Tomi Valkeinen [off-list ref] wrote on Thu [2013-Aug-01 08:44:00 +0300]:
On 31/07/13 21:56, Etheridge, Darren wrote:
quoted
quoted
quoted
+static int da8xxfb_set_par(struct fb_info *info) {
+ struct da8xx_fb_par *par = info->par;
+ int ret;
+ bool raster = da8xx_fb_is_raster_enabled();
+
+ if (raster)
+ lcd_disable_raster(true);
+ else
+ lcd_disable_raster(false);
This looks odd. If raster is enabled, you disable it. And if raster is disabled,
you disable it.
I corrected this one in patch 0011 - I agree this code is very confusing.
In patch 11 you add the enum. I wasn't referring to that. My point was
that even if raster is already disabled,
lcd_disable_raster(dont-wait-for-framedone) is called.
Agreed and removed, the lcd_disable_raster function does the same
check as da8xx_fb_is_raster_enabled() and the immediately exits if not
enabled so this path of the conditional appears completely redundant.
Darren