Re: NetBSD hardclock overhead growth

[Felix Deichmann <m4j0rd0m0%gmail.com@localhost>]

2015-08-26 20:57 GMT+02:00 Michael L. Hitch <mhitch%netbsd.org@localhost>:
>   The first two were from one of my VLC systems and shows that it has all 8
> banks of cache.  The second one was from another VLC and looks like one bank
> is missing on that.  A third VLC I wasn't able to boot from to look at.
>
>   You can see that I was able to read the BEHR register on my systems, so
> I'm also not sure why John was getting a panic trying to read it.

Interesting. I will test my two KA660 boards in the next days.
And while I'm there, a small patch which will print the real working
cache size instead of "6KB" flat should also be easy.

Now that you could run code which John says panics on his machine, I
bet that ka660_cache_enable() will also work for you...? It is almost
following the description in the docs, except for its own code to test
for working/enabled banks (but I already suggested that we could skip
that step which is done by firmware before).
We could have a common function for KA48 and KA660 (all SOC) in the end.

Regards,
Felix