Merge branch 'bridge-non-promisc'
Vlad Yasevich says:
====================
bridge: Non-promisc bridge ports support
This series adds functionality to the bridge device to enable
operations without setting all ports to promiscuous mode.
The basic concept is this. The bridge keeps track of the ports
that support learning and flooding packets to unknown destinations.
We call these ports auto-discovery ports since they automatically
discover who is behind them through learning and flooding.
If flooding and learning are disabled via flags, then the port
requires static configuration to tell it which mac addresses
are behind it. This is accomplished through adding of fdbs.
These fdbs should be static as dynamic fdbs can expire and systems
will become unreachable due to lack of flooding.
If the user marks all ports as needing static configuration then
we can safely make them non-promiscuous since we will know all the
information about them.
If the user leaves only 1 port as automatic, then we can mark
that port as not-promiscuous as well. One could think of
this a edge relay similar to what's support by embedded switches
in SRIOV devices. Since we have all the information about the
other ports, we can just program the mac addresses into the
single automatic port to receive all necessary traffic.
More information about this is patch 6.
In other cases, we keep all ports promiscuous as before.
There are some other cases when promiscuous mode has to be turned
back on. One is when the bridge itself if placed in promiscuous
mode (user sets promisc flag). The other is if vlan filtering is
turned off. Since this is the default configuration, the default
bridge operation is not changed.
Changes since v2:
- White space and spelling fixes from Michael Tsirkin
- Squash patches 6, 7 and 8 to prevent bisect breakage.
Changes since v1:
- Address issues rasied by Stephen Heminger
- Address initializer comments raised by Sergey Shtylyov
- Rebased recent net-next.
Changes since rfc v2:
- Better description of in the commit logs
- Leave port in promiscuous mode if IFF_UNICAST_FLT is disabled on the
device.
- Fix issue with flag masking
- Rework patch ordering a bit.
Changes since rfc v1:
- Removed private list. We now traverse the fdb hashtable itself
to write necessary addresses to the ports (Stephen's concern)
- Add learning flag to the mask for flags that decides if the port
is 'auto' or not (suggest by MST and Jamal).
- Simplified tracking of such ports at the cost of a loop over all
ports (suggested by MST)
I've played with quite a large number of ports and the current approach
seems to work fairly well.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9212015..d77e2f0 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -112,6 +112,12 @@
{
}
+static void br_dev_change_rx_flags(struct net_device *dev, int change)
+{
+ if (change & IFF_PROMISC)
+ br_manage_promisc(netdev_priv(dev));
+}
+
static int br_dev_stop(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
@@ -309,6 +315,7 @@
.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_rx_flags = br_dev_change_rx_flags,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 9203d5a..648d0e8 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -85,8 +85,58 @@
kmem_cache_free(br_fdb_cache, ent);
}
+/* When a static FDB entry is added, the mac address from the entry is
+ * added to the bridge private HW address list and all required ports
+ * are then updated with the new information.
+ * Called under RTNL.
+ */
+static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr)
+{
+ int err;
+ struct net_bridge_port *p, *tmp;
+
+ ASSERT_RTNL();
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (!br_promisc_port(p)) {
+ err = dev_uc_add(p->dev, addr);
+ if (err)
+ goto undo;
+ }
+ }
+
+ return;
+undo:
+ list_for_each_entry(tmp, &br->port_list, list) {
+ if (tmp == p)
+ break;
+ if (!br_promisc_port(tmp))
+ dev_uc_del(tmp->dev, addr);
+ }
+}
+
+/* When a static FDB entry is deleted, the HW address from that entry is
+ * also removed from the bridge private HW address list and updates all
+ * the ports with needed information.
+ * Called under RTNL.
+ */
+static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr)
+{
+ struct net_bridge_port *p;
+
+ ASSERT_RTNL();
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (!br_promisc_port(p))
+ dev_uc_del(p->dev, addr);
+ }
+}
+
static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
{
+ if (f->is_static)
+ fdb_del_hw(br, f->addr.addr);
+
hlist_del_rcu(&f->hlist);
fdb_notify(br, f, RTM_DELNEIGH);
call_rcu(&f->rcu, fdb_rcu_free);
@@ -466,6 +516,7 @@
return -ENOMEM;
fdb->is_local = fdb->is_static = 1;
+ fdb_add_hw(br, addr);
fdb_notify(br, fdb, RTM_NEWNEIGH);
return 0;
}
@@ -678,13 +729,25 @@
}
if (fdb_to_nud(fdb) != state) {
- if (state & NUD_PERMANENT)
- fdb->is_local = fdb->is_static = 1;
- else if (state & NUD_NOARP) {
+ if (state & NUD_PERMANENT) {
+ fdb->is_local = 1;
+ if (!fdb->is_static) {
+ fdb->is_static = 1;
+ fdb_add_hw(br, addr);
+ }
+ } else if (state & NUD_NOARP) {
fdb->is_local = 0;
- fdb->is_static = 1;
- } else
- fdb->is_local = fdb->is_static = 0;
+ if (!fdb->is_static) {
+ fdb->is_static = 1;
+ fdb_add_hw(br, addr);
+ }
+ } else {
+ fdb->is_local = 0;
+ if (fdb->is_static) {
+ fdb->is_static = 0;
+ fdb_del_hw(br, addr);
+ }
+ }
modified = true;
}
@@ -874,3 +937,59 @@
out:
return err;
}
+
+int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+ struct net_bridge_fdb_entry *fdb, *tmp;
+ int i;
+ int err;
+
+ ASSERT_RTNL();
+
+ for (i = 0; i < BR_HASH_SIZE; i++) {
+ hlist_for_each_entry(fdb, &br->hash[i], hlist) {
+ /* We only care for static entries */
+ if (!fdb->is_static)
+ continue;
+
+ err = dev_uc_add(p->dev, fdb->addr.addr);
+ if (err)
+ goto rollback;
+ }
+ }
+ return 0;
+
+rollback:
+ for (i = 0; i < BR_HASH_SIZE; i++) {
+ hlist_for_each_entry(tmp, &br->hash[i], hlist) {
+ /* If we reached the fdb that failed, we can stop */
+ if (tmp == fdb)
+ break;
+
+ /* We only care for static entries */
+ if (!tmp->is_static)
+ continue;
+
+ dev_uc_del(p->dev, tmp->addr.addr);
+ }
+ }
+ return err;
+}
+
+void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+ struct net_bridge_fdb_entry *fdb;
+ int i;
+
+ ASSERT_RTNL();
+
+ for (i = 0; i < BR_HASH_SIZE; i++) {
+ hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) {
+ /* We only care for static entries */
+ if (!fdb->is_static)
+ continue;
+
+ dev_uc_del(p->dev, fdb->addr.addr);
+ }
+ }
+}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 5262b86..091d39f 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -85,6 +85,110 @@
spin_unlock_bh(&br->lock);
}
+static void br_port_set_promisc(struct net_bridge_port *p)
+{
+ int err = 0;
+
+ if (br_promisc_port(p))
+ return;
+
+ err = dev_set_promiscuity(p->dev, 1);
+ if (err)
+ return;
+
+ br_fdb_unsync_static(p->br, p);
+ p->flags |= BR_PROMISC;
+}
+
+static void br_port_clear_promisc(struct net_bridge_port *p)
+{
+ int err;
+
+ /* Check if the port is already non-promisc or if it doesn't
+ * support UNICAST filtering. Without unicast filtering support
+ * we'll end up re-enabling promisc mode anyway, so just check for
+ * it here.
+ */
+ if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT))
+ return;
+
+ /* Since we'll be clearing the promisc mode, program the port
+ * first so that we don't have interruption in traffic.
+ */
+ err = br_fdb_sync_static(p->br, p);
+ if (err)
+ return;
+
+ dev_set_promiscuity(p->dev, -1);
+ p->flags &= ~BR_PROMISC;
+}
+
+/* When a port is added or removed or when certain port flags
+ * change, this function is called to automatically manage
+ * promiscuity setting of all the bridge ports. We are always called
+ * under RTNL so can skip using rcu primitives.
+ */
+void br_manage_promisc(struct net_bridge *br)
+{
+ struct net_bridge_port *p;
+ bool set_all = false;
+
+ /* If vlan filtering is disabled or bridge interface is placed
+ * into promiscuous mode, place all ports in promiscuous mode.
+ */
+ if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br))
+ set_all = true;
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (set_all) {
+ br_port_set_promisc(p);
+ } else {
+ /* If the number of auto-ports is <= 1, then all other
+ * ports will have their output configuration
+ * statically specified through fdbs. Since ingress
+ * on the auto-port becomes forwarding/egress to other
+ * ports and egress configuration is statically known,
+ * we can say that ingress configuration of the
+ * auto-port is also statically known.
+ * This lets us disable promiscuous mode and write
+ * this config to hw.
+ */
+ if (br->auto_cnt <= br_auto_port(p))
+ br_port_clear_promisc(p);
+ else
+ br_port_set_promisc(p);
+ }
+ }
+}
+
+static void nbp_update_port_count(struct net_bridge *br)
+{
+ struct net_bridge_port *p;
+ u32 cnt = 0;
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (br_auto_port(p))
+ cnt++;
+ }
+ if (br->auto_cnt != cnt) {
+ br->auto_cnt = cnt;
+ br_manage_promisc(br);
+ }
+}
+
+static void nbp_delete_promisc(struct net_bridge_port *p)
+{
+ /* If port is currently promiscous, unset promiscuity.
+ * Otherwise, it is a static port so remove all addresses
+ * from it.
+ */
+ dev_set_allmulti(p->dev, -1);
+ if (br_promisc_port(p))
+ dev_set_promiscuity(p->dev, -1);
+ else
+ br_fdb_unsync_static(p->br, p);
+}
+
static void release_nbp(struct kobject *kobj)
{
struct net_bridge_port *p
@@ -133,7 +237,7 @@
sysfs_remove_link(br->ifobj, p->dev->name);
- dev_set_promiscuity(dev, -1);
+ nbp_delete_promisc(p);
spin_lock_bh(&br->lock);
br_stp_disable_port(p);
@@ -141,10 +245,11 @@
br_ifinfo_notify(RTM_DELLINK, p);
+ list_del_rcu(&p->list);
+
nbp_vlan_flush(p);
br_fdb_delete_by_port(br, p, 1);
-
- list_del_rcu(&p->list);
+ nbp_update_port_count(br);
dev->priv_flags &= ~IFF_BRIDGE_PORT;
@@ -353,7 +458,7 @@
call_netdevice_notifiers(NETDEV_JOIN, dev);
- err = dev_set_promiscuity(dev, 1);
+ err = dev_set_allmulti(dev, 1);
if (err)
goto put_back;
@@ -384,6 +489,8 @@
list_add_rcu(&p->list, &br->port_list);
+ nbp_update_port_count(br);
+
netdev_update_features(br->dev);
if (br->dev->needed_headroom < dev->needed_headroom)
@@ -455,3 +562,11 @@
return 0;
}
+
+void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
+{
+ struct net_bridge *br = p->br;
+
+ if (mask & BR_AUTO_MASK)
+ nbp_update_port_count(br);
+}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e8844d9..26edb51 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -328,6 +328,7 @@
static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
{
int err;
+ unsigned long old_flags = p->flags;
br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
@@ -353,6 +354,8 @@
if (err)
return err;
}
+
+ br_port_flags_change(p, old_flags ^ p->flags);
return 0;
}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 06811d7..2b2286d 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -174,6 +174,8 @@
#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_query ip4_query;
@@ -198,6 +200,9 @@
#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)
@@ -290,6 +295,7 @@
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;
@@ -395,6 +401,8 @@
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);
@@ -415,6 +423,8 @@
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);
+void br_manage_promisc(struct net_bridge *br);
/* br_input.c */
int br_handle_frame_finish(struct sk_buff *skb);
@@ -632,6 +642,10 @@
return v->pvid ?: VLAN_N_VID;
}
+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,
@@ -712,6 +726,11 @@
{
return VLAN_N_VID; /* Returns invalid vid */
}
+
+static inline int br_vlan_enabled(struct net_bridge *br);
+{
+ return 0;
+}
#endif
/* br_netfilter.c */
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index dd595bd..e561cd5 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -41,20 +41,30 @@
} \
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; \
+ return store_flag(p, v, _mask); \
} \
static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR, \
show_##_name, store_##_name)
+static int store_flag(struct net_bridge_port *p, unsigned long v,
+ unsigned long mask)
+{
+ unsigned long flags;
+
+ flags = p->flags;
+
+ if (v)
+ flags |= mask;
+ else
+ flags &= ~mask;
+
+ if (flags != p->flags) {
+ p->flags = flags;
+ br_port_flags_change(p, mask);
+ br_ifinfo_notify(RTM_NEWLINK, p);
+ }
+ return 0;
+}
static ssize_t show_path_cost(struct net_bridge_port *p, char *buf)
{
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 4a37161..24c5cc5 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -332,6 +332,7 @@
goto unlock;
br->vlan_enabled = val;
+ br_manage_promisc(br);
unlock:
rtnl_unlock();