From mboxrd@z Thu Jan  1 00:00:00 1970
From: Christoph Hellwig <hch@lst.de>
Subject: Re: Kernel and ADM hardware roulette ( was AMD graphics
        performance regression in 4.15 and later )
Date: Mon, 11 Jun 2018 09:15:01 +0200
Message-ID: <20180611071501.GA1015@lst.de>
References: <CAEJqkgiNVDzboDK1vsn9rYP0G=Q_mGDrkx1VVB8TUkm35Rs9fA@mail.gmail.com> <516cddbe-73c2-01f3-a552-0d9fd75ce63a@amd.com> <8f7d00f9-992f-cc07-6bd0-b1b47c5d2ccf@amd.com> <ae904954-18f7-180a-ce69-7e7618bd398f@daenzer.net> <CAEJqkgjErpxG44CZXn2BzvPES7Ptf24ae6748dAcYdg2n5HuZw@mail.gmail.com> <267c42ce-91e2-4843-3815-904ac74b2f44@amd.com> <CAEJqkggsjnod79HFvYQHRFEsFaN-bb27P8Xf79_9DmxhLKs_Og@mail.gmail.com> <20180608060223.GB24107@lst.de> <1c8b3938-6656-5d5a-f65d-dfd2e55d989e@amd.com> <CAEJqkggkZynDvV8XxkFfy89x-DX5xDTyubUJ3oXBO6eUjBWBKw@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-kernel-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <CAEJqkggkZynDvV8XxkFfy89x-DX5xDTyubUJ3oXBO6eUjBWBKw@mail.gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
To: Gabriel C <nix.or.die@gmail.com>
Cc: Christian =?iso-8859-1?Q?K=F6nig?= <christian.koenig@amd.com>, Christoph Hellwig <hch@lst.de>, Tom Lendacky <thomas.lendacky@amd.com>, Jean-Marc Valin <jmvalin@mozilla.com>, Dave Airlie <airlied@linux.ie>, Felix Kuehling <Felix.Kuehling@amd.com>, LKML <linux-kernel@vger.kernel.org>, dri-devel@lists.freedesktop.org, Joerg Roedel <jroedel@suse.de>, alexander.deucher@amd.com, Andrew Morton <akpm@linux-foundation.org>, Linus Torvalds <torvalds@linux-foundation.org>, Michel =?iso-8859-1?Q?D=E4nzer?= <michel@daenzer.net>
List-Id: dri-devel@lists.freedesktop.org

I think the prime issue is that dma_direct_alloc respects the dma
mask.  Which we don't need if actually using the iommu.  This would
be mostly harmless exept for the the SEV bit high in the address that
makes the checks fail.

For now I'd say revert this commit for 4.17/4.18-rc and I'll look into
addressing these issues properly.