Re: [patch] x86, voyager: fix ioremap_nocache()

["H. Peter Anvin" <hpa@zytor.com>]

Jeff Garzik wrote:
> 
> Isn't there Yet More Breakage in lib/iomap.c, given these new semantics?
> 
>         if (flags & IORESOURCE_MEM) {
>                 if (flags & IORESOURCE_CACHEABLE)
>                         return ioremap(start, len);
>                 return ioremap_nocache(start, len);
>         }
> 
> Any driver using pci_iomap() (libata, and others) is affected.
> 
> I disagree with this semantics change.  A number of code places _and 
> drivers_ GET IT RIGHT, and these are all broken now?
> 

They don't, though.  They rely on the MTRRs to get it right for them, 
and the MTRRs will say "uncached" in nearly all cases.

Consider the case above: you would have gotten the same result 
*regardless*, because the MTRRs would not have made the memory 
cacheable.  Yes, it's broken, but it was broken before as well.

	-hpa