ipv4: ICMP packet inspection for multipath

ICMP packets are inspected to let them route together with the flow they
belong to, minimizing the chance that a problematic path will affect flows
on other paths, and so that anycast environments can work with ECMP.

Signed-off-by: Peter Nørlund <pch@ordbogen.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/route.h

@@ -28,6 +28,7 @@
 #include <net/inetpeer.h>
 #include <net/flow.h>
 #include <net/inet_sock.h>
+#include <net/ip_fib.h>
 #include <net/l3mdev.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
@@ -113,7 +114,15 @@ struct in_device;
 int ip_rt_init(void);
 void rt_cache_flush(struct net *net);
 void rt_flush_dev(struct net_device *dev);
-struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
+struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp,
+					  int mp_hash);
+
+static inline struct rtable *__ip_route_output_key(struct net *net,
+						   struct flowi4 *flp)
+{
+	return __ip_route_output_key_hash(net, flp, -1);
+}
+
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
 				    const struct sock *sk);
 struct dst_entry *ipv4_blackhole_route(struct net *net,

net/ipv4/icmp.c

@@ -440,6 +440,22 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	icmp_xmit_unlock(sk);
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* Source and destination is swapped. See ip_multipath_icmp_hash */
+static int icmp_multipath_hash_skb(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+
+	return fib_multipath_hash(iph->daddr, iph->saddr);
+}
+
+#else
+
+#define icmp_multipath_hash_skb(skb) (-1)
+
+#endif
+
 static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
@@ -464,7 +480,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key(net, fl4);
+	rt = __ip_route_output_key_hash(net, fl4,
+					icmp_multipath_hash_skb(skb_in));
 	if (IS_ERR(rt))
 		return rt;
 

net/ipv4/route.c

@@ -1651,6 +1651,48 @@ static int __mkroute_input(struct sk_buff *skb,
 	return err;
 }
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* To make ICMP packets follow the right flow, the multipath hash is
+ * calculated from the inner IP addresses in reverse order.
+ */
+static int ip_multipath_icmp_hash(struct sk_buff *skb)
+{
+	const struct iphdr *outer_iph = ip_hdr(skb);
+	struct icmphdr _icmph;
+	const struct icmphdr *icmph;
+	struct iphdr _inner_iph;
+	const struct iphdr *inner_iph;
+
+	if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
+		goto standard_hash;
+
+	icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
+				   &_icmph);
+	if (!icmph)
+		goto standard_hash;
+
+	if (icmph->type != ICMP_DEST_UNREACH &&
+	    icmph->type != ICMP_REDIRECT &&
+	    icmph->type != ICMP_TIME_EXCEEDED &&
+	    icmph->type != ICMP_PARAMETERPROB) {
+		goto standard_hash;
+	}
+
+	inner_iph = skb_header_pointer(skb,
+				       outer_iph->ihl * 4 + sizeof(_icmph),
+				       sizeof(_inner_iph), &_inner_iph);
+	if (!inner_iph)
+		goto standard_hash;
+
+	return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+
+standard_hash:
+	return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
+}
+
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+
 static int ip_mkroute_input(struct sk_buff *skb,
 			    struct fib_result *res,
 			    const struct flowi4 *fl4,
@@ -1661,7 +1703,10 @@ static int ip_mkroute_input(struct sk_buff *skb,
 	if (res->fi && res->fi->fib_nhs > 1) {
 		int h;
 
-		h = fib_multipath_hash(saddr, daddr);
+		if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
+			h = ip_multipath_icmp_hash(skb);
+		else
+			h = fib_multipath_hash(saddr, daddr);
 		fib_select_multipath(res, h);
 	}
 #endif
@@ -2030,7 +2075,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
  * Major route resolver routine.
  */
 
-struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
+					  int mp_hash)
 {
 	struct net_device *dev_out = NULL;
 	__u8 tos = RT_FL_TOS(fl4);
@@ -2194,10 +2240,9 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
-		int h;
-
-		h = fib_multipath_hash(fl4->saddr, fl4->daddr);
-		fib_select_multipath(&res, h);
+		if (mp_hash < 0)
+			mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr);
+		fib_select_multipath(&res, mp_hash);
 	}
 	else
 #endif
@@ -2220,7 +2265,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	rcu_read_unlock();
 	return rth;
 }
-EXPORT_SYMBOL_GPL(__ip_route_output_key);
+EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
 
 static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
 {