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>

4 files changed, 95 insertions, 50 deletions

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