From: Guillaume Chazarain <[EMAIL PROTECTED]>
Date: Wed, 19 Jul 2006 14:35:15 +0200
> Herbert Xu wrote :
> > Probably. Patches are welcome :)
> Here are they, in both case I checked that the stuff to clear
> was not already cleared, but I could not produce any misbehavior
> by writing random junk
Herbert Xu wrote :
Probably. Patches are welcome :)
Here are they, in both case I checked that the stuff to clear
was not already cleared, but I could not produce any misbehavior
by writing random junk instead of clearing the data. All my tests
were on the loopback using UML.
For IPv4, the adde
On Tue, Jul 18, 2006 at 08:19:34PM +0200, Guillaume Chazarain wrote:
>
> Why not clearing the whole IPCB(skb) instead of
> just IPCB(skb)->opts? that would also clear
> IPCB(skb)->flags.
I agree, we should clear the whole IPCB.
> And, does not ipv6 need the same treatment with
> IP6CB?
Probably.
chas williams - CONTRACTOR wrote:
why does the input side of the ip layer believe the cb contains valid
data? it should zero the contents of the cb, or just fill in the cb
correctly when the packet arrives at its doorstop.
Why not clearing the whole IPCB(skb) instead of
just IPCB(skb)->opts?
From: "chas williams - CONTRACTOR" <[EMAIL PROTECTED]>
Date: Sun, 16 Jul 2006 07:20:35 -0400
> why does the input side of the ip layer believe the cb contains valid
> data? it should zero the contents of the cb, or just fill in the cb
> correctly when the packet arrives at its doorstop.
Yes, tha
From: Herbert Xu <[EMAIL PROTECTED]>
Date: Mon, 17 Jul 2006 08:03:50 +1000
> The thing is qdiscs using cb means that this method of clearing cb
> before netif_rx doesn't work anymore.
>
> In particular, even if loopback clears cb before calling netif_rx,
> some qdisc could come along between neti
On Sat, Jul 15, 2006 at 06:12:22PM -0700, David Miller wrote:
>
> But I'm beginning to think that the onus of this may in fact fall upon
> the devices, in fact. Loopback is one of the few devices where the
> control block might not be cleared out, due to uses in the output
> path. Devices predom
In message <[EMAIL PROTECTED]>,David Miller writes:
>From: Herbert Xu <[EMAIL PROTECTED]>
>> At least this lets us get rid of a few other memsets :)
>>
>Applied, good spotting :-) I remember when we added those
>things.
>
>But I'm beginning to think that the onus of this may in fact fall upon
>th
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Sat, 15 Jul 2006 08:50:58 -0700
> Since skb->cb is aligned, we could optimize the initialization
> slightly by just using:
> *(unsigned long *)skb->cb = 0;
Well, that depends upon two things.
1) How much of the ip_options really needs to be z
From: Herbert Xu <[EMAIL PROTECTED]>
Date: Sat, 15 Jul 2006 23:28:34 +1000
> At least this lets us get rid of a few other memsets :)
>
> [IPV4]: Get rid of redundant IPCB->opts initialisation
>
> Now that we always zero the IPCB->opts in ip_rcv, it is no longer
> necessary to do so before callin
Herbert Xu wrote:
David Miller <[EMAIL PROTECTED]> wrote:
Thank goodness this thing is only 3-words in size, this is going to
run on every single IPv4 packet received by the system. :-/
At least this lets us get rid of a few other memsets :)
[IPV4]: Get rid of redundant IPCB->opts ini
David Miller <[EMAIL PROTECTED]> wrote:
>
> Thank goodness this thing is only 3-words in size, this is going to
> run on every single IPv4 packet received by the system. :-/
At least this lets us get rid of a few other memsets :)
[IPV4]: Get rid of redundant IPCB->opts initialisation
Now that w
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 14 Jul 2006 11:56:21 -0700
> when data arrives at IP through loopback (and possibly other devices).
> So the field needs to be cleared before it confuses the route code.
> This was seen when running netem over loopback, but there are probably
when data arrives at IP through loopback (and possibly other devices).
So the field needs to be cleared before it confuses the route code.
This was seen when running netem over loopback, but there are probably
other device cases. Maybe this should go into stable?
Signed-off-by: Stephen Hemminger <
14 matches
Mail list logo
