1 files changed, 330 insertions, 185 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2c5ed0a7cb18..c4d53e8e7c15 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
 #include <net/tls.h>
 #endif
 #include <net/ip6_route.h>
+#include <net/netdev_lock.h>
 #include <net/xdp.h>
 
 #include "bonding_priv.h"
@@ -322,9 +323,9 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-static bool bond_xdp_check(struct bonding *bond)
+bool bond_xdp_check(struct bonding *bond, int mode)
 {
-	switch (BOND_MODE(bond)) {
+	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
 	case BOND_MODE_ACTIVEBACKUP:
 		return true;
@@ -419,14 +420,49 @@ 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;
+
+	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
+ * @bond_dev: pointer to the bond net device
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int bond_ipsec_add_sa(struct xfrm_state *xs,
+static int bond_ipsec_add_sa(struct net_device *bond_dev,
+			     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;
@@ -438,112 +474,185 @@ 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);
+	err = real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, xs, extack);
 	if (!err) {
+		xs->xso.real_dev = real_dev;
 		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__);
-			ipsec->xs->xso.real_dev = NULL;
+		/* If new state is added before ipsec_lock acquired */
+		if (ipsec->xs->xso.real_dev == real_dev)
+			continue;
+
+		if (real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev,
+							     ipsec->xs, NULL)) {
+			slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
+			continue;
 		}
+
+		spin_lock_bh(&ipsec->xs->lock);
+		/* xs might have been killed by the user during the migration
+		 * to the new dev, but bond_ipsec_del_sa() should have done
+		 * nothing, as xso.real_dev is NULL.
+		 * Delete it from the device we just added it to. The pending
+		 * bond_ipsec_free_sa() call will do the rest of the cleanup.
+		 */
+		if (ipsec->xs->km.state == XFRM_STATE_DEAD &&
+		    real_dev->xfrmdev_ops->xdo_dev_state_delete)
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev,
+								    ipsec->xs);
+		ipsec->xs->xso.real_dev = real_dev;
+		spin_unlock_bh(&ipsec->xs->lock);
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
 out:
-	rcu_read_unlock();
+	mutex_unlock(&bond->ipsec_lock);
 }
 
 /**
  * bond_ipsec_del_sa - clear out this specific SA
+ * @bond_dev: pointer to the bond net device
  * @xs: pointer to transformer state struct
  **/
-static void bond_ipsec_del_sa(struct xfrm_state *xs)
+static void bond_ipsec_del_sa(struct net_device *bond_dev,
+			      struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+
+	if (!bond_dev || !xs->xso.real_dev)
+		return;
+
+	real_dev = xs->xso.real_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__);
+		return;
+	}
+
+	real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs);
+}
+
+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 bonding *bond;
 	struct slave *slave;
 
+	slave = rtnl_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	if (!real_dev)
+		return;
+
+	mutex_lock(&bond->ipsec_lock);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		if (!ipsec->xs->xso.real_dev)
+			continue;
+
+		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__);
+			continue;
+		}
+
+		spin_lock_bh(&ipsec->xs->lock);
+		ipsec->xs->xso.real_dev = NULL;
+		/* Don't double delete states killed by the user. */
+		if (ipsec->xs->km.state != XFRM_STATE_DEAD)
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev,
+								    ipsec->xs);
+		spin_unlock_bh(&ipsec->xs->lock);
+
+		if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+			real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev,
+								  ipsec->xs);
+	}
+	mutex_unlock(&bond->ipsec_lock);
+}
+
+static void bond_ipsec_free_sa(struct net_device *bond_dev,
+			       struct xfrm_state *xs)
+{
+	struct net_device *real_dev;
+	struct bond_ipsec *ipsec;
+	struct bonding *bond;
+
 	if (!bond_dev)
 		return;
 
-	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
-	slave = rcu_dereference(bond->curr_active_slave);
-
-	if (!slave)
-		goto out;
 
+	mutex_lock(&bond->ipsec_lock);
 	if (!xs->xso.real_dev)
 		goto out;
 
