Subject: [PATCH] kvmppc virtio-net: workaround for lost interrupt/polling

From: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>

This patch is (atm) just a debug workaround. The issue is that virtio-net
works fine for a while but then "something" happens and we see neither
vp_interrupts nor calls to virtnet_poll anymore.
Looking at the network traffic shows that the kvm guest still sends packets
via virtio-net and that userspace tries to deliver things to the guest, but
the guest receives nothing.
Somehow it loks loke polling and interrupts are disables (more debugging
needed).
For now anyone can continue with that workaround patch (which is
very slow, I had no time to tune the polling interval yet).
There's an ugly fixme, but I don't yet know what exactly causes this BUG()
to trigger so thats the way to get it out for now.
I'll update the patch once I have an improved version.

Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
---

[diffstat]
 virtio_net.c |   36 ++++++++++++++++++++++++++++++------
 1 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -194,17 +194,22 @@ again:
 		received++;
 	}
 
+
 	/* FIXME: If we oom and completely run out of inbufs, we need
 	 * to start a timer trying to fill more. */
 	if (vi->num < vi->max / 2)
 		try_fill_recv(vi);
 
-	/* Out of packets? */
-	if (received < budget) {
-		netif_rx_complete(vi->dev, napi);
-		if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
-		    && netif_rx_reschedule(vi->dev, napi))
-			goto again;
+	/* FIXME - fails when called by workaround timer polling (sometimes) */
+	if (budget != 42)
+	{
+		/* Out of packets? */
+		if (received < budget) {
+				netif_rx_complete(vi->dev, napi);
+			if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
+			    && netif_rx_reschedule(vi->dev, napi))
+				goto again;
+		}
 	}
 
 	return received;
@@ -294,6 +299,17 @@ again:
 	return 0;
 }
 
+static struct timer_list viopoll_timer;
+static void virtio_poll_wrap(unsigned long dev)
+{
+        struct virtnet_info *vi = netdev_priv((struct net_device *)dev);
+	/* poll more often if polling received something */
+	if (virtnet_poll(&vi->napi, 42))
+		mod_timer(&viopoll_timer, get_jiffies_64() + (HZ/150));
+	else
+		mod_timer(&viopoll_timer, get_jiffies_64() + (HZ/25));
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -308,12 +324,20 @@ static int virtnet_open(struct net_devic
 		vi->rvq->vq_ops->disable_cb(vi->rvq);
 		__netif_rx_schedule(dev, &vi->napi);
 	}
+
+	// DEBUG (Missing interrupts ?)
+	setup_timer(&viopoll_timer, virtio_poll_wrap, (unsigned long)(dev));
+	mod_timer(&viopoll_timer, get_jiffies_64() + HZ);
+	printk("%s - set up virtnet_poll timer\n", __func__);
+
 	return 0;
 }
 
 static int virtnet_close(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
+
+        del_timer(&viopoll_timer);
 
 	napi_disable(&vi->napi);