From: Viresh Kumar <viresh.kumar@linaro.org>
To: Jan Kara <jack@suse.cz>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
rjw@rjwysocki.net
Cc: Tejun Heo <tj@kernel.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
vlevenetz@mm-sol.com, vaibhav.hiremath@linaro.org,
alex.elder@linaro.org, johan@kernel.org,
akpm@linux-foundation.org, rostedt@goodmis.org,
Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>,
linux-pm@vger.kernel.org
Subject: Re: [Query] Preemption (hogging) of the work handler
Date: Tue, 12 Jul 2016 17:18:08 -0700 [thread overview]
Message-ID: <20160713001808.GT4695@ubuntu> (raw)
In-Reply-To: <20160712231903.GR4695@ubuntu>
On 12-07-16, 16:19, Viresh Kumar wrote:
> Okay, we have tracked this BUG and its really interesting.
>
> I hacked the platform's serial driver to implement a putchar() routine
> that simply writes to the FIFO in polling mode, that helped us in
> tracing on where we are going wrong.
>
> The problem is that we are running asynchronous printks and we call
> wake_up_process() from the last running CPU which has disabled
> interrupts. That takes us to: try_to_wake_up().
>
> In our case the CPU gets deadlocked on this line in try_to_wake_up().
>
> raw_spin_lock_irqsave(&p->pi_lock, flags);
>
> I will explain how:
>
> The try_to_wake_up() function takes us through the scheduler code (RT
> sched), to the hrtimer code, where we eventually call ktime_get() (for
> the MONOTONIC clock used for hrtimer). And this function has this:
>
> WARN_ON(timekeeping_suspended);
>
> This starts another printk while we are in the middle of
> wake_up_process() and the CPU tries to take the above lock again and
> gets stuck there :)
>
> This doesn't happen everytime because we don't always call ktime_get()
> and it is called only if hrtimer_active() returns false.
>
> This happened because of a WARN_ON() but it can happen anyway. Think
> about this case:
>
> - offline all CPUs, except 0
> - call any routine that prints messages after disabling interrupts,
> etc.
> - If any of the function within wake_up_process() does a print, we are
> screwed.
>
> So the thing is that we can't really call wake_up_process() in cases
> where the last CPU disables interrupts. And that's why my fixup patch
> (which moved to synchronous prints after suspend) really works.
Actually, any printk done from wake_up_process() will hit this, even
if all the others CPUs are up as well :)
Its only BUG_ON() which has special handling in printk, and so we
print that safely.
--
viresh
next prev parent reply other threads:[~2016-07-13 0:18 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-01 16:59 [Query] Preemption (hogging) of the work handler Viresh Kumar
2016-07-01 17:22 ` Tejun Heo
2016-07-01 17:28 ` Viresh Kumar
2016-07-06 18:28 ` Viresh Kumar
2016-07-06 19:23 ` Steven Rostedt
2016-07-06 19:25 ` Viresh Kumar
2016-07-11 10:26 ` Jan Kara
2016-07-11 15:44 ` Sergey Senozhatsky
2016-07-11 22:35 ` Viresh Kumar
2016-07-11 22:44 ` Rafael J. Wysocki
2016-07-11 22:46 ` Viresh Kumar
2016-07-12 12:24 ` Rafael J. Wysocki
2016-07-12 13:02 ` Viresh Kumar
2016-07-12 13:56 ` Petr Mladek
2016-07-12 14:04 ` Viresh Kumar
2016-07-12 9:38 ` Sergey Senozhatsky
2016-07-12 12:52 ` Petr Mladek
2016-07-12 13:12 ` Viresh Kumar
2016-07-12 17:11 ` Viresh Kumar
2016-07-12 19:59 ` Rafael J. Wysocki
2016-07-12 20:08 ` Viresh Kumar
2016-07-13 7:00 ` Sergey Senozhatsky
2016-07-13 12:05 ` Rafael J. Wysocki
2016-07-13 12:57 ` Sergey Senozhatsky
2016-07-13 13:22 ` Rafael J. Wysocki
2016-07-12 14:03 ` Sergey Senozhatsky
2016-07-12 14:12 ` Viresh Kumar
2016-07-14 23:52 ` Viresh Kumar
2016-07-15 13:11 ` Sergey Senozhatsky
2016-07-15 15:57 ` Viresh Kumar
2016-07-12 23:19 ` Viresh Kumar
2016-07-13 0:18 ` Viresh Kumar [this message]
2016-07-13 5:45 ` Sergey Senozhatsky
2016-07-13 15:39 ` Viresh Kumar
2016-07-13 23:08 ` Rafael J. Wysocki
2016-07-13 23:18 ` Viresh Kumar
2016-07-13 23:38 ` Greg Kroah-Hartman
2016-07-14 0:55 ` Sergey Senozhatsky
2016-07-14 1:09 ` Rafael J. Wysocki
2016-07-14 1:32 ` Sergey Senozhatsky
2016-07-14 21:57 ` Viresh Kumar
2016-07-14 21:55 ` Viresh Kumar
2016-07-14 14:12 ` Jan Kara
2016-07-14 14:33 ` Rafael J. Wysocki
2016-07-14 14:39 ` Jan Kara
2016-07-14 14:47 ` Rafael J. Wysocki
2016-07-14 14:55 ` Jan Kara
2016-07-14 22:14 ` Viresh Kumar
2016-07-14 14:34 ` Sergey Senozhatsky
2016-07-14 15:03 ` Jan Kara
2016-07-14 22:12 ` Viresh Kumar
2016-07-18 11:01 ` Jan Kara
2016-07-18 11:49 ` Rafael J. Wysocki
2016-07-29 20:42 ` Viresh Kumar
2016-07-30 2:12 ` Sergey Senozhatsky
2016-07-11 19:03 ` Viresh Kumar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160713001808.GT4695@ubuntu \
--to=viresh.kumar@linaro.org \
--cc=akpm@linux-foundation.org \
--cc=alex.elder@linaro.org \
--cc=gregkh@linuxfoundation.org \
--cc=jack@suse.cz \
--cc=johan@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rjw@rjwysocki.net \
--cc=rostedt@goodmis.org \
--cc=sergey.senozhatsky.work@gmail.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=tj@kernel.org \
--cc=vaibhav.hiremath@linaro.org \
--cc=vlevenetz@mm-sol.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).