Merge branch 'ICMP-error-handling-for-UDP-tunnels'

Stefano Brivio says:

====================
ICMP error handling for UDP tunnels

This series introduces ICMP error handling for UDP tunnels and
encapsulations and related selftests. We need to handle ICMP errors to
support PMTU discovery and route redirection -- this support is entirely
missing right now:

- patch 1/11 adds a socket lookup for UDP tunnels that use, by design,
  the same destination port on both endpoints -- i.e. VXLAN and GENEVE
- patches 2/11 to 7/11 are specific to VxLAN and GENEVE
- patches 8/11 and 9/11 add infrastructure for lookup of encapsulations
  where sent packets cannot be matched via receiving socket lookup, i.e.
  FoU and GUE
- patches 10/11 and 11/11 are specific to FoU and GUE

v2: changes are listed in the single patches
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 108 insertions, 13 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3488650b90ac..6f8890c5bc7e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -105,6 +105,7 @@
 #include <net/net_namespace.h>
 #include <net/icmp.h>
 #include <net/inet_hashtables.h>
+#include <net/ip_tunnels.h>
 #include <net/route.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
@@ -583,6 +584,89 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 	return true;
 }
 
+DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+void udp_encap_enable(void)
+{
+	static_branch_enable(&udp_encap_needed_key);
+}
+EXPORT_SYMBOL(udp_encap_enable);
+
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
+{
+	int i;
+
+	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+		int (*handler)(struct sk_buff *skb, u32 info);
+
+		if (!iptun_encaps[i])
+			continue;
+		handler = rcu_dereference(iptun_encaps[i]->err_handler);
+		if (handler && !handler(skb, info))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
+/* Try to match ICMP errors to UDP tunnels by looking up a socket without
+ * reversing source and destination port: this will match tunnels that force the
+ * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
+ * lwtunnels might actually break this assumption by being configured with
+ * different destination ports on endpoints, in this case we won't be able to
+ * trace ICMP messages back to them.
+ *
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
+ * Then ask the tunnel implementation to match the error against a valid
+ * association.
+ *
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
+ */
+static struct sock *__udp4_lib_err_encap(struct net *net,
+					 const struct iphdr *iph,
+					 struct udphdr *uh,
+					 struct udp_table *udptable,
+					 struct sk_buff *skb, u32 info)
+{
+	int network_offset, transport_offset;
+	struct sock *sk;
+
+	network_offset = skb_network_offset(skb);
+	transport_offset = skb_transport_offset(skb);
+
+	/* Network header needs to point to the outer IPv4 header inside ICMP */
+	skb_reset_network_header(skb);
+
+	/* Transport header needs to point to the UDP header */
+	skb_set_transport_header(skb, iph->ihl << 2);
+
+	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
+			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
+			       udptable, NULL);
+	if (sk) {
+		int (*lookup)(struct sock *sk, struct sk_buff *skb);
+		struct udp_sock *up = udp_sk(sk);
+
+		lookup = READ_ONCE(up->encap_err_lookup);
+		if (!lookup || lookup(sk, skb))
+			sk = NULL;
+	}
+
+	if (!sk)
+		sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
+
+	skb_set_transport_header(skb, transport_offset);
+	skb_set_network_header(skb, network_offset);
+
+	return sk;
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -594,13 +678,14 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
  * to find the appropriate port.
  */
 
-void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
+int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 {
 	struct inet_sock *inet;
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	bool tunnel = false;
 	struct sock *sk;
 	int harderr;
 	int err;
@@ -610,8 +695,21 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 			       iph->saddr, uh->source, skb->dev->ifindex,
 			       inet_sdif(skb), udptable, NULL);
 	if (!sk) {
-		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;	/* No socket for error */
+		/* No socket for error: try tunnels before discarding */
+		sk = ERR_PTR(-ENOENT);
+		if (static_branch_unlikely(&udp_encap_needed_key)) {
+			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+						  info);
+			if (!sk)
+				return 0;
+		}
+
+		if (IS_ERR(sk)) {
+			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
+			return PTR_ERR(sk);
+		}
+
+		tunnel = true;
 	}
 
 	err = 0;
@@ -654,6 +752,10 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
 	 *	4.1.3.3.
 	 */
+	if (tunnel) {
+		/* ...not for tunnels though: we don't have a sending socket */
+		goto out;
+	}
 	if (!inet->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
@@ -663,12 +765,12 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
-	return;
+	return 0;
 }
 
-void udp_err(struct sk_buff *skb, u32 info)
+int udp_err(struct sk_buff *skb, u32 info)
 {
-	__udp4_lib_err(skb, info, &udp_table);
+	return __udp4_lib_err(skb, info, &udp_table);
 }
 
 /*
@@ -1891,13 +1993,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
-void udp_encap_enable(void)
-{
-	static_branch_enable(&udp_encap_needed_key);
-}
-EXPORT_SYMBOL(udp_encap_enable);
-
 /* returns:
  *  -1: error
  *   0: success