On 10/7/07 14:12, "Tian, Kevin" <kevin.tian@xxxxxxxxx> wrote:
> Seems that I misunderstood your question. Normally such information
> is described in ICH spec and I didn't see VMX related warn by far for
> deep C states. Some deep C state is described with implicit cache flush
> which, I assume, also applies to the internal VMCS cache too. Or else
> all the side effects will be explicitly described such as LAPIC timer stop
> in some deep state. In that case, software needs to tackle that effect
> correspondingly.
Okay.
Anyway, back to your patch 3/10. With a view to cleanly adding VMXOFF on
suspend, and to allow efficient VMCLEARing if we need it in future, e.g.,
for deep-C states, I think you should change the suspend_domain() hook into
suspend_cpu():
 1. This is then symmetric with the resume_cpu() hook.
 2. It's a natural place to put VMXOFF (unlike suspend_domain()).
Of course, the question then is: how do you find the active VMCS's that need
clearing? I suggest you add a list_head to arch_vmx_struct, have a per-cpu
list of active VMCS's, enqueue on vmx_load_vmcs() and dequeue on
__vmx_clear_vmcs().
Could you revise patch 3/10 and resend, please?
 -- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel