litedram: l2: Latency improvements

litedram: l2: Latency improvements

This implements in the L2 cache the feature already in the L1s
allowing a request to be completed before the end of a refill
using partial line valid bits, and starting a refill from the
row of the first miss on that line instead of the beginning of
the line.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>