ARM: 9058/1: cache-v7: refactor v7_invalidate_l1 to avoid clobbering r5/r6

The cache invalidation code in v7_invalidate_l1 can be tweaked to
re-read the associativity from CCSIDR, and keep the way identifier
component in a single register that is assigned in the outer loop. This
way, we need 2 registers less.

Given that the number of sets is typically much larger than the
associativity, rearrange the code so that the outer loop has the fewer
number of iterations, ensuring that the re-read of CCSIDR only occurs a
handful of times in practice.

Fix the whitespace while at it, and update the comment to indicate that
this code is no longer a clone of anything else.

Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>