Hi John,

В Fri, 18 Feb 2011 13:34:41 -0800
john stultz <johnstul@us.ibm.com> пишет:

> On Fri, 2011-02-18 at 22:16 +0100, Thomas Gleixner wrote:
> > This driver causes hard lockups, when the active clock soure is
> > jiffies. The reason is that it loops with interrupts disabled waiting
> > for a timestamp to be reached by polling getnstimeofday(). Though with
> > a jiffies clocksource, when that code runs on the same CPU which is
> > responsible for updating jiffies, then we loop in circles for ever
> > simply because the timer interrupt cannot update jiffies. So both UP
> > and SMP can be affected.
> 
> Yuck.
> 
> Alexander, Rodolfo: Instead of polling on gtod, could you take a
> timestamp, calculate the delay and then use udelay()?

Sure, it's possible but it would be less precise IMHO. I'll test it.

-- 
  Alexander