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 <p...@ordbogen.com>
---
include/net/route.h | 12 +++++++++++-
net/ipv4/icmp.c | 16 ++++++++++++++++
net/ipv4/route.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++----
3 files changed, 77 insertions(+), 5 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index cc61cb9..bbbae2c 100644
--- a/include/net/route.h
+++ b/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 <linux/in_route.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.h>
@@ -110,7 +111,16 @@ 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,
+ multipath_hash_func_t hash_func,
+ void *ctx);
+
+static inline struct rtable *__ip_route_output_key(struct net *net,
+ struct flowi4 *flp)
+{
+ return __ip_route_output_key_hash(net, flp, NULL, NULL);
+}
+
struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
struct sock *sk);
struct dst_entry *ipv4_blackhole_route(struct net *net,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 79fe05b..9d7c97c 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -440,6 +440,17 @@ out_unlock:
icmp_xmit_unlock(sk);
}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+/* Source and destination is swapped. See ip_multipath_hash_skb */
+static int icmp_multipath_hash_skb(void *ctx)
+{
+ const struct sk_buff *skb = (const struct sk_buff *)ctx;
+ const struct iphdr *iph = ip_hdr(skb);
+
+ return jhash_2words(iph->daddr, iph->saddr, fib_multipath_secret);
+}
+#endif
+
static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
@@ -464,7 +475,12 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? :
skb_in->dev->ifindex;
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ rt = __ip_route_output_key_hash(net, fl4, icmp_multipath_hash_skb,
+ skb_in);
+#else
rt = __ip_route_output_key(net, fl4);
+#endif
if (IS_ERR(rt))
return rt;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 41d977c..b472d8c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1648,11 +1648,51 @@ out:
#ifdef CONFIG_IP_ROUTE_MULTIPATH
+static noinline int ip_multipath_icmp_hash_skb(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 jhash_2words(inner_iph->daddr, inner_iph->saddr,
+ fib_multipath_secret);
+
+standard_hash:
+ return jhash_2words(outer_iph->saddr, outer_iph->daddr,
+ fib_multipath_secret);
+}
+
static int ip_multipath_hash_skb(void *ctx)
{
- const struct sk_buff *skb = (struct sk_buff *)ctx;
+ struct sk_buff *skb = (struct sk_buff *)ctx;
const struct iphdr *iph = ip_hdr(skb);
+ if (unlikely(iph->protocol == IPPROTO_ICMP))
+ return ip_multipath_icmp_hash_skb(skb);
+
return jhash_2words(iph->saddr, iph->daddr, fib_multipath_secret);
}
@@ -2056,7 +2096,9 @@ add:
* 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,
+ multipath_hash_func_t hash_func,
+ void *ctx)
{
struct net_device *dev_out = NULL;
__u8 tos = RT_FL_TOS(fl4);
@@ -2218,8 +2260,12 @@ 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)
- fib_select_multipath(&res, ip_multipath_hash_fl4, fl4);
+ if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
+ if (hash_func)
+ fib_select_multipath(&res, hash_func, ctx);
+ else
+ fib_select_multipath(&res, ip_multipath_hash_fl4, fl4);
+ }
else
#endif
if (!res.prefixlen &&
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
