Merge tag 'ipsec-next-2025-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
1) Remove some unnecessary strscpy_pad() size arguments.
   From Thorsten Blum.

2) Correct use of xso.real_dev on bonding offloads.
   Patchset from Cosmin Ratiu.

3) Add hardware offload configuration to XFRM_MSG_MIGRATE.
   From Chiachang Wang.

4) Refactor migration setup during cloning. This was
   done after the clone was created. Now it is done
   in the cloning function itself.
   From Chiachang Wang.

5) Validate assignment of maximal possible SEQ number.
   Prevent from setting to the maximum sequrnce number
   as this would cause for traffic drop.
   From Leon Romanovsky.

6) Prevent configuration of interface index when offload
   is used. Hardware can't handle this case.i
   From Leon Romanovsky.

7) Always use kfree_sensitive() for SA secret zeroization.
   From Zilin Guan.

ipsec-next-2025-05-23

* tag 'ipsec-next-2025-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next:
  xfrm: use kfree_sensitive() for SA secret zeroization
  xfrm: prevent configuration of interface index when offload is used
  xfrm: validate assignment of maximal possible SEQ number
  xfrm: Refactor migration setup during the cloning process
  xfrm: Migrate offload configuration
  bonding: Fix multiple long standing offload races
  bonding: Mark active offloaded xfrm_states
  xfrm: Add explicit dev to .xdo_dev_state_{add,delete,free}
  xfrm: Remove unneeded device check from validate_xmit_xfrm
  xfrm: Use xdo.dev instead of xdo.real_dev
  net/mlx5: Avoid using xso.real_dev unnecessarily
  xfrm: Remove unnecessary strscpy_pad() size arguments
====================

Link: https://patch.msgid.link/20250523075611.3723340-1-steffen.klassert@secunet.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

18 files changed, 277 insertions, 201 deletions

diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst
index 7f24c09f2694..122204da0fff 100644
--- a/Documentation/networking/xfrm_device.rst
+++ b/Documentation/networking/xfrm_device.rst
@@ -65,9 +65,13 @@ Callbacks to implement
   /* from include/linux/netdevice.h */
   struct xfrmdev_ops {
         /* Crypto and Packet offload callbacks */
-	int	(*xdo_dev_state_add) (struct xfrm_state *x, struct netlink_ext_ack *extack);
-	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
-	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	int	(*xdo_dev_state_add)(struct net_device *dev,
+                                     struct xfrm_state *x,
+                                     struct netlink_ext_ack *extack);
+	void	(*xdo_dev_state_delete)(struct net_device *dev,
+                                        struct xfrm_state *x);
+	void	(*xdo_dev_state_free)(struct net_device *dev,
+                                      struct xfrm_state *x);
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void    (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d05226484c64..98cf4486fcee 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -453,13 +453,14 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
 
 /**
  * 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;
@@ -495,9 +496,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 		goto out;
 	}
 
-	xs->xso.real_dev = real_dev;
-	err = real_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);
 		mutex_lock(&bond->ipsec_lock);
@@ -539,11 +540,25 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
 		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)) {
+		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__);
-			ipsec->xs->xso.real_dev = NULL;
+			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);
 	}
 out:
 	mutex_unlock(&bond->ipsec_lock);
@@ -551,54 +566,27 @@ out:
 
 /**
  * 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;
-	netdevice_tracker tracker;
-	struct bond_ipsec *ipsec;
-	struct bonding *bond;
-	struct slave *slave;
 
-	if (!bond_dev)
+	if (!bond_dev || !xs->xso.real_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);
+	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__);
-		goto out;
+		return;
 	}
 
-	real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
-out:
-	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);
-			kfree(ipsec);
-			break;
-		}
-	}
-	mutex_unlock(&bond->ipsec_lock);
+	real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs);
 }
 
 static void bond_ipsec_del_sa_all(struct bonding *bond)
@@ -624,46 +612,55 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
 			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_delete\n",
 				   __func__);
-		} else {
-			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);
+			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 xfrm_state *xs)
+static void bond_ipsec_free_sa(struct net_device *bond_dev,
+			       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;
 
 	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;
 
+	mutex_lock(&bond->ipsec_lock);
 	if (!xs->xso.real_dev)
 		goto out;
 
-	WARN_ON(xs->xso.real_dev != real_dev);
+	real_dev = xs->xso.real_dev;
 
