[PATCH v7 03/31] mm: page_reporting: allow driver to set batch capacity

[Michael S. Tsirkin]

Add a capacity field to page_reporting_dev_info so drivers can
control the maximum number of pages per report batch. This is
useful when the driver needs to reserve virtqueue descriptors for
metadata (e.g., a bitmap buffer) alongside the page buffers.

The value is capped at PAGE_REPORTING_CAPACITY and rounded down
to a power of 2. If unset (0), defaults to PAGE_REPORTING_CAPACITY.

The virtio_balloon driver sets capacity to the reporting virtqueue
size, letting page_reporting adapt to whatever the device provides.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Assisted-by: Claude:claude-opus-4-6
---
 drivers/virtio/virtio_balloon.c |  5 +----
 include/linux/page_reporting.h  |  3 +++
 mm/page_reporting.c             | 26 +++++++++++++++-----------
 3 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index f6c2dff33f8a..6a1a610c2cb1 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1017,10 +1017,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		unsigned int capacity;
 
 		capacity = virtqueue_get_vring_size(vb->reporting_vq);
-		if (capacity < PAGE_REPORTING_CAPACITY) {
-			err = -ENOSPC;
-			goto out_unregister_oom;
-		}
 
 		vb->pr_dev_info.order = PAGE_REPORTING_ORDER_UNSPECIFIED;
 
@@ -1041,6 +1037,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		vb->pr_dev_info.order = 5;
 #endif
 
+		vb->pr_dev_info.capacity = capacity;
 		err = page_reporting_register(&vb->pr_dev_info);
 		if (err)
 			goto out_unregister_oom;
diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h
index 9d4ca5c218a0..5ab5be02fa15 100644
--- a/include/linux/page_reporting.h
+++ b/include/linux/page_reporting.h
@@ -22,6 +22,9 @@ struct page_reporting_dev_info {
 
 	/* Minimal order of page reporting */
 	unsigned int order;
+
+	/* Max pages per report batch (default PAGE_REPORTING_CAPACITY) */
+	unsigned int capacity;
 };
 
 /* Tear-down and bring-up for page reporting devices */
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index 7418f2e500bb..006f7cdddc18 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -174,10 +174,10 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone,
 	 * list processed. This should result in us reporting all pages on
 	 * an idle system in about 30 seconds.
 	 *
-	 * The division here should be cheap since PAGE_REPORTING_CAPACITY
-	 * should always be a power of 2.
+	 * The division here should be cheap since capacity should
+	 * always be a power of 2.
 	 */
-	budget = DIV_ROUND_UP(area->nr_free, PAGE_REPORTING_CAPACITY * 16);
+	budget = DIV_ROUND_UP(area->nr_free, prdev->capacity * 16);
 
 	/* loop through free list adding unreported pages to sg list */
 	list_for_each_entry_safe(page, next, list, lru) {
@@ -222,10 +222,10 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone,
 		spin_unlock_irq(&zone->lock);
 
 		/* begin processing pages in local list */
-		err = prdev->report(prdev, sgl, PAGE_REPORTING_CAPACITY);
+		err = prdev->report(prdev, sgl, prdev->capacity);
 
 		/* reset offset since the full list was reported */
-		*offset = PAGE_REPORTING_CAPACITY;
+		*offset = prdev->capacity;
 
 		/* update budget to reflect call to report function */
 		budget--;
@@ -234,7 +234,7 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone,
 		spin_lock_irq(&zone->lock);
 
 		/* flush reported pages from the sg list */
-		page_reporting_drain(prdev, sgl, PAGE_REPORTING_CAPACITY, !err);
+		page_reporting_drain(prdev, sgl, prdev->capacity, !err);
 
 		/*
 		 * Reset next to first entry, the old next isn't valid
@@ -260,13 +260,13 @@ static int
 page_reporting_process_zone(struct page_reporting_dev_info *prdev,
 			    struct scatterlist *sgl, struct zone *zone)
 {
-	unsigned int order, mt, leftover, offset = PAGE_REPORTING_CAPACITY;
+	unsigned int order, mt, leftover, offset = prdev->capacity;
 	unsigned long watermark;
 	int err = 0;
 
 	/* Generate minimum watermark to be able to guarantee progress */
 	watermark = low_wmark_pages(zone) +
-		    (PAGE_REPORTING_CAPACITY << page_reporting_order);
+		    (prdev->capacity << page_reporting_order);
 
 	/*
 	 * Cancel request if insufficient free memory or if we failed
@@ -290,7 +290,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev,
 	}
 
 	/* report the leftover pages before going idle */
-	leftover = PAGE_REPORTING_CAPACITY - offset;
+	leftover = prdev->capacity - offset;
 	if (leftover) {
 		sgl = &sgl[offset];
 		err = prdev->report(prdev, sgl, leftover);
@@ -322,11 +322,11 @@ static void page_reporting_process(struct work_struct *work)
 	atomic_set(&prdev->state, state);
 
 	/* allocate scatterlist to store pages being reported on */
-	sgl = kmalloc_objs(*sgl, PAGE_REPORTING_CAPACITY);
+	sgl = kmalloc_objs(*sgl, prdev->capacity);
 	if (!sgl)
 		goto err_out;
 
-	sg_init_table(sgl, PAGE_REPORTING_CAPACITY);
+	sg_init_table(sgl, prdev->capacity);
 
 	for_each_zone(zone) {
 		err = page_reporting_process_zone(prdev, sgl, zone);
@@ -377,6 +377,10 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
 			page_reporting_order = pageblock_order;
 	}
 
+	if (!prdev->capacity || prdev->capacity > PAGE_REPORTING_CAPACITY)
+		prdev->capacity = PAGE_REPORTING_CAPACITY;
+	prdev->capacity = rounddown_pow_of_two(prdev->capacity);
+
 	/* initialize state and work structures */
 	atomic_set(&prdev->state, PAGE_REPORTING_IDLE);
 	INIT_DELAYED_WORK(&prdev->work, &page_reporting_process);
-- 
MST