From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Wilson Subject: Re: [PATCH 4/4] drm/i915: enable forcewake voodoo also for gen6 Date: Wed, 08 Feb 2012 10:00:54 +0000 Message-ID: References: <1327496640-6735-1-git-send-email-daniel.vetter@ffwll.ch> <1327496640-6735-4-git-send-email-daniel.vetter@ffwll.ch> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mga03.intel.com (mga03.intel.com [143.182.124.21]) by gabe.freedesktop.org (Postfix) with ESMTP id 190039F639 for ; Wed, 8 Feb 2012 02:01:00 -0800 (PST) In-Reply-To: <1327496640-6735-4-git-send-email-daniel.vetter@ffwll.ch> 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: Intel Graphics Development Cc: Daniel Vetter List-Id: intel-gfx@lists.freedesktop.org On Wed, 25 Jan 2012 14:04:00 +0100, Daniel Vetter wrote: > We still have reports of missed irqs even on Sandybridge with the > HWSTAM workaround in place. Testing by the bug reporter gets rid of > them with the forcewake voodoo and no HWSTAM writes. > > Because I've slightly botched the rebasing I've left out the ACTHD > readback which is also required to get IVB working. Seems to still > work on the tester's machine, so I think we should go with the more > minmal approach on SNB. Especially since I've only found weak evidence > for holding forcewake while waiting for an interrupt to arrive, but > none for the ACTHD readback. > > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45181 > Tested-by: Nicolas Kalkhof nkalkhof()at()web.de > Signed-Off-by: Daniel Vetter Whilst this patch doesn't directly enable the ACTHD w/a, I have observed that with a very light load (drawing a single large transformed texture) reading back the ACTHD (along with the GT forcewake dance) becomes the predominant consumer of CPU time for the system. (The rate-limiting step is still the GPU, it just irked me to see the kernel consume more CPU time than X.) This workaround appears more successful than the last, and doesn't appear to break anything else, so Acked-by: Chris Wilson -Chris -- Chris Wilson, Intel Open Source Technology Centre