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_pppoe_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_pppoe_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)
pppoe_proto(skb) == htons(PPP_IPV6) && \
brnf_filter_pppoe_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 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 struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
+{
+ struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+
+ 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);
}
nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
- skb->dst = (struct dst_entry *)&__fake_rtable;
- dst_hold(skb->dst);
+ skb->rtable = bridge_parent_rtable(nf_bridge->physindev);
+ if (!skb->rtable) {
+ kfree_skb(skb);
+ return 0;
+ }
+ dst_hold(&skb->rtable->u.dst);
skb->dev = nf_bridge->physindev;
nf_bridge_push_encap_header(skb);
* 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()
+ * came in on, we can consider this bridging. The packet is passed
+ * through the neighbour output function to build a new destination
+ * MAC address, 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.
*
skb->nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
skb->dev = bridge_parent(skb->dev);
- if (!skb->dev)
- kfree_skb(skb);
- else {
+ if (skb->dev) {
+ struct dst_entry *dst = skb->dst;
+
nf_bridge_pull_encap_header(skb);
- skb->dst->output(skb);
+
+ if (dst->hh)
+ return neigh_hh_output(dst->hh, skb);
+ else if (dst->neighbour)
+ return dst->neighbour->output(skb);
}
+ kfree_skb(skb);
return 0;
}
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->pkt_type = PACKET_HOST;
}
} else {
- skb->dst = (struct dst_entry *)&__fake_rtable;
- dst_hold(skb->dst);
+ skb->rtable = bridge_parent_rtable(nf_bridge->physindev);
+ if (!skb->rtable) {
+ kfree_skb(skb);
+ return 0;
+ }
+ dst_hold(&skb->rtable->u.dst);
}
skb->dev = nf_bridge->physindev;
if (!setup_pre_routing(skb))
return NF_DROP;
- NF_HOOK(PF_INET6, NF_IP6_PRE_ROUTING, skb, skb->dev, NULL,
+ NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
br_nf_pre_routing_finish_ipv6);
return NF_STOLEN;
struct iphdr *iph;
__u32 len = nf_bridge_encap_header_len(skb);
- if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
- return NF_STOLEN;
-
if (unlikely(!pskb_may_pull(skb, len)))
goto out;
return NF_DROP;
store_orig_dstaddr(skb);
- NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+ NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
br_nf_pre_routing_finish);
return NF_STOLEN;
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- if (skb->dst == (struct dst_entry *)&__fake_rtable) {
- dst_release(skb->dst);
- skb->dst = NULL;
+ if (skb->rtable && skb->rtable == bridge_parent_rtable(in)) {
+ dst_release(&skb->rtable->u.dst);
+ skb->rtable = NULL;
}
return NF_ACCEPT;
{
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) ||
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;
nf_bridge_pull_encap_header(skb);
nf_bridge->mask |= BRNF_BRIDGED;
nf_bridge->physoutdev = skb->dev;
- 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;
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;
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 = skb->nf_bridge;
if (!(nf_bridge->mask & BRNF_BRIDGED_DNAT))
return NF_ACCEPT;
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) &&
+ if (skb->nfct != NULL &&
+ (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) &&
skb->len > 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 *skb,
{
struct nf_bridge_info *nf_bridge = skb->nf_bridge;
struct net_device *realoutdev = bridge_parent(skb->dev);
- int pf;
+ u_int8_t pf;
#ifdef CONFIG_NETFILTER_DEBUG
/* Be very paranoid. This probably won't happen anymore, but let's
if (!nf_bridge)
return NF_ACCEPT;
+ if (!(nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT)))
+ return NF_ACCEPT;
+
if (!realoutdev)
return NF_DROP;
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;
#ifdef CONFIG_NETFILTER_DEBUG
if (skb->dst == NULL) {
nf_bridge_pull_encap_header(skb);
nf_bridge_save_header(skb);
-#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;
* 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[] = {
+static struct nf_hook_ops br_nf_ops[] __read_mostly = {
{ .hook = br_nf_pre_routing,
.owner = THIS_MODULE,
.pf = PF_BRIDGE,
{ .hook = ip_sabotage_in,
.owner = THIS_MODULE,
.pf = PF_INET,
- .hooknum = NF_IP_PRE_ROUTING,
+ .hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_FIRST, },
{ .hook = ip_sabotage_in,
.owner = THIS_MODULE,
.pf = PF_INET6,
- .hooknum = NF_IP6_PRE_ROUTING,
+ .hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP6_PRI_FIRST, },
};
.data = &brnf_call_arptables,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &brnf_sysctl_call_tables,
+ .proc_handler = brnf_sysctl_call_tables,
},
{
.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,
},
{
.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,
},
{
.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,
},
{
.procname = "bridge-nf-filter-pppoe-tagged",
.data = &brnf_filter_pppoe_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,
- },
- { .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", .ctl_name = CTL_NET, },
+ { .procname = "bridge", .ctl_name = NET_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