usb_autopm_get_interface(9) [centos man page]

USB_AUTOPM_GET_INTER(9) 					   USB Core APIs					   USB_AUTOPM_GET_INTER(9)

NAME

       usb_autopm_get_interface - increment a USB interface's PM-usage counter

SYNOPSIS

       int usb_autopm_get_interface(struct usb_interface * intf);

ARGUMENTS

       intf
	   the usb_interface whose counter should be incremented

DESCRIPTION

       This routine should be called by an interface driver when it wants to use intf and needs to guarantee that it is not suspended. In
       addition, the routine prevents intf from being autosuspended subsequently. (Note that this will not prevent suspend events originating in
       the PM core.) This prevention will persist until usb_autopm_put_interface is called or intf is unbound. A typical example would be a
       character-device driver when its device file is opened.

       intf's usage counter is incremented to prevent subsequent autosuspends. However if the autoresume fails then the counter is re-decremented.

       This routine can run only in process context.

RETURN

       0 on success.

COPYRIGHT

Kernel Hackers Manual 3.10					     June 2014						   USB_AUTOPM_GET_INTER(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)