Initial commit; kernel source import

net/bridge/Kconfig

@@ -0,0 +1,62 @@
+#
+# 802.1d Ethernet Bridging
+#
+
+config BRIDGE
+	tristate "802.1d Ethernet Bridging"
+	select LLC
+	select STP
+	depends on IPV6 || IPV6=n
+	---help---
+	  If you say Y here, then your Linux box will be able to act as an
+	  Ethernet bridge, which means that the different Ethernet segments it
+	  is connected to will appear as one Ethernet to the participants.
+	  Several such bridges can work together to create even larger
+	  networks of Ethernets using the IEEE 802.1 spanning tree algorithm.
+	  As this is a standard, Linux bridges will cooperate properly with
+	  other third party bridge products.
+
+	  In order to use the Ethernet bridge, you'll need the bridge
+	  configuration tools; see <file:Documentation/networking/bridge.txt>
+	  for location. Please read the Bridge mini-HOWTO for more
+	  information.
+
+	  If you enable iptables support along with the bridge support then you
+	  turn your bridge into a bridging IP firewall.
+	  iptables will then see the IP packets being bridged, so you need to
+	  take this into account when setting up your firewall rules.
+	  Enabling arptables support when bridging will let arptables see
+	  bridged ARP traffic in the arptables FORWARD chain.
+
+	  To compile this code as a module, choose M here: the module
+	  will be called bridge.
+
+	  If unsure, say N.
+
+config BRIDGE_IGMP_SNOOPING
+	bool "IGMP/MLD snooping"
+	depends on BRIDGE
+	depends on INET
+	default y
+	---help---
+	  If you say Y here, then the Ethernet bridge will be able selectively
+	  forward multicast traffic based on IGMP/MLD traffic received from
+	  each port.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.
+
+config BRIDGE_VLAN_FILTERING
+	bool "VLAN filtering"
+	depends on BRIDGE
+	depends on VLAN_8021Q
+	default n
+	---help---
+	  If you say Y here, then the Ethernet bridge will be able selectively
+	  receive and forward traffic based on VLAN information in the packet
+	  any VLAN information configured on the bridge port or bridge device.
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say Y.

net/bridge/Makefile

@@ -0,0 +1,19 @@
+#
+# Makefile for the IEEE 802.1d ethernet bridging layer.
+#
+
+obj-$(CONFIG_BRIDGE) += bridge.o
+
+bridge-y	:= br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
+			br_ioctl.o br_notify.o br_stp.o br_stp_bpdu.o \
+			br_stp_if.o br_stp_timer.o br_netlink.o
+
+bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
+
+bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o
+
+bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
+
+bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o
+
+obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/

net/bridge/br.c

@@ -0,0 +1,107 @@
+/*
+ *	Generic parts
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/init.h>
+#include <linux/llc.h>
+#include <net/llc.h>
+#include <net/stp.h>
+
+#include "br_private.h"
+
+static const struct stp_proto br_stp_proto = {
+	.rcv	= br_stp_rcv,
+};
+
+static struct pernet_operations br_net_ops = {
+	.exit	= br_net_exit,
+};
+
+static int __init br_init(void)
+{
+	int err;
+
+	err = stp_proto_register(&br_stp_proto);
+	if (err < 0) {
+		pr_err("bridge: can't register sap for STP\n");
+		return err;
+	}
+
+	err = br_fdb_init();
+	if (err)
+		goto err_out;
+
+	err = register_pernet_subsys(&br_net_ops);
+	if (err)
+		goto err_out1;
+
+	err = br_netfilter_init();
+	if (err)
+		goto err_out2;
+
+	err = register_netdevice_notifier(&br_device_notifier);
+	if (err)
+		goto err_out3;
+
+	err = br_netlink_init();
+	if (err)
+		goto err_out4;
+
+	brioctl_set(br_ioctl_deviceless_stub);
+
+#if IS_ENABLED(CONFIG_ATM_LANE)
+	br_fdb_test_addr_hook = br_fdb_test_addr;
+#endif
+
+	return 0;
+err_out4:
+	unregister_netdevice_notifier(&br_device_notifier);
+err_out3:
+	br_netfilter_fini();
+err_out2:
+	unregister_pernet_subsys(&br_net_ops);
+err_out1:
+	br_fdb_fini();
+err_out:
+	stp_proto_unregister(&br_stp_proto);
+	return err;
+}
+
+static void __exit br_deinit(void)
+{
+	stp_proto_unregister(&br_stp_proto);
+
+	br_netlink_fini();
+	unregister_netdevice_notifier(&br_device_notifier);
+	brioctl_set(NULL);
+
+	unregister_pernet_subsys(&br_net_ops);
+
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
+
+	br_netfilter_fini();
+#if IS_ENABLED(CONFIG_ATM_LANE)
+	br_fdb_test_addr_hook = NULL;
+#endif
+
+	br_fdb_fini();
+}
+
+module_init(br_init)
+module_exit(br_deinit)
+MODULE_LICENSE("GPL");
+MODULE_VERSION(BR_VERSION);
+MODULE_ALIAS_RTNL_LINK("bridge");

net/bridge/br_device.c

@@ -0,0 +1,378 @@
+/*
+ *	Device handling code
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/netpoll.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/list.h>
+#include <linux/netfilter_bridge.h>
+
+#include <asm/uaccess.h>
+#include "br_private.h"
+
+/* net device transmit always called with BH disabled */
+netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	const unsigned char *dest = skb->data;
+	struct net_bridge_fdb_entry *dst;
+	struct net_bridge_mdb_entry *mdst;
+	struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+	u16 vid = 0;
+
+	rcu_read_lock();
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
+		br_nf_pre_routing_finish_bridge_slow(skb);
+		rcu_read_unlock();
+		return NETDEV_TX_OK;
+	}
+#endif
+
+	u64_stats_update_begin(&brstats->syncp);
+	brstats->tx_packets++;
+	brstats->tx_bytes += skb->len;
+	u64_stats_update_end(&brstats->syncp);
+
+	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+		goto out;
+
+	BR_INPUT_SKB_CB(skb)->brdev = dev;
+
+	skb_reset_mac_header(skb);
+	skb_pull(skb, ETH_HLEN);
+
+	if (is_broadcast_ether_addr(dest))
+		br_flood_deliver(br, skb);
+	else if (is_multicast_ether_addr(dest)) {
+		if (unlikely(netpoll_tx_running(dev))) {
+			br_flood_deliver(br, skb);
+			goto out;
+		}
+		if (br_multicast_rcv(br, NULL, skb)) {
+			kfree_skb(skb);
+			goto out;
+		}
+
+		mdst = br_mdb_get(br, skb, vid);
+		if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb))
+			br_multicast_deliver(mdst, skb);
+		else
+			br_flood_deliver(br, skb);
+	} else if ((dst = __br_fdb_get(br, dest, vid)) != NULL)
+		br_deliver(dst->dst, skb);
+	else
+		br_flood_deliver(br, skb);
+
+out:
+	rcu_read_unlock();
+	return NETDEV_TX_OK;
+}
+
+static int br_dev_init(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	br->stats = alloc_percpu(struct br_cpu_netstats);
+	if (!br->stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int br_dev_open(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	netdev_update_features(dev);
+	netif_start_queue(dev);
+	br_stp_enable_bridge(br);
+	br_multicast_open(br);
+
+	return 0;
+}
+
+static void br_dev_set_multicast_list(struct net_device *dev)
+{
+}
+
+static int br_dev_stop(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	br_stp_disable_bridge(br);
+	br_multicast_stop(br);
+
+	netif_stop_queue(dev);
+
+	return 0;
+}
+
+static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
+						struct rtnl_link_stats64 *stats)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct br_cpu_netstats tmp, sum = { 0 };
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		unsigned int start;
+		const struct br_cpu_netstats *bstats
+			= per_cpu_ptr(br->stats, cpu);
+		do {
+			start = u64_stats_fetch_begin_bh(&bstats->syncp);
+			memcpy(&tmp, bstats, sizeof(tmp));
+		} while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
+		sum.tx_bytes   += tmp.tx_bytes;
+		sum.tx_packets += tmp.tx_packets;
+		sum.rx_bytes   += tmp.rx_bytes;
+		sum.rx_packets += tmp.rx_packets;
+	}
+
+	stats->tx_bytes   = sum.tx_bytes;
+	stats->tx_packets = sum.tx_packets;
+	stats->rx_bytes   = sum.rx_bytes;
+	stats->rx_packets = sum.rx_packets;
+
+	return stats;
+}
+
+static int br_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	if (new_mtu < 68 || new_mtu > br_min_mtu(br))
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+	/* remember the MTU in the rtable for PMTU */
+	dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
+#endif
+
+	return 0;
+}
+
+/* Allow setting mac address to any valid ethernet address. */
+static int br_set_mac_address(struct net_device *dev, void *p)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	spin_lock_bh(&br->lock);
+	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
+		memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+		br_fdb_change_mac_address(br, addr->sa_data);
+		br_stp_change_bridge_id(br, addr->sa_data);
+	}
+	spin_unlock_bh(&br->lock);
+
+	return 0;
+}
+
+static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, "bridge", sizeof(info->driver));
+	strlcpy(info->version, BR_VERSION, sizeof(info->version));
+	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
+	strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
+}
+
+static netdev_features_t br_fix_features(struct net_device *dev,
+	netdev_features_t features)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	return br_features_recompute(br, features);
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void br_poll_controller(struct net_device *br_dev)
+{
+}
+
+static void br_netpoll_cleanup(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p;
+
+	list_for_each_entry(p, &br->port_list, list)
+		br_netpoll_disable(p);
+}
+
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
+			    gfp_t gfp)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p;
+	int err = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!p->dev)
+			continue;
+		err = br_netpoll_enable(p, gfp);
+		if (err)
+			goto fail;
+	}
+
+out:
+	return err;
+
+fail:
+	br_netpoll_cleanup(dev);
+	goto out;
+}
+
+int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+{
+	struct netpoll *np;
+	int err = 0;
+
+	np = kzalloc(sizeof(*p->np), gfp);
+	err = -ENOMEM;
+	if (!np)
+		goto out;
+
+	err = __netpoll_setup(np, p->dev, gfp);
+	if (err) {
+		kfree(np);
+		goto out;
+	}
+
+	p->np = np;
+
+out:
+	return err;
+}
+
+void br_netpoll_disable(struct net_bridge_port *p)
+{
+	struct netpoll *np = p->np;
+
+	if (!np)
+		return;
+
+	p->np = NULL;
+
+	__netpoll_free_async(np);
+}
+
+#endif
+
+static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
+
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	return br_add_if(br, slave_dev);
+}
+
+static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	return br_del_if(br, slave_dev);
+}
+
+static const struct ethtool_ops br_ethtool_ops = {
+	.get_drvinfo    = br_getinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+static const struct net_device_ops br_netdev_ops = {
+	.ndo_open		 = br_dev_open,
+	.ndo_stop		 = br_dev_stop,
+	.ndo_init		 = br_dev_init,
+	.ndo_start_xmit		 = br_dev_xmit,
+	.ndo_get_stats64	 = br_get_stats64,
+	.ndo_set_mac_address	 = br_set_mac_address,
+	.ndo_set_rx_mode	 = br_dev_set_multicast_list,
+	.ndo_change_mtu		 = br_change_mtu,
+	.ndo_do_ioctl		 = br_dev_ioctl,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_netpoll_setup	 = br_netpoll_setup,
+	.ndo_netpoll_cleanup	 = br_netpoll_cleanup,
+	.ndo_poll_controller	 = br_poll_controller,
+#endif
+	.ndo_add_slave		 = br_add_slave,
+	.ndo_del_slave		 = br_del_slave,
+	.ndo_fix_features        = br_fix_features,
+	.ndo_fdb_add		 = br_fdb_add,
+	.ndo_fdb_del		 = br_fdb_delete,
+	.ndo_fdb_dump		 = br_fdb_dump,
+	.ndo_bridge_getlink	 = br_getlink,
+	.ndo_bridge_setlink	 = br_setlink,
+	.ndo_bridge_dellink	 = br_dellink,
+};
+
+static void br_dev_free(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	free_percpu(br->stats);
+	free_netdev(dev);
+}
+
+static struct device_type br_type = {
+	.name	= "bridge",
+};
+
+void br_dev_setup(struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	eth_hw_addr_random(dev);
+	ether_setup(dev);
+
+	dev->netdev_ops = &br_netdev_ops;
+	dev->destructor = br_dev_free;
+	SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
+	SET_NETDEV_DEVTYPE(dev, &br_type);
+	dev->tx_queue_len = 0;
+	dev->priv_flags = IFF_EBRIDGE;
+
+	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+			NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX |
+			NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX;
+	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
+			   NETIF_F_HW_VLAN_CTAG_TX;
+
+	br->dev = dev;
+	spin_lock_init(&br->lock);
+	INIT_LIST_HEAD(&br->port_list);
+	spin_lock_init(&br->hash_lock);
+
+	br->bridge_id.prio[0] = 0x80;
+	br->bridge_id.prio[1] = 0x00;
+
+	memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN);
+
+	br->stp_enabled = BR_NO_STP;
+	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
+
+	br->designated_root = br->bridge_id;
+	br->bridge_max_age = br->max_age = 20 * HZ;
+	br->bridge_hello_time = br->hello_time = 2 * HZ;
+	br->bridge_forward_delay = br->forward_delay = 15 * HZ;
+	br->ageing_time = 300 * HZ;
+
+	br_netfilter_rtable_init(br);
+	br_stp_timer_init(br);
+	br_multicast_init(br);
+}

net/bridge/br_fdb.c

@@ -0,0 +1,831 @@
+/*
+ *	Forwarding database
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/times.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/atomic.h>
+#include <asm/unaligned.h>
+#include <linux/if_vlan.h>
+#include "br_private.h"
+
+static struct kmem_cache *br_fdb_cache __read_mostly;
+static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
+		      const unsigned char *addr, u16 vid);
+static void fdb_notify(struct net_bridge *br,
+		       const struct net_bridge_fdb_entry *, int);
+
+static u32 fdb_salt __read_mostly;
+
+int __init br_fdb_init(void)
+{
+	br_fdb_cache = kmem_cache_create("bridge_fdb_cache",
+					 sizeof(struct net_bridge_fdb_entry),
+					 0,
+					 SLAB_HWCACHE_ALIGN, NULL);
+	if (!br_fdb_cache)
+		return -ENOMEM;
+
+	get_random_bytes(&fdb_salt, sizeof(fdb_salt));
+	return 0;
+}
+
+void br_fdb_fini(void)
+{
+	kmem_cache_destroy(br_fdb_cache);
+}
+
+
+/* if topology_changing then use forward_delay (default 15 sec)
+ * otherwise keep longer (default 5 minutes)
+ */
+static inline unsigned long hold_time(const struct net_bridge *br)
+{
+	return br->topology_change ? br->forward_delay : br->ageing_time;
+}
+
+static inline int has_expired(const struct net_bridge *br,
+				  const struct net_bridge_fdb_entry *fdb)
+{
+	return !fdb->is_static &&
+		time_before_eq(fdb->updated + hold_time(br), jiffies);
+}
+
+static inline int br_mac_hash(const unsigned char *mac, __u16 vid)
+{
+	/* use 1 byte of OUI and 3 bytes of NIC */
+	u32 key = get_unaligned((u32 *)(mac + 2));
+	return jhash_2words(key, vid, fdb_salt) & (BR_HASH_SIZE - 1);
+}
+
+static void fdb_rcu_free(struct rcu_head *head)
+{
+	struct net_bridge_fdb_entry *ent
+		= container_of(head, struct net_bridge_fdb_entry, rcu);
+	kmem_cache_free(br_fdb_cache, ent);
+}
+
+static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
+{
+	hlist_del_rcu(&f->hlist);
+	fdb_notify(br, f, RTM_DELNEIGH);
+	call_rcu(&f->rcu, fdb_rcu_free);
+}
+
+void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
+{
+	struct net_bridge *br = p->br;
+	bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false;
+	int i;
+
+	spin_lock_bh(&br->hash_lock);
+
+	/* Search all chains since old address/hash is unknown */
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct hlist_node *h;
+		hlist_for_each(h, &br->hash[i]) {
+			struct net_bridge_fdb_entry *f;
+
+			f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
+			if (f->dst == p && f->is_local) {
+				/* maybe another port has same hw addr? */
+				struct net_bridge_port *op;
+				u16 vid = f->vlan_id;
+				list_for_each_entry(op, &br->port_list, list) {
+					if (op != p &&
+					    ether_addr_equal(op->dev->dev_addr,
+							     f->addr.addr) &&
+					    nbp_vlan_find(op, vid)) {
+						f->dst = op;
+						goto insert;
+					}
+				}
+
+				/* delete old one */
+				fdb_delete(br, f);
+insert:
+				/* insert new address,  may fail if invalid
+				 * address or dup.
+				 */
+				fdb_insert(br, p, newaddr, vid);
+
+				/* if this port has no vlan information
+				 * configured, we can safely be done at
+				 * this point.
+				 */
+				if (no_vlan)
+					goto done;
+			}
+		}
+	}
+
+done:
+	spin_unlock_bh(&br->hash_lock);
+}
+
+void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
+{
+	struct net_bridge_fdb_entry *f;
+	struct net_port_vlans *pv;
+	u16 vid = 0;
+
+	/* If old entry was unassociated with any port, then delete it. */
+	f = __br_fdb_get(br, br->dev->dev_addr, 0);
+	if (f && f->is_local && !f->dst)
+		fdb_delete(br, f);
+
+	fdb_insert(br, NULL, newaddr, 0);
+
+	/* Now remove and add entries for every VLAN configured on the
+	 * bridge.  This function runs under RTNL so the bitmap will not
+	 * change from under us.
+	 */
+	pv = br_get_vlan_info(br);
+	if (!pv)
+		return;
+
+	for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
+		f = __br_fdb_get(br, br->dev->dev_addr, vid);
+		if (f && f->is_local && !f->dst)
+			fdb_delete(br, f);
+		fdb_insert(br, NULL, newaddr, vid);
+	}
+}
+
+void br_fdb_cleanup(unsigned long _data)
+{
+	struct net_bridge *br = (struct net_bridge *)_data;
+	unsigned long delay = hold_time(br);
+	unsigned long next_timer = jiffies + br->ageing_time;
+	int i;
+
+	spin_lock(&br->hash_lock);
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct net_bridge_fdb_entry *f;
+		struct hlist_node *n;
+
+		hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) {
+			unsigned long this_timer;
+			if (f->is_static)
+				continue;
+			this_timer = f->updated + delay;
+			if (time_before_eq(this_timer, jiffies))
+				fdb_delete(br, f);
+			else if (time_before(this_timer, next_timer))
+				next_timer = this_timer;
+		}
+	}
+	spin_unlock(&br->hash_lock);
+
+	mod_timer(&br->gc_timer, round_jiffies_up(next_timer));
+}
+
+/* Completely flush all dynamic entries in forwarding database.*/
+void br_fdb_flush(struct net_bridge *br)
+{
+	int i;
+
+	spin_lock_bh(&br->hash_lock);
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct net_bridge_fdb_entry *f;
+		struct hlist_node *n;
+		hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) {
+			if (!f->is_static)
+				fdb_delete(br, f);
+		}
+	}
+	spin_unlock_bh(&br->hash_lock);
+}
+
+/* Flush all entries referring to a specific port.
+ * if do_all is set also flush static entries
+ */
+void br_fdb_delete_by_port(struct net_bridge *br,
+			   const struct net_bridge_port *p,
+			   int do_all)
+{
+	int i;
+
+	spin_lock_bh(&br->hash_lock);
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct hlist_node *h, *g;
+
+		hlist_for_each_safe(h, g, &br->hash[i]) {
+			struct net_bridge_fdb_entry *f
+				= hlist_entry(h, struct net_bridge_fdb_entry, hlist);
+			if (f->dst != p)
+				continue;
+
+			if (f->is_static && !do_all)
+				continue;
+			/*
+			 * if multiple ports all have the same device address
+			 * then when one port is deleted, assign
+			 * the local entry to other port
+			 */
+			if (f->is_local) {
+				struct net_bridge_port *op;
+				list_for_each_entry(op, &br->port_list, list) {
+					if (op != p &&
+					    ether_addr_equal(op->dev->dev_addr,
+							     f->addr.addr)) {
+						f->dst = op;
+						goto skip_delete;
+					}
+				}
+			}
+
+			fdb_delete(br, f);
+		skip_delete: ;
+		}
+	}
+	spin_unlock_bh(&br->hash_lock);
+}
+
+/* No locking or refcounting, assumes caller has rcu_read_lock */
+struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
+					  const unsigned char *addr,
+					  __u16 vid)
+{
+	struct net_bridge_fdb_entry *fdb;
+
+	hlist_for_each_entry_rcu(fdb,
+				&br->hash[br_mac_hash(addr, vid)], hlist) {
+		if (ether_addr_equal(fdb->addr.addr, addr) &&
+		    fdb->vlan_id == vid) {
+			if (unlikely(has_expired(br, fdb)))
+				break;
+			return fdb;
+		}
+	}
+
+	return NULL;
+}
+
+#if IS_ENABLED(CONFIG_ATM_LANE)
+/* Interface used by ATM LANE hook to test
+ * if an addr is on some other bridge port */
+int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
+{
+	struct net_bridge_fdb_entry *fdb;
+	struct net_bridge_port *port;
+	int ret;
+
+	rcu_read_lock();
+	port = br_port_get_rcu(dev);
+	if (!port)
+		ret = 0;
+	else {
+		fdb = __br_fdb_get(port->br, addr, 0);
+		ret = fdb && fdb->dst && fdb->dst->dev != dev &&
+			fdb->dst->state == BR_STATE_FORWARDING;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+#endif /* CONFIG_ATM_LANE */
+
+/*
+ * Fill buffer with forwarding table records in
+ * the API format.
+ */
+int br_fdb_fillbuf(struct net_bridge *br, void *buf,
+		   unsigned long maxnum, unsigned long skip)
+{
+	struct __fdb_entry *fe = buf;
+	int i, num = 0;
+	struct net_bridge_fdb_entry *f;
+
+	memset(buf, 0, maxnum*sizeof(struct __fdb_entry));
+
+	rcu_read_lock();
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry_rcu(f, &br->hash[i], hlist) {
+			if (num >= maxnum)
+				goto out;
+
+			if (has_expired(br, f))
+				continue;
+
+			/* ignore pseudo entry for local MAC address */
+			if (!f->dst)
+				continue;
+
+			if (skip) {
+				--skip;
+				continue;
+			}
+
+			/* convert from internal format to API */
+			memcpy(fe->mac_addr, f->addr.addr, ETH_ALEN);
+
+			/* due to ABI compat need to split into hi/lo */
+			fe->port_no = f->dst->port_no;
+			fe->port_hi = f->dst->port_no >> 8;
+
+			fe->is_local = f->is_local;
+			if (!f->is_static)
+				fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated);
+			++fe;
+			++num;
+		}
+	}
+
+ out:
+	rcu_read_unlock();
+
+	return num;
+}
+
+static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head,
+					     const unsigned char *addr,
+					     __u16 vid)
+{
+	struct net_bridge_fdb_entry *fdb;
+
+	hlist_for_each_entry(fdb, head, hlist) {
+		if (ether_addr_equal(fdb->addr.addr, addr) &&
+		    fdb->vlan_id == vid)
+			return fdb;
+	}
+	return NULL;
+}
+
+static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head,
+						 const unsigned char *addr,
+						 __u16 vid)
+{
+	struct net_bridge_fdb_entry *fdb;
+
+	hlist_for_each_entry_rcu(fdb, head, hlist) {
+		if (ether_addr_equal(fdb->addr.addr, addr) &&
+		    fdb->vlan_id == vid)
+			return fdb;
+	}
+	return NULL;
+}
+
+static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
+					       struct net_bridge_port *source,
+					       const unsigned char *addr,
+					       __u16 vid)
+{
+	struct net_bridge_fdb_entry *fdb;
+
+	fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC);
+	if (fdb) {
+		memcpy(fdb->addr.addr, addr, ETH_ALEN);
+		fdb->dst = source;
+		fdb->vlan_id = vid;
+		fdb->is_local = 0;
+		fdb->is_static = 0;
+		fdb->updated = fdb->used = jiffies;
+		hlist_add_head_rcu(&fdb->hlist, head);
+	}
+	return fdb;
+}
+
+static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
+		  const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+	struct net_bridge_fdb_entry *fdb;
+
+	if (!is_valid_ether_addr(addr))
+		return -EINVAL;
+
+	fdb = fdb_find(head, addr, vid);
+	if (fdb) {
+		/* it is okay to have multiple ports with same
+		 * address, just use the first one.
+		 */
+		if (fdb->is_local)
+			return 0;
+		br_warn(br, "adding interface %s with same address "
+		       "as a received packet\n",
+		       source ? source->dev->name : br->dev->name);
+		fdb_delete(br, fdb);
+	}
+
+	fdb = fdb_create(head, source, addr, vid);
+	if (!fdb)
+		return -ENOMEM;
+
+	fdb->is_local = fdb->is_static = 1;
+	fdb_notify(br, fdb, RTM_NEWNEIGH);
+	return 0;
+}
+
+/* Add entry for local address of interface */
+int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
+		  const unsigned char *addr, u16 vid)
+{
+	int ret;
+
+	spin_lock_bh(&br->hash_lock);
+	ret = fdb_insert(br, source, addr, vid);
+	spin_unlock_bh(&br->hash_lock);
+	return ret;
+}
+
+void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
+		   const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+	struct net_bridge_fdb_entry *fdb;
+
+	/* some users want to always flood. */
+	if (hold_time(br) == 0)
+		return;
+
+	/* ignore packets unless we are using this port */
+	if (!(source->state == BR_STATE_LEARNING ||
+	      source->state == BR_STATE_FORWARDING))
+		return;
+
+	fdb = fdb_find_rcu(head, addr, vid);
+	if (likely(fdb)) {
+		/* attempt to update an entry for a local interface */
+		if (unlikely(fdb->is_local)) {
+			if (net_ratelimit())
+				br_warn(br, "received packet on %s with "
+					"own address as source address\n",
+					source->dev->name);
+		} else {
+			/* fastpath: update of existing entry */
+			fdb->dst = source;
+			fdb->updated = jiffies;
+		}
+	} else {
+		spin_lock(&br->hash_lock);
+		if (likely(!fdb_find(head, addr, vid))) {
+			fdb = fdb_create(head, source, addr, vid);
+			if (fdb)
+				fdb_notify(br, fdb, RTM_NEWNEIGH);
+		}
+		/* else  we lose race and someone else inserts
+		 * it first, don't bother updating
+		 */
+		spin_unlock(&br->hash_lock);
+	}
+}
+
+static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb)
+{
+	if (fdb->is_local)
+		return NUD_PERMANENT;
+	else if (fdb->is_static)
+		return NUD_NOARP;
+	else if (has_expired(fdb->dst->br, fdb))
+		return NUD_STALE;
+	else
+		return NUD_REACHABLE;
+}
+
+static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
+			 const struct net_bridge_fdb_entry *fdb,
+			 u32 portid, u32 seq, int type, unsigned int flags)
+{
+	unsigned long now = jiffies;
+	struct nda_cacheinfo ci;
+	struct nlmsghdr *nlh;
+	struct ndmsg *ndm;
+
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ndm = nlmsg_data(nlh);
+	ndm->ndm_family	 = AF_BRIDGE;
+	ndm->ndm_pad1    = 0;
+	ndm->ndm_pad2    = 0;
+	ndm->ndm_flags	 = 0;
+	ndm->ndm_type	 = 0;
+	ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
+	ndm->ndm_state   = fdb_to_nud(fdb);
+
+	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr))
+		goto nla_put_failure;
+	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_confirmed = 0;
+	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_refcnt	 = 0;
+	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
+		goto nla_put_failure;
+
+	if (nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id))
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static inline size_t fdb_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ndmsg))
+		+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
+		+ nla_total_size(sizeof(u16)) /* NDA_VLAN */
+		+ nla_total_size(sizeof(struct nda_cacheinfo));
+}
+
+static void fdb_notify(struct net_bridge *br,
+		       const struct net_bridge_fdb_entry *fdb, int type)
+{
+	struct net *net = dev_net(br->dev);
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in fdb_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+}
+
+/* Dump information about entries, in response to GETNEIGH */
+int br_fdb_dump(struct sk_buff *skb,
+		struct netlink_callback *cb,
+		struct net_device *dev,
+		int idx)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	int i;
+
+	if (!(dev->priv_flags & IFF_EBRIDGE))
+		goto out;
+
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		struct net_bridge_fdb_entry *f;
+
+		hlist_for_each_entry_rcu(f, &br->hash[i], hlist) {
+			if (idx < cb->args[0])
+				goto skip;
+
+			if (fdb_fill_info(skb, br, f,
+					  NETLINK_CB(cb->skb).portid,
+					  cb->nlh->nlmsg_seq,
+					  RTM_NEWNEIGH,
+					  NLM_F_MULTI) < 0)
+				break;
+skip:
+			++idx;
+		}
+	}
+
+out:
+	return idx;
+}
+
+/* Update (create or replace) forwarding database entry */
+static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
+			 __u16 state, __u16 flags, __u16 vid)
+{
+	struct net_bridge *br = source->br;
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+	struct net_bridge_fdb_entry *fdb;
+	bool modified = false;
+
+	fdb = fdb_find(head, addr, vid);
+	if (fdb == NULL) {
+		if (!(flags & NLM_F_CREATE))
+			return -ENOENT;
+
+		fdb = fdb_create(head, source, addr, vid);
+		if (!fdb)
+			return -ENOMEM;
+
+		modified = true;
+	} else {
+		if (flags & NLM_F_EXCL)
+			return -EEXIST;
+
+		if (fdb->dst != source) {
+			fdb->dst = source;
+			modified = true;
+		}
+	}
+
+	if (fdb_to_nud(fdb) != state) {
+		if (state & NUD_PERMANENT)
+			fdb->is_local = fdb->is_static = 1;
+		else if (state & NUD_NOARP) {
+			fdb->is_local = 0;
+			fdb->is_static = 1;
+		} else
+			fdb->is_local = fdb->is_static = 0;
+
+		modified = true;
+	}
+
+	fdb->used = jiffies;
+	if (modified) {
+		fdb->updated = jiffies;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
+	}
+
+	return 0;
+}
+
+static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
+	       const unsigned char *addr, u16 nlh_flags, u16 vid)
+{
+	int err = 0;
+
+	if (ndm->ndm_flags & NTF_USE) {
+		rcu_read_lock();
+		br_fdb_update(p->br, p, addr, vid);
+		rcu_read_unlock();
+	} else {
+		spin_lock_bh(&p->br->hash_lock);
+		err = fdb_add_entry(p, addr, ndm->ndm_state,
+				    nlh_flags, vid);
+		spin_unlock_bh(&p->br->hash_lock);
+	}
+
+	return err;
+}
+
+/* Add new permanent fdb entry with RTM_NEWNEIGH */
+int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+	       struct net_device *dev,
+	       const unsigned char *addr, u16 nlh_flags)
+{
+	struct net_bridge_port *p;
+	int err = 0;
+	struct net_port_vlans *pv;
+	unsigned short vid = VLAN_N_VID;
+
+	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
+		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
+		return -EINVAL;
+	}
+
+	if (tb[NDA_VLAN]) {
+		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
+			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
+			return -EINVAL;
+		}
+
+		vid = nla_get_u16(tb[NDA_VLAN]);
+
+		if (vid >= VLAN_N_VID) {
+			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
+				vid);
+			return -EINVAL;
+		}
+	}
+
+	p = br_port_get_rtnl(dev);
+	if (p == NULL) {
+		pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
+			dev->name);
+		return -EINVAL;
+	}
+
+	pv = nbp_get_vlan_info(p);
+	if (vid != VLAN_N_VID) {
+		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
+			pr_info("bridge: RTM_NEWNEIGH with unconfigured "
+				"vlan %d on port %s\n", vid, dev->name);
+			return -EINVAL;
+		}
+
+		/* VID was specified, so use it. */
+		err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+	} else {
+		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
+			err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+			goto out;
+		}
+
+		/* We have vlans configured on this port and user didn't
+		 * specify a VLAN.  To be nice, add/update entry for every
+		 * vlan on this port.
+		 */
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	return err;
+}
+
+int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr,
+		       u16 vlan)
+{
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
+	struct net_bridge_fdb_entry *fdb;
+
+	fdb = fdb_find(head, addr, vlan);
+	if (!fdb)
+		return -ENOENT;
+
+	fdb_delete(br, fdb);
+	return 0;
+}
+
+static int __br_fdb_delete(struct net_bridge_port *p,
+			   const unsigned char *addr, u16 vid)
+{
+	int err;
+
+	spin_lock_bh(&p->br->hash_lock);
+	err = fdb_delete_by_addr(p->br, addr, vid);
+	spin_unlock_bh(&p->br->hash_lock);
+
+	return err;
+}
+
+/* Remove neighbor entry with RTM_DELNEIGH */
+int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
+		  struct net_device *dev,
+		  const unsigned char *addr)
+{
+	struct net_bridge_port *p;
+	int err;
+	struct net_port_vlans *pv;
+	unsigned short vid = VLAN_N_VID;
+
+	if (tb[NDA_VLAN]) {
+		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
+			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
+			return -EINVAL;
+		}
+
+		vid = nla_get_u16(tb[NDA_VLAN]);
+
+		if (vid >= VLAN_N_VID) {
+			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
+				vid);
+			return -EINVAL;
+		}
+	}
+	p = br_port_get_rtnl(dev);
+	if (p == NULL) {
+		pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
+			dev->name);
+		return -EINVAL;
+	}
+
+	pv = nbp_get_vlan_info(p);
+	if (vid != VLAN_N_VID) {
+		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
+			pr_info("bridge: RTM_DELNEIGH with unconfigured "
+				"vlan %d on port %s\n", vid, dev->name);
+			return -EINVAL;
+		}
+
+		err = __br_fdb_delete(p, addr, vid);
+	} else {
+		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
+			err = __br_fdb_delete(p, addr, 0);
+			goto out;
+		}
+
+		/* We have vlans configured on this port and user didn't
+		 * specify a VLAN.  To be nice, add/update entry for every
+		 * vlan on this port.
+		 */
+		err = -ENOENT;
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			err &= __br_fdb_delete(p, addr, vid);
+		}
+	}
+out:
+	return err;
+}

