From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757354Ab2DFOfB (ORCPT ); Fri, 6 Apr 2012 10:35:01 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:32863 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757172Ab2DFOe7 (ORCPT ); Fri, 6 Apr 2012 10:34:59 -0400 Date: Fri, 6 Apr 2012 09:34:55 -0500 From: Seth Forshee To: Matthew Garrett , Corentin Chary Cc: platform-driver-x86@vger.kernel.org, linux-kernel@vger.kernel.org, linux acpi , Len Brown Subject: Re: [PATCH] samsung-laptop: unregister ACPI video module for some well known laptops Message-ID: <20120406143455.GC8666@thinkpad-t410> Mail-Followup-To: Matthew Garrett , Corentin Chary , platform-driver-x86@vger.kernel.org, linux-kernel@vger.kernel.org, linux acpi , Len Brown References: <20120320163002.GB6811@srcf.ucam.org> <1332421699-5315-1-git-send-email-corentincj@iksaif.net> <20120327112105.GA2845@srcf.ucam.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Apr 06, 2012 at 11:42:18AM +0200, Corentin Chary wrote: > On Tue, Mar 27, 2012 at 1:21 PM, Matthew Garrett 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 ? I've recently noticed another problem with using acpi_video_unregister() to disable known broken backlights -- another module might call acpi_video_register() and make it reappear. i915 does this, so when I EFI boot the MacBook Pro 8,2 the acpi backlights reappear (under a BIOS compatible boot the Intel GPU doesn't show up on the bus). So Corentin's solution does seem like a better way to go, or else something similar that forces the ACPI video driver to behave as with acpi_video=vendor. Seth