Re: [Xen-devel] [PATCH v10 10/19] qspinlock, x86: Allow unfair spinlock in a virtual guest

[Peter Zijlstra <peterz@xxxxxxxxxxxxx>]

On Wed, May 07, 2014 at 11:01:38AM -0400, Waiman Long wrote:


No, we want the unfair thing for VIRT, not PARAVIRT.


> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index 9e7659e..10e87e1 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -227,6 +227,14 @@ static __always_inline int get_qlock(struct qspinlock 
> *lock)
>  {
>       struct __qspinlock *l = (void *)lock;
>  
> +#ifdef CONFIG_PARAVIRT_UNFAIR_LOCKS
> +     if (static_key_false(&paravirt_unfairlocks_enabled))
> +             /*
> +              * Need to use atomic operation to get the lock when
> +              * lock stealing can happen.
> +              */
> +             return cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0;

That's missing {}.

> +#endif


>       barrier();
>       ACCESS_ONCE(l->locked) = _Q_LOCKED_VAL;
>       barrier();


But no, what you want is:

static __always_inline bool virt_lock(struct qspinlock *lock)
{
#ifdef CONFIG_VIRT_MUCK
        if (static_key_false(&virt_unfairlocks_enabled)) {
                while (!queue_spin_trylock(lock))
                        cpu_relax();

                return true;
        }
#else
        return false;
}


void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
        if (virt_lock(lock))
                return;

        ...
}

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel