From mboxrd@z Thu Jan  1 00:00:00 1970
From: David Miller <davem@davemloft.net>
Subject: Re: [PATCH take 2] pkt_sched: Fix qdisc_watchdog() vs.
 dev_deactivate() race
Date: Thu, 11 Sep 2008 04:42:55 -0700 (PDT)
Message-ID: <20080911.044255.245121628.davem@davemloft.net>
References: <20080911104531.GA21913@gondor.apana.org.au>
	<20080911.034955.111797743.davem@davemloft.net>
	<20080911110035.GA22065@gondor.apana.org.au>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: jarkao2@gmail.com, netdev@vger.kernel.org
To: herbert@gondor.apana.org.au
Return-path: <netdev-owner@vger.kernel.org>
Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:51123
	"EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK)
	by vger.kernel.org with ESMTP id S1752149AbYIKLnB (ORCPT
	<rfc822;netdev@vger.kernel.org>); Thu, 11 Sep 2008 07:43:01 -0400
In-Reply-To: <20080911110035.GA22065@gondor.apana.org.au>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 11 Sep 2008 21:00:35 +1000

> On Thu, Sep 11, 2008 at 03:49:55AM -0700, David Miller wrote:
> > 
> > Well some kind of check has to be there.
> > 
> > I _did_ remove it during my initial implementation, and that
> > turned into a reported performance regression.
> 
> I see.  How about looking at the queue that the head-of-qdisc
> packet maps to? That should be fairly cheap to compute.

This gets us back to the whole qdisc->ops->peek() discussion :)

And we don't have the qdisc lock here, taking it is undesirable,
and if we do take it we have to transfer that lock down into
__qdisc_run() which means adjusting all the other __qdisc_run()
callers.

It's very clumsy at best.

I therefore don't think it's wise peeking into the qdisc here.

But I do realize we have to do something about this, hmmm...