Re: [PATCH 4/4] exit: Lockless iteration over task list in mm_update_next_owner()

[Peter Zijlstra]

On Thu, Apr 26, 2018 at 04:52:39PM +0300, Kirill Tkhai wrote:
> In the patch I used the logic, that the below code:
> 
> 	x = A;
> 	spin_lock();
> 	spin_unlock();
> 	spin_lock();
> 	spin_unlock();
> 	y = B;
> 
> cannot reorder much than:
> 
> 	spin_lock();
> 	x = A;		<- this can't become visible later, that spin_unlock()
> 	spin_unlock();
> 	spin_lock();
> 	y = B;		<- this can't become visible earlier, than spin_lock()
> 	spin_unlock();
> 
> Is there a problem?

The two stores will be ordered, but only at the strength of an
smp_wmb(). The above construct does not imply smp_mb(). The difference
is observable on real hardware (Power).