-	WARN_ON(xs->xso.real_dev != slave->dev);
+	real_dev = xs->xso.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__);
-		goto out;
-	}
-
-	slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+	xs->xso.real_dev = NULL;
+	if (real_dev->xfrmdev_ops &&
+	    real_dev->xfrmdev_ops->xdo_dev_state_free)
+		real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs);
 out:
-	spin_lock_bh(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
 		if (ipsec->xs == xs) {
 			list_del(&ipsec->list);
@@ -551,88 +660,84 @@ 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)
+/**
+ * bond_ipsec_offload_ok - can this packet use the xfrm hw offload
+ * @skb: current data packet
+ * @xs: pointer to transformer state struct
+ **/
+static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = bond->dev;
-	struct bond_ipsec *ipsec;
-	struct slave *slave;
+	struct net_device *real_dev;
 
 	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave) {
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev || netif_is_bond_master(real_dev)) {
 		rcu_read_unlock();
-		return;
+		return false;
 	}
 
-	spin_lock_bh(&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,
-				   "%s: no slave xdo_dev_state_delete\n",
-				   __func__);
-		} else {
-			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
-		}
-		ipsec->xs->xso.real_dev = NULL;
-	}
-	spin_unlock_bh(&bond->ipsec_lock);
 	rcu_read_unlock();
+	return true;
 }
 
 /**
- * bond_ipsec_offload_ok - can this packet use the xfrm hw offload
- * @skb: current data packet
+ * bond_advance_esn_state - ESN support for IPSec HW offload
  * @xs: pointer to transformer state struct
  **/
-static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+static void bond_advance_esn_state(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;
 
-	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_state_advance_esn) {
+		pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name);
 		goto out;
 	}
 
-	if (!xs->xso.real_dev) {
-		err = false;
+	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 */
 
@@ -742,9 +847,9 @@ static int bond_check_dev_link(struct bonding *bond,
 			       struct net_device *slave_dev, int reporting)
 {
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-	int (*ioctl)(struct net_device *, struct ifreq *, int);
-	struct ifreq ifr;
 	struct mii_ioctl_data *mii;
+	struct ifreq ifr;
+	int ret;
 
 	if (!reporting && !netif_running(slave_dev))
 		return 0;
@@ -753,13 +858,16 @@ static int bond_check_dev_link(struct bonding *bond,
 		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
 
 	/* Try to get link status using Ethtool first. */
-	if (slave_dev->ethtool_ops->get_link)
-		return slave_dev->ethtool_ops->get_link(slave_dev) ?
-			BMSR_LSTATUS : 0;
+	if (slave_dev->ethtool_ops->get_link) {
+		netdev_lock_ops(slave_dev);
+		ret = slave_dev->ethtool_ops->get_link(slave_dev);
+		netdev_unlock_ops(slave_dev);
+
+		return ret ? BMSR_LSTATUS : 0;
+	}
 
 	/* Ethtool can't be used, fallback to MII ioctls. */
-	ioctl = slave_ops->ndo_eth_ioctl;
-	if (ioctl) {
+	if (slave_ops->ndo_eth_ioctl) {
 		/* TODO: set pointer to correct ioctl on a per team member
 		 *       bases to make this more efficient. that is, once
 		 *       we determine the correct ioctl, we will always
@@ -775,9 +883,10 @@ static int bond_check_dev_link(struct bonding *bond,
 		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
 		strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
 		mii = if_mii(&ifr);
-		if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
+
+		if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
 			mii->reg_num = MII_BMSR;
-			if (ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
+			if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
 				return mii->val_out & BMSR_LSTATUS;
 		}
 	}
@@ -892,6 +1001,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 
 		if (bond->dev->flags & IFF_UP)
 			bond_hw_addr_flush(bond->dev, old_active->dev);
+
+		bond_slave_ns_maddrs_add(bond, old_active);
 	}
 
 	if (new_active) {
@@ -908,6 +1019,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 			dev_mc_sync(new_active->dev, bond->dev);
 			netif_addr_unlock_bh(bond->dev);
 		}
+
+		bond_slave_ns_maddrs_del(bond, new_active);
 	}
 }
 
@@ -999,8 +1112,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev,
-					 (struct sockaddr *)&ss, NULL);
+		rv = dev_set_mac_address(new_active->dev, &ss, NULL);
 		if (rv) {
 			slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n",
 				  -rv);
@@ -1014,8 +1126,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  new_active->dev->addr_len);
 		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev,
-					 (struct sockaddr *)&ss, NULL);
+		rv = dev_set_mac_address(old_active->dev, &ss, NULL);
 		if (rv)
 			slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n",
 				  -rv);
@@ -1121,13 +1232,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	return bestslave;
 }
 
+/* must be called in RCU critical section or with RTNL held */
 static bool bond_should_notify_peers(struct bonding *bond)
 {
-	struct slave *slave;
-
-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	rcu_read_unlock();
+	struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
 
 	if (!slave || !bond->send_peer_notif ||
 	    bond->send_peer_notif %
@@ -1363,7 +1471,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
 			slave_disable_netpoll(slave);
 }
 
-static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
+static int bond_netpoll_setup(struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
 	struct list_head *iter;
@@ -1403,9 +1511,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	struct slave *slave;
 
 	mask = features;
-
-	features &= ~NETIF_F_ONE_FOR_ALL;
-	features |= NETIF_F_ALL_FOR_ALL;
+	features = netdev_base_features(features);
 
 	bond_for_each_slave(bond, slave, iter) {
 		features = netdev_increment_features(features,
@@ -1419,17 +1525,22 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 
 #define BOND_VLAN_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
+				 NETIF_F_GSO_ENCAP_ALL | \
 				 NETIF_F_HIGHDMA | NETIF_F_LRO)
 
 #define BOND_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
-				 NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
+				 NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \
+				 NETIF_F_GSO_PARTIAL)
 
 #define BOND_MPLS_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_GSO_SOFTWARE)
 
+#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP)
+
 
 static void bond_compute_features(struct bonding *bond)
 {
+	netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES;
 	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
 					IFF_XMIT_DST_RELEASE_PERM;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
@@ -1447,8 +1558,9 @@ static void bond_compute_features(struct bonding *bond)
 
 	if (!bond_has_slaves(bond))
 		goto done;
-	vlan_features &= NETIF_F_ALL_FOR_ALL;
-	mpls_features &= NETIF_F_ALL_FOR_ALL;
+
+	vlan_features = netdev_base_features(vlan_features);
+	mpls_features = netdev_base_features(mpls_features);
 
 	bond_for_each_slave(bond, slave, iter) {
 		vlan_features = netdev_increment_features(vlan_features,
@@ -1464,6 +1576,10 @@ static void bond_compute_features(struct bonding *bond)
 							  BOND_XFRM_FEATURES);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
+		gso_partial_features = netdev_increment_features(gso_partial_features,
+								 slave->dev->gso_partial_features,
+								 BOND_GSO_PARTIAL_FEATURES);
+
 		mpls_features = netdev_increment_features(mpls_features,
 							  slave->dev->mpls_features,
 							  BOND_MPLS_FEATURES);
@@ -1478,6 +1594,7 @@ static void bond_compute_features(struct bonding *bond)
 	bond_dev->hard_header_len = max_hard_header_len;
 
 done:
+	bond_dev->gso_partial_features = gso_partial_features;
 	bond_dev->vlan_features = vlan_features;
 	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
 				    NETIF_F_HW_VLAN_CTAG_TX |
@@ -1811,7 +1928,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
+	if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) {
 		xdp_clear_features_flag(bond_dev);
 		return;
 	}
@@ -1996,15 +2113,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 * set the master's mac address to that of the first slave
 		 */
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
-		ss.ss_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
-					  extack);
-		if (res) {
-			slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
-			goto err_restore_mtu;
-		}
+	} else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW &&
+		   BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+		   memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) {
+		/* Set slave to random address to avoid duplicate mac
+		 * address in later fail over.
+		 */
+		eth_random_addr(ss.__data);
+	} else {
+		goto skip_mac_set;
+	}
+
+	ss.ss_family = slave_dev->type;
+	res = dev_set_mac_address(slave_dev, &ss, extack);
+	if (res) {
+		slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
+		goto err_restore_mtu;
 	}
 
+skip_mac_set:
+
 	/* set no_addrconf flag before open to prevent IPv6 addrconf */
 	slave_dev->priv_flags |= IFF_NO_ADDRCONF;
 
@@ -2228,6 +2356,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
 
+	/* Needs to be called before bond_select_active_slave(), which will
+	 * remove the maddrs if the slave is selected as active slave.
+	 */
+	bond_slave_ns_maddrs_add(bond, new_slave);
+
 	if (bond_uses_primary(bond)) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
@@ -2237,7 +2370,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_can_use_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
-
 	if (!slave_dev->netdev_ops->ndo_bpf ||
 	    !slave_dev->netdev_ops->ndo_xdp_xmit) {
 		if (bond->xdp_prog) {
@@ -2261,7 +2393,7 @@ 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);
@@ -2321,7 +2453,7 @@ err_restore_mac:
 		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
 				  new_slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
+		dev_set_mac_address(slave_dev, &ss, NULL);
 	}
 
 err_restore_mtu:
@@ -2397,7 +2529,7 @@ 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");
 	}
 
