Re: problem with cache flush routine for G5?

[Segher Boessenkool]

> After doing some digging in the 970fx specs, it seems that we may not 
> need to explicitly force a store of the L1 dcache at all.  According 
> to the docs, the L1 dcache is unconditionally store-through. Thus, for 
> a brute-force implementation we should be able to just invalidate the 
> whole icache, do the appropriate sync/isync, and it should pick up the 
> changed instructions from the L2 cache.  Do you see any problems with 
> this?  Do I actually still need the store?

You need a  sync  instruction before the instruction cache invalidate,
to make sure all stores to L2 have completed.

I don't know which "970fx specs" you mean, but if it's the programming
manual, it should tell you how to invalidate the entire instruction
cache (and how to flush the L2 cache, if you really must.  But just 
don't).


Segher

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/