diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a43062d4c734..8346b0d29542 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -308,6 +308,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee84e783e1df..6a7cb01f121c 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -595,21 +595,40 @@ 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; } @@ -677,51 +696,50 @@ 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, diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b045284849e..c9189a970eec 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include #include +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); -- knotmirror 0.0.1 From f7a70d650b0b6b0134ccba763d672c8439d9f09b Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 14 Feb 2024 22:40:04 +0100 Subject: [PATCH 2/2] net: bridge: switchdev: Ensure deferred event delivery on unoffload When unoffloading a device, it is important to ensure that all relevant deferred events are delivered to it before it disassociates itself from the bridge. Before this change, this was true for the normal case when a device maps 1:1 to a net_bridge_port, i.e. br0 / swp0 When swp0 leaves br0, the call to switchdev_deferred_process() in del_nbp() makes sure to process any outstanding events while the device is still associated with the bridge. In the case when the association is indirect though, i.e. when the device is attached to the bridge via an intermediate device, like a LAG... br0 / lag0 / swp0 ...then detaching swp0 from lag0 does not cause any net_bridge_port to be deleted, so there was no guarantee that all events had been processed before the device disassociated itself from the bridge. Fix this by always synchronously processing all deferred events before signaling completion of unoffloading back to the driver. Fixes: 4e51bf44a03a ("net: bridge: move the switchdev object replay helpers to "push" mode") Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/bridge/br_switchdev.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 6a7cb01f121c..7b41ee8740cb 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -804,6 +804,16 @@ 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