| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20251126023829.44946-2-tonghao@bamaicloud.com>
Date: Wed, 26 Nov 2025 10:38:25 +0800
From: Tonghao Zhang <tonghao@...aicloud.com>
To: netdev@...r.kernel.org
Cc: Tonghao Zhang <tonghao@...aicloud.com>,
Jay Vosburgh <jv@...sburgh.net>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Simon Horman <horms@...nel.org>,
Jonathan Corbet <corbet@....net>,
Andrew Lunn <andrew+netdev@...n.ch>,
Nikolay Aleksandrov <razor@...ckwall.org>,
Hangbin Liu <liuhangbin@...il.com>,
Jason Xing <kerneljasonxing@...il.com>
Subject: [PATCH net-next v2 1/5] net: bonding: use workqueue to make sure peer notify updated in lacp mode
The rtnl lock might be locked, preventing ad_cond_set_peer_notif() from
acquiring the lock and updating send_peer_notif. This patch addresses
the issue by using a workqueue. Since updating send_peer_notif does
not require high real-time performance, such delayed updates are entirely
acceptable.
In fact, checking this value and using it in multiple places, all operations
are protected at the same time by rtnl lock, such as
- read send_peer_notif
- send_peer_notif--
- bond_should_notify_peers
By the way, rtnl lock is still required, when accessing bond.params.* for
updating send_peer_notif. In lacp mode, resetting send_peer_notif in
workqueue is safe, simple and effective way.
Cc: Jay Vosburgh <jv@...sburgh.net>
Cc: "David S. Miller" <davem@...emloft.net>
Cc: Eric Dumazet <edumazet@...gle.com>
Cc: Jakub Kicinski <kuba@...nel.org>
Cc: Paolo Abeni <pabeni@...hat.com>
Cc: Simon Horman <horms@...nel.org>
Cc: Jonathan Corbet <corbet@....net>
Cc: Andrew Lunn <andrew+netdev@...n.ch>
Cc: Nikolay Aleksandrov <razor@...ckwall.org>
Cc: Hangbin Liu <liuhangbin@...il.com>
Cc: Jason Xing <kerneljasonxing@...il.com>
Suggested-by: Hangbin Liu <liuhangbin@...il.com>
Signed-off-by: Tonghao Zhang <tonghao@...aicloud.com>
---
v1:
- This patch is actually version v3, https://patchwork.kernel.org/project/netdevbpf/patch/20251118090305.35558-1-tonghao@bamaicloud.com/
- add a comment why we use the trylock.
- add this patch to series
---
drivers/net/bonding/bond_3ad.c | 7 ++---
drivers/net/bonding/bond_main.c | 55 ++++++++++++++++++++++++++-------
include/net/bonding.h | 2 ++
3 files changed, 47 insertions(+), 17 deletions(-)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 1a8de2bf8655..01ae0269a138 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1008,11 +1008,8 @@ static void ad_cond_set_peer_notif(struct port *port)
{
struct bonding *bond = port->slave->bond;
- if (bond->params.broadcast_neighbor && rtnl_trylock()) {
- bond->send_peer_notif = bond->params.num_peer_notif *
- max(1, bond->params.peer_notif_delay);
- rtnl_unlock();
- }
+ if (bond->params.broadcast_neighbor)
+ bond_peer_notify_work_rearm(bond, 0);
}
/**
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3d56339a8a10..811ced7680c1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1195,6 +1195,35 @@ static bool bond_should_notify_peers(struct bonding *bond)
return true;
}
+/* Use this to update send_peer_notif when RTNL may be held in other places. */
+void bond_peer_notify_work_rearm(struct bonding *bond, unsigned long delay)
+{
+ queue_delayed_work(bond->wq, &bond->peer_notify_work, delay);
+}
+
+/* Peer notify update handler. Holds only RTNL */
+static void bond_peer_notify_reset(struct bonding *bond)
+{
+ bond->send_peer_notif = bond->params.num_peer_notif *
+ max(1, bond->params.peer_notif_delay);
+}
+
+static void bond_peer_notify_handler(struct work_struct *work)
+{
+ struct bonding *bond = container_of(work, struct bonding,
+ peer_notify_work.work);
+
+ if (!rtnl_trylock()) {
+ bond_peer_notify_work_rearm(bond, 1);
+ return;
+ }
+
+ bond_peer_notify_reset(bond);
+
+ rtnl_unlock();
+ return;
+}
+
/**
* bond_change_active_slave - change the active slave into the specified one
* @bond: our bonding struct
@@ -1270,8 +1299,6 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
BOND_SLAVE_NOTIFY_NOW);
if (new_active) {
- bool should_notify_peers = false;
-
bond_set_slave_active_flags(new_active,
BOND_SLAVE_NOTIFY_NOW);
@@ -1280,19 +1307,17 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
old_active);
if (netif_running(bond->dev)) {
- bond->send_peer_notif =
- bond->params.num_peer_notif *
- max(1, bond->params.peer_notif_delay);
- should_notify_peers =
- bond_should_notify_peers(bond);
+ bond_peer_notify_reset(bond);
+
+ if (bond_should_notify_peers(bond)) {
+ bond->send_peer_notif--;
+ call_netdevice_notifiers(
+ NETDEV_NOTIFY_PEERS,
+ bond->dev);
+ }
}
call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
- if (should_notify_peers) {
- bond->send_peer_notif--;
- call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
- bond->dev);
- }
}
}
@@ -4213,6 +4238,10 @@ static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp)
void bond_work_init_all(struct bonding *bond)
{
+ /* .ndo_stop(), bond_close() will try to flush the work under
+ * the rtnl lock. The workqueue must not block on rtnl lock
+ * to avoid deadlock.
+ */
INIT_DELAYED_WORK(&bond->mcast_work,
bond_resend_igmp_join_requests_delayed);
INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
@@ -4220,6 +4249,7 @@ void bond_work_init_all(struct bonding *bond)
INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
+ INIT_DELAYED_WORK(&bond->peer_notify_work, bond_peer_notify_handler);
}
void bond_work_cancel_all(struct bonding *bond)
@@ -4230,6 +4260,7 @@ void bond_work_cancel_all(struct bonding *bond)
cancel_delayed_work_sync(&bond->ad_work);
cancel_delayed_work_sync(&bond->mcast_work);
cancel_delayed_work_sync(&bond->slave_arr_work);
+ cancel_delayed_work_sync(&bond->peer_notify_work);
}
static int bond_open(struct net_device *bond_dev)
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 49edc7da0586..63d08056a4a4 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -254,6 +254,7 @@ struct bonding {
struct delayed_work ad_work;
struct delayed_work mcast_work;
struct delayed_work slave_arr_work;
+ struct delayed_work peer_notify_work;
#ifdef CONFIG_DEBUG_FS
/* debugging support via debugfs */
struct dentry *debug_dir;
@@ -709,6 +710,7 @@ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
int level);
int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave);
void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay);
+void bond_peer_notify_work_rearm(struct bonding *bond, unsigned long delay);
void bond_work_init_all(struct bonding *bond);
void bond_work_cancel_all(struct bonding *bond);
--
2.34.1
Powered by blists - more mailing lists