From: Bjorn Helgaas <helgaas@kernel.org> To: Lu Baolu <baolu.lu@linux.intel.com> Cc: Stuart Yoder <stuyoder@gmail.com>, rafael@kernel.org, David Airlie <airlied@linux.ie>, linux-pci@vger.kernel.org, Thierry Reding <thierry.reding@gmail.com>, Diana Craciun <diana.craciun@oss.nxp.com>, Dmitry Osipenko <digetx@gmail.com>, Will Deacon <will@kernel.org>, Ashok Raj <ashok.raj@intel.com>, Jonathan Hunter <jonathanh@nvidia.com>, Christoph Hellwig <hch@infradead.org>, Jason Gunthorpe <jgg@nvidia.com>, Kevin Tian <kevin.tian@intel.com>, Chaitanya Kulkarni <kch@nvidia.com>, Alex Williamson <alex.williamson@redhat.com>, kvm@vger.kernel.org, Bjorn Helgaas <bhelgaas@google.com>, Dan Williams <dan.j.williams@intel.com>, Greg Kroah-Hartman <gregkh@linuxfoundation.org>, Cornelia Huck <cohuck@redhat.com>, linux-kernel@vger.kernel.org, Li Yang <leoyang.li@nxp.com>, iommu@lists.linux-foundation.org, Jacob jun Pan <jacob.jun.pan@intel.com>, Daniel Vetter <daniel@ffwll.ch>, Robin Murphy <robin.murphy@arm.com> Subject: Re: [PATCH v5 09/14] PCI: portdrv: Suppress kernel DMA ownership auto-claiming Date: Tue, 4 Jan 2022 11:06:31 -0600 [thread overview] Message-ID: <20220104170631.GA99771@bhelgaas> (raw) In-Reply-To: <20220104015644.2294354-10-baolu.lu@linux.intel.com> On Tue, Jan 04, 2022 at 09:56:39AM +0800, Lu Baolu wrote: > If a switch lacks ACS P2P Request Redirect, a device below the switch can > bypass the IOMMU and DMA directly to other devices below the switch, so > all the downstream devices must be in the same IOMMU group as the switch > itself. Help me think through what's going on here. IIUC, we put devices in the same IOMMU group when they can interfere with each other in any way (DMA, config access, etc). (We said "DMA" above, but I guess this would also apply to config requests, right?) *This* patch doesn't check for any ACS features. Can you connect the dots for me? I guess the presence or absence of P2P Request Redirect determines the size of the IOMMU group. And the following says something about what is allowed in the group? And .no_kernel_api_dma allows an exception to the general rule? > The existing vfio framework allows the portdrv driver to be bound > to the bridge while its downstream devices are assigned to user space. I.e., the existing VFIO framework allows a switch to be in the same IOMMU group as the devices below it, even though the switch has a kernel driver and the other devices may have userspace drivers? Is this a function of VFIO design or of the IOMMU driver? > The pci_dma_configure() marks the iommu_group as containing only devices > with kernel drivers that manage DMA. Avoid this default behavior for the > portdrv driver in order for compatibility with the current vfio policy. I assume "IOMMU group" means the same as "iommu_group"; maybe we can use one of them consistently? > Suggested-by: Jason Gunthorpe <jgg@nvidia.com> > Suggested-by: Kevin Tian <kevin.tian@intel.com> > Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com> > --- > drivers/pci/pcie/portdrv_pci.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c > index 35eca6277a96..2116f821c005 100644 > --- a/drivers/pci/pcie/portdrv_pci.c > +++ b/drivers/pci/pcie/portdrv_pci.c > @@ -202,6 +202,8 @@ static struct pci_driver pcie_portdriver = { > > .err_handler = &pcie_portdrv_err_handler, > > + .no_kernel_api_dma = true, > + > .driver.pm = PCIE_PORTDRV_PM_OPS, > }; > > -- > 2.25.1 > _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
WARNING: multiple messages have this Message-ID (diff)
From: Bjorn Helgaas <helgaas@kernel.org> To: Lu Baolu <baolu.lu@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>, Joerg Roedel <joro@8bytes.org>, Alex Williamson <alex.williamson@redhat.com>, Bjorn Helgaas <bhelgaas@google.com>, Jason Gunthorpe <jgg@nvidia.com>, Christoph Hellwig <hch@infradead.org>, Kevin Tian <kevin.tian@intel.com>, Ashok Raj <ashok.raj@intel.com>, Will Deacon <will@kernel.org>, Robin Murphy <robin.murphy@arm.com>, Dan Williams <dan.j.williams@intel.com>, rafael@kernel.org, Diana Craciun <diana.craciun@oss.nxp.com>, Cornelia Huck <cohuck@redhat.com>, Eric Auger <eric.auger@redhat.com>, Liu Yi L <yi.l.liu@intel.com>, Jacob jun Pan <jacob.jun.pan@intel.com>, Chaitanya Kulkarni <kch@nvidia.com>, Stuart Yoder <stuyoder@gmail.com>, Laurentiu Tudor <laurentiu.tudor@nxp.com>, Thierry Reding <thierry.reding@gmail.com>, David Airlie <airlied@linux.ie>, Daniel Vetter <daniel@ffwll.ch>, Jonathan Hunter <jonathanh@nvidia.com>, Li Yang <leoyang.li@nxp.com>, Dmitry Osipenko <digetx@gmail.com>, iommu@lists.linux-foundation.org, linux-pci@vger.kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH v5 09/14] PCI: portdrv: Suppress kernel DMA ownership auto-claiming Date: Tue, 4 Jan 2022 11:06:31 -0600 [thread overview] Message-ID: <20220104170631.GA99771@bhelgaas> (raw) In-Reply-To: <20220104015644.2294354-10-baolu.lu@linux.intel.com> On Tue, Jan 04, 2022 at 09:56:39AM +0800, Lu Baolu wrote: > If a switch lacks ACS P2P Request Redirect, a device below the switch can > bypass the IOMMU and DMA directly to other devices below the switch, so > all the downstream devices must be in the same IOMMU group as the switch > itself. Help me think through what's going on here. IIUC, we put devices in the same IOMMU group when they can interfere with each other in any way (DMA, config access, etc). (We said "DMA" above, but I guess this would also apply to config requests, right?) *This* patch doesn't check for any ACS features. Can you connect the dots for me? I guess the presence or absence of P2P Request Redirect determines the size of the IOMMU group. And the following says something about what is allowed in the group? And .no_kernel_api_dma allows an exception to the general rule? > The existing vfio framework allows the portdrv driver to be bound > to the bridge while its downstream devices are assigned to user space. I.e., the existing VFIO framework allows a switch to be in the same IOMMU group as the devices below it, even though the switch has a kernel driver and the other devices may have userspace drivers? Is this a function of VFIO design or of the IOMMU driver? > The pci_dma_configure() marks the iommu_group as containing only devices > with kernel drivers that manage DMA. Avoid this default behavior for the > portdrv driver in order for compatibility with the current vfio policy. I assume "IOMMU group" means the same as "iommu_group"; maybe we can use one of them consistently? > Suggested-by: Jason Gunthorpe <jgg@nvidia.com> > Suggested-by: Kevin Tian <kevin.tian@intel.com> > Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com> > --- > drivers/pci/pcie/portdrv_pci.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c > index 35eca6277a96..2116f821c005 100644 > --- a/drivers/pci/pcie/portdrv_pci.c > +++ b/drivers/pci/pcie/portdrv_pci.c > @@ -202,6 +202,8 @@ static struct pci_driver pcie_portdriver = { > > .err_handler = &pcie_portdrv_err_handler, > > + .no_kernel_api_dma = true, > + > .driver.pm = PCIE_PORTDRV_PM_OPS, > }; > > -- > 2.25.1 >
next prev parent reply other threads:[~2022-01-04 17:06 UTC|newest] Thread overview: 112+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-01-04 1:56 [PATCH v5 00/14] Fix BUG_ON in vfio_iommu_group_notifier() Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 01/14] iommu: Add dma ownership management interfaces Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 10:08 ` Christoph Hellwig 2022-01-04 10:08 ` Christoph Hellwig 2022-01-04 16:41 ` Bjorn Helgaas 2022-01-04 16:41 ` Bjorn Helgaas 2022-01-04 19:23 ` Jason Gunthorpe 2022-01-04 19:23 ` Jason Gunthorpe via iommu 2022-01-06 3:18 ` Lu Baolu 2022-01-06 3:18 ` Lu Baolu 2022-01-06 3:54 ` Lu Baolu 2022-01-06 3:54 ` Lu Baolu 2022-01-06 15:46 ` Jason Gunthorpe 2022-01-06 15:46 ` Jason Gunthorpe via iommu 2022-01-07 1:50 ` Lu Baolu 2022-01-07 1:50 ` Lu Baolu 2022-01-06 3:43 ` Lu Baolu 2022-01-06 3:43 ` Lu Baolu 2022-01-06 3:47 ` Lu Baolu 2022-01-06 3:47 ` Lu Baolu 2022-01-06 3:51 ` Lu Baolu 2022-01-06 3:51 ` Lu Baolu 2022-01-05 6:57 ` Lu Baolu 2022-01-05 6:57 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 02/14] driver core: Add dma_cleanup callback in bus_type Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 10:08 ` Christoph Hellwig 2022-01-04 10:08 ` Christoph Hellwig 2022-01-04 12:39 ` Jason Gunthorpe 2022-01-04 12:39 ` Jason Gunthorpe via iommu 2022-01-04 