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

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

[Ding Tianhong]

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.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
 net/8021q/vlan.c      | 10 +++++-----
 net/8021q/vlan_core.c |  2 +-
 net/8021q/vlan_dev.c  | 10 +++++-----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ec99099..16fb0f4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -286,19 +286,19 @@ static void vlan_sync_address(struct net_device *dev,
 	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
 	/* May be called without an actual change */
-	if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr))
+	if (ether_addr_equal_64bits(vlan->real_dev_addr, dev->dev_addr))
 		return;
 
 	/* vlan address was different from the old address and is equal to
 	 * the new address */
-	if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
-	    ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
+	if (!ether_addr_equal_64bits(vlandev->dev_addr, vlan->real_dev_addr) &&
+	    ether_addr_equal_64bits(vlandev->dev_addr, dev->dev_addr))
 		dev_uc_del(dev, vlandev->dev_addr);
 
 	/* vlan address was equal to the old address and is different from
 	 * the new address */
-	if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
-	    !ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
+	if (ether_addr_equal_64bits(vlandev->dev_addr, vlan->real_dev_addr) &&
+	    !ether_addr_equal_64bits(vlandev->dev_addr, dev->dev_addr))
 		dev_uc_add(dev, vlandev->dev_addr);
 
 	ether_addr_copy(vlan->real_dev_addr, dev->dev_addr);
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 6ee48aa..39cbb46 100644
--- 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;
 	}
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 76d8fab..5e1edd6 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -286,7 +286,7 @@ static int vlan_dev_open(struct net_device *dev)
 	    !(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
 		return -ENETDOWN;
 
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) {
+	if (!ether_addr_equal_64bits(dev->dev_addr, real_dev->dev_addr)) {
 		err = dev_uc_add(real_dev, dev->dev_addr);
 		if (err < 0)
 			goto out;
@@ -319,7 +319,7 @@ clear_allmulti:
 	if (dev->flags & IFF_ALLMULTI)
 		dev_set_allmulti(real_dev, -1);
 del_unicast:
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+	if (!ether_addr_equal_64bits(dev->dev_addr, real_dev->dev_addr))
 		dev_uc_del(real_dev, dev->dev_addr);
 out:
 	netif_carrier_off(dev);
@@ -338,7 +338,7 @@ static int vlan_dev_stop(struct net_device *dev)
 	if (dev->flags & IFF_PROMISC)
 		dev_set_promiscuity(real_dev, -1);
 
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+	if (!ether_addr_equal_64bits(dev->dev_addr, real_dev->dev_addr))
 		dev_uc_del(real_dev, dev->dev_addr);
 
 	netif_carrier_off(dev);
@@ -357,13 +357,13 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
 	if (!(dev->flags & IFF_UP))
 		goto out;
 
-	if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) {
+	if (!ether_addr_equal_64bits(addr->sa_data, real_dev->dev_addr)) {
 		err = dev_uc_add(real_dev, addr->sa_data);
 		if (err < 0)
 			return err;
 	}
 
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+	if (!ether_addr_equal_64bits(dev->dev_addr, real_dev->dev_addr))
 		dev_uc_del(real_dev, dev->dev_addr);
 
 out:
-- 
1.8.0

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

[Joe Perches]

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.

It's true that ether_addr_equal_64bits is faster for
64 bit architectures.  It's 1 64 bit compare and 1 
48 bit mask instead of a 32 bit and a 16 bit compare.

I think unless the code is _extremely_ performance or
fast-path sensitive, ether_addr_equal should be used.

I believe the vlan_do_receive use qualifies.

Are any of the others on the fast path?

Do you have any performance numbers?

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

[Joe Perches]

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)) {

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

[Ding Tianhong]

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?

Regards
Ding

> 

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

[Joe Perches]

(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

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

[Ding Tianhong]

On 2014/3/3 12:36, Joe Perches wrote:
> (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
> 

OK, I got it and I will review the commit 0b5c9db1b, try to
see the performance.

Regards
Ding

> 
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
>