1 files changed, 202 insertions, 84 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1cd92c12e782..b560644ee1b1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -419,6 +419,41 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
 
 #ifdef CONFIG_XFRM_OFFLOAD
 /**
+ * bond_ipsec_dev - Get active device for IPsec offload
+ * @xs: pointer to transformer state struct
+ *
+ * Context: caller must hold rcu_read_lock.
+ *
+ * Return: the device for ipsec offload, or NULL if not exist.
+ **/
+static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
+{
+	struct net_device *bond_dev = xs->xso.dev;
+	struct bonding *bond;
+	struct slave *slave;
+
+	if (!bond_dev)
+		return NULL;
+
+	bond = netdev_priv(bond_dev);
+	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
+		return NULL;
+
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (!slave)
+		return NULL;
+
+	if (!xs->xso.real_dev)
+		return NULL;
+
+	if (xs->xso.real_dev != slave->dev)
+		pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n",
+				    bond_dev->name, slave->dev->name, xs->xso.real_dev->name);
+
+	return slave->dev;
+}
+
+/**
  * bond_ipsec_add_sa - program device with a security association
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
@@ -427,6 +462,8 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 			     struct netlink_ext_ack *extack)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+	netdevice_tracker tracker;
 	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
@@ -438,74 +475,80 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
 	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave) {
-		rcu_read_unlock();
-		return -ENODEV;
+	real_dev = slave ? slave->dev : NULL;
+	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+	if (!real_dev) {
+		err = -ENODEV;
+		goto out;
 	}
 
-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
-	    netif_is_bond_master(slave->dev)) {
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(real_dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
-		rcu_read_unlock();
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+	ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
 	if (!ipsec) {
-		rcu_read_unlock();
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out;
 	}
-	xs->xso.real_dev = slave->dev;
 
-	err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+	xs->xso.real_dev = real_dev;
+	err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
 	if (!err) {
 		ipsec->xs = xs;
 		INIT_LIST_HEAD(&ipsec->list);
-		spin_lock_bh(&bond->ipsec_lock);
+		mutex_lock(&bond->ipsec_lock);
 		list_add(&ipsec->list, &bond->ipsec_list);
-		spin_unlock_bh(&bond->ipsec_lock);
+		mutex_unlock(&bond->ipsec_lock);
 	} else {
 		kfree(ipsec);
 	}
-	rcu_read_unlock();
+out:
+	netdev_put(real_dev, &tracker);
 	return err;
 }
 
 static void bond_ipsec_add_sa_all(struct bonding *bond)
 {
 	struct net_device *bond_dev = bond->dev;
+	struct net_device *real_dev;
 	struct bond_ipsec *ipsec;
 	struct slave *slave;
 
-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave)
-		goto out;
+	slave = rtnl_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	if (!real_dev)
+		return;
 
-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
-	    netif_is_bond_master(slave->dev)) {
-		spin_lock_bh(&bond->ipsec_lock);
+	mutex_lock(&bond->ipsec_lock);
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(real_dev)) {
 		if (!list_empty(&bond->ipsec_list))
-			slave_warn(bond_dev, slave->dev,
+			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_add\n",
 				   __func__);
-		spin_unlock_bh(&bond->ipsec_lock);
 		goto out;
 	}
 
-	spin_lock_bh(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
-		ipsec->xs->xso.real_dev = slave->dev;
-		if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
-			slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+		/* If new state is added before ipsec_lock acquired */
+		if (ipsec->xs->xso.real_dev == real_dev)
+			continue;
+
+		ipsec->xs->xso.real_dev = real_dev;
+		if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+			slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
 			ipsec->xs->xso.real_dev = NULL;
 		}
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
 out:
-	rcu_read_unlock();
+	mutex_unlock(&bond->ipsec_lock);
 }
 
 /**
@@ -515,6 +558,8 @@ out:
 static void bond_ipsec_del_sa(struct xfrm_state *xs)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+	netdevice_tracker tracker;
 	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
@@ -525,6 +570,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 	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;
@@ -532,18 +580,19 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 	if (!xs->xso.real_dev)
 		goto out;
 
-	WARN_ON(xs->xso.real_dev != slave->dev);
+	WARN_ON(xs->xso.real_dev != real_dev);
 
-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
-	    netif_is_bond_master(slave->dev)) {
-		slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+	    netif_is_bond_master(real_dev)) {
+		slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
 		goto out;
 	}
 
-	slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+	real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
 out:
-	spin_lock_bh(&bond->ipsec_lock);
+	netdev_put(real_dev, &tracker);
+	mutex_lock(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
 		if (ipsec->xs == xs) {
 			list_del(&ipsec->list);
@@ -551,41 +600,72 @@ out:
 			break;
 		}
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
-	rcu_read_unlock();
+	mutex_unlock(&bond->ipsec_lock);
 }
 
 static void bond_ipsec_del_sa_all(struct bonding *bond)
 {
 	struct net_device *bond_dev = bond->dev;
+	struct net_device *real_dev;
 	struct bond_ipsec *ipsec;
 	struct slave *slave;
 
-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave) {
-		rcu_read_unlock();
+	slave = rtnl_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	if (!real_dev)
 		return;
-	}
 
-	spin_lock_bh(&bond->ipsec_lock);
+	mutex_lock(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
 		if (!ipsec->xs->xso.real_dev)
 			continue;
 
