1 files changed, 98 insertions, 40 deletions

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 7eb6fd5bb917..fe3f7bbe86ee 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -17,6 +17,9 @@ static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p,
 	if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload))
 		return false;
 
+	if (br_multicast_igmp_type(skb))
+		return false;
+
 	return (p->flags & BR_TX_FWD_OFFLOAD) &&
 	       (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom);
 }
@@ -104,9 +107,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
 		return 0;
 
 	if (err) {
-		if (extack && !extack->_msg)
-			NL_SET_ERR_MSG_MOD(extack,
-					   "bridge flag offload is not supported");
+		NL_SET_ERR_MSG_WEAK_MOD(extack,
+					"bridge flag offload is not supported");
 		return -EOPNOTSUPP;
 	}
 
@@ -115,9 +117,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
 
 	err = switchdev_port_attr_set(p->dev, &attr, extack);
 	if (err) {
-		if (extack && !extack->_msg)
-			NL_SET_ERR_MSG_MOD(extack,
-					   "error setting offload flag on port");
+		NL_SET_ERR_MSG_WEAK_MOD(extack,
+					"error setting offload flag on port");
 		return err;
 	}
 
@@ -150,6 +151,17 @@ br_switchdev_fdb_notify(struct net_bridge *br,
 	if (test_bit(BR_FDB_LOCKED, &fdb->flags))
 		return;
 
+	/* Entries with these flags were created using ndm_state == NUD_REACHABLE,
+	 * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something
+	 * equivalent to 'bridge fdb add ... master dynamic (sticky)'.
+	 * Drivers don't know how to deal with these, so don't notify them to
+	 * avoid confusing them.
+	 */
+	if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) &&
+	    !test_bit(BR_FDB_STATIC, &fdb->flags) &&
+	    !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags))
+		return;
+
 	br_switchdev_fdb_populate(br, &item, fdb, NULL);
 
 	switch (type) {
@@ -495,9 +507,10 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port *port = data->port;
 	struct net_bridge *br = port->br;
+	u8 old_flags;
 
-	if (err)
-		goto err;
+	if (err == -EOPNOTSUPP)
+		goto out_free;
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &data->ip);
@@ -507,11 +520,15 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	     pp = &p->next) {
 		if (p->key.port != port)
 			continue;
-		p->flags |= MDB_PG_FLAGS_OFFLOAD;
+
+		old_flags = p->flags;
+		br_multicast_set_pg_offload_flags(p, !err);
+		if (br_mdb_should_notify(br, old_flags ^ p->flags))
+			br_mdb_flag_change_notify(br->dev, mp, p);
 	}
 out:
 	spin_unlock_bh(&br->multicast_lock);
-err:
+out_free:
 	kfree(priv);
 }
 
@@ -586,21 +603,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
 }
 
 static int br_switchdev_mdb_queue_one(struct list_head *mdb_list,
+				      struct net_device *dev,
+				      unsigned long action,
 				      enum switchdev_obj_id id,
 				      const struct net_bridge_mdb_entry *mp,
 				      struct net_device *orig_dev)
 {
-	struct switchdev_obj_port_mdb *mdb;
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = id,
+			.orig_dev = orig_dev,
+		},
+	};
+	struct switchdev_obj_port_mdb *pmdb;
 
-	mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC);
-	if (!mdb)
-		return -ENOMEM;
+	br_switchdev_mdb_populate(&mdb, mp);
 
-	mdb->obj.id = id;
-	mdb->obj.orig_dev = orig_dev;
-	br_switchdev_mdb_populate(mdb, mp);
-	list_add_tail(&mdb->obj.list, mdb_list);
+	if (action == SWITCHDEV_PORT_OBJ_ADD &&
+	    switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) {
+		/* This event is already in the deferred queue of
+		 * events, so this replay must be elided, lest the
+		 * driver receives duplicate events for it. This can
+		 * only happen when replaying additions, since
+		 * modifications are always immediately visible in
+		 * br->mdb_list, whereas actual event delivery may be
+		 * delayed.
+		 */
+		return 0;
+	}
 
+	pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC);
+	if (!pmdb)
+		return -ENOMEM;
+
+	list_add_tail(&pmdb->obj.list, mdb_list);
 	return 0;
 }
 
@@ -668,56 +704,57 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *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.
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	/* br_switchdev_mdb_queue_one() will take care to not queue a
+	 * replay of an event that is already pending in the switchdev
+	 * deferred queue. In order to safely determine that, there
+	 * must be no new deferred MDB notifications enqueued for the
+	 * duration of the MDB scan. Therefore, grab the write-side
+	 * lock to avoid racing with any concurrent IGMP/MLD snooping.
 	 */
-	rcu_read_lock();
+	spin_lock_bh(&br->multicast_lock);
 
-	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
+	hlist_for_each_entry(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_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_HOST_MDB,
 							 mp, br_dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 
-		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
+		for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 		     pp = &p->next) {
 			if (p->key.port->dev != dev)
 				continue;
 
-			err = br_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_PORT_MDB,
 							 mp, dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 	}
 
-	rcu_read_unlock();
-
-	if (adding)
-		action = SWITCHDEV_PORT_OBJ_ADD;
-	else
-		action = SWITCHDEV_PORT_OBJ_DEL;
+	spin_unlock_bh(&br->multicast_lock);
 
 	list_for_each_entry(obj, &mdb_list, list) {
 		err = br_switchdev_mdb_replay_one(nb, dev,
 						  SWITCHDEV_OBJ_PORT_MDB(obj),
 						  action, ctx, extack);
+		if (err == -EOPNOTSUPP)
+			err = 0;
 		if (err)
 			goto out_free_mdb;
 	}
@@ -750,8 +787,10 @@ static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
 
 	err = br_switchdev_mdb_replay(br_dev, dev, ctx, true, blocking_nb,
 				      extack);
-	if (err && err != -EOPNOTSUPP)
+	if (err) {
+		/* -EOPNOTSUPP not propagated from MDB replay. */
 		return err;
+	}
 
 	err = br_switchdev_fdb_replay(br_dev, ctx, true, atomic_nb);
 	if (err && err != -EOPNOTSUPP)
@@ -773,6 +812,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
 	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 
 	br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL);
+
+	/* Make sure that the device leaving this bridge has seen all
+	 * relevant events before it is disassociated. In the normal
+	 * case, when the device is directly attached to the bridge,
+	 * this is covered by del_nbp(). If the association was indirect
+	 * however, e.g. via a team or bond, and the device is leaving
+	 * that intermediate device, then the bridge port remains in
+	 * place.
+	 */
+	switchdev_deferred_process();
 }
 
 /* Let the bridge know that this port is offloaded, so that it can assign a
@@ -788,7 +837,7 @@ int br_switchdev_port_offload(struct net_bridge_port *p,
 	struct netdev_phys_item_id ppid;
 	int err;
 
-	err = dev_get_port_parent_id(dev, &ppid, false);
+	err = netif_get_port_parent_id(dev, &ppid, false);
 	if (err)
 		return err;
 
@@ -816,3 +865,12 @@ void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx,
 
 	nbp_switchdev_del(p);
 }
+
+int br_switchdev_port_replay(struct net_bridge_port *p,
+			     struct net_device *dev, const void *ctx,
+			     struct notifier_block *atomic_nb,
+			     struct notifier_block *blocking_nb,
+			     struct netlink_ext_ack *extack)
+{
+	return nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack);
+}