Flush the L1 cache for the CPU which is going down in cpu_die() so
that we don't end up with all platforms doing this.  This ensures
that any cache lines we own are pushed out before the cache becomes
inaccessible.

We may end up subsequently creating some dirty cache lines - for
example, with the complete() call, but this update must become
visible to other CPUs before __cpu_die() can proceed.  Subsequent
accesses from the platforms cpu_die() function should _not_ matter.

Also place a mb() after the complete() call to ensure that this is
visible to other CPUs.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>