Re: [RFC][Patch v12 2/2] virtio-balloon: interface to support free page reporting

From: Nitesh Narayan Lal
Date: Wed Aug 14 2019 - 10:01:52 EST



On 8/14/19 9:42 AM, Cornelia Huck wrote:
> On Wed, 14 Aug 2019 07:47:40 -0400
> Nitesh Narayan Lal <nitesh@xxxxxxxxxx> wrote:
>
>> On 8/14/19 6:29 AM, Cornelia Huck wrote:
>>> On Mon, 12 Aug 2019 09:12:35 -0400
>>> Nitesh Narayan Lal <nitesh@xxxxxxxxxx> wrote:
>>>
>>>> Enables the kernel to negotiate VIRTIO_BALLOON_F_REPORTING feature with
>>>> the host. If it is available and page_reporting_flag is set to true,
>>>> page_reporting is enabled and its callback is configured along with
>>>> the max_pages count which indicates the maximum number of pages that
>>>> can be isolated and reported at a time. Currently, only free pages of
>>>> order >= (MAX_ORDER - 2) are reported. To prevent any false OOM
>>>> max_pages count is set to 16.
>>>>
>>>> By default page_reporting feature is enabled and gets loaded as soon
>>>> as the virtio-balloon driver is loaded. However, it could be disabled
>>>> by writing the page_reporting_flag which is a virtio-balloon parameter.
>>>>
>>>> Signed-off-by: Nitesh Narayan Lal <nitesh@xxxxxxxxxx>
>>>> ---
>>>> drivers/virtio/Kconfig | 1 +
>>>> drivers/virtio/virtio_balloon.c | 64 ++++++++++++++++++++++++++++-
>>>> include/uapi/linux/virtio_balloon.h | 1 +
>>>> 3 files changed, 65 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
>>>> index 226fbb995fb0..defec00d4ee2 100644
>>>> --- a/drivers/virtio/virtio_balloon.c
>>>> +++ b/drivers/virtio/virtio_balloon.c
>>> (...)
>>>
>>>> +static void virtballoon_page_reporting_setup(struct virtio_balloon *vb)
>>>> +{
>>>> + struct device *dev = &vb->vdev->dev;
>>>> + int err;
>>>> +
>>>> + vb->page_reporting_conf.report = virtballoon_report_pages;
>>>> + vb->page_reporting_conf.max_pages = PAGE_REPORTING_MAX_PAGES;
>>>> + err = page_reporting_enable(&vb->page_reporting_conf);
>>>> + if (err < 0) {
>>>> + dev_err(dev, "Failed to enable reporting, err = %d\n", err);
>>>> + page_reporting_flag = false;
>>> Should we clear the feature bit in this case as well?
>> I think yes.
> Eww, I didn't recall that we don't call the ->probe callback until
> after feature negotiation has finished, so scratch that particular idea.
>
> For what reasons may page_reporting_enable() fail?

If the guest is low in memory and some allocation required for page reporting
setup fails.

> Does it make sense
> to fail probing the device in that case? And does it make sense to
> re-try later (i.e. leave page_reporting_flag set)?


Re-trying to setup page reporting will mean that virtballoon_probe has to be
called again.
For which the driver has to be re-loaded, isn't?

>
>> If I am not wrong then in a case where page reporting setup fails for some
>> reason and at a later point the user wants to re-enable it then for that balloon
>> driver has to be reloaded.
>> Which would mean re-negotiation of the feature bit.
> Re-negotiation actually already happens if a driver is unbound and
> rebound.
>
>>>
>>>> + vb->page_reporting_conf.report = NULL;
>>>> + vb->page_reporting_conf.max_pages = 0;
>>>> + return;
>>>> + }
>>>> +}
>>>> +
>>>> static void set_page_pfns(struct virtio_balloon *vb,
>>>> __virtio32 pfns[], struct page *page)
>>>> {
>>>> @@ -476,6 +524,7 @@ static int init_vqs(struct virtio_balloon *vb)
>>>> names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
>>>> names[VIRTIO_BALLOON_VQ_STATS] = NULL;
>>>> names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
>>>> + names[VIRTIO_BALLOON_VQ_REPORTING] = NULL;
>>>>
>>>> if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
>>>> names[VIRTIO_BALLOON_VQ_STATS] = "stats";
>>>> @@ -487,11 +536,18 @@ static int init_vqs(struct virtio_balloon *vb)
>>>> callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
>>>> }
>>>>
>>>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
>>>> + names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq";
>>>> + callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack;
>>> Do we even want to try to set up the reporting queue if reporting has
>>> been disabled via module parameter? Might make more sense to not even
>>> negotiate the feature bit in that case.
>> True.
>> I think this should be replaced with something like (page_reporting_flag &&
>> virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)).
> Yes.
>
> Is page_reporting_flag supposed to be changeable on the fly?


Yes.

> The only
> way to really turn off the feature bit from the driver is to not pass
> in the feature in the features table; we could provide two different
> tables depending on the flag if it were static.

I did have a plan of moving to static keys eventually instead of using module
parameters for this purpose. :)
That way I will be able to just control the kernel side of things on the fly
without changing the balloon-page-reporting framework.
The objective is to allow the user to enable/disable page tracking on the fly.

>
>>>
>>>> + }
>>>> err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
>>>> vqs, callbacks, names, NULL, NULL);
>>>> if (err)
>>>> return err;
>>>>
>>>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
>>>> + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING];
>>>> +
>>>> vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE];
>>>> vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE];
>>>> if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
>>>> @@ -924,6 +980,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
>>>> if (err)
>>>> goto out_del_balloon_wq;
>>>> }
>>>> + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING) &&
>>>> + page_reporting_flag)
>>>> + virtballoon_page_reporting_setup(vb);
>>> In that case, you'd only need to check for the feature bit here.
>> Why is that?
>> I think both the checks should be present here as we need both the conditions to
>> be true to enable page reporting.
> Yeah, because we can't clear the feature bit if the flag is not set.


+1

>
>> However, the order should be reversed because of the reason you mentioned earlier.
>>
>>>
>>>> virtio_device_ready(vdev);
>>>>
>>>> if (towards_target(vb))
--
Thanks
Nitesh