linux-kernel - Re: [PATCH 4/4] sched: Idle task shortcut optimization

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 17 Jan 2014 16:09:39 +0100
From:	Daniel Lezcano <daniel.lezcano@...aro.org>
To:	Peter Zijlstra <peterz@...radead.org>
CC:	mingo@...nel.org, linux-kernel@...r.kernel.org,
	linaro-kernel@...ts.linaro.org, alex.shi@...aro.org
Subject: Re: [PATCH 4/4] sched: Idle task shortcut optimization

On 01/17/2014 03:09 PM, Peter Zijlstra wrote:
> On Fri, Jan 17, 2014 at 10:04:04AM +0100, Daniel Lezcano wrote:
>> +	schedstat_inc(rq, sched_goidle);
>> +#ifdef CONFIG_SMP
>> +	/* Trigger the post schedule to do an idle_enter for CFS */
>> +	rq->post_schedule = 1;
>> +#endif
>> +	return rq->idle;
>
> Urgh, that retains the stupid idle crap like it is.
>
> I've not yet tested this, but is there a reason something like the below
> couldn't work?

I tested it by running hackbench and it seems to work as expected.

> ---
> Subject: sched: Clean up idle task SMP logic
> From: Peter Zijlstra <peterz@...radead.org>
> Date: Fri Jan 17 14:54:02 CET 2014
>
> The idle post_schedule hook is just a vile waste of time, fix it proper.
>
> Signed-off-by: Peter Zijlstra <peterz@...radead.org>
> ---
>   kernel/sched/fair.c      |    5 +++--
>   kernel/sched/idle_task.c |   21 ++++++---------------
>   2 files changed, 9 insertions(+), 17 deletions(-)
>
> Index: linux-2.6/kernel/sched/fair.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched/fair.c
> +++ linux-2.6/kernel/sched/fair.c
> @@ -2416,7 +2416,8 @@ void idle_exit_fair(struct rq *this_rq)
>   	update_rq_runnable_avg(this_rq, 0);
>   }
>
> -#else
> +#else /* CONFIG_SMP */
> +
>   static inline void update_entity_load_avg(struct sched_entity *se,
>   					  int update_cfs_rq) {}
>   static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
> @@ -2428,7 +2429,7 @@ static inline void dequeue_entity_load_a
>   					   int sleep) {}
>   static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
>   					      int force_update) {}
> -#endif
> +#endif /* CONFIG_SMP */
>
>   static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
>   {
> Index: linux-2.6/kernel/sched/idle_task.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched/idle_task.c
> +++ linux-2.6/kernel/sched/idle_task.c
> @@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *
>   {
>   	return task_cpu(p); /* IDLE tasks as never migrated */
>   }
> -
> -static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
> -{
> -	idle_exit_fair(rq);
> -	rq_last_tick_reset(rq);
> -}
> -
> -static void post_schedule_idle(struct rq *rq)
> -{
> -	idle_enter_fair(rq);
> -}
>   #endif /* CONFIG_SMP */
> +
>   /*
>    * Idle tasks are unconditionally rescheduled:
>    */
> @@ -37,8 +27,7 @@ static struct task_struct *pick_next_tas
>   {
>   	schedstat_inc(rq, sched_goidle);
>   #ifdef CONFIG_SMP
> -	/* Trigger the post schedule to do an idle_enter for CFS */
> -	rq->post_schedule = 1;
> +	idle_enter_fair(rq);
>   #endif
>   	return rq->idle;
>   }
> @@ -58,6 +47,10 @@ dequeue_task_idle(struct rq *rq, struct
>
>   static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
>   {
> +#ifdef CONFIG_SMP
> +	idle_exit_fair(rq);
> +	rq_last_tick_reset(rq);
> +#endif
>   }
>
>   static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
> @@ -101,8 +94,6 @@ const struct sched_class idle_sched_clas
>
>   #ifdef CONFIG_SMP
>   	.select_task_rq		= select_task_rq_idle,
> -	.pre_schedule		= pre_schedule_idle,
> -	.post_schedule		= post_schedule_idle,
>   #endif
>
>   	.set_curr_task          = set_curr_task_idle,
>


-- 
  <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/