From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>,
KOSAKI Motohiro <kosaki.motohiro@gmail.com>,
Gilad Ben-Yossef <gilad@benyossef.com>,
linux-kernel@vger.kernel.org, Chris Metcalf <cmetcalf@tilera.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Frederic Weisbecker <fweisbec@gmail.com>,
linux-mm@kvack.org, Pekka Enberg <penberg@kernel.org>,
Matt Mackall <mpm@selenic.com>,
Sasha Levin <levinsasha928@gmail.com>,
Rik van Riel <riel@redhat.com>, Andi Kleen <andi@firstfloor.org>,
Andrew Morton <akpm@linux-foundation.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH v5 7/8] mm: Only IPI CPUs to drain local pages if they exist
Date: Sat, 7 Jan 2012 08:52:01 -0800 [thread overview]
Message-ID: <20120107165201.GA23939@linux.vnet.ibm.com> (raw)
In-Reply-To: <20120105161739.GD27881@csn.ul.ie>
On Thu, Jan 05, 2012 at 04:17:39PM +0000, Mel Gorman wrote:
> On Thu, Jan 05, 2012 at 02:40:11PM +0000, Russell King - ARM Linux wrote:
> > On Thu, Jan 05, 2012 at 02:20:17PM +0000, Mel Gorman wrote:
[ . . . ]
> > I've been chasing that patch and getting no replies what so
> > ever from folk like Peter, Thomas and Ingo.
> >
> > The problem affects all IPI-raising functions, which mask with
> > cpu_online_mask directly.
>
> Actually, in one sense I'm glad to hear it because from my brief
> poking around, I was having trouble understanding why we were always
> safe from sending IPIs to CPUs in the process of being offlined.
The trick is to disable preemption (not interrupts!) across the IPI, which
prevents CPU-hotplug's stop_machine() from running. You also have to
have checked that the CPU is online within this same preemption-disabled
section of code. This means that the outgoing CPU has to accept IPIs
even after its CPU_DOWN_PREPARE notifier has been called -- right up
to the stop_machine() call to take_cpu_down().
Thanx, Paul
WARNING: multiple messages have this Message-ID (diff)
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>,
KOSAKI Motohiro <kosaki.motohiro@gmail.com>,
Gilad Ben-Yossef <gilad@benyossef.com>,
linux-kernel@vger.kernel.org, Chris Metcalf <cmetcalf@tilera.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Frederic Weisbecker <fweisbec@gmail.com>,
linux-mm@kvack.org, Pekka Enberg <penberg@kernel.org>,
Matt Mackall <mpm@selenic.com>,
Sasha Levin <levinsasha928@gmail.com>,
Rik van Riel <riel@redhat.com>, Andi Kleen <andi@firstfloor.org>,
Andrew Morton <akpm@linux-foundation.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH v5 7/8] mm: Only IPI CPUs to drain local pages if they exist
Date: Sat, 7 Jan 2012 08:52:01 -0800 [thread overview]
Message-ID: <20120107165201.GA23939@linux.vnet.ibm.com> (raw)
In-Reply-To: <20120105161739.GD27881@csn.ul.ie>
On Thu, Jan 05, 2012 at 04:17:39PM +0000, Mel Gorman wrote:
> On Thu, Jan 05, 2012 at 02:40:11PM +0000, Russell King - ARM Linux wrote:
> > On Thu, Jan 05, 2012 at 02:20:17PM +0000, Mel Gorman wrote:
[ . . . ]
> > I've been chasing that patch and getting no replies what so
> > ever from folk like Peter, Thomas and Ingo.
> >
> > The problem affects all IPI-raising functions, which mask with
> > cpu_online_mask directly.
>
> Actually, in one sense I'm glad to hear it because from my brief
> poking around, I was having trouble understanding why we were always
> safe from sending IPIs to CPUs in the process of being offlined.
The trick is to disable preemption (not interrupts!) across the IPI, which
prevents CPU-hotplug's stop_machine() from running. You also have to
have checked that the CPU is online within this same preemption-disabled
section of code. This means that the outgoing CPU has to accept IPIs
even after its CPU_DOWN_PREPARE notifier has been called -- right up
to the stop_machine() call to take_cpu_down().
Thanx, Paul
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-01-07 16:52 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-02 10:24 [PATCH v5 0/8] Reduce cross CPU IPI interference Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 1/8] smp: Introduce a generic on_each_cpu_mask function Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-03 7:51 ` Michal Nazarewicz
2012-01-03 7:51 ` Michal Nazarewicz
2012-01-03 7:51 ` Michal Nazarewicz
2012-01-03 8:12 ` Gilad Ben-Yossef
2012-01-03 8:12 ` Gilad Ben-Yossef
2012-01-03 8:57 ` Michal Nazarewicz
2012-01-03 8:57 ` Michal Nazarewicz
2012-01-03 8:57 ` Michal Nazarewicz
2012-01-03 22:26 ` Andrew Morton
2012-01-03 22:26 ` Andrew Morton
2012-01-05 13:17 ` Michal Nazarewicz
2012-01-05 13:17 ` Michal Nazarewicz
2012-01-08 16:04 ` Gilad Ben-Yossef
2012-01-08 16:04 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 2/8] arm: Move arm over to generic on_each_cpu_mask Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 3/8] tile: Move tile to use " Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 4/8] smp: Add func to IPI cpus based on parameter func Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-03 22:34 ` Andrew Morton
2012-01-03 22:34 ` Andrew Morton
2012-01-08 16:09 ` Gilad Ben-Yossef
2012-01-08 16:09 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 5/8] slub: Only IPI CPUs that have per cpu obj to flush Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 6/8] fs: only send IPI to invalidate LRU BH when needed Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 7/8] mm: Only IPI CPUs to drain local pages if they exist Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-03 17:45 ` KOSAKI Motohiro
2012-01-03 17:45 ` KOSAKI Motohiro
2012-01-03 18:58 ` Gilad Ben-Yossef
2012-01-03 18:58 ` Gilad Ben-Yossef
2012-01-03 22:02 ` KOSAKI Motohiro
2012-01-03 22:02 ` KOSAKI Motohiro
2012-01-05 14:20 ` Mel Gorman
2012-01-05 14:20 ` Mel Gorman
2012-01-05 14:40 ` Russell King - ARM Linux
2012-01-05 14:40 ` Russell King - ARM Linux
2012-01-05 15:24 ` Peter Zijlstra
2012-01-05 15:24 ` Peter Zijlstra
2012-01-05 16:17 ` Mel Gorman
2012-01-05 16:17 ` Mel Gorman
2012-01-05 16:35 ` Russell King - ARM Linux
2012-01-05 16:35 ` Russell King - ARM Linux
2012-01-05 18:35 ` Paul E. McKenney
2012-01-05 18:35 ` Paul E. McKenney
2012-01-05 22:21 ` Mel Gorman
2012-01-05 22:21 ` Mel Gorman
2012-01-06 6:06 ` Srivatsa S. Bhat
2012-01-06 6:06 ` Srivatsa S. Bhat
2012-01-06 10:46 ` Mel Gorman
2012-01-06 10:46 ` Mel Gorman
2012-01-06 13:28 ` Greg KH
2012-01-06 13:28 ` Greg KH
2012-01-06 14:09 ` Mel Gorman
2012-01-06 14:09 ` Mel Gorman
2012-01-05 22:06 ` Andrew Morton
2012-01-05 22:06 ` Andrew Morton
2012-01-05 22:31 ` Mel Gorman
2012-01-05 22:31 ` Mel Gorman
2012-01-05 23:19 ` Andrew Morton
2012-01-05 23:19 ` Andrew Morton
2012-01-09 17:25 ` Mel Gorman
2012-01-09 17:25 ` Mel Gorman
2012-01-07 16:52 ` Paul E. McKenney [this message]
2012-01-07 16:52 ` Paul E. McKenney
2012-01-07 17:05 ` Paul E. McKenney
2012-01-07 17:05 ` Paul E. McKenney
2012-01-05 15:54 ` Mel Gorman
2012-01-05 15:54 ` Mel Gorman
2012-01-08 16:01 ` Gilad Ben-Yossef
2012-01-08 16:01 ` Gilad Ben-Yossef
2012-01-02 10:24 ` [PATCH v5 8/8] mm: add vmstat counters for tracking PCP drains Gilad Ben-Yossef
2012-01-02 10:24 ` Gilad Ben-Yossef
2012-01-03 17:47 ` KOSAKI Motohiro
2012-01-03 17:47 ` KOSAKI Motohiro
2012-01-03 19:00 ` Gilad Ben-Yossef
2012-01-03 19:00 ` Gilad Ben-Yossef
2012-01-03 22:13 ` KOSAKI Motohiro
2012-01-03 22:13 ` KOSAKI Motohiro
2012-01-03 22:37 ` Andrew Morton
2012-01-03 22:37 ` Andrew Morton
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=20120107165201.GA23939@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=avi@redhat.com \
--cc=cmetcalf@tilera.com \
--cc=fweisbec@gmail.com \
--cc=gilad@benyossef.com \
--cc=kosaki.motohiro@gmail.com \
--cc=levinsasha928@gmail.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux@arm.linux.org.uk \
--cc=mel@csn.ul.ie \
--cc=mpm@selenic.com \
--cc=penberg@kernel.org \
--cc=riel@redhat.com \
--cc=viro@zeniv.linux.org.uk \
/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.