13:04 ` Greg Kroah-Hartman 2022-01-04 13:04 ` Greg Kroah-Hartman 2022-02-08 5:55 ` Lu Baolu 2022-02-08 5:55 ` Lu Baolu 2022-02-08 11:35 ` Greg Kroah-Hartman 2022-02-08 11:35 ` Greg Kroah-Hartman 2022-02-14 10:01 ` Greg Kroah-Hartman 2022-02-14 10:01 ` Greg Kroah-Hartman 2022-02-14 10:02 ` Greg Kroah-Hartman 2022-02-14 10:02 ` Greg Kroah-Hartman 2022-01-04 1:56 ` [PATCH v5 03/14] amba: Stop sharing platform_dma_configure() Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 04/14] driver core: platform: Add driver dma ownership management Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-02-14 9:59 ` Greg Kroah-Hartman 2022-02-14 9:59 ` Greg Kroah-Hartman 2022-02-14 13:18 ` Jason Gunthorpe 2022-02-14 13:18 ` Jason Gunthorpe via iommu 2022-02-14 13:37 ` Greg Kroah-Hartman 2022-02-14 13:37 ` Greg Kroah-Hartman 2022-02-14 13:43 ` Jason Gunthorpe 2022-02-14 13:43 ` Jason Gunthorpe via iommu 2022-01-04 1:56 ` [PATCH v5 05/14] amba: " Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 06/14] bus: fsl-mc: " Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 07/14] PCI: " Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-02-14 10:03 ` Greg Kroah-Hartman 2022-02-14 10:03 ` Greg Kroah-Hartman 2022-02-14 12:38 ` Jason Gunthorpe 2022-02-14 12:38 ` Jason Gunthorpe via iommu 2022-02-14 12:51 ` Greg Kroah-Hartman 2022-02-14 12:51 ` Greg Kroah-Hartman 2022-02-14 13:11 ` Jason Gunthorpe 2022-02-14 13:11 ` Jason Gunthorpe via iommu 2022-02-14 13:39 ` Greg Kroah-Hartman 2022-02-14 13:39 ` Greg Kroah-Hartman 2022-02-14 13:43 ` Jason Gunthorpe 2022-02-14 13:43 ` Jason Gunthorpe via iommu 2022-02-15 3:06 ` Lu Baolu 2022-02-15 3:06 ` Lu Baolu 2022-02-23 18:00 ` Bjorn Helgaas 2022-02-23 18:00 ` Bjorn Helgaas 2022-02-23 18:07 ` Jason Gunthorpe 2022-02-23 18:07 ` Jason Gunthorpe via iommu 2022-01-04 1:56 ` [PATCH v5 08/14] PCI: pci_stub: Suppress kernel DMA ownership auto-claiming Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 09/14] PCI: portdrv: " Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 17:06 ` Bjorn Helgaas [this message] 2022-01-04 17:06 ` Bjorn Helgaas 2022-01-04 19:26 ` Jason Gunthorpe 2022-01-04 19:26 ` Jason Gunthorpe via iommu 2022-01-04 19:51 ` Bjorn Helgaas 2022-01-04 19:51 ` Bjorn Helgaas 2022-01-05 0:35 ` Jason Gunthorpe 2022-01-05 0:35 ` Jason Gunthorpe via iommu 2022-01-06 4:12 ` Lu Baolu 2022-01-06 4:12 ` Lu Baolu 2022-01-06 18:32 ` Bjorn Helgaas 2022-01-06 18:32 ` Bjorn Helgaas 2022-01-07 1:53 ` Lu Baolu 2022-01-07 1:53 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 10/14] vfio: Set DMA ownership for VFIO devices Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 11/14] vfio: Remove use of vfio_group_viable() Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 12/14] vfio: Delete the unbound_list Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 13/14] vfio: Remove iommu group notifier Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 1:56 ` [PATCH v5 14/14] iommu: Remove iommu group changes notifier Lu Baolu 2022-01-04 1:56 ` Lu Baolu 2022-01-04 12:48 ` [PATCH v5 00/14] Fix BUG_ON in vfio_iommu_group_notifier() Jason Gunthorpe 2022-01-04 12:48 ` Jason Gunthorpe via iommu 2022-01-05 6:52 ` Lu Baolu 2022-01-05 6:52 ` Lu Baolu 2022-02-18 1:07 ` Lu Baolu 2022-02-18 1:07 ` Lu Baolu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20220104170631.GA99771@bhelgaas \ --to=helgaas@kernel.org \ --cc=airlied@linux.ie \ --cc=alex.williamson@redhat.com \ --cc=ashok.raj@intel.com \ --cc=baolu.lu@linux.intel.com \ --cc=bhelgaas@google.com \ --cc=cohuck@redhat.com \ --cc=dan.j.williams@intel.com \ --cc=daniel@ffwll.ch \ --cc=diana.craciun@oss.nxp.com \ --cc=digetx@gmail.com \ --cc=gregkh@linuxfoundation.org \ --cc=hch@infradead.org \ --cc=iommu@lists.linux-foundation.org \ --cc=jacob.jun.pan@intel.com \ --cc=jgg@nvidia.com \ --cc=jonathanh@nvidia.com \ --cc=kch@nvidia.com \ --cc=kevin.tian@intel.com \ --cc=kvm@vger.kernel.org \ --cc=leoyang.li@nxp.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-pci@vger.kernel.org \ --cc=rafael@kernel.org \ --cc=robin.murphy@arm.com \ --cc=stuyoder@gmail.com \ --cc=thierry.reding@gmail.com \ --cc=will@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.