[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <200609181839.45546.ak@suse.de>
Date: Mon, 18 Sep 2006 18:39:45 +0200
From: Andi Kleen <ak@...e.de>
To: Benjamin LaHaise <bcrl@...ck.org>
Cc: Linus Torvalds <torvalds@...l.org>, Andrew Morton <akpm@...l.org>,
Chuck Ebbert <76306.1226@...puserve.com>,
In Cognito <defend.the.world@...il.com>,
linux-kernel <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...e.hu>
Subject: Re: Sysenter crash with Nested Task Bit set
On Monday 18 September 2006 18:12, Benjamin LaHaise wrote:
> On Mon, Sep 18, 2006 at 05:29:23PM +0200, Andi Kleen wrote:
> > > - asm volatile("pushl %%ebp\n\t" \
> > > + asm volatile("pushfl\n\t" /* Save flags */ \
> > > + "pushl %%ebp\n\t" \
> >
> > We used to do that pushfl/popfl some time ago, but Ben removed it because
> > it was slow on P4. Ok, nobody thought of that case back then.
>
> It's the pushfl that will be slow on any OoO CPU, as it has dependancies on
> any previous instructions that modified the flags, which ends up bringing
> all of the memory ordering dependancies into play. Doing a popfl to set the
> flags to some known value is much less expensive.
Yes it's never fast, but on basically all non P4 CPUs it is still fast enough
to not be a problem. I suppose it causes a trace cache flush or something like
that there.
-Andi
-
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