virtio-balloon: add support for providing free page reports to host

Add support for the page reporting feature provided by virtio-balloon.
Reporting differs from the regular balloon functionality in that is is
much less durable than a standard memory balloon.  Instead of creating a
list of pages that cannot be accessed the pages are only inaccessible
while they are being indicated to the virtio interface.  Once the
interface has acknowledged them they are placed back into their respective
free lists and are once again accessible by the guest system.

Unlike a standard balloon we don't inflate and deflate the pages.  Instead
we perform the reporting, and once the reporting is completed it is
assumed that the page has been dropped from the guest and will be faulted
back in the next time the page is accessed.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Nitesh Narayan Lal <nitesh@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pankaj Gupta <pagupta@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Wang <wei.w.wang@intel.com>
Cc: Yang Zhang <yang.zhang.wz@gmail.com>
Cc: wei qi <weiqi4@huawei.com>
Link: http://lkml.kernel.org/r/20200211224657.29318.68624.stgit@localhost.localdomain
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/virtio/Kconfig

@@ -58,6 +58,7 @@ config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO
 	select MEMORY_BALLOON
+	select PAGE_REPORTING
 	---help---
 	 This driver supports increasing and decreasing the amount
 	 of memory within a KVM guest.

drivers/virtio/virtio_balloon.c

@@ -19,6 +19,7 @@
 #include <linux/mount.h>
 #include <linux/magic.h>
 #include <linux/pseudo_fs.h>
+#include <linux/page_reporting.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -47,6 +48,7 @@ enum virtio_balloon_vq {
 	VIRTIO_BALLOON_VQ_DEFLATE,
 	VIRTIO_BALLOON_VQ_STATS,
 	VIRTIO_BALLOON_VQ_FREE_PAGE,
+	VIRTIO_BALLOON_VQ_REPORTING,
 	VIRTIO_BALLOON_VQ_MAX
 };
 
@@ -114,6 +116,10 @@ struct virtio_balloon {
 
 	/* To register a shrinker to shrink memory upon memory pressure */
 	struct shrinker shrinker;
+
+	/* Free page reporting device */
+	struct virtqueue *reporting_vq;
+	struct page_reporting_dev_info pr_dev_info;
 };
 
 static struct virtio_device_id id_table[] = {
@@ -153,6 +159,33 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 
 }
 
+int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info,
+				   struct scatterlist *sg, unsigned int nents)
+{
+	struct virtio_balloon *vb =
+		container_of(pr_dev_info, struct virtio_balloon, pr_dev_info);
+	struct virtqueue *vq = vb->reporting_vq;
+	unsigned int unused, err;
+
+	/* We should always be able to add these buffers to an empty queue. */
+	err = virtqueue_add_inbuf(vq, sg, nents, vb, GFP_NOWAIT | __GFP_NOWARN);
+
+	/*
+	 * In the extremely unlikely case that something has occurred and we
+	 * are able to trigger an error we will simply display a warning
+	 * and exit without actually processing the pages.
+	 */
+	if (WARN_ON_ONCE(err))
+		return err;
+
+	virtqueue_kick(vq);
+
+	/* When host has read buffer, this completes via balloon_ack */
+	wait_event(vb->acked, virtqueue_get_buf(vq, &unused));
+
+	return 0;
+}
+
 static void set_page_pfns(struct virtio_balloon *vb,
 			  __virtio32 pfns[], struct page *page)
 {
@@ -481,6 +514,7 @@ static int init_vqs(struct virtio_balloon *vb)
 	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
 	callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = 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";
@@ -492,6 +526,11 @@ 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;
+	}
+
 	err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
 					 vqs, callbacks, names, NULL, NULL);
 	if (err)
@@ -524,6 +563,9 @@ static int init_vqs(struct virtio_balloon *vb)
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
 		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
 
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
+		vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING];
+
 	return 0;
 }
 
@@ -953,12 +995,31 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		if (err)
 			goto out_del_balloon_wq;
 	}
+
+	vb->pr_dev_info.report = virtballoon_free_page_report;
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
+		unsigned int capacity;
+
+		capacity = virtqueue_get_vring_size(vb->reporting_vq);
+		if (capacity < PAGE_REPORTING_CAPACITY) {
+			err = -ENOSPC;
+			goto out_unregister_shrinker;
+		}
+
+		err = page_reporting_register(&vb->pr_dev_info);
+		if (err)
+			goto out_unregister_shrinker;
+	}
+
 	virtio_device_ready(vdev);
 
 	if (towards_target(vb))
 		virtballoon_changed(vdev);
 	return 0;
 
+out_unregister_shrinker:
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
+		virtio_balloon_unregister_shrinker(vb);
 out_del_balloon_wq:
 	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
 		destroy_workqueue(vb->balloon_wq);
@@ -997,6 +1058,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
 
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
+		page_reporting_unregister(&vb->pr_dev_info);
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
 		virtio_balloon_unregister_shrinker(vb);
 	spin_lock_irq(&vb->stop_update_lock);
@@ -1069,6 +1132,7 @@ static unsigned int features[] = {
 	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
 	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
 	VIRTIO_BALLOON_F_PAGE_POISON,
+	VIRTIO_BALLOON_F_REPORTING,
 };
 
 static struct virtio_driver virtio_balloon_driver = {

include/uapi/linux/virtio_balloon.h

@@ -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