Re: [ANNOUNCE] 3.18.7-rt1

[Joakim Hernberg <jhernberg@xxxxxxxxxx>]

On Tue, 17 Feb 2015 09:37:44 +0100
Daniel Wagner <wagi@xxxxxxxxx> wrote:

> I needed the patch below to get it running stable under load on my
> shiny box.

FWIW, this patch makes 3.18-rt survive thermal events on my laptop.

> From c517743659575932d7b7c94a08276d0cee8a2fdd Mon Sep 17 00:00:00 2001
> From: Daniel Wagner <daniel.wagner@xxxxxxxxxxxx>
> Date: Fri, 11 Jul 2014 15:26:13 +0200
> Subject: [PATCH] thermal: Defer thermal wakups to threads
> 
> On RT the spin lock in pkg_temp_thermal_platfrom_thermal_notify will
> call schedule while we run in irq context.
> 
> [<ffffffff816850ac>] dump_stack+0x4e/0x8f
> [<ffffffff81680f7d>] __schedule_bug+0xa6/0xb4
> [<ffffffff816896b4>] __schedule+0x5b4/0x700
> [<ffffffff8168982a>] schedule+0x2a/0x90
> [<ffffffff8168a8b5>] rt_spin_lock_slowlock+0xe5/0x2d0
> [<ffffffff8168afd5>] rt_spin_lock+0x25/0x30
> [<ffffffffa03a7b75>]
> pkg_temp_thermal_platform_thermal_notify+0x45/0x134
> [x86_pkg_temp_thermal] [<ffffffff8103d4db>] ?
> therm_throt_process+0x1b/0x160 [<ffffffff8103d831>]
> intel_thermal_interrupt+0x211/0x250 [<ffffffff8103d8c1>]
> smp_thermal_interrupt+0x21/0x40 [<ffffffff8169415d>]
> thermal_interrupt+0x6d/0x80
> 
> Let's defer the work to a kthread.
> 
> Signed-off-by: Daniel Wagner <daniel.wagner@xxxxxxxxxxxx>
> Cc: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
> ---
>  drivers/thermal/x86_pkg_temp_thermal.c | 49
> ++++++++++++++++++++++++++++++++-- 1 file changed, 47 insertions(+),
> 2 deletions(-)
> 
> diff --git a/drivers/thermal/x86_pkg_temp_thermal.c
> b/drivers/thermal/x86_pkg_temp_thermal.c index 9ea3d9d..001ba02 100644
> --- a/drivers/thermal/x86_pkg_temp_thermal.c
> +++ b/drivers/thermal/x86_pkg_temp_thermal.c
> @@ -29,6 +29,7 @@
>  #include <linux/pm.h>
>  #include <linux/thermal.h>
>  #include <linux/debugfs.h>
> +#include <linux/work-simple.h>
>  #include <asm/cpu_device_id.h>
>  #include <asm/mce.h>
>  
> @@ -352,7 +353,7 @@ static void
> pkg_temp_thermal_threshold_work_fn(struct work_struct *work) }
>  }
>  
> -static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
> +static void platform_thermal_notify_work(struct swork_event *event)
>  {
>  	unsigned long flags;
>  	int cpu = smp_processor_id();
> @@ -369,7 +370,7 @@ static int
> pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
> pkg_work_scheduled[phy_id]) { disable_pkg_thres_interrupt();
>  		spin_unlock_irqrestore(&pkg_work_lock, flags);
> -		return -EINVAL;
> +		return;
>  	}
>  	pkg_work_scheduled[phy_id] = 1;
>  	spin_unlock_irqrestore(&pkg_work_lock, flags);
> @@ -378,9 +379,48 @@ static int
> pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
> schedule_delayed_work_on(cpu,
> &per_cpu(pkg_temp_thermal_threshold_work, cpu),
> msecs_to_jiffies(notify_delay_ms)); +}
> +
> +#ifdef CONFIG_PREEMPT_RT_FULL
> +static struct swork_event notify_work;
> +
> +static int thermal_notify_work_init(void)
> +{
> +	int err;
> +
> +	err = swork_get();
> +	if (!err)
> +		return err;
> +
> +	INIT_SWORK(&notify_work, platform_thermal_notify_work);
> +	return 0;
> +}
> +
> +static void thermal_notify_work_cleanup(void)
> +{
> +	swork_put();
> +}
> +
> +static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
> +{
> +	swork_queue(&notify_work);
>  	return 0;
>  }
>  
> +#else  /* !CONFIG_PREEMPT_RT_FULL */
> +
> +static int thermal_notify_work_init(void) { return 0; }
> +
> +static int thermal_notify_work_cleanup(void) {  }
> +
> +static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
> +{
> +	platform_thermal_notify_work(NULL);
> +
> +	return 0;
> +}
> +#endif /* CONFIG_PREEMPT_RT_FULL */
> +
>  static int find_siblings_cpu(int cpu)
>  {
>  	int i;
> @@ -594,6 +634,10 @@ static int __init pkg_temp_thermal_init(void)
>  	for_each_online_cpu(i)
>  		if (get_core_online(i))
>  			goto err_ret;
> +
> +	if (!thermal_notify_work_init())
> +		goto err_ret;
> +
>  	__register_hotcpu_notifier(&pkg_temp_thermal_notifier);
>  	cpu_notifier_register_done();
>  
> @@ -619,6 +663,7 @@ static void __exit pkg_temp_thermal_exit(void)
>  
>  	cpu_notifier_register_begin();
>  	__unregister_hotcpu_notifier(&pkg_temp_thermal_notifier);
> +	thermal_notify_work_cleanup();
>  	mutex_lock(&phy_dev_list_mutex);
>  	list_for_each_entry_safe(phdev, n, &phy_dev_list, list) {
>  		/* Retore old MSR value for package thermal
> interrupt */



-- 

   Joakim
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html