From: Gautham R Shenoy <ego@in.ibm.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Gautham R Shenoy <ego@in.ibm.com>,
akpm@osdl.org, linux-kernel@vger.kernel.org, torvalds@osdl.org,
davej@redhat.com, dipankar@in.ibm.com, vatsa@in.ibm.com
Subject: Re: CPUFREQ-CPUHOTPLUG: Possible circular locking dependency
Date: Thu, 30 Nov 2006 17:13:46 +0530 [thread overview]
Message-ID: <20061130114346.GC23354@in.ibm.com> (raw)
In-Reply-To: <20061130110315.GA30460@elte.hu>
On Thu, Nov 30, 2006 at 12:03:15PM +0100, Ingo Molnar wrote:
>
> * Gautham R Shenoy <ego@in.ibm.com> wrote:
>
> > a) cpufreq maintain's it's own cpumask in the variable
> > policy->affected_cpus and says : If a frequency change is issued to
> > any one of the cpu's in the affected_cpus mask, you change frequency
> > on all cpus in the mask. So this needs to be consistent with
> > cpu_online map and hence cpu hotplug aware. Furthermore, we don't want
> > cpus in this mask to go down when we are trying to change frequencies
> > on them. The function which drives the frequency change in
> > cpufreq-core is cpufreq_driver_target and it needs cpu-hotplug
> > protection.
>
> couldnt this complexity be radically simplified by having new kernel
> infrastructure that does something like:
>
> " 'gather' all CPUs mentioned in <mask> via scheduling a separate
> helper-kthread on every CPU that <mask> specifies, disable all
> interrupts, and execute function <fn> once all CPUs have been
> 'gathered' - and release all CPUs once <fn> has executed on each of
> them."
>
> ?
This is what is currently being done by cpufreq:
a) get_some_cpu_hotplug_protection() [use either some global mechanism
or a persubsystem mutex]
b) actual_freq_change_driver_function(mask)
/* You can check out cpufreq_p4_target() in
* arch/i386/kernel/cpu/cpufreq/p4-clockmod.c
*/
{
for_each_cpu_mask(i, mask) {
cpumask_t this_cpu = cpumask_of_cpu(i);
set_cpus_allowed(current, this_cpu);
function_to_change_frequency();
}
}
c) release_whatever_cpu_hotplug_protection()
>
> This would be done totally serialized and while holding the hotplug
> lock, so no CPU could go away or arrive while this operation is going
> on.
>
Isn't the above same as what you are suggesting? Or have I missed out
anything?
> Ingo
regards
gautham.
--
Gautham R Shenoy
Linux Technology Center
IBM India.
"Freedom comes with a price tag of responsibility, which is still a bargain,
because Freedom is priceless!"
next prev parent reply other threads:[~2006-11-30 11:43 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-11-29 15:24 CPUFREQ-CPUHOTPLUG: Possible circular locking dependency Gautham R Shenoy
2006-11-29 21:05 ` Andrew Morton
2006-11-30 4:28 ` Gautham R Shenoy
2006-11-30 6:35 ` Gautham R Shenoy
2006-11-30 8:29 ` Ingo Molnar
2006-11-30 8:52 ` Gautham R Shenoy
2006-12-01 1:43 ` Gautham R Shenoy
2006-12-01 8:55 ` Ingo Molnar
2006-11-30 8:31 ` Ingo Molnar
2006-11-30 10:24 ` Gautham R Shenoy
2006-11-30 11:03 ` Ingo Molnar
2006-11-30 11:19 ` Andrew Morton
2006-11-30 11:46 ` Ingo Molnar
2006-11-30 12:44 ` Gautham R Shenoy
2006-11-30 14:35 ` Ingo Molnar
2006-11-30 19:40 ` Andrew Morton
2006-11-30 20:24 ` Ingo Molnar
2006-11-30 11:43 ` Gautham R Shenoy [this message]
2006-11-30 11:53 ` Ingo Molnar
2006-11-30 12:19 ` Gautham R Shenoy
-- strict thread matches above, loose matches on Subject: below --
2006-12-06 18:27 Pallipadi, Venkatesh
2006-12-07 7:06 ` Gautham R Shenoy
2006-12-07 12:50 Pallipadi, Venkatesh
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=20061130114346.GC23354@in.ibm.com \
--to=ego@in.ibm.com \
--cc=akpm@osdl.org \
--cc=davej@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=torvalds@osdl.org \
--cc=vatsa@in.ibm.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 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.