[Qemu-devel] [RFD] virtio: Add memory statistics reporting to the balloon driver

[Adam Litke]

This patch has been discussed (and ACKed) in the past, but has not yet
been committed due to the congestion surrounding the 0.12 release and
other conflicting changes.  I would like to rekindle the discussion so
that I can make the necessary changes to get this merged.

This patch is ported to 0.12.1 and has one issue that I am aware of:

It still calls monitor_suspend() and monitor_resume() which I understand
is no longer allowed.  Does anyone have any ideas on how to enable async
monitor commands?

diff --git a/balloon.h b/balloon.h
index 60b4a5d..dc851d3 100644
--- a/balloon.h
+++ b/balloon.h
@@ -16,12 +16,12 @@
 
 #include "cpu-defs.h"
 
-typedef ram_addr_t (QEMUBalloonEvent)(void *opaque, ram_addr_t target);
+typedef QObject *(QEMUBalloonEvent)(void *opaque, ram_addr_t target);
 
 void qemu_add_balloon_handler(QEMUBalloonEvent *func, void *opaque);
 
-void qemu_balloon(ram_addr_t target);
+int qemu_balloon(ram_addr_t target);
 
-ram_addr_t qemu_balloon_status(void);
+QObject *qemu_balloon_status(void);
 
 #endif
diff --git a/hw/virtio-balloon.c b/hw/virtio-balloon.c
index cfd3b41..03b9e2e 100644
--- a/hw/virtio-balloon.c
+++ b/hw/virtio-balloon.c
@@ -19,6 +19,10 @@
 #include "balloon.h"
 #include "virtio-balloon.h"
 #include "kvm.h"
+#include "monitor.h"
+#include "qlist.h"
+#include "qint.h"
+#include "qstring.h"
 
 #if defined(__linux__)
 #include <sys/mman.h>
@@ -27,9 +31,13 @@
 typedef struct VirtIOBalloon
 {
     VirtIODevice vdev;
-    VirtQueue *ivq, *dvq;
+    VirtQueue *ivq, *dvq, *svq;
     uint32_t num_pages;
     uint32_t actual;
+    uint64_t stats[VIRTIO_BALLOON_S_NR];
+    VirtQueueElement stats_vq_elem;
+    size_t stats_vq_offset;
+    uint8_t stats_requested;
 } VirtIOBalloon;
 
 static VirtIOBalloon *to_virtio_balloon(VirtIODevice *vdev)
@@ -46,6 +54,33 @@ static void balloon_page(void *addr, int deflate)
 #endif
 }
 
+static inline void reset_stats(VirtIOBalloon *dev)
+{
+    int i;
+    for (i = 0; i < VIRTIO_BALLOON_S_NR; dev->stats[i++] = -1);
+}
+
+static void stat_put(QDict *dict, const char *label, uint64_t val)
+{
+    if (val != -1)
+        qdict_put(dict, label, qint_from_int(val));
+}
+
+static QObject *get_stats_qobject(VirtIOBalloon *dev)
+{
+    QDict *dict = qdict_new();
+    uint32_t actual = ram_size - (dev->actual << VIRTIO_BALLOON_PFN_SHIFT);
+
+    stat_put(dict, "actual", actual);
+    stat_put(dict, "mem_swapped_in", dev->stats[VIRTIO_BALLOON_S_SWAP_IN]);
+    stat_put(dict, "mem_swapped_out", dev->stats[VIRTIO_BALLOON_S_SWAP_OUT]);
+    stat_put(dict, "major_page_faults", dev->stats[VIRTIO_BALLOON_S_MAJFLT]);
+    stat_put(dict, "minor_page_faults", dev->stats[VIRTIO_BALLOON_S_MINFLT]);
+    stat_put(dict, "free_mem", dev->stats[VIRTIO_BALLOON_S_MEMFREE]);
+    stat_put(dict, "total_mem", dev->stats[VIRTIO_BALLOON_S_MEMTOT]);
+    return QOBJECT(dict);
+}
+
 /* FIXME: once we do a virtio refactoring, this will get subsumed into common
  * code */
 static size_t memcpy_from_iovector(void *data, size_t offset, size_t size,
@@ -104,6 +139,36 @@ static void virtio_balloon_handle_output(VirtIODevice 
*vdev, VirtQueue *vq)
     }
 }
 
+static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
+    VirtQueueElement *elem = &s->stats_vq_elem;
+    VirtIOBalloonStat stat;
+    size_t offset = 0;
+
+    if (!virtqueue_pop(vq, elem))
+        return;
+
+    while (memcpy_from_iovector(&stat, offset, sizeof(stat), elem->out_sg,
+                                elem->out_num) == sizeof(stat)) {
+        uint16_t tag = tswap16(stat.tag);
+        uint64_t val = tswap64(stat.val);
+
+        offset += sizeof(stat);
+        if (tag < VIRTIO_BALLOON_S_NR)
+            s->stats[tag] = val;
+    }
+    s->stats_vq_offset = offset;
+
+    if (s->stats_requested) {
+        QObject *stats = get_stats_qobject(s);
+        monitor_print_balloon(cur_mon, stats);
+        qobject_decref(stats);
+        monitor_resume(cur_mon);
+        s->stats_requested = 0;
+    }
+}
+
 static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
 {
     VirtIOBalloon *dev = to_virtio_balloon(vdev);
@@ -126,12 +191,22 @@ static void virtio_balloon_set_config(VirtIODevice *vdev,
 
 static uint32_t virtio_balloon_get_features(VirtIODevice *vdev)
 {
-    return 0;
+    return 1 << VIRTIO_BALLOON_F_STATS_VQ;
+}
+
+static void request_stats(VirtIOBalloon *vb)
+{
+    vb->stats_requested = 1;
+    reset_stats(vb);
+    monitor_suspend(cur_mon);
+    virtqueue_push(vb->svq, &vb->stats_vq_elem, vb->stats_vq_offset);
+    virtio_notify(&vb->vdev, vb->svq);
 }
 
-static ram_addr_t virtio_balloon_to_target(void *opaque, ram_addr_t target)
+static QObject *virtio_balloon_to_target(void *opaque, ram_addr_t target)
 {
     VirtIOBalloon *dev = opaque;
+    QObject *ret = NULL;
 
     if (target > ram_size)
         target = ram_size;
@@ -139,9 +214,15 @@ static ram_addr_t virtio_balloon_to_target(void *opaque, 
ram_addr_t target)
     if (target) {
         dev->num_pages = (ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
         virtio_notify_config(&dev->vdev);
+    } else if (dev->vdev.features & (1 << VIRTIO_BALLOON_F_STATS_VQ)) {
+        request_stats(dev);
+        ret = QOBJECT(qdict_new());
+    } else {
+        reset_stats(dev);
+        ret = get_stats_qobject(dev);
     }
 
-    return ram_size - (dev->actual << VIRTIO_BALLOON_PFN_SHIFT);
+    return ret;
 }
 
 static void virtio_balloon_save(QEMUFile *f, void *opaque)
@@ -152,6 +233,9 @@ static void virtio_balloon_save(QEMUFile *f, void *opaque)
 
     qemu_put_be32(f, s->num_pages);
     qemu_put_be32(f, s->actual);
+    qemu_put_buffer(f, (uint8_t *)&s->stats_vq_elem, sizeof(VirtQueueElement));
+    qemu_put_buffer(f, (uint8_t *)&s->stats_vq_offset, sizeof(size_t));
+    qemu_put_byte(f, s->stats_requested);
 }
 
 static int virtio_balloon_load(QEMUFile *f, void *opaque, int version_id)
@@ -165,6 +249,9 @@ static int virtio_balloon_load(QEMUFile *f, void *opaque, 
int version_id)
 
     s->num_pages = qemu_get_be32(f);
     s->actual = qemu_get_be32(f);
+    qemu_get_buffer(f, (uint8_t *)&s->stats_vq_elem, sizeof(VirtQueueElement));
+    qemu_get_buffer(f, (uint8_t *)&s->stats_vq_offset, sizeof(size_t));
+    s->stats_requested = qemu_get_byte(f);
 
     return 0;
 }
@@ -183,6 +270,7 @@ VirtIODevice *virtio_balloon_init(DeviceState *dev)
 
     s->ivq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
     s->dvq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
+    s->svq = virtio_add_queue(&s->vdev, 128, virtio_balloon_receive_stats);
 
     qemu_add_balloon_handler(virtio_balloon_to_target, s);
 
diff --git a/hw/virtio-balloon.h b/hw/virtio-balloon.h
index 9a0d119..e20cf6b 100644
--- a/hw/virtio-balloon.h
+++ b/hw/virtio-balloon.h
@@ -25,6 +25,7 @@
 
 /* The feature bitmap for virtio balloon */
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */
+#define VIRTIO_BALLOON_F_STATS_VQ 1       /* Memory stats virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
@@ -37,4 +38,18 @@ struct virtio_balloon_config
     uint32_t actual;
 };
 
+/* Memory Statistics */
+#define VIRTIO_BALLOON_S_SWAP_IN  0   /* Amount of memory swapped in */
+#define VIRTIO_BALLOON_S_SWAP_OUT 1   /* Amount of memory swapped out */
+#define VIRTIO_BALLOON_S_MAJFLT   2   /* Number of major faults */
+#define VIRTIO_BALLOON_S_MINFLT   3   /* Number of minor faults */
+#define VIRTIO_BALLOON_S_MEMFREE  4   /* Total amount of free memory */
+#define VIRTIO_BALLOON_S_MEMTOT   5   /* Total amount of memory */
+#define VIRTIO_BALLOON_S_NR       6
+
+typedef struct VirtIOBalloonStat {
+    uint16_t tag;
+    uint64_t val;
+} __attribute__((packed)) VirtIOBalloonStat;
+
 #endif
diff --git a/monitor.c b/monitor.c
index c0dc48e..c4a669a 100644
--- a/monitor.c
+++ b/monitor.c
@@ -2058,43 +2058,27 @@ static void do_info_status(Monitor *mon, QObject 
**ret_data)
                                     vm_running, singlestep);
 }
 
-static ram_addr_t balloon_get_value(void)
+static void print_balloon_stat(const char *key, QObject *obj, void *opaque)
 {
-    ram_addr_t actual;
-
-    if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        qemu_error_new(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
-        return 0;
-    }
-
-    actual = qemu_balloon_status();
-    if (actual == 0) {
-        qemu_error_new(QERR_DEVICE_NOT_ACTIVE, "balloon");
-        return 0;
-    }
-
-    return actual;
-}
+    Monitor *mon = opaque;
 
-/**
- * do_balloon(): Request VM to change its memory allocation
- */
-static void do_balloon(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
-    if (balloon_get_value()) {
-        /* ballooning is active */
-        qemu_balloon(qdict_get_int(qdict, "value"));
-    }
+    if (strcmp(key, "actual"))
+        monitor_printf(mon, ",%s=%" PRId64, key,
+                            qint_get_int(qobject_to_qint(obj)));
 }
 
-static void monitor_print_balloon(Monitor *mon, const QObject *data)
+void monitor_print_balloon(Monitor *mon, const QObject *data)
 {
     QDict *qdict;
 
     qdict = qobject_to_qdict(data);
+    if (!qdict_haskey(qdict, "actual"))
+        return;
 
