Merge tag 'ipsec-2026-05-29' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2026-05-29

1) xfrm: route MIGRATE notifications to caller's netns
   Thread the caller's netns through km_migrate() so that
   MIGRATE notifications go to the issuing netns, fixing both the
   init_net listener leak and MOBIKE notifications inside
   non-init netns. From Maoyi Xie.

2) xfrm: ipcomp: Free destination pages on acomp errors
   Move the out_free_req label up so that allocated destination
   pages are released on decompression errors, not only on success.
   From Herbert Xu.

3) xfrm: Check for underflow in xfrm_state_mtu
   Reject configurations that cause xfrm_state_mtu() to underflow,
   preventing a negative TFCPAD value from becoming a memset size
   that triggers an out-of-bounds write of several terabytes.
   From David Ahern.

4) xfrm: ah: use skb_to_full_sk in async output callbacks
   Convert the possibly-incomplete skb->sk to a full socket pointer
   in async AH callbacks so that a request_sock or timewait_sock
   never reaches xfrm_output_resume() downstream consumers.
   From Michael Bommarito.

5) Add and revert: esp: fix page frag reference leak on skb_to_sgvec failure
   The patch does not fix te issue completely.

6) xfrm: esp: restore combined single-frag length gate
   Check the aligned post-trailer combined length against a page limit
   in the fast path, preventing skb_page_frag_refill() from falling
   back to a page too small for the destination scatterlist.
   From Jingguo Tan.

7) xfrm: iptfs: reset runtime state when cloning SAs
   Reinitialise the clone's mode_data runtime objects before
   publishing it, preventing queued skbs from being freed with
   list state copied from the original SA when migration fails.
   From Shaomin Chen.

8) xfrm: move policy_bydst RCU sync from per-netns .exit to .pre_exit
   Flush policy tables and drain the workqueue in a .pre_exit handler
   so that cleanup_net() pays one RCU grace period per batch instead
   of one per namespace, fixing stalls at high CLONE_NEWNET rates.
   From Usama Arif.

9) xfrm: input: hold netns during deferred transport reinjection
   Take a netns reference when queueing deferred transport reinjection
   work and drop it after the callback completes, keeping the skb->cb
   net pointer valid until the deferred work runs.
   From Zhengchuan Liang.

* tag 'ipsec-2026-05-29' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  Revert "esp: fix page frag reference leak on skb_to_sgvec failure"
  xfrm: input: hold netns during deferred transport reinjection
  xfrm: move policy_bydst RCU sync from per-netns .exit to .pre_exit
  xfrm: iptfs: reset runtime state when cloning SAs
  xfrm: esp: restore combined single-frag length gate
  esp: fix page frag reference leak on skb_to_sgvec failure
  xfrm: ah: use skb_to_full_sk in async output callbacks
  xfrm: Check for underflow in xfrm_state_mtu
  xfrm: ipcomp: Free destination pages on acomp errors
  xfrm: route MIGRATE notifications to caller's netns
====================

Link: https://patch.msgid.link/20260529092648.3878973-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

12 files changed, 83 insertions, 39 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 10d3edde6b2f..874409127e29 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -715,6 +715,7 @@ struct xfrm_mgr {
 					   const struct xfrm_migrate *m,
 					   int num_bundles,
 					   const struct xfrm_kmaddress *k,
+					   struct net *net,
 					   const struct xfrm_encap_tmpl *encap);
 	bool			(*is_alive)(const struct km_event *c);
 };
@@ -1891,7 +1892,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
 #ifdef CONFIG_XFRM_MIGRATE
 int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	       const struct xfrm_migrate *m, int num_bundles,
-	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_kmaddress *k, struct net *net,
 	       const struct xfrm_encap_tmpl *encap);
 struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
 						u32 if_id);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 4366cbac3f06..6fd642d2278d 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -143,7 +143,7 @@ static void ah_output_done(void *data, int err)
 	}
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 6a5febbdbee4..513c8215c947 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -419,8 +419,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index de1e68199a01..76f7a2de9108 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -337,7 +337,7 @@ static void ah6_output_done(void *data, int err)
 	ah6_restore_hdrs(top_iph, iph_ext, extlen);
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9c06c5a1419d..57481e423e59 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -448,8 +448,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index a166a88d8788..9cffeef18cd9 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3564,7 +3564,7 @@ static int set_ipsecrequest(struct sk_buff *skb,
 #ifdef CONFIG_NET_KEY_MIGRATE
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	int i;
@@ -3669,7 +3669,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, net);
 
 	return 0;
 
