guest kick host base on avail_ring flags value and get perfermance
improved, vhost_zerocopy_callback could do the same thing. As
virtqueue_enable_cb need one more check after modifying the value of
avail_ring flags, vhost also need do the same thing after
vhost_enable_notify.

test result list as below:
guest and host: suse11sp3, netperf, intel CPU 2.4GHz
+------+----------+--------+----------+--------+--------+---------+
|      |             old              |            new            |
+------+----------+--------+----------+--------+--------+---------+
| UDP  |  Gbit/s  |  PPS   |CPU idle% | Gbit/s |   PPS  |CPU idle%|
| 256  | 0.74805  | 321309 |  87.16   | 0.77933| 334743 |  90.71  |
| 512  |   1.42   | 328475 |  87.03   |  1.44  | 333550 |  90.43  |
| 1024 |   2.79   | 334426 |  89.09   |  2.81  | 336986 |  89.55  |
| 1460 |   3.71   | 316215 |  87.53   |  4.02  | 342325 |  89.58  |
+------+----------+--------+----------+--------+--------+---------+

Signed-off-by: Chuanyu Qin <redacted>
---
 drivers/vhost/net.c |   13 ++++++++++++-
 1 files changed, 12 insertions(+), 1 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index a0fa5de..a90f51b 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c

@@ -315,6 +315,10 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
         VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
     cnt = vhost_net_ubuf_put(ubufs);

+    /* make sure len has been updated because handle_tx would use it
+     * and used_flags should also been checked.
+     */
+    smp_mb();
     /*
      * Trigger polling thread if guest stopped submitting new buffers:
      * in this case, the refcount after decrement will eventually reach 1.

@@ -322,7 +326,8 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
      * (the value 16 here is more or less arbitrary, it's tuned to trigger
      * less than 10% of times).
      */
-    if (cnt <= 1 || !(cnt % 16))
+    if ((!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
+            && (cnt <= 1 || !(cnt % 16)))
         vhost_poll_queue(&vq->poll);

     rcu_read_unlock_bh();

@@ -386,6 +391,12 @@ static void handle_tx(struct vhost_net *net)
                 vhost_disable_notify(&net->dev, vq);
                 continue;
             }
+            /* there might skb been freed between last