From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Vetter Subject: Re: [PATCH 1/3] drm/i915: Flush the context object from the CPU caches upon switching Date: Sun, 15 Jul 2012 17:16:34 +0200 Message-ID: <20120715151634.GD5184@phenom.ffwll.local> References: <1342352064-6749-1-git-send-email-chris@chris-wilson.co.uk> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-wi0-f171.google.com (mail-wi0-f171.google.com [209.85.212.171]) by gabe.freedesktop.org (Postfix) with ESMTP id 260039E752 for ; Sun, 15 Jul 2012 08:16:31 -0700 (PDT) Received: by wibhq4 with SMTP id hq4so1537152wib.12 for ; Sun, 15 Jul 2012 08:16:31 -0700 (PDT) Content-Disposition: inline In-Reply-To: <1342352064-6749-1-git-send-email-chris@chris-wilson.co.uk> 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: Chris Wilson Cc: intel-gfx@lists.freedesktop.org List-Id: intel-gfx@lists.freedesktop.org On Sun, Jul 15, 2012 at 12:34:22PM +0100, Chris Wilson wrote: > The issue is that we stale data in the CPU caches, when we come to > swap-out the object, the CPU may short-circuit the reads from those > cacheline and so corrupt the context object. > > Secondary, leaving the context object as being marked in the CPU write > domain whilst on the GPU active list is a bad idea and will throw > warnings later. > > Signed-off-by: Chris Wilson > Reviewed-by: Ben Widawsky > --- > drivers/gpu/drm/i915/i915_gem_context.c | 7 +++++++ > 1 file changed, 7 insertions(+) > > diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c > index 9ae3f2c..fd978bb 100644 > --- a/drivers/gpu/drm/i915/i915_gem_context.c > +++ b/drivers/gpu/drm/i915/i915_gem_context.c > @@ -374,6 +374,13 @@ static int do_switch(struct drm_i915_gem_object *from_obj, > if (ret) > return ret; > > + /* Clear this page out of any CPU caches for coherent swap-in/out */ > + ret = i915_gem_object_set_to_gtt_domain(to->obj, false); > + if (ret) { > + i915_gem_object_unpin(to->obj); > + return ret; > + } > + Do I understand things correctly that thanks to clever use of set_to_gtt_domain with write = false and not setting a write_domain when moving the old context object to the active list we won't block? If so, I'll add a short note to that effect to the commit message when merging. And given that we have similar clever interface abuse in the pwrite/pread code, some code rework is in order I guess. We could replace all that domain tracking with bool gpu_coherent would be simpler (after the flushing_list's permanent demise, of course). -Daniel > if (!to->obj->has_global_gtt_mapping) > i915_gem_gtt_bind_object(to->obj, to->obj->cache_level); > > -- > 1.7.10.4 > > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/intel-gfx -- Daniel Vetter Mail: daniel@ffwll.ch Mobile: +41 (0)79 365 57 48