From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Vetter Subject: Re: [PATCH] drm/i915: Invariably invalidate before ctx switch Date: Thu, 3 Apr 2014 11:42:13 +0200 Message-ID: <20140403094213.GD7225@phenom.ffwll.local> References: <1396503023-3114-1-git-send-email-benjamin.widawsky@intel.com> <20140403070535.GJ5602@nuc-i3427.alporthouse.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-wg0-f41.google.com (mail-wg0-f41.google.com [74.125.82.41]) by gabe.freedesktop.org (Postfix) with ESMTP id 4CA3C6E9EF for ; Thu, 3 Apr 2014 02:42:19 -0700 (PDT) Received: by mail-wg0-f41.google.com with SMTP id n12so1533546wgh.0 for ; Thu, 03 Apr 2014 02:42:16 -0700 (PDT) Content-Disposition: inline In-Reply-To: <20140403070535.GJ5602@nuc-i3427.alporthouse.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" To: Chris Wilson , Ben Widawsky , Intel GFX List-Id: intel-gfx@lists.freedesktop.org On Thu, Apr 03, 2014 at 08:05:35AM +0100, Chris Wilson wrote: > On Wed, Apr 02, 2014 at 10:30:23PM -0700, Ben Widawsky wrote: > > We have been setting the bit which was originally BIOS dependent since: > > commit f05bb0c7b624252a5e768287e340e8e45df96e42 > > Author: Chris Wilson > > Date: Sun Jan 20 16:33:32 2013 +0000 > > > > drm/i915: GFX_MODE Flush TLB Invalidate Mode must be '1' for scanline waits > > > > Therefore, we do not need to try to figure it out dynamically and we can > > just always invalidate the TLBs. > > > > It's a partial revert of: > > commit 12b0286f49947a6cdc9285032d918466a8c3f5f9 > > Author: Ben Widawsky > > Date: Mon Jun 4 14:42:50 2012 -0700 > > > > drm/i915: possibly invalidate TLB before context switch > > > > The original commit attempted to only invalidate when necessary > > (very much a relic from the old days). Now, we can just always invalidate. > > > > I guess the old TODO still exists. Since we seem to have abandoned ILK > > contexts however, there isn't much point in even remembering. > > > > Cc: Chris Wilson > > Signed-off-by: Ben Widawsky > > Seems reasonable, except in most cases (execbuffer) there will be > a following cache-invalidate as part of the move-to-gpu. > > Reviewed-by: Chris Wilson Queued for -next, thanks for the patch. > ILK ctx, never forget. Iirc those patches still hang in there ;-) Cheers, Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch