linux_old1/net/bridge/br_private.h

821 lines
23 KiB
C
Raw Normal View History

/*
* 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[ETH_ALEN];
};
struct mac_addr
{
unsigned char addr[ETH_ALEN];
};
struct br_ip
{
union {
__be32 ip4;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
} u;
__be16 proto;
__u16 vid;
};
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
/* our own querier */
struct bridge_mcast_own_query {
struct timer_list timer;
u32 startup_sent;
};
/* other querier */
struct bridge_mcast_other_query {
struct timer_list timer;
unsigned long delay_time;
};
#endif
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;
unsigned char added_by_user;
__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
#define BR_LEARNING 0x00000020
#define BR_FLOOD 0x00000040
#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
#define BR_PROMISC 0x00000080
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
struct bridge_mcast_own_query ip4_own_query;
#if IS_ENABLED(CONFIG_IPV6)
struct bridge_mcast_own_query ip6_own_query;
#endif /* IS_ENABLED(CONFIG_IPV6) */
unsigned char multicast_router;
struct timer_list multicast_router_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_auto_port(p) ((p)->flags & BR_AUTO_MASK)
#define br_promisc_port(p) ((p)->flags & BR_PROMISC)
#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 net_bridge
{
spinlock_t lock;
struct list_head port_list;
struct net_device *dev;
struct pcpu_sw_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;
u8 multicast_query_use_ifaddr:1;
u32 hash_elasticity;
u32 hash_max;
u32 multicast_last_member_count;
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 bridge_mcast_other_query ip4_other_query;
struct bridge_mcast_own_query ip4_own_query;
#if IS_ENABLED(CONFIG_IPV6)
struct bridge_mcast_other_query ip6_other_query;
struct bridge_mcast_own_query ip6_own_query;
#endif /* IS_ENABLED(CONFIG_IPV6) */
#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;
u32 auto_cnt;
#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)
/* 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 */
void br_dev_setup(struct net_device *dev);
void br_dev_delete(struct net_device *dev, struct list_head *list);
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev);
#ifdef CONFIG_NET_POLL_CONTROLLER
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);
}
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
int br_netpoll_enable(struct net_bridge_port *p);
void br_netpoll_disable(struct net_bridge_port *p);
#else
static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
struct sk_buff *skb)
{
}
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
static inline int br_netpoll_enable(struct net_bridge_port *p)
{
return 0;
}
static inline void br_netpoll_disable(struct net_bridge_port *p)
{
}
#endif
/* br_fdb.c */
int br_fdb_init(void);
void br_fdb_fini(void);
void br_fdb_flush(struct net_bridge *br);
void br_fdb_find_delete_local(struct net_bridge *br,
const struct net_bridge_port *p,
const unsigned char *addr, u16 vid);
void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr);
void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
void br_fdb_cleanup(unsigned long arg);
void br_fdb_delete_by_port(struct net_bridge *br,
const struct net_bridge_port *p, int do_all);
struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
const unsigned char *addr, __u16 vid);
int br_fdb_test_addr(struct net_device *dev, unsigned char *addr);
int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count,
unsigned long off);
int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid, bool added_by_user);
int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev, const unsigned char *addr);
int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
const unsigned char *addr, u16 nlh_flags);
int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev, int idx);
int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
/* br_forward.c */
void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
int br_dev_queue_push_xmit(struct sk_buff *skb);
void br_forward(const struct net_bridge_port *to,
struct sk_buff *skb, struct sk_buff *skb0);
int br_forward_finish(struct sk_buff *skb);
void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast);
void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
struct sk_buff *skb2, bool unicast);
/* br_if.c */
void br_port_carrier_check(struct net_bridge_port *p);
int br_add_bridge(struct net *net, const char *name);
int br_del_bridge(struct net *net, const char *name);
int br_add_if(struct net_bridge *br, struct net_device *dev);
int br_del_if(struct net_bridge *br, struct net_device *dev);
int br_min_mtu(const struct net_bridge *br);
netdev_features_t br_features_recompute(struct net_bridge *br,
netdev_features_t features);
void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
void br_manage_promisc(struct net_bridge *br);
/* br_input.c */
int br_handle_frame_finish(struct sk_buff *skb);
rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler) == br_handle_frame;
}
static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev)
{
return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL;
}
/* br_ioctl.c */
int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
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;
int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
struct sk_buff *skb, u16 vid);
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
struct sk_buff *skb, u16 vid);
void br_multicast_add_port(struct net_bridge_port *port);
void br_multicast_del_port(struct net_bridge_port *port);
void br_multicast_enable_port(struct net_bridge_port *port);
void br_multicast_disable_port(struct net_bridge_port *port);
void br_multicast_init(struct net_bridge *br);
void br_multicast_open(struct net_bridge *br);
void br_multicast_stop(struct net_bridge *br);
void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb);
void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb, struct sk_buff *skb2);
int br_multicast_set_router(struct net_bridge *br, unsigned long val);
int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val);
int br_multicast_toggle(struct net_bridge *br, unsigned long val);
int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
struct net_bridge_mdb_entry *
br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst);
struct net_bridge_mdb_entry *
br_multicast_new_group(struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group);
void br_multicast_free_pg(struct rcu_head *head);
struct net_bridge_port_group *
br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
struct net_bridge_port_group __rcu *next,
unsigned char state);
void br_mdb_init(void);
void br_mdb_uninit(void);
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))
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));
}
static inline bool
__br_multicast_querier_exists(struct net_bridge *br,
struct bridge_mcast_other_query *querier)
{
return time_is_before_jiffies(querier->delay_time) &&
(br->multicast_querier || timer_pending(&querier->timer));
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
struct ethhdr *eth)
{
switch (eth->h_proto) {
case (htons(ETH_P_IP)):
return __br_multicast_querier_exists(br, &br->ip4_other_query);
#if IS_ENABLED(CONFIG_IPV6)
case (htons(ETH_P_IPV6)):
return __br_multicast_querier_exists(br, &br->ip6_other_query);
#endif
default:
return false;
}
}
#else
static inline int br_multicast_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb,
u16 vid)
{
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 bool br_multicast_querier_exists(struct net_bridge *br,
struct ethhdr *eth)
{
return false;
}
static inline void br_mdb_init(void)
{
}
static inline void br_mdb_uninit(void)
{
}
#endif
/* br_vlan.c */
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
struct sk_buff *skb, u16 *vid);
bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
const struct sk_buff *skb);
bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *v,
struct sk_buff *skb);
int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
int br_vlan_delete(struct net_bridge *br, u16 vid);
void br_vlan_flush(struct net_bridge *br);
bridge: Fix the way to check if a local fdb entry can be deleted We should take into account the followings when deleting a local fdb entry. - nbp_vlan_find() can be used only when vid != 0 to check if an entry is deletable, because a fdb entry with vid 0 can exist at any time while nbp_vlan_find() always return false with vid 0. Example of problematic case: ip link set eth0 address 12:34:56:78:90:ab ip link set eth1 address 12:34:56:78:90:ab brctl addif br0 eth0 brctl addif br0 eth1 ip link set eth0 address aa:bb:cc:dd:ee:ff Then, the fdb entry 12:34:56:78:90:ab will be deleted even though the bridge port eth1 still has that address. - The port to which the bridge device is attached might needs a local entry if its mac address is set manually. Example of problematic case: ip link set eth0 address 12:34:56:78:90:ab brctl addif br0 eth0 ip link set br0 address 12:34:56:78:90:ab ip link set eth0 address aa:bb:cc:dd:ee:ff Then, the fdb still must have the entry 12:34:56:78:90:ab, but it will be deleted. We can use br->dev->addr_assign_type to check if the address is manually set or not, but I propose another approach. Since we delete and insert local entries whenever changing mac address of the bridge device, we can change dst of the entry to NULL regardless of addr_assign_type when deleting an entry associated with a certain port, and if it is found to be unnecessary later, then delete it. That is, if changing mac address of a port, the entry might be changed to its dst being NULL first, but is eventually deleted when recalculating and changing bridge id. This approach is especially useful when we want to share the code with deleting vlan in which the bridge device might want such an entry regardless of addr_assign_type, and makes things easy because we don't have to consider if mac address of the bridge device will be changed or not at the time we delete a local entry of a port, which means fdb code will not be bothered even if the bridge id calculating logic is changed in the future. Also, this change reduces inconsistent state, where frames whose dst is the mac address of the bridge, can't reach the bridge because of premature fdb entry deletion. This change reduces the possibility that the bridge device replies unreachable mac address to arp requests, which could occur during the short window between calling del_nbp() and br_stp_recalculate_bridge_id() in br_del_if(). This will effective after br_fdb_delete_by_port() starts to use the same code by following patch. Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-07 15:48:22 +08:00
bool br_vlan_find(struct net_bridge *br, u16 vid);
int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
void nbp_vlan_flush(struct net_bridge_port *port);
