>>> On 03.06.16 at 07:12, wrote:
>> From: Jan Beulich [mailto:jbeul...@suse.com]
>> Sent: Tuesday, May 31, 2016 7:52 PM
>> >>> On 31.05.16 at 12:22, wrote:
>> >> From: Jan Beulich [mailto:jbeul...@suse.com]
>> >> Sent: Friday, May 27, 2016 9:43 PM
>> >> >>>
> -Original Message-
> From: Jan Beulich [mailto:jbeul...@suse.com]
> Sent: Tuesday, May 31, 2016 7:52 PM
> To: Wu, Feng
> Cc: andrew.coop...@citrix.com; dario.faggi...@citrix.com;
> george.dun...@eu.citrix.com; Tian, Kevin ; xen-
>
>>> On 31.05.16 at 12:22, wrote:
>> From: Jan Beulich [mailto:jbeul...@suse.com]
>> Sent: Friday, May 27, 2016 9:43 PM
>> >>> On 26.05.16 at 15:39, wrote:
>> > --- a/xen/arch/x86/hvm/vmx/vmx.c
>> > +++ b/xen/arch/x86/hvm/vmx/vmx.c
>> > @@ -113,7 +113,19 @@
> -Original Message-
> From: Jan Beulich [mailto:jbeul...@suse.com]
> Sent: Friday, May 27, 2016 9:43 PM
> To: Wu, Feng
> Cc: andrew.coop...@citrix.com; dario.faggi...@citrix.com;
> george.dun...@eu.citrix.com; Tian, Kevin ; xen-
>
>>> On 26.05.16 at 15:39, wrote:
> --- a/xen/arch/x86/hvm/vmx/vmx.c
> +++ b/xen/arch/x86/hvm/vmx/vmx.c
> @@ -113,7 +113,19 @@ static void vmx_vcpu_block(struct vcpu *v)
> _cpu(vmx_pi_blocking, v->processor).lock;
> struct pi_desc *pi_desc =
This patch handles some concern case when the last assigned device
is removed from the domain. In this case we should carefully handle
pi descriptor and the per-cpu blocking list, to make sure:
- all the PI descriptor are in the right state when next time a
devices is assigned to the domain again.