bcachefs: Fix rereplicate when we already have a cached pointer

bcachefs: Fix rereplicate when we already have a cached pointer

When we need to add more replicas to an extent, it might be the case
that we already have a replica on every device, but some of them are
cached.

This patch fixes a bug where we'd spin on that extent because the write
path fails to find a device we can allocate from: we allow allocating
from devices that already have cached replicas on them, and change
bch2_data_update_index_update() to drop the cached replica if needed.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>