[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080904213945.GA18347@elte.hu>
Date: Thu, 4 Sep 2008 23:39:45 +0200
From: Ingo Molnar <mingo@...e.hu>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Alan Cox <alan@...rguk.ukuu.org.uk>,
Thomas Gleixner <tglx@...utronix.de>,
LKML <linux-kernel@...r.kernel.org>,
Alok Kataria <akataria@...are.com>,
Arjan van de Veen <arjan@...radead.org>,
"H. Peter Anvin" <hpa@...or.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: Re: [RFC patch 0/4] TSC calibration improvements
* Linus Torvalds <torvalds@...ux-foundation.org> wrote:
> On Thu, 4 Sep 2008, Linus Torvalds wrote:
> >
> > Face it, if somebody tries to make QUICK_PIT_MS be so large as to
> > that be an issue, then the whole point of the function goes away.
>
> Btw, the same is true of adding any random "sanity checking". The
> point of that thing was to simply only work when the PIT works as
> advertized, and fail immediately if it doesn't. Even *if* you were to
> pick a big calibration delay *and* if you happened to have a PIT that
> is broken and doesn't wrap correctly, the design of the thing would
> mean that it would then fail the calibration already.
>
> Exactly because it would _see_ that it's not wrapping.
yeah - pit_expect_msb() would return after 50,000 iterations with a
failure. So i was wondering whether for such PITs we _want_ the slow and
complicated case to run.
Probably not, because the PIT could quite likely still be counting very
precisely as long as no wraparound was involved.
Ingo
--
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