Merge tag 'ipsec-2025-05-21' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2025-05-21

1) Fix some missing kfree_skb in the error paths of espintcp.
   From Sabrina Dubroca.

2) Fix a reference leak in espintcp.
   From Sabrina Dubroca.

3) Fix UDP GRO handling for ESPINUDP.
   From Tobias Brunner.

4) Fix ipcomp truesize computation on the receive path.
   From Sabrina Dubroca.

5) Sanitize marks before policy/state insertation.
   From Paul Chaignon.

* tag 'ipsec-2025-05-21' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
  xfrm: Sanitize marks before insert
  xfrm: ipcomp: fix truesize computation on receive
  xfrm: Fix UDP GRO handling for some corner cases
  espintcp: remove encap socket caching to avoid reference leak
  espintcp: fix skb leaks
====================

Link: https://patch.msgid.link/20250521054348.4057269-1-steffen.klassert@secunet.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

9 files changed, 44 insertions, 115 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 39365fd2ea17..06ab2a3d2ebd 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -236,7 +236,6 @@ struct xfrm_state {
 
 	/* Data for encapsulator */
 	struct xfrm_encap_tmpl	*encap;
-	struct sock __rcu	*encap_sk;
 
 	/* NAT keepalive */
 	u32			nat_keepalive_interval; /* seconds */
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0e4076866c0a..f14a41ee4aa1 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 }
 
 #ifdef CONFIG_INET_ESPINTCP
-struct esp_tcp_sk {
-	struct sock *sk;
-	struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
-	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
-	sock_put(esk->sk);
-	kfree(esk);
-}
-
 static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 {
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct net *net = xs_net(x);
-	struct esp_tcp_sk *esk;
 	__be16 sport, dport;
-	struct sock *nsk;
 	struct sock *sk;
 
-	sk = rcu_dereference(x->encap_sk);
-	if (sk && sk->sk_state == TCP_ESTABLISHED)
-		return sk;
-
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
 	dport = encap->encap_dport;
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (sk && sk == nsk) {
-		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
-		if (!esk) {
-			spin_unlock_bh(&x->lock);
-			return ERR_PTR(-ENOMEM);
-		}
-		RCU_INIT_POINTER(x->encap_sk, NULL);
-		esk->sk = sk;
-		call_rcu(&esk->rcu, esp_free_tcp_sk);
-	}
 	spin_unlock_bh(&x->lock);
 
 	sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
@@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 		return ERR_PTR(-EINVAL);
 	}
 
-	spin_lock_bh(&x->lock);
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (encap->encap_sport != sport ||
-	    encap->encap_dport != dport) {
-		sock_put(sk);
-		sk = nsk ?: ERR_PTR(-EREMCHG);
-	} else if (sk == nsk) {
-		sock_put(sk);
-	} else {
-		rcu_assign_pointer(x->encap_sk, sk);
-	}
-	spin_unlock_bh(&x->lock);
-
 	return sk;
 }
 
@@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 
 	sk = esp_find_tcp_sk(x);
 	err = PTR_ERR_OR_ZERO(sk);
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		goto out;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 		err = espintcp_push_skb(sk, skb);
 	bh_unlock_sock(sk);
 
+	sock_put(sk);
+
 out:
 	rcu_read_unlock();
 	return err;
@@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
 	if (IS_ERR(sk))
 		return ERR_CAST(sk);
 
+	sock_put(sk);
+
 	*lenp = htons(len);
 	esph = (struct ip_esp_hdr *)(lenp + 1);
 
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index b5b06323cfd9..0d31a8c108d4 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	int offset = skb_gro_offset(skb);
 	const struct net_offload *ops;
 	struct sk_buff *pp = NULL;
-	int ret;
-
-	offset = offset - sizeof(struct udphdr);
+	int len, dlen;
+	__u8 *udpdata;
+	__be32 *udpdata32;
 
-	if (!pskb_pull(skb, offset))
+	len = skb->len - offset;
+	dlen = offset + min(len, 8);
+	udpdata = skb_gro_header(skb, dlen, offset);
+	udpdata32 = (__be32 *)udpdata;
+	if (unlikely(!udpdata))
 		return NULL;
 
 	rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out;
 
-	ret = __xfrm4_udp_encap_rcv(sk, skb, false);
-	if (ret)
+	/* check if it is a keepalive or IKE packet */
+	if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
 		goto out;
 
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
 
 	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 
 out:
 	rcu_read_unlock();
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
 	NAPI_GRO_CB(skb)->flush = 1;
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9e73944e3b53..72adfc107b55 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 }
 
 #ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
-	struct sock *sk;
-	struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
-	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
-	sock_put(esk->sk);
-	kfree(esk);
-}
-
 static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
 {
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct net *net = xs_net(x);
-	struct esp_tcp_sk *esk;
 	__be16 sport, dport;
-	struct sock *nsk;
 	struct sock *sk;
 
