On Tue, Jan 29, 2013 at 02:54:35PM +0100, Jean-Christophe PLAGNIOL-VILLARD wrote:
On 13:28 Mon 10 Dec , Johan Hovold wrote:
quoted
Fix regression introduced by commit 787f9fd23283 ("atmel_lcdfb: support
16bit BGR:565 mode, remove unsupported 15bit modes") which broke 16-bpp
modes for older SOCs which use IBGR:555 (msb is intensity) rather
than BGR:565.
Use SOC-type to determine the pixel layout.
Tested on custom at91sam9263-board.
Cc: <redacted>
Signed-off-by: Johan Hovold <redacted>
---
drivers/video/atmel_lcdfb.c | 22 +++++++++++++++-------
include/video/atmel_lcdc.h | 1 +
2 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 1505539..1f68fa6 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -422,17 +422,22 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
= var->bits_per_pixel;
break;
case 16:
+ /* Older SOCs use IBGR:555 rather than BGR:565. */
+ if (sinfo->have_intensity_bit)
+ var->green.length = 5;
+ else
+ var->green.length = 6;
+
if (sinfo->lcd_wiring_mode = ATMEL_LCDC_WIRING_RGB) {
- /* RGB:565 mode */
- var->red.offset = 11;
+ /* RGB:5X5 mode */
+ var->red.offset = var->green.length + 5;
var->blue.offset = 0;
} else {
- /* BGR:565 mode */
+ /* BGR:5X5 mode */
var->red.offset = 0;
- var->blue.offset = 11;
+ var->blue.offset = var->green.length + 5;
}
var->green.offset = 5;
- var->green.length = 6;
var->red.length = var->blue.length = 5;
break;
case 32:@@ -679,8 +684,7 @@ static int atmel_lcdfb_setcolreg(unsigned int regno, unsigned int red,
case FB_VISUAL_PSEUDOCOLOR:
if (regno < 256) {
- if (cpu_is_at91sam9261() || cpu_is_at91sam9263()
- || cpu_is_at91sam9rl()) {
+ if (sinfo->have_intensity_bit) {
/* old style I+BGR:555 */
val = ((red >> 11) & 0x001f);
val |= ((green >> 6) & 0x03e0);@@ -870,6 +874,10 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
}
sinfo->info = info;
sinfo->pdev = pdev;
+ if (cpu_is_at91sam9261() || cpu_is_at91sam9263() ||
+ cpu_is_at91sam9rl()) {
+ sinfo->have_intensity_bit = true;
+ }
nack
you need to drop the cpu_is as this can only be use now for the core
use platform_device_id to indetify the IP as done on at91-i2c as we can not
detect the IP version
If this was a new feature and not a regression, fix I'd fully agree. There
are however currently four places in atmel_lcdfb where cpu_is macros are
used, and my patch only refactors one of them.
I can submit a follow up patch which add platform_device_id support, but
such a patch will be quite invasive and thus not 3.8-rc or stable material.
How about accepting this patch as it is, considering that it fixes an
obvious regression and also facilitate the move to platform_device_id by
introducing the intensity-bit flag?
Thanks,
Johan