Re: [PATCH v2 1/4] locking/mutex: Add waiter parameter to mutex_optimistic_spin()

[Waiman Long]

On 02/12/2016 05:02 PM, Davidlohr Bueso wrote:
> On Fri, 12 Feb 2016, Waiman Long wrote:
>
> > This patch adds a new waiter parameter to the mutex_optimistic_spin()
> > function to prepare it to be used by a waiter-spinner that doesn't
> > need to go into the OSQ as there can only be one waiter-spinner which
> > is the head of the waiting queue.
> >
> > Signed-off-by: Waiman Long <Waiman.Long@xxxxxx>
> > ---
> > kernel/locking/mutex.c |   55 
> > ++++++++++++++++++++++++++++++++---------------
> > 1 files changed, 37 insertions(+), 18 deletions(-)
> >
> > diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> > index 0551c21..3c41448 100644
> > --- a/kernel/locking/mutex.c
> > +++ b/kernel/locking/mutex.c
> > @@ -273,11 +273,15 @@ static inline int 
> > mutex_can_spin_on_owner(struct mutex *lock)
> >
> > /*
> >  * Atomically try to take the lock when it is available
> > + *
> > + * For waiter-spinner, the count needs to be set to -1 first which 
> > will be
> > + * cleared to 0 later on if the list becomes empty. For regular 
> > spinner,
> > + * the count will be set to 0.
> >  */
> > -static inline bool mutex_try_to_acquire(struct mutex *lock)
> > +static inline bool mutex_try_to_acquire(struct mutex *lock, int waiter)
> > {
> >     return !mutex_is_locked(lock) &&
> > -        (atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1);
> > +        (atomic_cmpxchg_acquire(&lock->count, 1, waiter ? -1 : 0) == 
> > 1);
> > }
>
> This can be a really hot path, could we get rid of the waiter check 
> and just
> introduce mutex_tro_to_acquire_waiter() or such and set the counter to 
> -1 there?
>
> Thanks,
> Davidlohr

It is hot in the sense that the lock cacheline is highly contested. On 
x86, the ?: statement will most likely be translated to a cmov 
instruction before doing the cmpxchg. The cmov instruction won't affect 
the amount of cacheline contention on that lock cacheline. So I don't 
see there is any problem here.

Cheers,
Longman