Re: [PATCH -v7][RFC]: mutex: implement adaptive spinning

[Steven Rostedt]

On Thu, 8 Jan 2009, Peter Zijlstra wrote:
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -4672,6 +4672,72 @@ need_resched_nonpreemptible:
>  }
>  EXPORT_SYMBOL(schedule);
>  
> +#ifdef CONFIG_SMP
> +/*
> + * Look out! "owner" is an entirely speculative pointer
> + * access and not reliable.
> + */
> +int spin_on_owner(struct mutex *lock, struct thread_info *owner)
> +{
> +	unsigned int cpu;
> +	struct rq *rq;
> +	int ret = 1;
> +
> +	if (unlikely(!sched_feat(OWNER_SPIN)))

I would remove the "unlikely", if someone turns OWNER_SPIN off, then you 
have the wrong decision being made. Choices by users should never be in a 
"likely" or "unlikely" annotation. It's discrimination ;-)


> +		return 0;
> +
> +	preempt_disable();
> +#ifdef CONFIG_DEBUG_PAGEALLOC
> +	/*
> +	 * Need to access the cpu field knowing that
> +	 * DEBUG_PAGEALLOC could have unmapped it if
> +	 * the mutex owner just released it and exited.
> +	 */
> +	if (probe_kernel_address(&owner->cpu, cpu))
> +		goto out;
> +#else
> +	cpu = owner->cpu;
> +#endif
> +
> +	/*
> +	 * Even if the access succeeded (likely case),
> +	 * the cpu field may no longer be valid.
> +	 */
> +	if (cpu >= nr_cpumask_bits)
> +		goto out;
> +
> +	/*
> +	 * We need to validate that we can do a
> +	 * get_cpu() and that we have the percpu area.
> +	 */
> +	if (!cpu_online(cpu))
> +		goto out;

Should we need to do a "get_cpu" or something? Couldn't the CPU disappear 
between these two calls. Or does it do a stop-machine and the preempt 
disable will protect us?

-- Steve


> +
> +	rq = cpu_rq(cpu);
> +
> +	for (;;) {
> +		if (lock->owner != owner)
> +			break;
> +
> +		/*
> +		 * Is that owner really running on that cpu?
> +		 */
> +		if (task_thread_info(rq->curr) != owner)
> +			break;
> +
> +		if (need_resched()) {
> +			ret = 0;
> +			break;
> +		}
> +
> +		cpu_relax();
> +	}
> +out:
> +	preempt_enable_no_resched();
> +	return ret;
> +}
> +#endif
> +
>  #ifdef CONFIG_PREEMPT
>  /*
>   * this is the entry point to schedule() from in-kernel preemption
> Index: linux-2.6/include/linux/sched.h
> ===================================================================
> --- linux-2.6.orig/include/linux/sched.h
> +++ linux-2.6/include/linux/sched.h
> @@ -330,6 +330,7 @@ extern signed long schedule_timeout_inte
>  extern signed long schedule_timeout_killable(signed long timeout);
>  extern signed long schedule_timeout_uninterruptible(signed long timeout);
>  asmlinkage void schedule(void);
> +extern int spin_on_owner(struct mutex *lock, struct thread_info *owner);
>  
>  struct nsproxy;
>  struct user_namespace;
> Index: linux-2.6/kernel/sched_features.h
> ===================================================================
> --- linux-2.6.orig/kernel/sched_features.h
> +++ linux-2.6/kernel/sched_features.h
> @@ -13,3 +13,4 @@ SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
>  SCHED_FEAT(ASYM_EFF_LOAD, 1)
>  SCHED_FEAT(WAKEUP_OVERLAP, 0)
>  SCHED_FEAT(LAST_BUDDY, 1)
> +SCHED_FEAT(OWNER_SPIN, 1)
> 
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/