Re: [PATCH net-next] vlan: use ether_addr_equal_64bits to instead of ether_addr_equal

[Joe Perches <joe@perches.com>]

(adding Jiri Pirko to cc's)

On Mon, 2014-03-03 at 10:49 +0800, Ding Tianhong wrote:
> On 2014/3/3 9:49, Joe Perches wrote:
> > On Mon, 2014-03-03 at 09:14 +0800, Ding Tianhong wrote:
> >> Ether_addr_equal_64bits is more efficient than ether_addr_equal, and
> >> can be used when each argument is an array within a structure that
> >> contains at least two bytes of data beyond the array, so it is safe
> >> to use it for vlan.
> > []
> >> diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
> > []
> >> @@ -26,7 +26,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
> >>  		/* Our lower layer thinks this is not local, let's make sure.
> >>  		 * This allows the VLAN to have a different MAC than the
> >>  		 * underlying device, and still route correctly. */
> >> -		if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
> >> +		if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
> >>  			skb->pkt_type = PACKET_HOST;
> >>  	}
> > 
> > Hi again Ding
> > 
> > If you do have performance numbers:
> > 
> > The lines above this ether_addr_equal_64 are:
> > 
> > 	if (skb->pkt_type == PACKET_OTHERHOST) {
> > 		/* Our lower layer thinks this is not local, let's make sure.
> > 		 * This allows the VLAN to have a different MAC than the
> > 		 * underlying device, and still route correctly. */
> > 		if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
> > 			skb->pkt_type = PACKET_HOST;
> > 	}
> > 
> > Maybe it'd be faster overall to add an unlikely
> > to the == test
> > 
> > 	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
>
> Sorry, I can't understand it clearly, do you mean that if the skb deliver to the vlan dev,
> it is impossible that the pkt_type is PACKET_OTHERHOST at most time?

No, just that it's maybe better to add an unlikely
to the test.

Jiri Pirko's commit 0b5c9db1b modified the code
from a switch/case to a specific test.

I don't know how likely it is in normal uses for
a packet to be delivered as PACKET_OTHERHOST.

I just hoped that if you in fact had performance
numbers for your suggested ether_addr_equal_64bits
test, you might be able to run those same tests
with if (unlikely(skb->pkt_type == PACKET_OTHERHOST))
and see if that was better or worse for performance.

cheers, Joe