When batadv_iv_ogm_schedule_buff() fails to allocate and queue a forward
packet for OGM transmission, the work item that drives periodic OGM
scheduling is never re-armed. This silently halts transmission of the
node's own OGMs on the affected interface — only OGMs from other peers
continue to be aggregated and forwarded.
Fix this by tracking whether batadv_iv_ogm_queue_add() (and transitively
batadv_iv_ogm_aggregate_new()) successfully scheduled a forward packet.
When scheduling fails, batadv_iv_ogm_schedule_buff() falls back to queuing
a dedicated recovery work item (reschedule_work) that fires after one
originator interval and calls batadv_iv_ogm_schedule() again.
Fixes: d893c5d00f63 ("[batman-adv] Cleanup aggregation.[ch]")
Signed-off-by: Sven Eckelmann <[email protected]>
---
See https://www.open-mesh.org/issues/433
---
Changes in v2:
- move reschedule to central place at end of function
- remove RFC prefix
- Link to v1:
https://patch.msgid.link/20260515-bat_iv-own-fwd-failure-recover-v1-1-caa171e7d...@narfation.org
---
net/batman-adv/bat_iv_ogm.c | 70 ++++++++++++++++++++++++++++++++++++---------
net/batman-adv/types.h | 3 ++
2 files changed, 59 insertions(+), 14 deletions(-)
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 74ef7dc2..7115eaed 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -224,6 +224,8 @@ static void batadv_iv_ogm_iface_disable(struct
batadv_hard_iface *hard_iface)
hard_iface->bat_iv.ogm_buff = NULL;
mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
+
+ cancel_delayed_work_sync(&hard_iface->bat_iv.reschedule_work);
}
static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface
*hard_iface)
@@ -536,8 +538,10 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet
*new_bat_ogm_packet,
* @if_incoming: interface where the packet was received
* @if_outgoing: interface for which the retransmission should be considered
* @own_packet: true if it is a self-generated ogm
+ *
+ * Return: whether forward packet was scheduled
*/
-static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
+static bool batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
int packet_len, unsigned long send_time,
bool direct_link,
struct batadv_hard_iface *if_incoming,
@@ -561,13 +565,13 @@ static void batadv_iv_ogm_aggregate_new(const unsigned
char *packet_buff,
skb = netdev_alloc_skb_ip_align(NULL, skb_size);
if (!skb)
- return;
+ return false;
forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing,
queue_left, bat_priv, skb);
if (!forw_packet_aggr) {
kfree_skb(skb);
- return;
+ return false;
}
forw_packet_aggr->skb->priority = TC_PRIO_CONTROL;
@@ -590,6 +594,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char
*packet_buff,
batadv_iv_send_outstanding_bat_ogm_packet);
batadv_forw_packet_ogmv1_queue(bat_priv, forw_packet_aggr, send_time);
+
+ return true;
}
/* aggregate a new packet into the existing ogm packet */
@@ -617,8 +623,10 @@ static void batadv_iv_ogm_aggregate(struct
batadv_forw_packet *forw_packet_aggr,
* @if_outgoing: interface for which the retransmission should be considered
* @own_packet: true if it is a self-generated ogm
* @send_time: timestamp (jiffies) when the packet is to be sent
+ *
+ * Return: whether forward packet was scheduled
*/
-static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
+static bool batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
unsigned char *packet_buff,
int packet_len,
struct batadv_hard_iface *if_incoming,
@@ -670,14 +678,16 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv
*bat_priv,
if (!own_packet && atomic_read(&bat_priv->aggregated_ogms))
send_time += max_aggregation_jiffies;
- batadv_iv_ogm_aggregate_new(packet_buff, packet_len,
- send_time, direct_link,
- if_incoming, if_outgoing,
- own_packet);
+ return batadv_iv_ogm_aggregate_new(packet_buff, packet_len,
+ send_time, direct_link,
+ if_incoming, if_outgoing,
+ own_packet);
} else {
batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff,
packet_len, direct_link);
spin_unlock_bh(&bat_priv->forw_bat_list_lock);
+
+ return true;
}
}
@@ -790,6 +800,8 @@ static void batadv_iv_ogm_schedule_buff(struct
batadv_hard_iface *hard_iface)
u32 seqno;
u16 tvlv_len = 0;
unsigned long send_time;
+ bool reschedule = false;
+ bool scheduled;
lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);
@@ -834,8 +846,11 @@ static void batadv_iv_ogm_schedule_buff(struct
batadv_hard_iface *hard_iface)
/* OGMs from secondary interfaces are only scheduled on their
* respective interfaces.
*/
- batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len,
- hard_iface, hard_iface, 1, send_time);
+ scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff,
*ogm_buff_len,
+ hard_iface, hard_iface, 1,
send_time);
+ if (!scheduled)
+ reschedule = true;
+
goto out;
}
@@ -847,15 +862,29 @@ static void batadv_iv_ogm_schedule_buff(struct
batadv_hard_iface *hard_iface)
if (!kref_get_unless_zero(&tmp_hard_iface->refcount))
continue;
- batadv_iv_ogm_queue_add(bat_priv, *ogm_buff,
- *ogm_buff_len, hard_iface,
- tmp_hard_iface, 1, send_time);
-
+ scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff,
+ *ogm_buff_len, hard_iface,
+ tmp_hard_iface, 1,
send_time);
batadv_hardif_put(tmp_hard_iface);
+
+ if (!scheduled && tmp_hard_iface == hard_iface)
+ reschedule = true;
+
}
rcu_read_unlock();
out:
+ if (reschedule) {
+ /* there was a failure scheduling the own forward packet.
+ * as result, the batadv_iv_send_outstanding_bat_ogm_packet()
+ * work item is no longer scheduled. it is therefore necessary
+ * to reschedule it manually
+ */
+ queue_delayed_work(batadv_event_workqueue,
+ &hard_iface->bat_iv.reschedule_work,
+
msecs_to_jiffies(atomic_read(&bat_priv->orig_interval)));
+ }
+
batadv_hardif_put(primary_if);
}
@@ -870,6 +899,17 @@ static void batadv_iv_ogm_schedule(struct
batadv_hard_iface *hard_iface)
mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
}
+static void batadv_iv_ogm_reschedule(struct work_struct *work)
+{
+ struct delayed_work *delayed_work = to_delayed_work(work);
+ struct batadv_hard_iface *hard_iface;
+
+ hard_iface = container_of(delayed_work,
+ struct batadv_hard_iface,
+ bat_iv.reschedule_work);
+ batadv_iv_ogm_schedule(hard_iface);
+}
+
/**
* batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over
interface
* @orig_node: originator which reproadcasted the OGMs directly
@@ -2262,6 +2302,8 @@ batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node
*neigh1,
static void batadv_iv_iface_enabled(struct batadv_hard_iface *hard_iface)
{
+ INIT_DELAYED_WORK(&hard_iface->bat_iv.reschedule_work,
batadv_iv_ogm_reschedule);
+
/* begin scheduling originator messages on that interface */
batadv_iv_ogm_schedule(hard_iface);
}
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index c8c3e806..6138f63a 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -83,6 +83,9 @@ struct batadv_hard_iface_bat_iv {
/** @ogm_seqno: OGM sequence number - used to identify each OGM */
atomic_t ogm_seqno;
+ /** @reschedule_work: recover OGM schedule after schedule error */
+ struct delayed_work reschedule_work;
+
/** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */
struct mutex ogm_buff_mutex;
};
---
base-commit: ff182fc0c666754e3f35f7b63c9ccf0dff239e52
change-id: 20260515-bat_iv-own-fwd-failure-recover-01c6a7e48491
Best regards,
--
Sven Eckelmann <[email protected]>
