Re: [PATCH] x86: enable preemption in delay

From: Steven Rostedt
Date: Sun May 25 2008 - 15:33:17 EST



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?
>

That would be a good idea, but that wouldn't solve this issue. The issue
here is that the mdelay itself disables preemption. The caller had
preemption enabled.

The problem was caused by a quick fix by Andrew to handle out of sync
TSC's for a delay that used TSC's as a counter.

-- Steve

--
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/