RE: [Xen-devel] [PATCH] support protected mode mmio with non-zero CS base

["Jan Beulich" <jbeulich@xxxxxxxxxx>]

>Yes, but it's also possibly incorrect if the machine is in "big
>realmode", which is an entirely valid way to run code in x86 processors,
>and I think it's better to fix it "properly" than to have to fix it
>again when someone finds another fault in the code, because someone
>wrote some code differently. 

I meanwhile got convinced by Keir that this is indeed the better way.

>The next problem will of course be that data-fetches where the segment
>base is non-zero. I think the only case where that is likely to happen
>in mmio is for MOVS instructions, as everything else is presumably using
>the faulting address to know where the MMIO address is. But I'm OK with
>not fixing this right now. 

I intend to, and I suppose I'll find more places. The base address use is
only one part for string instructions - the more involved (or perhaps better
the one causing more overhead) is that for repeated ones, we'll now have
to do limit checks, as the CPU will have checked only the first item.

Jan

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel