Re: rcu_dyntick and suspicious RCU usage

[Fengguang Wu <wfg@linux.intel.com>]

On Thu, Jul 12, 2012 at 10:02:42AM -0700, Paul E. McKenney wrote:
> On Fri, Jul 13, 2012 at 12:57:38AM +0800, Fengguang Wu wrote:
> > On Thu, Jul 12, 2012 at 09:43:08AM -0700, Paul E. McKenney wrote:
> > > On Wed, Jul 11, 2012 at 12:49:24AM -0700, Paul E. McKenney wrote:
> > > > On Tue, Jul 10, 2012 at 12:47:00PM +0800, Fengguang Wu wrote:
> > > > > Hi Paul,
> > > > > 
> > > > > Fortunately this bug is bisectable and the first bad commit is:
> > > > > 
> > > > >         commit 9b2e4f1880b789be1f24f9684f7a54b90310b5c0
> > > > >         Author: Paul E. McKenney <paul.mckenney@linaro.org>
> > > > >         Date:   Fri Sep 30 12:10:22 2011 -0700
> > > > > 
> > > > >             rcu: Track idleness independent of idle tasks
> > > > 
> > > > OK, there is a problem in TINY_RCU's handling of dyntick-idle: it
> > > > traces while in idle.  The confusion on my part was that in TREE_RCU,
> > > > the nesting and dyntick-idle indication are different, while in
> > > > TINY_RCU they are one and the same.
> > > > 
> > > > Does the following patch help?
> > > 
> > > This one failed in my testing.  Please see the end for the fixed
> > > version, with on small but important change.
> > 
> > It worked, thanks!
> > 
> > Tested-by: Fengguang Wu <wfg@linux.intel.com>
> 
> Very good!  (And please ignore my resend of the same patch.)
> 
> I will queue this.

Will you recommend it for -stable? It impacts 3.3/3.4. I tested it on
3.4 and it works fine. However for 3.3, the patch cannot apply cleanly.

Thanks,
Fengguang