@@ -3680,7 +3680,7 @@ err:
 #else
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index f65291eba1f6..e4c2cd24936d 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -797,9 +797,12 @@ static void xfrm_trans_reinject(struct work_struct *work)
 	spin_unlock_bh(&trans->queue_lock);
 
 	local_bh_disable();
-	while ((skb = __skb_dequeue(&queue)))
-		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
-					       NULL, skb);
+	while ((skb = __skb_dequeue(&queue))) {
+		struct net *net = XFRM_TRANS_SKB_CB(skb)->net;
+
+		XFRM_TRANS_SKB_CB(skb)->finish(net, NULL, skb);
+		put_net(net);
+	}
 	local_bh_enable();
 }
 
@@ -808,6 +811,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 				       struct sk_buff *))
 {
 	struct xfrm_trans_tasklet *trans;
+	struct net *hold_net;
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
@@ -816,8 +820,12 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
 
+	hold_net = maybe_get_net(net);
+	if (!hold_net)
+		return -ENODEV;
+
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
-	XFRM_TRANS_SKB_CB(skb)->net = net;
+	XFRM_TRANS_SKB_CB(skb)->net = hold_net;
 	spin_lock_bh(&trans->queue_lock);
 	__skb_queue_tail(&trans->queue, skb);
 	spin_unlock_bh(&trans->queue_lock);
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 5f38dff16177..671d48f8c937 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -51,11 +51,15 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 	struct scatterlist *dsg;
 	int len, dlen;
 
-	if (unlikely(err))
-		goto out_free_req;
+	if (unlikely(!req))
+		return err;
 
 	extra = acomp_request_extra(req);
 	dsg = extra->sg;
+
+	if (unlikely(err))
+		goto out_free_req;
+
 	dlen = req->dlen;
 
 	pskb_trim_unique(skb, 0);
@@ -84,10 +88,10 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 		skb_shinfo(skb)->nr_frags++;
 	} while ((dlen -= len));
 
-	for (; dsg; dsg = sg_next(dsg))
+out_free_req:
+	for (; dsg && sg_page(dsg); dsg = sg_next(dsg))
 		__free_page(sg_page(dsg));
 
-out_free_req:
 	acomp_request_free(req);
 	return err;
 }
diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 97bc979e55ba..6c6bbc040517 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -2650,7 +2650,8 @@ static void __iptfs_init_state(struct xfrm_state *x,
 	x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr);
 
 	/* Always keep a module reference when x->mode_data is set */
-	__module_get(x->mode_cbs->owner);
+	if (x->mode_data != xtfs)
+		__module_get(x->mode_cbs->owner);
 
 	x->mode_data = xtfs;
 	xtfs->x = x;
@@ -2658,22 +2659,39 @@ static void __iptfs_init_state(struct xfrm_state *x,
 
 static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig)
 {
+	struct skb_wseq *w_saved = NULL;
 	struct xfrm_iptfs_data *xtfs;
 
 	xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL);
 	if (!xtfs)
 		return -ENOMEM;
 
-	xtfs->ra_newskb = NULL;
 	if (xtfs->cfg.reorder_win_size) {
-		xtfs->w_saved = kzalloc_objs(*xtfs->w_saved,
-					     xtfs->cfg.reorder_win_size);
-		if (!xtfs->w_saved) {
+		w_saved = kzalloc_objs(*w_saved, xtfs->cfg.reorder_win_size);
+		if (!w_saved) {
 			kfree_sensitive(xtfs);
 			return -ENOMEM;
 		}
 	}
+	xtfs->w_saved = w_saved;
+
+	__skb_queue_head_init(&xtfs->queue);
+	xtfs->queue_size = 0;
+	hrtimer_setup(&xtfs->iptfs_timer, iptfs_delay_timer, CLOCK_MONOTONIC,
+		      IPTFS_HRTIMER_MODE);
+
+	spin_lock_init(&xtfs->drop_lock);
+	hrtimer_setup(&xtfs->drop_timer, iptfs_drop_timer, CLOCK_MONOTONIC,
+		      IPTFS_HRTIMER_MODE);
 
