Re: [PATCH v4 2/2] iommu/arm-smmu-v3: Improve CMDQ lock fairness and efficiency

[Jacob Pan]

Hi Will,

On Tue, 25 Nov 2025 17:18:57 +0000
Will Deacon <will@xxxxxxxxxx> wrote:

> On Fri, Nov 14, 2025 at 09:17:18AM -0800, Jacob Pan wrote:
> > @@ -521,9 +527,14 @@ static bool
> > arm_smmu_cmdq_shared_tryunlock(struct arm_smmu_cmdq *cmdq)
> > __ret;
> > 	\ }) 
> > +/*
> > + * Only clear the sign bit when releasing the exclusive lock this
> > will
> > + * allow any shared_lock() waiters to proceed without the
> > possibility
> > + * of entering the exclusive lock in a tight loop.
> > + */
> >  #define arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq,
> > flags)		\ ({
> > 				\
> > -	atomic_set_release(&cmdq->lock, 0);
> > 	\
> > +	atomic_fetch_and_release(~INT_MIN, &cmdq->lock);
> > 	\  
> 
> nit: you can use atomic_fetch_andnot_release(INT_MIN)
> 
Good point, will do.

> That aside, doesn't this introduce a new fairness issue in that a
> steady stream of shared lockers will starve somebody trying to take
> the lock in exclusive state?
> 
I don't think this change will starve exclusive lockers in the
current code flow since new shared locker must acquire exclusive locker
first while polling for available queue spaces.