mm / virtio: Provide support for unused page reporting

index 3ce12481b1dc..9ba542ecf335 100644
@@ -183,25 +183,38 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
 		shuffle_zone(z);
 }
 
+struct batched_bit_entropy {
+	unsigned long entropy_bool;
+	int position;
+};
+
+static DEFINE_PER_CPU(struct batched_bit_entropy, batched_entropy_bool);
+
 void add_to_free_area_random(struct page *page, struct free_area *area,
 		int migratetype)
 {
-	static u64 rand;
-	static u8 rand_bits;
+	struct batched_bit_entropy *batch;
+	unsigned long entropy;
+	int position;
 
 	/*
-	 * The lack of locking is deliberate. If 2 threads race to
-	 * update the rand state it just adds to the entropy.
+	 * We shouldn't need to disable IRQs as the only caller is
+	 * __free_one_page and it should only be called with the zone lock
+	 * held and either from IRQ context or with local IRQs disabled.
 	 */
-	if (rand_bits == 0) {
-		rand_bits = 64;
-		rand = get_random_u64();
+	batch = raw_cpu_ptr(&batched_entropy_bool);
+	position = batch->position;
+
+	if (--position < 0) {
+		batch->entropy_bool = get_random_long();
+		position = BITS_PER_LONG - 1;
 	}
 
-	if (rand & 1)
+	batch->position = position;
+	entropy = batch->entropy_bool;
+
+	if (1ul & (entropy >> position))
 		add_to_free_area(page, area, migratetype);
 	else
 		add_to_free_area_tail(page, area, migratetype);
-	rand_bits--;
-	rand >>= 1;
 }

index bda20282746b..125f300981c6 100644
@@ -116,18 +116,6 @@ static inline void add_to_free_area_tail(struct page *page, struct free_area *ar
 	area->nr_free++;
 }
 
-#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
-/* Used to preserve page allocation order entropy */
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype);
-#else
-static inline void add_to_free_area_random(struct page *page,
-		struct free_area *area, int migratetype)
-{
-	add_to_free_area(page, area, migratetype);
-}
-#endif
-
 /* Used for pages which are on another list */
 static inline void move_to_free_area(struct page *page, struct free_area *area,
 			     int migratetype)

91 lines not on this page · raw message

index 9ba542ecf335..345cb4347455 100644
@@ -4,7 +4,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/mmzone.h>
-#include <linux/random.h>
 #include <linux/moduleparam.h>
 #include "internal.h"
 #include "shuffle.h"

@@ -190,8 +189,7 @@ struct batched_bit_entropy {
 
 static DEFINE_PER_CPU(struct batched_bit_entropy, batched_entropy_bool);
 
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype)
+bool __shuffle_pick_tail(void)
 {
 	struct batched_bit_entropy *batch;
 	unsigned long entropy;

@@ -213,8 +211,5 @@ void add_to_free_area_random(struct page *page, struct free_area *area,
 	batch->position = position;
 	entropy = batch->entropy_bool;
 
-	if (1ul & (entropy >> position))
-		add_to_free_area(page, area, migratetype);
-	else
-		add_to_free_area_tail(page, area, migratetype);
+	return 1ul & (entropy >> position);
 }

index 777a257a0d2f..0723eb97f22f 100644
@@ -3,6 +3,7 @@
 #ifndef _MM_SHUFFLE_H
 #define _MM_SHUFFLE_H
 #include <linux/jump_label.h>
+#include <linux/random.h>
 
 /*
  * SHUFFLE_ENABLE is called from the command line enabling path, or by

@@ -22,6 +23,7 @@ enum mm_shuffle_ctl {
 DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key);
 extern void page_alloc_shuffle(enum mm_shuffle_ctl ctl);
 extern void __shuffle_free_memory(pg_data_t *pgdat);
+extern bool __shuffle_pick_tail(void);
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {
 	if (!static_branch_unlikely(&page_alloc_shuffle_key))

@@ -43,6 +45,11 @@ static inline bool is_shuffle_order(int order)
 		return false;
 	return order >= SHUFFLE_ORDER;
 }
+
+static inline bool shuffle_pick_tail(void)
+{
+	return __shuffle_pick_tail();
+}
 #else
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {

@@ -60,5 +67,10 @@ static inline bool is_shuffle_order(int order)
 {
 	return false;
 }
+
+static inline bool shuffle_pick_tail(void)
+{
+	return false;
+}
 #endif
 #endif /* _MM_SHUFFLE_H */

index 0d5f720c75ab..e4a1a57bbd40 100644
@@ -549,6 +549,24 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 	return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC;
 }
 
+/*
+ * A cached value of the page's pageblock's migratetype, used when the page is
+ * put on a pcplist. Used to avoid the pageblock migratetype lookup when
+ * freeing from pcplists in most cases, at the cost of possibly becoming stale.
+ * Also the migratetype set in the page does not necessarily match the pcplist
+ * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
+ * other index - this ensures that it will be put on the correct CMA freelist.
+ */
+static inline int get_pcppage_migratetype(struct page *page)
+{
+	return page->index;
+}
+
+static inline void set_pcppage_migratetype(struct page *page, int migratetype)
+{
+	page->index = migratetype;
+}
+
 void setup_zone_pageset(struct zone *zone);
 extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
 #endif	/* __MM_INTERNAL_H */

index 4e4356ba66c7..a791f2baeeeb 100644
@@ -185,24 +185,6 @@ static int __init early_init_on_free(char *buf)
 }
 early_param("init_on_free", early_init_on_free);
 
-/*
- * A cached value of the page's pageblock's migratetype, used when the page is
- * put on a pcplist. Used to avoid the pageblock migratetype lookup when
- * freeing from pcplists in most cases, at the cost of possibly becoming stale.
- * Also the migratetype set in the page does not necessarily match the pcplist
- * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
- * other index - this ensures that it will be put on the correct CMA freelist.
- */
-static inline int get_pcppage_migratetype(struct page *page)
-{
-	return page->index;
-}
-
-static inline void set_pcppage_migratetype(struct page *page, int migratetype)
-{
-	page->index = migratetype;
-}
-
 #ifdef CONFIG_PM_SLEEP
 /*
  * The following functions are used by the suspend/hibernate code to temporarily

index 125f300981c6..2ddf1f1971c0 100644
@@ -100,29 +100,6 @@ struct free_area {
 	unsigned long		nr_free;
 };
 
-/* Used for pages not on another list */
-static inline void add_to_free_area(struct page *page, struct free_area *area,
-			     int migratetype)
-{
-	list_add(&page->lru, &area->free_list[migratetype]);
-	area->nr_free++;
-}
-
-/* Used for pages not on another list */
-static inline void add_to_free_area_tail(struct page *page, struct free_area *area,
-				  int migratetype)
-{
-	list_add_tail(&page->lru, &area->free_list[migratetype]);
-	area->nr_free++;
-}
-
-/* Used for pages which are on another list */
-static inline void move_to_free_area(struct page *page, struct free_area *area,
-			     int migratetype)
-{
-	list_move(&page->lru, &area->free_list[migratetype]);
-}
-
 static inline struct page *get_page_from_free_area(struct free_area *area,
 					    int migratetype)
 {

@@ -130,15 +107,6 @@ static inline struct page *get_page_from_free_area(struct free_area *area,
 					struct page, lru);
 }
 
-static inline void del_page_from_free_area(struct page *page,
-		struct free_area *area)
-{
-	list_del(&page->lru);
-	__ClearPageBuddy(page);
-	set_page_private(page, 0);
-	area->nr_free--;
-}
-
 static inline bool free_area_empty(struct free_area *area, int migratetype)
 {
 	return list_empty(&area->free_list[migratetype]);

@@ -796,6 +764,44 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
 }
 
+/* Used for pages not on another list */
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+				    unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_add(&page->lru, &area->free_list[migratetype]);
+	area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
+					 unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_add_tail(&page->lru, &area->free_list[migratetype]);
+	area->nr_free++;
+}
+
+/* Used for pages which are on another list */
+static inline void move_to_free_list(struct page *page, struct zone *zone,
+				     unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_move(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+					   unsigned int order)
+{
+	list_del(&page->lru);
+	__ClearPageBuddy(page);
+	set_page_private(page, 0);
+	zone->free_area[order].nr_free--;
+}
+
 #include <linux/memory_hotplug.h>
 
 void build_all_zonelists(pg_data_t *pgdat);

index a791f2baeeeb..f85dc1561b85 100644
@@ -921,7 +921,6 @@ static inline void __free_one_page(struct page *page,
 	struct capture_control *capc = task_capc(zone);
 	unsigned long uninitialized_var(buddy_pfn);
 	unsigned long combined_pfn;
-	struct free_area *area;
 	unsigned int max_order;
 	struct page *buddy;
 

@@ -958,7 +957,7 @@ static inline void __free_one_page(struct page *page,
 		if (page_is_guard(buddy))
 			clear_page_guard(zone, buddy, order, migratetype);
 		else
-			del_page_from_free_area(buddy, &zone->free_area[order]);
+			del_page_from_free_list(buddy, zone, order);
 		combined_pfn = buddy_pfn & pfn;
 		page = page + (combined_pfn - pfn);
 		pfn = combined_pfn;

@@ -992,12 +991,11 @@ static inline void __free_one_page(struct page *page,
 done_merging:
 	set_page_order(page, order);
 
-	area = &zone->free_area[order];
 	if (is_shuffle_order(order) ? shuffle_pick_tail() :
 	    buddy_merge_likely(pfn, buddy_pfn, page, order))
-		add_to_free_area_tail(page, area, migratetype);
+		add_to_free_list_tail(page, zone, order, migratetype);
 	else
-		add_to_free_area(page, area, migratetype);
+		add_to_free_list(page, zone, order, migratetype);
 }
 
 /*

@@ -2001,13 +1999,11 @@ void __init init_cma_reserved_pageblock(struct page *page)
  * -- nyc
  */
 static inline void expand(struct zone *zone, struct page *page,
-	int low, int high, struct free_area *area,
-	int migratetype)
+	int low, int high, int migratetype)
 {
 	unsigned long size = 1 << high;
 
 	while (high > low) {
-		area--;
 		high--;
 		size >>= 1;
 		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);

@@ -2021,7 +2017,7 @@ static inline void expand(struct zone *zone, struct page *page,
 		if (set_page_guard(zone, &page[size], high, migratetype))
 			continue;
 
-		add_to_free_area(&page[size], area, migratetype);
+		add_to_free_list(&page[size], zone, high, migratetype);
 		set_page_order(&page[size], high);
 	}
 }

@@ -2179,8 +2175,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		page = get_page_from_free_area(area, migratetype);
 		if (!page)
 			continue;
-		del_page_from_free_area(page, area);
-		expand(zone, page, order, current_order, area, migratetype);
+		del_page_from_free_list(page, zone, current_order);
+		expand(zone, page, order, current_order, migratetype);
 		set_pcppage_migratetype(page, migratetype);
 		return page;
 	}

@@ -2188,7 +2184,6 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 	return NULL;
 }
 
-
 /*
  * This array describes the order lists are fallen back to when
  * the free lists for the desirable migrate type are depleted

@@ -2254,7 +2249,7 @@ static int move_freepages(struct zone *zone,
 		VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
 		order = page_order(page);
-		move_to_free_area(page, &zone->free_area[order], migratetype);
+		move_to_free_list(page, zone, order, migratetype);
 		page += 1 << order;
 		pages_moved += 1 << order;
 	}

@@ -2370,7 +2365,6 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 		unsigned int alloc_flags, int start_type, bool whole_block)
 {
 	unsigned int current_order = page_order(page);
-	struct free_area *area;
 	int free_pages, movable_pages, alike_pages;
 	int old_block_type;
 

@@ -2441,8 +2435,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 	return;
 
 single_page:
-	area = &zone->free_area[current_order];
-	move_to_free_area(page, area, start_type);
+	move_to_free_list(page, zone, current_order, start_type);
 }
 
 /*

@@ -3113,7 +3106,6 @@ void split_page(struct page *page, unsigned int order)
 
 int __isolate_free_page(struct page *page, unsigned int order)
 {
-	struct free_area *area = &page_zone(page)->free_area[order];
 	unsigned long watermark;
 	struct zone *zone;
 	int mt;

@@ -3139,7 +3131,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 
 	/* Remove page from free list */
 
-	del_page_from_free_area(page, area);
+	del_page_from_free_list(page, zone, order);
 
 	/*
 	 * Set the pageblock if the isolated page is at least half of a

@@ -8560,7 +8552,7 @@ void zone_pcp_reset(struct zone *zone)
 		pr_info("remove from free list %lx %d %lx\n",
 			pfn, 1 << order, end_pfn);
 #endif
-		del_page_from_free_area(page, &zone->free_area[order]);
+		del_page_from_free_list(page, zone, order);
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);

index 2ddf1f1971c0..4b2c44d7e266 100644
@@ -463,6 +463,14 @@ struct zone {
 	seqlock_t		span_seqlock;
 #endif
 
+#ifdef CONFIG_PAGE_REPORTING
+	/*
+	 * Pointer to reported page tracking statistics array. The size of
+	 * the array is MAX_ORDER - PAGE_REPORTING_MIN_ORDER. NULL when
+	 * unused page reporting is not present.
+	 */
+	unsigned long		*reported_pages;
+#endif
 	int initialized;
 
 	/* Write-intensive fields used from the page allocator */

@@ -538,6 +546,14 @@ enum zone_flags {
 	ZONE_BOOSTED_WATERMARK,		/* zone recently boosted watermarks.
 					 * Cleared when kswapd is woken.
 					 */
+	ZONE_PAGE_REPORTING_REQUESTED,	/* zone enabled page reporting and has
+					 * requested flushing the data out of
+					 * higher order pages.
+					 */
+	ZONE_PAGE_REPORTING_ACTIVE,	/* zone enabled page reporting and is
+					 * activly flushing the data out of
+					 * higher order pages.
+					 */
 };
 
 static inline unsigned long zone_managed_pages(struct zone *zone)

@@ -764,6 +780,8 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
 }
 
+#include <linux/page_reporting.h>
+
 /* Used for pages not on another list */
 static inline void add_to_free_list(struct page *page, struct zone *zone,
 				    unsigned int order, int migratetype)

@@ -778,24 +796,48 @@ static inline void add_to_free_list(struct page *page, struct zone *zone,
 static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
 					 unsigned int order, int migratetype)
 {
-	struct free_area *area = &zone->free_area[order];
+	struct list_head *tail = get_unreported_tail(zone, order, migratetype);
 
-	list_add_tail(&page->lru, &area->free_list[migratetype]);
-	area->nr_free++;
+	/*
+	 * To prevent the unreported pages from being interleaved with the
+	 * reported ones while we are actively processing pages we will use
+	 * the head of the reported pages to determine the tail of the free
+	 * list.
+	 */
+	list_add_tail(&page->lru, tail);
+	zone->free_area[order].nr_free++;
 }
 
 /* Used for pages which are on another list */
 static inline void move_to_free_list(struct page *page, struct zone *zone,
 				     unsigned int order, int migratetype)
 {
-	struct free_area *area = &zone->free_area[order];
+	struct list_head *tail = get_unreported_tail(zone, order, migratetype);
+
+	/*
+	 * We must get the tail for our target list before moving the page on
+	 * the reported list as we will possibly be replacing the tail page of
+	 * the list with our current page if it is reported.
+	 */
+	if (unlikely(PageReported(page)))
+		move_page_to_reported_list(page, zone, migratetype);
 
-	list_move(&page->lru, &area->free_list[migratetype]);
+	/*
+	 * To prevent unreported pages from being mixed with the reported
+	 * ones we add pages to the tail of the list. By doing this the function
+	 * above can either label them as included in the reported list or not
+	 * and the result will be consistent.
+	 */
+	list_move_tail(&page->lru, tail);
 }
 
 static inline void del_page_from_free_list(struct page *page, struct zone *zone,
 					   unsigned int order)
 {
+	/* remove page from reported list, and clear reported state */
+	if (unlikely(PageReported(page)))
+		del_page_from_reported_list(page, zone);
+
 	list_del(&page->lru);
 	__ClearPageBuddy(page);
 	set_page_private(page, 0);

index f91cb8898ff0..759a3b3956f2 100644
@@ -163,6 +163,9 @@ enum pageflags {
 
 	/* non-lru isolated movable page */
 	PG_isolated = PG_reclaim,
+
+	/* Buddy pages. Used to track which pages have been reported */
+	PG_reported = PG_uptodate,
 };
 
 #ifndef __GENERATING_BOUNDS_H

@@ -432,6 +435,14 @@ static inline bool set_hwpoison_free_buddy_page(struct page *page)
 #endif
 
 /*
+ * PageReported() is used to track reported free pages within the Buddy
+ * allocator. We can use the non-atomic version of the test and set
+ * operations as both should be shielded with the zone lock to prevent
+ * any possible races on the setting or clearing of the bit.
+ */
+__PAGEFLAG(Reported, reported, PF_NO_COMPOUND)
+
+/*
  * On an anonymous page mapped into a user virtual memory area,
  * page->mapping points to its anon_vma, not to a struct address_space;
  * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.

177 lines not on this page · raw message

index 49f7bf91c25a..cb71a7190682 100644
@@ -1613,6 +1613,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	if (!populated_zone(zone)) {
 		zone_pcp_reset(zone);
 		build_all_zonelists(NULL);
+		page_reporting_reset(zone);
 	} else
 		zone_pcp_update(zone);
 

153 lines not on this page · raw message

340 lines not on this page · raw message

index 226fbb995fb0..d2547df7de93 100644
@@ -842,7 +842,6 @@ static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
-	__u32 poison_val;
 	int err;
 
 	if (!vdev->config->get) {

@@ -909,11 +908,18 @@ static int virtballoon_probe(struct virtio_device *vdev)
 						  VIRTIO_BALLOON_CMD_ID_STOP);
 		spin_lock_init(&vb->free_page_list_lock);
 		INIT_LIST_HEAD(&vb->free_page_list);
-		if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
-			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
-			virtio_cwrite(vb->vdev, struct virtio_balloon_config,
-				      poison_val, &poison_val);
-		}
+	}
+	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+		__u32 poison_val;
+
+		/*
+		 * Let hypervisor know that we are expecting a specific
+		 * value to be written back in unused pages.
+		 */
+		memset(&poison_val, PAGE_POISON, sizeof(poison_val));
+
+		virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+			      poison_val, &poison_val);
 	}
 	/*
 	 * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a

@@ -1014,7 +1020,9 @@ static int virtballoon_restore(struct virtio_device *vdev)
 
 static int virtballoon_validate(struct virtio_device *vdev)
 {
-	if (!page_poisoning_enabled())
+	/* Notify host if we care about poison value */
+	if (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) ||
+	    !page_poisoning_enabled())
 		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
 
 	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);

136 lines not on this page · raw message

index a1966cd7b677..19974392d324 100644
@@ -36,6 +36,7 @@
 #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 */
+#define VIRTIO_BALLOON_F_REPORTING	5 /* Page reporting virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12

index 25de15430710..003b3ebcfdfb 100644
@@ -530,6 +530,15 @@ static void virtio_balloon_free_page_start(VirtIOBalloon *s)
         return;
     }
 
+    /*
+     * If page poisoning is enabled then we probably shouldn't bother with
+     * the hinting since the poisoning will dirty the page and invalidate
+     * the work we are doing anyway.
+     */
+    if (virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+        return;
+    }
+
     if (s->free_page_report_cmd_id == UINT_MAX) {
         s->free_page_report_cmd_id =
                        VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN;

@@ -617,12 +626,10 @@ static size_t virtio_balloon_config_size(VirtIOBalloon *s)
     if (s->qemu_4_0_config_size) {
         return sizeof(struct virtio_balloon_config);
     }
-    if (virtio_has_feature(features, VIRTIO_BALLOON_F_PAGE_POISON)) {
+    if (virtio_has_feature(features, VIRTIO_BALLOON_F_PAGE_POISON) ||
+        virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
         return sizeof(struct virtio_balloon_config);
     }
-    if (virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
-        return offsetof(struct virtio_balloon_config, poison_val);
-    }
     return offsetof(struct virtio_balloon_config, free_page_report_cmd_id);
 }
 

@@ -633,6 +640,7 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
 
     config.num_pages = cpu_to_le32(dev->num_pages);
     config.actual = cpu_to_le32(dev->actual);
+    config.poison_val = cpu_to_le32(dev->poison_val);
 
     if (dev->free_page_report_status == FREE_PAGE_REPORT_S_REQUESTED) {
         config.free_page_report_cmd_id =

@@ -696,6 +704,8 @@ static void virtio_balloon_set_config(VirtIODevice *vdev,
         qapi_event_send_balloon_change(vm_ram_size -
                         ((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
     }
+    dev->poison_val = virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON) ? 
+                      le32_to_cpu(config.poison_val) : 0;
     trace_virtio_balloon_set_config(dev->actual, oldactual);
 }
 

@@ -705,6 +715,9 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
     VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
     f |= dev->host_features;
     virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ);
+    if (virtio_has_feature(f, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+        virtio_add_feature(&f, VIRTIO_BALLOON_F_PAGE_POISON);
+    }
 
     return f;
 }

@@ -846,6 +859,8 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev)
         g_free(s->stats_vq_elem);
         s->stats_vq_elem = NULL;
     }
+
+    s->poison_val = 0;
 }
 
 static void virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status)

@@ -908,6 +923,8 @@ static Property virtio_balloon_properties[] = {
                     VIRTIO_BALLOON_F_DEFLATE_ON_OOM, false),
     DEFINE_PROP_BIT("free-page-hint", VirtIOBalloon, host_features,
                     VIRTIO_BALLOON_F_FREE_PAGE_HINT, false),
+    DEFINE_PROP_BIT("x-page-poison", VirtIOBalloon, host_features,
+                    VIRTIO_BALLOON_F_PAGE_POISON, false),
     /* QEMU 4.0 accidentally changed the config size even when free-page-hint
      * is disabled, resulting in QEMU 3.1 migration incompatibility.  This
      * property retains this quirk for QEMU 4.1 machine types.

index d1c968d2376e..7fe78e5c14d7 100644
@@ -70,6 +70,7 @@ typedef struct VirtIOBalloon {
     uint32_t host_features;
 
     bool qemu_4_0_config_size;
+    uint32_t poison_val;
 } VirtIOBalloon;
 
 #endif

index 9375ca2a70de..1c5f6d6f2de6 100644
@@ -36,6 +36,7 @@
 #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 */
+#define VIRTIO_BALLOON_F_REPORTING	5 /* Page reporting virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12

index 003b3ebcfdfb..7a30df63bc77 100644
@@ -320,6 +320,40 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v,
     balloon_stats_change_timer(s, 0);
 }
 
+static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
+    VirtQueueElement *elem;
+
+    while ((elem = virtqueue_pop(vq, sizeof(VirtQueueElement)))) {
+    	unsigned int i;
+
+        for (i = 0; i < elem->in_num; i++) {
+            void *addr = elem->in_sg[i].iov_base;
+            size_t size = elem->in_sg[i].iov_len;
+            ram_addr_t ram_offset;
+            size_t rb_page_size;
+            RAMBlock *rb;
+
+            if (qemu_balloon_is_inhibited() || dev->poison_val)
+                continue;
+
+            rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+            rb_page_size = qemu_ram_pagesize(rb);
+
+            /* For now we will simply ignore unaligned memory regions */
+            if ((ram_offset | size) & (rb_page_size - 1))
+                continue;
+
+            ram_block_discard_range(rb, ram_offset, size);
+        }
+
+        virtqueue_push(vq, elem, 0);
+        virtio_notify(vdev, vq);
+        g_free(elem);
+    }
+}
+
 static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(vdev);

@@ -627,7 +661,8 @@ static size_t virtio_balloon_config_size(VirtIOBalloon *s)
         return sizeof(struct virtio_balloon_config);
     }
     if (virtio_has_feature(features, VIRTIO_BALLOON_F_PAGE_POISON) ||
-        virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+        virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT) ||
+        virtio_has_feature(features, VIRTIO_BALLOON_F_REPORTING)) {
         return sizeof(struct virtio_balloon_config);
     }
     return offsetof(struct virtio_balloon_config, free_page_report_cmd_id);

@@ -715,7 +750,8 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
     VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
     f |= dev->host_features;
     virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ);
-    if (virtio_has_feature(f, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+    if (virtio_has_feature(f, VIRTIO_BALLOON_F_FREE_PAGE_HINT) ||
+        virtio_has_feature(f, VIRTIO_BALLOON_F_REPORTING)) {
         virtio_add_feature(&f, VIRTIO_BALLOON_F_PAGE_POISON);
     }
 

@@ -805,6 +841,10 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
     s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
 
+    if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_REPORTING)) {
+        s->rvq = virtio_add_queue(vdev, 32, virtio_balloon_handle_report);
+    }
+
     if (virtio_has_feature(s->host_features,
                            VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
         s->free_page_vq = virtio_add_queue(vdev, VIRTQUEUE_MAX_SIZE,

@@ -931,6 +971,8 @@ static Property virtio_balloon_properties[] = {
      */
     DEFINE_PROP_BOOL("qemu-4-0-config-size", VirtIOBalloon,
                      qemu_4_0_config_size, false),
+    DEFINE_PROP_BIT("unused-page-reporting", VirtIOBalloon, host_features,
+                    VIRTIO_BALLOON_F_REPORTING, true),
     DEFINE_PROP_LINK("iothread", VirtIOBalloon, iothread, TYPE_IOTHREAD,
                      IOThread *),
     DEFINE_PROP_END_OF_LIST(),

index 7fe78e5c14d7..db5bf7127112 100644
@@ -42,7 +42,7 @@ enum virtio_balloon_free_page_report_status {
 
 typedef struct VirtIOBalloon {
     VirtIODevice parent_obj;
-    VirtQueue *ivq, *dvq, *svq, *free_page_vq;
+    VirtQueue *ivq, *dvq, *svq, *free_page_vq, *rvq;
     uint32_t free_page_report_status;
     uint32_t num_pages;
     uint32_t actual;