+	xtfs->w_seq_set = false;
+	xtfs->w_wantseq = 0;
+	xtfs->w_savedlen = 0;
+	xtfs->ra_newskb = NULL;
+	xtfs->ra_wantseq = 0;
+	xtfs->ra_runtlen = 0;
+
+	__module_get(x->mode_cbs->owner);
 	x->mode_data = xtfs;
 	xtfs->x = x;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c944327ce66c..dd09d2063da2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4276,21 +4276,21 @@ out_byidx:
 	return -ENOMEM;
 }
 
-static void xfrm_policy_fini(struct net *net)
+static void __net_exit xfrm_net_pre_exit(struct net *net)
 {
-	struct xfrm_pol_inexact_bin *b, *t;
-	unsigned int sz;
-	int dir;
-
 	disable_work_sync(&net->xfrm.policy_hthresh.work);
-
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
 #endif
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
+}
 
-	synchronize_rcu();
+static void xfrm_policy_fini(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *b, *t;
+	unsigned int sz;
+	int dir;
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
@@ -4368,6 +4368,7 @@ static void __net_exit xfrm_net_exit(struct net *net)
 
 static struct pernet_operations __net_initdata xfrm_net_ops = {
 	.init = xfrm_net_init,
+	.pre_exit = xfrm_net_pre_exit,
 	.exit = xfrm_net_exit,
 };
 
@@ -4703,7 +4704,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* Stage 5 - announce */
-	km_migrate(sel, dir, type, m, num_migrate, k, encap);
+	km_migrate(sel, dir, type, m, num_migrate, k, net, encap);
 
 	xfrm_pol_put(pol);
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 686014d39429..589c3b6e4679 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2837,7 +2837,7 @@ EXPORT_SYMBOL(km_policy_expired);
 #ifdef CONFIG_XFRM_MIGRATE
 int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	       const struct xfrm_migrate *m, int num_migrate,
-	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_kmaddress *k, struct net *net,
 	       const struct xfrm_encap_tmpl *encap)
 {
 	int err = -EINVAL;
@@ -2848,7 +2848,7 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->migrate) {
 			ret = km->migrate(sel, dir, type, m, num_migrate, k,
-					  encap);
+					  net, encap);
 			if (!ret)
 				err = ret;
 		}
@@ -3114,10 +3114,14 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	const struct xfrm_type *type = READ_ONCE(x->type);
 	struct crypto_aead *aead;
 	u32 blksize, net_adj = 0;
+	u32 overhead, payload_mtu;
 
 	if (x->km.state != XFRM_STATE_VALID ||
-	    !type || type->proto != IPPROTO_ESP)
+	    !type || type->proto != IPPROTO_ESP) {
+		if (mtu <= x->props.header_len)
+			return 1;
 		return mtu - x->props.header_len;
+	}
 
 	aead = x->data;
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
@@ -3140,8 +3144,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 		break;
 	}
 
-	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
-		 net_adj) & ~(blksize - 1)) + net_adj - 2;
+	overhead = x->props.header_len + crypto_aead_authsize(aead) + net_adj;
+	if (mtu <= overhead)
+		return 1;
+
+	payload_mtu = mtu - overhead;
+	payload_mtu &= ~(blksize - 1);
+	if (payload_mtu <= 2)
+		return 1;
+
+	return payload_mtu + net_adj - 2;
+
 }
 EXPORT_SYMBOL_GPL(xfrm_state_mtu);
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 38a90e5ee3d9..71a4b7278eba 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3271,10 +3271,9 @@ out_cancel:
 
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
-	struct net *net = &init_net;
 	struct sk_buff *skb;
 	int err;
 
@@ -3292,7 +3291,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;