flow_dissector: use a 64bit load/store

Le lundi 28 novembre 2011 à 19:06 -0500, David Miller a écrit :
> From: Dimitris Michailidis <dm@chelsio.com>
> Date: Mon, 28 Nov 2011 08:25:39 -0800
>
> >> +bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys
> >> *flow)
> >> +{
> >> +	int poff, nhoff = skb_network_offset(skb);
> >> +	u8 ip_proto;
> >> +	u16 proto = skb->protocol;
> >
> > __be16 instead of u16 for proto?
>
> I'll take care of this when I apply these patches.

( CC trimmed )

Thanks David !

Here is a small patch to use one 64bit load/store on x86_64 instead of
two 32bit load/stores.

[PATCH net-next] flow_dissector: use a 64bit load/store

gcc compiler is smart enough to use a single load/store if we
memcpy(dptr, sptr, 8) on x86_64, regardless of
CONFIG_CC_OPTIMIZE_FOR_SIZE

In IP header, daddr immediately follows saddr, this wont change in the
future. We only need to make sure our flow_keys (src,dst) fields wont
break the rule.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/flow_keys.h

@@ -2,6 +2,7 @@
 #define _NET_FLOW_KEYS_H
 
 struct flow_keys {
+	/* (src,dst) must be grouped, in the same way than in IP header */
 	__be32 src;
 	__be32 dst;
 	union {

net/core/flow_dissector.c

@@ -8,6 +8,16 @@
 #include <linux/ppp_defs.h>
 #include <net/flow_keys.h>
 
+/* copy saddr & daddr, possibly using 64bit load/store
+ * Equivalent to :	flow->src = iph->saddr;
+ *			flow->dst = iph->daddr;
+ */
+static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+{
+	BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
+		     offsetof(typeof(*flow), src) + sizeof(flow->src));
+	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+}
 
 bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
 {
@@ -31,8 +41,7 @@ ip:
 			ip_proto = 0;
 		else
 			ip_proto = iph->protocol;
-		flow->src = iph->saddr;
-		flow->dst = iph->daddr;
+		iph_to_flow_copy_addrs(flow, iph);
 		nhoff += iph->ihl * 4;
 		break;
 	}