From mboxrd@z Thu Jan  1 00:00:00 1970
From: fweisbec@gmail.com (Frederic Weisbecker)
Date: Fri, 22 Feb 2013 15:15:28 +0100
Subject: [PATCH 0/2] cpustat: use atomic operations to read/update stats
In-Reply-To: <1361541939.26780.63.camel@laptop>
References: <1361512604-2720-1-git-send-email-khilman@linaro.org>
 <1361522767.26780.44.camel@laptop>
 <20130222125019.GC17948@somewhere.redhat.com>
 <1361541939.26780.63.camel@laptop>
Message-ID: <20130222141526.GB18149@somewhere.redhat.com>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

On Fri, Feb 22, 2013 at 03:05:39PM +0100, Peter Zijlstra wrote:
> On Fri, 2013-02-22 at 13:50 +0100, Frederic Weisbecker wrote:
> > > Which is a problem how?
> > 
> > So here is a possible scenario, CPU 0 reads a kcpustat value, and CPU
> > 1 writes
> > it at the same time:
> > 
> >     //Initial value of "cpustat" is 0xffffffff
> >          == CPU 0 ==           == CPU 1 ==
> > 
> >        //load low part
> >        mov %eax, [cpustat]
> >                              inc [cpustat]
> >                              //Update the high part if necessary
> >                              jnc 1f
> >                              inc [cpustat + 4]
> >                              1:
> >        //load high part
> >        mov %edx, [cpustat + 4]
> > 
> > 
> > Afterward, CPU 0 will think the value is 0x1ffffffff while it's
> > actually
> > 0x100000000.
> > 
> > atomic64_read() and atomic64_set() are supposed to take care of that,
> > without
> > even the need for _inc() or _add() parts that use LOCK.
> 
> 
> Sure I get that, but again, why is that a problem,.. who relies on
> these statistics that makes it a problem?

I guess we want to provide at least some minimal reliability in /proc/stat
I mean we don't mind if the read is slightly off, reading stats from userspace
is inherently racy anyway, but if it suddenly shows a wrong increase of 4 billions
which disappear soon after, it looks like a bug to me.