We want to expose the pvclock shared memory areas, which
the hypervisor periodically updates, to userspace.
For a linear mapping from userspace, it is necessary that
entire page sized regions are used for array of pvclock
structures.
There is no such guarantee with per cpu areas, therefore move
On 11/16/2012 06:07 AM, Marcelo Tosatti wrote:
>
> We want to expose the pvclock shared memory areas, which
> the hypervisor periodically updates, to userspace.
>
> For a linear mapping from userspace, it is necessary that
> entire page sized regions are used for array of pvclock
> structures.
We want to expose the pvclock shared memory areas, which
the hypervisor periodically updates, to userspace.
For a linear mapping from userspace, it is necessary that
entire page sized regions are used for array of pvclock
structures.
There is no such guarantee with per cpu areas, therefore mov
On 11/15/2012 04:08 AM, Marcelo Tosatti wrote:
> We want to expose the pvclock shared memory areas, which
> the hypervisor periodically updates, to userspace.
>
> For a linear mapping from userspace, it is necessary that
> entire page sized regions are used for array of pvclock
> structures.
>
We want to expose the pvclock shared memory areas, which
the hypervisor periodically updates, to userspace.
For a linear mapping from userspace, it is necessary that
entire page sized regions are used for array of pvclock
structures.
There is no such guarantee with per cpu areas, therefore move