Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-03 Thread Amit Shah
* Avi Kivity wrote: > Amit Shah wrote: > > * Anthony Liguori wrote: > >   > > > >> Amit Shah wrote: > >>     > >> > >> What are you using to issue the hypercall? > >>     > > > > +       r = kvm_hypercall1(KVM_PV_PCI_DEVICE, page_gfn); > > > > Setup is done by: > > > > +       if (!kvm_para_availab

Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-03 Thread Avi Kivity
Amit Shah wrote: * Anthony Liguori wrote: Amit Shah wrote: * Anthony Liguori wrote: This patch refactors the current hypercall infrastructure to better support live migration and SMP. It eliminates the hypercall page by trapping the UD exception that would occur if you used

Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-03 Thread Amit Shah
* Anthony Liguori wrote: > Amit Shah wrote: > > * Anthony Liguori wrote: > >   > > > >> This patch refactors the current hypercall infrastructure to better > >> support live migration and SMP.  It eliminates the hypercall page by > >> trapping the UD exception that would occur if you used the wrong

Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-02 Thread Anthony Liguori
Amit Shah wrote: * Anthony Liguori wrote: This patch refactors the current hypercall infrastructure to better support live migration and SMP. It eliminates the hypercall page by trapping the UD exception that would occur if you used the wrong hypercall instruction for the underlying architec

Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-02 Thread Avi Kivity
Amit Shah wrote: * Anthony Liguori wrote: This patch refactors the current hypercall infrastructure to better support live migration and SMP. It eliminates the hypercall page by trapping the UD exception that would occur if you used the wrong hypercall instruction for the underlying architec

Re: [kvm-devel] [PATCH] Refactor hypercall infrastructure (v2)

2007-12-02 Thread Amit Shah
* Anthony Liguori wrote: > This patch refactors the current hypercall infrastructure to better support > live migration and SMP. It eliminates the hypercall page by trapping the > UD exception that would occur if you used the wrong hypercall instruction > for the underlying architecture and replac