[v20,QEMU,5/5] virtio-balloon: Provide an interface for free page reporting

Commit Message

Alexander Duyck April 16, 2020, 8 p.m. UTC

From: Alexander Duyck <[e-mail]>

Add support for free page reporting. 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 provides a new way of letting the guest proactively report free
pages to the hypervisor, so the hypervisor can reuse them. In contrast to
inflate/deflate that is triggered via the hypervisor explicitly.

Signed-off-by: Alexander Duyck <[e-mail]>
---
 hw/virtio/virtio-balloon.c         |   62 +++++++++++++++++++++++++++++++++++-
 include/hw/virtio/virtio-balloon.h |    2 +
 2 files changed, 62 insertions(+), 2 deletions(-)

Patch

diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 19d587fd05cb..e5c9317921a1 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -321,6 +321,59 @@  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;
+
+        if (qemu_balloon_is_inhibited() || dev->poison_val) {
+            continue;
+        }
+
+        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;
+            RAMBlock *rb;
+
+            /*
+             * There is no need to check the memory section to see if
+             * it is ram/readonly/romd like there is for handle_output
+             * below. If the region is not meant to be written to then
+             * address_space_map will have allocated a bounce buffer
+             * and it will be freed in address_space_unmap and trigger
+             * and unassigned_mem_write before failing to copy over the
+             * buffer. If more than one bad descriptor is provided it
+             * will return NULL after the first bounce buffer and fail
+             * to map any resources.
+             */
+            rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+            if (!rb) {
+                trace_virtio_balloon_bad_addr(elem->in_addr[i]);
+                continue;
+            }
+
+            /*
+             * For now we will simply ignore unaligned memory regions, or
+             * regions that overrun the end of the RAMBlock.
+             */
+            if (!QEMU_IS_ALIGNED(ram_offset | size, qemu_ram_pagesize(rb)) ||
+		(ram_offset + size) > qemu_ram_get_used_length(rb)) {
+                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);
@@ -728,7 +781,8 @@  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);
     }
 
@@ -818,6 +872,10 @@  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,
@@ -949,6 +1007,8 @@  static Property virtio_balloon_properties[] = {
      */
     DEFINE_PROP_BOOL("qemu-4-0-config-size", VirtIOBalloon,
                      qemu_4_0_config_size, false),
+    DEFINE_PROP_BIT("free-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 3ca2a78e1aca..ac4013d51010 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -42,7 +42,7 @@  enum virtio_balloon_free_page_hint_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_hint_status;
     uint32_t num_pages;
     uint32_t actual;