bonding: implement xdo_dev_state_free and call it after deletion

Add this implementation for bonding, so hardware resources can be
freed from the active slave after xfrm state is deleted. The netdev
used to invoke xdo_dev_state_free callback, is saved in the xfrm state
(xs->xso.real_dev), which is also the bond's active slave. To prevent
it from being freed, acquire netdev reference before leaving RCU
read-side critical section, and release it after callback is done.

And call it when deleting all SAs from old active real interface while
switching current active slave.

Fixes: 9a5605505d9c ("bonding: Add struct bond_ipesc to manage SA")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Link: https://patch.msgid.link/20240823031056.110999-2-jianbol@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f74bacf071fca0d3c09d02e1d5e52bbbc7d632c2..2b4b7ad9cd2de1fe2dba8832b6c32f13524c66a4 100644 (file)
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -581,12 +581,47 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
                                   __func__);
                } else {
                        slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+                       if (slave->dev->xfrmdev_ops->xdo_dev_state_free)
+                               slave->dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
                }
        }
        spin_unlock_bh(&bond->ipsec_lock);
        rcu_read_unlock();
 }
 
+static void bond_ipsec_free_sa(struct xfrm_state *xs)
+{
+       struct net_device *bond_dev = xs->xso.dev;
+       struct net_device *real_dev;
+       netdevice_tracker tracker;
+       struct bonding *bond;
+       struct slave *slave;
+
+       if (!bond_dev)
+               return;
+
+       rcu_read_lock();
+       bond = netdev_priv(bond_dev);
+       slave = rcu_dereference(bond->curr_active_slave);
+       real_dev = slave ? slave->dev : NULL;
+       netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+       rcu_read_unlock();
+
+       if (!slave)
+               goto out;
+
+       if (!xs->xso.real_dev)
+               goto out;
+
+       WARN_ON(xs->xso.real_dev != real_dev);
+
+       if (real_dev && real_dev->xfrmdev_ops &&
+           real_dev->xfrmdev_ops->xdo_dev_state_free)
+               real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
+out:
+       netdev_put(real_dev, &tracker);
+}
+
 /**
  * bond_ipsec_offload_ok - can this packet use the xfrm hw offload
  * @skb: current data packet
@@ -627,6 +662,7 @@ out:
 static const struct xfrmdev_ops bond_xfrmdev_ops = {
        .xdo_dev_state_add = bond_ipsec_add_sa,
        .xdo_dev_state_delete = bond_ipsec_del_sa,
+       .xdo_dev_state_free = bond_ipsec_free_sa,
        .xdo_dev_offload_ok = bond_ipsec_offload_ok,
 };
 #endif /* CONFIG_XFRM_OFFLOAD */