[PATCH v5 13/14] vfio: Remove iommu group notifier

From: Lu Baolu <baolu.lu@linux.intel.com>
To: 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>
Cc: 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,
	Lu Baolu <baolu.lu@linux.intel.com>
Subject: [PATCH v5 13/14] vfio: Remove iommu group notifier
Date: Tue,  4 Jan 2022 09:56:43 +0800	[thread overview]
Message-ID: <20220104015644.2294354-14-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20220104015644.2294354-1-baolu.lu@linux.intel.com>

The iommu core and driver core have been enhanced to avoid unsafe driver
binding to a live group after iommu_group_set_dma_owner(PRIVATE_USER)
has been called. There's no need to register iommu group notifier. This
removes the iommu group notifer which contains BUG_ON() and WARN().

The commit 5f096b14d421b ("vfio: Whitelist PCI bridges") allowed all
pcieport drivers to be bound with devices while the group is assigned to
user space. This is not always safe. For example, The shpchp_core driver
relies on the PCI MMIO access for the controller functionality. With its
downstream devices assigned to the userspace, the MMIO might be changed
through user initiated P2P accesses without any notification. This might
break the kernel driver integrity and lead to some unpredictable
consequences. As the result, currently we only allow the portdrv driver.

For any bridge driver, in order to avoiding default kernel DMA ownership
claiming, we should consider:

 1) Does the bridge driver use DMA? Calling pci_set_master() or
    a dma_map_* API is a sure indicate the driver is doing DMA

 2) If the bridge driver uses MMIO, is it tolerant to hostile
    userspace also touching the same MMIO registers via P2P DMA
    attacks?

Conservatively if the driver maps an MMIO region at all, we can say that
it fails the test.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/vfio/vfio.c | 147 --------------------------------------------
 1 file changed, 147 deletions(-)

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 2877ec47e32a..dce42ede3190 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -71,7 +71,6 @@ struct vfio_group {
 	struct vfio_container		*container;
 	struct list_head		device_list;
 	struct mutex			device_lock;
-	struct notifier_block		nb;
 	struct list_head		vfio_next;
 	struct list_head		container_next;
 	atomic_t			opened;
@@ -274,8 +273,6 @@ void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);
 
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data);
 static void vfio_group_get(struct vfio_group *group);
 
 /*
@@ -395,13 +392,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 		goto err_put;
 	}
 
-	group->nb.notifier_call = vfio_iommu_group_notifier;
-	err = iommu_group_register_notifier(iommu_group, &group->nb);
-	if (err) {
-		ret = ERR_PTR(err);
-		goto err_put;
-	}
-
 	mutex_lock(&vfio.group_lock);
 
 	/* Did we race creating this group? */
@@ -422,7 +412,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 
 err_unlock:
 	mutex_unlock(&vfio.group_lock);
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 err_put:
 	put_device(&group->dev);
 	return ret;
@@ -447,7 +436,6 @@ static void vfio_group_put(struct vfio_group *group)
 	cdev_device_del(&group->cdev, &group->dev);
 	mutex_unlock(&vfio.group_lock);
 
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
 	put_device(&group->dev);
 }
 
@@ -503,141 +491,6 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
 	return NULL;
 }
 
-/*
- * Some drivers, like pci-stub, are only used to prevent other drivers from
- * claiming a device and are therefore perfectly legitimate for a user owned
- * group.  The pci-stub driver has no dependencies on DMA or the IOVA mapping
- * of the device, but it does prevent the user from having direct access to
- * the device, which is useful in some circumstances.
- *
- * We also assume that we can include PCI interconnect devices, ie. bridges.
- * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge
- * then all of the downstream devices will be part of the same IOMMU group as
- * the bridge.  Thus, if placing the bridge into the user owned IOVA space
- * breaks anything, it only does so for user owned devices downstream.  Note
- * that error notification via MSI can be affected for platforms that handle
- * MSI within the same IOVA space as DMA.
- */
-static const char * const vfio_driver_allowed[] = { "pci-stub" };
-
-static bool vfio_dev_driver_allowed(struct device *dev,
-				    struct device_driver *drv)
-{
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-
-		if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
-			return true;
-	}
-
-	return match_string(vfio_driver_allowed,
-			    ARRAY_SIZE(vfio_driver_allowed),
-			    drv->name) >= 0;
-}
-
-/*
- * A vfio group is viable for use by userspace if all devices are in
- * one of the following states:
- *  - driver-less
- *  - bound to a vfio driver
- *  - bound to an otherwise allowed driver
- *  - a PCI interconnect device
- *
- * We use two methods to determine whether a device is bound to a vfio
- * driver.  The first is to test whether the device exists in the vfio
- * group.  The second is to test if the device exists on the group
- * unbound_list, indicating it's in the middle of transitioning from
- * a vfio driver to driver-less.
- */
-static int vfio_dev_viable(struct device *dev, void *data)
-{
-	struct vfio_group *group = data;
-	struct vfio_device *device;
-	struct device_driver *drv = READ_ONCE(dev->driver);
-
-	if (!drv || vfio_dev_driver_allowed(dev, drv))
-		return 0;
-
-	device = vfio_group_get_device(group, dev);
-	if (device) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-/*
- * Async device support
- */
-static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	/* Do we already know about it?  We shouldn't */
-	device = vfio_group_get_device(group, dev);
-	if (WARN_ON_ONCE(device)) {
-		vfio_device_put(device);
-		return 0;
-	}
-
-	/* Nothing to do for idle groups */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	/* TODO Prevent device auto probing */
-	dev_WARN(dev, "Device added to live group %d!\n",
-		 iommu_group_id(group->iommu_group));
-
-	return 0;
-}
-
-static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
-{
-	/* We don't care what happens when the group isn't in use */
-	if (!atomic_read(&group->container_users))
-		return 0;
-
-	return vfio_dev_viable(dev, group);
-}
-
-static int vfio_iommu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
-	struct device *dev = data;
-
-	switch (action) {
-	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
-		vfio_group_nb_add_dev(group, dev);
-		break;
-	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-		/*
-		 * Nothing to do here.  If the device is in use, then the
-		 * vfio sub-driver should block the remove callback until
-		 * it is unused.  If the device is unused or attached to a
-		 * stub driver, then it should be released and we don't
-		 * care that it will be going away.
-		 */
-		break;
-	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
-		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
-			iommu_group_id(group->iommu_group));
-		break;
-	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
-		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
-			iommu_group_id(group->iommu_group), dev->driver->name);
-		BUG_ON(vfio_group_nb_verify(group, dev));
-		break;
-	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
-		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
-			__func__, iommu_group_id(group->iommu_group),
-			dev->driver->name);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 /*
  * VFIO driver API
  */
-- 
2.25.1

