Re: [PATCH 2/7] sched, preempt: Fixup missed PREEMPT_NEED_RESCHEDfolding

[Peter Zijlstra]

On Wed, Nov 20, 2013 at 05:04:52PM +0100, Peter Zijlstra wrote:
> --- a/kernel/cpu/idle.c
> +++ b/kernel/cpu/idle.c
> @@ -105,14 +105,14 @@ static void cpu_idle_loop(void)
>  				__current_set_polling();
>  			}
>  			arch_cpu_idle_exit();
> -			/*
> -			 * We need to test and propagate the TIF_NEED_RESCHED
> -			 * bit here because we might not have send the
> -			 * reschedule IPI to idle tasks.
> -			 */
> -			if (tif_need_resched())
> -				set_preempt_need_resched();
>  		}


		/*
		 * Ensure our read doesn't slip before the read that
		 * terminates the loop above; in that situation we might
		 * actually fail to observe the TIF_NEED_RESCHED we
		 * _know_ must be set here.
		 */

		smp_rmb(); /* pairs with resched_task() */

> +
> +		/*
> +		 * We need to test and propagate the TIF_NEED_RESCHED bit here
> +		 * because we might not have send the reschedule IPI to idle
> +		 * tasks.
> +		 */
> +		preempt_fold_need_resched();
>  		tick_nohz_idle_exit();
>  		schedule_preempt_disabled();
>  	}
--
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/