From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35506) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cWHKF-0001ao-6k for qemu-devel@nongnu.org; Wed, 25 Jan 2017 01:45:00 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cWHKC-0003Ip-4y for qemu-devel@nongnu.org; Wed, 25 Jan 2017 01:44:59 -0500 Received: from mx1.redhat.com ([209.132.183.28]:53442) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1cWHKB-0003Hg-Tt for qemu-devel@nongnu.org; Wed, 25 Jan 2017 01:44:56 -0500 Date: Wed, 25 Jan 2017 14:44:50 +0800 From: Peter Xu Message-ID: <20170125064450.GF5151@pxdev.xzpeter.org> References: <1484917736-32056-1-git-send-email-peterx@redhat.com> <1484917736-32056-17-git-send-email-peterx@redhat.com> <20170124045242.GM26526@pxdev.xzpeter.org> <20170125034623.GA5151@pxdev.xzpeter.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH RFC v4 16/20] intel_iommu: do replay when context invalidate List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Tian, Kevin" Cc: Jason Wang , "Lan, Tianyu" , "mst@redhat.com" , "jan.kiszka@siemens.com" , "bd.aviv@gmail.com" , "qemu-devel@nongnu.org" , "alex.williamson@redhat.com" On Wed, Jan 25, 2017 at 06:37:23AM +0000, Tian, Kevin wrote: > > From: Peter Xu [mailto:peterx@redhat.com] > > Sent: Wednesday, January 25, 2017 11:46 AM > >=20 > > On Wed, Jan 25, 2017 at 11:09:39AM +0800, Jason Wang wrote: > > > > > > > > > On 2017=E5=B9=B401=E6=9C=8824=E6=97=A5 12:52, Peter Xu wrote: > > > >On Mon, Jan 23, 2017 at 06:36:17PM +0800, Jason Wang wrote: > > > >> > > > >>On 2017=E5=B9=B401=E6=9C=8820=E6=97=A5 21:08, Peter Xu wrote: > > > >>>Before this one we only invalidate context cache when we receive= context > > > >>>entry invalidations. However it's possible that the invalidation= also > > > >>>contains a domain switch (only if cache-mode is enabled for vIOM= MU). In > > > >>>that case we need to notify all the registered components about = the new > > > >>>mapping. > > > >>> > > > >>>Signed-off-by: Peter Xu > > > >>>--- > > > >>> hw/i386/intel_iommu.c | 10 ++++++++++ > > > >>> 1 file changed, 10 insertions(+) > > > >>> > > > >>>diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c > > > >>>index f9c5142..4b08b4d 100644 > > > >>>--- a/hw/i386/intel_iommu.c > > > >>>+++ b/hw/i386/intel_iommu.c > > > >>>@@ -1146,6 +1146,16 @@ static void > > vtd_context_device_invalidate(IntelIOMMUState *s, > > > >>> trace_vtd_inv_desc_cc_device(bus_n, VTD_PCI_SL= OT(devfn_it), > > > >>> VTD_PCI_FUNC(devf= n_it)); > > > >>> vtd_as->context_cache_entry.context_cache_gen = =3D 0; > > > >>>+ /* > > > >>>+ * So a device is moving out of (or moving into= ) a > > > >>>+ * domain, a replay() suites here to notify all= the > > > >>>+ * IOMMU_NOTIFIER_MAP registers about this chan= ge. > > > >>>+ * This won't bring bad even if we have no such > > > >>>+ * notifier registered - the IOMMU notification > > > >>>+ * framework will skip MAP notifications if tha= t > > > >>>+ * happened. > > > >>>+ */ > > > >>>+ memory_region_iommu_replay_all(&vtd_as->iommu); > > > >>DSI and GLOBAL questions come back again or no need to care about= them :) ? > > > >DSI/GLOBAL hanldings are in patch 20 (though it'll be squashed int= o 18 > > > >in my next post). Is that what you mean above? > > > > > > Seems not, I mean DSI/GLOBAL for context cache invalidation instead= of IOTLB > > > :) > >=20 > > Yes, I should possibly do the same thing for context cache global > > invalidations. IIUC context global invalidation should be a superset > > of iotlb invalidation, so maybe I'll add one more patch to call iotlb > > invalidation in context invalidation as well. Kevin/others, please > > correct me if I misunderstood the spec. Thanks, > >=20 >=20 > context invalidation is not superset of iotlb invalidation. The spec ju= st > requires software to always follow a context-cache invalidation with > a PASID-cache invalidation, followed by an IOTLB invalidation. Thanks for pointing out. If so, looks like current version suffice for this, right? (so no further change needed for this one) -- peterx