* Linux ethernet bridge
*
* Authors:
- * Lennert Buytenhek <buytenh@gnu.org>
- * Bart De Schuymer (maintainer) <bdschuym@pandora.be>
- *
- * Changes:
- * Apr 29 2003: physdev module support (bdschuym)
- * Jun 19 2003: let arptables see bridged ARP traffic (bdschuym)
- * Oct 06 2003: filter encapsulated IP/ARP VLAN traffic on untagged bridge
- * (bdschuym)
- * Sep 01 2004: add IPv6 filtering (bdschuym)
+ * Lennert Buytenhek <buytenh@gnu.org>
+ * Bart De Schuymer <bdschuym@pandora.be>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
static int brnf_call_iptables __read_mostly = 1;
static int brnf_call_ip6tables __read_mostly = 1;
static int brnf_call_arptables __read_mostly = 1;
-static int brnf_filter_vlan_tagged __read_mostly = 1;
+static int brnf_filter_vlan_tagged __read_mostly = 0;
+static int brnf_filter_pppoe_tagged __read_mostly = 0;
#else
-#define brnf_filter_vlan_tagged 1
+#define brnf_filter_vlan_tagged 0
+#define brnf_filter_pppoe_tagged 0
#endif
static inline __be16 vlan_proto(const struct sk_buff *skb)
vlan_proto(skb) == htons(ETH_P_ARP) && \
brnf_filter_vlan_tagged)
-/* We need these fake structures to make netfilter happy --
- * lots of places assume that skb->dst != NULL, which isn't
- * all that unreasonable.
- *
+static inline __be16 pppoe_proto(const struct sk_buff *skb)
+{
+ return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
+ sizeof(struct pppoe_hdr)));
+}
+
+#define IS_PPPOE_IP(skb) \
+ (skb->protocol == htons(ETH_P_PPP_SES) && \
+ pppoe_proto(skb) == htons(PPP_IP) && \
+ brnf_filter_pppoe_tagged)
+
+#define IS_PPPOE_IPV6(skb) \
+ (skb->protocol == htons(ETH_P_PPP_SES) && \
+ pppoe_proto(skb) == htons(PPP_IPV6) && \
+ brnf_filter_pppoe_tagged)
+
+static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+}
+
+static struct dst_ops fake_dst_ops = {
+ .family = AF_INET,
+ .protocol = cpu_to_be16(ETH_P_IP),
+ .update_pmtu = fake_update_pmtu,
+ .entries = ATOMIC_INIT(0),
+};
+
+/*
+ * Initialize bogus route table used to keep netfilter happy.
* Currently, we fill in the PMTU entry because netfilter
* refragmentation needs it, and the rt_flags entry because
* ipt_REJECT needs it. Future netfilter modules might
- * require us to fill additional fields. */
-static struct net_device __fake_net_device = {
- .hard_header_len = ETH_HLEN
-};
+ * require us to fill additional fields.
+ */
+void br_netfilter_rtable_init(struct net_bridge *br)
+{
+ struct rtable *rt = &br->fake_rtable;
+
+ atomic_set(&rt->u.dst.__refcnt, 1);
+ rt->u.dst.dev = br->dev;
+ rt->u.dst.path = &rt->u.dst;
+ rt->u.dst.metrics[RTAX_MTU - 1] = 1500;
+ rt->u.dst.flags = DST_NOXFRM;
+ rt->u.dst.ops = &fake_dst_ops;
+}
-static struct rtable __fake_rtable = {
- .u = {
- .dst = {
- .__refcnt = ATOMIC_INIT(1),
- .dev = &__fake_net_device,
- .path = &__fake_rtable.u.dst,
- .metrics = {[RTAX_MTU - 1] = 1500},
- .flags = DST_NOXFRM,
- }
- },
- .rt_flags = 0,
-};
+static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
+{
+ struct net_bridge_port *port = rcu_dereference(dev->br_port);
+
+ return port ? &port->br->fake_rtable : NULL;
+}
static inline struct net_device *bridge_parent(const struct net_device *dev)
{
return skb->nf_bridge;
}
-static inline void nf_bridge_save_header(struct sk_buff *skb)
+static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
{
- int header_size = ETH_HLEN;
+ struct nf_bridge_info *nf_bridge = skb->nf_bridge;
- if (skb->protocol == htons(ETH_P_8021Q))
- header_size += VLAN_HLEN;
+ if (atomic_read(&nf_bridge->use) > 1) {
+ struct nf_bridge_info *tmp = nf_bridge_alloc(skb);
+
+ if (tmp) {
+ memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info));
+ atomic_set(&tmp->use, 1);
+ nf_bridge_put(nf_bridge);
+ }
+ nf_bridge = tmp;
+ }
+ return nf_bridge;
+}
+
+static inline void nf_bridge_push_encap_header(struct sk_buff *skb)
+{
+ unsigned int len = nf_bridge_encap_header_len(skb);
+
+ skb_push(skb, len);
+ skb->network_header -= len;
+}
+
+static inline void nf_bridge_pull_encap_header(struct sk_buff *skb)
+{
+ unsigned int len = nf_bridge_encap_header_len(skb);
+
+ skb_pull(skb, len);
+ skb->network_header += len;
+}
+
+static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
+{
+ unsigned int len = nf_bridge_encap_header_len(skb);
+
+ skb_pull_rcsum(skb, len);
+ skb->network_header += len;
+}
+
+static inline void nf_bridge_save_header(struct sk_buff *skb)
+{
+ int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
skb_copy_from_linear_data_offset(skb, -header_size,
skb->nf_bridge->data, header_size);
}
-/*
- * When forwarding bridge frames, we save a copy of the original
- * header before processing.
+static inline void nf_bridge_update_protocol(struct sk_buff *skb)
+{
+ if (skb->nf_bridge->mask & BRNF_8021Q)
+ skb->protocol = htons(ETH_P_8021Q);
+ else if (skb->nf_bridge->mask & BRNF_PPPoE)
+ skb->protocol = htons(ETH_P_PPP_SES);
+}
+
+/* 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;
- int header_size = ETH_HLEN;
-
- if (skb->protocol == htons(ETH_P_8021Q))
- header_size += VLAN_HLEN;
+ unsigned int header_size;
- err = skb_cow(skb, 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;
- memcpy(skb->data - header_size, skb->nf_bridge->data, header_size);
-
- if (skb->protocol == htons(ETH_P_8021Q))
- __skb_push(skb, VLAN_HLEN);
+ 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;
}
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_NF_BRIDGE_PREROUTING;
- skb->dst = (struct dst_entry *)&__fake_rtable;
- dst_hold(skb->dst);
+ rt = bridge_parent_rtable(nf_bridge->physindev);
+ if (!rt) {
+ kfree_skb(skb);
+ return 0;
+ }
+ dst_hold(&rt->u.dst);
+ skb_dst_set(skb, &rt->u.dst);
skb->dev = nf_bridge->physindev;
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_push(skb, VLAN_HLEN);
- skb->network_header -= VLAN_HLEN;
- }
- NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+ 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;
}
-static void __br_dnat_complain(void)
+/* 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)
{
- static unsigned long last_complaint;
+ struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+ struct dst_entry *dst;
- if (jiffies - last_complaint >= 5 * HZ) {
- printk(KERN_WARNING "Performing cross-bridge DNAT requires IP "
- "forwarding to be enabled\n");
- last_complaint = jiffies;
+ skb->dev = bridge_parent(skb->dev);
+ if (!skb->dev)
+ goto free_skb;
+ dst = skb_dst(skb);
+ if (dst->hh) {
+ neigh_hh_bridge(dst->hh, skb);
+ skb->dev = nf_bridge->physindev;
+ return br_handle_frame_finish(skb);
+ } else if (dst->neighbour) {
+ /* 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 dst->neighbour->output(skb);
}
+free_skb:
+ kfree_skb(skb);
+ return 0;
}
/* This requires some explaining. If DNAT has taken place,
- * we will need to fix up the destination Ethernet address,
- * and this is a tricky process.
