Re: [PATCH 4/4] futex: Add FUTEX_LOCK with optional adaptive spinning

[Darren Hart]

Thomas Gleixner wrote:
> On Wed, 5 May 2010, Darren Hart wrote:
>
> > Add a non-pi TID value based futex locking mechanism. This enables the
> > use of adaptive spinning which was problematic with the basic FUTEX_WAIT
> > operation.
>
> You still do way too much work in that spin code with way too much
> code lines.
>
> Can you try the following (completely uncompiled/untested) patch ?
>
> Thanks,
>
> 	tglx
> Subject: futex-simplify.patch
> From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Date: Fri, 07 May 2010 17:56:38 +0200
>
> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> ---
>  kernel/futex.c |   42 ++++++++++++------------------------
>  kernel/sched.c |   66 ---------------------------------------------------------
>  2 files changed, 14 insertions(+), 94 deletions(-)


> +		if (to && !to->task) {
> +			ret = -ETIMEOUT;
>  			break;

I had hoped to be able to do it like this too. Unfortunately, we can't 
arm the timer until after we set TASK_INTERRUPTIBLE, and we don't do 
that until after we give up on spinning.


> -
> -		if (timeout) {
> -			now = ktime_get();
> -			if (timeout->tv64 < now.tv64)
> -				break;
>  		}

This bit clearly needs work. Either via some interpolated time 
calculation using something like jiffies, or via another timer that sets 
a bit we can check in here.

--
Darren Hart
IBM Linux Technology Center
Real-Time Linux Team
--
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/