summaryrefslogtreecommitdiff
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
authorPeter Nørlund <pch@ordbogen.com>2015-09-30 10:12:22 +0200
committerDavid S. Miller <davem@davemloft.net>2015-10-05 03:00:04 -0700
commit79a131592dbb81a2dba208622a2ffbfc53f28bc0 (patch)
tree16eb6cd39f9475f87223cbca93da02f1853570bd /net/ipv4/route.c
parent0e884c78ee19e902f300ed147083c28a0c6302f0 (diff)
downloadlwn-79a131592dbb81a2dba208622a2ffbfc53f28bc0.tar.gz
lwn-79a131592dbb81a2dba208622a2ffbfc53f28bc0.zip
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>
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c59
1 files changed, 52 insertions, 7 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0cca44476b1e..54297d3a0559 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1651,6 +1651,48 @@ out:
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 @@ 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,
+ 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 @@ out:
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)
{