Re: [PATCH] Greatly improve TSC calibration using a delayed workqueue

[Andi Kleen <andi@firstfloor.org>]

Hi John,

> +	/*
> +	 * Since the timer is started early in boot, we may be
> +	 * delayed the first time we expire. So set the timer
> +	 * again once we know timers are working.
> +	 */
> +	if (tsc_start == -1) {
> +		/*
> +		 * Only set hpet once, to avoid mixing hardware
> +		 * if the hpet becomes enabled later.
> +		 */
> +		hpet = is_hpet_enabled();
> +		schedule_delayed_work(&tsc_irqwork, HZ);
> +		tsc_start = tsc_read_refs(&ref_start, hpet);
> +		return;
> +	}
> +
> +	tsc_stop = tsc_read_refs(&ref_stop, hpet);

The HPET init code stops, starts the HPET. I think you need some
way to protect against that here, e.g. a variable and rearming the 
timer if it's true.

Another issue may be races against suspend, but that may be too
obscure.

I also worry a bit about NMIs etc. running later during this
and messing up the measurement, but I guess the longer period
makes up for it.

The rest of the patch looks ok to me.

-Andi