Re: [PATCH v2 5/6] locking/pvqspinlock: Opportunistically defer kicking to unlock time

[Peter Zijlstra <peterz@infradead.org>]

On Tue, Jul 14, 2015 at 10:13:36PM -0400, Waiman Long wrote:
> +static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
>  {
>  	struct pv_node *pn = (struct pv_node *)node;
>  
> +	if (xchg(&pn->state, vcpu_running) == vcpu_running)
> +		return;
> +
>  	/*
> +	 * Kicking the next node at lock time can actually be a bit faster
> +	 * than doing it at unlock time because the critical section time
> +	 * overlaps with the wakeup latency of the next node. However, if the
> +	 * VM is too overcommmitted, it can happen that we need to kick the
> +	 * CPU again at unlock time (double-kick). To avoid that and also to
> +	 * fully utilize the kick-ahead functionality at unlock time,
> +	 * the kicking will be deferred under either one of the following
> +	 * 2 conditions:
>  	 *
> +	 * 1) The VM guest has too few vCPUs that kick-ahead is not even
> +	 *    enabled. In this case, the chance of double-kick will be
> +	 *    higher.
> +	 * 2) The node after the next one is also in the halted state.
>  	 *
> +	 * In this case, the hashed flag is set to indicate that hashed
> +	 * table has been filled and _Q_SLOW_VAL is set.
>  	 */
> -	if (xchg(&pn->state, vcpu_running) == vcpu_halted) {
> -		pvstat_inc(pvstat_lock_kick);
> -		pv_kick(pn->cpu);
> +	if ((!pv_kick_ahead || pv_get_kick_node(pn, 1)) &&
> +	    (xchg(&pn->hashed, 1) == 0)) {
> +		struct __qspinlock *l = (void *)lock;
> +
> +		/*
> +		 * As this is the same vCPU that will check the _Q_SLOW_VAL
> +		 * value and the hash table later on at unlock time, no atomic
> +		 * instruction is needed.
> +		 */
> +		WRITE_ONCE(l->locked, _Q_SLOW_VAL);
> +		(void)pv_hash(lock, pn);
> +		return;
>  	}
> +
> +	/*
> +	 * Kicking the vCPU even if it is not really halted is safe.
> +	 */
> +	pvstat_inc(pvstat_lock_kick);
> +	pv_kick(pn->cpu);
>  }
>  
>  /*
> @@ -513,6 +545,13 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
>  			cpu_relax();
>  		}
>  
> +		if (!lp && (xchg(&pn->hashed, 1) == 1))
> +			/*
> +			 * The hashed table & _Q_SLOW_VAL had been filled
> +			 * by the lock holder.
> +			 */
> +			lp = (struct qspinlock **)-1;
> +
>  		if (!lp) { /* ONCE */
>  			lp = pv_hash(lock, pn);
>  			/*

*groan*, so you complained the previous version of this patch was too
complex, but let me say I vastly preferred it to this one :/