RE: [Xen-ia64-devel]Question about priv_ptc_e

["Magenheimer, Dan (HP Labs Fort Collins)" <dan.magenheimer@xxxxxx>]

> Subject: RE: [Xen-ia64-devel]Question about priv_ptc_e
> 
> Dan,
> Thanks for your sharing,
> This will definitely help developers in community greatly.
> 
> I still have some questions.
> 
> >into a privileged instruction.  This meant I couldn't
> >always just use a "break" instruction.
> I don't understand this, is this because fc has a parameter?
> But I don't think it is a big deal.

Yes, I had forgotten about that.  FC has a parameter
so would require 128 different break immediate values
to encode the full set of possible FC instructions.

But it gets worse:  Several of the privileged instructions
(e.g. thash) have two parameters, a source and a destination
register.  Thus to fully encode all possible combinations
of each of these instructions into break would require
2**14 break immediate values.
 
> *     mov rx=ar.cflg -> mov ar.cflg=r(x+64) [**]
> Did you find linux kernel use ar.cflg?

I don't remember whether I included this for completeness
or if it was necessary if CONFIG_IA32_SUPPORT was
turned on (which never got implemented in Xen/ia64).

Dan

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel