Date: Fri, 20 Feb 2015 19:26:21 -0800
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Manfred Spraul <manfred@colorfullife.com>
Cc: Oleg Nesterov <oleg@redhat.com>, Peter Zijlstra <peterz@infradead.org>,
        Kirill Tkhai <ktkhai@parallels.com>, linux-kernel@vger.kernel.org,
        Ingo Molnar <mingo@redhat.com>, Josh Poimboeuf <jpoimboe@redhat.com>
Subject: Re: [PATCH 2/2] [PATCH] sched: Add smp_rmb() in task rq locking
 cycles
Message-ID: <20150221032621.GQ5745@linux.vnet.ibm.com>
Reply-To: paulmck@linux.vnet.ibm.com
References: <20150217121258.GM5029@twins.programming.kicks-ass.net>
 <20150217130523.GV24151@twins.programming.kicks-ass.net>
 <20150217160532.GW4166@linux.vnet.ibm.com>
 <20150217183636.GR5029@twins.programming.kicks-ass.net>
 <20150217215231.GK4166@linux.vnet.ibm.com>
 <20150218155904.GA27687@redhat.com>
 <54E4E479.4050003@colorfullife.com>
 <20150218224317.GC5029@twins.programming.kicks-ass.net>
 <20150219141905.GA11018@redhat.com>
 <54E77CC0.5030401@colorfullife.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <54E77CC0.5030401@colorfullife.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1641
Lines: 59

On Fri, Feb 20, 2015 at 07:28:16PM +0100, Manfred Spraul wrote:
> Hi Oleg,
> 
> my example was bad, let's continue with your example.
> 
> And: If sem_lock() needs another smp_xmb(), then we must add it:
> Some apps do not have a user space hot path, i.e. it seems that on
> some setups, we have millions of calls per second.
> If there is a race, then it will happen.
> 
> I've tried to merge your example:
> >
> > int X = 0, Y = 0;
> >
> > void func(void)
> > {
> >     bool ll = rand();
> >
> >     if (ll) {
> >         spin_lock(&local);
> >         if (!spin_is_locked(&global))
> >             goto done;
> >         spin_unlock(&local);
> >     }
> >     ll = false;
> >     spin_lock(&global);
> >     spin_unlock_wait(&local);
> > done:
> >     smp_rmb(); <<<<<<<<<<<<<<<
> >     BUG_ON(X != Y);
> >
> >     ++X; ++Y;
> >
> >     if (ll)
> >         spin_unlock(&local);
> >     else
> >         spin_unlock(&global);
> > }
> I agree, we need the smp_rmb().
> I'll write a patch.
> 
> >We need the full barrier to serialize STORE's as well, but probably we can
> >rely on control dependancy and thus we only need rmb().
> Do we need a full barrier or not?
> 
> I don't manage to create a proper line of reasoning.

This has to be one of the more bizarre forms of Dekker's algorithm
that I have seen.  ;-)

I am going to have to put this through one of the tools...

							Thanx, Paul

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/