-	sk = rcu_dereference(x->encap_sk);
-	if (sk && sk->sk_state == TCP_ESTABLISHED)
-		return sk;
-
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
 	dport = encap->encap_dport;
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (sk && sk == nsk) {
-		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
-		if (!esk) {
-			spin_unlock_bh(&x->lock);
-			return ERR_PTR(-ENOMEM);
-		}
-		RCU_INIT_POINTER(x->encap_sk, NULL);
-		esk->sk = sk;
-		call_rcu(&esk->rcu, esp_free_tcp_sk);
-	}
 	spin_unlock_bh(&x->lock);
 
 	sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
 		return ERR_PTR(-EINVAL);
 	}
 
-	spin_lock_bh(&x->lock);
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (encap->encap_sport != sport ||
-	    encap->encap_dport != dport) {
-		sock_put(sk);
-		sk = nsk ?: ERR_PTR(-EREMCHG);
-	} else if (sk == nsk) {
-		sock_put(sk);
-	} else {
-		rcu_assign_pointer(x->encap_sk, sk);
-	}
-	spin_unlock_bh(&x->lock);
-
 	return sk;
 }
 
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 
 	sk = esp6_find_tcp_sk(x);
 	err = PTR_ERR_OR_ZERO(sk);
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		goto out;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 		err = espintcp_push_skb(sk, skb);
 	bh_unlock_sock(sk);
 
+	sock_put(sk);
+
 out:
 	rcu_read_unlock();
 	return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
 	if (IS_ERR(sk))
 		return ERR_CAST(sk);
 
+	sock_put(sk);
+
 	*lenp = htons(len);
 	esph = (struct ip_esp_hdr *)(lenp + 1);
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9d6322..841c81abaaf4 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	int offset = skb_gro_offset(skb);
 	const struct net_offload *ops;
 	struct sk_buff *pp = NULL;
-	int ret;
+	int len, dlen;
+	__u8 *udpdata;
+	__be32 *udpdata32;
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return xfrm4_gro_udp_encap_rcv(sk, head, skb);
 
-	offset = offset - sizeof(struct udphdr);
-
-	if (!pskb_pull(skb, offset))
+	len = skb->len - offset;
+	dlen = offset + min(len, 8);
+	udpdata = skb_gro_header(skb, dlen, offset);
+	udpdata32 = (__be32 *)udpdata;
+	if (unlikely(!udpdata))
 		return NULL;
 
 	rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out;
 
-	ret = __xfrm6_udp_encap_rcv(sk, skb, false);
-	if (ret)
+	/* check if it is a keepalive or IKE packet */
+	if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
 		goto out;
 
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
 
 	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 
 out:
 	rcu_read_unlock();
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
 	NAPI_GRO_CB(skb)->flush = 1;
 
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index fe82e2d07300..fc7a603b04f1 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
 	if (skb_queue_len(&ctx->out_queue) >=
-	    READ_ONCE(net_hotdata.max_backlog))
+	    READ_ONCE(net_hotdata.max_backlog)) {
+		kfree_skb(skb);
 		return -ENOBUFS;
+	}
 
 	__skb_queue_tail(&ctx->out_queue, skb);
 
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 0c1420534394..907c3ccb440d 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -48,7 +48,6 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 {
 	struct acomp_req *req = ipcomp_cb(skb)->req;
 	struct ipcomp_req_extra *extra;
-	const int plen = skb->data_len;
 	struct scatterlist *dsg;
 	int len, dlen;
 
@@ -64,7 +63,7 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 
 	/* Only update truesize on input. */
 	if (!hlen)
-		skb->truesize += dlen - plen;
+		skb->truesize += dlen;
 	skb->data_len = dlen;
 	skb->len += dlen;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 143ac3aa7537..f4bad8c895d6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1581,6 +1581,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *delpol;
 	struct hlist_head *chain;
 
+	/* Sanitize mark before store */
+	policy->mark.v &= policy->mark.m;
+
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
 	if (chain)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 341d79ecb5c2..07fe8e5daa32 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -838,9 +838,6 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		xfrm_nat_keepalive_state_updated(x);
 		spin_unlock(&net->xfrm.xfrm_state_lock);
 
-		if (x->encap_sk)
-			sock_put(rcu_dereference_raw(x->encap_sk));
-
 		xfrm_dev_state_delete(x);
 
 		/* All xfrm_state objects are created by xfrm_state_alloc.
@@ -1721,6 +1718,9 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 
 	list_add(&x->km.all, &net->xfrm.state_all);
 
+	/* Sanitize mark before store */
+	x->mark.v &= x->mark.m;
+
 	h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
 			  x->props.reqid, x->props.family);
 	XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,