Re: [RFC][Patch v12 1/2] mm: page_reporting: core infrastructure

[Nitesh Narayan Lal <nitesh@redhat.com>]

On 8/12/19 4:04 PM, Nitesh Narayan Lal wrote:
> On 8/12/19 2:47 PM, Alexander Duyck wrote:
>> On Mon, Aug 12, 2019 at 6:13 AM Nitesh Narayan Lal <nitesh@redhat.com> wrote:
>>> This patch introduces the core infrastructure for free page reporting in
>>> virtual environments. It enables the kernel to track the free pages which
>>> can be reported to its hypervisor so that the hypervisor could
>>> free and reuse that memory as per its requirement.
>>>
>>> While the pages are getting processed in the hypervisor (e.g.,
>>> via MADV_DONTNEED), the guest must not use them, otherwise, data loss
>>> would be possible. To avoid such a situation, these pages are
>>> temporarily removed from the buddy. The amount of pages removed
>>> temporarily from the buddy is governed by the backend(virtio-balloon
>>> in our case).
>>>
>>> To efficiently identify free pages that can to be reported to the
>>> hypervisor, bitmaps in a coarse granularity are used. Only fairly big
>>> chunks are reported to the hypervisor - especially, to not break up THP
>>> in the hypervisor - "MAX_ORDER - 2" on x86, and to save space. The bits
>>> in the bitmap are an indication whether a page *might* be free, not a
>>> guarantee. A new hook after buddy merging sets the bits.
>>>
>>> Bitmaps are stored per zone, protected by the zone lock. A workqueue
>>> asynchronously processes the bitmaps, trying to isolate and report pages
>>> that are still free. The backend (virtio-balloon) is responsible for
>>> reporting these batched pages to the host synchronously. Once reporting/
>>> freeing is complete, isolated pages are returned back to the buddy.
>>>
>>> Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
>> So if I understand correctly the hotplug support for this is still not
>> included correct? 
>
> That is correct, I have it as an ongoing-item in my cover-email.
> In case, we decide to go with this approach do you think it is a blocker?

I am planning to defer memory hotplug/hotremove support for the future. Due to
following reasons:
* I would like to first get a basic framework ready and merged (in case we
  decide to go ahead with this approach) and then build on top of it.
* Memory hotplug/hotremove is not a primary use case in our mind right now and
  hence I am not considering this as a blocker for the first step.

Following are the items which I intend to address before my next submission:
* Use zone flag and reference counter to track the number of zones requesting
  page reporting.
* Move the bitmap and its respective fields into a structure whose rcu-protected
  pointer object is maintained on a per-zone basis.
* Pick Alexander's patch for page poisoning support and test them with my patch
  set. (@Alexander: I will keep your signed-off for these patches to indicate
  you are the original author, please do let me know there is a better way to
  give credit).
* Address other suggestions/comments received on v12.

Looking forward to any suggestions/comments.


[...]
> +
> +       /* assign the configuration object provided by the backend */
> +       rcu_assign_pointer(page_reporting_conf, phconf);
> +
> +out:
> +       mutex_unlock(&page_reporting_mutex);
> +       return ret;
> +}
> +EXPORT_SYMBOL_GPL(page_reporting_enable);
> --
> 2.21.0
>
-- 
Thanks
Nitesh