-	if (real_dev && real_dev->xfrmdev_ops &&
+	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(xs);
+		real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs);
 out:
-	netdev_put(real_dev, &tracker);
+	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+		if (ipsec->xs == xs) {
+			list_del(&ipsec->list);
+			kfree(ipsec);
+			break;
+		}
+	}
+	mutex_unlock(&bond->ipsec_lock);
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 551c279dc14b..51395c96b2e9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -6480,10 +6480,11 @@ static const struct tlsdev_ops cxgb4_ktls_ops = {
 
 #if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
 
-static int cxgb4_xfrm_add_state(struct xfrm_state *x,
+static int cxgb4_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 	int ret;
 
 	if (!mutex_trylock(&uld_mutex)) {
@@ -6494,7 +6495,8 @@ static int cxgb4_xfrm_add_state(struct xfrm_state *x,
 	if (ret)
 		goto out_unlock;
 
-	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x, extack);
+	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(dev, x,
+									extack);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
@@ -6502,9 +6504,9 @@ out_unlock:
 	return ret;
 }
 
-static void cxgb4_xfrm_del_state(struct xfrm_state *x)
+static void cxgb4_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6514,15 +6516,15 @@ static void cxgb4_xfrm_del_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
 }
 
-static void cxgb4_xfrm_free_state(struct xfrm_state *x)
+static void cxgb4_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct adapter *adap = netdev2adap(x->xso.dev);
+	struct adapter *adap = netdev2adap(dev);
 
 	if (!mutex_trylock(&uld_mutex)) {
 		dev_dbg(adap->pdev_dev,
@@ -6532,7 +6534,7 @@ static void cxgb4_xfrm_free_state(struct xfrm_state *x)
 	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
 		goto out_unlock;
 
-	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x);
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(dev, x);
 
 out_unlock:
 	mutex_unlock(&uld_mutex);
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
index baba96883f48..ecd9a0bd5e18 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
@@ -75,9 +75,12 @@ static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state);
 static int ch_ipsec_xmit(struct sk_buff *skb, struct net_device *dev);
 static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop);
 static void ch_ipsec_advance_esn_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x);
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x);
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x);
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x);
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack);
 
 static const struct xfrmdev_ops ch_ipsec_xfrmdev_ops = {
@@ -223,7 +226,8 @@ out:
  * returns 0 on success, negative error if failed to send message to FPGA
  * positive error if FPGA returned a bad response
  */
-static int ch_ipsec_xfrm_add_state(struct xfrm_state *x,
+static int ch_ipsec_xfrm_add_state(struct net_device *dev,
+				   struct xfrm_state *x,
 				   struct netlink_ext_ack *extack)
 {
 	struct ipsec_sa_entry *sa_entry;
@@ -302,14 +306,16 @@ out:
 	return res;
 }
 
-static void ch_ipsec_xfrm_del_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_del_state(struct net_device *dev,
+				    struct xfrm_state *x)
 {
 	/* do nothing */
 	if (!x->xso.offload_handle)
 		return;
 }
 
-static void ch_ipsec_xfrm_free_state(struct xfrm_state *x)
+static void ch_ipsec_xfrm_free_state(struct net_device *dev,
+				     struct xfrm_state *x)
 {
 	struct ipsec_sa_entry *sa_entry;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 648a7c618cd1..d1f4073b36f9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -9,7 +9,7 @@
 #define IXGBE_IPSEC_KEY_BITS  160
 static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
 
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs);
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs);
 
 /**
  * ixgbe_ipsec_set_tx_sa - set the Tx SA registers
@@ -321,7 +321,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (r->used) {
 			if (r->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(r->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, r->xs);
 			else
 				ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi,
 						      r->key, r->salt,
@@ -330,7 +330,7 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
 
 		if (t->used) {
 			if (t->mode & IXGBE_RXTXMOD_VF)
-				ixgbe_ipsec_del_sa(t->xs);
+				ixgbe_ipsec_del_sa(adapter->netdev, t->xs);
 			else
 				ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt);
 		}
@@ -417,6 +417,7 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
 
 /**
  * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -424,10 +425,10 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbe_ipsec_parse_proto_keys(struct net_device *dev,
+					struct xfrm_state *xs,
 					u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -473,11 +474,12 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters
+ * @dev: pointer to net device
  * @xs: pointer to transformer state struct
  **/
-static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
+static int ixgbe_ipsec_check_mgmt_ip(struct net_device *dev,
+				     struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 mfval, manc, reg;
@@ -556,13 +558,14 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 
 /**
  * ixgbe_ipsec_add_sa - program device with a security association
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbe_ipsec_add_sa(struct net_device *dev,
+			      struct xfrm_state *xs,
 			      struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -581,7 +584,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		return -EINVAL;
 	}
 
-	if (ixgbe_ipsec_check_mgmt_ip(xs)) {
+	if (ixgbe_ipsec_check_mgmt_ip(dev, xs)) {
 		NL_SET_ERR_MSG_MOD(extack, "IPsec IP addr clash with mgmt filters");
 		return -EINVAL;
 	}
@@ -615,7 +618,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, rsa.key, &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -724,7 +727,7 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbe_ipsec_parse_proto_keys(dev, xs, tsa.key, &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -752,11 +755,11 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbe_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -841,7 +844,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->rx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->rx_tbl[i].xs);
 	}
 
 	/* search tx sa table */
@@ -850,7 +854,8 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 			continue;
 		if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF &&
 		    ipsec->tx_tbl[i].vf == vf)
-			ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs);
+			ixgbe_ipsec_del_sa(adapter->netdev,
+					   ipsec->tx_tbl[i].xs);
 	}
 }
 
@@ -930,7 +935,7 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 	memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name));
 
 	/* set up the HW offload */
-	err = ixgbe_ipsec_add_sa(xs, NULL);
+	err = ixgbe_ipsec_add_sa(adapter->netdev, xs, NULL);
 	if (err)
 		goto err_aead;
 
@@ -1034,7 +1039,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 		xs = ipsec->tx_tbl[sa_idx].xs;
 	}
 
-	ixgbe_ipsec_del_sa(xs);
+	ixgbe_ipsec_del_sa(adapter->netdev, xs);
 
 	/* remove the xs that was made-up in the add request */
 	kfree_sensitive(xs);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index 8ba037e3d9c2..65580b9cb06f 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -201,6 +201,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
 
 /**
  * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @dev: pointer to net device to program
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate
  * @mysalt: pointer to salt value to populate
@@ -208,10 +209,10 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec,
  * This copies the protocol keys and salt to our own data tables.  The
  * 82599 family only supports the one algorithm.
  **/
-static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int ixgbevf_ipsec_parse_proto_keys(struct net_device *dev,
+					  struct xfrm_state *xs,
 					  u32 *mykey, u32 *mysalt)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -256,13 +257,14 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_add_sa - program device with a security association
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  * @extack: extack point to fill failure reason
  **/
-static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
+static int ixgbevf_ipsec_add_sa(struct net_device *dev,
+				struct xfrm_state *xs,
 				struct netlink_ext_ack *extack)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
@@ -310,7 +312,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 			rsa.decrypt = xs->ealg || xs->aead;
 
 		/* get the key and salt */
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, rsa.key,
+						     &rsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Rx SA table");
 			return ret;
@@ -363,7 +366,8 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 		if (xs->id.proto & IPPROTO_ESP)
 			tsa.encrypt = xs->ealg || xs->aead;
 
-		ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		ret = ixgbevf_ipsec_parse_proto_keys(dev, xs, tsa.key,
+						     &tsa.salt);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for Tx SA table");
 			memset(&tsa, 0, sizeof(tsa));
@@ -388,11 +392,12 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs,
 
 /**
  * ixgbevf_ipsec_del_sa - clear out this specific SA
+ * @dev: pointer to net device to program
  * @xs: pointer to transformer state struct
  **/
-static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
+static void ixgbevf_ipsec_del_sa(struct net_device *dev,
+				 struct xfrm_state *xs)
 {
-	struct net_device *dev = xs->xso.real_dev;
 	struct ixgbevf_adapter *adapter;
 	struct ixgbevf_ipsec *ipsec;
 	u16 sa_idx;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
index fc59e50bafce..a6500e3673f2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
@@ -663,10 +663,10 @@ static int cn10k_ipsec_inb_add_state(struct xfrm_state *x,
 	return -EOPNOTSUPP;
 }
 
-static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
+static int cn10k_ipsec_outb_add_state(struct net_device *dev,
+				      struct xfrm_state *x,
 				      struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xso.dev;
 	struct cn10k_tx_sa_s *sa_entry;
 	struct qmem *sa_info;
 	struct otx2_nic *pf;
@@ -676,7 +676,7 @@ static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
 	if (err)
 		return err;
 
-	pf = netdev_priv(netdev);
+	pf = netdev_priv(dev);
 
 	err = qmem_alloc(pf->dev, &sa_info, pf->ipsec.sa_size, OTX2_ALIGN);
 	if (err)
@@ -700,18 +700,18 @@ static int cn10k_ipsec_outb_add_state(struct xfrm_state *x,
 	return 0;
 }
 
-static int cn10k_ipsec_add_state(struct xfrm_state *x,
+static int cn10k_ipsec_add_state(struct net_device *dev,
+				 struct xfrm_state *x,
 				 struct netlink_ext_ack *extack)
 {
 	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
 		return cn10k_ipsec_inb_add_state(x, extack);
 	else
-		return cn10k_ipsec_outb_add_state(x, extack);
+		return cn10k_ipsec_outb_add_state(dev, x, extack);
 }
 
-static void cn10k_ipsec_del_state(struct xfrm_state *x)
+static void cn10k_ipsec_del_state(struct net_device *dev, struct xfrm_state *x)
 {
-	struct net_device *netdev = x->xso.dev;
 	struct cn10k_tx_sa_s *sa_entry;
 	struct qmem *sa_info;
 	struct otx2_nic *pf;
@@ -720,7 +720,7 @@ static void cn10k_ipsec_del_state(struct xfrm_state *x)
 	if (x->xso.dir == XFRM_DEV_OFFLOAD_IN)
 		return;
 
-	pf = netdev_priv(netdev);
+	pf = netdev_priv(dev);
 
 	sa_info = (struct qmem *)x->xso.offload_handle;
 	sa_entry = (struct cn10k_tx_sa_s *)sa_info->base;
@@ -732,7 +732,7 @@ static void cn10k_ipsec_del_state(struct xfrm_state *x)
 
 	err = cn10k_outb_write_sa(pf, sa_info);
 	if (err)
-		netdev_err(netdev, "Error (%d) deleting SA\n", err);
+		netdev_err(dev, "Error (%d) deleting SA\n", err);
 
 	x->xso.offload_handle = 0;
 	qmem_free(pf->dev, sa_info);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 2dd842aac6fc..77f61cd28a79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -259,8 +259,7 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
-	struct xfrm_state *x = sa_entry->x;
-	struct net_device *netdev;
+	struct net_device *netdev = sa_entry->dev;
 	struct neighbour *n;
 	u8 addr[ETH_ALEN];
 	const void *pkey;
@@ -270,8 +269,6 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	netdev = x->xso.real_dev;
-
 	mlx5_query_mac_address(mdev, addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
@@ -692,17 +689,17 @@ static int mlx5e_ipsec_create_dwork(struct mlx5e_ipsec_sa_entry *sa_entry)
 	return 0;
 }
 
-static int mlx5e_xfrm_add_state(struct xfrm_state *x,
+static int mlx5e_xfrm_add_state(struct net_device *dev,
+				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = NULL;
-	struct net_device *netdev = x->xso.real_dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5e_priv *priv;
 	gfp_t gfp;
 	int err;
 
-	priv = netdev_priv(netdev);
+	priv = netdev_priv(dev);
 	if (!priv->ipsec)
 		return -EOPNOTSUPP;
 
@@ -713,6 +710,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		return -ENOMEM;
 
 	sa_entry->x = x;
+	sa_entry->dev = dev;
 	sa_entry->ipsec = ipsec;
 	/* Check if this SA is originated from acquire flow temporary SA */
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
@@ -809,7 +807,7 @@ err_xfrm:
 	return err;
 }
 
-static void mlx5e_xfrm_del_state(struct xfrm_state *x)
+static void mlx5e_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -822,7 +820,7 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x)
 	WARN_ON(old != sa_entry);
 }
 
-static void mlx5e_xfrm_free_state(struct xfrm_state *x)
+static void mlx5e_xfrm_free_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
@@ -855,8 +853,6 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct mlx5e_ipsec *ipsec;
 	struct neighbour *n = ptr;
-	struct net_device *netdev;
-	struct xfrm_state *x;
 	unsigned long idx;
 
 	if (event != NETEVENT_NEIGH_UPDATE || !(n->nud_state & NUD_VALID))
@@ -876,11 +872,9 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 				continue;
 		}
 
-		x = sa_entry->x;
-		netdev = x->xso.real_dev;
 		data = sa_entry->work->data;
 
-		neigh_ha_snapshot(data->addr, n, netdev);
+		neigh_ha_snapshot(data->addr, n, sa_entry->dev);
 		queue_work(ipsec->wq, &sa_entry->work->work);
 	}
 