@@ -2421,7 +2553,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	RCU_INIT_POINTER(bond->current_arp_slave, NULL);
 
-	if (!all && (!bond->params.fail_over_mac ||
+	if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 		     BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))
@@ -2435,6 +2567,12 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (oldcurrent == slave)
 		bond_change_active_slave(bond, NULL);
 
+	/* Must be called after bond_change_active_slave () as the slave
+	 * might change from an active slave to a backup slave. Then it is
+	 * necessary to clear the maddrs on the backup slave.
+	 */
+	bond_slave_ns_maddrs_del(bond, slave);
+
 	if (bond_is_lb(bond)) {
 		/* Must be called only after the slave has been
 		 * detached from the list and the curr_active_slave
@@ -2509,13 +2647,16 @@ static int __bond_release_one(struct net_device *bond_dev,
 		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
 				  slave->dev->addr_len);
 		ss.ss_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
+		dev_set_mac_address(slave_dev, &ss, NULL);
 	}
 
-	if (unregister)
+	if (unregister) {
+		netdev_lock_ops(slave_dev);
 		__dev_set_mtu(slave_dev, slave->original_mtu);
-	else
+		netdev_unlock_ops(slave_dev);
+	} else {
 		dev_set_mtu(slave_dev, slave->original_mtu);
+	}
 
 	if (!netif_is_bond_master(slave_dev))
 		slave_dev->priv_flags &= ~IFF_BONDING;
@@ -3014,8 +3155,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		tags = NULL;
 
 		/* Find out through which dev should the packet go */
-		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
-				     RTO_ONLINK, 0);
+		rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0,
+				     RT_SCOPE_LINK);
 		if (IS_ERR(rt)) {
 			/* there's no route to target - try to send arp
 			 * probe to generate any traffic (arp_validate=0)
@@ -4081,7 +4222,7 @@ static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *
 	}
 
 	if (l34 && *ip_proto >= 0)
-		fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
+		fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
 
 	return true;
 }
@@ -4710,7 +4851,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
 		}
 	}
 
-	bond_dev->mtu = new_mtu;
+	WRITE_ONCE(bond_dev->mtu, new_mtu);
 
 	return 0;
 
@@ -4793,8 +4934,7 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev,
-					      (struct sockaddr *)&tmp_ss, NULL);
+		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_ss, NULL);
 		if (tmp_res) {
 			slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n",
 				   __func__, tmp_res);
@@ -5245,7 +5385,7 @@ static inline int bond_slave_override(struct bonding *bond,
 
 	/* Find out if any slaves have the same mapping as this skb. */
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (slave->queue_id == skb_get_queue_mapping(skb)) {
+		if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) {
 			if (bond_slave_is_up(slave) &&
 			    slave->link == BOND_LINK_UP) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
@@ -5497,9 +5637,9 @@ bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
 		break;
 
 	default:
-		/* Should never happen. Mode guarded by bond_xdp_check() */
-		netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
-		WARN_ON_ONCE(1);
+		if (net_ratelimit())
+			netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
+				   BOND_MODE(bond));
 		return NULL;
 	}
 
@@ -5563,8 +5703,11 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond))
+	if (!bond_xdp_check(bond, BOND_MODE(bond))) {
+		BOND_NL_ERR(dev, extack,
+			    "No native XDP support for the current bonding mode");
 		return -EOPNOTSUPP;
+	}
 
 	old_prog = bond->xdp_prog;
 	bond->xdp_prog = prog;
@@ -5587,7 +5730,7 @@ 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);
@@ -5619,7 +5762,7 @@ 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);
@@ -5755,10 +5898,10 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev,
 }
 
 static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
-				    struct ethtool_ts_info *info)
+				    struct kernel_ethtool_ts_info *info)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct ethtool_ts_info ts_info;
+	struct kernel_ethtool_ts_info ts_info;
 	struct net_device *real_dev;
 	bool sw_tx_support = false;
 	struct list_head *iter;
@@ -5882,11 +6025,14 @@ 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_immutable = true;
 
