[PATCH 2/2] simplefb: use write-combined remapping

David Herrmann dh.herrmann at gmail.com
Wed Oct 30 08:49:05 CET 2013


Hi Tomi

Ping?

Thanks
David

On Wed, Oct 2, 2013 at 4:58 PM, David Herrmann <dh.herrmann at gmail.com> wrote:
> Framebuffers shouldn't be cached and it is usually very uncommon to read
> them. Therefore, use ioremap_wc() to get significant speed improvements on
> systems which provide it. On all other systems it's aliased to
> ioremap_nocache() which is also fine.
>
> Reported-by: Tom Gundersen <teg at jklm.no>
> Signed-off-by: David Herrmann <dh.herrmann at gmail.com>
> Tested-by: Tom Gundersen <teg at jklm.no>
> Tested-by: Alexandre Courbot <acourbot at nvidia.com>
> Tested-by: Stephen Warren <swarren at wwwdotorg.org>
> ---
>  drivers/video/simplefb.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/video/simplefb.c b/drivers/video/simplefb.c
> index 74b016c..64db54a 100644
> --- a/drivers/video/simplefb.c
> +++ b/drivers/video/simplefb.c
> @@ -219,8 +219,8 @@ static int simplefb_probe(struct platform_device *pdev)
>
>         info->fbops = &simplefb_ops;
>         info->flags = FBINFO_DEFAULT | FBINFO_MISC_FIRMWARE;
> -       info->screen_base = ioremap(info->fix.smem_start,
> -                                   info->fix.smem_len);
> +       info->screen_base = ioremap_wc(info->fix.smem_start,
> +                                      info->fix.smem_len);
>         if (!info->screen_base) {
>                 framebuffer_release(info);
>                 return -ENODEV;
> --
> 1.8.4
>


More information about the dri-devel mailing list