Merge tag 'vfio-for-v3.8-v2' of git://github.com/awilliam/linux-vfio

Pull vfio update from Alex Williamson.

* tag 'vfio-for-v3.8-v2' of git://github.com/awilliam/linux-vfio:
  vfio-pci: Enable device before attempting reset
  VFIO: fix out of order labels for error recovery in vfio_pci_init()
  VFIO: use ACCESS_ONCE() to guard access to dev->driver
  VFIO: unregister IOMMU notifier on error recovery path
  vfio-pci: Re-order device reset
  vfio: simplify kmalloc+copy_from_user to memdup_user

2 files changed, 64 insertions, 53 deletions

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 6c119944bbb..b28e66c4376 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -43,6 +43,10 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	u16 cmd;
 	u8 msix_pos;
 
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
 	vdev->reset_works = (pci_reset_function(pdev) == 0);
 	pci_save_state(pdev);
 	vdev->pci_saved_state = pci_store_saved_state(pdev);
@@ -51,8 +55,11 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 			 __func__, dev_name(&pdev->dev));
 
 	ret = vfio_config_init(vdev);
-	if (ret)
-		goto out;
+	if (ret) {
+		pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state);
+		pci_disable_device(pdev);
+		return ret;
+	}
 
 	if (likely(!nointxmask))
 		vdev->pci_2_3 = pci_intx_mask_supported(pdev);
@@ -77,24 +84,15 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	} else
 		vdev->msix_bar = 0xFF;
 
-	ret = pci_enable_device(pdev);
-	if (ret)
-		goto out;
-
-	return ret;
-
-out:
-	kfree(vdev->pci_saved_state);
-	vdev->pci_saved_state = NULL;
-	vfio_config_free(vdev);
-	return ret;
+	return 0;
 }
 
 static void vfio_pci_disable(struct vfio_pci_device *vdev)
 {
+	struct pci_dev *pdev = vdev->pdev;
 	int bar;
 
-	pci_disable_device(vdev->pdev);
+	pci_disable_device(pdev);
 
 	vfio_pci_set_irqs_ioctl(vdev, VFIO_IRQ_SET_DATA_NONE |
 				VFIO_IRQ_SET_ACTION_TRIGGER,
@@ -104,22 +102,40 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 
 	vfio_config_free(vdev);
 
-	pci_reset_function(vdev->pdev);
-
-	if (pci_load_and_free_saved_state(vdev->pdev,
-					  &vdev->pci_saved_state) == 0)
-		pci_restore_state(vdev->pdev);
-	else
-		pr_info("%s: Couldn't reload %s saved state\n",
-			__func__, dev_name(&vdev->pdev->dev));
-
 	for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
 		if (!vdev->barmap[bar])
 			continue;
-		pci_iounmap(vdev->pdev, vdev->barmap[bar]);
-		pci_release_selected_regions(vdev->pdev, 1 << bar);
+		pci_iounmap(pdev, vdev->barmap[bar]);
+		pci_release_selected_regions(pdev, 1 << bar);
 		vdev->barmap[bar] = NULL;
 	}
+
+	/*
+	 * If we have saved state, restore it.  If we can reset the device,
+	 * even better.  Resetting with current state seems better than
+	 * nothing, but saving and restoring current state without reset
+	 * is just busy work.
+	 */
+	if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
+		pr_info("%s: Couldn't reload %s saved state\n",
+			__func__, dev_name(&pdev->dev));
+
+		if (!vdev->reset_works)
+			return;
+
+		pci_save_state(pdev);
+	}
+
+	/*
+	 * Disable INTx and MSI, presumably to avoid spurious interrupts
+	 * during reset.  Stolen from pci_reset_function()
+	 */
+	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	if (vdev->reset_works)
+		__pci_reset_function(pdev);
+
+	pci_restore_state(pdev);
 }
 
 static void vfio_pci_release(void *device_data)
@@ -327,15 +343,10 @@ static long vfio_pci_ioctl(void *device_data,
 			    hdr.count > vfio_pci_get_irq_count(vdev, hdr.index))
 				return -EINVAL;
 
-			data = kmalloc(hdr.count * size, GFP_KERNEL);
-			if (!data)
-				return -ENOMEM;
-
-			if (copy_from_user(data, (void __user *)(arg + minsz),
-					   hdr.count * size)) {
-				kfree(data);
-				return -EFAULT;
-			}
+			data = memdup_user((void __user *)(arg + minsz),
+					   hdr.count * size);
+			if (IS_ERR(data))
+				return PTR_ERR(data);
 		}
 
 		mutex_lock(&vdev->igate);
@@ -562,9 +573,9 @@ static int __init vfio_pci_init(void)
 
 	return 0;
 
-out_virqfd:
-	vfio_pci_virqfd_exit();
 out_driver:
+	vfio_pci_virqfd_exit();
+out_virqfd:
 	vfio_pci_uninit_perm_bits();
 	return ret;
 }
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 56097c6d072..12c264d3b05 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -191,6 +191,17 @@ static void vfio_container_put(struct vfio_container *container)
 	kref_put(&container->kref, vfio_container_release);
 }
 
+static void vfio_group_unlock_and_free(struct vfio_group *group)
+{
+	mutex_unlock(&vfio.group_lock);
+	/*
+	 * Unregister outside of lock.  A spurious callback is harmless now
+	 * that the group is no longer in vfio.group_list.
+	 */
+	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
+	kfree(group);
+}
+
 /**
  * Group objects - create, release, get, put, search
  */
@@ -229,8 +240,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 
 	minor = vfio_alloc_group_minor(group);
 	if (minor < 0) {
-		mutex_unlock(&vfio.group_lock);
-		kfree(group);
+		vfio_group_unlock_and_free(group);
 		return ERR_PTR(minor);
 	}
 
@@ -239,8 +249,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 		if (tmp->iommu_group == iommu_group) {
 			vfio_group_get(tmp);
 			vfio_free_group_minor(minor);
-			mutex_unlock(&vfio.group_lock);
-			kfree(group);
+			vfio_group_unlock_and_free(group);
 			return tmp;
 		}
 	}
@@ -249,8 +258,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 			    group, "%d", iommu_group_id(iommu_group));
 	if (IS_ERR(dev)) {
 		vfio_free_group_minor(minor);
-		mutex_unlock(&vfio.group_lock);
-		kfree(group);
+		vfio_group_unlock_and_free(group);
 		return (struct vfio_group *)dev; /* ERR_PTR */
 	}
 
@@ -274,16 +282,7 @@ static void vfio_group_release(struct kref *kref)
 	device_destroy(vfio.class, MKDEV(MAJOR(vfio.devt), group->minor));
 	list_del(&group->vfio_next);
 	vfio_free_group_minor(group->minor);
-
-	mutex_unlock(&vfio.group_lock);
-
-	/*
-	 * Unregister outside of lock.  A spurious callback is harmless now
-	 * that the group is no longer in vfio.group_list.
-	 */
-	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
-
-	kfree(group);
+	vfio_group_unlock_and_free(group);
 }
 
 static void vfio_group_put(struct vfio_group *group)
@@ -466,8 +465,9 @@ static int vfio_dev_viable(struct device *dev, void *data)
 {
 	struct vfio_group *group = data;
 	struct vfio_device *device;
+	struct device_driver *drv = ACCESS_ONCE(dev->driver);
 
-	if (!dev->driver || vfio_whitelisted_driver(dev->driver))
+	if (!drv || vfio_whitelisted_driver(drv))
 		return 0;
 
 	device = vfio_group_get_device(group, dev);