AW: Linux/m68k on Atari

[<Bert.Jahn@t-systems.com>]

> Patrice Mandin píše v Čt 09. 04. 2009 v 21:40 +0200:
> > Fixing the kernel to run it from FastRam seems top priority for me, to
> > have it run at full speed.
> 
> I think I reported first FastRAM problems like 10-12 years ago. The
> symptoms were that time was running much faster (the bogomips 
> value was
> 3-4 times higher than normal) and there were many spurious interrupts
> (/proc/interrupts). And the IDE was not running correctly (because of
> that?).
> 
> We never figured out what was wrong - mainly because I was the only one
> with an AfterBurner040 - so the workaround with kernel in ST-RAM became
> sort of a given thing. I think I remember some TT030 were 
> having similar problems...

I'm not familiar with Atari but for Amiga this sounds like the usual interrupt acknowledge problem.
On faster cpus (all 68040/60) it is necessary to wait some cycles after clearing the interrupt request registers to let the interrupt logic in the custom chips clear the interrupt lines to the cpu. Otherwise after the interrupt handler is quitting the interrupt is caused immediately again because the custom chips still indicate the interrupt. Then when the interrupt handler checks the reason for interrupt there is none -> spurious.

-- 
bert