From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Vetter Subject: Re: [PATCH 2/2] drm/i915: Document the multi-threaded FORCEWAKE bits Date: Wed, 17 Oct 2012 21:10:40 +0200 Message-ID: <20121017191040.GO5753@phenom.ffwll.local> References: <1350472195-8051-1-git-send-email-chris@chris-wilson.co.uk> <1350472195-8051-2-git-send-email-chris@chris-wilson.co.uk> <20121017092724.22093e1c@jbarnes-desktop> <20121017100515.239e7eec@jbarnes-desktop> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-wi0-f177.google.com (mail-wi0-f177.google.com [209.85.212.177]) by gabe.freedesktop.org (Postfix) with ESMTP id A22599E709 for ; Wed, 17 Oct 2012 12:09:38 -0700 (PDT) Received: by mail-wi0-f177.google.com with SMTP id hj13so828984wib.12 for ; Wed, 17 Oct 2012 12:09:38 -0700 (PDT) Content-Disposition: inline In-Reply-To: <20121017100515.239e7eec@jbarnes-desktop> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org To: Jesse Barnes Cc: intel-gfx@lists.freedesktop.org List-Id: intel-gfx@lists.freedesktop.org On Wed, Oct 17, 2012 at 10:05:15AM -0700, Jesse Barnes wrote: > On Wed, 17 Oct 2012 09:27:24 -0700 > Jesse Barnes wrote: > > > On Wed, 17 Oct 2012 12:09:55 +0100 > > Chris Wilson wrote: > > > > > No functional change, but reserves 0x2 for use by userspace. > > > > > > Signed-off-by: Chris Wilson > > > --- > > > drivers/gpu/drm/i915/i915_reg.h | 2 ++ > > > drivers/gpu/drm/i915/intel_pm.c | 10 +++++----- > > > 2 files changed, 7 insertions(+), 5 deletions(-) > > > > Each of the bits in this reg correspond to a specific agent that may > > need to wake the GT. Unfortunately I don't have docs about which bits > > are used by which agents. IIRC the BIOS uses one as does the AMT > > engine if present. > > > > I'll try to find out who owns each and maybe we can reserve our own for > > userspace. > > Ok we're in the clear here. I was afraid there might be other system > components that would do sneaky things behind our back. But once the > driver loads, we own the GT, so we can make these bits whatever we want. I guess that counts for an ack - patch merged to dinq. Thanks, Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch