diff mbox

[v25,2/2] virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT

Message ID 1516871646-22741-3-git-send-email-wei.w.wang@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Wang, Wei W Jan. 25, 2018, 9:14 a.m. UTC
Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
support of reporting hints of guest free pages to host via virtio-balloon.

Host requests the guest to report free pages by sending a new cmd
id to the guest via the free_page_report_cmd_id configuration register.

When the guest starts to report, the first element added to the free page
vq is the cmd id given by host. When the guest finishes the reporting
of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
to the vq to tell host that the reporting is done. Host may also requests
the guest to stop the reporting in advance by sending the stop cmd id to
the guest via the configuration register.

Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
---
 drivers/virtio/virtio_balloon.c     | 251 ++++++++++++++++++++++++++++++------
 include/uapi/linux/virtio_balloon.h |   7 +
 2 files changed, 222 insertions(+), 36 deletions(-)

Comments

Michael S. Tsirkin Jan. 25, 2018, 1:49 p.m. UTC | #1
On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
> Negotiation of the VIRTIO_BALLOON_F_FREE_PAGE_HINT feature indicates the
> support of reporting hints of guest free pages to host via virtio-balloon.
> 
> Host requests the guest to report free pages by sending a new cmd
> id to the guest via the free_page_report_cmd_id configuration register.
> 
> When the guest starts to report, the first element added to the free page
> vq is the cmd id given by host. When the guest finishes the reporting
> of all the free pages, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID is added
> to the vq to tell host that the reporting is done. Host may also requests
> the guest to stop the reporting in advance by sending the stop cmd id to
> the guest via the configuration register.
> 
> Signed-off-by: Wei Wang <wei.w.wang@intel.com>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> ---
>  drivers/virtio/virtio_balloon.c     | 251 ++++++++++++++++++++++++++++++------
>  include/uapi/linux/virtio_balloon.h |   7 +
>  2 files changed, 222 insertions(+), 36 deletions(-)
> 
> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
> index a1fb52c..114985b 100644
> --- a/drivers/virtio/virtio_balloon.c
> +++ b/drivers/virtio/virtio_balloon.c
> @@ -51,9 +51,22 @@ MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
>  static struct vfsmount *balloon_mnt;
>  #endif
>  
> +enum virtio_balloon_vq {
> +	VIRTIO_BALLOON_VQ_INFLATE,
> +	VIRTIO_BALLOON_VQ_DEFLATE,
> +	VIRTIO_BALLOON_VQ_STATS,
> +	VIRTIO_BALLOON_VQ_FREE_PAGE,
> +	VIRTIO_BALLOON_VQ_MAX
> +};
> +
>  struct virtio_balloon {
>  	struct virtio_device *vdev;
> -	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
> +	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
> +
> +	/* Balloon's own wq for cpu-intensive work items */
> +	struct workqueue_struct *balloon_wq;
> +	/* The free page reporting work item submitted to the balloon wq */
> +	struct work_struct report_free_page_work;
>  
>  	/* The balloon servicing is delegated to a freezable workqueue. */
>  	struct work_struct update_balloon_stats_work;
> @@ -63,6 +76,11 @@ struct virtio_balloon {
>  	spinlock_t stop_update_lock;
>  	bool stop_update;
>  
> +	/* The new cmd id received from host */
> +	uint32_t cmd_id_received;
> +	/* The cmd id that is in use */
> +	__virtio32 cmd_id_use;
> +
>  	/* Waiting for host to ack the pages we released. */
>  	wait_queue_head_t acked;
>  
> @@ -316,17 +334,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
>  	virtqueue_kick(vq);
>  }
>  
> -static void virtballoon_changed(struct virtio_device *vdev)
> -{
> -	struct virtio_balloon *vb = vdev->priv;
> -	unsigned long flags;
> -
> -	spin_lock_irqsave(&vb->stop_update_lock, flags);
> -	if (!vb->stop_update)
> -		queue_work(system_freezable_wq, &vb->update_balloon_size_work);
> -	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> -}
> -
>  static inline s64 towards_target(struct virtio_balloon *vb)
>  {
>  	s64 target;
> @@ -343,6 +350,34 @@ static inline s64 towards_target(struct virtio_balloon *vb)
>  	return target - vb->num_pages;
>  }
>  
> +static void virtballoon_changed(struct virtio_device *vdev)
> +{
> +	struct virtio_balloon *vb = vdev->priv;
> +	unsigned long flags;
> +	s64 diff = towards_target(vb);
> +
> +	if (diff) {
> +		spin_lock_irqsave(&vb->stop_update_lock, flags);
> +		if (!vb->stop_update)
> +			queue_work(system_freezable_wq,
> +				   &vb->update_balloon_size_work);
> +		spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> +	}
> +
> +	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> +		virtio_cread(vdev, struct virtio_balloon_config,
> +			     free_page_report_cmd_id, &vb->cmd_id_received);
> +		if (vb->cmd_id_received !=
> +		    VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
> +			spin_lock_irqsave(&vb->stop_update_lock, flags);
> +			if (!vb->stop_update)
> +				queue_work(vb->balloon_wq,
> +					   &vb->report_free_page_work);
> +			spin_unlock_irqrestore(&vb->stop_update_lock, flags);
> +		}
> +	}
> +}
> +
>  static void update_balloon_size(struct virtio_balloon *vb)
>  {
>  	u32 actual = vb->num_pages;
> @@ -417,42 +452,151 @@ static void update_balloon_size_func(struct work_struct *work)
>  
>  static int init_vqs(struct virtio_balloon *vb)
>  {
> -	struct virtqueue *vqs[3];
> -	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
> -	static const char * const names[] = { "inflate", "deflate", "stats" };
> -	int err, nvqs;
> +	struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
> +	vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
> +	const char *names[VIRTIO_BALLOON_VQ_MAX];
> +	struct scatterlist sg;
> +	int ret;
>  
>  	/*
> -	 * We expect two virtqueues: inflate and deflate, and
> -	 * optionally stat.
> +	 * Inflateq and deflateq are used unconditionally. The names[]
> +	 * will be NULL if the related feature is not enabled, which will
> +	 * cause no allocation for the corresponding virtqueue in find_vqs.
>  	 */
> -	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
> -	err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
> -	if (err)
> -		return err;
> +	callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
> +	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
> +	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
> +	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
> +	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
> +	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
>  
> -	vb->inflate_vq = vqs[0];
> -	vb->deflate_vq = vqs[1];
>  	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
> -		struct scatterlist sg;
> -		unsigned int num_stats;
> -		vb->stats_vq = vqs[2];
> +		names[VIRTIO_BALLOON_VQ_STATS] = "stats";
> +		callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
> +	}
> +
> +	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> +		names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
> +		callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
> +	}
> +
> +	ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
> +					 vqs, callbacks, names, NULL, NULL);
> +	if (ret)
> +		return ret;
>  
> +	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)) {
> +		vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
>  		/*
>  		 * Prime this virtqueue with one buffer so the hypervisor can
>  		 * use it to signal us later (it can't be broken yet!).
>  		 */
> -		num_stats = update_balloon_stats(vb);
> -
> -		sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
> -		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
> -		    < 0)
> -			BUG();
> +		sg_init_one(&sg, vb->stats, sizeof(vb->stats));
> +		ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
> +					   GFP_KERNEL);
> +		if (ret) {
> +			dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
> +				 __func__);
> +			return ret;
> +		}
>  		virtqueue_kick(vb->stats_vq);
>  	}
> +
> +	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
> +		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
> +
>  	return 0;
>  }
>  
> +static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
> +{
> +	struct scatterlist sg;
> +	unsigned int unused;
> +	int ret = 0;
> +
> +	sg_init_table(&sg, 1);
> +	sg_set_page(&sg, pfn_to_page(pfn), len, 0);
> +
> +	/* Detach all the used buffers from the vq */
> +	while (virtqueue_get_buf(vq, &unused))
> +		;
> +
> +	/*
> +	 * Since this is an optimization feature, losing a couple of free
> +	 * pages to report isn't important. We simply return without adding
> +	 * the page if the vq is full.
> +	 * We are adding one entry each time, which essentially results in no
> +	 * memory allocation, so the GFP_KERNEL flag below can be ignored.
> +	 * There is always one entry reserved for the cmd id to use.
> +	 */
> +	if (vq->num_free > 1)
> +		ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
> +
> +	if (vq->num_free == virtqueue_get_vring_size(vq) / 2 ||
> +	    vq->num_free <= 2)
> +		virtqueue_kick(vq);
> +
> +	return ret;
> +}
> +
> +static int virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
> +					   unsigned long nr_pages)
> +{
> +	struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
> +	uint32_t len = nr_pages << PAGE_SHIFT;
> +
> +	/*
> +	 * If a stop id or a new cmd id was just received from host, stop
> +	 * the reporting, and return 1 to indicate an active stop.
> +	 */
> +	if (virtio32_to_cpu(vb->vdev, vb->cmd_id_use) != vb->cmd_id_received)
> +		return 1;
> +
> +	return add_one_sg(vb->free_page_vq, pfn, len);
> +}
> +
> +static int send_cmd_id(struct virtio_balloon *vb, uint32_t cmd_id)
> +{
> +	struct scatterlist sg;
> +	struct virtqueue *vq = vb->free_page_vq;
> +	int ret;
> +
> +	vb->cmd_id_use = cpu_to_virtio32(vb->vdev, cmd_id);
> +	sg_init_one(&sg, &vb->cmd_id_use, sizeof(vb->cmd_id_use));
> +
> +	ret = virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
> +	virtqueue_kick(vq);
> +
> +	return ret;
> +}
> +
> +static void report_free_page_func(struct work_struct *work)
> +{
> +	struct virtio_balloon *vb;
> +	int ret;
> +
> +	vb = container_of(work, struct virtio_balloon, report_free_page_work);
> +
> +	/* Start by sending the received cmd id to host with an outbuf */
> +	ret = send_cmd_id(vb, vb->cmd_id_received);
> +	if (unlikely(ret))
> +		goto err;
> +
> +	ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
> +	if (unlikely(ret < 0))
> +		goto err;
> +
> +	/* End by sending a stop id to host with an outbuf */
> +	ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> +	if (likely(!ret))
> +		return;
> +err:
> +	dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
> +		__func__);
> +}
> +

So that's very simple, but it only works well if the whole
free list fits in the queue or host processes the queue faster
than the guest. What if it doesn't?
If we had restartability you could just drop the lock
and wait for a vq interrupt to make more progress, which
would be better I think.


>  #ifdef CONFIG_BALLOON_COMPACTION
>  /*
>   * virtballoon_migratepage - perform the balloon page migration on behalf of
> @@ -537,6 +681,7 @@ static struct file_system_type balloon_fs = {
>  static int virtballoon_probe(struct virtio_device *vdev)
>  {
>  	struct virtio_balloon *vb;
> +	__u32 poison_val;
>  	int err;
>  
>  	if (!vdev->config->get) {
> @@ -566,18 +711,39 @@ static int virtballoon_probe(struct virtio_device *vdev)
>  	if (err)
>  		goto out_free_vb;
>  
> +	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> +		/*
> +		 * There is always one entry reserved for cmd id, so the ring
> +		 * size needs to be at least two to report free page hint.
> +		 */
> +		if (virtqueue_get_vring_size(vb->free_page_vq) < 2)
> +			goto out_free_vb;
> +		vb->balloon_wq = alloc_workqueue("balloon-wq",
> +					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
> +		if (!vb->balloon_wq) {
> +			err = -ENOMEM;
> +			goto out_del_vqs;
> +		}
> +		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
> +		if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
> +			poison_val = PAGE_POISON;
> +			virtio_cwrite(vb->vdev, struct virtio_balloon_config,
> +				      poison_val, &poison_val);
> +		}
> +	}
> +
>  	vb->nb.notifier_call = virtballoon_oom_notify;
>  	vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
>  	err = register_oom_notifier(&vb->nb);
>  	if (err < 0)
> -		goto out_del_vqs;
> +		goto out_del_balloon_wq;
>  
>  #ifdef CONFIG_BALLOON_COMPACTION
>  	balloon_mnt = kern_mount(&balloon_fs);
>  	if (IS_ERR(balloon_mnt)) {
>  		err = PTR_ERR(balloon_mnt);
>  		unregister_oom_notifier(&vb->nb);
> -		goto out_del_vqs;
> +		goto out_del_balloon_wq;
>  	}
>  
>  	vb->vb_dev_info.migratepage = virtballoon_migratepage;
> @@ -587,7 +753,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
>  		kern_unmount(balloon_mnt);
>  		unregister_oom_notifier(&vb->nb);
>  		vb->vb_dev_info.inode = NULL;
> -		goto out_del_vqs;
> +		goto out_del_balloon_wq;
>  	}
>  	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
>  #endif
> @@ -598,6 +764,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
>  		virtballoon_changed(vdev);
>  	return 0;
>  
> +out_del_balloon_wq:
> +	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
> +		destroy_workqueue(vb->balloon_wq);
>  out_del_vqs:
>  	vdev->config->del_vqs(vdev);
>  out_free_vb:
> @@ -631,6 +800,11 @@ static void virtballoon_remove(struct virtio_device *vdev)
>  	cancel_work_sync(&vb->update_balloon_size_work);
>  	cancel_work_sync(&vb->update_balloon_stats_work);
>  
> +	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
> +		cancel_work_sync(&vb->report_free_page_work);
> +		destroy_workqueue(vb->balloon_wq);
> +	}
> +
>  	remove_common(vb);
>  #ifdef CONFIG_BALLOON_COMPACTION
>  	if (vb->vb_dev_info.inode)
> @@ -674,6 +848,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
>  
>  static int virtballoon_validate(struct virtio_device *vdev)
>  {
> +	if (!page_poisoning_enabled())
> +		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
> +
>  	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
>  	return 0;
>  }
> @@ -682,6 +859,8 @@ static unsigned int features[] = {
>  	VIRTIO_BALLOON_F_MUST_TELL_HOST,
>  	VIRTIO_BALLOON_F_STATS_VQ,
>  	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
> +	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
> +	VIRTIO_BALLOON_F_PAGE_POISON,
>  };
>  
>  static struct virtio_driver virtio_balloon_driver = {
> diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
> index 343d7dd..3f97067 100644
> --- a/include/uapi/linux/virtio_balloon.h
> +++ b/include/uapi/linux/virtio_balloon.h
> @@ -34,15 +34,22 @@
>  #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
>  #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
>  #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
> +#define VIRTIO_BALLOON_F_FREE_PAGE_HINT	3 /* VQ to report free pages */
> +#define VIRTIO_BALLOON_F_PAGE_POISON	4 /* Guest is using page poisoning */
>  
>  /* Size of a PFN in the balloon interface. */
>  #define VIRTIO_BALLOON_PFN_SHIFT 12
>  
> +#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID		0
>  struct virtio_balloon_config {
>  	/* Number of pages host wants Guest to give up. */
>  	__u32 num_pages;
>  	/* Number of pages we've actually got in balloon. */
>  	__u32 actual;
> +	/* Free page report command id, readonly by guest */
> +	__u32 free_page_report_cmd_id;
> +	/* Stores PAGE_POISON if page poisoning is in use */
> +	__u32 poison_val;
>  };
>  
>  #define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */
> -- 
> 2.7.4
Wang, Wei W Jan. 26, 2018, 1:40 a.m. UTC | #2
On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
> On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
>> +
>> +static void report_free_page_func(struct work_struct *work)
>> +{
>> +	struct virtio_balloon *vb;
>> +	int ret;
>> +
>> +	vb = container_of(work, struct virtio_balloon, report_free_page_work);
>> +
>> +	/* Start by sending the received cmd id to host with an outbuf */
>> +	ret = send_cmd_id(vb, vb->cmd_id_received);
>> +	if (unlikely(ret))
>> +		goto err;
>> +
>> +	ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
>> +	if (unlikely(ret < 0))
>> +		goto err;
>> +
>> +	/* End by sending a stop id to host with an outbuf */
>> +	ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
>> +	if (likely(!ret))
>> +		return;
>> +err:
>> +	dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
>> +		__func__);
>> +}
>> +
> So that's very simple, but it only works well if the whole
> free list fits in the queue or host processes the queue faster
> than the guest. What if it doesn't?

This is the case that the virtqueue gets full, and I think we've agreed 
that this is an optimization feature and losing some hints to report 
isn't important, right?

Actually, in the tests, there is no chance to see the ring is full. If 
we check the host patches that were shared before, the device side 
operation is quite simple, it just clears the related bits from the 
bitmap, and then continues to take entries from the virtqueue till the 
virtqueue gets empty.


> If we had restartability you could just drop the lock
> and wait for a vq interrupt to make more progress, which
> would be better I think.
>

Restartability means that caller needs to record the state where it was 
when it stopped last time. The controversy is that the free list is not 
static once the lock is dropped, so everything is dynamically changing, 
including the state that was recorded. The method we are using is more 
prudent, IMHO. How about taking the fundamental solution, and seek to 
improve incrementally in the future?


Best,
Wei
Michael S. Tsirkin Jan. 26, 2018, 2:42 a.m. UTC | #3
On Fri, Jan 26, 2018 at 09:40:44AM +0800, Wei Wang wrote:
> On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
> > On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
> > > +
> > > +static void report_free_page_func(struct work_struct *work)
> > > +{
> > > +	struct virtio_balloon *vb;
> > > +	int ret;
> > > +
> > > +	vb = container_of(work, struct virtio_balloon, report_free_page_work);
> > > +
> > > +	/* Start by sending the received cmd id to host with an outbuf */
> > > +	ret = send_cmd_id(vb, vb->cmd_id_received);
> > > +	if (unlikely(ret))
> > > +		goto err;
> > > +
> > > +	ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
> > > +	if (unlikely(ret < 0))
> > > +		goto err;
> > > +
> > > +	/* End by sending a stop id to host with an outbuf */
> > > +	ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
> > > +	if (likely(!ret))
> > > +		return;
> > > +err:
> > > +	dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
> > > +		__func__);
> > > +}
> > > +
> > So that's very simple, but it only works well if the whole
> > free list fits in the queue or host processes the queue faster
> > than the guest. What if it doesn't?
> 
> This is the case that the virtqueue gets full, and I think we've agreed that
> this is an optimization feature and losing some hints to report isn't
> important, right?
> 
> Actually, in the tests, there is no chance to see the ring is full. If we
> check the host patches that were shared before, the device side operation is
> quite simple, it just clears the related bits from the bitmap, and then
> continues to take entries from the virtqueue till the virtqueue gets empty.
> 
> 
> > If we had restartability you could just drop the lock
> > and wait for a vq interrupt to make more progress, which
> > would be better I think.
> > 
> 
> Restartability means that caller needs to record the state where it was when
> it stopped last time.

See my comment on the mm patch: if you rotate the previously reported
pages towards the end, then you mostly get restartability for free,
if only per zone.
The only thing remaining will be stopping at a page you already reported.

There aren't many zones so restartability wrt zones is kind of
trivial.

> The controversy is that the free list is not static
> once the lock is dropped, so everything is dynamically changing, including
> the state that was recorded. The method we are using is more prudent, IMHO.
> How about taking the fundamental solution, and seek to improve incrementally
> in the future?
> 
> 
> Best,
> Wei

I'd like to see kicks happen outside the spinlock. kick with a spinlock
taken looks like a scalability issue that won't be easy to
reproduce but hurt workloads at random unexpected times.
Wang, Wei W Jan. 26, 2018, 3:31 a.m. UTC | #4
On 01/26/2018 10:42 AM, Michael S. Tsirkin wrote:
> On Fri, Jan 26, 2018 at 09:40:44AM +0800, Wei Wang wrote:
>> On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
>>> On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
>>>

>> The controversy is that the free list is not static
>> once the lock is dropped, so everything is dynamically changing, including
>> the state that was recorded. The method we are using is more prudent, IMHO.
>> How about taking the fundamental solution, and seek to improve incrementally
>> in the future?
>>
>>
>> Best,
>> Wei
> I'd like to see kicks happen outside the spinlock. kick with a spinlock
> taken looks like a scalability issue that won't be easy to
> reproduce but hurt workloads at random unexpected times.
>

Is that "kick inside the spinlock" the only concern you have? I think we 
can remove the kick actually. If we check how the host side works, it is 
worthwhile to let the host poll the virtqueue after it receives the cmd 
id from the guest (kick for cmd id isn't within the lock).


Best,
Wei
Tetsuo Handa Jan. 26, 2018, 1:35 p.m. UTC | #5
On 2018/01/26 12:31, Wei Wang wrote:
> On 01/26/2018 10:42 AM, Michael S. Tsirkin wrote:
>> On Fri, Jan 26, 2018 at 09:40:44AM +0800, Wei Wang wrote:
>>> On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
>>>> On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
>>>>
> 
>>> The controversy is that the free list is not static
>>> once the lock is dropped, so everything is dynamically changing, including
>>> the state that was recorded. The method we are using is more prudent, IMHO.
>>> How about taking the fundamental solution, and seek to improve incrementally
>>> in the future?
>>>
>>>
>>> Best,
>>> Wei
>> I'd like to see kicks happen outside the spinlock. kick with a spinlock
>> taken looks like a scalability issue that won't be easy to
>> reproduce but hurt workloads at random unexpected times.
>>
> 
> Is that "kick inside the spinlock" the only concern you have? I think we can remove the kick actually. If we check how the host side works, it is worthwhile to let the host poll the virtqueue after it receives the cmd id from the guest (kick for cmd id isn't within the lock).

We should start from the worst case.

+ * The callback itself must not sleep or perform any operations which would
+ * require any memory allocations directly (not even GFP_NOWAIT/GFP_ATOMIC)
+ * or via any lock dependency. It is generally advisable to implement
+ * the callback as simple as possible and defer any heavy lifting to a
+ * different context.

Making decision based on performance numbers of idle guests is dangerous.
There might be busy CPUs waiting for zone->lock.
Michael S. Tsirkin Jan. 30, 2018, 11:44 p.m. UTC | #6
On Fri, Jan 26, 2018 at 11:31:19AM +0800, Wei Wang wrote:
> On 01/26/2018 10:42 AM, Michael S. Tsirkin wrote:
> > On Fri, Jan 26, 2018 at 09:40:44AM +0800, Wei Wang wrote:
> > > On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
> > > > On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
> > > > 
> 
> > > The controversy is that the free list is not static
> > > once the lock is dropped, so everything is dynamically changing, including
> > > the state that was recorded. The method we are using is more prudent, IMHO.
> > > How about taking the fundamental solution, and seek to improve incrementally
> > > in the future?
> > > 
> > > 
> > > Best,
> > > Wei
> > I'd like to see kicks happen outside the spinlock. kick with a spinlock
> > taken looks like a scalability issue that won't be easy to
> > reproduce but hurt workloads at random unexpected times.
> > 
> 
> Is that "kick inside the spinlock" the only concern you have? I think we can
> remove the kick actually. If we check how the host side works, it is
> worthwhile to let the host poll the virtqueue after it receives the cmd id
> from the guest (kick for cmd id isn't within the lock).
> 
> 
> Best,
> Wei

So really there are different ways to put free page hints to use.

The current interface requires host to do dirty tracking
for all memory, and it's more or less useless for
things like freeing host memory.

So while your project's needs seem to be addressed, I'm
still a bit disappointed that so little collaboration
happened with e.g. Nitesh's project, to the point where
you don't even CC him on patches.

So I'm kind of trying to bridge this a bit - I would
like the interfaces that we build to at least superficially
look like they might be reusable for other uses of hinting.

Imagine that you don't have dirty tracking on the host.
What would it take to still use hinting information,
e.g. to call MADV_FREE on the pages guest gives us?

I think you need to kick and you need to wait for
host to consume the hint before page is reused.
And we know madvise takes a lot of time sometimes,
so locking out the free list does not sound like a
good idea.

That's why I was talking about kick out of lock,
so that eventually we can reuse that for hinting
and actually wait for an interrupt.

So how about we take a bunch of pages out of the free list, move them to
the balloon, kick (and optionally wait for host to consume), them move
them back? Preferably to end of the list? This will also make things
like sorting them much easier as you can just put them in a binary tree
or something.

For when we need to be careful to make sure we don't
create an OOM situation with this out of thin air,
and for when you can't give everything to host in one go,
you might want some kind of notifier that tells you
that you need to return pages to the free list ASAP.

How'd this sound?
Wang, Wei W Feb. 1, 2018, 9:43 a.m. UTC | #7
On 01/31/2018 07:44 AM, Michael S. Tsirkin wrote:
> On Fri, Jan 26, 2018 at 11:31:19AM +0800, Wei Wang wrote:
>> On 01/26/2018 10:42 AM, Michael S. Tsirkin wrote:
>>> On Fri, Jan 26, 2018 at 09:40:44AM +0800, Wei Wang wrote:
>>>> On 01/25/2018 09:49 PM, Michael S. Tsirkin wrote:
>>>>> On Thu, Jan 25, 2018 at 05:14:06PM +0800, Wei Wang wrote:
>>>>>
>>>> The controversy is that the free list is not static
>>>> once the lock is dropped, so everything is dynamically changing, including
>>>> the state that was recorded. The method we are using is more prudent, IMHO.
>>>> How about taking the fundamental solution, and seek to improve incrementally
>>>> in the future?
>>>>
>>>>
>>>> Best,
>>>> Wei
>>> I'd like to see kicks happen outside the spinlock. kick with a spinlock
>>> taken looks like a scalability issue that won't be easy to
>>> reproduce but hurt workloads at random unexpected times.
>>>
>> Is that "kick inside the spinlock" the only concern you have? I think we can
>> remove the kick actually. If we check how the host side works, it is
>> worthwhile to let the host poll the virtqueue after it receives the cmd id
>> from the guest (kick for cmd id isn't within the lock).
>>
>>
>> Best,
>> Wei
> So really there are different ways to put free page hints to use.
>
> The current interface requires host to do dirty tracking
> for all memory, and it's more or less useless for
> things like freeing host memory.
>
> So while your project's needs seem to be addressed, I'm
> still a bit disappointed that so little collaboration
> happened with e.g. Nitesh's project, to the point where
> you don't even CC him on patches.

Isn't "nilal@redhat.com" Nitesh? Actually it's been cc-ed long time ago.

I think we should at least see the performance numbers and a working 
prototype from them (I remember they lack the host side implementation).

Btw, this feature is requested by many customers of Linux (not our own 
project's need). They want to use this feature to optimize their *live 
migration*. Hope the community could understand our need.


> So I'm kind of trying to bridge this a bit - I would
> like the interfaces that we build to at least superficially
> look like they might be reusable for other uses of hinting.
>
> Imagine that you don't have dirty tracking on the host.
> What would it take to still use hinting information,
> e.g. to call MADV_FREE on the pages guest gives us?
>
> I think you need to kick and you need to wait for
> host to consume the hint before page is reused.
> And we know madvise takes a lot of time sometimes,
> so locking out the free list does not sound like a
> good idea.
>
> That's why I was talking about kick out of lock,
> so that eventually we can reuse that for hinting
> and actually wait for an interrupt.
>
> So how about we take a bunch of pages out of the free list, move them to
> the balloon, kick (and optionally wait for host to consume), them move
> them back? Preferably to end of the list? This will also make things
> like sorting them much easier as you can just put them in a binary tree
> or something.
>
> For when we need to be careful to make sure we don't
> create an OOM situation with this out of thin air,
> and for when you can't give everything to host in one go,
> you might want some kind of notifier that tells you
> that you need to return pages to the free list ASAP.
>
> How'd this sound?
>

I think the above is a duplicate function of ballooning, though there 
are some differences. Please see below my concerns and different thoughts:

1) From the previous discussion, the only acceptable method to get pages 
from mm is to do alloc() (btw, we are not getting pages in this patch, 
we are getting hints). The above sounds like we are going to take pages 
from the free list without mm's awareness. I'm not sure if you would be 
ready to convince the mm folks that this idea is allowed.

2) If the guest has 8G free memory, how much can virtio-balloon take 
with the above method? For example, if virtio-balloon only takes 1G, 
with 7G left in mm. The next moment, it is possible that something comes 
out and needs to use 7.5GB. I think it is barely possible to ensure that 
the amount of memory we take to virtio-balloon won't affect the system.

3) Hints means the pages are quite likely to be free pages (no 
guarantee). If the pages given to host are going to be freed, then we 
really couldn't call them hints, they are true free pages. Ballooning 
needs true free pages, while live migration needs hints, would you agree 
with this? From the perspective of features, they are two different 
features, and should be gated with two feature bits and separated 
implementations. Mixing them would cause many unexpected issues (e.g. 
the case when the two features function at the same time)

4) If we want to add another function of ballooning, how is this better 
than the existing ballooning? The difference I can see is the current 
ballooning takes free pages via alloc(), while the above hacks into the 
free page list.


Best,
Wei
Michael S. Tsirkin Feb. 1, 2018, 4:03 p.m. UTC | #8
On Thu, Feb 01, 2018 at 05:43:22PM +0800, Wei Wang wrote:
> 3) Hints means the pages are quite likely to be free pages (no guarantee).
> If the pages given to host are going to be freed, then we really couldn't
> call them hints, they are true free pages. Ballooning needs true free pages,
> while live migration needs hints, would you agree with this?

It's an interesting point, I'm convinced by it.
diff mbox

Patch

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index a1fb52c..114985b 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -51,9 +51,22 @@  MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
 static struct vfsmount *balloon_mnt;
 #endif
 
+enum virtio_balloon_vq {
+	VIRTIO_BALLOON_VQ_INFLATE,
+	VIRTIO_BALLOON_VQ_DEFLATE,
+	VIRTIO_BALLOON_VQ_STATS,
+	VIRTIO_BALLOON_VQ_FREE_PAGE,
+	VIRTIO_BALLOON_VQ_MAX
+};
+
 struct virtio_balloon {
 	struct virtio_device *vdev;
-	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
+
+	/* Balloon's own wq for cpu-intensive work items */
+	struct workqueue_struct *balloon_wq;
+	/* The free page reporting work item submitted to the balloon wq */
+	struct work_struct report_free_page_work;
 
 	/* The balloon servicing is delegated to a freezable workqueue. */
 	struct work_struct update_balloon_stats_work;
@@ -63,6 +76,11 @@  struct virtio_balloon {
 	spinlock_t stop_update_lock;
 	bool stop_update;
 
+	/* The new cmd id received from host */
+	uint32_t cmd_id_received;
+	/* The cmd id that is in use */
+	__virtio32 cmd_id_use;
+
 	/* Waiting for host to ack the pages we released. */
 	wait_queue_head_t acked;
 
@@ -316,17 +334,6 @@  static void stats_handle_request(struct virtio_balloon *vb)
 	virtqueue_kick(vq);
 }
 
-static void virtballoon_changed(struct virtio_device *vdev)
-{
-	struct virtio_balloon *vb = vdev->priv;
-	unsigned long flags;
-
-	spin_lock_irqsave(&vb->stop_update_lock, flags);
-	if (!vb->stop_update)
-		queue_work(system_freezable_wq, &vb->update_balloon_size_work);
-	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-}
-
 static inline s64 towards_target(struct virtio_balloon *vb)
 {
 	s64 target;
@@ -343,6 +350,34 @@  static inline s64 towards_target(struct virtio_balloon *vb)
 	return target - vb->num_pages;
 }
 
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+	unsigned long flags;
+	s64 diff = towards_target(vb);
+
+	if (diff) {
+		spin_lock_irqsave(&vb->stop_update_lock, flags);
+		if (!vb->stop_update)
+			queue_work(system_freezable_wq,
+				   &vb->update_balloon_size_work);
+		spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		virtio_cread(vdev, struct virtio_balloon_config,
+			     free_page_report_cmd_id, &vb->cmd_id_received);
+		if (vb->cmd_id_received !=
+		    VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID) {
+			spin_lock_irqsave(&vb->stop_update_lock, flags);
+			if (!vb->stop_update)
+				queue_work(vb->balloon_wq,
+					   &vb->report_free_page_work);
+			spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+		}
+	}
+}
+
 static void update_balloon_size(struct virtio_balloon *vb)
 {
 	u32 actual = vb->num_pages;
@@ -417,42 +452,151 @@  static void update_balloon_size_func(struct work_struct *work)
 
 static int init_vqs(struct virtio_balloon *vb)
 {
-	struct virtqueue *vqs[3];
-	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
-	static const char * const names[] = { "inflate", "deflate", "stats" };
-	int err, nvqs;
+	struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
+	vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
+	const char *names[VIRTIO_BALLOON_VQ_MAX];
+	struct scatterlist sg;
+	int ret;
 
 	/*
-	 * We expect two virtqueues: inflate and deflate, and
-	 * optionally stat.
+	 * Inflateq and deflateq are used unconditionally. The names[]
+	 * will be NULL if the related feature is not enabled, which will
+	 * cause no allocation for the corresponding virtqueue in find_vqs.
 	 */
-	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
-	if (err)
-		return err;
+	callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
+	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
+	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
+	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
+	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
+	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
 
-	vb->inflate_vq = vqs[0];
-	vb->deflate_vq = vqs[1];
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
-		struct scatterlist sg;
-		unsigned int num_stats;
-		vb->stats_vq = vqs[2];
+		names[VIRTIO_BALLOON_VQ_STATS] = "stats";
+		callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
+	}
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
+		callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+	}
+
+	ret = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
+					 vqs, callbacks, names, NULL, NULL);
+	if (ret)
+		return ret;
 
+	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)) {
+		vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
 		/*
 		 * Prime this virtqueue with one buffer so the hypervisor can
 		 * use it to signal us later (it can't be broken yet!).
 		 */
-		num_stats = update_balloon_stats(vb);
-
-		sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
-		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
-		    < 0)
-			BUG();
+		sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+		ret = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
+					   GFP_KERNEL);
+		if (ret) {
+			dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
+				 __func__);
+			return ret;
+		}
 		virtqueue_kick(vb->stats_vq);
 	}
+
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
+
 	return 0;
 }
 
+static int add_one_sg(struct virtqueue *vq, unsigned long pfn, uint32_t len)
+{
+	struct scatterlist sg;
+	unsigned int unused;
+	int ret = 0;
+
+	sg_init_table(&sg, 1);
+	sg_set_page(&sg, pfn_to_page(pfn), len, 0);
+
+	/* Detach all the used buffers from the vq */
+	while (virtqueue_get_buf(vq, &unused))
+		;
+
+	/*
+	 * Since this is an optimization feature, losing a couple of free
+	 * pages to report isn't important. We simply return without adding
+	 * the page if the vq is full.
+	 * We are adding one entry each time, which essentially results in no
+	 * memory allocation, so the GFP_KERNEL flag below can be ignored.
+	 * There is always one entry reserved for the cmd id to use.
+	 */
+	if (vq->num_free > 1)
+		ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
+
+	if (vq->num_free == virtqueue_get_vring_size(vq) / 2 ||
+	    vq->num_free <= 2)
+		virtqueue_kick(vq);
+
+	return ret;
+}
+
+static int virtio_balloon_send_free_pages(void *opaque, unsigned long pfn,
+					   unsigned long nr_pages)
+{
+	struct virtio_balloon *vb = (struct virtio_balloon *)opaque;
+	uint32_t len = nr_pages << PAGE_SHIFT;
+
+	/*
+	 * If a stop id or a new cmd id was just received from host, stop
+	 * the reporting, and return 1 to indicate an active stop.
+	 */
+	if (virtio32_to_cpu(vb->vdev, vb->cmd_id_use) != vb->cmd_id_received)
+		return 1;
+
+	return add_one_sg(vb->free_page_vq, pfn, len);
+}
+
+static int send_cmd_id(struct virtio_balloon *vb, uint32_t cmd_id)
+{
+	struct scatterlist sg;
+	struct virtqueue *vq = vb->free_page_vq;
+	int ret;
+
+	vb->cmd_id_use = cpu_to_virtio32(vb->vdev, cmd_id);
+	sg_init_one(&sg, &vb->cmd_id_use, sizeof(vb->cmd_id_use));
+
+	ret = virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
+	virtqueue_kick(vq);
+
+	return ret;
+}
+
+static void report_free_page_func(struct work_struct *work)
+{
+	struct virtio_balloon *vb;
+	int ret;
+
+	vb = container_of(work, struct virtio_balloon, report_free_page_work);
+
+	/* Start by sending the received cmd id to host with an outbuf */
+	ret = send_cmd_id(vb, vb->cmd_id_received);
+	if (unlikely(ret))
+		goto err;
+
+	ret = walk_free_mem_block(vb, 0, &virtio_balloon_send_free_pages);
+	if (unlikely(ret < 0))
+		goto err;
+
+	/* End by sending a stop id to host with an outbuf */
+	ret = send_cmd_id(vb, VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID);
+	if (likely(!ret))
+		return;
+err:
+	dev_err(&vb->vdev->dev, "%s failure: free page vq is broken\n",
+		__func__);
+}
+
 #ifdef CONFIG_BALLOON_COMPACTION
 /*
  * virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -537,6 +681,7 @@  static struct file_system_type balloon_fs = {
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
+	__u32 poison_val;
 	int err;
 
 	if (!vdev->config->get) {
@@ -566,18 +711,39 @@  static int virtballoon_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_vb;
 
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		/*
+		 * There is always one entry reserved for cmd id, so the ring
+		 * size needs to be at least two to report free page hint.
+		 */
+		if (virtqueue_get_vring_size(vb->free_page_vq) < 2)
+			goto out_free_vb;
+		vb->balloon_wq = alloc_workqueue("balloon-wq",
+					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
+		if (!vb->balloon_wq) {
+			err = -ENOMEM;
+			goto out_del_vqs;
+		}
+		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
+		if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+			poison_val = PAGE_POISON;
+			virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+				      poison_val, &poison_val);
+		}
+	}
+
 	vb->nb.notifier_call = virtballoon_oom_notify;
 	vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
 	err = register_oom_notifier(&vb->nb);
 	if (err < 0)
-		goto out_del_vqs;
+		goto out_del_balloon_wq;
 
 #ifdef CONFIG_BALLOON_COMPACTION
 	balloon_mnt = kern_mount(&balloon_fs);
 	if (IS_ERR(balloon_mnt)) {
 		err = PTR_ERR(balloon_mnt);
 		unregister_oom_notifier(&vb->nb);
-		goto out_del_vqs;
+		goto out_del_balloon_wq;
 	}
 
 	vb->vb_dev_info.migratepage = virtballoon_migratepage;
@@ -587,7 +753,7 @@  static int virtballoon_probe(struct virtio_device *vdev)
 		kern_unmount(balloon_mnt);
 		unregister_oom_notifier(&vb->nb);
 		vb->vb_dev_info.inode = NULL;
-		goto out_del_vqs;
+		goto out_del_balloon_wq;
 	}
 	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
 #endif
@@ -598,6 +764,9 @@  static int virtballoon_probe(struct virtio_device *vdev)
 		virtballoon_changed(vdev);
 	return 0;
 
+out_del_balloon_wq:
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		destroy_workqueue(vb->balloon_wq);
 out_del_vqs:
 	vdev->config->del_vqs(vdev);
 out_free_vb:
@@ -631,6 +800,11 @@  static void virtballoon_remove(struct virtio_device *vdev)
 	cancel_work_sync(&vb->update_balloon_size_work);
 	cancel_work_sync(&vb->update_balloon_stats_work);
 
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+		cancel_work_sync(&vb->report_free_page_work);
+		destroy_workqueue(vb->balloon_wq);
+	}
+
 	remove_common(vb);
 #ifdef CONFIG_BALLOON_COMPACTION
 	if (vb->vb_dev_info.inode)
@@ -674,6 +848,9 @@  static int virtballoon_restore(struct virtio_device *vdev)
 
 static int virtballoon_validate(struct virtio_device *vdev)
 {
+	if (!page_poisoning_enabled())
+		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+
 	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
 	return 0;
 }
@@ -682,6 +859,8 @@  static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
 	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
+	VIRTIO_BALLOON_F_PAGE_POISON,
 };
 
 static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 343d7dd..3f97067 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -34,15 +34,22 @@ 
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
 #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
+#define VIRTIO_BALLOON_F_FREE_PAGE_HINT	3 /* VQ to report free pages */
+#define VIRTIO_BALLOON_F_PAGE_POISON	4 /* Guest is using page poisoning */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
 
+#define VIRTIO_BALLOON_FREE_PAGE_REPORT_STOP_ID		0
 struct virtio_balloon_config {
 	/* Number of pages host wants Guest to give up. */
 	__u32 num_pages;
 	/* Number of pages we've actually got in balloon. */
 	__u32 actual;
+	/* Free page report command id, readonly by guest */
+	__u32 free_page_report_cmd_id;
+	/* Stores PAGE_POISON if page poisoning is in use */
+	__u32 poison_val;
 };
 
 #define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */