udp: restrict offloads to one namespace

udp tunnel offloads tend to aggregate datagrams based on inner
headers. gro engine gets notified by tunnel implementations about
possible offloads. The match is solely based on the port number.

Imagine a tunnel bound to port 53, the offloading will look into all
DNS packets and tries to aggregate them based on the inner data found
within. This could lead to data corruption and malformed DNS packets.

While this patch minimizes the problem and helps an administrator to find
the issue by querying ip tunnel/fou, a better way would be to match on
the specific destination ip address so if a user space socket is bound
to the same address it will conflict.

Cc: Tom Herbert <[email protected]>
Cc: Eric Dumazet <[email protected]>
Signed-off-by: Hannes Frederic Sowa <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

drivers/net/geneve.c

@@ -376,7 +376,7 @@ static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 	int err;
 
 	if (sa_family == AF_INET) {
-		err = udp_add_offload(&gs->udp_offloads);
+		err = udp_add_offload(sock_net(sk), &gs->udp_offloads);
 		if (err)
 			pr_warn("geneve: udp_add_offload failed with status %d\n",
 				err);

drivers/net/vxlan.c

@@ -621,7 +621,7 @@ static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
 	int err;
 
 	if (sa_family == AF_INET) {
-		err = udp_add_offload(&vs->udp_offloads);
+		err = udp_add_offload(net, &vs->udp_offloads);
 		if (err)
 			pr_warn("vxlan: udp_add_offload failed with status %d\n", err);
 	}

include/net/protocol.h

@@ -107,7 +107,7 @@ int inet_del_offload(const struct net_offload *prot, unsigned char num);
 void inet_register_protosw(struct inet_protosw *p);
 void inet_unregister_protosw(struct inet_protosw *p);
 
-int  udp_add_offload(struct udp_offload *prot);
+int  udp_add_offload(struct net *net, struct udp_offload *prot);
 void udp_del_offload(struct udp_offload *prot);
 
 #if IS_ENABLED(CONFIG_IPV6)

net/ipv4/fou.c

@@ -498,7 +498,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 	sk->sk_allocation = GFP_ATOMIC;
 
 	if (cfg->udp_config.family == AF_INET) {
-		err = udp_add_offload(&fou->udp_offloads);
+		err = udp_add_offload(net, &fou->udp_offloads);
 		if (err)
 			goto error;
 	}

net/ipv4/udp_offload.c

@@ -21,6 +21,7 @@ static struct udp_offload_priv __rcu *udp_offload_base __read_mostly;
 
 struct udp_offload_priv {
 	struct udp_offload	*offload;
+	possible_net_t	net;
 	struct rcu_head		rcu;
 	struct udp_offload_priv __rcu *next;
 };
@@ -241,13 +242,14 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	return segs;
 }
 
-int udp_add_offload(struct udp_offload *uo)
+int udp_add_offload(struct net *net, struct udp_offload *uo)
 {
 	struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC);
 
 	if (!new_offload)
 		return -ENOMEM;
 
+	write_pnet(&new_offload->net, net);
 	new_offload->offload = uo;
 
 	spin_lock(&udp_offload_lock);
@@ -311,7 +313,8 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
 	for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
-		if (uo_priv->offload->port == uh->dest &&
+		if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) &&
+		    uo_priv->offload->port == uh->dest &&
 		    uo_priv->offload->callbacks.gro_receive)
 			goto unflush;
 	}
@@ -389,7 +392,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 
 	uo_priv = rcu_dereference(udp_offload_base);
 	for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
-		if (uo_priv->offload->port == uh->dest &&
+		if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) &&
+		    uo_priv->offload->port == uh->dest &&
 		    uo_priv->offload->callbacks.gro_complete)
 			break;
 	}