[PATCH] bounce: call flush_dcache_page after bounce_copy_vec

[Stefan Bader]

On 09/13/2010 07:49 AM, Bryan Wu wrote:
> From: Gary King <gking at nvidia.com>
> 
> the bounced page needs to be flushed after data is copied into it,
> to ensure that architecture implementations can synchronize
> instruction and data caches if necessary.
> 
> This patch was posted at armlinux mail list and was asked by Andrew
> Morton and Jens Axboe. We tried this patch and found is fixed memtester
> issue.
> (http://lists.infradead.org/pipermail/linux-arm-kernel/2010-September/025373.html)
> 
Maybe I could guess where this patch ought to go (given that Leann is on the cc)
but is this ti-omap and by that should go to Lucid to be pulled into Maverick?

-Stefan
> BugLink: http://bugs.launchpad.net/bugs/633227
> 
> Signed-off-by: Gary King <gking at nvidia.com>
> Tested-by: Ricardo Salveti de Araujo <ricardo.salveti at canonical.com>
> Tested-by: Sebastien Jan <s-jan at ti.com>
> Signed-off-by: Bryan Wu <bryan.wu at canonical.com>
> ---
>  mm/bounce.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/mm/bounce.c b/mm/bounce.c
> index 13b6dad..1481de6 100644
> --- a/mm/bounce.c
> +++ b/mm/bounce.c
> @@ -116,8 +116,8 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
>  		 */
>  		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
>  
> -		flush_dcache_page(tovec->bv_page);
>  		bounce_copy_vec(tovec, vfrom);
> +		flush_dcache_page(tovec->bv_page);
>  	}
>  }
>