net/bridge/br_forward.c

@@ -0,0 +1,281 @@
+/*
+ *	Forwarding decision
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/netpoll.h>
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#include <linux/netfilter_bridge.h>
+#include "br_private.h"
+
+static int deliver_clone(const struct net_bridge_port *prev,
+			 struct sk_buff *skb,
+			 void (*__packet_hook)(const struct net_bridge_port *p,
+					       struct sk_buff *skb));
+
+/* Don't forward packets to originating port or forwarding diasabled */
+static inline int should_deliver(const struct net_bridge_port *p,
+				 const struct sk_buff *skb)
+{
+	return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
+		br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) &&
+		p->state == BR_STATE_FORWARDING);
+}
+
+static inline unsigned int packet_length(const struct sk_buff *skb)
+{
+	return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0);
+}
+
+int br_dev_queue_push_xmit(struct sk_buff *skb)
+{
+	/* ip_fragment doesn't copy the MAC header */
+	if (nf_bridge_maybe_copy_header(skb) ||
+	    (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))) {
+		kfree_skb(skb);
+	} else {
+		skb_push(skb, ETH_HLEN);
+		br_drop_fake_rtable(skb);
+		dev_queue_xmit(skb);
+	}
+
+	return 0;
+}
+
+int br_forward_finish(struct sk_buff *skb)
+{
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
+		       br_dev_queue_push_xmit);
+
+}
+
+static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
+{
+	skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb);
+	if (!skb)
+		return;
+
+	skb->dev = to->dev;
+
+	if (unlikely(netpoll_tx_running(to->br->dev))) {
+		if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))
+			kfree_skb(skb);
+		else {
+			skb_push(skb, ETH_HLEN);
+			br_netpoll_send_skb(to, skb);
+		}
+		return;
+	}
+
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+		br_forward_finish);
+}
+
+static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
+{
+	struct net_device *indev;
+
+	if (skb_warn_if_lro(skb)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb);
+	if (!skb)
+		return;
+
+	indev = skb->dev;
+	skb->dev = to->dev;
+	skb_forward_csum(skb);
+
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
+		br_forward_finish);
+}
+
+/* called with rcu_read_lock */
+void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
+{
+	if (to && should_deliver(to, skb)) {
+		__br_deliver(to, skb);
+		return;
+	}
+
+	kfree_skb(skb);
+}
+
+/* called with rcu_read_lock */
+void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0)
+{
+	if (should_deliver(to, skb)) {
+		if (skb0)
+			deliver_clone(to, skb, __br_forward);
+		else
+			__br_forward(to, skb);
+		return;
+	}
+
+	if (!skb0)
+		kfree_skb(skb);
+}
+
+static int deliver_clone(const struct net_bridge_port *prev,
+			 struct sk_buff *skb,
+			 void (*__packet_hook)(const struct net_bridge_port *p,
+					       struct sk_buff *skb))
+{
+	struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
+
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		dev->stats.tx_dropped++;
+		return -ENOMEM;
+	}
+
+	__packet_hook(prev, skb);
+	return 0;
+}
+
+static struct net_bridge_port *maybe_deliver(
+	struct net_bridge_port *prev, struct net_bridge_port *p,
+	struct sk_buff *skb,
+	void (*__packet_hook)(const struct net_bridge_port *p,
+			      struct sk_buff *skb))
+{
+	int err;
+
+	if (!should_deliver(p, skb))
+		return prev;
+
+	if (!prev)
+		goto out;
+
+	err = deliver_clone(prev, skb, __packet_hook);
+	if (err)
+		return ERR_PTR(err);
+
+out:
+	return p;
+}
+
+/* called under bridge lock */
+static void br_flood(struct net_bridge *br, struct sk_buff *skb,
+		     struct sk_buff *skb0,
+		     void (*__packet_hook)(const struct net_bridge_port *p,
+					   struct sk_buff *skb))
+{
+	struct net_bridge_port *p;
+	struct net_bridge_port *prev;
+
+	prev = NULL;
+
+	list_for_each_entry_rcu(p, &br->port_list, list) {
+		prev = maybe_deliver(prev, p, skb, __packet_hook);
+		if (IS_ERR(prev))
+			goto out;
+	}
+
+	if (!prev)
+		goto out;
+
+	if (skb0)
+		deliver_clone(prev, skb, __packet_hook);
+	else
+		__packet_hook(prev, skb);
+	return;
+
+out:
+	if (!skb0)
+		kfree_skb(skb);
+}
+
+
+/* called with rcu_read_lock */
+void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb)
+{
+	br_flood(br, skb, NULL, __br_deliver);
+}
+
+/* called under bridge lock */
+void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
+		      struct sk_buff *skb2)
+{
+	br_flood(br, skb, skb2, __br_forward);
+}
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+/* called with rcu_read_lock */
+static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
+			       struct sk_buff *skb, struct sk_buff *skb0,
+			       void (*__packet_hook)(
+					const struct net_bridge_port *p,
+					struct sk_buff *skb))
+{
+	struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *prev = NULL;
+	struct net_bridge_port_group *p;
+	struct hlist_node *rp;
+
+	rp = rcu_dereference(hlist_first_rcu(&br->router_list));
+	p = mdst ? rcu_dereference(mdst->ports) : NULL;
+	while (p || rp) {
+		struct net_bridge_port *port, *lport, *rport;
+
+		lport = p ? p->port : NULL;
+		rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) :
+			     NULL;
+
+		port = (unsigned long)lport > (unsigned long)rport ?
+		       lport : rport;
+
+		prev = maybe_deliver(prev, port, skb, __packet_hook);
+		if (IS_ERR(prev))
+			goto out;
+
+		if ((unsigned long)lport >= (unsigned long)port)
+			p = rcu_dereference(p->next);
+		if ((unsigned long)rport >= (unsigned long)port)
+			rp = rcu_dereference(hlist_next_rcu(rp));
+	}
+
+	if (!prev)
+		goto out;
+
+	if (skb0)
+		deliver_clone(prev, skb, __packet_hook);
+	else
+		__packet_hook(prev, skb);
+	return;
+
+out:
+	if (!skb0)
+		kfree_skb(skb);
+}
+
+/* called with rcu_read_lock */
+void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
+			  struct sk_buff *skb)
+{
+	br_multicast_flood(mdst, skb, NULL, __br_deliver);
+}
+
+/* called with rcu_read_lock */
+void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
+			  struct sk_buff *skb, struct sk_buff *skb2)
+{
+	br_multicast_flood(mdst, skb, skb2, __br_forward);
+}
+#endif

net/bridge/br_if.c

@@ -0,0 +1,465 @@
+/*
+ *	Userspace interface
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/netpoll.h>
+#include <linux/ethtool.h>
+#include <linux/if_arp.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_ether.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <linux/if_vlan.h>
+
+#include "br_private.h"
+
+/*
+ * Determine initial path cost based on speed.
+ * using recommendations from 802.1d standard
+ *
+ * Since driver might sleep need to not be holding any locks.
+ */
+static int port_cost(struct net_device *dev)
+{
+	struct ethtool_cmd ecmd;
+
+	if (!__ethtool_get_settings(dev, &ecmd)) {
+		switch (ethtool_cmd_speed(&ecmd)) {
+		case SPEED_10000:
+			return 2;
+		case SPEED_1000:
+			return 4;
+		case SPEED_100:
+			return 19;
+		case SPEED_10:
+			return 100;
+		}
+	}
+
+	/* Old silly heuristics based on name */
+	if (!strncmp(dev->name, "lec", 3))
+		return 7;
+
+	if (!strncmp(dev->name, "plip", 4))
+		return 2500;
+
+	return 100;	/* assume old 10Mbps */
+}
+
+
+/* Check for port carrier transistions. */
+void br_port_carrier_check(struct net_bridge_port *p)
+{
+	struct net_device *dev = p->dev;
+	struct net_bridge *br = p->br;
+
+	if (!(p->flags & BR_ADMIN_COST) &&
+	    netif_running(dev) && netif_oper_up(dev))
+		p->path_cost = port_cost(dev);
+
+	if (!netif_running(br->dev))
+		return;
+
+	spin_lock_bh(&br->lock);
+	if (netif_running(dev) && netif_oper_up(dev)) {
+		if (p->state == BR_STATE_DISABLED)
+			br_stp_enable_port(p);
+	} else {
+		if (p->state != BR_STATE_DISABLED)
+			br_stp_disable_port(p);
+	}
+	spin_unlock_bh(&br->lock);
+}
+
+static void release_nbp(struct kobject *kobj)
+{
+	struct net_bridge_port *p
+		= container_of(kobj, struct net_bridge_port, kobj);
+	kfree(p);
+}
+
+static struct kobj_type brport_ktype = {
+#ifdef CONFIG_SYSFS
+	.sysfs_ops = &brport_sysfs_ops,
+#endif
+	.release = release_nbp,
+};
+
+static void destroy_nbp(struct net_bridge_port *p)
+{
+	struct net_device *dev = p->dev;
+
+	p->br = NULL;
+	p->dev = NULL;
+	dev_put(dev);
+
+	kobject_put(&p->kobj);
+}
+
+static void destroy_nbp_rcu(struct rcu_head *head)
+{
+	struct net_bridge_port *p =
+			container_of(head, struct net_bridge_port, rcu);
+	destroy_nbp(p);
+}
+
+/* Delete port(interface) from bridge is done in two steps.
+ * via RCU. First step, marks device as down. That deletes
+ * all the timers and stops new packets from flowing through.
+ *
+ * Final cleanup doesn't occur until after all CPU's finished
+ * processing packets.
+ *
+ * Protected from multiple admin operations by RTNL mutex
+ */
+static void del_nbp(struct net_bridge_port *p)
+{
+	struct net_bridge *br = p->br;
+	struct net_device *dev = p->dev;
+
+	sysfs_remove_link(br->ifobj, p->dev->name);
+
+	dev_set_promiscuity(dev, -1);
+
+	spin_lock_bh(&br->lock);
+	br_stp_disable_port(p);
+	spin_unlock_bh(&br->lock);
+
+	br_ifinfo_notify(RTM_DELLINK, p);
+
+	nbp_vlan_flush(p);
+	br_fdb_delete_by_port(br, p, 1);
+
+	list_del_rcu(&p->list);
+
+	dev->priv_flags &= ~IFF_BRIDGE_PORT;
+
+	netdev_rx_handler_unregister(dev);
+
+	netdev_upper_dev_unlink(dev, br->dev);
+
+	br_multicast_del_port(p);
+
+	kobject_uevent(&p->kobj, KOBJ_REMOVE);
+	kobject_del(&p->kobj);
+
+	br_netpoll_disable(p);
+
+	call_rcu(&p->rcu, destroy_nbp_rcu);
+}
+
+/* Delete bridge device */
+void br_dev_delete(struct net_device *dev, struct list_head *head)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p, *n;
+
+	list_for_each_entry_safe(p, n, &br->port_list, list) {
+		del_nbp(p);
+	}
+
+	del_timer_sync(&br->gc_timer);
+
+	br_sysfs_delbr(br->dev);
+	unregister_netdevice_queue(br->dev, head);
+}
+
+/* find an available port number */
+static int find_portno(struct net_bridge *br)
+{
+	int index;
+	struct net_bridge_port *p;
+	unsigned long *inuse;
+
+	inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long),
+			GFP_KERNEL);
+	if (!inuse)
+		return -ENOMEM;
+
+	set_bit(0, inuse);	/* zero is reserved */
+	list_for_each_entry(p, &br->port_list, list) {
+		set_bit(p->port_no, inuse);
+	}
+	index = find_first_zero_bit(inuse, BR_MAX_PORTS);
+	kfree(inuse);
+
+	return (index >= BR_MAX_PORTS) ? -EXFULL : index;
+}
+
+/* called with RTNL but without bridge lock */
+static struct net_bridge_port *new_nbp(struct net_bridge *br,
+				       struct net_device *dev)
+{
+	int index;
+	struct net_bridge_port *p;
+
+	index = find_portno(br);
+	if (index < 0)
+		return ERR_PTR(index);
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (p == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	p->br = br;
+	dev_hold(dev);
+	p->dev = dev;
+	p->path_cost = port_cost(dev);
+	p->priority = 0x8000 >> BR_PORT_BITS;
+	p->port_no = index;
+	p->flags = 0;
+	br_init_port(p);
+	p->state = BR_STATE_DISABLED;
+	br_stp_port_timer_init(p);
+	br_multicast_add_port(p);
+
+	return p;
+}
+
+int br_add_bridge(struct net *net, const char *name)
+{
+	struct net_device *dev;
+	int res;
+
+	dev = alloc_netdev(sizeof(struct net_bridge), name,
+			   br_dev_setup);
+
+	if (!dev)
+		return -ENOMEM;
+
+	dev_net_set(dev, net);
+	dev->rtnl_link_ops = &br_link_ops;
+
+	res = register_netdev(dev);
+	if (res)
+		free_netdev(dev);
+	return res;
+}
+
+int br_del_bridge(struct net *net, const char *name)
+{
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	dev = __dev_get_by_name(net, name);
+	if (dev == NULL)
+		ret =  -ENXIO; 	/* Could not find device */
+
+	else if (!(dev->priv_flags & IFF_EBRIDGE)) {
+		/* Attempt to delete non bridge device! */
+		ret = -EPERM;
+	}
+
+	else if (dev->flags & IFF_UP) {
+		/* Not shutdown yet. */
+		ret = -EBUSY;
+	}
+
+	else
+		br_dev_delete(dev, NULL);
+
+	rtnl_unlock();
+	return ret;
+}
+
+/* MTU of the bridge pseudo-device: ETH_DATA_LEN or the minimum of the ports */
+int br_min_mtu(const struct net_bridge *br)
+{
+	const struct net_bridge_port *p;
+	int mtu = 0;
+
+	ASSERT_RTNL();
+
+	if (list_empty(&br->port_list))
+		mtu = ETH_DATA_LEN;
+	else {
+		list_for_each_entry(p, &br->port_list, list) {
+			if (!mtu  || p->dev->mtu < mtu)
+				mtu = p->dev->mtu;
+		}
+	}
+	return mtu;
+}
+
+/*
+ * Recomputes features using slave's features
+ */
+netdev_features_t br_features_recompute(struct net_bridge *br,
+	netdev_features_t features)
+{
+	struct net_bridge_port *p;
+	netdev_features_t mask;
+
+	if (list_empty(&br->port_list))
+		return features;
+
+	mask = features;
+	features &= ~NETIF_F_ONE_FOR_ALL;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		features = netdev_increment_features(features,
+						     p->dev->features, mask);
+	}
+
+	return features;
+}
+
+/* called with RTNL */
+int br_add_if(struct net_bridge *br, struct net_device *dev)
+{
+	struct net_bridge_port *p;
+	int err = 0;
+	bool changed_addr;
+
+	/* Don't allow bridging non-ethernet like devices */
+	if ((dev->flags & IFF_LOOPBACK) ||
+	    dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||
+	    !is_valid_ether_addr(dev->dev_addr))
+		return -EINVAL;
+
+	/* No bridging of bridges */
+	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
+		return -ELOOP;
+
+	/* Device is already being bridged */
+	if (br_port_exists(dev))
+		return -EBUSY;
+
+	/* No bridging devices that dislike that (e.g. wireless) */
+	if (dev->priv_flags & IFF_DONT_BRIDGE)
+		return -EOPNOTSUPP;
+
+	p = new_nbp(br, dev);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	call_netdevice_notifiers(NETDEV_JOIN, dev);
+
+	err = dev_set_promiscuity(dev, 1);
+	if (err)
+		goto put_back;
+
+	err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),
+				   SYSFS_BRIDGE_PORT_ATTR);
+	if (err)
+		goto err1;
+
+	err = br_sysfs_addif(p);
+	if (err)
+		goto err2;
+
+	if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL))))
+		goto err3;
+
+	err = netdev_master_upper_dev_link(dev, br->dev);
+	if (err)
+		goto err4;
+
+	err = netdev_rx_handler_register(dev, br_handle_frame, p);
+	if (err)
+		goto err5;
+
+	dev->priv_flags |= IFF_BRIDGE_PORT;
+
+	dev_disable_lro(dev);
+
+	list_add_rcu(&p->list, &br->port_list);
+
+	netdev_update_features(br->dev);
+
+	spin_lock_bh(&br->lock);
+	changed_addr = br_stp_recalculate_bridge_id(br);
+
+	if (netif_running(dev) && netif_oper_up(dev) &&
+	    (br->dev->flags & IFF_UP))
+		br_stp_enable_port(p);
+	spin_unlock_bh(&br->lock);
+
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (changed_addr)
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
+
+	dev_set_mtu(br->dev, br_min_mtu(br));
+
+	if (br_fdb_insert(br, p, dev->dev_addr, 0))
+		netdev_err(dev, "failed insert local address bridge forwarding table\n");
+
+	kobject_uevent(&p->kobj, KOBJ_ADD);
+
+	return 0;
+
+err5:
+	netdev_upper_dev_unlink(dev, br->dev);
+err4:
+	br_netpoll_disable(p);
+err3:
+	sysfs_remove_link(br->ifobj, p->dev->name);
+err2:
+	kobject_put(&p->kobj);
+	p = NULL; /* kobject_put frees */
+err1:
+	dev_set_promiscuity(dev, -1);
+put_back:
+	dev_put(dev);
+	kfree(p);
+	return err;
+}
+
+/* called with RTNL */
+int br_del_if(struct net_bridge *br, struct net_device *dev)
+{
+	struct net_bridge_port *p;
+	bool changed_addr;
+
+	p = br_port_get_rtnl(dev);
+	if (!p || p->br != br)
+		return -EINVAL;
+
+	/* Since more than one interface can be attached to a bridge,
+	 * there still maybe an alternate path for netconsole to use;
+	 * therefore there is no reason for a NETDEV_RELEASE event.
+	 */
+	del_nbp(p);
+
+	spin_lock_bh(&br->lock);
+	changed_addr = br_stp_recalculate_bridge_id(br);
+	spin_unlock_bh(&br->lock);
+
+	if (changed_addr)
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
+
+	netdev_update_features(br->dev);
+
+	return 0;
+}
+
+void __net_exit br_net_exit(struct net *net)
+{
+	struct net_device *dev;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	for_each_netdev(net, dev)
+		if (dev->priv_flags & IFF_EBRIDGE)
+			br_dev_delete(dev, &list);
+
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+
+}

net/bridge/br_input.c

@@ -0,0 +1,237 @@
+/*
+ *	Handle incoming frames
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/export.h>
+#include <linux/rculist.h>
+#include "br_private.h"
+
+/* Hook for brouter */
+br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
+EXPORT_SYMBOL(br_should_route_hook);
+
+static int br_pass_frame_up(struct sk_buff *skb)
+{
+	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
+	struct net_bridge *br = netdev_priv(brdev);
+	struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+
+	u64_stats_update_begin(&brstats->syncp);
+	brstats->rx_packets++;
+	brstats->rx_bytes += skb->len;
+	u64_stats_update_end(&brstats->syncp);
+
+	/* Bridge is just like any other port.  Make sure the
+	 * packet is allowed except in promisc modue when someone
+	 * may be running packet capture.
+	 */
+	if (!(brdev->flags & IFF_PROMISC) &&
+	    !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
+	if (!skb)
+		return NET_RX_DROP;
+
+	indev = skb->dev;
+	skb->dev = brdev;
+
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
+		       netif_receive_skb);
+}
+
+/* note: already called with rcu_read_lock */
+int br_handle_frame_finish(struct sk_buff *skb)
+{
+	const unsigned char *dest = eth_hdr(skb)->h_dest;
+	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
+	struct net_bridge *br;
+	struct net_bridge_fdb_entry *dst;
+	struct net_bridge_mdb_entry *mdst;
+	struct sk_buff *skb2;
+	u16 vid = 0;
+
+	if (!p || p->state == BR_STATE_DISABLED)
+		goto drop;
+
+	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
+		goto drop;
+
+	/* insert into forwarding database after filtering to avoid spoofing */
+	br = p->br;
+	br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
+
+	if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
+	    br_multicast_rcv(br, p, skb))
+		goto drop;
+
+	if (p->state == BR_STATE_LEARNING)
+		goto drop;
+
+	BR_INPUT_SKB_CB(skb)->brdev = br->dev;
+
+	/* The packet skb2 goes to the local host (NULL to skip). */
+	skb2 = NULL;
+
+	if (br->dev->flags & IFF_PROMISC)
+		skb2 = skb;
+
+	dst = NULL;
+
+	if (is_broadcast_ether_addr(dest))
+		skb2 = skb;
+	else if (is_multicast_ether_addr(dest)) {
+		mdst = br_mdb_get(br, skb, vid);
+		if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) {
+			if ((mdst && mdst->mglist) ||
+			    br_multicast_is_router(br))
+				skb2 = skb;
+			br_multicast_forward(mdst, skb, skb2);
+			skb = NULL;
+			if (!skb2)
+				goto out;
+		} else
+			skb2 = skb;
+
+		br->dev->stats.multicast++;
+	} else if ((dst = __br_fdb_get(br, dest, vid)) &&
+			dst->is_local) {
+		skb2 = skb;
+		/* Do not forward the packet since it's local. */
+		skb = NULL;
+	}
+
+	if (skb) {
+		if (dst) {
+			dst->used = jiffies;
+			br_forward(dst->dst, skb, skb2);
+		} else
+			br_flood_forward(br, skb, skb2);
+	}
+
+	if (skb2)
+		return br_pass_frame_up(skb2);
+
+out:
+	return 0;
+drop:
+	kfree_skb(skb);
+	goto out;
+}
+
+/* note: already called with rcu_read_lock */
+static int br_handle_local_finish(struct sk_buff *skb)
+{
+	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
+	u16 vid = 0;
+
+	br_vlan_get_tag(skb, &vid);
+	br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
+	return 0;	 /* process further */
+}
+
+/*
+ * Return NULL if skb is handled
+ * note: already called with rcu_read_lock
+ */
+rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
+{
+	struct net_bridge_port *p;
+	struct sk_buff *skb = *pskb;
+	const unsigned char *dest = eth_hdr(skb)->h_dest;
+	br_should_route_hook_t *rhook;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
+		goto drop;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return RX_HANDLER_CONSUMED;
+
+	p = br_port_get_rcu(skb->dev);
+
+	if (unlikely(is_link_local_ether_addr(dest))) {
+		/*
+		 * See IEEE 802.1D Table 7-10 Reserved addresses
+		 *
+		 * Assignment		 		Value
+		 * Bridge Group Address		01-80-C2-00-00-00
+		 * (MAC Control) 802.3		01-80-C2-00-00-01
+		 * (Link Aggregation) 802.3	01-80-C2-00-00-02
+		 * 802.1X PAE address		01-80-C2-00-00-03
+		 *
+		 * 802.1AB LLDP 		01-80-C2-00-00-0E
+		 *
+		 * Others reserved for future standardization
+		 */
+		switch (dest[5]) {
+		case 0x00:	/* Bridge Group Address */
+			/* If STP is turned off,
+			   then must forward to keep loop detection */
+			if (p->br->stp_enabled == BR_NO_STP)
+				goto forward;
+			break;
+
+		case 0x01:	/* IEEE MAC (Pause) */
+			goto drop;
+
+		default:
+			/* Allow selective forwarding for most other protocols */
+			if (p->br->group_fwd_mask & (1u << dest[5]))
+				goto forward;
+		}
+
+		/* Deliver packet to local host only */
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
+			    NULL, br_handle_local_finish)) {
+			return RX_HANDLER_CONSUMED; /* consumed by filter */
+		} else {
+			*pskb = skb;
+			return RX_HANDLER_PASS;	/* continue processing */
+		}
+	}
+
+forward:
+	switch (p->state) {
+	case BR_STATE_FORWARDING:
+		rhook = rcu_dereference(br_should_route_hook);
+		if (rhook) {
+			if ((*rhook)(skb)) {
+				*pskb = skb;
+				return RX_HANDLER_PASS;
+			}
+			dest = eth_hdr(skb)->h_dest;
+		}
+		/* fall through */
+	case BR_STATE_LEARNING:
+		if (ether_addr_equal(p->br->dev->dev_addr, dest))
+			skb->pkt_type = PACKET_HOST;
+
+		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+			br_handle_frame_finish);
+		break;
+	default:
+drop:
+		kfree_skb(skb);
+	}
+	return RX_HANDLER_CONSUMED;
+}

net/bridge/br_ioctl.c

@@ -0,0 +1,396 @@
+/*
+ *	Ioctl handler
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/capability.h>
+#include <linux/kernel.h>
+#include <linux/if_bridge.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/times.h>
+#include <net/net_namespace.h>
+#include <asm/uaccess.h>
+#include "br_private.h"
+
+/* called with RTNL */
+static int get_bridge_ifindices(struct net *net, int *indices, int num)
+{
+	struct net_device *dev;
+	int i = 0;
+
+	for_each_netdev(net, dev) {
+		if (i >= num)
+			break;
+		if (dev->priv_flags & IFF_EBRIDGE)
+			indices[i++] = dev->ifindex;
+	}
+
+	return i;
+}
+
+/* called with RTNL */
+static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num)
+{
+	struct net_bridge_port *p;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->port_no < num)
+			ifindices[p->port_no] = p->dev->ifindex;
+	}
+}
+
+/*
+ * Format up to a page worth of forwarding table entries
+ * userbuf -- where to copy result
+ * maxnum  -- maximum number of entries desired
+ *            (limited to a page for sanity)
+ * offset  -- number of records to skip
+ */
+static int get_fdb_entries(struct net_bridge *br, void __user *userbuf,
+			   unsigned long maxnum, unsigned long offset)
+{
+	int num;
+	void *buf;
+	size_t size;
+
+	/* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */
+	if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry))
+		maxnum = PAGE_SIZE/sizeof(struct __fdb_entry);
+
+	size = maxnum * sizeof(struct __fdb_entry);
+
+	buf = kmalloc(size, GFP_USER);
+	if (!buf)
+		return -ENOMEM;
+
+	num = br_fdb_fillbuf(br, buf, maxnum, offset);
+	if (num > 0) {
+		if (copy_to_user(userbuf, buf, num*sizeof(struct __fdb_entry)))
+			num = -EFAULT;
+	}
+	kfree(buf);
+
+	return num;
+}
+
+/* called with RTNL */
+static int add_del_if(struct net_bridge *br, int ifindex, int isadd)
+{
+	struct net *net = dev_net(br->dev);
+	struct net_device *dev;
+	int ret;
+
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	dev = __dev_get_by_index(net, ifindex);
+	if (dev == NULL)
+		return -EINVAL;
+
+	if (isadd)
+		ret = br_add_if(br, dev);
+	else
+		ret = br_del_if(br, dev);
+
+	return ret;
+}
+
+/*
+ * Legacy ioctl's through SIOCDEVPRIVATE
+ * This interface is deprecated because it was too difficult to
+ * to do the translation for 32/64bit ioctl compatibility.
+ */
+static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	unsigned long args[4];
+
+	if (copy_from_user(args, rq->ifr_data, sizeof(args)))
+		return -EFAULT;
+
+	switch (args[0]) {
+	case BRCTL_ADD_IF:
+	case BRCTL_DEL_IF:
+		return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF);
+
+	case BRCTL_GET_BRIDGE_INFO:
+	{
+		struct __bridge_info b;
+
+		memset(&b, 0, sizeof(struct __bridge_info));
+		rcu_read_lock();
+		memcpy(&b.designated_root, &br->designated_root, 8);
+		memcpy(&b.bridge_id, &br->bridge_id, 8);
+		b.root_path_cost = br->root_path_cost;
+		b.max_age = jiffies_to_clock_t(br->max_age);
+		b.hello_time = jiffies_to_clock_t(br->hello_time);
+		b.forward_delay = br->forward_delay;
+		b.bridge_max_age = br->bridge_max_age;
+		b.bridge_hello_time = br->bridge_hello_time;
+		b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay);
+		b.topology_change = br->topology_change;
+		b.topology_change_detected = br->topology_change_detected;
+		b.root_port = br->root_port;
+
+		b.stp_enabled = (br->stp_enabled != BR_NO_STP);
+		b.ageing_time = jiffies_to_clock_t(br->ageing_time);
+		b.hello_timer_value = br_timer_value(&br->hello_timer);
+		b.tcn_timer_value = br_timer_value(&br->tcn_timer);
+		b.topology_change_timer_value = br_timer_value(&br->topology_change_timer);
+		b.gc_timer_value = br_timer_value(&br->gc_timer);
+		rcu_read_unlock();
+
+		if (copy_to_user((void __user *)args[1], &b, sizeof(b)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	case BRCTL_GET_PORT_LIST:
+	{
+		int num, *indices;
+
+		num = args[2];
+		if (num < 0)
+			return -EINVAL;
+		if (num == 0)
+			num = 256;
+		if (num > BR_MAX_PORTS)
+			num = BR_MAX_PORTS;
+
+		indices = kcalloc(num, sizeof(int), GFP_KERNEL);
+		if (indices == NULL)
+			return -ENOMEM;
+
+		get_port_ifindices(br, indices, num);
+		if (copy_to_user((void __user *)args[1], indices, num*sizeof(int)))
+			num =  -EFAULT;
+		kfree(indices);
+		return num;
+	}
+
+	case BRCTL_SET_BRIDGE_FORWARD_DELAY:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		return br_set_forward_delay(br, args[1]);
+
+	case BRCTL_SET_BRIDGE_HELLO_TIME:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		return br_set_hello_time(br, args[1]);
+
+	case BRCTL_SET_BRIDGE_MAX_AGE:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		return br_set_max_age(br, args[1]);
+
+	case BRCTL_SET_AGEING_TIME:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		br->ageing_time = clock_t_to_jiffies(args[1]);
+		return 0;
+
+	case BRCTL_GET_PORT_INFO:
+	{
+		struct __port_info p;
+		struct net_bridge_port *pt;
+
+		rcu_read_lock();
+		if ((pt = br_get_port(br, args[2])) == NULL) {
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+
+		memset(&p, 0, sizeof(struct __port_info));
+		memcpy(&p.designated_root, &pt->designated_root, 8);
+		memcpy(&p.designated_bridge, &pt->designated_bridge, 8);
+		p.port_id = pt->port_id;
+		p.designated_port = pt->designated_port;
+		p.path_cost = pt->path_cost;
+		p.designated_cost = pt->designated_cost;
+		p.state = pt->state;
+		p.top_change_ack = pt->topology_change_ack;
+		p.config_pending = pt->config_pending;
+		p.message_age_timer_value = br_timer_value(&pt->message_age_timer);
+		p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer);
+		p.hold_timer_value = br_timer_value(&pt->hold_timer);
+
+		rcu_read_unlock();
+
+		if (copy_to_user((void __user *)args[1], &p, sizeof(p)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	case BRCTL_SET_BRIDGE_STP_STATE:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		br_stp_set_enabled(br, args[1]);
+		return 0;
+
+	case BRCTL_SET_BRIDGE_PRIORITY:
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		spin_lock_bh(&br->lock);
+		br_stp_set_bridge_priority(br, args[1]);
+		spin_unlock_bh(&br->lock);
+		return 0;
+
+	case BRCTL_SET_PORT_PRIORITY:
+	{
+		struct net_bridge_port *p;
+		int ret;
+
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		spin_lock_bh(&br->lock);
+		if ((p = br_get_port(br, args[1])) == NULL)
+			ret = -EINVAL;
+		else
+			ret = br_stp_set_port_priority(p, args[2]);
+		spin_unlock_bh(&br->lock);
+		return ret;
+	}
+
+	case BRCTL_SET_PATH_COST:
+	{
+		struct net_bridge_port *p;
+		int ret;
+
+		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		spin_lock_bh(&br->lock);
+		if ((p = br_get_port(br, args[1])) == NULL)
+			ret = -EINVAL;
+		else
+			ret = br_stp_set_path_cost(p, args[2]);
+		spin_unlock_bh(&br->lock);
+
+		return ret;
+	}
+
+	case BRCTL_GET_FDB_ENTRIES:
+		return get_fdb_entries(br, (void __user *)args[1],
+				       args[2], args[3]);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int old_deviceless(struct net *net, void __user *uarg)
+{
+	unsigned long args[3];
+
+	if (copy_from_user(args, uarg, sizeof(args)))
+		return -EFAULT;
+
+	switch (args[0]) {
+	case BRCTL_GET_VERSION:
+		return BRCTL_VERSION;
+
+	case BRCTL_GET_BRIDGES:
+	{
+		int *indices;
+		int ret = 0;
+
+		if (args[2] >= 2048)
+			return -ENOMEM;
+		indices = kcalloc(args[2], sizeof(int), GFP_KERNEL);
+		if (indices == NULL)
+			return -ENOMEM;
+
+		args[2] = get_bridge_ifindices(net, indices, args[2]);
+
+		ret = copy_to_user((void __user *)args[1], indices, args[2]*sizeof(int))
+			? -EFAULT : args[2];
+
+		kfree(indices);
+		return ret;
+	}
+
+	case BRCTL_ADD_BRIDGE:
+	case BRCTL_DEL_BRIDGE:
+	{
+		char buf[IFNAMSIZ];
+
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(buf, (void __user *)args[1], IFNAMSIZ))
+			return -EFAULT;
+
+		buf[IFNAMSIZ-1] = 0;
+
+		if (args[0] == BRCTL_ADD_BRIDGE)
+			return br_add_bridge(net, buf);
+
+		return br_del_bridge(net, buf);
+	}
+	}
+
+	return -EOPNOTSUPP;
+}
+
+int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uarg)
+{
+	switch (cmd) {
+	case SIOCGIFBR:
+	case SIOCSIFBR:
+		return old_deviceless(net, uarg);
+
+	case SIOCBRADDBR:
+	case SIOCBRDELBR:
+	{
+		char buf[IFNAMSIZ];
+
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(buf, uarg, IFNAMSIZ))
+			return -EFAULT;
+
+		buf[IFNAMSIZ-1] = 0;
+		if (cmd == SIOCBRADDBR)
+			return br_add_bridge(net, buf);
+
+		return br_del_bridge(net, buf);
+	}
+	}
+	return -EOPNOTSUPP;
+}
+
+int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	switch(cmd) {
+	case SIOCDEVPRIVATE:
+		return old_dev_ioctl(dev, rq, cmd);
+
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
+		return add_del_if(br, rq->ifr_ifindex, cmd == SIOCBRADDIF);
+
+	}
+
+	br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd);
+	return -EOPNOTSUPP;
+}

net/bridge/br_mdb.c

@@ -0,0 +1,492 @@
+#include <linux/err.h>
+#include <linux/igmp.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+#include <net/ip.h>
+#include <net/netlink.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#endif
+
+#include "br_private.h"
+
+static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
+			       struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p;
+	struct nlattr *nest;
+
+	if (!br->multicast_router || hlist_empty(&br->router_list))
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_ROUTER);
+	if (nest == NULL)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry_rcu(p, &br->router_list, rlist) {
+		if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex))
+			goto fail;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+fail:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_mdb_htable *mdb;
+	struct nlattr *nest, *nest2;
+	int i, err = 0;
+	int idx = 0, s_idx = cb->args[1];
+
+	if (br->multicast_disabled)
+		return 0;
+
+	mdb = rcu_dereference(br->mdb);
+	if (!mdb)
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_MDB);
+	if (nest == NULL)
+		return -EMSGSIZE;
+
+	for (i = 0; i < mdb->max; i++) {
+		struct net_bridge_mdb_entry *mp;
+		struct net_bridge_port_group *p, **pp;
+		struct net_bridge_port *port;
+
+		hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) {
+			if (idx < s_idx)
+				goto skip;
+
+			nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+			if (nest2 == NULL) {
+				err = -EMSGSIZE;
+				goto out;
+			}
+
+			for (pp = &mp->ports;
+			     (p = rcu_dereference(*pp)) != NULL;
+			      pp = &p->next) {
+				port = p->port;
+				if (port) {
+					struct br_mdb_entry e;
+					memset(&e, 0, sizeof(e));
+					e.ifindex = port->dev->ifindex;
+					e.state = p->state;
+					if (p->addr.proto == htons(ETH_P_IP))
+						e.addr.u.ip4 = p->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+					if (p->addr.proto == htons(ETH_P_IPV6))
+						e.addr.u.ip6 = p->addr.u.ip6;
+#endif
+					e.addr.proto = p->addr.proto;
+					if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) {
+						nla_nest_cancel(skb, nest2);
+						err = -EMSGSIZE;
+						goto out;
+					}
+				}
+			}
+			nla_nest_end(skb, nest2);
+		skip:
+			idx++;
+		}
+	}
+
+out:
+	cb->args[1] = idx;
+	nla_nest_end(skb, nest);
+	return err;
+}
+
+static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net_device *dev;
+	struct net *net = sock_net(skb->sk);
+	struct nlmsghdr *nlh = NULL;
+	int idx = 0, s_idx;
+
+	s_idx = cb->args[0];
+
+	rcu_read_lock();
+
+	/* In theory this could be wrapped to 0... */
+	cb->seq = net->dev_base_seq + br_mdb_rehash_seq;
+
+	for_each_netdev_rcu(net, dev) {
+		if (dev->priv_flags & IFF_EBRIDGE) {
+			struct br_port_msg *bpm;
+
+			if (idx < s_idx)
+				goto skip;
+
+			nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+					cb->nlh->nlmsg_seq, RTM_GETMDB,
+					sizeof(*bpm), NLM_F_MULTI);
+			if (nlh == NULL)
+				break;
+
+			bpm = nlmsg_data(nlh);
+			memset(bpm, 0, sizeof(*bpm));
+			bpm->ifindex = dev->ifindex;
+			if (br_mdb_fill_info(skb, cb, dev) < 0)
+				goto out;
+			if (br_rports_fill_info(skb, cb, dev) < 0)
+				goto out;
+
+			cb->args[1] = 0;
+			nlmsg_end(skb, nlh);
+		skip:
+			idx++;
+		}
+	}
+
+out:
+	if (nlh)
+		nlmsg_end(skb, nlh);
+	rcu_read_unlock();
+	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
+				   struct net_device *dev,
+				   struct br_mdb_entry *entry, u32 pid,
+				   u32 seq, int type, unsigned int flags)
+{
+	struct nlmsghdr *nlh;
+	struct br_port_msg *bpm;
+	struct nlattr *nest, *nest2;
+
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	bpm = nlmsg_data(nlh);
+	memset(bpm, 0, sizeof(*bpm));
+	bpm->family  = AF_BRIDGE;
+	bpm->ifindex = dev->ifindex;
+	nest = nla_nest_start(skb, MDBA_MDB);
+	if (nest == NULL)
+		goto cancel;
+	nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+	if (nest2 == NULL)
+		goto end;
+
+	if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry))
+		goto end;
+
+	nla_nest_end(skb, nest2);
+	nla_nest_end(skb, nest);
+	return nlmsg_end(skb, nlh);
+
+end:
+	nla_nest_end(skb, nest);
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static inline size_t rtnl_mdb_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct br_port_msg))
+		+ nla_total_size(sizeof(struct br_mdb_entry));
+}
+
+static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
+			    int type)
+{
+	struct net *net = dev_net(dev);
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
+	if (!skb)
+		goto errout;
+
+	err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
+	return;
+errout:
+	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
+}
+
+void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
+		   struct br_ip *group, int type)
+{
+	struct br_mdb_entry entry;
+
+	memset(&entry, 0, sizeof(entry));
+	entry.ifindex = port->dev->ifindex;
+	entry.addr.proto = group->proto;
+	entry.addr.u.ip4 = group->u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	entry.addr.u.ip6 = group->u.ip6;
+#endif
+	__br_mdb_notify(dev, &entry, type);
+}
+
+static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
+{
+	if (entry->ifindex == 0)
+		return false;
+
+	if (entry->addr.proto == htons(ETH_P_IP)) {
+		if (!ipv4_is_multicast(entry->addr.u.ip4))
+			return false;
+		if (ipv4_is_local_multicast(entry->addr.u.ip4))
+			return false;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
+		if (!ipv6_is_transient_multicast(&entry->addr.u.ip6))
+			return false;
+#endif
+	} else
+		return false;
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
+		return false;
+
+	return true;
+}
+
+static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct net_device **pdev, struct br_mdb_entry **pentry)
+{
+	struct net *net = sock_net(skb->sk);
+	struct br_mdb_entry *entry;
+	struct br_port_msg *bpm;
+	struct nlattr *tb[MDBA_SET_ENTRY_MAX+1];
+	struct net_device *dev;
+	int err;
+
+	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL);
+	if (err < 0)
+		return err;
+
+	bpm = nlmsg_data(nlh);
+	if (bpm->ifindex == 0) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
+		return -EINVAL;
+	}
+
+	dev = __dev_get_by_index(net, bpm->ifindex);
+	if (dev == NULL) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	if (!(dev->priv_flags & IFF_EBRIDGE)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
+		return -EOPNOTSUPP;
+	}
+
+	*pdev = dev;
+
+	if (!tb[MDBA_SET_ENTRY] ||
+	    nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
+		return -EINVAL;
+	}
+
+	entry = nla_data(tb[MDBA_SET_ENTRY]);
+	if (!is_valid_mdb_entry(entry)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
+		return -EINVAL;
+	}
+
+	*pentry = entry;
+	return 0;
+}
+
+static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
+			    struct br_ip *group, unsigned char state)
+{
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_mdb_htable *mdb;
+	int err;
+
+	mdb = mlock_dereference(br->mdb, br);
+	mp = br_mdb_ip_get(mdb, group);
+	if (!mp) {
+		mp = br_multicast_new_group(br, port, group);
+		err = PTR_ERR(mp);
+		if (IS_ERR(mp))
+			return err;
+	}
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (p->port == port)
+			return -EEXIST;
+		if ((unsigned long)p->port < (unsigned long)port)
+			break;
+	}
+
+	p = br_multicast_new_port_group(port, group, *pp, state);
+	if (unlikely(!p))
+		return -ENOMEM;
+	rcu_assign_pointer(*pp, p);
+
+	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
+	return 0;
+}
+
+static int __br_mdb_add(struct net *net, struct net_bridge *br,
+			struct br_mdb_entry *entry)
+{
+	struct br_ip ip;
+	struct net_device *dev;
+	struct net_bridge_port *p;
+	int ret;
+
+	if (!netif_running(br->dev) || br->multicast_disabled)
+		return -EINVAL;
+
+	dev = __dev_get_by_index(net, entry->ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	p = br_port_get_rtnl(dev);
+	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
+		return -EINVAL;
+
+	ip.proto = entry->addr.proto;
+	if (ip.proto == htons(ETH_P_IP))
+		ip.u.ip4 = entry->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		ip.u.ip6 = entry->addr.u.ip6;
+#endif
+
+	spin_lock_bh(&br->multicast_lock);
+	ret = br_mdb_add_group(br, p, &ip, entry->state);
+	spin_unlock_bh(&br->multicast_lock);
+	return ret;
+}
+
+static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct br_mdb_entry *entry;
+	struct net_device *dev;
+	struct net_bridge *br;
+	int err;
+
+	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	if (err < 0)
+		return err;
+
+	br = netdev_priv(dev);
+
+	err = __br_mdb_add(net, br, entry);
+	if (!err)
+		__br_mdb_notify(dev, entry, RTM_NEWMDB);
+	return err;
+}
+
+static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
+{
+	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_port_group __rcu **pp;
+	struct br_ip ip;
+	int err = -EINVAL;
+
+	if (!netif_running(br->dev) || br->multicast_disabled)
+		return -EINVAL;
+
+	if (timer_pending(&br->multicast_querier_timer))
+		return -EBUSY;
+
+	ip.proto = entry->addr.proto;
+	if (ip.proto == htons(ETH_P_IP))
+		ip.u.ip4 = entry->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		ip.u.ip6 = entry->addr.u.ip6;
+#endif
+
+	spin_lock_bh(&br->multicast_lock);
+	mdb = mlock_dereference(br->mdb, br);
+
+	mp = br_mdb_ip_get(mdb, &ip);
+	if (!mp)
+		goto unlock;
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (!p->port || p->port->dev->ifindex != entry->ifindex)
+			continue;
+
+		if (p->port->state == BR_STATE_DISABLED)
+			goto unlock;
+
+		rcu_assign_pointer(*pp, p->next);
+		hlist_del_init(&p->mglist);
+		del_timer(&p->timer);
+		call_rcu_bh(&p->rcu, br_multicast_free_pg);
+		err = 0;
+
+		if (!mp->ports && !mp->mglist &&
+		    netif_running(br->dev))
+			mod_timer(&mp->timer, jiffies);
+		break;
+	}
+
+unlock:
+	spin_unlock_bh(&br->multicast_lock);
+	return err;
+}
+
+static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net_device *dev;
+	struct br_mdb_entry *entry;
+	struct net_bridge *br;
+	int err;
+
+	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	if (err < 0)
+		return err;
+
+	br = netdev_priv(dev);
+
+	err = __br_mdb_del(br, entry);
+	if (!err)
+		__br_mdb_notify(dev, entry, RTM_DELMDB);
+	return err;
+}
+
+void br_mdb_init(void)
+{
+	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
+	rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL);
+	rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL);
+}
+
+void br_mdb_uninit(void)
+{
+	rtnl_unregister(PF_BRIDGE, RTM_GETMDB);
+	rtnl_unregister(PF_BRIDGE, RTM_NEWMDB);
+	rtnl_unregister(PF_BRIDGE, RTM_DELMDB);
+}

net/bridge/br_netlink.c

@@ -0,0 +1,499 @@
+/*
+ *	Bridge netlink control interface
+ *
+ *	Authors:
+ *	Stephen Hemminger		<shemminger@osdl.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/etherdevice.h>
+#include <net/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <uapi/linux/if_bridge.h>
+
+#include "br_private.h"
+#include "br_private_stp.h"
+
+static inline size_t br_port_info_size(void)
+{
+	return nla_total_size(1)	/* IFLA_BRPORT_STATE  */
+		+ nla_total_size(2)	/* IFLA_BRPORT_PRIORITY */
+		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
+		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
+		+ nla_total_size(1)	/* IFLA_BRPORT_GUARD */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROTECT */
+		+ nla_total_size(1)	/* IFLA_BRPORT_FAST_LEAVE */
+		+ 0;
+}
+
+static inline size_t br_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+		+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+		+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+		+ nla_total_size(4) /* IFLA_MASTER */
+		+ nla_total_size(4) /* IFLA_MTU */
+		+ nla_total_size(4) /* IFLA_LINK */
+		+ nla_total_size(1) /* IFLA_OPERSTATE */
+		+ nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */
+}
+
+static int br_port_fill_attrs(struct sk_buff *skb,
+			      const struct net_bridge_port *p)
+{
+	u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
+
+	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
+	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
+	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
+	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
+	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+/*
+ * Create one netlink message for one interface
+ * Contains port and master info as well as carrier and bridge state.
+ */
+static int br_fill_ifinfo(struct sk_buff *skb,
+			  const struct net_bridge_port *port,
+			  u32 pid, u32 seq, int event, unsigned int flags,
+			  u32 filter_mask, const struct net_device *dev)
+{
+	const struct net_bridge *br;
+	struct ifinfomsg *hdr;
+	struct nlmsghdr *nlh;
+	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+
+	if (port)
+		br = port->br;
+	else
+		br = netdev_priv(dev);
+
+	br_debug(br, "br_fill_info event %d port %s master %s\n",
+		     event, dev->name, br->dev->name);
+
+	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	hdr = nlmsg_data(nlh);
+	hdr->ifi_family = AF_BRIDGE;
+	hdr->__ifi_pad = 0;
+	hdr->ifi_type = dev->type;
+	hdr->ifi_index = dev->ifindex;
+	hdr->ifi_flags = dev_get_flags(dev);
+	hdr->ifi_change = 0;
+
+	if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
+	    nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) ||
+	    nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
+	    nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
+	    (dev->addr_len &&
+	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
+	    (dev->ifindex != dev->iflink &&
+	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+		goto nla_put_failure;
+
+	if (event == RTM_NEWLINK && port) {
+		struct nlattr *nest
+			= nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+
+		if (nest == NULL || br_port_fill_attrs(skb, port) < 0)
+			goto nla_put_failure;
+		nla_nest_end(skb, nest);
+	}
+
+	/* Check if  the VID information is requested */
+	if (filter_mask & RTEXT_FILTER_BRVLAN) {
+		struct nlattr *af;
+		const struct net_port_vlans *pv;
+		struct bridge_vlan_info vinfo;
+		u16 vid;
+		u16 pvid;
+
+		if (port)
+			pv = nbp_get_vlan_info(port);
+		else
+			pv = br_get_vlan_info(br);
+
+		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID))
+			goto done;
+
+		af = nla_nest_start(skb, IFLA_AF_SPEC);
+		if (!af)
+			goto nla_put_failure;
+
+		pvid = br_get_pvid(pv);
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			vinfo.vid = vid;
+			vinfo.flags = 0;
+			if (vid == pvid)
+				vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
+
+			if (test_bit(vid, pv->untagged_bitmap))
+				vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+
+			if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
+				    sizeof(vinfo), &vinfo))
+				goto nla_put_failure;
+		}
+
+		nla_nest_end(skb, af);
+	}
+
+done:
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+/*
+ * Notify listeners of a change in port information
+ */
+void br_ifinfo_notify(int event, struct net_bridge_port *port)
+{
+	struct net *net;
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	if (!port)
+		return;
+
+	net = dev_net(port->dev);
+	br_debug(port->br, "port %u(%s) event %d\n",
+		 (unsigned int)port->port_no, port->dev->name, event);
+
+	skb = nlmsg_new(br_nlmsg_size(), GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in br_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+}
+
+
+/*
+ * Dump information about all ports, in response to GETLINK
+ */
+int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+	       struct net_device *dev, u32 filter_mask)
+{
+	int err = 0;
+	struct net_bridge_port *port = br_port_get_rtnl(dev);
+
+	/* not a bridge port and  */
+	if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN))
+		goto out;
+
+	err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI,
+			     filter_mask, dev);
+out:
+	return err;
+}
+
+static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = {
+	[IFLA_BRIDGE_FLAGS]	= { .type = NLA_U16 },
+	[IFLA_BRIDGE_MODE]	= { .type = NLA_U16 },
+	[IFLA_BRIDGE_VLAN_INFO]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct bridge_vlan_info), },
+};
+
+static int br_afspec(struct net_bridge *br,
+		     struct net_bridge_port *p,
+		     struct nlattr *af_spec,
+		     int cmd)
+{
+	struct nlattr *tb[IFLA_BRIDGE_MAX+1];
+	int err = 0;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy);
+	if (err)
+		return err;
+
+	if (tb[IFLA_BRIDGE_VLAN_INFO]) {
+		struct bridge_vlan_info *vinfo;
+
+		vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]);
+
+		if (vinfo->vid >= VLAN_N_VID)
+			return -EINVAL;
+
+		switch (cmd) {
+		case RTM_SETLINK:
+			if (p) {
+				err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
+				if (err)
+					break;
+
+				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+					err = br_vlan_add(p->br, vinfo->vid,
+							  vinfo->flags);
+			} else
+				err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+
+			if (err)
+				break;
+
+			break;
+
+		case RTM_DELLINK:
+			if (p) {
+				nbp_vlan_delete(p, vinfo->vid);
+				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+					br_vlan_delete(p->br, vinfo->vid);
+			} else
+				br_vlan_delete(br, vinfo->vid);
+			break;
+		}
+	}
+
+	return err;
+}
+
+static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
+	[IFLA_BRPORT_STATE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_COST]	= { .type = NLA_U32 },
+	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
+	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROTECT]	= { .type = NLA_U8 },
+};
+
+/* Change the state of the port and notify spanning tree */
+static int br_set_port_state(struct net_bridge_port *p, u8 state)
+{
+	if (state > BR_STATE_BLOCKING)
+		return -EINVAL;
+
+	/* if kernel STP is running, don't allow changes */
+	if (p->br->stp_enabled == BR_KERNEL_STP)
+		return -EBUSY;
+
+	/* if device is not up, change is not allowed
+	 * if link is not present, only allowable state is disabled
+	 */
+	if (!netif_running(p->dev) ||
+	    (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED))
+		return -ENETDOWN;
+
+	p->state = state;
+	br_log_state(p);
+	br_port_state_selection(p->br);
+	return 0;
+}
+
+/* Set/clear or port flags based on attribute */
+static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
+			   int attrtype, unsigned long mask)
+{
+	if (tb[attrtype]) {
+		u8 flag = nla_get_u8(tb[attrtype]);
+		if (flag)
+			p->flags |= mask;
+		else
+			p->flags &= ~mask;
+	}
+}
+
+/* Process bridge protocol info on port */
+static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
+{
+	int err;
+
+	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
+	br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE);
+	br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
+
+	if (tb[IFLA_BRPORT_COST]) {
+		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_PRIORITY]) {
+		err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_STATE]) {
+		err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE]));
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/* Change state and parameters on port. */
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
+{
+	struct nlattr *protinfo;
+	struct nlattr *afspec;
+	struct net_bridge_port *p;
+	struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+	int err = 0;
+
+	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
+	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!protinfo && !afspec)
+		return 0;
+
+	p = br_port_get_rtnl(dev);
+	/* We want to accept dev as bridge itself if the AF_SPEC
+	 * is set to see if someone is setting vlan info on the brigde
+	 */
+	if (!p && !afspec)
+		return -EINVAL;
+
+	if (p && protinfo) {
+		if (protinfo->nla_type & NLA_F_NESTED) {
+			err = nla_parse_nested(tb, IFLA_BRPORT_MAX,
+					       protinfo, ifla_brport_policy);
+			if (err)
+				return err;
+
+			spin_lock_bh(&p->br->lock);
+			err = br_setport(p, tb);
+			spin_unlock_bh(&p->br->lock);
+		} else {
+			/* Binary compatability with old RSTP */
+			if (nla_len(protinfo) < sizeof(u8))
+				return -EINVAL;
+
+			spin_lock_bh(&p->br->lock);
+			err = br_set_port_state(p, nla_get_u8(protinfo));
+			spin_unlock_bh(&p->br->lock);
+		}
+		if (err)
+			goto out;
+	}
+
+	if (afspec) {
+		err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
+				afspec, RTM_SETLINK);
+	}
+
+	if (err == 0)
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+out:
+	return err;
+}
+
+/* Delete port information */
+int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
+{
+	struct nlattr *afspec;
+	struct net_bridge_port *p;
+	int err;
+
+	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!afspec)
+		return 0;
+
+	p = br_port_get_rtnl(dev);
+	/* We want to accept dev as bridge itself as well */
+	if (!p && !(dev->priv_flags & IFF_EBRIDGE))
+		return -EINVAL;
+
+	err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
+			afspec, RTM_DELLINK);
+
+	return err;
+}
+static int br_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+
+	return 0;
+}
+
+static size_t br_get_link_af_size(const struct net_device *dev)
+{
+	struct net_port_vlans *pv;
+
+	if (br_port_exists(dev))
+		pv = nbp_get_vlan_info(br_port_get_rtnl(dev));
+	else if (dev->priv_flags & IFF_EBRIDGE)
+		pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
+	else
+		return 0;
+
+	if (!pv)
+		return 0;
+
+	/* Each VLAN is returned in bridge_vlan_info along with flags */
+	return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info));
+}
+
+static struct rtnl_af_ops br_af_ops = {
+	.family			= AF_BRIDGE,
+	.get_link_af_size	= br_get_link_af_size,
+};
+
+struct rtnl_link_ops br_link_ops __read_mostly = {
+	.kind		= "bridge",
+	.priv_size	= sizeof(struct net_bridge),
+	.setup		= br_dev_setup,
+	.validate	= br_validate,
+	.dellink	= br_dev_delete,
+};
+
+int __init br_netlink_init(void)
+{
+	int err;
+
+	br_mdb_init();
+	err = rtnl_af_register(&br_af_ops);
+	if (err)
+		goto out;
+
+	err = rtnl_link_register(&br_link_ops);
+	if (err)
+		goto out_af;
+
+	return 0;
+
+out_af:
+	rtnl_af_unregister(&br_af_ops);
+out:
+	br_mdb_uninit();
+	return err;
+}
+
+void __exit br_netlink_fini(void)
+{
+	br_mdb_uninit();
+	rtnl_af_unregister(&br_af_ops);
+	rtnl_link_unregister(&br_link_ops);
+}

net/bridge/br_notify.c

@@ -0,0 +1,113 @@
+/*
+ *	Device event handling
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+
+#include "br_private.h"
+
+static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr);
+
+struct notifier_block br_device_notifier = {
+	.notifier_call = br_device_event
+};
+
+/*
+ * Handle changes in state of network devices enslaved to a bridge.
+ *
+ * Note: don't care about up/down if bridge itself is down, because
+ *     port state is checked when bridge is brought up.
+ */
+static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
+{
+	struct net_device *dev = ptr;
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	bool changed_addr;
+	int err;
+
+	/* register of bridge completed, add sysfs entries */
+	if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
+		br_sysfs_addbr(dev);
+		return NOTIFY_DONE;
+	}
+
+	/* not a port of a bridge */
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		return NOTIFY_DONE;
+
+	br = p->br;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU:
+		dev_set_mtu(br->dev, br_min_mtu(br));
+		break;
+
+	case NETDEV_CHANGEADDR:
+		spin_lock_bh(&br->lock);
+		br_fdb_changeaddr(p, dev->dev_addr);
+		changed_addr = br_stp_recalculate_bridge_id(br);
+		spin_unlock_bh(&br->lock);
+
+		if (changed_addr)
+			call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
+
+		break;
+
+	case NETDEV_CHANGE:
+		br_port_carrier_check(p);
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		netdev_update_features(br->dev);
+		break;
+
+	case NETDEV_DOWN:
+		spin_lock_bh(&br->lock);
+		if (br->dev->flags & IFF_UP)
+			br_stp_disable_port(p);
+		spin_unlock_bh(&br->lock);
+		break;
+
+	case NETDEV_UP:
+		if (netif_running(br->dev) && netif_oper_up(dev)) {
+			spin_lock_bh(&br->lock);
+			br_stp_enable_port(p);
+			spin_unlock_bh(&br->lock);
+		}
+		break;
+
+	case NETDEV_UNREGISTER:
+		br_del_if(br, dev);
+		break;
+
+	case NETDEV_CHANGENAME:
+		err = br_sysfs_renameif(p);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlaying device to change its type. */
+		return NOTIFY_BAD;
+	}
+
+	/* Events that may cause spanning tree to refresh */
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
+	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+	return NOTIFY_DONE;
+}

net/bridge/br_private.h

@@ -0,0 +1,779 @@
+/*
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _BR_PRIVATE_H
+#define _BR_PRIVATE_H
+
+#include <linux/netdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/netpoll.h>
+#include <linux/u64_stats_sync.h>
+#include <net/route.h>
+#include <linux/if_vlan.h>
+
+#define BR_HASH_BITS 8
+#define BR_HASH_SIZE (1 << BR_HASH_BITS)
+
+#define BR_HOLD_TIME (1*HZ)
+
+#define BR_PORT_BITS	10
+#define BR_MAX_PORTS	(1<<BR_PORT_BITS)
+#define BR_VLAN_BITMAP_LEN	BITS_TO_LONGS(VLAN_N_VID)
+
+#define BR_VERSION	"2.3"
+
+/* Control of forwarding link local multicast */
+#define BR_GROUPFWD_DEFAULT	0
+/* Don't allow forwarding control protocols like STP and LLDP */
+#define BR_GROUPFWD_RESTRICTED	0x4007u
+
+/* Path to usermode spanning tree program */
+#define BR_STP_PROG	"/sbin/bridge-stp"
+
+typedef struct bridge_id bridge_id;
+typedef struct mac_addr mac_addr;
+typedef __u16 port_id;
+
+struct bridge_id
+{
+	unsigned char	prio[2];
+	unsigned char	addr[6];
+};
+
+struct mac_addr
+{
+	unsigned char	addr[6];
+};
+
+struct br_ip
+{
+	union {
+		__be32	ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr ip6;
+#endif
+	} u;
+	__be16		proto;
+	__u16		vid;
+};
+
+struct net_port_vlans {
+	u16				port_idx;
+	u16				pvid;
+	union {
+		struct net_bridge_port		*port;
+		struct net_bridge		*br;
+	}				parent;
+	struct rcu_head			rcu;
+	unsigned long			vlan_bitmap[BR_VLAN_BITMAP_LEN];
+	unsigned long			untagged_bitmap[BR_VLAN_BITMAP_LEN];
+	u16				num_vlans;
+};
+
+struct net_bridge_fdb_entry
+{
+	struct hlist_node		hlist;
+	struct net_bridge_port		*dst;
+
+	struct rcu_head			rcu;
+	unsigned long			updated;
+	unsigned long			used;
+	mac_addr			addr;
+	unsigned char			is_local;
+	unsigned char			is_static;
+	__u16				vlan_id;
+};
+
+struct net_bridge_port_group {
+	struct net_bridge_port		*port;
+	struct net_bridge_port_group __rcu *next;
+	struct hlist_node		mglist;
+	struct rcu_head			rcu;
+	struct timer_list		timer;
+	struct br_ip			addr;
+	unsigned char			state;
+};
+
+struct net_bridge_mdb_entry
+{
+	struct hlist_node		hlist[2];
+	struct net_bridge		*br;
+	struct net_bridge_port_group __rcu *ports;
+	struct rcu_head			rcu;
+	struct timer_list		timer;
+	struct br_ip			addr;
+	bool				mglist;
+};
+
+struct net_bridge_mdb_htable
+{
+	struct hlist_head		*mhash;
+	struct rcu_head			rcu;
+	struct net_bridge_mdb_htable	*old;
+	u32				size;
+	u32				max;
+	u32				secret;
+	u32				ver;
+};
+
+struct net_bridge_port
+{
+	struct net_bridge		*br;
+	struct net_device		*dev;
+	struct list_head		list;
+
+	/* STP */
+	u8				priority;
+	u8				state;
+	u16				port_no;
+	unsigned char			topology_change_ack;
+	unsigned char			config_pending;
+	port_id				port_id;
+	port_id				designated_port;
+	bridge_id			designated_root;
+	bridge_id			designated_bridge;
+	u32				path_cost;
+	u32				designated_cost;
+	unsigned long			designated_age;
+
+	struct timer_list		forward_delay_timer;
+	struct timer_list		hold_timer;
+	struct timer_list		message_age_timer;
+	struct kobject			kobj;
+	struct rcu_head			rcu;
+
+	unsigned long 			flags;
+#define BR_HAIRPIN_MODE		0x00000001
+#define BR_BPDU_GUARD           0x00000002
+#define BR_ROOT_BLOCK		0x00000004
+#define BR_MULTICAST_FAST_LEAVE	0x00000008
+#define BR_ADMIN_COST		0x00000010
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	u32				multicast_startup_queries_sent;
+	unsigned char			multicast_router;
+	struct timer_list		multicast_router_timer;
+	struct timer_list		multicast_query_timer;
+	struct hlist_head		mglist;
+	struct hlist_node		rlist;
+#endif
+
+#ifdef CONFIG_SYSFS
+	char				sysfs_name[IFNAMSIZ];
+#endif
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll			*np;
+#endif
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	struct net_port_vlans __rcu	*vlan_info;
+#endif
+};
+
+#define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT)
+
+static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
+{
+	return rcu_dereference(dev->rx_handler_data);
+}
+
+static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev)
+{
+	return br_port_exists(dev) ?
+		rtnl_dereference(dev->rx_handler_data) : NULL;
+}
+
+struct br_cpu_netstats {
+	u64			rx_packets;
+	u64			rx_bytes;
+	u64			tx_packets;
+	u64			tx_bytes;
+	struct u64_stats_sync	syncp;
+};
+
+struct net_bridge
+{
+	spinlock_t			lock;
+	struct list_head		port_list;
+	struct net_device		*dev;
+
+	struct br_cpu_netstats __percpu *stats;
+	spinlock_t			hash_lock;
+	struct hlist_head		hash[BR_HASH_SIZE];
+#ifdef CONFIG_BRIDGE_NETFILTER
+	struct rtable 			fake_rtable;
+	bool				nf_call_iptables;
+	bool				nf_call_ip6tables;
+	bool				nf_call_arptables;
+#endif
+	u16				group_fwd_mask;
+
+	/* STP */
+	bridge_id			designated_root;
+	bridge_id			bridge_id;
+	u32				root_path_cost;
+	unsigned long			max_age;
+	unsigned long			hello_time;
+	unsigned long			forward_delay;
+	unsigned long			bridge_max_age;
+	unsigned long			ageing_time;
+	unsigned long			bridge_hello_time;
+	unsigned long			bridge_forward_delay;
+
+	u8				group_addr[ETH_ALEN];
+	u16				root_port;
+
+	enum {
+		BR_NO_STP, 		/* no spanning tree */
+		BR_KERNEL_STP,		/* old STP in kernel */
+		BR_USER_STP,		/* new RSTP in userspace */
+	} stp_enabled;
+
+	unsigned char			topology_change;
+	unsigned char			topology_change_detected;
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	unsigned char			multicast_router;
+
+	u8				multicast_disabled:1;
+	u8				multicast_querier:1;
+
+	u32				hash_elasticity;
+	u32				hash_max;
+
+	u32				multicast_last_member_count;
+	u32				multicast_startup_queries_sent;
+	u32				multicast_startup_query_count;
+
+	unsigned long			multicast_last_member_interval;
+	unsigned long			multicast_membership_interval;
+	unsigned long			multicast_querier_interval;
+	unsigned long			multicast_query_interval;
+	unsigned long			multicast_query_response_interval;
+	unsigned long			multicast_startup_query_interval;
+
+	spinlock_t			multicast_lock;
+	struct net_bridge_mdb_htable __rcu *mdb;
+	struct hlist_head		router_list;
+
+	struct timer_list		multicast_router_timer;
+	struct timer_list		multicast_querier_timer;
+	struct timer_list		multicast_query_timer;
+#endif
+
+	struct timer_list		hello_timer;
+	struct timer_list		tcn_timer;
+	struct timer_list		topology_change_timer;
+	struct timer_list		gc_timer;
+	struct kobject			*ifobj;
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	u8				vlan_enabled;
+	struct net_port_vlans __rcu	*vlan_info;
+#endif
+};
+
+struct br_input_skb_cb {
+	struct net_device *brdev;
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	int igmp;
+	int mrouters_only;
+#endif
+};
+
+#define BR_INPUT_SKB_CB(__skb)	((struct br_input_skb_cb *)(__skb)->cb)
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+# define BR_INPUT_SKB_CB_MROUTERS_ONLY(__skb)	(BR_INPUT_SKB_CB(__skb)->mrouters_only)
+#else
+# define BR_INPUT_SKB_CB_MROUTERS_ONLY(__skb)	(0)
+#endif
+
+#define br_printk(level, br, format, args...)	\
+	printk(level "%s: " format, (br)->dev->name, ##args)
+
+#define br_err(__br, format, args...)			\
+	br_printk(KERN_ERR, __br, format, ##args)
+#define br_warn(__br, format, args...)			\
+	br_printk(KERN_WARNING, __br, format, ##args)
+#define br_notice(__br, format, args...)		\
+	br_printk(KERN_NOTICE, __br, format, ##args)
+#define br_info(__br, format, args...)			\
+	br_printk(KERN_INFO, __br, format, ##args)
+
+#define br_debug(br, format, args...)			\
+	pr_debug("%s: " format,  (br)->dev->name, ##args)
+
+extern struct notifier_block br_device_notifier;
+
+/* called under bridge lock */
+static inline int br_is_root_bridge(const struct net_bridge *br)
+{
+	return !memcmp(&br->bridge_id, &br->designated_root, 8);
+}
+
+/* br_device.c */
+extern void br_dev_setup(struct net_device *dev);
+extern void br_dev_delete(struct net_device *dev, struct list_head *list);
+extern netdev_tx_t br_dev_xmit(struct sk_buff *skb,
+			       struct net_device *dev);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
+{
+	return br->dev->npinfo;
+}
+
+static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
+				       struct sk_buff *skb)
+{
+	struct netpoll *np = p->np;
+
+	if (np)
+		netpoll_send_skb(np, skb);
+}
+
+extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
+extern void br_netpoll_disable(struct net_bridge_port *p);
+#else
+static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
+{
+	return NULL;
+}
+
+static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
+				       struct sk_buff *skb)
+{
+}
+
+static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+{
+	return 0;
+}
+
+static inline void br_netpoll_disable(struct net_bridge_port *p)
+{
+}
+#endif
+
+/* br_fdb.c */
+extern int br_fdb_init(void);
+extern void br_fdb_fini(void);
+extern void br_fdb_flush(struct net_bridge *br);
+extern void br_fdb_changeaddr(struct net_bridge_port *p,
+			      const unsigned char *newaddr);
+extern void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
+extern void br_fdb_cleanup(unsigned long arg);
+extern void br_fdb_delete_by_port(struct net_bridge *br,
+				  const struct net_bridge_port *p, int do_all);
+extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
+						 const unsigned char *addr,
+						 __u16 vid);
+extern int br_fdb_test_addr(struct net_device *dev, unsigned char *addr);
+extern int br_fdb_fillbuf(struct net_bridge *br, void *buf,
+			  unsigned long count, unsigned long off);
+extern int br_fdb_insert(struct net_bridge *br,
+			 struct net_bridge_port *source,
+			 const unsigned char *addr,
+			 u16 vid);
+extern void br_fdb_update(struct net_bridge *br,
+			  struct net_bridge_port *source,
+			  const unsigned char *addr,
+			  u16 vid);
+extern int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid);
+
+extern int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
+			 struct net_device *dev,
+			 const unsigned char *addr);
+extern int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[],
+		      struct net_device *dev,
+		      const unsigned char *addr,
+		      u16 nlh_flags);
+extern int br_fdb_dump(struct sk_buff *skb,
+		       struct netlink_callback *cb,
+		       struct net_device *dev,
+		       int idx);
+
+/* br_forward.c */
+extern void br_deliver(const struct net_bridge_port *to,
+		struct sk_buff *skb);
+extern int br_dev_queue_push_xmit(struct sk_buff *skb);
+extern void br_forward(const struct net_bridge_port *to,
+		struct sk_buff *skb, struct sk_buff *skb0);
+extern int br_forward_finish(struct sk_buff *skb);
+extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb);
+extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
+			     struct sk_buff *skb2);
+
+/* br_if.c */
+extern void br_port_carrier_check(struct net_bridge_port *p);
+extern int br_add_bridge(struct net *net, const char *name);
+extern int br_del_bridge(struct net *net, const char *name);
+extern void br_net_exit(struct net *net);
+extern int br_add_if(struct net_bridge *br,
+	      struct net_device *dev);
+extern int br_del_if(struct net_bridge *br,
+	      struct net_device *dev);
+extern int br_min_mtu(const struct net_bridge *br);
+extern netdev_features_t br_features_recompute(struct net_bridge *br,
+	netdev_features_t features);
+
+/* br_input.c */
+extern int br_handle_frame_finish(struct sk_buff *skb);
+extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
+
+/* br_ioctl.c */
+extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg);
+
+/* br_multicast.c */
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+extern unsigned int br_mdb_rehash_seq;
+extern int br_multicast_rcv(struct net_bridge *br,
+			    struct net_bridge_port *port,
+			    struct sk_buff *skb);
+extern struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
+					       struct sk_buff *skb, u16 vid);
+extern void br_multicast_add_port(struct net_bridge_port *port);
+extern void br_multicast_del_port(struct net_bridge_port *port);
+extern void br_multicast_enable_port(struct net_bridge_port *port);
+extern void br_multicast_disable_port(struct net_bridge_port *port);
+extern void br_multicast_init(struct net_bridge *br);
+extern void br_multicast_open(struct net_bridge *br);
+extern void br_multicast_stop(struct net_bridge *br);
+extern void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
+				 struct sk_buff *skb);
+extern void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
+				 struct sk_buff *skb, struct sk_buff *skb2);
+extern int br_multicast_set_router(struct net_bridge *br, unsigned long val);
+extern int br_multicast_set_port_router(struct net_bridge_port *p,
+					unsigned long val);
+extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
+extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
+extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
+extern struct net_bridge_mdb_entry *br_mdb_ip_get(
+				struct net_bridge_mdb_htable *mdb,
+				struct br_ip *dst);
+extern struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
+				struct net_bridge_port *port, struct br_ip *group);
+extern void br_multicast_free_pg(struct rcu_head *head);
+extern struct net_bridge_port_group *br_multicast_new_port_group(
+				struct net_bridge_port *port,
+				struct br_ip *group,
+				struct net_bridge_port_group *next,
+				unsigned char state);
+extern void br_mdb_init(void);
+extern void br_mdb_uninit(void);
+extern void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
+			  struct br_ip *group, int type);
+
+#define mlock_dereference(X, br) \
+	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/addrconf.h>
+static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
+{
+	if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
+		return 1;
+	return 0;
+}
+#endif
+
+static inline bool br_multicast_is_router(struct net_bridge *br)
+{
+	return br->multicast_router == 2 ||
+	       (br->multicast_router == 1 &&
+		timer_pending(&br->multicast_router_timer));
+}
+#else
+static inline int br_multicast_rcv(struct net_bridge *br,
+				   struct net_bridge_port *port,
+				   struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
+						      struct sk_buff *skb, u16 vid)
+{
+	return NULL;
+}
+
+static inline void br_multicast_add_port(struct net_bridge_port *port)
+{
+}
+
+static inline void br_multicast_del_port(struct net_bridge_port *port)
+{
+}
+
+static inline void br_multicast_enable_port(struct net_bridge_port *port)
+{
+}
+
+static inline void br_multicast_disable_port(struct net_bridge_port *port)
+{
+}
+
+static inline void br_multicast_init(struct net_bridge *br)
+{
+}
+
+static inline void br_multicast_open(struct net_bridge *br)
+{
+}
+
+static inline void br_multicast_stop(struct net_bridge *br)
+{
+}
+
+static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
+					struct sk_buff *skb)
+{
+}
+
+static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
+					struct sk_buff *skb,
+					struct sk_buff *skb2)
+{
+}
+static inline bool br_multicast_is_router(struct net_bridge *br)
+{
+	return 0;
+}
+static inline void br_mdb_init(void)
+{
+}
+static inline void br_mdb_uninit(void)
+{
+}
+#endif
+
+/* br_vlan.c */
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+extern bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
+			       struct sk_buff *skb, u16 *vid);
+extern bool br_allowed_egress(struct net_bridge *br,
+			      const struct net_port_vlans *v,
+			      const struct sk_buff *skb);
+extern struct sk_buff *br_handle_vlan(struct net_bridge *br,
+				      const struct net_port_vlans *v,
+				      struct sk_buff *skb);
+extern int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
+extern int br_vlan_delete(struct net_bridge *br, u16 vid);
+extern void br_vlan_flush(struct net_bridge *br);
+extern int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
+extern int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
+extern int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
+extern void nbp_vlan_flush(struct net_bridge_port *port);
+extern bool nbp_vlan_find(struct net_bridge_port *port, u16 vid);
+
+static inline struct net_port_vlans *br_get_vlan_info(
+						const struct net_bridge *br)
+{
+	return rcu_dereference_rtnl(br->vlan_info);
+}
+
+static inline struct net_port_vlans *nbp_get_vlan_info(
+						const struct net_bridge_port *p)
+{
+	return rcu_dereference_rtnl(p->vlan_info);
+}
+
+/* Since bridge now depends on 8021Q module, but the time bridge sees the
+ * skb, the vlan tag will always be present if the frame was tagged.
+ */
+static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
+{
+	int err = 0;
+
+	if (vlan_tx_tag_present(skb))
+		*vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK;
+	else {
+		*vid = 0;
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static inline u16 br_get_pvid(const struct net_port_vlans *v)
+{
+	/* Return just the VID if it is set, or VLAN_N_VID (invalid vid) if
+	 * vid wasn't set
+	 */
+	smp_rmb();
+	return (v->pvid & VLAN_TAG_PRESENT) ?
+			(v->pvid & ~VLAN_TAG_PRESENT) :
+			VLAN_N_VID;
+}
+
+#else
+static inline bool br_allowed_ingress(struct net_bridge *br,
+				      struct net_port_vlans *v,
+				      struct sk_buff *skb,
+				      u16 *vid)
+{
+	return true;
+}
+
+static inline bool br_allowed_egress(struct net_bridge *br,
+				     const struct net_port_vlans *v,
+				     const struct sk_buff *skb)
+{
+	return true;
+}
+
+static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
+					     const struct net_port_vlans *v,
+					     struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int br_vlan_delete(struct net_bridge *br, u16 vid)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void br_vlan_flush(struct net_bridge *br)
+{
+}
+
+static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int nbp_vlan_delete(struct net_bridge_port *port, u16 vid)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void nbp_vlan_flush(struct net_bridge_port *port)
+{
+}
+
+static inline struct net_port_vlans *br_get_vlan_info(
+						const struct net_bridge *br)
+{
+	return NULL;
+}
+static inline struct net_port_vlans *nbp_get_vlan_info(
+						const struct net_bridge_port *p)
+{
+	return NULL;
+}
+
+static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid)
+{
+	return false;
+}
+
+static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag)
+{
+	return 0;
+}
+static inline u16 br_get_pvid(const struct net_port_vlans *v)
+{
+	return VLAN_N_VID;	/* Returns invalid vid */
+}
+#endif
+
+/* br_netfilter.c */
+#ifdef CONFIG_BRIDGE_NETFILTER
+extern int br_netfilter_init(void);
+extern void br_netfilter_fini(void);
+extern void br_netfilter_rtable_init(struct net_bridge *);
+#else
+#define br_netfilter_init()	(0)
+#define br_netfilter_fini()	do { } while(0)
+#define br_netfilter_rtable_init(x)
+#endif
+
+/* br_stp.c */
+extern void br_log_state(const struct net_bridge_port *p);
+extern struct net_bridge_port *br_get_port(struct net_bridge *br,
+					   u16 port_no);
+extern void br_init_port(struct net_bridge_port *p);
+extern void br_become_designated_port(struct net_bridge_port *p);
+
+extern void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
+extern int br_set_forward_delay(struct net_bridge *br, unsigned long x);
+extern int br_set_hello_time(struct net_bridge *br, unsigned long x);
+extern int br_set_max_age(struct net_bridge *br, unsigned long x);
+
+
+/* br_stp_if.c */
+extern void br_stp_enable_bridge(struct net_bridge *br);
+extern void br_stp_disable_bridge(struct net_bridge *br);
+extern void br_stp_set_enabled(struct net_bridge *br, unsigned long val);
+extern void br_stp_enable_port(struct net_bridge_port *p);
+extern void br_stp_disable_port(struct net_bridge_port *p);
+extern bool br_stp_recalculate_bridge_id(struct net_bridge *br);
+extern void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a);
+extern void br_stp_set_bridge_priority(struct net_bridge *br,
+				       u16 newprio);
+extern int br_stp_set_port_priority(struct net_bridge_port *p,
+				    unsigned long newprio);
+extern int br_stp_set_path_cost(struct net_bridge_port *p,
+				unsigned long path_cost);
+extern ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id);
+
+/* br_stp_bpdu.c */
+struct stp_proto;
+extern void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
+		       struct net_device *dev);
+
+/* br_stp_timer.c */
+extern void br_stp_timer_init(struct net_bridge *br);
+extern void br_stp_port_timer_init(struct net_bridge_port *p);
+extern unsigned long br_timer_value(const struct timer_list *timer);
+
+/* br.c */
+#if IS_ENABLED(CONFIG_ATM_LANE)
+extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr);
+#endif
+
+/* br_netlink.c */
+extern struct rtnl_link_ops br_link_ops;
+extern int br_netlink_init(void);
+extern void br_netlink_fini(void);
+extern void br_ifinfo_notify(int event, struct net_bridge_port *port);
+extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg);
+extern int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg);
+extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+		      struct net_device *dev, u32 filter_mask);
+
+#ifdef CONFIG_SYSFS
+/* br_sysfs_if.c */
+extern const struct sysfs_ops brport_sysfs_ops;
+extern int br_sysfs_addif(struct net_bridge_port *p);
+extern int br_sysfs_renameif(struct net_bridge_port *p);
+
+/* br_sysfs_br.c */
+extern int br_sysfs_addbr(struct net_device *dev);
+extern void br_sysfs_delbr(struct net_device *dev);
+
+#else
+
+static inline int br_sysfs_addif(struct net_bridge_port *p) { return 0; }
+static inline int br_sysfs_renameif(struct net_bridge_port *p) { return 0; }
+static inline int br_sysfs_addbr(struct net_device *dev) { return 0; }
+static inline void br_sysfs_delbr(struct net_device *dev) { return; }
+#endif /* CONFIG_SYSFS */
+
+#endif

