Re: [PATCH 02/16] perf: Unified API to record selective sets of arch registers

[Jiri Olsa <jolsa@redhat.com>]

On Wed, May 02, 2012 at 04:46:33PM +0200, Stephane Eranian wrote:
> On Wed, May 2, 2012 at 2:58 PM, Jiri Olsa <jolsa@redhat.com> wrote:
> >
> > SNIP
> >
> >> >
> >> > I just sent v3, with changed design to be more generic, please check
> >> >
> >> > anyway, currently there's no way to mix 32 and 64 bit registers in sample.
> >> >
> >> > As I mentioned above, once running compat task, 64 bit registers
> >> > are stored anyway. Given that all 32 bit registers have 64 equiv.
> >> > you can ask to store RAX|RBX|R15.
> >> >
> >> Well, R8-R15 do not exist in 32-bit mode. So I wonder what is saved
> >> on the stack for those, probably nothing. And in that case, how do you
> >> handle the case where the user asked for R15 but it is not available and
> >> you know that only on PMU interrupt.
> >
> > right, R8-R15 do not exist in 32 bit mode, meaning that the 32 bit task
> > do not use them... but when you enter 64 bit kernel from 32 bit compat
> > task, still 64bits registers are saved.. as for native 64 process,
> 
> I am confused by your term '64-bit registers' here. I assume you
> mean registers are saved as 64-bit integers. But that does not means
> that the full set of 64-bit registers (incl. R8-R15) is saved. Unless
same set as for 64 bit tasks.. it's not allways full as I described
in previous email

> you're telling
> me that whatever values are in those 64-bit ABI only registers are thus saved
> on the stack.
yep, thats what I see in arch/x86/ia32/ia32entry.S

jirka