lkml.org 
[lkml]   [2013]   [Jan]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH] hardlockup: detect hard lockups without NMIs using secondary cpus
From
On Thu, Jan 10, 2013 at 5:39 PM, Liu, Chuansheng
<chuansheng.liu@intel.com> wrote:
>
>
>> -----Original Message-----
>> From: Colin Cross [mailto:ccross@android.com]
>> Sent: Thursday, January 10, 2013 9:58 AM
>> To: linux-kernel@vger.kernel.org
>> Cc: Andrew Morton; Don Zickus; Ingo Molnar; Thomas Gleixner; Liu,
>> Chuansheng; linux-arm-kernel@lists.infradead.org; Colin Cross
>> Subject: [PATCH] hardlockup: detect hard lockups without NMIs using
>> secondary cpus
>>
>> Emulate NMIs on systems where they are not available by using timer
>> interrupts on other cpus. Each cpu will use its softlockup hrtimer
>> to check that the next cpu is processing hrtimer interrupts by
>> verifying that a counter is increasing.
>>
>> This patch is useful on systems where the hardlockup detector is not
>> available due to a lack of NMIs, for example most ARM SoCs.
>> Without this patch any cpu stuck with interrupts disabled can
>> cause a hardware watchdog reset with no debugging information,
>> but with this patch the kernel can detect the lockup and panic,
>> which can result in useful debugging info.
>>
>> Signed-off-by: Colin Cross <ccross@android.com>
>> +static void watchdog_check_hardlockup_other_cpu(void)
>> +{
>> + int cpu;
>> + cpumask_t cpus = watchdog_cpus;
>> +
>> + /*
>> + * Test for hardlockups every 3 samples. The sample period is
>> + * watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
>> + * watchdog_thresh (over by 20%).
>> + */
>> + if (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
>> + return;
>> +
>> + /* check for a hardlockup on the next cpu */
>> + cpu = cpumask_next(smp_processor_id(), &cpus);
>> + if (cpu >= nr_cpu_ids)
>> + cpu = cpumask_first(&cpus);
>> + if (cpu == smp_processor_id())
>> + return;
>> +
>> + smp_rmb();
>> +
>> + if (per_cpu(watchdog_nmi_touch, cpu) == true) {
>> + per_cpu(watchdog_nmi_touch, cpu) = false;
>> + return;
>> + }
>> +
>> + if (is_hardlockup_other_cpu(cpu)) {
>> + /* only warn once */
> One possible case for new hotplug CPU that false hardlockup case.
> 1/ Assume CPU1, CPU2 are online, CPU3 is being hotplug:
> CPU3: CPU2:
> watchdog_nmi_enable()
> per_cpu(watchdog_nmi_touch, cpu) = true;
> cpumask_set_cpu(cpu, &watchdog_cpus);
> watchdog_check_hardlockup_other_cpu()
> per_cpu(watchdog_nmi_touch, cpu) = false; == > Here cpu is CPU3
>
> 2/ Before CPU3's first hrtimer interrupt coming, CPU2 is been offlined.
> Then CPU1's next CPU is CPU3. But we can not use CPU3's watchdog_nmi_touch to defense
> false CPU3 hardlock more. When CPU1's hrtimer interrupt coming, it is possible report CPU3
> false hard lockup.
>
> Is it the case?

Yes, this is the same race condition I pointed out in reply to Don
Zickus earlier in the thread. I think the easiest solution is to set
per_cpu(watchdog_nmi_touch, next_cpu) = true during cpu offlining.


\
 
 \ /
  Last update: 2013-01-11 07:01    [W:0.112 / U:0.116 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site