On Tue, Mar 27, 2012 at 1:21 PM, Matthew Garrett <mjg59@xxxxxxxxxxxxx> wrote: > On Tue, Mar 27, 2012 at 11:11:18AM +0200, Corentin Chary wrote: >> Matthew, is this one ok ? I really hope this patch can go in 3.4 so we >> don't introduce a regression for old laptops. > > Yes, I've got this now. > > Thanks, A user just found a DSDT which is broken by this way of doing things (this is not really a regression since it was also broken before). _BCL contains a wierd "Or (VDRV, 0x02, VDRV)". So if you call _BLC once (video.ko will), it set a flag that affect the behavior of all backlight related stuff, and it breaks samsung-laptop's backlight even if samsung-laptop unload the acpi backlight. Using acpi_backlight=vendor solves that since it prevents the module from being loaded. My previous patch also fix that since it use acpi_backlight= mechanism. Do you think using acpi_backlight=vendor is a good enought solution here ? Should we use my first patch instead ? -- Corentin Chary http://xf.iksaif.net
Attachment:
acpidump.bin.gz
Description: GNU Zip compressed data
