AW: RE: RE: No C-States any longer...

AW: RE: RE: No C-States any longer...

[Carsten Schiers]

I was faster, just build a new acpi_processor.ko that will report with a lot of
printks in drivers/acpi/processor_xen drivers/acpi/processor_idle as the stuff 
from drivers/xen/ simply isn't called. 

Not able to test it right now, because I don't want to do a remote reboot and find
my family anoyed when Internet and TV is not working ;o). 

I will check this afternoon when I am back from work.

Carsten.

----- Originalnachricht -----
Von: "Tian, Kevin" <kevin.tian@intel.com>
Gesendet: Fre, 10.6.2011 10:48
An: Carsten Schiers <carsten@schiers.de> ; xen-devel <xen-devel@lists.xensource.com>
Betreff: RE: RE: RE: [Xen-devel] No C-States any longer...

> From: Carsten Schiers [mailto:carsten@schiers.de]
> Sent: Friday, June 10, 2011 3:09 AM
> 
> Through some adding of printk I was able at least to verify that for my
> 3 core CPU AMD Athlon X3 400e
> 
>   - xen_px_notifier is called six times
>   - Hypervisor is reporting XEN_PM_PX is called six times
>   - Hypervisor is never reporting XEN_PM_CX to have been called
>   - this is because xen_cx_notifier is never called.
>   -> set_cx_pminfo is never called.
> 
> What I will try to find out next is to check where xen_cx_notifier
> *should* be called. OS debugging is
> not realy my expertise, let's see whether you first can give me a hint
> or whether I am quicker to find
> it on my own.
> 

the entry point in dom0 looks like:

xen_acpi_processor_start
    xen_acpi_processor_power_init
        processor_cntl_xen_notify
            xen_ops.pm_ops
                xen_cx_notifier
                    HYPERVISOR_dom0_op

Thanks
Kevin

RE: RE: No C-States any longer...

[Tian, Kevin]

> From: Carsten Schiers [mailto:carsten@schiers.de]
> Sent: Thursday, June 09, 2011 12:05 PM
> 
> > to verify BIOS problem, you could run a native Linux to verify.
> 
> I can tell you that it worked with the old Xenified 2.6.18 kernel.

Then possibly some patches get lost in your current env...

> 
> > This looks strange. At least C1 should be available. You may check
> Xen/dom0
> > log to see any error there, or manually add some printk in
> set_cx_pminfo to
> > see any error there.
> 
> I check tonight. Does it make sense also to turn debug info on for Dom0
> acpi?
> 

You can have a try though I don't think that gives much hint because
basic ACPI logic doesn't change in Dom0. The more interesting thing is
about the gear logic between dom0 and Xen. Does the dom0 notify
Xen on earth? Is there some condition making Xen reject the call? ...

Thanks
Kevin

AW: RE: RE: No C-States any longer...

[Carsten Schiers]

Through some adding of printk I was able at least to verify that for my 
3 core CPU AMD Athlon X3 400e

  - xen_px_notifier is called six times
  - Hypervisor is reporting XEN_PM_PX is called six times
  - Hypervisor is never reporting XEN_PM_CX to have been called
  - this is because xen_cx_notifier is never called.
  -> set_cx_pminfo is never called.

What I will try to find out next is to check where xen_cx_notifier 
*should* be called. OS debugging is 
not realy my expertise, let's see whether you first can give me a hint 
or whether I am quicker to find 
it on my own.

Carsten.


-----Ursprüngliche Nachricht-----
Von: Tian, Kevin [mailto:kevin.tian@intel.com] 
Gesendet: Donnerstag, 9. Juni 2011 06:19
An: Carsten Schiers; xen-devel
Betreff: RE: RE: [Xen-devel] No C-States any longer...

> From: Carsten Schiers [mailto:carsten@schiers.de]
> Sent: Thursday, June 09, 2011 12:05 PM
> 
> > to verify BIOS problem, you could run a native Linux to verify.
> 
> I can tell you that it worked with the old Xenified 2.6.18 kernel.

Then possibly some patches get lost in your current env...

> 
> > This looks strange. At least C1 should be available. You may check
> Xen/dom0
> > log to see any error there, or manually add some printk in
> set_cx_pminfo to
> > see any error there.
> 
> I check tonight. Does it make sense also to turn debug info on for 
Dom0
> acpi?
> 

You can have a try though I don't think that gives much hint because
basic ACPI logic doesn't change in Dom0. The more interesting thing is
about the gear logic between dom0 and Xen. Does the dom0 notify
Xen on earth? Is there some condition making Xen reject the call? ...

Thanks
Kevin

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