Re: [PATCH] x86: enable preemption in delay

From: Arjan van de Ven
Date: Sun May 25 2008 - 15:30:25 EST


On Sun, 25 May 2008 21:01:32 +0200 (CEST)
Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:

> On Sun, 25 May 2008, Arjan van de Ven wrote:
>
> > On Sat, 24 May 2008 23:11:20 -0400 (EDT)
> > Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:
> > >
> > > In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew
> > > Morton placed preempt_disable around the entire delay due to
> > > TSC's not working nicely on SMP. Unfortunately for those that
> > > care about latencies this is devastating! Especially when we have
> > > callers to mdelay(8).
> >
> > we used to have a WARN_ON if mdelay was called while preemptable..
> > maybe we should put that back in?
>
> We'd better have one which warns, when mdelay is called with
> preemption disabled.

argument for my variant was "should have used msleep instead"...

I don't disagree that mdelay() is harmful in general; at some point I
stuck a WARN_ON in mdelay when called from irq context...
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/