net/bridge/br_private_stp.h

@@ -0,0 +1,69 @@
+/*
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _BR_PRIVATE_STP_H
+#define _BR_PRIVATE_STP_H
+
+#define BPDU_TYPE_CONFIG 0
+#define BPDU_TYPE_TCN 0x80
+
+/* IEEE 802.1D-1998 timer values */
+#define BR_MIN_HELLO_TIME	(1*HZ)
+#define BR_MAX_HELLO_TIME	(10*HZ)
+
+#define BR_MIN_FORWARD_DELAY	(2*HZ)
+#define BR_MAX_FORWARD_DELAY	(30*HZ)
+
+#define BR_MIN_MAX_AGE		(6*HZ)
+#define BR_MAX_MAX_AGE		(40*HZ)
+
+#define BR_MIN_PATH_COST	1
+#define BR_MAX_PATH_COST	65535
+
+struct br_config_bpdu {
+	unsigned int	topology_change:1;
+	unsigned int	topology_change_ack:1;
+	bridge_id	root;
+	int		root_path_cost;
+	bridge_id	bridge_id;
+	port_id		port_id;
+	int		message_age;
+	int		max_age;
+	int		hello_time;
+	int		forward_delay;
+};
+
+/* called under bridge lock */
+static inline int br_is_designated_port(const struct net_bridge_port *p)
+{
+	return !memcmp(&p->designated_bridge, &p->br->bridge_id, 8) &&
+		(p->designated_port == p->port_id);
+}
+
+
+/* br_stp.c */
+extern void br_become_root_bridge(struct net_bridge *br);
+extern void br_config_bpdu_generation(struct net_bridge *);
+extern void br_configuration_update(struct net_bridge *);
+extern void br_port_state_selection(struct net_bridge *);
+extern void br_received_config_bpdu(struct net_bridge_port *p,
+				    const struct br_config_bpdu *bpdu);
+extern void br_received_tcn_bpdu(struct net_bridge_port *p);
+extern void br_transmit_config(struct net_bridge_port *p);
+extern void br_transmit_tcn(struct net_bridge *br);
+extern void br_topology_change_detection(struct net_bridge *br);
+
+/* br_stp_bpdu.c */
+extern void br_send_config_bpdu(struct net_bridge_port *, struct br_config_bpdu *);
+extern void br_send_tcn_bpdu(struct net_bridge_port *);
+
+#endif

net/bridge/br_stp.c

@@ -0,0 +1,570 @@
+/*
+ *	Spanning tree protocol; generic parts
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/rculist.h>
+
+#include "br_private.h"
+#include "br_private_stp.h"
+
+/* since time values in bpdu are in jiffies and then scaled (1/256)
+ * before sending, make sure that is at least one STP tick.
+ */
+#define MESSAGE_AGE_INCR	((HZ / 256) + 1)
+
+static const char *const br_port_state_names[] = {
+	[BR_STATE_DISABLED] = "disabled",
+	[BR_STATE_LISTENING] = "listening",
+	[BR_STATE_LEARNING] = "learning",
+	[BR_STATE_FORWARDING] = "forwarding",
+	[BR_STATE_BLOCKING] = "blocking",
+};
+
+void br_log_state(const struct net_bridge_port *p)
+{
+	br_info(p->br, "port %u(%s) entered %s state\n",
+		(unsigned int) p->port_no, p->dev->name,
+		br_port_state_names[p->state]);
+}
+
+/* called under bridge lock */
+struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no)
+{
+	struct net_bridge_port *p;
+
+	list_for_each_entry_rcu(p, &br->port_list, list) {
+		if (p->port_no == port_no)
+			return p;
+	}
+
+	return NULL;
+}
+
+/* called under bridge lock */
+static int br_should_become_root_port(const struct net_bridge_port *p,
+				      u16 root_port)
+{
+	struct net_bridge *br;
+	struct net_bridge_port *rp;
+	int t;
+
+	br = p->br;
+	if (p->state == BR_STATE_DISABLED ||
+	    br_is_designated_port(p))
+		return 0;
+
+	if (memcmp(&br->bridge_id, &p->designated_root, 8) <= 0)
+		return 0;
+
+	if (!root_port)
+		return 1;
+
+	rp = br_get_port(br, root_port);
+
+	t = memcmp(&p->designated_root, &rp->designated_root, 8);
+	if (t < 0)
+		return 1;
+	else if (t > 0)
+		return 0;
+
+	if (p->designated_cost + p->path_cost <
+	    rp->designated_cost + rp->path_cost)
+		return 1;
+	else if (p->designated_cost + p->path_cost >
+		 rp->designated_cost + rp->path_cost)
+		return 0;
+
+	t = memcmp(&p->designated_bridge, &rp->designated_bridge, 8);
+	if (t < 0)
+		return 1;
+	else if (t > 0)
+		return 0;
+
+	if (p->designated_port < rp->designated_port)
+		return 1;
+	else if (p->designated_port > rp->designated_port)
+		return 0;
+
+	if (p->port_id < rp->port_id)
+		return 1;
+
+	return 0;
+}
+
+static void br_root_port_block(const struct net_bridge *br,
+			       struct net_bridge_port *p)
+{
+
+	br_notice(br, "port %u(%s) tried to become root port (blocked)",
+		  (unsigned int) p->port_no, p->dev->name);
+
+	p->state = BR_STATE_LISTENING;
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (br->forward_delay > 0)
+		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
+}
+
+/* called under bridge lock */
+static void br_root_selection(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	u16 root_port = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!br_should_become_root_port(p, root_port))
+			continue;
+
+		if (p->flags & BR_ROOT_BLOCK)
+			br_root_port_block(br, p);
+		else
+			root_port = p->port_no;
+	}
+
+	br->root_port = root_port;
+
+	if (!root_port) {
+		br->designated_root = br->bridge_id;
+		br->root_path_cost = 0;
+	} else {
+		p = br_get_port(br, root_port);
+		br->designated_root = p->designated_root;
+		br->root_path_cost = p->designated_cost + p->path_cost;
+	}
+}
+
+/* called under bridge lock */
+void br_become_root_bridge(struct net_bridge *br)
+{
+	br->max_age = br->bridge_max_age;
+	br->hello_time = br->bridge_hello_time;
+	br->forward_delay = br->bridge_forward_delay;
+	br_topology_change_detection(br);
+	del_timer(&br->tcn_timer);
+
+	if (br->dev->flags & IFF_UP) {
+		br_config_bpdu_generation(br);
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
+	}
+}
+
+/* called under bridge lock */
+void br_transmit_config(struct net_bridge_port *p)
+{
+	struct br_config_bpdu bpdu;
+	struct net_bridge *br;
+
+	if (timer_pending(&p->hold_timer)) {
+		p->config_pending = 1;
+		return;
+	}
+
+	br = p->br;
+
+	bpdu.topology_change = br->topology_change;
+	bpdu.topology_change_ack = p->topology_change_ack;
+	bpdu.root = br->designated_root;
+	bpdu.root_path_cost = br->root_path_cost;
+	bpdu.bridge_id = br->bridge_id;
+	bpdu.port_id = p->port_id;
+	if (br_is_root_bridge(br))
+		bpdu.message_age = 0;
+	else {
+		struct net_bridge_port *root
+			= br_get_port(br, br->root_port);
+		bpdu.message_age = (jiffies - root->designated_age)
+			+ MESSAGE_AGE_INCR;
+	}
+	bpdu.max_age = br->max_age;
+	bpdu.hello_time = br->hello_time;
+	bpdu.forward_delay = br->forward_delay;
+
+	if (bpdu.message_age < br->max_age) {
+		br_send_config_bpdu(p, &bpdu);
+		p->topology_change_ack = 0;
+		p->config_pending = 0;
+		mod_timer(&p->hold_timer,
+			  round_jiffies(jiffies + BR_HOLD_TIME));
+	}
+}
+
+/* called under bridge lock */
+static void br_record_config_information(struct net_bridge_port *p,
+					 const struct br_config_bpdu *bpdu)
+{
+	p->designated_root = bpdu->root;
+	p->designated_cost = bpdu->root_path_cost;
+	p->designated_bridge = bpdu->bridge_id;
+	p->designated_port = bpdu->port_id;
+	p->designated_age = jiffies - bpdu->message_age;
+
+	mod_timer(&p->message_age_timer, jiffies
+		  + (bpdu->max_age - bpdu->message_age));
+}
+
+/* called under bridge lock */
+static void br_record_config_timeout_values(struct net_bridge *br,
+					    const struct br_config_bpdu *bpdu)
+{
+	br->max_age = bpdu->max_age;
+	br->hello_time = bpdu->hello_time;
+	br->forward_delay = bpdu->forward_delay;
+	br->topology_change = bpdu->topology_change;
+}
+
+/* called under bridge lock */
+void br_transmit_tcn(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	p = br_get_port(br, br->root_port);
+	if (p)
+		br_send_tcn_bpdu(p);
+	else
+		br_notice(br, "root port %u not found for topology notice\n",
+			  br->root_port);
+}
+
+/* called under bridge lock */
+static int br_should_become_designated_port(const struct net_bridge_port *p)
+{
+	struct net_bridge *br;
+	int t;
+
+	br = p->br;
+	if (br_is_designated_port(p))
+		return 1;
+
+	if (memcmp(&p->designated_root, &br->designated_root, 8))
+		return 1;
+
+	if (br->root_path_cost < p->designated_cost)
+		return 1;
+	else if (br->root_path_cost > p->designated_cost)
+		return 0;
+
+	t = memcmp(&br->bridge_id, &p->designated_bridge, 8);
+	if (t < 0)
+		return 1;
+	else if (t > 0)
+		return 0;
+
+	if (p->port_id < p->designated_port)
+		return 1;
+
+	return 0;
+}
+
+/* called under bridge lock */
+static void br_designated_port_selection(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state != BR_STATE_DISABLED &&
+		    br_should_become_designated_port(p))
+			br_become_designated_port(p);
+
+	}
+}
+
+/* called under bridge lock */
+static int br_supersedes_port_info(const struct net_bridge_port *p,
+				   const struct br_config_bpdu *bpdu)
+{
+	int t;
+
+	t = memcmp(&bpdu->root, &p->designated_root, 8);
+	if (t < 0)
+		return 1;
+	else if (t > 0)
+		return 0;
+
+	if (bpdu->root_path_cost < p->designated_cost)
+		return 1;
+	else if (bpdu->root_path_cost > p->designated_cost)
+		return 0;
+
+	t = memcmp(&bpdu->bridge_id, &p->designated_bridge, 8);
+	if (t < 0)
+		return 1;
+	else if (t > 0)
+		return 0;
+
+	if (memcmp(&bpdu->bridge_id, &p->br->bridge_id, 8))
+		return 1;
+
+	if (bpdu->port_id <= p->designated_port)
+		return 1;
+
+	return 0;
+}
+
+/* called under bridge lock */
+static void br_topology_change_acknowledged(struct net_bridge *br)
+{
+	br->topology_change_detected = 0;
+	del_timer(&br->tcn_timer);
+}
+
+/* called under bridge lock */
+void br_topology_change_detection(struct net_bridge *br)
+{
+	int isroot = br_is_root_bridge(br);
+
+	if (br->stp_enabled != BR_KERNEL_STP)
+		return;
+
+	br_info(br, "topology change detected, %s\n",
+		isroot ? "propagating" : "sending tcn bpdu");
+
+	if (isroot) {
+		br->topology_change = 1;
+		mod_timer(&br->topology_change_timer, jiffies
+			  + br->bridge_forward_delay + br->bridge_max_age);
+	} else if (!br->topology_change_detected) {
+		br_transmit_tcn(br);
+		mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time);
+	}
+
+	br->topology_change_detected = 1;
+}
+
+/* called under bridge lock */
+void br_config_bpdu_generation(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state != BR_STATE_DISABLED &&
+		    br_is_designated_port(p))
+			br_transmit_config(p);
+	}
+}
+
+/* called under bridge lock */
+static void br_reply(struct net_bridge_port *p)
+{
+	br_transmit_config(p);
+}
+
+/* called under bridge lock */
+void br_configuration_update(struct net_bridge *br)
+{
+	br_root_selection(br);
+	br_designated_port_selection(br);
+}
+
+/* called under bridge lock */
+void br_become_designated_port(struct net_bridge_port *p)
+{
+	struct net_bridge *br;
+
+	br = p->br;
+	p->designated_root = br->designated_root;
+	p->designated_cost = br->root_path_cost;
+	p->designated_bridge = br->bridge_id;
+	p->designated_port = p->port_id;
+}
+
+
+/* called under bridge lock */
+static void br_make_blocking(struct net_bridge_port *p)
+{
+	if (p->state != BR_STATE_DISABLED &&
+	    p->state != BR_STATE_BLOCKING) {
+		if (p->state == BR_STATE_FORWARDING ||
+		    p->state == BR_STATE_LEARNING)
+			br_topology_change_detection(p->br);
+
+		p->state = BR_STATE_BLOCKING;
+		br_log_state(p);
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+		del_timer(&p->forward_delay_timer);
+	}
+}
+
+/* called under bridge lock */
+static void br_make_forwarding(struct net_bridge_port *p)
+{
+	struct net_bridge *br = p->br;
+
+	if (p->state != BR_STATE_BLOCKING)
+		return;
+
+	if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) {
+		p->state = BR_STATE_FORWARDING;
+		br_topology_change_detection(br);
+		del_timer(&p->forward_delay_timer);
+	} else if (br->stp_enabled == BR_KERNEL_STP)
+		p->state = BR_STATE_LISTENING;
+	else
+		p->state = BR_STATE_LEARNING;
+
+	br_multicast_enable_port(p);
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (br->forward_delay != 0)
+		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
+}
+
+/* called under bridge lock */
+void br_port_state_selection(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	unsigned int liveports = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state == BR_STATE_DISABLED)
+			continue;
+
+		/* Don't change port states if userspace is handling STP */
+		if (br->stp_enabled != BR_USER_STP) {
+			if (p->port_no == br->root_port) {
+				p->config_pending = 0;
+				p->topology_change_ack = 0;
+				br_make_forwarding(p);
+			} else if (br_is_designated_port(p)) {
+				del_timer(&p->message_age_timer);
+				br_make_forwarding(p);
+			} else {
+				p->config_pending = 0;
+				p->topology_change_ack = 0;
+				br_make_blocking(p);
+			}
+		}
+
+		if (p->state == BR_STATE_FORWARDING)
+			++liveports;
+	}
+
+	if (liveports == 0)
+		netif_carrier_off(br->dev);
+	else
+		netif_carrier_on(br->dev);
+}
+
+/* called under bridge lock */
+static void br_topology_change_acknowledge(struct net_bridge_port *p)
+{
+	p->topology_change_ack = 1;
+	br_transmit_config(p);
+}
+
+/* called under bridge lock */
+void br_received_config_bpdu(struct net_bridge_port *p,
+			     const struct br_config_bpdu *bpdu)
+{
+	struct net_bridge *br;
+	int was_root;
+
+	br = p->br;
+	was_root = br_is_root_bridge(br);
+
+	if (br_supersedes_port_info(p, bpdu)) {
+		br_record_config_information(p, bpdu);
+		br_configuration_update(br);
+		br_port_state_selection(br);
+
+		if (!br_is_root_bridge(br) && was_root) {
+			del_timer(&br->hello_timer);
+			if (br->topology_change_detected) {
+				del_timer(&br->topology_change_timer);
+				br_transmit_tcn(br);
+
+				mod_timer(&br->tcn_timer,
+					  jiffies + br->bridge_hello_time);
+			}
+		}
+
+		if (p->port_no == br->root_port) {
+			br_record_config_timeout_values(br, bpdu);
+			br_config_bpdu_generation(br);
+			if (bpdu->topology_change_ack)
+				br_topology_change_acknowledged(br);
+		}
+	} else if (br_is_designated_port(p)) {
+		br_reply(p);
+	}
+}
+
+/* called under bridge lock */
+void br_received_tcn_bpdu(struct net_bridge_port *p)
+{
+	if (br_is_designated_port(p)) {
+		br_info(p->br, "port %u(%s) received tcn bpdu\n",
+			(unsigned int) p->port_no, p->dev->name);
+
+		br_topology_change_detection(p->br);
+		br_topology_change_acknowledge(p);
+	}
+}
+
+/* Change bridge STP parameter */
+int br_set_hello_time(struct net_bridge *br, unsigned long val)
+{
+	unsigned long t = clock_t_to_jiffies(val);
+
+	if (t < BR_MIN_HELLO_TIME || t > BR_MAX_HELLO_TIME)
+		return -ERANGE;
+
+	spin_lock_bh(&br->lock);
+	br->bridge_hello_time = t;
+	if (br_is_root_bridge(br))
+		br->hello_time = br->bridge_hello_time;
+	spin_unlock_bh(&br->lock);
+	return 0;
+}
+
+int br_set_max_age(struct net_bridge *br, unsigned long val)
+{
+	unsigned long t = clock_t_to_jiffies(val);
+
+	if (t < BR_MIN_MAX_AGE || t > BR_MAX_MAX_AGE)
+		return -ERANGE;
+
+	spin_lock_bh(&br->lock);
+	br->bridge_max_age = t;
+	if (br_is_root_bridge(br))
+		br->max_age = br->bridge_max_age;
+	spin_unlock_bh(&br->lock);
+	return 0;
+
+}
+
+void __br_set_forward_delay(struct net_bridge *br, unsigned long t)
+{
+	br->bridge_forward_delay = t;
+	if (br_is_root_bridge(br))
+		br->forward_delay = br->bridge_forward_delay;
+}
+
+int br_set_forward_delay(struct net_bridge *br, unsigned long val)
+{
+	unsigned long t = clock_t_to_jiffies(val);
+	int err = -ERANGE;
+
+	spin_lock_bh(&br->lock);
+	if (br->stp_enabled != BR_NO_STP &&
+	    (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY))
+		goto unlock;
+
+	__br_set_forward_delay(br, t);
+	err = 0;
+
+unlock:
+	spin_unlock_bh(&br->lock);
+	return err;
+}

net/bridge/br_stp_bpdu.c

@@ -0,0 +1,241 @@
+/*
+ *	Spanning tree protocol; BPDU handling
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/etherdevice.h>
+#include <linux/llc.h>
+#include <linux/slab.h>
+#include <linux/pkt_sched.h>
+#include <net/net_namespace.h>
+#include <net/llc.h>
+#include <net/llc_pdu.h>
+#include <net/stp.h>
+#include <asm/unaligned.h>
+
+#include "br_private.h"
+#include "br_private_stp.h"
+
+#define STP_HZ		256
+
+#define LLC_RESERVE sizeof(struct llc_pdu_un)
+
+static void br_send_bpdu(struct net_bridge_port *p,
+			 const unsigned char *data, int length)
+{
+	struct sk_buff *skb;
+
+	skb = dev_alloc_skb(length+LLC_RESERVE);
+	if (!skb)
+		return;
+
+	skb->dev = p->dev;
+	skb->protocol = htons(ETH_P_802_2);
+	skb->priority = TC_PRIO_CONTROL;
+
+	skb_reserve(skb, LLC_RESERVE);
+	memcpy(__skb_put(skb, length), data, length);
+
+	llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN,
+			    LLC_SAP_BSPAN, LLC_PDU_CMD);
+	llc_pdu_init_as_ui_cmd(skb);
+
+	llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr);
+
+	skb_reset_mac_header(skb);
+
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+		dev_queue_xmit);
+}
+
+static inline void br_set_ticks(unsigned char *dest, int j)
+{
+	unsigned long ticks = (STP_HZ * j)/ HZ;
+
+	put_unaligned_be16(ticks, dest);
+}
+
+static inline int br_get_ticks(const unsigned char *src)
+{
+	unsigned long ticks = get_unaligned_be16(src);
+
+	return DIV_ROUND_UP(ticks * HZ, STP_HZ);
+}
+
+/* called under bridge lock */
+void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu)
+{
+	unsigned char buf[35];
+
+	if (p->br->stp_enabled != BR_KERNEL_STP)
+		return;
+
+	buf[0] = 0;
+	buf[1] = 0;
+	buf[2] = 0;
+	buf[3] = BPDU_TYPE_CONFIG;
+	buf[4] = (bpdu->topology_change ? 0x01 : 0) |
+		(bpdu->topology_change_ack ? 0x80 : 0);
+	buf[5] = bpdu->root.prio[0];
+	buf[6] = bpdu->root.prio[1];
+	buf[7] = bpdu->root.addr[0];
+	buf[8] = bpdu->root.addr[1];
+	buf[9] = bpdu->root.addr[2];
+	buf[10] = bpdu->root.addr[3];
+	buf[11] = bpdu->root.addr[4];
+	buf[12] = bpdu->root.addr[5];
+	buf[13] = (bpdu->root_path_cost >> 24) & 0xFF;
+	buf[14] = (bpdu->root_path_cost >> 16) & 0xFF;
+	buf[15] = (bpdu->root_path_cost >> 8) & 0xFF;
+	buf[16] = bpdu->root_path_cost & 0xFF;
+	buf[17] = bpdu->bridge_id.prio[0];
+	buf[18] = bpdu->bridge_id.prio[1];
+	buf[19] = bpdu->bridge_id.addr[0];
+	buf[20] = bpdu->bridge_id.addr[1];
+	buf[21] = bpdu->bridge_id.addr[2];
+	buf[22] = bpdu->bridge_id.addr[3];
+	buf[23] = bpdu->bridge_id.addr[4];
+	buf[24] = bpdu->bridge_id.addr[5];
+	buf[25] = (bpdu->port_id >> 8) & 0xFF;
+	buf[26] = bpdu->port_id & 0xFF;
+
+	br_set_ticks(buf+27, bpdu->message_age);
+	br_set_ticks(buf+29, bpdu->max_age);
+	br_set_ticks(buf+31, bpdu->hello_time);
+	br_set_ticks(buf+33, bpdu->forward_delay);
+
+	br_send_bpdu(p, buf, 35);
+}
+
+/* called under bridge lock */
+void br_send_tcn_bpdu(struct net_bridge_port *p)
+{
+	unsigned char buf[4];
+
+	if (p->br->stp_enabled != BR_KERNEL_STP)
+		return;
+
+	buf[0] = 0;
+	buf[1] = 0;
+	buf[2] = 0;
+	buf[3] = BPDU_TYPE_TCN;
+	br_send_bpdu(p, buf, 4);
+}
+
+/*
+ * Called from llc.
+ *
+ * NO locks, but rcu_read_lock
+ */
+void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
+		struct net_device *dev)
+{
+	const unsigned char *dest = eth_hdr(skb)->h_dest;
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	const unsigned char *buf;
+
+	if (!pskb_may_pull(skb, 4))
+		goto err;
+
+	/* compare of protocol id and version */
+	buf = skb->data;
+	if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0)
+		goto err;
+
+	p = br_port_get_rcu(dev);
+	if (!p)
+		goto err;
+
+	br = p->br;
+	spin_lock(&br->lock);
+
+	if (br->stp_enabled != BR_KERNEL_STP)
+		goto out;
+
+	if (!(br->dev->flags & IFF_UP))
+		goto out;
+
+	if (p->state == BR_STATE_DISABLED)
+		goto out;
+
+	if (!ether_addr_equal(dest, br->group_addr))
+		goto out;
+
+	if (p->flags & BR_BPDU_GUARD) {
+		br_notice(br, "BPDU received on blocked port %u(%s)\n",
+			  (unsigned int) p->port_no, p->dev->name);
+		br_stp_disable_port(p);
+		goto out;
+	}
+
+	buf = skb_pull(skb, 3);
+
+	if (buf[0] == BPDU_TYPE_CONFIG) {
+		struct br_config_bpdu bpdu;
+
+		if (!pskb_may_pull(skb, 32))
+			goto out;
+
+		buf = skb->data;
+		bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0;
+		bpdu.topology_change_ack = (buf[1] & 0x80) ? 1 : 0;
+
+		bpdu.root.prio[0] = buf[2];
+		bpdu.root.prio[1] = buf[3];
+		bpdu.root.addr[0] = buf[4];
+		bpdu.root.addr[1] = buf[5];
+		bpdu.root.addr[2] = buf[6];
+		bpdu.root.addr[3] = buf[7];
+		bpdu.root.addr[4] = buf[8];
+		bpdu.root.addr[5] = buf[9];
+		bpdu.root_path_cost =
+			(buf[10] << 24) |
+			(buf[11] << 16) |
+			(buf[12] << 8) |
+			buf[13];
+		bpdu.bridge_id.prio[0] = buf[14];
+		bpdu.bridge_id.prio[1] = buf[15];
+		bpdu.bridge_id.addr[0] = buf[16];
+		bpdu.bridge_id.addr[1] = buf[17];
+		bpdu.bridge_id.addr[2] = buf[18];
+		bpdu.bridge_id.addr[3] = buf[19];
+		bpdu.bridge_id.addr[4] = buf[20];
+		bpdu.bridge_id.addr[5] = buf[21];
+		bpdu.port_id = (buf[22] << 8) | buf[23];
+
+		bpdu.message_age = br_get_ticks(buf+24);
+		bpdu.max_age = br_get_ticks(buf+26);
+		bpdu.hello_time = br_get_ticks(buf+28);
+		bpdu.forward_delay = br_get_ticks(buf+30);
+
+		if (bpdu.message_age > bpdu.max_age) {
+			if (net_ratelimit())
+				br_notice(p->br,
+					  "port %u config from %pM"
+					  " (message_age %ul > max_age %ul)\n",
+					  p->port_no,
+					  eth_hdr(skb)->h_source,
+					  bpdu.message_age, bpdu.max_age);
+			goto out;
+		}
+
+		br_received_config_bpdu(p, &bpdu);
+	} else if (buf[0] == BPDU_TYPE_TCN) {
+		br_received_tcn_bpdu(p);
+	}
+ out:
+	spin_unlock(&br->lock);
+ err:
+	kfree_skb(skb);
+}

net/bridge/br_stp_if.c

@@ -0,0 +1,312 @@
+/*
+ *	Spanning tree protocol; interface code
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+
+#include "br_private.h"
+#include "br_private_stp.h"
+
+
+/* Port id is composed of priority and port number.
+ * NB: some bits of priority are dropped to
+ *     make room for more ports.
+ */
+static inline port_id br_make_port_id(__u8 priority, __u16 port_no)
+{
+	return ((u16)priority << BR_PORT_BITS)
+		| (port_no & ((1<<BR_PORT_BITS)-1));
+}
+
+#define BR_MAX_PORT_PRIORITY ((u16)~0 >> BR_PORT_BITS)
+
+/* called under bridge lock */
+void br_init_port(struct net_bridge_port *p)
+{
+	p->port_id = br_make_port_id(p->priority, p->port_no);
+	br_become_designated_port(p);
+	p->state = BR_STATE_BLOCKING;
+	p->topology_change_ack = 0;
+	p->config_pending = 0;
+}
+
+/* called under bridge lock */
+void br_stp_enable_bridge(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	spin_lock_bh(&br->lock);
+	mod_timer(&br->hello_timer, jiffies + br->hello_time);
+	mod_timer(&br->gc_timer, jiffies + HZ/10);
+
+	br_config_bpdu_generation(br);
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (netif_running(p->dev) && netif_oper_up(p->dev))
+			br_stp_enable_port(p);
+
+	}
+	spin_unlock_bh(&br->lock);
+}
+
+/* NO locks held */
+void br_stp_disable_bridge(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	spin_lock_bh(&br->lock);
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state != BR_STATE_DISABLED)
+			br_stp_disable_port(p);
+
+	}
+
+	br->topology_change = 0;
+	br->topology_change_detected = 0;
+	spin_unlock_bh(&br->lock);
+
+	del_timer_sync(&br->hello_timer);
+	del_timer_sync(&br->topology_change_timer);
+	del_timer_sync(&br->tcn_timer);
+	del_timer_sync(&br->gc_timer);
+}
+
+/* called under bridge lock */
+void br_stp_enable_port(struct net_bridge_port *p)
+{
+	br_init_port(p);
+	br_port_state_selection(p->br);
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+}
+
+/* called under bridge lock */
+void br_stp_disable_port(struct net_bridge_port *p)
+{
+	struct net_bridge *br = p->br;
+	int wasroot;
+
+	wasroot = br_is_root_bridge(br);
+	br_become_designated_port(p);
+	p->state = BR_STATE_DISABLED;
+	p->topology_change_ack = 0;
+	p->config_pending = 0;
+
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	del_timer(&p->message_age_timer);
+	del_timer(&p->forward_delay_timer);
+	del_timer(&p->hold_timer);
+
+	br_fdb_delete_by_port(br, p, 0);
+	br_multicast_disable_port(p);
+
+	br_configuration_update(br);
+
+	br_port_state_selection(br);
+
+	if (br_is_root_bridge(br) && !wasroot)
+		br_become_root_bridge(br);
+}
+
+static void br_stp_start(struct net_bridge *br)
+{
+	int r;
+	char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
+	char *envp[] = { NULL };
+
+	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+
+	spin_lock_bh(&br->lock);
+
+	if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY)
+		__br_set_forward_delay(br, BR_MIN_FORWARD_DELAY);
+	else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
+		__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
+
+	if (r == 0) {
+		br->stp_enabled = BR_USER_STP;
+		br_debug(br, "userspace STP started\n");
+	} else {
+		br->stp_enabled = BR_KERNEL_STP;
+		br_debug(br, "using kernel STP\n");
+
+		/* To start timers on any ports left in blocking */
+		br_port_state_selection(br);
+	}
+
+	spin_unlock_bh(&br->lock);
+}
+
+static void br_stp_stop(struct net_bridge *br)
+{
+	int r;
+	char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL };
+	char *envp[] = { NULL };
+
+	if (br->stp_enabled == BR_USER_STP) {
+		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+		br_info(br, "userspace STP stopped, return code %d\n", r);
+
+		/* To start timers on any ports left in blocking */
+		spin_lock_bh(&br->lock);
+		br_port_state_selection(br);
+		spin_unlock_bh(&br->lock);
+	}
+
+	br->stp_enabled = BR_NO_STP;
+}
+
+void br_stp_set_enabled(struct net_bridge *br, unsigned long val)
+{
+	ASSERT_RTNL();
+
+	if (val) {
+		if (br->stp_enabled == BR_NO_STP)
+			br_stp_start(br);
+	} else {
+		if (br->stp_enabled != BR_NO_STP)
+			br_stp_stop(br);
+	}
+}
+
+/* called under bridge lock */
+void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr)
+{
+	/* should be aligned on 2 bytes for ether_addr_equal() */
+	unsigned short oldaddr_aligned[ETH_ALEN >> 1];
+	unsigned char *oldaddr = (unsigned char *)oldaddr_aligned;
+	struct net_bridge_port *p;
+	int wasroot;
+
+	wasroot = br_is_root_bridge(br);
+
+	memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN);
+	memcpy(br->bridge_id.addr, addr, ETH_ALEN);
+	memcpy(br->dev->dev_addr, addr, ETH_ALEN);
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (ether_addr_equal(p->designated_bridge.addr, oldaddr))
+			memcpy(p->designated_bridge.addr, addr, ETH_ALEN);
+
+		if (ether_addr_equal(p->designated_root.addr, oldaddr))
+			memcpy(p->designated_root.addr, addr, ETH_ALEN);
+	}
+
+	br_configuration_update(br);
+	br_port_state_selection(br);
+	if (br_is_root_bridge(br) && !wasroot)
+		br_become_root_bridge(br);
+}
+
+/* should be aligned on 2 bytes for ether_addr_equal() */
+static const unsigned short br_mac_zero_aligned[ETH_ALEN >> 1];
+
+/* called under bridge lock */
+bool br_stp_recalculate_bridge_id(struct net_bridge *br)
+{
+	const unsigned char *br_mac_zero =
+			(const unsigned char *)br_mac_zero_aligned;
+	const unsigned char *addr = br_mac_zero;
+	struct net_bridge_port *p;
+
+	/* user has chosen a value so keep it */
+	if (br->dev->addr_assign_type == NET_ADDR_SET)
+		return false;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (addr == br_mac_zero ||
+		    memcmp(p->dev->dev_addr, addr, ETH_ALEN) < 0)
+			addr = p->dev->dev_addr;
+
+	}
+
+	if (ether_addr_equal(br->bridge_id.addr, addr))
+		return false;	/* no change */
+
+	br_stp_change_bridge_id(br, addr);
+	return true;
+}
+
+/* called under bridge lock */
+void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
+{
+	struct net_bridge_port *p;
+	int wasroot;
+
+	wasroot = br_is_root_bridge(br);
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state != BR_STATE_DISABLED &&
+		    br_is_designated_port(p)) {
+			p->designated_bridge.prio[0] = (newprio >> 8) & 0xFF;
+			p->designated_bridge.prio[1] = newprio & 0xFF;
+		}
+
+	}
+
+	br->bridge_id.prio[0] = (newprio >> 8) & 0xFF;
+	br->bridge_id.prio[1] = newprio & 0xFF;
+	br_configuration_update(br);
+	br_port_state_selection(br);
+	if (br_is_root_bridge(br) && !wasroot)
+		br_become_root_bridge(br);
+}
+
+/* called under bridge lock */
+int br_stp_set_port_priority(struct net_bridge_port *p, unsigned long newprio)
+{
+	port_id new_port_id;
+
+	if (newprio > BR_MAX_PORT_PRIORITY)
+		return -ERANGE;
+
+	new_port_id = br_make_port_id(newprio, p->port_no);
+	if (br_is_designated_port(p))
+		p->designated_port = new_port_id;
+
+	p->port_id = new_port_id;
+	p->priority = newprio;
+	if (!memcmp(&p->br->bridge_id, &p->designated_bridge, 8) &&
+	    p->port_id < p->designated_port) {
+		br_become_designated_port(p);
+		br_port_state_selection(p->br);
+	}
+
+	return 0;
+}
+
+/* called under bridge lock */
+int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost)
+{
+	if (path_cost < BR_MIN_PATH_COST ||
+	    path_cost > BR_MAX_PATH_COST)
+		return -ERANGE;
+
+	p->flags |= BR_ADMIN_COST;
+	p->path_cost = path_cost;
+	br_configuration_update(p->br);
+	br_port_state_selection(p->br);
+	return 0;
+}
+
+ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id)
+{
+	return sprintf(buf, "%.2x%.2x.%.2x%.2x%.2x%.2x%.2x%.2x\n",
+	       id->prio[0], id->prio[1],
+	       id->addr[0], id->addr[1], id->addr[2],
+	       id->addr[3], id->addr[4], id->addr[5]);
+}

net/bridge/br_stp_timer.c

@@ -0,0 +1,174 @@
+/*
+ *	Spanning tree protocol; timer-related code
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/times.h>
+
+#include "br_private.h"
+#include "br_private_stp.h"
+
+/* called under bridge lock */
+static int br_is_designated_for_some_port(const struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (p->state != BR_STATE_DISABLED &&
+		    !memcmp(&p->designated_bridge, &br->bridge_id, 8))
+			return 1;
+	}
+
+	return 0;
+}
+
+static void br_hello_timer_expired(unsigned long arg)
+{
+	struct net_bridge *br = (struct net_bridge *)arg;
+
+	br_debug(br, "hello timer expired\n");
+	spin_lock(&br->lock);
+	if (br->dev->flags & IFF_UP) {
+		br_config_bpdu_generation(br);
+
+		mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time));
+	}
+	spin_unlock(&br->lock);
+}
+
+static void br_message_age_timer_expired(unsigned long arg)
+{
+	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+	struct net_bridge *br = p->br;
+	const bridge_id *id = &p->designated_bridge;
+	int was_root;
+
+	if (p->state == BR_STATE_DISABLED)
+		return;
+
+	br_info(br, "port %u(%s) neighbor %.2x%.2x.%pM lost\n",
+		(unsigned int) p->port_no, p->dev->name,
+		id->prio[0], id->prio[1], &id->addr);
+
+	/*
+	 * According to the spec, the message age timer cannot be
+	 * running when we are the root bridge. So..  this was_root
+	 * check is redundant. I'm leaving it in for now, though.
+	 */
+	spin_lock(&br->lock);
+	if (p->state == BR_STATE_DISABLED)
+		goto unlock;
+	was_root = br_is_root_bridge(br);
+
+	br_become_designated_port(p);
+	br_configuration_update(br);
+	br_port_state_selection(br);
+	if (br_is_root_bridge(br) && !was_root)
+		br_become_root_bridge(br);
+ unlock:
+	spin_unlock(&br->lock);
+}
+
+static void br_forward_delay_timer_expired(unsigned long arg)
+{
+	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+	struct net_bridge *br = p->br;
+
+	br_debug(br, "port %u(%s) forward delay timer\n",
+		 (unsigned int) p->port_no, p->dev->name);
+	spin_lock(&br->lock);
+	if (p->state == BR_STATE_LISTENING) {
+		p->state = BR_STATE_LEARNING;
+		mod_timer(&p->forward_delay_timer,
+			  jiffies + br->forward_delay);
+	} else if (p->state == BR_STATE_LEARNING) {
+		p->state = BR_STATE_FORWARDING;
+		if (br_is_designated_for_some_port(br))
+			br_topology_change_detection(br);
+		netif_carrier_on(br->dev);
+	}
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+	spin_unlock(&br->lock);
+}
+
+static void br_tcn_timer_expired(unsigned long arg)
+{
+	struct net_bridge *br = (struct net_bridge *) arg;
+
+	br_debug(br, "tcn timer expired\n");
+	spin_lock(&br->lock);
+	if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) {
+		br_transmit_tcn(br);
+
+		mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time);
+	}
+	spin_unlock(&br->lock);
+}
+
+static void br_topology_change_timer_expired(unsigned long arg)
+{
+	struct net_bridge *br = (struct net_bridge *) arg;
+
+	br_debug(br, "topo change timer expired\n");
+	spin_lock(&br->lock);
+	br->topology_change_detected = 0;
+	br->topology_change = 0;
+	spin_unlock(&br->lock);
+}
+
+static void br_hold_timer_expired(unsigned long arg)
+{
+	struct net_bridge_port *p = (struct net_bridge_port *) arg;
+
+	br_debug(p->br, "port %u(%s) hold timer expired\n",
+		 (unsigned int) p->port_no, p->dev->name);
+
+	spin_lock(&p->br->lock);
+	if (p->config_pending)
+		br_transmit_config(p);
+	spin_unlock(&p->br->lock);
+}
+
+void br_stp_timer_init(struct net_bridge *br)
+{
+	setup_timer(&br->hello_timer, br_hello_timer_expired,
+		      (unsigned long) br);
+
+	setup_timer(&br->tcn_timer, br_tcn_timer_expired,
+		      (unsigned long) br);
+
+	setup_timer(&br->topology_change_timer,
+		      br_topology_change_timer_expired,
+		      (unsigned long) br);
+
+	setup_timer(&br->gc_timer, br_fdb_cleanup, (unsigned long) br);
+}
+
+void br_stp_port_timer_init(struct net_bridge_port *p)
+{
+	setup_timer(&p->message_age_timer, br_message_age_timer_expired,
+		      (unsigned long) p);
+
+	setup_timer(&p->forward_delay_timer, br_forward_delay_timer_expired,
+		      (unsigned long) p);
+
+	setup_timer(&p->hold_timer, br_hold_timer_expired,
+		      (unsigned long) p);
+}
+
+/* Report ticks left (in USER_HZ) used for API */
+unsigned long br_timer_value(const struct timer_list *timer)
+{
+	return timer_pending(timer)
+		? jiffies_delta_to_clock_t(timer->expires - jiffies) : 0;
+}

net/bridge/br_sysfs_br.c

@@ -0,0 +1,853 @@
+/*
+ *	Sysfs attributes of bridge ports
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Stephen Hemminger		<shemminger@osdl.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/capability.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/rtnetlink.h>
+#include <linux/spinlock.h>
+#include <linux/times.h>
+
+#include "br_private.h"
+
+#define to_dev(obj)	container_of(obj, struct device, kobj)
+#define to_bridge(cd)	((struct net_bridge *)netdev_priv(to_net_dev(cd)))
+
+/*
+ * Common code for storing bridge parameters.
+ */
+static ssize_t store_bridge_parm(struct device *d,
+				 const char *buf, size_t len,
+				 int (*set)(struct net_bridge *, unsigned long))
+{
+	struct net_bridge *br = to_bridge(d);
+	char *endp;
+	unsigned long val;
+	int err;
+
+	if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (endp == buf)
+		return -EINVAL;
+
+	err = (*set)(br, val);
+	return err ? err : len;
+}
+
+
+static ssize_t show_forward_delay(struct device *d,
+				  struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay));
+}
+
+static ssize_t store_forward_delay(struct device *d,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_set_forward_delay);
+}
+static DEVICE_ATTR(forward_delay, S_IRUGO | S_IWUSR,
+		   show_forward_delay, store_forward_delay);
+
+static ssize_t show_hello_time(struct device *d, struct device_attribute *attr,
+			       char *buf)
+{
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(to_bridge(d)->hello_time));
+}
+
+static ssize_t store_hello_time(struct device *d,
+				struct device_attribute *attr, const char *buf,
+				size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_set_hello_time);
+}
+static DEVICE_ATTR(hello_time, S_IRUGO | S_IWUSR, show_hello_time,
+		   store_hello_time);
+
+static ssize_t show_max_age(struct device *d, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(to_bridge(d)->max_age));
+}
+
+static ssize_t store_max_age(struct device *d, struct device_attribute *attr,
+			     const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_set_max_age);
+}
+static DEVICE_ATTR(max_age, S_IRUGO | S_IWUSR, show_max_age, store_max_age);
+
+static ssize_t show_ageing_time(struct device *d,
+				struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->ageing_time));
+}
+
+static int set_ageing_time(struct net_bridge *br, unsigned long val)
+{
+	br->ageing_time = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_ageing_time(struct device *d,
+				 struct device_attribute *attr,
+				 const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_ageing_time);
+}
+static DEVICE_ATTR(ageing_time, S_IRUGO | S_IWUSR, show_ageing_time,
+		   store_ageing_time);
+
+static ssize_t show_stp_state(struct device *d,
+			      struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br->stp_enabled);
+}
+
+
+static ssize_t store_stp_state(struct device *d,
+			       struct device_attribute *attr, const char *buf,
+			       size_t len)
+{
+	struct net_bridge *br = to_bridge(d);
+	char *endp;
+	unsigned long val;
+
+	if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (endp == buf)
+		return -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+	br_stp_set_enabled(br, val);
+	rtnl_unlock();
+
+	return len;
+}
+static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state,
+		   store_stp_state);
+
+static ssize_t show_group_fwd_mask(struct device *d,
+			      struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%#x\n", br->group_fwd_mask);
+}
+
+
+static ssize_t store_group_fwd_mask(struct device *d,
+			       struct device_attribute *attr, const char *buf,
+			       size_t len)
+{
+	struct net_bridge *br = to_bridge(d);
+	char *endp;
+	unsigned long val;
+
+	if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (endp == buf)
+		return -EINVAL;
+
+	if (val & BR_GROUPFWD_RESTRICTED)
+		return -EINVAL;
+
+	br->group_fwd_mask = val;
+
+	return len;
+}
+static DEVICE_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask,
+		   store_group_fwd_mask);
+
+static ssize_t show_priority(struct device *d, struct device_attribute *attr,
+			     char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n",
+		       (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]);
+}
+
+static int set_priority(struct net_bridge *br, unsigned long val)
+{
+	br_stp_set_bridge_priority(br, (u16) val);
+	return 0;
+}
+
+static ssize_t store_priority(struct device *d, struct device_attribute *attr,
+			       const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_priority);
+}
+static DEVICE_ATTR(priority, S_IRUGO | S_IWUSR, show_priority, store_priority);
+
+static ssize_t show_root_id(struct device *d, struct device_attribute *attr,
+			    char *buf)
+{
+	return br_show_bridge_id(buf, &to_bridge(d)->designated_root);
+}
+static DEVICE_ATTR(root_id, S_IRUGO, show_root_id, NULL);
+
+static ssize_t show_bridge_id(struct device *d, struct device_attribute *attr,
+			      char *buf)
+{
+	return br_show_bridge_id(buf, &to_bridge(d)->bridge_id);
+}
+static DEVICE_ATTR(bridge_id, S_IRUGO, show_bridge_id, NULL);
+
+static ssize_t show_root_port(struct device *d, struct device_attribute *attr,
+			      char *buf)
+{
+	return sprintf(buf, "%d\n", to_bridge(d)->root_port);
+}
+static DEVICE_ATTR(root_port, S_IRUGO, show_root_port, NULL);
+
+static ssize_t show_root_path_cost(struct device *d,
+				   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", to_bridge(d)->root_path_cost);
+}
+static DEVICE_ATTR(root_path_cost, S_IRUGO, show_root_path_cost, NULL);
+
+static ssize_t show_topology_change(struct device *d,
+				    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", to_bridge(d)->topology_change);
+}
+static DEVICE_ATTR(topology_change, S_IRUGO, show_topology_change, NULL);
+
+static ssize_t show_topology_change_detected(struct device *d,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br->topology_change_detected);
+}
+static DEVICE_ATTR(topology_change_detected, S_IRUGO,
+		   show_topology_change_detected, NULL);
+
+static ssize_t show_hello_timer(struct device *d,
+				struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%ld\n", br_timer_value(&br->hello_timer));
+}
+static DEVICE_ATTR(hello_timer, S_IRUGO, show_hello_timer, NULL);
+
+static ssize_t show_tcn_timer(struct device *d, struct device_attribute *attr,
+			      char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%ld\n", br_timer_value(&br->tcn_timer));
+}
+static DEVICE_ATTR(tcn_timer, S_IRUGO, show_tcn_timer, NULL);
+
+static ssize_t show_topology_change_timer(struct device *d,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%ld\n", br_timer_value(&br->topology_change_timer));
+}
+static DEVICE_ATTR(topology_change_timer, S_IRUGO, show_topology_change_timer,
+		   NULL);
+
+static ssize_t show_gc_timer(struct device *d, struct device_attribute *attr,
+			     char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%ld\n", br_timer_value(&br->gc_timer));
+}
+static DEVICE_ATTR(gc_timer, S_IRUGO, show_gc_timer, NULL);
+
+static ssize_t show_group_addr(struct device *d,
+			       struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%x:%x:%x:%x:%x:%x\n",
+		       br->group_addr[0], br->group_addr[1],
+		       br->group_addr[2], br->group_addr[3],
+		       br->group_addr[4], br->group_addr[5]);
+}
+
+static ssize_t store_group_addr(struct device *d,
+				struct device_attribute *attr,
+				const char *buf, size_t len)
+{
+	struct net_bridge *br = to_bridge(d);
+	u8 new_addr[6];
+	int i;
+
+	if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+		   &new_addr[0], &new_addr[1], &new_addr[2],
+		   &new_addr[3], &new_addr[4], &new_addr[5]) != 6)
+		return -EINVAL;
+
+	if (!is_link_local_ether_addr(new_addr))
+		return -EINVAL;
+
+	if (new_addr[5] == 1 ||		/* 802.3x Pause address */
+	    new_addr[5] == 2 ||		/* 802.3ad Slow protocols */
+	    new_addr[5] == 3)		/* 802.1X PAE address */
+		return -EINVAL;
+
+	spin_lock_bh(&br->lock);
+	for (i = 0; i < 6; i++)
+		br->group_addr[i] = new_addr[i];
+	spin_unlock_bh(&br->lock);
+	return len;
+}
+
+static DEVICE_ATTR(group_addr, S_IRUGO | S_IWUSR,
+		   show_group_addr, store_group_addr);
+
+static ssize_t store_flush(struct device *d,
+			   struct device_attribute *attr,
+			   const char *buf, size_t len)
+{
+	struct net_bridge *br = to_bridge(d);
+
+	if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	br_fdb_flush(br);
+	return len;
+}
+static DEVICE_ATTR(flush, S_IWUSR, NULL, store_flush);
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+static ssize_t show_multicast_router(struct device *d,
+				     struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br->multicast_router);
+}
+
+static ssize_t store_multicast_router(struct device *d,
+				      struct device_attribute *attr,
+				      const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_set_router);
+}
+static DEVICE_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
+		   store_multicast_router);
+
+static ssize_t show_multicast_snooping(struct device *d,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", !br->multicast_disabled);
+}
+
+static ssize_t store_multicast_snooping(struct device *d,
+					struct device_attribute *attr,
+					const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_toggle);
+}
+static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR,
+		   show_multicast_snooping, store_multicast_snooping);
+
+static ssize_t show_multicast_querier(struct device *d,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br->multicast_querier);
+}
+
+static ssize_t store_multicast_querier(struct device *d,
+				       struct device_attribute *attr,
+				       const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_set_querier);
+}
+static DEVICE_ATTR(multicast_querier, S_IRUGO | S_IWUSR,
+		   show_multicast_querier, store_multicast_querier);
+
+static ssize_t show_hash_elasticity(struct device *d,
+				    struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->hash_elasticity);
+}
+
+static int set_elasticity(struct net_bridge *br, unsigned long val)
+{
+	br->hash_elasticity = val;
+	return 0;
+}
+
+static ssize_t store_hash_elasticity(struct device *d,
+				     struct device_attribute *attr,
+				     const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_elasticity);
+}
+static DEVICE_ATTR(hash_elasticity, S_IRUGO | S_IWUSR, show_hash_elasticity,
+		   store_hash_elasticity);
+
+static ssize_t show_hash_max(struct device *d, struct device_attribute *attr,
+			     char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->hash_max);
+}
+
+static ssize_t store_hash_max(struct device *d, struct device_attribute *attr,
+			      const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_multicast_set_hash_max);
+}
+static DEVICE_ATTR(hash_max, S_IRUGO | S_IWUSR, show_hash_max,
+		   store_hash_max);
+
+static ssize_t show_multicast_last_member_count(struct device *d,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->multicast_last_member_count);
+}
+
+static int set_last_member_count(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_last_member_count = val;
+	return 0;
+}
+
+static ssize_t store_multicast_last_member_count(struct device *d,
+						 struct device_attribute *attr,
+						 const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_last_member_count);
+}
+static DEVICE_ATTR(multicast_last_member_count, S_IRUGO | S_IWUSR,
+		   show_multicast_last_member_count,
+		   store_multicast_last_member_count);
+
+static ssize_t show_multicast_startup_query_count(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->multicast_startup_query_count);
+}
+
+static int set_startup_query_count(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_startup_query_count = val;
+	return 0;
+}
+
+static ssize_t store_multicast_startup_query_count(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_startup_query_count);
+}
+static DEVICE_ATTR(multicast_startup_query_count, S_IRUGO | S_IWUSR,
+		   show_multicast_startup_query_count,
+		   store_multicast_startup_query_count);
+
+static ssize_t show_multicast_last_member_interval(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(br->multicast_last_member_interval));
+}
+
+static int set_last_member_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_last_member_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_last_member_interval(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_last_member_interval);
+}
+static DEVICE_ATTR(multicast_last_member_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_last_member_interval,
+		   store_multicast_last_member_interval);
+
+static ssize_t show_multicast_membership_interval(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(br->multicast_membership_interval));
+}
+
+static int set_membership_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_membership_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_membership_interval(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_membership_interval);
+}
+static DEVICE_ATTR(multicast_membership_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_membership_interval,
+		   store_multicast_membership_interval);
+
+static ssize_t show_multicast_querier_interval(struct device *d,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(br->multicast_querier_interval));
+}
+
+static int set_querier_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_querier_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_querier_interval(struct device *d,
+						struct device_attribute *attr,
+						const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_querier_interval);
+}
+static DEVICE_ATTR(multicast_querier_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_querier_interval,
+		   store_multicast_querier_interval);
+
+static ssize_t show_multicast_query_interval(struct device *d,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%lu\n",
+		       jiffies_to_clock_t(br->multicast_query_interval));
+}
+
+static int set_query_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_query_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_query_interval(struct device *d,
+					      struct device_attribute *attr,
+					      const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_query_interval);
+}
+static DEVICE_ATTR(multicast_query_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_query_interval,
+		   store_multicast_query_interval);
+
+static ssize_t show_multicast_query_response_interval(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(
+		buf, "%lu\n",
+		jiffies_to_clock_t(br->multicast_query_response_interval));
+}
+
+static int set_query_response_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_query_response_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_query_response_interval(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_query_response_interval);
+}
+static DEVICE_ATTR(multicast_query_response_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_query_response_interval,
+		   store_multicast_query_response_interval);
+
+static ssize_t show_multicast_startup_query_interval(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(
+		buf, "%lu\n",
+		jiffies_to_clock_t(br->multicast_startup_query_interval));
+}
+
+static int set_startup_query_interval(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_startup_query_interval = clock_t_to_jiffies(val);
+	return 0;
+}
+
+static ssize_t store_multicast_startup_query_interval(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_startup_query_interval);
+}
+static DEVICE_ATTR(multicast_startup_query_interval, S_IRUGO | S_IWUSR,
+		   show_multicast_startup_query_interval,
+		   store_multicast_startup_query_interval);
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+static ssize_t show_nf_call_iptables(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->nf_call_iptables);
+}
+
+static int set_nf_call_iptables(struct net_bridge *br, unsigned long val)
+{
+	br->nf_call_iptables = val ? true : false;
+	return 0;
+}
+
+static ssize_t store_nf_call_iptables(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_nf_call_iptables);
+}
+static DEVICE_ATTR(nf_call_iptables, S_IRUGO | S_IWUSR,
+		   show_nf_call_iptables, store_nf_call_iptables);
+
+static ssize_t show_nf_call_ip6tables(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->nf_call_ip6tables);
+}
+
+static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val)
+{
+	br->nf_call_ip6tables = val ? true : false;
+	return 0;
+}
+
+static ssize_t store_nf_call_ip6tables(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_nf_call_ip6tables);
+}
+static DEVICE_ATTR(nf_call_ip6tables, S_IRUGO | S_IWUSR,
+		   show_nf_call_ip6tables, store_nf_call_ip6tables);
+
+static ssize_t show_nf_call_arptables(
+	struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%u\n", br->nf_call_arptables);
+}
+
+static int set_nf_call_arptables(struct net_bridge *br, unsigned long val)
+{
+	br->nf_call_arptables = val ? true : false;
+	return 0;
+}
+
+static ssize_t store_nf_call_arptables(
+	struct device *d, struct device_attribute *attr, const char *buf,
+	size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_nf_call_arptables);
+}
+static DEVICE_ATTR(nf_call_arptables, S_IRUGO | S_IWUSR,
+		   show_nf_call_arptables, store_nf_call_arptables);
+#endif
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+static ssize_t show_vlan_filtering(struct device *d,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%d\n", br->vlan_enabled);
+}
+
+static ssize_t store_vlan_filtering(struct device *d,
+				    struct device_attribute *attr,
+				    const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_vlan_filter_toggle);
+}
+static DEVICE_ATTR(vlan_filtering, S_IRUGO | S_IWUSR,
+		   show_vlan_filtering, store_vlan_filtering);
+#endif
+
+static struct attribute *bridge_attrs[] = {
+	&dev_attr_forward_delay.attr,
+	&dev_attr_hello_time.attr,
+	&dev_attr_max_age.attr,
+	&dev_attr_ageing_time.attr,
+	&dev_attr_stp_state.attr,
+	&dev_attr_group_fwd_mask.attr,
+	&dev_attr_priority.attr,
+	&dev_attr_bridge_id.attr,
+	&dev_attr_root_id.attr,
+	&dev_attr_root_path_cost.attr,
+	&dev_attr_root_port.attr,
+	&dev_attr_topology_change.attr,
+	&dev_attr_topology_change_detected.attr,
+	&dev_attr_hello_timer.attr,
+	&dev_attr_tcn_timer.attr,
+	&dev_attr_topology_change_timer.attr,
+	&dev_attr_gc_timer.attr,
+	&dev_attr_group_addr.attr,
+	&dev_attr_flush.attr,
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	&dev_attr_multicast_router.attr,
+	&dev_attr_multicast_snooping.attr,
+	&dev_attr_multicast_querier.attr,
+	&dev_attr_hash_elasticity.attr,
+	&dev_attr_hash_max.attr,
+	&dev_attr_multicast_last_member_count.attr,
+	&dev_attr_multicast_startup_query_count.attr,
+	&dev_attr_multicast_last_member_interval.attr,
+	&dev_attr_multicast_membership_interval.attr,
+	&dev_attr_multicast_querier_interval.attr,
+	&dev_attr_multicast_query_interval.attr,
+	&dev_attr_multicast_query_response_interval.attr,
+	&dev_attr_multicast_startup_query_interval.attr,
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+	&dev_attr_nf_call_iptables.attr,
+	&dev_attr_nf_call_ip6tables.attr,
+	&dev_attr_nf_call_arptables.attr,
+#endif
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	&dev_attr_vlan_filtering.attr,
+#endif
+	NULL
+};
+
+static struct attribute_group bridge_group = {
+	.name = SYSFS_BRIDGE_ATTR,
+	.attrs = bridge_attrs,
+};
+
+/*
+ * Export the forwarding information table as a binary file
+ * The records are struct __fdb_entry.
+ *
+ * Returns the number of bytes read.
+ */
+static ssize_t brforward_read(struct file *filp, struct kobject *kobj,
+			      struct bin_attribute *bin_attr,
+			      char *buf, loff_t off, size_t count)
+{
+	struct device *dev = to_dev(kobj);
+	struct net_bridge *br = to_bridge(dev);
+	int n;
+
+	/* must read whole records */
+	if (off % sizeof(struct __fdb_entry) != 0)
+		return -EINVAL;
+
+	n =  br_fdb_fillbuf(br, buf,
+			    count / sizeof(struct __fdb_entry),
+			    off / sizeof(struct __fdb_entry));
+
+	if (n > 0)
+		n *= sizeof(struct __fdb_entry);
+
+	return n;
+}
+
+static struct bin_attribute bridge_forward = {
+	.attr = { .name = SYSFS_BRIDGE_FDB,
+		  .mode = S_IRUGO, },
+	.read = brforward_read,
+};
+
+/*
+ * Add entries in sysfs onto the existing network class device
+ * for the bridge.
+ *   Adds a attribute group "bridge" containing tuning parameters.
+ *   Binary attribute containing the forward table
+ *   Sub directory to hold links to interfaces.
+ *
+ * Note: the ifobj exists only to be a subdirectory
+ *   to hold links.  The ifobj exists in same data structure
+ *   as it's parent the bridge so reference counting works.
+ */
+int br_sysfs_addbr(struct net_device *dev)
+{
+	struct kobject *brobj = &dev->dev.kobj;
+	struct net_bridge *br = netdev_priv(dev);
+	int err;
+
+	err = sysfs_create_group(brobj, &bridge_group);
+	if (err) {
+		pr_info("%s: can't create group %s/%s\n",
+			__func__, dev->name, bridge_group.name);
+		goto out1;
+	}
+
+	err = sysfs_create_bin_file(brobj, &bridge_forward);
+	if (err) {
+		pr_info("%s: can't create attribute file %s/%s\n",
+			__func__, dev->name, bridge_forward.attr.name);
+		goto out2;
+	}
+
+	br->ifobj = kobject_create_and_add(SYSFS_BRIDGE_PORT_SUBDIR, brobj);
+	if (!br->ifobj) {
+		pr_info("%s: can't add kobject (directory) %s/%s\n",
+			__func__, dev->name, SYSFS_BRIDGE_PORT_SUBDIR);
+		goto out3;
+	}
+	return 0;
+ out3:
+	sysfs_remove_bin_file(&dev->dev.kobj, &bridge_forward);
+ out2:
+	sysfs_remove_group(&dev->dev.kobj, &bridge_group);
+ out1:
+	return err;
+
+}
+
+void br_sysfs_delbr(struct net_device *dev)
+{
+	struct kobject *kobj = &dev->dev.kobj;
+	struct net_bridge *br = netdev_priv(dev);
+
+	kobject_put(br->ifobj);
+	sysfs_remove_bin_file(kobj, &bridge_forward);
+	sysfs_remove_group(kobj, &bridge_group);
+}

net/bridge/br_sysfs_if.c

@@ -0,0 +1,298 @@
+/*
+ *	Sysfs attributes of bridge ports
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Stephen Hemminger		<shemminger@osdl.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/capability.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/rtnetlink.h>
+#include <linux/spinlock.h>
+
+#include "br_private.h"
+
+struct brport_attribute {
+	struct attribute	attr;
+	ssize_t (*show)(struct net_bridge_port *, char *);
+	int (*store)(struct net_bridge_port *, unsigned long);
+};
+
+#define BRPORT_ATTR(_name,_mode,_show,_store)		        \
+const struct brport_attribute brport_attr_##_name = { 	        \
+	.attr = {.name = __stringify(_name), 			\
+		 .mode = _mode },				\
+	.show	= _show,					\
+	.store	= _store,					\
+};
+
+#define BRPORT_ATTR_FLAG(_name, _mask)				\
+static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \
+{								\
+	return sprintf(buf, "%d\n", !!(p->flags & _mask));	\
+}								\
+static int store_##_name(struct net_bridge_port *p, unsigned long v) \
+{								\
+	unsigned long flags = p->flags;				\
+	if (v)							\
+		flags |= _mask;					\
+	else							\
+		flags &= ~_mask;				\
+	if (flags != p->flags) {				\
+		p->flags = flags;				\
+		br_ifinfo_notify(RTM_NEWLINK, p);		\
+	}							\
+	return 0;						\
+}								\
+static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR,			\
+		   show_##_name, store_##_name)
+
+
+static ssize_t show_path_cost(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->path_cost);
+}
+
+static BRPORT_ATTR(path_cost, S_IRUGO | S_IWUSR,
+		   show_path_cost, br_stp_set_path_cost);
+
+static ssize_t show_priority(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->priority);
+}
+
+static BRPORT_ATTR(priority, S_IRUGO | S_IWUSR,
+			 show_priority, br_stp_set_port_priority);
+
+static ssize_t show_designated_root(struct net_bridge_port *p, char *buf)
+{
+	return br_show_bridge_id(buf, &p->designated_root);
+}
+static BRPORT_ATTR(designated_root, S_IRUGO, show_designated_root, NULL);
+
+static ssize_t show_designated_bridge(struct net_bridge_port *p, char *buf)
+{
+	return br_show_bridge_id(buf, &p->designated_bridge);
+}
+static BRPORT_ATTR(designated_bridge, S_IRUGO, show_designated_bridge, NULL);
+
+static ssize_t show_designated_port(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->designated_port);
+}
+static BRPORT_ATTR(designated_port, S_IRUGO, show_designated_port, NULL);
+
+static ssize_t show_designated_cost(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->designated_cost);
+}
+static BRPORT_ATTR(designated_cost, S_IRUGO, show_designated_cost, NULL);
+
+static ssize_t show_port_id(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "0x%x\n", p->port_id);
+}
+static BRPORT_ATTR(port_id, S_IRUGO, show_port_id, NULL);
+
+static ssize_t show_port_no(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "0x%x\n", p->port_no);
+}
+
+static BRPORT_ATTR(port_no, S_IRUGO, show_port_no, NULL);
+
+static ssize_t show_change_ack(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->topology_change_ack);
+}
+static BRPORT_ATTR(change_ack, S_IRUGO, show_change_ack, NULL);
+
+static ssize_t show_config_pending(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->config_pending);
+}
+static BRPORT_ATTR(config_pending, S_IRUGO, show_config_pending, NULL);
+
+static ssize_t show_port_state(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->state);
+}
+static BRPORT_ATTR(state, S_IRUGO, show_port_state, NULL);
+
+static ssize_t show_message_age_timer(struct net_bridge_port *p,
+					    char *buf)
+{
+	return sprintf(buf, "%ld\n", br_timer_value(&p->message_age_timer));
+}
+static BRPORT_ATTR(message_age_timer, S_IRUGO, show_message_age_timer, NULL);
+
+static ssize_t show_forward_delay_timer(struct net_bridge_port *p,
+					    char *buf)
+{
+	return sprintf(buf, "%ld\n", br_timer_value(&p->forward_delay_timer));
+}
+static BRPORT_ATTR(forward_delay_timer, S_IRUGO, show_forward_delay_timer, NULL);
+
+static ssize_t show_hold_timer(struct net_bridge_port *p,
+					    char *buf)
+{
+	return sprintf(buf, "%ld\n", br_timer_value(&p->hold_timer));
+}
+static BRPORT_ATTR(hold_timer, S_IRUGO, show_hold_timer, NULL);
+
+static int store_flush(struct net_bridge_port *p, unsigned long v)
+{
+	br_fdb_delete_by_port(p->br, p, 0); // Don't delete local entry
+	return 0;
+}
+static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
+
+BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
+BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
+BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
+{
+	return sprintf(buf, "%d\n", p->multicast_router);
+}
+
+static int store_multicast_router(struct net_bridge_port *p,
+				      unsigned long v)
+{
+	return br_multicast_set_port_router(p, v);
+}
+static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
+		   store_multicast_router);
+
+BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE);
+#endif
+
+static const struct brport_attribute *brport_attrs[] = {
+	&brport_attr_path_cost,
+	&brport_attr_priority,
+	&brport_attr_port_id,
+	&brport_attr_port_no,
+	&brport_attr_designated_root,
+	&brport_attr_designated_bridge,
+	&brport_attr_designated_port,
+	&brport_attr_designated_cost,
+	&brport_attr_state,
+	&brport_attr_change_ack,
+	&brport_attr_config_pending,
+	&brport_attr_message_age_timer,
+	&brport_attr_forward_delay_timer,
+	&brport_attr_hold_timer,
+	&brport_attr_flush,
+	&brport_attr_hairpin_mode,
+	&brport_attr_bpdu_guard,
+	&brport_attr_root_block,
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	&brport_attr_multicast_router,
+	&brport_attr_multicast_fast_leave,
+#endif
+	NULL
+};
+
+#define to_brport_attr(_at) container_of(_at, struct brport_attribute, attr)
+#define to_brport(obj)	container_of(obj, struct net_bridge_port, kobj)
+
+static ssize_t brport_show(struct kobject * kobj,
+			   struct attribute * attr, char * buf)
+{
+	struct brport_attribute * brport_attr = to_brport_attr(attr);
+	struct net_bridge_port * p = to_brport(kobj);
+
+	return brport_attr->show(p, buf);
+}
+
+static ssize_t brport_store(struct kobject * kobj,
+			    struct attribute * attr,
+			    const char * buf, size_t count)
+{
+	struct brport_attribute * brport_attr = to_brport_attr(attr);
+	struct net_bridge_port * p = to_brport(kobj);
+	ssize_t ret = -EINVAL;
+	char *endp;
+	unsigned long val;
+
+	if (!ns_capable(dev_net(p->dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (endp != buf) {
+		if (!rtnl_trylock())
+			return restart_syscall();
+		if (p->dev && p->br && brport_attr->store) {
+			spin_lock_bh(&p->br->lock);
+			ret = brport_attr->store(p, val);
+			spin_unlock_bh(&p->br->lock);
+			if (ret == 0)
+				ret = count;
+		}
+		rtnl_unlock();
+	}
+	return ret;
+}
+
+const struct sysfs_ops brport_sysfs_ops = {
+	.show = brport_show,
+	.store = brport_store,
+};
+
+/*
+ * Add sysfs entries to ethernet device added to a bridge.
+ * Creates a brport subdirectory with bridge attributes.
+ * Puts symlink in bridge's brif subdirectory
+ */
+int br_sysfs_addif(struct net_bridge_port *p)
+{
+	struct net_bridge *br = p->br;
+	const struct brport_attribute **a;
+	int err;
+
+	err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj,
+				SYSFS_BRIDGE_PORT_LINK);
+	if (err)
+		return err;
+
+	for (a = brport_attrs; *a; ++a) {
+		err = sysfs_create_file(&p->kobj, &((*a)->attr));
+		if (err)
+			return err;
+	}
+
+	strlcpy(p->sysfs_name, p->dev->name, IFNAMSIZ);
+	return sysfs_create_link(br->ifobj, &p->kobj, p->sysfs_name);
+}
+
+/* Rename bridge's brif symlink */
+int br_sysfs_renameif(struct net_bridge_port *p)
+{
+	struct net_bridge *br = p->br;
+	int err;
+
+	/* If a rename fails, the rollback will cause another
+	 * rename call with the existing name.
+	 */
+	if (!strncmp(p->sysfs_name, p->dev->name, IFNAMSIZ))
+		return 0;
+
+	err = sysfs_rename_link(br->ifobj, &p->kobj,
+				p->sysfs_name, p->dev->name);
+	if (err)
+		netdev_notice(br->dev, "unable to rename link %s to %s",
+			      p->sysfs_name, p->dev->name);
+	else
+		strlcpy(p->sysfs_name, p->dev->name, IFNAMSIZ);
+
+	return err;
+}

net/bridge/br_vlan.c

@@ -0,0 +1,419 @@
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+
+#include "br_private.h"
+
+static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid)
+{
+	if (v->pvid == vid)
+		return;
+
+	smp_wmb();
+	v->pvid = vid;
+}
+
+static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid)
+{
+	if (v->pvid != vid)
+		return;
+
+	smp_wmb();
+	v->pvid = 0;
+}
+
+static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags)
+{
+	if (flags & BRIDGE_VLAN_INFO_PVID)
+		__vlan_add_pvid(v, vid);
+
+	if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
+		set_bit(vid, v->untagged_bitmap);
+}
+
+static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
+{
+	const struct net_device_ops *ops;
+	struct net_bridge_port *p = NULL;
+	struct net_bridge *br;
+	struct net_device *dev;
+	int err;
+
+	if (test_bit(vid, v->vlan_bitmap)) {
+		__vlan_add_flags(v, vid, flags);
+		return 0;
+	}
+
+	if (vid) {
+		if (v->port_idx) {
+			p = v->parent.port;
+			br = p->br;
+			dev = p->dev;
+		} else {
+			br = v->parent.br;
+			dev = br->dev;
+		}
+		ops = dev->netdev_ops;
+
+		if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) {
+			/* Add VLAN to the device filter if it is supported.
+			 * Stricly speaking, this is not necessary now, since
+			 * devices are made promiscuous by the bridge, but if
+			 * that ever changes this code will allow tagged
+			 * traffic to enter the bridge.
+			 */
+			err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q),
+						       vid);
+			if (err)
+				return err;
+		}
+
+		err = br_fdb_insert(br, p, dev->dev_addr, vid);
+		if (err) {
+			br_err(br, "failed insert local address into bridge "
+			       "forwarding table\n");
+			goto out_filt;
+		}
+
+	}
+
+	set_bit(vid, v->vlan_bitmap);
+	v->num_vlans++;
+	__vlan_add_flags(v, vid, flags);
+
+	return 0;
+
+out_filt:
+	if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		ops->ndo_vlan_rx_kill_vid(dev, htons(ETH_P_8021Q), vid);
+	return err;
+}
+
+static int __vlan_del(struct net_port_vlans *v, u16 vid)
+{
+	if (!test_bit(vid, v->vlan_bitmap))
+		return -EINVAL;
+
+	__vlan_delete_pvid(v, vid);
+	clear_bit(vid, v->untagged_bitmap);
+
+	if (v->port_idx && vid) {
+		struct net_device *dev = v->parent.port->dev;
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			ops->ndo_vlan_rx_kill_vid(dev, htons(ETH_P_8021Q), vid);
+	}
+
+	clear_bit(vid, v->vlan_bitmap);
+	v->num_vlans--;
+	if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) {
+		if (v->port_idx)
+			rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+		else
+			rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+		kfree_rcu(v, rcu);
+	}
+	return 0;
+}
+
+static void __vlan_flush(struct net_port_vlans *v)
+{
+	smp_wmb();
+	v->pvid = 0;
+	bitmap_zero(v->vlan_bitmap, VLAN_N_VID);
+	if (v->port_idx)
+		rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+	else
+		rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+	kfree_rcu(v, rcu);
+}
+
+/* Strip the tag from the packet.  Will return skb with tci set 0.  */
+static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
+{
+	if (skb->protocol != htons(ETH_P_8021Q)) {
+		skb->vlan_tci = 0;
+		return skb;
+	}
+
+	skb->vlan_tci = 0;
+	skb = vlan_untag(skb);
+	if (skb)
+		skb->vlan_tci = 0;
+
+	return skb;
+}
+
+struct sk_buff *br_handle_vlan(struct net_bridge *br,
+			       const struct net_port_vlans *pv,
+			       struct sk_buff *skb)
+{
+	u16 vid;
+
+	if (!br->vlan_enabled)
+		goto out;
+
+	/* At this point, we know that the frame was filtered and contains
+	 * a valid vlan id.  If the vlan id is set in the untagged bitmap,
+	 * send untagged; otherwise, send taged.
+	 */
+	br_vlan_get_tag(skb, &vid);
+	if (test_bit(vid, pv->untagged_bitmap))
+		skb = br_vlan_untag(skb);
+	else {
+		/* Egress policy says "send tagged".  If output device
+		 * is the  bridge, we need to add the VLAN header
+		 * ourselves since we'll be going through the RX path.
+		 * Sending to ports puts the frame on the TX path and
+		 * we let dev_hard_start_xmit() add the header.
+		 */
+		if (skb->protocol != htons(ETH_P_8021Q) &&
+		    pv->port_idx == 0) {
+			/* vlan_put_tag expects skb->data to point to
+			 * mac header.
+			 */
+			skb_push(skb, ETH_HLEN);
+			skb = __vlan_put_tag(skb, skb->vlan_proto, skb->vlan_tci);
+			if (!skb)
+				goto out;
+			/* put skb->data back to where it was */
+			skb_pull(skb, ETH_HLEN);
+			skb->vlan_tci = 0;
+		}
+	}
+
+out:
+	return skb;
+}
+
+/* Called under RCU */
+bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
+			struct sk_buff *skb, u16 *vid)
+{
+	/* If VLAN filtering is disabled on the bridge, all packets are
+	 * permitted.
+	 */
+	if (!br->vlan_enabled)
+		return true;
+
+	/* If there are no vlan in the permitted list, all packets are
+	 * rejected.
+	 */
+	if (!v)
+		return false;
+
+	if (br_vlan_get_tag(skb, vid)) {
+		u16 pvid = br_get_pvid(v);
+
+		/* Frame did not have a tag.  See if pvid is set
+		 * on this port.  That tells us which vlan untagged
+		 * traffic belongs to.
+		 */
+		if (pvid == VLAN_N_VID)
+			return false;
+
+		/* PVID is set on this port.  Any untagged ingress
+		 * frame is considered to belong to this vlan.
+		 */
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid);
+		return true;
+	}
+
+	/* Frame had a valid vlan tag.  See if vlan is allowed */
+	if (test_bit(*vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
+/* Called under RCU. */
+bool br_allowed_egress(struct net_bridge *br,
+		       const struct net_port_vlans *v,
+		       const struct sk_buff *skb)
+{
+	u16 vid;
+
+	if (!br->vlan_enabled)
+		return true;
+
+	if (!v)
+		return false;
+
+	br_vlan_get_tag(skb, &vid);
+	if (test_bit(vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
+/* Must be protected by RTNL */
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+{
+	struct net_port_vlans *pv = NULL;
+	int err;
+
+	ASSERT_RTNL();
+
+	pv = rtnl_dereference(br->vlan_info);
+	if (pv)
+		return __vlan_add(pv, vid, flags);
+
+	/* Create port vlan infomration
+	 */
+	pv = kzalloc(sizeof(*pv), GFP_KERNEL);
+	if (!pv)
+		return -ENOMEM;
+
+	pv->parent.br = br;
+	err = __vlan_add(pv, vid, flags);
+	if (err)
+		goto out;
+
+	rcu_assign_pointer(br->vlan_info, pv);
+	return 0;
+out:
+	kfree(pv);
+	return err;
+}
+
+/* Must be protected by RTNL */
+int br_vlan_delete(struct net_bridge *br, u16 vid)
+{
+	struct net_port_vlans *pv;
+
+	ASSERT_RTNL();
+
+	pv = rtnl_dereference(br->vlan_info);
+	if (!pv)
+		return -EINVAL;
+
+	if (vid) {
+		/* If the VID !=0 remove fdb for this vid. VID 0 is special
+		 * in that it's the default and is always there in the fdb.
+		 */
+		spin_lock_bh(&br->hash_lock);
+		fdb_delete_by_addr(br, br->dev->dev_addr, vid);
+		spin_unlock_bh(&br->hash_lock);
+	}
+
+	__vlan_del(pv, vid);
+	return 0;
+}
+
+void br_vlan_flush(struct net_bridge *br)
+{
+	struct net_port_vlans *pv;
+
+	ASSERT_RTNL();
+	pv = rtnl_dereference(br->vlan_info);
+	if (!pv)
+		return;
+
+	__vlan_flush(pv);
+}
+
+int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
+{
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (br->vlan_enabled == val)
+		goto unlock;
+
+	br->vlan_enabled = val;
+
+unlock:
+	rtnl_unlock();
+	return 0;
+}
+
+/* Must be protected by RTNL */
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+{
+	struct net_port_vlans *pv = NULL;
+	int err;
+
+	ASSERT_RTNL();
+
+	pv = rtnl_dereference(port->vlan_info);
+	if (pv)
+		return __vlan_add(pv, vid, flags);
+
+	/* Create port vlan infomration
+	 */
+	pv = kzalloc(sizeof(*pv), GFP_KERNEL);
+	if (!pv) {
+		err = -ENOMEM;
+		goto clean_up;
+	}
+
+	pv->port_idx = port->port_no;
+	pv->parent.port = port;
+	err = __vlan_add(pv, vid, flags);
+	if (err)
+		goto clean_up;
+
+	rcu_assign_pointer(port->vlan_info, pv);
+	return 0;
+
+clean_up:
+	kfree(pv);
+	return err;
+}
+
+/* Must be protected by RTNL */
+int nbp_vlan_delete(struct net_bridge_port *port, u16 vid)
+{
+	struct net_port_vlans *pv;
+
+	ASSERT_RTNL();
+
+	pv = rtnl_dereference(port->vlan_info);
+	if (!pv)
+		return -EINVAL;
+
+	if (vid) {
+		/* If the VID !=0 remove fdb for this vid. VID 0 is special
+		 * in that it's the default and is always there in the fdb.
+		 */
+		spin_lock_bh(&port->br->hash_lock);
+		fdb_delete_by_addr(port->br, port->dev->dev_addr, vid);
+		spin_unlock_bh(&port->br->hash_lock);
+	}
+
+	return __vlan_del(pv, vid);
+}
+
+void nbp_vlan_flush(struct net_bridge_port *port)
+{
+	struct net_port_vlans *pv;
+
+	ASSERT_RTNL();
+
+	pv = rtnl_dereference(port->vlan_info);
+	if (!pv)
+		return;
+
+	__vlan_flush(pv);
+}
+
+bool nbp_vlan_find(struct net_bridge_port *port, u16 vid)
+{
+	struct net_port_vlans *pv;
+	bool found = false;
+
+	rcu_read_lock();
+	pv = rcu_dereference(port->vlan_info);
+
+	if (!pv)
+		goto out;
+
+	if (test_bit(vid, pv->vlan_bitmap))
+		found = true;
+
+out:
+	rcu_read_unlock();
+	return found;
+}

net/bridge/netfilter/Kconfig

@@ -0,0 +1,221 @@
+#
+# Bridge netfilter configuration
+#
+
+menuconfig BRIDGE_NF_EBTABLES
+	tristate "Ethernet Bridge tables (ebtables) support"
+	depends on BRIDGE && NETFILTER
+	select NETFILTER_XTABLES
+	help
+	  ebtables is a general, extensible frame/packet identification
+	  framework. Say 'Y' or 'M' here if you want to do Ethernet
+	  filtering/NAT/brouting on the Ethernet bridge.
+
+if BRIDGE_NF_EBTABLES
+
+#
+# tables
+#
+config BRIDGE_EBT_BROUTE
+	tristate "ebt: broute table support"
+	help
+	  The ebtables broute table is used to define rules that decide between
+	  bridging and routing frames, giving Linux the functionality of a
+	  brouter. See the man page for ebtables(8) and examples on the ebtables
+	  website.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_T_FILTER
+	tristate "ebt: filter table support"
+	help
+	  The ebtables filter table is used to define frame filtering rules at
+	  local input, forwarding and local output. See the man page for
+	  ebtables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_T_NAT
+	tristate "ebt: nat table support"
+	help
+	  The ebtables nat table is used to define rules that alter the MAC
+	  source address (MAC SNAT) or the MAC destination address (MAC DNAT).
+	  See the man page for ebtables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+#
+# matches
+#
+config BRIDGE_EBT_802_3
+	tristate "ebt: 802.3 filter support"
+	help
+	  This option adds matching support for 802.3 Ethernet frames.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_AMONG
+	tristate "ebt: among filter support"
+	help
+	  This option adds the among match, which allows matching the MAC source
+	  and/or destination address on a list of addresses. Optionally,
+	  MAC/IP address pairs can be matched, f.e. for anti-spoofing rules.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_ARP
+	tristate "ebt: ARP filter support"
+	help
+	  This option adds the ARP match, which allows ARP and RARP header field
+	  filtering.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_IP
+	tristate "ebt: IP filter support"
+	help
+	  This option adds the IP match, which allows basic IP header field
+	  filtering.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_IP6
+	tristate "ebt: IP6 filter support"
+	depends on BRIDGE_NF_EBTABLES && IPV6
+	help
+	  This option adds the IP6 match, which allows basic IPV6 header field
+	  filtering.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_LIMIT
+	tristate "ebt: limit match support"
+	help
+	  This option adds the limit match, which allows you to control
+	  the rate at which a rule can be matched. This match is the
+	  equivalent of the iptables limit match.
+
+	  If you want to compile it as a module, say M here and read
+	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
+
+config BRIDGE_EBT_MARK
+	tristate "ebt: mark filter support"
+	help
+	  This option adds the mark match, which allows matching frames based on
+	  the 'nfmark' value in the frame. This can be set by the mark target.
+	  This value is the same as the one used in the iptables mark match and
+	  target.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_PKTTYPE
+	tristate "ebt: packet type filter support"
+	help
+	  This option adds the packet type match, which allows matching on the
+	  type of packet based on its Ethernet "class" (as determined by
+	  the generic networking code): broadcast, multicast,
+	  for this host alone or for another host.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_STP
+	tristate "ebt: STP filter support"
+	help
+	  This option adds the Spanning Tree Protocol match, which
+	  allows STP header field filtering.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_VLAN
+	tristate "ebt: 802.1Q VLAN filter support"
+	help
+	  This option adds the 802.1Q vlan match, which allows the filtering of
+	  802.1Q vlan fields.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+#
+# targets
+#
+config BRIDGE_EBT_ARPREPLY
+	tristate "ebt: arp reply target support"
+	depends on BRIDGE_NF_EBTABLES && INET
+	help
+	  This option adds the arp reply target, which allows
+	  automatically sending arp replies to arp requests.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_DNAT
+	tristate "ebt: dnat target support"
+	help
+	  This option adds the MAC DNAT target, which allows altering the MAC
+	  destination address of frames.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_MARK_T
+	tristate "ebt: mark target support"
+	help
+	  This option adds the mark target, which allows marking frames by
+	  setting the 'nfmark' value in the frame.
+	  This value is the same as the one used in the iptables mark match and
+	  target.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_REDIRECT
+	tristate "ebt: redirect target support"
+	help
+	  This option adds the MAC redirect target, which allows altering the MAC
+	  destination address of a frame to that of the device it arrived on.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_SNAT
+	tristate "ebt: snat target support"
+	help
+	  This option adds the MAC SNAT target, which allows altering the MAC
+	  source address of frames.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+#
+# watchers
+#
+config BRIDGE_EBT_LOG
+	tristate "ebt: log support"
+	help
+	  This option adds the log watcher, that you can use in any rule
+	  in any ebtables table. It records info about the frame header
+	  to the syslog.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_ULOG
+	tristate "ebt: ulog support (OBSOLETE)"
+	help
+	  This option enables the old bridge-specific "ebt_ulog" implementation
+	  which has been obsoleted by the new "nfnetlink_log" code (see
+	  CONFIG_NETFILTER_NETLINK_LOG).
+
+	  This option adds the ulog watcher, that you can use in any rule
+	  in any ebtables table. The packet is passed to a userspace
+	  logging daemon using netlink multicast sockets. This differs
+	  from the log watcher in the sense that the complete packet is
+	  sent to userspace instead of a descriptive text and that
+	  netlink multicast sockets are used instead of the syslog.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config BRIDGE_EBT_NFLOG
+	tristate "ebt: nflog support"
+	help
+	  This option enables the nflog watcher, which allows to LOG
+	  messages through the netfilter logging API, which can use
+	  either the old LOG target, the old ULOG target or nfnetlink_log
+	  as backend.
+
+	  This option adds the nflog watcher, that you can use in any rule
+	  in any ebtables table.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+endif # BRIDGE_NF_EBTABLES

net/bridge/netfilter/Makefile

@@ -0,0 +1,34 @@
+#
+# Makefile for the netfilter modules for Link Layer filtering on a bridge.
+#
+
+obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
+
+# tables
+obj-$(CONFIG_BRIDGE_EBT_BROUTE) += ebtable_broute.o
+obj-$(CONFIG_BRIDGE_EBT_T_FILTER) += ebtable_filter.o
+obj-$(CONFIG_BRIDGE_EBT_T_NAT) += ebtable_nat.o
+
+#matches
+obj-$(CONFIG_BRIDGE_EBT_802_3) += ebt_802_3.o
+obj-$(CONFIG_BRIDGE_EBT_AMONG) += ebt_among.o
+obj-$(CONFIG_BRIDGE_EBT_ARP) += ebt_arp.o
+obj-$(CONFIG_BRIDGE_EBT_IP) += ebt_ip.o
+obj-$(CONFIG_BRIDGE_EBT_IP6) += ebt_ip6.o
+obj-$(CONFIG_BRIDGE_EBT_LIMIT) += ebt_limit.o
+obj-$(CONFIG_BRIDGE_EBT_MARK) += ebt_mark_m.o
+obj-$(CONFIG_BRIDGE_EBT_PKTTYPE) += ebt_pkttype.o
+obj-$(CONFIG_BRIDGE_EBT_STP) += ebt_stp.o
+obj-$(CONFIG_BRIDGE_EBT_VLAN) += ebt_vlan.o
+
+# targets
+obj-$(CONFIG_BRIDGE_EBT_ARPREPLY) += ebt_arpreply.o
+obj-$(CONFIG_BRIDGE_EBT_MARK_T) += ebt_mark.o
+obj-$(CONFIG_BRIDGE_EBT_DNAT) += ebt_dnat.o
+obj-$(CONFIG_BRIDGE_EBT_REDIRECT) += ebt_redirect.o
+obj-$(CONFIG_BRIDGE_EBT_SNAT) += ebt_snat.o
+
+# watchers
+obj-$(CONFIG_BRIDGE_EBT_LOG) += ebt_log.o
+obj-$(CONFIG_BRIDGE_EBT_ULOG) += ebt_ulog.o
+obj-$(CONFIG_BRIDGE_EBT_NFLOG) += ebt_nflog.o

net/bridge/netfilter/ebt_802_3.c

@@ -0,0 +1,72 @@
+/*
+ * 802_3
+ *
+ * Author:
+ * Chris Vitale csv@bluetail.com
+ *
+ * May 2003
+ *
+ */
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_802_3.h>
+
+static bool
+ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_802_3_info *info = par->matchinfo;
+	const struct ebt_802_3_hdr *hdr = ebt_802_3_hdr(skb);
+	__be16 type = hdr->llc.ui.ctrl & IS_UI ? hdr->llc.ui.type : hdr->llc.ni.type;
+
+	if (info->bitmask & EBT_802_3_SAP) {
+		if (FWINV(info->sap != hdr->llc.ui.ssap, EBT_802_3_SAP))
+			return false;
+		if (FWINV(info->sap != hdr->llc.ui.dsap, EBT_802_3_SAP))
+			return false;
+	}
+
+	if (info->bitmask & EBT_802_3_TYPE) {
+		if (!(hdr->llc.ui.dsap == CHECK_TYPE && hdr->llc.ui.ssap == CHECK_TYPE))
+			return false;
+		if (FWINV(info->type != type, EBT_802_3_TYPE))
+			return false;
+	}
+
+	return true;
+}
+
+static int ebt_802_3_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_802_3_info *info = par->matchinfo;
+
+	if (info->bitmask & ~EBT_802_3_MASK || info->invflags & ~EBT_802_3_MASK)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct xt_match ebt_802_3_mt_reg __read_mostly = {
+	.name		= "802_3",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_802_3_mt,
+	.checkentry	= ebt_802_3_mt_check,
+	.matchsize	= sizeof(struct ebt_802_3_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_802_3_init(void)
+{
+	return xt_register_match(&ebt_802_3_mt_reg);
+}
+
+static void __exit ebt_802_3_fini(void)
+{
+	xt_unregister_match(&ebt_802_3_mt_reg);
+}
+
+module_init(ebt_802_3_init);
+module_exit(ebt_802_3_fini);
+MODULE_DESCRIPTION("Ebtables: DSAP/SSAP field and SNAP type matching");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_among.c

@@ -0,0 +1,229 @@
+/*
+ *  ebt_among
+ *
+ *	Authors:
+ *	Grzegorz Borowiak <grzes@gnu.univ.gda.pl>
+ *
+ *  August, 2003
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/ip.h>
+#include <linux/if_arp.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_among.h>
+
+static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh,
+				      const char *mac, __be32 ip)
+{
+	/* You may be puzzled as to how this code works.
+	 * Some tricks were used, refer to
+	 * 	include/linux/netfilter_bridge/ebt_among.h
+	 * as there you can find a solution of this mystery.
+	 */
+	const struct ebt_mac_wormhash_tuple *p;
+	int start, limit, i;
+	uint32_t cmp[2] = { 0, 0 };
+	int key = ((const unsigned char *)mac)[5];
+
+	memcpy(((char *) cmp) + 2, mac, 6);
+	start = wh->table[key];
+	limit = wh->table[key + 1];
+	if (ip) {
+		for (i = start; i < limit; i++) {
+			p = &wh->pool[i];
+			if (cmp[1] == p->cmp[1] && cmp[0] == p->cmp[0])
+				if (p->ip == 0 || p->ip == ip)
+					return true;
+		}
+	} else {
+		for (i = start; i < limit; i++) {
+			p = &wh->pool[i];
+			if (cmp[1] == p->cmp[1] && cmp[0] == p->cmp[0])
+				if (p->ip == 0)
+					return true;
+		}
+	}
+	return false;
+}
+
+static int ebt_mac_wormhash_check_integrity(const struct ebt_mac_wormhash
+					    *wh)
+{
+	int i;
+
+	for (i = 0; i < 256; i++) {
+		if (wh->table[i] > wh->table[i + 1])
+			return -0x100 - i;
+		if (wh->table[i] < 0)
+			return -0x200 - i;
+		if (wh->table[i] > wh->poolsize)
+			return -0x300 - i;
+	}
+	if (wh->table[256] > wh->poolsize)
+		return -0xc00;
+	return 0;
+}
+
+static int get_ip_dst(const struct sk_buff *skb, __be32 *addr)
+{
+	if (eth_hdr(skb)->h_proto == htons(ETH_P_IP)) {
+		const struct iphdr *ih;
+		struct iphdr _iph;
+
+		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+		if (ih == NULL)
+			return -1;
+		*addr = ih->daddr;
+	} else if (eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) {
+		const struct arphdr *ah;
+		struct arphdr _arph;
+		const __be32 *bp;
+		__be32 buf;
+
+		ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+		if (ah == NULL ||
+		    ah->ar_pln != sizeof(__be32) ||
+		    ah->ar_hln != ETH_ALEN)
+			return -1;
+		bp = skb_header_pointer(skb, sizeof(struct arphdr) +
+					2 * ETH_ALEN + sizeof(__be32),
+					sizeof(__be32), &buf);
+		if (bp == NULL)
+			return -1;
+		*addr = *bp;
+	}
+	return 0;
+}
+
+static int get_ip_src(const struct sk_buff *skb, __be32 *addr)
+{
+	if (eth_hdr(skb)->h_proto == htons(ETH_P_IP)) {
+		const struct iphdr *ih;
+		struct iphdr _iph;
+
+		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+		if (ih == NULL)
+			return -1;
+		*addr = ih->saddr;
+	} else if (eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) {
+		const struct arphdr *ah;
+		struct arphdr _arph;
+		const __be32 *bp;
+		__be32 buf;
+
+		ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+		if (ah == NULL ||
+		    ah->ar_pln != sizeof(__be32) ||
+		    ah->ar_hln != ETH_ALEN)
+			return -1;
+		bp = skb_header_pointer(skb, sizeof(struct arphdr) +
+					ETH_ALEN, sizeof(__be32), &buf);
+		if (bp == NULL)
+			return -1;
+		*addr = *bp;
+	}
+	return 0;
+}
+
+static bool
+ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_among_info *info = par->matchinfo;
+	const char *dmac, *smac;
+	const struct ebt_mac_wormhash *wh_dst, *wh_src;
+	__be32 dip = 0, sip = 0;
+
+	wh_dst = ebt_among_wh_dst(info);
+	wh_src = ebt_among_wh_src(info);
+
+	if (wh_src) {
+		smac = eth_hdr(skb)->h_source;
+		if (get_ip_src(skb, &sip))
+			return false;
+		if (!(info->bitmask & EBT_AMONG_SRC_NEG)) {
+			/* we match only if it contains */
+			if (!ebt_mac_wormhash_contains(wh_src, smac, sip))
+				return false;
+		} else {
+			/* we match only if it DOES NOT contain */
+			if (ebt_mac_wormhash_contains(wh_src, smac, sip))
+				return false;
+		}
+	}
+
+	if (wh_dst) {
+		dmac = eth_hdr(skb)->h_dest;
+		if (get_ip_dst(skb, &dip))
+			return false;
+		if (!(info->bitmask & EBT_AMONG_DST_NEG)) {
+			/* we match only if it contains */
+			if (!ebt_mac_wormhash_contains(wh_dst, dmac, dip))
+				return false;
+		} else {
+			/* we match only if it DOES NOT contain */
+			if (ebt_mac_wormhash_contains(wh_dst, dmac, dip))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static int ebt_among_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_among_info *info = par->matchinfo;
+	const struct ebt_entry_match *em =
+		container_of(par->matchinfo, const struct ebt_entry_match, data);
+	int expected_length = sizeof(struct ebt_among_info);
+	const struct ebt_mac_wormhash *wh_dst, *wh_src;
+	int err;
+
+	wh_dst = ebt_among_wh_dst(info);
+	wh_src = ebt_among_wh_src(info);
+	expected_length += ebt_mac_wormhash_size(wh_dst);
+	expected_length += ebt_mac_wormhash_size(wh_src);
+
+	if (em->match_size != EBT_ALIGN(expected_length)) {
+		pr_info("wrong size: %d against expected %d, rounded to %Zd\n",
+			em->match_size, expected_length,
+			EBT_ALIGN(expected_length));
+		return -EINVAL;
+	}
+	if (wh_dst && (err = ebt_mac_wormhash_check_integrity(wh_dst))) {
+		pr_info("dst integrity fail: %x\n", -err);
+		return -EINVAL;
+	}
+	if (wh_src && (err = ebt_mac_wormhash_check_integrity(wh_src))) {
+		pr_info("src integrity fail: %x\n", -err);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match ebt_among_mt_reg __read_mostly = {
+	.name		= "among",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_among_mt,
+	.checkentry	= ebt_among_mt_check,
+	.matchsize	= -1, /* special case */
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_among_init(void)
+{
+	return xt_register_match(&ebt_among_mt_reg);
+}
+
+static void __exit ebt_among_fini(void)
+{
+	xt_unregister_match(&ebt_among_mt_reg);
+}
+
+module_init(ebt_among_init);
+module_exit(ebt_among_fini);
+MODULE_DESCRIPTION("Ebtables: Combined MAC/IP address list matching");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_arp.c

@@ -0,0 +1,140 @@
+/*
+ *  ebt_arp
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *	Tim Gardner <timg@tpi.com>
+ *
+ *  April, 2002
+ *
+ */
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_arp.h>
+
+static bool
+ebt_arp_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_arp_info *info = par->matchinfo;
+	const struct arphdr *ah;
+	struct arphdr _arph;
+
+	ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+	if (ah == NULL)
+		return false;
+	if (info->bitmask & EBT_ARP_OPCODE && FWINV(info->opcode !=
+	   ah->ar_op, EBT_ARP_OPCODE))
+		return false;
+	if (info->bitmask & EBT_ARP_HTYPE && FWINV(info->htype !=
+	   ah->ar_hrd, EBT_ARP_HTYPE))
+		return false;
+	if (info->bitmask & EBT_ARP_PTYPE && FWINV(info->ptype !=
+	   ah->ar_pro, EBT_ARP_PTYPE))
+		return false;
+
+	if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP | EBT_ARP_GRAT)) {
+		const __be32 *sap, *dap;
+		__be32 saddr, daddr;
+
+		if (ah->ar_pln != sizeof(__be32) || ah->ar_pro != htons(ETH_P_IP))
+			return false;
+		sap = skb_header_pointer(skb, sizeof(struct arphdr) +
+					ah->ar_hln, sizeof(saddr),
+					&saddr);
+		if (sap == NULL)
+			return false;
+		dap = skb_header_pointer(skb, sizeof(struct arphdr) +
+					2*ah->ar_hln+sizeof(saddr),
+					sizeof(daddr), &daddr);
+		if (dap == NULL)
+			return false;
+		if (info->bitmask & EBT_ARP_SRC_IP &&
+		    FWINV(info->saddr != (*sap & info->smsk), EBT_ARP_SRC_IP))
+			return false;
+		if (info->bitmask & EBT_ARP_DST_IP &&
+		    FWINV(info->daddr != (*dap & info->dmsk), EBT_ARP_DST_IP))
+			return false;
+		if (info->bitmask & EBT_ARP_GRAT &&
+		    FWINV(*dap != *sap, EBT_ARP_GRAT))
+			return false;
+	}
+
+	if (info->bitmask & (EBT_ARP_SRC_MAC | EBT_ARP_DST_MAC)) {
+		const unsigned char *mp;
+		unsigned char _mac[ETH_ALEN];
+		uint8_t verdict, i;
+
+		if (ah->ar_hln != ETH_ALEN || ah->ar_hrd != htons(ARPHRD_ETHER))
+			return false;
+		if (info->bitmask & EBT_ARP_SRC_MAC) {
+			mp = skb_header_pointer(skb, sizeof(struct arphdr),
+						sizeof(_mac), &_mac);
+			if (mp == NULL)
+				return false;
+			verdict = 0;
+			for (i = 0; i < 6; i++)
+				verdict |= (mp[i] ^ info->smaddr[i]) &
+				       info->smmsk[i];
+			if (FWINV(verdict != 0, EBT_ARP_SRC_MAC))
+				return false;
+		}
+
+		if (info->bitmask & EBT_ARP_DST_MAC) {
+			mp = skb_header_pointer(skb, sizeof(struct arphdr) +
+						ah->ar_hln + ah->ar_pln,
+						sizeof(_mac), &_mac);
+			if (mp == NULL)
+				return false;
+			verdict = 0;
+			for (i = 0; i < 6; i++)
+				verdict |= (mp[i] ^ info->dmaddr[i]) &
+					info->dmmsk[i];
+			if (FWINV(verdict != 0, EBT_ARP_DST_MAC))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static int ebt_arp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_arp_info *info = par->matchinfo;
+	const struct ebt_entry *e = par->entryinfo;
+
+	if ((e->ethproto != htons(ETH_P_ARP) &&
+	   e->ethproto != htons(ETH_P_RARP)) ||
+	   e->invflags & EBT_IPROTO)
+		return -EINVAL;
+	if (info->bitmask & ~EBT_ARP_MASK || info->invflags & ~EBT_ARP_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_match ebt_arp_mt_reg __read_mostly = {
+	.name		= "arp",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_arp_mt,
+	.checkentry	= ebt_arp_mt_check,
+	.matchsize	= sizeof(struct ebt_arp_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_arp_init(void)
+{
+	return xt_register_match(&ebt_arp_mt_reg);
+}
+
+static void __exit ebt_arp_fini(void)
+{
+	xt_unregister_match(&ebt_arp_mt_reg);
+}
+
+module_init(ebt_arp_init);
+module_exit(ebt_arp_fini);
+MODULE_DESCRIPTION("Ebtables: ARP protocol packet match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_arpreply.c

