From mboxrd@z Thu Jan  1 00:00:00 1970
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [patch 5/6] ps3: BD/DVD/CD-ROM Storage Driver
Date: Tue, 17 Jul 2007 08:12:39 +1000
Message-ID: <1184623959.25235.100.camel@localhost.localdomain>
References: <20070704132212.726923000@pademelon.sonytel.be>
	 <Pine.LNX.4.62.0707131541150.18802@pademelon.sonytel.be>
	 <1184335333.3402.20.camel@localhost.localdomain>
	 <200707131619.54898.arnd@arndb.de>
	 <Pine.LNX.4.62.0707131707290.18802@pademelon.sonytel.be>
	 <1184340528.3402.32.camel@localhost.localdomain>
	 <Pine.LNX.4.62.0707132212520.23000@chinchilla.sonytel.be>
	 <Pine.LNX.4.62.0707161338230.1072@pademelon.sonytel.be>
	 <20070716121649.GI5195@kernel.dk>
	 <1184593643.3447.9.camel@localhost.localdomain>
	 <1184622555.25235.91.camel@localhost.localdomain>
	 <1184623415.3447.48.camel@localhost.localdomain>
Mime-Version: 1.0
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
Return-path: <linux-scsi-owner@vger.kernel.org>
Received: from gate.crashing.org ([63.228.1.57]:42958 "EHLO gate.crashing.org"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752568AbXGPWOo (ORCPT <rfc822;linux-scsi@vger.kernel.org>);
	Mon, 16 Jul 2007 18:14:44 -0400
In-Reply-To: <1184623415.3447.48.camel@localhost.localdomain>
Sender: linux-scsi-owner@vger.kernel.org
List-Id: linux-scsi@vger.kernel.org
To: James Bottomley <James.Bottomley@SteelEye.com>
Cc: Jens Axboe <jens.axboe@oracle.com>, Arnd Bergmann <arnd@arndb.de>, linux-scsi@vger.kernel.org, Linux Kernel Development <linux-kernel@vger.kernel.org>, Alessandro Rubini <rubini@vision.unipv.it>, Linux/PPC Development <linuxppc-dev@ozlabs.org>, Paul Mackerras <paulus@samba.org>, Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>

On Mon, 2007-07-16 at 17:03 -0500, James Bottomley wrote:
> On Tue, 2007-07-17 at 07:49 +1000, Benjamin Herrenschmidt wrote:
> > > No ... that was the point of flush_kernel_dcache_page().  The page in
> > > question is page cache backed and contains user mappings.  However, the
> > > block layer has already done a flush_dcache_page() in get_user_pages()
> > > and the user shouldn't be touching memory under I/O (unless they want
> > > self induced aliasing problems) so we're free to assume all the user
> > > cachelines are purged, hence all we have to do is flush the kernel alias
> > > to bring the page up to date and make the users see it correctly.
> > 
> > The block layer will have done that even in the swap-out path ? (Just
> > asking... I'm not very familiar with the block layer)
> 
> Er ... not really, this is the I/O path for user initiated I/O.  The
> page out path, by definition, can't have any extant user mappings.  For
> page out, the relevant page is flushed before its mapping is detached,
> and then it can be paged to the backing store (or for anonymous pages to
> the swap device) when no mappings remain.

Ok, thanks.

Ben.