Re: [PATCH 10/13] virtio_balloon: add higher-order page inflation

["Michael S. Tsirkin" <mst@redhat.com>]

On Tue, Oct 27, 2026 at 02:56:13AM +0000, Kevin Loughlin wrote:
> In confidential computing guests requiring page state transitions,
> unaccepted memory tracking operates at the EFI unaccepted memory unit
> granularity (typically 2MB / order 9 on x86). Inflating the balloon
> with 4KB pages would prevent unaccepting the backing 2MB unit.
> 
> Inflate balloon pages at unaccepted_memory_order() when
> virtballoon_cc_needs_state_transition() is true, while retaining
> order-0 allocations for non-CoCo guests and CoCo guests that do not
> use unaccepted memory transitions. When a higher-order balloon page
> spans more 4KB balloon PFNs than VIRTIO_BALLOON_ARRAY_PFNS_MAX (256),
> transmit its PFNs to the host in VIRTIO_BALLOON_ARRAY_PFNS_MAX chunks.
> 
> Signed-off-by: Kevin Loughlin <kevinloughlin@google.com>

BTW I'd say *everyone* prefers large pages. The fact that balloon
currently breaks them up isn't nice to anyone. The only setup
where they might be helpful is severe fragmentation, but even then,
it is not clear we aren't contributing to the problem
by making the fragmentation worse.


> ---
>  drivers/virtio/virtio_balloon.c | 87 ++++++++++++++++++++++++++-------
>  include/linux/balloon.h         |  1 +
>  mm/balloon.c                    | 67 +++++++++++++++++++------
>  3 files changed, 121 insertions(+), 34 deletions(-)
> 
> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
> index 11f74848fdc4..d162c162b496 100644
> --- a/drivers/virtio/virtio_balloon.c
> +++ b/drivers/virtio/virtio_balloon.c
> @@ -182,6 +182,13 @@ static void balloon_ack(struct virtqueue *vq)
>  	wake_up(&vb->acked);
>  }
>  
> +static inline bool virtballoon_cc_needs_state_transition(void)
> +{
> +	return IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
> +	       cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) &&
> +	       has_unaccepted_memory();
> +}
> +
>  static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
>  {
>  	struct scatterlist sg;
> @@ -243,24 +250,49 @@ static void set_page_pfns(struct virtio_balloon *vb,
>  					  page_to_balloon_pfn(page) + i);
>  }
>  
> +static void queue_page_pfns(struct virtio_balloon *vb, struct virtqueue *vq,
> +			    struct page *page, unsigned int order)
> +{
> +	unsigned int nr_pages = 1 << order;
> +	unsigned int i;
> +
> +	for (i = 0; i < nr_pages; i++) {
> +		set_page_pfns(vb, vb->pfns + vb->num_pfns, page + i);
> +		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
> +		if (vb->num_pfns == ARRAY_SIZE(vb->pfns)) {
> +			tell_host(vb, vq);
> +			vb->num_pfns = 0;
> +		}
> +	}
> +}
> +
> +static inline unsigned int virtballoon_preferred_order(void)
> +{
> +	if (virtballoon_cc_needs_state_transition())
> +		return unaccepted_memory_order();
> +	return 0;
> +}
> +
>  static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num)
>  {
> -	unsigned int num_allocated_pages;
> +	unsigned int order = virtballoon_preferred_order();
> +	unsigned int page_pfns = (1 << order) * VIRTIO_BALLOON_PAGES_PER_PAGE;
> +	unsigned int num_allocated_pages = 0;
>  	struct page *page, *next;
>  	unsigned int num_pfns;
>  	LIST_HEAD(pages);
>  
> -	/* We can only do one array worth at a time. */
> -	num = min(num, ARRAY_SIZE(vb->pfns));
> +	/* We can only do one array or preferred-order page worth at a time. */
> +	num = min(num, max_t(size_t, ARRAY_SIZE(vb->pfns), page_pfns));
>  
>  	for (num_pfns = 0; num_pfns < num;
> -	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
> -		page = balloon_page_alloc();
> +	     num_pfns += page_pfns) {
> +		page = balloon_pages_alloc(order);
>  
>  		if (!page) {
>  			dev_info_ratelimited(&vb->vdev->dev,
>  					     "Out of puff! Can't get %u pages\n",
> -					     VIRTIO_BALLOON_PAGES_PER_PAGE);
> +					     page_pfns);
>  			/* Sleep for at least 1/5 of a second before retry. */
>  			msleep(200);
>  			break;
> @@ -274,15 +306,17 @@ static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num)
>  	vb->num_pfns = 0;
>  
>  	list_for_each_entry_safe(page, next, &pages, lru) {
> +		unsigned int page_order = compound_order(page);
> +		unsigned int pfns = (1 << page_order) * VIRTIO_BALLOON_PAGES_PER_PAGE;
> +
>  		list_del(&page->lru);
>  		balloon_page_enqueue(&vb->vb_dev_info, page);
>  
> -		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
> -		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
> -		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
> +		vb->num_pages += pfns;
> +		num_allocated_pages += pfns;
> +		queue_page_pfns(vb, vb->inflate_vq, page, page_order);
>  	}
>  
> -	num_allocated_pages = vb->num_pfns;
>  	/* Did we get any? */
>  	if (vb->num_pfns != 0)
>  		tell_host(vb, vb->inflate_vq);
> @@ -304,28 +338,42 @@ static void release_pages_balloon(struct virtio_balloon *vb,
>  
>  static unsigned int leak_balloon(struct virtio_balloon *vb, size_t num)
>  {
> -	unsigned int num_freed_pages;
> +	unsigned int order = virtballoon_preferred_order();
> +	unsigned int page_pfns = (1 << order) * VIRTIO_BALLOON_PAGES_PER_PAGE;
> +	unsigned int num_freed_pages = 0;
>  	struct page *page;
>  	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
>  	LIST_HEAD(pages);
>  
> -	/* We can only do one array worth at a time. */
> -	num = min(num, ARRAY_SIZE(vb->pfns));
> +	/* We can only do one array or preferred-order page worth at a time. */
> +	num = min(num, max_t(size_t, ARRAY_SIZE(vb->pfns), page_pfns));
>  
>  	mutex_lock(&vb->balloon_lock);
>  	/* We can't release more pages than taken */
>  	num = min(num, (size_t)vb->num_pages);
> -	for (vb->num_pfns = 0; vb->num_pfns < num;
> -	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
> +	vb->num_pfns = 0;
> +	while (num_freed_pages < num) {
> +		unsigned int dequeued_order;
> +		unsigned int dequeued_pfns;
> +
>  		page = balloon_page_dequeue(vb_dev_info);
>  		if (!page)
>  			break;
> -		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
> +		dequeued_order = compound_order(page);
> +		dequeued_pfns = (1 << dequeued_order) * VIRTIO_BALLOON_PAGES_PER_PAGE;
> +
> +		if (num_freed_pages + dequeued_pfns > num &&
> +		    num_freed_pages > 0) {
> +			balloon_page_enqueue(vb_dev_info, page);
> +			break;
> +		}
> +
> +		queue_page_pfns(vb, vb->deflate_vq, page, dequeued_order);
>  		list_add(&page->lru, &pages);
> -		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
> +		vb->num_pages -= dequeued_pfns;
> +		num_freed_pages += dequeued_pfns;
>  	}
>  
> -	num_freed_pages = vb->num_pfns;
>  	/*
>  	 * Note that if
>  	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
> @@ -474,7 +522,8 @@ static inline s64 towards_target(struct virtio_balloon *vb)
>  	 * Aligned up to guest page size to avoid inflating and deflating
>  	 * balloon endlessly.
>  	 */
> -	target = ALIGN(num_pages, VIRTIO_BALLOON_PAGES_PER_PAGE);
> +	target = ALIGN((s64)num_pages,
> +		       VIRTIO_BALLOON_PAGES_PER_PAGE << virtballoon_preferred_order());
>  	return target - vb->num_pages;
>  }
>  
> diff --git a/include/linux/balloon.h b/include/linux/balloon.h
> index ca5b15150f42..bc46e36b997f 100644
> --- a/include/linux/balloon.h
> +++ b/include/linux/balloon.h
> @@ -58,6 +58,7 @@ struct balloon_dev_info {
>  	bool adjust_managed_page_count;
>  };
>  
> +struct page *balloon_pages_alloc(unsigned int order);
>  struct page *balloon_page_alloc(void);
>  void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
>  		struct page *page);
> diff --git a/mm/balloon.c b/mm/balloon.c
> index 96a8f1e20bc6..e9941d08d8e9 100644
> --- a/mm/balloon.c
> +++ b/mm/balloon.c
> @@ -27,9 +27,12 @@ static DEFINE_SPINLOCK(balloon_pages_lock);
>  static void balloon_page_insert(struct balloon_dev_info *balloon,
>  				       struct page *page)
>  {
> +	unsigned int i, nr_pages = 1U << compound_order(page);
> +
>  	lockdep_assert_held(&balloon_pages_lock);
> -	__SetPageOffline(page);
> -	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION)) {
> +	for (i = 0; i < nr_pages; i++)
> +		__SetPageOffline(page + i);
> +	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION) && !PageCompound(page)) {
>  		SetPageMovableOps(page);
>  		set_page_private(page, (unsigned long)balloon);
>  	}
> @@ -45,20 +48,31 @@ static void balloon_page_insert(struct balloon_dev_info *balloon,
>   */
>  static void balloon_page_finalize(struct page *page)
>  {
> +	unsigned int i, nr_pages = 1U << compound_order(page);
> +
>  	lockdep_assert_held(&balloon_pages_lock);
> -	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION))
> +	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION) && !PageCompound(page))
>  		set_page_private(page, 0);
> -	/* PageOffline is sticky until the page is freed to the buddy. */
> +	/*
> +	 * PageOffline is sticky on the head page until freed to the buddy,
> +	 * which resets the head page's page_type in __free_pages_prepare().
> +	 * Clear PageOffline on tail pages here as __free_pages_prepare()
> +	 * expects tail pages to have a default page_type.
> +	 */
> +	for (i = 1; i < nr_pages; i++)
> +		__ClearPageOffline(page + i);
>  }
>  
>  static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info,
>  				     struct page *page)
>  {
> +	unsigned int order = compound_order(page);
> +
>  	balloon_page_insert(b_dev_info, page);
>  	if (b_dev_info->adjust_managed_page_count)
> -		adjust_managed_page_count(page, -1);
> -	__count_vm_event(BALLOON_INFLATE);
> -	inc_node_page_state(page, NR_BALLOON_PAGES);
> +		adjust_managed_page_count(page, -(1L << order));
> +	__count_vm_events(BALLOON_INFLATE, 1UL << order);
> +	mod_node_page_state(page_pgdat(page), NR_BALLOON_PAGES, 1L << order);
>  }
>  
>  /**
> @@ -117,15 +131,18 @@ size_t balloon_page_list_dequeue(struct balloon_dev_info *b_dev_info,
>  
>  	spin_lock_irqsave(&balloon_pages_lock, flags);
>  	list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
> +		unsigned int order = compound_order(page);
> +
>  		if (n_pages == n_req_pages)
>  			break;
>  		list_del(&page->lru);
>  		if (b_dev_info->adjust_managed_page_count)
> -			adjust_managed_page_count(page, 1);
> +			adjust_managed_page_count(page, 1L << order);
>  		balloon_page_finalize(page);
> -		__count_vm_event(BALLOON_DEFLATE);
> +		__count_vm_events(BALLOON_DEFLATE, 1UL << order);
>  		list_add(&page->lru, pages);
> -		dec_node_page_state(page, NR_BALLOON_PAGES);
> +		mod_node_page_state(page_pgdat(page), NR_BALLOON_PAGES,
> +				    -(1L << order));
>  		n_pages++;
>  	}
>  	spin_unlock_irqrestore(&balloon_pages_lock, flags);
> @@ -135,8 +152,9 @@ size_t balloon_page_list_dequeue(struct balloon_dev_info *b_dev_info,
>  EXPORT_SYMBOL_GPL(balloon_page_list_dequeue);
>  
>  /**
> - * balloon_page_alloc - allocates a new page for insertion into the balloon
> - *			page list.
> + * balloon_pages_alloc - allocates a new page of given order for insertion
> + *			 into the balloon page list.
> + * @order: allocation order
>   *
>   * Driver must call this function to properly allocate a new balloon page.
>   * Driver must call balloon_page_enqueue before definitively removing the page
> @@ -144,16 +162,35 @@ EXPORT_SYMBOL_GPL(balloon_page_list_dequeue);
>   *
>   * Return: struct page for the allocated page or NULL on allocation failure.
>   */
> -struct page *balloon_page_alloc(void)
> +struct page *balloon_pages_alloc(unsigned int order)
>  {
>  	gfp_t gfp_flags = __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
>  
> -	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION))
> +	if (IS_ENABLED(CONFIG_BALLOON_MIGRATION) && !order)
>  		gfp_flags |= GFP_HIGHUSER_MOVABLE;
>  	else
>  		gfp_flags |= GFP_HIGHUSER;
>  
> -	return alloc_page(gfp_flags);
> +	if (order > 0)
> +		gfp_flags |= __GFP_COMP;
> +
> +	return alloc_pages(gfp_flags, order);
> +}
> +EXPORT_SYMBOL_GPL(balloon_pages_alloc);
> +
> +/**
> + * balloon_page_alloc - allocates a new page for insertion into the balloon
> + *			page list.
> + *
> + * Driver must call this function to properly allocate a new balloon page.
> + * Driver must call balloon_page_enqueue before definitively removing the page
> + * from the guest system.
> + *
> + * Return: struct page for the allocated page or NULL on allocation failure.
> + */
> +struct page *balloon_page_alloc(void)
> +{
> +	return balloon_pages_alloc(0);
>  }
>  EXPORT_SYMBOL_GPL(balloon_page_alloc);
>  
> -- 
> 2.56.0.307.g5fe7bd680c-goog