From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.fireflyinternet.com ([87.106.93.118]:58341 "EHLO fireflyinternet.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752063AbbGUJp4 (ORCPT ); Tue, 21 Jul 2015 05:45:56 -0400 Date: Tue, 21 Jul 2015 10:45:45 +0100 From: Chris Wilson To: Daniel Vetter Cc: =?utf-8?Q?Micha=C5=82?= Winiarski , intel-gfx@lists.freedesktop.org, stable@vger.kernel.org Subject: Re: [Intel-gfx] [PATCH v3] drm/i915: Use two 32bit reads for select 64bit REG_READ ioctls Message-ID: <20150721094545.GD6166@nuc-i3427.alporthouse.com> References: <1437045549-15455-1-git-send-email-michal.winiarski@intel.com> <1437046676-31811-1-git-send-email-chris@chris-wilson.co.uk> <20150717151025.GA26539@mwiniars-desk1.igk.intel.com> <20150721064931.GM16722@phenom.ffwll.local> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20150721064931.GM16722@phenom.ffwll.local> Sender: stable-owner@vger.kernel.org List-ID: On Tue, Jul 21, 2015 at 08:49:31AM +0200, Daniel Vetter wrote: > On Fri, Jul 17, 2015 at 05:10:25PM +0200, Michał Winiarski wrote: > > On Thu, Jul 16, 2015 at 12:37:56PM +0100, Chris Wilson wrote: > > > Since the hardware sometimes mysteriously totally flummoxes the 64bit > > > read of a 64bit register when read using a single instruction, split the > > > read into two instructions. Since the read here is of automatically > > > incrementing timestamp counters, we also have to be very careful in > > > order to make sure that it does not increment between the two > > > instructions. > > > > > > However, since userspace tried to workaround this issue and so enshrined > > > this ABI for a broken hardware read and in the process neglected that > > > the read only fails in some environments, we have to introduce a new > > > uABI flag for userspace to request the 2x32 bit accurate read of the > > > timestamp. > > > > > > v2: Fix alignment check and include details of the workaround for > > > userspace. > > > > > > Reported-by: Karol Herbst > > > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91317 > > > Testcase: igt/gem_reg_read > > Tested-by: Michał Winiarski > > Where are the mesa/beignet/libva patches for this? Trivial. Absolutely trivial. Just waiting for the kernel. -Chris -- Chris Wilson, Intel Open Source Technology Centre