*Sigh* I overlooked two patches in the original numbering...

This patch closes the race on the device and extension lists at USB disconnect 
time. Previously, the device was removed from the device list during 
em28xx_release_resources(), and then passed to the em28xx_close_extension() 
function so that all extensions could run their fini() operations. However, this 
left a (brief, theoretical, highly unlikely ;-)) window between these two calls 
during which a new module could call em28xx_register_extension(). The result 
would have been that the em28xx_usb_disconnect() function would also have passed 
the device to the new extension's fini() function, despite never having called 
the extension's init() function.

This patch also restores em28xx_close_extension()'s symmetry with 
em28xx_init_extension(), and establishes the property that every device in the 
device list must have been initialised for every extension in the extension list.

Signed-of-by: Chris Rankin <ranki...@yahoo.com>