Merge tag 'vfio-v3.11-rc4' of git://github.com/awilliam/linux-vfio

Pull vfio fixes from Alex Williamson:
 "misc fixes around overreacting to bus notifier events and a locking
  fix for a corner case blocked remove"

* tag 'vfio-v3.11-rc4' of git://github.com/awilliam/linux-vfio:
  vfio-pci: Avoid deadlock on remove
  vfio: Ignore sprurious notifies
  vfio: Don't overreact to DEL_DEVICE

2 files changed, 31 insertions, 29 deletions

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index c5179e269df6..cef6002acbd4 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -137,8 +137,27 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
          */
         pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
 
-        if (vdev->reset_works)
-                __pci_reset_function(pdev);
+        /*
+         * Careful, device_lock may already be held.  This is the case if
+         * a driver unbind is blocked.  Try to get the locks ourselves to
+         * prevent a deadlock.
+         */
+        if (vdev->reset_works) {
+                bool reset_done = false;
+
+                if (pci_cfg_access_trylock(pdev)) {
+                        if (device_trylock(&pdev->dev)) {
+                                __pci_reset_function_locked(pdev);
+                                reset_done = true;
+                                device_unlock(&pdev->dev);
+                        }
+                        pci_cfg_access_unlock(pdev);
+                }
+
+                if (!reset_done)
+                        pr_warn("%s: Unable to acquire locks for reset of %s\n",
+                                __func__, dev_name(&pdev->dev));
+        }
 
         pci_restore_state(pdev);
 }
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index c488da5db7c7..842f4507883e 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -494,27 +494,6 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
         return 0;
 }
 
-static int vfio_group_nb_del_dev(struct vfio_group *group, struct device *dev)
-{
-        struct vfio_device *device;
-
-        /*
-         * Expect to fall out here.  If a device was in use, it would
-         * have been bound to a vfio sub-driver, which would have blocked
-         * in .remove at vfio_del_group_dev.  Sanity check that we no
-         * longer track the device, so it's safe to remove.
-         */
-        device = vfio_group_get_device(group, dev);
-        if (likely(!device))
-                return 0;
-
-        WARN("Device %s removed from live group %d!\n", dev_name(dev),
-             iommu_group_id(group->iommu_group));
-
-        vfio_device_put(device);
-        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 */
@@ -531,13 +510,11 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
         struct device *dev = data;
 
         /*
-         * Need to go through a group_lock lookup to get a reference or
-         * we risk racing a group being removed.  Leave a WARN_ON for
-         * debuging, but if the group no longer exists, a spurious notify
-         * is harmless.
+         * Need to go through a group_lock lookup to get a reference or we
+         * risk racing a group being removed.  Ignore spurious notifies.
          */
         group = vfio_group_try_get(group);
-        if (WARN_ON(!group))
+        if (!group)
                 return NOTIFY_OK;
 
         switch (action) {
@@ -545,7 +522,13 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
                 vfio_group_nb_add_dev(group, dev);
                 break;
         case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-                vfio_group_nb_del_dev(group, dev);
+                /*
+                 * 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:
                 pr_debug("%s: Device %s, group %d binding to driver\n",