
return NF_DROP;
parent = bridge_parent(state->out);
if (!parent)
return NF_DROP;
if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
pf = NFPROTO_IPV4;
else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
pf = NFPROTO_IPV6;
else
return NF_ACCEPT;
nf_bridge_pull_encap_header(skb);
if (skb->pkt_type == PACKET_OTHERHOST) {
skb->pkt_type = PACKET_HOST;
nf_bridge->pkt_otherhost = true;
}
if (pf == NFPROTO_IPV4) {
int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size;
if (br_parse_ip_options(skb))
return NF_DROP;
IPCB(skb)->frag_max_size = frag_max;
}
nf_bridge->physoutdev = skb->dev;
if (pf == NFPROTO_IPV4)
skb->protocol = htons(ETH_P_IP);
else
skb->protocol = htons(ETH_P_IPV6);
NF_HOOK(pf, NF_INET_FORWARD, NULL, skb,
brnf_get_logical_dev(skb, state->in),
parent, br_nf_forward_finish);
return NF_STOLEN;
}
/* Direct IPv6 traffic to br_nf_pre_routing_ipv6.
* Replicate the checks that IPv4 does on packet reception.
* Set skb->dev to the bridge device (i.e. parent of the
* receiving device) to make netfilter happy, the REDIRECT
* target in particular. Save the original destination IP
* address to be able to detect DNAT afterwards. */
static unsigned int br_nf_pre_routing(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nf_bridge_info *nf_bridge;
struct net_bridge_port *p;
struct net_bridge *br;
__u32 len = nf_bridge_encap_header_len(skb);
if (unlikely(!pskb_may_pull(skb, len)))
return NF_DROP;
p = br_port_get_rcu(state->in);
if (p == NULL)
return NF_DROP;
br = p->br;
if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) {
if (!brnf_call_ip6tables && !br->nf_call_ip6tables)
return NF_ACCEPT;
nf_bridge_pull_encap_header_rcsum(skb);
return br_nf_pre_routing_ipv6(priv, skb, state);
}
if (!brnf_call_iptables && !br->nf_call_iptables)
return NF_ACCEPT;
if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb))
return NF_ACCEPT;
nf_bridge_pull_encap_header_rcsum(skb);
if (br_validate_ipv4(state->net, skb))
return NF_DROP;
nf_bridge_put(skb->nf_bridge);
if (!nf_bridge_alloc(skb))
return NF_DROP;
if (!setup_pre_routing(skb))
return NF_DROP;
nf_bridge = nf_bridge_info_get(skb);
nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;
skb->protocol = htons(ETH_P_IP);
NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb,
skb->dev, NULL,
br_nf_pre_routing_finish);
return NF_STOLEN;
}
/* PF_BRIDGE/PRE_ROUTING: Undo the changes made for ip6tables
* PREROUTING and continue the bridge PRE_ROUTING hook. See comment
* for br_nf_pre_routing_finish(), same logic is used here but
* equivalent IPv6 function ip6_route_input() called indirectly.
*/
static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct rtable *rt;
struct net_device *dev = skb->dev;
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge->in_prerouting = 0;
if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) {
skb_dst_drop(skb);
v6ops->route_input(skb);
if (skb_dst(skb)->error) {
kfree_skb(skb);
return 0;
}
if (skb_dst(skb)->dev == dev) {
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
sk, skb, skb->dev, NULL,
br_nf_pre_routing_finish_bridge,
1);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
skb->pkt_type = PACKET_HOST;
} else {
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
skb->dev, NULL,
br_handle_frame_finish, 1);
return 0;
}
/* This is called when br_netfilter has called into iptables/netfilter,
* and DNAT has taken place on a bridge-forwarded packet.
*
* neigh->output has created a new MAC header, with local br0 MAC
* as saddr.
*
* This restores the original MAC saddr of the bridged packet
* before invoking bridge forward logic to transmit the packet.
*/
static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
skb_pull(skb, ETH_HLEN);
nf_bridge->mask &= ~BRNF_BRIDGED_DNAT;
BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));
skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
nf_bridge->neigh_header,
ETH_HLEN - ETH_ALEN);
skb->dev = nf_bridge->physindev;
br_handle_frame_finish(NULL, skb);
}
/* This is called when br_netfilter has called into iptables/netfilter,
* and DNAT has taken place on a bridge-forwarded packet.
*
* neigh->output has created a new MAC header, with local br0 MAC
* as saddr.
*
* This restores the original MAC saddr of the bridged packet
* before invoking bridge forward logic to transmit the packet.
*/
static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
skb_pull(skb, ETH_HLEN);
nf_bridge->bridged_dnat = 0;
BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));
skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
nf_bridge->neigh_header,
ETH_HLEN - ETH_ALEN);
skb->dev = nf_bridge->physindev;
nf_bridge->physoutdev = NULL;
br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
}
/* PF_BRIDGE/POST_ROUTING ********************************************/
static unsigned int br_nf_post_routing(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct net_device *realoutdev = bridge_parent(skb->dev);
u_int8_t pf;
/* if nf_bridge is set, but ->physoutdev is NULL, this packet came in
* on a bridge, but was delivered locally and is now being routed:
*
* POST_ROUTING was already invoked from the ip stack.
*/
if (!nf_bridge || !nf_bridge->physoutdev)
return NF_ACCEPT;
if (!realoutdev)
return NF_DROP;
if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb))
pf = NFPROTO_IPV4;
else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb))
pf = NFPROTO_IPV6;
else
return NF_ACCEPT;
/* We assume any code from br_dev_queue_push_xmit onwards doesn't care
* about the value of skb->pkt_type. */
if (skb->pkt_type == PACKET_OTHERHOST) {
skb->pkt_type = PACKET_HOST;
nf_bridge->pkt_otherhost = true;
}
nf_bridge_pull_encap_header(skb);
if (pf == NFPROTO_IPV4)
skb->protocol = htons(ETH_P_IP);
else
skb->protocol = htons(ETH_P_IPV6);
NF_HOOK(pf, NF_INET_POST_ROUTING, state->net, state->sk, skb,
NULL, realoutdev,
br_nf_dev_queue_xmit);
return NF_STOLEN;
}
/* Some common code for IPv4/IPv6 */
struct net_device *setup_pre_routing(struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
if (skb->pkt_type == PACKET_OTHERHOST) {
skb->pkt_type = PACKET_HOST;
nf_bridge->pkt_otherhost = true;
}
nf_bridge->in_prerouting = 1;
nf_bridge->physindev = skb->dev;
skb->dev = brnf_get_logical_dev(skb, skb->dev);
if (skb->protocol == htons(ETH_P_8021Q))
nf_bridge->orig_proto = BRNF_PROTO_8021Q;
else if (skb->protocol == htons(ETH_P_PPP_SES))
nf_bridge->orig_proto = BRNF_PROTO_PPPOE;
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return skb->dev;
}
/* 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.
*/
int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb)
{
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_neigh_lookup_skb(dst, skb);
if (neigh) {
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
int ret;
if (neigh->hh.hh_len) {
neigh_hh_bridge(&neigh->hh, skb);
skb->dev = nf_bridge->physindev;
ret = br_handle_frame_finish(net, sk, 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),
nf_bridge->neigh_header,
ETH_HLEN-ETH_ALEN);
/* tell br_dev_xmit to continue with forwarding */
nf_bridge->bridged_dnat = 1;
/* FIXME Need to refragment */
ret = neigh->output(neigh, skb);
}
neigh_release(neigh);
return ret;
}
free_skb:
kfree_skb(skb);
return 0;
}
static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge;
unsigned int mtu_reserved;
mtu_reserved = nf_bridge_mtu_reduction(skb);
if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) {
nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(net, sk, skb);
}
nf_bridge = nf_bridge_info_get(skb);
/* This is wrong! We should preserve the original fragment
* boundaries by preserving frag_list rather than refragmenting.