@@ -996,8 +990,8 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	size_t headers;
 
 	lockdep_assert(lockdep_is_held(&x->lock) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock));
+		       lockdep_is_held(&net->xfrm.xfrm_cfg_mutex) ||
+		       lockdep_is_held(&net->xfrm.xfrm_state_lock));
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		return;
@@ -1170,7 +1164,7 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 				 struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xdo.real_dev;
+	struct net_device *netdev = x->xdo.dev;
 	struct mlx5e_ipsec_pol_entry *pol_entry;
 	struct mlx5e_priv *priv;
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index a63c2289f8af..ffcd0cdeb775 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -274,6 +274,7 @@ struct mlx5e_ipsec_limits {
 struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_esn_state esn_state;
 	struct xfrm_state *x;
+	struct net_device *dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	void (*set_iv_op)(struct sk_buff *skb, struct xfrm_state *x,
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
index 671af5d4c5d2..9e7c285eaa6b 100644
--- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
+++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c
@@ -266,17 +266,17 @@ static void set_sha2_512hmac(struct nfp_ipsec_cfg_add_sa *cfg, int *trunc_len)
 	}
 }
 
-static int nfp_net_xfrm_add_state(struct xfrm_state *x,
+static int nfp_net_xfrm_add_state(struct net_device *dev,
+				  struct xfrm_state *x,
 				  struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xso.real_dev;
 	struct nfp_ipsec_cfg_mssg msg = {};
 	int i, key_len, trunc_len, err = 0;
 	struct nfp_ipsec_cfg_add_sa *cfg;
 	struct nfp_net *nn;
 	unsigned int saidx;
 
-	nn = netdev_priv(netdev);
+	nn = netdev_priv(dev);
 	cfg = &msg.cfg_add_sa;
 
 	/* General */
@@ -546,17 +546,16 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x,
 	return 0;
 }
 
-static void nfp_net_xfrm_del_state(struct xfrm_state *x)
+static void nfp_net_xfrm_del_state(struct net_device *dev, struct xfrm_state *x)
 {
 	struct nfp_ipsec_cfg_mssg msg = {
 		.cmd = NFP_IPSEC_CFG_MSSG_INV_SA,
 		.sa_idx = x->xso.offload_handle - 1,
 	};
-	struct net_device *netdev = x->xso.real_dev;
 	struct nfp_net *nn;
 	int err;
 
-	nn = netdev_priv(netdev);
+	nn = netdev_priv(dev);
 	err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg,
 					   sizeof(msg), nfp_net_ipsec_cfg);
 	if (err)
diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
index d88bdb9a1717..47cdee5577d4 100644
--- a/drivers/net/netdevsim/ipsec.c
+++ b/drivers/net/netdevsim/ipsec.c
@@ -85,11 +85,11 @@ static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
 	return -ENOSPC;
 }
 
-static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+static int nsim_ipsec_parse_proto_keys(struct net_device *dev,
+				       struct xfrm_state *xs,
 				       u32 *mykey, u32 *mysalt)
 {
 	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
-	struct net_device *dev = xs->xso.real_dev;
 	unsigned char *key_data;
 	char *alg_name = NULL;
 	int key_len;
@@ -129,17 +129,16 @@ static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
 	return 0;
 }
 
-static int nsim_ipsec_add_sa(struct xfrm_state *xs,
+static int nsim_ipsec_add_sa(struct net_device *dev,
+			     struct xfrm_state *xs,
 			     struct netlink_ext_ack *extack)
 {
 	struct nsim_ipsec *ipsec;
-	struct net_device *dev;
 	struct netdevsim *ns;
 	struct nsim_sa sa;
 	u16 sa_idx;
 	int ret;
 
-	dev = xs->xso.real_dev;
 	ns = netdev_priv(dev);
 	ipsec = &ns->ipsec;
 
@@ -174,7 +173,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs,
 		sa.crypt = xs->ealg || xs->aead;
 
 	/* get the key and salt */
-	ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+	ret = nsim_ipsec_parse_proto_keys(dev, xs, sa.key, &sa.salt);
 	if (ret) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for SA table");
 		return ret;
@@ -200,9 +199,9 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs,
 	return 0;
 }
 
-static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+static void nsim_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs)
 {
-	struct netdevsim *ns = netdev_priv(xs->xso.real_dev);
+	struct netdevsim *ns = netdev_priv(dev);
 	struct nsim_ipsec *ipsec = &ns->ipsec;
 	u16 sa_idx;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 73a97cf1bbce..ea9d335de130 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1013,9 +1013,13 @@ struct netdev_bpf {
 
 #ifdef CONFIG_XFRM_OFFLOAD
 struct xfrmdev_ops {
-	int	(*xdo_dev_state_add) (struct xfrm_state *x, struct netlink_ext_ack *extack);
-	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
-	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	int	(*xdo_dev_state_add)(struct net_device *dev,
+				     struct xfrm_state *x,
+				     struct netlink_ext_ack *extack);
+	void	(*xdo_dev_state_delete)(struct net_device *dev,
+					struct xfrm_state *x);
+	void	(*xdo_dev_state_free)(struct net_device *dev,
+				      struct xfrm_state *x);
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void	(*xdo_dev_state_advance_esn) (struct xfrm_state *x);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 06ab2a3d2ebd..a21e276dbe44 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -147,8 +147,19 @@ enum {
 };
 
 struct xfrm_dev_offload {
+	/* The device for this offload.
+	 * Device drivers should not use this directly, as that will prevent
+	 * them from working with bonding device. Instead, the device passed
+	 * to the add/delete callbacks should be used.
+	 */
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
+	/* This is a private pointer used by the bonding driver (and eventually
+	 * should be moved there). Device drivers should not use it.
+	 * Protected by xfrm_state.lock AND bond.ipsec_lock in most cases,
+	 * except in the .xdo_dev_state_del() flow, where only xfrm_state.lock
+	 * is held.
+	 */
 	struct net_device	*real_dev;
 	unsigned long		offload_handle;
 	u8			dir : 2;
@@ -1892,12 +1903,16 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
 						u32 if_id);
 struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
 				      struct xfrm_migrate *m,
-				      struct xfrm_encap_tmpl *encap);
+				      struct xfrm_encap_tmpl *encap,
+				      struct net *net,
+				      struct xfrm_user_offload *xuo,
+				      struct netlink_ext_ack *extack);
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_bundles,
 		 struct xfrm_kmaddress *k, struct net *net,
 		 struct xfrm_encap_tmpl *encap, u32 if_id,
-		 struct netlink_ext_ack *extack);
+		 struct netlink_ext_ack *extack,
+		 struct xfrm_user_offload *xuo);
 #endif
 
 int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c56bb4f451e6..efc2a91f4c48 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2630,7 +2630,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 	}
 
 	return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i,
-			    kma ? &k : NULL, net, NULL, 0, NULL);
+			    kma ? &k : NULL, net, NULL, 0, NULL, NULL);
 
  out:
 	return err;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index d62f76161d83..81fd486b5e56 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -145,10 +145,6 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return NULL;
 	}
 
-	/* This skb was already validated on the upper/virtual dev */
-	if ((x->xso.dev != dev) && (x->xso.real_dev == dev))
-		return skb;
-
 	local_irq_save(flags);
 	sd = this_cpu_ptr(&softnet_data);
 	err = !skb_queue_empty(&sd->xfrm_backlog);
@@ -159,8 +155,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return skb;
 	}
 
-	if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) ||
-				unlikely(xmit_xfrm_check_overflow(skb)))) {
+	if (skb_is_gso(skb) && unlikely(xmit_xfrm_check_overflow(skb))) {
 		struct sk_buff *segs;
 
 		/* Packet got rerouted, fixup features and segment it. */
@@ -256,6 +251,11 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		return -EINVAL;
 	}
 
+	if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) {
+		NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path");
+		return -EINVAL;
+	}
+
 	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
 
 	/* We don't yet support TFC padding. */
@@ -314,7 +314,6 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 
 	xso->dev = dev;
 	netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC);
-	xso->real_dev = dev;
 
 	if (xuo->flags & XFRM_OFFLOAD_INBOUND)
 		xso->dir = XFRM_DEV_OFFLOAD_IN;
@@ -326,11 +325,10 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	else
 		xso->type = XFRM_DEV_OFFLOAD_CRYPTO;
 
-	err = dev->xfrmdev_ops->xdo_dev_state_add(x, extack);
+	err = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, extack);
 	if (err) {
 		xso->dev = NULL;
 		xso->dir = 0;
-		xso->real_dev = NULL;
 		netdev_put(dev, &xso->dev_tracker);
 		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
 
@@ -378,7 +376,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
 
 	xdo->dev = dev;
 	netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC);
-	xdo->real_dev = dev;
 	xdo->type = XFRM_DEV_OFFLOAD_PACKET;
 	switch (dir) {
 	case XFRM_POLICY_IN:
@@ -400,7 +397,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
 	err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack);
 	if (err) {
 		xdo->dev = NULL;
-		xdo->real_dev = NULL;
 		xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
 		xdo->dir = 0;
 		netdev_put(dev, &xdo->dev_tracker);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f4bad8c895d6..d4134a18c658 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4633,7 +4633,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
 		 struct xfrm_kmaddress *k, struct net *net,
 		 struct xfrm_encap_tmpl *encap, u32 if_id,
-		 struct netlink_ext_ack *extack)
+		 struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -4666,7 +4666,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
-			xc = xfrm_state_migrate(x, mp, encap);
+			xc = xfrm_state_migrate(x, mp, encap, net, xuo, extack);
 			if (xc) {
 				x_new[nx_new] = xc;
 				nx_new++;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 07fe8e5daa32..203b585c2ae2 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -599,9 +599,9 @@ static void ___xfrm_state_destroy(struct xfrm_state *x)
 		x->mode_cbs->destroy_state(x);
 	hrtimer_cancel(&x->mtimer);
 	timer_delete_sync(&x->rtimer);
-	kfree(x->aead);
-	kfree(x->aalg);
-	kfree(x->ealg);
+	kfree_sensitive(x->aead);
+	kfree_sensitive(x->aalg);
+	kfree_sensitive(x->ealg);
 	kfree(x->calg);
 	kfree(x->encap);
 	kfree(x->coaddr);
@@ -767,7 +767,7 @@ void xfrm_dev_state_delete(struct xfrm_state *x)
 	struct net_device *dev = READ_ONCE(xso->dev);
 
 	if (dev) {
-		dev->xfrmdev_ops->xdo_dev_state_delete(x);
+		dev->xfrmdev_ops->xdo_dev_state_delete(dev, x);
 		spin_lock_bh(&xfrm_state_dev_gc_lock);
 		hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list);
 		spin_unlock_bh(&xfrm_state_dev_gc_lock);
@@ -789,7 +789,7 @@ void xfrm_dev_state_free(struct xfrm_state *x)
 		spin_unlock_bh(&xfrm_state_dev_gc_lock);
 
 		if (dev->xfrmdev_ops->xdo_dev_state_free)
-			dev->xfrmdev_ops->xdo_dev_state_free(x);
+			dev->xfrmdev_ops->xdo_dev_state_free(dev, x);
 		WRITE_ONCE(xso->dev, NULL);
 		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
 		netdev_put(dev, &xso->dev_tracker);
@@ -1548,19 +1548,19 @@ found:
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			struct xfrm_dev_offload *xdo = &pol->xdo;
 			struct xfrm_dev_offload *xso = &x->xso;
+			struct net_device *dev = xdo->dev;
 
 			xso->type = XFRM_DEV_OFFLOAD_PACKET;
 			xso->dir = xdo->dir;
-			xso->dev = xdo->dev;
-			xso->real_dev = xdo->real_dev;
+			xso->dev = dev;
 			xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
-			netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC);
-			error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL);
+			netdev_hold(dev, &xso->dev_tracker, GFP_ATOMIC);
+			error = dev->xfrmdev_ops->xdo_dev_state_add(dev, x,
+								    NULL);
 			if (error) {
 				xso->dir = 0;
-				netdev_put(xso->dev, &xso->dev_tracker);
+				netdev_put(dev, &xso->dev_tracker);
 				xso->dev = NULL;
-				xso->real_dev = NULL;
 				xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
 				x->km.state = XFRM_STATE_DEAD;
 				to_put = x;
@@ -1958,8 +1958,9 @@ static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *secu
 	return 0;
 }
 
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
-					   struct xfrm_encap_tmpl *encap)
+static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
+					   struct xfrm_encap_tmpl *encap,
+					   struct xfrm_migrate *m)
 {
 	struct net *net = xs_net(orig);
 	struct xfrm_state *x = xfrm_state_alloc(net);
@@ -2058,6 +2059,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 			goto error;
 	}
 
+
+	x->props.family = m->new_family;
+	memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr));
+	memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr));
+
 	return x;
 
  error:
@@ -2120,21 +2126,23 @@ EXPORT_SYMBOL(xfrm_migrate_state_find);
 
 struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
 				      struct xfrm_migrate *m,
-				      struct xfrm_encap_tmpl *encap)
+				      struct xfrm_encap_tmpl *encap,
+				      struct net *net,
+				      struct xfrm_user_offload *xuo,
+				      struct netlink_ext_ack *extack)
 {
 	struct xfrm_state *xc;
 
