Geert,
On Sun, Dec 8, 2013 at 1:17 PM, Ingo Jürgensmann
<i...@2013.bluespice.org> wrote:
This means that the kernel would be located in the slow ZorroIII
memory (256M), which should be avoided in the long run. We need
support for SPARSEMEM and priority of mem chunks as in AmigaOS, i.e.
memory chunk with highest priority should be preferred first.
The next steps would be:
- start SPARSEMEM support in kernel
Yep.
Looks like it can't be avoided any longer.
- find out if we need a new amiboot
I'd really like to avoid the need for a new amiboot.
You would only need a new amiboot when extending the passed bootinfo.
Amiboot already has memfile support, so you can specify the order of
the
memory chunks. What's "missing" is a way to specify memory chunk
priorities.
A naive method is to just assume the first chunk has the highest
priority
(but you probably don't want that on Atari, where ST-RAM would be the
first
chunk by default).
It already is (has to be, due to lack of sparse mem support). And the
kernel lives in ST-RAM pretty much always.
Alternatively, it could be done automatically, by the kernel measuring
read
(and/or write) performance of the different memory chunks in a loop
similar
to the delay loop calibration.
While disabling caches, presumably? How do we do that - map the test
chunk as nocache?
Cheers,
Michael
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 --
ge...@linux-m68k.org
In personal conversations with technical people, I call myself a
hacker. But
when I'm talking to journalists I just say "programmer" or something
like that.
-- Linus Torvalds
--
To UNSUBSCRIBE, email to debian-68k-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact
listmas...@lists.debian.org
Archive:
http://lists.debian.org/CAMuHMdUCuO-5C5r21z1FzLc+0tvFv=vJ7AU+cu6P2PO-
utc...@mail.gmail.com
--
To UNSUBSCRIBE, email to debian-68k-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
Archive:
http://lists.debian.org/650d56f8e1a896e83e4992d36d46a...@biophys.uni-duesseldorf.de
