/* 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;
}
/* 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;
}
/* Undo the changes made for ip6tables PREROUTING and continue the
* bridge PRE_ROUTING hook. */
static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
{
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct rtable *rt;
if (nf_bridge->mask & BRNF_PKT_TYPE) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->mask ^= BRNF_PKT_TYPE;
}
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, skb, skb->dev, NULL,
br_handle_frame_finish, 1);
return 0;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
*
* 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 sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct rtable *rt;
int err;
if (nf_bridge->mask & BRNF_PKT_TYPE) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->mask ^= BRNF_PKT_TYPE;
}
nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
if (dnat_took_place(skb)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct flowi fl = {
.fl4_dst = iph->daddr,
.fl4_tos = RT_TOS(iph->tos),
};
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;
if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (((struct dst_entry *)rt)->dev == dev) {
skb_dst_set(skb, (struct dst_entry *)rt);
goto bridged_dnat;
}
dst_release((struct dst_entry *)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);
NF_HOOK_THRESH(NFPROTO_BRIDGE,
NF_BR_PRE_ROUTING,
skb, skb->dev, NULL,
br_nf_pre_routing_finish_bridge,
1);
return 0;
}
memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
skb->pkt_type = PACKET_HOST;
}
} else {
/* 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;
}
/* Fill in the header for fragmented IP packets handled by
* the IPv4 connection tracking code.
*/
int nf_bridge_copy_header(struct sk_buff *skb)
{
int err;
unsigned int header_size;
nf_bridge_update_protocol(skb);
header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
err = skb_cow_head(skb, header_size);
if (err)
return err;
skb_copy_to_linear_data_offset(skb, -header_size,
skb->nf_bridge->data, header_size);
__skb_push(skb, nf_bridge_encap_header_len(skb));
return 0;
}
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct sk_buff *skb) {
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct net_device *in;
if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
in = nf_bridge->physindev;
if (nf_bridge->mask & BRNF_PKT_TYPE) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->mask ^= BRNF_PKT_TYPE;
}
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, skb, in,
skb->dev, br_forward_finish, 1);
return 0;
}
static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
{
int ret;
int frag_max_size;
unsigned int mtu_reserved;
if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP))
return br_dev_queue_push_xmit(sk, skb);
mtu_reserved = nf_bridge_mtu_reduction(skb);
/* This is wrong! We should preserve the original fragment
* boundaries by preserving frag_list rather than refragmenting.
*/
if (skb->len + mtu_reserved > skb->dev->mtu) {
struct brnf_frag_data *data;
frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
if (br_parse_ip_options(skb))
/* Drop invalid packet */
return NF_DROP;
IPCB(skb)->frag_max_size = 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);
ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
} else {
ret = br_dev_queue_push_xmit(sk, skb);
}
return ret;
}
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;
}
