[Qemu-devel] [PATCH QEMU 3/5] virtio-balloon: Add a new feature to balloon device

[Liang Li <liang.z.li@intel.com>]

Extend the virtio balloon device to support a new feature, this
new feature can help to get guest's free pages information, which
can be used for live migration optimzation.

Signed-off-by: Liang Li <liang.z.li@intel.com>
---
 balloon.c                                       | 29 +++++++-
 hw/virtio/virtio-balloon.c                      | 92 ++++++++++++++++++++++++-
 include/hw/virtio/virtio-balloon.h              | 30 +++++++-
 include/standard-headers/linux/virtio_balloon.h |  1 +
 include/sysemu/balloon.h                        | 12 +++-
 5 files changed, 159 insertions(+), 5 deletions(-)

diff --git a/balloon.c b/balloon.c
index f2ef50c..346e215 100644
--- a/balloon.c
+++ b/balloon.c
@@ -36,6 +36,7 @@
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
+static QEMUBalloonGetFreePage *balloon_get_free_page_fn;
 static void *balloon_opaque;
 static bool balloon_inhibited;
 
@@ -65,9 +66,12 @@ static bool have_balloon(Error **errp)
 }
 
 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
-                             QEMUBalloonStatus *stat_func, void *opaque)
+                             QEMUBalloonStatus *stat_func,
+                             QEMUBalloonGetFreePage *get_free_page_func,
+                             void *opaque)
 {
-    if (balloon_event_fn || balloon_stat_fn || balloon_opaque) {
+    if (balloon_event_fn || balloon_stat_fn || balloon_get_free_page_fn
+        || balloon_opaque) {
         /* We're already registered one balloon handler.  How many can
          * a guest really have?
          */
@@ -75,6 +79,7 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
     }
     balloon_event_fn = event_func;
     balloon_stat_fn = stat_func;
+    balloon_get_free_page_fn = get_free_page_func;
     balloon_opaque = opaque;
     return 0;
 }
@@ -86,6 +91,7 @@ void qemu_remove_balloon_handler(void *opaque)
     }
     balloon_event_fn = NULL;
     balloon_stat_fn = NULL;
+    balloon_get_free_page_fn = NULL;
     balloon_opaque = NULL;
 }
 
@@ -116,3 +122,22 @@ void qmp_balloon(int64_t target, Error **errp)
     trace_balloon_event(balloon_opaque, target);
     balloon_event_fn(balloon_opaque, target);
 }
+
+bool balloon_free_pages_support(void)
+{
+    return balloon_get_free_page_fn ? true : false;
+}
+
+FreePageStatus balloon_get_free_pages(unsigned long *bitmap,
+                                      unsigned long len, int drop_cache)
+{
+    if (!balloon_get_free_page_fn) {
+        return FREE_PAGE_UNSUPPORT;
+    }
+
+    if (!bitmap) {
+        return FREE_PAGE_INVALID_PARAM;
+    }
+
+    return balloon_get_free_page_fn(balloon_opaque, bitmap, len, drop_cache);
+}
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 9dbe681..0abf375 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -78,6 +78,12 @@ static bool balloon_stats_supported(const VirtIOBalloon *s)
     return virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_STATS_VQ);
 }
 
+static bool balloon_free_pages_supported(const VirtIOBalloon *s)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(s);
+    return virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_GET_FREE_PAGE);
+}
+
 static bool balloon_stats_enabled(const VirtIOBalloon *s)
 {
     return s->stats_poll_interval > 0;
@@ -304,6 +310,38 @@ out:
     }
 }
 
+static void virtio_balloon_get_free_pages(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
+    VirtQueueElement *elem;
+    size_t offset = 0;
+    uint64_t bitmap_bytes = 0;
+
+    elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
+    if (!elem) {
+        s->req_status = REQ_ERROR;
+        return;
+    }
+
+    s->free_page_vq_elem = elem;
+
+    if (!elem->out_num) {
+        return;
+    }
+
+    iov_to_buf(elem->out_sg, elem->out_num, offset,
+               &bitmap_bytes, sizeof(uint64_t));
+
+    if (s->bmap_len < bitmap_bytes) {
+        s->req_status = REQ_INVALID_PARAM;
+        return;
+    }
+    offset += sizeof(uint64_t);
+    iov_to_buf(elem->out_sg, elem->out_num, offset,
+               s->free_page_bmap, bitmap_bytes);
+    s->req_status = REQ_DONE;
+}
+
 static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
 {
     VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
@@ -373,6 +411,7 @@ 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);
+    virtio_add_feature(&f, VIRTIO_BALLOON_F_GET_FREE_PAGE);
     return f;
 }
 
@@ -383,6 +422,48 @@ static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
                                              VIRTIO_BALLOON_PFN_SHIFT);
 }
 
+static FreePageStatus virtio_balloon_free_pages(void *opaque,
+                                                unsigned long *bitmap,
+                                                unsigned long bmap_len,
+                                                int drop_cache_ctl)
+{
+    VirtIOBalloon *s = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(s);
+    VirtQueueElement *elem = s->free_page_vq_elem;
+    int len;
+
+    if (!balloon_free_pages_supported(s)) {
+        return FREE_PAGE_UNSUPPORT;
+    }
+
+    if (s->req_status == REQ_INIT) {
+        s->free_page_bmap = bitmap;
+        if (elem == NULL || !elem->in_num) {
+            elem = virtqueue_pop(s->fvq, sizeof(VirtQueueElement));
+            if (!elem) {
+                return FREE_PAGE_ERROR;
+            }
+            s->free_page_vq_elem = elem;
+        }
+        s->free_page_req.param = drop_cache_ctl;
+        s->bmap_len = bmap_len;
+        len = iov_from_buf(elem->in_sg, elem->in_num, 0, &s->free_page_req,
+                           sizeof(s->free_page_req));
+        virtqueue_push(s->fvq, elem, len);
+        virtio_notify(vdev, s->fvq);
+        g_free(s->free_page_vq_elem);
+        s->free_page_vq_elem = NULL;
+        s->req_status = REQ_ON_GOING;
+        return FREE_PAGE_REQ;
+    } else if (s->req_status == REQ_ON_GOING) {
+        return FREE_PAGE_WAITING_FOR_RSP;
+    } else if (s->req_status == REQ_DONE) {
+        s->req_status = REQ_INIT;
+    }
+
+    return FREE_PAGE_READY;
+}
+
 static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
 {
     VirtIOBalloon *dev = VIRTIO_BALLOON(opaque);
@@ -444,7 +525,8 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
                 sizeof(struct virtio_balloon_config));
 
     ret = qemu_add_balloon_handler(virtio_balloon_to_target,
-                                   virtio_balloon_stat, s);
+                                   virtio_balloon_stat,
+                                   virtio_balloon_free_pages, s);
 
     if (ret < 0) {
         error_setg(errp, "Only one balloon device is supported");
@@ -455,8 +537,10 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
     s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
+    s->fvq = virtio_add_queue(vdev, 128, virtio_balloon_get_free_pages);
 
     reset_stats(s);
+    s->req_status = REQ_INIT;
 
     register_savevm(dev, "virtio-balloon", -1, 1,
                     virtio_balloon_save, virtio_balloon_load, s);
@@ -481,6 +565,12 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev)
         g_free(s->stats_vq_elem);
         s->stats_vq_elem = NULL;
     }
+
+    if (s->free_page_vq_elem != NULL) {
+        g_free(s->free_page_vq_elem);
+        s->free_page_vq_elem = NULL;
+    }
+    s->req_status = REQ_INIT;
 }
 
 static void virtio_balloon_instance_init(Object *obj)
diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h
index 35f62ac..fbed81c 100644
--- a/include/hw/virtio/virtio-balloon.h
+++ b/include/hw/virtio/virtio-balloon.h
@@ -23,6 +23,27 @@
 #define VIRTIO_BALLOON(obj) \
         OBJECT_CHECK(VirtIOBalloon, (obj), TYPE_VIRTIO_BALLOON)
 
+typedef enum {
+    REQ_INIT,
+    REQ_ON_GOING,
+    REQ_DONE,
+    REQ_ERROR,
+    REQ_INVALID_PARAM,
+} VirtIoReqStatus;
+
+typedef enum {
+    FREE_PAGE_REQ,
+    FREE_PAGE_WAITING_FOR_RSP,
+    FREE_PAGE_READY,
+    FREE_PAGE_INVALID_PARAM,
+    FREE_PAGE_UNSUPPORT,
+    FREE_PAGE_ERROR,
+} FreePageStatus;
+
+typedef struct GetFreePageReq {
+    uint64_t param;
+} GetFreePageReq;
+
 typedef struct virtio_balloon_stat VirtIOBalloonStat;
 
 typedef struct virtio_balloon_stat_modern {
@@ -33,16 +54,23 @@ typedef struct virtio_balloon_stat_modern {
 
 typedef struct VirtIOBalloon {
     VirtIODevice parent_obj;
-    VirtQueue *ivq, *dvq, *svq;
+    VirtQueue *ivq, *dvq, *svq, *fvq;
     uint32_t num_pages;
     uint32_t actual;
     uint64_t stats[VIRTIO_BALLOON_S_NR];
     VirtQueueElement *stats_vq_elem;
+    VirtQueueElement *free_page_vq_elem;
     size_t stats_vq_offset;
     QEMUTimer *stats_timer;
     int64_t stats_last_update;
     int64_t stats_poll_interval;
     uint32_t host_features;
+    uint64_t *free_page_bmap;
+    uint64_t bmap_len;
+    uint64_t free_pages;
+    uint64_t cache_pages;
+    GetFreePageReq free_page_req;
+    VirtIoReqStatus req_status;
 } VirtIOBalloon;
 
 #endif
diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h
index 9d06ccd..09211b0 100644
--- a/include/standard-headers/linux/virtio_balloon.h
+++ b/include/standard-headers/linux/virtio_balloon.h
@@ -34,6 +34,7 @@
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
 #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
+#define VIRTIO_BALLOON_F_GET_FREE_PAGE  3 /* Get the free page bitmap */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
diff --git a/include/sysemu/balloon.h b/include/sysemu/balloon.h
index 3f976b4..81a1b9f 100644
--- a/include/sysemu/balloon.h
+++ b/include/sysemu/balloon.h
@@ -15,14 +15,24 @@
 #define _QEMU_BALLOON_H
 
 #include "qapi-types.h"
+#include "hw/virtio/virtio-balloon.h"
 
 typedef void (QEMUBalloonEvent)(void *opaque, ram_addr_t target);
 typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info);
+typedef FreePageStatus (QEMUBalloonGetFreePage)(void *opaque,
+                                                unsigned long *bitmap,
+                                                unsigned long len,
+                                                int drop_cache_ctl);
 
 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
-			     QEMUBalloonStatus *stat_func, void *opaque);
+                             QEMUBalloonStatus *stat_func,
+                             QEMUBalloonGetFreePage *get_free_page_func,
+                             void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
 bool qemu_balloon_is_inhibited(void);
 void qemu_balloon_inhibit(bool state);
+bool balloon_free_pages_support(void);
+FreePageStatus balloon_get_free_pages(unsigned long *bitmap,
+                                      unsigned long len, int drop_cache_ctl);
 
 #endif
-- 
1.8.3.1