-    monitor_printf(mon, "balloon: actual=%" PRId64 "\n",
-                        qdict_get_int(qdict, "balloon") >> 20);
+    monitor_printf(mon, "balloon: actual=%" PRId64,
+                        qdict_get_int(qdict, "actual") >> 20);
+    qdict_iter(qdict, print_balloon_stat, mon);
+    monitor_printf(mon, "\n");
 }
 
 /**
@@ -2102,21 +2086,48 @@ static void monitor_print_balloon(Monitor *mon, const 
QObject *data)
  *
  * Return a QDict with the following information:
  *
- * - "balloon": current balloon value in bytes
+ * - "actual": current balloon value in bytes
+ * The following fields may or may not be present:
+ * - "mem_swapped_in": Amount of memory swapped in (bytes)
+ * - "mem_swapped_out": Amount of memory swapped out (bytes)
+ * - "major_page_faults": Number of major faults
+ * - "minor_page_faults": Number of minor faults
+ * - "free_mem": Total amount of free and unused memory (bytes)
+ * - "total_mem": Total amount of available memory (bytes)
  *
  * Example:
  *
- * { "balloon": 1073741824 }
+ * { "actual": 1073741824, "mem_swapped_in": 0, "mem_swapped_out": 0,
+ *   "major_page_faults": 142, "minor_page_faults": 239245,
+ *   "free_mem": 1014185984, "total_mem": 1044668416 }
  */
 static void do_info_balloon(Monitor *mon, QObject **ret_data)
 {
-    ram_addr_t actual;
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        qemu_error_new(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return;
+    }
+
+    *ret_data = qemu_balloon_status();
+    if (*ret_data == NULL)
+        qemu_error_new(QERR_DEVICE_NOT_ACTIVE, "balloon");
+}
 
-    actual = balloon_get_value();
-    if (actual != 0) {
-        *ret_data = qobject_from_jsonf("{ 'balloon': %" PRId64 "}",
-                                       (int64_t) actual);
+/**
+ * do_balloon(): Request VM to change its memory allocation
+ */
+static void do_balloon(Monitor *mon, const QDict *qdict, QObject **ret_data)
+{
+    int ret;
+
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        qemu_error_new(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return;
     }
+
+    ret = qemu_balloon(qdict_get_int(qdict, "value"));
+    if (ret == 0)
+        qemu_error_new(QERR_DEVICE_NOT_ACTIVE, "balloon");
 }
 
 static qemu_acl *find_acl(Monitor *mon, const char *name)
diff --git a/monitor.h b/monitor.h
index 6ed117a..f7d8780 100644
--- a/monitor.h
+++ b/monitor.h
@@ -32,6 +32,7 @@ void monitor_resume(Monitor *mon);
 void monitor_read_bdrv_key_start(Monitor *mon, BlockDriverState *bs,
                                  BlockDriverCompletionFunc *completion_cb,
                                  void *opaque);
+void monitor_print_balloon(Monitor *mon, const QObject *data);
 
 int monitor_get_fd(Monitor *mon, const char *fdname);
 
diff --git a/vl.c b/vl.c
index 8be3648..029e572 100644
--- a/vl.c
+++ b/vl.c
@@ -362,17 +362,21 @@ void qemu_add_balloon_handler(QEMUBalloonEvent *func, 
void *opaque)
     qemu_balloon_event_opaque = opaque;
 }
 
-void qemu_balloon(ram_addr_t target)
+int qemu_balloon(ram_addr_t target)
 {
-    if (qemu_balloon_event)
+    if (qemu_balloon_event) {
         qemu_balloon_event(qemu_balloon_event_opaque, target);
+        return 1;
+    } else {
+        return 0;
+    }
 }
 
-ram_addr_t qemu_balloon_status(void)
+QObject *qemu_balloon_status(void)
 {
     if (qemu_balloon_event)
         return qemu_balloon_event(qemu_balloon_event_opaque, 0);
-    return 0;
+    return NULL;
 }
 
 /***********************************************************/


-- 
Thanks,
Adam