net: ipv4: add support for ECMP hash policy choice

This patch adds support for ECMP hash policy choice via a new sysctl
called fib_multipath_hash_policy and also adds support for L4 hashes.
The current values for fib_multipath_hash_policy are:
 0 - layer 3 (default)
 1 - layer 4
If there's an skb hash already set and it matches the chosen policy then it
will be used instead of being calculated (currently only for L4).
In L3 mode we always calculate the hash due to the ICMP error special
case, the flow dissector's field consistentification should handle the
address order thus we can remove the address reversals.
If the skb is provided we always use it for the hash calculation,
otherwise we fallback to fl4, that is if skb is NULL fl4 has to be set.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 70 insertions, 22 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8471dd116771..5dda1ef81c7e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1734,45 +1734,97 @@ out:
 }
 
 #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.
+ * calculated from the inner IP addresses.
  */
-static int ip_multipath_icmp_hash(struct sk_buff *skb)
+static void ip_multipath_l3_keys(const struct sk_buff *skb,
+				 struct flow_keys *hash_keys)
 {
 	const struct iphdr *outer_iph = ip_hdr(skb);
-	struct icmphdr _icmph;
+	const struct iphdr *inner_iph;
 	const struct icmphdr *icmph;
 	struct iphdr _inner_iph;
-	const struct iphdr *inner_iph;
+	struct icmphdr _icmph;
+
+	hash_keys->addrs.v4addrs.src = outer_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = outer_iph->daddr;
+	if (likely(outer_iph->protocol != IPPROTO_ICMP))
+		return;
 
 	if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
-		goto standard_hash;
+		return;
 
 	icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
 				   &_icmph);
 	if (!icmph)
-		goto standard_hash;
+		return;
 
 	if (icmph->type != ICMP_DEST_UNREACH &&
 	    icmph->type != ICMP_REDIRECT &&
 	    icmph->type != ICMP_TIME_EXCEEDED &&
-	    icmph->type != ICMP_PARAMETERPROB) {
-		goto standard_hash;
-	}
+	    icmph->type != ICMP_PARAMETERPROB)
+		return;
 
 	inner_iph = skb_header_pointer(skb,
 				       outer_iph->ihl * 4 + sizeof(_icmph),
 				       sizeof(_inner_iph), &_inner_iph);
 	if (!inner_iph)
-		goto standard_hash;
+		return;
+	hash_keys->addrs.v4addrs.src = inner_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = inner_iph->daddr;
+}
 
-	return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+/* if skb is set it will be used and fl4 can be NULL */
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+		       const struct sk_buff *skb)
+{
+	struct net *net = fi->fib_net;
+	struct flow_keys hash_keys;
+	u32 mhash;
 
-standard_hash:
-	return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
-}
+	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	case 0:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		if (skb) {
+			ip_multipath_l3_keys(skb, &hash_keys);
+		} else {
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+		}
+		break;
+	case 1:
+		/* skb is currently provided only when forwarding */
+		if (skb) {
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			struct flow_keys keys;
+
+			/* short-circuit if we already have L4 hash present */
+			if (skb->l4_hash)
+				return skb_get_hash_raw(skb) >> 1;
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			skb_flow_dissect_flow_keys(skb, &keys, flag);
+			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+			hash_keys.ports.src = keys.ports.src;
+			hash_keys.ports.dst = keys.ports.dst;
+			hash_keys.basic.ip_proto = keys.basic.ip_proto;
+		} else {
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+			hash_keys.ports.src = fl4->fl4_sport;
+			hash_keys.ports.dst = fl4->fl4_dport;
+			hash_keys.basic.ip_proto = fl4->flowi4_proto;
+		}
+		break;
+	}
+	mhash = flow_hash_from_keys(&hash_keys);
 
+	return mhash >> 1;
+}
+EXPORT_SYMBOL_GPL(fib_multipath_hash);
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
 static int ip_mkroute_input(struct sk_buff *skb,
@@ -1782,12 +1834,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h;
+		int h = fib_multipath_hash(res->fi, NULL, skb);
 
-		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
@@ -2203,7 +2251,7 @@ add:
  */
 
 struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
-					  int mp_hash)
+					  const struct sk_buff *skb)
 {
 	struct net_device *dev_out = NULL;
 	__u8 tos = RT_FL_TOS(fl4);
@@ -2365,7 +2413,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 		goto make_route;
 	}
 
-	fib_select_path(net, &res, fl4, mp_hash);
+	fib_select_path(net, &res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(res);
 	fl4->flowi4_oif = dev_out->ifindex;