The v4l function has a better algorithm for aligning image size.

The existing code was casting pointers to u32 and to unsigned int into
pointers to u16.  This could mess up if someone passed in an image size
greater than 65,535 and on big-endian platforms it won't work at all.

The existing bounding code would shrink an image if it was too big, but
returned ERANGE if it was too small.  The code will not shrink or expand as
necessary.
Signed-off-by: Trent Piepho <xyzzy@speakeasy.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>