2010-08-09 19:52:40

by Geert Uytterhoeven

[permalink] [raw]
Subject: Re: netfilter: add xt_cpu match

On Wed, Aug 4, 2010 at 22:11, Linux Kernel Mailing List
<[email protected]> wrote:
> Gitweb:     http://git.kernel.org/linus/e8648a1fdb54da1f683784b36a17aa65ea56e931
> Commit:     e8648a1fdb54da1f683784b36a17aa65ea56e931
> Parent:     7f1c407579519e71a0dcadc05614fd98acec585e
> Author:     Eric Dumazet <[email protected]>
> AuthorDate: Fri Jul 23 12:59:36 2010 +0200
> Committer:  Patrick McHardy <[email protected]>
> CommitDate: Fri Jul 23 12:59:36 2010 +0200
>
>    netfilter: add xt_cpu match
>
>    In some situations a CPU match permits a better spreading of
>    connections, or select targets only for a given cpu.

> --- a/net/netfilter/Kconfig
> +++ b/net/netfilter/Kconfig
> @@ -663,6 +663,15 @@ config NETFILTER_XT_MATCH_CONNTRACK
>
>          To compile it as a module, choose M here.  If unsure, say N.
>
> +config NETFILTER_XT_MATCH_CPU
> +       tristate '"cpu" match support'
> +       depends on NETFILTER_ADVANCED
> +       help
> +         CPU matching allows you to match packets based on the CPU
> +         currently handling the packet.

Shouldn't this depend on SMP? Or does it make sense to have it on UP, too?

Gr{oetje,eeting}s,

                        Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds


2010-08-09 20:08:39

by Jan Engelhardt

[permalink] [raw]
Subject: Re: netfilter: add xt_cpu match


On Monday 2010-08-09 21:52, Geert Uytterhoeven wrote:
>>
>> +config NETFILTER_XT_MATCH_CPU
>> +       tristate '"cpu" match support'
>> +       depends on NETFILTER_ADVANCED
>> +       help
>> +         CPU matching allows you to match packets based on the CPU
>> +         currently handling the packet.
>
>Shouldn't this depend on SMP? Or does it make sense to have it on UP, too?

Well one thing to consider is that you certainly would not want to
make one ruleset willingly unloadable on another machine (think
automatic code/rule generators).