usb_deregister(9) [centos man page]

USB_DEREGISTER(9)						   USB Core APIs						 USB_DEREGISTER(9)

NAME

       usb_deregister - unregister a USB interface driver

SYNOPSIS

       void usb_deregister(struct usb_driver * driver);

ARGUMENTS

       driver
	   USB operations of the interface driver to unregister

CONTEXT

       must be able to sleep

DESCRIPTION

       Unlinks the specified driver from the internal USB driver list.

NOTE

       If you called usb_register_dev, you still need to call usb_deregister_dev to clean up your driver's allocated minor numbers, this * call
       will no longer do it for you.

COPYRIGHT

Kernel Hackers Manual 3.10					     June 2014							 USB_DEREGISTER(9)

USB_QUEUE_RESET_DEVI(9) 					   USB Core APIs					   USB_QUEUE_RESET_DEVI(9)

NAME

       usb_queue_reset_device - Reset a USB device from an atomic context

SYNOPSIS

       void usb_queue_reset_device(struct usb_interface * iface);

ARGUMENTS

       iface
	   USB interface belonging to the device to reset

DESCRIPTION

       This function can be used to reset a USB device from an atomic context, where usb_reset_device won't work (as it blocks).

       Doing a reset via this method is functionally equivalent to calling usb_reset_device, except for the fact that it is delayed to a
       workqueue. This means that any drivers bound to other interfaces might be unbound, as well as users from usbfs in user space.

CORNER CASES

       - Scheduling two resets at the same time from two different drivers attached to two different interfaces of the same device is possible;
       depending on how the driver attached to each interface handles ->pre_reset, the second reset might happen or not.

       - If a driver is unbound and it had a pending reset, the reset will be cancelled.

       - This function can be called during .probe or .disconnect times. On return from .disconnect, any pending resets will be cancelled.

       There is no no need to lock/unlock the reset_ws as schedule_work does its own.

NOTE

       We don't do any reference count tracking because it is not needed. The lifecycle of the work_struct is tied to the usb_interface. Before
       destroying the interface we cancel the work_struct, so the fact that work_struct is queued and or running means the interface (and thus,
       the device) exist and are referenced.

COPYRIGHT

Kernel Hackers Manual 3.10					     June 2014						   USB_QUEUE_RESET_DEVI(9)