From: Peter Zijlstra <peterz@infradead.org>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>,
lenb@kernel.org, "Rafael J. Wysocki" <rjw@rjwysocki.net>,
Eliezer Tamir <eliezer.tamir@linux.intel.com>,
Zhang Rui <rui.zhang@intel.com>,
jacob.jun.pan@linux.intel.com,
Mike Galbraith <bitbucket@online.de>,
Ingo Molnar <mingo@kernel.org>,
hpa@zytor.com, Paul McKenney <paulmck@linux.vnet.ibm.com>,
Thomas Gleixner <tglx@linutronix.de>,
John Stultz <john.stultz@linaro.org>,
Andy Lutomirski <luto@amacapital.net>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
registosites@hotmail.com, srivatsa@mit.edu
Subject: Re: [PATCH 11/15] x86: Rewrite cyc2ns to avoid the need to disable IRQs
Date: Tue, 17 Jun 2014 14:15:35 +0200 [thread overview]
Message-ID: <20140617121535.GY6758@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <CAOh2x=mgeozUMGYQubQ4GKPEB6k_TkcV3CSTzNLqjKok-gROQg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2515 bytes --]
On Mon, Jun 16, 2014 at 10:43:38PM +0530, Viresh Kumar wrote:
> Cc'ing Mauro/Rafael/Srivatsa..
>
> On Thu, Dec 12, 2013 at 7:38 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > Use a ring-buffer like multi-version object structure which allows
> > always having a coherent object; we use this to avoid having to
> > disable IRQs while reading sched_clock() and avoids a problem when
> > getting an NMI while changing the cyc2ns data.
> >
> > MAINLINE PRE POST
> >
> > sched_clock_stable: 1 1 1
> > (cold) sched_clock: 329841 331312 257223
> > (cold) local_clock: 301773 310296 309889
> > (warm) sched_clock: 38375 38247 25280
> > (warm) local_clock: 100371 102713 85268
> > (warm) rdtsc: 27340 27289 24247
> > sched_clock_stable: 0 0 0
> > (cold) sched_clock: 382634 372706 301224
> > (cold) local_clock: 396890 399275 399870
> > (warm) sched_clock: 38194 38124 25630
> > (warm) local_clock: 143452 148698 129629
> > (warm) rdtsc: 27345 27365 24307
> >
> > Signed-off-by: Peter Zijlstra <peterz@infradead.org>
> > ---
> > arch/x86/include/asm/timer.h | 23 +++
> > arch/x86/kernel/cpu/perf_event.c | 14 +-
> > arch/x86/kernel/tsc.c | 229 ++++++++++++++++++++++++++++++++++-----
> > 3 files changed, 236 insertions(+), 30 deletions(-)
>
> Hi Peter,
>
> We have been following a bug around cpufreq changes in 3.14
> (https://bugzilla.kernel.org/show_bug.cgi?id=77201) and our tests
> narrowed it down to this patch after which things aren't working
> as expected.
> Mauro (registosites@hotmail.com) have reported that since 3.14
> after doing hot-unplug/hotplug of CPU1, cpufreq POSTCHANGE notifications
> for every second frequency change hangs his machine ..
Ah, just a freeze?
> Last working tag was: 3.13.8 and it started failing from 3.14 and fails
> for latest 3.15 as well..
>
> model name : AMD Turion(tm) 64 X2 Mobile Technology TL-64
> CPUFreq driver: powernow-k8 ..
> CPUs: Only two CPUs, sharing clock line
What's specific to this particular CPU?
> Can you give any pointers, so that he can get it fixed ?
So what you can try is force a cyc2ns read before the write in
set_cyc2ns_scale(). I think its possible that if we do not do the read,
the write will wait for a 'free' slot indefinitely.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
next prev parent reply other threads:[~2014-06-17 12:15 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-12 14:08 [PATCH 00/15] cleanups and optimizations Peter Zijlstra
2013-12-12 14:08 ` [PATCH 01/15] x86, acpi, idle: Restructure the mwait idle routines Peter Zijlstra
2013-12-19 20:09 ` [tip:x86/idle] " tip-bot for Peter Zijlstra
2013-12-19 20:13 ` H. Peter Anvin
2013-12-19 20:16 ` Peter Zijlstra
2013-12-12 14:08 ` [PATCH 02/15] sched, preempt: Fixup missed PREEMPT_NEED_RESCHED folding Peter Zijlstra
2013-12-12 14:08 ` [PATCH 03/15] preempt, locking: Rework local_bh_{dis,en}able() Peter Zijlstra
2013-12-12 14:08 ` [PATCH 04/15] locking: Optimize lock_bh functions Peter Zijlstra
2013-12-12 14:08 ` [PATCH 05/15] sched, net: Clean up preempt_enable_no_resched() abuse Peter Zijlstra
2013-12-12 14:08 ` [PATCH 06/15] sched, net: Fixup busy_loop_us_clock() Peter Zijlstra
2013-12-12 14:08 ` [PATCH 07/15] sched, thermal: Clean up preempt_enable_no_resched() abuse Peter Zijlstra
2013-12-12 14:08 ` [PATCH 08/15] preempt: Take away preempt_enable_no_resched() from modules Peter Zijlstra
2013-12-12 14:08 ` [PATCH 09/15] x86: Use mul_u64_u32_shr() for native_sched_clock() Peter Zijlstra
2013-12-12 14:08 ` [PATCH 10/15] x86: Move some code around Peter Zijlstra
2013-12-12 14:08 ` [PATCH 11/15] x86: Rewrite cyc2ns to avoid the need to disable IRQs Peter Zijlstra
2014-06-16 17:13 ` Viresh Kumar
2014-06-17 12:15 ` Peter Zijlstra [this message]
2014-06-17 12:42 ` Viresh Kumar
2014-06-17 16:32 ` Mauro
2014-06-17 12:47 ` Mauro
2013-12-12 14:08 ` [PATCH 12/15] sched: Remove local_irq_disable() from the clocks Peter Zijlstra
2013-12-12 14:08 ` [PATCH 13/15] sched: Use a static_key for sched_clock_stable Peter Zijlstra
2014-01-21 22:28 ` Sasha Levin
2014-01-22 10:45 ` Peter Zijlstra
2014-01-22 11:59 ` Peter Zijlstra
2014-01-23 1:53 ` Dave Young
2014-01-23 16:46 ` [tip:sched/urgent] sched/clock: Fixup early initialization tip-bot for Peter Zijlstra
2014-01-22 12:00 ` [PATCH 13/15] sched: Use a static_key for sched_clock_stable Markus Trippelsdorf
2014-01-22 12:07 ` Peter Zijlstra
2014-01-22 12:16 ` Peter Zijlstra
2014-01-22 12:26 ` Markus Trippelsdorf
2014-01-22 12:30 ` Peter Zijlstra
2014-01-22 13:14 ` Markus Trippelsdorf
2014-01-22 14:26 ` Sasha Levin
2014-01-22 18:35 ` Markus Trippelsdorf
2014-01-22 18:42 ` Peter Zijlstra
2014-01-22 18:45 ` Markus Trippelsdorf
2014-01-22 19:17 ` Josh Boyer
2014-01-22 19:09 ` Markus Trippelsdorf
2014-01-22 19:12 ` Markus Trippelsdorf
2014-01-22 20:16 ` Peter Zijlstra
2014-01-22 21:08 ` Peter Zijlstra
2014-01-22 21:17 ` Markus Trippelsdorf
2014-01-23 9:48 ` Peter Zijlstra
2014-01-23 10:01 ` Markus Trippelsdorf
2014-01-23 10:04 ` Peter Zijlstra
2014-01-23 13:32 ` Josh Boyer
2014-01-23 16:46 ` [tip:sched/urgent] sched/x86/tsc: Initialize multiplier to 0 tip-bot for Peter Zijlstra
2014-01-22 23:53 ` [PATCH 13/15] sched: Use a static_key for sched_clock_stable Josh Boyer
2014-01-23 1:53 ` Dave Young
2014-01-23 2:10 ` Dave Young
2014-01-23 16:56 ` Peter Zijlstra
2014-01-24 3:15 ` Dave Young
2014-01-24 7:58 ` Ingo Molnar
2014-01-22 17:14 ` Peter Zijlstra
2014-01-22 22:31 ` Sasha Levin
2013-12-12 14:08 ` [PATCH 14/15] sched, clock: Fixup clear_sched_clock_stable() Peter Zijlstra
2013-12-12 14:08 ` [PATCH 15/15] x86: Avoid a runtime condition in native_sched_clock() Peter Zijlstra
2013-12-13 3:30 ` [PATCH 00/15] cleanups and optimizations Mike Galbraith
2013-12-13 10:49 ` Eliezer Tamir
2013-12-13 13:56 ` Peter Zijlstra
2013-12-16 17:48 ` Eliezer Tamir
2013-12-17 13:32 ` Peter Zijlstra
2013-12-17 14:03 ` Eliezer Tamir
2013-12-17 15:13 ` Peter Zijlstra
2013-12-17 18:19 ` Eliezer Tamir
2013-12-17 22:11 ` Thomas Gleixner
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=20140617121535.GY6758@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=arjan@linux.intel.com \
--cc=bitbucket@online.de \
--cc=eliezer.tamir@linux.intel.com \
--cc=hpa@zytor.com \
--cc=jacob.jun.pan@linux.intel.com \
--cc=john.stultz@linaro.org \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=registosites@hotmail.com \
--cc=rjw@rjwysocki.net \
--cc=rui.zhang@intel.com \
--cc=srivatsa@mit.edu \
--cc=tglx@linutronix.de \
--cc=viresh.kumar@linaro.org \
/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
Powered by JetHome