From mboxrd@z Thu Jan  1 00:00:00 1970
From: Christoph Lameter <cl-vYTEC60ixJUAvxtiuMwx3w@public.gmane.org>
Subject: Re: [PATCH 6/6] Add support for __read_mostly to linux/cache.h
Date: Fri, 1 May 2009 09:52:18 -0400 (EDT)
Message-ID: <alpine.DEB.1.10.0905010948140.18324@qirst.com>
References: <1241119956-31453-1-git-send-email-tabbott@mit.edu> <1241119956-31453-2-git-send-email-tabbott@mit.edu> <1241119956-31453-3-git-send-email-tabbott@mit.edu> <1241119956-31453-4-git-send-email-tabbott@mit.edu> <1241119956-31453-5-git-send-email-tabbott@mit.edu>
 <1241119956-31453-6-git-send-email-tabbott@mit.edu> <1241119956-31453-7-git-send-email-tabbott@mit.edu> <20090501094407.GD18326@uranus.ravnborg.org>
Reply-To: microblaze-uclinux-rVRm/Wmeqae7NGdpmJTKYQ@public.gmane.org
Mime-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Cc: Tim Abbott <tabbott-DPNOqEs/LNQ@public.gmane.org>, Anders Kaseorg <andersk-DPNOqEs/LNQ@public.gmane.org>,
        Waseem Daher <wdaher-DPNOqEs/LNQ@public.gmane.org>,
        Denys Vlasenko <vda.linux-gM/Ye1E23mwN+BqQ9rBEUg@public.gmane.org>,
        Jeff Arnold <jbarnold-DPNOqEs/LNQ@public.gmane.org>,
        Benjamin Herrenschmidt <benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>,
        Bryan Wu <cooloney-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, Chris Zankel <chris-YvXeqwSYzG2sTnJN9+BGXg@public.gmane.org>,
        Cyrill Gorcunov <gorcunov-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>,
        David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
        "David S. Miller" <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>, dev-etrax-VrBV9hrLPhE@public.gmane.org,
        Geert Uytterhoeven <geert-Td1EMuHUCqxL1ZNQvxDV9g@public.gmane.org>,
        Greg Ungerer <gerg-JBU5SbJe1FlAfugRpC6u6w@public.gmane.org>,
        Haavard Skinnemoen <hskinnemoen-AIFe0yeh4nAAvxtiuMwx3w@public.gmane.org>,
        Heiko Carstens <heiko.carstens-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>,
        Helge Deller <deller-Mmb7MZpHnFY@public.gmane.org>, Hirokazu Takata <takata-TMSiXQfHlQjsTix1lMzHGQ@public.gmane.org>,
        "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>, Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
        Jeff Dike <jdike-OPE4K8JWMJJBDgjK7y7TUQ@public.gmane.org>,
        Jesper Nilsso
To: Sam Ravnborg <sam-uyr5N9Q2VtJg9hUCZPvPmw@public.gmane.org>
Return-path: <owner-microblaze-uclinux-FR6EJeJVuqfA6Z3fQjNZrN9u6TNh0Fb7@public.gmane.org>
In-Reply-To: <20090501094407.GD18326-QabhHTsIXMSnlFQ6Q1D1Y0B+6BGkLq7r@public.gmane.org>
List-ID: <linux-parisc.vger.kernel.org>

On Fri, 1 May 2009, Sam Ravnborg wrote:

> Are there any specific reason why we do not support read_mostly on all
> architectures?

Not that I know of.

> read_mostly is about grouping rarely written data together
> so what is needed is to introduce this section in the remaining
> archtectures.
>
> Christoph - git log says you did the inital implmentation.
> Do you agree?

Yes.

There is some concern that __read_mostly is needlessly applied to
numerous variables that are not used in hot code paths. This may make
__read_mostly ineffective and actually increase the cache footprint of a
function since global variables are no longer in the same cacheline. If
such a function is called and the caches are cold then two cacheline
fetches have to be done instead of one.