*/
if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) &&
skb->protocol == htons(ETH_P_IP)) {
struct brnf_frag_data *data;
if (br_validate_ipv4(net, skb))
goto drop;
IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
nf_bridge_update_protocol(skb);
data = this_cpu_ptr(&brnf_frag_data_storage);
data->vlan_tci = skb->vlan_tci;
data->vlan_proto = skb->vlan_proto;
data->encap_size = nf_bridge_encap_header_len(skb);
data->size = ETH_HLEN + data->encap_size;
skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
data->size);
return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
}
if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) &&
skb->protocol == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
struct brnf_frag_data *data;
if (br_validate_ipv6(net, skb))
goto drop;
IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
nf_bridge_update_protocol(skb);
data = this_cpu_ptr(&brnf_frag_data_storage);
data->encap_size = nf_bridge_encap_header_len(skb);
data->size = ETH_HLEN + data->encap_size;
skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
data->size);
if (v6ops)
return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);
kfree_skb(skb);
return -EMSGSIZE;
}
nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(net, sk, skb);
drop:
kfree_skb(skb);
return 0;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
* This is also true when SNAT takes place (for the reply direction).
*
* There are two cases to consider:
* 1. The packet was DNAT'ed to a device in the same bridge
* port group as it was received on. We can still bridge
* the packet.
* 2. The packet was DNAT'ed to a different device, either
* a non-bridged device or another bridge port group.
* The packet will need to be routed.
*
* The correct way of distinguishing between these two cases is to
* call ip_route_input() and to look at skb->dst->dev, which is
* changed to the destination device if ip_route_input() succeeds.
*
* Let's first consider the case that ip_route_input() succeeds:
*
* If the output device equals the logical bridge device the packet
* came in on, we can consider this bridging. The corresponding MAC
* address will be obtained in br_nf_pre_routing_finish_bridge.
* Otherwise, the packet is considered to be routed and we just
* change the destination MAC address so that the packet will
* later be passed up to the IP stack to be routed. For a redirected
* packet, ip_route_input() will give back the localhost as output device,
* which differs from the bridge device.
*
* Let's now consider the case that ip_route_input() fails:
*
* This can be because the destination address is martian, in which case
* the packet will be dropped.
* If IP forwarding is disabled, ip_route_input() will fail, while
* ip_route_output_key() can return success. The source
* address for ip_route_output_key() is set to zero, so ip_route_output_key()
* thinks we're handling a locally generated packet and won't care
* if IP forwarding is enabled. If the output device equals the logical bridge
* device, we proceed as if ip_route_input() succeeded. If it differs from the
* logical bridge port or if ip_route_output_key() fails we drop the packet.
*/
static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct rtable *rt;
int err;
nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge->in_prerouting = 0;
if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* If err equals -EHOSTUNREACH the error is due to a
* martian destination or due to the fact that
* forwarding is disabled. For most martian packets,
* ip_route_output_key() will fail. It won't fail for 2 types of
* martian destinations: loopback destinations and destination
* 0.0.0.0. In both cases the packet will be dropped because the
* destination is the loopback device and not the bridge. */
if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
goto free_skb;
rt = ip_route_output(net, iph->daddr, 0,
RT_TOS(iph->tos), 0);
if (!IS_ERR(rt)) {
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (rt->dst.dev == dev) {
skb_dst_set(skb, &rt->dst);
goto bridged_dnat;
}
ip_rt_put(rt);
}
free_skb:
kfree_skb(skb);
return 0;
} else {
if (skb_dst(skb)->dev == dev) {
bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING,
net, sk, skb, skb->dev,
NULL,
br_nf_pre_routing_finish_bridge);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
skb->pkt_type = PACKET_HOST;
}
} else {
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
br_handle_frame_finish);
return 0;
}
