[Qemu-devel] [PATCH RFC V2] virtio-net: announce self by guest

[Jason Wang <jasowang@redhat.com>]

It's hard to track all mac addresses and their configurations (e.g
vlan or ipv6) in qemu. Without those informations, it's impossible to
build proper garp packet after migration. The only possible solution
to this is let guest (who knew all configurations) to do this.

So, this patch introduces a new readonly config status bit of virtio-net,
VIRTIO_NET_S_ANNOUNCE which is used to notify guest to announce
presence of its link through config update interrupt.When guest has
done the announcement, it should ack the notification through
VIRTIO_NET_CTRL_ANNOUNCE_ACK cmd. This feature is negotiated by a new
feature bit VIRTIO_NET_F_ANNOUNCE (which has already been supported by
Linux guest).

During load, a counter of announcing rounds were set so that the after
the vm is running it can trigger rounds of config interrupts to notify
the guest to build and send the correct garps.

Reference:
RFC v1: https://lists.gnu.org/archive/html/qemu-devel/2014-03/msg02648.html
V7:     https://lists.gnu.org/archive/html/qemu-devel/2013-03/msg01127.html

Changes from RFC v1:
- clean VIRTIO_NET_S_ANNOUNCE bit during reset
- free announce timer during clean
- make announce work for non-vhost case

Changes from V7:
- Instead of introducing a global method for each kind of nic, this
  version limits the changes to virtio-net itself.

Cc: Liuyongan <liuyongan@huawei.com>
Cc: Amos Kong <akong@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c            |   48 ++++++++++++++++++++++++++++++++++++++++
 include/hw/virtio/virtio-net.h |   16 +++++++++++++
 2 files changed, 64 insertions(+), 0 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 3626608..e2f0519 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -25,6 +25,7 @@
 #include "monitor/monitor.h"
 
 #define VIRTIO_NET_VM_VERSION    11
+#define VIRTIO_NET_ANNOUNCE_ROUNDS    3
 
 #define MAC_TABLE_ENTRIES    64
 #define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */
@@ -99,6 +100,25 @@ static bool virtio_net_started(VirtIONet *n, uint8_t status)
         (n->status & VIRTIO_NET_S_LINK_UP) && vdev->vm_running;
 }
 
+static void virtio_net_announce_timer(void *opaque)
+{
+    VirtIONet *n = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+
+    if (n->announce &&
+        virtio_net_started(n, vdev->status) &&
+        vdev->guest_features & (0x1 << VIRTIO_NET_F_GUEST_ANNOUNCE) &&
+        vdev->guest_features & (0x1 << VIRTIO_NET_F_CTRL_VQ)) {
+
+        n->announce--;
+        n->status |= VIRTIO_NET_S_ANNOUNCE;
+        virtio_notify_config(vdev);
+    } else {
+        timer_del(n->announce_timer);
+        n->announce = 0;
+    }
+}
+
 static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(n);
@@ -147,6 +167,8 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
 
     virtio_net_vhost_status(n, status);
 
+    virtio_net_announce_timer(n);
+
     for (i = 0; i < n->max_queues; i++) {
         q = &n->vqs[i];
 
@@ -306,6 +328,9 @@ static void virtio_net_reset(VirtIODevice *vdev)
     n->nobcast = 0;
     /* multiqueue is disabled by default */
     n->curr_queues = 1;
+    timer_del(n->announce_timer);
+    n->announce = 0;
+    n->status &= ~VIRTIO_NET_S_ANNOUNCE;
 
     /* Flush any MAC and VLAN filter table state */
     n->mac_table.in_use = 0;
@@ -710,6 +735,22 @@ static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
     return VIRTIO_NET_OK;
 }
 
+static int virtio_net_handle_announce(VirtIONet *n, uint8_t cmd,
+                                      struct iovec *iov, unsigned int iov_cnt)
+{
+    if (cmd == VIRTIO_NET_CTRL_ANNOUNCE_ACK) {
+        n->status &= ~VIRTIO_NET_S_ANNOUNCE;
+        if (n->announce) {
+            timer_mod(n->announce_timer,
+                      qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + 50 +
+                      (VIRTIO_NET_ANNOUNCE_ROUNDS - n->announce - 1) * 100);
+        }
+        return VIRTIO_NET_OK;
+    } else {
+        return VIRTIO_NET_ERR;
+    }
+}
+
 static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
                                 struct iovec *iov, unsigned int iov_cnt)
 {
@@ -773,6 +814,8 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
             status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt);
         } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {
             status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt);
+        } else if (ctrl.class == VIRTIO_NET_CTRL_ANNOUNCE) {
+            status = virtio_net_handle_announce(n, ctrl.cmd, iov, iov_cnt);
         } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {
             status = virtio_net_handle_mq(n, ctrl.cmd, iov, iov_cnt);
         } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) {
@@ -1418,6 +1461,7 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
         qemu_get_subqueue(n->nic, i)->link_down = link_down;
     }
 
+    n->announce = VIRTIO_NET_ANNOUNCE_ROUNDS;
     return 0;
 }
 
@@ -1529,6 +1573,8 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     qemu_macaddr_default_if_unset(&n->nic_conf.macaddr);
     memcpy(&n->mac[0], &n->nic_conf.macaddr, sizeof(n->mac));
     n->status = VIRTIO_NET_S_LINK_UP;
+    n->announce_timer = timer_new_ns(QEMU_CLOCK_REALTIME,
+                                     virtio_net_announce_timer, n);
 
     if (n->netclient_type) {
         /*
@@ -1609,6 +1655,8 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
         }
     }
 
+    timer_del(n->announce_timer);
+    timer_free(n->announce_timer);
     g_free(n->vqs);
     qemu_del_nic(n->nic);
     virtio_cleanup(vdev);
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index df60f16..e53b2c4 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -49,12 +49,14 @@
 #define VIRTIO_NET_F_CTRL_RX    18      /* Control channel RX mode support */
 #define VIRTIO_NET_F_CTRL_VLAN  19      /* Control channel VLAN filtering */
 #define VIRTIO_NET_F_CTRL_RX_EXTRA 20   /* Extra RX mode control support */
+#define VIRTIO_NET_F_GUEST_ANNOUNCE 21  /* Guest can announce itself */
 #define VIRTIO_NET_F_MQ         22      /* Device supports Receive Flow
                                          * Steering */
 
 #define VIRTIO_NET_F_CTRL_MAC_ADDR   23 /* Set MAC address */
 
 #define VIRTIO_NET_S_LINK_UP    1       /* Link is up */
+#define VIRTIO_NET_S_ANNOUNCE   2       /* Announcement is needed */
 
 #define TX_TIMER_INTERVAL 150000 /* 150 us */
 
@@ -193,6 +195,8 @@ typedef struct VirtIONet {
     char *netclient_name;
     char *netclient_type;
     uint64_t curr_guest_offloads;
+    QEMUTimer *announce_timer;
+    int announce;
 } VirtIONet;
 
 #define VIRTIO_NET_CTRL_MAC    1
@@ -213,6 +217,17 @@ typedef struct VirtIONet {
  #define VIRTIO_NET_CTRL_VLAN_DEL             1
 
 /*
+ * Control link announce acknowledgement
+ *
+ * The command VIRTIO_NET_CTRL_ANNOUNCE_ACK is used to indicate that
+ * driver has recevied the notification and device would clear the
+ * VIRTIO_NET_S_ANNOUNCE bit in the status filed after it received
+ * this command.
+ */
+#define VIRTIO_NET_CTRL_ANNOUNCE       3
+ #define VIRTIO_NET_CTRL_ANNOUNCE_ACK         0
+
+/*
  * Control Multiqueue
  *
  * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
@@ -251,6 +266,7 @@ struct virtio_net_ctrl_mq {
         DEFINE_PROP_BIT("guest_tso6", _state, _field, VIRTIO_NET_F_GUEST_TSO6, true), \
         DEFINE_PROP_BIT("guest_ecn", _state, _field, VIRTIO_NET_F_GUEST_ECN, true), \
         DEFINE_PROP_BIT("guest_ufo", _state, _field, VIRTIO_NET_F_GUEST_UFO, true), \
+        DEFINE_PROP_BIT("guest_announce", _state, _field, VIRTIO_NET_F_GUEST_ANNOUNCE, true), \
         DEFINE_PROP_BIT("host_tso4", _state, _field, VIRTIO_NET_F_HOST_TSO4, true), \
         DEFINE_PROP_BIT("host_tso6", _state, _field, VIRTIO_NET_F_HOST_TSO6, true), \
         DEFINE_PROP_BIT("host_ecn", _state, _field, VIRTIO_NET_F_HOST_ECN, true), \
-- 
1.7.1