net: bridge: mdb: move all switchdev logic to br_switchdev.c

The following functions:

br_mdb_complete
br_switchdev_mdb_populate
br_mdb_replay_one
br_mdb_queue_one
br_mdb_replay
br_mdb_switchdev_host_port
br_mdb_switchdev_host
br_switchdev_mdb_notify

are only accessible from code paths where CONFIG_NET_SWITCHDEV is
enabled. So move them to br_switchdev.c, in order for that code to be
compiled out if that config option is disabled.

Note that br_switchdev.c gets build regardless of whether
CONFIG_BRIDGE_IGMP_SNOOPING is enabled or not, whereas br_mdb.c only got
built when CONFIG_BRIDGE_IGMP_SNOOPING was enabled. So to preserve
correct compilation with CONFIG_BRIDGE_IGMP_SNOOPING being disabled, we
must now place an #ifdef around these functions in br_switchdev.c.
The offending bridge data structures that need this are
br->multicast_lock and br->mdb_list, these are also compiled out of
struct net_bridge when CONFIG_BRIDGE_IGMP_SNOOPING is turned off.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/bridge/br_mdb.c

@@ -552,250 +552,6 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
 	return nlmsg_size;
 }
 
-struct br_mdb_complete_info {
-	struct net_bridge_port *port;
-	struct br_ip ip;
-};
-
-static void br_mdb_complete(struct net_device *dev, int err, void *priv)
-{
-	struct br_mdb_complete_info *data = priv;
-	struct net_bridge_port_group __rcu **pp;
-	struct net_bridge_port_group *p;
-	struct net_bridge_mdb_entry *mp;
-	struct net_bridge_port *port = data->port;
-	struct net_bridge *br = port->br;
-
-	if (err)
-		goto err;
-
-	spin_lock_bh(&br->multicast_lock);
-	mp = br_mdb_ip_get(br, &data->ip);
-	if (!mp)
-		goto out;
-	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
-	     pp = &p->next) {
-		if (p->key.port != port)
-			continue;
-		p->flags |= MDB_PG_FLAGS_OFFLOAD;
-	}
-out:
-	spin_unlock_bh(&br->multicast_lock);
-err:
-	kfree(priv);
-}
-
-static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb,
-				      const struct net_bridge_mdb_entry *mp)
-{
-	if (mp->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr);
-#if IS_ENABLED(CONFIG_IPV6)
-	else if (mp->addr.proto == htons(ETH_P_IPV6))
-		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr);
-#endif
-	else
-		ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr);
-
-	mdb->vid = mp->addr.vid;
-}
-
-static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
-			     const struct switchdev_obj_port_mdb *mdb,
-			     unsigned long action, const void *ctx,
-			     struct netlink_ext_ack *extack)
-{
-	struct switchdev_notifier_port_obj_info obj_info = {
-		.info = {
-			.dev = dev,
-			.extack = extack,
-			.ctx = ctx,
-		},
-		.obj = &mdb->obj,
-	};
-	int err;
-
-	err = nb->notifier_call(nb, action, &obj_info);
-	return notifier_to_errno(err);
-}
-
-static int br_mdb_queue_one(struct list_head *mdb_list,
-			    enum switchdev_obj_id id,
-			    const struct net_bridge_mdb_entry *mp,
-			    struct net_device *orig_dev)
-{
-	struct switchdev_obj_port_mdb *mdb;
-
-	mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC);
-	if (!mdb)
-		return -ENOMEM;
-
-	mdb->obj.id = id;
-	mdb->obj.orig_dev = orig_dev;
-	br_switchdev_mdb_populate(mdb, mp);
-	list_add_tail(&mdb->obj.list, mdb_list);
-
-	return 0;
-}
-
-int br_mdb_replay(struct net_device *br_dev, struct net_device *dev,
-		  const void *ctx, bool adding, struct notifier_block *nb,
-		  struct netlink_ext_ack *extack)
-{
-	const struct net_bridge_mdb_entry *mp;
-	struct switchdev_obj *obj, *tmp;
-	struct net_bridge *br;
-	unsigned long action;
-	LIST_HEAD(mdb_list);
-	int err = 0;
-
-	ASSERT_RTNL();
-
-	if (!nb)
-		return 0;
-
-	if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev))
-		return -EINVAL;
-
-	br = netdev_priv(br_dev);
-
-	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
-		return 0;
-
-	/* We cannot walk over br->mdb_list protected just by the rtnl_mutex,
-	 * because the write-side protection is br->multicast_lock. But we
-	 * need to emulate the [ blocking ] calling context of a regular
-	 * switchdev event, so since both br->multicast_lock and RCU read side
-	 * critical sections are atomic, we have no choice but to pick the RCU
-	 * read side lock, queue up all our events, leave the critical section
-	 * and notify switchdev from blocking context.
-	 */
-	rcu_read_lock();
-
-	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
-		struct net_bridge_port_group __rcu * const *pp;
-		const struct net_bridge_port_group *p;
-
-		if (mp->host_joined) {
-			err = br_mdb_queue_one(&mdb_list,
-					       SWITCHDEV_OBJ_ID_HOST_MDB,
-					       mp, br_dev);
-			if (err) {
-				rcu_read_unlock();
-				goto out_free_mdb;
-			}
-		}
-
-		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
-		     pp = &p->next) {
-			if (p->key.port->dev != dev)
-				continue;
-
-			err = br_mdb_queue_one(&mdb_list,
-					       SWITCHDEV_OBJ_ID_PORT_MDB,
-					       mp, dev);
-			if (err) {
-				rcu_read_unlock();
-				goto out_free_mdb;
-			}
-		}
-	}
-
-	rcu_read_unlock();
-
-	if (adding)
-		action = SWITCHDEV_PORT_OBJ_ADD;
-	else
-		action = SWITCHDEV_PORT_OBJ_DEL;
-
-	list_for_each_entry(obj, &mdb_list, list) {
-		err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj),
-					action, ctx, extack);
-		if (err)
-			goto out_free_mdb;
-	}
-
-out_free_mdb:
-	list_for_each_entry_safe(obj, tmp, &mdb_list, list) {
-		list_del(&obj->list);
-		kfree(SWITCHDEV_OBJ_PORT_MDB(obj));
-	}
-
-	return err;
-}
-
-static void br_mdb_switchdev_host_port(struct net_device *dev,
-				       struct net_device *lower_dev,
-				       struct net_bridge_mdb_entry *mp,
-				       int type)
-{
-	struct switchdev_obj_port_mdb mdb = {
-		.obj = {
-			.id = SWITCHDEV_OBJ_ID_HOST_MDB,
-			.flags = SWITCHDEV_F_DEFER,
-			.orig_dev = dev,
-		},
-	};
-
-	br_switchdev_mdb_populate(&mdb, mp);
-
-	switch (type) {
-	case RTM_NEWMDB:
-		switchdev_port_obj_add(lower_dev, &mdb.obj, NULL);
-		break;
-	case RTM_DELMDB:
-		switchdev_port_obj_del(lower_dev, &mdb.obj);
-		break;
-	}
-}
-
-static void br_mdb_switchdev_host(struct net_device *dev,
-				  struct net_bridge_mdb_entry *mp, int type)
-{
-	struct net_device *lower_dev;
-	struct list_head *iter;
-
-	netdev_for_each_lower_dev(dev, lower_dev, iter)
-		br_mdb_switchdev_host_port(dev, lower_dev, mp, type);
-}
-
-static void br_switchdev_mdb_notify(struct net_device *dev,
-				    struct net_bridge_mdb_entry *mp,
-				    struct net_bridge_port_group *pg,
-				    int type)
-{
-	struct br_mdb_complete_info *complete_info;
-	struct switchdev_obj_port_mdb mdb = {
-		.obj = {
-			.id = SWITCHDEV_OBJ_ID_PORT_MDB,
-			.flags = SWITCHDEV_F_DEFER,
-		},
-	};
-
-	if (!pg)
-		return br_mdb_switchdev_host(dev, mp, type);
-
-	br_switchdev_mdb_populate(&mdb, mp);
-
-	mdb.obj.orig_dev = pg->key.port->dev;
-	switch (type) {
-	case RTM_NEWMDB:
-		complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
-		if (!complete_info)
-			break;
-		complete_info->port = pg->key.port;
-		complete_info->ip = mp->addr;
-		mdb.obj.complete_priv = complete_info;
-		mdb.obj.complete = br_mdb_complete;
-		if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
-			kfree(complete_info);
-		break;
-	case RTM_DELMDB:
-		switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
-		break;
-	}
-}
-
 void br_mdb_notify(struct net_device *dev,
 		   struct net_bridge_mdb_entry *mp,
 		   struct net_bridge_port_group *pg,

net/bridge/br_private.h

@@ -956,9 +956,11 @@ int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on,
 				      struct netlink_ext_ack *extack);
 bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on);
 
-int br_mdb_replay(struct net_device *br_dev, struct net_device *dev,
-		  const void *ctx, bool adding, struct notifier_block *nb,
-		  struct netlink_ext_ack *extack);
+void br_switchdev_mdb_notify(struct net_device *dev,
+			     struct net_bridge_mdb_entry *mp,
+			     struct net_bridge_port_group *pg,
+			     int type);
+
 int br_rports_fill_info(struct sk_buff *skb,
 			const struct net_bridge_mcast *brmctx);
 int br_multicast_dump_querier_state(struct sk_buff *skb,
@@ -1394,12 +1396,11 @@ static inline bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan,
 	return false;
 }
 
-static inline int br_mdb_replay(struct net_device *br_dev,
-				struct net_device *dev, const void *ctx,
-				bool adding, struct notifier_block *nb,
-				struct netlink_ext_ack *extack)
+static inline void br_switchdev_mdb_notify(struct net_device *dev,
+					   struct net_bridge_mdb_entry *mp,
+					   struct net_bridge_port_group *pg,
+					   int type)
 {
-	return -EOPNOTSUPP;
 }
 
 static inline bool

net/bridge/br_switchdev.c

@@ -4,6 +4,7 @@
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
+#include <net/ip.h>
 #include <net/switchdev.h>
 
 #include "br_private.h"
@@ -412,6 +413,258 @@ static int br_vlan_replay(struct net_device *br_dev, struct net_device *dev,
 	return err;
 }
 
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+struct br_mdb_complete_info {
+	struct net_bridge_port *port;
+	struct br_ip ip;
+};
+
+static void br_mdb_complete(struct net_device *dev, int err, void *priv)
+{
+	struct br_mdb_complete_info *data = priv;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port *port = data->port;
+	struct net_bridge *br = port->br;
+
+	if (err)
+		goto err;
+
+	spin_lock_bh(&br->multicast_lock);
+	mp = br_mdb_ip_get(br, &data->ip);
+	if (!mp)
+		goto out;
+	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (p->key.port != port)
+			continue;
+		p->flags |= MDB_PG_FLAGS_OFFLOAD;
+	}
+out:
+	spin_unlock_bh(&br->multicast_lock);
+err:
+	kfree(priv);
+}
+
+static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb,
+				      const struct net_bridge_mdb_entry *mp)
+{
+	if (mp->addr.proto == htons(ETH_P_IP))
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (mp->addr.proto == htons(ETH_P_IPV6))
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr);
+#endif
+	else
+		ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr);
+
+	mdb->vid = mp->addr.vid;
+}
+
+static void br_mdb_switchdev_host_port(struct net_device *dev,
+				       struct net_device *lower_dev,
+				       struct net_bridge_mdb_entry *mp,
+				       int type)
+{
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_ID_HOST_MDB,
+			.flags = SWITCHDEV_F_DEFER,
+			.orig_dev = dev,
+		},
+	};
+
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	switch (type) {
+	case RTM_NEWMDB:
+		switchdev_port_obj_add(lower_dev, &mdb.obj, NULL);
+		break;
+	case RTM_DELMDB:
+		switchdev_port_obj_del(lower_dev, &mdb.obj);
+		break;
+	}
+}
+
+static void br_mdb_switchdev_host(struct net_device *dev,
+				  struct net_bridge_mdb_entry *mp, int type)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter)
+		br_mdb_switchdev_host_port(dev, lower_dev, mp, type);
+}
+
+static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
+			     const struct switchdev_obj_port_mdb *mdb,
+			     unsigned long action, const void *ctx,
+			     struct netlink_ext_ack *extack)
+{
+	struct switchdev_notifier_port_obj_info obj_info = {
+		.info = {
+			.dev = dev,
+			.extack = extack,
+			.ctx = ctx,
+		},
+		.obj = &mdb->obj,
+	};
+	int err;
+
+	err = nb->notifier_call(nb, action, &obj_info);
+	return notifier_to_errno(err);
+}
+
+static int br_mdb_queue_one(struct list_head *mdb_list,
+			    enum switchdev_obj_id id,
+			    const struct net_bridge_mdb_entry *mp,
+			    struct net_device *orig_dev)
+{
+	struct switchdev_obj_port_mdb *mdb;
+
+	mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC);
+	if (!mdb)
+		return -ENOMEM;
+
+	mdb->obj.id = id;
+	mdb->obj.orig_dev = orig_dev;
+	br_switchdev_mdb_populate(mdb, mp);
+	list_add_tail(&mdb->obj.list, mdb_list);
+
+	return 0;
+}
+
+void br_switchdev_mdb_notify(struct net_device *dev,
+			     struct net_bridge_mdb_entry *mp,
+			     struct net_bridge_port_group *pg,
+			     int type)
+{
+	struct br_mdb_complete_info *complete_info;
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_ID_PORT_MDB,
+			.flags = SWITCHDEV_F_DEFER,
+		},
+	};
+
+	if (!pg)
+		return br_mdb_switchdev_host(dev, mp, type);
+
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	mdb.obj.orig_dev = pg->key.port->dev;
+	switch (type) {
+	case RTM_NEWMDB:
+		complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
+		if (!complete_info)
+			break;
+		complete_info->port = pg->key.port;
+		complete_info->ip = mp->addr;
+		mdb.obj.complete_priv = complete_info;
+		mdb.obj.complete = br_mdb_complete;
+		if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
+			kfree(complete_info);
+		break;
+	case RTM_DELMDB:
+		switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
+		break;
+	}
+}
+#endif
+
+static int br_mdb_replay(struct net_device *br_dev, struct net_device *dev,
+			 const void *ctx, bool adding,
+			 struct notifier_block *nb,
+			 struct netlink_ext_ack *extack)
+{
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	const struct net_bridge_mdb_entry *mp;
+	struct switchdev_obj *obj, *tmp;
+	struct net_bridge *br;
+	unsigned long action;
+	LIST_HEAD(mdb_list);
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	if (!nb)
+		return 0;
+
+	if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev))
+		return -EINVAL;
+
+	br = netdev_priv(br_dev);
+
+	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		return 0;
+
+	/* We cannot walk over br->mdb_list protected just by the rtnl_mutex,
+	 * because the write-side protection is br->multicast_lock. But we
+	 * need to emulate the [ blocking ] calling context of a regular
+	 * switchdev event, so since both br->multicast_lock and RCU read side
+	 * critical sections are atomic, we have no choice but to pick the RCU
+	 * read side lock, queue up all our events, leave the critical section
+	 * and notify switchdev from blocking context.
+	 */
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
+		struct net_bridge_port_group __rcu * const *pp;
+		const struct net_bridge_port_group *p;
+
+		if (mp->host_joined) {
+			err = br_mdb_queue_one(&mdb_list,
+					       SWITCHDEV_OBJ_ID_HOST_MDB,
+					       mp, br_dev);
+			if (err) {
+				rcu_read_unlock();
+				goto out_free_mdb;
+			}
+		}
+
+		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
+		     pp = &p->next) {
+			if (p->key.port->dev != dev)
+				continue;
+
+			err = br_mdb_queue_one(&mdb_list,
+					       SWITCHDEV_OBJ_ID_PORT_MDB,
+					       mp, dev);
+			if (err) {
+				rcu_read_unlock();
+				goto out_free_mdb;
+			}
+		}
+	}
+
+	rcu_read_unlock();
+
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	list_for_each_entry(obj, &mdb_list, list) {
+		err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj),
+					action, ctx, extack);
+		if (err)
+			goto out_free_mdb;
+	}
+
+out_free_mdb:
+	list_for_each_entry_safe(obj, tmp, &mdb_list, list) {
+		list_del(&obj->list);
+		kfree(SWITCHDEV_OBJ_PORT_MDB(obj));
+	}
+
+	if (err)
+		return err;
+#endif
+
+	return 0;
+}
+
 static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
 				   struct notifier_block *atomic_nb,
 				   struct notifier_block *blocking_nb,