Re: [PATCH v2] locking/mutex: Prevent lock starvation when spinning is enabled

[Peter Zijlstra]

On Thu, Aug 18, 2016 at 05:18:43PM +0200, Peter Zijlstra wrote:
> On Thu, Aug 18, 2016 at 04:27:35PM +0200, Peter Zijlstra wrote:
> > On Wed, Aug 10, 2016 at 11:44:08AM -0700, Jason Low wrote:
> > > @@ -556,8 +604,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
> > >  		 * other waiters. We only attempt the xchg if the count is
> > >  		 * non-negative in order to avoid unnecessary xchg operations:
> > >  		 */
> > > -		if (atomic_read(&lock->count) >= 0 &&
> > > +		if ((!need_yield_to_waiter(lock) || wakeups > 1) &&
> > > +		    atomic_read(&lock->count) >= 0 &&
> > >  		    (atomic_xchg_acquire(&lock->count, -1) == 1))
> > > +			if (wakeups > 1)
> > > +				clear_yield_to_waiter(lock);
> > > +
> > >  			break;
> > >  
> > >  		/*
> > 
> > There's some { } gone missing there...
> > 
> > Also, I think I'll change it to avoid that extra wakeups > 1 condition..
> 
> Also, its broken, even if we should not trylock, we should still very
> much xchg(-1) to mark the lock as having waiters.

Ah, no. Since need_yield_to_waiter() can only be true if there is an
actual waiter, at which point count must already be -1. /me adds a
comment.