Re: [patch] x86: improved memory barrier implementation
From: Alan Cox
Date: Fri Sep 28 2007 - 13:13:07 EST
> on the broken ppro stores config option if you just tell me what should
> be there (again, remember that my patch isn't actually changing anything
> already there except for smp_rmb side).
The PPro needs rmb to ensure a store doesn't go for a walk on the wild
side and pass the read especially when we are dealing with device space.
The rest of the stuff is a little vague which makes me nervous when
considering relaxing the PPro case for smp_rmb. With smp_rmb as it is at
the moment the PPro is effectively treated as an out of order cpu and so
shouldn't hit anything occassionally that a PPC wouldn't hit every time.
> > - and for modern processors its still not remotely clear your patch is
> > correct because of NT stores.
> No. We already _have_ to rely on this model for barriers
Well Linus has dealt with the question of NT stores for us now...
Given this isn't an issue on 64bit I'm inclined to argue that only 64bit
behaviour should be changed at this point.
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/