usb_lock_device_for_reset(9) [centos man page]

USB_LOCK_DEVICE_FOR_(9) 					   USB Core APIs					   USB_LOCK_DEVICE_FOR_(9)

NAME

       usb_lock_device_for_reset - cautiously acquire the lock for a usb device structure

SYNOPSIS

       int usb_lock_device_for_reset(struct usb_device * udev, const struct usb_interface * iface);

ARGUMENTS

       udev
	   device that's being locked

       iface
	   interface bound to the driver making the request (optional)

DESCRIPTION

       Attempts to acquire the device lock, but fails if the device is NOTATTACHED or SUSPENDED, or if iface is specified and the interface is
       neither BINDING nor BOUND. Rather than sleeping to wait for the lock, the routine polls repeatedly. This is to prevent deadlock with
       disconnect; in some drivers (such as usb-storage) the disconnect or suspend method will block waiting for a device reset to complete.

RETURN

       A negative error code for failure, otherwise 0.

COPYRIGHT

Kernel Hackers Manual 3.10					     June 2014						   USB_LOCK_DEVICE_FOR_(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)