From mboxrd@z Thu Jan 1 00:00:00 1970 From: Konrad Rzeszutek Wilk Subject: Re: Re: ATI radeon fails with "iommu=soft swiotlb=force" (seen on RV730/RV740 and RS780/RS800) Date: Mon, 5 Oct 2009 10:49:03 -0400 Message-ID: <20091005144903.GA3991@phenom.dumpdata.com> References: <41093.83224.qm@web56108.mail.re3.yahoo.com> <4AC649B0.5090700@goop.org> <4AC9E75F0200007800017F61@vpn.id2.novell.com> <20091005140152.GA3127@phenom.dumpdata.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Alex Deucher Cc: Jeremy Fitzhardinge , dri-devel@lists.sourceforge.net, xen-devel@lists.xensource.com, Jan Beulich List-Id: xen-devel@lists.xenproject.org On Mon, Oct 05, 2009 at 10:41:04AM -0400, Alex Deucher wrote: > On Mon, Oct 5, 2009 at 10:01 AM, Konrad Rzeszutek Wilk > wrote: > > On Mon, Oct 05, 2009 at 11:32:31AM +0100, Jan Beulich wrote: > >> >>> Jeremy Fitzhardinge 02.10.09 20:42 >>> > >> >On 10/02/09 10:23, Boris Derzhavets wrote: > >> >> Jeremy, > >> >> Please, =A0be aware of bugzilla.xensource.com [1519] =A0the most = recent > >> >> entries :- > >> >> > >> >> http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=3D1519 > >> >> > >> > > >> >Ah, OK. =A0I pushed a variant of Konrad's patches. =A0Could you try= them out? > >> > >> Are you really convinced fixing this in DRM is the right thing to do= ? To > >> me, the use of vmalloc_32() in drivers/ieee1394/ seems to make simil= ar > >> assumptions (pci_map_sg() not modifying the buffer addresses), and > >> who knows where else such assumptions exist. After all, vmalloc_32() > >> is *defined* to have the property assumed by both of the users, and > >> other than for most kmalloc() cases using GFP_DMA{,32} we're talking > >> about double buffering generally large amounts of data here even in > >> the cases where the DMA API is being used properly. > > > > I was chatting with Jeremy about this, and I realized that in some > > sense the radeon driver assumes that physical !=3D bus addresses. Whi= ch is > > OK on x86, but if this card was ever moved to a Sun box it would fail= . > > >=20 > FWIW, the radeon drm has been working fine on both sparc and ppc for ye= ars. Thank you for keeping me honest! I thought that the IOMMU on those boxes would return physical !=3D bus ad= dresses? Maybe those days are long gone?