1 files changed, 91 insertions, 21 deletions

diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 017069a455d4..cc3cbb4435f8 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -105,7 +105,7 @@ static void pcistub_device_release(struct kref *kref)
 	 */
 	__pci_reset_function_locked(dev);
 	if (pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
-		dev_dbg(&dev->dev, "Could not reload PCI state\n");
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	else
 		pci_restore_state(dev);
 
@@ -250,11 +250,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
  *  - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
  *
  *  As such we have to be careful.
+ *
+ *  To make this easier, the caller has to hold the device lock.
  */
 void pcistub_put_pci_dev(struct pci_dev *dev)
 {
 	struct pcistub_device *psdev, *found_psdev = NULL;
 	unsigned long flags;
+	struct xen_pcibk_dev_data *dev_data;
+	int ret;
 
 	spin_lock_irqsave(&pcistub_devices_lock, flags);
 
@@ -276,13 +280,20 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	/* Cleanup our device
 	 * (so it's ready for the next domain)
 	 */
+	device_lock_assert(&dev->dev);
+	__pci_reset_function_locked(dev);
 
-	/* This is OK - we are running from workqueue context
-	 * and want to inhibit the user from fiddling with 'reset'
-	 */
-	pci_reset_function(dev);
-	pci_restore_state(dev);
-
+	dev_data = pci_get_drvdata(dev);
+	ret = pci_load_saved_state(dev, dev_data->pci_saved_state);
+	if (!ret) {
+		/*
+		 * The usual sequence is pci_save_state & pci_restore_state
+		 * but the guest might have messed the configuration space up.
+		 * Use the initial version (when device was bound to us).
+		 */
+		pci_restore_state(dev);
+	} else
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	/* This disables the device. */
 	xen_pcibk_reset_device(dev);
 
@@ -554,12 +565,14 @@ static void pcistub_remove(struct pci_dev *dev)
 	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
 	if (found_psdev) {
-		dev_dbg(&dev->dev, "found device to remove - in use? %p\n",
-			found_psdev->pdev);
+		dev_dbg(&dev->dev, "found device to remove %s\n",
+			found_psdev->pdev ? "- in-use" : "");
 
 		if (found_psdev->pdev) {
-			pr_warn("****** removing device %s while still in-use! ******\n",
-			       pci_name(found_psdev->dev));
+			int domid = xen_find_device_domain_owner(dev);
+
+			pr_warn("****** removing device %s while still in-use by domain %d! ******\n",
+			       pci_name(found_psdev->dev), domid);
 			pr_warn("****** driver domain may still access this device's i/o resources!\n");
 			pr_warn("****** shutdown driver domain before binding device\n");
 			pr_warn("****** to other drivers or domains\n");
@@ -567,7 +580,8 @@ static void pcistub_remove(struct pci_dev *dev)
 			/* N.B. This ends up calling pcistub_put_pci_dev which ends up
 			 * doing the FLR. */
 			xen_pcibk_release_pci_dev(found_psdev->pdev,
-						found_psdev->dev);
+						found_psdev->dev,
+						false /* caller holds the lock. */);
 		}
 
 		spin_lock_irqsave(&pcistub_devices_lock, flags);
@@ -629,10 +643,12 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 {
 	pci_ers_result_t res = result;
 	struct xen_pcie_aer_op *aer_op;
+	struct xen_pcibk_device *pdev = psdev->pdev;
+	struct xen_pci_sharedinfo *sh_info = pdev->sh_info;
 	int ret;
 
 	/*with PV AER drivers*/
-	aer_op = &(psdev->pdev->sh_info->aer_op);
+	aer_op = &(sh_info->aer_op);
 	aer_op->cmd = aer_cmd ;
 	/*useful for error_detected callback*/
 	aer_op->err = state;
@@ -653,36 +669,36 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 	* this flag to judge whether we need to check pci-front give aer
 	* service ack signal
 	*/
-	set_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	set_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	/*It is possible that a pcifront conf_read_write ops request invokes
 	* the callback which cause the spurious execution of wake_up.
 	* Yet it is harmless and better than a spinlock here
 	*/
 	set_bit(_XEN_PCIB_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags);
+		(unsigned long *)&sh_info->flags);
 	wmb();
-	notify_remote_via_irq(psdev->pdev->evtchn_irq);
+	notify_remote_via_irq(pdev->evtchn_irq);
 
 	ret = wait_event_timeout(xen_pcibk_aer_wait_queue,
 				 !(test_bit(_XEN_PCIB_active, (unsigned long *)
-				 &psdev->pdev->sh_info->flags)), 300*HZ);
+				 &sh_info->flags)), 300*HZ);
 
 	if (!ret) {
 		if (test_bit(_XEN_PCIB_active,
-			(unsigned long *)&psdev->pdev->sh_info->flags)) {
+			(unsigned long *)&sh_info->flags)) {
 			dev_err(&psdev->dev->dev,
 				"pcifront aer process not responding!\n");
 			clear_bit(_XEN_PCIB_active,
-			  (unsigned long *)&psdev->pdev->sh_info->flags);
+			  (unsigned long *)&sh_info->flags);
 			aer_op->err = PCI_ERS_RESULT_NONE;
 			return res;
 		}
 	}
-	clear_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	if (test_bit(_XEN_PCIF_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		(unsigned long *)&sh_info->flags)) {
 		dev_dbg(&psdev->dev->dev,
 			"schedule pci_conf service in " DRV_NAME "\n");
 		xen_pcibk_test_and_schedule_op(psdev->pdev);
@@ -1502,6 +1518,53 @@ parse_error:
 fs_initcall(pcistub_init);
 #endif
 
+#ifdef CONFIG_PCI_IOV
+static struct pcistub_device *find_vfs(const struct pci_dev *pdev)
+{
+	struct pcistub_device *psdev = NULL;
+	unsigned long flags;
+	bool found = false;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (!psdev->pdev && psdev->dev != pdev
+		    && pci_physfn(psdev->dev) == pdev) {
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	if (found)
+		return psdev;
+	return NULL;
+}
+
+static int pci_stub_notifier(struct notifier_block *nb,
+			     unsigned long action, void *data)
+{
+	struct device *dev = data;
+	const struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (action != BUS_NOTIFY_UNBIND_DRIVER)
+		return NOTIFY_DONE;
+
+	if (!pdev->is_physfn)
+		return NOTIFY_DONE;
+
+	for (;;) {
+		struct pcistub_device *psdev = find_vfs(pdev);
+		if (!psdev)
+			break;
+		device_release_driver(&psdev->dev->dev);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block pci_stub_nb = {
+	.notifier_call = pci_stub_notifier,
+};
+#endif
+
 static int __init xen_pcibk_init(void)
 {
 	int err;
@@ -1523,12 +1586,19 @@ static int __init xen_pcibk_init(void)
 	err = xen_pcibk_xenbus_register();
 	if (err)
 		pcistub_exit();
+#ifdef CONFIG_PCI_IOV
+	else
+		bus_register_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 
 	return err;
 }
 
 static void __exit xen_pcibk_cleanup(void)
 {
+#ifdef CONFIG_PCI_IOV
+	bus_unregister_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 	xen_pcibk_xenbus_unregister();
 	pcistub_exit();
 }