From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [PATCH] IOMMU: don't disable bus mastering on faults for devices used by Xen or Dom0 Date: Tue, 6 Nov 2012 15:16:50 +0100 Message-ID: <1352211410.2155.7.camel@Solace> References: <5097FD2902000078000A66BF@nat28.tlf.novell.com> <5098E19D02000078000A697A@nat28.tlf.novell.com> <20121106094456.GA45690@ocelot.phlegethon.org> <1352203585.505.5.camel@Solace> <509915CD02000078000A6ABF@nat28.tlf.novell.com> <20121106135842.GB45690@ocelot.phlegethon.org> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5543024278306713870==" Return-path: In-Reply-To: <20121106135842.GB45690@ocelot.phlegethon.org> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Tim Deegan Cc: "Keir (Xen.org)" , "wei.huang2@amd.com" , xen-devel , Jan Beulich , "weiwang.dd@gmail.com" , "xiantao.zhang@intel.com" List-Id: xen-devel@lists.xenproject.org --===============5543024278306713870== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-ToUauuo/eo9Qf+ripbpI" --=-ToUauuo/eo9Qf+ripbpI Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Tue, 2012-11-06 at 13:58 +0000, Tim Deegan wrote: > > It helps keeping Xen alive, but doesn't for any specific domain > > (including Dom0). >=20 > Indeed. (Intel) IOMMU interrupts are suppressed until the softirq > handler acknowledges the error, but if the softirq handler doesn't > disable the device, it will take another IOMMU interrupt immediately. > Right. I wasn't considering the possibility of this 'back-to-back' variant of the thing. > I thought the AMD side behaved eth same but clearly not -- I'll try to > take a look at that later in the week. >=20 I think it does, or at least, I'm quite sure when I moved the fault handling code in softiq context, I did it so that behavior was consistent wrt both Intel and AMD (by explicitly silencing interrupts until within the tasklet), at least for faults. PPR came later and I moved them within the softirq as well after asking AMD people, without having the possibility to test that myself. So, to recap, feel free to check. Faults should behave as you're describing, PPR I'm not sure. :-) Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://retis.sssup.it/people/faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-ToUauuo/eo9Qf+ripbpI Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iEYEABECAAYFAlCZG9IACgkQk4XaBE3IOsTBagCgg35YIjm6u6e1OAFS6Q7GYB2e 3NoAnA66EpIC0C7UeFH/YD5RJsx2Ske6 =9kp6 -----END PGP SIGNATURE----- --=-ToUauuo/eo9Qf+ripbpI-- --===============5543024278306713870== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============5543024278306713870==--