[PATCH v17 RESUBMIT QEMU 3/3] virtio-balloon: Provide a interface for free page reporting

[Alexander Duyck]

From: Alexander Duyck <address@hidden>

Add support for what I am referring to as "free page reporting".
Basically the idea is to function very similar to how the balloon works
in that we basically end up madvising the page as not being used. However
we don't really need to bother with any deflate type logic since the page
will be faulted back into the guest when it is read or written to.

This is meant to be a simplification of the existing balloon interface
to use for providing hints to what memory needs to be freed. I am assuming
this is safe to do as the deflate logic does not actually appear to do very
much other than tracking what subpages have been released and which ones
haven't.

Signed-off-by: Alexander Duyck <address@hidden>
---
 hw/virtio/virtio-balloon.c         |   46 ++++++++++++++++++++++++++++++++++--
 include/hw/virtio/virtio-balloon.h |    2 +-
 2 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 455d85b7082f..5faafd2f62ac 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -321,6 +321,40 @@ 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);
@@ -628,7 +662,8 @@ 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);
@@ -716,7 +751,8 @@ 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);
     }
 
@@ -806,6 +842,10 @@ 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,
@@ -939,6 +979,8 @@ 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(),
diff --git a/include/hw/virtio/virtio-balloon.h 
b/include/hw/virtio/virtio-balloon.h
index 7fe78e5c14d7..db5bf7127112 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -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;