Consider two threads calling read() on the same uinput-fd, both
non-blocking. Assume there is data-available so both will simultaneously
pass:
	udev->head == udev->tail

Then the first thread goes to sleep and the second one pops the message
from the queue. Now assume udev->head == udev->tail. If the first thread
wakes up it will call wait_event_*() and sleep in the waitq. This
effectively turns the non-blocking FD into a blocking one.

We fix this by attempting to fetch events from the queue first and only
if we fail to retrieve any events we either return -EAGAIN (in case of
non-blocing read) or wait until there are more events.

This also fixes incorrect return code (we were returning 0 instead of
 -EAGAIN for non-blocking reads) when an event is "stolen" by another
thread. Blocking reads will now continue to wait instead of returning 0
in this scenario.

Count of 0 continues to be a special case, as per spec: we will check for
device existence and whether there are events in the queue, but no events
will be actually retrieved.
Reported-by: David Herrmann <dh.herrmann@googlemail.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>