On 2021/1/27 22:21, Alex Williamson wrote:
> On Wed, 27 Jan 2021 19:27:35 +0800
> Shenming Lu wrote:
>
>> On 2021/1/27 5:36, Alex Williamson wrote:
>>> On Wed, 9 Dec 2020 16:09:19 +0800
>>> Shenming Lu wrote:
>>>
Different from the normal situation when the guest starts, we can
On Wed, 27 Jan 2021 19:27:35 +0800
Shenming Lu wrote:
> On 2021/1/27 5:36, Alex Williamson wrote:
> > On Wed, 9 Dec 2020 16:09:19 +0800
> > Shenming Lu wrote:
> >
> >> Different from the normal situation when the guest starts, we can
> >> know the max unmasked vetctor (at the beginning)
On 2021/1/27 5:36, Alex Williamson wrote:
> On Wed, 9 Dec 2020 16:09:19 +0800
> Shenming Lu wrote:
>
>> Different from the normal situation when the guest starts, we can
>> know the max unmasked vetctor (at the beginning) after msix_load()
>> in VFIO migration. So in order to avoid ineffectively
On Wed, 9 Dec 2020 16:09:19 +0800
Shenming Lu wrote:
> Different from the normal situation when the guest starts, we can
> know the max unmasked vetctor (at the beginning) after msix_load()
> in VFIO migration. So in order to avoid ineffectively disabling and
s/ineffectively/inefficiently/?
Different from the normal situation when the guest starts, we can
know the max unmasked vetctor (at the beginning) after msix_load()
in VFIO migration. So in order to avoid ineffectively disabling and
enabling vectors repeatedly, let's allocate all needed vectors first
and then enable these