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
@@ -5895,9 +6041,6 @@ 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 |
@@ -5907,6 +6050,7 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
 	bond_dev->features |= bond_dev->hw_features;
 	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	bond_dev->features |= NETIF_F_GSO_PARTIAL;
 #ifdef CONFIG_XFRM_OFFLOAD
 	bond_dev->hw_features |= BOND_XFRM_FEATURES;
 	/* Only enable XFRM features if this is an active-backup config */
@@ -5931,9 +6075,13 @@ 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(&bond->bond_list);
+	list_del_rcu(&bond->bond_list);
 
 	bond_debug_unregister(bond);
 }
@@ -6338,7 +6486,8 @@ 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;
 
@@ -6347,7 +6496,7 @@ static int bond_init(struct net_device *bond_dev)
 	spin_lock_init(&bond->stats_lock);
 	netdev_lockdep_set_classes(bond_dev);
 
-	list_add_tail(&bond->bond_list, &bn->dev_list);
+	list_add_tail_rcu(&bond->bond_list, &bn->dev_list);
 
 	bond_prepare_sysfs_group(bond);
 
@@ -6419,7 +6568,7 @@ static int __net_init bond_net_init(struct net *net)
 
 /* According to commit 69b0216ac255 ("bonding: fix bonding_masters
  * race condition in bond unloading") we need to remove sysfs files
- * before we remove our devices (done later in bond_net_exit_batch_rtnl())
+ * before we remove our devices (done later in bond_net_exit_rtnl())
  */
 static void __net_exit bond_net_pre_exit(struct net *net)
 {
@@ -6428,25 +6577,20 @@ static void __net_exit bond_net_pre_exit(struct net *net)
 	bond_destroy_sysfs(bn);
 }
 
-static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list,
-						struct list_head *dev_kill_list)
+static void __net_exit bond_net_exit_rtnl(struct net *net,
+					  struct list_head *dev_kill_list)
 {
-	struct bond_net *bn;
-	struct net *net;
+	struct bond_net *bn = net_generic(net, bond_net_id);
+	struct bonding *bond, *tmp_bond;
 
 	/* Kill off any bonds created after unregistering bond rtnl ops */
-	list_for_each_entry(net, net_list, exit_list) {
-		struct bonding *bond, *tmp_bond;
-
-		bn = net_generic(net, bond_net_id);
-		list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
-			unregister_netdevice_queue(bond->dev, dev_kill_list);
-	}
+	list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
+		unregister_netdevice_queue(bond->dev, dev_kill_list);
 }
 
 /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory
  * only after all bonds are gone") bond_destroy_proc_dir() is called
- * after bond_net_exit_batch_rtnl() has completed.
+ * after bond_net_exit_rtnl() has completed.
  */
 static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 {
@@ -6462,7 +6606,7 @@ static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 static struct pernet_operations bond_net_ops = {
 	.init = bond_net_init,
 	.pre_exit = bond_net_pre_exit,
-	.exit_batch_rtnl = bond_net_exit_batch_rtnl,
+	.exit_rtnl = bond_net_exit_rtnl,
 	.exit_batch = bond_net_exit_batch,
 	.id   = &bond_net_id,
 	.size = sizeof(struct bond_net),
@@ -6477,16 +6621,16 @@ static int __init bonding_init(void)
 	if (res)
 		goto out;
 
+	bond_create_debugfs();
+
 	res = register_pernet_subsys(&bond_net_ops);
 	if (res)
-		goto out;
+		goto err_net_ops;
 
 	res = bond_netlink_init();
 	if (res)
 		goto err_link;
 
-	bond_create_debugfs();
-
 	for (i = 0; i < max_bonds; i++) {
 		res = bond_create(&init_net, NULL);
 		if (res)
@@ -6501,10 +6645,11 @@ static int __init bonding_init(void)
 out:
 	return res;
 err:
-	bond_destroy_debugfs();
 	bond_netlink_fini();
 err_link:
 	unregister_pernet_subsys(&bond_net_ops);
+err_net_ops:
+	bond_destroy_debugfs();
 	goto out;
 
 }
@@ -6513,11 +6658,11 @@ static void __exit bonding_exit(void)
 {
 	unregister_netdevice_notifier(&bond_netdev_notifier);
 
-	bond_destroy_debugfs();
-
 	bond_netlink_fini();
 	unregister_pernet_subsys(&bond_net_ops);
 
+	bond_destroy_debugfs();
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	/* Make sure we don't have an imbalance on our netpoll blocking */
 	WARN_ON(atomic_read(&netpoll_block_tx));