[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-id: <alpine.LFD.2.11.1502201707150.25484@knanqh.ubzr>
Date: Fri, 20 Feb 2015 19:56:17 -0500 (EST)
From: Nicolas Pitre <nico@...aro.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, mingo@...nel.org, rjw@...ysocki.net,
tglx@...utronix.de
Subject: Re: [PATCH 27/35] sched/idle: Use explicit broadcast oneshot control
function
On Mon, 16 Feb 2015, Peter Zijlstra wrote:
> From: Thomas Gleixner <tglx@...utronix.de>
>
> Replace the clockevents_notify() call with an explicit function call.
>
> Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
This patch makes my test system hang solid after letting it sit idle for
5 to 15 minutes. Reverting it and this issue goes away.
The explicit function call is not an equivalent replacement. In
clockevents_notify() the clockevents_lock is held across the call to
tick_broadcast_enter() or tick_broadcast_exit(). This patch drops the
locking.
> ---
> kernel/sched/idle.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
> Index: linux/kernel/sched/idle.c
> ===================================================================
> --- linux.orig/kernel/sched/idle.c
> +++ linux/kernel/sched/idle.c
> @@ -143,8 +143,7 @@ use_default:
> * is used from another cpu as a broadcast timer, this call may
> * fail if it is not available
> */
> - if (broadcast &&
> - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
> + if (broadcast && tick_broadcast_enter())
> goto use_default;
>
> /* Take note of the planned idle state. */
> @@ -161,7 +160,7 @@ use_default:
> idle_set_state(this_rq(), NULL);
>
> if (broadcast)
> - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
> + tick_broadcast_exit();
>
> /*
> * Give the governor an opportunity to reflect on the outcome
>
>
> --
> 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/
>
>
--
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/
Powered by blists - more mailing lists