batman-adv: fix TT VLAN inconsistency on VLAN re-add
When a VLAN interface (on top of batX) is removed and
re-added within a short timeframe TT does not have enough
time to properly cleanup. This creates an internal TT state
mismatch as the newly created softif_vlan will be
initialized from scratch with a TT client count of zero
(even if TT entries for this VLAN still exist). The
resulting TT messages are bogus due to the counter / tt
client listing mismatch, thus creating inconsistencies on
every node in the network
To fix this issue destroy_vlan() has to not free the VLAN
object immediately but it has to be kept alive until all the
TT entries for this VLAN have been removed. destroy_vlan()
still removes the sysfs folder so that the user has the
feeling that everything went fine.
If the same VLAN is re-added before the old object is free'd,
then the latter is resurrected and re-used.
Implement such behaviour by increasing the reference counter
of a softif_vlan object every time a new local TT entry for
such VLAN is created and remove the object from the list
only when all the TT entries have been destroyed.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index e7ee65d..cbd677f 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -448,10 +448,15 @@
* possibly free it
* @softif_vlan: the vlan object to release
*/
-void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *softif_vlan)
+void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan)
{
- if (atomic_dec_and_test(&softif_vlan->refcount))
- kfree_rcu(softif_vlan, rcu);
+ if (atomic_dec_and_test(&vlan->refcount)) {
+ spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+ hlist_del_rcu(&vlan->list);
+ spin_unlock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+
+ kfree_rcu(vlan, rcu);
+ }
}
/**
@@ -505,6 +510,7 @@
if (!vlan)
return -ENOMEM;
+ vlan->bat_priv = bat_priv;
vlan->vid = vid;
atomic_set(&vlan->refcount, 1);
@@ -516,6 +522,10 @@
return err;
}
+ spin_lock_bh(&bat_priv->softif_vlan_list_lock);
+ hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
+ spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+
/* add a new TT local entry. This one will be marked with the NOPURGE
* flag
*/
@@ -523,10 +533,6 @@
bat_priv->soft_iface->dev_addr, vid,
BATADV_NULL_IFINDEX, BATADV_NO_MARK);
- spin_lock_bh(&bat_priv->softif_vlan_list_lock);
- hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
- spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
return 0;
}
@@ -538,18 +544,13 @@
static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv,
struct batadv_softif_vlan *vlan)
{
- spin_lock_bh(&bat_priv->softif_vlan_list_lock);
- hlist_del_rcu(&vlan->list);
- spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
- batadv_sysfs_del_vlan(bat_priv, vlan);
-
/* explicitly remove the associated TT local entry because it is marked
* with the NOPURGE flag
*/
batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr,
vlan->vid, "vlan interface destroyed", false);
+ batadv_sysfs_del_vlan(bat_priv, vlan);
batadv_softif_vlan_free_ref(vlan);
}
@@ -567,6 +568,8 @@
unsigned short vid)
{
struct batadv_priv *bat_priv = netdev_priv(dev);
+ struct batadv_softif_vlan *vlan;
+ int ret;
/* only 802.1Q vlans are supported.
* batman-adv does not know how to handle other types
@@ -576,7 +579,36 @@
vid |= BATADV_VLAN_HAS_TAG;
- return batadv_softif_create_vlan(bat_priv, vid);
+ /* if a new vlan is getting created and it already exists, it means that
+ * it was not deleted yet. batadv_softif_vlan_get() increases the
+ * refcount in order to revive the object.
+ *
+ * if it does not exist then create it.
+ */
+ vlan = batadv_softif_vlan_get(bat_priv, vid);
+ if (!vlan)
+ return batadv_softif_create_vlan(bat_priv, vid);
+
+ /* recreate the sysfs object if it was already destroyed (and it should
+ * be since we received a kill_vid() for this vlan
+ */
+ if (!vlan->kobj) {
+ ret = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
+ if (ret) {
+ batadv_softif_vlan_free_ref(vlan);
+ return ret;
+ }
+ }
+
+ /* add a new TT local entry. This one will be marked with the NOPURGE
+ * flag. This must be added again, even if the vlan object already
+ * exists, because the entry was deleted by kill_vid()
+ */
+ batadv_tt_local_add(bat_priv->soft_iface,
+ bat_priv->soft_iface->dev_addr, vid,
+ BATADV_NULL_IFINDEX, BATADV_NO_MARK);
+
+ return 0;
}
/**