Reviewing a fresh portion of coverity defects in USB core (specifically CID 1458999), Alan Stern noted below in [1]:
On Tue, Feb 25, 2020 at 02:39:23PM -0500, Alan Stern wrote:
A revised search finds line 997 in drivers/usb/core/hub.c and lines 216, 269 in drivers/usb/core/port.c. (I didn't try looking in any other directories.) AFAICT all three of these should check the return value, although a error message in the kernel log probably isn't needed.
Factor out the usb_remove_device() change into a standalone patch to allow conflict-free integration on top of the earliest stable branches.
[1] https://lore.kernel.org/lkml/Pine.LNX.4.44L0.2002251419120.1485-100000@iolan...
Fixes: 253e05724f9230 ("USB: add a "remove hardware" sysfs attribute") Cc: stable@vger.kernel.org # v2.6.33+ Suggested-by: Alan Stern stern@rowland.harvard.edu Signed-off-by: Eugeniu Rosca erosca@de.adit-jv.com --- v3: - Newly submitted --- drivers/usb/core/hub.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 1105983b5c1c..54cd8ef795ec 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -988,13 +988,17 @@ int usb_remove_device(struct usb_device *udev) { struct usb_hub *hub; struct usb_interface *intf; + int ret;
if (!udev->parent) /* Can't remove a root hub */ return -EINVAL; hub = usb_hub_to_struct_hub(udev->parent); intf = to_usb_interface(hub->intfdev);
- usb_autopm_get_interface(intf); + ret = usb_autopm_get_interface(intf); + if (ret < 0) + return ret; + set_bit(udev->portnum, hub->removed_bits); hub_port_logical_disconnect(hub, udev->portnum); usb_autopm_put_interface(intf);