+ * 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
* call ip_route_input() and to look at skb->dst->dev, which is
* changed to the destination device if ip_route_input() succeeds.
*
- * Let us first consider the case that ip_route_input() succeeds:
- *
- * If skb->dst->dev equals the logical bridge device the packet
- * came in on, we can consider this bridging. We then call
- * skb->dst->output() which will make the packet enter br_nf_local_out()
- * not much later. In that function it is assured that the iptables
- * FORWARD chain is traversed for the packet.
+ * 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 us now consider the case that ip_route_input() fails:
+ * 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.
- * After a "echo '0' > /proc/sys/net/ipv4/ip_forward" ip_route_input()
- * will fail, while __ip_route_output_key() will return success. The source
- * address for __ip_route_output_key() is set to zero, so __ip_route_output_key
+ * 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 allowed. We send a warning message to the users's
- * log telling her to put IP forwarding on.
- *
- * ip_route_input() will also fail if there is no route available.
- * In that case we just drop the packet.
- *
- * --Lennert, 20020411
- * --Bart, 20020416 (updated)
- * --Bart, 20021007 (updated)
- * --Bart, 20062711 (updated) */
-static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
-{
- if (skb->pkt_type == PACKET_OTHERHOST) {
- skb->pkt_type = PACKET_HOST;
- skb->nf_bridge->mask |= BRNF_PKT_TYPE;
- }
- skb->nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
-
- skb->dev = bridge_parent(skb->dev);
- if (!skb->dev)
- kfree_skb(skb);
- else {
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_pull(skb, VLAN_HLEN);
- skb->network_header += VLAN_HLEN;
- }
- skb->dst->output(skb);
- }
- return 0;
-}
-
+ * 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) {
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 rtable *rt;
struct flowi fl = {
.nl_u = {
.ip4_u = {
},
.proto = 0,
};
- struct in_device *in_dev = in_dev_get(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
if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
goto free_skb;
- if (!ip_route_output_key(&rt, &fl)) {
+ 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 = (struct dst_entry *)rt;
+ skb_dst_set(skb, (struct dst_entry *)rt);
goto bridged_dnat;
}
- /* we are sure that forwarding is disabled, so printing
- * this message is no problem. Note that the packet could
- * still have a martian destination address, in which case
- * the packet could be dropped even if forwarding were enabled */
- __br_dnat_complain();
dst_release((struct dst_entry *)rt);
}
free_skb:
kfree_skb(skb);
return 0;
} else {
- if (skb->dst->dev == dev) {
+ if (skb_dst(skb)->dev == dev) {
bridged_dnat:
- /* Tell br_nf_local_out this is a
- * bridged frame */
- nf_bridge->mask |= BRNF_BRIDGED_DNAT;
skb->dev = nf_bridge->physindev;
- if (skb->protocol ==
- htons(ETH_P_8021Q)) {
- skb_push(skb, VLAN_HLEN);
- skb->network_header -= VLAN_HLEN;
- }
- NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING,
+ 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);
skb->pkt_type = PACKET_HOST;
}
} else {
- skb->dst = (struct dst_entry *)&__fake_rtable;
- dst_hold(skb->dst);
+ rt = bridge_parent_rtable(nf_bridge->physindev);
+ if (!rt) {
+ kfree_skb(skb);
+ return 0;
+ }
+ dst_hold(&rt->u.dst);
+ skb_dst_set(skb, &rt->u.dst);
}
skb->dev = nf_bridge->physindev;
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_push(skb, VLAN_HLEN);
- skb->network_header -= VLAN_HLEN;
- }
- NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+ 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;
nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING;
nf_bridge->physindev = skb->dev;
skb->dev = bridge_parent(skb->dev);
+ if (skb->protocol == htons(ETH_P_8021Q))
+ nf_bridge->mask |= BRNF_8021Q;
+ else if (skb->protocol == htons(ETH_P_PPP_SES))
+ nf_bridge->mask |= BRNF_PPPoE;
return skb->dev;
}
if (!setup_pre_routing(skb))
return NF_DROP;
- NF_HOOK(PF_INET6, NF_IP6_PRE_ROUTING, skb, skb->dev, NULL,
+ skb->protocol = htons(ETH_P_IPV6);
+ NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
br_nf_pre_routing_finish_ipv6);
return NF_STOLEN;
* 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(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct iphdr *iph;
- __u32 len;
- struct sk_buff *skb = *pskb;
+ __u32 len = nf_bridge_encap_header_len(skb);
- if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb)) {