@@ -0,0 +1,98 @@
+/*
+ *  ebt_arpreply
+ *
+ *	Authors:
+ *	Grzegorz Borowiak <grzes@gnu.univ.gda.pl>
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  August, 2003
+ *
+ */
+#include <linux/if_arp.h>
+#include <net/arp.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_arpreply.h>
+
+static unsigned int
+ebt_arpreply_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_arpreply_info *info = par->targinfo;
+	const __be32 *siptr, *diptr;
+	__be32 _sip, _dip;
+	const struct arphdr *ap;
+	struct arphdr _ah;
+	const unsigned char *shp;
+	unsigned char _sha[ETH_ALEN];
+
+	ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah);
+	if (ap == NULL)
+		return EBT_DROP;
+
+	if (ap->ar_op != htons(ARPOP_REQUEST) ||
+	    ap->ar_hln != ETH_ALEN ||
+	    ap->ar_pro != htons(ETH_P_IP) ||
+	    ap->ar_pln != 4)
+		return EBT_CONTINUE;
+
+	shp = skb_header_pointer(skb, sizeof(_ah), ETH_ALEN, &_sha);
+	if (shp == NULL)
+		return EBT_DROP;
+
+	siptr = skb_header_pointer(skb, sizeof(_ah) + ETH_ALEN,
+				   sizeof(_sip), &_sip);
+	if (siptr == NULL)
+		return EBT_DROP;
+
+	diptr = skb_header_pointer(skb,
+				   sizeof(_ah) + 2 * ETH_ALEN + sizeof(_sip),
+				   sizeof(_dip), &_dip);
+	if (diptr == NULL)
+		return EBT_DROP;
+
+	arp_send(ARPOP_REPLY, ETH_P_ARP, *siptr, (struct net_device *)par->in,
+		 *diptr, shp, info->mac, shp);
+
+	return info->target;
+}
+
+static int ebt_arpreply_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct ebt_arpreply_info *info = par->targinfo;
+	const struct ebt_entry *e = par->entryinfo;
+
+	if (BASE_CHAIN && info->target == EBT_RETURN)
+		return -EINVAL;
+	if (e->ethproto != htons(ETH_P_ARP) ||
+	    e->invflags & EBT_IPROTO)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target ebt_arpreply_tg_reg __read_mostly = {
+	.name		= "arpreply",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.table		= "nat",
+	.hooks		= (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING),
+	.target		= ebt_arpreply_tg,
+	.checkentry	= ebt_arpreply_tg_check,
+	.targetsize	= sizeof(struct ebt_arpreply_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_arpreply_init(void)
+{
+	return xt_register_target(&ebt_arpreply_tg_reg);
+}
+
+static void __exit ebt_arpreply_fini(void)
+{
+	xt_unregister_target(&ebt_arpreply_tg_reg);
+}
+
+module_init(ebt_arpreply_init);
+module_exit(ebt_arpreply_fini);
+MODULE_DESCRIPTION("Ebtables: ARP reply target");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_dnat.c

@@ -0,0 +1,74 @@
+/*
+ *  ebt_dnat
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  June, 2002
+ *
+ */
+#include <linux/module.h>
+#include <net/sock.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_nat.h>
+
+static unsigned int
+ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_nat_info *info = par->targinfo;
+
+	if (!skb_make_writable(skb, 0))
+		return EBT_DROP;
+
+	memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN);
+	return info->target;
+}
+
+static int ebt_dnat_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct ebt_nat_info *info = par->targinfo;
+	unsigned int hook_mask;
+
+	if (BASE_CHAIN && info->target == EBT_RETURN)
+		return -EINVAL;
+
+	hook_mask = par->hook_mask & ~(1 << NF_BR_NUMHOOKS);
+	if ((strcmp(par->table, "nat") != 0 ||
+	    (hook_mask & ~((1 << NF_BR_PRE_ROUTING) |
+	    (1 << NF_BR_LOCAL_OUT)))) &&
+	    (strcmp(par->table, "broute") != 0 ||
+	    hook_mask & ~(1 << NF_BR_BROUTING)))
+		return -EINVAL;
+	if (INVALID_TARGET)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target ebt_dnat_tg_reg __read_mostly = {
+	.name		= "dnat",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.hooks		= (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING) |
+			  (1 << NF_BR_LOCAL_OUT) | (1 << NF_BR_BROUTING),
+	.target		= ebt_dnat_tg,
+	.checkentry	= ebt_dnat_tg_check,
+	.targetsize	= sizeof(struct ebt_nat_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_dnat_init(void)
+{
+	return xt_register_target(&ebt_dnat_tg_reg);
+}
+
+static void __exit ebt_dnat_fini(void)
+{
+	xt_unregister_target(&ebt_dnat_tg_reg);
+}
+
+module_init(ebt_dnat_init);
+module_exit(ebt_dnat_fini);
+MODULE_DESCRIPTION("Ebtables: Destination MAC address translation");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_ip.c

@@ -0,0 +1,130 @@
+/*
+ *  ebt_ip
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2002
+ *
+ *  Changes:
+ *    added ip-sport and ip-dport
+ *    Innominate Security Technologies AG <mhopf@innominate.com>
+ *    September, 2002
+ */
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_ip.h>
+
+struct tcpudphdr {
+	__be16 src;
+	__be16 dst;
+};
+
+static bool
+ebt_ip_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_ip_info *info = par->matchinfo;
+	const struct iphdr *ih;
+	struct iphdr _iph;
+	const struct tcpudphdr *pptr;
+	struct tcpudphdr _ports;
+
+	ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+	if (ih == NULL)
+		return false;
+	if (info->bitmask & EBT_IP_TOS &&
+	   FWINV(info->tos != ih->tos, EBT_IP_TOS))
+		return false;
+	if (info->bitmask & EBT_IP_SOURCE &&
+	   FWINV((ih->saddr & info->smsk) !=
+	   info->saddr, EBT_IP_SOURCE))
+		return false;
+	if ((info->bitmask & EBT_IP_DEST) &&
+	   FWINV((ih->daddr & info->dmsk) !=
+	   info->daddr, EBT_IP_DEST))
+		return false;
+	if (info->bitmask & EBT_IP_PROTO) {
+		if (FWINV(info->protocol != ih->protocol, EBT_IP_PROTO))
+			return false;
+		if (!(info->bitmask & EBT_IP_DPORT) &&
+		    !(info->bitmask & EBT_IP_SPORT))
+			return true;
+		if (ntohs(ih->frag_off) & IP_OFFSET)
+			return false;
+		pptr = skb_header_pointer(skb, ih->ihl*4,
+					  sizeof(_ports), &_ports);
+		if (pptr == NULL)
+			return false;
+		if (info->bitmask & EBT_IP_DPORT) {
+			u32 dst = ntohs(pptr->dst);
+			if (FWINV(dst < info->dport[0] ||
+				  dst > info->dport[1],
+				  EBT_IP_DPORT))
+			return false;
+		}
+		if (info->bitmask & EBT_IP_SPORT) {
+			u32 src = ntohs(pptr->src);
+			if (FWINV(src < info->sport[0] ||
+				  src > info->sport[1],
+				  EBT_IP_SPORT))
+			return false;
+		}
+	}
+	return true;
+}
+
+static int ebt_ip_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_ip_info *info = par->matchinfo;
+	const struct ebt_entry *e = par->entryinfo;
+
+	if (e->ethproto != htons(ETH_P_IP) ||
+	   e->invflags & EBT_IPROTO)
+		return -EINVAL;
+	if (info->bitmask & ~EBT_IP_MASK || info->invflags & ~EBT_IP_MASK)
+		return -EINVAL;
+	if (info->bitmask & (EBT_IP_DPORT | EBT_IP_SPORT)) {
+		if (info->invflags & EBT_IP_PROTO)
+			return -EINVAL;
+		if (info->protocol != IPPROTO_TCP &&
+		    info->protocol != IPPROTO_UDP &&
+		    info->protocol != IPPROTO_UDPLITE &&
+		    info->protocol != IPPROTO_SCTP &&
+		    info->protocol != IPPROTO_DCCP)
+			 return -EINVAL;
+	}
+	if (info->bitmask & EBT_IP_DPORT && info->dport[0] > info->dport[1])
+		return -EINVAL;
+	if (info->bitmask & EBT_IP_SPORT && info->sport[0] > info->sport[1])
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_match ebt_ip_mt_reg __read_mostly = {
+	.name		= "ip",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_ip_mt,
+	.checkentry	= ebt_ip_mt_check,
+	.matchsize	= sizeof(struct ebt_ip_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_ip_init(void)
+{
+	return xt_register_match(&ebt_ip_mt_reg);
+}
+
+static void __exit ebt_ip_fini(void)
+{
+	xt_unregister_match(&ebt_ip_mt_reg);
+}
+
+module_init(ebt_ip_init);
+module_exit(ebt_ip_fini);
+MODULE_DESCRIPTION("Ebtables: IPv4 protocol packet match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_ip6.c

@@ -0,0 +1,156 @@
+/*
+ *  ebt_ip6
+ *
+ *	Authors:
+ *	Manohar Castelino <manohar.r.castelino@intel.com>
+ *	Kuo-Lang Tseng <kuo-lang.tseng@intel.com>
+ *	Jan Engelhardt <jengelh@medozas.de>
+ *
+ * Summary:
+ * This is just a modification of the IPv4 code written by
+ * Bart De Schuymer <bdschuym@pandora.be>
+ * with the changes required to support IPv6
+ *
+ *  Jan, 2008
+ */
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <linux/in.h>
+#include <linux/module.h>
+#include <net/dsfield.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_ip6.h>
+
+union pkthdr {
+	struct {
+		__be16 src;
+		__be16 dst;
+	} tcpudphdr;
+	struct {
+		u8 type;
+		u8 code;
+	} icmphdr;
+};
+
+static bool
+ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_ip6_info *info = par->matchinfo;
+	const struct ipv6hdr *ih6;
+	struct ipv6hdr _ip6h;
+	const union pkthdr *pptr;
+	union pkthdr _pkthdr;
+
+	ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
+	if (ih6 == NULL)
+		return false;
+	if (info->bitmask & EBT_IP6_TCLASS &&
+	   FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
+		return false;
+	if (FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
+				       &info->saddr), EBT_IP6_SOURCE) ||
+	    FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
+				       &info->daddr), EBT_IP6_DEST))
+		return false;
+	if (info->bitmask & EBT_IP6_PROTO) {
+		uint8_t nexthdr = ih6->nexthdr;
+		__be16 frag_off;
+		int offset_ph;
+
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
+		if (offset_ph == -1)
+			return false;
+		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
+			return false;
+		if (!(info->bitmask & ( EBT_IP6_DPORT |
+					EBT_IP6_SPORT | EBT_IP6_ICMP6)))
+			return true;
+
+		/* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */
+		pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr),
+					  &_pkthdr);
+		if (pptr == NULL)
+			return false;
+		if (info->bitmask & EBT_IP6_DPORT) {
+			u16 dst = ntohs(pptr->tcpudphdr.dst);
+			if (FWINV(dst < info->dport[0] ||
+				  dst > info->dport[1], EBT_IP6_DPORT))
+				return false;
+		}
+		if (info->bitmask & EBT_IP6_SPORT) {
+			u16 src = ntohs(pptr->tcpudphdr.src);
+			if (FWINV(src < info->sport[0] ||
+				  src > info->sport[1], EBT_IP6_SPORT))
+			return false;
+		}
+		if ((info->bitmask & EBT_IP6_ICMP6) &&
+		     FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
+			   pptr->icmphdr.type > info->icmpv6_type[1] ||
+			   pptr->icmphdr.code < info->icmpv6_code[0] ||
+			   pptr->icmphdr.code > info->icmpv6_code[1],
+							EBT_IP6_ICMP6))
+			return false;
+	}
+	return true;
+}
+
+static int ebt_ip6_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_entry *e = par->entryinfo;
+	struct ebt_ip6_info *info = par->matchinfo;
+
+	if (e->ethproto != htons(ETH_P_IPV6) || e->invflags & EBT_IPROTO)
+		return -EINVAL;
+	if (info->bitmask & ~EBT_IP6_MASK || info->invflags & ~EBT_IP6_MASK)
+		return -EINVAL;
+	if (info->bitmask & (EBT_IP6_DPORT | EBT_IP6_SPORT)) {
+		if (info->invflags & EBT_IP6_PROTO)
+			return -EINVAL;
+		if (info->protocol != IPPROTO_TCP &&
+		    info->protocol != IPPROTO_UDP &&
+		    info->protocol != IPPROTO_UDPLITE &&
+		    info->protocol != IPPROTO_SCTP &&
+		    info->protocol != IPPROTO_DCCP)
+			return -EINVAL;
+	}
+	if (info->bitmask & EBT_IP6_DPORT && info->dport[0] > info->dport[1])
+		return -EINVAL;
+	if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1])
+		return -EINVAL;
+	if (info->bitmask & EBT_IP6_ICMP6) {
+		if ((info->invflags & EBT_IP6_PROTO) ||
+		     info->protocol != IPPROTO_ICMPV6)
+			return -EINVAL;
+		if (info->icmpv6_type[0] > info->icmpv6_type[1] ||
+		    info->icmpv6_code[0] > info->icmpv6_code[1])
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match ebt_ip6_mt_reg __read_mostly = {
+	.name		= "ip6",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_ip6_mt,
+	.checkentry	= ebt_ip6_mt_check,
+	.matchsize	= sizeof(struct ebt_ip6_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_ip6_init(void)
+{
+	return xt_register_match(&ebt_ip6_mt_reg);
+}
+
+static void __exit ebt_ip6_fini(void)
+{
+	xt_unregister_match(&ebt_ip6_mt_reg);
+}
+
+module_init(ebt_ip6_init);
+module_exit(ebt_ip6_fini);
+MODULE_DESCRIPTION("Ebtables: IPv6 protocol packet match");
+MODULE_AUTHOR("Kuo-Lang Tseng <kuo-lang.tseng@intel.com>");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_limit.c

@@ -0,0 +1,127 @@
+/*
+ *  ebt_limit
+ *
+ *	Authors:
+ *	Tom Marshall <tommy@home.tig-grr.com>
+ *
+ *	Mostly copied from netfilter's ipt_limit.c, see that file for
+ *	more explanation
+ *
+ *  September, 2003
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_limit.h>
+
+static DEFINE_SPINLOCK(limit_lock);
+
+#define MAX_CPJ (0xFFFFFFFF / (HZ*60*60*24))
+
+#define _POW2_BELOW2(x) ((x)|((x)>>1))
+#define _POW2_BELOW4(x) (_POW2_BELOW2(x)|_POW2_BELOW2((x)>>2))
+#define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4))
+#define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8))
+#define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16))
+#define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1)
+
+#define CREDITS_PER_JIFFY POW2_BELOW32(MAX_CPJ)
+
+static bool
+ebt_limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ebt_limit_info *info = (void *)par->matchinfo;
+	unsigned long now = jiffies;
+
+	spin_lock_bh(&limit_lock);
+	info->credit += (now - xchg(&info->prev, now)) * CREDITS_PER_JIFFY;
+	if (info->credit > info->credit_cap)
+		info->credit = info->credit_cap;
+
+	if (info->credit >= info->cost) {
+		/* We're not limited. */
+		info->credit -= info->cost;
+		spin_unlock_bh(&limit_lock);
+		return true;
+	}
+
+	spin_unlock_bh(&limit_lock);
+	return false;
+}
+
+/* Precision saver. */
+static u_int32_t
+user2credits(u_int32_t user)
+{
+	/* If multiplying would overflow... */
+	if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY))
+		/* Divide first. */
+		return (user / EBT_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY;
+
+	return (user * HZ * CREDITS_PER_JIFFY) / EBT_LIMIT_SCALE;
+}
+
+static int ebt_limit_mt_check(const struct xt_mtchk_param *par)
+{
+	struct ebt_limit_info *info = par->matchinfo;
+
+	/* Check for overflow. */
+	if (info->burst == 0 ||
+	    user2credits(info->avg * info->burst) < user2credits(info->avg)) {
+		pr_info("overflow, try lower: %u/%u\n",
+			info->avg, info->burst);
+		return -EINVAL;
+	}
+
+	/* User avg in seconds * EBT_LIMIT_SCALE: convert to jiffies * 128. */
+	info->prev = jiffies;
+	info->credit = user2credits(info->avg * info->burst);
+	info->credit_cap = user2credits(info->avg * info->burst);
+	info->cost = user2credits(info->avg);
+	return 0;
+}
+
+
+#ifdef CONFIG_COMPAT
+/*
+ * no conversion function needed --
+ * only avg/burst have meaningful values in userspace.
+ */
+struct ebt_compat_limit_info {
+	compat_uint_t avg, burst;
+	compat_ulong_t prev;
+	compat_uint_t credit, credit_cap, cost;
+};
+#endif
+
+static struct xt_match ebt_limit_mt_reg __read_mostly = {
+	.name		= "limit",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_limit_mt,
+	.checkentry	= ebt_limit_mt_check,
+	.matchsize	= sizeof(struct ebt_limit_info),
+#ifdef CONFIG_COMPAT
+	.compatsize	= sizeof(struct ebt_compat_limit_info),
+#endif
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_limit_init(void)
+{
+	return xt_register_match(&ebt_limit_mt_reg);
+}
+
+static void __exit ebt_limit_fini(void)
+{
+	xt_unregister_match(&ebt_limit_mt_reg);
+}
+
+module_init(ebt_limit_init);
+module_exit(ebt_limit_fini);
+MODULE_DESCRIPTION("Ebtables: Rate-limit match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_log.c

@@ -0,0 +1,262 @@
+/*
+ *  ebt_log
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *	Harald Welte <laforge@netfilter.org>
+ *
+ *  April, 2002
+ *
+ */
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/if_arp.h>
+#include <linux/spinlock.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <linux/in6.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_log.h>
+#include <linux/netfilter.h>
+
+static DEFINE_SPINLOCK(ebt_log_lock);
+
+static int ebt_log_tg_check(const struct xt_tgchk_param *par)
+{
+	struct ebt_log_info *info = par->targinfo;
+
+	if (info->bitmask & ~EBT_LOG_MASK)
+		return -EINVAL;
+	if (info->loglevel >= 8)
+		return -EINVAL;
+	info->prefix[EBT_LOG_PREFIX_SIZE - 1] = '\0';
+	return 0;
+}
+
+struct tcpudphdr
+{
+	__be16 src;
+	__be16 dst;
+};
+
+struct arppayload
+{
+	unsigned char mac_src[ETH_ALEN];
+	unsigned char ip_src[4];
+	unsigned char mac_dst[ETH_ALEN];
+	unsigned char ip_dst[4];
+};
+
+static void
+print_ports(const struct sk_buff *skb, uint8_t protocol, int offset)
+{
+	if (protocol == IPPROTO_TCP ||
+	    protocol == IPPROTO_UDP ||
+	    protocol == IPPROTO_UDPLITE ||
+	    protocol == IPPROTO_SCTP ||
+	    protocol == IPPROTO_DCCP) {
+		const struct tcpudphdr *pptr;
+		struct tcpudphdr _ports;
+
+		pptr = skb_header_pointer(skb, offset,
+					  sizeof(_ports), &_ports);
+		if (pptr == NULL) {
+			printk(" INCOMPLETE TCP/UDP header");
+			return;
+		}
+		printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
+	}
+}
+
+static void
+ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
+	       const struct sk_buff *skb, const struct net_device *in,
+	       const struct net_device *out, const struct nf_loginfo *loginfo,
+	       const char *prefix)
+{
+	unsigned int bitmask;
+
+	/* FIXME: Disabled from containers until syslog ns is supported */
+	if (!net_eq(net, &init_net))
+		return;
+
+	spin_lock_bh(&ebt_log_lock);
+	printk(KERN_SOH "%c%s IN=%s OUT=%s MAC source = %pM MAC dest = %pM proto = 0x%04x",
+	       '0' + loginfo->u.log.level, prefix,
+	       in ? in->name : "", out ? out->name : "",
+	       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+	       ntohs(eth_hdr(skb)->h_proto));
+
+	if (loginfo->type == NF_LOG_TYPE_LOG)
+		bitmask = loginfo->u.log.logflags;
+	else
+		bitmask = NF_LOG_MASK;
+
+	if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto ==
+	   htons(ETH_P_IP)){
+		const struct iphdr *ih;
+		struct iphdr _iph;
+
+		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+		if (ih == NULL) {
+			printk(" INCOMPLETE IP header");
+			goto out;
+		}
+		printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
+		       &ih->saddr, &ih->daddr, ih->tos, ih->protocol);
+		print_ports(skb, ih->protocol, ih->ihl*4);
+		goto out;
+	}
+
+#if IS_ENABLED(CONFIG_BRIDGE_EBT_IP6)
+	if ((bitmask & EBT_LOG_IP6) && eth_hdr(skb)->h_proto ==
+	   htons(ETH_P_IPV6)) {
+		const struct ipv6hdr *ih;
+		struct ipv6hdr _iph;
+		uint8_t nexthdr;
+		__be16 frag_off;
+		int offset_ph;
+
+		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+		if (ih == NULL) {
+			printk(" INCOMPLETE IPv6 header");
+			goto out;
+		}
+		printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
+		       &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
+		nexthdr = ih->nexthdr;
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
+		if (offset_ph == -1)
+			goto out;
+		print_ports(skb, nexthdr, offset_ph);
+		goto out;
+	}
+#endif
+
+	if ((bitmask & EBT_LOG_ARP) &&
+	    ((eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) ||
+	     (eth_hdr(skb)->h_proto == htons(ETH_P_RARP)))) {
+		const struct arphdr *ah;
+		struct arphdr _arph;
+
+		ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+		if (ah == NULL) {
+			printk(" INCOMPLETE ARP header");
+			goto out;
+		}
+		printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
+		       ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
+		       ntohs(ah->ar_op));
+
+		/* If it's for Ethernet and the lengths are OK,
+		 * then log the ARP payload */
+		if (ah->ar_hrd == htons(1) &&
+		    ah->ar_hln == ETH_ALEN &&
+		    ah->ar_pln == sizeof(__be32)) {
+			const struct arppayload *ap;
+			struct arppayload _arpp;
+
+			ap = skb_header_pointer(skb, sizeof(_arph),
+						sizeof(_arpp), &_arpp);
+			if (ap == NULL) {
+				printk(" INCOMPLETE ARP payload");
+				goto out;
+			}
+			printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
+					ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
+		}
+	}
+out:
+	printk("\n");
+	spin_unlock_bh(&ebt_log_lock);
+
+}
+
+static unsigned int
+ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_log_info *info = par->targinfo;
+	struct nf_loginfo li;
+	struct net *net = dev_net(par->in ? par->in : par->out);
+
+	li.type = NF_LOG_TYPE_LOG;
+	li.u.log.level = info->loglevel;
+	li.u.log.logflags = info->bitmask;
+
+	if (info->bitmask & EBT_LOG_NFLOG)
+		nf_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb,
+			      par->in, par->out, &li, "%s", info->prefix);
+	else
+		ebt_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb, par->in,
+			       par->out, &li, info->prefix);
+	return EBT_CONTINUE;
+}
+
+static struct xt_target ebt_log_tg_reg __read_mostly = {
+	.name		= "log",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.target		= ebt_log_tg,
+	.checkentry	= ebt_log_tg_check,
+	.targetsize	= sizeof(struct ebt_log_info),
+	.me		= THIS_MODULE,
+};
+
+static struct nf_logger ebt_log_logger __read_mostly = {
+	.name 		= "ebt_log",
+	.logfn		= &ebt_log_packet,
+	.me		= THIS_MODULE,
+};
+
+static int __net_init ebt_log_net_init(struct net *net)
+{
+	nf_log_set(net, NFPROTO_BRIDGE, &ebt_log_logger);
+	return 0;
+}
+
+static void __net_exit ebt_log_net_fini(struct net *net)
+{
+	nf_log_unset(net, &ebt_log_logger);
+}
+
+static struct pernet_operations ebt_log_net_ops = {
+	.init = ebt_log_net_init,
+	.exit = ebt_log_net_fini,
+};
+
+static int __init ebt_log_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&ebt_log_net_ops);
+	if (ret < 0)
+		goto err_pernet;
+
+	ret = xt_register_target(&ebt_log_tg_reg);
+	if (ret < 0)
+		goto err_target;
+
+	nf_log_register(NFPROTO_BRIDGE, &ebt_log_logger);
+
+	return ret;
+
+err_target:
+	unregister_pernet_subsys(&ebt_log_net_ops);
+err_pernet:
+	return ret;
+}
+
+static void __exit ebt_log_fini(void)
+{
+	unregister_pernet_subsys(&ebt_log_net_ops);
+	nf_log_unregister(&ebt_log_logger);
+	xt_unregister_target(&ebt_log_tg_reg);
+}
+
+module_init(ebt_log_init);
+module_exit(ebt_log_fini);
+MODULE_DESCRIPTION("Ebtables: Packet logging to syslog");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_mark.c

@@ -0,0 +1,110 @@
+/*
+ *  ebt_mark
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  July, 2002
+ *
+ */
+
+/* The mark target can be used in any chain,
+ * I believe adding a mangle table just for marking is total overkill.
+ * Marking a frame doesn't really change anything in the frame anyway.
+ */
+
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_mark_t.h>
+
+static unsigned int
+ebt_mark_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_mark_t_info *info = par->targinfo;
+	int action = info->target & -16;
+
+	if (action == MARK_SET_VALUE)
+		skb->mark = info->mark;
+	else if (action == MARK_OR_VALUE)
+		skb->mark |= info->mark;
+	else if (action == MARK_AND_VALUE)
+		skb->mark &= info->mark;
+	else
+		skb->mark ^= info->mark;
+
+	return info->target | ~EBT_VERDICT_BITS;
+}
+
+static int ebt_mark_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct ebt_mark_t_info *info = par->targinfo;
+	int tmp;
+
+	tmp = info->target | ~EBT_VERDICT_BITS;
+	if (BASE_CHAIN && tmp == EBT_RETURN)
+		return -EINVAL;
+	if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0)
+		return -EINVAL;
+	tmp = info->target & ~EBT_VERDICT_BITS;
+	if (tmp != MARK_SET_VALUE && tmp != MARK_OR_VALUE &&
+	    tmp != MARK_AND_VALUE && tmp != MARK_XOR_VALUE)
+		return -EINVAL;
+	return 0;
+}
+#ifdef CONFIG_COMPAT
+struct compat_ebt_mark_t_info {
+	compat_ulong_t mark;
+	compat_uint_t target;
+};
+
+static void mark_tg_compat_from_user(void *dst, const void *src)
+{
+	const struct compat_ebt_mark_t_info *user = src;
+	struct ebt_mark_t_info *kern = dst;
+
+	kern->mark = user->mark;
+	kern->target = user->target;
+}
+
+static int mark_tg_compat_to_user(void __user *dst, const void *src)
+{
+	struct compat_ebt_mark_t_info __user *user = dst;
+	const struct ebt_mark_t_info *kern = src;
+
+	if (put_user(kern->mark, &user->mark) ||
+	    put_user(kern->target, &user->target))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
+static struct xt_target ebt_mark_tg_reg __read_mostly = {
+	.name		= "mark",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.target		= ebt_mark_tg,
+	.checkentry	= ebt_mark_tg_check,
+	.targetsize	= sizeof(struct ebt_mark_t_info),
+#ifdef CONFIG_COMPAT
+	.compatsize	= sizeof(struct compat_ebt_mark_t_info),
+	.compat_from_user = mark_tg_compat_from_user,
+	.compat_to_user	= mark_tg_compat_to_user,
+#endif
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_mark_init(void)
+{
+	return xt_register_target(&ebt_mark_tg_reg);
+}
+
+static void __exit ebt_mark_fini(void)
+{
+	xt_unregister_target(&ebt_mark_tg_reg);
+}
+
+module_init(ebt_mark_init);
+module_exit(ebt_mark_fini);
+MODULE_DESCRIPTION("Ebtables: Packet mark modification");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_mark_m.c

@@ -0,0 +1,98 @@
+/*
+ *  ebt_mark_m
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  July, 2002
+ *
+ */
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_mark_m.h>
+
+static bool
+ebt_mark_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_mark_m_info *info = par->matchinfo;
+
+	if (info->bitmask & EBT_MARK_OR)
+		return !!(skb->mark & info->mask) ^ info->invert;
+	return ((skb->mark & info->mask) == info->mark) ^ info->invert;
+}
+
+static int ebt_mark_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_mark_m_info *info = par->matchinfo;
+
+	if (info->bitmask & ~EBT_MARK_MASK)
+		return -EINVAL;
+	if ((info->bitmask & EBT_MARK_OR) && (info->bitmask & EBT_MARK_AND))
+		return -EINVAL;
+	if (!info->bitmask)
+		return -EINVAL;
+	return 0;
+}
+
+
+#ifdef CONFIG_COMPAT
+struct compat_ebt_mark_m_info {
+	compat_ulong_t mark, mask;
+	uint8_t invert, bitmask;
+};
+
+static void mark_mt_compat_from_user(void *dst, const void *src)
+{
+	const struct compat_ebt_mark_m_info *user = src;
+	struct ebt_mark_m_info *kern = dst;
+
+	kern->mark = user->mark;
+	kern->mask = user->mask;
+	kern->invert = user->invert;
+	kern->bitmask = user->bitmask;
+}
+
+static int mark_mt_compat_to_user(void __user *dst, const void *src)
+{
+	struct compat_ebt_mark_m_info __user *user = dst;
+	const struct ebt_mark_m_info *kern = src;
+
+	if (put_user(kern->mark, &user->mark) ||
+	    put_user(kern->mask, &user->mask) ||
+	    put_user(kern->invert, &user->invert) ||
+	    put_user(kern->bitmask, &user->bitmask))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
+static struct xt_match ebt_mark_mt_reg __read_mostly = {
+	.name		= "mark_m",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_mark_mt,
+	.checkentry	= ebt_mark_mt_check,
+	.matchsize	= sizeof(struct ebt_mark_m_info),
+#ifdef CONFIG_COMPAT
+	.compatsize	= sizeof(struct compat_ebt_mark_m_info),
+	.compat_from_user = mark_mt_compat_from_user,
+	.compat_to_user	= mark_mt_compat_to_user,
+#endif
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_mark_m_init(void)
+{
+	return xt_register_match(&ebt_mark_mt_reg);
+}
+
+static void __exit ebt_mark_m_fini(void)
+{
+	xt_unregister_match(&ebt_mark_mt_reg);
+}
+
+module_init(ebt_mark_m_init);
+module_exit(ebt_mark_m_fini);
+MODULE_DESCRIPTION("Ebtables: Packet mark match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_nflog.c

@@ -0,0 +1,73 @@
+/*
+ * ebt_nflog
+ *
+ *	Author:
+ *	Peter Warasin <peter@endian.com>
+ *
+ *  February, 2008
+ *
+ * Based on:
+ *  xt_NFLOG.c, (C) 2006 by Patrick McHardy <kaber@trash.net>
+ *  ebt_ulog.c, (C) 2004 by Bart De Schuymer <bdschuym@pandora.be>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_nflog.h>
+#include <net/netfilter/nf_log.h>
+
+static unsigned int
+ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_nflog_info *info = par->targinfo;
+	struct nf_loginfo li;
+	struct net *net = dev_net(par->in ? par->in : par->out);
+
+	li.type = NF_LOG_TYPE_ULOG;
+	li.u.ulog.copy_len = info->len;
+	li.u.ulog.group = info->group;
+	li.u.ulog.qthreshold = info->threshold;
+
+	nf_log_packet(net, PF_BRIDGE, par->hooknum, skb, par->in,
+		      par->out, &li, "%s", info->prefix);
+	return EBT_CONTINUE;
+}
+
+static int ebt_nflog_tg_check(const struct xt_tgchk_param *par)
+{
+	struct ebt_nflog_info *info = par->targinfo;
+
+	if (info->flags & ~EBT_NFLOG_MASK)
+		return -EINVAL;
+	info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0';
+	return 0;
+}
+
+static struct xt_target ebt_nflog_tg_reg __read_mostly = {
+	.name       = "nflog",
+	.revision   = 0,
+	.family     = NFPROTO_BRIDGE,
+	.target     = ebt_nflog_tg,
+	.checkentry = ebt_nflog_tg_check,
+	.targetsize = sizeof(struct ebt_nflog_info),
+	.me         = THIS_MODULE,
+};
+
+static int __init ebt_nflog_init(void)
+{
+	return xt_register_target(&ebt_nflog_tg_reg);
+}
+
+static void __exit ebt_nflog_fini(void)
+{
+	xt_unregister_target(&ebt_nflog_tg_reg);
+}
+
+module_init(ebt_nflog_init);
+module_exit(ebt_nflog_fini);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Peter Warasin <peter@endian.com>");
+MODULE_DESCRIPTION("ebtables NFLOG netfilter logging module");

net/bridge/netfilter/ebt_pkttype.c

@@ -0,0 +1,56 @@
+/*
+ *  ebt_pkttype
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2003
+ *
+ */
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_pkttype.h>
+
+static bool
+ebt_pkttype_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_pkttype_info *info = par->matchinfo;
+
+	return (skb->pkt_type == info->pkt_type) ^ info->invert;
+}
+
+static int ebt_pkttype_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_pkttype_info *info = par->matchinfo;
+
+	if (info->invert != 0 && info->invert != 1)
+		return -EINVAL;
+	/* Allow any pkt_type value */
+	return 0;
+}
+
+static struct xt_match ebt_pkttype_mt_reg __read_mostly = {
+	.name		= "pkttype",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_pkttype_mt,
+	.checkentry	= ebt_pkttype_mt_check,
+	.matchsize	= sizeof(struct ebt_pkttype_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_pkttype_init(void)
+{
+	return xt_register_match(&ebt_pkttype_mt_reg);
+}
+
+static void __exit ebt_pkttype_fini(void)
+{
+	xt_unregister_match(&ebt_pkttype_mt_reg);
+}
+
+module_init(ebt_pkttype_init);
+module_exit(ebt_pkttype_fini);
+MODULE_DESCRIPTION("Ebtables: Link layer packet type match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_redirect.c

@@ -0,0 +1,80 @@
+/*
+ *  ebt_redirect
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2002
+ *
+ */
+#include <linux/module.h>
+#include <net/sock.h>
+#include "../br_private.h"
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_redirect.h>
+
+static unsigned int
+ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_redirect_info *info = par->targinfo;
+
+	if (!skb_make_writable(skb, 0))
+		return EBT_DROP;
+
+	if (par->hooknum != NF_BR_BROUTING)
+		/* rcu_read_lock()ed by nf_hook_slow */
+		memcpy(eth_hdr(skb)->h_dest,
+		       br_port_get_rcu(par->in)->br->dev->dev_addr, ETH_ALEN);
+	else
+		memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN);
+	skb->pkt_type = PACKET_HOST;
+	return info->target;
+}
+
+static int ebt_redirect_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct ebt_redirect_info *info = par->targinfo;
+	unsigned int hook_mask;
+
+	if (BASE_CHAIN && info->target == EBT_RETURN)
+		return -EINVAL;
+
+	hook_mask = par->hook_mask & ~(1 << NF_BR_NUMHOOKS);
+	if ((strcmp(par->table, "nat") != 0 ||
+	    hook_mask & ~(1 << NF_BR_PRE_ROUTING)) &&
+	    (strcmp(par->table, "broute") != 0 ||
+	    hook_mask & ~(1 << NF_BR_BROUTING)))
+		return -EINVAL;
+	if (INVALID_TARGET)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target ebt_redirect_tg_reg __read_mostly = {
+	.name		= "redirect",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.hooks		= (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING) |
+			  (1 << NF_BR_BROUTING),
+	.target		= ebt_redirect_tg,
+	.checkentry	= ebt_redirect_tg_check,
+	.targetsize	= sizeof(struct ebt_redirect_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_redirect_init(void)
+{
+	return xt_register_target(&ebt_redirect_tg_reg);
+}
+
+static void __exit ebt_redirect_fini(void)
+{
+	xt_unregister_target(&ebt_redirect_tg_reg);
+}
+
+module_init(ebt_redirect_init);
+module_exit(ebt_redirect_fini);
+MODULE_DESCRIPTION("Ebtables: Packet redirection to localhost");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_snat.c

@@ -0,0 +1,87 @@
+/*
+ *  ebt_snat
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  June, 2002
+ *
+ */
+#include <linux/module.h>
+#include <net/sock.h>
+#include <linux/if_arp.h>
+#include <net/arp.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_nat.h>
+
+static unsigned int
+ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ebt_nat_info *info = par->targinfo;
+
+	if (!skb_make_writable(skb, 0))
+		return EBT_DROP;
+
+	memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN);
+	if (!(info->target & NAT_ARP_BIT) &&
+	    eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) {
+		const struct arphdr *ap;
+		struct arphdr _ah;
+
+		ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah);
+		if (ap == NULL)
+			return EBT_DROP;
+		if (ap->ar_hln != ETH_ALEN)
+			goto out;
+		if (skb_store_bits(skb, sizeof(_ah), info->mac,ETH_ALEN))
+			return EBT_DROP;
+	}
+out:
+	return info->target | ~EBT_VERDICT_BITS;
+}
+
+static int ebt_snat_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct ebt_nat_info *info = par->targinfo;
+	int tmp;
+
+	tmp = info->target | ~EBT_VERDICT_BITS;
+	if (BASE_CHAIN && tmp == EBT_RETURN)
+		return -EINVAL;
+
+	if (tmp < -NUM_STANDARD_TARGETS || tmp >= 0)
+		return -EINVAL;
+	tmp = info->target | EBT_VERDICT_BITS;
+	if ((tmp & ~NAT_ARP_BIT) != ~NAT_ARP_BIT)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target ebt_snat_tg_reg __read_mostly = {
+	.name		= "snat",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.table		= "nat",
+	.hooks		= (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_POST_ROUTING),
+	.target		= ebt_snat_tg,
+	.checkentry	= ebt_snat_tg_check,
+	.targetsize	= sizeof(struct ebt_nat_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_snat_init(void)
+{
+	return xt_register_target(&ebt_snat_tg_reg);
+}
+
+static void __exit ebt_snat_fini(void)
+{
+	xt_unregister_target(&ebt_snat_tg_reg);
+}
+
+module_init(ebt_snat_init);
+module_exit(ebt_snat_fini);
+MODULE_DESCRIPTION("Ebtables: Source MAC address translation");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_stp.c

@@ -0,0 +1,197 @@
+/*
+ *  ebt_stp
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *	Stephen Hemminger <shemminger@osdl.org>
+ *
+ *  July, 2003
+ */
+#include <linux/etherdevice.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_stp.h>
+
+#define BPDU_TYPE_CONFIG 0
+#define BPDU_TYPE_TCN 0x80
+
+struct stp_header {
+	uint8_t dsap;
+	uint8_t ssap;
+	uint8_t ctrl;
+	uint8_t pid;
+	uint8_t vers;
+	uint8_t type;
+};
+
+struct stp_config_pdu {
+	uint8_t flags;
+	uint8_t root[8];
+	uint8_t root_cost[4];
+	uint8_t sender[8];
+	uint8_t port[2];
+	uint8_t msg_age[2];
+	uint8_t max_age[2];
+	uint8_t hello_time[2];
+	uint8_t forward_delay[2];
+};
+
+#define NR16(p) (p[0] << 8 | p[1])
+#define NR32(p) ((p[0] << 24) | (p[1] << 16) | (p[2] << 8) | p[3])
+
+static bool ebt_filter_config(const struct ebt_stp_info *info,
+   const struct stp_config_pdu *stpc)
+{
+	const struct ebt_stp_config_info *c;
+	uint16_t v16;
+	uint32_t v32;
+	int verdict, i;
+
+	c = &info->config;
+	if ((info->bitmask & EBT_STP_FLAGS) &&
+	    FWINV(c->flags != stpc->flags, EBT_STP_FLAGS))
+		return false;
+	if (info->bitmask & EBT_STP_ROOTPRIO) {
+		v16 = NR16(stpc->root);
+		if (FWINV(v16 < c->root_priol ||
+		    v16 > c->root_priou, EBT_STP_ROOTPRIO))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_ROOTADDR) {
+		verdict = 0;
+		for (i = 0; i < 6; i++)
+			verdict |= (stpc->root[2+i] ^ c->root_addr[i]) &
+				   c->root_addrmsk[i];
+		if (FWINV(verdict != 0, EBT_STP_ROOTADDR))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_ROOTCOST) {
+		v32 = NR32(stpc->root_cost);
+		if (FWINV(v32 < c->root_costl ||
+		    v32 > c->root_costu, EBT_STP_ROOTCOST))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_SENDERPRIO) {
+		v16 = NR16(stpc->sender);
+		if (FWINV(v16 < c->sender_priol ||
+		    v16 > c->sender_priou, EBT_STP_SENDERPRIO))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_SENDERADDR) {
+		verdict = 0;
+		for (i = 0; i < 6; i++)
+			verdict |= (stpc->sender[2+i] ^ c->sender_addr[i]) &
+				   c->sender_addrmsk[i];
+		if (FWINV(verdict != 0, EBT_STP_SENDERADDR))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_PORT) {
+		v16 = NR16(stpc->port);
+		if (FWINV(v16 < c->portl ||
+		    v16 > c->portu, EBT_STP_PORT))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_MSGAGE) {
+		v16 = NR16(stpc->msg_age);
+		if (FWINV(v16 < c->msg_agel ||
+		    v16 > c->msg_ageu, EBT_STP_MSGAGE))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_MAXAGE) {
+		v16 = NR16(stpc->max_age);
+		if (FWINV(v16 < c->max_agel ||
+		    v16 > c->max_ageu, EBT_STP_MAXAGE))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_HELLOTIME) {
+		v16 = NR16(stpc->hello_time);
+		if (FWINV(v16 < c->hello_timel ||
+		    v16 > c->hello_timeu, EBT_STP_HELLOTIME))
+			return false;
+	}
+	if (info->bitmask & EBT_STP_FWDD) {
+		v16 = NR16(stpc->forward_delay);
+		if (FWINV(v16 < c->forward_delayl ||
+		    v16 > c->forward_delayu, EBT_STP_FWDD))
+			return false;
+	}
+	return true;
+}
+
+static bool
+ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_stp_info *info = par->matchinfo;
+	const struct stp_header *sp;
+	struct stp_header _stph;
+	const uint8_t header[6] = {0x42, 0x42, 0x03, 0x00, 0x00, 0x00};
+
+	sp = skb_header_pointer(skb, 0, sizeof(_stph), &_stph);
+	if (sp == NULL)
+		return false;
+
+	/* The stp code only considers these */
+	if (memcmp(sp, header, sizeof(header)))
+		return false;
+
+	if (info->bitmask & EBT_STP_TYPE &&
+	    FWINV(info->type != sp->type, EBT_STP_TYPE))
+		return false;
+
+	if (sp->type == BPDU_TYPE_CONFIG &&
+	    info->bitmask & EBT_STP_CONFIG_MASK) {
+		const struct stp_config_pdu *st;
+		struct stp_config_pdu _stpc;
+
+		st = skb_header_pointer(skb, sizeof(_stph),
+					sizeof(_stpc), &_stpc);
+		if (st == NULL)
+			return false;
+		return ebt_filter_config(info, st);
+	}
+	return true;
+}
+
+static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct ebt_stp_info *info = par->matchinfo;
+	const uint8_t bridge_ula[6] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+	const uint8_t msk[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	const struct ebt_entry *e = par->entryinfo;
+
+	if (info->bitmask & ~EBT_STP_MASK || info->invflags & ~EBT_STP_MASK ||
+	    !(info->bitmask & EBT_STP_MASK))
+		return -EINVAL;
+	/* Make sure the match only receives stp frames */
+	if (!ether_addr_equal(e->destmac, bridge_ula) ||
+	    !ether_addr_equal(e->destmsk, msk) || !(e->bitmask & EBT_DESTMAC))
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct xt_match ebt_stp_mt_reg __read_mostly = {
+	.name		= "stp",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_stp_mt,
+	.checkentry	= ebt_stp_mt_check,
+	.matchsize	= sizeof(struct ebt_stp_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_stp_init(void)
+{
+	return xt_register_match(&ebt_stp_mt_reg);
+}
+
+static void __exit ebt_stp_fini(void)
+{
+	xt_unregister_match(&ebt_stp_mt_reg);
+}
+
+module_init(ebt_stp_init);
+module_exit(ebt_stp_fini);
+MODULE_DESCRIPTION("Ebtables: Spanning Tree Protocol packet match");
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebt_ulog.c

@@ -0,0 +1,390 @@
+/*
+ * netfilter module for userspace bridged Ethernet frames logging daemons
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *	Harald Welte <laforge@netfilter.org>
+ *
+ *  November, 2004
+ *
+ * Based on ipt_ULOG.c, which is
+ * (C) 2000-2002 by Harald Welte <laforge@netfilter.org>
+ *
+ * This module accepts two parameters:
+ *
+ * nlbufsiz:
+ *   The parameter specifies how big the buffer for each netlink multicast
+ * group is. e.g. If you say nlbufsiz=8192, up to eight kb of packets will
+ * get accumulated in the kernel until they are sent to userspace. It is
+ * NOT possible to allocate more than 128kB, and it is strongly discouraged,
+ * because atomically allocating 128kB inside the network rx softirq is not
+ * reliable. Please also keep in mind that this buffer size is allocated for
+ * each nlgroup you are using, so the total kernel memory usage increases
+ * by that factor.
+ *
+ * flushtimeout:
+ *   Specify, after how many hundredths of a second the queue should be
+ *   flushed even if it is not full yet.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <net/netlink.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_ulog.h>
+#include <net/netfilter/nf_log.h>
+#include <net/netns/generic.h>
+#include <net/sock.h>
+#include "../br_private.h"
+
+static unsigned int nlbufsiz = NLMSG_GOODSIZE;
+module_param(nlbufsiz, uint, 0600);
+MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) "
+			   "(defaults to 4096)");
+
+static unsigned int flushtimeout = 10;
+module_param(flushtimeout, uint, 0600);
+MODULE_PARM_DESC(flushtimeout, "buffer flush timeout (hundredths ofa second) "
+			       "(defaults to 10)");
+
+typedef struct {
+	unsigned int qlen;		/* number of nlmsgs' in the skb */
+	struct nlmsghdr *lastnlh;	/* netlink header of last msg in skb */
+	struct sk_buff *skb;		/* the pre-allocated skb */
+	struct timer_list timer;	/* the timer function */
+	spinlock_t lock;		/* the per-queue lock */
+} ebt_ulog_buff_t;
+
+static int ebt_ulog_net_id __read_mostly;
+struct ebt_ulog_net {
+	unsigned int nlgroup[EBT_ULOG_MAXNLGROUPS];
+	ebt_ulog_buff_t ulog_buffers[EBT_ULOG_MAXNLGROUPS];
+	struct sock *ebtulognl;
+};
+
+static struct ebt_ulog_net *ebt_ulog_pernet(struct net *net)
+{
+	return net_generic(net, ebt_ulog_net_id);
+}
+
+/* send one ulog_buff_t to userspace */
+static void ulog_send(struct ebt_ulog_net *ebt, unsigned int nlgroup)
+{
+	ebt_ulog_buff_t *ub = &ebt->ulog_buffers[nlgroup];
+
+	del_timer(&ub->timer);
+
+	if (!ub->skb)
+		return;
+
+	/* last nlmsg needs NLMSG_DONE */
+	if (ub->qlen > 1)
+		ub->lastnlh->nlmsg_type = NLMSG_DONE;
+
+	NETLINK_CB(ub->skb).dst_group = nlgroup + 1;
+	netlink_broadcast(ebt->ebtulognl, ub->skb, 0, nlgroup + 1, GFP_ATOMIC);
+
+	ub->qlen = 0;
+	ub->skb = NULL;
+}
+
+/* timer function to flush queue in flushtimeout time */
+static void ulog_timer(unsigned long data)
+{
+	struct ebt_ulog_net *ebt = container_of((void *)data,
+						struct ebt_ulog_net,
+						nlgroup[*(unsigned int *)data]);
+
+	ebt_ulog_buff_t *ub = &ebt->ulog_buffers[*(unsigned int *)data];
+	spin_lock_bh(&ub->lock);
+	if (ub->skb)
+		ulog_send(ebt, *(unsigned int *)data);
+	spin_unlock_bh(&ub->lock);
+}
+
+static struct sk_buff *ulog_alloc_skb(unsigned int size)
+{
+	struct sk_buff *skb;
+	unsigned int n;
+
+	n = max(size, nlbufsiz);
+	skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN);
+	if (!skb) {
+		if (n > size) {
+			/* try to allocate only as much as we need for
+			 * current packet */
+			skb = alloc_skb(size, GFP_ATOMIC);
+			if (!skb)
+				pr_debug("cannot even allocate buffer of size %ub\n",
+					 size);
+		}
+	}
+
+	return skb;
+}
+
+static void ebt_ulog_packet(struct net *net, unsigned int hooknr,
+			    const struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    const struct ebt_ulog_info *uloginfo,
+			    const char *prefix)
+{
+	ebt_ulog_packet_msg_t *pm;
+	size_t size, copy_len;
+	struct nlmsghdr *nlh;
+	struct ebt_ulog_net *ebt = ebt_ulog_pernet(net);
+	unsigned int group = uloginfo->nlgroup;
+	ebt_ulog_buff_t *ub = &ebt->ulog_buffers[group];
+	spinlock_t *lock = &ub->lock;
+	ktime_t kt;
+
+	if ((uloginfo->cprange == 0) ||
+	    (uloginfo->cprange > skb->len + ETH_HLEN))
+		copy_len = skb->len + ETH_HLEN;
+	else
+		copy_len = uloginfo->cprange;
+
+	size = nlmsg_total_size(sizeof(*pm) + copy_len);
+	if (size > nlbufsiz) {
+		pr_debug("Size %Zd needed, but nlbufsiz=%d\n", size, nlbufsiz);
+		return;
+	}
+
+	spin_lock_bh(lock);
+
+	if (!ub->skb) {
+		if (!(ub->skb = ulog_alloc_skb(size)))
+			goto unlock;
+	} else if (size > skb_tailroom(ub->skb)) {
+		ulog_send(ebt, group);
+
+		if (!(ub->skb = ulog_alloc_skb(size)))
+			goto unlock;
+	}
+
+	nlh = nlmsg_put(ub->skb, 0, ub->qlen, 0,
+			size - NLMSG_ALIGN(sizeof(*nlh)), 0);
+	if (!nlh) {
+		kfree_skb(ub->skb);
+		ub->skb = NULL;
+		goto unlock;
+	}
+	ub->qlen++;
+
+	pm = nlmsg_data(nlh);
+
+	/* Fill in the ulog data */
+	pm->version = EBT_ULOG_VERSION;
+	kt = ktime_get_real();
+	pm->stamp = ktime_to_timeval(kt);
+	if (ub->qlen == 1)
+		ub->skb->tstamp = kt;
+	pm->data_len = copy_len;
+	pm->mark = skb->mark;
+	pm->hook = hooknr;
+	if (uloginfo->prefix != NULL)
+		strcpy(pm->prefix, uloginfo->prefix);
+	else
+		*(pm->prefix) = '\0';
+
+	if (in) {
+		strcpy(pm->physindev, in->name);
+		/* If in isn't a bridge, then physindev==indev */
+		if (br_port_exists(in))
+			/* rcu_read_lock()ed by nf_hook_slow */
+			strcpy(pm->indev, br_port_get_rcu(in)->br->dev->name);
+		else
+			strcpy(pm->indev, in->name);
+	} else
+		pm->indev[0] = pm->physindev[0] = '\0';
+
+	if (out) {
+		/* If out exists, then out is a bridge port */
+		strcpy(pm->physoutdev, out->name);
+		/* rcu_read_lock()ed by nf_hook_slow */
+		strcpy(pm->outdev, br_port_get_rcu(out)->br->dev->name);
+	} else
+		pm->outdev[0] = pm->physoutdev[0] = '\0';
+
+	if (skb_copy_bits(skb, -ETH_HLEN, pm->data, copy_len) < 0)
+		BUG();
+
+	if (ub->qlen > 1)
+		ub->lastnlh->nlmsg_flags |= NLM_F_MULTI;
+
+	ub->lastnlh = nlh;
+
+	if (ub->qlen >= uloginfo->qthreshold)
+		ulog_send(ebt, group);
+	else if (!timer_pending(&ub->timer)) {
+		ub->timer.expires = jiffies + flushtimeout * HZ / 100;
+		add_timer(&ub->timer);
+	}
+
+unlock:
+	spin_unlock_bh(lock);
+}
+
+/* this function is registered with the netfilter core */
+static void ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
+   const struct sk_buff *skb, const struct net_device *in,
+   const struct net_device *out, const struct nf_loginfo *li,
+   const char *prefix)
+{
+	struct ebt_ulog_info loginfo;
+
+	if (!li || li->type != NF_LOG_TYPE_ULOG) {
+		loginfo.nlgroup = EBT_ULOG_DEFAULT_NLGROUP;
+		loginfo.cprange = 0;
+		loginfo.qthreshold = EBT_ULOG_DEFAULT_QTHRESHOLD;
+		loginfo.prefix[0] = '\0';
+	} else {
+		loginfo.nlgroup = li->u.ulog.group;
+		loginfo.cprange = li->u.ulog.copy_len;
+		loginfo.qthreshold = li->u.ulog.qthreshold;
+		strlcpy(loginfo.prefix, prefix, sizeof(loginfo.prefix));
+	}
+
+	ebt_ulog_packet(net, hooknum, skb, in, out, &loginfo, prefix);
+}
+
+static unsigned int
+ebt_ulog_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	struct net *net = dev_net(par->in ? par->in : par->out);
+
+	ebt_ulog_packet(net, par->hooknum, skb, par->in, par->out,
+	                par->targinfo, NULL);
+	return EBT_CONTINUE;
+}
+
+static int ebt_ulog_tg_check(const struct xt_tgchk_param *par)
+{
+	struct ebt_ulog_info *uloginfo = par->targinfo;
+
+	if (uloginfo->nlgroup > 31)
+		return -EINVAL;
+
+	uloginfo->prefix[EBT_ULOG_PREFIX_LEN - 1] = '\0';
+
+	if (uloginfo->qthreshold > EBT_ULOG_MAX_QLEN)
+		uloginfo->qthreshold = EBT_ULOG_MAX_QLEN;
+
+	return 0;
+}
+
+static struct xt_target ebt_ulog_tg_reg __read_mostly = {
+	.name		= "ulog",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.target		= ebt_ulog_tg,
+	.checkentry	= ebt_ulog_tg_check,
+	.targetsize	= sizeof(struct ebt_ulog_info),
+	.me		= THIS_MODULE,
+};
+
+static struct nf_logger ebt_ulog_logger __read_mostly = {
+	.name		= "ebt_ulog",
+	.logfn		= &ebt_log_packet,
+	.me		= THIS_MODULE,
+};
+
+static int __net_init ebt_ulog_net_init(struct net *net)
+{
+	int i;
+	struct ebt_ulog_net *ebt = ebt_ulog_pernet(net);
+
+	struct netlink_kernel_cfg cfg = {
+		.groups	= EBT_ULOG_MAXNLGROUPS,
+	};
+
+	/* initialize ulog_buffers */
+	for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) {
+		ebt->nlgroup[i] = i;
+		setup_timer(&ebt->ulog_buffers[i].timer, ulog_timer,
+			    (unsigned long)&ebt->nlgroup[i]);
+		spin_lock_init(&ebt->ulog_buffers[i].lock);
+	}
+
+	ebt->ebtulognl = netlink_kernel_create(net, NETLINK_NFLOG, &cfg);
+	if (!ebt->ebtulognl)
+		return -ENOMEM;
+
+	nf_log_set(net, NFPROTO_BRIDGE, &ebt_ulog_logger);
+	return 0;
+}
+
+static void __net_exit ebt_ulog_net_fini(struct net *net)
+{
+	int i;
+	struct ebt_ulog_net *ebt = ebt_ulog_pernet(net);
+
+	nf_log_unset(net, &ebt_ulog_logger);
+	for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) {
+		ebt_ulog_buff_t *ub = &ebt->ulog_buffers[i];
+		del_timer(&ub->timer);
+
+		if (ub->skb) {
+			kfree_skb(ub->skb);
+			ub->skb = NULL;
+		}
+	}
+	netlink_kernel_release(ebt->ebtulognl);
+}
+
+static struct pernet_operations ebt_ulog_net_ops = {
+	.init = ebt_ulog_net_init,
+	.exit = ebt_ulog_net_fini,
+	.id   = &ebt_ulog_net_id,
+	.size = sizeof(struct ebt_ulog_net),
+};
+
+static int __init ebt_ulog_init(void)
+{
+	int ret;
+
+	if (nlbufsiz >= 128*1024) {
+		pr_warn("Netlink buffer has to be <= 128kB,"
+			"please try a smaller nlbufsiz parameter.\n");
+		return -EINVAL;
+	}
+
+	ret = register_pernet_subsys(&ebt_ulog_net_ops);
+	if (ret)
+		goto out_pernet;
+
+	ret = xt_register_target(&ebt_ulog_tg_reg);
+	if (ret)
+		goto out_target;
+
+	nf_log_register(NFPROTO_BRIDGE, &ebt_ulog_logger);
+
+	return 0;
+
+out_target:
+	unregister_pernet_subsys(&ebt_ulog_net_ops);
+out_pernet:
+	return ret;
+}
+
+static void __exit ebt_ulog_fini(void)
+{
+	nf_log_unregister(&ebt_ulog_logger);
+	xt_unregister_target(&ebt_ulog_tg_reg);
+	unregister_pernet_subsys(&ebt_ulog_net_ops);
+}
+
+module_init(ebt_ulog_init);
+module_exit(ebt_ulog_fini);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
+MODULE_DESCRIPTION("Ebtables: Packet logging to netlink using ULOG");

net/bridge/netfilter/ebt_vlan.c

@@ -0,0 +1,181 @@
+/*
+ * Description: EBTables 802.1Q match extension kernelspace module.
+ * Authors: Nick Fedchik <nick@fedchik.org.ua>
+ *          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 as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_bridge/ebt_vlan.h>
+
+#define MODULE_VERS "0.6"
+
+MODULE_AUTHOR("Nick Fedchik <nick@fedchik.org.ua>");
+MODULE_DESCRIPTION("Ebtables: 802.1Q VLAN tag match");
+MODULE_LICENSE("GPL");
+
+#define GET_BITMASK(_BIT_MASK_) info->bitmask & _BIT_MASK_
+#define EXIT_ON_MISMATCH(_MATCH_,_MASK_) {if (!((info->_MATCH_ == _MATCH_)^!!(info->invflags & _MASK_))) return false; }
+
+static bool
+ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ebt_vlan_info *info = par->matchinfo;
+
+	unsigned short TCI;	/* Whole TCI, given from parsed frame */
+	unsigned short id;	/* VLAN ID, given from frame TCI */
+	unsigned char prio;	/* user_priority, given from frame TCI */
+	/* VLAN encapsulated Type/Length field, given from orig frame */
+	__be16 encap;
+
+	if (vlan_tx_tag_present(skb)) {
+		TCI = vlan_tx_tag_get(skb);
+		encap = skb->protocol;
+	} else {
+		const struct vlan_hdr *fp;
+		struct vlan_hdr _frame;
+
+		fp = skb_header_pointer(skb, 0, sizeof(_frame), &_frame);
+		if (fp == NULL)
+			return false;
+
+		TCI = ntohs(fp->h_vlan_TCI);
+		encap = fp->h_vlan_encapsulated_proto;
+	}
+
+	/* Tag Control Information (TCI) consists of the following elements:
+	 * - User_priority. The user_priority field is three bits in length,
+	 * interpreted as a binary number.
+	 * - Canonical Format Indicator (CFI). The Canonical Format Indicator
+	 * (CFI) is a single bit flag value. Currently ignored.
+	 * - VLAN Identifier (VID). The VID is encoded as
+	 * an unsigned binary number. */
+	id = TCI & VLAN_VID_MASK;
+	prio = (TCI >> 13) & 0x7;
+
+	/* Checking VLAN Identifier (VID) */
+	if (GET_BITMASK(EBT_VLAN_ID))
+		EXIT_ON_MISMATCH(id, EBT_VLAN_ID);
+
+	/* Checking user_priority */
+	if (GET_BITMASK(EBT_VLAN_PRIO))
+		EXIT_ON_MISMATCH(prio, EBT_VLAN_PRIO);
+
+	/* Checking Encapsulated Proto (Length/Type) field */
+	if (GET_BITMASK(EBT_VLAN_ENCAP))
+		EXIT_ON_MISMATCH(encap, EBT_VLAN_ENCAP);
+
+	return true;
+}
+
+static int ebt_vlan_mt_check(const struct xt_mtchk_param *par)
+{
+	struct ebt_vlan_info *info = par->matchinfo;
+	const struct ebt_entry *e = par->entryinfo;
+
+	/* Is it 802.1Q frame checked? */
+	if (e->ethproto != htons(ETH_P_8021Q)) {
+		pr_debug("passed entry proto %2.4X is not 802.1Q (8100)\n",
+			 ntohs(e->ethproto));
+		return -EINVAL;
+	}
+
+	/* Check for bitmask range
+	 * True if even one bit is out of mask */
+	if (info->bitmask & ~EBT_VLAN_MASK) {
+		pr_debug("bitmask %2X is out of mask (%2X)\n",
+			 info->bitmask, EBT_VLAN_MASK);
+		return -EINVAL;
+	}
+
+	/* Check for inversion flags range */
+	if (info->invflags & ~EBT_VLAN_MASK) {
+		pr_debug("inversion flags %2X is out of mask (%2X)\n",
+			 info->invflags, EBT_VLAN_MASK);
+		return -EINVAL;
+	}
+
+	/* Reserved VLAN ID (VID) values
+	 * -----------------------------
+	 * 0 - The null VLAN ID.
+	 * 1 - The default Port VID (PVID)
+	 * 0x0FFF - Reserved for implementation use.
+	 * if_vlan.h: VLAN_N_VID 4096. */
+	if (GET_BITMASK(EBT_VLAN_ID)) {
+		if (!!info->id) { /* if id!=0 => check vid range */
+			if (info->id > VLAN_N_VID) {
+				pr_debug("id %d is out of range (1-4096)\n",
+					 info->id);
+				return -EINVAL;
+			}
+			/* Note: This is valid VLAN-tagged frame point.
+			 * Any value of user_priority are acceptable,
+			 * but should be ignored according to 802.1Q Std.
+			 * So we just drop the prio flag. */
+			info->bitmask &= ~EBT_VLAN_PRIO;
+		}
+		/* Else, id=0 (null VLAN ID)  => user_priority range (any?) */
+	}
+
+	if (GET_BITMASK(EBT_VLAN_PRIO)) {
+		if ((unsigned char) info->prio > 7) {
+			pr_debug("prio %d is out of range (0-7)\n",
+				 info->prio);
+			return -EINVAL;
+		}
+	}
+	/* Check for encapsulated proto range - it is possible to be
+	 * any value for u_short range.
+	 * if_ether.h:  ETH_ZLEN        60   -  Min. octets in frame sans FCS */
+	if (GET_BITMASK(EBT_VLAN_ENCAP)) {
+		if ((unsigned short) ntohs(info->encap) < ETH_ZLEN) {
+			pr_debug("encap frame length %d is less than "
+				 "minimal\n", ntohs(info->encap));
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static struct xt_match ebt_vlan_mt_reg __read_mostly = {
+	.name		= "vlan",
+	.revision	= 0,
+	.family		= NFPROTO_BRIDGE,
+	.match		= ebt_vlan_mt,
+	.checkentry	= ebt_vlan_mt_check,
+	.matchsize	= sizeof(struct ebt_vlan_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init ebt_vlan_init(void)
+{
+	pr_debug("ebtables 802.1Q extension module v" MODULE_VERS "\n");
+	return xt_register_match(&ebt_vlan_mt_reg);
+}
+
+static void __exit ebt_vlan_fini(void)
+{
+	xt_unregister_match(&ebt_vlan_mt_reg);
+}
+
+module_init(ebt_vlan_init);
+module_exit(ebt_vlan_fini);

net/bridge/netfilter/ebtable_broute.c

@@ -0,0 +1,102 @@
+/*
+ *  ebtable_broute
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2002
+ *
+ *  This table lets you choose between routing and bridging for frames
+ *  entering on a bridge enslaved nic. This table is traversed before any
+ *  other ebtables table. See net/bridge/br_input.c.
+ */
+
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/module.h>
+#include <linux/if_bridge.h>
+
+/* EBT_ACCEPT means the frame will be bridged
+ * EBT_DROP means the frame will be routed
+ */
+static struct ebt_entries initial_chain = {
+	.name		= "BROUTING",
+	.policy		= EBT_ACCEPT,
+};
+
+static struct ebt_replace_kernel initial_table =
+{
+	.name		= "broute",
+	.valid_hooks	= 1 << NF_BR_BROUTING,
+	.entries_size	= sizeof(struct ebt_entries),
+	.hook_entry	= {
+		[NF_BR_BROUTING]	= &initial_chain,
+	},
+	.entries	= (char *)&initial_chain,
+};
+
+static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
+{
+	if (valid_hooks & ~(1 << NF_BR_BROUTING))
+		return -EINVAL;
+	return 0;
+}
+
+static const struct ebt_table broute_table =
+{
+	.name		= "broute",
+	.table		= &initial_table,
+	.valid_hooks	= 1 << NF_BR_BROUTING,
+	.check		= check,
+	.me		= THIS_MODULE,
+};
+
+static int ebt_broute(struct sk_buff *skb)
+{
+	int ret;
+
+	ret = ebt_do_table(NF_BR_BROUTING, skb, skb->dev, NULL,
+			   dev_net(skb->dev)->xt.broute_table);
+	if (ret == NF_DROP)
+		return 1; /* route it */
+	return 0; /* bridge it */
+}
+
+static int __net_init broute_net_init(struct net *net)
+{
+	net->xt.broute_table = ebt_register_table(net, &broute_table);
+	return PTR_RET(net->xt.broute_table);
+}
+
+static void __net_exit broute_net_exit(struct net *net)
+{
+	ebt_unregister_table(net, net->xt.broute_table);
+}
+
+static struct pernet_operations broute_net_ops = {
+	.init = broute_net_init,
+	.exit = broute_net_exit,
+};
+
+static int __init ebtable_broute_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&broute_net_ops);
+	if (ret < 0)
+		return ret;
+	/* see br_input.c */
+	RCU_INIT_POINTER(br_should_route_hook,
+			   (br_should_route_hook_t *)ebt_broute);
+	return 0;
+}
+
+static void __exit ebtable_broute_fini(void)
+{
+	RCU_INIT_POINTER(br_should_route_hook, NULL);
+	synchronize_net();
+	unregister_pernet_subsys(&broute_net_ops);
+}
+
+module_init(ebtable_broute_init);
+module_exit(ebtable_broute_fini);
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebtable_filter.c

@@ -0,0 +1,137 @@
+/*
+ *  ebtable_filter
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2002
+ *
+ */
+
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/module.h>
+
+#define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \
+   (1 << NF_BR_LOCAL_OUT))
+
+static struct ebt_entries initial_chains[] =
+{
+	{
+		.name	= "INPUT",
+		.policy	= EBT_ACCEPT,
+	},
+	{
+		.name	= "FORWARD",
+		.policy	= EBT_ACCEPT,
+	},
+	{
+		.name	= "OUTPUT",
+		.policy	= EBT_ACCEPT,
+	},
+};
+
+static struct ebt_replace_kernel initial_table =
+{
+	.name		= "filter",
+	.valid_hooks	= FILTER_VALID_HOOKS,
+	.entries_size	= 3 * sizeof(struct ebt_entries),
+	.hook_entry	= {
+		[NF_BR_LOCAL_IN]	= &initial_chains[0],
+		[NF_BR_FORWARD]		= &initial_chains[1],
+		[NF_BR_LOCAL_OUT]	= &initial_chains[2],
+	},
+	.entries	= (char *)initial_chains,
+};
+
+static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
+{
+	if (valid_hooks & ~FILTER_VALID_HOOKS)
+		return -EINVAL;
+	return 0;
+}
+
+static const struct ebt_table frame_filter =
+{
+	.name		= "filter",
+	.table		= &initial_table,
+	.valid_hooks	= FILTER_VALID_HOOKS,
+	.check		= check,
+	.me		= THIS_MODULE,
+};
+
+static unsigned int
+ebt_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
+   const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_filter);
+}
+
+static unsigned int
+ebt_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
+   const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_filter);
+}
+
+static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
+	{
+		.hook		= ebt_in_hook,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_IN,
+		.priority	= NF_BR_PRI_FILTER_BRIDGED,
+	},
+	{
+		.hook		= ebt_in_hook,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_FORWARD,
+		.priority	= NF_BR_PRI_FILTER_BRIDGED,
+	},
+	{
+		.hook		= ebt_out_hook,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_OUT,
+		.priority	= NF_BR_PRI_FILTER_OTHER,
+	},
+};
+
+static int __net_init frame_filter_net_init(struct net *net)
+{
+	net->xt.frame_filter = ebt_register_table(net, &frame_filter);
+	return PTR_RET(net->xt.frame_filter);
+}
+
+static void __net_exit frame_filter_net_exit(struct net *net)
+{
+	ebt_unregister_table(net, net->xt.frame_filter);
+}
+
+static struct pernet_operations frame_filter_net_ops = {
+	.init = frame_filter_net_init,
+	.exit = frame_filter_net_exit,
+};
+
+static int __init ebtable_filter_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&frame_filter_net_ops);
+	if (ret < 0)
+		return ret;
+	ret = nf_register_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter));
+	if (ret < 0)
+		unregister_pernet_subsys(&frame_filter_net_ops);
+	return ret;
+}
+
+static void __exit ebtable_filter_fini(void)
+{
+	nf_unregister_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter));
+	unregister_pernet_subsys(&frame_filter_net_ops);
+}
+
+module_init(ebtable_filter_init);
+module_exit(ebtable_filter_fini);
+MODULE_LICENSE("GPL");

net/bridge/netfilter/ebtable_nat.c

@@ -0,0 +1,137 @@
+/*
+ *  ebtable_nat
+ *
+ *	Authors:
+ *	Bart De Schuymer <bdschuym@pandora.be>
+ *
+ *  April, 2002
+ *
+ */
+
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/module.h>
+
+#define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \
+   (1 << NF_BR_POST_ROUTING))
+
+static struct ebt_entries initial_chains[] =
+{
+	{
+		.name	= "PREROUTING",
+		.policy	= EBT_ACCEPT,
+	},
+	{
+		.name	= "OUTPUT",
+		.policy	= EBT_ACCEPT,
+	},
+	{
+		.name	= "POSTROUTING",
+		.policy	= EBT_ACCEPT,
+	}
+};
+
+static struct ebt_replace_kernel initial_table =
+{
+	.name		= "nat",
+	.valid_hooks	= NAT_VALID_HOOKS,
+	.entries_size	= 3 * sizeof(struct ebt_entries),
+	.hook_entry	= {
+		[NF_BR_PRE_ROUTING]	= &initial_chains[0],
+		[NF_BR_LOCAL_OUT]	= &initial_chains[1],
+		[NF_BR_POST_ROUTING]	= &initial_chains[2],
+	},
+	.entries	= (char *)initial_chains,
+};
+
+static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
+{
+	if (valid_hooks & ~NAT_VALID_HOOKS)
+		return -EINVAL;
+	return 0;
+}
+
+static struct ebt_table frame_nat =
+{
+	.name		= "nat",
+	.table		= &initial_table,
+	.valid_hooks	= NAT_VALID_HOOKS,
+	.check		= check,
+	.me		= THIS_MODULE,
+};
+
+static unsigned int
+ebt_nat_in(unsigned int hook, struct sk_buff *skb, const struct net_device *in
+   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_nat);
+}
+
+static unsigned int
+ebt_nat_out(unsigned int hook, struct sk_buff *skb, const struct net_device *in
+   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_nat);
+}
+
+static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
+	{
+		.hook		= ebt_nat_out,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_OUT,
+		.priority	= NF_BR_PRI_NAT_DST_OTHER,
+	},
+	{
+		.hook		= ebt_nat_out,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_POST_ROUTING,
+		.priority	= NF_BR_PRI_NAT_SRC,
+	},
+	{
+		.hook		= ebt_nat_in,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_PRE_ROUTING,
+		.priority	= NF_BR_PRI_NAT_DST_BRIDGED,
+	},
+};
+
+static int __net_init frame_nat_net_init(struct net *net)
+{
+	net->xt.frame_nat = ebt_register_table(net, &frame_nat);
+	return PTR_RET(net->xt.frame_nat);
+}
+
+static void __net_exit frame_nat_net_exit(struct net *net)
+{
+	ebt_unregister_table(net, net->xt.frame_nat);
+}
+
+static struct pernet_operations frame_nat_net_ops = {
+	.init = frame_nat_net_init,
+	.exit = frame_nat_net_exit,
+};
+
+static int __init ebtable_nat_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&frame_nat_net_ops);
+	if (ret < 0)
+		return ret;
+	ret = nf_register_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat));
+	if (ret < 0)
+		unregister_pernet_subsys(&frame_nat_net_ops);
+	return ret;
+}
+
+static void __exit ebtable_nat_fini(void)
+{
+	nf_unregister_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat));
+	unregister_pernet_subsys(&frame_nat_net_ops);
+}
+
+module_init(ebtable_nat_init);
+module_exit(ebtable_nat_fini);
+MODULE_LICENSE("GPL");