Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932772Ab1ERB5l (ORCPT ); Tue, 17 May 2011 21:57:41 -0400 Received: from mx1.redhat.com ([209.132.183.28]:32866 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932406Ab1ERB5j (ORCPT ); Tue, 17 May 2011 21:57:39 -0400 Subject: Re: [PATCH] pci, dmar: flush IOTLB before exit domain From: Alex Williamson To: David Woodhouse Cc: Yinghai Lu , Kalle Valo , "linux-pci@vger.kernel.org" , "iommu@lists.linux-foundation.org" , "linux-kernel@vger.kernel.org" , Jesse Barnes In-Reply-To: <1305661262.29268.27.camel@x201> References: <4DC34B21.9040203@oracle.com> <1304952530.30435.16.camel@i7.infradead.org> <1305558798.3146.48.camel@x201> <1305661262.29268.27.camel@x201> Content-Type: text/plain; charset="UTF-8" Date: Tue, 17 May 2011 19:57:25 -0600 Message-ID: <1305683845.29268.34.camel@x201> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3509 Lines: 98 On Tue, 2011-05-17 at 13:41 -0600, Alex Williamson wrote: > On Mon, 2011-05-16 at 09:13 -0600, Alex Williamson wrote: > > On Mon, 2011-05-09 at 15:48 +0100, David Woodhouse wrote: > > > On Thu, 2011-05-05 at 18:13 -0700, Yinghai Lu wrote: > > > > @@ -3252,6 +3252,9 @@ static int device_notifier(struct notifi > > > > return 0; > > > > > > > > if (action == BUS_NOTIFY_UNBOUND_DRIVER && !iommu_pass_through) { > > > > + /* before we remove dev with domain, flush IOTLB */ > > > > + flush_unmaps(); > > > > + > > > > domain_remove_one_dev_info(domain, pdev); > > > > > > > > if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) && > > > > > > That calls flush_unmaps() without the async_umap_flush_lock held, > > > doesn't it? A few days ago I asked someone else to test this candidate > > > patch for a similar issue: > > > > > > http://david.woodhou.se/flush-unmaps-on-unbind.patch > > > > Copying here: > > > > > diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c > > > index d552d2c..7e606d6 100644 > > > --- a/drivers/pci/intel-iommu.c > > > +++ b/drivers/pci/intel-iommu.c > > > @@ -3256,8 +3259,10 @@ static int device_notifier(struct notifier_block *nb, > > > > > > if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) && > > > !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) && > > > - list_empty(&domain->devices)) > > > + list_empty(&domain->devices)) { > > > + flush_unmaps_timeout(0); > > > domain_exit(domain); > > > + } > > > } > > > > > > return 0; > > > @@ -3587,6 +3592,7 @@ static void intel_iommu_domain_destroy(struct iommu_domain *domain) > > > struct dmar_domain *dmar_domain = domain->priv; > > > > > > domain->priv = NULL; > > > + flush_unmaps_timeout(0); > > > vm_domain_exit(dmar_domain); > > > } > > > > David, would it be worthwhile to push the unmaps into the > > {vm_}domain_exit() functions to avoid races like this in the future? I > > can verify the above resolves a panic after unbinding a device from > > snd_hda_intel that I hit recently. Do you plan to push this for .39? > > BTW, is this second chunk really needed? VM iommu mappings don't seem > to use the lazy unmap path. Thanks, David, what do you think of this instead? Thanks, Alex intel-iommu: Flush unmaps at domain_exit From: Alex Williamson We typically batch unmaps to be lazily flushed out at regular intervals. When we destroy a domain, we need to force a flush of these lazy unmaps to be sure none reference the domain we're about to free. Signed-off-by: Alex Williamson --- drivers/pci/intel-iommu.c | 4 ++++ 1 files changed, 4 insertions(+), 0 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index d552d2c..b04f84e 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -1416,6 +1416,10 @@ static void domain_exit(struct dmar_domain *domain) if (!domain) return; + /* Flush any lazy unmaps that may reference this domain */ + if (!intel_iommu_strict) + flush_unmaps_timeout(0); + domain_remove_dev_info(domain); /* destroy iovas */ put_iova_domain(&domain->iovad); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/