linux-fbdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 1/4] efifb: Enable write-combining
@ 2011-05-26 14:13 Andy Lutomirski
  2011-05-26 14:32 ` Peter Jones
  0 siblings, 1 reply; 2+ messages in thread
From: Andy Lutomirski @ 2011-05-26 14:13 UTC (permalink / raw)
  To: linux-fbdev

Running fbcon on an uncached framebuffer is remarkably slow.  So try
to enable write combining in efifb.

Without this patch, it takes 5.8 seconds from efifb probe to i915
probe (default options; no plymouth or quiet mode).  With this patch,
it only takes 1.7 seconds.  That means we wasted over 4 seconds just
writing to UC memory.

Signed-off-by: Andy Lutomirski <luto@mit.edu>
---
 drivers/video/efifb.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 4eb38db..a81c944 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -413,7 +413,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
+	info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
 	if (!info->screen_base) {
 		printk(KERN_ERR "efifb: abort, cannot ioremap video memory "
 				"0x%x @ 0x%lx\n",
-- 
1.7.5.1


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH 1/4] efifb: Enable write-combining
  2011-05-26 14:13 [PATCH 1/4] efifb: Enable write-combining Andy Lutomirski
@ 2011-05-26 14:32 ` Peter Jones
  0 siblings, 0 replies; 2+ messages in thread
From: Peter Jones @ 2011-05-26 14:32 UTC (permalink / raw)
  To: linux-fbdev

On 05/26/2011 10:13 AM, Andy Lutomirski wrote:
> Running fbcon on an uncached framebuffer is remarkably slow.  So try
> to enable write combining in efifb.
> 
> Without this patch, it takes 5.8 seconds from efifb probe to i915
> probe (default options; no plymouth or quiet mode).  With this patch,
> it only takes 1.7 seconds.  That means we wasted over 4 seconds just
> writing to UC memory.
> 
> Signed-off-by: Andy Lutomirski <luto@mit.edu>

Looks good:

Signed-off-by: Peter Jones <pjones@redhat.com>


> ---
>  drivers/video/efifb.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
> index 4eb38db..a81c944 100644
> --- a/drivers/video/efifb.c
> +++ b/drivers/video/efifb.c
> @@ -413,7 +413,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
>  	info->apertures->ranges[0].base = efifb_fix.smem_start;
>  	info->apertures->ranges[0].size = size_remap;
>  
> -	info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
> +	info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
>  	if (!info->screen_base) {
>  		printk(KERN_ERR "efifb: abort, cannot ioremap video memory "
>  				"0x%x @ 0x%lx\n",


-- 
        Peter

If you're not part of the solution, then you're part of the precipitate.

01234567890123456789012345678901234567890123456789012345678901234567890123456789

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2011-05-26 14:32 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-05-26 14:13 [PATCH 1/4] efifb: Enable write-combining Andy Lutomirski
2011-05-26 14:32 ` Peter Jones

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).