Re: [PATCH 1/1] mm: unify pmd_free() implementation

[James Bottomley]

On Mon, 2008-07-28 at 08:53 -0700, Linus Torvalds wrote:
> But this is horrible, because it forces a totally unnecessary function 
> call for that empty function.
> 
> Yeah, the function will be cheap, but the call itself will not be (it's a 
> C language barrier and basically disables optimizations around it, causing 
> thigns like register spill/reload for no good reason).

Are you sure about this (the barrier)?  We've been struggling to find a
paradigm for our trace points but the consensus seemed to be that
compiler barriers were pretty tiny perturbations in the optimiser stream
(they affect calculation ordering, but not usually enough to be
noticed).  The register spills to get known locations for the tracepoint
variables seemed to be the much more expensive thing.

If this basic assumption is wrong, we need to know now ...

James


--
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/