-	xc = xfrm_state_clone(x, encap);
+	xc = xfrm_state_clone_and_setup(x, encap, m);
 	if (!xc)
 		return NULL;
 
-	xc->props.family = m->new_family;
-
 	if (xfrm_init_state(xc) < 0)
 		goto error;
 
-	memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
-	memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
+	/* configure the hardware if offload is requested */
+	if (xuo && xfrm_dev_state_add(net, xc, xuo, extack))
+		goto error;
 
 	/* add state */
 	if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 784a2d124749..59f258daf830 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -178,11 +178,27 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
 				       "Replay seq and seq_hi should be 0 for output SA");
 			return -EINVAL;
 		}
-		if (rs->oseq_hi && !(p->flags & XFRM_STATE_ESN)) {
-			NL_SET_ERR_MSG(
-				extack,
-				"Replay oseq_hi should be 0 in non-ESN mode for output SA");
-			return -EINVAL;
+
+		if (!(p->flags & XFRM_STATE_ESN)) {
+			if (rs->oseq_hi) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay oseq_hi should be 0 in non-ESN mode for output SA");
+				return -EINVAL;
+			}
+			if (rs->oseq == U32_MAX) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay oseq should be less than 0xFFFFFFFF in non-ESN mode for output SA");
+				return -EINVAL;
+			}
+		} else {
+			if (rs->oseq == U32_MAX && rs->oseq_hi == U32_MAX) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay oseq and oseq_hi should be less than 0xFFFFFFFF for output SA");
+				return -EINVAL;
+			}
 		}
 		if (rs->bmp_len) {
 			NL_SET_ERR_MSG(extack, "Replay bmp_len should 0 for output SA");
@@ -196,11 +212,27 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
 				       "Replay oseq and oseq_hi should be 0 for input SA");
 			return -EINVAL;
 		}
-		if (rs->seq_hi && !(p->flags & XFRM_STATE_ESN)) {
-			NL_SET_ERR_MSG(
-				extack,
-				"Replay seq_hi should be 0 in non-ESN mode for input SA");
-			return -EINVAL;
+		if (!(p->flags & XFRM_STATE_ESN)) {
+			if (rs->seq_hi) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay seq_hi should be 0 in non-ESN mode for input SA");
+				return -EINVAL;
+			}
+
+			if (rs->seq == U32_MAX) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay seq should be less than 0xFFFFFFFF in non-ESN mode for input SA");
+				return -EINVAL;
+			}
+		} else {
+			if (rs->seq == U32_MAX && rs->seq_hi == U32_MAX) {
+				NL_SET_ERR_MSG(
+					extack,
+					"Replay seq and seq_hi should be less than 0xFFFFFFFF for input SA");
+				return -EINVAL;
+			}
 		}
 	}
 
@@ -1173,7 +1205,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	algo = nla_data(nla);
-	strscpy_pad(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
+	strscpy_pad(algo->alg_name, auth->alg_name);
 
 	if (redact_secret && auth->alg_key_len)
 		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
@@ -1186,7 +1218,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, auth->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, auth->alg_name);
 	ap->alg_key_len = auth->alg_key_len;
 	ap->alg_trunc_len = auth->alg_trunc_len;
 	if (redact_secret && auth->alg_key_len)
@@ -1207,7 +1239,7 @@ static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, aead->alg_name);
 	ap->alg_key_len = aead->alg_key_len;
 	ap->alg_icv_len = aead->alg_icv_len;
 
@@ -1229,7 +1261,7 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, ealg->alg_name);
 	ap->alg_key_len = ealg->alg_key_len;
 
 	if (redact_secret && ealg->alg_key_len)
@@ -1250,7 +1282,7 @@ static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, calg->alg_name);
 	ap->alg_key_len = 0;
 
 	return 0;
@@ -3069,6 +3101,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int n = 0;
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_encap_tmpl  *encap = NULL;
+	struct xfrm_user_offload *xuo = NULL;
 	u32 if_id = 0;
 
 	if (!attrs[XFRMA_MIGRATE]) {
@@ -3099,11 +3132,19 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
 
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		xuo = kmemdup(nla_data(attrs[XFRMA_OFFLOAD_DEV]),
+			      sizeof(*xuo), GFP_KERNEL);
+		if (!xuo) {
+			err = -ENOMEM;
+			goto error;
+		}
+	}
 	err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap,
-			   if_id, extack);
-
+			   if_id, extack, xuo);
+error:
 	kfree(encap);
-
+	kfree(xuo);
 	return err;
 }
 #else