-		if (!slave->dev->xfrmdev_ops ||
-		    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
-		    netif_is_bond_master(slave->dev)) {
-			slave_warn(bond_dev, slave->dev,
+		if (!real_dev->xfrmdev_ops ||
+		    !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+		    netif_is_bond_master(real_dev)) {
+			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_delete\n",
 				   __func__);
 		} else {
-			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+			if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+				real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
 		}
-		ipsec->xs->xso.real_dev = NULL;
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
+	mutex_unlock(&bond->ipsec_lock);
+}
+
+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);
 }
 
 /**
@@ -595,44 +675,80 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
  **/
 static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = xs->xso.dev;
 	struct net_device *real_dev;
-	struct slave *curr_active;
-	struct bonding *bond;
-	int err;
+	bool ok = false;
 
-	bond = netdev_priv(bond_dev);
 	rcu_read_lock();
-	curr_active = rcu_dereference(bond->curr_active_slave);
-	real_dev = curr_active->dev;
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
+		goto out;
 
-	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
-		err = false;
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+	    netif_is_bond_master(real_dev))
 		goto out;
-	}
 
-	if (!xs->xso.real_dev) {
-		err = false;
+	ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+out:
+	rcu_read_unlock();
+	return ok;
+}
+
+/**
+ * bond_advance_esn_state - ESN support for IPSec HW offload
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_advance_esn_state(struct xfrm_state *xs)
+{
+	struct net_device *real_dev;
+
+	rcu_read_lock();
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
+		goto out;
+
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
+		pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name);
 		goto out;
 	}
 
+	real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs);
+out:
+	rcu_read_unlock();
+}
+
+/**
+ * bond_xfrm_update_stats - Update xfrm state
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_xfrm_update_stats(struct xfrm_state *xs)
+{
+	struct net_device *real_dev;
+
+	rcu_read_lock();
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
+		goto out;
+
 	if (!real_dev->xfrmdev_ops ||
-	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
-	    netif_is_bond_master(real_dev)) {
-		err = false;
+	    !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) {
+		pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name);
 		goto out;
 	}
 
-	err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+	real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs);
 out:
 	rcu_read_unlock();
-	return err;
 }
 
 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,
+	.xdo_dev_state_advance_esn = bond_advance_esn_state,
+	.xdo_dev_state_update_stats = bond_xfrm_update_stats,
 };
 #endif /* CONFIG_XFRM_OFFLOAD */
 
@@ -2258,7 +2374,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 			goto err_sysfs_del;
 		}
 
-		res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		res = dev_xdp_propagate(slave_dev, &xdp);
 		if (res < 0) {
 			/* ndo_bpf() sets extack error message */
 			slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
@@ -2394,7 +2510,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 			.prog	 = NULL,
 			.extack  = NULL,
 		};
-		if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp))
+		if (dev_xdp_propagate(slave_dev, &xdp))
 			slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
 	}
 
@@ -5584,7 +5700,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			goto err;
 		}
 
-		err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		err = dev_xdp_propagate(slave_dev, &xdp);
 		if (err < 0) {
 			/* ndo_bpf() sets extack error message */
 			slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
@@ -5616,7 +5732,7 @@ err:
 		if (slave == rollback_slave)
 			break;
 
-		err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		err_unwind = dev_xdp_propagate(slave_dev, &xdp);
 		if (err_unwind < 0)
 			slave_err(dev, slave_dev,
 				  "Error %d when unwinding XDP program change\n", err_unwind);
@@ -5770,9 +5886,6 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 	if (real_dev) {
 		ret = ethtool_get_ts_info_by_layer(real_dev, info);
 	} else {
-		info->phc_index = -1;
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE;
 		/* Check if all slaves support software tx timestamping */
 		rcu_read_lock();
 		bond_for_each_slave_rcu(bond, slave, iter) {
@@ -5882,11 +5995,14 @@ void bond_setup(struct net_device *bond_dev)
 	/* set up xfrm device ops (only supported in active-backup right now) */
 	bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
 	INIT_LIST_HEAD(&bond->ipsec_list);
-	spin_lock_init(&bond->ipsec_lock);
+	mutex_init(&bond->ipsec_lock);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
 	/* don't acquire bond device's netif_tx_lock when transmitting */
-	bond_dev->features |= NETIF_F_LLTX;
+	bond_dev->lltx = true;
+
+	/* Don't allow bond devices to change network namespaces. */
+	bond_dev->netns_local = true;
 
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
@@ -5895,9 +6011,6 @@ void bond_setup(struct net_device *bond_dev)
 	 * capable
 	 */
 
-	/* Don't allow bond devices to change network namespaces. */
-	bond_dev->features |= NETIF_F_NETNS_LOCAL;
-
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -5931,6 +6044,10 @@ static void bond_uninit(struct net_device *bond_dev)
 		__bond_release_one(bond_dev, slave->dev, true, true);
 	netdev_info(bond_dev, "Released all slaves\n");
 
+#ifdef CONFIG_XFRM_OFFLOAD
+	mutex_destroy(&bond->ipsec_lock);
+#endif /* CONFIG_XFRM_OFFLOAD */
+
 	bond_set_slave_arr(bond, NULL, NULL);
 
 	list_del_rcu(&bond->bond_list);
@@ -6338,7 +6455,8 @@ static int bond_init(struct net_device *bond_dev)
 
 	netdev_dbg(bond_dev, "Begin bond_init\n");
 
-	bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
+	bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+					   bond_dev->name);
 	if (!bond->wq)
 		return -ENOMEM;