[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20110706204201.GA19985@somewhere>
Date: Wed, 6 Jul 2011 22:42:06 +0200
From: Frederic Weisbecker <fweisbec@...il.com>
To: "H. Peter Anvin" <hpa@...or.com>
Cc: Andi Kleen <andi@...stfloor.org>,
Jan Beulich <JBeulich@...ell.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Ingo Molnar <mingo@...e.hu>,
Thomas Gleixner <tglx@...utronix.de>,
Arnaldo Carvalho de Melo <acme@...hat.com>,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 3/6] x86,64: Simplify save_regs()
On Wed, Jul 06, 2011 at 11:20:49AM -0700, H. Peter Anvin wrote:
> On 07/06/2011 10:34 AM, Andi Kleen wrote:
> > Frederic Weisbecker <fweisbec@...il.com> writes:
> >>
> >> I really did not think about code duplication, considering
> >> it's better to optimize the irq entry path.
> >>
> >> What do you guys think? We can still revert the whole patchset.
> >
> > FWIW I think it should be a macro, like it was in the original code.
> >
> > Optimizing entry*.S for code size doesn't make a lot of sense.
> >
>
> Code size, no.
>
> *Path* size and cache/prefetch friendliness is another matter.
> The subroutine is bad on that account, too, so yes, this really seems
> like a losing proposition.
>
> I'm not too fond of the gajillion obtuse macros we have, but subroutines
> doesn't make it really any better.
Fine, so I guess we can keep that macro conversion.
--
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