[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100323144757.GB17587@isilmar.linta.de>
Date: Tue, 23 Mar 2010 15:47:57 +0100
From: Dominik Brodowski <linux@...inikbrodowski.net>
To: Borislav Petkov <bp@...64.org>
Cc: Thomas Renninger <trenn@...e.de>, akpm@...ux-foundation.org,
davej@...hat.com, cpufreq@...r.kernel.org, x86@...nel.org,
linux-kernel@...r.kernel.org, "H. Peter Anvin" <hpa@...or.com>
Subject: Re: [PATCH 2/5] powernow-k8: Add core performance boost support
Hey Borislav,
On Tue, Mar 23, 2010 at 03:19:34PM +0100, Borislav Petkov wrote:
> From: Dominik Brodowski <linux@...inikbrodowski.net>
> Date: Tue, Mar 23, 2010 at 02:27:37PM +0100
>
> Hi Dominik,
>
> > On Tue, Mar 23, 2010 at 12:58:58PM +0100, Borislav Petkov wrote:
> > > > It could already be set in arch/x86/kernel/cpu/amd.c and
> > > > powernow-k8 could use cpu_has(cpu, X86_FEATURE_CPB);
> > >
> > > I'd still like to cache the cpb_capable value locally instead of getting
> > > x86_cpuinfo percpu var and querying it. Especially if this happens often
> > > and not only at driver init.
> >
> > If it's a percpu var, isn't it local anyway?
>
> I meant driver-local. So that I don't have to deref even the per_cpu var
> and thus save some cycles.
Well, it doesn't seem to be used in any hot path (and if it were, using a
per-cpu var was better anyway, because of no contention etc.). If it really
saves some cycles, I'm more than fine with keeping it; still, informing the
user in /proc/cpuinfo seems like a sensible thing to do.
Best,
Dominik
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists