From: Guenter Roeck <linux@roeck-us.net>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>,
linux-kernel@vger.kernel.org, Don Zickus <dzickus@redhat.com>,
Ingo Molnar <mingo@kernel.org>
Subject: Re: Crashes in perf_event_ctx_lock_nested
Date: Tue, 31 Oct 2017 15:11:07 -0700 [thread overview]
Message-ID: <20171031221107.GA12133@roeck-us.net> (raw)
In-Reply-To: <alpine.DEB.2.20.1710312145190.1942@nanos>
On Tue, Oct 31, 2017 at 10:32:00PM +0100, Thomas Gleixner wrote:
[ ...]
> So we have to revert
>
> a33d44843d45 ("watchdog/hardlockup/perf: Simplify deferred event destroy")
>
> Patch attached.
>
Tested-by: Guenter Roeck <linux@roeck-us.net>
There is still a problem. When running
echo 6 > /proc/sys/kernel/watchdog_thresh
echo 5 > /proc/sys/kernel/watchdog_thresh
repeatedly, the message
NMI watchdog: Enabled. Permanently consumes one hw-PMU counter.
stops after a while (after ~10-30 iterations, with fluctuations).
After adding trace messages into hardlockup_detector_perf_disable()
and hardlockup_detector_perf_enable(), I see:
hardlockup_detector_perf_disable: disable(0): Number of CPUs: 3
hardlockup_detector_perf_disable: disable(1): Number of CPUs: 2
hardlockup_detector_perf_disable: disable(2): Number of CPUs: 1
hardlockup_detector_perf_disable: disable(3): Number of CPUs: 0
...
hardlockup_detector_perf_disable: disable(0): Number of CPUs: 2
hardlockup_detector_perf_disable: disable(1): Number of CPUs: 1
hardlockup_detector_perf_disable: disable(2): Number of CPUs: 0
hardlockup_detector_perf_disable: disable(3): Number of CPUs: -1
...
hardlockup_detector_perf_enable: enable(1): Number of CPUs: -6
hardlockup_detector_perf_enable: enable(3): Number of CPUs: -5
hardlockup_detector_perf_enable: enable(2): Number of CPUs: -4
hardlockup_detector_perf_enable: enable(0): Number of CPUs: -3
Maybe watchdog_cpus needs to be atomic ?
Guenter
next prev parent reply other threads:[~2017-10-31 22:11 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-30 22:45 Crashes in perf_event_ctx_lock_nested Guenter Roeck
2017-10-31 13:48 ` Peter Zijlstra
2017-10-31 17:16 ` Guenter Roeck
2017-10-31 18:50 ` Don Zickus
2017-10-31 20:12 ` Guenter Roeck
2017-10-31 20:23 ` Don Zickus
2017-10-31 21:32 ` Thomas Gleixner
2017-10-31 22:11 ` Guenter Roeck [this message]
2017-11-01 18:11 ` Don Zickus
2017-11-01 18:34 ` Guenter Roeck
2017-11-01 19:46 ` [tip:core/urgent] watchdog/hardlockup/perf: Use atomics to track in-use cpu counter tip-bot for Don Zickus
2017-11-01 20:28 ` tip-bot for Don Zickus
2017-11-01 18:22 ` Crashes in perf_event_ctx_lock_nested Thomas Gleixner
2017-11-01 8:14 ` Peter Zijlstra
2017-11-01 8:26 ` Thomas Gleixner
2017-11-01 19:46 ` [tip:core/urgent] watchdog/harclockup/perf: Revert a33d44843d45 ("watchdog/hardlockup/perf: Simplify deferred event destroy") tip-bot for Thomas Gleixner
2017-11-01 20:32 ` Guenter Roeck
2017-11-01 20:52 ` Thomas Gleixner
2017-11-01 20:27 ` tip-bot for Thomas Gleixner
2017-10-31 18:48 ` Crashes in perf_event_ctx_lock_nested Don Zickus
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=20171031221107.GA12133@roeck-us.net \
--to=linux@roeck-us.net \
--cc=dzickus@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.