PCI: Protect pci_error_handlers->reset_notify() usage with device_lock()

commit b014e96d upstream.

Every method in struct device_driver or structures derived from it like
struct pci_driver MUST provide exclusion vs the driver's ->remove() method,
usually by using device_lock().

Protect use of pci_error_handlers->reset_notify() by holding the device
lock while calling it.

Note:

  - pci_dev_lock() calls device_lock() in addition to blocking user-space
    config accesses.

  - pci_err_handlers->reset_notify() is used inside
    pci_dev_save_and_disable() and pci_dev_restore().  We could hold the
    device lock directly in pci_reset_notify(), but we expand the region
    since we have several calls following each other.

Without this, ->reset_notify() may race with ->remove() calls, which can be
easily triggered in NVMe.

[bhelgaas: changelog, add pci_reset_notify() comment]
[bhelgaas: fold in fix from Dan Carpenter <dan.carpenter@oracle.com>:
http://lkml.kernel.org/r/20170701135323.x5vaj4e2wcs2mcro@mwanda]
Link: http://lkml.kernel.org/r/20170601111039.8913-2-hch@lst.deReported-by: Rakesh Pandit <rakesh@tuxera.com>
Tested-by: Rakesh Pandit <rakesh@tuxera.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/pci/pci.c

@@ -4141,6 +4141,12 @@ static void pci_reset_notify(struct pci_dev *dev, bool prepare)
 {
 	const struct pci_error_handlers *err_handler =
 			dev->driver ? dev->driver->err_handler : NULL;
+
+	/*
+	 * dev->driver->err_handler->reset_notify() is protected against
+	 * races with ->remove() by the device lock, which must be held by
+	 * the caller.
+	 */
 	if (err_handler && err_handler->reset_notify)
 		err_handler->reset_notify(dev, prepare);
 }
@@ -4276,11 +4282,13 @@ int pci_reset_function(struct pci_dev *dev)
 	if (rc)
 		return rc;
 
+	pci_dev_lock(dev);
 	pci_dev_save_and_disable(dev);
 
-	rc = pci_dev_reset(dev, 0);
+	rc = __pci_dev_reset(dev, 0);
 
 	pci_dev_restore(dev);
+	pci_dev_unlock(dev);
 
 	return rc;
 }
@@ -4300,16 +4308,14 @@ int pci_try_reset_function(struct pci_dev *dev)
 	if (rc)
 		return rc;
 
-	pci_dev_save_and_disable(dev);
+	if (!pci_dev_trylock(dev))
+		return -EAGAIN;
 
-	if (pci_dev_trylock(dev)) {
-		rc = __pci_dev_reset(dev, 0);
-		pci_dev_unlock(dev);
-	} else
-		rc = -EAGAIN;
+	pci_dev_save_and_disable(dev);
+	rc = __pci_dev_reset(dev, 0);
+	pci_dev_unlock(dev);
 
 	pci_dev_restore(dev);
-
 	return rc;
 }
 EXPORT_SYMBOL_GPL(pci_try_reset_function);
@@ -4459,7 +4465,9 @@ static void pci_bus_save_and_disable(struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_dev_lock(dev);
 		pci_dev_save_and_disable(dev);
+		pci_dev_unlock(dev);
 		if (dev->subordinate)
 			pci_bus_save_and_disable(dev->subordinate);
 	}
@@ -4474,7 +4482,9 @@ static void pci_bus_restore(struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_dev_lock(dev);
 		pci_dev_restore(dev);
+		pci_dev_unlock(dev);
 		if (dev->subordinate)
 			pci_bus_restore(dev->subordinate);
 	}