vfio: fix deadlock between group lock and kvm lock

After 51cdc8bc120e, we have another deadlock scenario between the
kvm->lock and the vfio group_lock with two different codepaths acquiring
the locks in different order.  Specifically in vfio_open_device, vfio
holds the vfio group_lock when issuing device->ops->open_device but some
drivers (like vfio-ap) need to acquire kvm->lock during their open_device
routine;  Meanwhile, kvm_vfio_release will acquire the kvm->lock first
before calling vfio_file_set_kvm which will acquire the vfio group_lock.

To resolve this, let's remove the need for the vfio group_lock from the
kvm_vfio_release codepath.  This is done by introducing a new spinlock to
protect modifications to the vfio group kvm pointer, and acquiring a kvm
ref from within vfio while holding this spinlock, with the reference held
until the last close for the device in question.

Fixes: 51cdc8bc120e ("kvm/vfio: Fix potential deadlock on vfio group_lock")
Reported-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20230203215027.151988-2-mjrosato@linux.ibm.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 37 insertions, 7 deletions

diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index bb24b2f0271e..98621ac082f0 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -154,6 +154,18 @@ out_unlock:
 	return ret;
 }
 
+static void vfio_device_group_get_kvm_safe(struct vfio_device *device)
+{
+	spin_lock(&device->group->kvm_ref_lock);
+	if (!device->group->kvm)
+		goto unlock;
+
+	_vfio_device_get_kvm_safe(device, device->group->kvm);
+
+unlock:
+	spin_unlock(&device->group->kvm_ref_lock);
+}
+
 static int vfio_device_group_open(struct vfio_device *device)
 {
 	int ret;
@@ -164,13 +176,23 @@ static int vfio_device_group_open(struct vfio_device *device)
 		goto out_unlock;
 	}
 
+	mutex_lock(&device->dev_set->lock);
+
 	/*
-	 * Here we pass the KVM pointer with the group under the lock.  If the
-	 * device driver will use it, it must obtain a reference and release it
-	 * during close_device.
+	 * Before the first device open, get the KVM pointer currently
+	 * associated with the group (if there is one) and obtain a reference
+	 * now that will be held until the open_count reaches 0 again.  Save
+	 * the pointer in the device for use by drivers.
 	 */
-	ret = vfio_device_open(device, device->group->iommufd,
-			       device->group->kvm);
+	if (device->open_count == 0)
+		vfio_device_group_get_kvm_safe(device);
+
+	ret = vfio_device_open(device, device->group->iommufd, device->kvm);
+
+	if (device->open_count == 0)
+		vfio_device_put_kvm(device);
+
+	mutex_unlock(&device->dev_set->lock);
 
 out_unlock:
 	mutex_unlock(&device->group->group_lock);
@@ -180,7 +202,14 @@ out_unlock:
 void vfio_device_group_close(struct vfio_device *device)
 {
 	mutex_lock(&device->group->group_lock);
+	mutex_lock(&device->dev_set->lock);
+
 	vfio_device_close(device, device->group->iommufd);
+
+	if (device->open_count == 0)
+		vfio_device_put_kvm(device);
+
+	mutex_unlock(&device->dev_set->lock);
 	mutex_unlock(&device->group->group_lock);
 }
 
@@ -450,6 +479,7 @@ static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
 
 	refcount_set(&group->drivers, 1);
 	mutex_init(&group->group_lock);
+	spin_lock_init(&group->kvm_ref_lock);
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
 	group->iommu_group = iommu_group;
@@ -803,9 +833,9 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 	if (!vfio_file_is_group(file))
 		return;
 
-	mutex_lock(&group->group_lock);
+	spin_lock(&group->kvm_ref_lock);
 	group->kvm = kvm;
-	mutex_unlock(&group->group_lock);
+	spin_unlock(&group->kvm_ref_lock);
 }
 EXPORT_SYMBOL_GPL(vfio_file_set_kvm);