+ if (unlikely(!pskb_may_pull(skb, len)))
+ goto out;
+
+ if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+ IS_PPPOE_IPV6(skb)) {
#ifdef CONFIG_SYSCTL
if (!brnf_call_ip6tables)
return NF_ACCEPT;
#endif
- if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
- goto out;
-
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_pull_rcsum(skb, VLAN_HLEN);
- skb->network_header += VLAN_HLEN;
- }
+ nf_bridge_pull_encap_header_rcsum(skb);
return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn);
}
#ifdef CONFIG_SYSCTL
return NF_ACCEPT;
#endif
- if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb))
+ if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) &&
+ !IS_PPPOE_IP(skb))
return NF_ACCEPT;
- if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
- goto out;
-
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_pull_rcsum(skb, VLAN_HLEN);
- skb->network_header += VLAN_HLEN;
- }
+ nf_bridge_pull_encap_header_rcsum(skb);
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
if (!setup_pre_routing(skb))
return NF_DROP;
store_orig_dstaddr(skb);
+ skb->protocol = htons(ETH_P_IP);
- NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+ NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
br_nf_pre_routing_finish);
return NF_STOLEN;
* took place when the packet entered the bridge), but we
* register an IPv4 PRE_ROUTING 'sabotage' hook that will
* prevent this from happening. */
-static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- struct sk_buff *skb = *pskb;
+ struct rtable *rt = skb_rtable(skb);
- if (skb->dst == (struct dst_entry *)&__fake_rtable) {
- dst_release(skb->dst);
- skb->dst = NULL;
- }
+ if (rt && rt == bridge_parent_rtable(in))
+ skb_dst_drop(skb);
return NF_ACCEPT;
}
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->mask ^= BRNF_PKT_TYPE;
}
+ nf_bridge_update_protocol(skb);
} else {
in = *((struct net_device **)(skb->cb));
}
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_push(skb, VLAN_HLEN);
- skb->network_header -= VLAN_HLEN;
- }
- NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, in,
+ nf_bridge_push_encap_header(skb);
+
+ NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in,
skb->dev, br_forward_finish, 1);
return 0;
}
* 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(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- struct sk_buff *skb = *pskb;
struct nf_bridge_info *nf_bridge;
struct net_device *parent;
- int pf;
+ 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;
+
parent = bridge_parent(out);
if (!parent)
return NF_DROP;
- if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb))
+ if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
+ IS_PPPOE_IP(skb))
pf = PF_INET;
- else
+ else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+ IS_PPPOE_IPV6(skb))
pf = PF_INET6;
+ else
+ return NF_ACCEPT;
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_pull(*pskb, VLAN_HLEN);
- (*pskb)->network_header += VLAN_HLEN;
- }
+ nf_bridge_pull_encap_header(skb);
nf_bridge = skb->nf_bridge;
if (skb->pkt_type == PACKET_OTHERHOST) {
/* The physdev module checks on this */
nf_bridge->mask |= BRNF_BRIDGED;
nf_bridge->physoutdev = skb->dev;
+ if (pf == PF_INET)
+ skb->protocol = htons(ETH_P_IP);
+ else
+ skb->protocol = htons(ETH_P_IPV6);
- NF_HOOK(pf, NF_IP_FORWARD, skb, bridge_parent(in), parent,
+ NF_HOOK(pf, NF_INET_FORWARD, skb, bridge_parent(in), parent,
br_nf_forward_finish);
return NF_STOLEN;
}
-static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- struct sk_buff *skb = *pskb;
struct net_device **d = (struct net_device **)(skb->cb);
#ifdef CONFIG_SYSCTL
if (skb->protocol != htons(ETH_P_ARP)) {
if (!IS_VLAN_ARP(skb))
return NF_ACCEPT;
- skb_pull(*pskb, VLAN_HLEN);
- (*pskb)->network_header += VLAN_HLEN;
+ nf_bridge_pull_encap_header(skb);
}
if (arp_hdr(skb)->ar_pln != 4) {
- if (IS_VLAN_ARP(skb)) {
- skb_push(*pskb, VLAN_HLEN);
- (*pskb)->network_header -= VLAN_HLEN;
- }
+ if (IS_VLAN_ARP(skb))
+ nf_bridge_push_encap_header(skb);
return NF_ACCEPT;
}
*d = (struct net_device *)in;
- NF_HOOK(NF_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
+ NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
(struct net_device *)out, br_nf_forward_finish);
return NF_STOLEN;
}
-/* PF_BRIDGE/LOCAL_OUT ***********************************************
- *
- * This function sees both locally originated IP packets and forwarded
- * IP packets (in both cases the destination device is a bridge
- * device). It also sees bridged-and-DNAT'ed packets.
- *
- * If (nf_bridge->mask & BRNF_BRIDGED_DNAT) then the packet is bridged
- * and we fake the PF_BRIDGE/FORWARD hook. The function br_nf_forward()
- * will then fake the PF_INET/FORWARD hook. br_nf_local_out() has priority
- * NF_BR_PRI_FIRST, so no relevant PF_BRIDGE/INPUT functions have been nor
- * will be executed.
- */
-static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct net_device *realindev;
- struct sk_buff *skb = *pskb;
- struct nf_bridge_info *nf_bridge;
-
- if (!skb->nf_bridge)
- return NF_ACCEPT;
-
- nf_bridge = skb->nf_bridge;
- if (!(nf_bridge->mask & BRNF_BRIDGED_DNAT))
- return NF_ACCEPT;
-
- /* Bridged, take PF_BRIDGE/FORWARD.
- * (see big note in front of br_nf_pre_routing_finish) */
- nf_bridge->physoutdev = skb->dev;
- realindev = nf_bridge->physindev;
-
- if (nf_bridge->mask & BRNF_PKT_TYPE) {
- skb->pkt_type = PACKET_OTHERHOST;
- nf_bridge->mask ^= BRNF_PKT_TYPE;
- }
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_push(skb, VLAN_HLEN);
- skb->network_header -= VLAN_HLEN;
- }
-
- NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, realindev, skb->dev,
- br_forward_finish);
- return NF_STOLEN;
-}
-
+#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE)
static int br_nf_dev_queue_xmit(struct sk_buff *skb)
{
- if (skb->protocol == htons(ETH_P_IP) &&
- skb->len > skb->dev->mtu &&
+ if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
+ skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
!skb_is_gso(skb))
return ip_fragment(skb, br_dev_queue_push_xmit);
else
return br_dev_queue_push_xmit(skb);
}
+#else
+static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+{
+ return br_dev_queue_push_xmit(skb);
+}
+#endif
/* PF_BRIDGE/POST_ROUTING ********************************************/
-static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb,
+static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- struct sk_buff *skb = *pskb;
- struct nf_bridge_info *nf_bridge = (*pskb)->nf_bridge;
+ struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct net_device *realoutdev = bridge_parent(skb->dev);
- int pf;
-
-#ifdef CONFIG_NETFILTER_DEBUG
- /* Be very paranoid. This probably won't happen anymore, but let's
- * keep the check just to be sure... */
- if (skb_mac_header(skb) < skb->head ||
- skb_mac_header(skb) + ETH_HLEN > skb->data) {
- printk(KERN_CRIT "br_netfilter: Argh!! br_nf_post_routing: "
- "bad mac.raw pointer.\n");
- goto print_error;
- }
-#endif
+ u_int8_t pf;
- if (!nf_bridge)
+ if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED))
return NF_ACCEPT;
if (!realoutdev)
return NF_DROP;
- if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb))
+ if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) ||
+ IS_PPPOE_IP(skb))
pf = PF_INET;
- else
+ else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) ||
+ IS_PPPOE_IPV6(skb))
pf = PF_INET6;
-
-#ifdef CONFIG_NETFILTER_DEBUG
- if (skb->dst == NULL) {
- printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n");
- goto print_error;
- }
-#endif
+ 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. */
nf_bridge->mask |= BRNF_PKT_TYPE;
}
- if (skb->protocol == htons(ETH_P_8021Q)) {
- skb_pull(skb, VLAN_HLEN);
- skb->network_header += VLAN_HLEN;
- }
-
+ nf_bridge_pull_encap_header(skb);
nf_bridge_save_header(skb);
+ if (pf == PF_INET)
+ skb->protocol = htons(ETH_P_IP);
+ else
+ skb->protocol = htons(ETH_P_IPV6);
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
- if (nf_bridge->netoutdev)
- realoutdev = nf_bridge->netoutdev;
-#endif
- NF_HOOK(pf, NF_IP_POST_ROUTING, skb, NULL, realoutdev,
+ NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev,
br_nf_dev_queue_xmit);
return NF_STOLEN;
-
-#ifdef CONFIG_NETFILTER_DEBUG
-print_error:
- if (skb->dev != NULL) {
- printk("[%s]", skb->dev->name);
- if (realoutdev)
- printk("[%s]", realoutdev->name);
- }
- printk(" head:%p, raw:%p, data:%p\n", skb->head, skb_mac_header(skb),
- skb->data);
- dump_stack();
- return NF_ACCEPT;
-#endif
}
/* IP/SABOTAGE *****************************************************/
/* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING
* for the second time. */
-static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff **pskb,
+static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- if ((*pskb)->nf_bridge &&
- !((*pskb)->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
+ if (skb->nf_bridge &&
+ !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
return NF_STOP;
}
return NF_ACCEPT;
}
-/* For br_nf_local_out we need (prio = NF_BR_PRI_FIRST), to insure that innocent
- * PF_BRIDGE/NF_BR_LOCAL_OUT functions don't get bridged traffic as input.
- * For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
- * ip_refrag() can return NF_STOLEN. */
-static struct nf_hook_ops br_nf_ops[] = {
- { .hook = br_nf_pre_routing,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_PRE_ROUTING,
- .priority = NF_BR_PRI_BRNF, },
- { .hook = br_nf_local_in,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_LOCAL_IN,
- .priority = NF_BR_PRI_BRNF, },
- { .hook = br_nf_forward_ip,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_FORWARD,
- .priority = NF_BR_PRI_BRNF - 1, },
- { .hook = br_nf_forward_arp,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_FORWARD,
- .priority = NF_BR_PRI_BRNF, },
- { .hook = br_nf_local_out,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_LOCAL_OUT,
- .priority = NF_BR_PRI_FIRST, },
- { .hook = br_nf_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_BRIDGE,
- .hooknum = NF_BR_POST_ROUTING,
- .priority = NF_BR_PRI_LAST, },
- { .hook = ip_sabotage_in,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_IP_PRE_ROUTING,
- .priority = NF_IP_PRI_FIRST, },
- { .hook = ip_sabotage_in,
- .owner = THIS_MODULE,
- .pf = PF_INET6,
- .hooknum = NF_IP6_PRE_ROUTING,
- .priority = NF_IP6_PRI_FIRST, },
+/* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
+ * br_dev_queue_push_xmit is called afterwards */
+static struct nf_hook_ops br_nf_ops[] __read_mostly = {
+ {
+ .hook = br_nf_pre_routing,
+ .owner = THIS_MODULE,
+ .pf = PF_BRIDGE,
+ .hooknum = NF_BR_PRE_ROUTING,
+ .priority = NF_BR_PRI_BRNF,
+ },
+ {
+ .hook = br_nf_local_in,
+ .owner = THIS_MODULE,
+ .pf = PF_BRIDGE,
+ .hooknum = NF_BR_LOCAL_IN,
+ .priority = NF_BR_PRI_BRNF,
+ },
+ {
+ .hook = br_nf_forward_ip,
+ .owner = THIS_MODULE,
+ .pf = PF_BRIDGE,
+ .hooknum = NF_BR_FORWARD,
+ .priority = NF_BR_PRI_BRNF - 1,
+ },
+ {
+ .hook = br_nf_forward_arp,
+ .owner = THIS_MODULE,
+ .pf = PF_BRIDGE,
+ .hooknum = NF_BR_FORWARD,
+ .priority = NF_BR_PRI_BRNF,
+ },
+ {
+ .hook = br_nf_post_routing,
+ .owner = THIS_MODULE,
+ .pf = PF_BRIDGE,
+ .hooknum = NF_BR_POST_ROUTING,
+ .priority = NF_BR_PRI_LAST,
+ },
+ {
+ .hook = ip_sabotage_in,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_PRE_ROUTING,
+ .priority = NF_IP_PRI_FIRST,
+ },
+ {
+ .hook = ip_sabotage_in,
+ .owner = THIS_MODULE,
+ .pf = PF_INET6,
+ .hooknum = NF_INET_PRE_ROUTING,
+ .priority = NF_IP6_PRI_FIRST,
+ },
};
#ifdef CONFIG_SYSCTL
static
-int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp,
+int brnf_sysctl_call_tables(ctl_table * ctl, int write,
void __user * buffer, size_t * lenp, loff_t * ppos)
{
int ret;
- ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write && *(int *)(ctl->data))
*(int *)(ctl->data) = 1;
static ctl_table brnf_table[] = {
{
- .ctl_name = NET_BRIDGE_NF_CALL_ARPTABLES,
.procname = "bridge-nf-call-arptables",
.data = &brnf_call_arptables,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &brnf_sysctl_call_tables,
+ .proc_handler = brnf_sysctl_call_tables,
},
{
- .ctl_name = NET_BRIDGE_NF_CALL_IPTABLES,
.procname = "bridge-nf-call-iptables",
.data = &brnf_call_iptables,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &brnf_sysctl_call_tables,
+ .proc_handler = brnf_sysctl_call_tables,
},
{
- .ctl_name = NET_BRIDGE_NF_CALL_IP6TABLES,
.procname = "bridge-nf-call-ip6tables",
.data = &brnf_call_ip6tables,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &brnf_sysctl_call_tables,
+ .proc_handler = brnf_sysctl_call_tables,
},
{
- .ctl_name = NET_BRIDGE_NF_FILTER_VLAN_TAGGED,
.procname = "bridge-nf-filter-vlan-tagged",
.data = &brnf_filter_vlan_tagged,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &brnf_sysctl_call_tables,
+ .proc_handler = brnf_sysctl_call_tables,
},
- { .ctl_name = 0 }
-};
-
-static ctl_table brnf_bridge_table[] = {
{
- .ctl_name = NET_BRIDGE,
- .procname = "bridge",
- .mode = 0555,
- .child = brnf_table,
+ .procname = "bridge-nf-filter-pppoe-tagged",
+ .data = &brnf_filter_pppoe_tagged,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = brnf_sysctl_call_tables,
},
- { .ctl_name = 0 }
+ { }
};
-static ctl_table brnf_net_table[] = {
- {
- .ctl_name = CTL_NET,
- .procname = "net",
- .mode = 0555,
- .child = brnf_bridge_table,
- },
- { .ctl_name = 0 }
+static struct ctl_path brnf_path[] = {
+ { .procname = "net", },
+ { .procname = "bridge", },
+ { }
};
#endif
if (ret < 0)
return ret;
#ifdef CONFIG_SYSCTL
- brnf_sysctl_header = register_sysctl_table(brnf_net_table);
+ brnf_sysctl_header = register_sysctl_paths(brnf_path, brnf_table);
if (brnf_sysctl_header == NULL) {
printk(KERN_WARNING
"br_netfilter: can't register to sysctl.\n");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff