@@ -52,6 +52,7 @@ enum virtio_balloon_vq {
VIRTIO_BALLOON_VQ_STATS,
VIRTIO_BALLOON_VQ_FREE_PAGE,
VIRTIO_BALLOON_VQ_REPORTING,
+ VIRTIO_BALLOON_VQ_HPG_REPORTING,
VIRTIO_BALLOON_VQ_MAX
};
@@ -126,6 +127,10 @@ struct virtio_balloon {
/* Free page reporting device */
struct virtqueue *reporting_vq;
struct page_reporting_dev_info pr_dev_info;
+
+ /* Free hugepage reporting device */
+ struct virtqueue *hpg_reporting_vq;
+ struct page_reporting_dev_info hpr_dev_info;
};
static const struct virtio_device_id id_table[] = {
@@ -192,6 +197,33 @@ static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_i
return 0;
}
+static int virtballoon_free_hugepage_report(struct page_reporting_dev_info *hpr_dev_info,
+ struct scatterlist *sg, unsigned int nents)
+{
+ struct virtio_balloon *vb =
+ container_of(hpr_dev_info, struct virtio_balloon, hpr_dev_info);
+ struct virtqueue *vq = vb->hpg_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)
{
@@ -515,6 +547,7 @@ static int init_vqs(struct virtio_balloon *vb)
callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
names[VIRTIO_BALLOON_VQ_REPORTING] = NULL;
+ names[VIRTIO_BALLOON_VQ_HPG_REPORTING] = NULL;
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
names[VIRTIO_BALLOON_VQ_STATS] = "stats";
@@ -531,6 +564,11 @@ static int init_vqs(struct virtio_balloon *vb)
callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack;
}
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HPG_REPORTING)) {
+ names[VIRTIO_BALLOON_VQ_HPG_REPORTING] = "hpg_reporting_vq";
+ callbacks[VIRTIO_BALLOON_VQ_HPG_REPORTING] = balloon_ack;
+ }
+
err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
vqs, callbacks, names, NULL, NULL);
if (err)
@@ -566,6 +604,8 @@ static int init_vqs(struct virtio_balloon *vb)
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING];
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HPG_REPORTING))
+ vb->hpg_reporting_vq = vqs[VIRTIO_BALLOON_VQ_HPG_REPORTING];
return 0;
}
@@ -1001,6 +1041,24 @@ static int virtballoon_probe(struct virtio_device *vdev)
goto out_unregister_oom;
}
+ vb->hpr_dev_info.report = virtballoon_free_hugepage_report;
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_HPG_REPORTING)) {
+ unsigned int capacity;
+
+ capacity = virtqueue_get_vring_size(vb->hpg_reporting_vq);
+ if (capacity < PAGE_REPORTING_CAPACITY) {
+ err = -ENOSPC;
+ goto out_unregister_oom;
+ }
+
+ vb->hpr_dev_info.mini_order = 0;
+ vb->hpr_dev_info.batch_size = 2 * 1024 * 1024; /* 2M */
+ vb->hpr_dev_info.delay_jiffies = 1 * HZ; /* 1 seconds */
+ err = hugepage_reporting_register(&vb->hpr_dev_info);
+ if (err)
+ goto out_unregister_oom;
+ }
+
virtio_device_ready(vdev);
if (towards_target(vb))
@@ -1053,6 +1111,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
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_HPG_REPORTING))
+ hugepage_reporting_unregister(&vb->hpr_dev_info);
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
unregister_oom_notifier(&vb->oom_nb);
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
@@ -1133,6 +1193,7 @@ static unsigned int features[] = {
VIRTIO_BALLOON_F_FREE_PAGE_HINT,
VIRTIO_BALLOON_F_PAGE_POISON,
VIRTIO_BALLOON_F_REPORTING,
+ VIRTIO_BALLOON_F_HPG_REPORTING,
};
static struct virtio_driver virtio_balloon_driver = {
@@ -37,6 +37,7 @@
#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 */
+#define VIRTIO_BALLOON_F_HPG_REPORTING 6 /* Huge page reporting virtqueue */
/* Size of a PFN in the balloon interface. */
#define VIRTIO_BALLOON_PFN_SHIFT 12
Free page reporting only supports buddy pages, it can't report the free pages reserved for hugetlbfs case. On the other hand, hugetlbfs is a good choice for a system with a huge amount of RAM, because it can help to reduce the memory management overhead and improve system performance. This patch add support for reporting free hugepage to host when guest use hugetlbfs. A new feature bit and a new vq is added for this new feature. Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Liang Li <liliang324@gmail.com> Signed-off-by: Liang Li <liliangleo@didiglobal.com> --- drivers/virtio/virtio_balloon.c | 61 +++++++++++++++++++++++++++++ include/uapi/linux/virtio_balloon.h | 1 + 2 files changed, 62 insertions(+)