The readenv() implementation of env_nand uses the mtd layer which is
unnecessary overhead in SPL when we already have a nand_spl_load_image()
function that doesn't need it. Using this instead eliminates the need
to provide a mtd_read for SPL env as well as reduces code (4KB savings in IMX6
SPL).

Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Acked-by: Scott Wood <scottwood@freescale.com>