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_N_VID;
}
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
static inline int br_vlan_enabled(struct net_bridge *br)
{
return br->vlan_enabled;
}
#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 bool br_should_learn(struct net_bridge_port *p,
struct sk_buff *skb, u16 *vid)
{
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)
{
}
bridge: Fix the way to check if a local fdb entry can be deleted We should take into account the followings when deleting a local fdb entry. - nbp_vlan_find() can be used only when vid != 0 to check if an entry is deletable, because a fdb entry with vid 0 can exist at any time while nbp_vlan_find() always return false with vid 0. Example of problematic case: ip link set eth0 address 12:34:56:78:90:ab ip link set eth1 address 12:34:56:78:90:ab brctl addif br0 eth0 brctl addif br0 eth1 ip link set eth0 address aa:bb:cc:dd:ee:ff Then, the fdb entry 12:34:56:78:90:ab will be deleted even though the bridge port eth1 still has that address. - The port to which the bridge device is attached might needs a local entry if its mac address is set manually. Example of problematic case: ip link set eth0 address 12:34:56:78:90:ab brctl addif br0 eth0 ip link set br0 address 12:34:56:78:90:ab ip link set eth0 address aa:bb:cc:dd:ee:ff Then, the fdb still must have the entry 12:34:56:78:90:ab, but it will be deleted. We can use br->dev->addr_assign_type to check if the address is manually set or not, but I propose another approach. Since we delete and insert local entries whenever changing mac address of the bridge device, we can change dst of the entry to NULL regardless of addr_assign_type when deleting an entry associated with a certain port, and if it is found to be unnecessary later, then delete it. That is, if changing mac address of a port, the entry might be changed to its dst being NULL first, but is eventually deleted when recalculating and changing bridge id. This approach is especially useful when we want to share the code with deleting vlan in which the bridge device might want such an entry regardless of addr_assign_type, and makes things easy because we don't have to consider if mac address of the bridge device will be changed or not at the time we delete a local entry of a port, which means fdb code will not be bothered even if the bridge id calculating logic is changed in the future. Also, this change reduces inconsistent state, where frames whose dst is the mac address of the bridge, can't reach the bridge because of premature fdb entry deletion. This change reduces the possibility that the bridge device replies unreachable mac address to arp requests, which could occur during the short window between calling del_nbp() and br_stp_recalculate_bridge_id() in br_del_if(). This will effective after br_fdb_delete_by_port() starts to use the same code by following patch. Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-07 15:48:22 +08:00
static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
{
return false;
}
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 */
}
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
static inline int br_vlan_enabled(struct net_bridge *br)
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
{
return 0;
}
#endif
/* br_netfilter.c */
#ifdef CONFIG_BRIDGE_NETFILTER
int br_netfilter_init(void);
void br_netfilter_fini(void);
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 */
void br_log_state(const struct net_bridge_port *p);
struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no);
void br_init_port(struct net_bridge_port *p);
void br_become_designated_port(struct net_bridge_port *p);
void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
int br_set_forward_delay(struct net_bridge *br, unsigned long x);
int br_set_hello_time(struct net_bridge *br, unsigned long x);
int br_set_max_age(struct net_bridge *br, unsigned long x);
/* br_stp_if.c */
void br_stp_enable_bridge(struct net_bridge *br);
void br_stp_disable_bridge(struct net_bridge *br);
void br_stp_set_enabled(struct net_bridge *br, unsigned long val);
void br_stp_enable_port(struct net_bridge_port *p);
void br_stp_disable_port(struct net_bridge_port *p);
bool br_stp_recalculate_bridge_id(struct net_bridge *br);
void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a);
void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio);
int br_stp_set_port_priority(struct net_bridge_port *p, unsigned long newprio);
int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost);
ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id);
/* br_stp_bpdu.c */
struct stp_proto;
void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
struct net_device *dev);
/* br_stp_timer.c */
void br_stp_timer_init(struct net_bridge *br);
void br_stp_port_timer_init(struct net_bridge_port *p);
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;
int br_netlink_init(void);
void br_netlink_fini(void);
void br_ifinfo_notify(int event, struct net_bridge_port *port);
int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg);
int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg);
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;
int br_sysfs_addif(struct net_bridge_port *p);
int br_sysfs_renameif(struct net_bridge_port *p);
/* br_sysfs_br.c */
int br_sysfs_addbr(struct net_device *dev);
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