LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jens Axboe <jens.axboe@oracle.com>
To: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: "paulmck@linux.vnet.ibm.com" <paulmck@linux.vnet.ibm.com>,
	"mingo@elte.hu" <mingo@elte.hu>,
	"jeremy.fitzhardinge@citrix.com" <jeremy.fitzhardinge@citrix.com>,
	"nickpiggin@yahoo.com.au" <nickpiggin@yahoo.com.au>,
	"torvalds@linux-foundation.org" <torvalds@linux-foundation.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Mallick, Asit K" <asit.k.mallick@intel.com>
Subject: Re: [patch] generic-ipi: fix the smp_mb() placement
Date: Thu, 30 Oct 2008 18:25:15 +0100	[thread overview]
Message-ID: <20081030172515.GW31673@kernel.dk> (raw)
In-Reply-To: <20081030163008.GL30573@linux-os.sc.intel.com>

On Thu, Oct 30 2008, Suresh Siddha wrote:
> On Thu, Oct 30, 2008 at 12:20:30AM -0700, Jens Axboe wrote:
> > > @@ -76,6 +72,11 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
> > >  	list_add_tail(&data->list, &dst->list);
> > >  	spin_unlock_irqrestore(&dst->lock, flags);
> > >  
> > > +	/*
> > > +	 * Make the list addition visible before sending the ipi.
> > > +	 */
> > > +	smp_mb();
> > > +
> > >  	if (ipi)
> > >  		arch_send_call_function_single_ipi(cpu);
> > 
> > We can downgrade this to a smp_wmb().
> 
> No. We want the ipi receiver to see the new consistent data rather
> than possible old consistent data.

Oh right, we need visibility here and not just store ordering.

> 
> And on x86, smp_wmb() is a simple barrier() (in !CONFIG_X86_OOSTORE)
> and which doesn't do much in this case.
> 
> on x86 mfence (smp_mb()) will ensure that msr based APIC (x2apic)
> accesses (ipi) will be visible only after the memory operations before
> smp_mb() are made visible.

OK, I'm convinced. I'll queue up the patch, thanks!

-- 
Jens Axboe


  reply	other threads:[~2008-10-30 17:26 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-10-29 22:42 Suresh Siddha
2008-10-30  7:20 ` Jens Axboe
2008-10-30 16:30   ` Suresh Siddha
2008-10-30 17:25     ` Jens Axboe [this message]
2008-10-30 18:53 ` Ingo Molnar
2008-10-30 20:23   ` Suresh Siddha
2008-10-31  5:10     ` Jeremy Fitzhardinge
2008-10-31  9:39       ` Ingo Molnar
2008-10-31 11:12         ` Jeremy Fitzhardinge
2008-10-31 16:53           ` Suresh Siddha
2008-10-31 20:30             ` Jeremy Fitzhardinge
2008-11-03 10:17               ` Ingo Molnar
2008-11-03 23:48                 ` Jeremy Fitzhardinge
2008-11-04  9:19                   ` Ingo Molnar
2008-11-04 22:25                     ` Suresh Siddha
2008-11-05  9:20                       ` Jens Axboe

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=20081030172515.GW31673@kernel.dk \
    --to=jens.axboe@oracle.com \
    --cc=asit.k.mallick@intel.com \
    --cc=jeremy.fitzhardinge@citrix.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=nickpiggin@yahoo.com.au \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=suresh.b.siddha@intel.com \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [patch] generic-ipi: fix the smp_mb() placement' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).