mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: David Vrabel <david.vrabel@citrix.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>, "H. Peter Anvin" <hpa@zytor.com>,
	LKML <linux-kernel@vger.kernel.org>, <konrad.wilk@oracle.com>,
	<john.stultz@linaro.org>, <xen-devel@lists.xen.org>,
	Artem Savkov <artem.savkov@gmail.com>
Subject: Re: [tip:timers/core] hrtimers: Support resuming with two or more CPUs online (but stopped)
Date: Fri, 5 Jul 2013 14:46:01 +0100	[thread overview]
Message-ID: <51D6CE19.1050503@citrix.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1307051225060.11637@ionos.tec.linutronix.de>

On 05/07/13 11:25, Thomas Gleixner wrote:
> On Fri, 5 Jul 2013, David Vrabel wrote:
> 
> You failed to CC Artem :(
> 
>> On 05/07/13 10:30, Artem Savkov wrote:
>>> This commit brings up a warning about a potential deadlock in
>>> smp_call_function_many() discussed previously:
>>> https://lkml.org/lkml/2013/4/18/546
>>
>> Can we just avoid the wait in clock_was_set()?  Something like this?
>>
>> 8<------------------------------------------------------
>> hrtimers: do not wait for other CPUs in clock_was_set()
>>
>> Calling on_each_cpu() and waiting in a softirq causes a WARNing about
>> a potential deadlock.
>>
>> Because hrtimers are per-CPU, it is sufficient to ensure that all
>> other CPUs' timers are reprogrammed as soon as possible and before the
>> next softirq on that CPU.  There is no need to wait for this to be
>> complete on all CPUs.

Unfortunately this doesn't look sufficient.  on_each_cpu(..., 0) may
still wait for other calls to complete before queuing the calls due to
the use of a single set of per-CPU csd data.

David

  parent reply	other threads:[~2013-07-05 13:46 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-27 10:35 [PATCHv6 0/5] xen: maintain an accurate persistent clock in more cases David Vrabel
2013-06-27 10:35 ` [PATCH 1/5] hrtimers: support resuming with two or more CPUs online (but stopped) David Vrabel
2013-06-28 21:18   ` [tip:timers/core] hrtimers: Support " tip-bot for David Vrabel
2013-07-05  9:30     ` Artem Savkov
2013-07-05 10:07       ` David Vrabel
2013-07-05 10:10         ` Thomas Gleixner
2013-07-05 10:25         ` Thomas Gleixner
2013-07-05 10:36           ` Thomas Gleixner
2013-07-05 10:45             ` Artem Savkov
2013-07-05 13:26               ` Thomas Gleixner
2013-07-05 10:38           ` Artem Savkov
2013-07-05 13:46           ` David Vrabel [this message]
2013-07-05 13:51             ` Thomas Gleixner
2013-07-05 10:09       ` Thomas Gleixner
2013-06-28 21:18   ` [tip:timers/core] xen: Remove clock_was_set() call in the resume path tip-bot for David Vrabel
2013-06-27 10:35 ` [PATCH 2/5] time: pass flags instead of multiple bools to timekeeping_update() David Vrabel
2013-06-27 17:39   ` John Stultz
2013-06-28 21:18   ` [tip:timers/core] timekeeping: Pass " tip-bot for David Vrabel
2013-06-27 10:35 ` [PATCH 3/5] time: indicate that the clock was set in the pvclock gtod notifier chain David Vrabel
2013-06-27 17:37   ` John Stultz
2013-06-28 10:20     ` David Vrabel
2013-06-28 21:19   ` [tip:timers/core] timekeeping: Indicate that clock was set in the pvclock gtod notifier tip-bot for David Vrabel
2013-06-27 10:35 ` [PATCH 4/5] x86/xen: sync the wallclock when the system time is set David Vrabel
2013-06-28 21:19   ` [tip:timers/core] x86: xen: Sync " tip-bot for David Vrabel
2013-06-27 10:35 ` [PATCH 5/5] x86/xen: sync the CMOS RTC as well as the Xen wallclock David Vrabel
2013-06-28 15:38   ` Thomas Gleixner
2013-06-28 15:49     ` David Vrabel
2013-06-28 16:09       ` Thomas Gleixner
2013-06-28 16:51         ` David Vrabel
2013-06-28 20:41           ` Thomas Gleixner
2013-06-28 21:19   ` [tip:timers/core] x86: xen: Sync " tip-bot for David Vrabel
2013-06-28 13:14 ` [PATCHv6 0/5] xen: maintain an accurate persistent clock in more cases Thomas Gleixner
2013-06-28 15:01   ` Konrad Rzeszutek Wilk
2013-06-28 15:12     ` Thomas Gleixner
2013-06-28 16:19       ` Konrad Rzeszutek Wilk
2013-06-28 18:58         ` 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=51D6CE19.1050503@citrix.com \
    --to=david.vrabel@citrix.com \
    --cc=artem.savkov@gmail.com \
    --cc=hpa@zytor.com \
    --cc=john.stultz@linaro.org \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=xen-devel@lists.xen.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