From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andi Kleen <ak@suse.de>
Date: Tue, 06 Feb 2007 08:00:20 +0000
Subject: Re: [patch 03/13] ia64: swiotlb bug fixes
Message-Id: <200702060900.20219.ak@suse.de>
List-Id: <linux-ia64.vger.kernel.org>
References: <200702060021.l160L48p004187@shell0.pdx.osdl.net>
In-Reply-To: <200702060021.l160L48p004187@shell0.pdx.osdl.net>
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
To: linux-ia64@vger.kernel.org

On Tuesday 06 February 2007 04:33, Luck, Tony wrote:
> On Mon, Feb 05, 2007 at 04:20:00PM -0800, akpm@linux-foundation.org wrote:
> > From: "Jan Beulich" <jbeulich@novell.com>
> > 
> > This patch fixes
> > - marking I-cache clean of pages DMAed to now only done for IA64
> > - broken multiple inclusion in include/asm-x86_64/swiotlb.h
> > - missing call to mark_clean in swiotlb_sync_sg()
> > - a (perhaps only theoretical) issue in swiotlb_dma_supported() when
> >   io_tlb_end is exactly at the end of memory
> > 
> > Signed-off-by: Jan Beulich <jbeulich@novell.com>
> > Cc: "Luck, Tony" <tony.luck@intel.com>
> > Cc: Andi Kleen <ak@suse.de>
> > Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
> 
> Andi,
> 
> Are you OK with these changes (and the ones in parts 4, 5, 6 that
> also touch swiotlb)?  They build cleanly on x86_64, but I haven't
> tested them there.

If they build they are ok for me. x86-64 ignores the struct page
bits anyways because everything is coherent, i just never bothered
to ifdef that because they're harmless.

(I suppose an alternative would be to move dma_mark_clean into arch/ia64
and provide a weak dummy default in swiotlb.c) 

-Andi